From 9fa45070a2e59a871e1cd3370173369f3a4f61e2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 4 Sep 2018 11:48:26 +0100 Subject: locking/atomics: Switch to generated fallbacks As a step to ensuring the atomic* APIs are consistent, switch to fallbacks generated by gen-atomic-fallback.sh. These are checked in rather than generated with Kbuild, since: * This allows inspection of the atomics with git grep and ctags on a pristine tree, which Linus strongly prefers being able to do. * The fallbacks are not affected by machine details or configuration options, so it is not necessary to regenerate them to take these into account. * These are included by files required *very* early in the build process (e.g. for generating bounds.h), and we'd rather not complicate the top-level Kbuild file with dependencies. The new fallback header should be equivalent to the old fallbacks in , but: * It is formatted a little differently due to scripting ensuring things are more regular than they used to be. * Fallbacks are now expanded in-place as static inline functions rather than macros. * The prototypes for fallbacks are arragned consistently with the return type on a separate line to try to keep to a sensible line length. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: catalin.marinas@arm.com Cc: linuxdrivers@attotech.com Cc: dvyukov@google.com Cc: Boqun Feng Cc: arnd@arndb.de Cc: aryabinin@virtuozzo.com Cc: glider@google.com Link: http://lkml.kernel.org/r/20180904104830.2975-3-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic-fallback.h | 2294 +++++++++++++++++++++++++++++++++++++++ include/linux/atomic.h | 1241 +-------------------- 2 files changed, 2295 insertions(+), 1240 deletions(-) create mode 100644 include/linux/atomic-fallback.h (limited to 'include') diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h new file mode 100644 index 000000000000..1c02c0112fbb --- /dev/null +++ b/include/linux/atomic-fallback.h @@ -0,0 +1,2294 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-fallback.sh +// DO NOT MODIFY THIS FILE DIRECTLY + +#ifndef _LINUX_ATOMIC_FALLBACK_H +#define _LINUX_ATOMIC_FALLBACK_H + +#ifndef xchg_relaxed +#define xchg_relaxed xchg +#define xchg_acquire xchg +#define xchg_release xchg +#else /* xchg_relaxed */ + +#ifndef xchg_acquire +#define xchg_acquire(...) \ + __atomic_op_acquire(xchg, __VA_ARGS__) +#endif + +#ifndef xchg_release +#define xchg_release(...) \ + __atomic_op_release(xchg, __VA_ARGS__) +#endif + +#ifndef xchg +#define xchg(...) \ + __atomic_op_fence(xchg, __VA_ARGS__) +#endif + +#endif /* xchg_relaxed */ + +#ifndef cmpxchg_relaxed +#define cmpxchg_relaxed cmpxchg +#define cmpxchg_acquire cmpxchg +#define cmpxchg_release cmpxchg +#else /* cmpxchg_relaxed */ + +#ifndef cmpxchg_acquire +#define cmpxchg_acquire(...) \ + __atomic_op_acquire(cmpxchg, __VA_ARGS__) +#endif + +#ifndef cmpxchg_release +#define cmpxchg_release(...) \ + __atomic_op_release(cmpxchg, __VA_ARGS__) +#endif + +#ifndef cmpxchg +#define cmpxchg(...) \ + __atomic_op_fence(cmpxchg, __VA_ARGS__) +#endif + +#endif /* cmpxchg_relaxed */ + +#ifndef cmpxchg64_relaxed +#define cmpxchg64_relaxed cmpxchg64 +#define cmpxchg64_acquire cmpxchg64 +#define cmpxchg64_release cmpxchg64 +#else /* cmpxchg64_relaxed */ + +#ifndef cmpxchg64_acquire +#define cmpxchg64_acquire(...) \ + __atomic_op_acquire(cmpxchg64, __VA_ARGS__) +#endif + +#ifndef cmpxchg64_release +#define cmpxchg64_release(...) \ + __atomic_op_release(cmpxchg64, __VA_ARGS__) +#endif + +#ifndef cmpxchg64 +#define cmpxchg64(...) \ + __atomic_op_fence(cmpxchg64, __VA_ARGS__) +#endif + +#endif /* cmpxchg64_relaxed */ + +#ifndef atomic_read_acquire +static inline int +atomic_read_acquire(const atomic_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define atomic_read_acquire atomic_read_acquire +#endif + +#ifndef atomic_set_release +static inline void +atomic_set_release(atomic_t *v, int i) +{ + smp_store_release(&(v)->counter, i); +} +#define atomic_set_release atomic_set_release +#endif + +#ifndef atomic_add_return_relaxed +#define atomic_add_return_acquire atomic_add_return +#define atomic_add_return_release atomic_add_return +#define atomic_add_return_relaxed atomic_add_return +#else /* atomic_add_return_relaxed */ + +#ifndef atomic_add_return_acquire +static inline int +atomic_add_return_acquire(int i, atomic_t *v) +{ + int ret = atomic_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_add_return_acquire atomic_add_return_acquire +#endif + +#ifndef atomic_add_return_release +static inline int +atomic_add_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return atomic_add_return_relaxed(i, v); +} +#define atomic_add_return_release atomic_add_return_release +#endif + +#ifndef atomic_add_return +static inline int +atomic_add_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_add_return atomic_add_return +#endif + +#endif /* atomic_add_return_relaxed */ + +#ifndef atomic_fetch_add_relaxed +#define atomic_fetch_add_acquire atomic_fetch_add +#define atomic_fetch_add_release atomic_fetch_add +#define atomic_fetch_add_relaxed atomic_fetch_add +#else /* atomic_fetch_add_relaxed */ + +#ifndef atomic_fetch_add_acquire +static inline int +atomic_fetch_add_acquire(int i, atomic_t *v) +{ + int ret = atomic_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_fetch_add_acquire atomic_fetch_add_acquire +#endif + +#ifndef atomic_fetch_add_release +static inline int +atomic_fetch_add_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return atomic_fetch_add_relaxed(i, v); +} +#define atomic_fetch_add_release atomic_fetch_add_release +#endif + +#ifndef atomic_fetch_add +static inline int +atomic_fetch_add(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_fetch_add atomic_fetch_add +#endif + +#endif /* atomic_fetch_add_relaxed */ + +#ifndef atomic_sub_return_relaxed +#define atomic_sub_return_acquire atomic_sub_return +#define atomic_sub_return_release atomic_sub_return +#define atomic_sub_return_relaxed atomic_sub_return +#else /* atomic_sub_return_relaxed */ + +#ifndef atomic_sub_return_acquire +static inline int +atomic_sub_return_acquire(int i, atomic_t *v) +{ + int ret = atomic_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_sub_return_acquire atomic_sub_return_acquire +#endif + +#ifndef atomic_sub_return_release +static inline int +atomic_sub_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return atomic_sub_return_relaxed(i, v); +} +#define atomic_sub_return_release atomic_sub_return_release +#endif + +#ifndef atomic_sub_return +static inline int +atomic_sub_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_sub_return atomic_sub_return +#endif + +#endif /* atomic_sub_return_relaxed */ + +#ifndef atomic_fetch_sub_relaxed +#define atomic_fetch_sub_acquire atomic_fetch_sub +#define atomic_fetch_sub_release atomic_fetch_sub +#define atomic_fetch_sub_relaxed atomic_fetch_sub +#else /* atomic_fetch_sub_relaxed */ + +#ifndef atomic_fetch_sub_acquire +static inline int +atomic_fetch_sub_acquire(int i, atomic_t *v) +{ + int ret = atomic_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_fetch_sub_acquire atomic_fetch_sub_acquire +#endif + +#ifndef atomic_fetch_sub_release +static inline int +atomic_fetch_sub_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return atomic_fetch_sub_relaxed(i, v); +} +#define atomic_fetch_sub_release atomic_fetch_sub_release +#endif + +#ifndef atomic_fetch_sub +static inline int +atomic_fetch_sub(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_fetch_sub atomic_fetch_sub +#endif + +#endif /* atomic_fetch_sub_relaxed */ + +#ifndef atomic_inc +static inline void +atomic_inc(atomic_t *v) +{ + atomic_add(1, v); +} +#define atomic_inc atomic_inc +#endif + +#ifndef atomic_inc_return_relaxed +#ifdef atomic_inc_return +#define atomic_inc_return_acquire atomic_inc_return +#define atomic_inc_return_release atomic_inc_return +#define atomic_inc_return_relaxed atomic_inc_return +#endif /* atomic_inc_return */ + +#ifndef atomic_inc_return +static inline int +atomic_inc_return(atomic_t *v) +{ + return atomic_add_return(1, v); +} +#define atomic_inc_return atomic_inc_return +#endif + +#ifndef atomic_inc_return_acquire +static inline int +atomic_inc_return_acquire(atomic_t *v) +{ + return atomic_add_return_acquire(1, v); +} +#define atomic_inc_return_acquire atomic_inc_return_acquire +#endif + +#ifndef atomic_inc_return_release +static inline int +atomic_inc_return_release(atomic_t *v) +{ + return atomic_add_return_release(1, v); +} +#define atomic_inc_return_release atomic_inc_return_release +#endif + +#ifndef atomic_inc_return_relaxed +static inline int +atomic_inc_return_relaxed(atomic_t *v) +{ + return atomic_add_return_relaxed(1, v); +} +#define atomic_inc_return_relaxed atomic_inc_return_relaxed +#endif + +#else /* atomic_inc_return_relaxed */ + +#ifndef atomic_inc_return_acquire +static inline int +atomic_inc_return_acquire(atomic_t *v) +{ + int ret = atomic_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_inc_return_acquire atomic_inc_return_acquire +#endif + +#ifndef atomic_inc_return_release +static inline int +atomic_inc_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return atomic_inc_return_relaxed(v); +} +#define atomic_inc_return_release atomic_inc_return_release +#endif + +#ifndef atomic_inc_return +static inline int +atomic_inc_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_inc_return atomic_inc_return +#endif + +#endif /* atomic_inc_return_relaxed */ + +#ifndef atomic_fetch_inc_relaxed +#ifdef atomic_fetch_inc +#define atomic_fetch_inc_acquire atomic_fetch_inc +#define atomic_fetch_inc_release atomic_fetch_inc +#define atomic_fetch_inc_relaxed atomic_fetch_inc +#endif /* atomic_fetch_inc */ + +#ifndef atomic_fetch_inc +static inline int +atomic_fetch_inc(atomic_t *v) +{ + return atomic_fetch_add(1, v); +} +#define atomic_fetch_inc atomic_fetch_inc +#endif + +#ifndef atomic_fetch_inc_acquire +static inline int +atomic_fetch_inc_acquire(atomic_t *v) +{ + return atomic_fetch_add_acquire(1, v); +} +#define atomic_fetch_inc_acquire atomic_fetch_inc_acquire +#endif + +#ifndef atomic_fetch_inc_release +static inline int +atomic_fetch_inc_release(atomic_t *v) +{ + return atomic_fetch_add_release(1, v); +} +#define atomic_fetch_inc_release atomic_fetch_inc_release +#endif + +#ifndef atomic_fetch_inc_relaxed +static inline int +atomic_fetch_inc_relaxed(atomic_t *v) +{ + return atomic_fetch_add_relaxed(1, v); +} +#define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed +#endif + +#else /* atomic_fetch_inc_relaxed */ + +#ifndef atomic_fetch_inc_acquire +static inline int +atomic_fetch_inc_acquire(atomic_t *v) +{ + int ret = atomic_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_fetch_inc_acquire atomic_fetch_inc_acquire +#endif + +#ifndef atomic_fetch_inc_release +static inline int +atomic_fetch_inc_release(atomic_t *v) +{ + __atomic_release_fence(); + return atomic_fetch_inc_relaxed(v); +} +#define atomic_fetch_inc_release atomic_fetch_inc_release +#endif + +#ifndef atomic_fetch_inc +static inline int +atomic_fetch_inc(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_fetch_inc atomic_fetch_inc +#endif + +#endif /* atomic_fetch_inc_relaxed */ + +#ifndef atomic_dec +static inline void +atomic_dec(atomic_t *v) +{ + atomic_sub(1, v); +} +#define atomic_dec atomic_dec +#endif + +#ifndef atomic_dec_return_relaxed +#ifdef atomic_dec_return +#define atomic_dec_return_acquire atomic_dec_return +#define atomic_dec_return_release atomic_dec_return +#define atomic_dec_return_relaxed atomic_dec_return +#endif /* atomic_dec_return */ + +#ifndef atomic_dec_return +static inline int +atomic_dec_return(atomic_t *v) +{ + return atomic_sub_return(1, v); +} +#define atomic_dec_return atomic_dec_return +#endif + +#ifndef atomic_dec_return_acquire +static inline int +atomic_dec_return_acquire(atomic_t *v) +{ + return atomic_sub_return_acquire(1, v); +} +#define atomic_dec_return_acquire atomic_dec_return_acquire +#endif + +#ifndef atomic_dec_return_release +static inline int +atomic_dec_return_release(atomic_t *v) +{ + return atomic_sub_return_release(1, v); +} +#define atomic_dec_return_release atomic_dec_return_release +#endif + +#ifndef atomic_dec_return_relaxed +static inline int +atomic_dec_return_relaxed(atomic_t *v) +{ + return atomic_sub_return_relaxed(1, v); +} +#define atomic_dec_return_relaxed atomic_dec_return_relaxed +#endif + +#else /* atomic_dec_return_relaxed */ + +#ifndef atomic_dec_return_acquire +static inline int +atomic_dec_return_acquire(atomic_t *v) +{ + int ret = atomic_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_dec_return_acquire atomic_dec_return_acquire +#endif + +#ifndef atomic_dec_return_release +static inline int +atomic_dec_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return atomic_dec_return_relaxed(v); +} +#define atomic_dec_return_release atomic_dec_return_release +#endif + +#ifndef atomic_dec_return +static inline int +atomic_dec_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_dec_return atomic_dec_return +#endif + +#endif /* atomic_dec_return_relaxed */ + +#ifndef atomic_fetch_dec_relaxed +#ifdef atomic_fetch_dec +#define atomic_fetch_dec_acquire atomic_fetch_dec +#define atomic_fetch_dec_release atomic_fetch_dec +#define atomic_fetch_dec_relaxed atomic_fetch_dec +#endif /* atomic_fetch_dec */ + +#ifndef atomic_fetch_dec +static inline int +atomic_fetch_dec(atomic_t *v) +{ + return atomic_fetch_sub(1, v); +} +#define atomic_fetch_dec atomic_fetch_dec +#endif + +#ifndef atomic_fetch_dec_acquire +static inline int +atomic_fetch_dec_acquire(atomic_t *v) +{ + return atomic_fetch_sub_acquire(1, v); +} +#define atomic_fetch_dec_acquire atomic_fetch_dec_acquire +#endif + +#ifndef atomic_fetch_dec_release +static inline int +atomic_fetch_dec_release(atomic_t *v) +{ + return atomic_fetch_sub_release(1, v); +} +#define atomic_fetch_dec_release atomic_fetch_dec_release +#endif + +#ifndef atomic_fetch_dec_relaxed +static inline int +atomic_fetch_dec_relaxed(atomic_t *v) +{ + return atomic_fetch_sub_relaxed(1, v); +} +#define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed +#endif + +#else /* atomic_fetch_dec_relaxed */ + +#ifndef atomic_fetch_dec_acquire +static inline int +atomic_fetch_dec_acquire(atomic_t *v) +{ + int ret = atomic_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_fetch_dec_acquire atomic_fetch_dec_acquire +#endif + +#ifndef atomic_fetch_dec_release +static inline int +atomic_fetch_dec_release(atomic_t *v) +{ + __atomic_release_fence(); + return atomic_fetch_dec_relaxed(v); +} +#define atomic_fetch_dec_release atomic_fetch_dec_release +#endif + +#ifndef atomic_fetch_dec +static inline int +atomic_fetch_dec(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_fetch_dec atomic_fetch_dec +#endif + +#endif /* atomic_fetch_dec_relaxed */ + +#ifndef atomic_fetch_and_relaxed +#define atomic_fetch_and_acquire atomic_fetch_and +#define atomic_fetch_and_release atomic_fetch_and +#define atomic_fetch_and_relaxed atomic_fetch_and +#else /* atomic_fetch_and_relaxed */ + +#ifndef atomic_fetch_and_acquire +static inline int +atomic_fetch_and_acquire(int i, atomic_t *v) +{ + int ret = atomic_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_fetch_and_acquire atomic_fetch_and_acquire +#endif + +#ifndef atomic_fetch_and_release +static inline int +atomic_fetch_and_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return atomic_fetch_and_relaxed(i, v); +} +#define atomic_fetch_and_release atomic_fetch_and_release +#endif + +#ifndef atomic_fetch_and +static inline int +atomic_fetch_and(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_fetch_and atomic_fetch_and +#endif + +#endif /* atomic_fetch_and_relaxed */ + +#ifndef atomic_andnot +static inline void +atomic_andnot(int i, atomic_t *v) +{ + atomic_and(~i, v); +} +#define atomic_andnot atomic_andnot +#endif + +#ifndef atomic_fetch_andnot_relaxed +#ifdef atomic_fetch_andnot +#define atomic_fetch_andnot_acquire atomic_fetch_andnot +#define atomic_fetch_andnot_release atomic_fetch_andnot +#define atomic_fetch_andnot_relaxed atomic_fetch_andnot +#endif /* atomic_fetch_andnot */ + +#ifndef atomic_fetch_andnot +static inline int +atomic_fetch_andnot(int i, atomic_t *v) +{ + return atomic_fetch_and(~i, v); +} +#define atomic_fetch_andnot atomic_fetch_andnot +#endif + +#ifndef atomic_fetch_andnot_acquire +static inline int +atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + return atomic_fetch_and_acquire(~i, v); +} +#define atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire +#endif + +#ifndef atomic_fetch_andnot_release +static inline int +atomic_fetch_andnot_release(int i, atomic_t *v) +{ + return atomic_fetch_and_release(~i, v); +} +#define atomic_fetch_andnot_release atomic_fetch_andnot_release +#endif + +#ifndef atomic_fetch_andnot_relaxed +static inline int +atomic_fetch_andnot_relaxed(int i, atomic_t *v) +{ + return atomic_fetch_and_relaxed(~i, v); +} +#define atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed +#endif + +#else /* atomic_fetch_andnot_relaxed */ + +#ifndef atomic_fetch_andnot_acquire +static inline int +atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + int ret = atomic_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire +#endif + +#ifndef atomic_fetch_andnot_release +static inline int +atomic_fetch_andnot_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return atomic_fetch_andnot_relaxed(i, v); +} +#define atomic_fetch_andnot_release atomic_fetch_andnot_release +#endif + +#ifndef atomic_fetch_andnot +static inline int +atomic_fetch_andnot(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_fetch_andnot atomic_fetch_andnot +#endif + +#endif /* atomic_fetch_andnot_relaxed */ + +#ifndef atomic_fetch_or_relaxed +#define atomic_fetch_or_acquire atomic_fetch_or +#define atomic_fetch_or_release atomic_fetch_or +#define atomic_fetch_or_relaxed atomic_fetch_or +#else /* atomic_fetch_or_relaxed */ + +#ifndef atomic_fetch_or_acquire +static inline int +atomic_fetch_or_acquire(int i, atomic_t *v) +{ + int ret = atomic_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_fetch_or_acquire atomic_fetch_or_acquire +#endif + +#ifndef atomic_fetch_or_release +static inline int +atomic_fetch_or_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return atomic_fetch_or_relaxed(i, v); +} +#define atomic_fetch_or_release atomic_fetch_or_release +#endif + +#ifndef atomic_fetch_or +static inline int +atomic_fetch_or(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_fetch_or atomic_fetch_or +#endif + +#endif /* atomic_fetch_or_relaxed */ + +#ifndef atomic_fetch_xor_relaxed +#define atomic_fetch_xor_acquire atomic_fetch_xor +#define atomic_fetch_xor_release atomic_fetch_xor +#define atomic_fetch_xor_relaxed atomic_fetch_xor +#else /* atomic_fetch_xor_relaxed */ + +#ifndef atomic_fetch_xor_acquire +static inline int +atomic_fetch_xor_acquire(int i, atomic_t *v) +{ + int ret = atomic_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic_fetch_xor_acquire atomic_fetch_xor_acquire +#endif + +#ifndef atomic_fetch_xor_release +static inline int +atomic_fetch_xor_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return atomic_fetch_xor_relaxed(i, v); +} +#define atomic_fetch_xor_release atomic_fetch_xor_release +#endif + +#ifndef atomic_fetch_xor +static inline int +atomic_fetch_xor(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic_fetch_xor atomic_fetch_xor +#endif + +#endif /* atomic_fetch_xor_relaxed */ + +#ifndef atomic_xchg_relaxed +#define atomic_xchg_acquire atomic_xchg +#define atomic_xchg_release atomic_xchg +#define atomic_xchg_relaxed atomic_xchg +#else /* atomic_xchg_relaxed */ + +#ifndef atomic_xchg_acquire +static inline int +atomic_xchg_acquire(atomic_t *v, int i) +{ + int ret = atomic_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define atomic_xchg_acquire atomic_xchg_acquire +#endif + +#ifndef atomic_xchg_release +static inline int +atomic_xchg_release(atomic_t *v, int i) +{ + __atomic_release_fence(); + return atomic_xchg_relaxed(v, i); +} +#define atomic_xchg_release atomic_xchg_release +#endif + +#ifndef atomic_xchg +static inline int +atomic_xchg(atomic_t *v, int i) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define atomic_xchg atomic_xchg +#endif + +#endif /* atomic_xchg_relaxed */ + +#ifndef atomic_cmpxchg_relaxed +#define atomic_cmpxchg_acquire atomic_cmpxchg +#define atomic_cmpxchg_release atomic_cmpxchg +#define atomic_cmpxchg_relaxed atomic_cmpxchg +#else /* atomic_cmpxchg_relaxed */ + +#ifndef atomic_cmpxchg_acquire +static inline int +atomic_cmpxchg_acquire(atomic_t *v, int old, int new) +{ + int ret = atomic_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define atomic_cmpxchg_acquire atomic_cmpxchg_acquire +#endif + +#ifndef atomic_cmpxchg_release +static inline int +atomic_cmpxchg_release(atomic_t *v, int old, int new) +{ + __atomic_release_fence(); + return atomic_cmpxchg_relaxed(v, old, new); +} +#define atomic_cmpxchg_release atomic_cmpxchg_release +#endif + +#ifndef atomic_cmpxchg +static inline int +atomic_cmpxchg(atomic_t *v, int old, int new) +{ + int ret; + __atomic_pre_full_fence(); + ret = atomic_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define atomic_cmpxchg atomic_cmpxchg +#endif + +#endif /* atomic_cmpxchg_relaxed */ + +#ifndef atomic_try_cmpxchg_relaxed +#ifdef atomic_try_cmpxchg +#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg +#define atomic_try_cmpxchg_release atomic_try_cmpxchg +#define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg +#endif /* atomic_try_cmpxchg */ + +#ifndef atomic_try_cmpxchg +static inline bool +atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = atomic_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define atomic_try_cmpxchg atomic_try_cmpxchg +#endif + +#ifndef atomic_try_cmpxchg_acquire +static inline bool +atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = atomic_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire +#endif + +#ifndef atomic_try_cmpxchg_release +static inline bool +atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = atomic_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define atomic_try_cmpxchg_release atomic_try_cmpxchg_release +#endif + +#ifndef atomic_try_cmpxchg_relaxed +static inline bool +atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = atomic_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed +#endif + +#else /* atomic_try_cmpxchg_relaxed */ + +#ifndef atomic_try_cmpxchg_acquire +static inline bool +atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + bool ret = atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire +#endif + +#ifndef atomic_try_cmpxchg_release +static inline bool +atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + __atomic_release_fence(); + return atomic_try_cmpxchg_relaxed(v, old, new); +} +#define atomic_try_cmpxchg_release atomic_try_cmpxchg_release +#endif + +#ifndef atomic_try_cmpxchg +static inline bool +atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define atomic_try_cmpxchg atomic_try_cmpxchg +#endif + +#endif /* atomic_try_cmpxchg_relaxed */ + +#ifndef atomic_sub_and_test +/** + * atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static inline bool +atomic_sub_and_test(int i, atomic_t *v) +{ + return atomic_sub_return(i, v) == 0; +} +#define atomic_sub_and_test atomic_sub_and_test +#endif + +#ifndef atomic_dec_and_test +/** + * atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static inline bool +atomic_dec_and_test(atomic_t *v) +{ + return atomic_dec_return(v) == 0; +} +#define atomic_dec_and_test atomic_dec_and_test +#endif + +#ifndef atomic_inc_and_test +/** + * atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static inline bool +atomic_inc_and_test(atomic_t *v) +{ + return atomic_inc_return(v) == 0; +} +#define atomic_inc_and_test atomic_inc_and_test +#endif + +#ifndef atomic_add_negative +/** + * atomic_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static inline bool +atomic_add_negative(int i, atomic_t *v) +{ + return atomic_add_return(i, v) < 0; +} +#define atomic_add_negative atomic_add_negative +#endif + +#ifndef atomic_fetch_add_unless +/** + * atomic_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static inline int +atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int c = atomic_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define atomic_fetch_add_unless atomic_fetch_add_unless +#endif + +#ifndef atomic_add_unless +/** + * atomic_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static inline bool +atomic_add_unless(atomic_t *v, int a, int u) +{ + return atomic_fetch_add_unless(v, a, u) != u; +} +#define atomic_add_unless atomic_add_unless +#endif + +#ifndef atomic_inc_not_zero +/** + * atomic_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static inline bool +atomic_inc_not_zero(atomic_t *v) +{ + return atomic_add_unless(v, 1, 0); +} +#define atomic_inc_not_zero atomic_inc_not_zero +#endif + +#ifndef atomic_inc_unless_negative +static inline bool +atomic_inc_unless_negative(atomic_t *v) +{ + int c = atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define atomic_inc_unless_negative atomic_inc_unless_negative +#endif + +#ifndef atomic_dec_unless_positive +static inline bool +atomic_dec_unless_positive(atomic_t *v) +{ + int c = atomic_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define atomic_dec_unless_positive atomic_dec_unless_positive +#endif + +#ifndef atomic_dec_if_positive +static inline int +atomic_dec_if_positive(atomic_t *v) +{ + int dec, c = atomic_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!atomic_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define atomic_dec_if_positive atomic_dec_if_positive +#endif + +#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) +#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) + +#ifdef CONFIG_GENERIC_ATOMIC64 +#include +#endif + +#ifndef atomic64_read_acquire +static inline s64 +atomic64_read_acquire(const atomic64_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define atomic64_read_acquire atomic64_read_acquire +#endif + +#ifndef atomic64_set_release +static inline void +atomic64_set_release(atomic64_t *v, s64 i) +{ + smp_store_release(&(v)->counter, i); +} +#define atomic64_set_release atomic64_set_release +#endif + +#ifndef atomic64_add_return_relaxed +#define atomic64_add_return_acquire atomic64_add_return +#define atomic64_add_return_release atomic64_add_return +#define atomic64_add_return_relaxed atomic64_add_return +#else /* atomic64_add_return_relaxed */ + +#ifndef atomic64_add_return_acquire +static inline s64 +atomic64_add_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = atomic64_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_add_return_acquire atomic64_add_return_acquire +#endif + +#ifndef atomic64_add_return_release +static inline s64 +atomic64_add_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_add_return_relaxed(i, v); +} +#define atomic64_add_return_release atomic64_add_return_release +#endif + +#ifndef atomic64_add_return +static inline s64 +atomic64_add_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_add_return atomic64_add_return +#endif + +#endif /* atomic64_add_return_relaxed */ + +#ifndef atomic64_fetch_add_relaxed +#define atomic64_fetch_add_acquire atomic64_fetch_add +#define atomic64_fetch_add_release atomic64_fetch_add +#define atomic64_fetch_add_relaxed atomic64_fetch_add +#else /* atomic64_fetch_add_relaxed */ + +#ifndef atomic64_fetch_add_acquire +static inline s64 +atomic64_fetch_add_acquire(s64 i, atomic64_t *v) +{ + s64 ret = atomic64_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_fetch_add_acquire atomic64_fetch_add_acquire +#endif + +#ifndef atomic64_fetch_add_release +static inline s64 +atomic64_fetch_add_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_fetch_add_relaxed(i, v); +} +#define atomic64_fetch_add_release atomic64_fetch_add_release +#endif + +#ifndef atomic64_fetch_add +static inline s64 +atomic64_fetch_add(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_fetch_add atomic64_fetch_add +#endif + +#endif /* atomic64_fetch_add_relaxed */ + +#ifndef atomic64_sub_return_relaxed +#define atomic64_sub_return_acquire atomic64_sub_return +#define atomic64_sub_return_release atomic64_sub_return +#define atomic64_sub_return_relaxed atomic64_sub_return +#else /* atomic64_sub_return_relaxed */ + +#ifndef atomic64_sub_return_acquire +static inline s64 +atomic64_sub_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = atomic64_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_sub_return_acquire atomic64_sub_return_acquire +#endif + +#ifndef atomic64_sub_return_release +static inline s64 +atomic64_sub_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_sub_return_relaxed(i, v); +} +#define atomic64_sub_return_release atomic64_sub_return_release +#endif + +#ifndef atomic64_sub_return +static inline s64 +atomic64_sub_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_sub_return atomic64_sub_return +#endif + +#endif /* atomic64_sub_return_relaxed */ + +#ifndef atomic64_fetch_sub_relaxed +#define atomic64_fetch_sub_acquire atomic64_fetch_sub +#define atomic64_fetch_sub_release atomic64_fetch_sub +#define atomic64_fetch_sub_relaxed atomic64_fetch_sub +#else /* atomic64_fetch_sub_relaxed */ + +#ifndef atomic64_fetch_sub_acquire +static inline s64 +atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) +{ + s64 ret = atomic64_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire +#endif + +#ifndef atomic64_fetch_sub_release +static inline s64 +atomic64_fetch_sub_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_fetch_sub_relaxed(i, v); +} +#define atomic64_fetch_sub_release atomic64_fetch_sub_release +#endif + +#ifndef atomic64_fetch_sub +static inline s64 +atomic64_fetch_sub(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_fetch_sub atomic64_fetch_sub +#endif + +#endif /* atomic64_fetch_sub_relaxed */ + +#ifndef atomic64_inc +static inline void +atomic64_inc(atomic64_t *v) +{ + atomic64_add(1, v); +} +#define atomic64_inc atomic64_inc +#endif + +#ifndef atomic64_inc_return_relaxed +#ifdef atomic64_inc_return +#define atomic64_inc_return_acquire atomic64_inc_return +#define atomic64_inc_return_release atomic64_inc_return +#define atomic64_inc_return_relaxed atomic64_inc_return +#endif /* atomic64_inc_return */ + +#ifndef atomic64_inc_return +static inline s64 +atomic64_inc_return(atomic64_t *v) +{ + return atomic64_add_return(1, v); +} +#define atomic64_inc_return atomic64_inc_return +#endif + +#ifndef atomic64_inc_return_acquire +static inline s64 +atomic64_inc_return_acquire(atomic64_t *v) +{ + return atomic64_add_return_acquire(1, v); +} +#define atomic64_inc_return_acquire atomic64_inc_return_acquire +#endif + +#ifndef atomic64_inc_return_release +static inline s64 +atomic64_inc_return_release(atomic64_t *v) +{ + return atomic64_add_return_release(1, v); +} +#define atomic64_inc_return_release atomic64_inc_return_release +#endif + +#ifndef atomic64_inc_return_relaxed +static inline s64 +atomic64_inc_return_relaxed(atomic64_t *v) +{ + return atomic64_add_return_relaxed(1, v); +} +#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed +#endif + +#else /* atomic64_inc_return_relaxed */ + +#ifndef atomic64_inc_return_acquire +static inline s64 +atomic64_inc_return_acquire(atomic64_t *v) +{ + s64 ret = atomic64_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_inc_return_acquire atomic64_inc_return_acquire +#endif + +#ifndef atomic64_inc_return_release +static inline s64 +atomic64_inc_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_inc_return_relaxed(v); +} +#define atomic64_inc_return_release atomic64_inc_return_release +#endif + +#ifndef atomic64_inc_return +static inline s64 +atomic64_inc_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_inc_return atomic64_inc_return +#endif + +#endif /* atomic64_inc_return_relaxed */ + +#ifndef atomic64_fetch_inc_relaxed +#ifdef atomic64_fetch_inc +#define atomic64_fetch_inc_acquire atomic64_fetch_inc +#define atomic64_fetch_inc_release atomic64_fetch_inc +#define atomic64_fetch_inc_relaxed atomic64_fetch_inc +#endif /* atomic64_fetch_inc */ + +#ifndef atomic64_fetch_inc +static inline s64 +atomic64_fetch_inc(atomic64_t *v) +{ + return atomic64_fetch_add(1, v); +} +#define atomic64_fetch_inc atomic64_fetch_inc +#endif + +#ifndef atomic64_fetch_inc_acquire +static inline s64 +atomic64_fetch_inc_acquire(atomic64_t *v) +{ + return atomic64_fetch_add_acquire(1, v); +} +#define atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire +#endif + +#ifndef atomic64_fetch_inc_release +static inline s64 +atomic64_fetch_inc_release(atomic64_t *v) +{ + return atomic64_fetch_add_release(1, v); +} +#define atomic64_fetch_inc_release atomic64_fetch_inc_release +#endif + +#ifndef atomic64_fetch_inc_relaxed +static inline s64 +atomic64_fetch_inc_relaxed(atomic64_t *v) +{ + return atomic64_fetch_add_relaxed(1, v); +} +#define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed +#endif + +#else /* atomic64_fetch_inc_relaxed */ + +#ifndef atomic64_fetch_inc_acquire +static inline s64 +atomic64_fetch_inc_acquire(atomic64_t *v) +{ + s64 ret = atomic64_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire +#endif + +#ifndef atomic64_fetch_inc_release +static inline s64 +atomic64_fetch_inc_release(atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_fetch_inc_relaxed(v); +} +#define atomic64_fetch_inc_release atomic64_fetch_inc_release +#endif + +#ifndef atomic64_fetch_inc +static inline s64 +atomic64_fetch_inc(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_fetch_inc atomic64_fetch_inc +#endif + +#endif /* atomic64_fetch_inc_relaxed */ + +#ifndef atomic64_dec +static inline void +atomic64_dec(atomic64_t *v) +{ + atomic64_sub(1, v); +} +#define atomic64_dec atomic64_dec +#endif + +#ifndef atomic64_dec_return_relaxed +#ifdef atomic64_dec_return +#define atomic64_dec_return_acquire atomic64_dec_return +#define atomic64_dec_return_release atomic64_dec_return +#define atomic64_dec_return_relaxed atomic64_dec_return +#endif /* atomic64_dec_return */ + +#ifndef atomic64_dec_return +static inline s64 +atomic64_dec_return(atomic64_t *v) +{ + return atomic64_sub_return(1, v); +} +#define atomic64_dec_return atomic64_dec_return +#endif + +#ifndef atomic64_dec_return_acquire +static inline s64 +atomic64_dec_return_acquire(atomic64_t *v) +{ + return atomic64_sub_return_acquire(1, v); +} +#define atomic64_dec_return_acquire atomic64_dec_return_acquire +#endif + +#ifndef atomic64_dec_return_release +static inline s64 +atomic64_dec_return_release(atomic64_t *v) +{ + return atomic64_sub_return_release(1, v); +} +#define atomic64_dec_return_release atomic64_dec_return_release +#endif + +#ifndef atomic64_dec_return_relaxed +static inline s64 +atomic64_dec_return_relaxed(atomic64_t *v) +{ + return atomic64_sub_return_relaxed(1, v); +} +#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed +#endif + +#else /* atomic64_dec_return_relaxed */ + +#ifndef atomic64_dec_return_acquire +static inline s64 +atomic64_dec_return_acquire(atomic64_t *v) +{ + s64 ret = atomic64_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_dec_return_acquire atomic64_dec_return_acquire +#endif + +#ifndef atomic64_dec_return_release +static inline s64 +atomic64_dec_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_dec_return_relaxed(v); +} +#define atomic64_dec_return_release atomic64_dec_return_release +#endif + +#ifndef atomic64_dec_return +static inline s64 +atomic64_dec_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_dec_return atomic64_dec_return +#endif + +#endif /* atomic64_dec_return_relaxed */ + +#ifndef atomic64_fetch_dec_relaxed +#ifdef atomic64_fetch_dec +#define atomic64_fetch_dec_acquire atomic64_fetch_dec +#define atomic64_fetch_dec_release atomic64_fetch_dec +#define atomic64_fetch_dec_relaxed atomic64_fetch_dec +#endif /* atomic64_fetch_dec */ + +#ifndef atomic64_fetch_dec +static inline s64 +atomic64_fetch_dec(atomic64_t *v) +{ + return atomic64_fetch_sub(1, v); +} +#define atomic64_fetch_dec atomic64_fetch_dec +#endif + +#ifndef atomic64_fetch_dec_acquire +static inline s64 +atomic64_fetch_dec_acquire(atomic64_t *v) +{ + return atomic64_fetch_sub_acquire(1, v); +} +#define atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire +#endif + +#ifndef atomic64_fetch_dec_release +static inline s64 +atomic64_fetch_dec_release(atomic64_t *v) +{ + return atomic64_fetch_sub_release(1, v); +} +#define atomic64_fetch_dec_release atomic64_fetch_dec_release +#endif + +#ifndef atomic64_fetch_dec_relaxed +static inline s64 +atomic64_fetch_dec_relaxed(atomic64_t *v) +{ + return atomic64_fetch_sub_relaxed(1, v); +} +#define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed +#endif + +#else /* atomic64_fetch_dec_relaxed */ + +#ifndef atomic64_fetch_dec_acquire +static inline s64 +atomic64_fetch_dec_acquire(atomic64_t *v) +{ + s64 ret = atomic64_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire +#endif + +#ifndef atomic64_fetch_dec_release +static inline s64 +atomic64_fetch_dec_release(atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_fetch_dec_relaxed(v); +} +#define atomic64_fetch_dec_release atomic64_fetch_dec_release +#endif + +#ifndef atomic64_fetch_dec +static inline s64 +atomic64_fetch_dec(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_fetch_dec atomic64_fetch_dec +#endif + +#endif /* atomic64_fetch_dec_relaxed */ + +#ifndef atomic64_fetch_and_relaxed +#define atomic64_fetch_and_acquire atomic64_fetch_and +#define atomic64_fetch_and_release atomic64_fetch_and +#define atomic64_fetch_and_relaxed atomic64_fetch_and +#else /* atomic64_fetch_and_relaxed */ + +#ifndef atomic64_fetch_and_acquire +static inline s64 +atomic64_fetch_and_acquire(s64 i, atomic64_t *v) +{ + s64 ret = atomic64_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_fetch_and_acquire atomic64_fetch_and_acquire +#endif + +#ifndef atomic64_fetch_and_release +static inline s64 +atomic64_fetch_and_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_fetch_and_relaxed(i, v); +} +#define atomic64_fetch_and_release atomic64_fetch_and_release +#endif + +#ifndef atomic64_fetch_and +static inline s64 +atomic64_fetch_and(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_fetch_and atomic64_fetch_and +#endif + +#endif /* atomic64_fetch_and_relaxed */ + +#ifndef atomic64_andnot +static inline void +atomic64_andnot(s64 i, atomic64_t *v) +{ + atomic64_and(~i, v); +} +#define atomic64_andnot atomic64_andnot +#endif + +#ifndef atomic64_fetch_andnot_relaxed +#ifdef atomic64_fetch_andnot +#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot +#define atomic64_fetch_andnot_release atomic64_fetch_andnot +#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot +#endif /* atomic64_fetch_andnot */ + +#ifndef atomic64_fetch_andnot +static inline s64 +atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + return atomic64_fetch_and(~i, v); +} +#define atomic64_fetch_andnot atomic64_fetch_andnot +#endif + +#ifndef atomic64_fetch_andnot_acquire +static inline s64 +atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + return atomic64_fetch_and_acquire(~i, v); +} +#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire +#endif + +#ifndef atomic64_fetch_andnot_release +static inline s64 +atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + return atomic64_fetch_and_release(~i, v); +} +#define atomic64_fetch_andnot_release atomic64_fetch_andnot_release +#endif + +#ifndef atomic64_fetch_andnot_relaxed +static inline s64 +atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) +{ + return atomic64_fetch_and_relaxed(~i, v); +} +#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed +#endif + +#else /* atomic64_fetch_andnot_relaxed */ + +#ifndef atomic64_fetch_andnot_acquire +static inline s64 +atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + s64 ret = atomic64_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire +#endif + +#ifndef atomic64_fetch_andnot_release +static inline s64 +atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_fetch_andnot_relaxed(i, v); +} +#define atomic64_fetch_andnot_release atomic64_fetch_andnot_release +#endif + +#ifndef atomic64_fetch_andnot +static inline s64 +atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_fetch_andnot atomic64_fetch_andnot +#endif + +#endif /* atomic64_fetch_andnot_relaxed */ + +#ifndef atomic64_fetch_or_relaxed +#define atomic64_fetch_or_acquire atomic64_fetch_or +#define atomic64_fetch_or_release atomic64_fetch_or +#define atomic64_fetch_or_relaxed atomic64_fetch_or +#else /* atomic64_fetch_or_relaxed */ + +#ifndef atomic64_fetch_or_acquire +static inline s64 +atomic64_fetch_or_acquire(s64 i, atomic64_t *v) +{ + s64 ret = atomic64_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_fetch_or_acquire atomic64_fetch_or_acquire +#endif + +#ifndef atomic64_fetch_or_release +static inline s64 +atomic64_fetch_or_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_fetch_or_relaxed(i, v); +} +#define atomic64_fetch_or_release atomic64_fetch_or_release +#endif + +#ifndef atomic64_fetch_or +static inline s64 +atomic64_fetch_or(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_fetch_or atomic64_fetch_or +#endif + +#endif /* atomic64_fetch_or_relaxed */ + +#ifndef atomic64_fetch_xor_relaxed +#define atomic64_fetch_xor_acquire atomic64_fetch_xor +#define atomic64_fetch_xor_release atomic64_fetch_xor +#define atomic64_fetch_xor_relaxed atomic64_fetch_xor +#else /* atomic64_fetch_xor_relaxed */ + +#ifndef atomic64_fetch_xor_acquire +static inline s64 +atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) +{ + s64 ret = atomic64_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire +#endif + +#ifndef atomic64_fetch_xor_release +static inline s64 +atomic64_fetch_xor_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return atomic64_fetch_xor_relaxed(i, v); +} +#define atomic64_fetch_xor_release atomic64_fetch_xor_release +#endif + +#ifndef atomic64_fetch_xor +static inline s64 +atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_fetch_xor atomic64_fetch_xor +#endif + +#endif /* atomic64_fetch_xor_relaxed */ + +#ifndef atomic64_xchg_relaxed +#define atomic64_xchg_acquire atomic64_xchg +#define atomic64_xchg_release atomic64_xchg +#define atomic64_xchg_relaxed atomic64_xchg +#else /* atomic64_xchg_relaxed */ + +#ifndef atomic64_xchg_acquire +static inline s64 +atomic64_xchg_acquire(atomic64_t *v, s64 i) +{ + s64 ret = atomic64_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_xchg_acquire atomic64_xchg_acquire +#endif + +#ifndef atomic64_xchg_release +static inline s64 +atomic64_xchg_release(atomic64_t *v, s64 i) +{ + __atomic_release_fence(); + return atomic64_xchg_relaxed(v, i); +} +#define atomic64_xchg_release atomic64_xchg_release +#endif + +#ifndef atomic64_xchg +static inline s64 +atomic64_xchg(atomic64_t *v, s64 i) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_xchg atomic64_xchg +#endif + +#endif /* atomic64_xchg_relaxed */ + +#ifndef atomic64_cmpxchg_relaxed +#define atomic64_cmpxchg_acquire atomic64_cmpxchg +#define atomic64_cmpxchg_release atomic64_cmpxchg +#define atomic64_cmpxchg_relaxed atomic64_cmpxchg +#else /* atomic64_cmpxchg_relaxed */ + +#ifndef atomic64_cmpxchg_acquire +static inline s64 +atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) +{ + s64 ret = atomic64_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire +#endif + +#ifndef atomic64_cmpxchg_release +static inline s64 +atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) +{ + __atomic_release_fence(); + return atomic64_cmpxchg_relaxed(v, old, new); +} +#define atomic64_cmpxchg_release atomic64_cmpxchg_release +#endif + +#ifndef atomic64_cmpxchg +static inline s64 +atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = atomic64_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_cmpxchg atomic64_cmpxchg +#endif + +#endif /* atomic64_cmpxchg_relaxed */ + +#ifndef atomic64_try_cmpxchg_relaxed +#ifdef atomic64_try_cmpxchg +#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg +#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg +#define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg +#endif /* atomic64_try_cmpxchg */ + +#ifndef atomic64_try_cmpxchg +static inline bool +atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = atomic64_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define atomic64_try_cmpxchg atomic64_try_cmpxchg +#endif + +#ifndef atomic64_try_cmpxchg_acquire +static inline bool +atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = atomic64_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire +#endif + +#ifndef atomic64_try_cmpxchg_release +static inline bool +atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = atomic64_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release +#endif + +#ifndef atomic64_try_cmpxchg_relaxed +static inline bool +atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = atomic64_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed +#endif + +#else /* atomic64_try_cmpxchg_relaxed */ + +#ifndef atomic64_try_cmpxchg_acquire +static inline bool +atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + bool ret = atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire +#endif + +#ifndef atomic64_try_cmpxchg_release +static inline bool +atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + __atomic_release_fence(); + return atomic64_try_cmpxchg_relaxed(v, old, new); +} +#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release +#endif + +#ifndef atomic64_try_cmpxchg +static inline bool +atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define atomic64_try_cmpxchg atomic64_try_cmpxchg +#endif + +#endif /* atomic64_try_cmpxchg_relaxed */ + +#ifndef atomic64_sub_and_test +/** + * atomic64_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic64_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static inline bool +atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + return atomic64_sub_return(i, v) == 0; +} +#define atomic64_sub_and_test atomic64_sub_and_test +#endif + +#ifndef atomic64_dec_and_test +/** + * atomic64_dec_and_test - decrement and test + * @v: pointer of type atomic64_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static inline bool +atomic64_dec_and_test(atomic64_t *v) +{ + return atomic64_dec_return(v) == 0; +} +#define atomic64_dec_and_test atomic64_dec_and_test +#endif + +#ifndef atomic64_inc_and_test +/** + * atomic64_inc_and_test - increment and test + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static inline bool +atomic64_inc_and_test(atomic64_t *v) +{ + return atomic64_inc_return(v) == 0; +} +#define atomic64_inc_and_test atomic64_inc_and_test +#endif + +#ifndef atomic64_add_negative +/** + * atomic64_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static inline bool +atomic64_add_negative(s64 i, atomic64_t *v) +{ + return atomic64_add_return(i, v) < 0; +} +#define atomic64_add_negative atomic64_add_negative +#endif + +#ifndef atomic64_fetch_add_unless +/** + * atomic64_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static inline s64 +atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + s64 c = atomic64_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic64_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define atomic64_fetch_add_unless atomic64_fetch_add_unless +#endif + +#ifndef atomic64_add_unless +/** + * atomic64_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static inline bool +atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +{ + return atomic64_fetch_add_unless(v, a, u) != u; +} +#define atomic64_add_unless atomic64_add_unless +#endif + +#ifndef atomic64_inc_not_zero +/** + * atomic64_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static inline bool +atomic64_inc_not_zero(atomic64_t *v) +{ + return atomic64_add_unless(v, 1, 0); +} +#define atomic64_inc_not_zero atomic64_inc_not_zero +#endif + +#ifndef atomic64_inc_unless_negative +static inline bool +atomic64_inc_unless_negative(atomic64_t *v) +{ + s64 c = atomic64_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define atomic64_inc_unless_negative atomic64_inc_unless_negative +#endif + +#ifndef atomic64_dec_unless_positive +static inline bool +atomic64_dec_unless_positive(atomic64_t *v) +{ + s64 c = atomic64_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define atomic64_dec_unless_positive atomic64_dec_unless_positive +#endif + +#ifndef atomic64_dec_if_positive +static inline s64 +atomic64_dec_if_positive(atomic64_t *v) +{ + s64 dec, c = atomic64_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!atomic64_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define atomic64_dec_if_positive atomic64_dec_if_positive +#endif + +#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) +#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) + +#endif /* _LINUX_ATOMIC_FALLBACK_H */ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 1e8e88bdaf09..4c0d009a46f0 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -25,14 +25,6 @@ * See Documentation/memory-barriers.txt for ACQUIRE/RELEASE definitions. */ -#ifndef atomic_read_acquire -#define atomic_read_acquire(v) smp_load_acquire(&(v)->counter) -#endif - -#ifndef atomic_set_release -#define atomic_set_release(v, i) smp_store_release(&(v)->counter, (i)) -#endif - /* * The idea here is to build acquire/release variants by adding explicit * barriers on top of the relaxed variant. In the case where the relaxed @@ -79,1238 +71,7 @@ __ret; \ }) -/* atomic_add_return_relaxed */ -#ifndef atomic_add_return_relaxed -#define atomic_add_return_relaxed atomic_add_return -#define atomic_add_return_acquire atomic_add_return -#define atomic_add_return_release atomic_add_return - -#else /* atomic_add_return_relaxed */ - -#ifndef atomic_add_return_acquire -#define atomic_add_return_acquire(...) \ - __atomic_op_acquire(atomic_add_return, __VA_ARGS__) -#endif - -#ifndef atomic_add_return_release -#define atomic_add_return_release(...) \ - __atomic_op_release(atomic_add_return, __VA_ARGS__) -#endif - -#ifndef atomic_add_return -#define atomic_add_return(...) \ - __atomic_op_fence(atomic_add_return, __VA_ARGS__) -#endif -#endif /* atomic_add_return_relaxed */ - -#ifndef atomic_inc -#define atomic_inc(v) atomic_add(1, (v)) -#endif - -/* atomic_inc_return_relaxed */ -#ifndef atomic_inc_return_relaxed - -#ifndef atomic_inc_return -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) -#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) -#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) -#else /* atomic_inc_return */ -#define atomic_inc_return_relaxed atomic_inc_return -#define atomic_inc_return_acquire atomic_inc_return -#define atomic_inc_return_release atomic_inc_return -#endif /* atomic_inc_return */ - -#else /* atomic_inc_return_relaxed */ - -#ifndef atomic_inc_return_acquire -#define atomic_inc_return_acquire(...) \ - __atomic_op_acquire(atomic_inc_return, __VA_ARGS__) -#endif - -#ifndef atomic_inc_return_release -#define atomic_inc_return_release(...) \ - __atomic_op_release(atomic_inc_return, __VA_ARGS__) -#endif - -#ifndef atomic_inc_return -#define atomic_inc_return(...) \ - __atomic_op_fence(atomic_inc_return, __VA_ARGS__) -#endif -#endif /* atomic_inc_return_relaxed */ - -/* atomic_sub_return_relaxed */ -#ifndef atomic_sub_return_relaxed -#define atomic_sub_return_relaxed atomic_sub_return -#define atomic_sub_return_acquire atomic_sub_return -#define atomic_sub_return_release atomic_sub_return - -#else /* atomic_sub_return_relaxed */ - -#ifndef atomic_sub_return_acquire -#define atomic_sub_return_acquire(...) \ - __atomic_op_acquire(atomic_sub_return, __VA_ARGS__) -#endif - -#ifndef atomic_sub_return_release -#define atomic_sub_return_release(...) \ - __atomic_op_release(atomic_sub_return, __VA_ARGS__) -#endif - -#ifndef atomic_sub_return -#define atomic_sub_return(...) \ - __atomic_op_fence(atomic_sub_return, __VA_ARGS__) -#endif -#endif /* atomic_sub_return_relaxed */ - -#ifndef atomic_dec -#define atomic_dec(v) atomic_sub(1, (v)) -#endif - -/* atomic_dec_return_relaxed */ -#ifndef atomic_dec_return_relaxed - -#ifndef atomic_dec_return -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) -#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) -#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) -#else /* atomic_dec_return */ -#define atomic_dec_return_relaxed atomic_dec_return -#define atomic_dec_return_acquire atomic_dec_return -#define atomic_dec_return_release atomic_dec_return -#endif /* atomic_dec_return */ - -#else /* atomic_dec_return_relaxed */ - -#ifndef atomic_dec_return_acquire -#define atomic_dec_return_acquire(...) \ - __atomic_op_acquire(atomic_dec_return, __VA_ARGS__) -#endif - -#ifndef atomic_dec_return_release -#define atomic_dec_return_release(...) \ - __atomic_op_release(atomic_dec_return, __VA_ARGS__) -#endif - -#ifndef atomic_dec_return -#define atomic_dec_return(...) \ - __atomic_op_fence(atomic_dec_return, __VA_ARGS__) -#endif -#endif /* atomic_dec_return_relaxed */ - - -/* atomic_fetch_add_relaxed */ -#ifndef atomic_fetch_add_relaxed -#define atomic_fetch_add_relaxed atomic_fetch_add -#define atomic_fetch_add_acquire atomic_fetch_add -#define atomic_fetch_add_release atomic_fetch_add - -#else /* atomic_fetch_add_relaxed */ - -#ifndef atomic_fetch_add_acquire -#define atomic_fetch_add_acquire(...) \ - __atomic_op_acquire(atomic_fetch_add, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_add_release -#define atomic_fetch_add_release(...) \ - __atomic_op_release(atomic_fetch_add, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_add -#define atomic_fetch_add(...) \ - __atomic_op_fence(atomic_fetch_add, __VA_ARGS__) -#endif -#endif /* atomic_fetch_add_relaxed */ - -/* atomic_fetch_inc_relaxed */ -#ifndef atomic_fetch_inc_relaxed - -#ifndef atomic_fetch_inc -#define atomic_fetch_inc(v) atomic_fetch_add(1, (v)) -#define atomic_fetch_inc_relaxed(v) atomic_fetch_add_relaxed(1, (v)) -#define atomic_fetch_inc_acquire(v) atomic_fetch_add_acquire(1, (v)) -#define atomic_fetch_inc_release(v) atomic_fetch_add_release(1, (v)) -#else /* atomic_fetch_inc */ -#define atomic_fetch_inc_relaxed atomic_fetch_inc -#define atomic_fetch_inc_acquire atomic_fetch_inc -#define atomic_fetch_inc_release atomic_fetch_inc -#endif /* atomic_fetch_inc */ - -#else /* atomic_fetch_inc_relaxed */ - -#ifndef atomic_fetch_inc_acquire -#define atomic_fetch_inc_acquire(...) \ - __atomic_op_acquire(atomic_fetch_inc, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_inc_release -#define atomic_fetch_inc_release(...) \ - __atomic_op_release(atomic_fetch_inc, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_inc -#define atomic_fetch_inc(...) \ - __atomic_op_fence(atomic_fetch_inc, __VA_ARGS__) -#endif -#endif /* atomic_fetch_inc_relaxed */ - -/* atomic_fetch_sub_relaxed */ -#ifndef atomic_fetch_sub_relaxed -#define atomic_fetch_sub_relaxed atomic_fetch_sub -#define atomic_fetch_sub_acquire atomic_fetch_sub -#define atomic_fetch_sub_release atomic_fetch_sub - -#else /* atomic_fetch_sub_relaxed */ - -#ifndef atomic_fetch_sub_acquire -#define atomic_fetch_sub_acquire(...) \ - __atomic_op_acquire(atomic_fetch_sub, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_sub_release -#define atomic_fetch_sub_release(...) \ - __atomic_op_release(atomic_fetch_sub, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_sub -#define atomic_fetch_sub(...) \ - __atomic_op_fence(atomic_fetch_sub, __VA_ARGS__) -#endif -#endif /* atomic_fetch_sub_relaxed */ - -/* atomic_fetch_dec_relaxed */ -#ifndef atomic_fetch_dec_relaxed - -#ifndef atomic_fetch_dec -#define atomic_fetch_dec(v) atomic_fetch_sub(1, (v)) -#define atomic_fetch_dec_relaxed(v) atomic_fetch_sub_relaxed(1, (v)) -#define atomic_fetch_dec_acquire(v) atomic_fetch_sub_acquire(1, (v)) -#define atomic_fetch_dec_release(v) atomic_fetch_sub_release(1, (v)) -#else /* atomic_fetch_dec */ -#define atomic_fetch_dec_relaxed atomic_fetch_dec -#define atomic_fetch_dec_acquire atomic_fetch_dec -#define atomic_fetch_dec_release atomic_fetch_dec -#endif /* atomic_fetch_dec */ - -#else /* atomic_fetch_dec_relaxed */ - -#ifndef atomic_fetch_dec_acquire -#define atomic_fetch_dec_acquire(...) \ - __atomic_op_acquire(atomic_fetch_dec, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_dec_release -#define atomic_fetch_dec_release(...) \ - __atomic_op_release(atomic_fetch_dec, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_dec -#define atomic_fetch_dec(...) \ - __atomic_op_fence(atomic_fetch_dec, __VA_ARGS__) -#endif -#endif /* atomic_fetch_dec_relaxed */ - -/* atomic_fetch_or_relaxed */ -#ifndef atomic_fetch_or_relaxed -#define atomic_fetch_or_relaxed atomic_fetch_or -#define atomic_fetch_or_acquire atomic_fetch_or -#define atomic_fetch_or_release atomic_fetch_or - -#else /* atomic_fetch_or_relaxed */ - -#ifndef atomic_fetch_or_acquire -#define atomic_fetch_or_acquire(...) \ - __atomic_op_acquire(atomic_fetch_or, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_or_release -#define atomic_fetch_or_release(...) \ - __atomic_op_release(atomic_fetch_or, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_or -#define atomic_fetch_or(...) \ - __atomic_op_fence(atomic_fetch_or, __VA_ARGS__) -#endif -#endif /* atomic_fetch_or_relaxed */ - -/* atomic_fetch_and_relaxed */ -#ifndef atomic_fetch_and_relaxed -#define atomic_fetch_and_relaxed atomic_fetch_and -#define atomic_fetch_and_acquire atomic_fetch_and -#define atomic_fetch_and_release atomic_fetch_and - -#else /* atomic_fetch_and_relaxed */ - -#ifndef atomic_fetch_and_acquire -#define atomic_fetch_and_acquire(...) \ - __atomic_op_acquire(atomic_fetch_and, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_and_release -#define atomic_fetch_and_release(...) \ - __atomic_op_release(atomic_fetch_and, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_and -#define atomic_fetch_and(...) \ - __atomic_op_fence(atomic_fetch_and, __VA_ARGS__) -#endif -#endif /* atomic_fetch_and_relaxed */ - -#ifndef atomic_andnot -#define atomic_andnot(i, v) atomic_and(~(int)(i), (v)) -#endif - -#ifndef atomic_fetch_andnot_relaxed - -#ifndef atomic_fetch_andnot -#define atomic_fetch_andnot(i, v) atomic_fetch_and(~(int)(i), (v)) -#define atomic_fetch_andnot_relaxed(i, v) atomic_fetch_and_relaxed(~(int)(i), (v)) -#define atomic_fetch_andnot_acquire(i, v) atomic_fetch_and_acquire(~(int)(i), (v)) -#define atomic_fetch_andnot_release(i, v) atomic_fetch_and_release(~(int)(i), (v)) -#else /* atomic_fetch_andnot */ -#define atomic_fetch_andnot_relaxed atomic_fetch_andnot -#define atomic_fetch_andnot_acquire atomic_fetch_andnot -#define atomic_fetch_andnot_release atomic_fetch_andnot -#endif /* atomic_fetch_andnot */ - -#else /* atomic_fetch_andnot_relaxed */ - -#ifndef atomic_fetch_andnot_acquire -#define atomic_fetch_andnot_acquire(...) \ - __atomic_op_acquire(atomic_fetch_andnot, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_andnot_release -#define atomic_fetch_andnot_release(...) \ - __atomic_op_release(atomic_fetch_andnot, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_andnot -#define atomic_fetch_andnot(...) \ - __atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__) -#endif -#endif /* atomic_fetch_andnot_relaxed */ - -/* atomic_fetch_xor_relaxed */ -#ifndef atomic_fetch_xor_relaxed -#define atomic_fetch_xor_relaxed atomic_fetch_xor -#define atomic_fetch_xor_acquire atomic_fetch_xor -#define atomic_fetch_xor_release atomic_fetch_xor - -#else /* atomic_fetch_xor_relaxed */ - -#ifndef atomic_fetch_xor_acquire -#define atomic_fetch_xor_acquire(...) \ - __atomic_op_acquire(atomic_fetch_xor, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_xor_release -#define atomic_fetch_xor_release(...) \ - __atomic_op_release(atomic_fetch_xor, __VA_ARGS__) -#endif - -#ifndef atomic_fetch_xor -#define atomic_fetch_xor(...) \ - __atomic_op_fence(atomic_fetch_xor, __VA_ARGS__) -#endif -#endif /* atomic_fetch_xor_relaxed */ - - -/* atomic_xchg_relaxed */ -#ifndef atomic_xchg_relaxed -#define atomic_xchg_relaxed atomic_xchg -#define atomic_xchg_acquire atomic_xchg -#define atomic_xchg_release atomic_xchg - -#else /* atomic_xchg_relaxed */ - -#ifndef atomic_xchg_acquire -#define atomic_xchg_acquire(...) \ - __atomic_op_acquire(atomic_xchg, __VA_ARGS__) -#endif - -#ifndef atomic_xchg_release -#define atomic_xchg_release(...) \ - __atomic_op_release(atomic_xchg, __VA_ARGS__) -#endif - -#ifndef atomic_xchg -#define atomic_xchg(...) \ - __atomic_op_fence(atomic_xchg, __VA_ARGS__) -#endif -#endif /* atomic_xchg_relaxed */ - -/* atomic_cmpxchg_relaxed */ -#ifndef atomic_cmpxchg_relaxed -#define atomic_cmpxchg_relaxed atomic_cmpxchg -#define atomic_cmpxchg_acquire atomic_cmpxchg -#define atomic_cmpxchg_release atomic_cmpxchg - -#else /* atomic_cmpxchg_relaxed */ - -#ifndef atomic_cmpxchg_acquire -#define atomic_cmpxchg_acquire(...) \ - __atomic_op_acquire(atomic_cmpxchg, __VA_ARGS__) -#endif - -#ifndef atomic_cmpxchg_release -#define atomic_cmpxchg_release(...) \ - __atomic_op_release(atomic_cmpxchg, __VA_ARGS__) -#endif - -#ifndef atomic_cmpxchg -#define atomic_cmpxchg(...) \ - __atomic_op_fence(atomic_cmpxchg, __VA_ARGS__) -#endif -#endif /* atomic_cmpxchg_relaxed */ - -#ifndef atomic_try_cmpxchg - -#define __atomic_try_cmpxchg(type, _p, _po, _n) \ -({ \ - typeof(_po) __po = (_po); \ - typeof(*(_po)) __r, __o = *__po; \ - __r = atomic_cmpxchg##type((_p), __o, (_n)); \ - if (unlikely(__r != __o)) \ - *__po = __r; \ - likely(__r == __o); \ -}) - -#define atomic_try_cmpxchg(_p, _po, _n) __atomic_try_cmpxchg(, _p, _po, _n) -#define atomic_try_cmpxchg_relaxed(_p, _po, _n) __atomic_try_cmpxchg(_relaxed, _p, _po, _n) -#define atomic_try_cmpxchg_acquire(_p, _po, _n) __atomic_try_cmpxchg(_acquire, _p, _po, _n) -#define atomic_try_cmpxchg_release(_p, _po, _n) __atomic_try_cmpxchg(_release, _p, _po, _n) - -#else /* atomic_try_cmpxchg */ -#define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg -#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg -#define atomic_try_cmpxchg_release atomic_try_cmpxchg -#endif /* atomic_try_cmpxchg */ - -/* cmpxchg_relaxed */ -#ifndef cmpxchg_relaxed -#define cmpxchg_relaxed cmpxchg -#define cmpxchg_acquire cmpxchg -#define cmpxchg_release cmpxchg - -#else /* cmpxchg_relaxed */ - -#ifndef cmpxchg_acquire -#define cmpxchg_acquire(...) \ - __atomic_op_acquire(cmpxchg, __VA_ARGS__) -#endif - -#ifndef cmpxchg_release -#define cmpxchg_release(...) \ - __atomic_op_release(cmpxchg, __VA_ARGS__) -#endif - -#ifndef cmpxchg -#define cmpxchg(...) \ - __atomic_op_fence(cmpxchg, __VA_ARGS__) -#endif -#endif /* cmpxchg_relaxed */ - -/* cmpxchg64_relaxed */ -#ifndef cmpxchg64_relaxed -#define cmpxchg64_relaxed cmpxchg64 -#define cmpxchg64_acquire cmpxchg64 -#define cmpxchg64_release cmpxchg64 - -#else /* cmpxchg64_relaxed */ - -#ifndef cmpxchg64_acquire -#define cmpxchg64_acquire(...) \ - __atomic_op_acquire(cmpxchg64, __VA_ARGS__) -#endif - -#ifndef cmpxchg64_release -#define cmpxchg64_release(...) \ - __atomic_op_release(cmpxchg64, __VA_ARGS__) -#endif - -#ifndef cmpxchg64 -#define cmpxchg64(...) \ - __atomic_op_fence(cmpxchg64, __VA_ARGS__) -#endif -#endif /* cmpxchg64_relaxed */ - -/* xchg_relaxed */ -#ifndef xchg_relaxed -#define xchg_relaxed xchg -#define xchg_acquire xchg -#define xchg_release xchg - -#else /* xchg_relaxed */ - -#ifndef xchg_acquire -#define xchg_acquire(...) __atomic_op_acquire(xchg, __VA_ARGS__) -#endif - -#ifndef xchg_release -#define xchg_release(...) __atomic_op_release(xchg, __VA_ARGS__) -#endif - -#ifndef xchg -#define xchg(...) __atomic_op_fence(xchg, __VA_ARGS__) -#endif -#endif /* xchg_relaxed */ - -/** - * atomic_fetch_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns the original value of @v. - */ -#ifndef atomic_fetch_add_unless -static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c = atomic_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!atomic_try_cmpxchg(v, &c, c + a)); - - return c; -} -#endif - -/** - * atomic_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns true if the addition was done. - */ -static inline bool atomic_add_unless(atomic_t *v, int a, int u) -{ - return atomic_fetch_add_unless(v, a, u) != u; -} - -/** - * atomic_inc_not_zero - increment unless the number is zero - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1, if @v is non-zero. - * Returns true if the increment was done. - */ -#ifndef atomic_inc_not_zero -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) -#endif - -/** - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#ifndef atomic_inc_and_test -static inline bool atomic_inc_and_test(atomic_t *v) -{ - return atomic_inc_return(v) == 0; -} -#endif - -/** - * atomic_dec_and_test - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#ifndef atomic_dec_and_test -static inline bool atomic_dec_and_test(atomic_t *v) -{ - return atomic_dec_return(v) == 0; -} -#endif - -/** - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#ifndef atomic_sub_and_test -static inline bool atomic_sub_and_test(int i, atomic_t *v) -{ - return atomic_sub_return(i, v) == 0; -} -#endif - -/** - * atomic_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer of type atomic_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#ifndef atomic_add_negative -static inline bool atomic_add_negative(int i, atomic_t *v) -{ - return atomic_add_return(i, v) < 0; -} -#endif - -#ifndef atomic_inc_unless_negative -static inline bool atomic_inc_unless_negative(atomic_t *v) -{ - int c = atomic_read(v); - - do { - if (unlikely(c < 0)) - return false; - } while (!atomic_try_cmpxchg(v, &c, c + 1)); - - return true; -} -#endif - -#ifndef atomic_dec_unless_positive -static inline bool atomic_dec_unless_positive(atomic_t *v) -{ - int c = atomic_read(v); - - do { - if (unlikely(c > 0)) - return false; - } while (!atomic_try_cmpxchg(v, &c, c - 1)); - - return true; -} -#endif - -/* - * atomic_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -#ifndef atomic_dec_if_positive -static inline int atomic_dec_if_positive(atomic_t *v) -{ - int dec, c = atomic_read(v); - - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!atomic_try_cmpxchg(v, &c, dec)); - - return dec; -} -#endif - -#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) -#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) - -#ifdef CONFIG_GENERIC_ATOMIC64 -#include -#endif - -#ifndef atomic64_read_acquire -#define atomic64_read_acquire(v) smp_load_acquire(&(v)->counter) -#endif - -#ifndef atomic64_set_release -#define atomic64_set_release(v, i) smp_store_release(&(v)->counter, (i)) -#endif - -/* atomic64_add_return_relaxed */ -#ifndef atomic64_add_return_relaxed -#define atomic64_add_return_relaxed atomic64_add_return -#define atomic64_add_return_acquire atomic64_add_return -#define atomic64_add_return_release atomic64_add_return - -#else /* atomic64_add_return_relaxed */ - -#ifndef atomic64_add_return_acquire -#define atomic64_add_return_acquire(...) \ - __atomic_op_acquire(atomic64_add_return, __VA_ARGS__) -#endif - -#ifndef atomic64_add_return_release -#define atomic64_add_return_release(...) \ - __atomic_op_release(atomic64_add_return, __VA_ARGS__) -#endif - -#ifndef atomic64_add_return -#define atomic64_add_return(...) \ - __atomic_op_fence(atomic64_add_return, __VA_ARGS__) -#endif -#endif /* atomic64_add_return_relaxed */ - -#ifndef atomic64_inc -#define atomic64_inc(v) atomic64_add(1, (v)) -#endif - -/* atomic64_inc_return_relaxed */ -#ifndef atomic64_inc_return_relaxed - -#ifndef atomic64_inc_return -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) -#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) -#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) -#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) -#else /* atomic64_inc_return */ -#define atomic64_inc_return_relaxed atomic64_inc_return -#define atomic64_inc_return_acquire atomic64_inc_return -#define atomic64_inc_return_release atomic64_inc_return -#endif /* atomic64_inc_return */ - -#else /* atomic64_inc_return_relaxed */ - -#ifndef atomic64_inc_return_acquire -#define atomic64_inc_return_acquire(...) \ - __atomic_op_acquire(atomic64_inc_return, __VA_ARGS__) -#endif - -#ifndef atomic64_inc_return_release -#define atomic64_inc_return_release(...) \ - __atomic_op_release(atomic64_inc_return, __VA_ARGS__) -#endif - -#ifndef atomic64_inc_return -#define atomic64_inc_return(...) \ - __atomic_op_fence(atomic64_inc_return, __VA_ARGS__) -#endif -#endif /* atomic64_inc_return_relaxed */ - - -/* atomic64_sub_return_relaxed */ -#ifndef atomic64_sub_return_relaxed -#define atomic64_sub_return_relaxed atomic64_sub_return -#define atomic64_sub_return_acquire atomic64_sub_return -#define atomic64_sub_return_release atomic64_sub_return - -#else /* atomic64_sub_return_relaxed */ - -#ifndef atomic64_sub_return_acquire -#define atomic64_sub_return_acquire(...) \ - __atomic_op_acquire(atomic64_sub_return, __VA_ARGS__) -#endif - -#ifndef atomic64_sub_return_release -#define atomic64_sub_return_release(...) \ - __atomic_op_release(atomic64_sub_return, __VA_ARGS__) -#endif - -#ifndef atomic64_sub_return -#define atomic64_sub_return(...) \ - __atomic_op_fence(atomic64_sub_return, __VA_ARGS__) -#endif -#endif /* atomic64_sub_return_relaxed */ - -#ifndef atomic64_dec -#define atomic64_dec(v) atomic64_sub(1, (v)) -#endif - -/* atomic64_dec_return_relaxed */ -#ifndef atomic64_dec_return_relaxed - -#ifndef atomic64_dec_return -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) -#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) -#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) -#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) -#else /* atomic64_dec_return */ -#define atomic64_dec_return_relaxed atomic64_dec_return -#define atomic64_dec_return_acquire atomic64_dec_return -#define atomic64_dec_return_release atomic64_dec_return -#endif /* atomic64_dec_return */ - -#else /* atomic64_dec_return_relaxed */ - -#ifndef atomic64_dec_return_acquire -#define atomic64_dec_return_acquire(...) \ - __atomic_op_acquire(atomic64_dec_return, __VA_ARGS__) -#endif - -#ifndef atomic64_dec_return_release -#define atomic64_dec_return_release(...) \ - __atomic_op_release(atomic64_dec_return, __VA_ARGS__) -#endif - -#ifndef atomic64_dec_return -#define atomic64_dec_return(...) \ - __atomic_op_fence(atomic64_dec_return, __VA_ARGS__) -#endif -#endif /* atomic64_dec_return_relaxed */ - - -/* atomic64_fetch_add_relaxed */ -#ifndef atomic64_fetch_add_relaxed -#define atomic64_fetch_add_relaxed atomic64_fetch_add -#define atomic64_fetch_add_acquire atomic64_fetch_add -#define atomic64_fetch_add_release atomic64_fetch_add - -#else /* atomic64_fetch_add_relaxed */ - -#ifndef atomic64_fetch_add_acquire -#define atomic64_fetch_add_acquire(...) \ - __atomic_op_acquire(atomic64_fetch_add, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_add_release -#define atomic64_fetch_add_release(...) \ - __atomic_op_release(atomic64_fetch_add, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_add -#define atomic64_fetch_add(...) \ - __atomic_op_fence(atomic64_fetch_add, __VA_ARGS__) -#endif -#endif /* atomic64_fetch_add_relaxed */ - -/* atomic64_fetch_inc_relaxed */ -#ifndef atomic64_fetch_inc_relaxed - -#ifndef atomic64_fetch_inc -#define atomic64_fetch_inc(v) atomic64_fetch_add(1, (v)) -#define atomic64_fetch_inc_relaxed(v) atomic64_fetch_add_relaxed(1, (v)) -#define atomic64_fetch_inc_acquire(v) atomic64_fetch_add_acquire(1, (v)) -#define atomic64_fetch_inc_release(v) atomic64_fetch_add_release(1, (v)) -#else /* atomic64_fetch_inc */ -#define atomic64_fetch_inc_relaxed atomic64_fetch_inc -#define atomic64_fetch_inc_acquire atomic64_fetch_inc -#define atomic64_fetch_inc_release atomic64_fetch_inc -#endif /* atomic64_fetch_inc */ - -#else /* atomic64_fetch_inc_relaxed */ - -#ifndef atomic64_fetch_inc_acquire -#define atomic64_fetch_inc_acquire(...) \ - __atomic_op_acquire(atomic64_fetch_inc, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_inc_release -#define atomic64_fetch_inc_release(...) \ - __atomic_op_release(atomic64_fetch_inc, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_inc -#define atomic64_fetch_inc(...) \ - __atomic_op_fence(atomic64_fetch_inc, __VA_ARGS__) -#endif -#endif /* atomic64_fetch_inc_relaxed */ - -/* atomic64_fetch_sub_relaxed */ -#ifndef atomic64_fetch_sub_relaxed -#define atomic64_fetch_sub_relaxed atomic64_fetch_sub -#define atomic64_fetch_sub_acquire atomic64_fetch_sub -#define atomic64_fetch_sub_release atomic64_fetch_sub - -#else /* atomic64_fetch_sub_relaxed */ - -#ifndef atomic64_fetch_sub_acquire -#define atomic64_fetch_sub_acquire(...) \ - __atomic_op_acquire(atomic64_fetch_sub, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_sub_release -#define atomic64_fetch_sub_release(...) \ - __atomic_op_release(atomic64_fetch_sub, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_sub -#define atomic64_fetch_sub(...) \ - __atomic_op_fence(atomic64_fetch_sub, __VA_ARGS__) -#endif -#endif /* atomic64_fetch_sub_relaxed */ - -/* atomic64_fetch_dec_relaxed */ -#ifndef atomic64_fetch_dec_relaxed - -#ifndef atomic64_fetch_dec -#define atomic64_fetch_dec(v) atomic64_fetch_sub(1, (v)) -#define atomic64_fetch_dec_relaxed(v) atomic64_fetch_sub_relaxed(1, (v)) -#define atomic64_fetch_dec_acquire(v) atomic64_fetch_sub_acquire(1, (v)) -#define atomic64_fetch_dec_release(v) atomic64_fetch_sub_release(1, (v)) -#else /* atomic64_fetch_dec */ -#define atomic64_fetch_dec_relaxed atomic64_fetch_dec -#define atomic64_fetch_dec_acquire atomic64_fetch_dec -#define atomic64_fetch_dec_release atomic64_fetch_dec -#endif /* atomic64_fetch_dec */ - -#else /* atomic64_fetch_dec_relaxed */ - -#ifndef atomic64_fetch_dec_acquire -#define atomic64_fetch_dec_acquire(...) \ - __atomic_op_acquire(atomic64_fetch_dec, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_dec_release -#define atomic64_fetch_dec_release(...) \ - __atomic_op_release(atomic64_fetch_dec, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_dec -#define atomic64_fetch_dec(...) \ - __atomic_op_fence(atomic64_fetch_dec, __VA_ARGS__) -#endif -#endif /* atomic64_fetch_dec_relaxed */ - -/* atomic64_fetch_or_relaxed */ -#ifndef atomic64_fetch_or_relaxed -#define atomic64_fetch_or_relaxed atomic64_fetch_or -#define atomic64_fetch_or_acquire atomic64_fetch_or -#define atomic64_fetch_or_release atomic64_fetch_or - -#else /* atomic64_fetch_or_relaxed */ - -#ifndef atomic64_fetch_or_acquire -#define atomic64_fetch_or_acquire(...) \ - __atomic_op_acquire(atomic64_fetch_or, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_or_release -#define atomic64_fetch_or_release(...) \ - __atomic_op_release(atomic64_fetch_or, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_or -#define atomic64_fetch_or(...) \ - __atomic_op_fence(atomic64_fetch_or, __VA_ARGS__) -#endif -#endif /* atomic64_fetch_or_relaxed */ - -/* atomic64_fetch_and_relaxed */ -#ifndef atomic64_fetch_and_relaxed -#define atomic64_fetch_and_relaxed atomic64_fetch_and -#define atomic64_fetch_and_acquire atomic64_fetch_and -#define atomic64_fetch_and_release atomic64_fetch_and - -#else /* atomic64_fetch_and_relaxed */ - -#ifndef atomic64_fetch_and_acquire -#define atomic64_fetch_and_acquire(...) \ - __atomic_op_acquire(atomic64_fetch_and, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_and_release -#define atomic64_fetch_and_release(...) \ - __atomic_op_release(atomic64_fetch_and, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_and -#define atomic64_fetch_and(...) \ - __atomic_op_fence(atomic64_fetch_and, __VA_ARGS__) -#endif -#endif /* atomic64_fetch_and_relaxed */ - -#ifndef atomic64_andnot -#define atomic64_andnot(i, v) atomic64_and(~(long long)(i), (v)) -#endif - -#ifndef atomic64_fetch_andnot_relaxed - -#ifndef atomic64_fetch_andnot -#define atomic64_fetch_andnot(i, v) atomic64_fetch_and(~(long long)(i), (v)) -#define atomic64_fetch_andnot_relaxed(i, v) atomic64_fetch_and_relaxed(~(long long)(i), (v)) -#define atomic64_fetch_andnot_acquire(i, v) atomic64_fetch_and_acquire(~(long long)(i), (v)) -#define atomic64_fetch_andnot_release(i, v) atomic64_fetch_and_release(~(long long)(i), (v)) -#else /* atomic64_fetch_andnot */ -#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot -#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot -#define atomic64_fetch_andnot_release atomic64_fetch_andnot -#endif /* atomic64_fetch_andnot */ - -#else /* atomic64_fetch_andnot_relaxed */ - -#ifndef atomic64_fetch_andnot_acquire -#define atomic64_fetch_andnot_acquire(...) \ - __atomic_op_acquire(atomic64_fetch_andnot, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_andnot_release -#define atomic64_fetch_andnot_release(...) \ - __atomic_op_release(atomic64_fetch_andnot, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_andnot -#define atomic64_fetch_andnot(...) \ - __atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__) -#endif -#endif /* atomic64_fetch_andnot_relaxed */ - -/* atomic64_fetch_xor_relaxed */ -#ifndef atomic64_fetch_xor_relaxed -#define atomic64_fetch_xor_relaxed atomic64_fetch_xor -#define atomic64_fetch_xor_acquire atomic64_fetch_xor -#define atomic64_fetch_xor_release atomic64_fetch_xor - -#else /* atomic64_fetch_xor_relaxed */ - -#ifndef atomic64_fetch_xor_acquire -#define atomic64_fetch_xor_acquire(...) \ - __atomic_op_acquire(atomic64_fetch_xor, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_xor_release -#define atomic64_fetch_xor_release(...) \ - __atomic_op_release(atomic64_fetch_xor, __VA_ARGS__) -#endif - -#ifndef atomic64_fetch_xor -#define atomic64_fetch_xor(...) \ - __atomic_op_fence(atomic64_fetch_xor, __VA_ARGS__) -#endif -#endif /* atomic64_fetch_xor_relaxed */ - - -/* atomic64_xchg_relaxed */ -#ifndef atomic64_xchg_relaxed -#define atomic64_xchg_relaxed atomic64_xchg -#define atomic64_xchg_acquire atomic64_xchg -#define atomic64_xchg_release atomic64_xchg - -#else /* atomic64_xchg_relaxed */ - -#ifndef atomic64_xchg_acquire -#define atomic64_xchg_acquire(...) \ - __atomic_op_acquire(atomic64_xchg, __VA_ARGS__) -#endif - -#ifndef atomic64_xchg_release -#define atomic64_xchg_release(...) \ - __atomic_op_release(atomic64_xchg, __VA_ARGS__) -#endif - -#ifndef atomic64_xchg -#define atomic64_xchg(...) \ - __atomic_op_fence(atomic64_xchg, __VA_ARGS__) -#endif -#endif /* atomic64_xchg_relaxed */ - -/* atomic64_cmpxchg_relaxed */ -#ifndef atomic64_cmpxchg_relaxed -#define atomic64_cmpxchg_relaxed atomic64_cmpxchg -#define atomic64_cmpxchg_acquire atomic64_cmpxchg -#define atomic64_cmpxchg_release atomic64_cmpxchg - -#else /* atomic64_cmpxchg_relaxed */ - -#ifndef atomic64_cmpxchg_acquire -#define atomic64_cmpxchg_acquire(...) \ - __atomic_op_acquire(atomic64_cmpxchg, __VA_ARGS__) -#endif - -#ifndef atomic64_cmpxchg_release -#define atomic64_cmpxchg_release(...) \ - __atomic_op_release(atomic64_cmpxchg, __VA_ARGS__) -#endif - -#ifndef atomic64_cmpxchg -#define atomic64_cmpxchg(...) \ - __atomic_op_fence(atomic64_cmpxchg, __VA_ARGS__) -#endif -#endif /* atomic64_cmpxchg_relaxed */ - -#ifndef atomic64_try_cmpxchg - -#define __atomic64_try_cmpxchg(type, _p, _po, _n) \ -({ \ - typeof(_po) __po = (_po); \ - typeof(*(_po)) __r, __o = *__po; \ - __r = atomic64_cmpxchg##type((_p), __o, (_n)); \ - if (unlikely(__r != __o)) \ - *__po = __r; \ - likely(__r == __o); \ -}) - -#define atomic64_try_cmpxchg(_p, _po, _n) __atomic64_try_cmpxchg(, _p, _po, _n) -#define atomic64_try_cmpxchg_relaxed(_p, _po, _n) __atomic64_try_cmpxchg(_relaxed, _p, _po, _n) -#define atomic64_try_cmpxchg_acquire(_p, _po, _n) __atomic64_try_cmpxchg(_acquire, _p, _po, _n) -#define atomic64_try_cmpxchg_release(_p, _po, _n) __atomic64_try_cmpxchg(_release, _p, _po, _n) - -#else /* atomic64_try_cmpxchg */ -#define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg -#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg -#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg -#endif /* atomic64_try_cmpxchg */ - -/** - * atomic64_fetch_add_unless - add unless the number is already a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns the original value of @v. - */ -#ifndef atomic64_fetch_add_unless -static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, - long long u) -{ - long long c = atomic64_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!atomic64_try_cmpxchg(v, &c, c + a)); - - return c; -} -#endif - -/** - * atomic64_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns true if the addition was done. - */ -static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u) -{ - return atomic64_fetch_add_unless(v, a, u) != u; -} - -/** - * atomic64_inc_not_zero - increment unless the number is zero - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1, if @v is non-zero. - * Returns true if the increment was done. - */ -#ifndef atomic64_inc_not_zero -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) -#endif - -/** - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#ifndef atomic64_inc_and_test -static inline bool atomic64_inc_and_test(atomic64_t *v) -{ - return atomic64_inc_return(v) == 0; -} -#endif - -/** - * atomic64_dec_and_test - decrement and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#ifndef atomic64_dec_and_test -static inline bool atomic64_dec_and_test(atomic64_t *v) -{ - return atomic64_dec_return(v) == 0; -} -#endif - -/** - * atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#ifndef atomic64_sub_and_test -static inline bool atomic64_sub_and_test(long long i, atomic64_t *v) -{ - return atomic64_sub_return(i, v) == 0; -} -#endif - -/** - * atomic64_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer of type atomic64_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#ifndef atomic64_add_negative -static inline bool atomic64_add_negative(long long i, atomic64_t *v) -{ - return atomic64_add_return(i, v) < 0; -} -#endif - -#ifndef atomic64_inc_unless_negative -static inline bool atomic64_inc_unless_negative(atomic64_t *v) -{ - long long c = atomic64_read(v); - - do { - if (unlikely(c < 0)) - return false; - } while (!atomic64_try_cmpxchg(v, &c, c + 1)); - - return true; -} -#endif - -#ifndef atomic64_dec_unless_positive -static inline bool atomic64_dec_unless_positive(atomic64_t *v) -{ - long long c = atomic64_read(v); - - do { - if (unlikely(c > 0)) - return false; - } while (!atomic64_try_cmpxchg(v, &c, c - 1)); - - return true; -} -#endif - -/* - * atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic64_t - * - * The function returns the old value of *v minus 1, even if - * the atomic64 variable, v, was not decremented. - */ -#ifndef atomic64_dec_if_positive -static inline long long atomic64_dec_if_positive(atomic64_t *v) -{ - long long dec, c = atomic64_read(v); - - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!atomic64_try_cmpxchg(v, &c, dec)); - - return dec; -} -#endif - -#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) -#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) +#include #include -- cgit v1.2.3 From b5d47ef9ea5c5fe31d7eabeb79f697629bd9e2cb Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 4 Sep 2018 11:48:27 +0100 Subject: locking/atomics: Switch to generated atomic-long As a step towards ensuring the atomic* APIs are consistent, let's switch to wrappers generated by gen-atomic-long.h, using the same table that gen-atomic-fallbacks.h uses to fill in gaps in the atomic_* and atomic64_* APIs. These are checked in rather than generated with Kbuild, since: * This allows inspection of the atomics with git grep and ctags on a pristine tree, which Linus strongly prefers being able to do. * The fallbacks are not affected by machine details or configuration options, so it is not necessary to regenerate them to take these into account. * These are included by files required *very* early in the build process (e.g. for generating bounds.h), and we'd rather not complicate the top-level Kbuild file with dependencies. Other than *_INIT() and *_cond_read_acquire(), all API functions are implemented as static inline C functions, ensuring consistent type promotion and/or truncation without requiring explicit casts to be applied to parameters or return values. Since we typedef atomic_long_t to either atomic_t or atomic64_t, we know these types are equivalent, and don't require explicit casts between them. However, as the try_cmpxchg*() functions take a pointer for the 'old' parameter, which may be an int or s64, an explicit cast is generated for this. There should be no functional change as a result of this patch (i.e. existing code should not be affected). However, this introduces a number of functions into the atomic_long_* API, bringing it into line with the atomic_* and atomic64_* APIs. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: catalin.marinas@arm.com Cc: linuxdrivers@attotech.com Cc: dvyukov@google.com Cc: Boqun Feng Cc: Arnd Bergmann Cc: aryabinin@virtuozzo.com Cc: glider@google.com Link: http://lkml.kernel.org/r/20180904104830.2975-4-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/atomic-long.h | 1173 ++++++++++++++++++++++++++++++------- 1 file changed, 958 insertions(+), 215 deletions(-) (limited to 'include') diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h index 87d14476edc2..a833d385a70b 100644 --- a/include/asm-generic/atomic-long.h +++ b/include/asm-generic/atomic-long.h @@ -1,269 +1,1012 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-long.sh +// DO NOT MODIFY THIS FILE DIRECTLY + #ifndef _ASM_GENERIC_ATOMIC_LONG_H #define _ASM_GENERIC_ATOMIC_LONG_H -/* - * Copyright (C) 2005 Silicon Graphics, Inc. - * Christoph Lameter - * - * Allows to provide arch independent atomic definitions without the need to - * edit all arch specific atomic.h files. - */ #include -/* - * Suppport for atomic_long_t - * - * Casts for parameters are avoided for existing atomic functions in order to - * avoid issues with cast-as-lval under gcc 4.x and other limitations that the - * macros of a platform may have. - */ +#ifdef CONFIG_64BIT +typedef atomic64_t atomic_long_t; +#define ATOMIC_LONG_INIT(i) ATOMIC64_INIT(i) +#define atomic_long_cond_read_acquire atomic64_cond_read_acquire +#define atomic_long_cond_read_relaxed atomic64_cond_read_relaxed +#else +typedef atomic_t atomic_long_t; +#define ATOMIC_LONG_INIT(i) ATOMIC_INIT(i) +#define atomic_long_cond_read_acquire atomic_cond_read_acquire +#define atomic_long_cond_read_relaxed atomic_cond_read_relaxed +#endif -#if BITS_PER_LONG == 64 +#ifdef CONFIG_64BIT -typedef atomic64_t atomic_long_t; +static inline long +atomic_long_read(const atomic_long_t *v) +{ + return atomic64_read(v); +} -#define ATOMIC_LONG_INIT(i) ATOMIC64_INIT(i) -#define ATOMIC_LONG_PFX(x) atomic64 ## x -#define ATOMIC_LONG_TYPE s64 +static inline long +atomic_long_read_acquire(const atomic_long_t *v) +{ + return atomic64_read_acquire(v); +} -#else +static inline void +atomic_long_set(atomic_long_t *v, long i) +{ + atomic64_set(v, i); +} -typedef atomic_t atomic_long_t; +static inline void +atomic_long_set_release(atomic_long_t *v, long i) +{ + atomic64_set_release(v, i); +} -#define ATOMIC_LONG_INIT(i) ATOMIC_INIT(i) -#define ATOMIC_LONG_PFX(x) atomic ## x -#define ATOMIC_LONG_TYPE int +static inline void +atomic_long_add(long i, atomic_long_t *v) +{ + atomic64_add(i, v); +} -#endif +static inline long +atomic_long_add_return(long i, atomic_long_t *v) +{ + return atomic64_add_return(i, v); +} + +static inline long +atomic_long_add_return_acquire(long i, atomic_long_t *v) +{ + return atomic64_add_return_acquire(i, v); +} + +static inline long +atomic_long_add_return_release(long i, atomic_long_t *v) +{ + return atomic64_add_return_release(i, v); +} + +static inline long +atomic_long_add_return_relaxed(long i, atomic_long_t *v) +{ + return atomic64_add_return_relaxed(i, v); +} + +static inline long +atomic_long_fetch_add(long i, atomic_long_t *v) +{ + return atomic64_fetch_add(i, v); +} + +static inline long +atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_add_acquire(i, v); +} + +static inline long +atomic_long_fetch_add_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_add_release(i, v); +} + +static inline long +atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_add_relaxed(i, v); +} + +static inline void +atomic_long_sub(long i, atomic_long_t *v) +{ + atomic64_sub(i, v); +} + +static inline long +atomic_long_sub_return(long i, atomic_long_t *v) +{ + return atomic64_sub_return(i, v); +} + +static inline long +atomic_long_sub_return_acquire(long i, atomic_long_t *v) +{ + return atomic64_sub_return_acquire(i, v); +} + +static inline long +atomic_long_sub_return_release(long i, atomic_long_t *v) +{ + return atomic64_sub_return_release(i, v); +} + +static inline long +atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +{ + return atomic64_sub_return_relaxed(i, v); +} + +static inline long +atomic_long_fetch_sub(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub(i, v); +} + +static inline long +atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub_acquire(i, v); +} + +static inline long +atomic_long_fetch_sub_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub_release(i, v); +} + +static inline long +atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub_relaxed(i, v); +} + +static inline void +atomic_long_inc(atomic_long_t *v) +{ + atomic64_inc(v); +} + +static inline long +atomic_long_inc_return(atomic_long_t *v) +{ + return atomic64_inc_return(v); +} + +static inline long +atomic_long_inc_return_acquire(atomic_long_t *v) +{ + return atomic64_inc_return_acquire(v); +} + +static inline long +atomic_long_inc_return_release(atomic_long_t *v) +{ + return atomic64_inc_return_release(v); +} + +static inline long +atomic_long_inc_return_relaxed(atomic_long_t *v) +{ + return atomic64_inc_return_relaxed(v); +} + +static inline long +atomic_long_fetch_inc(atomic_long_t *v) +{ + return atomic64_fetch_inc(v); +} + +static inline long +atomic_long_fetch_inc_acquire(atomic_long_t *v) +{ + return atomic64_fetch_inc_acquire(v); +} + +static inline long +atomic_long_fetch_inc_release(atomic_long_t *v) +{ + return atomic64_fetch_inc_release(v); +} + +static inline long +atomic_long_fetch_inc_relaxed(atomic_long_t *v) +{ + return atomic64_fetch_inc_relaxed(v); +} + +static inline void +atomic_long_dec(atomic_long_t *v) +{ + atomic64_dec(v); +} + +static inline long +atomic_long_dec_return(atomic_long_t *v) +{ + return atomic64_dec_return(v); +} + +static inline long +atomic_long_dec_return_acquire(atomic_long_t *v) +{ + return atomic64_dec_return_acquire(v); +} + +static inline long +atomic_long_dec_return_release(atomic_long_t *v) +{ + return atomic64_dec_return_release(v); +} + +static inline long +atomic_long_dec_return_relaxed(atomic_long_t *v) +{ + return atomic64_dec_return_relaxed(v); +} + +static inline long +atomic_long_fetch_dec(atomic_long_t *v) +{ + return atomic64_fetch_dec(v); +} + +static inline long +atomic_long_fetch_dec_acquire(atomic_long_t *v) +{ + return atomic64_fetch_dec_acquire(v); +} + +static inline long +atomic_long_fetch_dec_release(atomic_long_t *v) +{ + return atomic64_fetch_dec_release(v); +} + +static inline long +atomic_long_fetch_dec_relaxed(atomic_long_t *v) +{ + return atomic64_fetch_dec_relaxed(v); +} + +static inline void +atomic_long_and(long i, atomic_long_t *v) +{ + atomic64_and(i, v); +} + +static inline long +atomic_long_fetch_and(long i, atomic_long_t *v) +{ + return atomic64_fetch_and(i, v); +} + +static inline long +atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_and_acquire(i, v); +} + +static inline long +atomic_long_fetch_and_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_and_release(i, v); +} + +static inline long +atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_and_relaxed(i, v); +} + +static inline void +atomic_long_andnot(long i, atomic_long_t *v) +{ + atomic64_andnot(i, v); +} + +static inline long +atomic_long_fetch_andnot(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot(i, v); +} + +static inline long +atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot_acquire(i, v); +} + +static inline long +atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot_release(i, v); +} + +static inline long +atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot_relaxed(i, v); +} + +static inline void +atomic_long_or(long i, atomic_long_t *v) +{ + atomic64_or(i, v); +} + +static inline long +atomic_long_fetch_or(long i, atomic_long_t *v) +{ + return atomic64_fetch_or(i, v); +} + +static inline long +atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_or_acquire(i, v); +} + +static inline long +atomic_long_fetch_or_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_or_release(i, v); +} + +static inline long +atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_or_relaxed(i, v); +} + +static inline void +atomic_long_xor(long i, atomic_long_t *v) +{ + atomic64_xor(i, v); +} + +static inline long +atomic_long_fetch_xor(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor(i, v); +} + +static inline long +atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor_acquire(i, v); +} + +static inline long +atomic_long_fetch_xor_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor_release(i, v); +} + +static inline long +atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor_relaxed(i, v); +} + +static inline long +atomic_long_xchg(atomic_long_t *v, long i) +{ + return atomic64_xchg(v, i); +} + +static inline long +atomic_long_xchg_acquire(atomic_long_t *v, long i) +{ + return atomic64_xchg_acquire(v, i); +} + +static inline long +atomic_long_xchg_release(atomic_long_t *v, long i) +{ + return atomic64_xchg_release(v, i); +} + +static inline long +atomic_long_xchg_relaxed(atomic_long_t *v, long i) +{ + return atomic64_xchg_relaxed(v, i); +} + +static inline long +atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg(v, old, new); +} + +static inline long +atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg_acquire(v, old, new); +} + +static inline long +atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg_release(v, old, new); +} + +static inline long +atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg_relaxed(v, old, new); +} + +static inline bool +atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg(v, (s64 *)old, new); +} + +static inline bool +atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); +} + +static inline bool +atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg_release(v, (s64 *)old, new); +} + +static inline bool +atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); +} + +static inline bool +atomic_long_sub_and_test(long i, atomic_long_t *v) +{ + return atomic64_sub_and_test(i, v); +} + +static inline bool +atomic_long_dec_and_test(atomic_long_t *v) +{ + return atomic64_dec_and_test(v); +} + +static inline bool +atomic_long_inc_and_test(atomic_long_t *v) +{ + return atomic64_inc_and_test(v); +} + +static inline bool +atomic_long_add_negative(long i, atomic_long_t *v) +{ + return atomic64_add_negative(i, v); +} + +static inline long +atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic64_fetch_add_unless(v, a, u); +} + +static inline bool +atomic_long_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic64_add_unless(v, a, u); +} + +static inline bool +atomic_long_inc_not_zero(atomic_long_t *v) +{ + return atomic64_inc_not_zero(v); +} + +static inline bool +atomic_long_inc_unless_negative(atomic_long_t *v) +{ + return atomic64_inc_unless_negative(v); +} + +static inline bool +atomic_long_dec_unless_positive(atomic_long_t *v) +{ + return atomic64_dec_unless_positive(v); +} + +static inline long +atomic_long_dec_if_positive(atomic_long_t *v) +{ + return atomic64_dec_if_positive(v); +} + +#else /* CONFIG_64BIT */ + +static inline long +atomic_long_read(const atomic_long_t *v) +{ + return atomic_read(v); +} + +static inline long +atomic_long_read_acquire(const atomic_long_t *v) +{ + return atomic_read_acquire(v); +} + +static inline void +atomic_long_set(atomic_long_t *v, long i) +{ + atomic_set(v, i); +} + +static inline void +atomic_long_set_release(atomic_long_t *v, long i) +{ + atomic_set_release(v, i); +} + +static inline void +atomic_long_add(long i, atomic_long_t *v) +{ + atomic_add(i, v); +} + +static inline long +atomic_long_add_return(long i, atomic_long_t *v) +{ + return atomic_add_return(i, v); +} + +static inline long +atomic_long_add_return_acquire(long i, atomic_long_t *v) +{ + return atomic_add_return_acquire(i, v); +} + +static inline long +atomic_long_add_return_release(long i, atomic_long_t *v) +{ + return atomic_add_return_release(i, v); +} + +static inline long +atomic_long_add_return_relaxed(long i, atomic_long_t *v) +{ + return atomic_add_return_relaxed(i, v); +} + +static inline long +atomic_long_fetch_add(long i, atomic_long_t *v) +{ + return atomic_fetch_add(i, v); +} + +static inline long +atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_add_acquire(i, v); +} + +static inline long +atomic_long_fetch_add_release(long i, atomic_long_t *v) +{ + return atomic_fetch_add_release(i, v); +} + +static inline long +atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_add_relaxed(i, v); +} + +static inline void +atomic_long_sub(long i, atomic_long_t *v) +{ + atomic_sub(i, v); +} + +static inline long +atomic_long_sub_return(long i, atomic_long_t *v) +{ + return atomic_sub_return(i, v); +} + +static inline long +atomic_long_sub_return_acquire(long i, atomic_long_t *v) +{ + return atomic_sub_return_acquire(i, v); +} + +static inline long +atomic_long_sub_return_release(long i, atomic_long_t *v) +{ + return atomic_sub_return_release(i, v); +} + +static inline long +atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +{ + return atomic_sub_return_relaxed(i, v); +} + +static inline long +atomic_long_fetch_sub(long i, atomic_long_t *v) +{ + return atomic_fetch_sub(i, v); +} + +static inline long +atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_sub_acquire(i, v); +} + +static inline long +atomic_long_fetch_sub_release(long i, atomic_long_t *v) +{ + return atomic_fetch_sub_release(i, v); +} + +static inline long +atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_sub_relaxed(i, v); +} + +static inline void +atomic_long_inc(atomic_long_t *v) +{ + atomic_inc(v); +} + +static inline long +atomic_long_inc_return(atomic_long_t *v) +{ + return atomic_inc_return(v); +} + +static inline long +atomic_long_inc_return_acquire(atomic_long_t *v) +{ + return atomic_inc_return_acquire(v); +} + +static inline long +atomic_long_inc_return_release(atomic_long_t *v) +{ + return atomic_inc_return_release(v); +} + +static inline long +atomic_long_inc_return_relaxed(atomic_long_t *v) +{ + return atomic_inc_return_relaxed(v); +} + +static inline long +atomic_long_fetch_inc(atomic_long_t *v) +{ + return atomic_fetch_inc(v); +} + +static inline long +atomic_long_fetch_inc_acquire(atomic_long_t *v) +{ + return atomic_fetch_inc_acquire(v); +} + +static inline long +atomic_long_fetch_inc_release(atomic_long_t *v) +{ + return atomic_fetch_inc_release(v); +} + +static inline long +atomic_long_fetch_inc_relaxed(atomic_long_t *v) +{ + return atomic_fetch_inc_relaxed(v); +} + +static inline void +atomic_long_dec(atomic_long_t *v) +{ + atomic_dec(v); +} + +static inline long +atomic_long_dec_return(atomic_long_t *v) +{ + return atomic_dec_return(v); +} + +static inline long +atomic_long_dec_return_acquire(atomic_long_t *v) +{ + return atomic_dec_return_acquire(v); +} + +static inline long +atomic_long_dec_return_release(atomic_long_t *v) +{ + return atomic_dec_return_release(v); +} + +static inline long +atomic_long_dec_return_relaxed(atomic_long_t *v) +{ + return atomic_dec_return_relaxed(v); +} + +static inline long +atomic_long_fetch_dec(atomic_long_t *v) +{ + return atomic_fetch_dec(v); +} + +static inline long +atomic_long_fetch_dec_acquire(atomic_long_t *v) +{ + return atomic_fetch_dec_acquire(v); +} + +static inline long +atomic_long_fetch_dec_release(atomic_long_t *v) +{ + return atomic_fetch_dec_release(v); +} + +static inline long +atomic_long_fetch_dec_relaxed(atomic_long_t *v) +{ + return atomic_fetch_dec_relaxed(v); +} + +static inline void +atomic_long_and(long i, atomic_long_t *v) +{ + atomic_and(i, v); +} + +static inline long +atomic_long_fetch_and(long i, atomic_long_t *v) +{ + return atomic_fetch_and(i, v); +} + +static inline long +atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_and_acquire(i, v); +} + +static inline long +atomic_long_fetch_and_release(long i, atomic_long_t *v) +{ + return atomic_fetch_and_release(i, v); +} + +static inline long +atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_and_relaxed(i, v); +} + +static inline void +atomic_long_andnot(long i, atomic_long_t *v) +{ + atomic_andnot(i, v); +} + +static inline long +atomic_long_fetch_andnot(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot(i, v); +} + +static inline long +atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot_acquire(i, v); +} + +static inline long +atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot_release(i, v); +} + +static inline long +atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot_relaxed(i, v); +} -#define ATOMIC_LONG_READ_OP(mo) \ -static inline long atomic_long_read##mo(const atomic_long_t *l) \ -{ \ - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; \ - \ - return (long)ATOMIC_LONG_PFX(_read##mo)(v); \ -} -ATOMIC_LONG_READ_OP() -ATOMIC_LONG_READ_OP(_acquire) - -#undef ATOMIC_LONG_READ_OP - -#define ATOMIC_LONG_SET_OP(mo) \ -static inline void atomic_long_set##mo(atomic_long_t *l, long i) \ -{ \ - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; \ - \ - ATOMIC_LONG_PFX(_set##mo)(v, i); \ -} -ATOMIC_LONG_SET_OP() -ATOMIC_LONG_SET_OP(_release) - -#undef ATOMIC_LONG_SET_OP - -#define ATOMIC_LONG_ADD_SUB_OP(op, mo) \ -static inline long \ -atomic_long_##op##_return##mo(long i, atomic_long_t *l) \ -{ \ - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; \ - \ - return (long)ATOMIC_LONG_PFX(_##op##_return##mo)(i, v); \ -} -ATOMIC_LONG_ADD_SUB_OP(add,) -ATOMIC_LONG_ADD_SUB_OP(add, _relaxed) -ATOMIC_LONG_ADD_SUB_OP(add, _acquire) -ATOMIC_LONG_ADD_SUB_OP(add, _release) -ATOMIC_LONG_ADD_SUB_OP(sub,) -ATOMIC_LONG_ADD_SUB_OP(sub, _relaxed) -ATOMIC_LONG_ADD_SUB_OP(sub, _acquire) -ATOMIC_LONG_ADD_SUB_OP(sub, _release) - -#undef ATOMIC_LONG_ADD_SUB_OP - -#define atomic_long_cmpxchg_relaxed(l, old, new) \ - (ATOMIC_LONG_PFX(_cmpxchg_relaxed)((ATOMIC_LONG_PFX(_t) *)(l), \ - (old), (new))) -#define atomic_long_cmpxchg_acquire(l, old, new) \ - (ATOMIC_LONG_PFX(_cmpxchg_acquire)((ATOMIC_LONG_PFX(_t) *)(l), \ - (old), (new))) -#define atomic_long_cmpxchg_release(l, old, new) \ - (ATOMIC_LONG_PFX(_cmpxchg_release)((ATOMIC_LONG_PFX(_t) *)(l), \ - (old), (new))) -#define atomic_long_cmpxchg(l, old, new) \ - (ATOMIC_LONG_PFX(_cmpxchg)((ATOMIC_LONG_PFX(_t) *)(l), (old), (new))) - - -#define atomic_long_try_cmpxchg_relaxed(l, old, new) \ - (ATOMIC_LONG_PFX(_try_cmpxchg_relaxed)((ATOMIC_LONG_PFX(_t) *)(l), \ - (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new))) -#define atomic_long_try_cmpxchg_acquire(l, old, new) \ - (ATOMIC_LONG_PFX(_try_cmpxchg_acquire)((ATOMIC_LONG_PFX(_t) *)(l), \ - (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new))) -#define atomic_long_try_cmpxchg_release(l, old, new) \ - (ATOMIC_LONG_PFX(_try_cmpxchg_release)((ATOMIC_LONG_PFX(_t) *)(l), \ - (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new))) -#define atomic_long_try_cmpxchg(l, old, new) \ - (ATOMIC_LONG_PFX(_try_cmpxchg)((ATOMIC_LONG_PFX(_t) *)(l), \ - (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new))) - - -#define atomic_long_xchg_relaxed(v, new) \ - (ATOMIC_LONG_PFX(_xchg_relaxed)((ATOMIC_LONG_PFX(_t) *)(v), (new))) -#define atomic_long_xchg_acquire(v, new) \ - (ATOMIC_LONG_PFX(_xchg_acquire)((ATOMIC_LONG_PFX(_t) *)(v), (new))) -#define atomic_long_xchg_release(v, new) \ - (ATOMIC_LONG_PFX(_xchg_release)((ATOMIC_LONG_PFX(_t) *)(v), (new))) -#define atomic_long_xchg(v, new) \ - (ATOMIC_LONG_PFX(_xchg)((ATOMIC_LONG_PFX(_t) *)(v), (new))) - -static __always_inline void atomic_long_inc(atomic_long_t *l) -{ - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; - - ATOMIC_LONG_PFX(_inc)(v); -} - -static __always_inline void atomic_long_dec(atomic_long_t *l) +static inline void +atomic_long_or(long i, atomic_long_t *v) { - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; + atomic_or(i, v); +} - ATOMIC_LONG_PFX(_dec)(v); +static inline long +atomic_long_fetch_or(long i, atomic_long_t *v) +{ + return atomic_fetch_or(i, v); } -#define ATOMIC_LONG_FETCH_OP(op, mo) \ -static inline long \ -atomic_long_fetch_##op##mo(long i, atomic_long_t *l) \ -{ \ - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; \ - \ - return (long)ATOMIC_LONG_PFX(_fetch_##op##mo)(i, v); \ +static inline long +atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_or_acquire(i, v); } -ATOMIC_LONG_FETCH_OP(add, ) -ATOMIC_LONG_FETCH_OP(add, _relaxed) -ATOMIC_LONG_FETCH_OP(add, _acquire) -ATOMIC_LONG_FETCH_OP(add, _release) -ATOMIC_LONG_FETCH_OP(sub, ) -ATOMIC_LONG_FETCH_OP(sub, _relaxed) -ATOMIC_LONG_FETCH_OP(sub, _acquire) -ATOMIC_LONG_FETCH_OP(sub, _release) -ATOMIC_LONG_FETCH_OP(and, ) -ATOMIC_LONG_FETCH_OP(and, _relaxed) -ATOMIC_LONG_FETCH_OP(and, _acquire) -ATOMIC_LONG_FETCH_OP(and, _release) -ATOMIC_LONG_FETCH_OP(andnot, ) -ATOMIC_LONG_FETCH_OP(andnot, _relaxed) -ATOMIC_LONG_FETCH_OP(andnot, _acquire) -ATOMIC_LONG_FETCH_OP(andnot, _release) -ATOMIC_LONG_FETCH_OP(or, ) -ATOMIC_LONG_FETCH_OP(or, _relaxed) -ATOMIC_LONG_FETCH_OP(or, _acquire) -ATOMIC_LONG_FETCH_OP(or, _release) -ATOMIC_LONG_FETCH_OP(xor, ) -ATOMIC_LONG_FETCH_OP(xor, _relaxed) -ATOMIC_LONG_FETCH_OP(xor, _acquire) -ATOMIC_LONG_FETCH_OP(xor, _release) +static inline long +atomic_long_fetch_or_release(long i, atomic_long_t *v) +{ + return atomic_fetch_or_release(i, v); +} -#undef ATOMIC_LONG_FETCH_OP +static inline long +atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_or_relaxed(i, v); +} -#define ATOMIC_LONG_FETCH_INC_DEC_OP(op, mo) \ -static inline long \ -atomic_long_fetch_##op##mo(atomic_long_t *l) \ -{ \ - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; \ - \ - return (long)ATOMIC_LONG_PFX(_fetch_##op##mo)(v); \ +static inline void +atomic_long_xor(long i, atomic_long_t *v) +{ + atomic_xor(i, v); } -ATOMIC_LONG_FETCH_INC_DEC_OP(inc,) -ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _relaxed) -ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _acquire) -ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _release) -ATOMIC_LONG_FETCH_INC_DEC_OP(dec,) -ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _relaxed) -ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _acquire) -ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _release) +static inline long +atomic_long_fetch_xor(long i, atomic_long_t *v) +{ + return atomic_fetch_xor(i, v); +} -#undef ATOMIC_LONG_FETCH_INC_DEC_OP +static inline long +atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_xor_acquire(i, v); +} -#define ATOMIC_LONG_OP(op) \ -static __always_inline void \ -atomic_long_##op(long i, atomic_long_t *l) \ -{ \ - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; \ - \ - ATOMIC_LONG_PFX(_##op)(i, v); \ +static inline long +atomic_long_fetch_xor_release(long i, atomic_long_t *v) +{ + return atomic_fetch_xor_release(i, v); } -ATOMIC_LONG_OP(add) -ATOMIC_LONG_OP(sub) -ATOMIC_LONG_OP(and) -ATOMIC_LONG_OP(andnot) -ATOMIC_LONG_OP(or) -ATOMIC_LONG_OP(xor) +static inline long +atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_xor_relaxed(i, v); +} -#undef ATOMIC_LONG_OP +static inline long +atomic_long_xchg(atomic_long_t *v, long i) +{ + return atomic_xchg(v, i); +} -static inline int atomic_long_sub_and_test(long i, atomic_long_t *l) +static inline long +atomic_long_xchg_acquire(atomic_long_t *v, long i) { - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; + return atomic_xchg_acquire(v, i); +} - return ATOMIC_LONG_PFX(_sub_and_test)(i, v); +static inline long +atomic_long_xchg_release(atomic_long_t *v, long i) +{ + return atomic_xchg_release(v, i); } -static inline int atomic_long_dec_and_test(atomic_long_t *l) +static inline long +atomic_long_xchg_relaxed(atomic_long_t *v, long i) { - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; + return atomic_xchg_relaxed(v, i); +} - return ATOMIC_LONG_PFX(_dec_and_test)(v); +static inline long +atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg(v, old, new); } -static inline int atomic_long_inc_and_test(atomic_long_t *l) +static inline long +atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; + return atomic_cmpxchg_acquire(v, old, new); +} - return ATOMIC_LONG_PFX(_inc_and_test)(v); +static inline long +atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg_release(v, old, new); } -static inline int atomic_long_add_negative(long i, atomic_long_t *l) +static inline long +atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; + return atomic_cmpxchg_relaxed(v, old, new); +} - return ATOMIC_LONG_PFX(_add_negative)(i, v); +static inline bool +atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg(v, (int *)old, new); } -#define ATOMIC_LONG_INC_DEC_OP(op, mo) \ -static inline long \ -atomic_long_##op##_return##mo(atomic_long_t *l) \ -{ \ - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; \ - \ - return (long)ATOMIC_LONG_PFX(_##op##_return##mo)(v); \ +static inline bool +atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg_acquire(v, (int *)old, new); } -ATOMIC_LONG_INC_DEC_OP(inc,) -ATOMIC_LONG_INC_DEC_OP(inc, _relaxed) -ATOMIC_LONG_INC_DEC_OP(inc, _acquire) -ATOMIC_LONG_INC_DEC_OP(inc, _release) -ATOMIC_LONG_INC_DEC_OP(dec,) -ATOMIC_LONG_INC_DEC_OP(dec, _relaxed) -ATOMIC_LONG_INC_DEC_OP(dec, _acquire) -ATOMIC_LONG_INC_DEC_OP(dec, _release) -#undef ATOMIC_LONG_INC_DEC_OP +static inline bool +atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg_release(v, (int *)old, new); +} + +static inline bool +atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg_relaxed(v, (int *)old, new); +} + +static inline bool +atomic_long_sub_and_test(long i, atomic_long_t *v) +{ + return atomic_sub_and_test(i, v); +} + +static inline bool +atomic_long_dec_and_test(atomic_long_t *v) +{ + return atomic_dec_and_test(v); +} + +static inline bool +atomic_long_inc_and_test(atomic_long_t *v) +{ + return atomic_inc_and_test(v); +} + +static inline bool +atomic_long_add_negative(long i, atomic_long_t *v) +{ + return atomic_add_negative(i, v); +} + +static inline long +atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic_fetch_add_unless(v, a, u); +} + +static inline bool +atomic_long_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic_add_unless(v, a, u); +} -static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u) +static inline bool +atomic_long_inc_not_zero(atomic_long_t *v) { - ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; + return atomic_inc_not_zero(v); +} - return (long)ATOMIC_LONG_PFX(_add_unless)(v, a, u); +static inline bool +atomic_long_inc_unless_negative(atomic_long_t *v) +{ + return atomic_inc_unless_negative(v); } -#define atomic_long_inc_not_zero(l) \ - ATOMIC_LONG_PFX(_inc_not_zero)((ATOMIC_LONG_PFX(_t) *)(l)) +static inline bool +atomic_long_dec_unless_positive(atomic_long_t *v) +{ + return atomic_dec_unless_positive(v); +} -#define atomic_long_cond_read_relaxed(v, c) \ - ATOMIC_LONG_PFX(_cond_read_relaxed)((ATOMIC_LONG_PFX(_t) *)(v), (c)) -#define atomic_long_cond_read_acquire(v, c) \ - ATOMIC_LONG_PFX(_cond_read_acquire)((ATOMIC_LONG_PFX(_t) *)(v), (c)) +static inline long +atomic_long_dec_if_positive(atomic_long_t *v) +{ + return atomic_dec_if_positive(v); +} -#endif /* _ASM_GENERIC_ATOMIC_LONG_H */ +#endif /* CONFIG_64BIT */ +#endif /* _ASM_GENERIC_ATOMIC_LONG_H */ -- cgit v1.2.3 From aa525d063851a98e020b827fdd1d7776ae652301 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 4 Sep 2018 11:48:28 +0100 Subject: locking/atomics: Switch to generated instrumentation As a step towards ensuring the atomic* APIs are consistent, let's switch to wrappers generated by gen-atomic-instrumented.h, using the same table used to generate the fallbacks and atomic-long wrappers. These are checked in rather than generated with Kbuild, since: * This allows inspection of the atomics with git grep and ctags on a pristine tree, which Linus strongly prefers being able to do. * The fallbacks are not affected by machine details or configuration options, so it is not necessary to regenerate them to take these into account. * These are included by files required *very* early in the build process (e.g. for generating bounds.h), and we'd rather not complicate the top-level Kbuild file with dependencies. Generating the atomic headers means that the instrumented wrappers will remain in sync with the rest of the atomic APIs, and we gain all the ordering variants of each atomic without having to manually expanded them all. The KASAN checks are automatically generated based on the function parameters defined in atomics.tbl. Note that try_cmpxchg() now correctly treats 'old' as a parameter that may be written to, and not only read as the hand-written instrumentation assumed. Other than the change to try_cmpxchg(), existing code should not be affected by this patch. The patch introduces instrumentation for all optional atomics (and ordering variants), along with the ifdeffery this requires, enabling other architectures to make use of the instrumented atomics. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: catalin.marinas@arm.com Cc: linuxdrivers@attotech.com Cc: Dmitry Vyukov Cc: Boqun Feng Cc: Arnd Bergmann Cc: Andrey Ryabinin Cc: Alexander Potapenko Link: http://lkml.kernel.org/r/20180904104830.2975-5-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/atomic-instrumented.h | 1688 +++++++++++++++++++++++++---- 1 file changed, 1504 insertions(+), 184 deletions(-) (limited to 'include') diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 0d4b1d3dbc1e..b8f5b35216e1 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -1,3 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-instrumented.sh +// DO NOT MODIFY THIS FILE DIRECTLY + /* * This file provides wrappers with KASAN instrumentation for atomic operations. * To use this functionality an arch's atomic.h file needs to define all @@ -9,459 +14,1774 @@ * arch_ variants (i.e. arch_atomic_read()/arch_atomic_cmpxchg()) to avoid * double instrumentation. */ +#ifndef _ASM_GENERIC_ATOMIC_INSTRUMENTED_H +#define _ASM_GENERIC_ATOMIC_INSTRUMENTED_H + +#include +#include + +static inline int +atomic_read(const atomic_t *v) +{ + kasan_check_read(v, sizeof(*v)); + return arch_atomic_read(v); +} +#define atomic_read atomic_read + +#if defined(arch_atomic_read_acquire) +static inline int +atomic_read_acquire(const atomic_t *v) +{ + kasan_check_read(v, sizeof(*v)); + return arch_atomic_read_acquire(v); +} +#define atomic_read_acquire atomic_read_acquire +#endif + +static inline void +atomic_set(atomic_t *v, int i) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_set(v, i); +} +#define atomic_set atomic_set + +#if defined(arch_atomic_set_release) +static inline void +atomic_set_release(atomic_t *v, int i) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_set_release(v, i); +} +#define atomic_set_release atomic_set_release +#endif + +static inline void +atomic_add(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_add(i, v); +} +#define atomic_add atomic_add + +#if !defined(arch_atomic_add_return_relaxed) || defined(arch_atomic_add_return) +static inline int +atomic_add_return(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_add_return(i, v); +} +#define atomic_add_return atomic_add_return +#endif + +#if defined(arch_atomic_add_return_acquire) +static inline int +atomic_add_return_acquire(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_add_return_acquire(i, v); +} +#define atomic_add_return_acquire atomic_add_return_acquire +#endif + +#if defined(arch_atomic_add_return_release) +static inline int +atomic_add_return_release(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_add_return_release(i, v); +} +#define atomic_add_return_release atomic_add_return_release +#endif + +#if defined(arch_atomic_add_return_relaxed) +static inline int +atomic_add_return_relaxed(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_add_return_relaxed(i, v); +} +#define atomic_add_return_relaxed atomic_add_return_relaxed +#endif + +#if !defined(arch_atomic_fetch_add_relaxed) || defined(arch_atomic_fetch_add) +static inline int +atomic_fetch_add(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_add(i, v); +} +#define atomic_fetch_add atomic_fetch_add +#endif + +#if defined(arch_atomic_fetch_add_acquire) +static inline int +atomic_fetch_add_acquire(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_add_acquire(i, v); +} +#define atomic_fetch_add_acquire atomic_fetch_add_acquire +#endif + +#if defined(arch_atomic_fetch_add_release) +static inline int +atomic_fetch_add_release(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_add_release(i, v); +} +#define atomic_fetch_add_release atomic_fetch_add_release +#endif + +#if defined(arch_atomic_fetch_add_relaxed) +static inline int +atomic_fetch_add_relaxed(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_add_relaxed(i, v); +} +#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed +#endif + +static inline void +atomic_sub(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_sub(i, v); +} +#define atomic_sub atomic_sub + +#if !defined(arch_atomic_sub_return_relaxed) || defined(arch_atomic_sub_return) +static inline int +atomic_sub_return(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_sub_return(i, v); +} +#define atomic_sub_return atomic_sub_return +#endif + +#if defined(arch_atomic_sub_return_acquire) +static inline int +atomic_sub_return_acquire(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_sub_return_acquire(i, v); +} +#define atomic_sub_return_acquire atomic_sub_return_acquire +#endif + +#if defined(arch_atomic_sub_return_release) +static inline int +atomic_sub_return_release(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_sub_return_release(i, v); +} +#define atomic_sub_return_release atomic_sub_return_release +#endif + +#if defined(arch_atomic_sub_return_relaxed) +static inline int +atomic_sub_return_relaxed(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_sub_return_relaxed(i, v); +} +#define atomic_sub_return_relaxed atomic_sub_return_relaxed +#endif + +#if !defined(arch_atomic_fetch_sub_relaxed) || defined(arch_atomic_fetch_sub) +static inline int +atomic_fetch_sub(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_sub(i, v); +} +#define atomic_fetch_sub atomic_fetch_sub +#endif + +#if defined(arch_atomic_fetch_sub_acquire) +static inline int +atomic_fetch_sub_acquire(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_sub_acquire(i, v); +} +#define atomic_fetch_sub_acquire atomic_fetch_sub_acquire +#endif + +#if defined(arch_atomic_fetch_sub_release) +static inline int +atomic_fetch_sub_release(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_sub_release(i, v); +} +#define atomic_fetch_sub_release atomic_fetch_sub_release +#endif + +#if defined(arch_atomic_fetch_sub_relaxed) +static inline int +atomic_fetch_sub_relaxed(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_sub_relaxed(i, v); +} +#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed +#endif + +#if defined(arch_atomic_inc) +static inline void +atomic_inc(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_inc(v); +} +#define atomic_inc atomic_inc +#endif + +#if defined(arch_atomic_inc_return) +static inline int +atomic_inc_return(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_inc_return(v); +} +#define atomic_inc_return atomic_inc_return +#endif + +#if defined(arch_atomic_inc_return_acquire) +static inline int +atomic_inc_return_acquire(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_inc_return_acquire(v); +} +#define atomic_inc_return_acquire atomic_inc_return_acquire +#endif + +#if defined(arch_atomic_inc_return_release) +static inline int +atomic_inc_return_release(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_inc_return_release(v); +} +#define atomic_inc_return_release atomic_inc_return_release +#endif + +#if defined(arch_atomic_inc_return_relaxed) +static inline int +atomic_inc_return_relaxed(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_inc_return_relaxed(v); +} +#define atomic_inc_return_relaxed atomic_inc_return_relaxed +#endif + +#if defined(arch_atomic_fetch_inc) +static inline int +atomic_fetch_inc(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_inc(v); +} +#define atomic_fetch_inc atomic_fetch_inc +#endif + +#if defined(arch_atomic_fetch_inc_acquire) +static inline int +atomic_fetch_inc_acquire(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_inc_acquire(v); +} +#define atomic_fetch_inc_acquire atomic_fetch_inc_acquire +#endif + +#if defined(arch_atomic_fetch_inc_release) +static inline int +atomic_fetch_inc_release(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_inc_release(v); +} +#define atomic_fetch_inc_release atomic_fetch_inc_release +#endif + +#if defined(arch_atomic_fetch_inc_relaxed) +static inline int +atomic_fetch_inc_relaxed(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_inc_relaxed(v); +} +#define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed +#endif + +#if defined(arch_atomic_dec) +static inline void +atomic_dec(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_dec(v); +} +#define atomic_dec atomic_dec +#endif + +#if defined(arch_atomic_dec_return) +static inline int +atomic_dec_return(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_dec_return(v); +} +#define atomic_dec_return atomic_dec_return +#endif + +#if defined(arch_atomic_dec_return_acquire) +static inline int +atomic_dec_return_acquire(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_dec_return_acquire(v); +} +#define atomic_dec_return_acquire atomic_dec_return_acquire +#endif + +#if defined(arch_atomic_dec_return_release) +static inline int +atomic_dec_return_release(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_dec_return_release(v); +} +#define atomic_dec_return_release atomic_dec_return_release +#endif + +#if defined(arch_atomic_dec_return_relaxed) +static inline int +atomic_dec_return_relaxed(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_dec_return_relaxed(v); +} +#define atomic_dec_return_relaxed atomic_dec_return_relaxed +#endif + +#if defined(arch_atomic_fetch_dec) +static inline int +atomic_fetch_dec(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_dec(v); +} +#define atomic_fetch_dec atomic_fetch_dec +#endif + +#if defined(arch_atomic_fetch_dec_acquire) +static inline int +atomic_fetch_dec_acquire(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_dec_acquire(v); +} +#define atomic_fetch_dec_acquire atomic_fetch_dec_acquire +#endif + +#if defined(arch_atomic_fetch_dec_release) +static inline int +atomic_fetch_dec_release(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_dec_release(v); +} +#define atomic_fetch_dec_release atomic_fetch_dec_release +#endif + +#if defined(arch_atomic_fetch_dec_relaxed) +static inline int +atomic_fetch_dec_relaxed(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_dec_relaxed(v); +} +#define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed +#endif + +static inline void +atomic_and(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_and(i, v); +} +#define atomic_and atomic_and + +#if !defined(arch_atomic_fetch_and_relaxed) || defined(arch_atomic_fetch_and) +static inline int +atomic_fetch_and(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_and(i, v); +} +#define atomic_fetch_and atomic_fetch_and +#endif + +#if defined(arch_atomic_fetch_and_acquire) +static inline int +atomic_fetch_and_acquire(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_and_acquire(i, v); +} +#define atomic_fetch_and_acquire atomic_fetch_and_acquire +#endif + +#if defined(arch_atomic_fetch_and_release) +static inline int +atomic_fetch_and_release(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_and_release(i, v); +} +#define atomic_fetch_and_release atomic_fetch_and_release +#endif + +#if defined(arch_atomic_fetch_and_relaxed) +static inline int +atomic_fetch_and_relaxed(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_and_relaxed(i, v); +} +#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed +#endif + +#if defined(arch_atomic_andnot) +static inline void +atomic_andnot(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_andnot(i, v); +} +#define atomic_andnot atomic_andnot +#endif + +#if defined(arch_atomic_fetch_andnot) +static inline int +atomic_fetch_andnot(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot(i, v); +} +#define atomic_fetch_andnot atomic_fetch_andnot +#endif + +#if defined(arch_atomic_fetch_andnot_acquire) +static inline int +atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot_acquire(i, v); +} +#define atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire +#endif + +#if defined(arch_atomic_fetch_andnot_release) +static inline int +atomic_fetch_andnot_release(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot_release(i, v); +} +#define atomic_fetch_andnot_release atomic_fetch_andnot_release +#endif + +#if defined(arch_atomic_fetch_andnot_relaxed) +static inline int +atomic_fetch_andnot_relaxed(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot_relaxed(i, v); +} +#define atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed +#endif + +static inline void +atomic_or(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_or(i, v); +} +#define atomic_or atomic_or + +#if !defined(arch_atomic_fetch_or_relaxed) || defined(arch_atomic_fetch_or) +static inline int +atomic_fetch_or(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_or(i, v); +} +#define atomic_fetch_or atomic_fetch_or +#endif + +#if defined(arch_atomic_fetch_or_acquire) +static inline int +atomic_fetch_or_acquire(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_or_acquire(i, v); +} +#define atomic_fetch_or_acquire atomic_fetch_or_acquire +#endif + +#if defined(arch_atomic_fetch_or_release) +static inline int +atomic_fetch_or_release(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_or_release(i, v); +} +#define atomic_fetch_or_release atomic_fetch_or_release +#endif + +#if defined(arch_atomic_fetch_or_relaxed) +static inline int +atomic_fetch_or_relaxed(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_or_relaxed(i, v); +} +#define atomic_fetch_or_relaxed atomic_fetch_or_relaxed +#endif + +static inline void +atomic_xor(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic_xor(i, v); +} +#define atomic_xor atomic_xor + +#if !defined(arch_atomic_fetch_xor_relaxed) || defined(arch_atomic_fetch_xor) +static inline int +atomic_fetch_xor(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_xor(i, v); +} +#define atomic_fetch_xor atomic_fetch_xor +#endif + +#if defined(arch_atomic_fetch_xor_acquire) +static inline int +atomic_fetch_xor_acquire(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_xor_acquire(i, v); +} +#define atomic_fetch_xor_acquire atomic_fetch_xor_acquire +#endif + +#if defined(arch_atomic_fetch_xor_release) +static inline int +atomic_fetch_xor_release(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_xor_release(i, v); +} +#define atomic_fetch_xor_release atomic_fetch_xor_release +#endif + +#if defined(arch_atomic_fetch_xor_relaxed) +static inline int +atomic_fetch_xor_relaxed(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_xor_relaxed(i, v); +} +#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed +#endif + +#if !defined(arch_atomic_xchg_relaxed) || defined(arch_atomic_xchg) +static inline int +atomic_xchg(atomic_t *v, int i) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_xchg(v, i); +} +#define atomic_xchg atomic_xchg +#endif + +#if defined(arch_atomic_xchg_acquire) +static inline int +atomic_xchg_acquire(atomic_t *v, int i) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_xchg_acquire(v, i); +} +#define atomic_xchg_acquire atomic_xchg_acquire +#endif + +#if defined(arch_atomic_xchg_release) +static inline int +atomic_xchg_release(atomic_t *v, int i) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_xchg_release(v, i); +} +#define atomic_xchg_release atomic_xchg_release +#endif + +#if defined(arch_atomic_xchg_relaxed) +static inline int +atomic_xchg_relaxed(atomic_t *v, int i) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_xchg_relaxed(v, i); +} +#define atomic_xchg_relaxed atomic_xchg_relaxed +#endif + +#if !defined(arch_atomic_cmpxchg_relaxed) || defined(arch_atomic_cmpxchg) +static inline int +atomic_cmpxchg(atomic_t *v, int old, int new) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_cmpxchg(v, old, new); +} +#define atomic_cmpxchg atomic_cmpxchg +#endif + +#if defined(arch_atomic_cmpxchg_acquire) +static inline int +atomic_cmpxchg_acquire(atomic_t *v, int old, int new) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_cmpxchg_acquire(v, old, new); +} +#define atomic_cmpxchg_acquire atomic_cmpxchg_acquire +#endif + +#if defined(arch_atomic_cmpxchg_release) +static inline int +atomic_cmpxchg_release(atomic_t *v, int old, int new) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_cmpxchg_release(v, old, new); +} +#define atomic_cmpxchg_release atomic_cmpxchg_release +#endif + +#if defined(arch_atomic_cmpxchg_relaxed) +static inline int +atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_cmpxchg_relaxed(v, old, new); +} +#define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed +#endif + +#if defined(arch_atomic_try_cmpxchg) +static inline bool +atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + kasan_check_write(v, sizeof(*v)); + kasan_check_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg(v, old, new); +} +#define atomic_try_cmpxchg atomic_try_cmpxchg +#endif + +#if defined(arch_atomic_try_cmpxchg_acquire) +static inline bool +atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + kasan_check_write(v, sizeof(*v)); + kasan_check_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg_acquire(v, old, new); +} +#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire +#endif + +#if defined(arch_atomic_try_cmpxchg_release) +static inline bool +atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + kasan_check_write(v, sizeof(*v)); + kasan_check_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg_release(v, old, new); +} +#define atomic_try_cmpxchg_release atomic_try_cmpxchg_release +#endif + +#if defined(arch_atomic_try_cmpxchg_relaxed) +static inline bool +atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) +{ + kasan_check_write(v, sizeof(*v)); + kasan_check_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg_relaxed(v, old, new); +} +#define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed +#endif + +#if defined(arch_atomic_sub_and_test) +static inline bool +atomic_sub_and_test(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_sub_and_test(i, v); +} +#define atomic_sub_and_test atomic_sub_and_test +#endif + +#if defined(arch_atomic_dec_and_test) +static inline bool +atomic_dec_and_test(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_dec_and_test(v); +} +#define atomic_dec_and_test atomic_dec_and_test +#endif + +#if defined(arch_atomic_inc_and_test) +static inline bool +atomic_inc_and_test(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_inc_and_test(v); +} +#define atomic_inc_and_test atomic_inc_and_test +#endif + +#if defined(arch_atomic_add_negative) +static inline bool +atomic_add_negative(int i, atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_add_negative(i, v); +} +#define atomic_add_negative atomic_add_negative +#endif + +#if defined(arch_atomic_fetch_add_unless) +static inline int +atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_fetch_add_unless(v, a, u); +} +#define atomic_fetch_add_unless atomic_fetch_add_unless +#endif + +#if defined(arch_atomic_add_unless) +static inline bool +atomic_add_unless(atomic_t *v, int a, int u) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_add_unless(v, a, u); +} +#define atomic_add_unless atomic_add_unless +#endif + +#if defined(arch_atomic_inc_not_zero) +static inline bool +atomic_inc_not_zero(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_inc_not_zero(v); +} +#define atomic_inc_not_zero atomic_inc_not_zero +#endif + +#if defined(arch_atomic_inc_unless_negative) +static inline bool +atomic_inc_unless_negative(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_inc_unless_negative(v); +} +#define atomic_inc_unless_negative atomic_inc_unless_negative +#endif + +#if defined(arch_atomic_dec_unless_positive) +static inline bool +atomic_dec_unless_positive(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_dec_unless_positive(v); +} +#define atomic_dec_unless_positive atomic_dec_unless_positive +#endif + +#if defined(arch_atomic_dec_if_positive) +static inline int +atomic_dec_if_positive(atomic_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic_dec_if_positive(v); +} +#define atomic_dec_if_positive atomic_dec_if_positive +#endif + +static inline s64 +atomic64_read(const atomic64_t *v) +{ + kasan_check_read(v, sizeof(*v)); + return arch_atomic64_read(v); +} +#define atomic64_read atomic64_read + +#if defined(arch_atomic64_read_acquire) +static inline s64 +atomic64_read_acquire(const atomic64_t *v) +{ + kasan_check_read(v, sizeof(*v)); + return arch_atomic64_read_acquire(v); +} +#define atomic64_read_acquire atomic64_read_acquire +#endif + +static inline void +atomic64_set(atomic64_t *v, s64 i) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic64_set(v, i); +} +#define atomic64_set atomic64_set + +#if defined(arch_atomic64_set_release) +static inline void +atomic64_set_release(atomic64_t *v, s64 i) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic64_set_release(v, i); +} +#define atomic64_set_release atomic64_set_release +#endif + +static inline void +atomic64_add(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic64_add(i, v); +} +#define atomic64_add atomic64_add + +#if !defined(arch_atomic64_add_return_relaxed) || defined(arch_atomic64_add_return) +static inline s64 +atomic64_add_return(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_add_return(i, v); +} +#define atomic64_add_return atomic64_add_return +#endif + +#if defined(arch_atomic64_add_return_acquire) +static inline s64 +atomic64_add_return_acquire(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_add_return_acquire(i, v); +} +#define atomic64_add_return_acquire atomic64_add_return_acquire +#endif + +#if defined(arch_atomic64_add_return_release) +static inline s64 +atomic64_add_return_release(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_add_return_release(i, v); +} +#define atomic64_add_return_release atomic64_add_return_release +#endif + +#if defined(arch_atomic64_add_return_relaxed) +static inline s64 +atomic64_add_return_relaxed(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_add_return_relaxed(i, v); +} +#define atomic64_add_return_relaxed atomic64_add_return_relaxed +#endif + +#if !defined(arch_atomic64_fetch_add_relaxed) || defined(arch_atomic64_fetch_add) +static inline s64 +atomic64_fetch_add(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_add(i, v); +} +#define atomic64_fetch_add atomic64_fetch_add +#endif + +#if defined(arch_atomic64_fetch_add_acquire) +static inline s64 +atomic64_fetch_add_acquire(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_acquire(i, v); +} +#define atomic64_fetch_add_acquire atomic64_fetch_add_acquire +#endif + +#if defined(arch_atomic64_fetch_add_release) +static inline s64 +atomic64_fetch_add_release(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_release(i, v); +} +#define atomic64_fetch_add_release atomic64_fetch_add_release +#endif + +#if defined(arch_atomic64_fetch_add_relaxed) +static inline s64 +atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_relaxed(i, v); +} +#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed +#endif + +static inline void +atomic64_sub(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + arch_atomic64_sub(i, v); +} +#define atomic64_sub atomic64_sub -#ifndef _LINUX_ATOMIC_INSTRUMENTED_H -#define _LINUX_ATOMIC_INSTRUMENTED_H +#if !defined(arch_atomic64_sub_return_relaxed) || defined(arch_atomic64_sub_return) +static inline s64 +atomic64_sub_return(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_sub_return(i, v); +} +#define atomic64_sub_return atomic64_sub_return +#endif -#include -#include +#if defined(arch_atomic64_sub_return_acquire) +static inline s64 +atomic64_sub_return_acquire(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_sub_return_acquire(i, v); +} +#define atomic64_sub_return_acquire atomic64_sub_return_acquire +#endif -static __always_inline int atomic_read(const atomic_t *v) +#if defined(arch_atomic64_sub_return_release) +static inline s64 +atomic64_sub_return_release(s64 i, atomic64_t *v) { - kasan_check_read(v, sizeof(*v)); - return arch_atomic_read(v); + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_sub_return_release(i, v); } +#define atomic64_sub_return_release atomic64_sub_return_release +#endif -static __always_inline s64 atomic64_read(const atomic64_t *v) +#if defined(arch_atomic64_sub_return_relaxed) +static inline s64 +atomic64_sub_return_relaxed(s64 i, atomic64_t *v) { - kasan_check_read(v, sizeof(*v)); - return arch_atomic64_read(v); + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_sub_return_relaxed(i, v); } +#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed +#endif -static __always_inline void atomic_set(atomic_t *v, int i) +#if !defined(arch_atomic64_fetch_sub_relaxed) || defined(arch_atomic64_fetch_sub) +static inline s64 +atomic64_fetch_sub(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic_set(v, i); + return arch_atomic64_fetch_sub(i, v); } +#define atomic64_fetch_sub atomic64_fetch_sub +#endif -static __always_inline void atomic64_set(atomic64_t *v, s64 i) +#if defined(arch_atomic64_fetch_sub_acquire) +static inline s64 +atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic64_set(v, i); + return arch_atomic64_fetch_sub_acquire(i, v); } +#define atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire +#endif -static __always_inline int atomic_xchg(atomic_t *v, int i) +#if defined(arch_atomic64_fetch_sub_release) +static inline s64 +atomic64_fetch_sub_release(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_xchg(v, i); + return arch_atomic64_fetch_sub_release(i, v); } +#define atomic64_fetch_sub_release atomic64_fetch_sub_release +#endif -static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i) +#if defined(arch_atomic64_fetch_sub_relaxed) +static inline s64 +atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_xchg(v, i); + return arch_atomic64_fetch_sub_relaxed(i, v); } +#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed +#endif -static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) +#if defined(arch_atomic64_inc) +static inline void +atomic64_inc(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_cmpxchg(v, old, new); + arch_atomic64_inc(v); } +#define atomic64_inc atomic64_inc +#endif -static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +#if defined(arch_atomic64_inc_return) +static inline s64 +atomic64_inc_return(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_cmpxchg(v, old, new); + return arch_atomic64_inc_return(v); } +#define atomic64_inc_return atomic64_inc_return +#endif -#ifdef arch_atomic_try_cmpxchg -#define atomic_try_cmpxchg atomic_try_cmpxchg -static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) +#if defined(arch_atomic64_inc_return_acquire) +static inline s64 +atomic64_inc_return_acquire(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - kasan_check_read(old, sizeof(*old)); - return arch_atomic_try_cmpxchg(v, old, new); + return arch_atomic64_inc_return_acquire(v); } +#define atomic64_inc_return_acquire atomic64_inc_return_acquire #endif -#ifdef arch_atomic64_try_cmpxchg -#define atomic64_try_cmpxchg atomic64_try_cmpxchg -static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +#if defined(arch_atomic64_inc_return_release) +static inline s64 +atomic64_inc_return_release(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - kasan_check_read(old, sizeof(*old)); - return arch_atomic64_try_cmpxchg(v, old, new); + return arch_atomic64_inc_return_release(v); } +#define atomic64_inc_return_release atomic64_inc_return_release #endif -#ifdef arch_atomic_fetch_add_unless -#define atomic_fetch_add_unless atomic_fetch_add_unless -static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) +#if defined(arch_atomic64_inc_return_relaxed) +static inline s64 +atomic64_inc_return_relaxed(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_fetch_add_unless(v, a, u); + return arch_atomic64_inc_return_relaxed(v); } +#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed #endif -#ifdef arch_atomic64_fetch_add_unless -#define atomic64_fetch_add_unless atomic64_fetch_add_unless -static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +#if defined(arch_atomic64_fetch_inc) +static inline s64 +atomic64_fetch_inc(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_fetch_add_unless(v, a, u); + return arch_atomic64_fetch_inc(v); } +#define atomic64_fetch_inc atomic64_fetch_inc #endif -#ifdef arch_atomic_inc -#define atomic_inc atomic_inc -static __always_inline void atomic_inc(atomic_t *v) +#if defined(arch_atomic64_fetch_inc_acquire) +static inline s64 +atomic64_fetch_inc_acquire(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic_inc(v); + return arch_atomic64_fetch_inc_acquire(v); } +#define atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire #endif -#ifdef arch_atomic64_inc -#define atomic64_inc atomic64_inc -static __always_inline void atomic64_inc(atomic64_t *v) +#if defined(arch_atomic64_fetch_inc_release) +static inline s64 +atomic64_fetch_inc_release(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic64_inc(v); + return arch_atomic64_fetch_inc_release(v); } +#define atomic64_fetch_inc_release atomic64_fetch_inc_release #endif -#ifdef arch_atomic_dec -#define atomic_dec atomic_dec -static __always_inline void atomic_dec(atomic_t *v) +#if defined(arch_atomic64_fetch_inc_relaxed) +static inline s64 +atomic64_fetch_inc_relaxed(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic_dec(v); + return arch_atomic64_fetch_inc_relaxed(v); } +#define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed #endif -#ifdef atch_atomic64_dec -#define atomic64_dec -static __always_inline void atomic64_dec(atomic64_t *v) +#if defined(arch_atomic64_dec) +static inline void +atomic64_dec(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic64_dec(v); } +#define atomic64_dec atomic64_dec #endif -static __always_inline void atomic_add(int i, atomic_t *v) +#if defined(arch_atomic64_dec_return) +static inline s64 +atomic64_dec_return(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic_add(i, v); + return arch_atomic64_dec_return(v); } +#define atomic64_dec_return atomic64_dec_return +#endif -static __always_inline void atomic64_add(s64 i, atomic64_t *v) +#if defined(arch_atomic64_dec_return_acquire) +static inline s64 +atomic64_dec_return_acquire(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic64_add(i, v); + return arch_atomic64_dec_return_acquire(v); } +#define atomic64_dec_return_acquire atomic64_dec_return_acquire +#endif -static __always_inline void atomic_sub(int i, atomic_t *v) +#if defined(arch_atomic64_dec_return_release) +static inline s64 +atomic64_dec_return_release(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic_sub(i, v); + return arch_atomic64_dec_return_release(v); } +#define atomic64_dec_return_release atomic64_dec_return_release +#endif -static __always_inline void atomic64_sub(s64 i, atomic64_t *v) +#if defined(arch_atomic64_dec_return_relaxed) +static inline s64 +atomic64_dec_return_relaxed(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic64_sub(i, v); + return arch_atomic64_dec_return_relaxed(v); } +#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed +#endif -static __always_inline void atomic_and(int i, atomic_t *v) +#if defined(arch_atomic64_fetch_dec) +static inline s64 +atomic64_fetch_dec(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic_and(i, v); + return arch_atomic64_fetch_dec(v); +} +#define atomic64_fetch_dec atomic64_fetch_dec +#endif + +#if defined(arch_atomic64_fetch_dec_acquire) +static inline s64 +atomic64_fetch_dec_acquire(atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec_acquire(v); +} +#define atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire +#endif + +#if defined(arch_atomic64_fetch_dec_release) +static inline s64 +atomic64_fetch_dec_release(atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec_release(v); } +#define atomic64_fetch_dec_release atomic64_fetch_dec_release +#endif + +#if defined(arch_atomic64_fetch_dec_relaxed) +static inline s64 +atomic64_fetch_dec_relaxed(atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec_relaxed(v); +} +#define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed +#endif -static __always_inline void atomic64_and(s64 i, atomic64_t *v) +static inline void +atomic64_and(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic64_and(i, v); } +#define atomic64_and atomic64_and -static __always_inline void atomic_or(int i, atomic_t *v) +#if !defined(arch_atomic64_fetch_and_relaxed) || defined(arch_atomic64_fetch_and) +static inline s64 +atomic64_fetch_and(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic_or(i, v); + return arch_atomic64_fetch_and(i, v); } +#define atomic64_fetch_and atomic64_fetch_and +#endif -static __always_inline void atomic64_or(s64 i, atomic64_t *v) +#if defined(arch_atomic64_fetch_and_acquire) +static inline s64 +atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic64_or(i, v); + return arch_atomic64_fetch_and_acquire(i, v); } +#define atomic64_fetch_and_acquire atomic64_fetch_and_acquire +#endif -static __always_inline void atomic_xor(int i, atomic_t *v) +#if defined(arch_atomic64_fetch_and_release) +static inline s64 +atomic64_fetch_and_release(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic_xor(i, v); + return arch_atomic64_fetch_and_release(i, v); } +#define atomic64_fetch_and_release atomic64_fetch_and_release +#endif -static __always_inline void atomic64_xor(s64 i, atomic64_t *v) +#if defined(arch_atomic64_fetch_and_relaxed) +static inline s64 +atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - arch_atomic64_xor(i, v); + return arch_atomic64_fetch_and_relaxed(i, v); } +#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed +#endif -#ifdef arch_atomic_inc_return -#define atomic_inc_return atomic_inc_return -static __always_inline int atomic_inc_return(atomic_t *v) +#if defined(arch_atomic64_andnot) +static inline void +atomic64_andnot(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_inc_return(v); + arch_atomic64_andnot(i, v); } +#define atomic64_andnot atomic64_andnot #endif -#ifdef arch_atomic64_in_return -#define atomic64_inc_return atomic64_inc_return -static __always_inline s64 atomic64_inc_return(atomic64_t *v) +#if defined(arch_atomic64_fetch_andnot) +static inline s64 +atomic64_fetch_andnot(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_inc_return(v); + return arch_atomic64_fetch_andnot(i, v); } +#define atomic64_fetch_andnot atomic64_fetch_andnot #endif -#ifdef arch_atomic_dec_return -#define atomic_dec_return atomic_dec_return -static __always_inline int atomic_dec_return(atomic_t *v) +#if defined(arch_atomic64_fetch_andnot_acquire) +static inline s64 +atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_dec_return(v); + return arch_atomic64_fetch_andnot_acquire(i, v); } +#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire #endif -#ifdef arch_atomic64_dec_return -#define atomic64_dec_return atomic64_dec_return -static __always_inline s64 atomic64_dec_return(atomic64_t *v) +#if defined(arch_atomic64_fetch_andnot_release) +static inline s64 +atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_dec_return(v); + return arch_atomic64_fetch_andnot_release(i, v); } +#define atomic64_fetch_andnot_release atomic64_fetch_andnot_release #endif -#ifdef arch_atomic64_inc_not_zero -#define atomic64_inc_not_zero atomic64_inc_not_zero -static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) +#if defined(arch_atomic64_fetch_andnot_relaxed) +static inline s64 +atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_inc_not_zero(v); + return arch_atomic64_fetch_andnot_relaxed(i, v); } +#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed #endif -#ifdef arch_atomic64_dec_if_positive -#define atomic64_dec_if_positive atomic64_dec_if_positive -static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) +static inline void +atomic64_or(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_dec_if_positive(v); + arch_atomic64_or(i, v); +} +#define atomic64_or atomic64_or + +#if !defined(arch_atomic64_fetch_or_relaxed) || defined(arch_atomic64_fetch_or) +static inline s64 +atomic64_fetch_or(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_or(i, v); } +#define atomic64_fetch_or atomic64_fetch_or #endif -#ifdef arch_atomic_dec_and_test -#define atomic_dec_and_test atomic_dec_and_test -static __always_inline bool atomic_dec_and_test(atomic_t *v) +#if defined(arch_atomic64_fetch_or_acquire) +static inline s64 +atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_dec_and_test(v); + return arch_atomic64_fetch_or_acquire(i, v); } +#define atomic64_fetch_or_acquire atomic64_fetch_or_acquire #endif -#ifdef arch_atomic64_dec_and_test -#define atomic64_dec_and_test atomic64_dec_and_test -static __always_inline bool atomic64_dec_and_test(atomic64_t *v) +#if defined(arch_atomic64_fetch_or_release) +static inline s64 +atomic64_fetch_or_release(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_dec_and_test(v); + return arch_atomic64_fetch_or_release(i, v); } +#define atomic64_fetch_or_release atomic64_fetch_or_release #endif -#ifdef arch_atomic_inc_and_test -#define atomic_inc_and_test atomic_inc_and_test -static __always_inline bool atomic_inc_and_test(atomic_t *v) +#if defined(arch_atomic64_fetch_or_relaxed) +static inline s64 +atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_inc_and_test(v); + return arch_atomic64_fetch_or_relaxed(i, v); } +#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed #endif -#ifdef arch_atomic64_inc_and_test -#define atomic64_inc_and_test atomic64_inc_and_test -static __always_inline bool atomic64_inc_and_test(atomic64_t *v) +static inline void +atomic64_xor(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_inc_and_test(v); + arch_atomic64_xor(i, v); +} +#define atomic64_xor atomic64_xor + +#if !defined(arch_atomic64_fetch_xor_relaxed) || defined(arch_atomic64_fetch_xor) +static inline s64 +atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_xor(i, v); } +#define atomic64_fetch_xor atomic64_fetch_xor #endif -static __always_inline int atomic_add_return(int i, atomic_t *v) +#if defined(arch_atomic64_fetch_xor_acquire) +static inline s64 +atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_add_return(i, v); + return arch_atomic64_fetch_xor_acquire(i, v); } +#define atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire +#endif -static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) +#if defined(arch_atomic64_fetch_xor_release) +static inline s64 +atomic64_fetch_xor_release(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_add_return(i, v); + return arch_atomic64_fetch_xor_release(i, v); } +#define atomic64_fetch_xor_release atomic64_fetch_xor_release +#endif -static __always_inline int atomic_sub_return(int i, atomic_t *v) +#if defined(arch_atomic64_fetch_xor_relaxed) +static inline s64 +atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_sub_return(i, v); + return arch_atomic64_fetch_xor_relaxed(i, v); } +#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed +#endif -static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) +#if !defined(arch_atomic64_xchg_relaxed) || defined(arch_atomic64_xchg) +static inline s64 +atomic64_xchg(atomic64_t *v, s64 i) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_sub_return(i, v); + return arch_atomic64_xchg(v, i); } +#define atomic64_xchg atomic64_xchg +#endif -static __always_inline int atomic_fetch_add(int i, atomic_t *v) +#if defined(arch_atomic64_xchg_acquire) +static inline s64 +atomic64_xchg_acquire(atomic64_t *v, s64 i) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_fetch_add(i, v); + return arch_atomic64_xchg_acquire(v, i); } +#define atomic64_xchg_acquire atomic64_xchg_acquire +#endif -static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) +#if defined(arch_atomic64_xchg_release) +static inline s64 +atomic64_xchg_release(atomic64_t *v, s64 i) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_fetch_add(i, v); + return arch_atomic64_xchg_release(v, i); } +#define atomic64_xchg_release atomic64_xchg_release +#endif -static __always_inline int atomic_fetch_sub(int i, atomic_t *v) +#if defined(arch_atomic64_xchg_relaxed) +static inline s64 +atomic64_xchg_relaxed(atomic64_t *v, s64 i) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_fetch_sub(i, v); + return arch_atomic64_xchg_relaxed(v, i); } +#define atomic64_xchg_relaxed atomic64_xchg_relaxed +#endif -static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) +#if !defined(arch_atomic64_cmpxchg_relaxed) || defined(arch_atomic64_cmpxchg) +static inline s64 +atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_fetch_sub(i, v); + return arch_atomic64_cmpxchg(v, old, new); } +#define atomic64_cmpxchg atomic64_cmpxchg +#endif -static __always_inline int atomic_fetch_and(int i, atomic_t *v) +#if defined(arch_atomic64_cmpxchg_acquire) +static inline s64 +atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_fetch_and(i, v); + return arch_atomic64_cmpxchg_acquire(v, old, new); } +#define atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire +#endif -static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) +#if defined(arch_atomic64_cmpxchg_release) +static inline s64 +atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_fetch_and(i, v); + return arch_atomic64_cmpxchg_release(v, old, new); } +#define atomic64_cmpxchg_release atomic64_cmpxchg_release +#endif -static __always_inline int atomic_fetch_or(int i, atomic_t *v) +#if defined(arch_atomic64_cmpxchg_relaxed) +static inline s64 +atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_fetch_or(i, v); + return arch_atomic64_cmpxchg_relaxed(v, old, new); } +#define atomic64_cmpxchg_relaxed atomic64_cmpxchg_relaxed +#endif -static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) +#if defined(arch_atomic64_try_cmpxchg) +static inline bool +atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_fetch_or(i, v); + kasan_check_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg(v, old, new); } +#define atomic64_try_cmpxchg atomic64_try_cmpxchg +#endif -static __always_inline int atomic_fetch_xor(int i, atomic_t *v) +#if defined(arch_atomic64_try_cmpxchg_acquire) +static inline bool +atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_fetch_xor(i, v); + kasan_check_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg_acquire(v, old, new); } +#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire +#endif -static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) +#if defined(arch_atomic64_try_cmpxchg_release) +static inline bool +atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_fetch_xor(i, v); + kasan_check_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg_release(v, old, new); } +#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release +#endif -#ifdef arch_atomic_sub_and_test -#define atomic_sub_and_test atomic_sub_and_test -static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) +#if defined(arch_atomic64_try_cmpxchg_relaxed) +static inline bool +atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_sub_and_test(i, v); + kasan_check_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg_relaxed(v, old, new); } +#define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed #endif -#ifdef arch_atomic64_sub_and_test -#define atomic64_sub_and_test atomic64_sub_and_test -static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) +#if defined(arch_atomic64_sub_and_test) +static inline bool +atomic64_sub_and_test(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_sub_and_test(i, v); } +#define atomic64_sub_and_test atomic64_sub_and_test #endif -#ifdef arch_atomic_add_negative -#define atomic_add_negative atomic_add_negative -static __always_inline bool atomic_add_negative(int i, atomic_t *v) +#if defined(arch_atomic64_dec_and_test) +static inline bool +atomic64_dec_and_test(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); - return arch_atomic_add_negative(i, v); + return arch_atomic64_dec_and_test(v); } +#define atomic64_dec_and_test atomic64_dec_and_test #endif -#ifdef arch_atomic64_add_negative -#define atomic64_add_negative atomic64_add_negative -static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) +#if defined(arch_atomic64_inc_and_test) +static inline bool +atomic64_inc_and_test(atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_inc_and_test(v); +} +#define atomic64_inc_and_test atomic64_inc_and_test +#endif + +#if defined(arch_atomic64_add_negative) +static inline bool +atomic64_add_negative(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_add_negative(i, v); } +#define atomic64_add_negative atomic64_add_negative +#endif + +#if defined(arch_atomic64_fetch_add_unless) +static inline s64 +atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_unless(v, a, u); +} +#define atomic64_fetch_add_unless atomic64_fetch_add_unless +#endif + +#if defined(arch_atomic64_add_unless) +static inline bool +atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_add_unless(v, a, u); +} +#define atomic64_add_unless atomic64_add_unless +#endif + +#if defined(arch_atomic64_inc_not_zero) +static inline bool +atomic64_inc_not_zero(atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_inc_not_zero(v); +} +#define atomic64_inc_not_zero atomic64_inc_not_zero +#endif + +#if defined(arch_atomic64_inc_unless_negative) +static inline bool +atomic64_inc_unless_negative(atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_inc_unless_negative(v); +} +#define atomic64_inc_unless_negative atomic64_inc_unless_negative #endif -#define xchg(ptr, new) \ +#if defined(arch_atomic64_dec_unless_positive) +static inline bool +atomic64_dec_unless_positive(atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_dec_unless_positive(v); +} +#define atomic64_dec_unless_positive atomic64_dec_unless_positive +#endif + +#if defined(arch_atomic64_dec_if_positive) +static inline s64 +atomic64_dec_if_positive(atomic64_t *v) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_dec_if_positive(v); +} +#define atomic64_dec_if_positive atomic64_dec_if_positive +#endif + +#if !defined(arch_xchg_relaxed) || defined(arch_xchg) +#define xchg(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg(__ai_ptr, __VA_ARGS__); \ +}) +#endif + +#if defined(arch_xchg_acquire) +#define xchg_acquire(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \ +}) +#endif + +#if defined(arch_xchg_release) +#define xchg_release(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg_release(__ai_ptr, __VA_ARGS__); \ +}) +#endif + +#if defined(arch_xchg_relaxed) +#define xchg_relaxed(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ +}) +#endif + +#if !defined(arch_cmpxchg_relaxed) || defined(arch_cmpxchg) +#define cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_xchg(__ai_ptr, (new)); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) +#endif + +#if defined(arch_cmpxchg_acquire) +#define cmpxchg_acquire(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ +}) +#endif + +#if defined(arch_cmpxchg_release) +#define cmpxchg_release(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ +}) +#endif + +#if defined(arch_cmpxchg_relaxed) +#define cmpxchg_relaxed(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ +}) +#endif -#define cmpxchg(ptr, old, new) \ +#if !defined(arch_cmpxchg64_relaxed) || defined(arch_cmpxchg64) +#define cmpxchg64(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg(__ai_ptr, (old), (new)); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \ }) +#endif + +#if defined(arch_cmpxchg64_acquire) +#define cmpxchg64_acquire(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ +}) +#endif + +#if defined(arch_cmpxchg64_release) +#define cmpxchg64_release(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ +}) +#endif -#define sync_cmpxchg(ptr, old, new) \ +#if defined(arch_cmpxchg64_relaxed) +#define cmpxchg64_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_sync_cmpxchg(__ai_ptr, (old), (new)); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ }) +#endif -#define cmpxchg_local(ptr, old, new) \ +#define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg_local(__ai_ptr, (old), (new)); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ }) -#define cmpxchg64(ptr, old, new) \ +#define cmpxchg64_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg64(__ai_ptr, (old), (new)); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ }) -#define cmpxchg64_local(ptr, old, new) \ +#define sync_cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg64_local(__ai_ptr, (old), (new)); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) -#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \ +#define cmpxchg_double(ptr, ...) \ ({ \ - typeof(p1) __ai_p1 = (p1); \ - kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \ - arch_cmpxchg_double(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \ }) -#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ -({ \ - typeof(p1) __ai_p1 = (p1); \ - kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \ - arch_cmpxchg_double_local(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \ + +#define cmpxchg_double_local(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \ }) -#endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ +#endif /* _ASM_GENERIC_ATOMIC_INSTRUMENTED_H */ -- cgit v1.2.3 From 17abc9ec68b73ddeb262a507a62421016b9c54d5 Mon Sep 17 00:00:00 2001 From: Tomasz Duszynski Date: Fri, 14 Dec 2018 19:28:01 +0100 Subject: iio: add IIO_MASSCONCENTRATION channel type Measuring particulate matter in ug / m3 (micro-grams per cubic meter) is de facto standard. Existing air quality sensors usually follow this convention and are capable of returning measurements using this unit. IIO currently does not offer suitable channel type for this type of measurements hence this patch adds this. In addition, extra modifiers are introduced used for distinguishing between fine pm1, pm2p5 and coarse pm4, pm10 particle measurements, i.e IIO_MOD_PM1, IIO_MOD_PM25 and IIO_MOD_PM4, IIO_MOD_PM10. pmX consists of particles with aerodynamic diameter less or equal to X micrometers. Signed-off-by: Tomasz Duszynski Acked-by: Matt Ranostay Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 17 ++++++++++++++++- drivers/iio/industrialio-core.c | 5 +++++ include/uapi/linux/iio/types.h | 5 +++++ tools/iio/iio_event_monitor.c | 10 ++++++++++ 4 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 8127a08e366d..67fd88bf7910 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1684,4 +1684,19 @@ KernelVersion: 4.18 Contact: linux-iio@vger.kernel.org Description: Raw (unscaled) phase difference reading from channel Y - that can be processed to radians. \ No newline at end of file + that can be processed to radians. + +What: /sys/bus/iio/devices/iio:deviceX/in_massconcentration_pm1_input +What: /sys/bus/iio/devices/iio:deviceX/in_massconcentrationY_pm1_input +What: /sys/bus/iio/devices/iio:deviceX/in_massconcentration_pm2p5_input +What: /sys/bus/iio/devices/iio:deviceX/in_massconcentrationY_pm2p5_input +What: /sys/bus/iio/devices/iio:deviceX/in_massconcentration_pm4_input +What: /sys/bus/iio/devices/iio:deviceX/in_massconcentrationY_pm4_input +What: /sys/bus/iio/devices/iio:deviceX/in_massconcentration_pm10_input +What: /sys/bus/iio/devices/iio:deviceX/in_massconcentrationY_pm10_input +KernelVersion: 4.22 +Contact: linux-iio@vger.kernel.org +Description: + Mass concentration reading of particulate matter in ug / m3. + pmX consists of particles with aerodynamic diameter less or + equal to X micrometers. diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 4f5cd9f60870..4700fd5d8c90 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -87,6 +87,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_GRAVITY] = "gravity", [IIO_POSITIONRELATIVE] = "positionrelative", [IIO_PHASE] = "phase", + [IIO_MASSCONCENTRATION] = "massconcentration", }; static const char * const iio_modifier_names[] = { @@ -127,6 +128,10 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_Q] = "q", [IIO_MOD_CO2] = "co2", [IIO_MOD_VOC] = "voc", + [IIO_MOD_PM1] = "pm1", + [IIO_MOD_PM2P5] = "pm2p5", + [IIO_MOD_PM4] = "pm4", + [IIO_MOD_PM10] = "pm10", }; /* relies on pairs of these shared then separate */ diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 92baabc103ac..c59adac24b1c 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -46,6 +46,7 @@ enum iio_chan_type { IIO_GRAVITY, IIO_POSITIONRELATIVE, IIO_PHASE, + IIO_MASSCONCENTRATION, }; enum iio_modifier { @@ -87,6 +88,10 @@ enum iio_modifier { IIO_MOD_VOC, IIO_MOD_LIGHT_UV, IIO_MOD_LIGHT_DUV, + IIO_MOD_PM1, + IIO_MOD_PM2P5, + IIO_MOD_PM4, + IIO_MOD_PM10, }; enum iio_event_type { diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index ac2de6b7e89f..f6b8003fbe3c 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -60,6 +60,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_GRAVITY] = "gravity", [IIO_POSITIONRELATIVE] = "positionrelative", [IIO_PHASE] = "phase", + [IIO_MASSCONCENTRATION] = "massconcentration", }; static const char * const iio_ev_type_text[] = { @@ -115,6 +116,10 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_Q] = "q", [IIO_MOD_CO2] = "co2", [IIO_MOD_VOC] = "voc", + [IIO_MOD_PM1] = "pm1", + [IIO_MOD_PM2P5] = "pm2p5", + [IIO_MOD_PM4] = "pm4", + [IIO_MOD_PM10] = "pm10", }; static bool event_is_known(struct iio_event_data *event) @@ -156,6 +161,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_GRAVITY: case IIO_POSITIONRELATIVE: case IIO_PHASE: + case IIO_MASSCONCENTRATION: break; default: return false; @@ -200,6 +206,10 @@ static bool event_is_known(struct iio_event_data *event) case IIO_MOD_Q: case IIO_MOD_CO2: case IIO_MOD_VOC: + case IIO_MOD_PM1: + case IIO_MOD_PM2P5: + case IIO_MOD_PM4: + case IIO_MOD_PM10: break; default: return false; -- cgit v1.2.3 From b170f7d48443d1ea3e4ffbf409025b5e5b1146fe Mon Sep 17 00:00:00 2001 From: Andreas Brauchli Date: Thu, 13 Dec 2018 15:43:22 +0100 Subject: iio: Add modifiers for ethanol and H2 gases Add ethanol and H2 gas modifiers: * IIO_MOD_ETHANOL * IIO_MOD_H2 Signed-off-by: Andreas Brauchli Acked-by: Matt Ranostay Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 4 ++++ include/uapi/linux/iio/types.h | 2 ++ tools/iio/iio_event_monitor.c | 4 ++++ 3 files changed, 10 insertions(+) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 67fd88bf7910..864f8efd12e5 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1554,6 +1554,10 @@ What: /sys/bus/iio/devices/iio:deviceX/in_concentration_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentration_co2_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_co2_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentration_ethanol_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_ethanol_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentration_h2_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_h2_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentration_voc_raw What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw KernelVersion: 4.3 diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index c59adac24b1c..fdd81affca4b 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -92,6 +92,8 @@ enum iio_modifier { IIO_MOD_PM2P5, IIO_MOD_PM4, IIO_MOD_PM10, + IIO_MOD_ETHANOL, + IIO_MOD_H2, }; enum iio_event_type { diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index f6b8003fbe3c..7bf9bde28bcc 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -115,6 +115,8 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_I] = "i", [IIO_MOD_Q] = "q", [IIO_MOD_CO2] = "co2", + [IIO_MOD_ETHANOL] = "ethanol", + [IIO_MOD_H2] = "h2", [IIO_MOD_VOC] = "voc", [IIO_MOD_PM1] = "pm1", [IIO_MOD_PM2P5] = "pm2p5", @@ -205,6 +207,8 @@ static bool event_is_known(struct iio_event_data *event) case IIO_MOD_I: case IIO_MOD_Q: case IIO_MOD_CO2: + case IIO_MOD_ETHANOL: + case IIO_MOD_H2: case IIO_MOD_VOC: case IIO_MOD_PM1: case IIO_MOD_PM2P5: -- cgit v1.2.3 From 7a79d717e0817610932ce3b7b6033ea06ee1d577 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Mon, 31 Dec 2018 23:59:59 +0100 Subject: batman-adv: Update copyright years for 2019 Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/batadv_packet.h | 2 +- include/uapi/linux/batman_adv.h | 2 +- net/batman-adv/Kconfig | 2 +- net/batman-adv/Makefile | 2 +- net/batman-adv/bat_algo.c | 2 +- net/batman-adv/bat_algo.h | 2 +- net/batman-adv/bat_iv_ogm.c | 2 +- net/batman-adv/bat_iv_ogm.h | 2 +- net/batman-adv/bat_v.c | 2 +- net/batman-adv/bat_v.h | 2 +- net/batman-adv/bat_v_elp.c | 2 +- net/batman-adv/bat_v_elp.h | 2 +- net/batman-adv/bat_v_ogm.c | 2 +- net/batman-adv/bat_v_ogm.h | 2 +- net/batman-adv/bitarray.c | 2 +- net/batman-adv/bitarray.h | 2 +- net/batman-adv/bridge_loop_avoidance.c | 2 +- net/batman-adv/bridge_loop_avoidance.h | 2 +- net/batman-adv/debugfs.c | 2 +- net/batman-adv/debugfs.h | 2 +- net/batman-adv/distributed-arp-table.c | 2 +- net/batman-adv/distributed-arp-table.h | 2 +- net/batman-adv/fragmentation.c | 2 +- net/batman-adv/fragmentation.h | 2 +- net/batman-adv/gateway_client.c | 2 +- net/batman-adv/gateway_client.h | 2 +- net/batman-adv/gateway_common.c | 2 +- net/batman-adv/gateway_common.h | 2 +- net/batman-adv/hard-interface.c | 2 +- net/batman-adv/hard-interface.h | 2 +- net/batman-adv/hash.c | 2 +- net/batman-adv/hash.h | 2 +- net/batman-adv/icmp_socket.c | 2 +- net/batman-adv/icmp_socket.h | 2 +- net/batman-adv/log.c | 2 +- net/batman-adv/log.h | 2 +- net/batman-adv/main.c | 2 +- net/batman-adv/main.h | 2 +- net/batman-adv/multicast.c | 2 +- net/batman-adv/multicast.h | 2 +- net/batman-adv/netlink.c | 2 +- net/batman-adv/netlink.h | 2 +- net/batman-adv/network-coding.c | 2 +- net/batman-adv/network-coding.h | 2 +- net/batman-adv/originator.c | 2 +- net/batman-adv/originator.h | 2 +- net/batman-adv/routing.c | 2 +- net/batman-adv/routing.h | 2 +- net/batman-adv/send.c | 2 +- net/batman-adv/send.h | 2 +- net/batman-adv/soft-interface.c | 2 +- net/batman-adv/soft-interface.h | 2 +- net/batman-adv/sysfs.c | 2 +- net/batman-adv/sysfs.h | 2 +- net/batman-adv/tp_meter.c | 2 +- net/batman-adv/tp_meter.h | 2 +- net/batman-adv/trace.c | 2 +- net/batman-adv/trace.h | 2 +- net/batman-adv/translation-table.c | 2 +- net/batman-adv/translation-table.h | 2 +- net/batman-adv/tvlv.c | 2 +- net/batman-adv/tvlv.h | 2 +- net/batman-adv/types.h | 2 +- 63 files changed, 63 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 894d8d2f713d..7eb2936a8e22 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 324a0e1143e7..a28e76a7e0a2 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: MIT */ -/* Copyright (C) 2016-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: * * Matthias Schiffer * diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index c386e6981416..a31db5e9ac8e 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 9b58160fe485..a887ecc3efa1 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index ea309ad06175..7b7e15641fef 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 534b790c3753..25e7bb51928c 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index f97e566f0402..de61091af666 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h index 3dc6a7a43eb7..785f6666273c 100644 --- a/net/batman-adv/bat_iv_ogm.h +++ b/net/batman-adv/bat_iv_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 90e33f84d37a..445594ed58af 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h index ec4a2a569750..465a4fc23354 100644 --- a/net/batman-adv/bat_v.h +++ b/net/batman-adv/bat_v.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing * diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index e8090f099eb8..7b80f6f8d4dc 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index e8c7b7fd290d..75f189ee4a1c 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 2948b41b06d4..c9698ad41854 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index e5be14c908c6..f67cf7ee06b2 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index a296a4d851f5..63e134e763e3 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 48f683289531..f3a05ad9afad 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 5fdde2947802..ef39aabdb694 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 71f95a3e4d3f..31771c751efb 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index d4a7702e48d8..3b9d1ad2f467 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 8de018e5c577..c0b8694041ec 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index c7f3e2231233..899ab051ffce 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index e58d7a9bfc8d..68c0ff321acd 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 5b71a289d04f..b506d15b8230 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Martin Hundebøll * diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index 944512e07782..abdac26579bf 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Martin Hundebøll * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 9d8e5eda2314..0a6b9b30eabd 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index f0b86fcb2493..b5732c8be81a 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 936c107f3199..53d03adc9bfc 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 80afb2793687..89bae100a0b0 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 508f4416dfc9..28c1fb8d1af0 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index d1c0f6189301..48de28c83401 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 9194f4d891b1..56a08ce193d5 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 0e36fa1c7c3e..37507b6d4006 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index d70f363c52ae..d34bb79e0405 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 958be22beda9..5f8926522ff0 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index 02e55b78132f..f97849a8380b 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index 35f4f397ed57..660e9bcc85a2 100644 --- a/net/batman-adv/log.h +++ b/net/batman-adv/log.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index d1ed839fd32b..75750870cf04 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index f3ef2c725a41..3ed669d7dc6b 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 69244e4598f5..5de6a37525f5 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2014-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 3b04ab13f0eb..466013fe88af 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2014-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 2dc3304cee54..5fe833cc9507 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2016-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: * * Matthias Schiffer * diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index 571d9a5ae7aa..216484b8b82d 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2016-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: * * Matthias Schiffer * diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 34caf129a9bf..278762bd94c6 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 65c346812bc1..96ef0a511fc7 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 56a981af5c92..e5cdf89ef63c 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index a8b4c7b667ec..dca1e4a34ec6 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 469fa97d1add..cae0e5dd0768 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index db54c2d9b8bf..0102d69d345c 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 4a35f5c2f52b..66a8b3e44501 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 64cce07b8fe6..1f6132922e60 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 943071008670..b14fb3462af7 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index daf87f07fadd..538bb661878c 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 09427fc6494a..e1b816262c53 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index c1e3fb69952d..705ffbe763f4 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 11520de96ccb..500109bbd551 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli * diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index 68e600974759..6b4d0f733896 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli * diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c index 8e1024217cff..f77c917ed20d 100644 --- a/net/batman-adv/trace.c +++ b/net/batman-adv/trace.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Sven Eckelmann * diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h index 104784be94d7..5e5579051400 100644 --- a/net/batman-adv/trace.h +++ b/net/batman-adv/trace.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Sven Eckelmann * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 8dcd4968cde7..f73d79139ae7 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 01b6c8eafaf9..61bca75e5911 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 40e69c9346d2..7e947b01919d 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index ef5867f49824..c0f033b1acb8 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index cbe17da36fcb..a21b34ed6548 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * -- cgit v1.2.3 From 95f295f9fe08166307d94b641fba0b0e924d5d31 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Wed, 21 Nov 2018 16:13:23 +0000 Subject: dmaengine: tegra: add tracepoints to driver Add some trace-points to the driver to allow for debuging via the trace pipe. Signed-off-by: Ben Dooks Reviewed-by: Steven Rostedt (VMware) Signed-off-by: Vinod Koul --- drivers/dma/tegra20-apb-dma.c | 7 +++++ include/trace/events/tegra_apb_dma.h | 61 ++++++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) create mode 100644 include/trace/events/tegra_apb_dma.h (limited to 'include') diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index c60c3f7cad5f..659b49bf6fdb 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -38,6 +38,9 @@ #include "dmaengine.h" +#define CREATE_TRACE_POINTS +#include + #define TEGRA_APBDMA_GENERAL 0x0 #define TEGRA_APBDMA_GENERAL_ENABLE BIT(31) @@ -672,6 +675,8 @@ static void tegra_dma_tasklet(unsigned long data) dmaengine_desc_get_callback(&dma_desc->txd, &cb); cb_count = dma_desc->cb_count; dma_desc->cb_count = 0; + trace_tegra_dma_complete_cb(&tdc->dma_chan, cb_count, + cb.callback); spin_unlock_irqrestore(&tdc->lock, flags); while (cb_count--) dmaengine_desc_callback_invoke(&cb, NULL); @@ -688,6 +693,7 @@ static irqreturn_t tegra_dma_isr(int irq, void *dev_id) spin_lock_irqsave(&tdc->lock, flags); + trace_tegra_dma_isr(&tdc->dma_chan, irq); status = tdc_read(tdc, TEGRA_APBDMA_CHAN_STATUS); if (status & TEGRA_APBDMA_STATUS_ISE_EOC) { tdc_write(tdc, TEGRA_APBDMA_CHAN_STATUS, status); @@ -846,6 +852,7 @@ found: dma_set_residue(txstate, residual); } + trace_tegra_dma_tx_status(&tdc->dma_chan, cookie, txstate); spin_unlock_irqrestore(&tdc->lock, flags); return ret; } diff --git a/include/trace/events/tegra_apb_dma.h b/include/trace/events/tegra_apb_dma.h new file mode 100644 index 000000000000..0818f6286110 --- /dev/null +++ b/include/trace/events/tegra_apb_dma.h @@ -0,0 +1,61 @@ +#if !defined(_TRACE_TEGRA_APB_DMA_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TEGRA_APM_DMA_H + +#include +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM tegra_apb_dma + +TRACE_EVENT(tegra_dma_tx_status, + TP_PROTO(struct dma_chan *dc, dma_cookie_t cookie, struct dma_tx_state *state), + TP_ARGS(dc, cookie, state), + TP_STRUCT__entry( + __string(chan, dev_name(&dc->dev->device)) + __field(dma_cookie_t, cookie) + __field(__u32, residue) + ), + TP_fast_assign( + __assign_str(chan, dev_name(&dc->dev->device)); + __entry->cookie = cookie; + __entry->residue = state ? state->residue : (u32)-1; + ), + TP_printk("channel %s: dma cookie %d, residue %u", + __get_str(chan), __entry->cookie, __entry->residue) +); + +TRACE_EVENT(tegra_dma_complete_cb, + TP_PROTO(struct dma_chan *dc, int count, void *ptr), + TP_ARGS(dc, count, ptr), + TP_STRUCT__entry( + __string(chan, dev_name(&dc->dev->device)) + __field(int, count) + __field(void *, ptr) + ), + TP_fast_assign( + __assign_str(chan, dev_name(&dc->dev->device)); + __entry->count = count; + __entry->ptr = ptr; + ), + TP_printk("channel %s: done %d, ptr %p", + __get_str(chan), __entry->count, __entry->ptr) +); + +TRACE_EVENT(tegra_dma_isr, + TP_PROTO(struct dma_chan *dc, int irq), + TP_ARGS(dc, irq), + TP_STRUCT__entry( + __string(chan, dev_name(&dc->dev->device)) + __field(int, irq) + ), + TP_fast_assign( + __assign_str(chan, dev_name(&dc->dev->device)); + __entry->irq = irq; + ), + TP_printk("%s: irq %d\n", __get_str(chan), __entry->irq) +); + +#endif /* _TRACE_TEGRADMA_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 8fc5c73554db0ac18c0c6ac5b2099ab917f83bdf Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 9 Nov 2018 12:43:07 -0800 Subject: acpi/nfit, device-dax: Identify differentiated memory with a unique numa-node MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Persistent memory, as described by the ACPI NFIT (NVDIMM Firmware Interface Table), is the first known instance of a memory range described by a unique "target" proximity domain. Where "initiator" and "target" proximity domains is an approach that the ACPI HMAT (Heterogeneous Memory Attributes Table) uses to described the unique performance properties of a memory range relative to a given initiator (e.g. CPU or DMA device). Currently the numa-node for a /dev/pmemX block-device or /dev/daxX.Y char-device follows the traditional notion of 'numa-node' where the attribute conveys the closest online numa-node. That numa-node attribute is useful for cpu-binding and memory-binding processes *near* the device. However, when the memory range backing a 'pmem', or 'dax' device is onlined (memory hot-add) the memory-only-numa-node representing that address needs to be differentiated from the set of online nodes. In other words, the numa-node association of the device depends on whether you can bind processes *near* the cpu-numa-node in the offline device-case, or bind process *on* the memory-range directly after the backing address range is onlined. Allow for the case that platform firmware describes persistent memory with a unique proximity domain, i.e. when it is distinct from the proximity of DRAM and CPUs that are on the same socket. Plumb the Linux numa-node translation of that proximity through the libnvdimm region device to namespaces that are in device-dax mode. With this in place the proposed kmem driver [1] can optionally discover a unique numa-node number for the address range as it transitions the memory from an offline state managed by a device-driver to an online memory range managed by the core-mm. [1]: https://lore.kernel.org/lkml/20181022201317.8558C1D8@viggo.jf.intel.com Reported-by: Fan Du Cc: Michael Ellerman Cc: "Oliver O'Halloran" Cc: Dave Hansen Cc: Jérôme Glisse Reviewed-by: Yang Shi Signed-off-by: Dan Williams --- arch/powerpc/platforms/pseries/papr_scm.c | 1 + drivers/acpi/nfit/core.c | 8 ++++++-- drivers/acpi/numa.c | 1 + drivers/dax/bus.c | 4 +++- drivers/dax/bus.h | 3 ++- drivers/dax/dax-private.h | 4 ++++ drivers/dax/pmem/core.c | 4 +++- drivers/nvdimm/e820.c | 1 + drivers/nvdimm/nd.h | 2 +- drivers/nvdimm/of_pmem.c | 1 + drivers/nvdimm/region_devs.c | 1 + include/linux/acpi.h | 5 +++++ include/linux/libnvdimm.h | 1 + 13 files changed, 30 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 7d6457ab5d34..8806ac822627 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -236,6 +236,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) memset(&ndr_desc, 0, sizeof(ndr_desc)); ndr_desc.attr_groups = region_attr_groups; ndr_desc.numa_node = dev_to_node(&p->pdev->dev); + ndr_desc.target_node = ndr_desc.numa_node; ndr_desc.res = &p->res; ndr_desc.of_node = p->dn; ndr_desc.provider_data = p; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 011d3db19c80..475899974c70 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2869,11 +2869,15 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, ndr_desc->res = &res; ndr_desc->provider_data = nfit_spa; ndr_desc->attr_groups = acpi_nfit_region_attribute_groups; - if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) + if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) { ndr_desc->numa_node = acpi_map_pxm_to_online_node( spa->proximity_domain); - else + ndr_desc->target_node = acpi_map_pxm_to_node( + spa->proximity_domain); + } else { ndr_desc->numa_node = NUMA_NO_NODE; + ndr_desc->target_node = NUMA_NO_NODE; + } /* * Persistence domain bits are hierarchical, if diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c index 274699463b4f..b9d86babb13a 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -84,6 +84,7 @@ int acpi_map_pxm_to_node(int pxm) return node; } +EXPORT_SYMBOL(acpi_map_pxm_to_node); /** * acpi_map_pxm_to_online_node - Map proximity ID to online node diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 568168500217..c620ad52d7e5 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -214,7 +214,7 @@ static void dax_region_unregister(void *region) } struct dax_region *alloc_dax_region(struct device *parent, int region_id, - struct resource *res, unsigned int align, + struct resource *res, int target_node, unsigned int align, unsigned long pfn_flags) { struct dax_region *dax_region; @@ -244,6 +244,7 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id, dax_region->id = region_id; dax_region->align = align; dax_region->dev = parent; + dax_region->target_node = target_node; if (sysfs_create_groups(&parent->kobj, dax_region_attribute_groups)) { kfree(dax_region); return NULL; @@ -348,6 +349,7 @@ struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id, dev_dax->dax_dev = dax_dev; dev_dax->region = dax_region; + dev_dax->target_node = dax_region->target_node; kref_get(&dax_region->kref); inode = dax_inode(dax_dev); diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h index ce977552ffb5..8619e3299943 100644 --- a/drivers/dax/bus.h +++ b/drivers/dax/bus.h @@ -10,7 +10,8 @@ struct dax_device; struct dax_region; void dax_region_put(struct dax_region *dax_region); struct dax_region *alloc_dax_region(struct device *parent, int region_id, - struct resource *res, unsigned int align, unsigned long flags); + struct resource *res, int target_node, unsigned int align, + unsigned long flags); enum dev_dax_subsys { DEV_DAX_BUS, diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h index a82ce48f5884..a45612148ca0 100644 --- a/drivers/dax/dax-private.h +++ b/drivers/dax/dax-private.h @@ -26,6 +26,7 @@ void dax_bus_exit(void); /** * struct dax_region - mapping infrastructure for dax devices * @id: kernel-wide unique region for a memory range + * @target_node: effective numa node if this memory range is onlined * @kref: to pin while other agents have a need to do lookups * @dev: parent device backing this region * @align: allocation and mapping alignment for child dax devices @@ -34,6 +35,7 @@ void dax_bus_exit(void); */ struct dax_region { int id; + int target_node; struct kref kref; struct device *dev; unsigned int align; @@ -46,6 +48,7 @@ struct dax_region { * data while the device is activated in the driver. * @region - parent region * @dax_dev - core dax functionality + * @target_node: effective numa node if dev_dax memory range is onlined * @dev - device core * @pgmap - pgmap for memmap setup / lifetime (driver owned) * @ref: pgmap reference count (driver owned) @@ -54,6 +57,7 @@ struct dax_region { struct dev_dax { struct dax_region *region; struct dax_device *dax_dev; + int target_node; struct device dev; struct dev_pagemap pgmap; struct percpu_ref ref; diff --git a/drivers/dax/pmem/core.c b/drivers/dax/pmem/core.c index bdcff1b14e95..f71019ce0647 100644 --- a/drivers/dax/pmem/core.c +++ b/drivers/dax/pmem/core.c @@ -20,6 +20,7 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys) struct nd_namespace_common *ndns; struct nd_dax *nd_dax = to_nd_dax(dev); struct nd_pfn *nd_pfn = &nd_dax->nd_pfn; + struct nd_region *nd_region = to_nd_region(dev->parent); ndns = nvdimm_namespace_common_probe(dev); if (IS_ERR(ndns)) @@ -52,7 +53,8 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys) memcpy(&res, &pgmap.res, sizeof(res)); res.start += offset; dax_region = alloc_dax_region(dev, region_id, &res, - le32_to_cpu(pfn_sb->align), PFN_DEV|PFN_MAP); + nd_region->target_node, le32_to_cpu(pfn_sb->align), + PFN_DEV|PFN_MAP); if (!dax_region) return ERR_PTR(-ENOMEM); diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c index 521eaf53a52a..36be9b619187 100644 --- a/drivers/nvdimm/e820.c +++ b/drivers/nvdimm/e820.c @@ -47,6 +47,7 @@ static int e820_register_one(struct resource *res, void *data) ndr_desc.res = res; ndr_desc.attr_groups = e820_pmem_region_attribute_groups; ndr_desc.numa_node = e820_range_to_nid(res->start); + ndr_desc.target_node = ndr_desc.numa_node; set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags); if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc)) return -ENXIO; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index cfde992684e7..0b3d7595b3cb 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -153,7 +153,7 @@ struct nd_region { u16 ndr_mappings; u64 ndr_size; u64 ndr_start; - int id, num_lanes, ro, numa_node; + int id, num_lanes, ro, numa_node, target_node; void *provider_data; struct kernfs_node *bb_state; struct badblocks bb; diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c index 0a701837dfc0..ecaaa27438e2 100644 --- a/drivers/nvdimm/of_pmem.c +++ b/drivers/nvdimm/of_pmem.c @@ -68,6 +68,7 @@ static int of_pmem_region_probe(struct platform_device *pdev) memset(&ndr_desc, 0, sizeof(ndr_desc)); ndr_desc.attr_groups = region_attr_groups; ndr_desc.numa_node = dev_to_node(&pdev->dev); + ndr_desc.target_node = ndr_desc.numa_node; ndr_desc.res = &pdev->resource[i]; ndr_desc.of_node = np; set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index e2818f94f292..caf2f3129ccd 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -1065,6 +1065,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, nd_region->flags = ndr_desc->flags; nd_region->ro = ro; nd_region->numa_node = ndr_desc->numa_node; + nd_region->target_node = ndr_desc->target_node; ida_init(&nd_region->ns_ida); ida_init(&nd_region->btt_ida); ida_init(&nd_region->pfn_ida); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 87715f20b69a..eddf2736e5a6 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -400,12 +400,17 @@ extern bool acpi_osi_is_win8(void); #ifdef CONFIG_ACPI_NUMA int acpi_map_pxm_to_online_node(int pxm); +int acpi_map_pxm_to_node(int pxm); int acpi_get_node(acpi_handle handle); #else static inline int acpi_map_pxm_to_online_node(int pxm) { return 0; } +static inline int acpi_map_pxm_to_node(int pxm) +{ + return 0; +} static inline int acpi_get_node(acpi_handle handle) { return 0; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 5440f11b0907..56bc545ad3b2 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -128,6 +128,7 @@ struct nd_region_desc { void *provider_data; int num_lanes; int numa_node; + int target_node; unsigned long flags; struct device_node *of_node; }; -- cgit v1.2.3 From ebc40be2b8eec093abbbd87658a6726ff84a61f5 Mon Sep 17 00:00:00 2001 From: Fabien Dessenne Date: Wed, 7 Nov 2018 11:18:34 +0100 Subject: remoteproc: fix kernel-doc comment for parse_fw Fix the kernel-doc comment for "parse_fw" and fix a typo. Signed-off-by: Fabien Dessenne Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 507a2b524208..68e72f33c705 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -345,9 +345,9 @@ struct firmware; * @stop: power off the device * @kick: kick a virtqueue (virtqueue id given as a parameter) * @da_to_va: optional platform hook to perform address translations - * @load_rsc_table: load resource table from firmware image + * @parse_fw: parse firmware to extract information (e.g. resource table) * @find_loaded_rsc_table: find the loaded resouce table - * @load: load firmeware to memory, where the remote processor + * @load: load firmware to memory, where the remote processor * expects to find it * @sanity_check: sanity check the fw image * @get_boot_addr: get boot address to entry point specified in firmware -- cgit v1.2.3 From d7dba6be0f31ae61f5f3296aa130f45d57d30f74 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 7 Jan 2019 13:07:36 +0200 Subject: dmaengine: dw: Remove misleading is_private property The commit a9ddb575d6d6 ("dmaengine: dw_dmac: Enhance device tree support") introduces is_private property in uncertain understanding what does it mean. First of all, documentation defines DMA_PRIVATE capability as Documentation/crypto/async-tx-api.txt: The DMA_PRIVATE capability flag is used to tag dma devices that should not be used by the general-purpose allocator. It can be set at initialization time if it is known that a channel will always be private. Alternatively, it is set when dma_request_channel() finds an unused "public" channel. A couple caveats to note when implementing a driver and consumer: 1/ Once a channel has been privately allocated it will no longer be considered by the general-purpose allocator even after a call to dma_release_channel(). 2/ Since capabilities are specified at the device level a dma_device with multiple channels will either have all channels public, or all channels private. Documentation/driver-api/dmaengine/provider.rst: - DMA_PRIVATE The devices only supports slave transfers, and as such isn't available for async transfers. The capability had been introduced by the commit 59b5ec21446b ("dmaengine: introduce dma_request_channel and private channels") and some code didn't changed from that times ever. Taking into consideration above and the fact that on all known platforms Synopsys DesignWare DMA engine is attached to serve slave transfers, the DMA_PRIVATE capability must be enabled for this device unconditionally. Otherwise, as rightfully noticed in drivers/dma/at_xdmac.c: /* * Without DMA_PRIVATE the driver is not able to allocate more than * one channel, second allocation fails in private_candidate. */ because of of a caveats mentioned in above documentation excerpts. So, remove conditional around DMA_PRIVATE followed by removal leftovers. If someone wonders, DMA_PRIVATE can be not used if and only if the all channels of the DMA controller are supposed to serve memory-to-memory like operations. For example, EP93xx has two controllers, one of which can only perform memory-to-memory transfers Note, this change doesn't affect dmatest to be able to test such controllers. Cc: Greg Kroah-Hartman (maintainer:SERIAL DRIVERS) Cc: Dan Williams Signed-off-by: Andy Shevchenko Acked-by: Greg Kroah-Hartman Signed-off-by: Vinod Koul --- Documentation/devicetree/bindings/dma/snps-dma.txt | 2 -- drivers/dma/dw/core.c | 4 +--- drivers/dma/dw/pci.c | 1 - drivers/dma/dw/platform.c | 3 --- drivers/tty/serial/8250/8250_lpss.c | 1 - include/linux/platform_data/dma-dw.h | 3 --- 6 files changed, 1 insertion(+), 13 deletions(-) (limited to 'include') diff --git a/Documentation/devicetree/bindings/dma/snps-dma.txt b/Documentation/devicetree/bindings/dma/snps-dma.txt index db757df7057d..0bedceed1963 100644 --- a/Documentation/devicetree/bindings/dma/snps-dma.txt +++ b/Documentation/devicetree/bindings/dma/snps-dma.txt @@ -23,8 +23,6 @@ Deprecated properties: Optional properties: -- is_private: The device channels should be marked as private and not for by the - general purpose DMA channel allocator. False if not passed. - multi-block: Multi block transfers supported by hardware. Array property with one cell per channel. 0: not supported, 1 (default): supported. - snps,dma-protection-control: AHB HPROT[3:1] protection setting. diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index dc053e62f894..e25503986680 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -1227,7 +1227,6 @@ int dw_dma_probe(struct dw_dma_chip *chip) pdata->block_size = dma_readl(dw, MAX_BLK_SIZE); /* Fill platform data with the default values */ - pdata->is_private = true; pdata->is_memcpy = true; pdata->chan_allocation_order = CHAN_ALLOCATION_ASCENDING; pdata->chan_priority = CHAN_PRIORITY_ASCENDING; @@ -1340,8 +1339,7 @@ int dw_dma_probe(struct dw_dma_chip *chip) /* Set capabilities */ dma_cap_set(DMA_SLAVE, dw->dma.cap_mask); - if (pdata->is_private) - dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask); + dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask); if (pdata->is_memcpy) dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask); diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index 313ba10c6224..570498faadc3 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -17,7 +17,6 @@ static struct dw_dma_platform_data mrfld_pdata = { .nr_channels = 8, - .is_private = true, .is_memcpy = true, .is_idma32 = true, .chan_allocation_order = CHAN_ALLOCATION_ASCENDING, diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index 31ff8113c3de..6dd8cd1820c1 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -128,9 +128,6 @@ dw_dma_parse_dt(struct platform_device *pdev) pdata->nr_masters = nr_masters; pdata->nr_channels = nr_channels; - if (of_property_read_bool(np, "is_private")) - pdata->is_private = true; - /* * All known devices, which use DT for configuration, support * memory-to-memory transfers. So enable it by default. diff --git a/drivers/tty/serial/8250/8250_lpss.c b/drivers/tty/serial/8250/8250_lpss.c index 98dbc796353f..53ca9ba6ab4b 100644 --- a/drivers/tty/serial/8250/8250_lpss.c +++ b/drivers/tty/serial/8250/8250_lpss.c @@ -153,7 +153,6 @@ static int byt_serial_setup(struct lpss8250 *lpss, struct uart_port *port) #ifdef CONFIG_SERIAL_8250_DMA static const struct dw_dma_platform_data qrk_serial_dma_pdata = { .nr_channels = 2, - .is_private = true, .chan_allocation_order = CHAN_ALLOCATION_ASCENDING, .chan_priority = CHAN_PRIORITY_ASCENDING, .block_size = 4095, diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index 1a1d58ebffbf..d443025c5c72 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -38,8 +38,6 @@ struct dw_dma_slave { /** * struct dw_dma_platform_data - Controller configuration parameters * @nr_channels: Number of channels supported by hardware (max 8) - * @is_private: The device channels should be marked as private and not for - * by the general purpose DMA channel allocator. * @is_memcpy: The device channels do support memory-to-memory transfers. * @is_idma32: The type of the DMA controller is iDMA32 * @chan_allocation_order: Allocate channels starting from 0 or 7 @@ -53,7 +51,6 @@ struct dw_dma_slave { */ struct dw_dma_platform_data { unsigned int nr_channels; - bool is_private; bool is_memcpy; bool is_idma32; #define CHAN_ALLOCATION_ASCENDING 0 /* zero to seven */ -- cgit v1.2.3 From 078165779608873e7b6eae1316a39c73af9f3edc Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 7 Jan 2019 13:07:37 +0200 Subject: dmaengine: dw: Remove unused internal property All known devices, which use DT for configuration, support memory-to-memory transfers. So enable it by default. The rest two cases, i.e. Intel Quark and PPC460ex, instantiate DMA driver and use its channels exclusively for hardware, which means there is no available channel for any other purposes anyway. Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- drivers/dma/dw/core.c | 4 +--- drivers/dma/dw/pci.c | 1 - drivers/dma/dw/platform.c | 6 ------ include/linux/platform_data/dma-dw.h | 2 -- 4 files changed, 1 insertion(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index e25503986680..4982e443869c 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -1227,7 +1227,6 @@ int dw_dma_probe(struct dw_dma_chip *chip) pdata->block_size = dma_readl(dw, MAX_BLK_SIZE); /* Fill platform data with the default values */ - pdata->is_memcpy = true; pdata->chan_allocation_order = CHAN_ALLOCATION_ASCENDING; pdata->chan_priority = CHAN_PRIORITY_ASCENDING; } else if (chip->pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS) { @@ -1340,8 +1339,7 @@ int dw_dma_probe(struct dw_dma_chip *chip) /* Set capabilities */ dma_cap_set(DMA_SLAVE, dw->dma.cap_mask); dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask); - if (pdata->is_memcpy) - dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask); + dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask); dw->dma.dev = chip->dev; dw->dma.device_alloc_chan_resources = dwc_alloc_chan_resources; diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index 570498faadc3..66d98d7ccad0 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -17,7 +17,6 @@ static struct dw_dma_platform_data mrfld_pdata = { .nr_channels = 8, - .is_memcpy = true, .is_idma32 = true, .chan_allocation_order = CHAN_ALLOCATION_ASCENDING, .chan_priority = CHAN_PRIORITY_ASCENDING, diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index 6dd8cd1820c1..58fc1ba02a1e 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -128,12 +128,6 @@ dw_dma_parse_dt(struct platform_device *pdev) pdata->nr_masters = nr_masters; pdata->nr_channels = nr_channels; - /* - * All known devices, which use DT for configuration, support - * memory-to-memory transfers. So enable it by default. - */ - pdata->is_memcpy = true; - if (!of_property_read_u32(np, "chan_allocation_order", &tmp)) pdata->chan_allocation_order = (unsigned char)tmp; diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index d443025c5c72..1c85eeee4171 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -38,7 +38,6 @@ struct dw_dma_slave { /** * struct dw_dma_platform_data - Controller configuration parameters * @nr_channels: Number of channels supported by hardware (max 8) - * @is_memcpy: The device channels do support memory-to-memory transfers. * @is_idma32: The type of the DMA controller is iDMA32 * @chan_allocation_order: Allocate channels starting from 0 or 7 * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0. @@ -51,7 +50,6 @@ struct dw_dma_slave { */ struct dw_dma_platform_data { unsigned int nr_channels; - bool is_memcpy; bool is_idma32; #define CHAN_ALLOCATION_ASCENDING 0 /* zero to seven */ #define CHAN_ALLOCATION_DESCENDING 1 /* seven to zero */ -- cgit v1.2.3 From 69da8be90d5e85e60b5377c47384154b9dabf592 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 7 Jan 2019 13:07:38 +0200 Subject: dmaengine: dw: Split DW and iDMA 32-bit operations Here is a kinda big refactoring that should have been done in the first place, when Intel iDMA 32-bit support appeared. It splits operations which are different to Synopsys DesignWare and Intel iDMA 32-bit controllers. No functional change intended. Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- drivers/dma/dw/Makefile | 2 +- drivers/dma/dw/core.c | 190 +++++++---------------------------- drivers/dma/dw/dw.c | 112 +++++++++++++++++++++ drivers/dma/dw/idma32.c | 138 +++++++++++++++++++++++++ drivers/dma/dw/internal.h | 10 +- drivers/dma/dw/pci.c | 45 ++++++--- drivers/dma/dw/platform.c | 8 +- drivers/dma/dw/regs.h | 13 +++ include/linux/dma/dw.h | 4 + include/linux/platform_data/dma-dw.h | 2 - 10 files changed, 343 insertions(+), 181 deletions(-) create mode 100644 drivers/dma/dw/dw.c create mode 100644 drivers/dma/dw/idma32.c (limited to 'include') diff --git a/drivers/dma/dw/Makefile b/drivers/dma/dw/Makefile index 2b949c2e4504..63ed895c09aa 100644 --- a/drivers/dma/dw/Makefile +++ b/drivers/dma/dw/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DW_DMAC_CORE) += dw_dmac_core.o -dw_dmac_core-objs := core.o +dw_dmac_core-objs := core.o dw.o idma32.o obj-$(CONFIG_DW_DMAC) += dw_dmac.o dw_dmac-objs := platform.o diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 4982e443869c..8a581d86ea8d 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -138,44 +138,6 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc) dwc->descs_allocated--; } -static void dwc_initialize_chan_idma32(struct dw_dma_chan *dwc) -{ - u32 cfghi = 0; - u32 cfglo = 0; - - /* Set default burst alignment */ - cfglo |= IDMA32C_CFGL_DST_BURST_ALIGN | IDMA32C_CFGL_SRC_BURST_ALIGN; - - /* Low 4 bits of the request lines */ - cfghi |= IDMA32C_CFGH_DST_PER(dwc->dws.dst_id & 0xf); - cfghi |= IDMA32C_CFGH_SRC_PER(dwc->dws.src_id & 0xf); - - /* Request line extension (2 bits) */ - cfghi |= IDMA32C_CFGH_DST_PER_EXT(dwc->dws.dst_id >> 4 & 0x3); - cfghi |= IDMA32C_CFGH_SRC_PER_EXT(dwc->dws.src_id >> 4 & 0x3); - - channel_writel(dwc, CFG_LO, cfglo); - channel_writel(dwc, CFG_HI, cfghi); -} - -static void dwc_initialize_chan_dw(struct dw_dma_chan *dwc) -{ - struct dw_dma *dw = to_dw_dma(dwc->chan.device); - u32 cfghi = DWC_CFGH_FIFO_MODE; - u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority); - bool hs_polarity = dwc->dws.hs_polarity; - - cfghi |= DWC_CFGH_DST_PER(dwc->dws.dst_id); - cfghi |= DWC_CFGH_SRC_PER(dwc->dws.src_id); - cfghi |= DWC_CFGH_PROTCTL(dw->pdata->protctl); - - /* Set polarity of handshake interface */ - cfglo |= hs_polarity ? DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL : 0; - - channel_writel(dwc, CFG_LO, cfglo); - channel_writel(dwc, CFG_HI, cfghi); -} - static void dwc_initialize(struct dw_dma_chan *dwc) { struct dw_dma *dw = to_dw_dma(dwc->chan.device); @@ -183,10 +145,7 @@ static void dwc_initialize(struct dw_dma_chan *dwc) if (test_bit(DW_DMA_IS_INITIALIZED, &dwc->flags)) return; - if (dw->pdata->is_idma32) - dwc_initialize_chan_idma32(dwc); - else - dwc_initialize_chan_dw(dwc); + dw->initialize_chan(dwc); /* Enable interrupts */ channel_set_bit(dw, MASK.XFER, dwc->mask); @@ -215,37 +174,6 @@ static inline void dwc_chan_disable(struct dw_dma *dw, struct dw_dma_chan *dwc) cpu_relax(); } -static u32 bytes2block(struct dw_dma_chan *dwc, size_t bytes, - unsigned int width, size_t *len) -{ - struct dw_dma *dw = to_dw_dma(dwc->chan.device); - u32 block; - - /* Always in bytes for iDMA 32-bit */ - if (dw->pdata->is_idma32) - width = 0; - - if ((bytes >> width) > dwc->block_size) { - block = dwc->block_size; - *len = block << width; - } else { - block = bytes >> width; - *len = bytes; - } - - return block; -} - -static size_t block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width) -{ - struct dw_dma *dw = to_dw_dma(dwc->chan.device); - - if (dw->pdata->is_idma32) - return IDMA32C_CTLH_BLOCK_TS(block); - - return DWC_CTLH_BLOCK_TS(block) << width; -} - /*----------------------------------------------------------------------*/ /* Perform single block transfer */ @@ -391,10 +319,11 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc) /* Returns how many bytes were already received from source */ static inline u32 dwc_get_sent(struct dw_dma_chan *dwc) { + struct dw_dma *dw = to_dw_dma(dwc->chan.device); u32 ctlhi = channel_readl(dwc, CTL_HI); u32 ctllo = channel_readl(dwc, CTL_LO); - return block2bytes(dwc, ctlhi, ctllo >> 4 & 7); + return dw->block2bytes(dwc, ctlhi, ctllo >> 4 & 7); } static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc) @@ -651,7 +580,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, unsigned int src_width; unsigned int dst_width; unsigned int data_width = dw->pdata->data_width[m_master]; - u32 ctllo; + u32 ctllo, ctlhi; u8 lms = DWC_LLP_LMS(m_master); dev_vdbg(chan2dev(chan), @@ -680,10 +609,12 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, if (!desc) goto err_desc_get; + ctlhi = dw->bytes2block(dwc, len - offset, src_width, &xfer_count); + lli_write(desc, sar, src + offset); lli_write(desc, dar, dest + offset); lli_write(desc, ctllo, ctllo); - lli_write(desc, ctlhi, bytes2block(dwc, len - offset, src_width, &xfer_count)); + lli_write(desc, ctlhi, ctlhi); desc->len = xfer_count; if (!first) { @@ -721,7 +652,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, struct dma_slave_config *sconfig = &dwc->dma_sconfig; struct dw_desc *prev; struct dw_desc *first; - u32 ctllo; + u32 ctllo, ctlhi; u8 m_master = dwc->dws.m_master; u8 lms = DWC_LLP_LMS(m_master); dma_addr_t reg; @@ -768,9 +699,11 @@ slave_sg_todev_fill_desc: if (!desc) goto err_desc_get; + ctlhi = dw->bytes2block(dwc, len, mem_width, &dlen); + lli_write(desc, sar, mem); lli_write(desc, dar, reg); - lli_write(desc, ctlhi, bytes2block(dwc, len, mem_width, &dlen)); + lli_write(desc, ctlhi, ctlhi); lli_write(desc, ctllo, ctllo | DWC_CTLL_SRC_WIDTH(mem_width)); desc->len = dlen; @@ -814,9 +747,11 @@ slave_sg_fromdev_fill_desc: if (!desc) goto err_desc_get; + ctlhi = dw->bytes2block(dwc, len, reg_width, &dlen); + lli_write(desc, sar, reg); lli_write(desc, dar, mem); - lli_write(desc, ctlhi, bytes2block(dwc, len, reg_width, &dlen)); + lli_write(desc, ctlhi, ctlhi); mem_width = __ffs(data_width | mem | dlen); lli_write(desc, ctllo, ctllo | DWC_CTLL_DST_WIDTH(mem_width)); desc->len = dlen; @@ -876,22 +811,12 @@ EXPORT_SYMBOL_GPL(dw_dma_filter); static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dma_slave_config *sc = &dwc->dma_sconfig; struct dw_dma *dw = to_dw_dma(chan->device); - /* - * Fix sconfig's burst size according to dw_dmac. We need to convert - * them as: - * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3. - * - * NOTE: burst size 2 is not supported by DesignWare controller. - * iDMA 32-bit supports it. - */ - u32 s = dw->pdata->is_idma32 ? 1 : 2; memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig)); - sc->src_maxburst = sc->src_maxburst > 1 ? fls(sc->src_maxburst) - s : 0; - sc->dst_maxburst = sc->dst_maxburst > 1 ? fls(sc->dst_maxburst) - s : 0; + dw->encode_maxburst(dwc, &dwc->dma_sconfig.src_maxburst); + dw->encode_maxburst(dwc, &dwc->dma_sconfig.dst_maxburst); return 0; } @@ -900,16 +825,9 @@ static void dwc_chan_pause(struct dw_dma_chan *dwc, bool drain) { struct dw_dma *dw = to_dw_dma(dwc->chan.device); unsigned int count = 20; /* timeout iterations */ - u32 cfglo; - cfglo = channel_readl(dwc, CFG_LO); - if (dw->pdata->is_idma32) { - if (drain) - cfglo |= IDMA32C_CFGL_CH_DRAIN; - else - cfglo &= ~IDMA32C_CFGL_CH_DRAIN; - } - channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP); + dw->suspend_chan(dwc, drain); + while (!(channel_readl(dwc, CFG_LO) & DWC_CFGL_FIFO_EMPTY) && count--) udelay(2); @@ -1058,33 +976,7 @@ static void dwc_issue_pending(struct dma_chan *chan) /*----------------------------------------------------------------------*/ -/* - * Program FIFO size of channels. - * - * By default full FIFO (512 bytes) is assigned to channel 0. Here we - * slice FIFO on equal parts between channels. - */ -static void idma32_fifo_partition(struct dw_dma *dw) -{ - u64 value = IDMA32C_FP_PSIZE_CH0(64) | IDMA32C_FP_PSIZE_CH1(64) | - IDMA32C_FP_UPDATE; - u64 fifo_partition = 0; - - if (!dw->pdata->is_idma32) - return; - - /* Fill FIFO_PARTITION low bits (Channels 0..1, 4..5) */ - fifo_partition |= value << 0; - - /* Fill FIFO_PARTITION high bits (Channels 2..3, 6..7) */ - fifo_partition |= value << 32; - - /* Program FIFO Partition registers - 64 bytes per channel */ - idma32_writeq(dw, FIFO_PARTITION1, fifo_partition); - idma32_writeq(dw, FIFO_PARTITION0, fifo_partition); -} - -static void dw_dma_off(struct dw_dma *dw) +void do_dw_dma_off(struct dw_dma *dw) { unsigned int i; @@ -1103,7 +995,7 @@ static void dw_dma_off(struct dw_dma *dw) clear_bit(DW_DMA_IS_INITIALIZED, &dw->chan[i].flags); } -static void dw_dma_on(struct dw_dma *dw) +void do_dw_dma_on(struct dw_dma *dw) { dma_writel(dw, CFG, DW_CFG_DMA_EN); } @@ -1139,7 +1031,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan) /* Enable controller here if needed */ if (!dw->in_use) - dw_dma_on(dw); + do_dw_dma_on(dw); dw->in_use |= dwc->mask; return 0; @@ -1177,30 +1069,25 @@ static void dwc_free_chan_resources(struct dma_chan *chan) /* Disable controller in case it was a last user */ dw->in_use &= ~dwc->mask; if (!dw->in_use) - dw_dma_off(dw); + do_dw_dma_off(dw); dev_vdbg(chan2dev(chan), "%s: done\n", __func__); } -int dw_dma_probe(struct dw_dma_chip *chip) +int do_dma_probe(struct dw_dma_chip *chip) { + struct dw_dma *dw = chip->dw; struct dw_dma_platform_data *pdata; - struct dw_dma *dw; bool autocfg = false; unsigned int dw_params; unsigned int i; int err; - dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL); - if (!dw) - return -ENOMEM; - dw->pdata = devm_kzalloc(chip->dev, sizeof(*dw->pdata), GFP_KERNEL); if (!dw->pdata) return -ENOMEM; dw->regs = chip->regs; - chip->dw = dw; pm_runtime_get_sync(chip->dev); @@ -1250,15 +1137,10 @@ int dw_dma_probe(struct dw_dma_chip *chip) dw->all_chan_mask = (1 << pdata->nr_channels) - 1; /* Force dma off, just in case */ - dw_dma_off(dw); - - idma32_fifo_partition(dw); + dw->disable(dw); /* Device and instance ID for IRQ and DMA pool */ - if (pdata->is_idma32) - snprintf(dw->name, sizeof(dw->name), "idma32:dmac%d", chip->id); - else - snprintf(dw->name, sizeof(dw->name), "dw:dmac%d", chip->id); + dw->set_device_name(dw, chip->id); /* Create a pool of consistent memory blocks for hardware descriptors */ dw->desc_pool = dmam_pool_create(dw->name, chip->dev, @@ -1380,16 +1262,15 @@ err_pdata: pm_runtime_put_sync_suspend(chip->dev); return err; } -EXPORT_SYMBOL_GPL(dw_dma_probe); -int dw_dma_remove(struct dw_dma_chip *chip) +int do_dma_remove(struct dw_dma_chip *chip) { struct dw_dma *dw = chip->dw; struct dw_dma_chan *dwc, *_dwc; pm_runtime_get_sync(chip->dev); - dw_dma_off(dw); + do_dw_dma_off(dw); dma_async_device_unregister(&dw->dma); free_irq(chip->irq, dw); @@ -1404,27 +1285,24 @@ int dw_dma_remove(struct dw_dma_chip *chip) pm_runtime_put_sync_suspend(chip->dev); return 0; } -EXPORT_SYMBOL_GPL(dw_dma_remove); -int dw_dma_disable(struct dw_dma_chip *chip) +int do_dw_dma_disable(struct dw_dma_chip *chip) { struct dw_dma *dw = chip->dw; - dw_dma_off(dw); + dw->disable(dw); return 0; } -EXPORT_SYMBOL_GPL(dw_dma_disable); +EXPORT_SYMBOL_GPL(do_dw_dma_disable); -int dw_dma_enable(struct dw_dma_chip *chip) +int do_dw_dma_enable(struct dw_dma_chip *chip) { struct dw_dma *dw = chip->dw; - idma32_fifo_partition(dw); - - dw_dma_on(dw); + dw->enable(dw); return 0; } -EXPORT_SYMBOL_GPL(dw_dma_enable); +EXPORT_SYMBOL_GPL(do_dw_dma_enable); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller core driver"); diff --git a/drivers/dma/dw/dw.c b/drivers/dma/dw/dw.c new file mode 100644 index 000000000000..977aa28bf81d --- /dev/null +++ b/drivers/dma/dw/dw.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2007-2008 Atmel Corporation +// Copyright (C) 2010-2011 ST Microelectronics +// Copyright (C) 2013,2018 Intel Corporation + +#include +#include +#include +#include + +#include "internal.h" + +static void dw_dma_initialize_chan(struct dw_dma_chan *dwc) +{ + struct dw_dma *dw = to_dw_dma(dwc->chan.device); + u32 cfghi = DWC_CFGH_FIFO_MODE; + u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority); + bool hs_polarity = dwc->dws.hs_polarity; + + cfghi |= DWC_CFGH_DST_PER(dwc->dws.dst_id); + cfghi |= DWC_CFGH_SRC_PER(dwc->dws.src_id); + cfghi |= DWC_CFGH_PROTCTL(dw->pdata->protctl); + + /* Set polarity of handshake interface */ + cfglo |= hs_polarity ? DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL : 0; + + channel_writel(dwc, CFG_LO, cfglo); + channel_writel(dwc, CFG_HI, cfghi); +} + +static void dw_dma_suspend_chan(struct dw_dma_chan *dwc, bool drain) +{ + u32 cfglo = channel_readl(dwc, CFG_LO); + + channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP); +} + +static u32 dw_dma_bytes2block(struct dw_dma_chan *dwc, + size_t bytes, unsigned int width, size_t *len) +{ + u32 block; + + if ((bytes >> width) > dwc->block_size) { + block = dwc->block_size; + *len = dwc->block_size << width; + } else { + block = bytes >> width; + *len = bytes; + } + + return block; +} + +static size_t dw_dma_block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width) +{ + return DWC_CTLH_BLOCK_TS(block) << width; +} + +static void dw_dma_encode_maxburst(struct dw_dma_chan *dwc, u32 *maxburst) +{ + /* + * Fix burst size according to dw_dmac. We need to convert them as: + * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3. + */ + *maxburst = *maxburst > 1 ? fls(*maxburst) - 2 : 0; +} + +static void dw_dma_set_device_name(struct dw_dma *dw, int id) +{ + snprintf(dw->name, sizeof(dw->name), "dw:dmac%d", id); +} + +static void dw_dma_disable(struct dw_dma *dw) +{ + do_dw_dma_off(dw); +} + +static void dw_dma_enable(struct dw_dma *dw) +{ + do_dw_dma_on(dw); +} + +int dw_dma_probe(struct dw_dma_chip *chip) +{ + struct dw_dma *dw; + + dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL); + if (!dw) + return -ENOMEM; + + /* Channel operations */ + dw->initialize_chan = dw_dma_initialize_chan; + dw->suspend_chan = dw_dma_suspend_chan; + dw->encode_maxburst = dw_dma_encode_maxburst; + dw->bytes2block = dw_dma_bytes2block; + dw->block2bytes = dw_dma_block2bytes; + + /* Device operations */ + dw->set_device_name = dw_dma_set_device_name; + dw->disable = dw_dma_disable; + dw->enable = dw_dma_enable; + + chip->dw = dw; + return do_dma_probe(chip); +} +EXPORT_SYMBOL_GPL(dw_dma_probe); + +int dw_dma_remove(struct dw_dma_chip *chip) +{ + return do_dma_remove(chip); +} +EXPORT_SYMBOL_GPL(dw_dma_remove); diff --git a/drivers/dma/dw/idma32.c b/drivers/dma/dw/idma32.c new file mode 100644 index 000000000000..8707830f39ad --- /dev/null +++ b/drivers/dma/dw/idma32.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2013,2018 Intel Corporation + +#include +#include +#include +#include + +#include "internal.h" + +static void idma32_initialize_chan(struct dw_dma_chan *dwc) +{ + u32 cfghi = 0; + u32 cfglo = 0; + + /* Set default burst alignment */ + cfglo |= IDMA32C_CFGL_DST_BURST_ALIGN | IDMA32C_CFGL_SRC_BURST_ALIGN; + + /* Low 4 bits of the request lines */ + cfghi |= IDMA32C_CFGH_DST_PER(dwc->dws.dst_id & 0xf); + cfghi |= IDMA32C_CFGH_SRC_PER(dwc->dws.src_id & 0xf); + + /* Request line extension (2 bits) */ + cfghi |= IDMA32C_CFGH_DST_PER_EXT(dwc->dws.dst_id >> 4 & 0x3); + cfghi |= IDMA32C_CFGH_SRC_PER_EXT(dwc->dws.src_id >> 4 & 0x3); + + channel_writel(dwc, CFG_LO, cfglo); + channel_writel(dwc, CFG_HI, cfghi); +} + +static void idma32_suspend_chan(struct dw_dma_chan *dwc, bool drain) +{ + u32 cfglo = channel_readl(dwc, CFG_LO); + + if (drain) + cfglo |= IDMA32C_CFGL_CH_DRAIN; + else + cfglo &= ~IDMA32C_CFGL_CH_DRAIN; + + channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP); +} + +static u32 idma32_bytes2block(struct dw_dma_chan *dwc, + size_t bytes, unsigned int width, size_t *len) +{ + u32 block; + + if (bytes > dwc->block_size) { + block = dwc->block_size; + *len = dwc->block_size; + } else { + block = bytes; + *len = bytes; + } + + return block; +} + +static size_t idma32_block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width) +{ + return IDMA32C_CTLH_BLOCK_TS(block); +} + +static void idma32_encode_maxburst(struct dw_dma_chan *dwc, u32 *maxburst) +{ + *maxburst = *maxburst > 1 ? fls(*maxburst) - 1 : 0; +} + +static void idma32_set_device_name(struct dw_dma *dw, int id) +{ + snprintf(dw->name, sizeof(dw->name), "idma32:dmac%d", id); +} + +/* + * Program FIFO size of channels. + * + * By default full FIFO (512 bytes) is assigned to channel 0. Here we + * slice FIFO on equal parts between channels. + */ +static void idma32_fifo_partition(struct dw_dma *dw) +{ + u64 value = IDMA32C_FP_PSIZE_CH0(64) | IDMA32C_FP_PSIZE_CH1(64) | + IDMA32C_FP_UPDATE; + u64 fifo_partition = 0; + + /* Fill FIFO_PARTITION low bits (Channels 0..1, 4..5) */ + fifo_partition |= value << 0; + + /* Fill FIFO_PARTITION high bits (Channels 2..3, 6..7) */ + fifo_partition |= value << 32; + + /* Program FIFO Partition registers - 64 bytes per channel */ + idma32_writeq(dw, FIFO_PARTITION1, fifo_partition); + idma32_writeq(dw, FIFO_PARTITION0, fifo_partition); +} + +static void idma32_disable(struct dw_dma *dw) +{ + do_dw_dma_off(dw); + idma32_fifo_partition(dw); +} + +static void idma32_enable(struct dw_dma *dw) +{ + idma32_fifo_partition(dw); + do_dw_dma_on(dw); +} + +int idma32_dma_probe(struct dw_dma_chip *chip) +{ + struct dw_dma *dw; + + dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL); + if (!dw) + return -ENOMEM; + + /* Channel operations */ + dw->initialize_chan = idma32_initialize_chan; + dw->suspend_chan = idma32_suspend_chan; + dw->encode_maxburst = idma32_encode_maxburst; + dw->bytes2block = idma32_bytes2block; + dw->block2bytes = idma32_block2bytes; + + /* Device operations */ + dw->set_device_name = idma32_set_device_name; + dw->disable = idma32_disable; + dw->enable = idma32_enable; + + chip->dw = dw; + return do_dma_probe(chip); +} +EXPORT_SYMBOL_GPL(idma32_dma_probe); + +int idma32_dma_remove(struct dw_dma_chip *chip) +{ + return do_dma_remove(chip); +} +EXPORT_SYMBOL_GPL(idma32_dma_remove); diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h index 41439732ff6b..fdcac21ea665 100644 --- a/drivers/dma/dw/internal.h +++ b/drivers/dma/dw/internal.h @@ -15,8 +15,14 @@ #include "regs.h" -int dw_dma_disable(struct dw_dma_chip *chip); -int dw_dma_enable(struct dw_dma_chip *chip); +int do_dma_probe(struct dw_dma_chip *chip); +int do_dma_remove(struct dw_dma_chip *chip); + +void do_dw_dma_on(struct dw_dma *dw); +void do_dw_dma_off(struct dw_dma *dw); + +int do_dw_dma_disable(struct dw_dma_chip *chip); +int do_dw_dma_enable(struct dw_dma_chip *chip); extern bool dw_dma_filter(struct dma_chan *chan, void *param); diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index 66d98d7ccad0..e9ba25b4f950 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -15,9 +15,17 @@ #include "internal.h" -static struct dw_dma_platform_data mrfld_pdata = { +struct dw_dma_pci_data { + const struct dw_dma_platform_data *pdata; + int (*probe)(struct dw_dma_chip *chip); +}; + +static const struct dw_dma_pci_data dw_pci_data = { + .probe = dw_dma_probe, +}; + +static const struct dw_dma_platform_data idma32_pdata = { .nr_channels = 8, - .is_idma32 = true, .chan_allocation_order = CHAN_ALLOCATION_ASCENDING, .chan_priority = CHAN_PRIORITY_ASCENDING, .block_size = 131071, @@ -26,9 +34,14 @@ static struct dw_dma_platform_data mrfld_pdata = { .multi_block = {1, 1, 1, 1, 1, 1, 1, 1}, }; +static const struct dw_dma_pci_data idma32_pci_data = { + .pdata = &idma32_pdata, + .probe = idma32_dma_probe, +}; + static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid) { - const struct dw_dma_platform_data *pdata = (void *)pid->driver_data; + const struct dw_dma_pci_data *data = (void *)pid->driver_data; struct dw_dma_chip *chip; int ret; @@ -61,9 +74,9 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid) chip->id = pdev->devfn; chip->regs = pcim_iomap_table(pdev)[0]; chip->irq = pdev->irq; - chip->pdata = pdata; + chip->pdata = data->pdata; - ret = dw_dma_probe(chip); + ret = data->probe(chip); if (ret) return ret; @@ -89,7 +102,7 @@ static int dw_pci_suspend_late(struct device *dev) struct pci_dev *pci = to_pci_dev(dev); struct dw_dma_chip *chip = pci_get_drvdata(pci); - return dw_dma_disable(chip); + return do_dw_dma_disable(chip); }; static int dw_pci_resume_early(struct device *dev) @@ -97,7 +110,7 @@ static int dw_pci_resume_early(struct device *dev) struct pci_dev *pci = to_pci_dev(dev); struct dw_dma_chip *chip = pci_get_drvdata(pci); - return dw_dma_enable(chip); + return do_dw_dma_enable(chip); }; #endif /* CONFIG_PM_SLEEP */ @@ -108,24 +121,24 @@ static const struct dev_pm_ops dw_pci_dev_pm_ops = { static const struct pci_device_id dw_pci_id_table[] = { /* Medfield (GPDMA) */ - { PCI_VDEVICE(INTEL, 0x0827) }, + { PCI_VDEVICE(INTEL, 0x0827), (kernel_ulong_t)&dw_pci_data }, /* BayTrail */ - { PCI_VDEVICE(INTEL, 0x0f06) }, - { PCI_VDEVICE(INTEL, 0x0f40) }, + { PCI_VDEVICE(INTEL, 0x0f06), (kernel_ulong_t)&dw_pci_data }, + { PCI_VDEVICE(INTEL, 0x0f40), (kernel_ulong_t)&dw_pci_data }, - /* Merrifield iDMA 32-bit (GPDMA) */ - { PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&mrfld_pdata }, + /* Merrifield */ + { PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&idma32_pci_data }, /* Braswell */ - { PCI_VDEVICE(INTEL, 0x2286) }, - { PCI_VDEVICE(INTEL, 0x22c0) }, + { PCI_VDEVICE(INTEL, 0x2286), (kernel_ulong_t)&dw_pci_data }, + { PCI_VDEVICE(INTEL, 0x22c0), (kernel_ulong_t)&dw_pci_data }, /* Haswell */ - { PCI_VDEVICE(INTEL, 0x9c60) }, + { PCI_VDEVICE(INTEL, 0x9c60), (kernel_ulong_t)&dw_pci_data }, /* Broadwell */ - { PCI_VDEVICE(INTEL, 0x9ce0) }, + { PCI_VDEVICE(INTEL, 0x9ce0), (kernel_ulong_t)&dw_pci_data }, { } }; diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index 58fc1ba02a1e..d5196c97e4f4 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -255,7 +255,7 @@ static void dw_shutdown(struct platform_device *pdev) struct dw_dma_chip *chip = platform_get_drvdata(pdev); /* - * We have to call dw_dma_disable() to stop any ongoing transfer. On + * We have to call do_dw_dma_disable() to stop any ongoing transfer. On * some platforms we can't do that since DMA device is powered off. * Moreover we have no possibility to check if the platform is affected * or not. That's why we call pm_runtime_get_sync() / pm_runtime_put() @@ -264,7 +264,7 @@ static void dw_shutdown(struct platform_device *pdev) * used by the driver. */ pm_runtime_get_sync(chip->dev); - dw_dma_disable(chip); + do_dw_dma_disable(chip); pm_runtime_put_sync_suspend(chip->dev); clk_disable_unprepare(chip->clk); @@ -294,7 +294,7 @@ static int dw_suspend_late(struct device *dev) { struct dw_dma_chip *chip = dev_get_drvdata(dev); - dw_dma_disable(chip); + do_dw_dma_disable(chip); clk_disable_unprepare(chip->clk); return 0; @@ -309,7 +309,7 @@ static int dw_resume_early(struct device *dev) if (ret) return ret; - return dw_dma_enable(chip); + return do_dw_dma_enable(chip); } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h index 646c9c960c07..66aa8b227248 100644 --- a/drivers/dma/dw/regs.h +++ b/drivers/dma/dw/regs.h @@ -312,6 +312,19 @@ struct dw_dma { u8 all_chan_mask; u8 in_use; + /* Channel operations */ + void (*initialize_chan)(struct dw_dma_chan *dwc); + void (*suspend_chan)(struct dw_dma_chan *dwc, bool drain); + void (*encode_maxburst)(struct dw_dma_chan *dwc, u32 *maxburst); + u32 (*bytes2block)(struct dw_dma_chan *dwc, size_t bytes, + unsigned int width, size_t *len); + size_t (*block2bytes)(struct dw_dma_chan *dwc, u32 block, u32 width); + + /* Device operations */ + void (*set_device_name)(struct dw_dma *dw, int id); + void (*disable)(struct dw_dma *dw); + void (*enable)(struct dw_dma *dw); + /* platform data */ struct dw_dma_platform_data *pdata; }; diff --git a/include/linux/dma/dw.h b/include/linux/dma/dw.h index e166cac8e870..d643d331c20e 100644 --- a/include/linux/dma/dw.h +++ b/include/linux/dma/dw.h @@ -45,9 +45,13 @@ struct dw_dma_chip { #if IS_ENABLED(CONFIG_DW_DMAC_CORE) int dw_dma_probe(struct dw_dma_chip *chip); int dw_dma_remove(struct dw_dma_chip *chip); +int idma32_dma_probe(struct dw_dma_chip *chip); +int idma32_dma_remove(struct dw_dma_chip *chip); #else static inline int dw_dma_probe(struct dw_dma_chip *chip) { return -ENODEV; } static inline int dw_dma_remove(struct dw_dma_chip *chip) { return 0; } +static inline int idma32_dma_probe(struct dw_dma_chip *chip) { return -ENODEV; } +static inline int idma32_dma_remove(struct dw_dma_chip *chip) { return 0; } #endif /* CONFIG_DW_DMAC_CORE */ #endif /* _DMA_DW_H */ diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index 1c85eeee4171..576048433809 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -38,7 +38,6 @@ struct dw_dma_slave { /** * struct dw_dma_platform_data - Controller configuration parameters * @nr_channels: Number of channels supported by hardware (max 8) - * @is_idma32: The type of the DMA controller is iDMA32 * @chan_allocation_order: Allocate channels starting from 0 or 7 * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0. * @block_size: Maximum block size supported by the controller @@ -50,7 +49,6 @@ struct dw_dma_slave { */ struct dw_dma_platform_data { unsigned int nr_channels; - bool is_idma32; #define CHAN_ALLOCATION_ASCENDING 0 /* zero to seven */ #define CHAN_ALLOCATION_DESCENDING 1 /* seven to zero */ unsigned char chan_allocation_order; -- cgit v1.2.3 From b466a37fbcc99ef79ea59e40ef6aa8391430b0d8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 7 Jan 2019 13:07:41 +0200 Subject: dmaengine: dw: convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- drivers/dma/dw/Kconfig | 2 ++ drivers/dma/dw/core.c | 5 +---- drivers/dma/dw/internal.h | 5 +---- drivers/dma/dw/pci.c | 5 +---- drivers/dma/dw/platform.c | 5 +---- drivers/dma/dw/regs.h | 5 +---- include/linux/dma/dw.h | 5 +---- include/linux/platform_data/dma-dw.h | 5 +---- 8 files changed, 9 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig index 04b9728c1d26..e5162690de8f 100644 --- a/drivers/dma/dw/Kconfig +++ b/drivers/dma/dw/Kconfig @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + # # DMA engine configuration for dw # diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index b7e4dab28f8a..3a1ab52ffae0 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Core driver for the Synopsys DesignWare DMA Controller * * Copyright (C) 2007-2008 Atmel Corporation * Copyright (C) 2010-2011 ST Microelectronics * Copyright (C) 2013 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h index fdcac21ea665..1dd7a4e6dd23 100644 --- a/drivers/dma/dw/internal.h +++ b/drivers/dma/dw/internal.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Driver for the Synopsys DesignWare DMA Controller * * Copyright (C) 2013 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _DMA_DW_INTERNAL_H diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index e9ba25b4f950..e79a75db0852 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * PCI driver for the Synopsys DesignWare DMA Controller * * Copyright (C) 2013 Intel Corporation * Author: Andy Shevchenko - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index d5196c97e4f4..382dfd9e9600 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Platform driver for the Synopsys DesignWare DMA Controller * @@ -6,10 +7,6 @@ * Copyright (C) 2013 Intel Corporation * * Some parts of this driver are derived from the original dw_dmac. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h index 07f91325e559..3fce66ecee7a 100644 --- a/drivers/dma/dw/regs.h +++ b/drivers/dma/dw/regs.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Driver for the Synopsys DesignWare AHB DMA Controller * * Copyright (C) 2005-2007 Atmel Corporation * Copyright (C) 2010-2011 ST Microelectronics * Copyright (C) 2016 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/include/linux/dma/dw.h b/include/linux/dma/dw.h index d643d331c20e..9752f3745f76 100644 --- a/include/linux/dma/dw.h +++ b/include/linux/dma/dw.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Driver for the Synopsys DesignWare DMA Controller * * Copyright (C) 2007 Atmel Corporation * Copyright (C) 2010-2011 ST Microelectronics * Copyright (C) 2014 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _DMA_DW_H #define _DMA_DW_H diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index 576048433809..f3eaf9ec00a1 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Driver for the Synopsys DesignWare DMA Controller * * Copyright (C) 2007 Atmel Corporation * Copyright (C) 2010-2011 ST Microelectronics - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _PLATFORM_DATA_DMA_DW_H #define _PLATFORM_DATA_DMA_DW_H -- cgit v1.2.3 From 83d0ea237bac5fb6a7509c69a8939e999693d311 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Fri, 21 Dec 2018 17:02:35 +0100 Subject: dt-bindings: clk: meson: add ao slow clock path ids Add the CLKIDs for the slow clock generation path Reviewed-by: Rob Herring Signed-off-by: Jerome Brunet Acked-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://lkml.kernel.org/r/20181221160239.26265-2-jbrunet@baylibre.com --- include/dt-bindings/clock/axg-aoclkc.h | 7 ++++++- include/dt-bindings/clock/gxbb-aoclkc.h | 7 +++++++ 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/axg-aoclkc.h b/include/dt-bindings/clock/axg-aoclkc.h index 61955016a55b..8ec4a269c7a6 100644 --- a/include/dt-bindings/clock/axg-aoclkc.h +++ b/include/dt-bindings/clock/axg-aoclkc.h @@ -21,6 +21,11 @@ #define CLKID_AO_SAR_ADC_SEL 8 #define CLKID_AO_SAR_ADC_DIV 9 #define CLKID_AO_SAR_ADC_CLK 10 -#define CLKID_AO_ALT_XTAL 11 +#define CLKID_AO_CTS_OSCIN 11 +#define CLKID_AO_32K_PRE 12 +#define CLKID_AO_32K_DIV 13 +#define CLKID_AO_32K_SEL 14 +#define CLKID_AO_32K 15 +#define CLKID_AO_CTS_RTC_OSCIN 16 #endif diff --git a/include/dt-bindings/clock/gxbb-aoclkc.h b/include/dt-bindings/clock/gxbb-aoclkc.h index 9d15e2221fdb..ec3b26319fc4 100644 --- a/include/dt-bindings/clock/gxbb-aoclkc.h +++ b/include/dt-bindings/clock/gxbb-aoclkc.h @@ -63,5 +63,12 @@ #define CLKID_AO_UART2 4 #define CLKID_AO_IR_BLASTER 5 #define CLKID_AO_CEC_32K 6 +#define CLKID_AO_CTS_OSCIN 7 +#define CLKID_AO_32K_PRE 8 +#define CLKID_AO_32K_DIV 9 +#define CLKID_AO_32K_SEL 10 +#define CLKID_AO_32K 11 +#define CLKID_AO_CTS_RTC_OSCIN 12 +#define CLKID_AO_CLK81 13 #endif -- cgit v1.2.3 From e2d8ffe2e76028457759988ba6216fd13eeea01b Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 13 Nov 2018 03:52:18 -0500 Subject: media: v4l2-mem2mem: add v4l2_m2m_buf_copy_data helper function Memory-to-memory devices should copy various parts of struct v4l2_buffer from the output buffer to the capture buffer. Add a helper function that does that to simplify the driver code. Signed-off-by: Hans Verkuil Reviewed-by: Paul Kocialkowski Reviewed-by: Alexandre Courbot Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-mem2mem.c | 20 ++++++++++++++++++++ include/media/v4l2-mem2mem.h | 20 ++++++++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 5bbdec55b7d7..631f4e2aa942 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -975,6 +975,26 @@ void v4l2_m2m_buf_queue(struct v4l2_m2m_ctx *m2m_ctx, } EXPORT_SYMBOL_GPL(v4l2_m2m_buf_queue); +void v4l2_m2m_buf_copy_data(const struct vb2_v4l2_buffer *out_vb, + struct vb2_v4l2_buffer *cap_vb, + bool copy_frame_flags) +{ + u32 mask = V4L2_BUF_FLAG_TIMECODE | V4L2_BUF_FLAG_TSTAMP_SRC_MASK; + + if (copy_frame_flags) + mask |= V4L2_BUF_FLAG_KEYFRAME | V4L2_BUF_FLAG_PFRAME | + V4L2_BUF_FLAG_BFRAME; + + cap_vb->vb2_buf.timestamp = out_vb->vb2_buf.timestamp; + + if (out_vb->flags & V4L2_BUF_FLAG_TIMECODE) + cap_vb->timecode = out_vb->timecode; + cap_vb->field = out_vb->field; + cap_vb->flags &= ~mask; + cap_vb->flags |= out_vb->flags & mask; +} +EXPORT_SYMBOL_GPL(v4l2_m2m_buf_copy_data); + void v4l2_m2m_request_queue(struct media_request *req) { struct media_request_object *obj, *obj_safe; diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h index 5467264771ec..43e447dcf69d 100644 --- a/include/media/v4l2-mem2mem.h +++ b/include/media/v4l2-mem2mem.h @@ -622,6 +622,26 @@ v4l2_m2m_dst_buf_remove_by_idx(struct v4l2_m2m_ctx *m2m_ctx, unsigned int idx) return v4l2_m2m_buf_remove_by_idx(&m2m_ctx->cap_q_ctx, idx); } +/** + * v4l2_m2m_buf_copy_data() - copy buffer data from the output buffer to the + * capture buffer + * + * @out_vb: the output buffer that is the source of the data. + * @cap_vb: the capture buffer that will receive the data. + * @copy_frame_flags: copy the KEY/B/PFRAME flags as well. + * + * This helper function copies the timestamp, timecode (if the TIMECODE + * buffer flag was set), field and the TIMECODE, KEYFRAME, BFRAME, PFRAME + * and TSTAMP_SRC_MASK flags from @out_vb to @cap_vb. + * + * If @copy_frame_flags is false, then the KEYFRAME, BFRAME and PFRAME + * flags are not copied. This is typically needed for encoders that + * set this bits explicitly. + */ +void v4l2_m2m_buf_copy_data(const struct vb2_v4l2_buffer *out_vb, + struct vb2_v4l2_buffer *cap_vb, + bool copy_frame_flags); + /* v4l2 request helper */ void v4l2_m2m_request_queue(struct media_request *req); -- cgit v1.2.3 From c2eb8effb265ac5cdd960d8e61ecb931e9c767cd Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 24 Oct 2018 06:50:34 -0400 Subject: media: videodev2.h: add v4l2_timeval_to_ns inline function We want to be able to uniquely identify buffers for stateless codecs. The internal timestamp (a u64) as stored internally in the kernel is a suitable candidate for that, but in struct v4l2_buffer it is represented as a struct timeval. Add a v4l2_timeval_to_ns() function that converts the struct timeval into a u64 in the same way that the kernel does. This makes it possible to use this u64 elsewhere as a unique identifier of the buffer. Since timestamps are also copied from the output buffer to the corresponding capture buffer(s) by M2M devices, the u64 can be used to refer to both output and capture buffers. The plan is that in the future we redesign struct v4l2_buffer and use u64 for the timestamp instead of a struct timeval (which has lots of problems with 32 vs 64 bit and y2038 layout changes), and then there is no more need to use this function. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index b5671ce2724f..d6eed479c3a6 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -973,6 +973,18 @@ struct v4l2_buffer { }; }; +/** + * v4l2_timeval_to_ns - Convert timeval to nanoseconds + * @ts: pointer to the timeval variable to be converted + * + * Returns the scalar nanosecond representation of the timeval + * parameter. + */ +static inline __u64 v4l2_timeval_to_ns(const struct timeval *tv) +{ + return (__u64)tv->tv_sec * 1000000000ULL + tv->tv_usec * 1000; +} + /* Flags for 'flags' field */ /* Buffer is mapped (flag) */ #define V4L2_BUF_FLAG_MAPPED 0x00000001 -- cgit v1.2.3 From 245ede423b43a6e081e94e0e5d4e895bd1f31228 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 24 Oct 2018 06:51:01 -0400 Subject: media: vb2: add vb2_find_timestamp() Use v4l2_timeval_to_ns instead of timeval_to_ns to ensure that both kernelspace and userspace will use the same conversion function. Next add a new vb2_find_timestamp() function to find buffers with a specific timestamp. This function will only look at DEQUEUED and DONE buffers, i.e. buffers that are already processed. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-v4l2.c | 19 ++++++++++++++++++- include/media/videobuf2-v4l2.h | 17 +++++++++++++++++ 2 files changed, 35 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index 3a0ca2f9854f..75ea90e795d8 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -143,7 +143,7 @@ static void __copy_timestamp(struct vb2_buffer *vb, const void *pb) * and the timecode field and flag if needed. */ if (q->copy_timestamp) - vb->timestamp = timeval_to_ns(&b->timestamp); + vb->timestamp = v4l2_timeval_to_ns(&b->timestamp); vbuf->flags |= b->flags & V4L2_BUF_FLAG_TIMECODE; if (b->flags & V4L2_BUF_FLAG_TIMECODE) vbuf->timecode = b->timecode; @@ -589,6 +589,23 @@ static const struct vb2_buf_ops v4l2_buf_ops = { .copy_timestamp = __copy_timestamp, }; +int vb2_find_timestamp(const struct vb2_queue *q, u64 timestamp, + unsigned int start_idx) +{ + unsigned int i; + + for (i = start_idx; i < q->num_buffers; i++) { + struct vb2_buffer *vb = q->bufs[i]; + + if ((vb->state == VB2_BUF_STATE_DEQUEUED || + vb->state == VB2_BUF_STATE_DONE) && + vb->timestamp == timestamp) + return i; + } + return -1; +} +EXPORT_SYMBOL_GPL(vb2_find_timestamp); + /* * vb2_querybuf() - query video buffer information * @q: videobuf queue diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h index 727855463838..a9961bc776dc 100644 --- a/include/media/videobuf2-v4l2.h +++ b/include/media/videobuf2-v4l2.h @@ -55,6 +55,23 @@ struct vb2_v4l2_buffer { #define to_vb2_v4l2_buffer(vb) \ container_of(vb, struct vb2_v4l2_buffer, vb2_buf) +/** + * vb2_find_timestamp() - Find buffer with given timestamp in the queue + * + * @q: pointer to &struct vb2_queue with videobuf2 queue. + * @timestamp: the timestamp to find. Only buffers in state DEQUEUED or DONE + * are considered. + * @start_idx: the start index (usually 0) in the buffer array to start + * searching from. Note that there may be multiple buffers + * with the same timestamp value, so you can restart the search + * by setting @start_idx to the previously found index + 1. + * + * Returns the buffer index of the buffer with the given @timestamp, or + * -1 if no buffer with @timestamp was found. + */ +int vb2_find_timestamp(const struct vb2_queue *q, u64 timestamp, + unsigned int start_idx); + int vb2_querybuf(struct vb2_queue *q, struct v4l2_buffer *b); /** -- cgit v1.2.3 From d998e03e322fc497454f584adfc35743713a44c5 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 9 Nov 2018 04:16:21 -0500 Subject: media: cedrus: identify buffers by timestamp Use the new v4l2_m2m_buf_copy_data helper function and use timestamps to refer to reference frames instead of using buffer indices. Also remove the padding fields in the structs, that's a bad idea. Just use the right types to keep everything aligned. Signed-off-by: Hans Verkuil Tested-by: Paul Kocialkowski Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ctrls.c | 9 --------- drivers/staging/media/sunxi/cedrus/cedrus.h | 9 ++++++--- drivers/staging/media/sunxi/cedrus/cedrus_dec.c | 2 ++ drivers/staging/media/sunxi/cedrus/cedrus_mpeg2.c | 23 +++++++++++------------ include/media/mpeg2-ctrls.h | 14 +++++--------- 5 files changed, 24 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 5e3806feb5d7..e3bd441fa29a 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -1661,15 +1661,6 @@ static int std_validate(const struct v4l2_ctrl *ctrl, u32 idx, return -EINVAL; } - if (p_mpeg2_slice_params->backward_ref_index >= VIDEO_MAX_FRAME || - p_mpeg2_slice_params->forward_ref_index >= VIDEO_MAX_FRAME) - return -EINVAL; - - if (p_mpeg2_slice_params->pad || - p_mpeg2_slice_params->picture.pad || - p_mpeg2_slice_params->sequence.pad) - return -EINVAL; - return 0; case V4L2_CTRL_TYPE_MPEG2_QUANTIZATION: diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.h b/drivers/staging/media/sunxi/cedrus/cedrus.h index 3acfdcf83691..4aedd24a9848 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.h +++ b/drivers/staging/media/sunxi/cedrus/cedrus.h @@ -140,11 +140,14 @@ static inline dma_addr_t cedrus_buf_addr(struct vb2_buffer *buf, } static inline dma_addr_t cedrus_dst_buf_addr(struct cedrus_ctx *ctx, - unsigned int index, - unsigned int plane) + int index, unsigned int plane) { - struct vb2_buffer *buf = ctx->dst_bufs[index]; + struct vb2_buffer *buf; + if (index < 0) + return 0; + + buf = ctx->dst_bufs[index]; return buf ? cedrus_buf_addr(buf, &ctx->dst_fmt, plane) : 0; } diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c index 591d191d4286..443fb037e1cf 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c @@ -50,6 +50,8 @@ void cedrus_device_run(void *priv) break; } + v4l2_m2m_buf_copy_data(run.src, run.dst, true); + dev->dec_ops[ctx->current_codec]->setup(ctx, &run); /* Complete request(s) controls if needed. */ diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_mpeg2.c b/drivers/staging/media/sunxi/cedrus/cedrus_mpeg2.c index 9abd39cae38c..cb45fda9aaeb 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_mpeg2.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_mpeg2.c @@ -82,7 +82,10 @@ static void cedrus_mpeg2_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) dma_addr_t fwd_luma_addr, fwd_chroma_addr; dma_addr_t bwd_luma_addr, bwd_chroma_addr; struct cedrus_dev *dev = ctx->dev; + struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q; const u8 *matrix; + int forward_idx; + int backward_idx; unsigned int i; u32 reg; @@ -156,23 +159,19 @@ static void cedrus_mpeg2_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) cedrus_write(dev, VE_DEC_MPEG_PICBOUNDSIZE, reg); /* Forward and backward prediction reference buffers. */ + forward_idx = vb2_find_timestamp(cap_q, + slice_params->forward_ref_ts, 0); - fwd_luma_addr = cedrus_dst_buf_addr(ctx, - slice_params->forward_ref_index, - 0); - fwd_chroma_addr = cedrus_dst_buf_addr(ctx, - slice_params->forward_ref_index, - 1); + fwd_luma_addr = cedrus_dst_buf_addr(ctx, forward_idx, 0); + fwd_chroma_addr = cedrus_dst_buf_addr(ctx, forward_idx, 1); cedrus_write(dev, VE_DEC_MPEG_FWD_REF_LUMA_ADDR, fwd_luma_addr); cedrus_write(dev, VE_DEC_MPEG_FWD_REF_CHROMA_ADDR, fwd_chroma_addr); - bwd_luma_addr = cedrus_dst_buf_addr(ctx, - slice_params->backward_ref_index, - 0); - bwd_chroma_addr = cedrus_dst_buf_addr(ctx, - slice_params->backward_ref_index, - 1); + backward_idx = vb2_find_timestamp(cap_q, + slice_params->backward_ref_ts, 0); + bwd_luma_addr = cedrus_dst_buf_addr(ctx, backward_idx, 0); + bwd_chroma_addr = cedrus_dst_buf_addr(ctx, backward_idx, 1); cedrus_write(dev, VE_DEC_MPEG_BWD_REF_LUMA_ADDR, bwd_luma_addr); cedrus_write(dev, VE_DEC_MPEG_BWD_REF_CHROMA_ADDR, bwd_chroma_addr); diff --git a/include/media/mpeg2-ctrls.h b/include/media/mpeg2-ctrls.h index d21f40edc09e..6601455b3d5e 100644 --- a/include/media/mpeg2-ctrls.h +++ b/include/media/mpeg2-ctrls.h @@ -30,10 +30,9 @@ struct v4l2_mpeg2_sequence { __u32 vbv_buffer_size; /* ISO/IEC 13818-2, ITU-T Rec. H.262: Sequence extension */ - __u8 profile_and_level_indication; + __u16 profile_and_level_indication; __u8 progressive_sequence; __u8 chroma_format; - __u8 pad; }; struct v4l2_mpeg2_picture { @@ -51,23 +50,20 @@ struct v4l2_mpeg2_picture { __u8 intra_vlc_format; __u8 alternate_scan; __u8 repeat_first_field; - __u8 progressive_frame; - __u8 pad; + __u16 progressive_frame; }; struct v4l2_ctrl_mpeg2_slice_params { __u32 bit_size; __u32 data_bit_offset; + __u64 backward_ref_ts; + __u64 forward_ref_ts; struct v4l2_mpeg2_sequence sequence; struct v4l2_mpeg2_picture picture; /* ISO/IEC 13818-2, ITU-T Rec. H.262: Slice */ - __u8 quantiser_scale_code; - - __u8 backward_ref_index; - __u8 forward_ref_index; - __u8 pad; + __u32 quantiser_scale_code; }; struct v4l2_ctrl_mpeg2_quantization { -- cgit v1.2.3 From 983f6ae944c273c3a64e30f451b60d40398afc8a Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 21 Dec 2018 11:35:35 +0100 Subject: spi/trace: drop useless and wrong (but harmless) casts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit bus_num, chip_select and len are already ints, so there is no gain in casting them to int. xfer is a pointer to a struct spi_transfer. Casting that to struct spi_message * is wrong but as only the pointer value is used for the %p format specifier no harm is done. Signed-off-by: Uwe Kleine-König Signed-off-by: Mark Brown --- include/trace/events/spi.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/spi.h b/include/trace/events/spi.h index 277bb9d25779..6eb014f59efb 100644 --- a/include/trace/events/spi.h +++ b/include/trace/events/spi.h @@ -129,10 +129,9 @@ DECLARE_EVENT_CLASS(spi_transfer, __entry->len = xfer->len; ), - TP_printk("spi%d.%d %p len=%d", (int)__entry->bus_num, - (int)__entry->chip_select, - (struct spi_message *)__entry->xfer, - (int)__entry->len) + TP_printk("spi%d.%d %p len=%d", + __entry->bus_num, __entry->chip_select, + __entry->xfer, __entry->len) ); DEFINE_EVENT(spi_transfer, spi_transfer_start, -- cgit v1.2.3 From 8d245475c3f6e82d4685d5d9fd7b95ea118a7e25 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 21 Dec 2018 11:35:36 +0100 Subject: spi/trace: include buffer contents in traces MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It highly improves usability when the buffer contents are inspecable via tracing. Signed-off-by: Uwe Kleine-König Signed-off-by: Mark Brown --- include/trace/events/spi.h | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/spi.h b/include/trace/events/spi.h index 6eb014f59efb..aef6869f563d 100644 --- a/include/trace/events/spi.h +++ b/include/trace/events/spi.h @@ -109,6 +109,16 @@ TRACE_EVENT(spi_message_done, (unsigned)__entry->actual, (unsigned)__entry->frame) ); +/* + * consider a buffer valid if non-NULL and if it doesn't match the dummy buffer + * that only exist to work with controllers that have SPI_CONTROLLER_MUST_TX or + * SPI_CONTROLLER_MUST_RX. + */ +#define spi_valid_txbuf(msg, xfer) \ + (xfer->tx_buf && xfer->tx_buf != msg->spi->controller->dummy_tx) +#define spi_valid_rxbuf(msg, xfer) \ + (xfer->rx_buf && xfer->rx_buf != msg->spi->controller->dummy_rx) + DECLARE_EVENT_CLASS(spi_transfer, TP_PROTO(struct spi_message *msg, struct spi_transfer *xfer), @@ -120,6 +130,10 @@ DECLARE_EVENT_CLASS(spi_transfer, __field( int, chip_select ) __field( struct spi_transfer *, xfer ) __field( int, len ) + __dynamic_array(u8, rx_buf, + spi_valid_rxbuf(msg, xfer) ? xfer->len : 0) + __dynamic_array(u8, tx_buf, + spi_valid_txbuf(msg, xfer) ? xfer->len : 0) ), TP_fast_assign( @@ -127,11 +141,21 @@ DECLARE_EVENT_CLASS(spi_transfer, __entry->chip_select = msg->spi->chip_select; __entry->xfer = xfer; __entry->len = xfer->len; + + if (spi_valid_txbuf(msg, xfer)) + memcpy(__get_dynamic_array(tx_buf), + xfer->tx_buf, xfer->len); + + if (spi_valid_rxbuf(msg, xfer)) + memcpy(__get_dynamic_array(rx_buf), + xfer->rx_buf, xfer->len); ), - TP_printk("spi%d.%d %p len=%d", + TP_printk("spi%d.%d %p len=%d tx=[%*phD] rx=[%*phD]", __entry->bus_num, __entry->chip_select, - __entry->xfer, __entry->len) + __entry->xfer, __entry->len, + __get_dynamic_array_len(tx_buf), __get_dynamic_array(tx_buf), + __get_dynamic_array_len(rx_buf), __get_dynamic_array(rx_buf)) ); DEFINE_EVENT(spi_transfer, spi_transfer_start, -- cgit v1.2.3 From d0dcde6426ce071ad447fb9d91c85ab649026114 Mon Sep 17 00:00:00 2001 From: Otto Sabart Date: Sun, 6 Jan 2019 00:29:15 +0100 Subject: doc: networking: convert offload files into RST and update references This patch renames offload files. This is necessary for Sphinx. Also update reference to checksum-offloads.rst file. Whole kernel code was grepped for references using: $ grep -r "\(segmentation\|checksum\)-offloads.txt" . There should be no other references to {segmentation,checksum}-offloads.txt files. Signed-off-by: Otto Sabart Acked-by: David S. Miller Signed-off-by: Jonathan Corbet --- Documentation/networking/checksum-offloads.rst | 143 ++++++++++++++++ Documentation/networking/checksum-offloads.txt | 143 ---------------- Documentation/networking/segmentation-offloads.rst | 184 +++++++++++++++++++++ Documentation/networking/segmentation-offloads.txt | 184 --------------------- include/linux/skbuff.h | 2 +- 5 files changed, 328 insertions(+), 328 deletions(-) create mode 100644 Documentation/networking/checksum-offloads.rst delete mode 100644 Documentation/networking/checksum-offloads.txt create mode 100644 Documentation/networking/segmentation-offloads.rst delete mode 100644 Documentation/networking/segmentation-offloads.txt (limited to 'include') diff --git a/Documentation/networking/checksum-offloads.rst b/Documentation/networking/checksum-offloads.rst new file mode 100644 index 000000000000..1a1cd94a3f6d --- /dev/null +++ b/Documentation/networking/checksum-offloads.rst @@ -0,0 +1,143 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============================================== +Checksum Offloads in the Linux Networking Stack +=============================================== + + +Introduction +============ + +This document describes a set of techniques in the Linux networking stack to +take advantage of checksum offload capabilities of various NICs. + +The following technologies are described: + +* TX Checksum Offload +* LCO: Local Checksum Offload +* RCO: Remote Checksum Offload + +Things that should be documented here but aren't yet: + +* RX Checksum Offload +* CHECKSUM_UNNECESSARY conversion + + +TX Checksum Offload +=================== + +The interface for offloading a transmit checksum to a device is explained in +detail in comments near the top of include/linux/skbuff.h. + +In brief, it allows to request the device fill in a single ones-complement +checksum defined by the sk_buff fields skb->csum_start and skb->csum_offset. +The device should compute the 16-bit ones-complement checksum (i.e. the +'IP-style' checksum) from csum_start to the end of the packet, and fill in the +result at (csum_start + csum_offset). + +Because csum_offset cannot be negative, this ensures that the previous value of +the checksum field is included in the checksum computation, thus it can be used +to supply any needed corrections to the checksum (such as the sum of the +pseudo-header for UDP or TCP). + +This interface only allows a single checksum to be offloaded. Where +encapsulation is used, the packet may have multiple checksum fields in +different header layers, and the rest will have to be handled by another +mechanism such as LCO or RCO. + +CRC32c can also be offloaded using this interface, by means of filling +skb->csum_start and skb->csum_offset as described above, and setting +skb->csum_not_inet: see skbuff.h comment (section 'D') for more details. + +No offloading of the IP header checksum is performed; it is always done in +software. This is OK because when we build the IP header, we obviously have it +in cache, so summing it isn't expensive. It's also rather short. + +The requirements for GSO are more complicated, because when segmenting an +encapsulated packet both the inner and outer checksums may need to be edited or +recomputed for each resulting segment. See the skbuff.h comment (section 'E') +for more details. + +A driver declares its offload capabilities in netdev->hw_features; see +Documentation/networking/netdev-features.txt for more. Note that a device +which only advertises NETIF_F_IP[V6]_CSUM must still obey the csum_start and +csum_offset given in the SKB; if it tries to deduce these itself in hardware +(as some NICs do) the driver should check that the values in the SKB match +those which the hardware will deduce, and if not, fall back to checksumming in +software instead (with skb_csum_hwoffload_help() or one of the +skb_checksum_help() / skb_crc32c_csum_help functions, as mentioned in +include/linux/skbuff.h). + +The stack should, for the most part, assume that checksum offload is supported +by the underlying device. The only place that should check is +validate_xmit_skb(), and the functions it calls directly or indirectly. That +function compares the offload features requested by the SKB (which may include +other offloads besides TX Checksum Offload) and, if they are not supported or +enabled on the device (determined by netdev->features), performs the +corresponding offload in software. In the case of TX Checksum Offload, that +means calling skb_csum_hwoffload_help(skb, features). + + +LCO: Local Checksum Offload +=========================== + +LCO is a technique for efficiently computing the outer checksum of an +encapsulated datagram when the inner checksum is due to be offloaded. + +The ones-complement sum of a correctly checksummed TCP or UDP packet is equal +to the complement of the sum of the pseudo header, because everything else gets +'cancelled out' by the checksum field. This is because the sum was +complemented before being written to the checksum field. + +More generally, this holds in any case where the 'IP-style' ones complement +checksum is used, and thus any checksum that TX Checksum Offload supports. + +That is, if we have set up TX Checksum Offload with a start/offset pair, we +know that after the device has filled in that checksum, the ones complement sum +from csum_start to the end of the packet will be equal to the complement of +whatever value we put in the checksum field beforehand. This allows us to +compute the outer checksum without looking at the payload: we simply stop +summing when we get to csum_start, then add the complement of the 16-bit word +at (csum_start + csum_offset). + +Then, when the true inner checksum is filled in (either by hardware or by +skb_checksum_help()), the outer checksum will become correct by virtue of the +arithmetic. + +LCO is performed by the stack when constructing an outer UDP header for an +encapsulation such as VXLAN or GENEVE, in udp_set_csum(). Similarly for the +IPv6 equivalents, in udp6_set_csum(). + +It is also performed when constructing an IPv4 GRE header, in +net/ipv4/ip_gre.c:build_header(). It is *not* currently performed when +constructing an IPv6 GRE header; the GRE checksum is computed over the whole +packet in net/ipv6/ip6_gre.c:ip6gre_xmit2(), but it should be possible to use +LCO here as IPv6 GRE still uses an IP-style checksum. + +All of the LCO implementations use a helper function lco_csum(), in +include/linux/skbuff.h. + +LCO can safely be used for nested encapsulations; in this case, the outer +encapsulation layer will sum over both its own header and the 'middle' header. +This does mean that the 'middle' header will get summed multiple times, but +there doesn't seem to be a way to avoid that without incurring bigger costs +(e.g. in SKB bloat). + + +RCO: Remote Checksum Offload +============================ + +RCO is a technique for eliding the inner checksum of an encapsulated datagram, +allowing the outer checksum to be offloaded. It does, however, involve a +change to the encapsulation protocols, which the receiver must also support. +For this reason, it is disabled by default. + +RCO is detailed in the following Internet-Drafts: + +* https://tools.ietf.org/html/draft-herbert-remotecsumoffload-00 +* https://tools.ietf.org/html/draft-herbert-vxlan-rco-00 + +In Linux, RCO is implemented individually in each encapsulation protocol, and +most tunnel types have flags controlling its use. For instance, VXLAN has the +flag VXLAN_F_REMCSUM_TX (per struct vxlan_rdst) to indicate that RCO should be +used when transmitting to a given remote destination. diff --git a/Documentation/networking/checksum-offloads.txt b/Documentation/networking/checksum-offloads.txt deleted file mode 100644 index 1a1cd94a3f6d..000000000000 --- a/Documentation/networking/checksum-offloads.txt +++ /dev/null @@ -1,143 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -=============================================== -Checksum Offloads in the Linux Networking Stack -=============================================== - - -Introduction -============ - -This document describes a set of techniques in the Linux networking stack to -take advantage of checksum offload capabilities of various NICs. - -The following technologies are described: - -* TX Checksum Offload -* LCO: Local Checksum Offload -* RCO: Remote Checksum Offload - -Things that should be documented here but aren't yet: - -* RX Checksum Offload -* CHECKSUM_UNNECESSARY conversion - - -TX Checksum Offload -=================== - -The interface for offloading a transmit checksum to a device is explained in -detail in comments near the top of include/linux/skbuff.h. - -In brief, it allows to request the device fill in a single ones-complement -checksum defined by the sk_buff fields skb->csum_start and skb->csum_offset. -The device should compute the 16-bit ones-complement checksum (i.e. the -'IP-style' checksum) from csum_start to the end of the packet, and fill in the -result at (csum_start + csum_offset). - -Because csum_offset cannot be negative, this ensures that the previous value of -the checksum field is included in the checksum computation, thus it can be used -to supply any needed corrections to the checksum (such as the sum of the -pseudo-header for UDP or TCP). - -This interface only allows a single checksum to be offloaded. Where -encapsulation is used, the packet may have multiple checksum fields in -different header layers, and the rest will have to be handled by another -mechanism such as LCO or RCO. - -CRC32c can also be offloaded using this interface, by means of filling -skb->csum_start and skb->csum_offset as described above, and setting -skb->csum_not_inet: see skbuff.h comment (section 'D') for more details. - -No offloading of the IP header checksum is performed; it is always done in -software. This is OK because when we build the IP header, we obviously have it -in cache, so summing it isn't expensive. It's also rather short. - -The requirements for GSO are more complicated, because when segmenting an -encapsulated packet both the inner and outer checksums may need to be edited or -recomputed for each resulting segment. See the skbuff.h comment (section 'E') -for more details. - -A driver declares its offload capabilities in netdev->hw_features; see -Documentation/networking/netdev-features.txt for more. Note that a device -which only advertises NETIF_F_IP[V6]_CSUM must still obey the csum_start and -csum_offset given in the SKB; if it tries to deduce these itself in hardware -(as some NICs do) the driver should check that the values in the SKB match -those which the hardware will deduce, and if not, fall back to checksumming in -software instead (with skb_csum_hwoffload_help() or one of the -skb_checksum_help() / skb_crc32c_csum_help functions, as mentioned in -include/linux/skbuff.h). - -The stack should, for the most part, assume that checksum offload is supported -by the underlying device. The only place that should check is -validate_xmit_skb(), and the functions it calls directly or indirectly. That -function compares the offload features requested by the SKB (which may include -other offloads besides TX Checksum Offload) and, if they are not supported or -enabled on the device (determined by netdev->features), performs the -corresponding offload in software. In the case of TX Checksum Offload, that -means calling skb_csum_hwoffload_help(skb, features). - - -LCO: Local Checksum Offload -=========================== - -LCO is a technique for efficiently computing the outer checksum of an -encapsulated datagram when the inner checksum is due to be offloaded. - -The ones-complement sum of a correctly checksummed TCP or UDP packet is equal -to the complement of the sum of the pseudo header, because everything else gets -'cancelled out' by the checksum field. This is because the sum was -complemented before being written to the checksum field. - -More generally, this holds in any case where the 'IP-style' ones complement -checksum is used, and thus any checksum that TX Checksum Offload supports. - -That is, if we have set up TX Checksum Offload with a start/offset pair, we -know that after the device has filled in that checksum, the ones complement sum -from csum_start to the end of the packet will be equal to the complement of -whatever value we put in the checksum field beforehand. This allows us to -compute the outer checksum without looking at the payload: we simply stop -summing when we get to csum_start, then add the complement of the 16-bit word -at (csum_start + csum_offset). - -Then, when the true inner checksum is filled in (either by hardware or by -skb_checksum_help()), the outer checksum will become correct by virtue of the -arithmetic. - -LCO is performed by the stack when constructing an outer UDP header for an -encapsulation such as VXLAN or GENEVE, in udp_set_csum(). Similarly for the -IPv6 equivalents, in udp6_set_csum(). - -It is also performed when constructing an IPv4 GRE header, in -net/ipv4/ip_gre.c:build_header(). It is *not* currently performed when -constructing an IPv6 GRE header; the GRE checksum is computed over the whole -packet in net/ipv6/ip6_gre.c:ip6gre_xmit2(), but it should be possible to use -LCO here as IPv6 GRE still uses an IP-style checksum. - -All of the LCO implementations use a helper function lco_csum(), in -include/linux/skbuff.h. - -LCO can safely be used for nested encapsulations; in this case, the outer -encapsulation layer will sum over both its own header and the 'middle' header. -This does mean that the 'middle' header will get summed multiple times, but -there doesn't seem to be a way to avoid that without incurring bigger costs -(e.g. in SKB bloat). - - -RCO: Remote Checksum Offload -============================ - -RCO is a technique for eliding the inner checksum of an encapsulated datagram, -allowing the outer checksum to be offloaded. It does, however, involve a -change to the encapsulation protocols, which the receiver must also support. -For this reason, it is disabled by default. - -RCO is detailed in the following Internet-Drafts: - -* https://tools.ietf.org/html/draft-herbert-remotecsumoffload-00 -* https://tools.ietf.org/html/draft-herbert-vxlan-rco-00 - -In Linux, RCO is implemented individually in each encapsulation protocol, and -most tunnel types have flags controlling its use. For instance, VXLAN has the -flag VXLAN_F_REMCSUM_TX (per struct vxlan_rdst) to indicate that RCO should be -used when transmitting to a given remote destination. diff --git a/Documentation/networking/segmentation-offloads.rst b/Documentation/networking/segmentation-offloads.rst new file mode 100644 index 000000000000..1794bfe98196 --- /dev/null +++ b/Documentation/networking/segmentation-offloads.rst @@ -0,0 +1,184 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================================================== +Segmentation Offloads in the Linux Networking Stack +=================================================== + + +Introduction +============ + +This document describes a set of techniques in the Linux networking stack +to take advantage of segmentation offload capabilities of various NICs. + +The following technologies are described: + * TCP Segmentation Offload - TSO + * UDP Fragmentation Offload - UFO + * IPIP, SIT, GRE, and UDP Tunnel Offloads + * Generic Segmentation Offload - GSO + * Generic Receive Offload - GRO + * Partial Generic Segmentation Offload - GSO_PARTIAL + * SCTP accelleration with GSO - GSO_BY_FRAGS + + +TCP Segmentation Offload +======================== + +TCP segmentation allows a device to segment a single frame into multiple +frames with a data payload size specified in skb_shinfo()->gso_size. +When TCP segmentation requested the bit for either SKB_GSO_TCPV4 or +SKB_GSO_TCPV6 should be set in skb_shinfo()->gso_type and +skb_shinfo()->gso_size should be set to a non-zero value. + +TCP segmentation is dependent on support for the use of partial checksum +offload. For this reason TSO is normally disabled if the Tx checksum +offload for a given device is disabled. + +In order to support TCP segmentation offload it is necessary to populate +the network and transport header offsets of the skbuff so that the device +drivers will be able determine the offsets of the IP or IPv6 header and the +TCP header. In addition as CHECKSUM_PARTIAL is required csum_start should +also point to the TCP header of the packet. + +For IPv4 segmentation we support one of two types in terms of the IP ID. +The default behavior is to increment the IP ID with every segment. If the +GSO type SKB_GSO_TCP_FIXEDID is specified then we will not increment the IP +ID and all segments will use the same IP ID. If a device has +NETIF_F_TSO_MANGLEID set then the IP ID can be ignored when performing TSO +and we will either increment the IP ID for all frames, or leave it at a +static value based on driver preference. + + +UDP Fragmentation Offload +========================= + +UDP fragmentation offload allows a device to fragment an oversized UDP +datagram into multiple IPv4 fragments. Many of the requirements for UDP +fragmentation offload are the same as TSO. However the IPv4 ID for +fragments should not increment as a single IPv4 datagram is fragmented. + +UFO is deprecated: modern kernels will no longer generate UFO skbs, but can +still receive them from tuntap and similar devices. Offload of UDP-based +tunnel protocols is still supported. + + +IPIP, SIT, GRE, UDP Tunnel, and Remote Checksum Offloads +======================================================== + +In addition to the offloads described above it is possible for a frame to +contain additional headers such as an outer tunnel. In order to account +for such instances an additional set of segmentation offload types were +introduced including SKB_GSO_IPXIP4, SKB_GSO_IPXIP6, SKB_GSO_GRE, and +SKB_GSO_UDP_TUNNEL. These extra segmentation types are used to identify +cases where there are more than just 1 set of headers. For example in the +case of IPIP and SIT we should have the network and transport headers moved +from the standard list of headers to "inner" header offsets. + +Currently only two levels of headers are supported. The convention is to +refer to the tunnel headers as the outer headers, while the encapsulated +data is normally referred to as the inner headers. Below is the list of +calls to access the given headers: + +IPIP/SIT Tunnel:: + + Outer Inner + MAC skb_mac_header + Network skb_network_header skb_inner_network_header + Transport skb_transport_header + +UDP/GRE Tunnel:: + + Outer Inner + MAC skb_mac_header skb_inner_mac_header + Network skb_network_header skb_inner_network_header + Transport skb_transport_header skb_inner_transport_header + +In addition to the above tunnel types there are also SKB_GSO_GRE_CSUM and +SKB_GSO_UDP_TUNNEL_CSUM. These two additional tunnel types reflect the +fact that the outer header also requests to have a non-zero checksum +included in the outer header. + +Finally there is SKB_GSO_TUNNEL_REMCSUM which indicates that a given tunnel +header has requested a remote checksum offload. In this case the inner +headers will be left with a partial checksum and only the outer header +checksum will be computed. + + +Generic Segmentation Offload +============================ + +Generic segmentation offload is a pure software offload that is meant to +deal with cases where device drivers cannot perform the offloads described +above. What occurs in GSO is that a given skbuff will have its data broken +out over multiple skbuffs that have been resized to match the MSS provided +via skb_shinfo()->gso_size. + +Before enabling any hardware segmentation offload a corresponding software +offload is required in GSO. Otherwise it becomes possible for a frame to +be re-routed between devices and end up being unable to be transmitted. + + +Generic Receive Offload +======================= + +Generic receive offload is the complement to GSO. Ideally any frame +assembled by GRO should be segmented to create an identical sequence of +frames using GSO, and any sequence of frames segmented by GSO should be +able to be reassembled back to the original by GRO. The only exception to +this is IPv4 ID in the case that the DF bit is set for a given IP header. +If the value of the IPv4 ID is not sequentially incrementing it will be +altered so that it is when a frame assembled via GRO is segmented via GSO. + + +Partial Generic Segmentation Offload +==================================== + +Partial generic segmentation offload is a hybrid between TSO and GSO. What +it effectively does is take advantage of certain traits of TCP and tunnels +so that instead of having to rewrite the packet headers for each segment +only the inner-most transport header and possibly the outer-most network +header need to be updated. This allows devices that do not support tunnel +offloads or tunnel offloads with checksum to still make use of segmentation. + +With the partial offload what occurs is that all headers excluding the +inner transport header are updated such that they will contain the correct +values for if the header was simply duplicated. The one exception to this +is the outer IPv4 ID field. It is up to the device drivers to guarantee +that the IPv4 ID field is incremented in the case that a given header does +not have the DF bit set. + + +SCTP accelleration with GSO +=========================== + +SCTP - despite the lack of hardware support - can still take advantage of +GSO to pass one large packet through the network stack, rather than +multiple small packets. + +This requires a different approach to other offloads, as SCTP packets +cannot be just segmented to (P)MTU. Rather, the chunks must be contained in +IP segments, padding respected. So unlike regular GSO, SCTP can't just +generate a big skb, set gso_size to the fragmentation point and deliver it +to IP layer. + +Instead, the SCTP protocol layer builds an skb with the segments correctly +padded and stored as chained skbs, and skb_segment() splits based on those. +To signal this, gso_size is set to the special value GSO_BY_FRAGS. + +Therefore, any code in the core networking stack must be aware of the +possibility that gso_size will be GSO_BY_FRAGS and handle that case +appropriately. + +There are some helpers to make this easier: + +- skb_is_gso(skb) && skb_is_gso_sctp(skb) is the best way to see if + an skb is an SCTP GSO skb. + +- For size checks, the skb_gso_validate_*_len family of helpers correctly + considers GSO_BY_FRAGS. + +- For manipulating packets, skb_increase_gso_size and skb_decrease_gso_size + will check for GSO_BY_FRAGS and WARN if asked to manipulate these skbs. + +This also affects drivers with the NETIF_F_FRAGLIST & NETIF_F_GSO_SCTP bits +set. Note also that NETIF_F_GSO_SCTP is included in NETIF_F_GSO_SOFTWARE. diff --git a/Documentation/networking/segmentation-offloads.txt b/Documentation/networking/segmentation-offloads.txt deleted file mode 100644 index 1794bfe98196..000000000000 --- a/Documentation/networking/segmentation-offloads.txt +++ /dev/null @@ -1,184 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -=================================================== -Segmentation Offloads in the Linux Networking Stack -=================================================== - - -Introduction -============ - -This document describes a set of techniques in the Linux networking stack -to take advantage of segmentation offload capabilities of various NICs. - -The following technologies are described: - * TCP Segmentation Offload - TSO - * UDP Fragmentation Offload - UFO - * IPIP, SIT, GRE, and UDP Tunnel Offloads - * Generic Segmentation Offload - GSO - * Generic Receive Offload - GRO - * Partial Generic Segmentation Offload - GSO_PARTIAL - * SCTP accelleration with GSO - GSO_BY_FRAGS - - -TCP Segmentation Offload -======================== - -TCP segmentation allows a device to segment a single frame into multiple -frames with a data payload size specified in skb_shinfo()->gso_size. -When TCP segmentation requested the bit for either SKB_GSO_TCPV4 or -SKB_GSO_TCPV6 should be set in skb_shinfo()->gso_type and -skb_shinfo()->gso_size should be set to a non-zero value. - -TCP segmentation is dependent on support for the use of partial checksum -offload. For this reason TSO is normally disabled if the Tx checksum -offload for a given device is disabled. - -In order to support TCP segmentation offload it is necessary to populate -the network and transport header offsets of the skbuff so that the device -drivers will be able determine the offsets of the IP or IPv6 header and the -TCP header. In addition as CHECKSUM_PARTIAL is required csum_start should -also point to the TCP header of the packet. - -For IPv4 segmentation we support one of two types in terms of the IP ID. -The default behavior is to increment the IP ID with every segment. If the -GSO type SKB_GSO_TCP_FIXEDID is specified then we will not increment the IP -ID and all segments will use the same IP ID. If a device has -NETIF_F_TSO_MANGLEID set then the IP ID can be ignored when performing TSO -and we will either increment the IP ID for all frames, or leave it at a -static value based on driver preference. - - -UDP Fragmentation Offload -========================= - -UDP fragmentation offload allows a device to fragment an oversized UDP -datagram into multiple IPv4 fragments. Many of the requirements for UDP -fragmentation offload are the same as TSO. However the IPv4 ID for -fragments should not increment as a single IPv4 datagram is fragmented. - -UFO is deprecated: modern kernels will no longer generate UFO skbs, but can -still receive them from tuntap and similar devices. Offload of UDP-based -tunnel protocols is still supported. - - -IPIP, SIT, GRE, UDP Tunnel, and Remote Checksum Offloads -======================================================== - -In addition to the offloads described above it is possible for a frame to -contain additional headers such as an outer tunnel. In order to account -for such instances an additional set of segmentation offload types were -introduced including SKB_GSO_IPXIP4, SKB_GSO_IPXIP6, SKB_GSO_GRE, and -SKB_GSO_UDP_TUNNEL. These extra segmentation types are used to identify -cases where there are more than just 1 set of headers. For example in the -case of IPIP and SIT we should have the network and transport headers moved -from the standard list of headers to "inner" header offsets. - -Currently only two levels of headers are supported. The convention is to -refer to the tunnel headers as the outer headers, while the encapsulated -data is normally referred to as the inner headers. Below is the list of -calls to access the given headers: - -IPIP/SIT Tunnel:: - - Outer Inner - MAC skb_mac_header - Network skb_network_header skb_inner_network_header - Transport skb_transport_header - -UDP/GRE Tunnel:: - - Outer Inner - MAC skb_mac_header skb_inner_mac_header - Network skb_network_header skb_inner_network_header - Transport skb_transport_header skb_inner_transport_header - -In addition to the above tunnel types there are also SKB_GSO_GRE_CSUM and -SKB_GSO_UDP_TUNNEL_CSUM. These two additional tunnel types reflect the -fact that the outer header also requests to have a non-zero checksum -included in the outer header. - -Finally there is SKB_GSO_TUNNEL_REMCSUM which indicates that a given tunnel -header has requested a remote checksum offload. In this case the inner -headers will be left with a partial checksum and only the outer header -checksum will be computed. - - -Generic Segmentation Offload -============================ - -Generic segmentation offload is a pure software offload that is meant to -deal with cases where device drivers cannot perform the offloads described -above. What occurs in GSO is that a given skbuff will have its data broken -out over multiple skbuffs that have been resized to match the MSS provided -via skb_shinfo()->gso_size. - -Before enabling any hardware segmentation offload a corresponding software -offload is required in GSO. Otherwise it becomes possible for a frame to -be re-routed between devices and end up being unable to be transmitted. - - -Generic Receive Offload -======================= - -Generic receive offload is the complement to GSO. Ideally any frame -assembled by GRO should be segmented to create an identical sequence of -frames using GSO, and any sequence of frames segmented by GSO should be -able to be reassembled back to the original by GRO. The only exception to -this is IPv4 ID in the case that the DF bit is set for a given IP header. -If the value of the IPv4 ID is not sequentially incrementing it will be -altered so that it is when a frame assembled via GRO is segmented via GSO. - - -Partial Generic Segmentation Offload -==================================== - -Partial generic segmentation offload is a hybrid between TSO and GSO. What -it effectively does is take advantage of certain traits of TCP and tunnels -so that instead of having to rewrite the packet headers for each segment -only the inner-most transport header and possibly the outer-most network -header need to be updated. This allows devices that do not support tunnel -offloads or tunnel offloads with checksum to still make use of segmentation. - -With the partial offload what occurs is that all headers excluding the -inner transport header are updated such that they will contain the correct -values for if the header was simply duplicated. The one exception to this -is the outer IPv4 ID field. It is up to the device drivers to guarantee -that the IPv4 ID field is incremented in the case that a given header does -not have the DF bit set. - - -SCTP accelleration with GSO -=========================== - -SCTP - despite the lack of hardware support - can still take advantage of -GSO to pass one large packet through the network stack, rather than -multiple small packets. - -This requires a different approach to other offloads, as SCTP packets -cannot be just segmented to (P)MTU. Rather, the chunks must be contained in -IP segments, padding respected. So unlike regular GSO, SCTP can't just -generate a big skb, set gso_size to the fragmentation point and deliver it -to IP layer. - -Instead, the SCTP protocol layer builds an skb with the segments correctly -padded and stored as chained skbs, and skb_segment() splits based on those. -To signal this, gso_size is set to the special value GSO_BY_FRAGS. - -Therefore, any code in the core networking stack must be aware of the -possibility that gso_size will be GSO_BY_FRAGS and handle that case -appropriately. - -There are some helpers to make this easier: - -- skb_is_gso(skb) && skb_is_gso_sctp(skb) is the best way to see if - an skb is an SCTP GSO skb. - -- For size checks, the skb_gso_validate_*_len family of helpers correctly - considers GSO_BY_FRAGS. - -- For manipulating packets, skb_increase_gso_size and skb_decrease_gso_size - will check for GSO_BY_FRAGS and WARN if asked to manipulate these skbs. - -This also affects drivers with the NETIF_F_FRAGLIST & NETIF_F_GSO_SCTP bits -set. Note also that NETIF_F_GSO_SCTP is included in NETIF_F_GSO_SOFTWARE. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 93f56fddd92a..4e671b46e767 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4296,7 +4296,7 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. - * See Documentation/networking/checksum-offloads.txt for + * See Documentation/networking/checksum-offloads.rst for * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. -- cgit v1.2.3 From 539cd352239f6acae4a7997bf31edca5c9a69c81 Mon Sep 17 00:00:00 2001 From: Zhikang Zhang Date: Thu, 3 Jan 2019 20:06:38 +0800 Subject: f2fs: fix compile warnings: 'struct *' declared inside parameter list We meet these compile warnings below, which caused by missing declare structs: struct f2fs_io_info, struct extent, struct f2fs_sb_info. warning: 'struct f2fs_io_info' declared inside parameter list warning: 'struct extent_info' declared inside parameter list warning: 'struct f2fs_sb_info' declared inside parameter list Signed-off-by: Zhikang Zhang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 3ec73f17ee2a..8a28a2b1be74 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -149,6 +149,9 @@ TRACE_DEFINE_ENUM(CP_TRIMMED); { CP_SPEC_LOG_NUM, "log type is 2" }, \ { CP_RECOVER_DIR, "dir needs recovery" }) +struct f2fs_sb_info; +struct f2fs_io_info; +struct extent_info; struct victim_sel_policy; struct f2fs_map_blocks; -- cgit v1.2.3 From 9ac6cb5fbb1781d120ca0ad29d014d35c9c3f0c4 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 19 Dec 2018 17:48:17 +0100 Subject: i2c: add suspended flag and accessors for i2c adapters A few drivers open code the handling of suspended adapters. It could be handled by the core, though, to ensure generic handling. This patch adds the flag and accessor functions. The usage of these helpers is optional, though. See the kerneldoc in this patch. Using the new flag, we now reject further transfers if the adapter is already marked suspended. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- Documentation/i2c/fault-codes | 4 ++++ drivers/i2c/i2c-core-base.c | 3 +++ include/linux/i2c.h | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 41 insertions(+) (limited to 'include') diff --git a/Documentation/i2c/fault-codes b/Documentation/i2c/fault-codes index 47c25abb7d52..0cee0fc545b4 100644 --- a/Documentation/i2c/fault-codes +++ b/Documentation/i2c/fault-codes @@ -112,6 +112,10 @@ EPROTO case is when the length of an SMBus block data response (from the SMBus slave) is outside the range 1-32 bytes. +ESHUTDOWN + Returned when a transfer was requested using an adapter + which is already suspended. + ETIMEDOUT This is returned by drivers when an operation took too much time, and was aborted before it completed. diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 28460f6a60cc..926ca0a7477f 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -1232,6 +1232,7 @@ static int i2c_register_adapter(struct i2c_adapter *adap) if (!adap->lock_ops) adap->lock_ops = &i2c_adapter_lock_ops; + adap->locked_flags = 0; rt_mutex_init(&adap->bus_lock); rt_mutex_init(&adap->mux_lock); mutex_init(&adap->userspace_clients_lock); @@ -1865,6 +1866,8 @@ int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) if (WARN_ON(!msgs || num < 1)) return -EINVAL; + if (WARN_ON(test_bit(I2C_ALF_IS_SUSPENDED, &adap->locked_flags))) + return -ESHUTDOWN; if (adap->quirks && i2c_check_for_quirks(adap, msgs, num)) return -EOPNOTSUPP; diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 65b4eaed1d96..cba59d66c00d 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -680,6 +680,8 @@ struct i2c_adapter { int timeout; /* in jiffies */ int retries; struct device dev; /* the adapter device */ + unsigned long locked_flags; /* owned by the I2C core */ +#define I2C_ALF_IS_SUSPENDED 0 int nr; char name[48]; @@ -762,6 +764,38 @@ i2c_unlock_bus(struct i2c_adapter *adapter, unsigned int flags) adapter->lock_ops->unlock_bus(adapter, flags); } +/** + * i2c_mark_adapter_suspended - Report suspended state of the adapter to the core + * @adap: Adapter to mark as suspended + * + * When using this helper to mark an adapter as suspended, the core will reject + * further transfers to this adapter. The usage of this helper is optional but + * recommended for devices having distinct handlers for system suspend and + * runtime suspend. More complex devices are free to implement custom solutions + * to reject transfers when suspended. + */ +static inline void i2c_mark_adapter_suspended(struct i2c_adapter *adap) +{ + i2c_lock_bus(adap, I2C_LOCK_ROOT_ADAPTER); + set_bit(I2C_ALF_IS_SUSPENDED, &adap->locked_flags); + i2c_unlock_bus(adap, I2C_LOCK_ROOT_ADAPTER); +} + +/** + * i2c_mark_adapter_resumed - Report resumed state of the adapter to the core + * @adap: Adapter to mark as resumed + * + * When using this helper to mark an adapter as resumed, the core will allow + * further transfers to this adapter. See also further notes to + * @i2c_mark_adapter_suspended(). + */ +static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) +{ + i2c_lock_bus(adap, I2C_LOCK_ROOT_ADAPTER); + clear_bit(I2C_ALF_IS_SUSPENDED, &adap->locked_flags); + i2c_unlock_bus(adap, I2C_LOCK_ROOT_ADAPTER); +} + /*flags for the client struct: */ #define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ #define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ -- cgit v1.2.3 From 991e873223e9bcfaf10a0074eec1507c1ddfb6ab Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Tue, 4 Dec 2018 11:20:29 +0000 Subject: soc: fsl: dpio: use a cpumask to identify which cpus are unused The current implementation of the dpio driver uses a static next_cpu variable to keep track of the index of the next cpu available. This approach does not handle well unbinding and binding dpio devices in a random order. For example, unbinding a dpio and then binding it again with the driver, will generate the below error: $ echo dpio.5 > /sys/bus/fsl-mc/drivers/fsl_mc_dpio/unbind $ echo dpio.5 > /sys/bus/fsl-mc/drivers/fsl_mc_dpio/bind [ 103.946380] fsl_mc_dpio dpio.5: probe failed. Number of DPIOs exceeds NR_CPUS. [ 103.955157] fsl_mc_dpio dpio.5: fsl_mc_driver_probe failed: -34 -bash: echo: write error: No such device Fix this error by keeping a global cpumask of unused cpus that will be updated at every dpaa2_dpio_[probe,remove]. Signed-off-by: Ioana Ciornei Signed-off-by: Li Yang --- drivers/soc/fsl/dpio/dpio-driver.c | 25 ++++++++++++++++--------- drivers/soc/fsl/dpio/dpio-service.c | 13 +++++++++++++ include/soc/fsl/dpaa2-io.h | 2 ++ 3 files changed, 31 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/soc/fsl/dpio/dpio-driver.c b/drivers/soc/fsl/dpio/dpio-driver.c index e58fcc9096e8..832175cac739 100644 --- a/drivers/soc/fsl/dpio/dpio-driver.c +++ b/drivers/soc/fsl/dpio/dpio-driver.c @@ -30,6 +30,8 @@ struct dpio_priv { struct dpaa2_io *io; }; +static cpumask_var_t cpus_unused_mask; + static irqreturn_t dpio_irq_handler(int irq_num, void *arg) { struct device *dev = (struct device *)arg; @@ -86,7 +88,7 @@ static int dpaa2_dpio_probe(struct fsl_mc_device *dpio_dev) struct dpio_priv *priv; int err = -ENOMEM; struct device *dev = &dpio_dev->dev; - static int next_cpu = -1; + int possible_next_cpu; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -128,17 +130,14 @@ static int dpaa2_dpio_probe(struct fsl_mc_device *dpio_dev) desc.dpio_id = dpio_dev->obj_desc.id; /* get the cpu to use for the affinity hint */ - if (next_cpu == -1) - next_cpu = cpumask_first(cpu_online_mask); - else - next_cpu = cpumask_next(next_cpu, cpu_online_mask); - - if (!cpu_possible(next_cpu)) { + possible_next_cpu = cpumask_first(cpus_unused_mask); + if (possible_next_cpu >= nr_cpu_ids) { dev_err(dev, "probe failed. Number of DPIOs exceeds NR_CPUS.\n"); err = -ERANGE; goto err_allocate_irqs; } - desc.cpu = next_cpu; + desc.cpu = possible_next_cpu; + cpumask_clear_cpu(possible_next_cpu, cpus_unused_mask); /* * Set the CENA regs to be the cache inhibited area of the portal to @@ -211,7 +210,7 @@ static int dpaa2_dpio_remove(struct fsl_mc_device *dpio_dev) { struct device *dev; struct dpio_priv *priv; - int err; + int err = 0, cpu; dev = &dpio_dev->dev; priv = dev_get_drvdata(dev); @@ -220,6 +219,9 @@ static int dpaa2_dpio_remove(struct fsl_mc_device *dpio_dev) dpio_teardown_irqs(dpio_dev); + cpu = dpaa2_io_get_cpu(priv->io); + cpumask_set_cpu(cpu, cpus_unused_mask); + err = fsl_mc_portal_allocate(dpio_dev, 0, &dpio_dev->mc_io); if (err) { dev_err(dev, "MC portal allocation failed\n"); @@ -267,11 +269,16 @@ static struct fsl_mc_driver dpaa2_dpio_driver = { static int dpio_driver_init(void) { + if (!zalloc_cpumask_var(&cpus_unused_mask, GFP_KERNEL)) + return -ENOMEM; + cpumask_copy(cpus_unused_mask, cpu_online_mask); + return fsl_mc_driver_register(&dpaa2_dpio_driver); } static void dpio_driver_exit(void) { + free_cpumask_var(cpus_unused_mask); fsl_mc_driver_unregister(&dpaa2_dpio_driver); } module_init(dpio_driver_init); diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index ab046f241d32..c02bfb18a1f0 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -214,6 +214,19 @@ done: return IRQ_HANDLED; } +/** + * dpaa2_io_get_cpu() - get the cpu associated with a given DPIO object + * + * @d: the given DPIO object. + * + * Return the cpu associated with the DPIO object + */ +int dpaa2_io_get_cpu(struct dpaa2_io *d) +{ + return d->dpio_desc.cpu; +} +EXPORT_SYMBOL(dpaa2_io_get_cpu); + /** * dpaa2_io_service_register() - Prepare for servicing of FQDAN or CDAN * notifications on the given DPIO service. diff --git a/include/soc/fsl/dpaa2-io.h b/include/soc/fsl/dpaa2-io.h index 3fbd71c27ba3..243119c53cdf 100644 --- a/include/soc/fsl/dpaa2-io.h +++ b/include/soc/fsl/dpaa2-io.h @@ -90,6 +90,8 @@ struct dpaa2_io_notification_ctx { void *dpio_private; }; +int dpaa2_io_get_cpu(struct dpaa2_io *d); + int dpaa2_io_service_register(struct dpaa2_io *service, struct dpaa2_io_notification_ctx *ctx); void dpaa2_io_service_deregister(struct dpaa2_io *service, -- cgit v1.2.3 From 47008e5161fa097ce9b848dee194b43262b743a5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 19 Sep 2018 16:13:25 -0700 Subject: LSM: Introduce LSM_FLAG_LEGACY_MAJOR This adds a flag for the current "major" LSMs to distinguish them when we have a universal method for ordering all LSMs. It's called "legacy" since the distinction of "major" will go away in the blob-sharing world. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: John Johansen --- include/linux/lsm_hooks.h | 3 +++ security/apparmor/lsm.c | 1 + security/selinux/hooks.c | 1 + security/smack/smack_lsm.c | 1 + security/tomoyo/tomoyo.c | 1 + 5 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9a0bdf91e646..318d93f918c3 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2042,8 +2042,11 @@ extern char *lsm_names; extern void security_add_hooks(struct security_hook_list *hooks, int count, char *lsm); +#define LSM_FLAG_LEGACY_MAJOR BIT(0) + struct lsm_info { const char *name; /* Required. */ + unsigned long flags; /* Optional: flags describing LSM */ int (*init)(void); /* Required. */ }; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 2c010874329f..e49c50e0d5ab 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1729,5 +1729,6 @@ alloc_out: DEFINE_LSM(apparmor) = { .name = "apparmor", + .flags = LSM_FLAG_LEGACY_MAJOR, .init = apparmor_init, }; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f0e36c3492ba..41908d2d6149 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6999,6 +6999,7 @@ void selinux_complete_init(void) all processes and objects when they are created. */ DEFINE_LSM(selinux) = { .name = "selinux", + .flags = LSM_FLAG_LEGACY_MAJOR, .init = selinux_init, }; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 430d4f35e55c..d72d215d7fde 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4812,5 +4812,6 @@ static __init int smack_init(void) */ DEFINE_LSM(smack) = { .name = "smack", + .flags = LSM_FLAG_LEGACY_MAJOR, .init = smack_init, }; diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 1b5b5097efd7..09f7af130d3a 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -552,5 +552,6 @@ static int __init tomoyo_init(void) DEFINE_LSM(tomoyo) = { .name = "tomoyo", + .flags = LSM_FLAG_LEGACY_MAJOR, .init = tomoyo_init, }; -- cgit v1.2.3 From c5459b829b716dafd226ad270f25c9a3050f7586 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 13 Sep 2018 22:28:48 -0700 Subject: LSM: Plumb visibility into optional "enabled" state In preparation for lifting the "is this LSM enabled?" logic out of the individual LSMs, pass in any special enabled state tracking (as needed for SELinux, AppArmor, and LoadPin). This should be an "int" to include handling any future cases where "enabled" is exposed via sysctl which has no "bool" type. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: John Johansen --- include/linux/lsm_hooks.h | 1 + security/apparmor/lsm.c | 5 +++-- security/selinux/hooks.c | 1 + 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 318d93f918c3..7bbe5e287161 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2047,6 +2047,7 @@ extern void security_add_hooks(struct security_hook_list *hooks, int count, struct lsm_info { const char *name; /* Required. */ unsigned long flags; /* Optional: flags describing LSM */ + int *enabled; /* Optional: NULL means enabled. */ int (*init)(void); /* Required. */ }; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index e49c50e0d5ab..a4652ff622cf 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1333,8 +1333,8 @@ bool aa_g_paranoid_load = true; module_param_named(paranoid_load, aa_g_paranoid_load, aabool, S_IRUGO); /* Boot time disable flag */ -static bool apparmor_enabled = CONFIG_SECURITY_APPARMOR_BOOTPARAM_VALUE; -module_param_named(enabled, apparmor_enabled, bool, S_IRUGO); +static int apparmor_enabled = CONFIG_SECURITY_APPARMOR_BOOTPARAM_VALUE; +module_param_named(enabled, apparmor_enabled, int, 0444); static int __init apparmor_enabled_setup(char *str) { @@ -1730,5 +1730,6 @@ alloc_out: DEFINE_LSM(apparmor) = { .name = "apparmor", .flags = LSM_FLAG_LEGACY_MAJOR, + .enabled = &apparmor_enabled, .init = apparmor_init, }; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 41908d2d6149..f847514d6f03 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -7000,6 +7000,7 @@ void selinux_complete_init(void) DEFINE_LSM(selinux) = { .name = "selinux", .flags = LSM_FLAG_LEGACY_MAJOR, + .enabled = &selinux_enabled, .init = selinux_init, }; -- cgit v1.2.3 From f4941d75b9cba5e1fae1aebe0139dcca0703a294 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 13 Sep 2018 23:17:50 -0700 Subject: LSM: Lift LSM selection out of individual LSMs As a prerequisite to adjusting LSM selection logic in the future, this moves the selection logic up out of the individual major LSMs, making their init functions only run when actually enabled. This considers all LSMs enabled by default unless they specified an external "enable" variable. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: John Johansen --- include/linux/lsm_hooks.h | 1 - security/apparmor/lsm.c | 6 --- security/security.c | 102 +++++++++++++++++++++++++++++++-------------- security/selinux/hooks.c | 10 ----- security/smack/smack_lsm.c | 3 -- security/tomoyo/tomoyo.c | 2 - 6 files changed, 71 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 7bbe5e287161..be1581d18e3e 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2088,7 +2088,6 @@ static inline void security_delete_hooks(struct security_hook_list *hooks, #define __lsm_ro_after_init __ro_after_init #endif /* CONFIG_SECURITY_WRITABLE_HOOKS */ -extern int __init security_module_enable(const char *module); extern void __init capability_add_hooks(void); #ifdef CONFIG_SECURITY_YAMA extern void __init yama_add_hooks(void); diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index a4652ff622cf..dfc5fbf8ba82 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1663,12 +1663,6 @@ static int __init apparmor_init(void) { int error; - if (!apparmor_enabled || !security_module_enable("apparmor")) { - aa_info_message("AppArmor disabled by boot time parameter"); - apparmor_enabled = false; - return 0; - } - aa_secids_init(); error = aa_setup_dfa_engine(); diff --git a/security/security.c b/security/security.c index 6bc591f77b1a..c900d7a1441a 100644 --- a/security/security.c +++ b/security/security.c @@ -52,33 +52,96 @@ static __initdata bool debug; pr_info(__VA_ARGS__); \ } while (0) +static bool __init is_enabled(struct lsm_info *lsm) +{ + if (!lsm->enabled || *lsm->enabled) + return true; + + return false; +} + +/* Mark an LSM's enabled flag. */ +static int lsm_enabled_true __initdata = 1; +static int lsm_enabled_false __initdata = 0; +static void __init set_enabled(struct lsm_info *lsm, bool enabled) +{ + /* + * When an LSM hasn't configured an enable variable, we can use + * a hard-coded location for storing the default enabled state. + */ + if (!lsm->enabled) { + if (enabled) + lsm->enabled = &lsm_enabled_true; + else + lsm->enabled = &lsm_enabled_false; + } else if (lsm->enabled == &lsm_enabled_true) { + if (!enabled) + lsm->enabled = &lsm_enabled_false; + } else if (lsm->enabled == &lsm_enabled_false) { + if (enabled) + lsm->enabled = &lsm_enabled_true; + } else { + *lsm->enabled = enabled; + } +} + +/* Is an LSM allowed to be initialized? */ +static bool __init lsm_allowed(struct lsm_info *lsm) +{ + /* Skip if the LSM is disabled. */ + if (!is_enabled(lsm)) + return false; + + /* Skip major-specific checks if not a major LSM. */ + if ((lsm->flags & LSM_FLAG_LEGACY_MAJOR) == 0) + return true; + + /* Disabled if this LSM isn't the chosen one. */ + if (strcmp(lsm->name, chosen_lsm) != 0) + return false; + + return true; +} + +/* Check if LSM should be initialized. */ +static void __init maybe_initialize_lsm(struct lsm_info *lsm) +{ + int enabled = lsm_allowed(lsm); + + /* Record enablement (to handle any following exclusive LSMs). */ + set_enabled(lsm, enabled); + + /* If selected, initialize the LSM. */ + if (enabled) { + int ret; + + init_debug("initializing %s\n", lsm->name); + ret = lsm->init(); + WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret); + } +} + static void __init ordered_lsm_init(void) { struct lsm_info *lsm; - int ret; for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if ((lsm->flags & LSM_FLAG_LEGACY_MAJOR) != 0) continue; - init_debug("initializing %s\n", lsm->name); - ret = lsm->init(); - WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret); + maybe_initialize_lsm(lsm); } } static void __init major_lsm_init(void) { struct lsm_info *lsm; - int ret; for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if ((lsm->flags & LSM_FLAG_LEGACY_MAJOR) == 0) continue; - init_debug("initializing %s\n", lsm->name); - ret = lsm->init(); - WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret); + maybe_initialize_lsm(lsm); } } @@ -168,29 +231,6 @@ static int lsm_append(char *new, char **result) return 0; } -/** - * security_module_enable - Load given security module on boot ? - * @module: the name of the module - * - * Each LSM must pass this method before registering its own operations - * to avoid security registration races. This method may also be used - * to check if your LSM is currently loaded during kernel initialization. - * - * Returns: - * - * true if: - * - * - The passed LSM is the one chosen by user at boot time, - * - or the passed LSM is configured as the default and the user did not - * choose an alternate LSM at boot time. - * - * Otherwise, return false. - */ -int __init security_module_enable(const char *module) -{ - return !strcmp(module, chosen_lsm); -} - /** * security_add_hooks - Add a modules hooks to the hook lists. * @hooks: the hooks to add diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f847514d6f03..0f8ae2fbd14a 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6928,16 +6928,6 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { static __init int selinux_init(void) { - if (!security_module_enable("selinux")) { - selinux_enabled = 0; - return 0; - } - - if (!selinux_enabled) { - pr_info("SELinux: Disabled at boot.\n"); - return 0; - } - pr_info("SELinux: Initializing.\n"); memset(&selinux_state, 0, sizeof(selinux_state)); diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index d72d215d7fde..580e9d6e5680 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4762,9 +4762,6 @@ static __init int smack_init(void) struct cred *cred; struct task_smack *tsp; - if (!security_module_enable("smack")) - return 0; - smack_inode_cache = KMEM_CACHE(inode_smack, 0); if (!smack_inode_cache) return -ENOMEM; diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 09f7af130d3a..a46f6bc1e97c 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -540,8 +540,6 @@ static int __init tomoyo_init(void) { struct cred *cred = (struct cred *) current_cred(); - if (!security_module_enable("tomoyo")) - return 0; /* register ourselves with the security framework */ security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), "tomoyo"); printk(KERN_INFO "TOMOYO Linux initialized\n"); -- cgit v1.2.3 From a8027fb0d188599ccdb2096f49f708bae04d86c4 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 9 Oct 2018 14:42:57 -0700 Subject: LSM: Tie enabling logic to presence in ordered list Until now, any LSM without an enable storage variable was considered enabled. This inverts the logic and sets defaults to true only if the LSM gets added to the ordered initialization list. (And an exception continues for the major LSMs until they are integrated into the ordered initialization in a later patch.) Signed-off-by: Kees Cook --- include/linux/lsm_hooks.h | 2 +- security/security.c | 14 +++++++++++--- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index be1581d18e3e..e28a3aa639e8 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2047,7 +2047,7 @@ extern void security_add_hooks(struct security_hook_list *hooks, int count, struct lsm_info { const char *name; /* Required. */ unsigned long flags; /* Optional: flags describing LSM */ - int *enabled; /* Optional: NULL means enabled. */ + int *enabled; /* Optional: controlled by CONFIG_LSM */ int (*init)(void); /* Required. */ }; diff --git a/security/security.c b/security/security.c index 2e1f48e8a6f2..b6d3456978a4 100644 --- a/security/security.c +++ b/security/security.c @@ -63,10 +63,10 @@ static __initdata bool debug; static bool __init is_enabled(struct lsm_info *lsm) { - if (!lsm->enabled || *lsm->enabled) - return true; + if (!lsm->enabled) + return false; - return false; + return *lsm->enabled; } /* Mark an LSM's enabled flag. */ @@ -117,7 +117,11 @@ static void __init append_ordered_lsm(struct lsm_info *lsm, const char *from) if (WARN(last_lsm == LSM_COUNT, "%s: out of LSM slots!?\n", from)) return; + /* Enable this LSM, if it is not already set. */ + if (!lsm->enabled) + lsm->enabled = &lsm_enabled_true; ordered_lsms[last_lsm++] = lsm; + init_debug("%s ordering: %s (%sabled)\n", from, lsm->name, is_enabled(lsm) ? "en" : "dis"); } @@ -210,6 +214,10 @@ static void __init major_lsm_init(void) if ((lsm->flags & LSM_FLAG_LEGACY_MAJOR) == 0) continue; + /* Enable this LSM, if it is not already set. */ + if (!lsm->enabled) + lsm->enabled = &lsm_enabled_true; + maybe_initialize_lsm(lsm); } } -- cgit v1.2.3 From 14bd99c821f7ace0e8110a1bfdfaa27e1788e20f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 19 Sep 2018 19:57:06 -0700 Subject: LSM: Separate idea of "major" LSM from "exclusive" LSM In order to both support old "security=" Legacy Major LSM selection, and handling real exclusivity, this creates LSM_FLAG_EXCLUSIVE and updates the selection logic to handle them. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler --- include/linux/lsm_hooks.h | 1 + security/apparmor/lsm.c | 2 +- security/security.c | 12 ++++++++++++ security/selinux/hooks.c | 2 +- security/smack/smack_lsm.c | 2 +- security/tomoyo/tomoyo.c | 2 +- 6 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index e28a3aa639e8..c3843b33da9e 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2043,6 +2043,7 @@ extern void security_add_hooks(struct security_hook_list *hooks, int count, char *lsm); #define LSM_FLAG_LEGACY_MAJOR BIT(0) +#define LSM_FLAG_EXCLUSIVE BIT(1) struct lsm_info { const char *name; /* Required. */ diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index dfc5fbf8ba82..149a3e16b5da 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1723,7 +1723,7 @@ alloc_out: DEFINE_LSM(apparmor) = { .name = "apparmor", - .flags = LSM_FLAG_LEGACY_MAJOR, + .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &apparmor_enabled, .init = apparmor_init, }; diff --git a/security/security.c b/security/security.c index 88de6b073246..a8dd7defe30a 100644 --- a/security/security.c +++ b/security/security.c @@ -49,6 +49,7 @@ static __initconst const char * const builtin_lsm_order = CONFIG_LSM; /* Ordered list of LSMs to initialize. */ static __initdata struct lsm_info **ordered_lsms; +static __initdata struct lsm_info *exclusive; static __initdata bool debug; #define init_debug(...) \ @@ -129,6 +130,12 @@ static bool __init lsm_allowed(struct lsm_info *lsm) if (!is_enabled(lsm)) return false; + /* Not allowed if another exclusive LSM already initialized. */ + if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && exclusive) { + init_debug("exclusive disabled: %s\n", lsm->name); + return false; + } + return true; } @@ -144,6 +151,11 @@ static void __init maybe_initialize_lsm(struct lsm_info *lsm) if (enabled) { int ret; + if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && !exclusive) { + exclusive = lsm; + init_debug("exclusive chosen: %s\n", lsm->name); + } + init_debug("initializing %s\n", lsm->name); ret = lsm->init(); WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 0f8ae2fbd14a..49865f119b16 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6989,7 +6989,7 @@ void selinux_complete_init(void) all processes and objects when they are created. */ DEFINE_LSM(selinux) = { .name = "selinux", - .flags = LSM_FLAG_LEGACY_MAJOR, + .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &selinux_enabled, .init = selinux_init, }; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 580e9d6e5680..780733341d02 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4809,6 +4809,6 @@ static __init int smack_init(void) */ DEFINE_LSM(smack) = { .name = "smack", - .flags = LSM_FLAG_LEGACY_MAJOR, + .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .init = smack_init, }; diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index a46f6bc1e97c..daff7d7897ad 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -550,6 +550,6 @@ static int __init tomoyo_init(void) DEFINE_LSM(tomoyo) = { .name = "tomoyo", - .flags = LSM_FLAG_LEGACY_MAJOR, + .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .init = tomoyo_init, }; -- cgit v1.2.3 From 70b62c25665f636c9f6c700b26af7df296b0887e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 14 Sep 2018 15:26:37 -0700 Subject: LoadPin: Initialize as ordered LSM This converts LoadPin from being a direct "minor" LSM into an ordered LSM. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler --- include/linux/lsm_hooks.h | 5 ----- security/Kconfig | 39 +-------------------------------------- security/loadpin/loadpin.c | 8 +++++++- security/security.c | 1 - 4 files changed, 8 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index c3843b33da9e..fb1a653ccfcb 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2095,10 +2095,5 @@ extern void __init yama_add_hooks(void); #else static inline void __init yama_add_hooks(void) { } #endif -#ifdef CONFIG_SECURITY_LOADPIN -void __init loadpin_add_hooks(void); -#else -static inline void loadpin_add_hooks(void) { }; -#endif #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/security/Kconfig b/security/Kconfig index cedf69e8a22c..2cd737ba7660 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -239,46 +239,9 @@ source "security/yama/Kconfig" source "security/integrity/Kconfig" -choice - prompt "Default security module" - default DEFAULT_SECURITY_SELINUX if SECURITY_SELINUX - default DEFAULT_SECURITY_SMACK if SECURITY_SMACK - default DEFAULT_SECURITY_TOMOYO if SECURITY_TOMOYO - default DEFAULT_SECURITY_APPARMOR if SECURITY_APPARMOR - default DEFAULT_SECURITY_DAC - - help - Select the security module that will be used by default if the - kernel parameter security= is not specified. - - config DEFAULT_SECURITY_SELINUX - bool "SELinux" if SECURITY_SELINUX=y - - config DEFAULT_SECURITY_SMACK - bool "Simplified Mandatory Access Control" if SECURITY_SMACK=y - - config DEFAULT_SECURITY_TOMOYO - bool "TOMOYO" if SECURITY_TOMOYO=y - - config DEFAULT_SECURITY_APPARMOR - bool "AppArmor" if SECURITY_APPARMOR=y - - config DEFAULT_SECURITY_DAC - bool "Unix Discretionary Access Controls" - -endchoice - -config DEFAULT_SECURITY - string - default "selinux" if DEFAULT_SECURITY_SELINUX - default "smack" if DEFAULT_SECURITY_SMACK - default "tomoyo" if DEFAULT_SECURITY_TOMOYO - default "apparmor" if DEFAULT_SECURITY_APPARMOR - default "" if DEFAULT_SECURITY_DAC - config LSM string "Ordered list of enabled LSMs" - default "integrity" + default "loadpin,integrity,selinux,smack,tomoyo,apparmor" help A comma-separated list of LSMs, in initialization order. Any LSMs left off this list will be ignored. This can be diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index 48f39631b370..055fb0a64169 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -187,13 +187,19 @@ static struct security_hook_list loadpin_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(kernel_load_data, loadpin_load_data), }; -void __init loadpin_add_hooks(void) +static int __init loadpin_init(void) { pr_info("ready to pin (currently %senforcing)\n", enforce ? "" : "not "); security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks), "loadpin"); + return 0; } +DEFINE_LSM(loadpin) = { + .name = "loadpin", + .init = loadpin_init, +}; + /* Should not be mutable after boot, so not listed in sysfs (perm == 0). */ module_param(enforce, int, 0); MODULE_PARM_DESC(enforce, "Enforce module/firmware pinning"); diff --git a/security/security.c b/security/security.c index 46c5b0fa515e..b8d75f5a948d 100644 --- a/security/security.c +++ b/security/security.c @@ -275,7 +275,6 @@ int __init security_init(void) */ capability_add_hooks(); yama_add_hooks(); - loadpin_add_hooks(); /* Load LSMs in specified order. */ ordered_lsm_init(); -- cgit v1.2.3 From d6aed64b74b73b64278c059eacd59d87167aa968 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 14 Sep 2018 15:37:20 -0700 Subject: Yama: Initialize as ordered LSM This converts Yama from being a direct "minor" LSM into an ordered LSM. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler --- include/linux/lsm_hooks.h | 5 ----- security/Kconfig | 2 +- security/security.c | 1 - security/yama/yama_lsm.c | 8 +++++++- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index fb1a653ccfcb..2849e9b2c01d 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2090,10 +2090,5 @@ static inline void security_delete_hooks(struct security_hook_list *hooks, #endif /* CONFIG_SECURITY_WRITABLE_HOOKS */ extern void __init capability_add_hooks(void); -#ifdef CONFIG_SECURITY_YAMA -extern void __init yama_add_hooks(void); -#else -static inline void __init yama_add_hooks(void) { } -#endif #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/security/Kconfig b/security/Kconfig index 2cd737ba7660..78dc12b7eeb3 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -241,7 +241,7 @@ source "security/integrity/Kconfig" config LSM string "Ordered list of enabled LSMs" - default "loadpin,integrity,selinux,smack,tomoyo,apparmor" + default "yama,loadpin,integrity,selinux,smack,tomoyo,apparmor" help A comma-separated list of LSMs, in initialization order. Any LSMs left off this list will be ignored. This can be diff --git a/security/security.c b/security/security.c index b8d75f5a948d..35f93b7c585b 100644 --- a/security/security.c +++ b/security/security.c @@ -274,7 +274,6 @@ int __init security_init(void) * Load minor LSMs, with the capability module always first. */ capability_add_hooks(); - yama_add_hooks(); /* Load LSMs in specified order. */ ordered_lsm_init(); diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index ffda91a4a1aa..eb1da1303d2e 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -477,9 +477,15 @@ static void __init yama_init_sysctl(void) static inline void yama_init_sysctl(void) { } #endif /* CONFIG_SYSCTL */ -void __init yama_add_hooks(void) +static int __init yama_init(void) { pr_info("Yama: becoming mindful.\n"); security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), "yama"); yama_init_sysctl(); + return 0; } + +DEFINE_LSM(yama) = { + .name = "yama", + .init = yama_init, +}; -- cgit v1.2.3 From e2bc445b66cad25b0627391df8138a83d0e48f97 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 19 Sep 2018 17:48:21 -0700 Subject: LSM: Introduce enum lsm_order In preparation for distinguishing the "capability" LSM from other LSMs, it must be ordered first. This introduces LSM_ORDER_MUTABLE for the general LSMs and LSM_ORDER_FIRST for capability. In the future LSM_ORDER_LAST for could be added for anything that must run last (e.g. Landlock may use this). Signed-off-by: Kees Cook --- include/linux/lsm_hooks.h | 6 ++++++ security/security.c | 9 ++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 2849e9b2c01d..27d4db9588bb 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2045,8 +2045,14 @@ extern void security_add_hooks(struct security_hook_list *hooks, int count, #define LSM_FLAG_LEGACY_MAJOR BIT(0) #define LSM_FLAG_EXCLUSIVE BIT(1) +enum lsm_order { + LSM_ORDER_FIRST = -1, /* This is only for capabilities. */ + LSM_ORDER_MUTABLE = 0, +}; + struct lsm_info { const char *name; /* Required. */ + enum lsm_order order; /* Optional: default is LSM_ORDER_MUTABLE */ unsigned long flags; /* Optional: flags describing LSM */ int *enabled; /* Optional: controlled by CONFIG_LSM */ int (*init)(void); /* Required. */ diff --git a/security/security.c b/security/security.c index 35f93b7c585b..8b673bb2a0dd 100644 --- a/security/security.c +++ b/security/security.c @@ -174,6 +174,12 @@ static void __init ordered_lsm_parse(const char *order, const char *origin) struct lsm_info *lsm; char *sep, *name, *next; + /* LSM_ORDER_FIRST is always first. */ + for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { + if (lsm->order == LSM_ORDER_FIRST) + append_ordered_lsm(lsm, "first"); + } + /* Process "security=", if given. */ if (chosen_major_lsm) { struct lsm_info *major; @@ -202,7 +208,8 @@ static void __init ordered_lsm_parse(const char *order, const char *origin) bool found = false; for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { - if (strcmp(lsm->name, name) == 0) { + if (lsm->order == LSM_ORDER_MUTABLE && + strcmp(lsm->name, name) == 0) { append_ordered_lsm(lsm, origin); found = true; } -- cgit v1.2.3 From d117a154e6128abac5409d3f173584e7b25981a2 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 14 Sep 2018 15:40:45 -0700 Subject: capability: Initialize as LSM_ORDER_FIRST This converts capabilities to use the new LSM_ORDER_FIRST position. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler --- include/linux/lsm_hooks.h | 2 -- security/commoncap.c | 9 ++++++++- security/security.c | 5 ----- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 27d4db9588bb..0c908c091a03 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2095,6 +2095,4 @@ static inline void security_delete_hooks(struct security_hook_list *hooks, #define __lsm_ro_after_init __ro_after_init #endif /* CONFIG_SECURITY_WRITABLE_HOOKS */ -extern void __init capability_add_hooks(void); - #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/security/commoncap.c b/security/commoncap.c index 232db019f051..52e04136bfa8 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -1362,10 +1362,17 @@ struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; -void __init capability_add_hooks(void) +static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), "capability"); + return 0; } +DEFINE_LSM(capability) = { + .name = "capability", + .order = LSM_ORDER_FIRST, + .init = capability_init, +}; + #endif /* CONFIG_SECURITY */ diff --git a/security/security.c b/security/security.c index 8b673bb2a0dd..9411f659454b 100644 --- a/security/security.c +++ b/security/security.c @@ -277,11 +277,6 @@ int __init security_init(void) i++) INIT_HLIST_HEAD(&list[i]); - /* - * Load minor LSMs, with the capability module always first. - */ - capability_add_hooks(); - /* Load LSMs in specified order. */ ordered_lsm_init(); -- cgit v1.2.3 From 6d9c939dbe4d0bcea09cd4b410f624cde1acb678 Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Fri, 21 Sep 2018 17:16:59 -0700 Subject: procfs: add smack subdir to attrs Back in 2007 I made what turned out to be a rather serious mistake in the implementation of the Smack security module. The SELinux module used an interface in /proc to manipulate the security context on processes. Rather than use a similar interface, I used the same interface. The AppArmor team did likewise. Now /proc/.../attr/current will tell you the security "context" of the process, but it will be different depending on the security module you're using. This patch provides a subdirectory in /proc/.../attr for Smack. Smack user space can use the "current" file in this subdirectory and never have to worry about getting SELinux attributes by mistake. Programs that use the old interface will continue to work (or fail, as the case may be) as before. The proposed S.A.R.A security module is dependent on the mechanism to create its own attr subdirectory. The original implementation is by Kees Cook. Signed-off-by: Casey Schaufler Reviewed-by: Kees Cook Signed-off-by: Kees Cook --- Documentation/admin-guide/LSM/index.rst | 13 +++++-- fs/proc/base.c | 64 ++++++++++++++++++++++++++++----- fs/proc/internal.h | 1 + include/linux/security.h | 15 +++++--- security/security.c | 24 ++++++++++--- 5 files changed, 96 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/Documentation/admin-guide/LSM/index.rst b/Documentation/admin-guide/LSM/index.rst index c980dfe9abf1..9842e21afd4a 100644 --- a/Documentation/admin-guide/LSM/index.rst +++ b/Documentation/admin-guide/LSM/index.rst @@ -17,9 +17,8 @@ MAC extensions, other extensions can be built using the LSM to provide specific changes to system operation when these tweaks are not available in the core functionality of Linux itself. -Without a specific LSM built into the kernel, the default LSM will be the -Linux capabilities system. Most LSMs choose to extend the capabilities -system, building their checks on top of the defined capability hooks. +The Linux capabilities modules will always be included. This may be +followed by any number of "minor" modules and at most one "major" module. For more details on capabilities, see ``capabilities(7)`` in the Linux man-pages project. @@ -30,6 +29,14 @@ order in which checks are made. The capability module will always be first, followed by any "minor" modules (e.g. Yama) and then the one "major" module (e.g. SELinux) if there is one configured. +Process attributes associated with "major" security modules should +be accessed and maintained using the special files in ``/proc/.../attr``. +A security module may maintain a module specific subdirectory there, +named after the module. ``/proc/.../attr/smack`` is provided by the Smack +security module and contains all its special files. The files directly +in ``/proc/.../attr`` remain as legacy interfaces for modules that provide +subdirectories. + .. toctree:: :maxdepth: 1 diff --git a/fs/proc/base.c b/fs/proc/base.c index 633a63462573..c9d775fd24ef 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -140,9 +140,13 @@ struct pid_entry { #define REG(NAME, MODE, fops) \ NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {}) #define ONE(NAME, MODE, show) \ - NOD(NAME, (S_IFREG|(MODE)), \ + NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_single_file_operations, \ { .proc_show = show } ) +#define ATTR(LSM, NAME, MODE) \ + NOD(NAME, (S_IFREG|(MODE)), \ + NULL, &proc_pid_attr_operations, \ + { .lsm = LSM }) /* * Count the number of hardlinks for the pid_entry table, excluding the . @@ -2525,7 +2529,7 @@ static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, if (!task) return -ESRCH; - length = security_getprocattr(task, + length = security_getprocattr(task, PROC_I(inode)->op.lsm, (char*)file->f_path.dentry->d_name.name, &p); put_task_struct(task); @@ -2574,7 +2578,9 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, if (rv < 0) goto out_free; - rv = security_setprocattr(file->f_path.dentry->d_name.name, page, count); + rv = security_setprocattr(PROC_I(inode)->op.lsm, + file->f_path.dentry->d_name.name, page, + count); mutex_unlock(¤t->signal->cred_guard_mutex); out_free: kfree(page); @@ -2588,13 +2594,53 @@ static const struct file_operations proc_pid_attr_operations = { .llseek = generic_file_llseek, }; +#define LSM_DIR_OPS(LSM) \ +static int proc_##LSM##_attr_dir_iterate(struct file *filp, \ + struct dir_context *ctx) \ +{ \ + return proc_pident_readdir(filp, ctx, \ + LSM##_attr_dir_stuff, \ + ARRAY_SIZE(LSM##_attr_dir_stuff)); \ +} \ +\ +static const struct file_operations proc_##LSM##_attr_dir_ops = { \ + .read = generic_read_dir, \ + .iterate = proc_##LSM##_attr_dir_iterate, \ + .llseek = default_llseek, \ +}; \ +\ +static struct dentry *proc_##LSM##_attr_dir_lookup(struct inode *dir, \ + struct dentry *dentry, unsigned int flags) \ +{ \ + return proc_pident_lookup(dir, dentry, \ + LSM##_attr_dir_stuff, \ + ARRAY_SIZE(LSM##_attr_dir_stuff)); \ +} \ +\ +static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \ + .lookup = proc_##LSM##_attr_dir_lookup, \ + .getattr = pid_getattr, \ + .setattr = proc_setattr, \ +} + +#ifdef CONFIG_SECURITY_SMACK +static const struct pid_entry smack_attr_dir_stuff[] = { + ATTR("smack", "current", 0666), +}; +LSM_DIR_OPS(smack); +#endif + static const struct pid_entry attr_dir_stuff[] = { - REG("current", S_IRUGO|S_IWUGO, proc_pid_attr_operations), - REG("prev", S_IRUGO, proc_pid_attr_operations), - REG("exec", S_IRUGO|S_IWUGO, proc_pid_attr_operations), - REG("fscreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations), - REG("keycreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations), - REG("sockcreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations), + ATTR(NULL, "current", 0666), + ATTR(NULL, "prev", 0444), + ATTR(NULL, "exec", 0666), + ATTR(NULL, "fscreate", 0666), + ATTR(NULL, "keycreate", 0666), + ATTR(NULL, "sockcreate", 0666), +#ifdef CONFIG_SECURITY_SMACK + DIR("smack", 0555, + proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops), +#endif }; static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 5185d7f6a51e..d4f9989063d0 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -81,6 +81,7 @@ union proc_op { int (*proc_show)(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); + const char *lsm; }; struct proc_inode { diff --git a/include/linux/security.h b/include/linux/security.h index dbfb5a66babb..b2c5333ed4b5 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -366,8 +366,10 @@ int security_sem_semctl(struct kern_ipc_perm *sma, int cmd); int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter); void security_d_instantiate(struct dentry *dentry, struct inode *inode); -int security_getprocattr(struct task_struct *p, char *name, char **value); -int security_setprocattr(const char *name, void *value, size_t size); +int security_getprocattr(struct task_struct *p, const char *lsm, char *name, + char **value); +int security_setprocattr(const char *lsm, const char *name, void *value, + size_t size); int security_netlink_send(struct sock *sk, struct sk_buff *skb); int security_ismaclabel(const char *name); int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); @@ -1112,15 +1114,18 @@ static inline int security_sem_semop(struct kern_ipc_perm *sma, return 0; } -static inline void security_d_instantiate(struct dentry *dentry, struct inode *inode) +static inline void security_d_instantiate(struct dentry *dentry, + struct inode *inode) { } -static inline int security_getprocattr(struct task_struct *p, char *name, char **value) +static inline int security_getprocattr(struct task_struct *p, const char *lsm, + char *name, char **value) { return -EINVAL; } -static inline int security_setprocattr(char *name, void *value, size_t size) +static inline int security_setprocattr(const char *lsm, char *name, + void *value, size_t size) { return -EINVAL; } diff --git a/security/security.c b/security/security.c index 9411f659454b..60b39db95c2f 100644 --- a/security/security.c +++ b/security/security.c @@ -1485,14 +1485,30 @@ void security_d_instantiate(struct dentry *dentry, struct inode *inode) } EXPORT_SYMBOL(security_d_instantiate); -int security_getprocattr(struct task_struct *p, char *name, char **value) +int security_getprocattr(struct task_struct *p, const char *lsm, char *name, + char **value) { - return call_int_hook(getprocattr, -EINVAL, p, name, value); + struct security_hook_list *hp; + + hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) { + if (lsm != NULL && strcmp(lsm, hp->lsm)) + continue; + return hp->hook.getprocattr(p, name, value); + } + return -EINVAL; } -int security_setprocattr(const char *name, void *value, size_t size) +int security_setprocattr(const char *lsm, const char *name, void *value, + size_t size) { - return call_int_hook(setprocattr, -EINVAL, name, value, size); + struct security_hook_list *hp; + + hlist_for_each_entry(hp, &security_hook_heads.setprocattr, list) { + if (lsm != NULL && strcmp(lsm, hp->lsm)) + continue; + return hp->hook.setprocattr(name, value, size); + } + return -EINVAL; } int security_netlink_send(struct sock *sk, struct sk_buff *skb) -- cgit v1.2.3 From 3d252529480c68bfd6a6774652df7c8968b28e41 Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Fri, 21 Sep 2018 17:17:34 -0700 Subject: SELinux: Remove unused selinux_is_enabled There are no longer users of selinux_is_enabled(). Remove it. As selinux_is_enabled() is the only reason for include/linux/selinux.h remove that as well. Signed-off-by: Casey Schaufler Reviewed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/cred.h | 1 - include/linux/selinux.h | 35 ----------------------------------- security/selinux/Makefile | 2 +- security/selinux/exports.c | 23 ----------------------- security/selinux/hooks.c | 1 - security/selinux/include/audit.h | 3 --- security/selinux/ss/services.c | 1 - 7 files changed, 1 insertion(+), 65 deletions(-) delete mode 100644 include/linux/selinux.h delete mode 100644 security/selinux/exports.c (limited to 'include') diff --git a/include/linux/cred.h b/include/linux/cred.h index 4907c9df86b3..ddd45bb74887 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/selinux.h b/include/linux/selinux.h deleted file mode 100644 index 44f459612690..000000000000 --- a/include/linux/selinux.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * SELinux services exported to the rest of the kernel. - * - * Author: James Morris - * - * Copyright (C) 2005 Red Hat, Inc., James Morris - * Copyright (C) 2006 Trusted Computer Solutions, Inc. - * Copyright (C) 2006 IBM Corporation, Timothy R. Chavez - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2, - * as published by the Free Software Foundation. - */ -#ifndef _LINUX_SELINUX_H -#define _LINUX_SELINUX_H - -struct selinux_audit_rule; -struct audit_context; -struct kern_ipc_perm; - -#ifdef CONFIG_SECURITY_SELINUX - -/** - * selinux_is_enabled - is SELinux enabled? - */ -bool selinux_is_enabled(void); -#else - -static inline bool selinux_is_enabled(void) -{ - return false; -} -#endif /* CONFIG_SECURITY_SELINUX */ - -#endif /* _LINUX_SELINUX_H */ diff --git a/security/selinux/Makefile b/security/selinux/Makefile index c7161f8792b2..ccf950409384 100644 --- a/security/selinux/Makefile +++ b/security/selinux/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_SECURITY_SELINUX) := selinux.o selinux-y := avc.o hooks.o selinuxfs.o netlink.o nlmsgtab.o netif.o \ - netnode.o netport.o ibpkey.o exports.o \ + netnode.o netport.o ibpkey.o \ ss/ebitmap.o ss/hashtab.o ss/symtab.o ss/sidtab.o ss/avtab.o \ ss/policydb.o ss/services.o ss/conditional.o ss/mls.o ss/status.o diff --git a/security/selinux/exports.c b/security/selinux/exports.c deleted file mode 100644 index e75dd94e2d2b..000000000000 --- a/security/selinux/exports.c +++ /dev/null @@ -1,23 +0,0 @@ -/* - * SELinux services exported to the rest of the kernel. - * - * Author: James Morris - * - * Copyright (C) 2005 Red Hat, Inc., James Morris - * Copyright (C) 2006 Trusted Computer Solutions, Inc. - * Copyright (C) 2006 IBM Corporation, Timothy R. Chavez - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2, - * as published by the Free Software Foundation. - */ -#include -#include - -#include "security.h" - -bool selinux_is_enabled(void) -{ - return selinux_enabled; -} -EXPORT_SYMBOL_GPL(selinux_is_enabled); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index ad227177550b..169cf5b3334b 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -79,7 +79,6 @@ #include #include #include -#include #include #include #include diff --git a/security/selinux/include/audit.h b/security/selinux/include/audit.h index 1bdf973433cc..36e1d44c0209 100644 --- a/security/selinux/include/audit.h +++ b/security/selinux/include/audit.h @@ -1,9 +1,6 @@ /* * SELinux support for the Audit LSM hooks * - * Most of below header was moved from include/linux/selinux.h which - * is released under below copyrights: - * * Author: James Morris * * Copyright (C) 2005 Red Hat, Inc., James Morris diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index dd44126c8d14..d6e7b4856d93 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -49,7 +49,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From bbd3662a834813730912a58efb44dd6df6d952e6 Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Mon, 12 Nov 2018 09:30:56 -0800 Subject: Infrastructure management of the cred security blob Move management of the cred security blob out of the security modules and into the security infrastructre. Instead of allocating and freeing space the security modules tell the infrastructure how much space they require. Signed-off-by: Casey Schaufler Reviewed-by: Kees Cook [kees: adjusted for ordered init series] Signed-off-by: Kees Cook --- include/linux/lsm_hooks.h | 12 ++++++ security/apparmor/include/cred.h | 4 +- security/apparmor/include/lib.h | 4 ++ security/apparmor/lsm.c | 9 ++++ security/security.c | 89 ++++++++++++++++++++++++++++++++++++++- security/selinux/hooks.c | 51 +++++----------------- security/selinux/include/objsec.h | 4 +- security/smack/smack.h | 3 +- security/smack/smack_lsm.c | 79 +++++++++++----------------------- security/tomoyo/common.h | 3 +- security/tomoyo/tomoyo.c | 6 +++ 11 files changed, 162 insertions(+), 102 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0c908c091a03..dd33666567bc 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2027,6 +2027,13 @@ struct security_hook_list { char *lsm; } __randomize_layout; +/* + * Security blob size or offset data. + */ +struct lsm_blob_sizes { + int lbs_cred; +}; + /* * Initializing a security_hook_list structure takes * up a lot of space in a source file. This macro takes @@ -2056,6 +2063,7 @@ struct lsm_info { unsigned long flags; /* Optional: flags describing LSM */ int *enabled; /* Optional: controlled by CONFIG_LSM */ int (*init)(void); /* Required. */ + struct lsm_blob_sizes *blobs; /* Optional: for blob sharing. */ }; extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; @@ -2095,4 +2103,8 @@ static inline void security_delete_hooks(struct security_hook_list *hooks, #define __lsm_ro_after_init __ro_after_init #endif /* CONFIG_SECURITY_WRITABLE_HOOKS */ +#ifdef CONFIG_SECURITY +void __init lsm_early_cred(struct cred *cred); +#endif + #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/security/apparmor/include/cred.h b/security/apparmor/include/cred.h index a757370f2a0c..b9504a05fddc 100644 --- a/security/apparmor/include/cred.h +++ b/security/apparmor/include/cred.h @@ -25,7 +25,7 @@ static inline struct aa_label *cred_label(const struct cred *cred) { - struct aa_label **blob = cred->security; + struct aa_label **blob = cred->security + apparmor_blob_sizes.lbs_cred; AA_BUG(!blob); return *blob; @@ -34,7 +34,7 @@ static inline struct aa_label *cred_label(const struct cred *cred) static inline void set_cred_label(const struct cred *cred, struct aa_label *label) { - struct aa_label **blob = cred->security; + struct aa_label **blob = cred->security + apparmor_blob_sizes.lbs_cred; AA_BUG(!blob); *blob = label; diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h index 6505e1ad9e23..bbe9b384d71d 100644 --- a/security/apparmor/include/lib.h +++ b/security/apparmor/include/lib.h @@ -16,6 +16,7 @@ #include #include +#include #include "match.h" @@ -55,6 +56,9 @@ const char *aa_splitn_fqname(const char *fqname, size_t n, const char **ns_name, size_t *ns_len); void aa_info_message(const char *str); +/* Security blob offsets */ +extern struct lsm_blob_sizes apparmor_blob_sizes; + /** * aa_strneq - compare null terminated @str to a non null terminated substring * @str: a null terminated string diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 8c2cb4b1a6c3..d5e4a384f205 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1151,6 +1151,13 @@ static int apparmor_inet_conn_request(struct sock *sk, struct sk_buff *skb, } #endif +/* + * The cred blob is a pointer to, not an instance of, an aa_task_ctx. + */ +struct lsm_blob_sizes apparmor_blob_sizes __lsm_ro_after_init = { + .lbs_cred = sizeof(struct aa_task_ctx *), +}; + static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme), @@ -1485,6 +1492,7 @@ static int __init set_init_ctx(void) if (!ctx) return -ENOMEM; + lsm_early_cred(cred); set_cred_label(cred, aa_get_label(ns_unconfined(root_ns))); task_ctx(current) = ctx; @@ -1725,5 +1733,6 @@ DEFINE_LSM(apparmor) = { .name = "apparmor", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &apparmor_enabled, + .blobs = &apparmor_blob_sizes, .init = apparmor_init, }; diff --git a/security/security.c b/security/security.c index 60b39db95c2f..09be8ce007a2 100644 --- a/security/security.c +++ b/security/security.c @@ -41,6 +41,8 @@ struct security_hook_heads security_hook_heads __lsm_ro_after_init; static ATOMIC_NOTIFIER_HEAD(lsm_notifier_chain); char *lsm_names; +static struct lsm_blob_sizes blob_sizes __lsm_ro_after_init; + /* Boot-time LSM user choice */ static __initdata const char *chosen_lsm_order; static __initdata const char *chosen_major_lsm; @@ -139,6 +141,25 @@ static bool __init lsm_allowed(struct lsm_info *lsm) return true; } +static void __init lsm_set_blob_size(int *need, int *lbs) +{ + int offset; + + if (*need > 0) { + offset = *lbs; + *lbs += *need; + *need = offset; + } +} + +static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) +{ + if (!needed) + return; + + lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred); +} + /* Prepare LSM for initialization. */ static void __init prepare_lsm(struct lsm_info *lsm) { @@ -153,6 +174,8 @@ static void __init prepare_lsm(struct lsm_info *lsm) exclusive = lsm; init_debug("exclusive chosen: %s\n", lsm->name); } + + lsm_set_blob_sizes(lsm->blobs); } } @@ -255,6 +278,8 @@ static void __init ordered_lsm_init(void) for (lsm = ordered_lsms; *lsm; lsm++) prepare_lsm(*lsm); + init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); + for (lsm = ordered_lsms; *lsm; lsm++) initialize_lsm(*lsm); @@ -382,6 +407,47 @@ int unregister_lsm_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_lsm_notifier); +/** + * lsm_cred_alloc - allocate a composite cred blob + * @cred: the cred that needs a blob + * @gfp: allocation type + * + * Allocate the cred blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +static int lsm_cred_alloc(struct cred *cred, gfp_t gfp) +{ + if (blob_sizes.lbs_cred == 0) { + cred->security = NULL; + return 0; + } + + cred->security = kzalloc(blob_sizes.lbs_cred, gfp); + if (cred->security == NULL) + return -ENOMEM; + return 0; +} + +/** + * lsm_early_cred - during initialization allocate a composite cred blob + * @cred: the cred that needs a blob + * + * Allocate the cred blob for all the modules if it's not already there + */ +void __init lsm_early_cred(struct cred *cred) +{ + int rc; + + if (cred == NULL) + panic("%s: NULL cred.\n", __func__); + if (cred->security != NULL) + return; + rc = lsm_cred_alloc(cred, GFP_KERNEL); + if (rc) + panic("%s: Early cred alloc failed.\n", __func__); +} + /* * Hook list operation macros. * @@ -1195,17 +1261,36 @@ void security_task_free(struct task_struct *task) int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) { - return call_int_hook(cred_alloc_blank, 0, cred, gfp); + int rc = lsm_cred_alloc(cred, gfp); + + if (rc) + return rc; + + rc = call_int_hook(cred_alloc_blank, 0, cred, gfp); + if (rc) + security_cred_free(cred); + return rc; } void security_cred_free(struct cred *cred) { call_void_hook(cred_free, cred); + + kfree(cred->security); + cred->security = NULL; } int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp) { - return call_int_hook(cred_prepare, 0, new, old, gfp); + int rc = lsm_cred_alloc(new, gfp); + + if (rc) + return rc; + + rc = call_int_hook(cred_prepare, 0, new, old, gfp); + if (rc) + security_cred_free(new); + return rc; } void security_transfer_creds(struct cred *new, const struct cred *old) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 169cf5b3334b..239b13b442e7 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -210,12 +210,9 @@ static void cred_init_security(void) struct cred *cred = (struct cred *) current->real_cred; struct task_security_struct *tsec; - tsec = kzalloc(sizeof(struct task_security_struct), GFP_KERNEL); - if (!tsec) - panic("SELinux: Failed to initialize initial task.\n"); - + lsm_early_cred(cred); + tsec = selinux_cred(cred); tsec->osid = tsec->sid = SECINITSID_KERNEL; - cred->security = tsec; } /* @@ -3685,47 +3682,16 @@ static int selinux_task_alloc(struct task_struct *task, sid, sid, SECCLASS_PROCESS, PROCESS__FORK, NULL); } -/* - * allocate the SELinux part of blank credentials - */ -static int selinux_cred_alloc_blank(struct cred *cred, gfp_t gfp) -{ - struct task_security_struct *tsec; - - tsec = kzalloc(sizeof(struct task_security_struct), gfp); - if (!tsec) - return -ENOMEM; - - cred->security = tsec; - return 0; -} - -/* - * detach and free the LSM part of a set of credentials - */ -static void selinux_cred_free(struct cred *cred) -{ - struct task_security_struct *tsec = selinux_cred(cred); - - kfree(tsec); -} - /* * prepare a new set of credentials for modification */ static int selinux_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { - const struct task_security_struct *old_tsec; - struct task_security_struct *tsec; - - old_tsec = selinux_cred(old); - - tsec = kmemdup(old_tsec, sizeof(struct task_security_struct), gfp); - if (!tsec) - return -ENOMEM; + const struct task_security_struct *old_tsec = selinux_cred(old); + struct task_security_struct *tsec = selinux_cred(new); - new->security = tsec; + *tsec = *old_tsec; return 0; } @@ -6678,6 +6644,10 @@ static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) } #endif +struct lsm_blob_sizes selinux_blob_sizes __lsm_ro_after_init = { + .lbs_cred = sizeof(struct task_security_struct), +}; + static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), @@ -6761,8 +6731,6 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(file_open, selinux_file_open), LSM_HOOK_INIT(task_alloc, selinux_task_alloc), - LSM_HOOK_INIT(cred_alloc_blank, selinux_cred_alloc_blank), - LSM_HOOK_INIT(cred_free, selinux_cred_free), LSM_HOOK_INIT(cred_prepare, selinux_cred_prepare), LSM_HOOK_INIT(cred_transfer, selinux_cred_transfer), LSM_HOOK_INIT(cred_getsecid, selinux_cred_getsecid), @@ -6981,6 +6949,7 @@ DEFINE_LSM(selinux) = { .name = "selinux", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &selinux_enabled, + .blobs = &selinux_blob_sizes, .init = selinux_init, }; diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index 734b6833bdff..c2974b031d05 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include "flask.h" #include "avc.h" @@ -158,9 +159,10 @@ struct bpf_security_struct { u32 sid; /*SID of bpf obj creater*/ }; +extern struct lsm_blob_sizes selinux_blob_sizes; static inline struct task_security_struct *selinux_cred(const struct cred *cred) { - return cred->security; + return cred->security + selinux_blob_sizes.lbs_cred; } #endif /* _SELINUX_OBJSEC_H_ */ diff --git a/security/smack/smack.h b/security/smack/smack.h index 01a922856eba..b27eb252e953 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -336,6 +336,7 @@ extern struct smack_known *smack_syslog_label; extern struct smack_known *smack_unconfined; #endif extern int smack_ptrace_rule; +extern struct lsm_blob_sizes smack_blob_sizes; extern struct smack_known smack_known_floor; extern struct smack_known smack_known_hat; @@ -358,7 +359,7 @@ extern struct hlist_head smack_known_hash[SMACK_HASH_SLOTS]; static inline struct task_smack *smack_cred(const struct cred *cred) { - return cred->security; + return cred->security + smack_blob_sizes.lbs_cred; } /* diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 9a050ca17296..bad27a8e1631 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -326,29 +326,20 @@ static struct inode_smack *new_inode_smack(struct smack_known *skp) } /** - * new_task_smack - allocate a task security blob + * init_task_smack - initialize a task security blob + * @tsp: blob to initialize * @task: a pointer to the Smack label for the running task * @forked: a pointer to the Smack label for the forked task - * @gfp: type of the memory for the allocation * - * Returns the new blob or NULL if there's no memory available */ -static struct task_smack *new_task_smack(struct smack_known *task, - struct smack_known *forked, gfp_t gfp) +static void init_task_smack(struct task_smack *tsp, struct smack_known *task, + struct smack_known *forked) { - struct task_smack *tsp; - - tsp = kzalloc(sizeof(struct task_smack), gfp); - if (tsp == NULL) - return NULL; - tsp->smk_task = task; tsp->smk_forked = forked; INIT_LIST_HEAD(&tsp->smk_rules); INIT_LIST_HEAD(&tsp->smk_relabel); mutex_init(&tsp->smk_rules_lock); - - return tsp; } /** @@ -1881,14 +1872,7 @@ static int smack_file_open(struct file *file) */ static int smack_cred_alloc_blank(struct cred *cred, gfp_t gfp) { - struct task_smack *tsp; - - tsp = new_task_smack(NULL, NULL, gfp); - if (tsp == NULL) - return -ENOMEM; - - cred->security = tsp; - + init_task_smack(smack_cred(cred), NULL, NULL); return 0; } @@ -1905,10 +1889,6 @@ static void smack_cred_free(struct cred *cred) struct list_head *l; struct list_head *n; - if (tsp == NULL) - return; - cred->security = NULL; - smk_destroy_label_list(&tsp->smk_relabel); list_for_each_safe(l, n, &tsp->smk_rules) { @@ -1916,7 +1896,6 @@ static void smack_cred_free(struct cred *cred) list_del(&rp->list); kfree(rp); } - kfree(tsp); } /** @@ -1931,14 +1910,10 @@ static int smack_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { struct task_smack *old_tsp = smack_cred(old); - struct task_smack *new_tsp; + struct task_smack *new_tsp = smack_cred(new); int rc; - new_tsp = new_task_smack(old_tsp->smk_task, old_tsp->smk_task, gfp); - if (new_tsp == NULL) - return -ENOMEM; - - new->security = new_tsp; + init_task_smack(new_tsp, old_tsp->smk_task, old_tsp->smk_task); rc = smk_copy_rules(&new_tsp->smk_rules, &old_tsp->smk_rules, gfp); if (rc != 0) @@ -1946,10 +1921,7 @@ static int smack_cred_prepare(struct cred *new, const struct cred *old, rc = smk_copy_relabel(&new_tsp->smk_relabel, &old_tsp->smk_relabel, gfp); - if (rc != 0) - return rc; - - return 0; + return rc; } /** @@ -4581,6 +4553,10 @@ static int smack_dentry_create_files_as(struct dentry *dentry, int mode, return 0; } +struct lsm_blob_sizes smack_blob_sizes __lsm_ro_after_init = { + .lbs_cred = sizeof(struct task_smack), +}; + static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, smack_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, smack_ptrace_traceme), @@ -4758,20 +4734,25 @@ static __init void init_smack_known_list(void) */ static __init int smack_init(void) { - struct cred *cred; + struct cred *cred = (struct cred *) current->cred; struct task_smack *tsp; smack_inode_cache = KMEM_CACHE(inode_smack, 0); if (!smack_inode_cache) return -ENOMEM; - tsp = new_task_smack(&smack_known_floor, &smack_known_floor, - GFP_KERNEL); - if (tsp == NULL) { - kmem_cache_destroy(smack_inode_cache); - return -ENOMEM; - } + lsm_early_cred(cred); + /* + * Set the security state for the initial task. + */ + tsp = smack_cred(cred); + init_task_smack(tsp, &smack_known_floor, &smack_known_floor); + + /* + * Register with LSM + */ + security_add_hooks(smack_hooks, ARRAY_SIZE(smack_hooks), "smack"); smack_enabled = 1; pr_info("Smack: Initializing.\n"); @@ -4785,20 +4766,9 @@ static __init int smack_init(void) pr_info("Smack: IPv6 Netfilter enabled.\n"); #endif - /* - * Set the security state for the initial task. - */ - cred = (struct cred *) current->cred; - cred->security = tsp; - /* initialize the smack_known_list */ init_smack_known_list(); - /* - * Register with LSM - */ - security_add_hooks(smack_hooks, ARRAY_SIZE(smack_hooks), "smack"); - return 0; } @@ -4809,5 +4779,6 @@ static __init int smack_init(void) DEFINE_LSM(smack) = { .name = "smack", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, + .blobs = &smack_blob_sizes, .init = smack_init, }; diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h index 41898613d93b..4fc17294a12d 100644 --- a/security/tomoyo/common.h +++ b/security/tomoyo/common.h @@ -1087,6 +1087,7 @@ extern struct tomoyo_domain_info tomoyo_kernel_domain; extern struct tomoyo_policy_namespace tomoyo_kernel_namespace; extern unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT]; extern unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT]; +extern struct lsm_blob_sizes tomoyo_blob_sizes; /********** Inlined functions. **********/ @@ -1206,7 +1207,7 @@ static inline void tomoyo_put_group(struct tomoyo_group *group) */ static inline struct tomoyo_domain_info **tomoyo_cred(const struct cred *cred) { - return (struct tomoyo_domain_info **)&cred->security; + return cred->security + tomoyo_blob_sizes.lbs_cred; } /** diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 15864307925d..9094cf41a247 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -509,6 +509,10 @@ static int tomoyo_socket_sendmsg(struct socket *sock, struct msghdr *msg, return tomoyo_socket_sendmsg_permission(sock, msg, size); } +struct lsm_blob_sizes tomoyo_blob_sizes __lsm_ro_after_init = { + .lbs_cred = sizeof(struct tomoyo_domain_info *), +}; + /* * tomoyo_security_ops is a "struct security_operations" which is used for * registering TOMOYO. @@ -562,6 +566,7 @@ static int __init tomoyo_init(void) /* register ourselves with the security framework */ security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), "tomoyo"); printk(KERN_INFO "TOMOYO Linux initialized\n"); + lsm_early_cred(cred); blob = tomoyo_cred(cred); *blob = &tomoyo_kernel_domain; tomoyo_mm_init(); @@ -573,5 +578,6 @@ DEFINE_LSM(tomoyo) = { .name = "tomoyo", .enabled = &tomoyo_enabled, .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, + .blobs = &tomoyo_blob_sizes, .init = tomoyo_init, }; -- cgit v1.2.3 From 33bf60cabcc7687b194a689b068b65e9ecd556be Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Mon, 12 Nov 2018 12:02:49 -0800 Subject: LSM: Infrastructure management of the file security Move management of the file->f_security blob out of the individual security modules and into the infrastructure. The modules no longer allocate or free the data, instead they tell the infrastructure how much space they require. Signed-off-by: Casey Schaufler Reviewed-by: Kees Cook [kees: adjusted for ordered init series] Signed-off-by: Kees Cook --- include/linux/lsm_hooks.h | 1 + security/apparmor/include/file.h | 5 +++- security/apparmor/lsm.c | 19 +++++++------- security/security.c | 54 ++++++++++++++++++++++++++++++++++++--- security/selinux/hooks.c | 25 ++---------------- security/selinux/include/objsec.h | 2 +- security/smack/smack.h | 3 ++- security/smack/smack_lsm.c | 14 +--------- 8 files changed, 72 insertions(+), 51 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index dd33666567bc..e8cef019b645 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2032,6 +2032,7 @@ struct security_hook_list { */ struct lsm_blob_sizes { int lbs_cred; + int lbs_file; }; /* diff --git a/security/apparmor/include/file.h b/security/apparmor/include/file.h index 4c2c8ac8842f..8be09208cf7c 100644 --- a/security/apparmor/include/file.h +++ b/security/apparmor/include/file.h @@ -32,7 +32,10 @@ struct path; AA_MAY_CHMOD | AA_MAY_CHOWN | AA_MAY_LOCK | \ AA_EXEC_MMAP | AA_MAY_LINK) -#define file_ctx(X) ((struct aa_file_ctx *)(X)->f_security) +static inline struct aa_file_ctx *file_ctx(struct file *file) +{ + return file->f_security + apparmor_blob_sizes.lbs_file; +} /* struct aa_file_ctx - the AppArmor context the file was opened in * @lock: lock to update the ctx diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index d5e4a384f205..6821187b06ad 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -434,21 +434,21 @@ static int apparmor_file_open(struct file *file) static int apparmor_file_alloc_security(struct file *file) { - int error = 0; - - /* freed by apparmor_file_free_security */ + struct aa_file_ctx *ctx = file_ctx(file); struct aa_label *label = begin_current_label_crit_section(); - file->f_security = aa_alloc_file_ctx(label, GFP_KERNEL); - if (!file_ctx(file)) - error = -ENOMEM; - end_current_label_crit_section(label); - return error; + spin_lock_init(&ctx->lock); + rcu_assign_pointer(ctx->label, aa_get_label(label)); + end_current_label_crit_section(label); + return 0; } static void apparmor_file_free_security(struct file *file) { - aa_free_file_ctx(file_ctx(file)); + struct aa_file_ctx *ctx = file_ctx(file); + + if (ctx) + aa_put_label(rcu_access_pointer(ctx->label)); } static int common_file_perm(const char *op, struct file *file, u32 mask) @@ -1156,6 +1156,7 @@ static int apparmor_inet_conn_request(struct sock *sk, struct sk_buff *skb, */ struct lsm_blob_sizes apparmor_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct aa_task_ctx *), + .lbs_file = sizeof(struct aa_file_ctx), }; static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { diff --git a/security/security.c b/security/security.c index 09be8ce007a2..f32d7d2075c6 100644 --- a/security/security.c +++ b/security/security.c @@ -40,6 +40,8 @@ struct security_hook_heads security_hook_heads __lsm_ro_after_init; static ATOMIC_NOTIFIER_HEAD(lsm_notifier_chain); +static struct kmem_cache *lsm_file_cache; + char *lsm_names; static struct lsm_blob_sizes blob_sizes __lsm_ro_after_init; @@ -158,6 +160,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) return; lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred); + lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file); } /* Prepare LSM for initialization. */ @@ -279,6 +282,15 @@ static void __init ordered_lsm_init(void) prepare_lsm(*lsm); init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); + init_debug("file blob size = %d\n", blob_sizes.lbs_file); + + /* + * Create any kmem_caches needed for blobs + */ + if (blob_sizes.lbs_file) + lsm_file_cache = kmem_cache_create("lsm_file_cache", + blob_sizes.lbs_file, 0, + SLAB_PANIC, NULL); for (lsm = ordered_lsms; *lsm; lsm++) initialize_lsm(*lsm); @@ -448,6 +460,27 @@ void __init lsm_early_cred(struct cred *cred) panic("%s: Early cred alloc failed.\n", __func__); } +/** + * lsm_file_alloc - allocate a composite file blob + * @file: the file that needs a blob + * + * Allocate the file blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +static int lsm_file_alloc(struct file *file) +{ + if (!lsm_file_cache) { + file->f_security = NULL; + return 0; + } + + file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL); + if (file->f_security == NULL) + return -ENOMEM; + return 0; +} + /* * Hook list operation macros. * @@ -1144,12 +1177,27 @@ int security_file_permission(struct file *file, int mask) int security_file_alloc(struct file *file) { - return call_int_hook(file_alloc_security, 0, file); + int rc = lsm_file_alloc(file); + + if (rc) + return rc; + rc = call_int_hook(file_alloc_security, 0, file); + if (unlikely(rc)) + security_file_free(file); + return rc; } void security_file_free(struct file *file) { + void *blob; + call_void_hook(file_free_security, file); + + blob = file->f_security; + if (blob) { + file->f_security = NULL; + kmem_cache_free(lsm_file_cache, blob); + } } int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) @@ -1267,7 +1315,7 @@ int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) return rc; rc = call_int_hook(cred_alloc_blank, 0, cred, gfp); - if (rc) + if (unlikely(rc)) security_cred_free(cred); return rc; } @@ -1288,7 +1336,7 @@ int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp) return rc; rc = call_int_hook(cred_prepare, 0, new, old, gfp); - if (rc) + if (unlikely(rc)) security_cred_free(new); return rc; } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 620be0367c0b..632813821da6 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -146,7 +146,6 @@ static int __init checkreqprot_setup(char *str) __setup("checkreqprot=", checkreqprot_setup); static struct kmem_cache *sel_inode_cache; -static struct kmem_cache *file_security_cache; /** * selinux_secmark_enabled - Check to see if SECMARK is currently enabled @@ -378,27 +377,15 @@ static void inode_free_security(struct inode *inode) static int file_alloc_security(struct file *file) { - struct file_security_struct *fsec; + struct file_security_struct *fsec = selinux_file(file); u32 sid = current_sid(); - fsec = kmem_cache_zalloc(file_security_cache, GFP_KERNEL); - if (!fsec) - return -ENOMEM; - fsec->sid = sid; fsec->fown_sid = sid; - file->f_security = fsec; return 0; } -static void file_free_security(struct file *file) -{ - struct file_security_struct *fsec = selinux_file(file); - file->f_security = NULL; - kmem_cache_free(file_security_cache, fsec); -} - static int superblock_alloc_security(struct super_block *sb) { struct superblock_security_struct *sbsec; @@ -3345,11 +3332,6 @@ static int selinux_file_alloc_security(struct file *file) return file_alloc_security(file); } -static void selinux_file_free_security(struct file *file) -{ - file_free_security(file); -} - /* * Check whether a task has the ioctl permission and cmd * operation to an inode. @@ -6646,6 +6628,7 @@ static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) struct lsm_blob_sizes selinux_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct task_security_struct), + .lbs_file = sizeof(struct file_security_struct), }; static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { @@ -6717,7 +6700,6 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(file_permission, selinux_file_permission), LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), - LSM_HOOK_INIT(file_free_security, selinux_file_free_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr), @@ -6902,9 +6884,6 @@ static __init int selinux_init(void) sel_inode_cache = kmem_cache_create("selinux_inode_security", sizeof(struct inode_security_struct), 0, SLAB_PANIC, NULL); - file_security_cache = kmem_cache_create("selinux_file_security", - sizeof(struct file_security_struct), - 0, SLAB_PANIC, NULL); avc_init(); avtab_cache_init(); diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index e0ac2992e059..96374dbf4ace 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -167,7 +167,7 @@ static inline struct task_security_struct *selinux_cred(const struct cred *cred) static inline struct file_security_struct *selinux_file(const struct file *file) { - return file->f_security; + return file->f_security + selinux_blob_sizes.lbs_file; } #endif /* _SELINUX_OBJSEC_H_ */ diff --git a/security/smack/smack.h b/security/smack/smack.h index 50854969a391..2007d38d0e46 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -364,7 +364,8 @@ static inline struct task_smack *smack_cred(const struct cred *cred) static inline struct smack_known **smack_file(const struct file *file) { - return (struct smack_known **)&file->f_security; + return (struct smack_known **)(file->f_security + + smack_blob_sizes.lbs_file); } /* diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 8f72641f94ab..7c76668ea3a6 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1495,18 +1495,6 @@ static int smack_file_alloc_security(struct file *file) return 0; } -/** - * smack_file_free_security - clear a file security blob - * @file: the object - * - * The security blob for a file is a pointer to the master - * label list, so no memory is freed. - */ -static void smack_file_free_security(struct file *file) -{ - file->f_security = NULL; -} - /** * smack_file_ioctl - Smack check on ioctls * @file: the object @@ -4559,6 +4547,7 @@ static int smack_dentry_create_files_as(struct dentry *dentry, int mode, struct lsm_blob_sizes smack_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct task_smack), + .lbs_file = sizeof(struct smack_known *), }; static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { @@ -4595,7 +4584,6 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(inode_getsecid, smack_inode_getsecid), LSM_HOOK_INIT(file_alloc_security, smack_file_alloc_security), - LSM_HOOK_INIT(file_free_security, smack_file_free_security), LSM_HOOK_INIT(file_ioctl, smack_file_ioctl), LSM_HOOK_INIT(file_lock, smack_file_lock), LSM_HOOK_INIT(file_fcntl, smack_file_fcntl), -- cgit v1.2.3 From afb1cbe37440c7f38b9cf46fc331cc9dfd5cce21 Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Fri, 21 Sep 2018 17:19:29 -0700 Subject: LSM: Infrastructure management of the inode security Move management of the inode->i_security blob out of the individual security modules and into the security infrastructure. Instead of allocating the blobs from within the modules the modules tell the infrastructure how much space is required, and the space is allocated there. Signed-off-by: Casey Schaufler Reviewed-by: Kees Cook [kees: adjusted for ordered init series] Signed-off-by: Kees Cook --- include/linux/lsm_hooks.h | 3 ++ security/security.c | 64 +++++++++++++++++++++++++++++++-- security/selinux/hooks.c | 37 ++++--------------- security/selinux/include/objsec.h | 9 +++-- security/smack/smack.h | 2 +- security/smack/smack_lsm.c | 76 +++++++++------------------------------ 6 files changed, 93 insertions(+), 98 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index e8cef019b645..1c798e842de2 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2033,6 +2033,7 @@ struct security_hook_list { struct lsm_blob_sizes { int lbs_cred; int lbs_file; + int lbs_inode; }; /* @@ -2104,6 +2105,8 @@ static inline void security_delete_hooks(struct security_hook_list *hooks, #define __lsm_ro_after_init __ro_after_init #endif /* CONFIG_SECURITY_WRITABLE_HOOKS */ +extern int lsm_inode_alloc(struct inode *inode); + #ifdef CONFIG_SECURITY void __init lsm_early_cred(struct cred *cred); #endif diff --git a/security/security.c b/security/security.c index f32d7d2075c6..4989fb65e662 100644 --- a/security/security.c +++ b/security/security.c @@ -41,6 +41,7 @@ struct security_hook_heads security_hook_heads __lsm_ro_after_init; static ATOMIC_NOTIFIER_HEAD(lsm_notifier_chain); static struct kmem_cache *lsm_file_cache; +static struct kmem_cache *lsm_inode_cache; char *lsm_names; static struct lsm_blob_sizes blob_sizes __lsm_ro_after_init; @@ -161,6 +162,13 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred); lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file); + /* + * The inode blob gets an rcu_head in addition to + * what the modules might need. + */ + if (needed->lbs_inode && blob_sizes.lbs_inode == 0) + blob_sizes.lbs_inode = sizeof(struct rcu_head); + lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); } /* Prepare LSM for initialization. */ @@ -283,6 +291,7 @@ static void __init ordered_lsm_init(void) init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); init_debug("file blob size = %d\n", blob_sizes.lbs_file); + init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); /* * Create any kmem_caches needed for blobs @@ -291,6 +300,10 @@ static void __init ordered_lsm_init(void) lsm_file_cache = kmem_cache_create("lsm_file_cache", blob_sizes.lbs_file, 0, SLAB_PANIC, NULL); + if (blob_sizes.lbs_inode) + lsm_inode_cache = kmem_cache_create("lsm_inode_cache", + blob_sizes.lbs_inode, 0, + SLAB_PANIC, NULL); for (lsm = ordered_lsms; *lsm; lsm++) initialize_lsm(*lsm); @@ -481,6 +494,27 @@ static int lsm_file_alloc(struct file *file) return 0; } +/** + * lsm_inode_alloc - allocate a composite inode blob + * @inode: the inode that needs a blob + * + * Allocate the inode blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +int lsm_inode_alloc(struct inode *inode) +{ + if (!lsm_inode_cache) { + inode->i_security = NULL; + return 0; + } + + inode->i_security = kmem_cache_zalloc(lsm_inode_cache, GFP_NOFS); + if (inode->i_security == NULL) + return -ENOMEM; + return 0; +} + /* * Hook list operation macros. * @@ -740,14 +774,40 @@ EXPORT_SYMBOL(security_add_mnt_opt); int security_inode_alloc(struct inode *inode) { - inode->i_security = NULL; - return call_int_hook(inode_alloc_security, 0, inode); + int rc = lsm_inode_alloc(inode); + + if (unlikely(rc)) + return rc; + rc = call_int_hook(inode_alloc_security, 0, inode); + if (unlikely(rc)) + security_inode_free(inode); + return rc; +} + +static void inode_free_by_rcu(struct rcu_head *head) +{ + /* + * The rcu head is at the start of the inode blob + */ + kmem_cache_free(lsm_inode_cache, head); } void security_inode_free(struct inode *inode) { integrity_inode_free(inode); call_void_hook(inode_free_security, inode); + /* + * The inode may still be referenced in a path walk and + * a call to security_inode_permission() can be made + * after inode_free_security() is called. Ideally, the VFS + * wouldn't do this, but fixing that is a much harder + * job. For now, simply free the i_security via RCU, and + * leave the current inode->i_security pointer intact. + * The inode will be freed after the RCU grace period too. + */ + if (inode->i_security) + call_rcu((struct rcu_head *)inode->i_security, + inode_free_by_rcu); } int security_dentry_init_security(struct dentry *dentry, int mode, diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 2d691e8dfbbf..23da46cd6e37 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -145,8 +145,6 @@ static int __init checkreqprot_setup(char *str) } __setup("checkreqprot=", checkreqprot_setup); -static struct kmem_cache *sel_inode_cache; - /** * selinux_secmark_enabled - Check to see if SECMARK is currently enabled * @@ -242,13 +240,9 @@ static inline u32 task_sid(const struct task_struct *task) static int inode_alloc_security(struct inode *inode) { - struct inode_security_struct *isec; + struct inode_security_struct *isec = selinux_inode(inode); u32 sid = current_sid(); - isec = kmem_cache_zalloc(sel_inode_cache, GFP_NOFS); - if (!isec) - return -ENOMEM; - spin_lock_init(&isec->lock); INIT_LIST_HEAD(&isec->list); isec->inode = inode; @@ -256,7 +250,6 @@ static int inode_alloc_security(struct inode *inode) isec->sclass = SECCLASS_FILE; isec->task_sid = sid; isec->initialized = LABEL_INVALID; - inode->i_security = isec; return 0; } @@ -334,19 +327,14 @@ static struct inode_security_struct *backing_inode_security(struct dentry *dentr return selinux_inode(inode); } -static void inode_free_rcu(struct rcu_head *head) -{ - struct inode_security_struct *isec; - - isec = container_of(head, struct inode_security_struct, rcu); - kmem_cache_free(sel_inode_cache, isec); -} - static void inode_free_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); - struct superblock_security_struct *sbsec = inode->i_sb->s_security; + struct superblock_security_struct *sbsec; + if (!isec) + return; + sbsec = inode->i_sb->s_security; /* * As not all inode security structures are in a list, we check for * empty list outside of the lock to make sure that we won't waste @@ -362,17 +350,6 @@ static void inode_free_security(struct inode *inode) list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); } - - /* - * The inode may still be referenced in a path walk and - * a call to selinux_inode_permission() can be made - * after inode_free_security() is called. Ideally, the VFS - * wouldn't do this, but fixing that is a much harder - * job. For now, simply free the i_security via RCU, and - * leave the current inode->i_security pointer intact. - * The inode will be freed after the RCU grace period too. - */ - call_rcu(&isec->rcu, inode_free_rcu); } static int file_alloc_security(struct file *file) @@ -6629,6 +6606,7 @@ static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) struct lsm_blob_sizes selinux_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct task_security_struct), .lbs_file = sizeof(struct file_security_struct), + .lbs_inode = sizeof(struct inode_security_struct), }; static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { @@ -6881,9 +6859,6 @@ static __init int selinux_init(void) default_noexec = !(VM_DATA_DEFAULT_FLAGS & VM_EXEC); - sel_inode_cache = kmem_cache_create("selinux_inode_security", - sizeof(struct inode_security_struct), - 0, SLAB_PANIC, NULL); avc_init(); avtab_cache_init(); diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index 26b4ff6b4d81..562fad58c56b 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -57,10 +57,7 @@ enum label_initialized { struct inode_security_struct { struct inode *inode; /* back pointer to inode object */ - union { - struct list_head list; /* list of inode_security_struct */ - struct rcu_head rcu; /* for freeing the inode_security_struct */ - }; + struct list_head list; /* list of inode_security_struct */ u32 task_sid; /* SID of creating task */ u32 sid; /* SID of this object */ u16 sclass; /* security class of this object */ @@ -173,7 +170,9 @@ static inline struct file_security_struct *selinux_file(const struct file *file) static inline struct inode_security_struct *selinux_inode( const struct inode *inode) { - return inode->i_security; + if (unlikely(!inode->i_security)) + return NULL; + return inode->i_security + selinux_blob_sizes.lbs_inode; } #endif /* _SELINUX_OBJSEC_H_ */ diff --git a/security/smack/smack.h b/security/smack/smack.h index 436231dfae33..bf0abc35ca1c 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -370,7 +370,7 @@ static inline struct smack_known **smack_file(const struct file *file) static inline struct inode_smack *smack_inode(const struct inode *inode) { - return inode->i_security; + return inode->i_security + smack_blob_sizes.lbs_inode; } /* diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index ddffda39d107..804897c82810 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -305,24 +305,18 @@ static struct smack_known *smk_fetch(const char *name, struct inode *ip, } /** - * new_inode_smack - allocate an inode security blob + * init_inode_smack - initialize an inode security blob + * @isp: the blob to initialize * @skp: a pointer to the Smack label entry to use in the blob * - * Returns the new blob or NULL if there's no memory available */ -static struct inode_smack *new_inode_smack(struct smack_known *skp) +static void init_inode_smack(struct inode *inode, struct smack_known *skp) { - struct inode_smack *isp; - - isp = kmem_cache_zalloc(smack_inode_cache, GFP_NOFS); - if (isp == NULL) - return NULL; + struct inode_smack *isp = smack_inode(inode); isp->smk_inode = skp; isp->smk_flags = 0; mutex_init(&isp->smk_lock); - - return isp; } /** @@ -709,6 +703,13 @@ static int smack_set_mnt_opts(struct super_block *sb, if (sp->smk_flags & SMK_SB_INITIALIZED) return 0; + if (inode->i_security == NULL) { + int rc = lsm_inode_alloc(inode); + + if (rc) + return rc; + } + if (!smack_privileged(CAP_MAC_ADMIN)) { /* * Unprivileged mounts don't get to specify Smack values. @@ -773,17 +774,12 @@ static int smack_set_mnt_opts(struct super_block *sb, /* * Initialize the root inode. */ - isp = smack_inode(inode); - if (isp == NULL) { - isp = new_inode_smack(sp->smk_root); - if (isp == NULL) - return -ENOMEM; - inode->i_security = isp; - } else - isp->smk_inode = sp->smk_root; + init_inode_smack(inode, sp->smk_root); - if (transmute) + if (transmute) { + isp = smack_inode(inode); isp->smk_flags |= SMK_INODE_TRANSMUTE; + } return 0; } @@ -881,48 +877,10 @@ static int smack_inode_alloc_security(struct inode *inode) { struct smack_known *skp = smk_of_current(); - inode->i_security = new_inode_smack(skp); - if (inode->i_security == NULL) - return -ENOMEM; + init_inode_smack(inode, skp); return 0; } -/** - * smack_inode_free_rcu - Free inode_smack blob from cache - * @head: the rcu_head for getting inode_smack pointer - * - * Call back function called from call_rcu() to free - * the i_security blob pointer in inode - */ -static void smack_inode_free_rcu(struct rcu_head *head) -{ - struct inode_smack *issp; - - issp = container_of(head, struct inode_smack, smk_rcu); - kmem_cache_free(smack_inode_cache, issp); -} - -/** - * smack_inode_free_security - free an inode blob using call_rcu() - * @inode: the inode with a blob - * - * Clears the blob pointer in inode using RCU - */ -static void smack_inode_free_security(struct inode *inode) -{ - struct inode_smack *issp = smack_inode(inode); - - /* - * The inode may still be referenced in a path walk and - * a call to smack_inode_permission() can be made - * after smack_inode_free_security() is called. - * To avoid race condition free the i_security via RCU - * and leave the current inode->i_security pointer intact. - * The inode will be freed after the RCU grace period too. - */ - call_rcu(&issp->smk_rcu, smack_inode_free_rcu); -} - /** * smack_inode_init_security - copy out the smack from an inode * @inode: the newly created inode @@ -4548,6 +4506,7 @@ static int smack_dentry_create_files_as(struct dentry *dentry, int mode, struct lsm_blob_sizes smack_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct task_smack), .lbs_file = sizeof(struct smack_known *), + .lbs_inode = sizeof(struct inode_smack), }; static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { @@ -4565,7 +4524,6 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(bprm_set_creds, smack_bprm_set_creds), LSM_HOOK_INIT(inode_alloc_security, smack_inode_alloc_security), - LSM_HOOK_INIT(inode_free_security, smack_inode_free_security), LSM_HOOK_INIT(inode_init_security, smack_inode_init_security), LSM_HOOK_INIT(inode_link, smack_inode_link), LSM_HOOK_INIT(inode_unlink, smack_inode_unlink), -- cgit v1.2.3 From f4ad8f2c40769b3cc9497ba0883bbaf823f7752f Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Fri, 21 Sep 2018 17:19:37 -0700 Subject: LSM: Infrastructure management of the task security Move management of the task_struct->security blob out of the individual security modules and into the security infrastructure. Instead of allocating the blobs from within the modules the modules tell the infrastructure how much space is required, and the space is allocated there. The only user of this blob is AppArmor. The AppArmor use is abstracted to avoid future conflict. Signed-off-by: Casey Schaufler Reviewed-by: Kees Cook [kees: adjusted for ordered init series] Signed-off-by: Kees Cook --- include/linux/lsm_hooks.h | 2 ++ security/apparmor/include/task.h | 18 +++----------- security/apparmor/lsm.c | 15 +++-------- security/security.c | 54 +++++++++++++++++++++++++++++++++++++++- 4 files changed, 62 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 1c798e842de2..9b39fefa88c4 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2034,6 +2034,7 @@ struct lsm_blob_sizes { int lbs_cred; int lbs_file; int lbs_inode; + int lbs_task; }; /* @@ -2109,6 +2110,7 @@ extern int lsm_inode_alloc(struct inode *inode); #ifdef CONFIG_SECURITY void __init lsm_early_cred(struct cred *cred); +void __init lsm_early_task(struct task_struct *task); #endif #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/security/apparmor/include/task.h b/security/apparmor/include/task.h index 55edaa1d83f8..039c1e60887a 100644 --- a/security/apparmor/include/task.h +++ b/security/apparmor/include/task.h @@ -14,7 +14,10 @@ #ifndef __AA_TASK_H #define __AA_TASK_H -#define task_ctx(X) ((X)->security) +static inline struct aa_task_ctx *task_ctx(struct task_struct *task) +{ + return task->security; +} /* * struct aa_task_ctx - information for current task label change @@ -36,17 +39,6 @@ int aa_set_current_hat(struct aa_label *label, u64 token); int aa_restore_previous_label(u64 cookie); struct aa_label *aa_get_task_label(struct task_struct *task); -/** - * aa_alloc_task_ctx - allocate a new task_ctx - * @flags: gfp flags for allocation - * - * Returns: allocated buffer or NULL on failure - */ -static inline struct aa_task_ctx *aa_alloc_task_ctx(gfp_t flags) -{ - return kzalloc(sizeof(struct aa_task_ctx), flags); -} - /** * aa_free_task_ctx - free a task_ctx * @ctx: task_ctx to free (MAYBE NULL) @@ -57,8 +49,6 @@ static inline void aa_free_task_ctx(struct aa_task_ctx *ctx) aa_put_label(ctx->nnp); aa_put_label(ctx->previous); aa_put_label(ctx->onexec); - - kzfree(ctx); } } diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 6821187b06ad..60ef71268ccf 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -94,19 +94,14 @@ static void apparmor_task_free(struct task_struct *task) { aa_free_task_ctx(task_ctx(task)); - task_ctx(task) = NULL; } static int apparmor_task_alloc(struct task_struct *task, unsigned long clone_flags) { - struct aa_task_ctx *new = aa_alloc_task_ctx(GFP_KERNEL); - - if (!new) - return -ENOMEM; + struct aa_task_ctx *new = task_ctx(task); aa_dup_task_ctx(new, task_ctx(current)); - task_ctx(task) = new; return 0; } @@ -1157,6 +1152,7 @@ static int apparmor_inet_conn_request(struct sock *sk, struct sk_buff *skb, struct lsm_blob_sizes apparmor_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct aa_task_ctx *), .lbs_file = sizeof(struct aa_file_ctx), + .lbs_task = sizeof(struct aa_task_ctx), }; static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { @@ -1487,15 +1483,10 @@ static int param_set_mode(const char *val, const struct kernel_param *kp) static int __init set_init_ctx(void) { struct cred *cred = (struct cred *)current->real_cred; - struct aa_task_ctx *ctx; - - ctx = aa_alloc_task_ctx(GFP_KERNEL); - if (!ctx) - return -ENOMEM; lsm_early_cred(cred); + lsm_early_task(current); set_cred_label(cred, aa_get_label(ns_unconfined(root_ns))); - task_ctx(current) = ctx; return 0; } diff --git a/security/security.c b/security/security.c index 4989fb65e662..e59a1e1514ee 100644 --- a/security/security.c +++ b/security/security.c @@ -169,6 +169,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) if (needed->lbs_inode && blob_sizes.lbs_inode == 0) blob_sizes.lbs_inode = sizeof(struct rcu_head); lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); + lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); } /* Prepare LSM for initialization. */ @@ -292,6 +293,7 @@ static void __init ordered_lsm_init(void) init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); init_debug("file blob size = %d\n", blob_sizes.lbs_file); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); + init_debug("task blob size = %d\n", blob_sizes.lbs_task); /* * Create any kmem_caches needed for blobs @@ -515,6 +517,46 @@ int lsm_inode_alloc(struct inode *inode) return 0; } +/** + * lsm_task_alloc - allocate a composite task blob + * @task: the task that needs a blob + * + * Allocate the task blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +int lsm_task_alloc(struct task_struct *task) +{ + if (blob_sizes.lbs_task == 0) { + task->security = NULL; + return 0; + } + + task->security = kzalloc(blob_sizes.lbs_task, GFP_KERNEL); + if (task->security == NULL) + return -ENOMEM; + return 0; +} + +/** + * lsm_early_task - during initialization allocate a composite task blob + * @task: the task that needs a blob + * + * Allocate the task blob for all the modules if it's not already there + */ +void __init lsm_early_task(struct task_struct *task) +{ + int rc; + + if (task == NULL) + panic("%s: task cred.\n", __func__); + if (task->security != NULL) + return; + rc = lsm_task_alloc(task); + if (rc) + panic("%s: Early task alloc failed.\n", __func__); +} + /* * Hook list operation macros. * @@ -1359,12 +1401,22 @@ int security_file_open(struct file *file) int security_task_alloc(struct task_struct *task, unsigned long clone_flags) { - return call_int_hook(task_alloc, 0, task, clone_flags); + int rc = lsm_task_alloc(task); + + if (rc) + return rc; + rc = call_int_hook(task_alloc, 0, task, clone_flags); + if (unlikely(rc)) + security_task_free(task); + return rc; } void security_task_free(struct task_struct *task) { call_void_hook(task_free, task); + + kfree(task->security); + task->security = NULL; } int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) -- cgit v1.2.3 From ecd5f82e05ddd9b06c258167ec7467ac79741d77 Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Tue, 20 Nov 2018 11:55:02 -0800 Subject: LSM: Infrastructure management of the ipc security blob Move management of the kern_ipc_perm->security and msg_msg->security blobs out of the individual security modules and into the security infrastructure. Instead of allocating the blobs from within the modules the modules tell the infrastructure how much space is required, and the space is allocated there. Signed-off-by: Casey Schaufler Reviewed-by: Kees Cook [kees: adjusted for ordered init series] Signed-off-by: Kees Cook --- include/linux/lsm_hooks.h | 2 + security/security.c | 91 ++++++++++++++++++++++++++++++++++-- security/selinux/hooks.c | 98 ++++++--------------------------------- security/selinux/include/objsec.h | 4 +- security/smack/smack.h | 4 +- security/smack/smack_lsm.c | 32 ++----------- 6 files changed, 110 insertions(+), 121 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9b39fefa88c4..40511a8a5ae6 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2034,6 +2034,8 @@ struct lsm_blob_sizes { int lbs_cred; int lbs_file; int lbs_inode; + int lbs_ipc; + int lbs_msg_msg; int lbs_task; }; diff --git a/security/security.c b/security/security.c index e59a1e1514ee..953fc3ea18a9 100644 --- a/security/security.c +++ b/security/security.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #define MAX_LSM_EVM_XATTR 2 @@ -169,6 +170,8 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) if (needed->lbs_inode && blob_sizes.lbs_inode == 0) blob_sizes.lbs_inode = sizeof(struct rcu_head); lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); + lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); + lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); } @@ -293,6 +296,8 @@ static void __init ordered_lsm_init(void) init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); init_debug("file blob size = %d\n", blob_sizes.lbs_file); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); + init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); + init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); init_debug("task blob size = %d\n", blob_sizes.lbs_task); /* @@ -538,6 +543,48 @@ int lsm_task_alloc(struct task_struct *task) return 0; } +/** + * lsm_ipc_alloc - allocate a composite ipc blob + * @kip: the ipc that needs a blob + * + * Allocate the ipc blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +int lsm_ipc_alloc(struct kern_ipc_perm *kip) +{ + if (blob_sizes.lbs_ipc == 0) { + kip->security = NULL; + return 0; + } + + kip->security = kzalloc(blob_sizes.lbs_ipc, GFP_KERNEL); + if (kip->security == NULL) + return -ENOMEM; + return 0; +} + +/** + * lsm_msg_msg_alloc - allocate a composite msg_msg blob + * @mp: the msg_msg that needs a blob + * + * Allocate the ipc blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +int lsm_msg_msg_alloc(struct msg_msg *mp) +{ + if (blob_sizes.lbs_msg_msg == 0) { + mp->security = NULL; + return 0; + } + + mp->security = kzalloc(blob_sizes.lbs_msg_msg, GFP_KERNEL); + if (mp->security == NULL) + return -ENOMEM; + return 0; +} + /** * lsm_early_task - during initialization allocate a composite task blob * @task: the task that needs a blob @@ -1631,22 +1678,40 @@ void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) int security_msg_msg_alloc(struct msg_msg *msg) { - return call_int_hook(msg_msg_alloc_security, 0, msg); + int rc = lsm_msg_msg_alloc(msg); + + if (unlikely(rc)) + return rc; + rc = call_int_hook(msg_msg_alloc_security, 0, msg); + if (unlikely(rc)) + security_msg_msg_free(msg); + return rc; } void security_msg_msg_free(struct msg_msg *msg) { call_void_hook(msg_msg_free_security, msg); + kfree(msg->security); + msg->security = NULL; } int security_msg_queue_alloc(struct kern_ipc_perm *msq) { - return call_int_hook(msg_queue_alloc_security, 0, msq); + int rc = lsm_ipc_alloc(msq); + + if (unlikely(rc)) + return rc; + rc = call_int_hook(msg_queue_alloc_security, 0, msq); + if (unlikely(rc)) + security_msg_queue_free(msq); + return rc; } void security_msg_queue_free(struct kern_ipc_perm *msq) { call_void_hook(msg_queue_free_security, msq); + kfree(msq->security); + msq->security = NULL; } int security_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) @@ -1673,12 +1738,21 @@ int security_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, int security_shm_alloc(struct kern_ipc_perm *shp) { - return call_int_hook(shm_alloc_security, 0, shp); + int rc = lsm_ipc_alloc(shp); + + if (unlikely(rc)) + return rc; + rc = call_int_hook(shm_alloc_security, 0, shp); + if (unlikely(rc)) + security_shm_free(shp); + return rc; } void security_shm_free(struct kern_ipc_perm *shp) { call_void_hook(shm_free_security, shp); + kfree(shp->security); + shp->security = NULL; } int security_shm_associate(struct kern_ipc_perm *shp, int shmflg) @@ -1698,12 +1772,21 @@ int security_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmf int security_sem_alloc(struct kern_ipc_perm *sma) { - return call_int_hook(sem_alloc_security, 0, sma); + int rc = lsm_ipc_alloc(sma); + + if (unlikely(rc)) + return rc; + rc = call_int_hook(sem_alloc_security, 0, sma); + if (unlikely(rc)) + security_sem_free(sma); + return rc; } void security_sem_free(struct kern_ipc_perm *sma) { call_void_hook(sem_free_security, sma); + kfree(sma->security); + sma->security = NULL; } int security_sem_associate(struct kern_ipc_perm *sma, int semflg) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4b64ad31326f..d98e1d8d18f6 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5626,51 +5626,22 @@ static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) return selinux_nlmsg_perm(sk, skb); } -static int ipc_alloc_security(struct kern_ipc_perm *perm, - u16 sclass) +static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass) { - struct ipc_security_struct *isec; - - isec = kzalloc(sizeof(struct ipc_security_struct), GFP_KERNEL); - if (!isec) - return -ENOMEM; - isec->sclass = sclass; isec->sid = current_sid(); - perm->security = isec; - - return 0; -} - -static void ipc_free_security(struct kern_ipc_perm *perm) -{ - struct ipc_security_struct *isec = perm->security; - perm->security = NULL; - kfree(isec); } static int msg_msg_alloc_security(struct msg_msg *msg) { struct msg_security_struct *msec; - msec = kzalloc(sizeof(struct msg_security_struct), GFP_KERNEL); - if (!msec) - return -ENOMEM; - + msec = selinux_msg_msg(msg); msec->sid = SECINITSID_UNLABELED; - msg->security = msec; return 0; } -static void msg_msg_free_security(struct msg_msg *msg) -{ - struct msg_security_struct *msec = msg->security; - - msg->security = NULL; - kfree(msec); -} - static int ipc_has_perm(struct kern_ipc_perm *ipc_perms, u32 perms) { @@ -5692,11 +5663,6 @@ static int selinux_msg_msg_alloc_security(struct msg_msg *msg) return msg_msg_alloc_security(msg); } -static void selinux_msg_msg_free_security(struct msg_msg *msg) -{ - msg_msg_free_security(msg); -} - /* message queue security operations */ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq) { @@ -5705,11 +5671,8 @@ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq) u32 sid = current_sid(); int rc; - rc = ipc_alloc_security(msq, SECCLASS_MSGQ); - if (rc) - return rc; - - isec = msq->security; + isec = selinux_ipc(msq); + ipc_init_security(isec, SECCLASS_MSGQ); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; @@ -5717,16 +5680,7 @@ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq) rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_MSGQ, MSGQ__CREATE, &ad); - if (rc) { - ipc_free_security(msq); - return rc; - } - return 0; -} - -static void selinux_msg_queue_free_security(struct kern_ipc_perm *msq) -{ - ipc_free_security(msq); + return rc; } static int selinux_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) @@ -5856,11 +5810,8 @@ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp) u32 sid = current_sid(); int rc; - rc = ipc_alloc_security(shp, SECCLASS_SHM); - if (rc) - return rc; - - isec = shp->security; + isec = selinux_ipc(shp); + ipc_init_security(isec, SECCLASS_SHM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; @@ -5868,16 +5819,7 @@ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp) rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SHM, SHM__CREATE, &ad); - if (rc) { - ipc_free_security(shp); - return rc; - } - return 0; -} - -static void selinux_shm_free_security(struct kern_ipc_perm *shp) -{ - ipc_free_security(shp); + return rc; } static int selinux_shm_associate(struct kern_ipc_perm *shp, int shmflg) @@ -5953,11 +5895,8 @@ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma) u32 sid = current_sid(); int rc; - rc = ipc_alloc_security(sma, SECCLASS_SEM); - if (rc) - return rc; - - isec = sma->security; + isec = selinux_ipc(sma); + ipc_init_security(isec, SECCLASS_SEM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; @@ -5965,16 +5904,7 @@ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma) rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SEM, SEM__CREATE, &ad); - if (rc) { - ipc_free_security(sma); - return rc; - } - return 0; -} - -static void selinux_sem_free_security(struct kern_ipc_perm *sma) -{ - ipc_free_security(sma); + return rc; } static int selinux_sem_associate(struct kern_ipc_perm *sma, int semflg) @@ -6607,6 +6537,8 @@ struct lsm_blob_sizes selinux_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct task_security_struct), .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), + .lbs_ipc = sizeof(struct ipc_security_struct), + .lbs_msg_msg = sizeof(struct msg_security_struct), }; static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { @@ -6718,24 +6650,20 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(ipc_getsecid, selinux_ipc_getsecid), LSM_HOOK_INIT(msg_msg_alloc_security, selinux_msg_msg_alloc_security), - LSM_HOOK_INIT(msg_msg_free_security, selinux_msg_msg_free_security), LSM_HOOK_INIT(msg_queue_alloc_security, selinux_msg_queue_alloc_security), - LSM_HOOK_INIT(msg_queue_free_security, selinux_msg_queue_free_security), LSM_HOOK_INIT(msg_queue_associate, selinux_msg_queue_associate), LSM_HOOK_INIT(msg_queue_msgctl, selinux_msg_queue_msgctl), LSM_HOOK_INIT(msg_queue_msgsnd, selinux_msg_queue_msgsnd), LSM_HOOK_INIT(msg_queue_msgrcv, selinux_msg_queue_msgrcv), LSM_HOOK_INIT(shm_alloc_security, selinux_shm_alloc_security), - LSM_HOOK_INIT(shm_free_security, selinux_shm_free_security), LSM_HOOK_INIT(shm_associate, selinux_shm_associate), LSM_HOOK_INIT(shm_shmctl, selinux_shm_shmctl), LSM_HOOK_INIT(shm_shmat, selinux_shm_shmat), LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security), - LSM_HOOK_INIT(sem_free_security, selinux_sem_free_security), LSM_HOOK_INIT(sem_associate, selinux_sem_associate), LSM_HOOK_INIT(sem_semctl, selinux_sem_semctl), LSM_HOOK_INIT(sem_semop, selinux_sem_semop), diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index 539cacf4a572..231262d8eac9 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -179,13 +179,13 @@ static inline struct inode_security_struct *selinux_inode( static inline struct msg_security_struct *selinux_msg_msg( const struct msg_msg *msg_msg) { - return msg_msg->security; + return msg_msg->security + selinux_blob_sizes.lbs_msg_msg; } static inline struct ipc_security_struct *selinux_ipc( const struct kern_ipc_perm *ipc) { - return ipc->security; + return ipc->security + selinux_blob_sizes.lbs_ipc; } #endif /* _SELINUX_OBJSEC_H_ */ diff --git a/security/smack/smack.h b/security/smack/smack.h index 0adddbeecc62..9c7c95a5c497 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -376,12 +376,12 @@ static inline struct inode_smack *smack_inode(const struct inode *inode) static inline struct smack_known **smack_msg_msg(const struct msg_msg *msg) { - return (struct smack_known **)&msg->security; + return msg->security + smack_blob_sizes.lbs_msg_msg; } static inline struct smack_known **smack_ipc(const struct kern_ipc_perm *ipc) { - return (struct smack_known **)&ipc->security; + return ipc->security + smack_blob_sizes.lbs_ipc; } /* diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 154521b6843b..0b848b1f6366 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -2809,23 +2809,12 @@ static int smack_flags_to_may(int flags) */ static int smack_msg_msg_alloc_security(struct msg_msg *msg) { - struct smack_known *skp = smk_of_current(); + struct smack_known **blob = smack_msg_msg(msg); - msg->security = skp; + *blob = smk_of_current(); return 0; } -/** - * smack_msg_msg_free_security - Clear the security blob for msg_msg - * @msg: the object - * - * Clears the blob pointer - */ -static void smack_msg_msg_free_security(struct msg_msg *msg) -{ - msg->security = NULL; -} - /** * smack_of_ipc - the smack pointer for the ipc * @isp: the object @@ -2853,17 +2842,6 @@ static int smack_ipc_alloc_security(struct kern_ipc_perm *isp) return 0; } -/** - * smack_ipc_free_security - Clear the security blob for ipc - * @isp: the object - * - * Clears the blob pointer - */ -static void smack_ipc_free_security(struct kern_ipc_perm *isp) -{ - isp->security = NULL; -} - /** * smk_curacc_shm : check if current has access on shm * @isp : the object @@ -4511,6 +4489,8 @@ struct lsm_blob_sizes smack_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct task_smack), .lbs_file = sizeof(struct smack_known *), .lbs_inode = sizeof(struct inode_smack), + .lbs_ipc = sizeof(struct smack_known *), + .lbs_msg_msg = sizeof(struct smack_known *), }; static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { @@ -4581,23 +4561,19 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(ipc_getsecid, smack_ipc_getsecid), LSM_HOOK_INIT(msg_msg_alloc_security, smack_msg_msg_alloc_security), - LSM_HOOK_INIT(msg_msg_free_security, smack_msg_msg_free_security), LSM_HOOK_INIT(msg_queue_alloc_security, smack_ipc_alloc_security), - LSM_HOOK_INIT(msg_queue_free_security, smack_ipc_free_security), LSM_HOOK_INIT(msg_queue_associate, smack_msg_queue_associate), LSM_HOOK_INIT(msg_queue_msgctl, smack_msg_queue_msgctl), LSM_HOOK_INIT(msg_queue_msgsnd, smack_msg_queue_msgsnd), LSM_HOOK_INIT(msg_queue_msgrcv, smack_msg_queue_msgrcv), LSM_HOOK_INIT(shm_alloc_security, smack_ipc_alloc_security), - LSM_HOOK_INIT(shm_free_security, smack_ipc_free_security), LSM_HOOK_INIT(shm_associate, smack_shm_associate), LSM_HOOK_INIT(shm_shmctl, smack_shm_shmctl), LSM_HOOK_INIT(shm_shmat, smack_shm_shmat), LSM_HOOK_INIT(sem_alloc_security, smack_ipc_alloc_security), - LSM_HOOK_INIT(sem_free_security, smack_ipc_free_security), LSM_HOOK_INIT(sem_associate, smack_sem_associate), LSM_HOOK_INIT(sem_semctl, smack_sem_semctl), LSM_HOOK_INIT(sem_semop, smack_sem_semop), -- cgit v1.2.3 From 96f87ee1811306d0c8cf94b8c37b0e4f725b01d1 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 8 Jan 2019 16:07:23 +0200 Subject: RDMA: Clean structures from CONFIG_INFINIBAND_ON_DEMAND_PAGING CONFIG_INFINIBAND_ON_DEMAND_PAGING is used in general structures to micro-optimize the memory footprint. Remove it, so it will allow us to simplify various ODP device flows. Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 -- include/rdma/ib_verbs.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index b06d3b1efea8..93c288a4de2b 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -911,7 +911,6 @@ struct mlx5_ib_dev { /* Prevents soft lock on massive reg MRs */ struct mutex slow_path_mutex; int fill_delay; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING struct ib_odp_caps odp_caps; u64 odp_max_size; struct mlx5_ib_pf_eq odp_pf_eq; @@ -923,7 +922,6 @@ struct mlx5_ib_dev { struct srcu_struct mr_srcu; u32 null_mkey; struct workqueue_struct *advise_mr_wq; -#endif struct mlx5_ib_flow_db *flow_db; /* protect resources needed as part of reset flow */ spinlock_t reset_flow_resource_lock; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a3ceed3a040a..3ddd199ba602 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1504,12 +1504,10 @@ struct ib_ucontext { bool cleanup_retryable; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING void (*invalidate_range)(struct ib_umem_odp *umem_odp, unsigned long start, unsigned long end); struct mutex per_mm_list_lock; struct list_head per_mm_list; -#endif struct ib_rdmacg_object cg_obj; /* -- cgit v1.2.3 From 13859d5df418ea535926e2b57c29d5161c522b9d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 8 Jan 2019 16:07:26 +0200 Subject: RDMA/mlx5: Embed into the code flow the ODP config option Convert various places to more readable code, which embeds CONFIG_INFINIBAND_ON_DEMAND_PAGING into the code flow. Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/uverbs_cmd.c | 3 --- drivers/infiniband/hw/mlx5/main.c | 41 ++++++++++++++++++------------------ drivers/infiniband/hw/mlx5/mem.c | 5 +---- drivers/infiniband/hw/mlx5/mr.c | 28 +++++++++++------------- include/rdma/ib_umem_odp.h | 26 +++++++++++------------ 5 files changed, 46 insertions(+), 57 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 549d9eedf62e..d4f1a2ef5015 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -234,14 +234,11 @@ static int ib_uverbs_get_context(struct uverbs_attr_bundle *attrs) ucontext->closing = false; ucontext->cleanup_retryable = false; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING mutex_init(&ucontext->per_mm_list_lock); INIT_LIST_HEAD(&ucontext->per_mm_list); if (!(ib_dev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING)) ucontext->invalidate_range = NULL; -#endif - resp.num_comp_vectors = file->device->num_comp_vectors; ret = get_unused_fd_flags(O_CLOEXEC); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 06ee1f0cb22d..11e9783cefcc 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1763,9 +1763,9 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (err) goto out_sys_pages; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - context->ibucontext.invalidate_range = &mlx5_ib_invalidate_range; -#endif + if (ibdev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING) + context->ibucontext.invalidate_range = + &mlx5_ib_invalidate_range; if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) { err = mlx5_ib_devx_create(dev, true); @@ -1897,12 +1897,10 @@ static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext) struct mlx5_ib_dev *dev = to_mdev(ibcontext->device); struct mlx5_bfreg_info *bfregi; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING /* All umem's must be destroyed before destroying the ucontext. */ mutex_lock(&ibcontext->per_mm_list_lock); WARN_ON(!list_empty(&ibcontext->per_mm_list)); mutex_unlock(&ibcontext->per_mm_list_lock); -#endif bfregi = &context->bfregi; mlx5_ib_dealloc_transport_domain(dev, context->tdn, context->devx_uid); @@ -5722,11 +5720,11 @@ static struct ib_counters *mlx5_ib_create_counters(struct ib_device *device, void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) { mlx5_ib_cleanup_multiport_master(dev); -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - cleanup_srcu_struct(&dev->mr_srcu); - drain_workqueue(dev->advise_mr_wq); - destroy_workqueue(dev->advise_mr_wq); -#endif + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { + cleanup_srcu_struct(&dev->mr_srcu); + drain_workqueue(dev->advise_mr_wq); + destroy_workqueue(dev->advise_mr_wq); + } kfree(dev->port); } @@ -5779,19 +5777,20 @@ int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) spin_lock_init(&dev->memic.memic_lock); dev->memic.dev = mdev; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - dev->advise_mr_wq = alloc_ordered_workqueue("mlx5_ib_advise_mr_wq", 0); - if (!dev->advise_mr_wq) { - err = -ENOMEM; - goto err_mp; - } + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { + dev->advise_mr_wq = + alloc_ordered_workqueue("mlx5_ib_advise_mr_wq", 0); + if (!dev->advise_mr_wq) { + err = -ENOMEM; + goto err_mp; + } - err = init_srcu_struct(&dev->mr_srcu); - if (err) { - destroy_workqueue(dev->advise_mr_wq); - goto err_mp; + err = init_srcu_struct(&dev->mr_srcu); + if (err) { + destroy_workqueue(dev->advise_mr_wq); + goto err_mp; + } } -#endif return 0; err_mp: diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c index 549234988bb4..9f90be296ee0 100644 --- a/drivers/infiniband/hw/mlx5/mem.c +++ b/drivers/infiniband/hw/mlx5/mem.c @@ -111,7 +111,6 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, *count = i; } -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING static u64 umem_dma_to_mtt(dma_addr_t umem_dma) { u64 mtt_entry = umem_dma & ODP_DMA_ADDR_MASK; @@ -123,7 +122,6 @@ static u64 umem_dma_to_mtt(dma_addr_t umem_dma) return mtt_entry; } -#endif /* * Populate the given array with bus addresses from the umem. @@ -151,7 +149,7 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem, int len; struct scatterlist *sg; int entry; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING + if (umem->is_odp) { WARN_ON(shift != 0); WARN_ON(access_flags != (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE)); @@ -164,7 +162,6 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem, } return; } -#endif i = 0; for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) { diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index c389750f771e..494a90f4348c 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -71,10 +71,9 @@ static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { int err = mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey); -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - /* Wait until all page fault handlers using the mr complete. */ - synchronize_srcu(&dev->mr_srcu); -#endif + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) + /* Wait until all page fault handlers using the mr complete. */ + synchronize_srcu(&dev->mr_srcu); return err; } @@ -254,9 +253,8 @@ static void remove_keys(struct mlx5_ib_dev *dev, int c, int num) mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey); } -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - synchronize_srcu(&dev->mr_srcu); -#endif + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) + synchronize_srcu(&dev->mr_srcu); list_for_each_entry_safe(mr, tmp_mr, &del_list, list) { list_del(&mr->list); @@ -1329,8 +1327,8 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx, access_flags 0x%x\n", start, virt_addr, length, access_flags); -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - if (!start && length == U64_MAX) { + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && !start && + length == U64_MAX) { if (!(access_flags & IB_ACCESS_ON_DEMAND) || !(dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT)) return ERR_PTR(-EINVAL); @@ -1340,7 +1338,6 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, return ERR_CAST(mr); return &mr->ibmr; } -#endif err = mr_umem_get(pd, start, length, access_flags, &umem, &npages, &page_shift, &ncont, &order); @@ -1401,9 +1398,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, } } -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - mr->live = 1; -#endif + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) + mr->live = 1; + return &mr->ibmr; error: ib_umem_release(umem); @@ -1518,9 +1515,8 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, } mr->allocated_from_cache = 0; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - mr->live = 1; -#endif + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) + mr->live = 1; } else { /* * Send a UMR WQE diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h index 0b1446fe2fab..d3725cf13ecd 100644 --- a/include/rdma/ib_umem_odp.h +++ b/include/rdma/ib_umem_odp.h @@ -83,6 +83,19 @@ static inline struct ib_umem_odp *to_ib_umem_odp(struct ib_umem *umem) return container_of(umem, struct ib_umem_odp, umem); } +/* + * The lower 2 bits of the DMA address signal the R/W permissions for + * the entry. To upgrade the permissions, provide the appropriate + * bitmask to the map_dma_pages function. + * + * Be aware that upgrading a mapped address might result in change of + * the DMA address for the page. + */ +#define ODP_READ_ALLOWED_BIT (1<<0ULL) +#define ODP_WRITE_ALLOWED_BIT (1<<1ULL) + +#define ODP_DMA_ADDR_MASK (~(ODP_READ_ALLOWED_BIT | ODP_WRITE_ALLOWED_BIT)) + #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING struct ib_ucontext_per_mm { @@ -107,19 +120,6 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm, unsigned long addr, size_t size); void ib_umem_odp_release(struct ib_umem_odp *umem_odp); -/* - * The lower 2 bits of the DMA address signal the R/W permissions for - * the entry. To upgrade the permissions, provide the appropriate - * bitmask to the map_dma_pages function. - * - * Be aware that upgrading a mapped address might result in change of - * the DMA address for the page. - */ -#define ODP_READ_ALLOWED_BIT (1<<0ULL) -#define ODP_WRITE_ALLOWED_BIT (1<<1ULL) - -#define ODP_DMA_ADDR_MASK (~(ODP_READ_ALLOWED_BIT | ODP_WRITE_ALLOWED_BIT)) - int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset, u64 bcnt, u64 access_mask, unsigned long current_seq); -- cgit v1.2.3 From 0ada768517dafa1504ef5986ba04f118b7436960 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 8 Jan 2019 16:07:27 +0200 Subject: RDMA/mlx5: Delete declaration of already removed function The implementation of mlx5_core_page_fault_resume() was removed in commit d5d284b829a6 ("{net,IB}/mlx5: Move Page fault EQ and ODP logic to RDMA"). This patch removes declaration too. Fixes: d5d284b829a6 ("{net,IB}/mlx5: Move Page fault EQ and ODP logic to RDMA") Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/driver.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 54299251d40d..b6f5839f129a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -939,10 +939,6 @@ int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev, u8 port_num, void *out, size_t sz); -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING -int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token, - u32 wq_num, u8 type, int error); -#endif int mlx5_init_rl_table(struct mlx5_core_dev *dev); void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev); -- cgit v1.2.3 From f3186dd876697e696d07136623d5cf0a6fb0bc0f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 7 Jan 2019 16:51:50 +0100 Subject: spi: Optionally use GPIO descriptors for CS GPIOs This augments the SPI core to optionally use GPIO descriptors for chip select on a per-master-driver opt-in basis. Drivers using this will rely on the SPI core to look up GPIO descriptors associated with the device, such as when using device tree or board files with GPIO descriptor tables. When getting descriptors from the device tree, this will in turn activate the code in gpiolib that was added in commit 6953c57ab172 ("gpio: of: Handle SPI chipselect legacy bindings") which means that these descriptors are aware of the active low semantics that is the default for SPI CS GPIO lines and we can assume that all of these are "active high" and thus assign SPI_CS_HIGH to all CS lines on the DT path. The previously used gpio_set_value() would call down into gpiod_set_raw_value() and ignore the polarity inversion semantics. It seems like many drivers go to great lengths to set up the CS GPIO line as non-asserted, respecting SPI_CS_HIGH. We pull this out of the SPI drivers and into the core, and by simply requesting the line as GPIOD_OUT_LOW when retrieveing it from the device and relying on the gpiolib to handle any inversion semantics. This way a lot of code can be simplified and removed in each converted driver. The end goal after dealing with each driver in turn, is to delete the non-descriptor path (of_spi_register_master() for example) and let the core deal with only descriptors. The different SPI drivers have complex interactions with the core so we cannot simply change them all over, we need to use a stepwise, bisectable approach so that each driver can be converted and fixed in isolation. This patch has the intended side effect of adding support for ACPI GPIOs as it starts relying on gpiod_get_*() to get the GPIO handle associated with the device. Cc: Linuxarm Acked-by: Jonathan Cameron Tested-by: Fangjian (Turing) Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- drivers/spi/spi.c | 104 +++++++++++++++++++++++++++++++++++++++++++----- include/linux/spi/spi.h | 23 +++++++++-- 2 files changed, 113 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 9a7def7c3237..13f447a67d67 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -578,7 +579,10 @@ int spi_add_device(struct spi_device *spi) goto done; } - if (ctlr->cs_gpios) + /* Descriptors take precedence */ + if (ctlr->cs_gpiods) + spi->cs_gpiod = ctlr->cs_gpiods[spi->chip_select]; + else if (ctlr->cs_gpios) spi->cs_gpio = ctlr->cs_gpios[spi->chip_select]; /* Drivers may modify this initial i/o setup, but will @@ -772,10 +776,20 @@ static void spi_set_cs(struct spi_device *spi, bool enable) if (spi->mode & SPI_CS_HIGH) enable = !enable; - if (gpio_is_valid(spi->cs_gpio)) { - /* Honour the SPI_NO_CS flag */ - if (!(spi->mode & SPI_NO_CS)) - gpio_set_value(spi->cs_gpio, !enable); + if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio)) { + /* + * Honour the SPI_NO_CS flag and invert the enable line, as + * active low is default for SPI. Execution paths that handle + * polarity inversion in gpiolib (such as device tree) will + * enforce active high using the SPI_CS_HIGH resulting in a + * double inversion through the code above. + */ + if (!(spi->mode & SPI_NO_CS)) { + if (spi->cs_gpiod) + gpiod_set_value(spi->cs_gpiod, !enable); + else + gpio_set_value(spi->cs_gpio, !enable); + } /* Some SPI masters need both GPIO CS & slave_select */ if ((spi->controller->flags & SPI_MASTER_GPIO_SS) && spi->controller->set_cs) @@ -1615,13 +1629,21 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, spi->mode |= SPI_CPHA; if (of_property_read_bool(nc, "spi-cpol")) spi->mode |= SPI_CPOL; - if (of_property_read_bool(nc, "spi-cs-high")) - spi->mode |= SPI_CS_HIGH; if (of_property_read_bool(nc, "spi-3wire")) spi->mode |= SPI_3WIRE; if (of_property_read_bool(nc, "spi-lsb-first")) spi->mode |= SPI_LSB_FIRST; + /* + * For descriptors associated with the device, polarity inversion is + * handled in the gpiolib, so all chip selects are "active high" in + * the logical sense, the gpiolib will invert the line if need be. + */ + if (ctlr->use_gpio_descriptors) + spi->mode |= SPI_CS_HIGH; + else if (of_property_read_bool(nc, "spi-cs-high")) + spi->mode |= SPI_CS_HIGH; + /* Device DUAL/QUAD mode */ if (!of_property_read_u32(nc, "spi-tx-bus-width", &value)) { switch (value) { @@ -2137,6 +2159,60 @@ static int of_spi_register_master(struct spi_controller *ctlr) } #endif +/** + * spi_get_gpio_descs() - grab chip select GPIOs for the master + * @ctlr: The SPI master to grab GPIO descriptors for + */ +static int spi_get_gpio_descs(struct spi_controller *ctlr) +{ + int nb, i; + struct gpio_desc **cs; + struct device *dev = &ctlr->dev; + + nb = gpiod_count(dev, "cs"); + ctlr->num_chipselect = max_t(int, nb, ctlr->num_chipselect); + + /* No GPIOs at all is fine, else return the error */ + if (nb == 0 || nb == -ENOENT) + return 0; + else if (nb < 0) + return nb; + + cs = devm_kcalloc(dev, ctlr->num_chipselect, sizeof(*cs), + GFP_KERNEL); + if (!cs) + return -ENOMEM; + ctlr->cs_gpiods = cs; + + for (i = 0; i < nb; i++) { + /* + * Most chipselects are active low, the inverted + * semantics are handled by special quirks in gpiolib, + * so initializing them GPIOD_OUT_LOW here means + * "unasserted", in most cases this will drive the physical + * line high. + */ + cs[i] = devm_gpiod_get_index_optional(dev, "cs", i, + GPIOD_OUT_LOW); + + if (cs[i]) { + /* + * If we find a CS GPIO, name it after the device and + * chip select line. + */ + char *gpioname; + + gpioname = devm_kasprintf(dev, GFP_KERNEL, "%s CS%d", + dev_name(dev), i); + if (!gpioname) + return -ENOMEM; + gpiod_set_consumer_name(cs[i], gpioname); + } + } + + return 0; +} + static int spi_controller_check_ops(struct spi_controller *ctlr) { /* @@ -2199,9 +2275,16 @@ int spi_register_controller(struct spi_controller *ctlr) return status; if (!spi_controller_is_slave(ctlr)) { - status = of_spi_register_master(ctlr); - if (status) - return status; + if (ctlr->use_gpio_descriptors) { + status = spi_get_gpio_descs(ctlr); + if (status) + return status; + } else { + /* Legacy code path for GPIOs from DT */ + status = of_spi_register_master(ctlr); + if (status) + return status; + } } /* even if it's just one always-selected device, there must @@ -2915,6 +2998,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) * cs_change is set for each transfer. */ if ((spi->mode & SPI_CS_WORD) && (!(ctlr->mode_bits & SPI_CS_WORD) || + spi->cs_gpiod || gpio_is_valid(spi->cs_gpio))) { size_t maxsize; int ret; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 314d922ca607..916bba47d156 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -12,6 +12,7 @@ #include #include #include +#include struct dma_chan; struct property_entry; @@ -116,7 +117,10 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, * @modalias: Name of the driver to use with this device, or an alias * for that name. This appears in the sysfs "modalias" attribute * for driver coldplugging, and in uevents used for hotplugging - * @cs_gpio: gpio number of the chipselect line (optional, -ENOENT when + * @cs_gpio: LEGACY: gpio number of the chipselect line (optional, -ENOENT when + * not using a GPIO line) use cs_gpiod in new drivers by opting in on + * the spi_master. + * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when * not using a GPIO line) * * @statistics: statistics for the spi_device @@ -163,7 +167,8 @@ struct spi_device { void *controller_data; char modalias[SPI_NAME_SIZE]; const char *driver_override; - int cs_gpio; /* chip select gpio */ + int cs_gpio; /* LEGACY: chip select gpio */ + struct gpio_desc *cs_gpiod; /* chip select gpio desc */ /* the statistics */ struct spi_statistics statistics; @@ -376,9 +381,17 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * controller has native support for memory like operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller - * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS - * number. Any individual value may be -ENOENT for CS lines that + * @cs_gpios: LEGACY: array of GPIO descs to use as chip select lines; one per + * CS number. Any individual value may be -ENOENT for CS lines that + * are not GPIOs (driven by the SPI controller itself). Use the cs_gpiods + * in new drivers. + * @cs_gpiods: Array of GPIO descs to use as chip select lines; one per CS + * number. Any individual value may be NULL for CS lines that * are not GPIOs (driven by the SPI controller itself). + * @use_gpio_descriptors: Turns on the code in the SPI core to parse and grab + * GPIO descriptors rather than using global GPIO numbers grabbed by the + * driver. This will fill in @cs_gpiods and @cs_gpios should not be used, + * and SPI devices will have the cs_gpiod assigned rather than cs_gpio. * @statistics: statistics for the spi_controller * @dma_tx: DMA transmit channel * @dma_rx: DMA receive channel @@ -557,6 +570,8 @@ struct spi_controller { /* gpio chip select */ int *cs_gpios; + struct gpio_desc **cs_gpiods; + bool use_gpio_descriptors; /* statistics */ struct spi_statistics statistics; -- cgit v1.2.3 From c6275e4b12bfb53097bca852dd49c15b1af50cb4 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Fri, 7 Dec 2018 19:21:10 +0100 Subject: soc: bcm2835: sync firmware properties with downstream Add latest firmware property tags from the latest Raspberry Pi downstream kernel. This is needed to use the reboot notify in the following commit. Signed-off-by: Stefan Wahren Reviewed-by: Eric Anholt --- include/soc/bcm2835/raspberrypi-firmware.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h index 4be1aa4435ae..7800e12ee042 100644 --- a/include/soc/bcm2835/raspberrypi-firmware.h +++ b/include/soc/bcm2835/raspberrypi-firmware.h @@ -73,6 +73,8 @@ enum rpi_firmware_property_tag { RPI_FIRMWARE_GET_CUSTOMER_OTP = 0x00030021, RPI_FIRMWARE_GET_DOMAIN_STATE = 0x00030030, RPI_FIRMWARE_GET_THROTTLED = 0x00030046, + RPI_FIRMWARE_GET_CLOCK_MEASURED = 0x00030047, + RPI_FIRMWARE_NOTIFY_REBOOT = 0x00030048, RPI_FIRMWARE_SET_CLOCK_STATE = 0x00038001, RPI_FIRMWARE_SET_CLOCK_RATE = 0x00038002, RPI_FIRMWARE_SET_VOLTAGE = 0x00038003, @@ -86,6 +88,8 @@ enum rpi_firmware_property_tag { RPI_FIRMWARE_SET_GPIO_CONFIG = 0x00038043, RPI_FIRMWARE_GET_PERIPH_REG = 0x00030045, RPI_FIRMWARE_SET_PERIPH_REG = 0x00038045, + RPI_FIRMWARE_GET_POE_HAT_VAL = 0x00030049, + RPI_FIRMWARE_SET_POE_HAT_VAL = 0x00030050, /* Dispmanx TAGS */ -- cgit v1.2.3 From 5e6acc3e678ed3db746ab4fb53a980861cd711b6 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Wed, 12 Dec 2018 15:51:47 -0800 Subject: bcm2835-pm: Move bcm2835-watchdog's DT probe to an MFD. The PM block that the wdt driver was binding to actually has multiple features we want to expose (power domains, reset, watchdog). Move the DT attachment to a MFD driver and make WDT probe against MFD. Signed-off-by: Eric Anholt Reviewed-by: Guenter Roeck Acked-by: Stefan Wahren Signed-off-by: Stefan Wahren --- arch/arm/mach-bcm/Kconfig | 1 + drivers/mfd/Makefile | 1 + drivers/mfd/bcm2835-pm.c | 64 ++++++++++++++++++++++++++++++++++++++++++ drivers/watchdog/bcm2835_wdt.c | 26 ++++++----------- include/linux/mfd/bcm2835-pm.h | 13 +++++++++ 5 files changed, 88 insertions(+), 17 deletions(-) create mode 100644 drivers/mfd/bcm2835-pm.c create mode 100644 include/linux/mfd/bcm2835-pm.h (limited to 'include') diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig index a067adf9f1ee..4ef1e55f4a0b 100644 --- a/arch/arm/mach-bcm/Kconfig +++ b/arch/arm/mach-bcm/Kconfig @@ -167,6 +167,7 @@ config ARCH_BCM2835 select BCM2835_TIMER select PINCTRL select PINCTRL_BCM2835 + select MFD_CORE help This enables support for the Broadcom BCM2835 and BCM2836 SoCs. This SoC is used in the Raspberry Pi and Roku 2 devices. diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 12980a4ad460..ee6fb6af655e 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -10,6 +10,7 @@ obj-$(CONFIG_MFD_88PM805) += 88pm805.o 88pm80x.o obj-$(CONFIG_MFD_ACT8945A) += act8945a.o obj-$(CONFIG_MFD_SM501) += sm501.o obj-$(CONFIG_MFD_ASIC3) += asic3.o tmio_core.o +obj-$(CONFIG_ARCH_BCM2835) += bcm2835-pm.o obj-$(CONFIG_MFD_BCM590XX) += bcm590xx.o obj-$(CONFIG_MFD_BD9571MWV) += bd9571mwv.o cros_ec_core-objs := cros_ec.o diff --git a/drivers/mfd/bcm2835-pm.c b/drivers/mfd/bcm2835-pm.c new file mode 100644 index 000000000000..53839e6a81e7 --- /dev/null +++ b/drivers/mfd/bcm2835-pm.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PM MFD driver for Broadcom BCM2835 + * + * This driver binds to the PM block and creates the MFD device for + * the WDT driver. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static const struct mfd_cell bcm2835_pm_devs[] = { + { .name = "bcm2835-wdt" }, +}; + +static int bcm2835_pm_probe(struct platform_device *pdev) +{ + struct resource *res; + struct device *dev = &pdev->dev; + struct bcm2835_pm *pm; + + pm = devm_kzalloc(dev, sizeof(*pm), GFP_KERNEL); + if (!pm) + return -ENOMEM; + platform_set_drvdata(pdev, pm); + + pm->dev = dev; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + pm->base = devm_ioremap_resource(dev, res); + if (IS_ERR(pm->base)) + return PTR_ERR(pm->base); + + return devm_mfd_add_devices(dev, -1, + bcm2835_pm_devs, ARRAY_SIZE(bcm2835_pm_devs), + NULL, 0, NULL); +} + +static const struct of_device_id bcm2835_pm_of_match[] = { + { .compatible = "brcm,bcm2835-pm-wdt", }, + {}, +}; +MODULE_DEVICE_TABLE(of, bcm2835_pm_of_match); + +static struct platform_driver bcm2835_pm_driver = { + .probe = bcm2835_pm_probe, + .driver = { + .name = "bcm2835-pm", + .of_match_table = bcm2835_pm_of_match, + }, +}; +module_platform_driver(bcm2835_pm_driver); + +MODULE_AUTHOR("Eric Anholt "); +MODULE_DESCRIPTION("Driver for Broadcom BCM2835 PM MFD"); +MODULE_LICENSE("GPL"); diff --git a/drivers/watchdog/bcm2835_wdt.c b/drivers/watchdog/bcm2835_wdt.c index ed05514cc2dc..1834524ae373 100644 --- a/drivers/watchdog/bcm2835_wdt.c +++ b/drivers/watchdog/bcm2835_wdt.c @@ -12,6 +12,7 @@ #include #include +#include #include #include #include @@ -47,6 +48,8 @@ struct bcm2835_wdt { spinlock_t lock; }; +static struct bcm2835_wdt *bcm2835_power_off_wdt; + static unsigned int heartbeat; static bool nowayout = WATCHDOG_NOWAYOUT; @@ -148,10 +151,7 @@ static struct watchdog_device bcm2835_wdt_wdd = { */ static void bcm2835_power_off(void) { - struct device_node *np = - of_find_compatible_node(NULL, NULL, "brcm,bcm2835-pm-wdt"); - struct platform_device *pdev = of_find_device_by_node(np); - struct bcm2835_wdt *wdt = platform_get_drvdata(pdev); + struct bcm2835_wdt *wdt = bcm2835_power_off_wdt; u32 val; /* @@ -169,7 +169,7 @@ static void bcm2835_power_off(void) static int bcm2835_wdt_probe(struct platform_device *pdev) { - struct resource *res; + struct bcm2835_pm *pm = dev_get_drvdata(pdev->dev.parent); struct device *dev = &pdev->dev; struct bcm2835_wdt *wdt; int err; @@ -181,10 +181,7 @@ static int bcm2835_wdt_probe(struct platform_device *pdev) spin_lock_init(&wdt->lock); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - wdt->base = devm_ioremap_resource(dev, res); - if (IS_ERR(wdt->base)) - return PTR_ERR(wdt->base); + wdt->base = pm->base; watchdog_set_drvdata(&bcm2835_wdt_wdd, wdt); watchdog_init_timeout(&bcm2835_wdt_wdd, heartbeat, dev); @@ -211,8 +208,10 @@ static int bcm2835_wdt_probe(struct platform_device *pdev) return err; } - if (pm_power_off == NULL) + if (pm_power_off == NULL) { pm_power_off = bcm2835_power_off; + bcm2835_power_off_wdt = wdt; + } dev_info(dev, "Broadcom BCM2835 watchdog timer"); return 0; @@ -226,18 +225,11 @@ static int bcm2835_wdt_remove(struct platform_device *pdev) return 0; } -static const struct of_device_id bcm2835_wdt_of_match[] = { - { .compatible = "brcm,bcm2835-pm-wdt", }, - {}, -}; -MODULE_DEVICE_TABLE(of, bcm2835_wdt_of_match); - static struct platform_driver bcm2835_wdt_driver = { .probe = bcm2835_wdt_probe, .remove = bcm2835_wdt_remove, .driver = { .name = "bcm2835-wdt", - .of_match_table = bcm2835_wdt_of_match, }, }; module_platform_driver(bcm2835_wdt_driver); diff --git a/include/linux/mfd/bcm2835-pm.h b/include/linux/mfd/bcm2835-pm.h new file mode 100644 index 000000000000..b7d0ee1feffa --- /dev/null +++ b/include/linux/mfd/bcm2835-pm.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef BCM2835_MFD_PM_H +#define BCM2835_MFD_PM_H + +#include + +struct bcm2835_pm { + struct device *dev; + void __iomem *base; +}; + +#endif /* BCM2835_MFD_PM_H */ -- cgit v1.2.3 From 670c672608a1ffcbc7ac0f872734843593bb8b15 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Wed, 12 Dec 2018 15:51:48 -0800 Subject: soc: bcm: bcm2835-pm: Add support for power domains under a new binding. This provides a free software alternative to raspberrypi-power.c's firmware calls to manage power domains. It also exposes a reset line, where previously the vc4 driver had to try to force power off the domain in order to trigger a reset. Signed-off-by: Eric Anholt Acked-by: Rob Herring Acked-by: Stefan Wahren Signed-off-by: Stefan Wahren --- drivers/mfd/bcm2835-pm.c | 36 +- drivers/soc/bcm/Kconfig | 11 + drivers/soc/bcm/Makefile | 1 + drivers/soc/bcm/bcm2835-power.c | 661 +++++++++++++++++++++++++++++++++++ include/dt-bindings/soc/bcm2835-pm.h | 28 ++ include/linux/mfd/bcm2835-pm.h | 1 + 6 files changed, 734 insertions(+), 4 deletions(-) create mode 100644 drivers/soc/bcm/bcm2835-power.c create mode 100644 include/dt-bindings/soc/bcm2835-pm.h (limited to 'include') diff --git a/drivers/mfd/bcm2835-pm.c b/drivers/mfd/bcm2835-pm.c index 53839e6a81e7..42fe67f1538e 100644 --- a/drivers/mfd/bcm2835-pm.c +++ b/drivers/mfd/bcm2835-pm.c @@ -3,7 +3,7 @@ * PM MFD driver for Broadcom BCM2835 * * This driver binds to the PM block and creates the MFD device for - * the WDT driver. + * the WDT and power drivers. */ #include @@ -21,11 +21,16 @@ static const struct mfd_cell bcm2835_pm_devs[] = { { .name = "bcm2835-wdt" }, }; +static const struct mfd_cell bcm2835_power_devs[] = { + { .name = "bcm2835-power" }, +}; + static int bcm2835_pm_probe(struct platform_device *pdev) { struct resource *res; struct device *dev = &pdev->dev; struct bcm2835_pm *pm; + int ret; pm = devm_kzalloc(dev, sizeof(*pm), GFP_KERNEL); if (!pm) @@ -39,13 +44,36 @@ static int bcm2835_pm_probe(struct platform_device *pdev) if (IS_ERR(pm->base)) return PTR_ERR(pm->base); - return devm_mfd_add_devices(dev, -1, - bcm2835_pm_devs, ARRAY_SIZE(bcm2835_pm_devs), - NULL, 0, NULL); + ret = devm_mfd_add_devices(dev, -1, + bcm2835_pm_devs, ARRAY_SIZE(bcm2835_pm_devs), + NULL, 0, NULL); + if (ret) + return ret; + + /* We'll use the presence of the AXI ASB regs in the + * bcm2835-pm binding as the key for whether we can reference + * the full PM register range and support power domains. + */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (res) { + pm->asb = devm_ioremap_resource(dev, res); + if (IS_ERR(pm->asb)) + return PTR_ERR(pm->asb); + + ret = devm_mfd_add_devices(dev, -1, + bcm2835_power_devs, + ARRAY_SIZE(bcm2835_power_devs), + NULL, 0, NULL); + if (ret) + return ret; + } + + return 0; } static const struct of_device_id bcm2835_pm_of_match[] = { { .compatible = "brcm,bcm2835-pm-wdt", }, + { .compatible = "brcm,bcm2835-pm", }, {}, }; MODULE_DEVICE_TABLE(of, bcm2835_pm_of_match); diff --git a/drivers/soc/bcm/Kconfig b/drivers/soc/bcm/Kconfig index 055a845ed979..fe1af29560e9 100644 --- a/drivers/soc/bcm/Kconfig +++ b/drivers/soc/bcm/Kconfig @@ -1,5 +1,16 @@ menu "Broadcom SoC drivers" +config BCM2835_POWER + bool "BCM2835 power domain driver" + depends on ARCH_BCM2835 || (COMPILE_TEST && OF) + select PM_GENERIC_DOMAINS if PM + select RESET_CONTROLLER + help + This enables support for the BCM2835 power domains and reset + controller. Any usage of power domains by the Raspberry Pi + firmware means that Linux usage of the same power domain + must be accessed using the RASPBERRYPI_POWER driver + config RASPBERRYPI_POWER bool "Raspberry Pi power domain driver" depends on ARCH_BCM2835 || (COMPILE_TEST && OF) diff --git a/drivers/soc/bcm/Makefile b/drivers/soc/bcm/Makefile index dc4fced72d21..c81df4b2403c 100644 --- a/drivers/soc/bcm/Makefile +++ b/drivers/soc/bcm/Makefile @@ -1,2 +1,3 @@ +obj-$(CONFIG_BCM2835_POWER) += bcm2835-power.o obj-$(CONFIG_RASPBERRYPI_POWER) += raspberrypi-power.o obj-$(CONFIG_SOC_BRCMSTB) += brcmstb/ diff --git a/drivers/soc/bcm/bcm2835-power.c b/drivers/soc/bcm/bcm2835-power.c new file mode 100644 index 000000000000..48412957ec7a --- /dev/null +++ b/drivers/soc/bcm/bcm2835-power.c @@ -0,0 +1,661 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Power domain driver for Broadcom BCM2835 + * + * Copyright (C) 2018 Broadcom + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define PM_GNRIC 0x00 +#define PM_AUDIO 0x04 +#define PM_STATUS 0x18 +#define PM_RSTC 0x1c +#define PM_RSTS 0x20 +#define PM_WDOG 0x24 +#define PM_PADS0 0x28 +#define PM_PADS2 0x2c +#define PM_PADS3 0x30 +#define PM_PADS4 0x34 +#define PM_PADS5 0x38 +#define PM_PADS6 0x3c +#define PM_CAM0 0x44 +#define PM_CAM0_LDOHPEN BIT(2) +#define PM_CAM0_LDOLPEN BIT(1) +#define PM_CAM0_CTRLEN BIT(0) + +#define PM_CAM1 0x48 +#define PM_CAM1_LDOHPEN BIT(2) +#define PM_CAM1_LDOLPEN BIT(1) +#define PM_CAM1_CTRLEN BIT(0) + +#define PM_CCP2TX 0x4c +#define PM_CCP2TX_LDOEN BIT(1) +#define PM_CCP2TX_CTRLEN BIT(0) + +#define PM_DSI0 0x50 +#define PM_DSI0_LDOHPEN BIT(2) +#define PM_DSI0_LDOLPEN BIT(1) +#define PM_DSI0_CTRLEN BIT(0) + +#define PM_DSI1 0x54 +#define PM_DSI1_LDOHPEN BIT(2) +#define PM_DSI1_LDOLPEN BIT(1) +#define PM_DSI1_CTRLEN BIT(0) + +#define PM_HDMI 0x58 +#define PM_HDMI_RSTDR BIT(19) +#define PM_HDMI_LDOPD BIT(1) +#define PM_HDMI_CTRLEN BIT(0) + +#define PM_USB 0x5c +/* The power gates must be enabled with this bit before enabling the LDO in the + * USB block. + */ +#define PM_USB_CTRLEN BIT(0) + +#define PM_PXLDO 0x60 +#define PM_PXBG 0x64 +#define PM_DFT 0x68 +#define PM_SMPS 0x6c +#define PM_XOSC 0x70 +#define PM_SPAREW 0x74 +#define PM_SPARER 0x78 +#define PM_AVS_RSTDR 0x7c +#define PM_AVS_STAT 0x80 +#define PM_AVS_EVENT 0x84 +#define PM_AVS_INTEN 0x88 +#define PM_DUMMY 0xfc + +#define PM_IMAGE 0x108 +#define PM_GRAFX 0x10c +#define PM_PROC 0x110 +#define PM_ENAB BIT(12) +#define PM_ISPRSTN BIT(8) +#define PM_H264RSTN BIT(7) +#define PM_PERIRSTN BIT(6) +#define PM_V3DRSTN BIT(6) +#define PM_ISFUNC BIT(5) +#define PM_MRDONE BIT(4) +#define PM_MEMREP BIT(3) +#define PM_ISPOW BIT(2) +#define PM_POWOK BIT(1) +#define PM_POWUP BIT(0) +#define PM_INRUSH_SHIFT 13 +#define PM_INRUSH_3_5_MA 0 +#define PM_INRUSH_5_MA 1 +#define PM_INRUSH_10_MA 2 +#define PM_INRUSH_20_MA 3 +#define PM_INRUSH_MASK (3 << PM_INRUSH_SHIFT) + +#define PM_PASSWORD 0x5a000000 + +#define PM_WDOG_TIME_SET 0x000fffff +#define PM_RSTC_WRCFG_CLR 0xffffffcf +#define PM_RSTS_HADWRH_SET 0x00000040 +#define PM_RSTC_WRCFG_SET 0x00000030 +#define PM_RSTC_WRCFG_FULL_RESET 0x00000020 +#define PM_RSTC_RESET 0x00000102 + +#define PM_READ(reg) readl(power->base + (reg)) +#define PM_WRITE(reg, val) writel(PM_PASSWORD | (val), power->base + (reg)) + +#define ASB_BRDG_VERSION 0x00 +#define ASB_CPR_CTRL 0x04 + +#define ASB_V3D_S_CTRL 0x08 +#define ASB_V3D_M_CTRL 0x0c +#define ASB_ISP_S_CTRL 0x10 +#define ASB_ISP_M_CTRL 0x14 +#define ASB_H264_S_CTRL 0x18 +#define ASB_H264_M_CTRL 0x1c + +#define ASB_REQ_STOP BIT(0) +#define ASB_ACK BIT(1) +#define ASB_EMPTY BIT(2) +#define ASB_FULL BIT(3) + +#define ASB_AXI_BRDG_ID 0x20 + +#define ASB_READ(reg) readl(power->asb + (reg)) +#define ASB_WRITE(reg, val) writel(PM_PASSWORD | (val), power->asb + (reg)) + +struct bcm2835_power_domain { + struct generic_pm_domain base; + struct bcm2835_power *power; + u32 domain; + struct clk *clk; +}; + +struct bcm2835_power { + struct device *dev; + /* PM registers. */ + void __iomem *base; + /* AXI Async bridge registers. */ + void __iomem *asb; + + struct genpd_onecell_data pd_xlate; + struct bcm2835_power_domain domains[BCM2835_POWER_DOMAIN_COUNT]; + struct reset_controller_dev reset; +}; + +static int bcm2835_asb_enable(struct bcm2835_power *power, u32 reg) +{ + u64 start = ktime_get_ns(); + + /* Enable the module's async AXI bridges. */ + ASB_WRITE(reg, ASB_READ(reg) & ~ASB_REQ_STOP); + while (ASB_READ(reg) & ASB_ACK) { + cpu_relax(); + if (ktime_get_ns() - start >= 1000) + return -ETIMEDOUT; + } + + return 0; +} + +static int bcm2835_asb_disable(struct bcm2835_power *power, u32 reg) +{ + u64 start = ktime_get_ns(); + + /* Enable the module's async AXI bridges. */ + ASB_WRITE(reg, ASB_READ(reg) | ASB_REQ_STOP); + while (!(ASB_READ(reg) & ASB_ACK)) { + cpu_relax(); + if (ktime_get_ns() - start >= 1000) + return -ETIMEDOUT; + } + + return 0; +} + +static int bcm2835_power_power_off(struct bcm2835_power_domain *pd, u32 pm_reg) +{ + struct bcm2835_power *power = pd->power; + + /* Enable functional isolation */ + PM_WRITE(pm_reg, PM_READ(pm_reg) & ~PM_ISFUNC); + + /* Enable electrical isolation */ + PM_WRITE(pm_reg, PM_READ(pm_reg) & ~PM_ISPOW); + + /* Open the power switches. */ + PM_WRITE(pm_reg, PM_READ(pm_reg) & ~PM_POWUP); + + return 0; +} + +static int bcm2835_power_power_on(struct bcm2835_power_domain *pd, u32 pm_reg) +{ + struct bcm2835_power *power = pd->power; + struct device *dev = power->dev; + u64 start; + int ret; + int inrush; + bool powok; + + /* If it was already powered on by the fw, leave it that way. */ + if (PM_READ(pm_reg) & PM_POWUP) + return 0; + + /* Enable power. Allowing too much current at once may result + * in POWOK never getting set, so start low and ramp it up as + * necessary to succeed. + */ + powok = false; + for (inrush = PM_INRUSH_3_5_MA; inrush <= PM_INRUSH_20_MA; inrush++) { + PM_WRITE(pm_reg, + (PM_READ(pm_reg) & ~PM_INRUSH_MASK) | + (inrush << PM_INRUSH_SHIFT) | + PM_POWUP); + + start = ktime_get_ns(); + while (!(powok = !!(PM_READ(pm_reg) & PM_POWOK))) { + cpu_relax(); + if (ktime_get_ns() - start >= 3000) + break; + } + } + if (!powok) { + dev_err(dev, "Timeout waiting for %s power OK\n", + pd->base.name); + ret = -ETIMEDOUT; + goto err_disable_powup; + } + + /* Disable electrical isolation */ + PM_WRITE(pm_reg, PM_READ(pm_reg) | PM_ISPOW); + + /* Repair memory */ + PM_WRITE(pm_reg, PM_READ(pm_reg) | PM_MEMREP); + start = ktime_get_ns(); + while (!(PM_READ(pm_reg) & PM_MRDONE)) { + cpu_relax(); + if (ktime_get_ns() - start >= 1000) { + dev_err(dev, "Timeout waiting for %s memory repair\n", + pd->base.name); + ret = -ETIMEDOUT; + goto err_disable_ispow; + } + } + + /* Disable functional isolation */ + PM_WRITE(pm_reg, PM_READ(pm_reg) | PM_ISFUNC); + + return 0; + +err_disable_ispow: + PM_WRITE(pm_reg, PM_READ(pm_reg) & ~PM_ISPOW); +err_disable_powup: + PM_WRITE(pm_reg, PM_READ(pm_reg) & ~(PM_POWUP | PM_INRUSH_MASK)); + return ret; +} + +static int bcm2835_asb_power_on(struct bcm2835_power_domain *pd, + u32 pm_reg, + u32 asb_m_reg, + u32 asb_s_reg, + u32 reset_flags) +{ + struct bcm2835_power *power = pd->power; + int ret; + + ret = clk_prepare_enable(pd->clk); + if (ret) { + dev_err(power->dev, "Failed to enable clock for %s\n", + pd->base.name); + return ret; + } + + /* Wait 32 clocks for reset to propagate, 1 us will be enough */ + udelay(1); + + clk_disable_unprepare(pd->clk); + + /* Deassert the resets. */ + PM_WRITE(pm_reg, PM_READ(pm_reg) | reset_flags); + + ret = clk_prepare_enable(pd->clk); + if (ret) { + dev_err(power->dev, "Failed to enable clock for %s\n", + pd->base.name); + goto err_enable_resets; + } + + ret = bcm2835_asb_enable(power, asb_m_reg); + if (ret) { + dev_err(power->dev, "Failed to enable ASB master for %s\n", + pd->base.name); + goto err_disable_clk; + } + ret = bcm2835_asb_enable(power, asb_s_reg); + if (ret) { + dev_err(power->dev, "Failed to enable ASB slave for %s\n", + pd->base.name); + goto err_disable_asb_master; + } + + return 0; + +err_disable_asb_master: + bcm2835_asb_disable(power, asb_m_reg); +err_disable_clk: + clk_disable_unprepare(pd->clk); +err_enable_resets: + PM_WRITE(pm_reg, PM_READ(pm_reg) & ~reset_flags); + return ret; +} + +static int bcm2835_asb_power_off(struct bcm2835_power_domain *pd, + u32 pm_reg, + u32 asb_m_reg, + u32 asb_s_reg, + u32 reset_flags) +{ + struct bcm2835_power *power = pd->power; + int ret; + + ret = bcm2835_asb_disable(power, asb_s_reg); + if (ret) { + dev_warn(power->dev, "Failed to disable ASB slave for %s\n", + pd->base.name); + return ret; + } + ret = bcm2835_asb_disable(power, asb_m_reg); + if (ret) { + dev_warn(power->dev, "Failed to disable ASB master for %s\n", + pd->base.name); + bcm2835_asb_enable(power, asb_s_reg); + return ret; + } + + clk_disable_unprepare(pd->clk); + + /* Assert the resets. */ + PM_WRITE(pm_reg, PM_READ(pm_reg) & ~reset_flags); + + return 0; +} + +static int bcm2835_power_pd_power_on(struct generic_pm_domain *domain) +{ + struct bcm2835_power_domain *pd = + container_of(domain, struct bcm2835_power_domain, base); + struct bcm2835_power *power = pd->power; + + switch (pd->domain) { + case BCM2835_POWER_DOMAIN_GRAFX: + return bcm2835_power_power_on(pd, PM_GRAFX); + + case BCM2835_POWER_DOMAIN_GRAFX_V3D: + return bcm2835_asb_power_on(pd, PM_GRAFX, + ASB_V3D_M_CTRL, ASB_V3D_S_CTRL, + PM_V3DRSTN); + + case BCM2835_POWER_DOMAIN_IMAGE: + return bcm2835_power_power_on(pd, PM_IMAGE); + + case BCM2835_POWER_DOMAIN_IMAGE_PERI: + return bcm2835_asb_power_on(pd, PM_IMAGE, + 0, 0, + PM_PERIRSTN); + + case BCM2835_POWER_DOMAIN_IMAGE_ISP: + return bcm2835_asb_power_on(pd, PM_IMAGE, + ASB_ISP_M_CTRL, ASB_ISP_S_CTRL, + PM_ISPRSTN); + + case BCM2835_POWER_DOMAIN_IMAGE_H264: + return bcm2835_asb_power_on(pd, PM_IMAGE, + ASB_H264_M_CTRL, ASB_H264_S_CTRL, + PM_H264RSTN); + + case BCM2835_POWER_DOMAIN_USB: + PM_WRITE(PM_USB, PM_USB_CTRLEN); + return 0; + + case BCM2835_POWER_DOMAIN_DSI0: + PM_WRITE(PM_DSI0, PM_DSI0_CTRLEN); + PM_WRITE(PM_DSI0, PM_DSI0_CTRLEN | PM_DSI0_LDOHPEN); + return 0; + + case BCM2835_POWER_DOMAIN_DSI1: + PM_WRITE(PM_DSI1, PM_DSI1_CTRLEN); + PM_WRITE(PM_DSI1, PM_DSI1_CTRLEN | PM_DSI1_LDOHPEN); + return 0; + + case BCM2835_POWER_DOMAIN_CCP2TX: + PM_WRITE(PM_CCP2TX, PM_CCP2TX_CTRLEN); + PM_WRITE(PM_CCP2TX, PM_CCP2TX_CTRLEN | PM_CCP2TX_LDOEN); + return 0; + + case BCM2835_POWER_DOMAIN_HDMI: + PM_WRITE(PM_HDMI, PM_READ(PM_HDMI) | PM_HDMI_RSTDR); + PM_WRITE(PM_HDMI, PM_READ(PM_HDMI) | PM_HDMI_CTRLEN); + PM_WRITE(PM_HDMI, PM_READ(PM_HDMI) & ~PM_HDMI_LDOPD); + usleep_range(100, 200); + PM_WRITE(PM_HDMI, PM_READ(PM_HDMI) & ~PM_HDMI_RSTDR); + return 0; + + default: + dev_err(power->dev, "Invalid domain %d\n", pd->domain); + return -EINVAL; + } +} + +static int bcm2835_power_pd_power_off(struct generic_pm_domain *domain) +{ + struct bcm2835_power_domain *pd = + container_of(domain, struct bcm2835_power_domain, base); + struct bcm2835_power *power = pd->power; + + switch (pd->domain) { + case BCM2835_POWER_DOMAIN_GRAFX: + return bcm2835_power_power_off(pd, PM_GRAFX); + + case BCM2835_POWER_DOMAIN_GRAFX_V3D: + return bcm2835_asb_power_off(pd, PM_GRAFX, + ASB_V3D_M_CTRL, ASB_V3D_S_CTRL, + PM_V3DRSTN); + + case BCM2835_POWER_DOMAIN_IMAGE: + return bcm2835_power_power_off(pd, PM_IMAGE); + + case BCM2835_POWER_DOMAIN_IMAGE_PERI: + return bcm2835_asb_power_off(pd, PM_IMAGE, + 0, 0, + PM_PERIRSTN); + + case BCM2835_POWER_DOMAIN_IMAGE_ISP: + return bcm2835_asb_power_off(pd, PM_IMAGE, + ASB_ISP_M_CTRL, ASB_ISP_S_CTRL, + PM_ISPRSTN); + + case BCM2835_POWER_DOMAIN_IMAGE_H264: + return bcm2835_asb_power_off(pd, PM_IMAGE, + ASB_H264_M_CTRL, ASB_H264_S_CTRL, + PM_H264RSTN); + + case BCM2835_POWER_DOMAIN_USB: + PM_WRITE(PM_USB, 0); + return 0; + + case BCM2835_POWER_DOMAIN_DSI0: + PM_WRITE(PM_DSI0, PM_DSI0_CTRLEN); + PM_WRITE(PM_DSI0, 0); + return 0; + + case BCM2835_POWER_DOMAIN_DSI1: + PM_WRITE(PM_DSI1, PM_DSI1_CTRLEN); + PM_WRITE(PM_DSI1, 0); + return 0; + + case BCM2835_POWER_DOMAIN_CCP2TX: + PM_WRITE(PM_CCP2TX, PM_CCP2TX_CTRLEN); + PM_WRITE(PM_CCP2TX, 0); + return 0; + + case BCM2835_POWER_DOMAIN_HDMI: + PM_WRITE(PM_HDMI, PM_READ(PM_HDMI) | PM_HDMI_LDOPD); + PM_WRITE(PM_HDMI, PM_READ(PM_HDMI) & ~PM_HDMI_CTRLEN); + return 0; + + default: + dev_err(power->dev, "Invalid domain %d\n", pd->domain); + return -EINVAL; + } +} + +static void +bcm2835_init_power_domain(struct bcm2835_power *power, + int pd_xlate_index, const char *name) +{ + struct device *dev = power->dev; + struct bcm2835_power_domain *dom = &power->domains[pd_xlate_index]; + + dom->clk = devm_clk_get(dev->parent, name); + + dom->base.name = name; + dom->base.power_on = bcm2835_power_pd_power_on; + dom->base.power_off = bcm2835_power_pd_power_off; + + dom->domain = pd_xlate_index; + dom->power = power; + + /* XXX: on/off at boot? */ + pm_genpd_init(&dom->base, NULL, true); + + power->pd_xlate.domains[pd_xlate_index] = &dom->base; +} + +/** bcm2835_reset_reset - Resets a block that has a reset line in the + * PM block. + * + * The consumer of the reset controller must have the power domain up + * -- there's no reset ability with the power domain down. To reset + * the sub-block, we just disable its access to memory through the + * ASB, reset, and re-enable. + */ +static int bcm2835_reset_reset(struct reset_controller_dev *rcdev, + unsigned long id) +{ + struct bcm2835_power *power = container_of(rcdev, struct bcm2835_power, + reset); + struct bcm2835_power_domain *pd; + int ret; + + switch (id) { + case BCM2835_RESET_V3D: + pd = &power->domains[BCM2835_POWER_DOMAIN_GRAFX_V3D]; + break; + case BCM2835_RESET_H264: + pd = &power->domains[BCM2835_POWER_DOMAIN_IMAGE_H264]; + break; + case BCM2835_RESET_ISP: + pd = &power->domains[BCM2835_POWER_DOMAIN_IMAGE_ISP]; + break; + default: + dev_err(power->dev, "Bad reset id %ld\n", id); + return -EINVAL; + } + + ret = bcm2835_power_pd_power_off(&pd->base); + if (ret) + return ret; + + return bcm2835_power_pd_power_on(&pd->base); +} + +static int bcm2835_reset_status(struct reset_controller_dev *rcdev, + unsigned long id) +{ + struct bcm2835_power *power = container_of(rcdev, struct bcm2835_power, + reset); + + switch (id) { + case BCM2835_RESET_V3D: + return !PM_READ(PM_GRAFX & PM_V3DRSTN); + case BCM2835_RESET_H264: + return !PM_READ(PM_IMAGE & PM_H264RSTN); + case BCM2835_RESET_ISP: + return !PM_READ(PM_IMAGE & PM_ISPRSTN); + default: + return -EINVAL; + } +} + +const struct reset_control_ops bcm2835_reset_ops = { + .reset = bcm2835_reset_reset, + .status = bcm2835_reset_status, +}; + +static const char *const power_domain_names[] = { + [BCM2835_POWER_DOMAIN_GRAFX] = "grafx", + [BCM2835_POWER_DOMAIN_GRAFX_V3D] = "v3d", + + [BCM2835_POWER_DOMAIN_IMAGE] = "image", + [BCM2835_POWER_DOMAIN_IMAGE_PERI] = "peri_image", + [BCM2835_POWER_DOMAIN_IMAGE_H264] = "h264", + [BCM2835_POWER_DOMAIN_IMAGE_ISP] = "isp", + + [BCM2835_POWER_DOMAIN_USB] = "usb", + [BCM2835_POWER_DOMAIN_DSI0] = "dsi0", + [BCM2835_POWER_DOMAIN_DSI1] = "dsi1", + [BCM2835_POWER_DOMAIN_CAM0] = "cam0", + [BCM2835_POWER_DOMAIN_CAM1] = "cam1", + [BCM2835_POWER_DOMAIN_CCP2TX] = "ccp2tx", + [BCM2835_POWER_DOMAIN_HDMI] = "hdmi", +}; + +static int bcm2835_power_probe(struct platform_device *pdev) +{ + struct bcm2835_pm *pm = dev_get_drvdata(pdev->dev.parent); + struct device *dev = &pdev->dev; + struct bcm2835_power *power; + static const struct { + int parent, child; + } domain_deps[] = { + { BCM2835_POWER_DOMAIN_GRAFX, BCM2835_POWER_DOMAIN_GRAFX_V3D }, + { BCM2835_POWER_DOMAIN_IMAGE, BCM2835_POWER_DOMAIN_IMAGE_PERI }, + { BCM2835_POWER_DOMAIN_IMAGE, BCM2835_POWER_DOMAIN_IMAGE_H264 }, + { BCM2835_POWER_DOMAIN_IMAGE, BCM2835_POWER_DOMAIN_IMAGE_ISP }, + { BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_USB }, + { BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM0 }, + { BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM1 }, + }; + int ret, i; + u32 id; + + power = devm_kzalloc(dev, sizeof(*power), GFP_KERNEL); + if (!power) + return -ENOMEM; + platform_set_drvdata(pdev, power); + + power->dev = dev; + power->base = pm->base; + power->asb = pm->asb; + + id = ASB_READ(ASB_AXI_BRDG_ID); + if (id != 0x62726467 /* "BRDG" */) { + dev_err(dev, "ASB register ID returned 0x%08x\n", id); + return -ENODEV; + } + + power->pd_xlate.domains = devm_kcalloc(dev, + ARRAY_SIZE(power_domain_names), + sizeof(*power->pd_xlate.domains), + GFP_KERNEL); + if (!power->pd_xlate.domains) + return -ENOMEM; + + power->pd_xlate.num_domains = ARRAY_SIZE(power_domain_names); + + for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) + bcm2835_init_power_domain(power, i, power_domain_names[i]); + + for (i = 0; i < ARRAY_SIZE(domain_deps); i++) { + pm_genpd_add_subdomain(&power->domains[domain_deps[i].parent].base, + &power->domains[domain_deps[i].child].base); + } + + power->reset.owner = THIS_MODULE; + power->reset.nr_resets = BCM2835_RESET_COUNT; + power->reset.ops = &bcm2835_reset_ops; + power->reset.of_node = dev->parent->of_node; + + ret = devm_reset_controller_register(dev, &power->reset); + if (ret) + return ret; + + of_genpd_add_provider_onecell(dev->parent->of_node, &power->pd_xlate); + + dev_info(dev, "Broadcom BCM2835 power domains driver"); + return 0; +} + +static int bcm2835_power_remove(struct platform_device *pdev) +{ + return 0; +} + +static struct platform_driver bcm2835_power_driver = { + .probe = bcm2835_power_probe, + .remove = bcm2835_power_remove, + .driver = { + .name = "bcm2835-power", + }, +}; +module_platform_driver(bcm2835_power_driver); + +MODULE_AUTHOR("Eric Anholt "); +MODULE_DESCRIPTION("Driver for Broadcom BCM2835 PM power domains and reset"); +MODULE_LICENSE("GPL"); diff --git a/include/dt-bindings/soc/bcm2835-pm.h b/include/dt-bindings/soc/bcm2835-pm.h new file mode 100644 index 000000000000..153d75b8d99f --- /dev/null +++ b/include/dt-bindings/soc/bcm2835-pm.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */ + +#ifndef _DT_BINDINGS_ARM_BCM2835_PM_H +#define _DT_BINDINGS_ARM_BCM2835_PM_H + +#define BCM2835_POWER_DOMAIN_GRAFX 0 +#define BCM2835_POWER_DOMAIN_GRAFX_V3D 1 +#define BCM2835_POWER_DOMAIN_IMAGE 2 +#define BCM2835_POWER_DOMAIN_IMAGE_PERI 3 +#define BCM2835_POWER_DOMAIN_IMAGE_ISP 4 +#define BCM2835_POWER_DOMAIN_IMAGE_H264 5 +#define BCM2835_POWER_DOMAIN_USB 6 +#define BCM2835_POWER_DOMAIN_DSI0 7 +#define BCM2835_POWER_DOMAIN_DSI1 8 +#define BCM2835_POWER_DOMAIN_CAM0 9 +#define BCM2835_POWER_DOMAIN_CAM1 10 +#define BCM2835_POWER_DOMAIN_CCP2TX 11 +#define BCM2835_POWER_DOMAIN_HDMI 12 + +#define BCM2835_POWER_DOMAIN_COUNT 13 + +#define BCM2835_RESET_V3D 0 +#define BCM2835_RESET_ISP 1 +#define BCM2835_RESET_H264 2 + +#define BCM2835_RESET_COUNT 3 + +#endif /* _DT_BINDINGS_ARM_BCM2835_PM_H */ diff --git a/include/linux/mfd/bcm2835-pm.h b/include/linux/mfd/bcm2835-pm.h index b7d0ee1feffa..ed37dc40e82a 100644 --- a/include/linux/mfd/bcm2835-pm.h +++ b/include/linux/mfd/bcm2835-pm.h @@ -8,6 +8,7 @@ struct bcm2835_pm { struct device *dev; void __iomem *base; + void __iomem *asb; }; #endif /* BCM2835_MFD_PM_H */ -- cgit v1.2.3 From 03c87b95ac04c2a34045641b25dded6e3e889556 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 9 Jan 2019 18:44:00 +0100 Subject: regulator: provide rdev_get_regmap() Provide a helper allowing to access regulator's regmap. Signed-off-by: Bartosz Golaszewski Signed-off-by: Mark Brown --- drivers/regulator/core.c | 6 ++++++ include/linux/regulator/driver.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 3f9d81b6e763..430a73dea487 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5251,6 +5251,12 @@ struct device *rdev_get_dev(struct regulator_dev *rdev) } EXPORT_SYMBOL_GPL(rdev_get_dev); +struct regmap *rdev_get_regmap(struct regulator_dev *rdev) +{ + return rdev->regmap; +} +EXPORT_SYMBOL_GPL(rdev_get_regmap); + void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data) { return reg_init_data->driver_data; diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 389bcaf7900f..795b38a06b6c 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -503,6 +503,7 @@ int regulator_notifier_call_chain(struct regulator_dev *rdev, void *rdev_get_drvdata(struct regulator_dev *rdev); struct device *rdev_get_dev(struct regulator_dev *rdev); +struct regmap *rdev_get_regmap(struct regulator_dev *rdev); int rdev_get_id(struct regulator_dev *rdev); int regulator_mode_to_status(unsigned int); -- cgit v1.2.3 From 412e60373245fd1dfae8d4d44c5d1406b3d90971 Mon Sep 17 00:00:00 2001 From: Martin Sperl Date: Tue, 8 Jan 2019 12:13:45 +0000 Subject: spi: core: avoid waking pump thread from spi_sync instead run teardown delayed When spi_sync is running alone with no other spi devices connected to the bus the worker thread is woken during spi_finalize_current_message to run the teardown code every time. This is totally unnecessary in the case that there is no message queued. On a multi-core system this results in one wakeup of the thread for each spi_message processed via spi_sync where in most cases the teardown does not happen as the hw is already in use. This patch now delays the teardown by 1 second by using a separate kthread_delayed_work for the teardown. This avoids waking the kthread too often. For spi_sync transfers in a tight loop (say 40k messages/s) this avoids the penalty of waking the worker thread 40k times/s. On a rasperry pi 3 with 4 cores the results in 32% of a single core only to find out that there is nothing in the queue and it can go back to sleep. With this patch applied the spi-worker is woken exactly once: after the load finishes and the spi bus is idle for 1 second. I believe I have also seen situations where during a spi_sync loop the worker thread (triggered by the last message finished) is slightly faster and _wins_ the race to process the message, so we are actually running the kthread and letting it do some work... This is also no longer observed with this patch applied as. Tested with a new CAN controller driver for the mcp2517fd which uses spi_sync for interrupt handling and spi_async for scheduling of can frames for transmission (in a different thread) Some statistics when receiving 100000 CAN frames with the mcp25xxfd driver on a Raspberry pi 3: without the patch: ------------------ root@raspcm3:~# for x in $(pgrep spi0) $(pgrep irq/94-mcp25xxf) ; do awk '{printf "%-20s %6i\n", $2,$15}' /proc/$x/stat; done (spi0) 5 (irq/94-mcp25xxf) 0 root@raspcm3:~# vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu----- r b swpd free buff cache si so bi bo in cs us sy id wa st 1 0 0 821960 13592 50848 0 0 80 2 1986 105 1 2 97 0 0 0 0 0 821968 13592 50876 0 0 0 0 8046 30 0 0 100 0 0 0 0 0 821936 13592 50876 0 0 0 0 8032 24 0 0 100 0 0 0 0 0 821936 13592 50876 0 0 0 0 8035 30 0 0 100 0 0 0 0 0 821936 13592 50876 0 0 0 0 8033 22 0 0 100 0 0 2 0 0 821936 13592 50876 0 0 0 0 11598 7129 0 3 97 0 0 1 0 0 821872 13592 50876 0 0 0 0 37741 59003 0 31 69 0 0 2 0 0 821840 13592 50876 0 0 0 0 37762 59078 0 29 71 0 0 2 0 0 821776 13592 50876 0 0 0 0 37593 58792 0 28 72 0 0 1 0 0 821744 13592 50876 0 0 0 0 37642 58881 0 30 70 0 0 2 0 0 821680 13592 50876 0 0 0 0 37490 58602 0 27 73 0 0 1 0 0 821648 13592 50876 0 0 0 0 37412 58418 0 29 71 0 0 1 0 0 821584 13592 50876 0 0 0 0 37337 58288 0 27 73 0 0 1 0 0 821552 13592 50876 0 0 0 0 37584 58774 0 27 73 0 0 0 0 0 821520 13592 50876 0 0 0 0 18363 20566 0 9 91 0 0 0 0 0 821520 13592 50876 0 0 0 0 8037 32 0 0 100 0 0 0 0 0 821520 13592 50876 0 0 0 0 8031 23 0 0 100 0 0 0 0 0 821520 13592 50876 0 0 0 0 8034 26 0 0 100 0 0 0 0 0 821520 13592 50876 0 0 0 0 8033 24 0 0 100 0 0 ^C root@raspcm3:~# for x in $(pgrep spi0) $(pgrep irq/94-mcp25xxf) ; do awk '{printf "%-20s %6i\n", $2,$15}' /proc/$x/stat; done (spi0) 228 (irq/94-mcp25xxf) 794 root@raspcm3:~# cat /proc/interrupts CPU0 CPU1 CPU2 CPU3 17: 34 0 0 0 ARMCTRL-level 1 Edge 3f00b880.mailbox 27: 1 0 0 0 ARMCTRL-level 35 Edge timer 33: 1416870 0 0 0 ARMCTRL-level 41 Edge 3f980000.usb, dwc2_hsotg:usb1 34: 1 0 0 0 ARMCTRL-level 42 Edge vc4 35: 0 0 0 0 ARMCTRL-level 43 Edge 3f004000.txp 40: 1753 0 0 0 ARMCTRL-level 48 Edge DMA IRQ 42: 11 0 0 0 ARMCTRL-level 50 Edge DMA IRQ 44: 11 0 0 0 ARMCTRL-level 52 Edge DMA IRQ 45: 0 0 0 0 ARMCTRL-level 53 Edge DMA IRQ 66: 0 0 0 0 ARMCTRL-level 74 Edge vc4 crtc 69: 0 0 0 0 ARMCTRL-level 77 Edge vc4 crtc 70: 0 0 0 0 ARMCTRL-level 78 Edge vc4 crtc 77: 20 0 0 0 ARMCTRL-level 85 Edge 3f205000.i2c, 3f804000.i2c, 3f805000.i2c 78: 6346 0 0 0 ARMCTRL-level 86 Edge 3f204000.spi 80: 205 0 0 0 ARMCTRL-level 88 Edge mmc0 81: 493 0 0 0 ARMCTRL-level 89 Edge uart-pl011 89: 0 0 0 0 bcm2836-timer 0 Edge arch_timer 90: 4291 3821 2180 1649 bcm2836-timer 1 Edge arch_timer 94: 14289 0 0 0 pinctrl-bcm2835 16 Level mcp25xxfd IPI0: 0 0 0 0 CPU wakeup interrupts IPI1: 0 0 0 0 Timer broadcast interrupts IPI2: 3645 242371 7919 1328 Rescheduling interrupts IPI3: 112 543 273 194 Function call interrupts IPI4: 0 0 0 0 CPU stop interrupts IPI5: 1 0 0 0 IRQ work interrupts IPI6: 0 0 0 0 completion interrupts Err: 0 top shows 93% for the mcp25xxfd interrupt handler, 31% for spi0. with the patch: --------------- root@raspcm3:~# for x in $(pgrep spi0) $(pgrep irq/94-mcp25xxf) ; do awk '{printf "%-20s %6i\n", $2,$15}' /proc/$x/stat; done (spi0) 0 (irq/94-mcp25xxf) 0 root@raspcm3:~# vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu----- 0 0 0 804768 13584 62628 0 0 0 0 8038 24 0 0 100 0 0 0 0 0 804768 13584 62628 0 0 0 0 8042 25 0 0 100 0 0 1 0 0 804704 13584 62628 0 0 0 0 9603 2967 0 20 80 0 0 1 0 0 804672 13584 62628 0 0 0 0 9828 3380 0 24 76 0 0 1 0 0 804608 13584 62628 0 0 0 0 9823 3375 0 23 77 0 0 1 0 0 804608 13584 62628 0 0 0 12 9829 3394 0 23 77 0 0 1 0 0 804544 13584 62628 0 0 0 0 9816 3362 0 22 78 0 0 1 0 0 804512 13584 62628 0 0 0 0 9817 3367 0 23 77 0 0 1 0 0 804448 13584 62628 0 0 0 0 9822 3370 0 22 78 0 0 1 0 0 804416 13584 62628 0 0 0 0 9815 3367 0 23 77 0 0 0 0 0 804352 13584 62628 0 0 0 84 9222 2250 0 14 86 0 0 0 0 0 804352 13592 62620 0 0 0 24 8131 209 0 0 93 7 0 0 0 0 804320 13592 62628 0 0 0 0 8041 27 0 0 100 0 0 0 0 0 804352 13592 62628 0 0 0 0 8040 26 0 0 100 0 0 root@raspcm3:~# for x in $(pgrep spi0) $(pgrep irq/94-mcp25xxf) ; do awk '{printf "%-20s %6i\n", $2,$15}' /proc/$x/stat; done (spi0) 0 (irq/94-mcp25xxf) 767 root@raspcm3:~# cat /proc/interrupts CPU0 CPU1 CPU2 CPU3 17: 29 0 0 0 ARMCTRL-level 1 Edge 3f00b880.mailbox 27: 1 0 0 0 ARMCTRL-level 35 Edge timer 33: 1024412 0 0 0 ARMCTRL-level 41 Edge 3f980000.usb, dwc2_hsotg:usb1 34: 1 0 0 0 ARMCTRL-level 42 Edge vc4 35: 0 0 0 0 ARMCTRL-level 43 Edge 3f004000.txp 40: 1773 0 0 0 ARMCTRL-level 48 Edge DMA IRQ 42: 11 0 0 0 ARMCTRL-level 50 Edge DMA IRQ 44: 11 0 0 0 ARMCTRL-level 52 Edge DMA IRQ 45: 0 0 0 0 ARMCTRL-level 53 Edge DMA IRQ 66: 0 0 0 0 ARMCTRL-level 74 Edge vc4 crtc 69: 0 0 0 0 ARMCTRL-level 77 Edge vc4 crtc 70: 0 0 0 0 ARMCTRL-level 78 Edge vc4 crtc 77: 20 0 0 0 ARMCTRL-level 85 Edge 3f205000.i2c, 3f804000.i2c, 3f805000.i2c 78: 6417 0 0 0 ARMCTRL-level 86 Edge 3f204000.spi 80: 237 0 0 0 ARMCTRL-level 88 Edge mmc0 81: 489 0 0 0 ARMCTRL-level 89 Edge uart-pl011 89: 0 0 0 0 bcm2836-timer 0 Edge arch_timer 90: 4048 3704 2383 1892 bcm2836-timer 1 Edge arch_timer 94: 14287 0 0 0 pinctrl-bcm2835 16 Level mcp25xxfd IPI0: 0 0 0 0 CPU wakeup interrupts IPI1: 0 0 0 0 Timer broadcast interrupts IPI2: 2361 2948 7890 1616 Rescheduling interrupts IPI3: 65 617 301 166 Function call interrupts IPI4: 0 0 0 0 CPU stop interrupts IPI5: 1 0 0 0 IRQ work interrupts IPI6: 0 0 0 0 completion interrupts Err: 0 top shows 91% for the mcp25xxfd interrupt handler, 0% for spi0 So we see that spi0 is no longer getting scheduled wasting CPU cycles There are a lot less context switches and corresponding Rescheduling interrupts All of these show that this improves efficiency of the system and reduces CPU utilization. Signed-off-by: Martin Sperl Signed-off-by: Mark Brown --- drivers/spi/spi.c | 122 +++++++++++++++++++++++++++++++++++------------- include/linux/spi/spi.h | 2 + 2 files changed, 91 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 13f447a67d67..06b9139664a3 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1225,7 +1225,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) return; } - /* If another context is idling the device then defer */ + /* If another context is idling the device then defer to kthread */ if (ctlr->idling) { kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages); spin_unlock_irqrestore(&ctlr->queue_lock, flags); @@ -1239,34 +1239,10 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) return; } - /* Only do teardown in the thread */ - if (!in_kthread) { - kthread_queue_work(&ctlr->kworker, - &ctlr->pump_messages); - spin_unlock_irqrestore(&ctlr->queue_lock, flags); - return; - } - - ctlr->busy = false; - ctlr->idling = true; - spin_unlock_irqrestore(&ctlr->queue_lock, flags); - - kfree(ctlr->dummy_rx); - ctlr->dummy_rx = NULL; - kfree(ctlr->dummy_tx); - ctlr->dummy_tx = NULL; - if (ctlr->unprepare_transfer_hardware && - ctlr->unprepare_transfer_hardware(ctlr)) - dev_err(&ctlr->dev, - "failed to unprepare transfer hardware\n"); - if (ctlr->auto_runtime_pm) { - pm_runtime_mark_last_busy(ctlr->dev.parent); - pm_runtime_put_autosuspend(ctlr->dev.parent); - } - trace_spi_controller_idle(ctlr); - - spin_lock_irqsave(&ctlr->queue_lock, flags); - ctlr->idling = false; + /* schedule idle teardown with a delay of 1 second */ + kthread_mod_delayed_work(&ctlr->kworker, + &ctlr->pump_idle_teardown, + HZ); spin_unlock_irqrestore(&ctlr->queue_lock, flags); return; } @@ -1359,6 +1335,77 @@ static void spi_pump_messages(struct kthread_work *work) __spi_pump_messages(ctlr, true); } +/** + * spi_pump_idle_teardown - kthread delayed work function which tears down + * the controller settings after some delay + * @work: pointer to kthread work struct contained in the controller struct + */ +static void spi_pump_idle_teardown(struct kthread_work *work) +{ + struct spi_controller *ctlr = + container_of(work, struct spi_controller, + pump_idle_teardown.work); + unsigned long flags; + + /* Lock queue */ + spin_lock_irqsave(&ctlr->queue_lock, flags); + + /* Make sure we are not already running a message */ + if (ctlr->cur_msg) + goto out; + + /* if there is anything in the list then exit */ + if (!list_empty(&ctlr->queue)) + goto out; + + /* if the controller is running then exit */ + if (ctlr->running) + goto out; + + /* if the controller is busy then exit */ + if (ctlr->busy) + goto out; + + /* if the controller is idling then exit + * this is actually a bit strange and would indicate that + * this function is scheduled twice, which should not happen + */ + if (ctlr->idling) + goto out; + + /* set up the initial states */ + ctlr->busy = false; + ctlr->idling = true; + spin_unlock_irqrestore(&ctlr->queue_lock, flags); + + /* free dummy receive buffers */ + kfree(ctlr->dummy_rx); + ctlr->dummy_rx = NULL; + kfree(ctlr->dummy_tx); + ctlr->dummy_tx = NULL; + + /* unprepare hardware */ + if (ctlr->unprepare_transfer_hardware && + ctlr->unprepare_transfer_hardware(ctlr)) + dev_err(&ctlr->dev, + "failed to unprepare transfer hardware\n"); + /* handle pm */ + if (ctlr->auto_runtime_pm) { + pm_runtime_mark_last_busy(ctlr->dev.parent); + pm_runtime_put_autosuspend(ctlr->dev.parent); + } + + /* mark controller as idle */ + trace_spi_controller_idle(ctlr); + + /* finally put us from idling into stopped */ + spin_lock_irqsave(&ctlr->queue_lock, flags); + ctlr->idling = false; + +out: + spin_unlock_irqrestore(&ctlr->queue_lock, flags); +} + static int spi_init_queue(struct spi_controller *ctlr) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; @@ -1374,7 +1421,8 @@ static int spi_init_queue(struct spi_controller *ctlr) return PTR_ERR(ctlr->kworker_task); } kthread_init_work(&ctlr->pump_messages, spi_pump_messages); - + kthread_init_delayed_work(&ctlr->pump_idle_teardown, + spi_pump_idle_teardown); /* * Controller config will indicate if this controller should run the * message pump with high (realtime) priority to reduce the transfer @@ -1446,7 +1494,16 @@ void spi_finalize_current_message(struct spi_controller *ctlr) spin_lock_irqsave(&ctlr->queue_lock, flags); ctlr->cur_msg = NULL; ctlr->cur_msg_prepared = false; - kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages); + + /* if there is something queued, then wake the queue */ + if (!list_empty(&ctlr->queue)) + kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages); + else + /* otherwise schedule delayed teardown */ + kthread_mod_delayed_work(&ctlr->kworker, + &ctlr->pump_idle_teardown, + HZ); + spin_unlock_irqrestore(&ctlr->queue_lock, flags); trace_spi_message_done(mesg); @@ -1551,7 +1608,7 @@ static int __spi_queued_transfer(struct spi_device *spi, msg->status = -EINPROGRESS; list_add_tail(&msg->queue, &ctlr->queue); - if (!ctlr->busy && need_pump) + if (need_pump) kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages); spin_unlock_irqrestore(&ctlr->queue_lock, flags); @@ -3726,4 +3783,3 @@ err0: * include needing to have boardinfo data structures be much more public. */ postcore_initcall(spi_init); - diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 916bba47d156..79ad62e2487c 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -334,6 +334,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @kworker: thread struct for message pump * @kworker_task: pointer to task for message pump kworker thread * @pump_messages: work struct for scheduling work to the message pump + * @pump_idle_teardown: work structure for scheduling a teardown delayed * @queue_lock: spinlock to syncronise access to message queue * @queue: message queue * @idling: the device is entering idle state @@ -532,6 +533,7 @@ struct spi_controller { struct kthread_worker kworker; struct task_struct *kworker_task; struct kthread_work pump_messages; + struct kthread_delayed_work pump_idle_teardown; spinlock_t queue_lock; struct list_head queue; struct spi_message *cur_msg; -- cgit v1.2.3 From 6131dc81211cfcd8b7bd210665fbe0b6ba2e5fc5 Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Mon, 17 Dec 2018 19:15:36 -0700 Subject: clk: qcom: smd: Add support for MSM8998 rpm clocks Add rpm smd clocks, PMIC and bus clocks which are required on MSM8998 for clients to vote on. Signed-off-by: Jeffrey Hugo Reviewed-by: Rob Herring Signed-off-by: Stephen Boyd --- .../devicetree/bindings/clock/qcom,rpmcc.txt | 1 + drivers/clk/qcom/clk-smd-rpm.c | 63 ++++++++++++++++++++++ include/dt-bindings/clock/qcom,rpmcc.h | 10 ++++ 3 files changed, 74 insertions(+) (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/qcom,rpmcc.txt b/Documentation/devicetree/bindings/clock/qcom,rpmcc.txt index 87b4949e9bc8..944719bd586f 100644 --- a/Documentation/devicetree/bindings/clock/qcom,rpmcc.txt +++ b/Documentation/devicetree/bindings/clock/qcom,rpmcc.txt @@ -16,6 +16,7 @@ Required properties : "qcom,rpmcc-msm8974", "qcom,rpmcc" "qcom,rpmcc-apq8064", "qcom,rpmcc" "qcom,rpmcc-msm8996", "qcom,rpmcc" + "qcom,rpmcc-msm8998", "qcom,rpmcc" "qcom,rpmcc-qcs404", "qcom,rpmcc" - #clock-cells : shall contain 1 diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index d3aadaeb2903..22dd42ad9223 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -655,10 +655,73 @@ static const struct rpm_smd_clk_desc rpm_clk_qcs404 = { .num_clks = ARRAY_SIZE(qcs404_clks), }; +/* msm8998 */ +DEFINE_CLK_SMD_RPM(msm8998, snoc_clk, snoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 1); +DEFINE_CLK_SMD_RPM(msm8998, cnoc_clk, cnoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 2); +DEFINE_CLK_SMD_RPM(msm8998, ce1_clk, ce1_a_clk, QCOM_SMD_RPM_CE_CLK, 0); +DEFINE_CLK_SMD_RPM_XO_BUFFER(msm8998, div_clk1, div_clk1_a, 0xb); +DEFINE_CLK_SMD_RPM(msm8998, ipa_clk, ipa_a_clk, QCOM_SMD_RPM_IPA_CLK, 0); +DEFINE_CLK_SMD_RPM_XO_BUFFER(msm8998, ln_bb_clk1, ln_bb_clk1_a, 1); +DEFINE_CLK_SMD_RPM_XO_BUFFER(msm8998, ln_bb_clk2, ln_bb_clk2_a, 2); +DEFINE_CLK_SMD_RPM_XO_BUFFER_PINCTRL(msm8998, ln_bb_clk3_pin, ln_bb_clk3_a_pin, + 3); +DEFINE_CLK_SMD_RPM(msm8998, mmssnoc_axi_rpm_clk, mmssnoc_axi_rpm_a_clk, + QCOM_SMD_RPM_MMAXI_CLK, 0); +DEFINE_CLK_SMD_RPM(msm8998, aggre1_noc_clk, aggre1_noc_a_clk, + QCOM_SMD_RPM_AGGR_CLK, 1); +DEFINE_CLK_SMD_RPM(msm8998, aggre2_noc_clk, aggre2_noc_a_clk, + QCOM_SMD_RPM_AGGR_CLK, 2); +DEFINE_CLK_SMD_RPM_QDSS(msm8998, qdss_clk, qdss_a_clk, + QCOM_SMD_RPM_MISC_CLK, 1); +DEFINE_CLK_SMD_RPM_XO_BUFFER(msm8998, rf_clk1, rf_clk1_a, 4); +DEFINE_CLK_SMD_RPM_XO_BUFFER_PINCTRL(msm8998, rf_clk2_pin, rf_clk2_a_pin, 5); +DEFINE_CLK_SMD_RPM_XO_BUFFER(msm8998, rf_clk3, rf_clk3_a, 6); +DEFINE_CLK_SMD_RPM_XO_BUFFER_PINCTRL(msm8998, rf_clk3_pin, rf_clk3_a_pin, 6); +static struct clk_smd_rpm *msm8998_clks[] = { + [RPM_SMD_SNOC_CLK] = &msm8998_snoc_clk, + [RPM_SMD_SNOC_A_CLK] = &msm8998_snoc_a_clk, + [RPM_SMD_CNOC_CLK] = &msm8998_cnoc_clk, + [RPM_SMD_CNOC_A_CLK] = &msm8998_cnoc_a_clk, + [RPM_SMD_CE1_CLK] = &msm8998_ce1_clk, + [RPM_SMD_CE1_A_CLK] = &msm8998_ce1_a_clk, + [RPM_SMD_DIV_CLK1] = &msm8998_div_clk1, + [RPM_SMD_DIV_A_CLK1] = &msm8998_div_clk1_a, + [RPM_SMD_IPA_CLK] = &msm8998_ipa_clk, + [RPM_SMD_IPA_A_CLK] = &msm8998_ipa_a_clk, + [RPM_SMD_LN_BB_CLK1] = &msm8998_ln_bb_clk1, + [RPM_SMD_LN_BB_CLK1_A] = &msm8998_ln_bb_clk1_a, + [RPM_SMD_LN_BB_CLK2] = &msm8998_ln_bb_clk2, + [RPM_SMD_LN_BB_CLK2_A] = &msm8998_ln_bb_clk2_a, + [RPM_SMD_LN_BB_CLK3_PIN] = &msm8998_ln_bb_clk3_pin, + [RPM_SMD_LN_BB_CLK3_A_PIN] = &msm8998_ln_bb_clk3_a_pin, + [RPM_SMD_MMAXI_CLK] = &msm8998_mmssnoc_axi_rpm_clk, + [RPM_SMD_MMAXI_A_CLK] = &msm8998_mmssnoc_axi_rpm_a_clk, + [RPM_SMD_AGGR1_NOC_CLK] = &msm8998_aggre1_noc_clk, + [RPM_SMD_AGGR1_NOC_A_CLK] = &msm8998_aggre1_noc_a_clk, + [RPM_SMD_AGGR2_NOC_CLK] = &msm8998_aggre2_noc_clk, + [RPM_SMD_AGGR2_NOC_A_CLK] = &msm8998_aggre2_noc_a_clk, + [RPM_SMD_QDSS_CLK] = &msm8998_qdss_clk, + [RPM_SMD_QDSS_A_CLK] = &msm8998_qdss_a_clk, + [RPM_SMD_RF_CLK1] = &msm8998_rf_clk1, + [RPM_SMD_RF_CLK1_A] = &msm8998_rf_clk1_a, + [RPM_SMD_RF_CLK2_PIN] = &msm8998_rf_clk2_pin, + [RPM_SMD_RF_CLK2_A_PIN] = &msm8998_rf_clk2_a_pin, + [RPM_SMD_RF_CLK3] = &msm8998_rf_clk3, + [RPM_SMD_RF_CLK3_A] = &msm8998_rf_clk3_a, + [RPM_SMD_RF_CLK3_PIN] = &msm8998_rf_clk3_pin, + [RPM_SMD_RF_CLK3_A_PIN] = &msm8998_rf_clk3_a_pin, +}; + +static const struct rpm_smd_clk_desc rpm_clk_msm8998 = { + .clks = msm8998_clks, + .num_clks = ARRAY_SIZE(msm8998_clks), +}; + static const struct of_device_id rpm_smd_clk_match_table[] = { { .compatible = "qcom,rpmcc-msm8916", .data = &rpm_clk_msm8916 }, { .compatible = "qcom,rpmcc-msm8974", .data = &rpm_clk_msm8974 }, { .compatible = "qcom,rpmcc-msm8996", .data = &rpm_clk_msm8996 }, + { .compatible = "qcom,rpmcc-msm8998", .data = &rpm_clk_msm8998 }, { .compatible = "qcom,rpmcc-qcs404", .data = &rpm_clk_qcs404 }, { } }; diff --git a/include/dt-bindings/clock/qcom,rpmcc.h b/include/dt-bindings/clock/qcom,rpmcc.h index 3658b0c14966..ede93a0ca156 100644 --- a/include/dt-bindings/clock/qcom,rpmcc.h +++ b/include/dt-bindings/clock/qcom,rpmcc.h @@ -127,5 +127,15 @@ #define RPM_SMD_BIMC_GPU_A_CLK 77 #define RPM_SMD_QPIC_CLK 78 #define RPM_SMD_QPIC_CLK_A 79 +#define RPM_SMD_LN_BB_CLK1 80 +#define RPM_SMD_LN_BB_CLK1_A 81 +#define RPM_SMD_LN_BB_CLK2 82 +#define RPM_SMD_LN_BB_CLK2_A 83 +#define RPM_SMD_LN_BB_CLK3_PIN 84 +#define RPM_SMD_LN_BB_CLK3_A_PIN 85 +#define RPM_SMD_RF_CLK3 86 +#define RPM_SMD_RF_CLK3_A 87 +#define RPM_SMD_RF_CLK3_PIN 88 +#define RPM_SMD_RF_CLK3_A_PIN 89 #endif -- cgit v1.2.3 From 19e99de9a53f9ece6baf8e9a15428aedd4b20c86 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 8 Jan 2019 10:15:36 +0100 Subject: ARM: davinci: remove dead code related to MAC address reading There are no more users of davinci_get_mac_addr(). Remove it. Signed-off-by: Bartosz Golaszewski Signed-off-by: Sekhar Nori --- arch/arm/mach-davinci/common.c | 15 --------------- include/linux/davinci_emac.h | 1 - 2 files changed, 16 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-davinci/common.c b/arch/arm/mach-davinci/common.c index e1d0f0d841ff..0c638fe15dcb 100644 --- a/arch/arm/mach-davinci/common.c +++ b/arch/arm/mach-davinci/common.c @@ -26,21 +26,6 @@ EXPORT_SYMBOL(davinci_soc_info); void __iomem *davinci_intc_base; int davinci_intc_type; -void davinci_get_mac_addr(struct nvmem_device *nvmem, void *context) -{ - char *mac_addr = davinci_soc_info.emac_pdata->mac_addr; - off_t offset = (off_t)context; - - if (!IS_BUILTIN(CONFIG_NVMEM)) { - pr_warn("Cannot read MAC addr from EEPROM without CONFIG_NVMEM\n"); - return; - } - - /* Read MAC addr from EEPROM */ - if (nvmem_device_read(nvmem, offset, ETH_ALEN, mac_addr) == ETH_ALEN) - pr_info("Read MAC addr from EEPROM: %pM\n", mac_addr); -} - static int __init davinci_init_id(struct davinci_soc_info *soc_info) { int i; diff --git a/include/linux/davinci_emac.h b/include/linux/davinci_emac.h index 05b97144d342..28e6cf1356da 100644 --- a/include/linux/davinci_emac.h +++ b/include/linux/davinci_emac.h @@ -46,5 +46,4 @@ enum { EMAC_VERSION_2, /* DM646x */ }; -void davinci_get_mac_addr(struct nvmem_device *nvmem, void *context); #endif -- cgit v1.2.3 From cc2d22477779f189595db5c515bd5ef9c75a1f35 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Mon, 7 Jan 2019 20:49:39 +0100 Subject: pwm: Drop per-chip dbg_show callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This callback was introduced in commit 62099abf67a2 ("pwm: Add debugfs interface") in 2012 and up to now there is not a single user. So drop this unused code. Signed-off-by: Uwe Kleine-König [thierry.reding@gmail.com: remove kerneldoc for ->dbg_show()] Signed-off-by: Thierry Reding --- drivers/pwm/core.c | 5 +---- include/linux/pwm.h | 4 ---- 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 253a459fe0d8..3149204567f3 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -1036,10 +1036,7 @@ static int pwm_seq_show(struct seq_file *s, void *v) dev_name(chip->dev), chip->npwm, (chip->npwm != 1) ? "s" : ""); - if (chip->ops->dbg_show) - chip->ops->dbg_show(chip, s); - else - pwm_dbg_show(chip, s); + pwm_dbg_show(chip, s); return 0; } diff --git a/include/linux/pwm.h b/include/linux/pwm.h index d5199b507d79..6a544cb89de4 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -254,7 +254,6 @@ pwm_set_relative_duty_cycle(struct pwm_state *state, unsigned int duty_cycle, * @get_state: get the current PWM state. This function is only * called once per PWM device when the PWM chip is * registered. - * @dbg_show: optional routine to show contents in debugfs * @owner: helps prevent removal of modules exporting active PWMs */ struct pwm_ops { @@ -272,9 +271,6 @@ struct pwm_ops { struct pwm_state *state); void (*get_state)(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_state *state); -#ifdef CONFIG_DEBUG_FS - void (*dbg_show)(struct pwm_chip *chip, struct seq_file *s); -#endif struct module *owner; }; -- cgit v1.2.3 From 5d0a4c11896e8b83f816f135c24b184d4ba57741 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Mon, 7 Jan 2019 20:49:41 +0100 Subject: pwm: Rearrange structures to group members by purpose MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In pwm_ops there are a few callbacks that are not supposed to be used by new drivers. Group them at the end of the structure and add a comment. Similarily for struct pwm_chip group the members that drivers shouldn't care about at the end and mark them as internal with another comment. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/linux/pwm.h | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 6a544cb89de4..b628abfffacc 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -242,11 +242,7 @@ pwm_set_relative_duty_cycle(struct pwm_state *state, unsigned int duty_cycle, * struct pwm_ops - PWM controller operations * @request: optional hook for requesting a PWM * @free: optional hook for freeing a PWM - * @config: configure duty cycles and period length for this PWM - * @set_polarity: configure the polarity of this PWM * @capture: capture and report PWM signal - * @enable: enable PWM output toggling - * @disable: disable PWM output toggling * @apply: atomically apply a new PWM config. The state argument * should be adjusted with the real hardware config (if the * approximate the period or duty_cycle value, state should @@ -255,48 +251,55 @@ pwm_set_relative_duty_cycle(struct pwm_state *state, unsigned int duty_cycle, * called once per PWM device when the PWM chip is * registered. * @owner: helps prevent removal of modules exporting active PWMs + * @config: configure duty cycles and period length for this PWM + * @set_polarity: configure the polarity of this PWM + * @enable: enable PWM output toggling + * @disable: disable PWM output toggling */ struct pwm_ops { int (*request)(struct pwm_chip *chip, struct pwm_device *pwm); void (*free)(struct pwm_chip *chip, struct pwm_device *pwm); - int (*config)(struct pwm_chip *chip, struct pwm_device *pwm, - int duty_ns, int period_ns); - int (*set_polarity)(struct pwm_chip *chip, struct pwm_device *pwm, - enum pwm_polarity polarity); int (*capture)(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_capture *result, unsigned long timeout); - int (*enable)(struct pwm_chip *chip, struct pwm_device *pwm); - void (*disable)(struct pwm_chip *chip, struct pwm_device *pwm); int (*apply)(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_state *state); void (*get_state)(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_state *state); struct module *owner; + + /* Only used by legacy drivers */ + int (*config)(struct pwm_chip *chip, struct pwm_device *pwm, + int duty_ns, int period_ns); + int (*set_polarity)(struct pwm_chip *chip, struct pwm_device *pwm, + enum pwm_polarity polarity); + int (*enable)(struct pwm_chip *chip, struct pwm_device *pwm); + void (*disable)(struct pwm_chip *chip, struct pwm_device *pwm); }; /** * struct pwm_chip - abstract a PWM controller * @dev: device providing the PWMs - * @list: list node for internal use * @ops: callbacks for this PWM controller * @base: number of first PWM controlled by this chip * @npwm: number of PWMs controlled by this chip - * @pwms: array of PWM devices allocated by the framework * @of_xlate: request a PWM device given a device tree PWM specifier * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier + * @list: list node for internal use + * @pwms: array of PWM devices allocated by the framework */ struct pwm_chip { struct device *dev; - struct list_head list; const struct pwm_ops *ops; int base; unsigned int npwm; - struct pwm_device *pwms; - struct pwm_device * (*of_xlate)(struct pwm_chip *pc, const struct of_phandle_args *args); unsigned int of_pwm_n_cells; + + /* only used internally by the PWM framework */ + struct list_head list; + struct pwm_device *pwms; }; /** -- cgit v1.2.3 From 5a1c18b761ddb299a06746948b9ec2814b04fa92 Mon Sep 17 00:00:00 2001 From: RafaÅ‚ MiÅ‚ecki Date: Wed, 2 Jan 2019 00:00:01 +0100 Subject: bcma: keep a direct pointer to the struct device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Accessing struct device is pretty useful/common so having a direct pointer: 1) Simplifies some code 2) Makes bcma_bus_get_host_dev() unneeded 3) Allows further improvements like using dev_* printing helpers Signed-off-by: RafaÅ‚ MiÅ‚ecki Signed-off-by: Kalle Valo --- drivers/bcma/bcma_private.h | 1 - drivers/bcma/driver_gpio.c | 2 +- drivers/bcma/host_pci.c | 2 ++ drivers/bcma/host_soc.c | 4 ++-- drivers/bcma/main.c | 45 ++++++++++----------------------------------- include/linux/bcma/bcma.h | 11 +++-------- 6 files changed, 18 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index a4aac370f21f..1f0e66310b23 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -33,7 +33,6 @@ int __init bcma_bus_early_register(struct bcma_bus *bus); int bcma_bus_suspend(struct bcma_bus *bus); int bcma_bus_resume(struct bcma_bus *bus); #endif -struct device *bcma_bus_get_host_dev(struct bcma_bus *bus); /* scan.c */ void bcma_detect_chip(struct bcma_bus *bus); diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c index 2c0ffb77d738..a5df3d111334 100644 --- a/drivers/bcma/driver_gpio.c +++ b/drivers/bcma/driver_gpio.c @@ -183,7 +183,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc) chip->direction_input = bcma_gpio_direction_input; chip->direction_output = bcma_gpio_direction_output; chip->owner = THIS_MODULE; - chip->parent = bcma_bus_get_host_dev(bus); + chip->parent = bus->dev; #if IS_BUILTIN(CONFIG_OF) chip->of_node = cc->core->dev.of_node; #endif diff --git a/drivers/bcma/host_pci.c b/drivers/bcma/host_pci.c index 63410ecfe640..f52239feb4cb 100644 --- a/drivers/bcma/host_pci.c +++ b/drivers/bcma/host_pci.c @@ -196,6 +196,8 @@ static int bcma_host_pci_probe(struct pci_dev *dev, goto err_pci_release_regions; } + bus->dev = &dev->dev; + /* Map MMIO */ err = -ENOMEM; bus->mmio = pci_iomap(dev, 0, ~0UL); diff --git a/drivers/bcma/host_soc.c b/drivers/bcma/host_soc.c index 2dce34789329..c8073b509a2b 100644 --- a/drivers/bcma/host_soc.c +++ b/drivers/bcma/host_soc.c @@ -179,7 +179,6 @@ int __init bcma_host_soc_register(struct bcma_soc *soc) /* Host specific */ bus->hosttype = BCMA_HOSTTYPE_SOC; bus->ops = &bcma_host_soc_ops; - bus->host_pdev = NULL; /* Initialize struct, detect chip */ bcma_init_bus(bus); @@ -213,6 +212,8 @@ static int bcma_host_soc_probe(struct platform_device *pdev) if (!bus) return -ENOMEM; + bus->dev = dev; + /* Map MMIO */ bus->mmio = of_iomap(np, 0); if (!bus->mmio) @@ -221,7 +222,6 @@ static int bcma_host_soc_probe(struct platform_device *pdev) /* Host specific */ bus->hosttype = BCMA_HOSTTYPE_SOC; bus->ops = &bcma_host_soc_ops; - bus->host_pdev = pdev; /* Initialize struct, detect chip */ bcma_init_bus(bus); diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index fc1f4acdd189..6535614a7dc1 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -223,8 +223,8 @@ unsigned int bcma_core_irq(struct bcma_device *core, int num) mips_irq = bcma_core_mips_irq(core); return mips_irq <= 4 ? mips_irq + 2 : 0; } - if (bus->host_pdev) - return bcma_of_get_irq(&bus->host_pdev->dev, core, num); + if (bus->dev) + return bcma_of_get_irq(bus->dev, core, num); return 0; case BCMA_HOSTTYPE_SDIO: return 0; @@ -239,18 +239,18 @@ void bcma_prepare_core(struct bcma_bus *bus, struct bcma_device *core) core->dev.release = bcma_release_core_dev; core->dev.bus = &bcma_bus_type; dev_set_name(&core->dev, "bcma%d:%d", bus->num, core->core_index); - core->dev.parent = bcma_bus_get_host_dev(bus); - if (core->dev.parent) - bcma_of_fill_device(core->dev.parent, core); + core->dev.parent = bus->dev; + if (bus->dev) + bcma_of_fill_device(bus->dev, core); switch (bus->hosttype) { case BCMA_HOSTTYPE_PCI: - core->dma_dev = &bus->host_pci->dev; + core->dma_dev = bus->dev; core->irq = bus->host_pci->irq; break; case BCMA_HOSTTYPE_SOC: - if (IS_ENABLED(CONFIG_OF) && bus->host_pdev) { - core->dma_dev = &bus->host_pdev->dev; + if (IS_ENABLED(CONFIG_OF) && bus->dev) { + core->dma_dev = bus->dev; } else { core->dev.dma_mask = &core->dev.coherent_dma_mask; core->dma_dev = &core->dev; @@ -261,28 +261,6 @@ void bcma_prepare_core(struct bcma_bus *bus, struct bcma_device *core) } } -struct device *bcma_bus_get_host_dev(struct bcma_bus *bus) -{ - switch (bus->hosttype) { - case BCMA_HOSTTYPE_PCI: - if (bus->host_pci) - return &bus->host_pci->dev; - else - return NULL; - case BCMA_HOSTTYPE_SOC: - if (bus->host_pdev) - return &bus->host_pdev->dev; - else - return NULL; - case BCMA_HOSTTYPE_SDIO: - if (bus->host_sdio) - return &bus->host_sdio->dev; - else - return NULL; - } - return NULL; -} - void bcma_init_bus(struct bcma_bus *bus) { mutex_lock(&bcma_buses_mutex); @@ -402,7 +380,6 @@ int bcma_bus_register(struct bcma_bus *bus) { int err; struct bcma_device *core; - struct device *dev; /* Scan for devices (cores) */ err = bcma_bus_scan(bus); @@ -425,10 +402,8 @@ int bcma_bus_register(struct bcma_bus *bus) bcma_core_pci_early_init(&bus->drv_pci[0]); } - dev = bcma_bus_get_host_dev(bus); - if (dev) { - of_platform_default_populate(dev->of_node, NULL, dev); - } + if (bus->dev) + of_platform_default_populate(bus->dev->of_node, NULL, bus->dev); /* Cores providing flash access go before SPROM init */ list_for_each_entry(core, &bus->cores, list) { diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index ef61f3607e99..60b94b944e9f 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -332,6 +332,8 @@ extern int bcma_arch_register_fallback_sprom( struct ssb_sprom *out)); struct bcma_bus { + struct device *dev; + /* The MMIO area. */ void __iomem *mmio; @@ -339,14 +341,7 @@ struct bcma_bus { enum bcma_hosttype hosttype; bool host_is_pcie2; /* Used for BCMA_HOSTTYPE_PCI only */ - union { - /* Pointer to the PCI bus (only for BCMA_HOSTTYPE_PCI) */ - struct pci_dev *host_pci; - /* Pointer to the SDIO device (only for BCMA_HOSTTYPE_SDIO) */ - struct sdio_func *host_sdio; - /* Pointer to platform device (only for BCMA_HOSTTYPE_SOC) */ - struct platform_device *host_pdev; - }; + struct pci_dev *host_pci; /* PCI bus pointer (BCMA_HOSTTYPE_PCI only) */ struct bcma_chipinfo chipinfo; -- cgit v1.2.3 From c1a85a00ea66cb6f0bd0f14e47c28c2b0999799f Mon Sep 17 00:00:00 2001 From: Micah Morton Date: Mon, 7 Jan 2019 16:10:53 -0800 Subject: LSM: generalize flag passing to security_capable This patch provides a general mechanism for passing flags to the security_capable LSM hook. It replaces the specific 'audit' flag that is used to tell security_capable whether it should log an audit message for the given capability check. The reason for generalizing this flag passing is so we can add an additional flag that signifies whether security_capable is being called by a setid syscall (which is needed by the proposed SafeSetID LSM). Signed-off-by: Micah Morton Reviewed-by: Kees Cook Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 8 +++++--- include/linux/security.h | 28 ++++++++++++++-------------- kernel/capability.c | 22 +++++++++++++--------- kernel/seccomp.c | 4 ++-- security/apparmor/capability.c | 14 +++++++------- security/apparmor/include/capability.h | 2 +- security/apparmor/ipc.c | 3 ++- security/apparmor/lsm.c | 4 ++-- security/apparmor/resource.c | 2 +- security/commoncap.c | 17 +++++++++-------- security/security.c | 14 +++++--------- security/selinux/hooks.c | 18 +++++++++--------- security/smack/smack_access.c | 2 +- 13 files changed, 71 insertions(+), 67 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 40511a8a5ae6..195707210975 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1270,7 +1270,7 @@ * @cred contains the credentials to use. * @ns contains the user namespace we want the capability in * @cap contains the capability . - * @audit contains whether to write an audit message or not + * @opts contains options for the capable check * Return 0 if the capability is granted for @tsk. * @syslog: * Check permission before accessing the kernel message ring or changing @@ -1446,8 +1446,10 @@ union security_list_options { const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); - int (*capable)(const struct cred *cred, struct user_namespace *ns, - int cap, int audit); + int (*capable)(const struct cred *cred, + struct user_namespace *ns, + int cap, + unsigned int opts); int (*quotactl)(int cmds, int type, int id, struct super_block *sb); int (*quota_on)(struct dentry *dentry); int (*syslog)(int type); diff --git a/include/linux/security.h b/include/linux/security.h index b2c5333ed4b5..13537a49ae97 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -54,9 +54,12 @@ struct xattr; struct xfrm_sec_ctx; struct mm_struct; +/* Default (no) options for the capable function */ +#define CAP_OPT_NONE 0x0 /* If capable should audit the security request */ -#define SECURITY_CAP_NOAUDIT 0 -#define SECURITY_CAP_AUDIT 1 +#define CAP_OPT_NOAUDIT BIT(1) +/* If capable is being called by a setid function */ +#define CAP_OPT_INSETID BIT(2) /* LSM Agnostic defines for sb_set_mnt_opts */ #define SECURITY_LSM_NATIVE_LABELS 1 @@ -72,7 +75,7 @@ enum lsm_event { /* These functions are in security/commoncap.c */ extern int cap_capable(const struct cred *cred, struct user_namespace *ns, - int cap, int audit); + int cap, unsigned int opts); extern int cap_settime(const struct timespec64 *ts, const struct timezone *tz); extern int cap_ptrace_access_check(struct task_struct *child, unsigned int mode); extern int cap_ptrace_traceme(struct task_struct *parent); @@ -207,10 +210,10 @@ int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); -int security_capable(const struct cred *cred, struct user_namespace *ns, - int cap); -int security_capable_noaudit(const struct cred *cred, struct user_namespace *ns, - int cap); +int security_capable(const struct cred *cred, + struct user_namespace *ns, + int cap, + unsigned int opts); int security_quotactl(int cmds, int type, int id, struct super_block *sb); int security_quota_on(struct dentry *dentry); int security_syslog(int type); @@ -464,14 +467,11 @@ static inline int security_capset(struct cred *new, } static inline int security_capable(const struct cred *cred, - struct user_namespace *ns, int cap) + struct user_namespace *ns, + int cap, + unsigned int opts) { - return cap_capable(cred, ns, cap, SECURITY_CAP_AUDIT); -} - -static inline int security_capable_noaudit(const struct cred *cred, - struct user_namespace *ns, int cap) { - return cap_capable(cred, ns, cap, SECURITY_CAP_NOAUDIT); + return cap_capable(cred, ns, cap, opts); } static inline int security_quotactl(int cmds, int type, int id, diff --git a/kernel/capability.c b/kernel/capability.c index 1e1c0236f55b..7718d7dcadc7 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -299,7 +299,7 @@ bool has_ns_capability(struct task_struct *t, int ret; rcu_read_lock(); - ret = security_capable(__task_cred(t), ns, cap); + ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE); rcu_read_unlock(); return (ret == 0); @@ -340,7 +340,7 @@ bool has_ns_capability_noaudit(struct task_struct *t, int ret; rcu_read_lock(); - ret = security_capable_noaudit(__task_cred(t), ns, cap); + ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); @@ -363,7 +363,9 @@ bool has_capability_noaudit(struct task_struct *t, int cap) return has_ns_capability_noaudit(t, &init_user_ns, cap); } -static bool ns_capable_common(struct user_namespace *ns, int cap, bool audit) +static bool ns_capable_common(struct user_namespace *ns, + int cap, + unsigned int opts) { int capable; @@ -372,8 +374,7 @@ static bool ns_capable_common(struct user_namespace *ns, int cap, bool audit) BUG(); } - capable = audit ? security_capable(current_cred(), ns, cap) : - security_capable_noaudit(current_cred(), ns, cap); + capable = security_capable(current_cred(), ns, cap, opts); if (capable == 0) { current->flags |= PF_SUPERPRIV; return true; @@ -394,7 +395,7 @@ static bool ns_capable_common(struct user_namespace *ns, int cap, bool audit) */ bool ns_capable(struct user_namespace *ns, int cap) { - return ns_capable_common(ns, cap, true); + return ns_capable_common(ns, cap, CAP_OPT_NONE); } EXPORT_SYMBOL(ns_capable); @@ -412,7 +413,7 @@ EXPORT_SYMBOL(ns_capable); */ bool ns_capable_noaudit(struct user_namespace *ns, int cap) { - return ns_capable_common(ns, cap, false); + return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT); } EXPORT_SYMBOL(ns_capable_noaudit); @@ -448,10 +449,11 @@ EXPORT_SYMBOL(capable); bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) { + if (WARN_ON_ONCE(!cap_valid(cap))) return false; - if (security_capable(file->f_cred, ns, cap) == 0) + if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0) return true; return false; @@ -500,10 +502,12 @@ bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns) { int ret = 0; /* An absent tracer adds no restrictions */ const struct cred *cred; + rcu_read_lock(); cred = rcu_dereference(tsk->ptracer_cred); if (cred) - ret = security_capable_noaudit(cred, ns, CAP_SYS_PTRACE); + ret = security_capable(cred, ns, CAP_SYS_PTRACE, + CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index d7f538847b84..38a77800def6 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -443,8 +443,8 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) * behavior of privileged children. */ if (!task_no_new_privs(current) && - security_capable_noaudit(current_cred(), current_user_ns(), - CAP_SYS_ADMIN) != 0) + security_capable(current_cred(), current_user_ns(), + CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) != 0) return ERR_PTR(-EACCES); /* Allocate a new seccomp_filter */ diff --git a/security/apparmor/capability.c b/security/apparmor/capability.c index 253ef6e9d445..752f73980e30 100644 --- a/security/apparmor/capability.c +++ b/security/apparmor/capability.c @@ -110,13 +110,13 @@ static int audit_caps(struct common_audit_data *sa, struct aa_profile *profile, * profile_capable - test if profile allows use of capability @cap * @profile: profile being enforced (NOT NULL, NOT unconfined) * @cap: capability to test if allowed - * @audit: whether an audit record should be generated + * @opts: CAP_OPT_NOAUDIT bit determines whether audit record is generated * @sa: audit data (MAY BE NULL indicating no auditing) * * Returns: 0 if allowed else -EPERM */ -static int profile_capable(struct aa_profile *profile, int cap, int audit, - struct common_audit_data *sa) +static int profile_capable(struct aa_profile *profile, int cap, + unsigned int opts, struct common_audit_data *sa) { int error; @@ -126,7 +126,7 @@ static int profile_capable(struct aa_profile *profile, int cap, int audit, else error = -EPERM; - if (audit == SECURITY_CAP_NOAUDIT) { + if (opts & CAP_OPT_NOAUDIT) { if (!COMPLAIN_MODE(profile)) return error; /* audit the cap request in complain mode but note that it @@ -142,13 +142,13 @@ static int profile_capable(struct aa_profile *profile, int cap, int audit, * aa_capable - test permission to use capability * @label: label being tested for capability (NOT NULL) * @cap: capability to be tested - * @audit: whether an audit record should be generated + * @opts: CAP_OPT_NOAUDIT bit determines whether audit record is generated * * Look up capability in profile capability set. * * Returns: 0 on success, or else an error code. */ -int aa_capable(struct aa_label *label, int cap, int audit) +int aa_capable(struct aa_label *label, int cap, unsigned int opts) { struct aa_profile *profile; int error = 0; @@ -156,7 +156,7 @@ int aa_capable(struct aa_label *label, int cap, int audit) sa.u.cap = cap; error = fn_for_each_confined(label, profile, - profile_capable(profile, cap, audit, &sa)); + profile_capable(profile, cap, opts, &sa)); return error; } diff --git a/security/apparmor/include/capability.h b/security/apparmor/include/capability.h index e0304e2aeb7f..1b3663b6ab12 100644 --- a/security/apparmor/include/capability.h +++ b/security/apparmor/include/capability.h @@ -40,7 +40,7 @@ struct aa_caps { extern struct aa_sfs_entry aa_sfs_entry_caps[]; -int aa_capable(struct aa_label *label, int cap, int audit); +int aa_capable(struct aa_label *label, int cap, unsigned int opts); static inline void aa_free_cap_rules(struct aa_caps *caps) { diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c index 527ea1557120..aacd1e95cb59 100644 --- a/security/apparmor/ipc.c +++ b/security/apparmor/ipc.c @@ -107,7 +107,8 @@ static int profile_tracer_perm(struct aa_profile *tracer, aad(sa)->label = &tracer->label; aad(sa)->peer = tracee; aad(sa)->request = 0; - aad(sa)->error = aa_capable(&tracer->label, CAP_SYS_PTRACE, 1); + aad(sa)->error = aa_capable(&tracer->label, CAP_SYS_PTRACE, + CAP_OPT_NONE); return aa_audit(AUDIT_APPARMOR_AUTO, tracer, sa, audit_ptrace_cb); } diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 60ef71268ccf..b6c395e2acd0 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -172,14 +172,14 @@ static int apparmor_capget(struct task_struct *target, kernel_cap_t *effective, } static int apparmor_capable(const struct cred *cred, struct user_namespace *ns, - int cap, int audit) + int cap, unsigned int opts) { struct aa_label *label; int error = 0; label = aa_get_newest_cred_label(cred); if (!unconfined(label)) - error = aa_capable(label, cap, audit); + error = aa_capable(label, cap, opts); aa_put_label(label); return error; diff --git a/security/apparmor/resource.c b/security/apparmor/resource.c index 95fd26d09757..552ed09cb47e 100644 --- a/security/apparmor/resource.c +++ b/security/apparmor/resource.c @@ -124,7 +124,7 @@ int aa_task_setrlimit(struct aa_label *label, struct task_struct *task, */ if (label != peer && - aa_capable(label, CAP_SYS_RESOURCE, SECURITY_CAP_NOAUDIT) != 0) + aa_capable(label, CAP_SYS_RESOURCE, CAP_OPT_NOAUDIT) != 0) error = fn_for_each(label, profile, audit_resource(profile, resource, new_rlim->rlim_max, peer, diff --git a/security/commoncap.c b/security/commoncap.c index 52e04136bfa8..188eaf59f82f 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -68,7 +68,7 @@ static void warn_setuid_and_fcaps_mixed(const char *fname) * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, - int cap, int audit) + int cap, unsigned int opts) { struct user_namespace *ns = targ_ns; @@ -222,12 +222,11 @@ int cap_capget(struct task_struct *target, kernel_cap_t *effective, */ static inline int cap_inh_is_capped(void) { - /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, - CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0) + CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } @@ -1208,8 +1207,9 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), - current_cred()->user_ns, CAP_SETPCAP, - SECURITY_CAP_AUDIT) != 0) /*[4]*/ + current_cred()->user_ns, + CAP_SETPCAP, + CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks @@ -1304,9 +1304,10 @@ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; - if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, - SECURITY_CAP_NOAUDIT) == 0) + if (cap_capable(current_cred(), &init_user_ns, + CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) == 0) cap_sys_admin = 1; + return cap_sys_admin; } @@ -1325,7 +1326,7 @@ int cap_mmap_addr(unsigned long addr) if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, - SECURITY_CAP_AUDIT); + CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; diff --git a/security/security.c b/security/security.c index 953fc3ea18a9..a618e22df5c6 100644 --- a/security/security.c +++ b/security/security.c @@ -689,16 +689,12 @@ int security_capset(struct cred *new, const struct cred *old, effective, inheritable, permitted); } -int security_capable(const struct cred *cred, struct user_namespace *ns, - int cap) +int security_capable(const struct cred *cred, + struct user_namespace *ns, + int cap, + unsigned int opts) { - return call_int_hook(capable, 0, cred, ns, cap, SECURITY_CAP_AUDIT); -} - -int security_capable_noaudit(const struct cred *cred, struct user_namespace *ns, - int cap) -{ - return call_int_hook(capable, 0, cred, ns, cap, SECURITY_CAP_NOAUDIT); + return call_int_hook(capable, 0, cred, ns, cap, opts); } int security_quotactl(int cmds, int type, int id, struct super_block *sb) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index d98e1d8d18f6..b2ee49f938f1 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1578,7 +1578,7 @@ static inline u32 signal_to_av(int sig) /* Check whether a task is allowed to use a capability. */ static int cred_has_capability(const struct cred *cred, - int cap, int audit, bool initns) + int cap, unsigned int opts, bool initns) { struct common_audit_data ad; struct av_decision avd; @@ -1605,7 +1605,7 @@ static int cred_has_capability(const struct cred *cred, rc = avc_has_perm_noaudit(&selinux_state, sid, sid, sclass, av, 0, &avd); - if (audit == SECURITY_CAP_AUDIT) { + if (!(opts & CAP_OPT_NOAUDIT)) { int rc2 = avc_audit(&selinux_state, sid, sid, sclass, av, &avd, rc, &ad, 0); if (rc2) @@ -2125,9 +2125,9 @@ static int selinux_capset(struct cred *new, const struct cred *old, */ static int selinux_capable(const struct cred *cred, struct user_namespace *ns, - int cap, int audit) + int cap, unsigned int opts) { - return cred_has_capability(cred, cap, audit, ns == &init_user_ns); + return cred_has_capability(cred, cap, opts, ns == &init_user_ns); } static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb) @@ -2201,7 +2201,7 @@ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) int rc, cap_sys_admin = 0; rc = cred_has_capability(current_cred(), CAP_SYS_ADMIN, - SECURITY_CAP_NOAUDIT, true); + CAP_OPT_NOAUDIT, true); if (rc == 0) cap_sys_admin = 1; @@ -2988,11 +2988,11 @@ static int selinux_inode_getattr(const struct path *path) static bool has_cap_mac_admin(bool audit) { const struct cred *cred = current_cred(); - int cap_audit = audit ? SECURITY_CAP_AUDIT : SECURITY_CAP_NOAUDIT; + unsigned int opts = audit ? CAP_OPT_NONE : CAP_OPT_NOAUDIT; - if (cap_capable(cred, &init_user_ns, CAP_MAC_ADMIN, cap_audit)) + if (cap_capable(cred, &init_user_ns, CAP_MAC_ADMIN, opts)) return false; - if (cred_has_capability(cred, CAP_MAC_ADMIN, cap_audit, true)) + if (cred_has_capability(cred, CAP_MAC_ADMIN, opts, true)) return false; return true; } @@ -3387,7 +3387,7 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd, case KDSKBENT: case KDSKBSENT: error = cred_has_capability(cred, CAP_SYS_TTY_CONFIG, - SECURITY_CAP_AUDIT, true); + CAP_OPT_NONE, true); break; /* default case assumes that the command will go diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c index 489d49a20b47..fe2ce3a65822 100644 --- a/security/smack/smack_access.c +++ b/security/smack/smack_access.c @@ -640,7 +640,7 @@ bool smack_privileged_cred(int cap, const struct cred *cred) struct smack_known_list_elem *sklep; int rc; - rc = cap_capable(cred, &init_user_ns, cap, SECURITY_CAP_AUDIT); + rc = cap_capable(cred, &init_user_ns, cap, CAP_OPT_NONE); if (rc) return false; -- cgit v1.2.3 From b0ea0fa5435f9df7213a9af098558f7dd584d8e8 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 9 Jan 2019 11:15:16 +0200 Subject: IB/{core,hw}: Have ib_umem_get extract the ib_ucontext from ib_udata ib_umem_get() can only be called in a method callback, which always has a udata parameter. This allows ib_umem_get() to derive the ucontext pointer directly from the udata without requiring the drivers to find it in some way or another. Signed-off-by: Jason Gunthorpe Signed-off-by: Shamir Rabinovitch --- drivers/infiniband/core/umem.c | 9 ++++-- drivers/infiniband/core/uverbs_main.c | 24 ++++++++++++++++ drivers/infiniband/hw/bnxt_re/ib_verbs.c | 13 ++++----- drivers/infiniband/hw/cxgb3/iwch_provider.c | 2 +- drivers/infiniband/hw/cxgb4/mem.c | 2 +- drivers/infiniband/hw/hns/hns_roce_cq.c | 9 +++--- drivers/infiniband/hw/hns/hns_roce_db.c | 6 ++-- drivers/infiniband/hw/hns/hns_roce_device.h | 3 +- drivers/infiniband/hw/hns/hns_roce_mr.c | 7 ++--- drivers/infiniband/hw/hns/hns_roce_qp.c | 13 ++++----- drivers/infiniband/hw/hns/hns_roce_srq.c | 7 ++--- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 2 +- drivers/infiniband/hw/mlx4/cq.c | 17 ++++++------ drivers/infiniband/hw/mlx4/doorbell.c | 6 ++-- drivers/infiniband/hw/mlx4/mlx4_ib.h | 3 +- drivers/infiniband/hw/mlx4/mr.c | 11 ++++---- drivers/infiniband/hw/mlx4/qp.c | 14 ++++++---- drivers/infiniband/hw/mlx4/srq.c | 5 ++-- drivers/infiniband/hw/mlx5/cq.c | 11 ++++---- drivers/infiniband/hw/mlx5/devx.c | 2 +- drivers/infiniband/hw/mlx5/doorbell.c | 6 ++-- drivers/infiniband/hw/mlx5/mlx5_ib.h | 4 ++- drivers/infiniband/hw/mlx5/mr.c | 22 +++++++-------- drivers/infiniband/hw/mlx5/odp.c | 4 +-- drivers/infiniband/hw/mlx5/qp.c | 40 ++++++++++++--------------- drivers/infiniband/hw/mlx5/srq.c | 5 ++-- drivers/infiniband/hw/mthca/mthca_provider.c | 2 +- drivers/infiniband/hw/nes/nes_verbs.c | 2 +- drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 2 +- drivers/infiniband/hw/qedr/verbs.c | 33 +++++++++++----------- drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c | 2 +- drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c | 3 +- drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c | 6 ++-- drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c | 4 +-- drivers/infiniband/sw/rdmavt/mr.c | 3 +- drivers/infiniband/sw/rxe/rxe_mr.c | 2 +- include/rdma/ib_umem.h | 8 ++++-- include/rdma/ib_verbs.h | 1 + 38 files changed, 168 insertions(+), 147 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index c6144df47ea4..1efe0a74e06b 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -72,15 +72,16 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d * If access flags indicate ODP memory, avoid pinning. Instead, stores * the mm for future page fault handling in conjunction with MMU notifiers. * - * @context: userspace context to pin memory for + * @udata: userspace context to pin memory for * @addr: userspace virtual address to start at * @size: length of region to pin * @access: IB_ACCESS_xxx flags for memory being pinned * @dmasync: flush in-flight DMA when the memory region is written */ -struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, +struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, size_t size, int access, int dmasync) { + struct ib_ucontext *context; struct ib_umem *umem; struct page **page_list; struct vm_area_struct **vma_list; @@ -95,6 +96,10 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, struct scatterlist *sg, *sg_list_start; unsigned int gup_flags = FOLL_WRITE; + context = rdma_get_ucontext(udata); + if (IS_ERR(context)) + return ERR_CAST(context); + if (dmasync) dma_attrs |= DMA_ATTR_WRITE_BARRIER; diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index fb0007aa0c27..996f167d1436 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -101,6 +101,30 @@ struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile) } EXPORT_SYMBOL(ib_uverbs_get_ucontext_file); +/* rdma_get_ucontext - Return the ucontext from a udata + * @udata: The udata to get the context from + * + * This can only be called from within a uapi method that was passed ib_udata + * as a parameter. It returns the ucontext associated with the udata, or ERR_PTR + * if the udata is NULL or the ucontext has been disassociated. + */ +struct ib_ucontext *rdma_get_ucontext(struct ib_udata *udata) +{ + if (!udata) + return ERR_PTR(-EIO); + + /* + * FIXME: Really all cases that get here with a udata will have + * already called ib_uverbs_get_ucontext_file, or located a uobject + * that points to a ucontext. We could store that result in the udata + * so this function can't fail. + */ + return ib_uverbs_get_ucontext_file( + container_of(udata, struct uverbs_attr_bundle, driver_udata) + ->ufile); +} +EXPORT_SYMBOL(rdma_get_ucontext); + int uverbs_dealloc_mw(struct ib_mw *mw) { struct ib_pd *pd = mw->pd; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 1e2515e2eb62..9bc637e49faa 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -895,8 +895,7 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd, if (qplib_qp->type == CMDQ_CREATE_QP_TYPE_RC) bytes += (qplib_qp->sq.max_wqe * sizeof(struct sq_psn_search)); bytes = PAGE_ALIGN(bytes); - umem = ib_umem_get(context, ureq.qpsva, bytes, - IB_ACCESS_LOCAL_WRITE, 1); + umem = ib_umem_get(udata, ureq.qpsva, bytes, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(umem)) return PTR_ERR(umem); @@ -908,7 +907,7 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd, if (!qp->qplib_qp.srq) { bytes = (qplib_qp->rq.max_wqe * BNXT_QPLIB_MAX_RQE_ENTRY_SIZE); bytes = PAGE_ALIGN(bytes); - umem = ib_umem_get(context, ureq.qprva, bytes, + umem = ib_umem_get(udata, ureq.qprva, bytes, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(umem)) goto rqfail; @@ -1370,8 +1369,7 @@ static int bnxt_re_init_user_srq(struct bnxt_re_dev *rdev, bytes = (qplib_srq->max_wqe * BNXT_QPLIB_MAX_RQE_ENTRY_SIZE); bytes = PAGE_ALIGN(bytes); - umem = ib_umem_get(context, ureq.srqva, bytes, - IB_ACCESS_LOCAL_WRITE, 1); + umem = ib_umem_get(udata, ureq.srqva, bytes, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(umem)) return PTR_ERR(umem); @@ -2622,7 +2620,7 @@ struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev, goto fail; } - cq->umem = ib_umem_get(context, req.cq_va, + cq->umem = ib_umem_get(udata, req.cq_va, entries * sizeof(struct cq_base), IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(cq->umem)) { @@ -3589,8 +3587,7 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length, /* The fixed portion of the rkey is the same as the lkey */ mr->ib_mr.rkey = mr->qplib_mr.rkey; - umem = ib_umem_get(ib_pd->uobject->context, start, length, - mr_access_flags, 0); + umem = ib_umem_get(udata, start, length, mr_access_flags, 0); if (IS_ERR(umem)) { dev_err(rdev_to_dev(rdev), "Failed to get umem"); rc = -EFAULT; diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index b34b1a1bd94b..92ee6761a3bd 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -540,7 +540,7 @@ static struct ib_mr *iwch_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, mhp->rhp = rhp; - mhp->umem = ib_umem_get(pd->uobject->context, start, length, acc, 0); + mhp->umem = ib_umem_get(udata, start, length, acc, 0); if (IS_ERR(mhp->umem)) { err = PTR_ERR(mhp->umem); kfree(mhp); diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 7b76e6f81aeb..96760a36b9fc 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -537,7 +537,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, mhp->rhp = rhp; - mhp->umem = ib_umem_get(pd->uobject->context, start, length, acc, 0); + mhp->umem = ib_umem_get(udata, start, length, acc, 0); if (IS_ERR(mhp->umem)) goto err_free_skb; diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c index 3a485f50fede..1dfe5627006c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cq.c +++ b/drivers/infiniband/hw/hns/hns_roce_cq.c @@ -215,7 +215,7 @@ void hns_roce_free_cq(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) EXPORT_SYMBOL_GPL(hns_roce_free_cq); static int hns_roce_ib_get_cq_umem(struct hns_roce_dev *hr_dev, - struct ib_ucontext *context, + struct ib_udata *udata, struct hns_roce_cq_buf *buf, struct ib_umem **umem, u64 buf_addr, int cqe) { @@ -223,7 +223,7 @@ static int hns_roce_ib_get_cq_umem(struct hns_roce_dev *hr_dev, u32 page_shift; u32 npages; - *umem = ib_umem_get(context, buf_addr, cqe * hr_dev->caps.cq_entry_sz, + *umem = ib_umem_get(udata, buf_addr, cqe * hr_dev->caps.cq_entry_sz, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(*umem)) return PTR_ERR(*umem); @@ -347,7 +347,7 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev, } /* Get user space address, write it into mtt table */ - ret = hns_roce_ib_get_cq_umem(hr_dev, context, &hr_cq->hr_buf, + ret = hns_roce_ib_get_cq_umem(hr_dev, udata, &hr_cq->hr_buf, &hr_cq->umem, ucmd.buf_addr, cq_entries); if (ret) { @@ -358,7 +358,8 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev, if ((hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RECORD_DB) && (udata->outlen >= sizeof(resp))) { ret = hns_roce_db_map_user(to_hr_ucontext(context), - ucmd.db_addr, &hr_cq->db); + udata, ucmd.db_addr, + &hr_cq->db); if (ret) { dev_err(dev, "cq record doorbell map failed!\n"); goto err_mtt; diff --git a/drivers/infiniband/hw/hns/hns_roce_db.c b/drivers/infiniband/hw/hns/hns_roce_db.c index e2f93c1ce86a..0c6c1fe87705 100644 --- a/drivers/infiniband/hw/hns/hns_roce_db.c +++ b/drivers/infiniband/hw/hns/hns_roce_db.c @@ -8,7 +8,8 @@ #include #include "hns_roce_device.h" -int hns_roce_db_map_user(struct hns_roce_ucontext *context, unsigned long virt, +int hns_roce_db_map_user(struct hns_roce_ucontext *context, + struct ib_udata *udata, unsigned long virt, struct hns_roce_db *db) { struct hns_roce_user_db_page *page; @@ -28,8 +29,7 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context, unsigned long virt, refcount_set(&page->refcount, 1); page->user_virt = (virt & PAGE_MASK); - page->umem = ib_umem_get(&context->ibucontext, virt & PAGE_MASK, - PAGE_SIZE, 0, 0); + page->umem = ib_umem_get(udata, virt & PAGE_MASK, PAGE_SIZE, 0, 0); if (IS_ERR(page->umem)) { ret = PTR_ERR(page->umem); kfree(page); diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 509e467843f6..9a4be70936e0 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -1133,7 +1133,8 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev, int hns_roce_ib_destroy_cq(struct ib_cq *ib_cq); void hns_roce_free_cq(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq); -int hns_roce_db_map_user(struct hns_roce_ucontext *context, unsigned long virt, +int hns_roce_db_map_user(struct hns_roce_ucontext *context, + struct ib_udata *udata, unsigned long virt, struct hns_roce_db *db); void hns_roce_db_unmap_user(struct hns_roce_ucontext *context, struct hns_roce_db *db); diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index ee5991bd4171..da4fffedb879 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -1110,8 +1110,7 @@ struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (!mr) return ERR_PTR(-ENOMEM); - mr->umem = ib_umem_get(pd->uobject->context, start, length, - access_flags, 0); + mr->umem = ib_umem_get(udata, start, length, access_flags, 0); if (IS_ERR(mr->umem)) { ret = PTR_ERR(mr->umem); goto err_free; @@ -1220,8 +1219,8 @@ int hns_roce_rereg_user_mr(struct ib_mr *ibmr, int flags, u64 start, u64 length, } ib_umem_release(mr->umem); - mr->umem = ib_umem_get(ibmr->uobject->context, start, length, - mr_access_flags, 0); + mr->umem = + ib_umem_get(udata, start, length, mr_access_flags, 0); if (IS_ERR(mr->umem)) { ret = PTR_ERR(mr->umem); mr->umem = NULL; diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index b9ba140b50d4..accf9ce1507d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -613,9 +613,8 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, goto err_rq_sge_list; } - hr_qp->umem = ib_umem_get(ib_pd->uobject->context, - ucmd.buf_addr, hr_qp->buff_size, 0, - 0); + hr_qp->umem = ib_umem_get(udata, ucmd.buf_addr, + hr_qp->buff_size, 0, 0); if (IS_ERR(hr_qp->umem)) { dev_err(dev, "ib_umem_get error for create qp\n"); ret = PTR_ERR(hr_qp->umem); @@ -654,8 +653,8 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, (udata->outlen >= sizeof(resp)) && hns_roce_qp_has_sq(init_attr)) { ret = hns_roce_db_map_user( - to_hr_ucontext(ib_pd->uobject->context), - ucmd.sdb_addr, &hr_qp->sdb); + to_hr_ucontext(ib_pd->uobject->context), udata, + ucmd.sdb_addr, &hr_qp->sdb); if (ret) { dev_err(dev, "sq record doorbell map failed!\n"); goto err_mtt; @@ -670,8 +669,8 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, (udata->outlen >= sizeof(resp)) && hns_roce_qp_has_rq(init_attr)) { ret = hns_roce_db_map_user( - to_hr_ucontext(ib_pd->uobject->context), - ucmd.db_addr, &hr_qp->rdb); + to_hr_ucontext(ib_pd->uobject->context), udata, + ucmd.db_addr, &hr_qp->rdb); if (ret) { dev_err(dev, "rq record doorbell map failed!\n"); goto err_sq_dbmap; diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index 960b1946c365..8975f858b36f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -252,8 +252,8 @@ struct ib_srq *hns_roce_create_srq(struct ib_pd *pd, goto err_srq; } - srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, - srq_buf_size, 0, 0); + srq->umem = + ib_umem_get(udata, ucmd.buf_addr, srq_buf_size, 0, 0); if (IS_ERR(srq->umem)) { ret = PTR_ERR(srq->umem); goto err_srq; @@ -280,8 +280,7 @@ struct ib_srq *hns_roce_create_srq(struct ib_pd *pd, goto err_srq_mtt; /* config index queue BA */ - srq->idx_que.umem = ib_umem_get(pd->uobject->context, - ucmd.que_addr, + srq->idx_que.umem = ib_umem_get(udata, ucmd.que_addr, srq->idx_que.buf_size, 0, 0); if (IS_ERR(srq->idx_que.umem)) { dev_err(hr_dev->dev, diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 0b675b0742c2..80b66df95362 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -1852,7 +1852,7 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd, if (length > I40IW_MAX_MR_SIZE) return ERR_PTR(-EINVAL); - region = ib_umem_get(pd->uobject->context, start, length, acc, 0); + region = ib_umem_get(udata, start, length, acc, 0); if (IS_ERR(region)) return (struct ib_mr *)region; diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 43512347b4f0..db936c12b5bd 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -134,16 +134,16 @@ static void mlx4_ib_free_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf * mlx4_buf_free(dev->dev, (cqe + 1) * buf->entry_size, &buf->buf); } -static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_ucontext *context, - struct mlx4_ib_cq_buf *buf, struct ib_umem **umem, - u64 buf_addr, int cqe) +static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_udata *udata, + struct mlx4_ib_cq_buf *buf, + struct ib_umem **umem, u64 buf_addr, int cqe) { int err; int cqe_size = dev->dev->caps.cqe_size; int shift; int n; - *umem = ib_umem_get(context, buf_addr, cqe * cqe_size, + *umem = ib_umem_get(udata, buf_addr, cqe * cqe_size, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(*umem)) return PTR_ERR(*umem); @@ -213,14 +213,13 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, } buf_addr = (void *)(unsigned long)ucmd.buf_addr; - - err = mlx4_ib_get_cq_umem(dev, context, &cq->buf, &cq->umem, + err = mlx4_ib_get_cq_umem(dev, udata, &cq->buf, &cq->umem, ucmd.buf_addr, entries); if (err) goto err_cq; - err = mlx4_ib_db_map_user(to_mucontext(context), ucmd.db_addr, - &cq->db); + err = mlx4_ib_db_map_user(to_mucontext(context), udata, + ucmd.db_addr, &cq->db); if (err) goto err_mtt; @@ -336,7 +335,7 @@ static int mlx4_alloc_resize_umem(struct mlx4_ib_dev *dev, struct mlx4_ib_cq *cq if (!cq->resize_buf) return -ENOMEM; - err = mlx4_ib_get_cq_umem(dev, cq->umem->context, &cq->resize_buf->buf, + err = mlx4_ib_get_cq_umem(dev, udata, &cq->resize_buf->buf, &cq->resize_umem, ucmd.buf_addr, entries); if (err) { kfree(cq->resize_buf); diff --git a/drivers/infiniband/hw/mlx4/doorbell.c b/drivers/infiniband/hw/mlx4/doorbell.c index c51740986367..3aab71b29ce8 100644 --- a/drivers/infiniband/hw/mlx4/doorbell.c +++ b/drivers/infiniband/hw/mlx4/doorbell.c @@ -41,7 +41,8 @@ struct mlx4_ib_user_db_page { int refcnt; }; -int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt, +int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, + struct ib_udata *udata, unsigned long virt, struct mlx4_db *db) { struct mlx4_ib_user_db_page *page; @@ -61,8 +62,7 @@ int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt, page->user_virt = (virt & PAGE_MASK); page->refcnt = 0; - page->umem = ib_umem_get(&context->ibucontext, virt & PAGE_MASK, - PAGE_SIZE, 0, 0); + page->umem = ib_umem_get(udata, virt & PAGE_MASK, PAGE_SIZE, 0, 0); if (IS_ERR(page->umem)) { err = PTR_ERR(page->umem); kfree(page); diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index e491f3eda6e7..60dc1347c5ab 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -722,7 +722,8 @@ static inline u8 mlx4_ib_bond_next_port(struct mlx4_ib_dev *dev) int mlx4_ib_init_sriov(struct mlx4_ib_dev *dev); void mlx4_ib_close_sriov(struct mlx4_ib_dev *dev); -int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt, +int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, + struct ib_udata *udata, unsigned long virt, struct mlx4_db *db); void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_db *db); diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index c7c85c22e4e3..56639ecd53ad 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -367,7 +367,8 @@ end: return block_shift; } -static struct ib_umem *mlx4_get_umem_mr(struct ib_ucontext *context, u64 start, +static struct ib_umem *mlx4_get_umem_mr(struct ib_ucontext *context, + struct ib_udata *udata, u64 start, u64 length, u64 virt_addr, int access_flags) { @@ -398,7 +399,7 @@ static struct ib_umem *mlx4_get_umem_mr(struct ib_ucontext *context, u64 start, up_read(¤t->mm->mmap_sem); } - return ib_umem_get(context, start, length, access_flags, 0); + return ib_umem_get(udata, start, length, access_flags, 0); } struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, @@ -415,7 +416,7 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (!mr) return ERR_PTR(-ENOMEM); - mr->umem = mlx4_get_umem_mr(pd->uobject->context, start, length, + mr->umem = mlx4_get_umem_mr(pd->uobject->context, udata, start, length, virt_addr, access_flags); if (IS_ERR(mr->umem)) { err = PTR_ERR(mr->umem); @@ -506,8 +507,8 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr); ib_umem_release(mmr->umem); mmr->umem = - mlx4_get_umem_mr(mr->uobject->context, start, length, - virt_addr, mr_access_flags); + mlx4_get_umem_mr(mr->uobject->context, udata, start, + length, virt_addr, mr_access_flags); if (IS_ERR(mmr->umem)) { err = PTR_ERR(mmr->umem); /* Prevent mlx4_ib_dereg_mr from free'ing invalid pointer */ diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 971e9a9ebdaf..e38bab50cecf 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1015,9 +1015,11 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, (qp->sq.wqe_cnt << qp->sq.wqe_shift); } - qp->umem = ib_umem_get(pd->uobject->context, - (src == MLX4_IB_QP_SRC) ? ucmd.qp.buf_addr : - ucmd.wq.buf_addr, qp->buf_size, 0, 0); + qp->umem = + ib_umem_get(udata, + (src == MLX4_IB_QP_SRC) ? ucmd.qp.buf_addr : + ucmd.wq.buf_addr, + qp->buf_size, 0, 0); if (IS_ERR(qp->umem)) { err = PTR_ERR(qp->umem); goto err; @@ -1035,9 +1037,11 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, goto err_mtt; if (qp_has_rq(init_attr)) { - err = mlx4_ib_db_map_user(to_mucontext(pd->uobject->context), + err = mlx4_ib_db_map_user( + to_mucontext(pd->uobject->context), udata, (src == MLX4_IB_QP_SRC) ? ucmd.qp.db_addr : - ucmd.wq.db_addr, &qp->db); + ucmd.wq.db_addr, + &qp->db); if (err) goto err_mtt; } diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c index 4456f1b8921d..498588eac051 100644 --- a/drivers/infiniband/hw/mlx4/srq.c +++ b/drivers/infiniband/hw/mlx4/srq.c @@ -113,8 +113,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd, goto err_srq; } - srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, - buf_size, 0, 0); + srq->umem = ib_umem_get(udata, ucmd.buf_addr, buf_size, 0, 0); if (IS_ERR(srq->umem)) { err = PTR_ERR(srq->umem); goto err_srq; @@ -130,7 +129,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd, goto err_mtt; err = mlx4_ib_db_map_user(to_mucontext(pd->uobject->context), - ucmd.db_addr, &srq->db); + udata, ucmd.db_addr, &srq->db); if (err) goto err_mtt; } else { diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 90f1b0bae5b5..c283c32f30fe 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -707,15 +707,15 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata, *cqe_size = ucmd.cqe_size; - cq->buf.umem = ib_umem_get(context, ucmd.buf_addr, - entries * ucmd.cqe_size, - IB_ACCESS_LOCAL_WRITE, 1); + cq->buf.umem = + ib_umem_get(udata, ucmd.buf_addr, entries * ucmd.cqe_size, + IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(cq->buf.umem)) { err = PTR_ERR(cq->buf.umem); return err; } - err = mlx5_ib_db_map_user(to_mucontext(context), ucmd.db_addr, + err = mlx5_ib_db_map_user(to_mucontext(context), udata, ucmd.db_addr, &cq->db); if (err) goto err_umem; @@ -1111,7 +1111,6 @@ static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, struct ib_umem *umem; int err; int npages; - struct ib_ucontext *context = cq->buf.umem->context; err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)); if (err) @@ -1124,7 +1123,7 @@ static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (ucmd.cqe_size && SIZE_MAX / ucmd.cqe_size <= entries - 1) return -EINVAL; - umem = ib_umem_get(context, ucmd.buf_addr, + umem = ib_umem_get(udata, ucmd.buf_addr, (size_t)ucmd.cqe_size * entries, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(umem)) { diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 5a588f3cfb1b..8bb711da7ee1 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1195,7 +1195,7 @@ static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext, if (err) return err; - obj->umem = ib_umem_get(ucontext, addr, size, access, 0); + obj->umem = ib_umem_get(&attrs->driver_udata, addr, size, access, 0); if (IS_ERR(obj->umem)) return PTR_ERR(obj->umem); diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index a0e4e6ddb71a..8f4e5f22b84c 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -43,7 +43,8 @@ struct mlx5_ib_user_db_page { int refcnt; }; -int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt, +int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, + struct ib_udata *udata, unsigned long virt, struct mlx5_db *db) { struct mlx5_ib_user_db_page *page; @@ -63,8 +64,7 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt, page->user_virt = (virt & PAGE_MASK); page->refcnt = 0; - page->umem = ib_umem_get(&context->ibucontext, virt & PAGE_MASK, - PAGE_SIZE, 0, 0); + page->umem = ib_umem_get(udata, virt & PAGE_MASK, PAGE_SIZE, 0, 0); if (IS_ERR(page->umem)) { err = PTR_ERR(page->umem); kfree(page); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 81efa5def8ad..b0a37ca2a714 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1037,7 +1037,8 @@ to_mflow_act(struct ib_flow_action *ibact) return container_of(ibact, struct mlx5_ib_flow_action, ib_action); } -int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt, +int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, + struct ib_udata *udata, unsigned long virt, struct mlx5_db *db); void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db); void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq); @@ -1103,6 +1104,7 @@ int mlx5_ib_dealloc_mw(struct ib_mw *mw); int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, int page_shift, int flags); struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, + struct ib_udata *udata, int access_flags); void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *mr); int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 494a90f4348c..6d763d6a189f 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -843,18 +843,17 @@ static int mr_cache_max_order(struct mlx5_ib_dev *dev) return MLX5_MAX_UMR_SHIFT; } -static int mr_umem_get(struct ib_pd *pd, u64 start, u64 length, - int access_flags, struct ib_umem **umem, - int *npages, int *page_shift, int *ncont, - int *order) +static int mr_umem_get(struct mlx5_ib_dev *dev, struct ib_udata *udata, + u64 start, u64 length, int access_flags, + struct ib_umem **umem, int *npages, int *page_shift, + int *ncont, int *order) { - struct mlx5_ib_dev *dev = to_mdev(pd->device); struct ib_umem *u; int err; *umem = NULL; - u = ib_umem_get(pd->uobject->context, start, length, access_flags, 0); + u = ib_umem_get(udata, start, length, access_flags, 0); err = PTR_ERR_OR_ZERO(u); if (err) { mlx5_ib_dbg(dev, "umem get failed (%d)\n", err); @@ -1333,14 +1332,14 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, !(dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT)) return ERR_PTR(-EINVAL); - mr = mlx5_ib_alloc_implicit_mr(to_mpd(pd), access_flags); + mr = mlx5_ib_alloc_implicit_mr(to_mpd(pd), udata, access_flags); if (IS_ERR(mr)) return ERR_CAST(mr); return &mr->ibmr; } - err = mr_umem_get(pd, start, length, access_flags, &umem, &npages, - &page_shift, &ncont, &order); + err = mr_umem_get(dev, udata, start, length, access_flags, &umem, + &npages, &page_shift, &ncont, &order); if (err < 0) return ERR_PTR(err); @@ -1488,8 +1487,9 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, flags |= IB_MR_REREG_TRANS; ib_umem_release(mr->umem); mr->umem = NULL; - err = mr_umem_get(pd, addr, len, access_flags, &mr->umem, - &npages, &page_shift, &ncont, &order); + err = mr_umem_get(dev, udata, addr, len, access_flags, + &mr->umem, &npages, &page_shift, &ncont, + &order); if (err) goto err; } diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 37d6653f9636..8d46b1dc5658 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -492,13 +492,13 @@ next_mr: } struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, + struct ib_udata *udata, int access_flags) { - struct ib_ucontext *ctx = pd->ibpd.uobject->context; struct mlx5_ib_mr *imr; struct ib_umem *umem; - umem = ib_umem_get(ctx, 0, 0, IB_ACCESS_ON_DEMAND, 0); + umem = ib_umem_get(udata, 0, 0, IB_ACCESS_ON_DEMAND, 0); if (IS_ERR(umem)) return ERR_CAST(umem); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index dd2ae640bc84..529e76f67cb6 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -645,16 +645,14 @@ int bfregn_to_uar_index(struct mlx5_ib_dev *dev, return bfregi->sys_pages[index_of_sys_page] + offset; } -static int mlx5_ib_umem_get(struct mlx5_ib_dev *dev, - struct ib_pd *pd, +static int mlx5_ib_umem_get(struct mlx5_ib_dev *dev, struct ib_udata *udata, unsigned long addr, size_t size, - struct ib_umem **umem, - int *npages, int *page_shift, int *ncont, - u32 *offset) + struct ib_umem **umem, int *npages, int *page_shift, + int *ncont, u32 *offset) { int err; - *umem = ib_umem_get(pd->uobject->context, addr, size, 0, 0); + *umem = ib_umem_get(udata, addr, size, 0, 0); if (IS_ERR(*umem)) { mlx5_ib_dbg(dev, "umem_get failed\n"); return PTR_ERR(*umem); @@ -695,10 +693,9 @@ static void destroy_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd, } static int create_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd, - struct mlx5_ib_rwq *rwq, + struct ib_udata *udata, struct mlx5_ib_rwq *rwq, struct mlx5_ib_create_wq *ucmd) { - struct mlx5_ib_ucontext *context; int page_shift = 0; int npages; u32 offset = 0; @@ -708,9 +705,7 @@ static int create_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd, if (!ucmd->buf_addr) return -EINVAL; - context = to_mucontext(pd->uobject->context); - rwq->umem = ib_umem_get(pd->uobject->context, ucmd->buf_addr, - rwq->buf_size, 0, 0); + rwq->umem = ib_umem_get(udata, ucmd->buf_addr, rwq->buf_size, 0, 0); if (IS_ERR(rwq->umem)) { mlx5_ib_dbg(dev, "umem_get failed\n"); err = PTR_ERR(rwq->umem); @@ -735,7 +730,8 @@ static int create_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd, (unsigned long long)ucmd->buf_addr, rwq->buf_size, npages, page_shift, ncont, offset); - err = mlx5_ib_db_map_user(context, ucmd->db_addr, &rwq->db); + err = mlx5_ib_db_map_user(to_mucontext(pd->uobject->context), udata, + ucmd->db_addr, &rwq->db); if (err) { mlx5_ib_dbg(dev, "map failed\n"); goto err_umem; @@ -819,10 +815,9 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, if (ucmd.buf_addr && ubuffer->buf_size) { ubuffer->buf_addr = ucmd.buf_addr; - err = mlx5_ib_umem_get(dev, pd, ubuffer->buf_addr, - ubuffer->buf_size, - &ubuffer->umem, &npages, &page_shift, - &ncont, &offset); + err = mlx5_ib_umem_get(dev, udata, ubuffer->buf_addr, + ubuffer->buf_size, &ubuffer->umem, + &npages, &page_shift, &ncont, &offset); if (err) goto err_bfreg; } else { @@ -856,7 +851,7 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, resp->bfreg_index = MLX5_IB_INVALID_BFREG; qp->bfregn = bfregn; - err = mlx5_ib_db_map_user(context, ucmd.db_addr, &qp->db); + err = mlx5_ib_db_map_user(context, udata, ucmd.db_addr, &qp->db); if (err) { mlx5_ib_dbg(dev, "map failed\n"); goto err_free; @@ -1119,6 +1114,7 @@ static void destroy_flow_rule_vport_sq(struct mlx5_ib_dev *dev, } static int create_raw_packet_qp_sq(struct mlx5_ib_dev *dev, + struct ib_udata *udata, struct mlx5_ib_sq *sq, void *qpin, struct ib_pd *pd) { @@ -1135,9 +1131,9 @@ static int create_raw_packet_qp_sq(struct mlx5_ib_dev *dev, int ncont = 0; u32 offset = 0; - err = mlx5_ib_umem_get(dev, pd, ubuffer->buf_addr, ubuffer->buf_size, - &sq->ubuffer.umem, &npages, &page_shift, - &ncont, &offset); + err = mlx5_ib_umem_get(dev, udata, ubuffer->buf_addr, ubuffer->buf_size, + &sq->ubuffer.umem, &npages, &page_shift, &ncont, + &offset); if (err) return err; @@ -1374,7 +1370,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, if (err) return err; - err = create_raw_packet_qp_sq(dev, sq, in, pd); + err = create_raw_packet_qp_sq(dev, udata, sq, in, pd); if (err) goto err_destroy_tis; @@ -5793,7 +5789,7 @@ static int prepare_user_rq(struct ib_pd *pd, return err; } - err = create_user_rq(dev, pd, rwq, &ucmd); + err = create_user_rq(dev, pd, udata, rwq, &ucmd); if (err) { mlx5_ib_dbg(dev, "err %d\n", err); return err; diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 4e8d18009f58..22bd774e0b4e 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -79,8 +79,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE); - srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, buf_size, - 0, 0); + srq->umem = ib_umem_get(udata, ucmd.buf_addr, buf_size, 0, 0); if (IS_ERR(srq->umem)) { mlx5_ib_dbg(dev, "failed umem get, size %d\n", buf_size); err = PTR_ERR(srq->umem); @@ -104,7 +103,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, mlx5_ib_populate_pas(dev, srq->umem, page_shift, in->pas, 0); - err = mlx5_ib_db_map_user(to_mucontext(pd->uobject->context), + err = mlx5_ib_db_map_user(to_mucontext(pd->uobject->context), udata, ucmd.db_addr, &srq->db); if (err) { mlx5_ib_dbg(dev, "map doorbell failed\n"); diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 82cb6b71ac7c..53fff6aed896 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -931,7 +931,7 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (!mr) return ERR_PTR(-ENOMEM); - mr->umem = ib_umem_get(pd->uobject->context, start, length, acc, + mr->umem = ib_umem_get(udata, start, length, acc, ucmd.mr_attrs & MTHCA_MR_DMASYNC); if (IS_ERR(mr->umem)) { diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index 4e7f08ee1907..feb4d259aab9 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -2134,7 +2134,7 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u8 stag_key; int first_page = 1; - region = ib_umem_get(pd->uobject->context, start, length, acc, 0); + region = ib_umem_get(udata, start, length, acc, 0); if (IS_ERR(region)) { return (struct ib_mr *)region; } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index c46bed0c5513..a8b40cb7679e 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -916,7 +916,7 @@ struct ib_mr *ocrdma_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len, mr = kzalloc(sizeof(*mr), GFP_KERNEL); if (!mr) return ERR_PTR(status); - mr->umem = ib_umem_get(ibpd->uobject->context, start, len, acc, 0); + mr->umem = ib_umem_get(udata, start, len, acc, 0); if (IS_ERR(mr->umem)) { status = -EFAULT; goto umem_err; diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index b342a70e2814..ba8cb6559122 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -736,11 +736,10 @@ static inline int qedr_align_cq_entries(int entries) return aligned_size / QEDR_CQE_SIZE; } -static inline int qedr_init_user_queue(struct ib_ucontext *ib_ctx, +static inline int qedr_init_user_queue(struct ib_udata *udata, struct qedr_dev *dev, - struct qedr_userq *q, - u64 buf_addr, size_t buf_len, - int access, int dmasync, + struct qedr_userq *q, u64 buf_addr, + size_t buf_len, int access, int dmasync, int alloc_and_init) { u32 fw_pages; @@ -748,7 +747,7 @@ static inline int qedr_init_user_queue(struct ib_ucontext *ib_ctx, q->buf_addr = buf_addr; q->buf_len = buf_len; - q->umem = ib_umem_get(ib_ctx, q->buf_addr, q->buf_len, access, dmasync); + q->umem = ib_umem_get(udata, q->buf_addr, q->buf_len, access, dmasync); if (IS_ERR(q->umem)) { DP_ERR(dev, "create user queue: failed ib_umem_get, got %ld\n", PTR_ERR(q->umem)); @@ -905,9 +904,9 @@ struct ib_cq *qedr_create_cq(struct ib_device *ibdev, cq->cq_type = QEDR_CQ_TYPE_USER; - rc = qedr_init_user_queue(ib_ctx, dev, &cq->q, ureq.addr, - ureq.len, IB_ACCESS_LOCAL_WRITE, - 1, 1); + rc = qedr_init_user_queue(udata, dev, &cq->q, ureq.addr, + ureq.len, IB_ACCESS_LOCAL_WRITE, 1, + 1); if (rc) goto err0; @@ -1344,7 +1343,7 @@ static void qedr_free_srq_kernel_params(struct qedr_srq *srq) hw_srq->phy_prod_pair_addr); } -static int qedr_init_srq_user_params(struct ib_ucontext *ib_ctx, +static int qedr_init_srq_user_params(struct ib_udata *udata, struct qedr_srq *srq, struct qedr_create_srq_ureq *ureq, int access, int dmasync) @@ -1352,14 +1351,14 @@ static int qedr_init_srq_user_params(struct ib_ucontext *ib_ctx, struct scatterlist *sg; int rc; - rc = qedr_init_user_queue(ib_ctx, srq->dev, &srq->usrq, ureq->srq_addr, + rc = qedr_init_user_queue(udata, srq->dev, &srq->usrq, ureq->srq_addr, ureq->srq_len, access, dmasync, 1); if (rc) return rc; - srq->prod_umem = ib_umem_get(ib_ctx, ureq->prod_pair_addr, - sizeof(struct rdma_srq_producers), - access, dmasync); + srq->prod_umem = + ib_umem_get(udata, ureq->prod_pair_addr, + sizeof(struct rdma_srq_producers), access, dmasync); if (IS_ERR(srq->prod_umem)) { qedr_free_pbl(srq->dev, &srq->usrq.pbl_info, srq->usrq.pbl_tbl); ib_umem_release(srq->usrq.umem); @@ -1468,7 +1467,7 @@ struct ib_srq *qedr_create_srq(struct ib_pd *ibpd, goto err0; } - rc = qedr_init_srq_user_params(ib_ctx, srq, &ureq, 0, 0); + rc = qedr_init_srq_user_params(udata, srq, &ureq, 0, 0); if (rc) goto err0; @@ -1714,14 +1713,14 @@ static int qedr_create_user_qp(struct qedr_dev *dev, } /* SQ - read access only (0), dma sync not required (0) */ - rc = qedr_init_user_queue(ib_ctx, dev, &qp->usq, ureq.sq_addr, + rc = qedr_init_user_queue(udata, dev, &qp->usq, ureq.sq_addr, ureq.sq_len, 0, 0, alloc_and_init); if (rc) return rc; if (!qp->srq) { /* RQ - read access only (0), dma sync not required (0) */ - rc = qedr_init_user_queue(ib_ctx, dev, &qp->urq, ureq.rq_addr, + rc = qedr_init_user_queue(udata, dev, &qp->urq, ureq.rq_addr, ureq.rq_len, 0, 0, alloc_and_init); if (rc) return rc; @@ -2719,7 +2718,7 @@ struct ib_mr *qedr_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len, mr->type = QEDR_MR_USER; - mr->umem = ib_umem_get(ibpd->uobject->context, start, len, acc, 0); + mr->umem = ib_umem_get(udata, start, len, acc, 0); if (IS_ERR(mr->umem)) { rc = -EFAULT; goto err0; diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c index 0f004c737620..104c7db4704f 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c @@ -141,7 +141,7 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev, goto err_cq; } - cq->umem = ib_umem_get(context, ucmd.buf_addr, ucmd.buf_size, + cq->umem = ib_umem_get(udata, ucmd.buf_addr, ucmd.buf_size, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(cq->umem)) { ret = PTR_ERR(cq->umem); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c index fa96fa4fb829..a85884e90e84 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c @@ -126,8 +126,7 @@ struct ib_mr *pvrdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, return ERR_PTR(-EINVAL); } - umem = ib_umem_get(pd->uobject->context, start, - length, access_flags, 0); + umem = ib_umem_get(udata, start, length, access_flags, 0); if (IS_ERR(umem)) { dev_warn(&dev->pdev->dev, "could not get umem for mem region\n"); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c index 3acf74cbe266..5fc444cef011 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c @@ -262,8 +262,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd, if (!is_srq) { /* set qp->sq.wqe_cnt, shift, buf_size.. */ - qp->rumem = ib_umem_get(pd->uobject->context, - ucmd.rbuf_addr, + qp->rumem = ib_umem_get(udata, ucmd.rbuf_addr, ucmd.rbuf_size, 0, 0); if (IS_ERR(qp->rumem)) { ret = PTR_ERR(qp->rumem); @@ -275,8 +274,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd, qp->srq = to_vsrq(init_attr->srq); } - qp->sumem = ib_umem_get(pd->uobject->context, - ucmd.sbuf_addr, + qp->sumem = ib_umem_get(udata, ucmd.sbuf_addr, ucmd.sbuf_size, 0, 0); if (IS_ERR(qp->sumem)) { if (!is_srq) diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c index 06ba7c7a2235..951d9d68107a 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c @@ -153,9 +153,7 @@ struct ib_srq *pvrdma_create_srq(struct ib_pd *pd, goto err_srq; } - srq->umem = ib_umem_get(pd->uobject->context, - ucmd.buf_addr, - ucmd.buf_size, 0, 0); + srq->umem = ib_umem_get(udata, ucmd.buf_addr, ucmd.buf_size, 0, 0); if (IS_ERR(srq->umem)) { ret = PTR_ERR(srq->umem); goto err_srq; diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c index 49c9541050d4..8b1c1e8dd7ef 100644 --- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -388,8 +388,7 @@ struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (length == 0) return ERR_PTR(-EINVAL); - umem = ib_umem_get(pd->uobject->context, start, length, - mr_access_flags, 0); + umem = ib_umem_get(udata, start, length, mr_access_flags, 0); if (IS_ERR(umem)) return (void *)umem; diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index 9d3916b93f23..2438093776a0 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -171,7 +171,7 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start, void *vaddr; int err; - umem = ib_umem_get(pd->ibpd.uobject->context, start, length, access, 0); + umem = ib_umem_get(udata, start, length, access, 0); if (IS_ERR(umem)) { pr_warn("err %d from rxe_umem_get\n", (int)PTR_ERR(umem)); diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 5d3755ec5afa..73af05db04c7 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -36,6 +36,7 @@ #include #include #include +#include struct ib_ucontext; struct ib_umem_odp; @@ -80,7 +81,7 @@ static inline size_t ib_umem_num_pages(struct ib_umem *umem) #ifdef CONFIG_INFINIBAND_USER_MEM -struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, +struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, size_t size, int access, int dmasync); void ib_umem_release(struct ib_umem *umem); int ib_umem_page_count(struct ib_umem *umem); @@ -91,9 +92,10 @@ int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset, #include -static inline struct ib_umem *ib_umem_get(struct ib_ucontext *context, +static inline struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, size_t size, - int access, int dmasync) { + int access, int dmasync) +{ return ERR_PTR(-EINVAL); } static inline void ib_umem_release(struct ib_umem *umem) { } diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 3ddd199ba602..aa1f126d3383 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -4200,6 +4200,7 @@ void rdma_roce_rescan_device(struct ib_device *ibdev); struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile); +struct ib_ucontext *rdma_get_ucontext(struct ib_udata *udata); int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs); -- cgit v1.2.3 From bec9ba7f37631e794cbfaa4c2274074d631217a9 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 16 Dec 2018 19:12:18 -0800 Subject: crypto: cipher - remove struct cipher_desc 'struct cipher_desc' is unused. Remove it. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 902ec171fc6d..c3c98a62e503 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -188,14 +188,6 @@ struct blkcipher_desc { u32 flags; }; -struct cipher_desc { - struct crypto_tfm *tfm; - void (*crfn)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); - unsigned int (*prfn)(const struct cipher_desc *desc, u8 *dst, - const u8 *src, unsigned int nbytes); - void *info; -}; - /** * DOC: Block Cipher Algorithm Definitions * -- cgit v1.2.3 From 0872da16dd632e5d1d3f80388f7ae6fbeb17ad53 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 3 Jan 2019 20:16:14 -0800 Subject: crypto: skcipher - add helper for simple block cipher modes The majority of skcipher templates (including both the existing ones and the ones remaining to be converted from the "blkcipher" API) just wrap a single block cipher algorithm. This includes cbc, cfb, ctr, ecb, kw, ofb, and pcbc. Add a helper function skcipher_alloc_instance_simple() that handles allocating an skcipher instance for this common case. Signed-off-by: Eric Biggers Reviewed-by: Stephan Mueller Signed-off-by: Herbert Xu --- crypto/skcipher.c | 131 +++++++++++++++++++++++++++++++++++++ include/crypto/internal/skcipher.h | 15 +++++ 2 files changed, 146 insertions(+) (limited to 'include') diff --git a/crypto/skcipher.c b/crypto/skcipher.c index 2a969296bc24..040ae6377b32 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -1058,5 +1058,136 @@ int skcipher_register_instance(struct crypto_template *tmpl, } EXPORT_SYMBOL_GPL(skcipher_register_instance); +static int skcipher_setkey_simple(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keylen) +{ + struct crypto_cipher *cipher = skcipher_cipher_simple(tfm); + int err; + + crypto_cipher_clear_flags(cipher, CRYPTO_TFM_REQ_MASK); + crypto_cipher_set_flags(cipher, crypto_skcipher_get_flags(tfm) & + CRYPTO_TFM_REQ_MASK); + err = crypto_cipher_setkey(cipher, key, keylen); + crypto_skcipher_set_flags(tfm, crypto_cipher_get_flags(cipher) & + CRYPTO_TFM_RES_MASK); + return err; +} + +static int skcipher_init_tfm_simple(struct crypto_skcipher *tfm) +{ + struct skcipher_instance *inst = skcipher_alg_instance(tfm); + struct crypto_spawn *spawn = skcipher_instance_ctx(inst); + struct skcipher_ctx_simple *ctx = crypto_skcipher_ctx(tfm); + struct crypto_cipher *cipher; + + cipher = crypto_spawn_cipher(spawn); + if (IS_ERR(cipher)) + return PTR_ERR(cipher); + + ctx->cipher = cipher; + return 0; +} + +static void skcipher_exit_tfm_simple(struct crypto_skcipher *tfm) +{ + struct skcipher_ctx_simple *ctx = crypto_skcipher_ctx(tfm); + + crypto_free_cipher(ctx->cipher); +} + +static void skcipher_free_instance_simple(struct skcipher_instance *inst) +{ + crypto_drop_spawn(skcipher_instance_ctx(inst)); + kfree(inst); +} + +/** + * skcipher_alloc_instance_simple - allocate instance of simple block cipher mode + * + * Allocate an skcipher_instance for a simple block cipher mode of operation, + * e.g. cbc or ecb. The instance context will have just a single crypto_spawn, + * that for the underlying cipher. The {min,max}_keysize, ivsize, blocksize, + * alignmask, and priority are set from the underlying cipher but can be + * overridden if needed. The tfm context defaults to skcipher_ctx_simple, and + * default ->setkey(), ->init(), and ->exit() methods are installed. + * + * @tmpl: the template being instantiated + * @tb: the template parameters + * @cipher_alg_ret: on success, a pointer to the underlying cipher algorithm is + * returned here. It must be dropped with crypto_mod_put(). + * + * Return: a pointer to the new instance, or an ERR_PTR(). The caller still + * needs to register the instance. + */ +struct skcipher_instance * +skcipher_alloc_instance_simple(struct crypto_template *tmpl, struct rtattr **tb, + struct crypto_alg **cipher_alg_ret) +{ + struct crypto_attr_type *algt; + struct crypto_alg *cipher_alg; + struct skcipher_instance *inst; + struct crypto_spawn *spawn; + u32 mask; + int err; + + algt = crypto_get_attr_type(tb); + if (IS_ERR(algt)) + return ERR_CAST(algt); + + if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask) + return ERR_PTR(-EINVAL); + + mask = CRYPTO_ALG_TYPE_MASK | + crypto_requires_off(algt->type, algt->mask, + CRYPTO_ALG_NEED_FALLBACK); + + cipher_alg = crypto_get_attr_alg(tb, CRYPTO_ALG_TYPE_CIPHER, mask); + if (IS_ERR(cipher_alg)) + return ERR_CAST(cipher_alg); + + inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); + if (!inst) { + err = -ENOMEM; + goto err_put_cipher_alg; + } + spawn = skcipher_instance_ctx(inst); + + err = crypto_inst_setname(skcipher_crypto_instance(inst), tmpl->name, + cipher_alg); + if (err) + goto err_free_inst; + + err = crypto_init_spawn(spawn, cipher_alg, + skcipher_crypto_instance(inst), + CRYPTO_ALG_TYPE_MASK); + if (err) + goto err_free_inst; + inst->free = skcipher_free_instance_simple; + + /* Default algorithm properties, can be overridden */ + inst->alg.base.cra_blocksize = cipher_alg->cra_blocksize; + inst->alg.base.cra_alignmask = cipher_alg->cra_alignmask; + inst->alg.base.cra_priority = cipher_alg->cra_priority; + inst->alg.min_keysize = cipher_alg->cra_cipher.cia_min_keysize; + inst->alg.max_keysize = cipher_alg->cra_cipher.cia_max_keysize; + inst->alg.ivsize = cipher_alg->cra_blocksize; + + /* Use skcipher_ctx_simple by default, can be overridden */ + inst->alg.base.cra_ctxsize = sizeof(struct skcipher_ctx_simple); + inst->alg.setkey = skcipher_setkey_simple; + inst->alg.init = skcipher_init_tfm_simple; + inst->alg.exit = skcipher_exit_tfm_simple; + + *cipher_alg_ret = cipher_alg; + return inst; + +err_free_inst: + kfree(inst); +err_put_cipher_alg: + crypto_mod_put(cipher_alg); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(skcipher_alloc_instance_simple); + MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Symmetric key cipher type"); diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index 453e867b4bd9..9de6032209cb 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -205,5 +205,20 @@ static inline unsigned int crypto_skcipher_alg_max_keysize( return alg->max_keysize; } +/* Helpers for simple block cipher modes of operation */ +struct skcipher_ctx_simple { + struct crypto_cipher *cipher; /* underlying block cipher */ +}; +static inline struct crypto_cipher * +skcipher_cipher_simple(struct crypto_skcipher *tfm) +{ + struct skcipher_ctx_simple *ctx = crypto_skcipher_ctx(tfm); + + return ctx->cipher; +} +struct skcipher_instance * +skcipher_alloc_instance_simple(struct crypto_template *tmpl, struct rtattr **tb, + struct crypto_alg **cipher_alg_ret); + #endif /* _CRYPTO_INTERNAL_SKCIPHER_H */ -- cgit v1.2.3 From 14aa1a839a33b4ade7479ffcad8a5fabe5cc4000 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 3 Jan 2019 20:16:25 -0800 Subject: crypto: algapi - remove crypto_alloc_instance() Now that all "blkcipher" templates have been converted to "skcipher", crypto_alloc_instance() is no longer used. And it's not useful any longer as it creates an old-style weakly typed instance rather than a new-style strongly typed instance. So remove it, and now that the name is freed up rename crypto_alloc_instance2() to crypto_alloc_instance(). Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- crypto/algapi.c | 33 ++------------------------------- include/crypto/algapi.h | 6 ++---- include/crypto/internal/hash.h | 6 +++--- 3 files changed, 7 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/crypto/algapi.c b/crypto/algapi.c index 8b65ada33e5d..f3d766312bd9 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -845,8 +845,8 @@ int crypto_inst_setname(struct crypto_instance *inst, const char *name, } EXPORT_SYMBOL_GPL(crypto_inst_setname); -void *crypto_alloc_instance2(const char *name, struct crypto_alg *alg, - unsigned int head) +void *crypto_alloc_instance(const char *name, struct crypto_alg *alg, + unsigned int head) { struct crypto_instance *inst; char *p; @@ -869,35 +869,6 @@ err_free_inst: kfree(p); return ERR_PTR(err); } -EXPORT_SYMBOL_GPL(crypto_alloc_instance2); - -struct crypto_instance *crypto_alloc_instance(const char *name, - struct crypto_alg *alg) -{ - struct crypto_instance *inst; - struct crypto_spawn *spawn; - int err; - - inst = crypto_alloc_instance2(name, alg, 0); - if (IS_ERR(inst)) - goto out; - - spawn = crypto_instance_ctx(inst); - err = crypto_init_spawn(spawn, alg, inst, - CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_ASYNC); - - if (err) - goto err_free_inst; - - return inst; - -err_free_inst: - kfree(inst); - inst = ERR_PTR(err); - -out: - return inst; -} EXPORT_SYMBOL_GPL(crypto_alloc_instance); void crypto_init_queue(struct crypto_queue *queue, unsigned int max_qlen) diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 4a5ad10e75f0..093869f175d6 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -185,10 +185,8 @@ static inline struct crypto_alg *crypto_attr_alg(struct rtattr *rta, int crypto_attr_u32(struct rtattr *rta, u32 *num); int crypto_inst_setname(struct crypto_instance *inst, const char *name, struct crypto_alg *alg); -void *crypto_alloc_instance2(const char *name, struct crypto_alg *alg, - unsigned int head); -struct crypto_instance *crypto_alloc_instance(const char *name, - struct crypto_alg *alg); +void *crypto_alloc_instance(const char *name, struct crypto_alg *alg, + unsigned int head); void crypto_init_queue(struct crypto_queue *queue, unsigned int max_qlen); int crypto_enqueue_request(struct crypto_queue *queue, diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index a0b0ad9d585e..e355fdb642a9 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -170,7 +170,7 @@ static inline unsigned int ahash_instance_headroom(void) static inline struct ahash_instance *ahash_alloc_instance( const char *name, struct crypto_alg *alg) { - return crypto_alloc_instance2(name, alg, ahash_instance_headroom()); + return crypto_alloc_instance(name, alg, ahash_instance_headroom()); } static inline void ahash_request_complete(struct ahash_request *req, int err) @@ -233,8 +233,8 @@ static inline void *shash_instance_ctx(struct shash_instance *inst) static inline struct shash_instance *shash_alloc_instance( const char *name, struct crypto_alg *alg) { - return crypto_alloc_instance2(name, alg, - sizeof(struct shash_alg) - sizeof(*alg)); + return crypto_alloc_instance(name, alg, + sizeof(struct shash_alg) - sizeof(*alg)); } static inline struct crypto_shash *crypto_spawn_shash( -- cgit v1.2.3 From 5b438f4ba315db4f8c1489d175656798d58c014f Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 11 Jan 2019 13:04:57 +0800 Subject: iommu/vt-d: Support page request in scalable mode VT-d Rev3.0 has made a few changes to the page request interface, 1. widened PRQ descriptor from 128 bits to 256 bits; 2. removed streaming response type; 3. introduced private data that requires page response even the request is not last request in group (LPIG). This is a supplement to commit 1c4f88b7f1f92 ("iommu/vt-d: Shared virtual address in scalable mode") and makes the svm code compliant with VT-d Rev3.0. Cc: Ashok Raj Cc: Liu Yi L Cc: Kevin Tian Signed-off-by: Jacob Pan Fixes: 1c4f88b7f1f92 ("iommu/vt-d: Shared virtual address in scalable mode") Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-svm.c | 77 ++++++++++++++++++++++++++------------------- include/linux/intel-iommu.h | 21 ++++++------- include/linux/intel-svm.h | 2 +- 3 files changed, 55 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index a2a2aa4439aa..79add5716552 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -470,20 +470,31 @@ EXPORT_SYMBOL_GPL(intel_svm_is_pasid_valid); /* Page request queue descriptor */ struct page_req_dsc { - u64 srr:1; - u64 bof:1; - u64 pasid_present:1; - u64 lpig:1; - u64 pasid:20; - u64 bus:8; - u64 private:23; - u64 prg_index:9; - u64 rd_req:1; - u64 wr_req:1; - u64 exe_req:1; - u64 priv_req:1; - u64 devfn:8; - u64 addr:52; + union { + struct { + u64 type:8; + u64 pasid_present:1; + u64 priv_data_present:1; + u64 rsvd:6; + u64 rid:16; + u64 pasid:20; + u64 exe_req:1; + u64 pm_req:1; + u64 rsvd2:10; + }; + u64 qw_0; + }; + union { + struct { + u64 rd_req:1; + u64 wr_req:1; + u64 lpig:1; + u64 prg_index:9; + u64 addr:52; + }; + u64 qw_1; + }; + u64 priv_data[2]; }; #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x10) @@ -596,7 +607,7 @@ static irqreturn_t prq_event_thread(int irq, void *d) /* Accounting for major/minor faults? */ rcu_read_lock(); list_for_each_entry_rcu(sdev, &svm->devs, list) { - if (sdev->sid == PCI_DEVID(req->bus, req->devfn)) + if (sdev->sid == req->rid) break; } /* Other devices can go away, but the drivers are not permitted @@ -609,33 +620,35 @@ static irqreturn_t prq_event_thread(int irq, void *d) if (sdev && sdev->ops && sdev->ops->fault_cb) { int rwxp = (req->rd_req << 3) | (req->wr_req << 2) | - (req->exe_req << 1) | (req->priv_req); - sdev->ops->fault_cb(sdev->dev, req->pasid, req->addr, req->private, rwxp, result); + (req->exe_req << 1) | (req->pm_req); + sdev->ops->fault_cb(sdev->dev, req->pasid, req->addr, + req->priv_data, rwxp, result); } /* We get here in the error case where the PASID lookup failed, and these can be NULL. Do not use them below this point! */ sdev = NULL; svm = NULL; no_pasid: - if (req->lpig) { - /* Page Group Response */ + if (req->lpig || req->priv_data_present) { + /* + * Per VT-d spec. v3.0 ch7.7, system software must + * respond with page group response if private data + * is present (PDP) or last page in group (LPIG) bit + * is set. This is an additional VT-d feature beyond + * PCI ATS spec. + */ resp.qw0 = QI_PGRP_PASID(req->pasid) | - QI_PGRP_DID((req->bus << 8) | req->devfn) | + QI_PGRP_DID(req->rid) | QI_PGRP_PASID_P(req->pasid_present) | + QI_PGRP_PDP(req->pasid_present) | + QI_PGRP_RESP_CODE(result) | QI_PGRP_RESP_TYPE; resp.qw1 = QI_PGRP_IDX(req->prg_index) | - QI_PGRP_PRIV(req->private) | - QI_PGRP_RESP_CODE(result); - } else if (req->srr) { - /* Page Stream Response */ - resp.qw0 = QI_PSTRM_IDX(req->prg_index) | - QI_PSTRM_PRIV(req->private) | - QI_PSTRM_BUS(req->bus) | - QI_PSTRM_PASID(req->pasid) | - QI_PSTRM_RESP_TYPE; - resp.qw1 = QI_PSTRM_ADDR(address) | - QI_PSTRM_DEVFN(req->devfn) | - QI_PSTRM_RESP_CODE(result); + QI_PGRP_LPIG(req->lpig); + + if (req->priv_data_present) + memcpy(&resp.qw2, req->priv_data, + sizeof(req->priv_data)); } resp.qw2 = 0; resp.qw3 = 0; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 0605f3bf6e79..fa364de9db18 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -374,20 +374,17 @@ enum { #define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) #define QI_DEV_EIOTLB_MAX_INVS 32 -#define QI_PGRP_IDX(idx) (((u64)(idx)) << 55) -#define QI_PGRP_PRIV(priv) (((u64)(priv)) << 32) -#define QI_PGRP_RESP_CODE(res) ((u64)(res)) -#define QI_PGRP_PASID(pasid) (((u64)(pasid)) << 32) -#define QI_PGRP_DID(did) (((u64)(did)) << 16) +/* Page group response descriptor QW0 */ #define QI_PGRP_PASID_P(p) (((u64)(p)) << 4) +#define QI_PGRP_PDP(p) (((u64)(p)) << 5) +#define QI_PGRP_RESP_CODE(res) (((u64)(res)) << 12) +#define QI_PGRP_DID(rid) (((u64)(rid)) << 16) +#define QI_PGRP_PASID(pasid) (((u64)(pasid)) << 32) + +/* Page group response descriptor QW1 */ +#define QI_PGRP_LPIG(x) (((u64)(x)) << 2) +#define QI_PGRP_IDX(idx) (((u64)(idx)) << 3) -#define QI_PSTRM_ADDR(addr) (((u64)(addr)) & VTD_PAGE_MASK) -#define QI_PSTRM_DEVFN(devfn) (((u64)(devfn)) << 4) -#define QI_PSTRM_RESP_CODE(res) ((u64)(res)) -#define QI_PSTRM_IDX(idx) (((u64)(idx)) << 55) -#define QI_PSTRM_PRIV(priv) (((u64)(priv)) << 32) -#define QI_PSTRM_BUS(bus) (((u64)(bus)) << 24) -#define QI_PSTRM_PASID(pasid) (((u64)(pasid)) << 4) #define QI_RESP_SUCCESS 0x0 #define QI_RESP_INVALID 0x1 diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 99bc5b3ae26e..e3f76315ca4d 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -20,7 +20,7 @@ struct device; struct svm_dev_ops { void (*fault_cb)(struct device *dev, int pasid, u64 address, - u32 private, int rwxp, int response); + void *private, int rwxp, int response); }; /* Values for rxwp in fault_cb callback */ -- cgit v1.2.3 From 19514910d021c93c7823ec32067e6b7dea224f0f Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 9 Jan 2019 13:43:19 +0100 Subject: livepatch: Change unsigned long old_addr -> void *old_func in struct klp_func The address of the to be patched function and new function is stored in struct klp_func as: void *new_func; unsigned long old_addr; The different naming scheme and type are derived from the way the addresses are set. @old_addr is assigned at runtime using kallsyms-based search. @new_func is statically initialized, for example: static struct klp_func funcs[] = { { .old_name = "cmdline_proc_show", .new_func = livepatch_cmdline_proc_show, }, { } }; This patch changes unsigned long old_addr -> void *old_func. It removes some confusion when these address are later used in the code. It is motivated by a followup patch that adds special NOP struct klp_func where we want to assign func->new_func = func->old_addr respectively func->new_func = func->old_func. This patch does not modify the existing behavior. Suggested-by: Josh Poimboeuf Signed-off-by: Petr Mladek Acked-by: Miroslav Benes Acked-by: Joe Lawrence Acked-by: Alice Ferrazzi Acked-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 4 ++-- kernel/livepatch/core.c | 6 +++--- kernel/livepatch/patch.c | 18 ++++++++++-------- kernel/livepatch/patch.h | 4 ++-- kernel/livepatch/transition.c | 4 ++-- 5 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index aec44b1d9582..634e13876380 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -40,7 +40,7 @@ * @new_func: pointer to the patched function code * @old_sympos: a hint indicating which symbol position the old function * can be found (optional) - * @old_addr: the address of the function being patched + * @old_func: pointer to the function being patched * @kobj: kobject for sysfs resources * @stack_node: list node for klp_ops func_stack list * @old_size: size of the old function @@ -77,7 +77,7 @@ struct klp_func { unsigned long old_sympos; /* internal */ - unsigned long old_addr; + void *old_func; struct kobject kobj; struct list_head stack_node; unsigned long old_size, new_size; diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 5b77a7314e01..cb59c7fb94cb 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -648,7 +648,7 @@ static void klp_free_object_loaded(struct klp_object *obj) obj->mod = NULL; klp_for_each_func(obj, func) - func->old_addr = 0; + func->old_func = NULL; } /* @@ -721,11 +721,11 @@ static int klp_init_object_loaded(struct klp_patch *patch, klp_for_each_func(obj, func) { ret = klp_find_object_symbol(obj->name, func->old_name, func->old_sympos, - &func->old_addr); + (unsigned long *)&func->old_func); if (ret) return ret; - ret = kallsyms_lookup_size_offset(func->old_addr, + ret = kallsyms_lookup_size_offset((unsigned long)func->old_func, &func->old_size, NULL); if (!ret) { pr_err("kallsyms size lookup failed for '%s'\n", diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c index 7702cb4064fc..825022d70912 100644 --- a/kernel/livepatch/patch.c +++ b/kernel/livepatch/patch.c @@ -34,7 +34,7 @@ static LIST_HEAD(klp_ops); -struct klp_ops *klp_find_ops(unsigned long old_addr) +struct klp_ops *klp_find_ops(void *old_func) { struct klp_ops *ops; struct klp_func *func; @@ -42,7 +42,7 @@ struct klp_ops *klp_find_ops(unsigned long old_addr) list_for_each_entry(ops, &klp_ops, node) { func = list_first_entry(&ops->func_stack, struct klp_func, stack_node); - if (func->old_addr == old_addr) + if (func->old_func == old_func) return ops; } @@ -142,17 +142,18 @@ static void klp_unpatch_func(struct klp_func *func) if (WARN_ON(!func->patched)) return; - if (WARN_ON(!func->old_addr)) + if (WARN_ON(!func->old_func)) return; - ops = klp_find_ops(func->old_addr); + ops = klp_find_ops(func->old_func); if (WARN_ON(!ops)) return; if (list_is_singular(&ops->func_stack)) { unsigned long ftrace_loc; - ftrace_loc = klp_get_ftrace_location(func->old_addr); + ftrace_loc = + klp_get_ftrace_location((unsigned long)func->old_func); if (WARN_ON(!ftrace_loc)) return; @@ -174,17 +175,18 @@ static int klp_patch_func(struct klp_func *func) struct klp_ops *ops; int ret; - if (WARN_ON(!func->old_addr)) + if (WARN_ON(!func->old_func)) return -EINVAL; if (WARN_ON(func->patched)) return -EINVAL; - ops = klp_find_ops(func->old_addr); + ops = klp_find_ops(func->old_func); if (!ops) { unsigned long ftrace_loc; - ftrace_loc = klp_get_ftrace_location(func->old_addr); + ftrace_loc = + klp_get_ftrace_location((unsigned long)func->old_func); if (!ftrace_loc) { pr_err("failed to find location for function '%s'\n", func->old_name); diff --git a/kernel/livepatch/patch.h b/kernel/livepatch/patch.h index e72d8250d04b..a9b16e513656 100644 --- a/kernel/livepatch/patch.h +++ b/kernel/livepatch/patch.h @@ -10,7 +10,7 @@ * struct klp_ops - structure for tracking registered ftrace ops structs * * A single ftrace_ops is shared between all enabled replacement functions - * (klp_func structs) which have the same old_addr. This allows the switch + * (klp_func structs) which have the same old_func. This allows the switch * between function versions to happen instantaneously by updating the klp_ops * struct's func_stack list. The winner is the klp_func at the top of the * func_stack (front of the list). @@ -25,7 +25,7 @@ struct klp_ops { struct ftrace_ops fops; }; -struct klp_ops *klp_find_ops(unsigned long old_addr); +struct klp_ops *klp_find_ops(void *old_func); int klp_patch_object(struct klp_object *obj); void klp_unpatch_object(struct klp_object *obj); diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index 304d5eb8a98c..f27a378ad5e1 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -224,11 +224,11 @@ static int klp_check_stack_func(struct klp_func *func, * Check for the to-be-patched function * (the previous func). */ - ops = klp_find_ops(func->old_addr); + ops = klp_find_ops(func->old_func); if (list_is_singular(&ops->func_stack)) { /* original function */ - func_addr = func->old_addr; + func_addr = (unsigned long)func->old_func; func_size = func->old_size; } else { /* previously patched function */ -- cgit v1.2.3 From 0430f78bf38f9972f0cf0522709cc63d49fa164c Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 9 Jan 2019 13:43:21 +0100 Subject: livepatch: Consolidate klp_free functions The code for freeing livepatch structures is a bit scattered and tricky: + direct calls to klp_free_*_limited() and kobject_put() are used to release partially initialized objects + klp_free_patch() removes the patch from the public list and releases all objects except for patch->kobj + object_put(&patch->kobj) and the related wait_for_completion() are called directly outside klp_mutex; this code is duplicated; Now, we are going to remove the registration stage to simplify the API and the code. This would require handling more situations in klp_enable_patch() error paths. More importantly, we are going to add a feature called atomic replace. It will need to dynamically create func and object structures. We will want to reuse the existing init() and free() functions. This would create even more error path scenarios. This patch implements more straightforward free functions: + checks kobj_added flag instead of @limit[*] + initializes patch->list early so that the check for empty list always works + The action(s) that has to be done outside klp_mutex are done in separate klp_free_patch_finish() function. It waits only when patch->kobj was really released via the _start() part. The patch does not change the existing behavior. [*] We need our own flag to track that the kobject was successfully added to the hierarchy. Note that kobj.state_initialized only indicates that kobject has been initialized, not whether is has been added (and needs to be removed on cleanup). Signed-off-by: Petr Mladek Cc: Josh Poimboeuf Cc: Miroslav Benes Cc: Jessica Yu Cc: Jiri Kosina Cc: Jason Baron Acked-by: Miroslav Benes Acked-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 6 ++ kernel/livepatch/core.c | 137 +++++++++++++++++++++++++++++++--------------- 2 files changed, 98 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 634e13876380..6978785bc059 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -45,6 +45,7 @@ * @stack_node: list node for klp_ops func_stack list * @old_size: size of the old function * @new_size: size of the new function + * @kobj_added: @kobj has been added and needs freeing * @patched: the func has been added to the klp_ops list * @transition: the func is currently being applied or reverted * @@ -81,6 +82,7 @@ struct klp_func { struct kobject kobj; struct list_head stack_node; unsigned long old_size, new_size; + bool kobj_added; bool patched; bool transition; }; @@ -117,6 +119,7 @@ struct klp_callbacks { * @kobj: kobject for sysfs resources * @mod: kernel module associated with the patched object * (NULL for vmlinux) + * @kobj_added: @kobj has been added and needs freeing * @patched: the object's funcs have been added to the klp_ops list */ struct klp_object { @@ -128,6 +131,7 @@ struct klp_object { /* internal */ struct kobject kobj; struct module *mod; + bool kobj_added; bool patched; }; @@ -137,6 +141,7 @@ struct klp_object { * @objs: object entries for kernel objects to be patched * @list: list node for global list of registered patches * @kobj: kobject for sysfs resources + * @kobj_added: @kobj has been added and needs freeing * @enabled: the patch is enabled (but operation may be incomplete) * @finish: for waiting till it is safe to remove the patch module */ @@ -148,6 +153,7 @@ struct klp_patch { /* internal */ struct list_head list; struct kobject kobj; + bool kobj_added; bool enabled; struct completion finish; }; diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 20589da35194..6f0d9095f662 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -465,17 +465,15 @@ static struct kobj_type klp_ktype_func = { .sysfs_ops = &kobj_sysfs_ops, }; -/* - * Free all functions' kobjects in the array up to some limit. When limit is - * NULL, all kobjects are freed. - */ -static void klp_free_funcs_limited(struct klp_object *obj, - struct klp_func *limit) +static void klp_free_funcs(struct klp_object *obj) { struct klp_func *func; - for (func = obj->funcs; func->old_name && func != limit; func++) - kobject_put(&func->kobj); + klp_for_each_func(obj, func) { + /* Might be called from klp_init_patch() error path. */ + if (func->kobj_added) + kobject_put(&func->kobj); + } } /* Clean up when a patched object is unloaded */ @@ -489,30 +487,60 @@ static void klp_free_object_loaded(struct klp_object *obj) func->old_func = NULL; } -/* - * Free all objects' kobjects in the array up to some limit. When limit is - * NULL, all kobjects are freed. - */ -static void klp_free_objects_limited(struct klp_patch *patch, - struct klp_object *limit) +static void klp_free_objects(struct klp_patch *patch) { struct klp_object *obj; - for (obj = patch->objs; obj->funcs && obj != limit; obj++) { - klp_free_funcs_limited(obj, NULL); - kobject_put(&obj->kobj); + klp_for_each_object(patch, obj) { + klp_free_funcs(obj); + + /* Might be called from klp_init_patch() error path. */ + if (obj->kobj_added) + kobject_put(&obj->kobj); } } -static void klp_free_patch(struct klp_patch *patch) +/* + * This function implements the free operations that can be called safely + * under klp_mutex. + * + * The operation must be completed by calling klp_free_patch_finish() + * outside klp_mutex. + */ +static void klp_free_patch_start(struct klp_patch *patch) { - klp_free_objects_limited(patch, NULL); if (!list_empty(&patch->list)) list_del(&patch->list); + + klp_free_objects(patch); +} + +/* + * This function implements the free part that must be called outside + * klp_mutex. + * + * It must be called after klp_free_patch_start(). And it has to be + * the last function accessing the livepatch structures when the patch + * gets disabled. + */ +static void klp_free_patch_finish(struct klp_patch *patch) +{ + /* + * Avoid deadlock with enabled_store() sysfs callback by + * calling this outside klp_mutex. It is safe because + * this is called when the patch gets disabled and it + * cannot get enabled again. + */ + if (patch->kobj_added) { + kobject_put(&patch->kobj); + wait_for_completion(&patch->finish); + } } static int klp_init_func(struct klp_object *obj, struct klp_func *func) { + int ret; + if (!func->old_name || !func->new_func) return -EINVAL; @@ -528,9 +556,13 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func) * object. If the user selects 0 for old_sympos, then 1 will be used * since a unique symbol will be the first occurrence. */ - return kobject_init_and_add(&func->kobj, &klp_ktype_func, - &obj->kobj, "%s,%lu", func->old_name, - func->old_sympos ? func->old_sympos : 1); + ret = kobject_init_and_add(&func->kobj, &klp_ktype_func, + &obj->kobj, "%s,%lu", func->old_name, + func->old_sympos ? func->old_sympos : 1); + if (!ret) + func->kobj_added = true; + + return ret; } /* Arches may override this to finish any remaining arch-specific tasks */ @@ -589,9 +621,6 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj) int ret; const char *name; - if (!obj->funcs) - return -EINVAL; - if (klp_is_module(obj) && strlen(obj->name) >= MODULE_NAME_LEN) return -EINVAL; @@ -605,46 +634,66 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj) &patch->kobj, "%s", name); if (ret) return ret; + obj->kobj_added = true; klp_for_each_func(obj, func) { ret = klp_init_func(obj, func); if (ret) - goto free; + return ret; } - if (klp_is_object_loaded(obj)) { + if (klp_is_object_loaded(obj)) ret = klp_init_object_loaded(patch, obj); - if (ret) - goto free; - } - - return 0; -free: - klp_free_funcs_limited(obj, func); - kobject_put(&obj->kobj); return ret; } -static int klp_init_patch(struct klp_patch *patch) +static int klp_init_patch_early(struct klp_patch *patch) { struct klp_object *obj; - int ret; + struct klp_func *func; if (!patch->objs) return -EINVAL; - mutex_lock(&klp_mutex); - + INIT_LIST_HEAD(&patch->list); + patch->kobj_added = false; patch->enabled = false; init_completion(&patch->finish); + klp_for_each_object(patch, obj) { + if (!obj->funcs) + return -EINVAL; + + obj->kobj_added = false; + + klp_for_each_func(obj, func) + func->kobj_added = false; + } + + return 0; +} + +static int klp_init_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + int ret; + + mutex_lock(&klp_mutex); + + ret = klp_init_patch_early(patch); + if (ret) { + mutex_unlock(&klp_mutex); + return ret; + } + ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch, klp_root_kobj, "%s", patch->mod->name); if (ret) { mutex_unlock(&klp_mutex); return ret; } + patch->kobj_added = true; klp_for_each_object(patch, obj) { ret = klp_init_object(patch, obj); @@ -659,12 +708,11 @@ static int klp_init_patch(struct klp_patch *patch) return 0; free: - klp_free_objects_limited(patch, obj); + klp_free_patch_start(patch); mutex_unlock(&klp_mutex); - kobject_put(&patch->kobj); - wait_for_completion(&patch->finish); + klp_free_patch_finish(patch); return ret; } @@ -693,12 +741,11 @@ int klp_unregister_patch(struct klp_patch *patch) goto err; } - klp_free_patch(patch); + klp_free_patch_start(patch); mutex_unlock(&klp_mutex); - kobject_put(&patch->kobj); - wait_for_completion(&patch->finish); + klp_free_patch_finish(patch); return 0; err: -- cgit v1.2.3 From 68007289bf3cd937a5b8fc4987d2787167bd06ca Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 9 Jan 2019 13:43:22 +0100 Subject: livepatch: Don't block the removal of patches loaded after a forced transition module_put() is currently never called in klp_complete_transition() when klp_force is set. As a result, we might keep the reference count even when klp_enable_patch() fails and klp_cancel_transition() is called. This might give the impression that a module might get blocked in some strange init state. Fortunately, it is not the case. The reference count is ignored when mod->init fails and erroneous modules are always removed. Anyway, this might be confusing. Instead, this patch moves the global klp_forced flag into struct klp_patch. As a result, we block only modules that might still be in use after a forced transition. Newly loaded livepatches might be eventually completely removed later. It is not a big deal. But the code is at least consistent with the reality. Signed-off-by: Petr Mladek Acked-by: Joe Lawrence Acked-by: Miroslav Benes Acked-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 2 ++ kernel/livepatch/core.c | 4 +++- kernel/livepatch/core.h | 1 + kernel/livepatch/transition.c | 10 +++++----- 4 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 6978785bc059..6a9165d9b090 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -143,6 +143,7 @@ struct klp_object { * @kobj: kobject for sysfs resources * @kobj_added: @kobj has been added and needs freeing * @enabled: the patch is enabled (but operation may be incomplete) + * @forced: was involved in a forced transition * @finish: for waiting till it is safe to remove the patch module */ struct klp_patch { @@ -155,6 +156,7 @@ struct klp_patch { struct kobject kobj; bool kobj_added; bool enabled; + bool forced; struct completion finish; }; diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 6f0d9095f662..e77c5017ae0c 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -45,7 +45,8 @@ */ DEFINE_MUTEX(klp_mutex); -static LIST_HEAD(klp_patches); +/* Registered patches */ +LIST_HEAD(klp_patches); static struct kobject *klp_root_kobj; @@ -659,6 +660,7 @@ static int klp_init_patch_early(struct klp_patch *patch) INIT_LIST_HEAD(&patch->list); patch->kobj_added = false; patch->enabled = false; + patch->forced = false; init_completion(&patch->finish); klp_for_each_object(patch, obj) { diff --git a/kernel/livepatch/core.h b/kernel/livepatch/core.h index 48a83d4364cf..d0cb5390e247 100644 --- a/kernel/livepatch/core.h +++ b/kernel/livepatch/core.h @@ -5,6 +5,7 @@ #include extern struct mutex klp_mutex; +extern struct list_head klp_patches; static inline bool klp_is_object_loaded(struct klp_object *obj) { diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index f27a378ad5e1..a4c921364003 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -33,8 +33,6 @@ struct klp_patch *klp_transition_patch; static int klp_target_state = KLP_UNDEFINED; -static bool klp_forced = false; - /* * This work can be performed periodically to finish patching or unpatching any * "straggler" tasks which failed to transition in the first attempt. @@ -137,10 +135,10 @@ static void klp_complete_transition(void) klp_target_state == KLP_PATCHED ? "patching" : "unpatching"); /* - * klp_forced set implies unbounded increase of module's ref count if + * patch->forced set implies unbounded increase of module's ref count if * the module is disabled/enabled in a loop. */ - if (!klp_forced && klp_target_state == KLP_UNPATCHED) + if (!klp_transition_patch->forced && klp_target_state == KLP_UNPATCHED) module_put(klp_transition_patch->mod); klp_target_state = KLP_UNDEFINED; @@ -620,6 +618,7 @@ void klp_send_signals(void) */ void klp_force_transition(void) { + struct klp_patch *patch; struct task_struct *g, *task; unsigned int cpu; @@ -633,5 +632,6 @@ void klp_force_transition(void) for_each_possible_cpu(cpu) klp_update_patch_state(idle_task(cpu)); - klp_forced = true; + list_for_each_entry(patch, &klp_patches, list) + patch->forced = true; } -- cgit v1.2.3 From 958ef1e39d24d6cb8bf2a7406130a98c9564230f Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 9 Jan 2019 13:43:23 +0100 Subject: livepatch: Simplify API by removing registration step The possibility to re-enable a registered patch was useful for immediate patches where the livepatch module had to stay until the system reboot. The improved consistency model allows to achieve the same result by unloading and loading the livepatch module again. Also we are going to add a feature called atomic replace. It will allow to create a patch that would replace all already registered patches. The aim is to handle dependent patches more securely. It will obsolete the stack of patches that helped to handle the dependencies so far. Then it might be unclear when a cumulative patch re-enabling is safe. It would be complicated to support the many modes. Instead we could actually make the API and code easier to understand. Therefore, remove the two step public API. All the checks and init calls are moved from klp_register_patch() to klp_enabled_patch(). Also the patch is automatically freed, including the sysfs interface when the transition to the disabled state is completed. As a result, there is never a disabled patch on the top of the stack. Therefore we do not need to check the stack in __klp_enable_patch(). And we could simplify the check in __klp_disable_patch(). Also the API and logic is much easier. It is enough to call klp_enable_patch() in module_init() call. The patch can be disabled by writing '0' into /sys/kernel/livepatch//enabled. Then the module can be removed once the transition finishes and sysfs interface is freed. The only problem is how to free the structures and kobjects safely. The operation is triggered from the sysfs interface. We could not put the related kobject from there because it would cause lock inversion between klp_mutex and kernfs locks, see kn->count lockdep map. Therefore, offload the free task to a workqueue. It is perfectly fine: + The patch can no longer be used in the livepatch operations. + The module could not be removed until the free operation finishes and module_put() is called. + The operation is asynchronous already when the first klp_try_complete_transition() fails and another call is queued with a delay. Suggested-by: Josh Poimboeuf Signed-off-by: Petr Mladek Acked-by: Miroslav Benes Acked-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- Documentation/livepatch/livepatch.txt | 135 +++++-------- include/linux/livepatch.h | 7 +- kernel/livepatch/core.c | 280 +++++++++------------------ kernel/livepatch/core.h | 2 + kernel/livepatch/transition.c | 19 +- samples/livepatch/livepatch-callbacks-demo.c | 13 +- samples/livepatch/livepatch-sample.c | 13 +- samples/livepatch/livepatch-shadow-fix1.c | 14 +- samples/livepatch/livepatch-shadow-fix2.c | 14 +- 9 files changed, 168 insertions(+), 329 deletions(-) (limited to 'include') diff --git a/Documentation/livepatch/livepatch.txt b/Documentation/livepatch/livepatch.txt index 2d7ed09dbd59..8f56490a4bb6 100644 --- a/Documentation/livepatch/livepatch.txt +++ b/Documentation/livepatch/livepatch.txt @@ -12,12 +12,11 @@ Table of Contents: 4. Livepatch module 4.1. New functions 4.2. Metadata - 4.3. Livepatch module handling 5. Livepatch life-cycle - 5.1. Registration + 5.1. Loading 5.2. Enabling 5.3. Disabling - 5.4. Unregistration + 5.4. Removing 6. Sysfs 7. Limitations @@ -298,117 +297,89 @@ into three levels: see the "Consistency model" section. -4.3. Livepatch module handling ------------------------------- - -The usual behavior is that the new functions will get used when -the livepatch module is loaded. For this, the module init() function -has to register the patch (struct klp_patch) and enable it. See the -section "Livepatch life-cycle" below for more details about these -two operations. - -Module removal is only safe when there are no users of the underlying -functions. This is the reason why the force feature permanently disables -the removal. The forced tasks entered the functions but we cannot say -that they returned back. Therefore it cannot be decided when the -livepatch module can be safely removed. When the system is successfully -transitioned to a new patch state (patched/unpatched) without being -forced it is guaranteed that no task sleeps or runs in the old code. - - 5. Livepatch life-cycle ======================= -Livepatching defines four basic operations that define the life cycle of each -live patch: registration, enabling, disabling and unregistration. There are -several reasons why it is done this way. - -First, the patch is applied only when all patched symbols for already -loaded objects are found. The error handling is much easier if this -check is done before particular functions get redirected. +Livepatching can be described by four basic operations: +loading, enabling, disabling, removing. -Second, it might take some time until the entire system is migrated with -the hybrid consistency model being used. The patch revert might block -the livepatch module removal for too long. Therefore it is useful to -revert the patch using a separate operation that might be called -explicitly. But it does not make sense to remove all information until -the livepatch module is really removed. +5.1. Loading +------------ -5.1. Registration ------------------ +The only reasonable way is to enable the patch when the livepatch kernel +module is being loaded. For this, klp_enable_patch() has to be called +in the module_init() callback. There are two main reasons: -Each patch first has to be registered using klp_register_patch(). This makes -the patch known to the livepatch framework. Also it does some preliminary -computing and checks. +First, only the module has an easy access to the related struct klp_patch. -In particular, the patch is added into the list of known patches. The -addresses of the patched functions are found according to their names. -The special relocations, mentioned in the section "New functions", are -applied. The relevant entries are created under -/sys/kernel/livepatch/. The patch is rejected when any operation -fails. +Second, the error code might be used to refuse loading the module when +the patch cannot get enabled. 5.2. Enabling ------------- -Registered patches might be enabled either by calling klp_enable_patch() or -by writing '1' to /sys/kernel/livepatch//enabled. The system will -start using the new implementation of the patched functions at this stage. +The livepatch gets enabled by calling klp_enable_patch() from +the module_init() callback. The system will start using the new +implementation of the patched functions at this stage. -When a patch is enabled, livepatch enters into a transition state where -tasks are converging to the patched state. This is indicated by a value -of '1' in /sys/kernel/livepatch//transition. Once all tasks have -been patched, the 'transition' value changes to '0'. For more -information about this process, see the "Consistency model" section. +First, the addresses of the patched functions are found according to their +names. The special relocations, mentioned in the section "New functions", +are applied. The relevant entries are created under +/sys/kernel/livepatch/. The patch is rejected when any above +operation fails. -If an original function is patched for the first time, a function -specific struct klp_ops is created and an universal ftrace handler is -registered. +Second, livepatch enters into a transition state where tasks are converging +to the patched state. If an original function is patched for the first +time, a function specific struct klp_ops is created and an universal +ftrace handler is registered[*]. This stage is indicated by a value of '1' +in /sys/kernel/livepatch//transition. For more information about +this process, see the "Consistency model" section. -Functions might be patched multiple times. The ftrace handler is registered -only once for the given function. Further patches just add an entry to the -list (see field `func_stack`) of the struct klp_ops. The last added -entry is chosen by the ftrace handler and becomes the active function -replacement. +Finally, once all tasks have been patched, the 'transition' value changes +to '0'. -Note that the patches might be enabled in a different order than they were -registered. +[*] Note that functions might be patched multiple times. The ftrace handler + is registered only once for a given function. Further patches just add + an entry to the list (see field `func_stack`) of the struct klp_ops. + The right implementation is selected by the ftrace handler, see + the "Consistency model" section. 5.3. Disabling -------------- -Enabled patches might get disabled either by calling klp_disable_patch() or -by writing '0' to /sys/kernel/livepatch//enabled. At this stage -either the code from the previously enabled patch or even the original -code gets used. +Enabled patches might get disabled by writing '0' to +/sys/kernel/livepatch//enabled. -When a patch is disabled, livepatch enters into a transition state where -tasks are converging to the unpatched state. This is indicated by a -value of '1' in /sys/kernel/livepatch//transition. Once all tasks -have been unpatched, the 'transition' value changes to '0'. For more -information about this process, see the "Consistency model" section. +First, livepatch enters into a transition state where tasks are converging +to the unpatched state. The system starts using either the code from +the previously enabled patch or even the original one. This stage is +indicated by a value of '1' in /sys/kernel/livepatch//transition. +For more information about this process, see the "Consistency model" +section. -Here all the functions (struct klp_func) associated with the to-be-disabled +Second, once all tasks have been unpatched, the 'transition' value changes +to '0'. All the functions (struct klp_func) associated with the to-be-disabled patch are removed from the corresponding struct klp_ops. The ftrace handler is unregistered and the struct klp_ops is freed when the func_stack list becomes empty. -Patches must be disabled in exactly the reverse order in which they were -enabled. It makes the problem and the implementation much easier. +Third, the sysfs interface is destroyed. +Note that patches must be disabled in exactly the reverse order in which +they were enabled. It makes the problem and the implementation much easier. -5.4. Unregistration -------------------- -Disabled patches might be unregistered by calling klp_unregister_patch(). -This can be done only when the patch is disabled and the code is no longer -used. It must be called before the livepatch module gets unloaded. +5.4. Removing +------------- -At this stage, all the relevant sys-fs entries are removed and the patch -is removed from the list of known patches. +Module removal is only safe when there are no users of functions provided +by the module. This is the reason why the force feature permanently +disables the removal. Only when the system is successfully transitioned +to a new patch state (patched/unpatched) without being forced it is +guaranteed that no task sleeps or runs in the old code. 6. Sysfs diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 6a9165d9b090..8f9c19c69744 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -139,11 +139,12 @@ struct klp_object { * struct klp_patch - patch structure for live patching * @mod: reference to the live patch module * @objs: object entries for kernel objects to be patched - * @list: list node for global list of registered patches + * @list: list node for global list of actively used patches * @kobj: kobject for sysfs resources * @kobj_added: @kobj has been added and needs freeing * @enabled: the patch is enabled (but operation may be incomplete) * @forced: was involved in a forced transition + * @free_work: patch cleanup from workqueue-context * @finish: for waiting till it is safe to remove the patch module */ struct klp_patch { @@ -157,6 +158,7 @@ struct klp_patch { bool kobj_added; bool enabled; bool forced; + struct work_struct free_work; struct completion finish; }; @@ -168,10 +170,7 @@ struct klp_patch { func->old_name || func->new_func || func->old_sympos; \ func++) -int klp_register_patch(struct klp_patch *); -int klp_unregister_patch(struct klp_patch *); int klp_enable_patch(struct klp_patch *); -int klp_disable_patch(struct klp_patch *); void arch_klp_init_object_loaded(struct klp_patch *patch, struct klp_object *obj); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index e77c5017ae0c..bd41b03a72d5 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -45,7 +45,11 @@ */ DEFINE_MUTEX(klp_mutex); -/* Registered patches */ +/* + * Actively used patches: enabled or in transition. Note that replaced + * or disabled patches are not listed even though the related kernel + * module still can be loaded. + */ LIST_HEAD(klp_patches); static struct kobject *klp_root_kobj; @@ -83,17 +87,6 @@ static void klp_find_object_module(struct klp_object *obj) mutex_unlock(&module_mutex); } -static bool klp_is_patch_registered(struct klp_patch *patch) -{ - struct klp_patch *mypatch; - - list_for_each_entry(mypatch, &klp_patches, list) - if (mypatch == patch) - return true; - - return false; -} - static bool klp_initialized(void) { return !!klp_root_kobj; @@ -292,7 +285,6 @@ static int klp_write_object_relocations(struct module *pmod, * /sys/kernel/livepatch/// */ static int __klp_disable_patch(struct klp_patch *patch); -static int __klp_enable_patch(struct klp_patch *patch); static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) @@ -309,40 +301,32 @@ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, mutex_lock(&klp_mutex); - if (!klp_is_patch_registered(patch)) { - /* - * Module with the patch could either disappear meanwhile or is - * not properly initialized yet. - */ - ret = -EINVAL; - goto err; - } - if (patch->enabled == enabled) { /* already in requested state */ ret = -EINVAL; - goto err; + goto out; } - if (patch == klp_transition_patch) { + /* + * Allow to reverse a pending transition in both ways. It might be + * necessary to complete the transition without forcing and breaking + * the system integrity. + * + * Do not allow to re-enable a disabled patch. + */ + if (patch == klp_transition_patch) klp_reverse_transition(); - } else if (enabled) { - ret = __klp_enable_patch(patch); - if (ret) - goto err; - } else { + else if (!enabled) ret = __klp_disable_patch(patch); - if (ret) - goto err; - } + else + ret = -EINVAL; +out: mutex_unlock(&klp_mutex); + if (ret) + return ret; return count; - -err: - mutex_unlock(&klp_mutex); - return ret; } static ssize_t enabled_show(struct kobject *kobj, @@ -508,7 +492,7 @@ static void klp_free_objects(struct klp_patch *patch) * The operation must be completed by calling klp_free_patch_finish() * outside klp_mutex. */ -static void klp_free_patch_start(struct klp_patch *patch) +void klp_free_patch_start(struct klp_patch *patch) { if (!list_empty(&patch->list)) list_del(&patch->list); @@ -536,6 +520,23 @@ static void klp_free_patch_finish(struct klp_patch *patch) kobject_put(&patch->kobj); wait_for_completion(&patch->finish); } + + /* Put the module after the last access to struct klp_patch. */ + if (!patch->forced) + module_put(patch->mod); +} + +/* + * The livepatch might be freed from sysfs interface created by the patch. + * This work allows to wait until the interface is destroyed in a separate + * context. + */ +static void klp_free_patch_work_fn(struct work_struct *work) +{ + struct klp_patch *patch = + container_of(work, struct klp_patch, free_work); + + klp_free_patch_finish(patch); } static int klp_init_func(struct klp_object *obj, struct klp_func *func) @@ -661,6 +662,7 @@ static int klp_init_patch_early(struct klp_patch *patch) patch->kobj_added = false; patch->enabled = false; patch->forced = false; + INIT_WORK(&patch->free_work, klp_free_patch_work_fn); init_completion(&patch->finish); klp_for_each_object(patch, obj) { @@ -673,6 +675,9 @@ static int klp_init_patch_early(struct klp_patch *patch) func->kobj_added = false; } + if (!try_module_get(patch->mod)) + return -ENODEV; + return 0; } @@ -681,115 +686,22 @@ static int klp_init_patch(struct klp_patch *patch) struct klp_object *obj; int ret; - mutex_lock(&klp_mutex); - - ret = klp_init_patch_early(patch); - if (ret) { - mutex_unlock(&klp_mutex); - return ret; - } - ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch, klp_root_kobj, "%s", patch->mod->name); - if (ret) { - mutex_unlock(&klp_mutex); + if (ret) return ret; - } patch->kobj_added = true; klp_for_each_object(patch, obj) { ret = klp_init_object(patch, obj); if (ret) - goto free; + return ret; } list_add_tail(&patch->list, &klp_patches); - mutex_unlock(&klp_mutex); - - return 0; - -free: - klp_free_patch_start(patch); - - mutex_unlock(&klp_mutex); - - klp_free_patch_finish(patch); - - return ret; -} - -/** - * klp_unregister_patch() - unregisters a patch - * @patch: Disabled patch to be unregistered - * - * Frees the data structures and removes the sysfs interface. - * - * Return: 0 on success, otherwise error - */ -int klp_unregister_patch(struct klp_patch *patch) -{ - int ret; - - mutex_lock(&klp_mutex); - - if (!klp_is_patch_registered(patch)) { - ret = -EINVAL; - goto err; - } - - if (patch->enabled) { - ret = -EBUSY; - goto err; - } - - klp_free_patch_start(patch); - - mutex_unlock(&klp_mutex); - - klp_free_patch_finish(patch); - return 0; -err: - mutex_unlock(&klp_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(klp_unregister_patch); - -/** - * klp_register_patch() - registers a patch - * @patch: Patch to be registered - * - * Initializes the data structure associated with the patch and - * creates the sysfs interface. - * - * There is no need to take the reference on the patch module here. It is done - * later when the patch is enabled. - * - * Return: 0 on success, otherwise error - */ -int klp_register_patch(struct klp_patch *patch) -{ - if (!patch || !patch->mod) - return -EINVAL; - - if (!is_livepatch_module(patch->mod)) { - pr_err("module %s is not marked as a livepatch module\n", - patch->mod->name); - return -EINVAL; - } - - if (!klp_initialized()) - return -ENODEV; - - if (!klp_have_reliable_stack()) { - pr_err("This architecture doesn't have support for the livepatch consistency model.\n"); - return -ENOSYS; - } - - return klp_init_patch(patch); } -EXPORT_SYMBOL_GPL(klp_register_patch); static int __klp_disable_patch(struct klp_patch *patch) { @@ -802,8 +714,7 @@ static int __klp_disable_patch(struct klp_patch *patch) return -EBUSY; /* enforce stacking: only the last enabled patch can be disabled */ - if (!list_is_last(&patch->list, &klp_patches) && - list_next_entry(patch, list)->enabled) + if (!list_is_last(&patch->list, &klp_patches)) return -EBUSY; klp_init_transition(patch, KLP_UNPATCHED); @@ -822,44 +733,12 @@ static int __klp_disable_patch(struct klp_patch *patch) smp_wmb(); klp_start_transition(); - klp_try_complete_transition(); patch->enabled = false; + klp_try_complete_transition(); return 0; } -/** - * klp_disable_patch() - disables a registered patch - * @patch: The registered, enabled patch to be disabled - * - * Unregisters the patched functions from ftrace. - * - * Return: 0 on success, otherwise error - */ -int klp_disable_patch(struct klp_patch *patch) -{ - int ret; - - mutex_lock(&klp_mutex); - - if (!klp_is_patch_registered(patch)) { - ret = -EINVAL; - goto err; - } - - if (!patch->enabled) { - ret = -EINVAL; - goto err; - } - - ret = __klp_disable_patch(patch); - -err: - mutex_unlock(&klp_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(klp_disable_patch); - static int __klp_enable_patch(struct klp_patch *patch) { struct klp_object *obj; @@ -871,17 +750,8 @@ static int __klp_enable_patch(struct klp_patch *patch) if (WARN_ON(patch->enabled)) return -EINVAL; - /* enforce stacking: only the first disabled patch can be enabled */ - if (patch->list.prev != &klp_patches && - !list_prev_entry(patch, list)->enabled) - return -EBUSY; - - /* - * A reference is taken on the patch module to prevent it from being - * unloaded. - */ - if (!try_module_get(patch->mod)) - return -ENODEV; + if (!patch->kobj_added) + return -EINVAL; pr_notice("enabling patch '%s'\n", patch->mod->name); @@ -916,8 +786,8 @@ static int __klp_enable_patch(struct klp_patch *patch) } klp_start_transition(); - klp_try_complete_transition(); patch->enabled = true; + klp_try_complete_transition(); return 0; err: @@ -928,11 +798,15 @@ err: } /** - * klp_enable_patch() - enables a registered patch - * @patch: The registered, disabled patch to be enabled + * klp_enable_patch() - enable the livepatch + * @patch: patch to be enabled * - * Performs the needed symbol lookups and code relocations, - * then registers the patched functions with ftrace. + * Initializes the data structure associated with the patch, creates the sysfs + * interface, performs the needed symbol lookups and code relocations, + * registers the patched functions with ftrace. + * + * This function is supposed to be called from the livepatch module_init() + * callback. * * Return: 0 on success, otherwise error */ @@ -940,17 +814,51 @@ int klp_enable_patch(struct klp_patch *patch) { int ret; + if (!patch || !patch->mod) + return -EINVAL; + + if (!is_livepatch_module(patch->mod)) { + pr_err("module %s is not marked as a livepatch module\n", + patch->mod->name); + return -EINVAL; + } + + if (!klp_initialized()) + return -ENODEV; + + if (!klp_have_reliable_stack()) { + pr_err("This architecture doesn't have support for the livepatch consistency model.\n"); + return -ENOSYS; + } + + mutex_lock(&klp_mutex); - if (!klp_is_patch_registered(patch)) { - ret = -EINVAL; - goto err; + ret = klp_init_patch_early(patch); + if (ret) { + mutex_unlock(&klp_mutex); + return ret; } + ret = klp_init_patch(patch); + if (ret) + goto err; + ret = __klp_enable_patch(patch); + if (ret) + goto err; + + mutex_unlock(&klp_mutex); + + return 0; err: + klp_free_patch_start(patch); + mutex_unlock(&klp_mutex); + + klp_free_patch_finish(patch); + return ret; } EXPORT_SYMBOL_GPL(klp_enable_patch); diff --git a/kernel/livepatch/core.h b/kernel/livepatch/core.h index d0cb5390e247..d4eefc520c08 100644 --- a/kernel/livepatch/core.h +++ b/kernel/livepatch/core.h @@ -7,6 +7,8 @@ extern struct mutex klp_mutex; extern struct list_head klp_patches; +void klp_free_patch_start(struct klp_patch *patch); + static inline bool klp_is_object_loaded(struct klp_object *obj) { return !obj->name || obj->mod; diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index a4c921364003..c9917a24b3a4 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -134,13 +134,6 @@ static void klp_complete_transition(void) pr_notice("'%s': %s complete\n", klp_transition_patch->mod->name, klp_target_state == KLP_PATCHED ? "patching" : "unpatching"); - /* - * patch->forced set implies unbounded increase of module's ref count if - * the module is disabled/enabled in a loop. - */ - if (!klp_transition_patch->forced && klp_target_state == KLP_UNPATCHED) - module_put(klp_transition_patch->mod); - klp_target_state = KLP_UNDEFINED; klp_transition_patch = NULL; } @@ -357,6 +350,7 @@ void klp_try_complete_transition(void) { unsigned int cpu; struct task_struct *g, *task; + struct klp_patch *patch; bool complete = true; WARN_ON_ONCE(klp_target_state == KLP_UNDEFINED); @@ -405,7 +399,18 @@ void klp_try_complete_transition(void) } /* we're done, now cleanup the data structures */ + patch = klp_transition_patch; klp_complete_transition(); + + /* + * It would make more sense to free the patch in + * klp_complete_transition() but it is called also + * from klp_cancel_transition(). + */ + if (!patch->enabled) { + klp_free_patch_start(patch); + schedule_work(&patch->free_work); + } } /* diff --git a/samples/livepatch/livepatch-callbacks-demo.c b/samples/livepatch/livepatch-callbacks-demo.c index 72f9e6d1387b..62d97953ad02 100644 --- a/samples/livepatch/livepatch-callbacks-demo.c +++ b/samples/livepatch/livepatch-callbacks-demo.c @@ -195,22 +195,11 @@ static struct klp_patch patch = { static int livepatch_callbacks_demo_init(void) { - int ret; - - ret = klp_register_patch(&patch); - if (ret) - return ret; - ret = klp_enable_patch(&patch); - if (ret) { - WARN_ON(klp_unregister_patch(&patch)); - return ret; - } - return 0; + return klp_enable_patch(&patch); } static void livepatch_callbacks_demo_exit(void) { - WARN_ON(klp_unregister_patch(&patch)); } module_init(livepatch_callbacks_demo_init); diff --git a/samples/livepatch/livepatch-sample.c b/samples/livepatch/livepatch-sample.c index 2d554dd930e2..01c9cf003ca2 100644 --- a/samples/livepatch/livepatch-sample.c +++ b/samples/livepatch/livepatch-sample.c @@ -69,22 +69,11 @@ static struct klp_patch patch = { static int livepatch_init(void) { - int ret; - - ret = klp_register_patch(&patch); - if (ret) - return ret; - ret = klp_enable_patch(&patch); - if (ret) { - WARN_ON(klp_unregister_patch(&patch)); - return ret; - } - return 0; + return klp_enable_patch(&patch); } static void livepatch_exit(void) { - WARN_ON(klp_unregister_patch(&patch)); } module_init(livepatch_init); diff --git a/samples/livepatch/livepatch-shadow-fix1.c b/samples/livepatch/livepatch-shadow-fix1.c index e8f1bd6b29b1..a5a5cac21d4d 100644 --- a/samples/livepatch/livepatch-shadow-fix1.c +++ b/samples/livepatch/livepatch-shadow-fix1.c @@ -157,25 +157,13 @@ static struct klp_patch patch = { static int livepatch_shadow_fix1_init(void) { - int ret; - - ret = klp_register_patch(&patch); - if (ret) - return ret; - ret = klp_enable_patch(&patch); - if (ret) { - WARN_ON(klp_unregister_patch(&patch)); - return ret; - } - return 0; + return klp_enable_patch(&patch); } static void livepatch_shadow_fix1_exit(void) { /* Cleanup any existing SV_LEAK shadow variables */ klp_shadow_free_all(SV_LEAK, livepatch_fix1_dummy_leak_dtor); - - WARN_ON(klp_unregister_patch(&patch)); } module_init(livepatch_shadow_fix1_init); diff --git a/samples/livepatch/livepatch-shadow-fix2.c b/samples/livepatch/livepatch-shadow-fix2.c index b34c7bf83356..52de947b5526 100644 --- a/samples/livepatch/livepatch-shadow-fix2.c +++ b/samples/livepatch/livepatch-shadow-fix2.c @@ -129,25 +129,13 @@ static struct klp_patch patch = { static int livepatch_shadow_fix2_init(void) { - int ret; - - ret = klp_register_patch(&patch); - if (ret) - return ret; - ret = klp_enable_patch(&patch); - if (ret) { - WARN_ON(klp_unregister_patch(&patch)); - return ret; - } - return 0; + return klp_enable_patch(&patch); } static void livepatch_shadow_fix2_exit(void) { /* Cleanup any existing SV_COUNTER shadow variables */ klp_shadow_free_all(SV_COUNTER, NULL); - - WARN_ON(klp_unregister_patch(&patch)); } module_init(livepatch_shadow_fix2_init); -- cgit v1.2.3 From 20e55025958e18e671d92c7adea00c301ac93c43 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 9 Jan 2019 13:43:24 +0100 Subject: livepatch: Use lists to manage patches, objects and functions Currently klp_patch contains a pointer to a statically allocated array of struct klp_object and struct klp_objects contains a pointer to a statically allocated array of klp_func. In order to allow for the dynamic allocation of objects and functions, link klp_patch, klp_object, and klp_func together via linked lists. This allows us to more easily allocate new objects and functions, while having the iterator be a simple linked list walk. The static structures are added to the lists early. It allows to add the dynamically allocated objects before klp_init_object() and klp_init_func() calls. Therefore it reduces the further changes to the code. This patch does not change the existing behavior. Signed-off-by: Jason Baron [pmladek@suse.com: Initialize lists before init calls] Signed-off-by: Petr Mladek Acked-by: Miroslav Benes Acked-by: Joe Lawrence Cc: Josh Poimboeuf Cc: Jiri Kosina Acked-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 19 +++++++++++++++++-- kernel/livepatch/core.c | 9 +++++++-- 2 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 8f9c19c69744..e117e20ff771 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -24,6 +24,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_LIVEPATCH) @@ -42,6 +43,7 @@ * can be found (optional) * @old_func: pointer to the function being patched * @kobj: kobject for sysfs resources + * @node: list node for klp_object func_list * @stack_node: list node for klp_ops func_stack list * @old_size: size of the old function * @new_size: size of the new function @@ -80,6 +82,7 @@ struct klp_func { /* internal */ void *old_func; struct kobject kobj; + struct list_head node; struct list_head stack_node; unsigned long old_size, new_size; bool kobj_added; @@ -117,6 +120,8 @@ struct klp_callbacks { * @funcs: function entries for functions to be patched in the object * @callbacks: functions to be executed pre/post (un)patching * @kobj: kobject for sysfs resources + * @func_list: dynamic list of the function entries + * @node: list node for klp_patch obj_list * @mod: kernel module associated with the patched object * (NULL for vmlinux) * @kobj_added: @kobj has been added and needs freeing @@ -130,6 +135,8 @@ struct klp_object { /* internal */ struct kobject kobj; + struct list_head func_list; + struct list_head node; struct module *mod; bool kobj_added; bool patched; @@ -141,6 +148,7 @@ struct klp_object { * @objs: object entries for kernel objects to be patched * @list: list node for global list of actively used patches * @kobj: kobject for sysfs resources + * @obj_list: dynamic list of the object entries * @kobj_added: @kobj has been added and needs freeing * @enabled: the patch is enabled (but operation may be incomplete) * @forced: was involved in a forced transition @@ -155,6 +163,7 @@ struct klp_patch { /* internal */ struct list_head list; struct kobject kobj; + struct list_head obj_list; bool kobj_added; bool enabled; bool forced; @@ -162,14 +171,20 @@ struct klp_patch { struct completion finish; }; -#define klp_for_each_object(patch, obj) \ +#define klp_for_each_object_static(patch, obj) \ for (obj = patch->objs; obj->funcs || obj->name; obj++) -#define klp_for_each_func(obj, func) \ +#define klp_for_each_object(patch, obj) \ + list_for_each_entry(obj, &patch->obj_list, node) + +#define klp_for_each_func_static(obj, func) \ for (func = obj->funcs; \ func->old_name || func->new_func || func->old_sympos; \ func++) +#define klp_for_each_func(obj, func) \ + list_for_each_entry(func, &obj->func_list, node) + int klp_enable_patch(struct klp_patch *); void arch_klp_init_object_loaded(struct klp_patch *patch, diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index bd41b03a72d5..37d0d3645fa6 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -659,20 +659,25 @@ static int klp_init_patch_early(struct klp_patch *patch) return -EINVAL; INIT_LIST_HEAD(&patch->list); + INIT_LIST_HEAD(&patch->obj_list); patch->kobj_added = false; patch->enabled = false; patch->forced = false; INIT_WORK(&patch->free_work, klp_free_patch_work_fn); init_completion(&patch->finish); - klp_for_each_object(patch, obj) { + klp_for_each_object_static(patch, obj) { if (!obj->funcs) return -EINVAL; + INIT_LIST_HEAD(&obj->func_list); obj->kobj_added = false; + list_add_tail(&obj->node, &patch->obj_list); - klp_for_each_func(obj, func) + klp_for_each_func_static(obj, func) { func->kobj_added = false; + list_add_tail(&func->node, &obj->func_list); + } } if (!try_module_get(patch->mod)) -- cgit v1.2.3 From e1452b607c48c642caf57299f4da83aa002f8533 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 9 Jan 2019 13:43:25 +0100 Subject: livepatch: Add atomic replace Sometimes we would like to revert a particular fix. Currently, this is not easy because we want to keep all other fixes active and we could revert only the last applied patch. One solution would be to apply new patch that implemented all the reverted functions like in the original code. It would work as expected but there will be unnecessary redirections. In addition, it would also require knowing which functions need to be reverted at build time. Another problem is when there are many patches that touch the same functions. There might be dependencies between patches that are not enforced on the kernel side. Also it might be pretty hard to actually prepare the patch and ensure compatibility with the other patches. Atomic replace && cumulative patches: A better solution would be to create cumulative patch and say that it replaces all older ones. This patch adds a new "replace" flag to struct klp_patch. When it is enabled, a set of 'nop' klp_func will be dynamically created for all functions that are already being patched but that will no longer be modified by the new patch. They are used as a new target during the patch transition. The idea is to handle Nops' structures like the static ones. When the dynamic structures are allocated, we initialize all values that are normally statically defined. The only exception is "new_func" in struct klp_func. It has to point to the original function and the address is known only when the object (module) is loaded. Note that we really need to set it. The address is used, for example, in klp_check_stack_func(). Nevertheless we still need to distinguish the dynamically allocated structures in some operations. For this, we add "nop" flag into struct klp_func and "dynamic" flag into struct klp_object. They need special handling in the following situations: + The structures are added into the lists of objects and functions immediately. In fact, the lists were created for this purpose. + The address of the original function is known only when the patched object (module) is loaded. Therefore it is copied later in klp_init_object_loaded(). + The ftrace handler must not set PC to func->new_func. It would cause infinite loop because the address points back to the beginning of the original function. + The various free() functions must free the structure itself. Note that other ways to detect the dynamic structures are not considered safe. For example, even the statically defined struct klp_object might include empty funcs array. It might be there just to run some callbacks. Also note that the safe iterator must be used in the free() functions. Otherwise already freed structures might get accessed. Special callbacks handling: The callbacks from the replaced patches are _not_ called by intention. It would be pretty hard to define a reasonable semantic and implement it. It might even be counter-productive. The new patch is cumulative. It is supposed to include most of the changes from older patches. In most cases, it will not want to call pre_unpatch() post_unpatch() callbacks from the replaced patches. It would disable/break things for no good reasons. Also it should be easier to handle various scenarios in a single script in the new patch than think about interactions caused by running many scripts from older patches. Not to say that the old scripts even would not expect to be called in this situation. Removing replaced patches: One nice effect of the cumulative patches is that the code from the older patches is no longer used. Therefore the replaced patches can be removed. It has several advantages: + Nops' structs will no longer be necessary and might be removed. This would save memory, restore performance (no ftrace handler), allow clear view on what is really patched. + Disabling the patch will cause using the original code everywhere. Therefore the livepatch callbacks could handle only one scenario. Note that the complication is already complex enough when the patch gets enabled. It is currently solved by calling callbacks only from the new cumulative patch. + The state is clean in both the sysfs interface and lsmod. The modules with the replaced livepatches might even get removed from the system. Some people actually expected this behavior from the beginning. After all a cumulative patch is supposed to "completely" replace an existing one. It is like when a new version of an application replaces an older one. This patch does the first step. It removes the replaced patches from the list of patches. It is safe. The consistency model ensures that they are no longer used. By other words, each process works only with the structures from klp_transition_patch. The removal is done by a special function. It combines actions done by __disable_patch() and klp_complete_transition(). But it is a fast track without all the transaction-related stuff. Signed-off-by: Jason Baron [pmladek@suse.com: Split, reuse existing code, simplified] Signed-off-by: Petr Mladek Cc: Josh Poimboeuf Cc: Jessica Yu Cc: Jiri Kosina Cc: Miroslav Benes Acked-by: Miroslav Benes Acked-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- Documentation/livepatch/livepatch.txt | 31 ++++- include/linux/livepatch.h | 12 ++ kernel/livepatch/core.c | 232 ++++++++++++++++++++++++++++++++-- kernel/livepatch/core.h | 1 + kernel/livepatch/patch.c | 8 ++ kernel/livepatch/transition.c | 3 + 6 files changed, 273 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/Documentation/livepatch/livepatch.txt b/Documentation/livepatch/livepatch.txt index 8f56490a4bb6..2a70f43166f6 100644 --- a/Documentation/livepatch/livepatch.txt +++ b/Documentation/livepatch/livepatch.txt @@ -15,8 +15,9 @@ Table of Contents: 5. Livepatch life-cycle 5.1. Loading 5.2. Enabling - 5.3. Disabling - 5.4. Removing + 5.3. Replacing + 5.4. Disabling + 5.5. Removing 6. Sysfs 7. Limitations @@ -300,8 +301,12 @@ into three levels: 5. Livepatch life-cycle ======================= -Livepatching can be described by four basic operations: -loading, enabling, disabling, removing. +Livepatching can be described by five basic operations: +loading, enabling, replacing, disabling, removing. + +Where the replacing and the disabling operations are mutually +exclusive. They have the same result for the given patch but +not for the system. 5.1. Loading @@ -347,7 +352,21 @@ to '0'. the "Consistency model" section. -5.3. Disabling +5.3. Replacing +-------------- + +All enabled patches might get replaced by a cumulative patch that +has the .replace flag set. + +Once the new patch is enabled and the 'transition' finishes then +all the functions (struct klp_func) associated with the replaced +patches are removed from the corresponding struct klp_ops. Also +the ftrace handler is unregistered and the struct klp_ops is +freed when the related function is not modified by the new patch +and func_stack list becomes empty. + + +5.4. Disabling -------------- Enabled patches might get disabled by writing '0' to @@ -372,7 +391,7 @@ Note that patches must be disabled in exactly the reverse order in which they were enabled. It makes the problem and the implementation much easier. -5.4. Removing +5.5. Removing ------------- Module removal is only safe when there are no users of functions provided diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index e117e20ff771..53551f470722 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -48,6 +48,7 @@ * @old_size: size of the old function * @new_size: size of the new function * @kobj_added: @kobj has been added and needs freeing + * @nop: temporary patch to use the original code again; dyn. allocated * @patched: the func has been added to the klp_ops list * @transition: the func is currently being applied or reverted * @@ -86,6 +87,7 @@ struct klp_func { struct list_head stack_node; unsigned long old_size, new_size; bool kobj_added; + bool nop; bool patched; bool transition; }; @@ -125,6 +127,7 @@ struct klp_callbacks { * @mod: kernel module associated with the patched object * (NULL for vmlinux) * @kobj_added: @kobj has been added and needs freeing + * @dynamic: temporary object for nop functions; dynamically allocated * @patched: the object's funcs have been added to the klp_ops list */ struct klp_object { @@ -139,6 +142,7 @@ struct klp_object { struct list_head node; struct module *mod; bool kobj_added; + bool dynamic; bool patched; }; @@ -146,6 +150,7 @@ struct klp_object { * struct klp_patch - patch structure for live patching * @mod: reference to the live patch module * @objs: object entries for kernel objects to be patched + * @replace: replace all actively used patches * @list: list node for global list of actively used patches * @kobj: kobject for sysfs resources * @obj_list: dynamic list of the object entries @@ -159,6 +164,7 @@ struct klp_patch { /* external */ struct module *mod; struct klp_object *objs; + bool replace; /* internal */ struct list_head list; @@ -174,6 +180,9 @@ struct klp_patch { #define klp_for_each_object_static(patch, obj) \ for (obj = patch->objs; obj->funcs || obj->name; obj++) +#define klp_for_each_object_safe(patch, obj, tmp_obj) \ + list_for_each_entry_safe(obj, tmp_obj, &patch->obj_list, node) + #define klp_for_each_object(patch, obj) \ list_for_each_entry(obj, &patch->obj_list, node) @@ -182,6 +191,9 @@ struct klp_patch { func->old_name || func->new_func || func->old_sympos; \ func++) +#define klp_for_each_func_safe(obj, func, tmp_func) \ + list_for_each_entry_safe(func, tmp_func, &obj->func_list, node) + #define klp_for_each_func(obj, func) \ list_for_each_entry(func, &obj->func_list, node) diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 37d0d3645fa6..ecb7660f1d8b 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -92,6 +92,40 @@ static bool klp_initialized(void) return !!klp_root_kobj; } +static struct klp_func *klp_find_func(struct klp_object *obj, + struct klp_func *old_func) +{ + struct klp_func *func; + + klp_for_each_func(obj, func) { + if ((strcmp(old_func->old_name, func->old_name) == 0) && + (old_func->old_sympos == func->old_sympos)) { + return func; + } + } + + return NULL; +} + +static struct klp_object *klp_find_object(struct klp_patch *patch, + struct klp_object *old_obj) +{ + struct klp_object *obj; + + klp_for_each_object(patch, obj) { + if (klp_is_module(old_obj)) { + if (klp_is_module(obj) && + strcmp(old_obj->name, obj->name) == 0) { + return obj; + } + } else if (!klp_is_module(obj)) { + return obj; + } + } + + return NULL; +} + struct klp_find_arg { const char *objname; const char *name; @@ -418,6 +452,121 @@ static struct attribute *klp_patch_attrs[] = { NULL }; +static void klp_free_object_dynamic(struct klp_object *obj) +{ + kfree(obj->name); + kfree(obj); +} + +static struct klp_object *klp_alloc_object_dynamic(const char *name) +{ + struct klp_object *obj; + + obj = kzalloc(sizeof(*obj), GFP_KERNEL); + if (!obj) + return NULL; + + if (name) { + obj->name = kstrdup(name, GFP_KERNEL); + if (!obj->name) { + kfree(obj); + return NULL; + } + } + + INIT_LIST_HEAD(&obj->func_list); + obj->dynamic = true; + + return obj; +} + +static void klp_free_func_nop(struct klp_func *func) +{ + kfree(func->old_name); + kfree(func); +} + +static struct klp_func *klp_alloc_func_nop(struct klp_func *old_func, + struct klp_object *obj) +{ + struct klp_func *func; + + func = kzalloc(sizeof(*func), GFP_KERNEL); + if (!func) + return NULL; + + if (old_func->old_name) { + func->old_name = kstrdup(old_func->old_name, GFP_KERNEL); + if (!func->old_name) { + kfree(func); + return NULL; + } + } + + /* + * func->new_func is same as func->old_func. These addresses are + * set when the object is loaded, see klp_init_object_loaded(). + */ + func->old_sympos = old_func->old_sympos; + func->nop = true; + + return func; +} + +static int klp_add_object_nops(struct klp_patch *patch, + struct klp_object *old_obj) +{ + struct klp_object *obj; + struct klp_func *func, *old_func; + + obj = klp_find_object(patch, old_obj); + + if (!obj) { + obj = klp_alloc_object_dynamic(old_obj->name); + if (!obj) + return -ENOMEM; + + list_add_tail(&obj->node, &patch->obj_list); + } + + klp_for_each_func(old_obj, old_func) { + func = klp_find_func(obj, old_func); + if (func) + continue; + + func = klp_alloc_func_nop(old_func, obj); + if (!func) + return -ENOMEM; + + list_add_tail(&func->node, &obj->func_list); + } + + return 0; +} + +/* + * Add 'nop' functions which simply return to the caller to run + * the original function. The 'nop' functions are added to a + * patch to facilitate a 'replace' mode. + */ +static int klp_add_nops(struct klp_patch *patch) +{ + struct klp_patch *old_patch; + struct klp_object *old_obj; + + list_for_each_entry(old_patch, &klp_patches, list) { + klp_for_each_object(old_patch, old_obj) { + int err; + + err = klp_add_object_nops(patch, old_obj); + if (err) + return err; + } + } + + return 0; +} + static void klp_kobj_release_patch(struct kobject *kobj) { struct klp_patch *patch; @@ -434,6 +583,12 @@ static struct kobj_type klp_ktype_patch = { static void klp_kobj_release_object(struct kobject *kobj) { + struct klp_object *obj; + + obj = container_of(kobj, struct klp_object, kobj); + + if (obj->dynamic) + klp_free_object_dynamic(obj); } static struct kobj_type klp_ktype_object = { @@ -443,6 +598,12 @@ static struct kobj_type klp_ktype_object = { static void klp_kobj_release_func(struct kobject *kobj) { + struct klp_func *func; + + func = container_of(kobj, struct klp_func, kobj); + + if (func->nop) + klp_free_func_nop(func); } static struct kobj_type klp_ktype_func = { @@ -452,12 +613,15 @@ static struct kobj_type klp_ktype_func = { static void klp_free_funcs(struct klp_object *obj) { - struct klp_func *func; + struct klp_func *func, *tmp_func; - klp_for_each_func(obj, func) { + klp_for_each_func_safe(obj, func, tmp_func) { /* Might be called from klp_init_patch() error path. */ - if (func->kobj_added) + if (func->kobj_added) { kobject_put(&func->kobj); + } else if (func->nop) { + klp_free_func_nop(func); + } } } @@ -468,20 +632,27 @@ static void klp_free_object_loaded(struct klp_object *obj) obj->mod = NULL; - klp_for_each_func(obj, func) + klp_for_each_func(obj, func) { func->old_func = NULL; + + if (func->nop) + func->new_func = NULL; + } } static void klp_free_objects(struct klp_patch *patch) { - struct klp_object *obj; + struct klp_object *obj, *tmp_obj; - klp_for_each_object(patch, obj) { + klp_for_each_object_safe(patch, obj, tmp_obj) { klp_free_funcs(obj); /* Might be called from klp_init_patch() error path. */ - if (obj->kobj_added) + if (obj->kobj_added) { kobject_put(&obj->kobj); + } else if (obj->dynamic) { + klp_free_object_dynamic(obj); + } } } @@ -543,7 +714,14 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func) { int ret; - if (!func->old_name || !func->new_func) + if (!func->old_name) + return -EINVAL; + + /* + * NOPs get the address later. The patched module must be loaded, + * see klp_init_object_loaded(). + */ + if (!func->new_func && !func->nop) return -EINVAL; if (strlen(func->old_name) >= KSYM_NAME_LEN) @@ -605,6 +783,9 @@ static int klp_init_object_loaded(struct klp_patch *patch, return -ENOENT; } + if (func->nop) + func->new_func = func->old_func; + ret = kallsyms_lookup_size_offset((unsigned long)func->new_func, &func->new_size, NULL); if (!ret) { @@ -697,6 +878,12 @@ static int klp_init_patch(struct klp_patch *patch) return ret; patch->kobj_added = true; + if (patch->replace) { + ret = klp_add_nops(patch); + if (ret) + return ret; + } + klp_for_each_object(patch, obj) { ret = klp_init_object(patch, obj); if (ret) @@ -868,6 +1055,35 @@ err: } EXPORT_SYMBOL_GPL(klp_enable_patch); +/* + * This function removes replaced patches. + * + * We could be pretty aggressive here. It is called in the situation where + * these structures are no longer accessible. All functions are redirected + * by the klp_transition_patch. They use either a new code or they are in + * the original code because of the special nop function patches. + * + * The only exception is when the transition was forced. In this case, + * klp_ftrace_handler() might still see the replaced patch on the stack. + * Fortunately, it is carefully designed to work with removed functions + * thanks to RCU. We only have to keep the patches on the system. Also + * this is handled transparently by patch->module_put. + */ +void klp_discard_replaced_patches(struct klp_patch *new_patch) +{ + struct klp_patch *old_patch, *tmp_patch; + + list_for_each_entry_safe(old_patch, tmp_patch, &klp_patches, list) { + if (old_patch == new_patch) + return; + + old_patch->enabled = false; + klp_unpatch_objects(old_patch); + klp_free_patch_start(old_patch); + schedule_work(&old_patch->free_work); + } +} + /* * Remove parts of patches that touch a given kernel module. The list of * patches processed might be limited. When limit is NULL, all patches diff --git a/kernel/livepatch/core.h b/kernel/livepatch/core.h index d4eefc520c08..f6a853adcc00 100644 --- a/kernel/livepatch/core.h +++ b/kernel/livepatch/core.h @@ -8,6 +8,7 @@ extern struct mutex klp_mutex; extern struct list_head klp_patches; void klp_free_patch_start(struct klp_patch *patch); +void klp_discard_replaced_patches(struct klp_patch *new_patch); static inline bool klp_is_object_loaded(struct klp_object *obj) { diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c index 825022d70912..0ff466ab4b5a 100644 --- a/kernel/livepatch/patch.c +++ b/kernel/livepatch/patch.c @@ -118,7 +118,15 @@ static void notrace klp_ftrace_handler(unsigned long ip, } } + /* + * NOPs are used to replace existing patches with original code. + * Do nothing! Setting pc would cause an infinite loop. + */ + if (func->nop) + goto unlock; + klp_arch_set_pc(regs, (unsigned long)func->new_func); + unlock: preempt_enable_notrace(); } diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index c9917a24b3a4..f4c5908a9731 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -85,6 +85,9 @@ static void klp_complete_transition(void) klp_transition_patch->mod->name, klp_target_state == KLP_PATCHED ? "patching" : "unpatching"); + if (klp_transition_patch->replace && klp_target_state == KLP_PATCHED) + klp_discard_replaced_patches(klp_transition_patch); + if (klp_target_state == KLP_UNPATCHED) { /* * All tasks have transitioned to KLP_UNPATCHED so we can now -- cgit v1.2.3 From cf9ff75d15a9bbd625519997c2ca864d1fa80227 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Mon, 10 Dec 2018 16:50:18 +0000 Subject: soc: fsl: dpio: store a backpointer to the device backing the dpaa2_io Add a new field in the dpaa2_io structure to hold a backpointer to the actual DPIO device. Signed-off-by: Ioana Ciornei Signed-off-by: Li Yang --- drivers/soc/fsl/dpio/dpio-driver.c | 2 +- drivers/soc/fsl/dpio/dpio-service.c | 7 ++++++- include/soc/fsl/dpaa2-io.h | 3 ++- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/soc/fsl/dpio/dpio-driver.c b/drivers/soc/fsl/dpio/dpio-driver.c index 5286723d4a14..2d4af32a0dec 100644 --- a/drivers/soc/fsl/dpio/dpio-driver.c +++ b/drivers/soc/fsl/dpio/dpio-driver.c @@ -176,7 +176,7 @@ static int dpaa2_dpio_probe(struct fsl_mc_device *dpio_dev) if (err) goto err_register_dpio_irq; - priv->io = dpaa2_io_create(&desc); + priv->io = dpaa2_io_create(&desc, dev); if (!priv->io) { dev_err(dev, "dpaa2_io_create failed\n"); err = -ENOMEM; diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index c02bfb18a1f0..52d800aa4774 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -27,6 +27,7 @@ struct dpaa2_io { /* protect notifications list */ spinlock_t lock_notifications; struct list_head notifications; + struct device *dev; }; struct dpaa2_io_store { @@ -98,13 +99,15 @@ EXPORT_SYMBOL_GPL(dpaa2_io_service_select); /** * dpaa2_io_create() - create a dpaa2_io object. * @desc: the dpaa2_io descriptor + * @dev: the actual DPIO device * * Activates a "struct dpaa2_io" corresponding to the given config of an actual * DPIO object. * * Return a valid dpaa2_io object for success, or NULL for failure. */ -struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc) +struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, + struct device *dev) { struct dpaa2_io *obj = kmalloc(sizeof(*obj), GFP_KERNEL); @@ -146,6 +149,8 @@ struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc) dpio_by_cpu[desc->cpu] = obj; spin_unlock(&dpio_list_lock); + obj->dev = dev; + return obj; } diff --git a/include/soc/fsl/dpaa2-io.h b/include/soc/fsl/dpaa2-io.h index 243119c53cdf..e252066d1f43 100644 --- a/include/soc/fsl/dpaa2-io.h +++ b/include/soc/fsl/dpaa2-io.h @@ -57,7 +57,8 @@ struct dpaa2_io_desc { u32 qman_version; }; -struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc); +struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, + struct device *dev); void dpaa2_io_down(struct dpaa2_io *d); -- cgit v1.2.3 From 47441f7f73b7cf0c2d6e7d6372f026ea81193fd6 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Mon, 10 Dec 2018 16:50:19 +0000 Subject: soc: fsl: dpio: add a device_link at dpaa2_io_service_register Automatically add a device link between the actual device requesting the dpaa2_io_service_register and the underlying dpaa2_io used. This link will ensure that when a DPIO device, which is indirectly used by other devices, is unbound any consumer devices will be also unbound from their drivers. For example, any DPNI, bound to the dpaa2-eth driver, which is using DPIO devices will be unbound before its supplier device. Also, add a new parameter to the dpaa2_io_service_[de]register functions to specify the requesting device (ie the consumer). Signed-off-by: Ioana Ciornei Reviewed-by: Horia Geanta Reviewed-by: Ioana Radulescu Signed-off-by: Li Yang --- drivers/crypto/caam/caamalg_qi2.c | 6 +++--- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 9 +++++---- drivers/soc/fsl/dpio/dpio-service.c | 16 ++++++++++++++-- include/soc/fsl/dpaa2-io.h | 6 ++++-- 4 files changed, 26 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c index 425d5d974613..77f4c0045de2 100644 --- a/drivers/crypto/caam/caamalg_qi2.c +++ b/drivers/crypto/caam/caamalg_qi2.c @@ -4503,7 +4503,7 @@ static int __cold dpaa2_dpseci_dpio_setup(struct dpaa2_caam_priv *priv) nctx->cb = dpaa2_caam_fqdan_cb; /* Register notification callbacks */ - err = dpaa2_io_service_register(NULL, nctx); + err = dpaa2_io_service_register(NULL, nctx, dev); if (unlikely(err)) { dev_dbg(dev, "No affine DPIO for cpu %d\n", cpu); nctx->cb = NULL; @@ -4536,7 +4536,7 @@ err: ppriv = per_cpu_ptr(priv->ppriv, cpu); if (!ppriv->nctx.cb) break; - dpaa2_io_service_deregister(NULL, &ppriv->nctx); + dpaa2_io_service_deregister(NULL, &ppriv->nctx, dev); } for_each_online_cpu(cpu) { @@ -4556,7 +4556,7 @@ static void __cold dpaa2_dpseci_dpio_free(struct dpaa2_caam_priv *priv) for_each_online_cpu(cpu) { ppriv = per_cpu_ptr(priv->ppriv, cpu); - dpaa2_io_service_deregister(NULL, &ppriv->nctx); + dpaa2_io_service_deregister(NULL, &ppriv->nctx, priv->dev); dpaa2_io_store_destroy(ppriv->store); if (++i == priv->num_pairs) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 1ca9a18139ec..c500ea77aaa0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1902,7 +1902,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv) /* Register the new context */ channel->dpio = dpaa2_io_service_select(i); - err = dpaa2_io_service_register(channel->dpio, nctx); + err = dpaa2_io_service_register(channel->dpio, nctx, dev); if (err) { dev_dbg(dev, "No affine DPIO for cpu %d\n", i); /* If no affine DPIO for this core, there's probably @@ -1942,7 +1942,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv) return 0; err_set_cdan: - dpaa2_io_service_deregister(channel->dpio, nctx); + dpaa2_io_service_deregister(channel->dpio, nctx, dev); err_service_reg: free_channel(priv, channel); err_alloc_ch: @@ -1962,13 +1962,14 @@ err_alloc_ch: static void free_dpio(struct dpaa2_eth_priv *priv) { - int i; + struct device *dev = priv->net_dev->dev.parent; struct dpaa2_eth_channel *ch; + int i; /* deregister CDAN notifications and free channels */ for (i = 0; i < priv->num_channels; i++) { ch = priv->channel[i]; - dpaa2_io_service_deregister(ch->dpio, &ch->nctx); + dpaa2_io_service_deregister(ch->dpio, &ch->nctx, dev); free_channel(priv, ch); } } diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index 52d800aa4774..bc801934602a 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -237,6 +237,7 @@ EXPORT_SYMBOL(dpaa2_io_get_cpu); * notifications on the given DPIO service. * @d: the given DPIO service. * @ctx: the notification context. + * @dev: the device that requests the register * * The caller should make the MC command to attach a DPAA2 object to * a DPIO after this function completes successfully. In that way: @@ -251,14 +252,20 @@ EXPORT_SYMBOL(dpaa2_io_get_cpu); * Return 0 for success, or -ENODEV for failure. */ int dpaa2_io_service_register(struct dpaa2_io *d, - struct dpaa2_io_notification_ctx *ctx) + struct dpaa2_io_notification_ctx *ctx, + struct device *dev) { + struct device_link *link; unsigned long irqflags; d = service_select_by_cpu(d, ctx->desired_cpu); if (!d) return -ENODEV; + link = device_link_add(dev, d->dev, DL_FLAG_AUTOREMOVE_CONSUMER); + if (!link) + return -EINVAL; + ctx->dpio_id = d->dpio_desc.dpio_id; ctx->qman64 = (u64)(uintptr_t)ctx; ctx->dpio_private = d; @@ -279,12 +286,14 @@ EXPORT_SYMBOL_GPL(dpaa2_io_service_register); * dpaa2_io_service_deregister - The opposite of 'register'. * @service: the given DPIO service. * @ctx: the notification context. + * @dev: the device that requests to be deregistered * * This function should be called only after sending the MC command to * to detach the notification-producing device from the DPIO. */ void dpaa2_io_service_deregister(struct dpaa2_io *service, - struct dpaa2_io_notification_ctx *ctx) + struct dpaa2_io_notification_ctx *ctx, + struct device *dev) { struct dpaa2_io *d = ctx->dpio_private; unsigned long irqflags; @@ -295,6 +304,9 @@ void dpaa2_io_service_deregister(struct dpaa2_io *service, spin_lock_irqsave(&d->lock_notifications, irqflags); list_del(&ctx->node); spin_unlock_irqrestore(&d->lock_notifications, irqflags); + + if (dev) + device_link_remove(dev, d->dev); } EXPORT_SYMBOL_GPL(dpaa2_io_service_deregister); diff --git a/include/soc/fsl/dpaa2-io.h b/include/soc/fsl/dpaa2-io.h index e252066d1f43..3447fd10a3e6 100644 --- a/include/soc/fsl/dpaa2-io.h +++ b/include/soc/fsl/dpaa2-io.h @@ -94,9 +94,11 @@ struct dpaa2_io_notification_ctx { int dpaa2_io_get_cpu(struct dpaa2_io *d); int dpaa2_io_service_register(struct dpaa2_io *service, - struct dpaa2_io_notification_ctx *ctx); + struct dpaa2_io_notification_ctx *ctx, + struct device *dev); void dpaa2_io_service_deregister(struct dpaa2_io *service, - struct dpaa2_io_notification_ctx *ctx); + struct dpaa2_io_notification_ctx *ctx, + struct device *dev); int dpaa2_io_service_rearm(struct dpaa2_io *service, struct dpaa2_io_notification_ctx *ctx); -- cgit v1.2.3 From 8a533a7de21aa69cf9a3e55223c819858fbc7da2 Mon Sep 17 00:00:00 2001 From: Ioana Ciocoi Radulescu Date: Fri, 14 Dec 2018 16:04:06 +0000 Subject: soc: fsl: dpio: Change bpid type to u16 In all QBMan registers, the buffer pool id field is two bytes long. The low level qbman APIs reflect this, but the high level DPIO ones use u32. Modify them in order to avoid implicit downcasts. Signed-off-by: Ioana Radulescu Signed-off-by: Li Yang --- drivers/soc/fsl/dpio/dpio-service.c | 4 ++-- include/soc/fsl/dpaa2-io.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index 5389336463c0..b9539ef2c3cd 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -473,7 +473,7 @@ EXPORT_SYMBOL_GPL(dpaa2_io_service_enqueue_qd); * Return 0 for success, and negative error code for failure. */ int dpaa2_io_service_release(struct dpaa2_io *d, - u32 bpid, + u16 bpid, const u64 *buffers, unsigned int num_buffers) { @@ -502,7 +502,7 @@ EXPORT_SYMBOL_GPL(dpaa2_io_service_release); * Eg. if the buffer pool is empty, this will return zero. */ int dpaa2_io_service_acquire(struct dpaa2_io *d, - u32 bpid, + u16 bpid, u64 *buffers, unsigned int num_buffers) { diff --git a/include/soc/fsl/dpaa2-io.h b/include/soc/fsl/dpaa2-io.h index 3447fd10a3e6..672cfb58046f 100644 --- a/include/soc/fsl/dpaa2-io.h +++ b/include/soc/fsl/dpaa2-io.h @@ -111,9 +111,9 @@ int dpaa2_io_service_enqueue_fq(struct dpaa2_io *d, u32 fqid, const struct dpaa2_fd *fd); int dpaa2_io_service_enqueue_qd(struct dpaa2_io *d, u32 qdid, u8 prio, u16 qdbin, const struct dpaa2_fd *fd); -int dpaa2_io_service_release(struct dpaa2_io *d, u32 bpid, +int dpaa2_io_service_release(struct dpaa2_io *d, u16 bpid, const u64 *buffers, unsigned int num_buffers); -int dpaa2_io_service_acquire(struct dpaa2_io *d, u32 bpid, +int dpaa2_io_service_acquire(struct dpaa2_io *d, u16 bpid, u64 *buffers, unsigned int num_buffers); struct dpaa2_io_store *dpaa2_io_store_create(unsigned int max_frames, -- cgit v1.2.3 From afb77422819ff60612e9b7d36461b9b2bc8e038e Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Mon, 10 Dec 2018 16:50:19 +0000 Subject: bus: fsl-mc: automatically add a device_link on fsl_mc_[portal,object]_allocate Allocatable devices can be acquired by drivers on the fsl-mc bus using the fsl_mc_portal_allocate or fsl_mc_object_allocate functions. Add a device link between the consumer device and the supplier device so that proper resource management is achieved. Also, adding a link between these devices ensures that a proper unbind order is respected (ie before the supplier device is unbound from its respective driver all consumer devices will be notified and unbound first). Signed-off-by: Ioana Ciornei Reviewed-by: Laurentiu Tudor Signed-off-by: Li Yang --- drivers/bus/fsl-mc/fsl-mc-allocator.c | 11 +++++++++++ drivers/bus/fsl-mc/mc-io.c | 13 +++++++++++++ include/linux/fsl/mc.h | 1 + 3 files changed, 25 insertions(+) (limited to 'include') diff --git a/drivers/bus/fsl-mc/fsl-mc-allocator.c b/drivers/bus/fsl-mc/fsl-mc-allocator.c index e906ecfe23dd..8ad77246f322 100644 --- a/drivers/bus/fsl-mc/fsl-mc-allocator.c +++ b/drivers/bus/fsl-mc/fsl-mc-allocator.c @@ -295,6 +295,14 @@ int __must_check fsl_mc_object_allocate(struct fsl_mc_device *mc_dev, if (!mc_adev) goto error; + mc_adev->consumer_link = device_link_add(&mc_dev->dev, + &mc_adev->dev, + DL_FLAG_AUTOREMOVE_CONSUMER); + if (!mc_adev->consumer_link) { + error = -EINVAL; + goto error; + } + *new_mc_adev = mc_adev; return 0; error: @@ -321,6 +329,9 @@ void fsl_mc_object_free(struct fsl_mc_device *mc_adev) return; fsl_mc_resource_free(resource); + + device_link_del(mc_adev->consumer_link); + mc_adev->consumer_link = NULL; } EXPORT_SYMBOL_GPL(fsl_mc_object_free); diff --git a/drivers/bus/fsl-mc/mc-io.c b/drivers/bus/fsl-mc/mc-io.c index 7226cfc49b6f..3ae574a58cce 100644 --- a/drivers/bus/fsl-mc/mc-io.c +++ b/drivers/bus/fsl-mc/mc-io.c @@ -209,9 +209,19 @@ int __must_check fsl_mc_portal_allocate(struct fsl_mc_device *mc_dev, if (error < 0) goto error_cleanup_resource; + dpmcp_dev->consumer_link = device_link_add(&mc_dev->dev, + &dpmcp_dev->dev, + DL_FLAG_AUTOREMOVE_CONSUMER); + if (!dpmcp_dev->consumer_link) { + error = -EINVAL; + goto error_cleanup_mc_io; + } + *new_mc_io = mc_io; return 0; +error_cleanup_mc_io: + fsl_destroy_mc_io(mc_io); error_cleanup_resource: fsl_mc_resource_free(resource); return error; @@ -244,6 +254,9 @@ void fsl_mc_portal_free(struct fsl_mc_io *mc_io) fsl_destroy_mc_io(mc_io); fsl_mc_resource_free(resource); + + device_link_del(dpmcp_dev->consumer_link); + dpmcp_dev->consumer_link = NULL; } EXPORT_SYMBOL_GPL(fsl_mc_portal_free); diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 741f567253ef..975553a9f75d 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -193,6 +193,7 @@ struct fsl_mc_device { struct resource *regions; struct fsl_mc_device_irq **irqs; struct fsl_mc_resource *resource; + struct device_link *consumer_link; }; #define to_fsl_mc_device(_dev) \ -- cgit v1.2.3 From ff525b6e2d3011d5a1ef08d8b3f4f745c7245412 Mon Sep 17 00:00:00 2001 From: John Garry Date: Sat, 5 Jan 2019 00:01:26 +0800 Subject: scsi: libsas: Fix some indentation in libsas.h Currently much indentation in this file is done with whitespaces instead of tabs, which can make reading difficult, so fix this up. Some other little minor tidy-up is done, but this file still has many other checkpatch warnings (generally linelength > 80 or function arguments have no identifier names). All libsas code can be audited for checkpatch issues later. Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 56 +++++++++++++++++++++++++-------------------------- 1 file changed, 27 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 3de3b10da19a..857086cf7ebf 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -52,8 +52,8 @@ enum sas_phy_role { }; enum sas_phy_type { - PHY_TYPE_PHYSICAL, - PHY_TYPE_VIRTUAL + PHY_TYPE_PHYSICAL, + PHY_TYPE_VIRTUAL }; /* The events are mnemonically described in sas_dump.c @@ -91,7 +91,7 @@ enum discover_event { #define to_dom_device(_obj) container_of(_obj, struct domain_device, dev_obj) #define to_dev_attr(_attr) container_of(_attr, struct domain_dev_attribute,\ - attr) + attr) enum routing_attribute { DIRECT_ROUTING, @@ -184,37 +184,37 @@ struct domain_device { spinlock_t done_lock; enum sas_device_type dev_type; - enum sas_linkrate linkrate; - enum sas_linkrate min_linkrate; - enum sas_linkrate max_linkrate; + enum sas_linkrate linkrate; + enum sas_linkrate min_linkrate; + enum sas_linkrate max_linkrate; - int pathways; + int pathways; - struct domain_device *parent; - struct list_head siblings; /* devices on the same level */ - struct asd_sas_port *port; /* shortcut to root of the tree */ + struct domain_device *parent; + struct list_head siblings; /* devices on the same level */ + struct asd_sas_port *port; /* shortcut to root of the tree */ struct sas_phy *phy; - struct list_head dev_list_node; + struct list_head dev_list_node; struct list_head disco_list_node; /* awaiting probe or destruct */ - enum sas_protocol iproto; - enum sas_protocol tproto; + enum sas_protocol iproto; + enum sas_protocol tproto; - struct sas_rphy *rphy; + struct sas_rphy *rphy; - u8 sas_addr[SAS_ADDR_SIZE]; - u8 hashed_sas_addr[HASHED_SAS_ADDR_SIZE]; + u8 sas_addr[SAS_ADDR_SIZE]; + u8 hashed_sas_addr[HASHED_SAS_ADDR_SIZE]; - u8 frame_rcvd[32]; + u8 frame_rcvd[32]; - union { - struct expander_device ex_dev; - struct sata_device sata_dev; /* STP & directly attached */ + union { + struct expander_device ex_dev; + struct sata_device sata_dev; /* STP & directly attached */ struct ssp_device ssp_dev; - }; + }; - void *lldd_dev; + void *lldd_dev; unsigned long state; struct kref kref; }; @@ -512,10 +512,10 @@ enum exec_status { /* When a task finishes with a response, the LLDD examines the * response: - * - For an ATA task task_status_struct::stat is set to + * - For an ATA task task_status_struct::stat is set to * SAS_PROTO_RESPONSE, and the task_status_struct::buf is set to the * contents of struct ata_task_resp. - * - For SSP tasks, if no data is present or status/TMF response + * - For SSP tasks, if no data is present or status/TMF response * is valid, task_status_struct::stat is set. If data is present * (SENSE data), the LLDD copies up to SAS_STATUS_BUF_SIZE, sets * task_status_struct::buf_valid_size, and task_status_struct::stat is @@ -671,15 +671,13 @@ extern void sas_prep_resume_ha(struct sas_ha_struct *sas_ha); extern void sas_resume_ha(struct sas_ha_struct *sas_ha); extern void sas_suspend_ha(struct sas_ha_struct *sas_ha); -int sas_set_phy_speed(struct sas_phy *phy, - struct sas_phy_linkrates *rates); +int sas_set_phy_speed(struct sas_phy *phy, struct sas_phy_linkrates *rates); int sas_phy_reset(struct sas_phy *phy, int hard_reset); -extern int sas_queuecommand(struct Scsi_Host * ,struct scsi_cmnd *); +extern int sas_queuecommand(struct Scsi_Host *, struct scsi_cmnd *); extern int sas_target_alloc(struct scsi_target *); extern int sas_slave_configure(struct scsi_device *); extern int sas_change_queue_depth(struct scsi_device *, int new_depth); -extern int sas_bios_param(struct scsi_device *, - struct block_device *, +extern int sas_bios_param(struct scsi_device *, struct block_device *, sector_t capacity, int *hsc); extern struct scsi_transport_template * sas_domain_attach_transport(struct sas_domain_function_template *); -- cgit v1.2.3 From 98a455d91e7116ca417bc37da6aa2dd633206a6f Mon Sep 17 00:00:00 2001 From: Shunyong Yang Date: Tue, 18 Dec 2018 14:02:45 +0800 Subject: ACPI / tables: table override from built-in initrd In some scenario, we need to build initrd with kernel in a single image. This can simplify system deployment process by downloading the whole system once, such as in IC verification. This patch adds support to override ACPI tables from built-in initrd. Signed-off-by: Shunyong Yang [ rjw: Minor cleanups ] Signed-off-by: Rafael J. Wysocki --- Documentation/acpi/initrd_table_override.txt | 4 ++++ drivers/acpi/Kconfig | 10 ++++++++++ drivers/acpi/tables.c | 12 ++++++++++-- include/linux/initrd.h | 3 +++ 4 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/acpi/initrd_table_override.txt b/Documentation/acpi/initrd_table_override.txt index eb651a6aa285..30437a6db373 100644 --- a/Documentation/acpi/initrd_table_override.txt +++ b/Documentation/acpi/initrd_table_override.txt @@ -14,6 +14,10 @@ upgrade the ACPI execution environment that is defined by the ACPI tables via upgrading the ACPI tables provided by the BIOS with an instrumented, modified, more recent version one, or installing brand new ACPI tables. +When building initrd with kernel in a single image, option +ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD should also be true for this +feature to work. + For a full list of ACPI tables that can be upgraded/installed, take a look at the char *table_sigs[MAX_ACPI_SIGNATURE]; definition in drivers/acpi/tables.c. diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 90ff0a47c12e..4e015c77e48e 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -357,6 +357,16 @@ config ACPI_TABLE_UPGRADE initrd, therefore it's safe to say Y. See Documentation/acpi/initrd_table_override.txt for details +config ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD + bool "Override ACPI tables from built-in initrd" + depends on ACPI_TABLE_UPGRADE + depends on INITRAMFS_SOURCE!="" && INITRAMFS_COMPRESSION="" + help + This option provides functionality to override arbitrary ACPI tables + from built-in uncompressed initrd. + + See Documentation/acpi/initrd_table_override.txt for details + config ACPI_DEBUG bool "Debug Statements" help diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 48eabb6c2d4f..8fccbe49612a 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -473,14 +473,22 @@ static DECLARE_BITMAP(acpi_initrd_installed, NR_ACPI_INITRD_TABLES); void __init acpi_table_upgrade(void) { - void *data = (void *)initrd_start; - size_t size = initrd_end - initrd_start; + void *data; + size_t size; int sig, no, table_nr = 0, total_offset = 0; long offset = 0; struct acpi_table_header *table; char cpio_path[32] = "kernel/firmware/acpi/"; struct cpio_data file; + if (IS_ENABLED(CONFIG_ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD)) { + data = __initramfs_start; + size = __initramfs_size; + } else { + data = (void *)initrd_start; + size = initrd_end - initrd_start; + } + if (data == NULL || size == 0) return; diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 14beaff9b445..d77fe34fb00a 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -25,3 +25,6 @@ extern phys_addr_t phys_initrd_start; extern unsigned long phys_initrd_size; extern unsigned int real_root_dev; + +extern char __initramfs_start[]; +extern unsigned long __initramfs_size; -- cgit v1.2.3 From e6ce7943231fcba95a3c8842ab65f257cb5ab124 Mon Sep 17 00:00:00 2001 From: Sameer Pujar Date: Mon, 14 Jan 2019 23:51:08 +0530 Subject: ALSA: hda: add verbs for stripe control Controllers can support multiple Serial Data Out(SDO) lines, for extended outbound bandwidth, to pump data to all codecs on the link. Codecs can sample data present on SDO. Add verbs AC_VERB_GET_STRIPE_CONTROL and AC_VERB_SET_STRIPE_CONTROL These can be used to program usage of SDO lines for codec. Signed-off-by: Sameer Pujar Reviewed-by: Mohan Kumar D Reviewed-by: Ravindra Lokhande Reviewed-by: Pierre-Louis Bossart Signed-off-by: Takashi Iwai --- include/sound/hda_verbs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/hda_verbs.h b/include/sound/hda_verbs.h index 2a8573a00ea6..e36b77531c5c 100644 --- a/include/sound/hda_verbs.h +++ b/include/sound/hda_verbs.h @@ -66,6 +66,7 @@ enum { #define AC_VERB_GET_CONFIG_DEFAULT 0x0f1c /* f20: AFG/MFG */ #define AC_VERB_GET_SUBSYSTEM_ID 0x0f20 +#define AC_VERB_GET_STRIPE_CONTROL 0x0f24 #define AC_VERB_GET_CVT_CHAN_COUNT 0x0f2d #define AC_VERB_GET_HDMI_DIP_SIZE 0x0f2e #define AC_VERB_GET_HDMI_ELDD 0x0f2f @@ -110,6 +111,7 @@ enum { #define AC_VERB_SET_CONFIG_DEFAULT_BYTES_3 0x71f #define AC_VERB_SET_EAPD 0x788 #define AC_VERB_SET_CODEC_RESET 0x7ff +#define AC_VERB_SET_STRIPE_CONTROL 0x724 #define AC_VERB_SET_CVT_CHAN_COUNT 0x72d #define AC_VERB_SET_HDMI_DIP_INDEX 0x730 #define AC_VERB_SET_HDMI_DIP_DATA 0x731 -- cgit v1.2.3 From 5dd3d271320d888bb708ca6252b8a9e416a7fe64 Mon Sep 17 00:00:00 2001 From: Sameer Pujar Date: Mon, 14 Jan 2019 23:51:09 +0530 Subject: ALSA: hda: Add api to program stripe control bits Controllers and codecs can support striping of audio out across multiple SDO lines. The number of supported SDO lines can be specific to chip. GCAP register can be read to know the maximum supported SDO lines. snd_hdac_get_stream_stripe_ctl() is exposed to program stripe bits on controller and codec side. stripe value: 0 for 1SDO, 1 for 2SDO, 2 for 4SDO lines, etc., Signed-off-by: Sameer Pujar Reviewed-by: Mohan Kumar D Reviewed-by: Ravindra Lokhande Reviewed-by: Pierre-Louis Bossart Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 3 +++ sound/hda/hdac_stream.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) (limited to 'include') diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index b4fa1c775251..45f944d57982 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -539,6 +539,9 @@ void snd_hdac_stream_sync(struct hdac_stream *azx_dev, bool start, unsigned int streams); void snd_hdac_stream_timecounter_init(struct hdac_stream *azx_dev, unsigned int streams); +int snd_hdac_get_stream_stripe_ctl(struct hdac_bus *bus, + struct snd_pcm_substream *substream); + /* * macros for easy use */ diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index ba73a33480b6..820694a2061e 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -12,6 +12,40 @@ #include #include "trace.h" +/** + * snd_hdac_get_stream_stripe_ctl - get stripe control value + * @bus: HD-audio core bus + * @substream: PCM substream + */ +int snd_hdac_get_stream_stripe_ctl(struct hdac_bus *bus, + struct snd_pcm_substream *substream) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + unsigned int channels = runtime->channels, + rate = runtime->rate, + bits_per_sample = runtime->sample_bits, + max_sdo_lines, value, sdo_line; + + /* T_AZA_GCAP_NSDO is 1:2 bitfields in GCAP */ + max_sdo_lines = snd_hdac_chip_readl(bus, GCAP) & AZX_GCAP_NSDO; + + /* following is from HD audio spec */ + for (sdo_line = max_sdo_lines; sdo_line > 0; sdo_line >>= 1) { + if (rate > 48000) + value = (channels * bits_per_sample * + (rate / 48000)) / sdo_line; + else + value = (channels * bits_per_sample) / sdo_line; + + if (value >= 8) + break; + } + + /* stripe value: 0 for 1SDO, 1 for 2SDO, 2 for 4SDO lines */ + return sdo_line >> 1; +} +EXPORT_SYMBOL_GPL(snd_hdac_get_stream_stripe_ctl); + /** * snd_hdac_stream_init - initialize each stream (aka device) * @bus: HD-audio core bus -- cgit v1.2.3 From b59c8e7a73160b11f99b9008a5f215dd54b9d581 Mon Sep 17 00:00:00 2001 From: Sameer Pujar Date: Mon, 14 Jan 2019 23:51:10 +0530 Subject: ALSA: hda: add register offset for stripe control bits 16:17 in SD_CTL register refer to stripe control. Added an offset register(AZX_REG_SD_CTL_3B) to have exclusive read/write of corresponding register byte. This helps to avoid unnecessary 32-bit read/write of SD_CTL whenever only stripe or other bits of corresponding byte need to be updated. Also HD audio spec defines SD_CTL as 3 byte register. SD_CTL_STRIPE_MASK(0x3) can be used for stripe control programming and when updating AZX_REG_SD_CTL_3B. Signed-off-by: Sameer Pujar Reviewed-by: Mohan Kumar D Reviewed-by: Ravindra Lokhande Reviewed-by: Pierre-Louis Bossart Signed-off-by: Takashi Iwai --- include/sound/hda_register.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/hda_register.h b/include/sound/hda_register.h index 2ab39fb52d7a..0fd39295b426 100644 --- a/include/sound/hda_register.h +++ b/include/sound/hda_register.h @@ -79,6 +79,7 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 }; /* stream register offsets from stream base */ #define AZX_REG_SD_CTL 0x00 +#define AZX_REG_SD_CTL_3B 0x02 /* 3rd byte of SD_CTL register */ #define AZX_REG_SD_STS 0x03 #define AZX_REG_SD_LPIB 0x04 #define AZX_REG_SD_CBL 0x08 @@ -165,6 +166,7 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 }; #define SD_INT_COMPLETE 0x04 /* completion interrupt */ #define SD_INT_MASK (SD_INT_DESC_ERR|SD_INT_FIFO_ERR|\ SD_INT_COMPLETE) +#define SD_CTL_STRIPE_MASK 0x3 /* stripe control mask */ /* SD_STS */ #define SD_STS_FIFO_READY 0x20 /* FIFO ready */ -- cgit v1.2.3 From ea4baf7f116a18382df331db2123d98bc1c3cd83 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 18 Dec 2018 14:28:30 +0200 Subject: RDMA: Rename port_callback to init_port Most provider routines are callback routines which ib core invokes. _callback suffix doesn't convey information about when such callback is invoked. Therefore, rename port_callback to init_port. Additionally, store the init_port function pointer in ib_device_ops, so that it can be accessed in subsequent patches when binding rdma device to net namespace. Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/core_priv.h | 4 +--- drivers/infiniband/core/device.c | 7 +++---- drivers/infiniband/core/sysfs.c | 16 ++++++---------- drivers/infiniband/hw/bnxt_re/main.c | 2 +- drivers/infiniband/hw/cxgb3/iwch_provider.c | 2 +- drivers/infiniband/hw/cxgb4/provider.c | 2 +- drivers/infiniband/hw/hfi1/verbs.c | 2 +- drivers/infiniband/hw/hns/hns_roce_main.c | 2 +- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 2 +- drivers/infiniband/hw/mlx4/main.c | 2 +- drivers/infiniband/hw/mlx5/main.c | 2 +- drivers/infiniband/hw/mthca/mthca_provider.c | 2 +- drivers/infiniband/hw/nes/nes_verbs.c | 2 +- drivers/infiniband/hw/ocrdma/ocrdma_main.c | 2 +- drivers/infiniband/hw/qedr/main.c | 2 +- drivers/infiniband/hw/qib/qib_verbs.c | 2 +- drivers/infiniband/hw/usnic/usnic_ib_main.c | 2 +- drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c | 2 +- drivers/infiniband/sw/rdmavt/vt.c | 5 ++--- drivers/infiniband/sw/rxe/rxe_verbs.c | 2 +- include/rdma/ib_verbs.h | 10 +++++++--- include/rdma/rdma_vt.h | 3 --- 22 files changed, 35 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index 3cd830d52967..aca75c74e451 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -54,9 +54,7 @@ struct pkey_index_qp_list { struct list_head qp_list; }; -int ib_device_register_sysfs(struct ib_device *device, - int (*port_callback)(struct ib_device *, - u8, struct kobject *)); +int ib_device_register_sysfs(struct ib_device *device); void ib_device_unregister_sysfs(struct ib_device *device); int ib_device_rename(struct ib_device *ibdev, const char *name); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 8872453e26c0..66867e92ddea 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -574,9 +574,7 @@ port_cleanup: * callback for each device that is added. @device must be allocated * with ib_alloc_device(). */ -int ib_register_device(struct ib_device *device, const char *name, - int (*port_callback)(struct ib_device *, u8, - struct kobject *)) +int ib_register_device(struct ib_device *device, const char *name) { int ret; struct ib_client *client; @@ -613,7 +611,7 @@ int ib_register_device(struct ib_device *device, const char *name, goto dev_cleanup; } - ret = ib_device_register_sysfs(device, port_callback); + ret = ib_device_register_sysfs(device); if (ret) { dev_warn(&device->dev, "Couldn't register device with driver model\n"); @@ -1283,6 +1281,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) SET_DEVICE_OP(dev_ops, get_vector_affinity); SET_DEVICE_OP(dev_ops, get_vf_config); SET_DEVICE_OP(dev_ops, get_vf_stats); + SET_DEVICE_OP(dev_ops, init_port); SET_DEVICE_OP(dev_ops, map_mr_sg); SET_DEVICE_OP(dev_ops, map_phys_fmr); SET_DEVICE_OP(dev_ops, mmap); diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index 80f68eb0ba5c..7a5679933df6 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -1015,9 +1015,7 @@ err_free_stats: return; } -static int add_port(struct ib_device *device, int port_num, - int (*port_callback)(struct ib_device *, - u8, struct kobject *)) +static int add_port(struct ib_device *device, int port_num) { struct ib_port *p; struct ib_port_attr attr; @@ -1113,8 +1111,8 @@ static int add_port(struct ib_device *device, int port_num, if (ret) goto err_free_pkey; - if (port_callback) { - ret = port_callback(device, port_num, &p->kobj); + if (device->ops.init_port) { + ret = device->ops.init_port(device, port_num, &p->kobj); if (ret) goto err_remove_pkey; } @@ -1308,9 +1306,7 @@ static void free_port_list_attributes(struct ib_device *device) kobject_put(device->ports_kobj); } -int ib_device_register_sysfs(struct ib_device *device, - int (*port_callback)(struct ib_device *, - u8, struct kobject *)) +int ib_device_register_sysfs(struct ib_device *device) { struct device *class_dev = &device->dev; int ret; @@ -1330,12 +1326,12 @@ int ib_device_register_sysfs(struct ib_device *device, } if (rdma_cap_ib_switch(device)) { - ret = add_port(device, 0, port_callback); + ret = add_port(device, 0); if (ret) goto err_put; } else { for (i = 1; i <= device->phys_port_cnt; ++i) { - ret = add_port(device, i, port_callback); + ret = add_port(device, i); if (ret) goto err_put; } diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index e7a997f2a537..797a3e943366 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -662,7 +662,7 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev) rdma_set_device_sysfs_group(ibdev, &bnxt_re_dev_attr_group); ibdev->driver_id = RDMA_DRIVER_BNXT_RE; ib_set_device_ops(ibdev, &bnxt_re_dev_ops); - return ib_register_device(ibdev, "bnxt_re%d", NULL); + return ib_register_device(ibdev, "bnxt_re%d"); } static void bnxt_re_dev_remove(struct bnxt_re_dev *rdev) diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 92ee6761a3bd..ffdde3cca268 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -1409,7 +1409,7 @@ int iwch_register_device(struct iwch_dev *dev) dev->ibdev.driver_id = RDMA_DRIVER_CXGB3; rdma_set_device_sysfs_group(&dev->ibdev, &iwch_attr_group); ib_set_device_ops(&dev->ibdev, &iwch_dev_ops); - ret = ib_register_device(&dev->ibdev, "cxgb3_%d", NULL); + ret = ib_register_device(&dev->ibdev, "cxgb3_%d"); if (ret) kfree(dev->ibdev.iwcm); return ret; diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 586b0c37481f..0a99894b0160 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -634,7 +634,7 @@ void c4iw_register_device(struct work_struct *work) rdma_set_device_sysfs_group(&dev->ibdev, &c4iw_attr_group); dev->ibdev.driver_id = RDMA_DRIVER_CXGB4; ib_set_device_ops(&dev->ibdev, &c4iw_dev_ops); - ret = ib_register_device(&dev->ibdev, "cxgb4_%d", NULL); + ret = ib_register_device(&dev->ibdev, "cxgb4_%d"); if (ret) goto err_kfree_iwcm; return; diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index ec582d86025f..8957adf58af7 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -1622,6 +1622,7 @@ static const struct ib_device_ops hfi1_dev_ops = { .alloc_rdma_netdev = hfi1_vnic_alloc_rn, .get_dev_fw_str = hfi1_get_dev_fw_str, .get_hw_stats = get_hw_stats, + .init_port = hfi1_create_port_files, .modify_device = modify_device, /* keep process mad in the driver */ .process_mad = hfi1_process_mad, @@ -1679,7 +1680,6 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd) /* * Fill in rvt info object. */ - dd->verbs_dev.rdi.driver_f.port_callback = hfi1_create_port_files; dd->verbs_dev.rdi.driver_f.get_pci_dev = get_pci_dev; dd->verbs_dev.rdi.driver_f.check_ah = hfi1_check_ah; dd->verbs_dev.rdi.driver_f.notify_new_ah = hfi1_notify_new_ah; diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index 44a07fce0617..46ede58ef3b8 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -564,7 +564,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev) ib_dev->driver_id = RDMA_DRIVER_HNS; ib_set_device_ops(ib_dev, hr_dev->hw->hns_roce_dev_ops); ib_set_device_ops(ib_dev, &hns_roce_dev_ops); - ret = ib_register_device(ib_dev, "hns_%d", NULL); + ret = ib_register_device(ib_dev, "hns_%d"); if (ret) { dev_err(dev, "ib_register_device failed!\n"); return ret; diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 80b66df95362..af66ab9d150b 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -2868,7 +2868,7 @@ int i40iw_register_rdma_device(struct i40iw_device *iwdev) iwibdev = iwdev->iwibdev; rdma_set_device_sysfs_group(&iwibdev->ibdev, &i40iw_attr_group); iwibdev->ibdev.driver_id = RDMA_DRIVER_I40IW; - ret = ib_register_device(&iwibdev->ibdev, "i40iw%d", NULL); + ret = ib_register_device(&iwibdev->ibdev, "i40iw%d"); if (ret) goto error; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 1f15ec3e2b83..c3f950d82ed0 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -2856,7 +2856,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) rdma_set_device_sysfs_group(&ibdev->ib_dev, &mlx4_attr_group); ibdev->ib_dev.driver_id = RDMA_DRIVER_MLX4; - if (ib_register_device(&ibdev->ib_dev, "mlx4_%d", NULL)) + if (ib_register_device(&ibdev->ib_dev, "mlx4_%d")) goto err_diag_counters; if (mlx4_ib_mad_init(ibdev)) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 717e8535b41a..948617a60d44 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -6233,7 +6233,7 @@ int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev) name = "mlx5_%d"; else name = "mlx5_bond_%d"; - return ib_register_device(&dev->ib_dev, name, NULL); + return ib_register_device(&dev->ib_dev, name); } void mlx5_ib_stage_pre_ib_reg_umr_cleanup(struct mlx5_ib_dev *dev) diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 0a939ea5497b..3473c6c51b92 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -1338,7 +1338,7 @@ int mthca_register_device(struct mthca_dev *dev) rdma_set_device_sysfs_group(&dev->ib_dev, &mthca_attr_group); dev->ib_dev.driver_id = RDMA_DRIVER_MTHCA; - ret = ib_register_device(&dev->ib_dev, "mthca%d", NULL); + ret = ib_register_device(&dev->ib_dev, "mthca%d"); if (ret) return ret; diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index feb4d259aab9..34601f0cbd74 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -3801,7 +3801,7 @@ int nes_register_ofa_device(struct nes_ib_device *nesibdev) rdma_set_device_sysfs_group(&nesvnic->nesibdev->ibdev, &nes_attr_group); nesvnic->nesibdev->ibdev.driver_id = RDMA_DRIVER_NES; - ret = ib_register_device(&nesvnic->nesibdev->ibdev, "nes%d", NULL); + ret = ib_register_device(&nesvnic->nesibdev->ibdev, "nes%d"); if (ret) { return ret; } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 1f393842453a..f45b996f617f 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -243,7 +243,7 @@ static int ocrdma_register_device(struct ocrdma_dev *dev) } rdma_set_device_sysfs_group(&dev->ibdev, &ocrdma_attr_group); dev->ibdev.driver_id = RDMA_DRIVER_OCRDMA; - return ib_register_device(&dev->ibdev, "ocrdma%d", NULL); + return ib_register_device(&dev->ibdev, "ocrdma%d"); } static int ocrdma_alloc_resources(struct ocrdma_dev *dev) diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 75940e2a8791..8e5c76d06855 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -290,7 +290,7 @@ static int qedr_register_device(struct qedr_dev *dev) ib_set_device_ops(&dev->ibdev, &qedr_dev_ops); dev->ibdev.driver_id = RDMA_DRIVER_QEDR; - return ib_register_device(&dev->ibdev, "qedr%d", NULL); + return ib_register_device(&dev->ibdev, "qedr%d"); } /* This function allocates fast-path status block memory */ diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c index 276304f611ab..ff8dab8e2344 100644 --- a/drivers/infiniband/hw/qib/qib_verbs.c +++ b/drivers/infiniband/hw/qib/qib_verbs.c @@ -1494,6 +1494,7 @@ static void qib_fill_device_attr(struct qib_devdata *dd) } static const struct ib_device_ops qib_dev_ops = { + .init_port = qib_create_port_files, .modify_device = qib_modify_device, .process_mad = qib_process_mad, }; @@ -1567,7 +1568,6 @@ int qib_register_ib_device(struct qib_devdata *dd) /* * Fill in rvt info object. */ - dd->verbs_dev.rdi.driver_f.port_callback = qib_create_port_files; dd->verbs_dev.rdi.driver_f.get_pci_dev = qib_get_pci_dev; dd->verbs_dev.rdi.driver_f.check_ah = qib_check_ah; dd->verbs_dev.rdi.driver_f.setup_wqe = qib_check_send_wqe; diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index b2323a52a0dd..3201dd1899c7 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -422,7 +422,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev) us_ibdev->ib_dev.driver_id = RDMA_DRIVER_USNIC; rdma_set_device_sysfs_group(&us_ibdev->ib_dev, &usnic_attr_group); - if (ib_register_device(&us_ibdev->ib_dev, "usnic_%d", NULL)) + if (ib_register_device(&us_ibdev->ib_dev, "usnic_%d")) goto err_fwd_dealloc; usnic_fwd_set_mtu(us_ibdev->ufdev, us_ibdev->netdev->mtu); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index eaa109dbc96a..1bc415483d9b 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -278,7 +278,7 @@ static int pvrdma_register_device(struct pvrdma_dev *dev) spin_lock_init(&dev->srq_tbl_lock); rdma_set_device_sysfs_group(&dev->ib_dev, &pvrdma_attr_group); - ret = ib_register_device(&dev->ib_dev, "vmw_pvrdma%d", NULL); + ret = ib_register_device(&dev->ib_dev, "vmw_pvrdma%d"); if (ret) goto err_srq_free; diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c index 8724a1817158..7de7389d0235 100644 --- a/drivers/infiniband/sw/rdmavt/vt.c +++ b/drivers/infiniband/sw/rdmavt/vt.c @@ -446,7 +446,7 @@ static noinline int check_support(struct rvt_dev_info *rdi, int verb) * These functions are not part of verbs specifically but are * required for rdmavt to function. */ - if ((!rdi->driver_f.port_callback) || + if ((!rdi->ibdev.ops.init_port) || (!rdi->driver_f.get_pci_dev)) return -EINVAL; break; @@ -644,8 +644,7 @@ int rvt_register_device(struct rvt_dev_info *rdi, u32 driver_id) rdi->ibdev.driver_id = driver_id; /* We are now good to announce we exist */ - ret = ib_register_device(&rdi->ibdev, dev_name(&rdi->ibdev.dev), - rdi->driver_f.port_callback); + ret = ib_register_device(&rdi->ibdev, dev_name(&rdi->ibdev.dev)); if (ret) { rvt_pr_err(rdi, "Failed to register driver with ib core.\n"); goto bail_wss; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index b20e6e0415f5..43171148e9c5 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1258,7 +1258,7 @@ int rxe_register_device(struct rxe_dev *rxe) rdma_set_device_sysfs_group(dev, &rxe_attr_group); dev->driver_id = RDMA_DRIVER_RXE; - err = ib_register_device(dev, "rxe%d", NULL); + err = ib_register_device(dev, "rxe%d"); if (err) { pr_warn("%s failed with error %d\n", __func__, err); goto err1; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index aa1f126d3383..1d1902fd9f87 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2504,6 +2504,12 @@ struct ib_device_ops { */ int (*get_hw_stats)(struct ib_device *device, struct rdma_hw_stats *stats, u8 port, int index); + /* + * This function is called once for each port when a ib device is + * registered. + */ + int (*init_port)(struct ib_device *device, u8 port_num, + struct kobject *port_sysfs); }; struct ib_device { @@ -2620,9 +2626,7 @@ void ib_dealloc_device(struct ib_device *device); void ib_get_device_fw_str(struct ib_device *device, char *str); -int ib_register_device(struct ib_device *device, const char *name, - int (*port_callback)(struct ib_device *, u8, - struct kobject *)); +int ib_register_device(struct ib_device *device, const char *name); void ib_unregister_device(struct ib_device *device); int ib_register_client (struct ib_client *client); diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h index dd0ed8048bb4..acb3bc96dfa7 100644 --- a/include/rdma/rdma_vt.h +++ b/include/rdma/rdma_vt.h @@ -250,9 +250,6 @@ struct rvt_driver_provided { */ void (*do_send)(struct rvt_qp *qp); - /* Passed to ib core registration. Callback to create syfs files */ - int (*port_callback)(struct ib_device *, u8, struct kobject *); - /* * Returns a pointer to the undelying hardware's PCI device. This is * used to display information as to what hardware is being referenced -- cgit v1.2.3 From 54747231150f0dddf68f2ee29ec2970fcc433909 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 18 Dec 2018 14:15:56 +0200 Subject: RDMA: Introduce and use rdma_device_to_ibdev() Introduce and use rdma_device_to_ibdev() API for those drivers which are registering one sysfs group and also use in ib_core. In subsequent patch, device->provider_ibdev one-to-one mapping is no longer holds true during accessing sysfs entries. Therefore, introduce an API rdma_device_to_ibdev() that provides such information. Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/device.c | 2 -- drivers/infiniband/core/sysfs.c | 12 ++++++------ drivers/infiniband/hw/bnxt_re/main.c | 6 ++++-- drivers/infiniband/hw/cxgb3/iwch_provider.c | 14 ++++++++------ drivers/infiniband/hw/cxgb4/provider.c | 14 ++++++++------ drivers/infiniband/hw/hfi1/sysfs.c | 16 ++++++++-------- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 5 ++--- drivers/infiniband/hw/mlx4/main.c | 7 ++++--- drivers/infiniband/hw/mlx5/main.c | 13 ++++++++----- drivers/infiniband/hw/mthca/mthca_provider.c | 9 ++++++--- drivers/infiniband/hw/nes/nes_verbs.c | 2 +- drivers/infiniband/hw/ocrdma/ocrdma_main.c | 6 ++++-- drivers/infiniband/hw/qedr/main.c | 3 ++- drivers/infiniband/hw/qib/qib_sysfs.c | 18 +++++++++--------- drivers/infiniband/hw/usnic/usnic_ib_sysfs.c | 26 +++++++++++--------------- drivers/infiniband/sw/rxe/rxe_verbs.c | 4 ++-- include/rdma/ib_verbs.h | 23 +++++++++++++++++++++++ 17 files changed, 106 insertions(+), 74 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 66867e92ddea..f8180cf1a004 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -296,8 +296,6 @@ struct ib_device *ib_alloc_device(size_t size) device->dev.class = &ib_class; device_initialize(&device->dev); - dev_set_drvdata(&device->dev, device); - INIT_LIST_HEAD(&device->event_handler_list); spin_lock_init(&device->event_handler_lock); rwlock_init(&device->client_data_lock); diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index 7a5679933df6..c75692802da8 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -1187,7 +1187,7 @@ err_put: static ssize_t node_type_show(struct device *device, struct device_attribute *attr, char *buf) { - struct ib_device *dev = container_of(device, struct ib_device, dev); + struct ib_device *dev = rdma_device_to_ibdev(device); switch (dev->node_type) { case RDMA_NODE_IB_CA: return sprintf(buf, "%d: CA\n", dev->node_type); @@ -1204,7 +1204,7 @@ static DEVICE_ATTR_RO(node_type); static ssize_t sys_image_guid_show(struct device *device, struct device_attribute *dev_attr, char *buf) { - struct ib_device *dev = container_of(device, struct ib_device, dev); + struct ib_device *dev = rdma_device_to_ibdev(device); return sprintf(buf, "%04x:%04x:%04x:%04x\n", be16_to_cpu(((__be16 *) &dev->attrs.sys_image_guid)[0]), @@ -1217,7 +1217,7 @@ static DEVICE_ATTR_RO(sys_image_guid); static ssize_t node_guid_show(struct device *device, struct device_attribute *attr, char *buf) { - struct ib_device *dev = container_of(device, struct ib_device, dev); + struct ib_device *dev = rdma_device_to_ibdev(device); return sprintf(buf, "%04x:%04x:%04x:%04x\n", be16_to_cpu(((__be16 *) &dev->node_guid)[0]), @@ -1230,7 +1230,7 @@ static DEVICE_ATTR_RO(node_guid); static ssize_t node_desc_show(struct device *device, struct device_attribute *attr, char *buf) { - struct ib_device *dev = container_of(device, struct ib_device, dev); + struct ib_device *dev = rdma_device_to_ibdev(device); return sprintf(buf, "%.64s\n", dev->node_desc); } @@ -1239,7 +1239,7 @@ static ssize_t node_desc_store(struct device *device, struct device_attribute *attr, const char *buf, size_t count) { - struct ib_device *dev = container_of(device, struct ib_device, dev); + struct ib_device *dev = rdma_device_to_ibdev(device); struct ib_device_modify desc = {}; int ret; @@ -1258,7 +1258,7 @@ static DEVICE_ATTR_RW(node_desc); static ssize_t fw_ver_show(struct device *device, struct device_attribute *attr, char *buf) { - struct ib_device *dev = container_of(device, struct ib_device, dev); + struct ib_device *dev = rdma_device_to_ibdev(device); ib_get_device_fw_str(dev, buf); strlcat(buf, "\n", IB_FW_VERSION_NAME_MAX); diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 797a3e943366..16eecfa5882c 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -538,7 +538,8 @@ static struct bnxt_en_dev *bnxt_re_dev_probe(struct net_device *netdev) static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { - struct bnxt_re_dev *rdev = to_bnxt_re_dev(device, ibdev.dev); + struct bnxt_re_dev *rdev = + rdma_device_to_drv_device(device, struct bnxt_re_dev, ibdev); return scnprintf(buf, PAGE_SIZE, "0x%x\n", rdev->en_dev->pdev->vendor); } @@ -547,7 +548,8 @@ static DEVICE_ATTR_RO(hw_rev); static ssize_t hca_type_show(struct device *device, struct device_attribute *attr, char *buf) { - struct bnxt_re_dev *rdev = to_bnxt_re_dev(device, ibdev.dev); + struct bnxt_re_dev *rdev = + rdma_device_to_drv_device(device, struct bnxt_re_dev, ibdev); return scnprintf(buf, PAGE_SIZE, "%s\n", rdev->ibdev.node_desc); } diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index ffdde3cca268..07c20cd07f33 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -1130,8 +1130,9 @@ static int iwch_query_port(struct ib_device *ibdev, static ssize_t hw_rev_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct iwch_dev *iwch_dev = container_of(dev, struct iwch_dev, - ibdev.dev); + struct iwch_dev *iwch_dev = + rdma_device_to_drv_device(dev, struct iwch_dev, ibdev); + pr_debug("%s dev 0x%p\n", __func__, dev); return sprintf(buf, "%d\n", iwch_dev->rdev.t3cdev_p->type); } @@ -1140,8 +1141,8 @@ static DEVICE_ATTR_RO(hw_rev); static ssize_t hca_type_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct iwch_dev *iwch_dev = container_of(dev, struct iwch_dev, - ibdev.dev); + struct iwch_dev *iwch_dev = + rdma_device_to_drv_device(dev, struct iwch_dev, ibdev); struct ethtool_drvinfo info; struct net_device *lldev = iwch_dev->rdev.t3cdev_p->lldev; @@ -1154,8 +1155,9 @@ static DEVICE_ATTR_RO(hca_type); static ssize_t board_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct iwch_dev *iwch_dev = container_of(dev, struct iwch_dev, - ibdev.dev); + struct iwch_dev *iwch_dev = + rdma_device_to_drv_device(dev, struct iwch_dev, ibdev); + pr_debug("%s dev 0x%p\n", __func__, dev); return sprintf(buf, "%x.%x\n", iwch_dev->rdev.rnic_info.pdev->vendor, iwch_dev->rdev.rnic_info.pdev->device); diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 0a99894b0160..f977f8e7e162 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -376,8 +376,9 @@ static int c4iw_query_port(struct ib_device *ibdev, u8 port, static ssize_t hw_rev_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev, - ibdev.dev); + struct c4iw_dev *c4iw_dev = + rdma_device_to_drv_device(dev, struct c4iw_dev, ibdev); + pr_debug("dev 0x%p\n", dev); return sprintf(buf, "%d\n", CHELSIO_CHIP_RELEASE(c4iw_dev->rdev.lldi.adapter_type)); @@ -387,8 +388,8 @@ static DEVICE_ATTR_RO(hw_rev); static ssize_t hca_type_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev, - ibdev.dev); + struct c4iw_dev *c4iw_dev = + rdma_device_to_drv_device(dev, struct c4iw_dev, ibdev); struct ethtool_drvinfo info; struct net_device *lldev = c4iw_dev->rdev.lldi.ports[0]; @@ -401,8 +402,9 @@ static DEVICE_ATTR_RO(hca_type); static ssize_t board_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev, - ibdev.dev); + struct c4iw_dev *c4iw_dev = + rdma_device_to_drv_device(dev, struct c4iw_dev, ibdev); + pr_debug("dev 0x%p\n", dev); return sprintf(buf, "%x.%x\n", c4iw_dev->rdev.lldi.pdev->vendor, c4iw_dev->rdev.lldi.pdev->device); diff --git a/drivers/infiniband/hw/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c index 2be513d4c9da..90f62c4bddba 100644 --- a/drivers/infiniband/hw/hfi1/sysfs.c +++ b/drivers/infiniband/hw/hfi1/sysfs.c @@ -498,7 +498,7 @@ static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct hfi1_ibdev, rdi.ibdev); return sprintf(buf, "%x\n", dd_from_dev(dev)->minrev); } @@ -508,7 +508,7 @@ static ssize_t board_id_show(struct device *device, struct device_attribute *attr, char *buf) { struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct hfi1_ibdev, rdi.ibdev); struct hfi1_devdata *dd = dd_from_dev(dev); int ret; @@ -524,7 +524,7 @@ static ssize_t boardversion_show(struct device *device, struct device_attribute *attr, char *buf) { struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct hfi1_ibdev, rdi.ibdev); struct hfi1_devdata *dd = dd_from_dev(dev); /* The string printed here is already newline-terminated. */ @@ -536,7 +536,7 @@ static ssize_t nctxts_show(struct device *device, struct device_attribute *attr, char *buf) { struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct hfi1_ibdev, rdi.ibdev); struct hfi1_devdata *dd = dd_from_dev(dev); /* @@ -555,7 +555,7 @@ static ssize_t nfreectxts_show(struct device *device, struct device_attribute *attr, char *buf) { struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct hfi1_ibdev, rdi.ibdev); struct hfi1_devdata *dd = dd_from_dev(dev); /* Return the number of free user ports (contexts) available. */ @@ -567,7 +567,7 @@ static ssize_t serial_show(struct device *device, struct device_attribute *attr, char *buf) { struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct hfi1_ibdev, rdi.ibdev); struct hfi1_devdata *dd = dd_from_dev(dev); return scnprintf(buf, PAGE_SIZE, "%s", dd->serial); @@ -579,7 +579,7 @@ static ssize_t chip_reset_store(struct device *device, size_t count) { struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct hfi1_ibdev, rdi.ibdev); struct hfi1_devdata *dd = dd_from_dev(dev); int ret; @@ -609,7 +609,7 @@ static ssize_t tempsense_show(struct device *device, struct device_attribute *attr, char *buf) { struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct hfi1_ibdev, rdi.ibdev); struct hfi1_devdata *dd = dd_from_dev(dev); struct hfi1_temp temp; int ret; diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index af66ab9d150b..12b31a8440be 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -2139,9 +2139,8 @@ static int i40iw_dereg_mr(struct ib_mr *ib_mr) static ssize_t hw_rev_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct i40iw_ib_device *iwibdev = container_of(dev, - struct i40iw_ib_device, - ibdev.dev); + struct i40iw_ib_device *iwibdev = + rdma_device_to_drv_device(dev, struct i40iw_ib_device, ibdev); u32 hw_rev = iwibdev->iwdev->sc_dev.hw_rev; return sprintf(buf, "%x\n", hw_rev); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index c3f950d82ed0..dc2ffd293a11 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -2043,7 +2043,7 @@ static ssize_t hca_type_show(struct device *device, struct device_attribute *attr, char *buf) { struct mlx4_ib_dev *dev = - container_of(device, struct mlx4_ib_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev); return sprintf(buf, "MT%d\n", dev->dev->persist->pdev->device); } static DEVICE_ATTR_RO(hca_type); @@ -2052,7 +2052,7 @@ static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { struct mlx4_ib_dev *dev = - container_of(device, struct mlx4_ib_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev); return sprintf(buf, "%x\n", dev->dev->rev_id); } static DEVICE_ATTR_RO(hw_rev); @@ -2061,7 +2061,8 @@ static ssize_t board_id_show(struct device *device, struct device_attribute *attr, char *buf) { struct mlx4_ib_dev *dev = - container_of(device, struct mlx4_ib_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev); + return sprintf(buf, "%.*s\n", MLX4_BOARD_ID_LEN, dev->dev->board_id); } diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 948617a60d44..4b1b56d54301 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4104,7 +4104,7 @@ static ssize_t fw_pages_show(struct device *device, struct device_attribute *attr, char *buf) { struct mlx5_ib_dev *dev = - container_of(device, struct mlx5_ib_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mlx5_ib_dev, ib_dev); return sprintf(buf, "%d\n", dev->mdev->priv.fw_pages); } @@ -4114,7 +4114,7 @@ static ssize_t reg_pages_show(struct device *device, struct device_attribute *attr, char *buf) { struct mlx5_ib_dev *dev = - container_of(device, struct mlx5_ib_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mlx5_ib_dev, ib_dev); return sprintf(buf, "%d\n", atomic_read(&dev->mdev->priv.reg_pages)); } @@ -4124,7 +4124,8 @@ static ssize_t hca_type_show(struct device *device, struct device_attribute *attr, char *buf) { struct mlx5_ib_dev *dev = - container_of(device, struct mlx5_ib_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mlx5_ib_dev, ib_dev); + return sprintf(buf, "MT%d\n", dev->mdev->pdev->device); } static DEVICE_ATTR_RO(hca_type); @@ -4133,7 +4134,8 @@ static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { struct mlx5_ib_dev *dev = - container_of(device, struct mlx5_ib_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mlx5_ib_dev, ib_dev); + return sprintf(buf, "%x\n", dev->mdev->rev_id); } static DEVICE_ATTR_RO(hw_rev); @@ -4142,7 +4144,8 @@ static ssize_t board_id_show(struct device *device, struct device_attribute *attr, char *buf) { struct mlx5_ib_dev *dev = - container_of(device, struct mlx5_ib_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mlx5_ib_dev, ib_dev); + return sprintf(buf, "%.*s\n", MLX5_BOARD_ID_LEN, dev->mdev->board_id); } diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 3473c6c51b92..63003b4d2485 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -1081,7 +1081,8 @@ static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { struct mthca_dev *dev = - container_of(device, struct mthca_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mthca_dev, ib_dev); + return sprintf(buf, "%x\n", dev->rev_id); } static DEVICE_ATTR_RO(hw_rev); @@ -1090,7 +1091,8 @@ static ssize_t hca_type_show(struct device *device, struct device_attribute *attr, char *buf) { struct mthca_dev *dev = - container_of(device, struct mthca_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mthca_dev, ib_dev); + switch (dev->pdev->device) { case PCI_DEVICE_ID_MELLANOX_TAVOR: return sprintf(buf, "MT23108\n"); @@ -1111,7 +1113,8 @@ static ssize_t board_id_show(struct device *device, struct device_attribute *attr, char *buf) { struct mthca_dev *dev = - container_of(device, struct mthca_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct mthca_dev, ib_dev); + return sprintf(buf, "%.*s\n", MTHCA_BOARD_ID_LEN, dev->board_id); } static DEVICE_ATTR_RO(board_id); diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index 34601f0cbd74..034156f7e9ed 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -2560,7 +2560,7 @@ static ssize_t hw_rev_show(struct device *dev, struct device_attribute *attr, char *buf) { struct nes_ib_device *nesibdev = - container_of(dev, struct nes_ib_device, ibdev.dev); + rdma_device_to_drv_device(dev, struct nes_ib_device, ibdev); struct nes_vnic *nesvnic = nesibdev->nesvnic; nes_debug(NES_DBG_INIT, "\n"); diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index f45b996f617f..b0491b9ecfe4 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -118,7 +118,8 @@ static void get_dev_fw_str(struct ib_device *device, char *str) static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { - struct ocrdma_dev *dev = dev_get_drvdata(device); + struct ocrdma_dev *dev = + rdma_device_to_drv_device(device, struct ocrdma_dev, ibdev); return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->nic_info.pdev->vendor); } @@ -127,7 +128,8 @@ static DEVICE_ATTR_RO(hw_rev); static ssize_t hca_type_show(struct device *device, struct device_attribute *attr, char *buf) { - struct ocrdma_dev *dev = dev_get_drvdata(device); + struct ocrdma_dev *dev = + rdma_device_to_drv_device(device, struct ocrdma_dev, ibdev); return scnprintf(buf, PAGE_SIZE, "%s\n", &dev->model_number[0]); } diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 8e5c76d06855..f85e72b65a10 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -137,7 +137,8 @@ static int qedr_iw_port_immutable(struct ib_device *ibdev, u8 port_num, static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { - struct qedr_dev *dev = dev_get_drvdata(device); + struct qedr_dev *dev = + rdma_device_to_drv_device(device, struct qedr_dev, ibdev); return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->pdev->vendor); } diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index 1cf4ca3f23e3..905206a0c2d5 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -555,7 +555,7 @@ static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev); return sprintf(buf, "%x\n", dd_from_dev(dev)->minrev); } @@ -565,7 +565,7 @@ static ssize_t hca_type_show(struct device *device, struct device_attribute *attr, char *buf) { struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev); struct qib_devdata *dd = dd_from_dev(dev); int ret; @@ -590,7 +590,7 @@ static ssize_t boardversion_show(struct device *device, struct device_attribute *attr, char *buf) { struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev); struct qib_devdata *dd = dd_from_dev(dev); /* The string printed here is already newline-terminated. */ @@ -602,7 +602,7 @@ static ssize_t localbus_info_show(struct device *device, struct device_attribute *attr, char *buf) { struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev); struct qib_devdata *dd = dd_from_dev(dev); /* The string printed here is already newline-terminated. */ @@ -614,7 +614,7 @@ static ssize_t nctxts_show(struct device *device, struct device_attribute *attr, char *buf) { struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev); struct qib_devdata *dd = dd_from_dev(dev); /* Return the number of user ports (contexts) available. */ @@ -630,7 +630,7 @@ static ssize_t nfreectxts_show(struct device *device, struct device_attribute *attr, char *buf) { struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev); struct qib_devdata *dd = dd_from_dev(dev); /* Return the number of free user ports (contexts) available. */ @@ -642,7 +642,7 @@ static ssize_t serial_show(struct device *device, struct device_attribute *attr, char *buf) { struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev); struct qib_devdata *dd = dd_from_dev(dev); buf[sizeof(dd->serial)] = '\0'; @@ -657,7 +657,7 @@ static ssize_t chip_reset_store(struct device *device, size_t count) { struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev); struct qib_devdata *dd = dd_from_dev(dev); int ret; @@ -679,7 +679,7 @@ static ssize_t tempsense_show(struct device *device, struct device_attribute *attr, char *buf) { struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, rdi.ibdev.dev); + rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev); struct qib_devdata *dd = dd_from_dev(dev); int ret; int idx; diff --git a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c index a7e4b2ccfaf8..c85d48ae7442 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c @@ -50,7 +50,7 @@ static ssize_t board_id_show(struct device *device, struct device_attribute *attr, char *buf) { struct usnic_ib_dev *us_ibdev = - container_of(device, struct usnic_ib_dev, ib_dev.dev); + rdma_device_to_drv_device(device, struct usnic_ib_dev, ib_dev); unsigned short subsystem_device_id; mutex_lock(&us_ibdev->usdev_lock); @@ -67,14 +67,13 @@ static DEVICE_ATTR_RO(board_id); static ssize_t config_show(struct device *device, struct device_attribute *attr, char *buf) { - struct usnic_ib_dev *us_ibdev; + struct usnic_ib_dev *us_ibdev = + rdma_device_to_drv_device(device, struct usnic_ib_dev, ib_dev); char *ptr; unsigned left; unsigned n; enum usnic_vnic_res_type res_type; - us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev); - /* Buffer space limit is 1 page */ ptr = buf; left = PAGE_SIZE; @@ -130,9 +129,8 @@ static DEVICE_ATTR_RO(config); static ssize_t iface_show(struct device *device, struct device_attribute *attr, char *buf) { - struct usnic_ib_dev *us_ibdev; - - us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev); + struct usnic_ib_dev *us_ibdev = + rdma_device_to_drv_device(device, struct usnic_ib_dev, ib_dev); return scnprintf(buf, PAGE_SIZE, "%s\n", netdev_name(us_ibdev->netdev)); @@ -142,9 +140,8 @@ static DEVICE_ATTR_RO(iface); static ssize_t max_vf_show(struct device *device, struct device_attribute *attr, char *buf) { - struct usnic_ib_dev *us_ibdev; - - us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev); + struct usnic_ib_dev *us_ibdev = + rdma_device_to_drv_device(device, struct usnic_ib_dev, ib_dev); return scnprintf(buf, PAGE_SIZE, "%u\n", kref_read(&us_ibdev->vf_cnt)); @@ -154,10 +151,10 @@ static DEVICE_ATTR_RO(max_vf); static ssize_t qp_per_vf_show(struct device *device, struct device_attribute *attr, char *buf) { - struct usnic_ib_dev *us_ibdev; + struct usnic_ib_dev *us_ibdev = + rdma_device_to_drv_device(device, struct usnic_ib_dev, ib_dev); int qp_per_vf; - us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev); qp_per_vf = max(us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_WQ], us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_RQ]); @@ -169,9 +166,8 @@ static DEVICE_ATTR_RO(qp_per_vf); static ssize_t cq_per_vf_show(struct device *device, struct device_attribute *attr, char *buf) { - struct usnic_ib_dev *us_ibdev; - - us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev); + struct usnic_ib_dev *us_ibdev = + rdma_device_to_drv_device(device, struct usnic_ib_dev, ib_dev); return scnprintf(buf, PAGE_SIZE, "%d\n", us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_CQ]); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 43171148e9c5..3d01247a28db 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1129,8 +1129,8 @@ static int rxe_detach_mcast(struct ib_qp *ibqp, union ib_gid *mgid, u16 mlid) static ssize_t parent_show(struct device *device, struct device_attribute *attr, char *buf) { - struct rxe_dev *rxe = container_of(device, struct rxe_dev, - ib_dev.dev); + struct rxe_dev *rxe = + rdma_device_to_drv_device(device, struct rxe_dev, ib_dev); return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1)); } diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 1d1902fd9f87..94b6e1dd4dab 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -4241,4 +4241,27 @@ rdma_set_device_sysfs_group(struct ib_device *dev, dev->groups[1] = group; } +/** + * rdma_device_to_ibdev - Get ib_device pointer from device pointer + * + * @device: device pointer for which ib_device pointer to retrieve + * + * rdma_device_to_ibdev() retrieves ib_device pointer from device. + * + */ +static inline struct ib_device *rdma_device_to_ibdev(struct device *device) +{ + return container_of(device, struct ib_device, dev); +} + +/** + * rdma_device_to_drv_device - Helper macro to reach back to driver's + * ib_device holder structure from device pointer. + * + * NOTE: New drivers should not make use of this API; This API is only for + * existing drivers who have exposed sysfs entries using + * rdma_set_device_sysfs_group(). + */ +#define rdma_device_to_drv_device(dev, drv_dev_struct, ibdev_member) \ + container_of(rdma_device_to_ibdev(dev), drv_dev_struct, ibdev_member) #endif /* IB_VERBS_H */ -- cgit v1.2.3 From 73f5a82bb3c9fce550da4a74a32b8cb064b50663 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 13 Jan 2019 15:57:04 +0200 Subject: RDMA/mad: Reduce MAD scope to mlx5_ib only Management Datagram Interface (MAD) is applicable only when physical port is Infiniband. It makes MAD command logic to be completely unrelated to eth/core parts of mlx5. Signed-off-by: Leon Romanovsky Acked-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/cmd.c | 37 ++++++++++++ drivers/infiniband/hw/mlx5/cmd.h | 2 + drivers/infiniband/hw/mlx5/mad.c | 11 ++-- drivers/infiniband/hw/mlx5/mlx5_ib.h | 3 - drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/mad.c | 75 ------------------------ include/linux/mlx5/driver.h | 2 - 7 files changed, 47 insertions(+), 85 deletions(-) delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/mad.c (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c index 356bccc715ee..6bcc63aaa50b 100644 --- a/drivers/infiniband/hw/mlx5/cmd.c +++ b/drivers/infiniband/hw/mlx5/cmd.c @@ -345,3 +345,40 @@ int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id, counter_set_id); return err; } + +int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, + u16 opmod, u8 port) +{ + int outlen = MLX5_ST_SZ_BYTES(mad_ifc_out); + int inlen = MLX5_ST_SZ_BYTES(mad_ifc_in); + int err = -ENOMEM; + void *data; + void *resp; + u32 *out; + u32 *in; + + in = kzalloc(inlen, GFP_KERNEL); + out = kzalloc(outlen, GFP_KERNEL); + if (!in || !out) + goto out; + + MLX5_SET(mad_ifc_in, in, opcode, MLX5_CMD_OP_MAD_IFC); + MLX5_SET(mad_ifc_in, in, op_mod, opmod); + MLX5_SET(mad_ifc_in, in, port, port); + + data = MLX5_ADDR_OF(mad_ifc_in, in, mad); + memcpy(data, inb, MLX5_FLD_SZ_BYTES(mad_ifc_in, mad)); + + err = mlx5_cmd_exec(dev, in, inlen, out, outlen); + if (err) + goto out; + + resp = MLX5_ADDR_OF(mad_ifc_out, out, response_mad_packet); + memcpy(outb, resp, + MLX5_FLD_SZ_BYTES(mad_ifc_out, response_mad_packet)); + +out: + kfree(out); + kfree(in); + return err; +} diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h index 1e76dc67a369..923a7b93f507 100644 --- a/drivers/infiniband/hw/mlx5/cmd.h +++ b/drivers/infiniband/hw/mlx5/cmd.h @@ -63,4 +63,6 @@ int mlx5_cmd_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn, u16 uid); int mlx5_cmd_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn, u16 uid); int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id, u16 uid); +int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, + u16 opmod, u8 port); #endif /* MLX5_IB_CMD_H */ diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 558638468edb..6c529e6f3a01 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -36,6 +36,7 @@ #include #include #include "mlx5_ib.h" +#include "cmd.h" enum { MLX5_IB_VENDOR_CLASS1 = 0x9, @@ -51,9 +52,10 @@ static bool can_do_mad_ifc(struct mlx5_ib_dev *dev, u8 port_num, return dev->mdev->port_caps[port_num - 1].has_smi; } -int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey, - u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh, - const void *in_mad, void *response_mad) +static int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, + int ignore_bkey, u8 port, const struct ib_wc *in_wc, + const struct ib_grh *in_grh, const void *in_mad, + void *response_mad) { u8 op_modifier = 0; @@ -68,7 +70,8 @@ int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey, if (ignore_bkey || !in_wc) op_modifier |= 0x2; - return mlx5_core_mad_ifc(dev->mdev, in_mad, response_mad, op_modifier, port); + return mlx5_cmd_mad_ifc(dev->mdev, in_mad, response_mad, op_modifier, + port); } static int process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index b06d3b1efea8..efe383c0ac86 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1038,9 +1038,6 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq); void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq); void mlx5_ib_free_srq_wqe(struct mlx5_ib_srq *srq, int wqe_index); -int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey, - u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh, - const void *in_mad, void *response_mad); struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, u32 flags, struct ib_udata *udata); int mlx5_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 9de9abacf7f6..0257731e6d42 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o # mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \ - mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ + transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o diag/fs_tracepoint.o diag/fw_tracer.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mad.c b/drivers/net/ethernet/mellanox/mlx5/core/mad.c deleted file mode 100644 index 3a3b0005fd2b..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/mad.c +++ /dev/null @@ -1,75 +0,0 @@ -/* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include -#include -#include -#include -#include "mlx5_core.h" - -int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, - u16 opmod, u8 port) -{ - int outlen = MLX5_ST_SZ_BYTES(mad_ifc_out); - int inlen = MLX5_ST_SZ_BYTES(mad_ifc_in); - int err = -ENOMEM; - void *data; - void *resp; - u32 *out; - u32 *in; - - in = kzalloc(inlen, GFP_KERNEL); - out = kzalloc(outlen, GFP_KERNEL); - if (!in || !out) - goto out; - - MLX5_SET(mad_ifc_in, in, opcode, MLX5_CMD_OP_MAD_IFC); - MLX5_SET(mad_ifc_in, in, op_mod, opmod); - MLX5_SET(mad_ifc_in, in, port, port); - - data = MLX5_ADDR_OF(mad_ifc_in, in, mad); - memcpy(data, inb, MLX5_FLD_SZ_BYTES(mad_ifc_in, mad)); - - err = mlx5_cmd_exec(dev, in, inlen, out, outlen); - if (err) - goto out; - - resp = MLX5_ADDR_OF(mad_ifc_out, out, response_mad_packet); - memcpy(outb, resp, - MLX5_FLD_SZ_BYTES(mad_ifc_out, response_mad_packet)); - -out: - kfree(out); - kfree(in); - return err; -} -EXPORT_SYMBOL_GPL(mlx5_core_mad_ifc); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 54299251d40d..4e444863054a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -897,8 +897,6 @@ int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, u32 *out, int outlen); int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); -int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, - u16 opmod, u8 port); int mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); void mlx5_pagealloc_start(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 16118794ede91aac1a73abe15de22d3de9d2b775 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Jan 2019 14:33:17 +0100 Subject: posix-cpu-timers: Remove private interval storage Posix CPU timers store the interval in private storage for historical reasons (it_interval used to be a non scalar representation on 32bit systems). This is gone and there is no reason for duplicated storage anymore. Use it_interval everywhere. Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Peter Zijlstra Cc: "H.J. Lu" Link: https://lkml.kernel.org/r/20190111133500.945255655@linutronix.de --- include/linux/posix-timers.h | 2 +- kernel/time/posix-cpu-timers.c | 13 ++++++------- 2 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index e96581ca7c9d..b20798fc5191 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -12,7 +12,7 @@ struct siginfo; struct cpu_timer_list { struct list_head entry; - u64 expires, incr; + u64 expires; struct task_struct *task; int firing; }; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 80f955210861..0a426f4e3125 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -67,13 +67,13 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now) int i; u64 delta, incr; - if (timer->it.cpu.incr == 0) + if (!timer->it_interval) return; if (now < timer->it.cpu.expires) return; - incr = timer->it.cpu.incr; + incr = timer->it_interval; delta = now + incr - timer->it.cpu.expires; /* Don't use (incr*2 < delta), incr*2 might overflow. */ @@ -520,7 +520,7 @@ static void cpu_timer_fire(struct k_itimer *timer) */ wake_up_process(timer->it_process); timer->it.cpu.expires = 0; - } else if (timer->it.cpu.incr == 0) { + } else if (!timer->it_interval) { /* * One-shot timer. Clear it as soon as it's fired. */ @@ -606,7 +606,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, */ ret = 0; - old_incr = timer->it.cpu.incr; + old_incr = timer->it_interval; old_expires = timer->it.cpu.expires; if (unlikely(timer->it.cpu.firing)) { timer->it.cpu.firing = -1; @@ -684,8 +684,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, * Install the new reload setting, and * set up the signal and overrun bookkeeping. */ - timer->it.cpu.incr = timespec64_to_ns(&new->it_interval); - timer->it_interval = ns_to_ktime(timer->it.cpu.incr); + timer->it_interval = timespec64_to_ktime(new->it_interval); /* * This acts as a modification timestamp for the timer, @@ -724,7 +723,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp /* * Easy part: convert the reload time. */ - itp->it_interval = ns_to_timespec64(timer->it.cpu.incr); + itp->it_interval = ktime_to_timespec64(timer->it_interval); if (!timer->it.cpu.expires) return; -- cgit v1.2.3 From 3d21ef0b49f84d3341984caafc5c658739674927 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 11 Jan 2019 15:58:39 +0100 Subject: ALSA: pcm: Suspend streams globally via device type PM ops Until now we rely on each driver calling snd_pcm_suspend*() explicitly at its own PM handling. However, this can be done far more easily by setting the PM ops to each actual snd_pcm device object. This patch adds the device_type object for PCM stream and assigns to each PCM stream object. The type contains only the PM ops for system suspend; we don't need to deal with the resume in general. The suspend hook simply calls snd_pcm_suspend_all() for the given PCM streams. This implies that the PM order is correctly put, i.e. PCM is suspended before the main (or codec) driver, which should be true in general. If a special ordering is needed, you'd need to adjust the device PM order manually later. This patch introduces a new flag, snd_pcm.no_device_suspend, too. With this flag set, the PCM device object won't invoke snd_pcm_suspend_all() by itself. This is needed for ASoC who wants to manage the PM call orders in its serialized way, and the flag is set in soc_new_pcm() as default. For the non-ASoC world, we can get rid of the manual snd_pcm_suspend calls. This will be done in the later patches. Reviewed-by: Jaroslav Kysela Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 1 + sound/core/pcm.c | 26 ++++++++++++++++++++++++++ sound/soc/soc-pcm.c | 1 + 3 files changed, 28 insertions(+) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index d6bd3caf6878..04e97564949c 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -538,6 +538,7 @@ struct snd_pcm { void (*private_free) (struct snd_pcm *pcm); bool internal; /* pcm is for internal use only */ bool nonatomic; /* whole PCM operations are in non-atomic context */ + bool no_device_suspend; /* don't invoke device PM suspend */ #if IS_ENABLED(CONFIG_SND_PCM_OSS) struct snd_pcm_oss oss; #endif diff --git a/sound/core/pcm.c b/sound/core/pcm.c index 01b9d62eef14..ca1ea3cf9350 100644 --- a/sound/core/pcm.c +++ b/sound/core/pcm.c @@ -683,6 +683,31 @@ static inline int snd_pcm_substream_proc_done(struct snd_pcm_substream *substrea static const struct attribute_group *pcm_dev_attr_groups[]; +/* + * PM callbacks: we need to deal only with suspend here, as the resume is + * triggered either from user-space or the driver's resume callback + */ +#ifdef CONFIG_PM_SLEEP +static int do_pcm_suspend(struct device *dev) +{ + struct snd_pcm_str *pstr = container_of(dev, struct snd_pcm_str, dev); + + if (!pstr->pcm->no_device_suspend) + snd_pcm_suspend_all(pstr->pcm); + return 0; +} +#endif + +static const struct dev_pm_ops pcm_dev_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(do_pcm_suspend, NULL) +}; + +/* device type for PCM -- basically only for passing PM callbacks */ +static const struct device_type pcm_dev_type = { + .name = "pcm", + .pm = &pcm_dev_pm_ops, +}; + /** * snd_pcm_new_stream - create a new PCM stream * @pcm: the pcm instance @@ -713,6 +738,7 @@ int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count) snd_device_initialize(&pstr->dev, pcm->card); pstr->dev.groups = pcm_dev_attr_groups; + pstr->dev.type = &pcm_dev_type; dev_set_name(&pstr->dev, "pcmC%iD%i%c", pcm->card->number, pcm->device, stream == SNDRV_PCM_STREAM_PLAYBACK ? 'p' : 'c'); diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 03f36e534050..485eec5be608 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -3155,6 +3155,7 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num) } pcm->private_free = soc_pcm_private_free; + pcm->no_device_suspend = true; out: dev_info(rtd->card->dev, "%s <-> %s mapping ok\n", (rtd->num_codecs > 1) ? "multicodec" : rtd->codec_dai->name, -- cgit v1.2.3 From ce7f93e2bd6f649980846914e4a04ad6ba141fa6 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 15 Jan 2019 10:54:02 +0100 Subject: ALSA: pcm: Make snd_pcm_suspend() local static snd_pcm_suspend() is no longer called from outside, so let's make it local static. Also drop a superfluous NULL check there. Reviewed-by: Jaroslav Kysela Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 5 ----- sound/core/pcm_native.c | 11 +++-------- 2 files changed, 3 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 04e97564949c..2c30c1ad1b0d 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -582,13 +582,8 @@ int snd_pcm_stop(struct snd_pcm_substream *substream, snd_pcm_state_t status); int snd_pcm_drain_done(struct snd_pcm_substream *substream); int snd_pcm_stop_xrun(struct snd_pcm_substream *substream); #ifdef CONFIG_PM -int snd_pcm_suspend(struct snd_pcm_substream *substream); int snd_pcm_suspend_all(struct snd_pcm *pcm); #else -static inline int snd_pcm_suspend(struct snd_pcm_substream *substream) -{ - return 0; -} static inline int snd_pcm_suspend_all(struct snd_pcm *pcm) { return 0; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 818dff1de545..26afb6b0889a 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1460,29 +1460,24 @@ static const struct action_ops snd_pcm_action_suspend = { .post_action = snd_pcm_post_suspend }; -/** +/* * snd_pcm_suspend - trigger SUSPEND to all linked streams * @substream: the PCM substream * * After this call, all streams are changed to SUSPENDED state. * - * Return: Zero if successful (or @substream is %NULL), or a negative error - * code. + * Return: Zero if successful, or a negative error code. */ -int snd_pcm_suspend(struct snd_pcm_substream *substream) +static int snd_pcm_suspend(struct snd_pcm_substream *substream) { int err; unsigned long flags; - if (! substream) - return 0; - snd_pcm_stream_lock_irqsave(substream, flags); err = snd_pcm_action(&snd_pcm_action_suspend, substream, 0); snd_pcm_stream_unlock_irqrestore(substream, flags); return err; } -EXPORT_SYMBOL(snd_pcm_suspend); /** * snd_pcm_suspend_all - trigger SUSPEND to all substreams in the given pcm -- cgit v1.2.3 From f13c274da3896da705169409ad9b41df1ed84a33 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 14 Jan 2019 09:55:23 -0800 Subject: ACPICA: Convert more ACPI errors to firmware errors ACPICA commit f3198c12f2df9d170b3da891a180b774cfe01e59 Also adds a new firmware error function, acpi_bios_exception. Link: https://github.com/acpica/acpica/commit/f3198c12 Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpica/dsopcode.c | 15 +++++++------- drivers/acpi/acpica/exoparg2.c | 8 ++++---- drivers/acpi/acpica/utxferror.c | 44 +++++++++++++++++++++++++++++++++++++++++ include/acpi/acoutput.h | 2 ++ include/acpi/acpixf.h | 6 ++++++ 5 files changed, 64 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c index 78f9de260d5f..a0b821031063 100644 --- a/drivers/acpi/acpica/dsopcode.c +++ b/drivers/acpi/acpica/dsopcode.c @@ -130,8 +130,8 @@ acpi_ds_init_buffer_field(u16 aml_opcode, /* Must have a valid (>0) bit count */ if (bit_count == 0) { - ACPI_ERROR((AE_INFO, - "Attempt to CreateField of length zero")); + ACPI_BIOS_ERROR((AE_INFO, + "Attempt to CreateField of length zero")); status = AE_AML_OPERAND_VALUE; goto cleanup; } @@ -194,12 +194,13 @@ acpi_ds_init_buffer_field(u16 aml_opcode, /* Entire field must fit within the current length of the buffer */ if ((bit_offset + bit_count) > (8 * (u32)buffer_desc->buffer.length)) { - ACPI_ERROR((AE_INFO, - "Field [%4.4s] at bit offset/length %u/%u " - "exceeds size of target Buffer (%u bits)", - acpi_ut_get_node_name(result_desc), bit_offset, - bit_count, 8 * (u32)buffer_desc->buffer.length)); status = AE_AML_BUFFER_LIMIT; + ACPI_BIOS_EXCEPTION((AE_INFO, status, + "Field [%4.4s] at bit offset/length %u/%u " + "exceeds size of target Buffer (%u bits)", + acpi_ut_get_node_name(result_desc), + bit_offset, bit_count, + 8 * (u32)buffer_desc->buffer.length)); goto cleanup; } diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c index 3a477566ba1b..e9509b1c9a3a 100644 --- a/drivers/acpi/acpica/exoparg2.c +++ b/drivers/acpi/acpica/exoparg2.c @@ -390,10 +390,10 @@ acpi_status acpi_ex_opcode_2A_1T_1R(struct acpi_walk_state *walk_state) /* Failure means that the Index was beyond the end of the object */ if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, - "Index (0x%X%8.8X) is beyond end of object (length 0x%X)", - ACPI_FORMAT_UINT64(index), - (u32)length)); + ACPI_BIOS_EXCEPTION((AE_INFO, status, + "Index (0x%X%8.8X) is beyond end of object (length 0x%X)", + ACPI_FORMAT_UINT64(index), + (u32)length)); goto cleanup; } diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c index 6bb85d691fcb..a1ed7fced4db 100644 --- a/drivers/acpi/acpica/utxferror.c +++ b/drivers/acpi/acpica/utxferror.c @@ -185,6 +185,50 @@ acpi_bios_error(const char *module_name, ACPI_EXPORT_SYMBOL(acpi_bios_error) +/******************************************************************************* + * + * FUNCTION: acpi_bios_exception + * + * PARAMETERS: module_name - Caller's module name (for error output) + * line_number - Caller's line number (for error output) + * status - Status value to be decoded/formatted + * format - Printf format string + additional args + * + * RETURN: None + * + * DESCRIPTION: Print an "ACPI Firmware Error" message with module/line/version + * info as well as decoded acpi_status. + * + ******************************************************************************/ +void ACPI_INTERNAL_VAR_XFACE +acpi_bios_exception(const char *module_name, + u32 line_number, + acpi_status status, const char *format, ...) +{ + va_list arg_list; + + ACPI_MSG_REDIRECT_BEGIN; + + /* For AE_OK, just print the message */ + + if (ACPI_SUCCESS(status)) { + acpi_os_printf(ACPI_MSG_BIOS_ERROR); + + } else { + acpi_os_printf(ACPI_MSG_BIOS_ERROR "%s, ", + acpi_format_exception(status)); + } + + va_start(arg_list, format); + acpi_os_vprintf(format, arg_list); + ACPI_MSG_SUFFIX; + va_end(arg_list); + + ACPI_MSG_REDIRECT_END; +} + +ACPI_EXPORT_SYMBOL(acpi_bios_exception) + /******************************************************************************* * * FUNCTION: acpi_bios_warning diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index 6db9a6d40c85..93a280703318 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -201,6 +201,7 @@ #define ACPI_EXCEPTION(plist) acpi_exception plist #define ACPI_ERROR(plist) acpi_error plist #define ACPI_BIOS_WARNING(plist) acpi_bios_warning plist +#define ACPI_BIOS_EXCEPTION(plist) acpi_bios_exception plist #define ACPI_BIOS_ERROR(plist) acpi_bios_error plist #define ACPI_DEBUG_OBJECT(obj,l,i) acpi_ex_do_debug_object(obj,l,i) @@ -213,6 +214,7 @@ #define ACPI_EXCEPTION(plist) #define ACPI_ERROR(plist) #define ACPI_BIOS_WARNING(plist) +#define ACPI_BIOS_EXCEPTION(plist) #define ACPI_BIOS_ERROR(plist) #define ACPI_DEBUG_OBJECT(obj,l,i) diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 7aa38b648564..f0adda015fc7 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -903,6 +903,12 @@ ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(3) acpi_bios_error(const char *module_name, u32 line_number, const char *format, ...)) +ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(4) + void ACPI_INTERNAL_VAR_XFACE + acpi_bios_exception(const char *module_name, + u32 line_number, + acpi_status status, + const char *format, ...)) ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(3) void ACPI_INTERNAL_VAR_XFACE acpi_bios_warning(const char *module_name, -- cgit v1.2.3 From 840c02ca2215af648c781ae680d93d8aecd083b7 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 14 Jan 2019 09:55:25 -0800 Subject: ACPICA: All acpica: Update copyrights to 2019 ACPICA commit 62f4f98e941d86e41969bf2ab5a93b8dc94dc49e The update includes userspace tool signons. Link: https://github.com/acpica/acpica/commit/62f4f98e Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpica/acapps.h | 4 ++-- drivers/acpi/acpica/accommon.h | 2 +- drivers/acpi/acpica/acconvert.h | 2 +- drivers/acpi/acpica/acdebug.h | 2 +- drivers/acpi/acpica/acdispat.h | 2 +- drivers/acpi/acpica/acevents.h | 2 +- drivers/acpi/acpica/acglobal.h | 2 +- drivers/acpi/acpica/achware.h | 2 +- drivers/acpi/acpica/acinterp.h | 2 +- drivers/acpi/acpica/aclocal.h | 2 +- drivers/acpi/acpica/acmacros.h | 2 +- drivers/acpi/acpica/acnamesp.h | 2 +- drivers/acpi/acpica/acobject.h | 2 +- drivers/acpi/acpica/acopcode.h | 2 +- drivers/acpi/acpica/acparser.h | 2 +- drivers/acpi/acpica/acpredef.h | 2 +- drivers/acpi/acpica/acresrc.h | 2 +- drivers/acpi/acpica/acstruct.h | 2 +- drivers/acpi/acpica/actables.h | 2 +- drivers/acpi/acpica/acutils.h | 2 +- drivers/acpi/acpica/amlcode.h | 2 +- drivers/acpi/acpica/amlresrc.h | 2 +- drivers/acpi/acpica/dbhistry.c | 2 +- drivers/acpi/acpica/dsargs.c | 2 +- drivers/acpi/acpica/dscontrol.c | 2 +- drivers/acpi/acpica/dsdebug.c | 2 +- drivers/acpi/acpica/dsfield.c | 2 +- drivers/acpi/acpica/dsinit.c | 2 +- drivers/acpi/acpica/dsmethod.c | 2 +- drivers/acpi/acpica/dsobject.c | 2 +- drivers/acpi/acpica/dsopcode.c | 2 +- drivers/acpi/acpica/dspkginit.c | 2 +- drivers/acpi/acpica/dswexec.c | 2 +- drivers/acpi/acpica/dswload.c | 2 +- drivers/acpi/acpica/dswload2.c | 2 +- drivers/acpi/acpica/dswscope.c | 2 +- drivers/acpi/acpica/dswstate.c | 2 +- drivers/acpi/acpica/evevent.c | 2 +- drivers/acpi/acpica/evglock.c | 2 +- drivers/acpi/acpica/evgpe.c | 2 +- drivers/acpi/acpica/evgpeblk.c | 2 +- drivers/acpi/acpica/evgpeinit.c | 2 +- drivers/acpi/acpica/evgpeutil.c | 2 +- drivers/acpi/acpica/evhandler.c | 2 +- drivers/acpi/acpica/evmisc.c | 2 +- drivers/acpi/acpica/evregion.c | 2 +- drivers/acpi/acpica/evrgnini.c | 2 +- drivers/acpi/acpica/evxface.c | 2 +- drivers/acpi/acpica/evxfevnt.c | 2 +- drivers/acpi/acpica/evxfgpe.c | 2 +- drivers/acpi/acpica/evxfregn.c | 2 +- drivers/acpi/acpica/exconcat.c | 2 +- drivers/acpi/acpica/exconfig.c | 2 +- drivers/acpi/acpica/exconvrt.c | 2 +- drivers/acpi/acpica/excreate.c | 2 +- drivers/acpi/acpica/exdebug.c | 2 +- drivers/acpi/acpica/exdump.c | 2 +- drivers/acpi/acpica/exfield.c | 2 +- drivers/acpi/acpica/exfldio.c | 2 +- drivers/acpi/acpica/exmisc.c | 2 +- drivers/acpi/acpica/exmutex.c | 2 +- drivers/acpi/acpica/exnames.c | 2 +- drivers/acpi/acpica/exoparg1.c | 2 +- drivers/acpi/acpica/exoparg2.c | 2 +- drivers/acpi/acpica/exoparg3.c | 2 +- drivers/acpi/acpica/exoparg6.c | 2 +- drivers/acpi/acpica/exprep.c | 2 +- drivers/acpi/acpica/exregion.c | 2 +- drivers/acpi/acpica/exresnte.c | 2 +- drivers/acpi/acpica/exresolv.c | 2 +- drivers/acpi/acpica/exresop.c | 2 +- drivers/acpi/acpica/exserial.c | 2 +- drivers/acpi/acpica/exstore.c | 2 +- drivers/acpi/acpica/exstoren.c | 2 +- drivers/acpi/acpica/exstorob.c | 2 +- drivers/acpi/acpica/exsystem.c | 2 +- drivers/acpi/acpica/extrace.c | 2 +- drivers/acpi/acpica/exutils.c | 2 +- drivers/acpi/acpica/hwacpi.c | 2 +- drivers/acpi/acpica/hwesleep.c | 2 +- drivers/acpi/acpica/hwgpe.c | 2 +- drivers/acpi/acpica/hwsleep.c | 2 +- drivers/acpi/acpica/hwtimer.c | 2 +- drivers/acpi/acpica/hwvalid.c | 2 +- drivers/acpi/acpica/hwxface.c | 2 +- drivers/acpi/acpica/hwxfsleep.c | 2 +- drivers/acpi/acpica/nsarguments.c | 2 +- drivers/acpi/acpica/nsconvert.c | 2 +- drivers/acpi/acpica/nsdump.c | 2 +- drivers/acpi/acpica/nsdumpdv.c | 2 +- drivers/acpi/acpica/nsinit.c | 2 +- drivers/acpi/acpica/nsload.c | 2 +- drivers/acpi/acpica/nsparse.c | 2 +- drivers/acpi/acpica/nspredef.c | 2 +- drivers/acpi/acpica/nsprepkg.c | 2 +- drivers/acpi/acpica/nsrepair.c | 2 +- drivers/acpi/acpica/nsrepair2.c | 2 +- drivers/acpi/acpica/nsutils.c | 2 +- drivers/acpi/acpica/nswalk.c | 2 +- drivers/acpi/acpica/nsxfname.c | 2 +- drivers/acpi/acpica/psargs.c | 2 +- drivers/acpi/acpica/psloop.c | 2 +- drivers/acpi/acpica/psobject.c | 2 +- drivers/acpi/acpica/psopcode.c | 2 +- drivers/acpi/acpica/psopinfo.c | 2 +- drivers/acpi/acpica/psparse.c | 2 +- drivers/acpi/acpica/psscope.c | 2 +- drivers/acpi/acpica/pstree.c | 2 +- drivers/acpi/acpica/psutils.c | 2 +- drivers/acpi/acpica/pswalk.c | 2 +- drivers/acpi/acpica/psxface.c | 2 +- drivers/acpi/acpica/tbdata.c | 2 +- drivers/acpi/acpica/tbfadt.c | 2 +- drivers/acpi/acpica/tbfind.c | 2 +- drivers/acpi/acpica/tbinstal.c | 2 +- drivers/acpi/acpica/tbprint.c | 2 +- drivers/acpi/acpica/tbutils.c | 2 +- drivers/acpi/acpica/tbxface.c | 2 +- drivers/acpi/acpica/tbxfload.c | 2 +- drivers/acpi/acpica/tbxfroot.c | 2 +- drivers/acpi/acpica/utaddress.c | 2 +- drivers/acpi/acpica/utalloc.c | 2 +- drivers/acpi/acpica/utascii.c | 2 +- drivers/acpi/acpica/utbuffer.c | 2 +- drivers/acpi/acpica/utcache.c | 2 +- drivers/acpi/acpica/utcopy.c | 2 +- drivers/acpi/acpica/utdebug.c | 2 +- drivers/acpi/acpica/utdecode.c | 2 +- drivers/acpi/acpica/uteval.c | 2 +- drivers/acpi/acpica/utglobal.c | 2 +- drivers/acpi/acpica/uthex.c | 2 +- drivers/acpi/acpica/utids.c | 2 +- drivers/acpi/acpica/utinit.c | 2 +- drivers/acpi/acpica/utlock.c | 2 +- drivers/acpi/acpica/utobject.c | 2 +- drivers/acpi/acpica/utosi.c | 2 +- drivers/acpi/acpica/utpredef.c | 2 +- drivers/acpi/acpica/utprint.c | 2 +- drivers/acpi/acpica/uttrack.c | 2 +- drivers/acpi/acpica/utuuid.c | 2 +- drivers/acpi/acpica/utxface.c | 2 +- drivers/acpi/acpica/utxfinit.c | 2 +- include/acpi/acbuffer.h | 2 +- include/acpi/acconfig.h | 2 +- include/acpi/acexcep.h | 2 +- include/acpi/acnames.h | 2 +- include/acpi/acoutput.h | 2 +- include/acpi/acpi.h | 2 +- include/acpi/acpiosxf.h | 2 +- include/acpi/acpixf.h | 2 +- include/acpi/acrestyp.h | 2 +- include/acpi/actbl.h | 2 +- include/acpi/actbl1.h | 2 +- include/acpi/actbl2.h | 2 +- include/acpi/actbl3.h | 2 +- include/acpi/actypes.h | 2 +- include/acpi/acuuid.h | 2 +- include/acpi/platform/acenv.h | 2 +- include/acpi/platform/acenvex.h | 2 +- include/acpi/platform/acgcc.h | 2 +- include/acpi/platform/acgccex.h | 2 +- include/acpi/platform/acintel.h | 2 +- include/acpi/platform/aclinux.h | 2 +- include/acpi/platform/aclinuxex.h | 2 +- tools/power/acpi/common/cmfsize.c | 2 +- tools/power/acpi/common/getopt.c | 2 +- tools/power/acpi/os_specific/service_layers/oslinuxtbl.c | 2 +- tools/power/acpi/os_specific/service_layers/osunixdir.c | 2 +- tools/power/acpi/os_specific/service_layers/osunixmap.c | 2 +- tools/power/acpi/os_specific/service_layers/osunixxf.c | 2 +- tools/power/acpi/tools/acpidump/acpidump.h | 2 +- tools/power/acpi/tools/acpidump/apdump.c | 2 +- tools/power/acpi/tools/acpidump/apfiles.c | 2 +- tools/power/acpi/tools/acpidump/apmain.c | 2 +- 174 files changed, 175 insertions(+), 175 deletions(-) (limited to 'include') diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h index 5a9c2febc0fb..863ade9add6d 100644 --- a/drivers/acpi/acpica/acapps.h +++ b/drivers/acpi/acpica/acapps.h @@ -3,7 +3,7 @@ * * Module Name: acapps - common include for ACPI applications/tools * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ @@ -17,7 +17,7 @@ /* Common info for tool signons */ #define ACPICA_NAME "Intel ACPI Component Architecture" -#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2018 Intel Corporation" +#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2019 Intel Corporation" #if ACPI_MACHINE_WIDTH == 64 #define ACPI_WIDTH " (64-bit version)" diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h index 8bc935977d8e..54f81eac7ec9 100644 --- a/drivers/acpi/acpica/accommon.h +++ b/drivers/acpi/acpica/accommon.h @@ -3,7 +3,7 @@ * * Name: accommon.h - Common include files for generation of ACPICA source * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acconvert.h b/drivers/acpi/acpica/acconvert.h index 4ebe18826646..d5478cd4a857 100644 --- a/drivers/acpi/acpica/acconvert.h +++ b/drivers/acpi/acpica/acconvert.h @@ -3,7 +3,7 @@ * * Module Name: acapps - common include for ACPI applications/tools * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h index 57d9495e5933..3a339045b1bf 100644 --- a/drivers/acpi/acpica/acdebug.h +++ b/drivers/acpi/acpica/acdebug.h @@ -3,7 +3,7 @@ * * Name: acdebug.h - ACPI/AML debugger * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h index e577f3a40e6a..82f81501566b 100644 --- a/drivers/acpi/acpica/acdispat.h +++ b/drivers/acpi/acpica/acdispat.h @@ -3,7 +3,7 @@ * * Name: acdispat.h - dispatcher (parser to interpreter interface) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index b412aa909907..831660179662 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -3,7 +3,7 @@ * * Name: acevents.h - Event subcomponent prototypes and defines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 7a0aeb70ec34..d056a1845613 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -3,7 +3,7 @@ * * Name: acglobal.h - Declarations for global variables * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h index ef99e2fc37f8..bcf8f7501db7 100644 --- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -3,7 +3,7 @@ * * Name: achware.h -- hardware specific interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h index c5b2be0b6613..20706adbc148 100644 --- a/drivers/acpi/acpica/acinterp.h +++ b/drivers/acpi/acpica/acinterp.h @@ -3,7 +3,7 @@ * * Name: acinterp.h - Interpreter subcomponent prototypes and defines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index 99b0da899109..18ec6627d674 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -3,7 +3,7 @@ * * Name: aclocal.h - Internal data types used across the ACPI subsystem * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h index de52cd6e868a..99131cd4e389 100644 --- a/drivers/acpi/acpica/acmacros.h +++ b/drivers/acpi/acpica/acmacros.h @@ -3,7 +3,7 @@ * * Name: acmacros.h - C macros for the entire subsystem. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h index 9bd25f36c608..39812fc4386a 100644 --- a/drivers/acpi/acpica/acnamesp.h +++ b/drivers/acpi/acpica/acnamesp.h @@ -3,7 +3,7 @@ * * Name: acnamesp.h - Namespace subcomponent prototypes and defines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h index ac992b6ebce9..0edf8fca7567 100644 --- a/drivers/acpi/acpica/acobject.h +++ b/drivers/acpi/acpica/acobject.h @@ -3,7 +3,7 @@ * * Name: acobject.h - Definition of union acpi_operand_object (Internal object only) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acopcode.h b/drivers/acpi/acpica/acopcode.h index 818eba413614..9d78134428e3 100644 --- a/drivers/acpi/acpica/acopcode.h +++ b/drivers/acpi/acpica/acopcode.h @@ -3,7 +3,7 @@ * * Name: acopcode.h - AML opcode information for the AML parser and interpreter * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h index ab48196ae55e..6e32c97cba6c 100644 --- a/drivers/acpi/acpica/acparser.h +++ b/drivers/acpi/acpica/acparser.h @@ -3,7 +3,7 @@ * * Module Name: acparser.h - AML Parser subcomponent prototypes and defines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index d31bb04facb6..cc96b40032b3 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -3,7 +3,7 @@ * * Name: acpredef - Information table for ACPI predefined methods and objects * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acresrc.h b/drivers/acpi/acpica/acresrc.h index 59ae8b1a6e40..422cd8f2b92e 100644 --- a/drivers/acpi/acpica/acresrc.h +++ b/drivers/acpi/acpica/acresrc.h @@ -3,7 +3,7 @@ * * Name: acresrc.h - Resource Manager function prototypes * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h index 14be32961b4c..8a4e6b4aaf2c 100644 --- a/drivers/acpi/acpica/acstruct.h +++ b/drivers/acpi/acpica/acstruct.h @@ -3,7 +3,7 @@ * * Name: acstruct.h - Internal structs * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h index 12fac33ce77e..dfbf1dbd4033 100644 --- a/drivers/acpi/acpica/actables.h +++ b/drivers/acpi/acpica/actables.h @@ -3,7 +3,7 @@ * * Name: actables.h - ACPI table management * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h index 3374d41582b5..9022537567e9 100644 --- a/drivers/acpi/acpica/acutils.h +++ b/drivers/acpi/acpica/acutils.h @@ -3,7 +3,7 @@ * * Name: acutils.h -- prototypes for the common (subsystem-wide) procedures * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h index 6c05355447c1..49e412edd7c6 100644 --- a/drivers/acpi/acpica/amlcode.h +++ b/drivers/acpi/acpica/amlcode.h @@ -5,7 +5,7 @@ * Declarations and definitions contained herein are derived * directly from the ACPI specification. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h index cdb590176e9d..7c3bd4ab60fc 100644 --- a/drivers/acpi/acpica/amlresrc.h +++ b/drivers/acpi/acpica/amlresrc.h @@ -3,7 +3,7 @@ * * Module Name: amlresrc.h - AML resource descriptors * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dbhistry.c b/drivers/acpi/acpica/dbhistry.c index b0b9a26c7db5..7809bd94a18d 100644 --- a/drivers/acpi/acpica/dbhistry.c +++ b/drivers/acpi/acpica/dbhistry.c @@ -3,7 +3,7 @@ * * Module Name: dbhistry - debugger HISTORY command * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c index 6b15625e8099..85b34d02233e 100644 --- a/drivers/acpi/acpica/dsargs.c +++ b/drivers/acpi/acpica/dsargs.c @@ -4,7 +4,7 @@ * Module Name: dsargs - Support for execution of dynamic arguments for static * objects (regions, fields, buffer fields, etc.) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c index 0da96268deb5..4847f89c678c 100644 --- a/drivers/acpi/acpica/dscontrol.c +++ b/drivers/acpi/acpica/dscontrol.c @@ -4,7 +4,7 @@ * Module Name: dscontrol - Support for execution control opcodes - * if/else/while/return * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsdebug.c b/drivers/acpi/acpica/dsdebug.c index 9d33f0bb2885..0d3e1ced1f57 100644 --- a/drivers/acpi/acpica/dsdebug.c +++ b/drivers/acpi/acpica/dsdebug.c @@ -3,7 +3,7 @@ * * Module Name: dsdebug - Parser/Interpreter interface - debugging * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index 30fe89545d6a..d51216c9d891 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -3,7 +3,7 @@ * * Module Name: dsfield - Dispatcher field routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c index e8de1b0ce2f5..a4a24ffe5fae 100644 --- a/drivers/acpi/acpica/dsinit.c +++ b/drivers/acpi/acpica/dsinit.c @@ -3,7 +3,7 @@ * * Module Name: dsinit - Object initialization namespace walk * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index c1a4d02fafd5..f59b4d944f7f 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -3,7 +3,7 @@ * * Module Name: dsmethod - Parser/Interpreter interface - control method parsing * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c index 6a9cc613adaa..179129a2deb1 100644 --- a/drivers/acpi/acpica/dsobject.c +++ b/drivers/acpi/acpica/dsobject.c @@ -3,7 +3,7 @@ * * Module Name: dsobject - Dispatcher object management routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c index a0b821031063..cab14713e591 100644 --- a/drivers/acpi/acpica/dsopcode.c +++ b/drivers/acpi/acpica/dsopcode.c @@ -3,7 +3,7 @@ * * Module Name: dsopcode - Dispatcher support for regions and fields * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dspkginit.c b/drivers/acpi/acpica/dspkginit.c index 584853385268..997faa10f615 100644 --- a/drivers/acpi/acpica/dspkginit.c +++ b/drivers/acpi/acpica/dspkginit.c @@ -3,7 +3,7 @@ * * Module Name: dspkginit - Completion of deferred package initialization * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c index 1504b93cc5f4..d75aae304595 100644 --- a/drivers/acpi/acpica/dswexec.c +++ b/drivers/acpi/acpica/dswexec.c @@ -4,7 +4,7 @@ * Module Name: dswexec - Dispatcher method execution callbacks; * dispatch to interpreter. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c index e2ef09643d50..c88fd31208a5 100644 --- a/drivers/acpi/acpica/dswload.c +++ b/drivers/acpi/acpica/dswload.c @@ -3,7 +3,7 @@ * * Module Name: dswload - Dispatcher first pass namespace load callbacks * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c index 9a309f5c4de8..98cdc24c640f 100644 --- a/drivers/acpi/acpica/dswload2.c +++ b/drivers/acpi/acpica/dswload2.c @@ -3,7 +3,7 @@ * * Module Name: dswload2 - Dispatcher second pass namespace load callbacks * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c index 7592176a8fa2..39acf7b286da 100644 --- a/drivers/acpi/acpica/dswscope.c +++ b/drivers/acpi/acpica/dswscope.c @@ -3,7 +3,7 @@ * * Module Name: dswscope - Scope stack manipulation * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c index 4c1ec202d5ab..de79f835a373 100644 --- a/drivers/acpi/acpica/dswstate.c +++ b/drivers/acpi/acpica/dswstate.c @@ -3,7 +3,7 @@ * * Module Name: dswstate - Dispatcher parse tree walk management routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c index b3d07cc14d75..9e2f5a05c066 100644 --- a/drivers/acpi/acpica/evevent.c +++ b/drivers/acpi/acpica/evevent.c @@ -3,7 +3,7 @@ * * Module Name: evevent - Fixed Event handling and dispatch * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c index 1b8a662a14a9..5c77bee5d31f 100644 --- a/drivers/acpi/acpica/evglock.c +++ b/drivers/acpi/acpica/evglock.c @@ -3,7 +3,7 @@ * * Module Name: evglock - Global Lock support * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c index e10fec99a182..a5d435849d0d 100644 --- a/drivers/acpi/acpica/evgpe.c +++ b/drivers/acpi/acpica/evgpe.c @@ -3,7 +3,7 @@ * * Module Name: evgpe - General Purpose Event handling and dispatch * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c index b253063b09d3..328d1d6123ad 100644 --- a/drivers/acpi/acpica/evgpeblk.c +++ b/drivers/acpi/acpica/evgpeblk.c @@ -3,7 +3,7 @@ * * Module Name: evgpeblk - GPE block creation and initialization. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c index 1f686750bb1a..c92d2f6ebe01 100644 --- a/drivers/acpi/acpica/evgpeinit.c +++ b/drivers/acpi/acpica/evgpeinit.c @@ -3,7 +3,7 @@ * * Module Name: evgpeinit - System GPE initialization and update * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c index 0fb6c70f44ed..917892227e09 100644 --- a/drivers/acpi/acpica/evgpeutil.c +++ b/drivers/acpi/acpica/evgpeutil.c @@ -3,7 +3,7 @@ * * Module Name: evgpeutil - GPE utilities * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evhandler.c b/drivers/acpi/acpica/evhandler.c index 4ed1e67db6be..3ef4e27995f0 100644 --- a/drivers/acpi/acpica/evhandler.c +++ b/drivers/acpi/acpica/evhandler.c @@ -3,7 +3,7 @@ * * Module Name: evhandler - Support for Address Space handlers * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c index baadd635b5af..d45f7639f7ee 100644 --- a/drivers/acpi/acpica/evmisc.c +++ b/drivers/acpi/acpica/evmisc.c @@ -3,7 +3,7 @@ * * Module Name: evmisc - Miscellaneous event manager support functions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 49decca4e08f..b683b3ad6baa 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -3,7 +3,7 @@ * * Module Name: evregion - Operation Region support * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c index 17df5dacd43c..163dd4a142eb 100644 --- a/drivers/acpi/acpica/evrgnini.c +++ b/drivers/acpi/acpica/evrgnini.c @@ -3,7 +3,7 @@ * * Module Name: evrgnini- ACPI address_space (op_region) init * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c index febc332b00ac..3df00eb6621b 100644 --- a/drivers/acpi/acpica/evxface.c +++ b/drivers/acpi/acpica/evxface.c @@ -3,7 +3,7 @@ * * Module Name: evxface - External interfaces for ACPI events * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c index 970e940bdb17..e528fe56b755 100644 --- a/drivers/acpi/acpica/evxfevnt.c +++ b/drivers/acpi/acpica/evxfevnt.c @@ -3,7 +3,7 @@ * * Module Name: evxfevnt - External Interfaces, ACPI event disable/enable * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c index b2d5f66cc1b0..fb1d215dd288 100644 --- a/drivers/acpi/acpica/evxfgpe.c +++ b/drivers/acpi/acpica/evxfgpe.c @@ -3,7 +3,7 @@ * * Module Name: evxfgpe - External Interfaces for General Purpose Events (GPEs) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 3b3a25d9f0e6..47265b073e6f 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -4,7 +4,7 @@ * Module Name: evxfregn - External Interfaces, ACPI Operation Regions and * Address Spaces. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exconcat.c b/drivers/acpi/acpica/exconcat.c index 5e75c510ca25..c7af07566b7b 100644 --- a/drivers/acpi/acpica/exconcat.c +++ b/drivers/acpi/acpica/exconcat.c @@ -3,7 +3,7 @@ * * Module Name: exconcat - Concatenate-type AML operators * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c index 2373a7492151..587aeeeb5070 100644 --- a/drivers/acpi/acpica/exconfig.c +++ b/drivers/acpi/acpica/exconfig.c @@ -3,7 +3,7 @@ * * Module Name: exconfig - Namespace reconfiguration (Load/Unload opcodes) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c index 1a70b80cc406..f5675f1b1928 100644 --- a/drivers/acpi/acpica/exconvrt.c +++ b/drivers/acpi/acpica/exconvrt.c @@ -3,7 +3,7 @@ * * Module Name: exconvrt - Object conversion routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c index 3304c6b1e8a7..f376fc00064e 100644 --- a/drivers/acpi/acpica/excreate.c +++ b/drivers/acpi/acpica/excreate.c @@ -3,7 +3,7 @@ * * Module Name: excreate - Named object creation * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c index ebbc244039ab..b1aeec8cac55 100644 --- a/drivers/acpi/acpica/exdebug.c +++ b/drivers/acpi/acpica/exdebug.c @@ -3,7 +3,7 @@ * * Module Name: exdebug - Support for stores to the AML Debug Object * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c index f71dfa1e90e1..6526b2deeaad 100644 --- a/drivers/acpi/acpica/exdump.c +++ b/drivers/acpi/acpica/exdump.c @@ -3,7 +3,7 @@ * * Module Name: exdump - Interpreter debug output routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c index e5798f15793a..7dcdde094582 100644 --- a/drivers/acpi/acpica/exfield.c +++ b/drivers/acpi/acpica/exfield.c @@ -3,7 +3,7 @@ * * Module Name: exfield - AML execution - field_unit read/write * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c index 516994133128..95a0dcb4f7b9 100644 --- a/drivers/acpi/acpica/exfldio.c +++ b/drivers/acpi/acpica/exfldio.c @@ -3,7 +3,7 @@ * * Module Name: exfldio - Aml Field I/O * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c index d91f15cdf3ae..60e854965af9 100644 --- a/drivers/acpi/acpica/exmisc.c +++ b/drivers/acpi/acpica/exmisc.c @@ -3,7 +3,7 @@ * * Module Name: exmisc - ACPI AML (p-code) execution - specific opcodes * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c index c06079774bad..775cd62af5b3 100644 --- a/drivers/acpi/acpica/exmutex.c +++ b/drivers/acpi/acpica/exmutex.c @@ -3,7 +3,7 @@ * * Module Name: exmutex - ASL Mutex Acquire/Release functions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c index 7eed79dcda83..bd68d66e89f0 100644 --- a/drivers/acpi/acpica/exnames.c +++ b/drivers/acpi/acpica/exnames.c @@ -3,7 +3,7 @@ * * Module Name: exnames - interpreter/scanner name load/execute * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c index ba9fbae0cf91..06e35ea09823 100644 --- a/drivers/acpi/acpica/exoparg1.c +++ b/drivers/acpi/acpica/exoparg1.c @@ -3,7 +3,7 @@ * * Module Name: exoparg1 - AML execution - opcodes with 1 argument * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c index e9509b1c9a3a..5e4a31a11df4 100644 --- a/drivers/acpi/acpica/exoparg2.c +++ b/drivers/acpi/acpica/exoparg2.c @@ -3,7 +3,7 @@ * * Module Name: exoparg2 - AML execution - opcodes with 2 arguments * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c index 764fa6f924ff..a4ebce417930 100644 --- a/drivers/acpi/acpica/exoparg3.c +++ b/drivers/acpi/acpica/exoparg3.c @@ -3,7 +3,7 @@ * * Module Name: exoparg3 - AML execution - opcodes with 3 arguments * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c index 3941525f3d6b..31385a0b2dab 100644 --- a/drivers/acpi/acpica/exoparg6.c +++ b/drivers/acpi/acpica/exoparg6.c @@ -3,7 +3,7 @@ * * Module Name: exoparg6 - AML execution - opcodes with 6 arguments * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 738f3c732363..728d752f7adc 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -3,7 +3,7 @@ * * Module Name: exprep - ACPI AML field prep utilities * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c index 2c58f5e00b1a..c08521194b29 100644 --- a/drivers/acpi/acpica/exregion.c +++ b/drivers/acpi/acpica/exregion.c @@ -3,7 +3,7 @@ * * Module Name: exregion - ACPI default op_region (address space) handlers * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c index ea4b0fe674f1..b223d01e6bf8 100644 --- a/drivers/acpi/acpica/exresnte.c +++ b/drivers/acpi/acpica/exresnte.c @@ -3,7 +3,7 @@ * * Module Name: exresnte - AML Interpreter object resolution * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c index 5e42c7de46fa..36da5c0ef69c 100644 --- a/drivers/acpi/acpica/exresolv.c +++ b/drivers/acpi/acpica/exresolv.c @@ -3,7 +3,7 @@ * * Module Name: exresolv - AML Interpreter object resolution * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c index d94190bc5985..bdfe4d33b483 100644 --- a/drivers/acpi/acpica/exresop.c +++ b/drivers/acpi/acpica/exresop.c @@ -3,7 +3,7 @@ * * Module Name: exresop - AML Interpreter operand/object resolution * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exserial.c b/drivers/acpi/acpica/exserial.c index ec61553c4483..89bc0a2d8163 100644 --- a/drivers/acpi/acpica/exserial.c +++ b/drivers/acpi/acpica/exserial.c @@ -3,7 +3,7 @@ * * Module Name: exserial - field_unit support for serial address spaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c index 75d5665b7b2f..7f3c3571c292 100644 --- a/drivers/acpi/acpica/exstore.c +++ b/drivers/acpi/acpica/exstore.c @@ -3,7 +3,7 @@ * * Module Name: exstore - AML Interpreter object store support * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c index 31cba19652ed..4e43c8277f07 100644 --- a/drivers/acpi/acpica/exstoren.c +++ b/drivers/acpi/acpica/exstoren.c @@ -4,7 +4,7 @@ * Module Name: exstoren - AML Interpreter object store support, * Store to Node (namespace object) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c index 4cd82ff509bc..dc9e2b1c1ad9 100644 --- a/drivers/acpi/acpica/exstorob.c +++ b/drivers/acpi/acpica/exstorob.c @@ -3,7 +3,7 @@ * * Module Name: exstorob - AML object store support, store to object * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c index ec8b5a22cad4..a538f7799b78 100644 --- a/drivers/acpi/acpica/exsystem.c +++ b/drivers/acpi/acpica/exsystem.c @@ -3,7 +3,7 @@ * * Module Name: exsystem - Interface to OS services * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/extrace.c b/drivers/acpi/acpica/extrace.c index 9bd3fa56b51a..db7f93ca539f 100644 --- a/drivers/acpi/acpica/extrace.c +++ b/drivers/acpi/acpica/extrace.c @@ -3,7 +3,7 @@ * * Module Name: extrace - Support for interpreter execution tracing * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c index bd22e27adf9b..a1f26b0ad449 100644 --- a/drivers/acpi/acpica/exutils.c +++ b/drivers/acpi/acpica/exutils.c @@ -3,7 +3,7 @@ * * Module Name: exutils - interpreter/scanner utilities * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c index 525e6ea5c114..926f7e080f22 100644 --- a/drivers/acpi/acpica/hwacpi.c +++ b/drivers/acpi/acpica/hwacpi.c @@ -3,7 +3,7 @@ * * Module Name: hwacpi - ACPI Hardware Initialization/Mode Interface * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c index e0ad3f11142e..dee3affaca49 100644 --- a/drivers/acpi/acpica/hwesleep.c +++ b/drivers/acpi/acpica/hwesleep.c @@ -4,7 +4,7 @@ * Name: hwesleep.c - ACPI Hardware Sleep/Wake Support functions for the * extended FADT-V5 sleep registers. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c index 2d2e2e41a685..565bd3f29f31 100644 --- a/drivers/acpi/acpica/hwgpe.c +++ b/drivers/acpi/acpica/hwgpe.c @@ -3,7 +3,7 @@ * * Module Name: hwgpe - Low level GPE enable/disable/clear functions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c index d8b8fc2ff563..b62db8ec446f 100644 --- a/drivers/acpi/acpica/hwsleep.c +++ b/drivers/acpi/acpica/hwsleep.c @@ -4,7 +4,7 @@ * Name: hwsleep.c - ACPI Hardware Sleep/Wake Support functions for the * original/legacy sleep/PM registers. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c index 5d5e27146fc2..2fb9f75d71c5 100644 --- a/drivers/acpi/acpica/hwtimer.c +++ b/drivers/acpi/acpica/hwtimer.c @@ -3,7 +3,7 @@ * * Name: hwtimer.c - ACPI Power Management Timer Interface * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c index 24f9b61aa404..cd576153257c 100644 --- a/drivers/acpi/acpica/hwvalid.c +++ b/drivers/acpi/acpica/hwvalid.c @@ -3,7 +3,7 @@ * * Module Name: hwvalid - I/O request validation * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c index 6e39a771a56e..c4fd97104024 100644 --- a/drivers/acpi/acpica/hwxface.c +++ b/drivers/acpi/acpica/hwxface.c @@ -3,7 +3,7 @@ * * Module Name: hwxface - Public ACPICA hardware interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c index 3f22f7dd4556..669fa73dd794 100644 --- a/drivers/acpi/acpica/hwxfsleep.c +++ b/drivers/acpi/acpica/hwxfsleep.c @@ -3,7 +3,7 @@ * * Name: hwxfsleep.c - ACPI Hardware Sleep/Wake External Interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsarguments.c b/drivers/acpi/acpica/nsarguments.c index b9ede797b654..0e97ed38973f 100644 --- a/drivers/acpi/acpica/nsarguments.c +++ b/drivers/acpi/acpica/nsarguments.c @@ -3,7 +3,7 @@ * * Module Name: nsarguments - Validation of args for ACPI predefined methods * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c index f9527346b0f7..14cbf63f1991 100644 --- a/drivers/acpi/acpica/nsconvert.c +++ b/drivers/acpi/acpica/nsconvert.c @@ -4,7 +4,7 @@ * Module Name: nsconvert - Object conversions for objects returned by * predefined methods * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c index 90ccffcd770b..15070bd0c28a 100644 --- a/drivers/acpi/acpica/nsdump.c +++ b/drivers/acpi/acpica/nsdump.c @@ -3,7 +3,7 @@ * * Module Name: nsdump - table dumping routines for debug * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c index 2b291c500fb0..73e5c83c8c9f 100644 --- a/drivers/acpi/acpica/nsdumpdv.c +++ b/drivers/acpi/acpica/nsdumpdv.c @@ -3,7 +3,7 @@ * * Module Name: nsdump - table dumping routines for debug * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c index d77257d1c827..19fb8dda870f 100644 --- a/drivers/acpi/acpica/nsinit.c +++ b/drivers/acpi/acpica/nsinit.c @@ -3,7 +3,7 @@ * * Module Name: nsinit - namespace initialization * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c index 04bc73e82aed..6b90aa89f942 100644 --- a/drivers/acpi/acpica/nsload.c +++ b/drivers/acpi/acpica/nsload.c @@ -3,7 +3,7 @@ * * Module Name: nsload - namespace loading/expanding/contracting procedures * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c index 488ff39d86f7..bfa408f7fd39 100644 --- a/drivers/acpi/acpica/nsparse.c +++ b/drivers/acpi/acpica/nsparse.c @@ -3,7 +3,7 @@ * * Module Name: nsparse - namespace interface to AML parser * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c index 29c68b15a64f..2f9d93122d0c 100644 --- a/drivers/acpi/acpica/nspredef.c +++ b/drivers/acpi/acpica/nspredef.c @@ -3,7 +3,7 @@ * * Module Name: nspredef - Validation of ACPI predefined methods and objects * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c index 51523473e7fe..9a80e3b23496 100644 --- a/drivers/acpi/acpica/nsprepkg.c +++ b/drivers/acpi/acpica/nsprepkg.c @@ -3,7 +3,7 @@ * * Module Name: nsprepkg - Validation of package objects for predefined names * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c index ff2ab8fbec38..0aacfa48e20d 100644 --- a/drivers/acpi/acpica/nsrepair.c +++ b/drivers/acpi/acpica/nsrepair.c @@ -3,7 +3,7 @@ * * Module Name: nsrepair - Repair for objects returned by predefined methods * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c index a3bd6280882c..d5804a6d1d65 100644 --- a/drivers/acpi/acpica/nsrepair2.c +++ b/drivers/acpi/acpica/nsrepair2.c @@ -4,7 +4,7 @@ * Module Name: nsrepair2 - Repair for objects returned by specific * predefined methods * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c index a2bf4b2caa6c..0c5662c4168c 100644 --- a/drivers/acpi/acpica/nsutils.c +++ b/drivers/acpi/acpica/nsutils.c @@ -4,7 +4,7 @@ * Module Name: nsutils - Utilities for accessing ACPI namespace, accessing * parents and siblings and Scope manipulation * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c index e9a061da9bb2..ceea6af79d12 100644 --- a/drivers/acpi/acpica/nswalk.c +++ b/drivers/acpi/acpica/nswalk.c @@ -3,7 +3,7 @@ * * Module Name: nswalk - Functions for walking the ACPI namespace * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c index b2915c9cceaf..de2d3135d6a9 100644 --- a/drivers/acpi/acpica/nsxfname.c +++ b/drivers/acpi/acpica/nsxfname.c @@ -4,7 +4,7 @@ * Module Name: nsxfname - Public interfaces to the ACPI subsystem * ACPI Namespace oriented interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c index 176d28d60125..9d9d442cd999 100644 --- a/drivers/acpi/acpica/psargs.c +++ b/drivers/acpi/acpica/psargs.c @@ -3,7 +3,7 @@ * * Module Name: psargs - Parse AML opcode arguments * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c index e00d1af6fa80..4796f17805ac 100644 --- a/drivers/acpi/acpica/psloop.c +++ b/drivers/acpi/acpica/psloop.c @@ -3,7 +3,7 @@ * * Module Name: psloop - Main AML parse loop * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c index e1fd819a2955..98e5c7400e54 100644 --- a/drivers/acpi/acpica/psobject.c +++ b/drivers/acpi/acpica/psobject.c @@ -3,7 +3,7 @@ * * Module Name: psobject - Support for parse objects * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c index 8d7dc98bad17..43775c5ce17c 100644 --- a/drivers/acpi/acpica/psopcode.c +++ b/drivers/acpi/acpica/psopcode.c @@ -3,7 +3,7 @@ * * Module Name: psopcode - Parser/Interpreter opcode information table * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c index f310954eea59..15e7563829f1 100644 --- a/drivers/acpi/acpica/psopinfo.c +++ b/drivers/acpi/acpica/psopinfo.c @@ -3,7 +3,7 @@ * * Module Name: psopinfo - AML opcode information functions and dispatch tables * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c index 65603473b6cb..3f381ffd9581 100644 --- a/drivers/acpi/acpica/psparse.c +++ b/drivers/acpi/acpica/psparse.c @@ -3,7 +3,7 @@ * * Module Name: psparse - Parser top level AML parse routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psscope.c b/drivers/acpi/acpica/psscope.c index 00c67bc249aa..f153ca804740 100644 --- a/drivers/acpi/acpica/psscope.c +++ b/drivers/acpi/acpica/psscope.c @@ -3,7 +3,7 @@ * * Module Name: psscope - Parser scope stack management routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/pstree.c b/drivers/acpi/acpica/pstree.c index 64a8329a17f1..22d8a2becdd0 100644 --- a/drivers/acpi/acpica/pstree.c +++ b/drivers/acpi/acpica/pstree.c @@ -3,7 +3,7 @@ * * Module Name: pstree - Parser op tree manipulation/traversal/search * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c index ef8a5805a836..2512f584fa3c 100644 --- a/drivers/acpi/acpica/psutils.c +++ b/drivers/acpi/acpica/psutils.c @@ -3,7 +3,7 @@ * * Module Name: psutils - Parser miscellaneous utilities (Parser only) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/pswalk.c b/drivers/acpi/acpica/pswalk.c index bd6af8c87d48..cf91841297c2 100644 --- a/drivers/acpi/acpica/pswalk.c +++ b/drivers/acpi/acpica/pswalk.c @@ -3,7 +3,7 @@ * * Module Name: pswalk - Parser routines to walk parsed op tree(s) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c index 5743b22399a0..ee2ee2c858f2 100644 --- a/drivers/acpi/acpica/psxface.c +++ b/drivers/acpi/acpica/psxface.c @@ -3,7 +3,7 @@ * * Module Name: psxface - Parser external interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c index 862149c8a208..0cecd0039acf 100644 --- a/drivers/acpi/acpica/tbdata.c +++ b/drivers/acpi/acpica/tbdata.c @@ -3,7 +3,7 @@ * * Module Name: tbdata - Table manager data structure functions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c index 99d325a51816..2c67351d5a79 100644 --- a/drivers/acpi/acpica/tbfadt.c +++ b/drivers/acpi/acpica/tbfadt.c @@ -3,7 +3,7 @@ * * Module Name: tbfadt - FADT table utilities * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c index f00694b1d000..951bd8e1c50a 100644 --- a/drivers/acpi/acpica/tbfind.c +++ b/drivers/acpi/acpica/tbfind.c @@ -3,7 +3,7 @@ * * Module Name: tbfind - find table * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index 5f8e7b561c90..be6642bf6366 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -3,7 +3,7 @@ * * Module Name: tbinstal - ACPI table installation and removal * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c index e303418a895b..9b5df95d881b 100644 --- a/drivers/acpi/acpica/tbprint.c +++ b/drivers/acpi/acpica/tbprint.c @@ -3,7 +3,7 @@ * * Module Name: tbprint - Table output utilities * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index b526096560b5..2469e01310e2 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -3,7 +3,7 @@ * * Module Name: tbutils - ACPI Table utilities * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c index e4d0dc8948cd..593c20c20104 100644 --- a/drivers/acpi/acpica/tbxface.c +++ b/drivers/acpi/acpica/tbxface.c @@ -3,7 +3,7 @@ * * Module Name: tbxface - ACPI table-oriented external interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c index 9011297552af..2c573fcc8c70 100644 --- a/drivers/acpi/acpica/tbxfload.c +++ b/drivers/acpi/acpica/tbxfload.c @@ -3,7 +3,7 @@ * * Module Name: tbxfload - Table load/unload external interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c index 483d0ce5180a..e2859d09ca2e 100644 --- a/drivers/acpi/acpica/tbxfroot.c +++ b/drivers/acpi/acpica/tbxfroot.c @@ -3,7 +3,7 @@ * * Module Name: tbxfroot - Find the root ACPI table (RSDT) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c index dbabe680ff58..bb260376bd59 100644 --- a/drivers/acpi/acpica/utaddress.c +++ b/drivers/acpi/acpica/utaddress.c @@ -3,7 +3,7 @@ * * Module Name: utaddress - op_region address range check * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c index 8cbcd7d6bd5e..d64da4d9e8d0 100644 --- a/drivers/acpi/acpica/utalloc.c +++ b/drivers/acpi/acpica/utalloc.c @@ -3,7 +3,7 @@ * * Module Name: utalloc - local memory allocation routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utascii.c b/drivers/acpi/acpica/utascii.c index 04ff61e284f5..79d7426fd7bf 100644 --- a/drivers/acpi/acpica/utascii.c +++ b/drivers/acpi/acpica/utascii.c @@ -3,7 +3,7 @@ * * Module Name: utascii - Utility ascii functions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c index fffa6f5ae59e..61db9967ebe4 100644 --- a/drivers/acpi/acpica/utbuffer.c +++ b/drivers/acpi/acpica/utbuffer.c @@ -3,7 +3,7 @@ * * Module Name: utbuffer - Buffer dump routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c index 97d6ec174c28..8533fce7fa93 100644 --- a/drivers/acpi/acpica/utcache.c +++ b/drivers/acpi/acpica/utcache.c @@ -3,7 +3,7 @@ * * Module Name: utcache - local cache allocation routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c index a872ed7879ca..1fb8327f3c3b 100644 --- a/drivers/acpi/acpica/utcopy.c +++ b/drivers/acpi/acpica/utcopy.c @@ -3,7 +3,7 @@ * * Module Name: utcopy - Internal to external object translation utilities * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c index aabdc25effd9..01b1b36c8a8e 100644 --- a/drivers/acpi/acpica/utdebug.c +++ b/drivers/acpi/acpica/utdebug.c @@ -3,7 +3,7 @@ * * Module Name: utdebug - Debug print/trace routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c index d0a375c3f4e2..6be69c28c34e 100644 --- a/drivers/acpi/acpica/utdecode.c +++ b/drivers/acpi/acpica/utdecode.c @@ -3,7 +3,7 @@ * * Module Name: utdecode - Utility decoding routines (value-to-string) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c index c56ae6e058d5..558a9f3b0678 100644 --- a/drivers/acpi/acpica/uteval.c +++ b/drivers/acpi/acpica/uteval.c @@ -3,7 +3,7 @@ * * Module Name: uteval - Object evaluation * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c index f8c5b49344df..b0622ec4bb85 100644 --- a/drivers/acpi/acpica/utglobal.c +++ b/drivers/acpi/acpica/utglobal.c @@ -3,7 +3,7 @@ * * Module Name: utglobal - Global variables for the ACPI subsystem * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c index 3d63a9e8da4f..b6da135d5f41 100644 --- a/drivers/acpi/acpica/uthex.c +++ b/drivers/acpi/acpica/uthex.c @@ -3,7 +3,7 @@ * * Module Name: uthex -- Hex/ASCII support functions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c index 70e6bf1107a1..e805abdd95b8 100644 --- a/drivers/acpi/acpica/utids.c +++ b/drivers/acpi/acpica/utids.c @@ -3,7 +3,7 @@ * * Module Name: utids - support for device Ids - HID, UID, CID, SUB, CLS * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c index 0646ed62b351..bc124591320e 100644 --- a/drivers/acpi/acpica/utinit.c +++ b/drivers/acpi/acpica/utinit.c @@ -3,7 +3,7 @@ * * Module Name: utinit - Common ACPI subsystem initialization * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utlock.c b/drivers/acpi/acpica/utlock.c index d61e01bd01a3..8b4ff11d617a 100644 --- a/drivers/acpi/acpica/utlock.c +++ b/drivers/acpi/acpica/utlock.c @@ -3,7 +3,7 @@ * * Module Name: utlock - Reader/Writer lock interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c index ae6d8cc18cec..eee97a902696 100644 --- a/drivers/acpi/acpica/utobject.c +++ b/drivers/acpi/acpica/utobject.c @@ -3,7 +3,7 @@ * * Module Name: utobject - ACPI object create/delete/size/cache routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c index 902a47463abf..688c61a90725 100644 --- a/drivers/acpi/acpica/utosi.c +++ b/drivers/acpi/acpica/utosi.c @@ -3,7 +3,7 @@ * * Module Name: utosi - Support for the _OSI predefined control method * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c index 65ca9807c2a8..a9f08f43c685 100644 --- a/drivers/acpi/acpica/utpredef.c +++ b/drivers/acpi/acpica/utpredef.c @@ -3,7 +3,7 @@ * * Module Name: utpredef - support functions for predefined names * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c index a98c334c3bb7..5839f2fa7400 100644 --- a/drivers/acpi/acpica/utprint.c +++ b/drivers/acpi/acpica/utprint.c @@ -3,7 +3,7 @@ * * Module Name: utprint - Formatted printing routines * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c index f6b55e2482ee..8052f7ef5025 100644 --- a/drivers/acpi/acpica/uttrack.c +++ b/drivers/acpi/acpica/uttrack.c @@ -3,7 +3,7 @@ * * Module Name: uttrack - Memory allocation tracking routines (debug only) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c index 59ae118092a3..0a7cf8007643 100644 --- a/drivers/acpi/acpica/utuuid.c +++ b/drivers/acpi/acpica/utuuid.c @@ -3,7 +3,7 @@ * * Module Name: utuuid -- UUID support functions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c index d2d6cc065181..f497c4b30e65 100644 --- a/drivers/acpi/acpica/utxface.c +++ b/drivers/acpi/acpica/utxface.c @@ -3,7 +3,7 @@ * * Module Name: utxface - External interfaces, miscellaneous utility functions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c index e3c60f57c9f0..9f3b1e3a09de 100644 --- a/drivers/acpi/acpica/utxfinit.c +++ b/drivers/acpi/acpica/utxfinit.c @@ -3,7 +3,7 @@ * * Module Name: utxfinit - External interfaces for ACPICA initialization * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h index 6488d572739c..c2acd29f973d 100644 --- a/include/acpi/acbuffer.h +++ b/include/acpi/acbuffer.h @@ -3,7 +3,7 @@ * * Name: acbuffer.h - Support for buffers returned by ACPI predefined names * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index 53c088247d36..298e15100789 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -3,7 +3,7 @@ * * Name: acconfig.h - Global configuration constants * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index 09f46050961f..6b4fed5b9d11 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -3,7 +3,7 @@ * * Name: acexcep.h - Exception codes returned by the ACPI subsystem * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h index 6f69a4f638f8..8b3eae96706a 100644 --- a/include/acpi/acnames.h +++ b/include/acpi/acnames.h @@ -3,7 +3,7 @@ * * Name: acnames.h - Global names and strings * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index 93a280703318..30b1ae53689f 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -3,7 +3,7 @@ * * Name: acoutput.h -- debug output * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpi.h b/include/acpi/acpi.h index ccdc5981bc91..bc7d39ecf574 100644 --- a/include/acpi/acpi.h +++ b/include/acpi/acpi.h @@ -3,7 +3,7 @@ * * Name: acpi.h - Master public include file used to interface to ACPICA * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index eb1f21af7556..1b59fb61f67d 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -5,7 +5,7 @@ * interfaces must be implemented by OSL to interface the * ACPI components to the host operating system. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index f0adda015fc7..3a3febc9b979 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -3,7 +3,7 @@ * * Name: acpixf.h - External interfaces to the ACPI subsystem * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h index 724ad5f29a16..000145ded0ec 100644 --- a/include/acpi/acrestyp.h +++ b/include/acpi/acrestyp.h @@ -3,7 +3,7 @@ * * Name: acrestyp.h - Defines, types, and structures for resource descriptors * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index 0a977eca0a74..65cc9cbf1141 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -3,7 +3,7 @@ * * Name: actbl.h - Basic ACPI Table Definitions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index ab424509cae9..45b0f532f63b 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -3,7 +3,7 @@ * * Name: actbl1.h - Additional ACPI table definitions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index c50ef7e6b942..be01efdede32 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -3,7 +3,7 @@ * * Name: actbl2.h - ACPI Table Definitions (tables not in ACPI spec) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index ea1ca49c9c1b..a6014e9a7113 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -3,7 +3,7 @@ * * Name: actbl3.h - ACPI Table Definitions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 2590627dbfcc..913a7cfb61e6 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -3,7 +3,7 @@ * * Name: actypes.h - Common data types for the entire ACPI subsystem * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acuuid.h b/include/acpi/acuuid.h index e63f214531ad..23262cab047a 100644 --- a/include/acpi/acuuid.h +++ b/include/acpi/acuuid.h @@ -3,7 +3,7 @@ * * Name: acuuid.h - ACPI-related UUID/GUID definitions * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h index f444e5b0fdaa..35ab3f87cc29 100644 --- a/include/acpi/platform/acenv.h +++ b/include/acpi/platform/acenv.h @@ -3,7 +3,7 @@ * * Name: acenv.h - Host and compiler configuration * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h index 47d690eafe4c..2e36c8344897 100644 --- a/include/acpi/platform/acenvex.h +++ b/include/acpi/platform/acenvex.h @@ -3,7 +3,7 @@ * * Name: acenvex.h - Extra host and compiler configuration * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index 085db95a3dae..6a0705b433d2 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -3,7 +3,7 @@ * * Name: acgcc.h - GCC specific defines, etc. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acgccex.h b/include/acpi/platform/acgccex.h index 5d2b667af829..8dda2856aca1 100644 --- a/include/acpi/platform/acgccex.h +++ b/include/acpi/platform/acgccex.h @@ -3,7 +3,7 @@ * * Name: acgccex.h - Extra GCC specific defines, etc. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acintel.h b/include/acpi/platform/acintel.h index 626265833a54..d2cc247248cb 100644 --- a/include/acpi/platform/acintel.h +++ b/include/acpi/platform/acintel.h @@ -3,7 +3,7 @@ * * Name: acintel.h - VC specific defines, etc. * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index e3d21d014fcc..9ff328fd946a 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -3,7 +3,7 @@ * * Name: aclinux.h - OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index d754a1b12721..cc4f1eb53cba 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -3,7 +3,7 @@ * * Name: aclinuxex.h - Extra OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c index ff8025de8237..28c11c6b4d06 100644 --- a/tools/power/acpi/common/cmfsize.c +++ b/tools/power/acpi/common/cmfsize.c @@ -3,7 +3,7 @@ * * Module Name: cfsize - Common get file size function * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c index 7be89b873661..6b41d8b64a00 100644 --- a/tools/power/acpi/common/getopt.c +++ b/tools/power/acpi/common/getopt.c @@ -3,7 +3,7 @@ * * Module Name: getopt * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index a20c703f8b7d..2a1fd9182f94 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -3,7 +3,7 @@ * * Module Name: oslinuxtbl - Linux OSL for obtaining ACPI tables * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c index 4fd44e218a83..30913f124dd5 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixdir.c +++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c @@ -3,7 +3,7 @@ * * Module Name: osunixdir - Unix directory access interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c index 93d8359309b6..29dfb47adfeb 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixmap.c +++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c @@ -3,7 +3,7 @@ * * Module Name: osunixmap - Unix OSL for file mappings * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c index 8a88e87778bd..83d3b3b829b8 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixxf.c +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -3,7 +3,7 @@ * * Module Name: osunixxf - UNIX OSL interfaces * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h index f69f1f559743..2eb0aaa4f462 100644 --- a/tools/power/acpi/tools/acpidump/acpidump.h +++ b/tools/power/acpi/tools/acpidump/acpidump.h @@ -3,7 +3,7 @@ * * Module Name: acpidump.h - Include file for acpi_dump utility * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c index a9848de32d8e..e256c2ac5ddc 100644 --- a/tools/power/acpi/tools/acpidump/apdump.c +++ b/tools/power/acpi/tools/acpidump/apdump.c @@ -3,7 +3,7 @@ * * Module Name: apdump - Dump routines for ACPI tables (acpidump) * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index e86207e5afcf..49972bc78bc5 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -3,7 +3,7 @@ * * Module Name: apfiles - File-related functions for acpidump utility * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index 2d9b94b631cb..d8f1b57537d3 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -3,7 +3,7 @@ * * Module Name: apmain - Main module for the acpidump utility * - * Copyright (C) 2000 - 2018, Intel Corp. + * Copyright (C) 2000 - 2019, Intel Corp. * *****************************************************************************/ -- cgit v1.2.3 From 075470d88930dd16858a844f9dfb611c11f798d3 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 14 Jan 2019 09:55:26 -0800 Subject: ACPICA: Update version to 20190108 ACPICA commit aace846bb8f9b5877e100017f37fefc09dd2fde6 Version 20190108 Link: https://github.com/acpica/acpica/commit/aace846b Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 3a3febc9b979..4cc74954fea3 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -12,7 +12,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20181213 +#define ACPI_CA_VERSION 0x20190108 #include #include -- cgit v1.2.3 From 8a62ffe2753a845272f4f2100b5fca0b6053ff6f Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 21 Dec 2018 11:33:54 +0100 Subject: PM-runtime: Add new interface to get accounted time Some drivers (like i915/drm) needs to get the accounted suspended time. pm_runtime_suspended_time() will return the suspended accounted time in ns unit. Reviewed-by: Ulf Hansson Signed-off-by: Vincent Guittot Signed-off-by: Rafael J. Wysocki --- drivers/base/power/runtime.c | 15 +++++++++++++++ include/linux/pm_runtime.h | 2 ++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 457be03b744d..a453090c9449 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -88,6 +88,21 @@ static void __update_runtime_status(struct device *dev, enum rpm_status status) dev->power.runtime_status = status; } +u64 pm_runtime_suspended_time(struct device *dev) +{ + unsigned long flags, time; + + spin_lock_irqsave(&dev->power.lock, flags); + + update_pm_runtime_accounting(dev); + time = dev->power.suspended_jiffies; + + spin_unlock_irqrestore(&dev->power.lock, flags); + + return jiffies_to_nsecs(time); +} +EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); + /** * pm_runtime_deactivate_timer - Deactivate given device's suspend timer. * @dev: Device to handle. diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 54af4eef169f..a370006921c0 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -113,6 +113,8 @@ static inline bool pm_runtime_is_irq_safe(struct device *dev) return dev->power.irq_safe; } +extern u64 pm_runtime_suspended_time(struct device *dev); + #else /* !CONFIG_PM */ static inline bool queue_pm_work(struct work_struct *work) { return false; } -- cgit v1.2.3 From b33a02aadcc6330a61e511240b634dc11112e65e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 9 Jan 2019 17:24:55 +0200 Subject: i2c: acpi: Move I2C bits from acpi.h to i2c.h As discussed previously the best location for certain bus related bits, e.g. I2C, is its own realm of the headers. In order to uncontaminate acpi.h move the I2C bits to i2c.h. There is no functional change intended. Link: https://lkml.org/lkml/2018/11/28/744 Signed-off-by: Andy Shevchenko Acked-by: Mika Westerberg Acked-by: Rafael J. Wysocki Signed-off-by: Wolfram Sang --- include/linux/acpi.h | 11 ----------- include/linux/i2c.h | 10 ++++++++++ 2 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 87715f20b69a..13f5cb2c4763 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1061,17 +1061,6 @@ static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) } #endif -#if defined(CONFIG_ACPI) && IS_ENABLED(CONFIG_I2C) -bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, - struct acpi_resource_i2c_serialbus **i2c); -#else -static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, - struct acpi_resource_i2c_serialbus **i2c) -{ - return false; -} -#endif - /* Device properties */ #ifdef CONFIG_ACPI diff --git a/include/linux/i2c.h b/include/linux/i2c.h index cba59d66c00d..1f45331924d6 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -967,11 +967,21 @@ static inline int of_i2c_get_board_info(struct device *dev, #endif /* CONFIG_OF */ +struct acpi_resource; +struct acpi_resource_i2c_serialbus; + #if IS_ENABLED(CONFIG_ACPI) +bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, + struct acpi_resource_i2c_serialbus **i2c); u32 i2c_acpi_find_bus_speed(struct device *dev); struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info); #else +static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, + struct acpi_resource_i2c_serialbus **i2c) +{ + return false; +} static inline u32 i2c_acpi_find_bus_speed(struct device *dev) { return 0; -- cgit v1.2.3 From 063755ab1d1c1127adc09703185967862584935b Mon Sep 17 00:00:00 2001 From: Philippe Schenker Date: Fri, 21 Dec 2018 14:46:31 +0100 Subject: mfd: stmpe: Move ADC related defines to MFD header Move defines that are ADC related to the header of the overlying MFD, so they can be used from multiple sub-devices. Signed-off-by: Philippe Schenker Acked-by: Dmitry Torokhov Signed-off-by: Lee Jones --- drivers/input/touchscreen/stmpe-ts.c | 34 +++++++++++++--------------------- include/linux/mfd/stmpe.h | 11 +++++++++++ 2 files changed, 24 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c index 2a78e27b4495..c5d9006588a2 100644 --- a/drivers/input/touchscreen/stmpe-ts.c +++ b/drivers/input/touchscreen/stmpe-ts.c @@ -49,17 +49,6 @@ #define STMPE_IRQ_TOUCH_DET 0 -#define SAMPLE_TIME(x) ((x & 0xf) << 4) -#define MOD_12B(x) ((x & 0x1) << 3) -#define REF_SEL(x) ((x & 0x1) << 1) -#define ADC_FREQ(x) (x & 0x3) -#define AVE_CTRL(x) ((x & 0x3) << 6) -#define DET_DELAY(x) ((x & 0x7) << 3) -#define SETTLING(x) (x & 0x7) -#define FRACTION_Z(x) (x & 0x7) -#define I_DRIVE(x) (x & 0x1) -#define OP_MODE(x) ((x & 0x7) << 1) - #define STMPE_TS_NAME "stmpe-ts" #define XY_MASK 0xfff @@ -213,9 +202,10 @@ static int stmpe_init_hw(struct stmpe_touch *ts) return ret; } - adc_ctrl1 = SAMPLE_TIME(ts->sample_time) | MOD_12B(ts->mod_12b) | - REF_SEL(ts->ref_sel); - adc_ctrl1_mask = SAMPLE_TIME(0xff) | MOD_12B(0xff) | REF_SEL(0xff); + adc_ctrl1 = STMPE_SAMPLE_TIME(ts->sample_time) | + STMPE_MOD_12B(ts->mod_12b) | STMPE_REF_SEL(ts->ref_sel); + adc_ctrl1_mask = STMPE_SAMPLE_TIME(0xff) | STMPE_MOD_12B(0xff) | + STMPE_REF_SEL(0xff); ret = stmpe_set_bits(stmpe, STMPE_REG_ADC_CTRL1, adc_ctrl1_mask, adc_ctrl1); @@ -225,15 +215,17 @@ static int stmpe_init_hw(struct stmpe_touch *ts) } ret = stmpe_set_bits(stmpe, STMPE_REG_ADC_CTRL2, - ADC_FREQ(0xff), ADC_FREQ(ts->adc_freq)); + STMPE_ADC_FREQ(0xff), STMPE_ADC_FREQ(ts->adc_freq)); if (ret) { dev_err(dev, "Could not setup ADC\n"); return ret; } - tsc_cfg = AVE_CTRL(ts->ave_ctrl) | DET_DELAY(ts->touch_det_delay) | - SETTLING(ts->settling); - tsc_cfg_mask = AVE_CTRL(0xff) | DET_DELAY(0xff) | SETTLING(0xff); + tsc_cfg = STMPE_AVE_CTRL(ts->ave_ctrl) | + STMPE_DET_DELAY(ts->touch_det_delay) | + STMPE_SETTLING(ts->settling); + tsc_cfg_mask = STMPE_AVE_CTRL(0xff) | STMPE_DET_DELAY(0xff) | + STMPE_SETTLING(0xff); ret = stmpe_set_bits(stmpe, STMPE_REG_TSC_CFG, tsc_cfg_mask, tsc_cfg); if (ret) { @@ -242,14 +234,14 @@ static int stmpe_init_hw(struct stmpe_touch *ts) } ret = stmpe_set_bits(stmpe, STMPE_REG_TSC_FRACTION_Z, - FRACTION_Z(0xff), FRACTION_Z(ts->fraction_z)); + STMPE_FRACTION_Z(0xff), STMPE_FRACTION_Z(ts->fraction_z)); if (ret) { dev_err(dev, "Could not config touch\n"); return ret; } ret = stmpe_set_bits(stmpe, STMPE_REG_TSC_I_DRIVE, - I_DRIVE(0xff), I_DRIVE(ts->i_drive)); + STMPE_I_DRIVE(0xff), STMPE_I_DRIVE(ts->i_drive)); if (ret) { dev_err(dev, "Could not config touch\n"); return ret; @@ -263,7 +255,7 @@ static int stmpe_init_hw(struct stmpe_touch *ts) } ret = stmpe_set_bits(stmpe, STMPE_REG_TSC_CTRL, - OP_MODE(0xff), OP_MODE(OP_MOD_XYZ)); + STMPE_OP_MODE(0xff), STMPE_OP_MODE(OP_MOD_XYZ)); if (ret) { dev_err(dev, "Could not set mode\n"); return ret; diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index 4a827af17e59..c0353f6431f9 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -10,6 +10,17 @@ #include +#define STMPE_SAMPLE_TIME(x) ((x & 0xf) << 4) +#define STMPE_MOD_12B(x) ((x & 0x1) << 3) +#define STMPE_REF_SEL(x) ((x & 0x1) << 1) +#define STMPE_ADC_FREQ(x) (x & 0x3) +#define STMPE_AVE_CTRL(x) ((x & 0x3) << 6) +#define STMPE_DET_DELAY(x) ((x & 0x7) << 3) +#define STMPE_SETTLING(x) (x & 0x7) +#define STMPE_FRACTION_Z(x) (x & 0x7) +#define STMPE_I_DRIVE(x) (x & 0x1) +#define STMPE_OP_MODE(x) ((x & 0x7) << 1) + struct device; struct regulator; -- cgit v1.2.3 From 6377cfa3b857ced301f2079ac97de6c19057ab65 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Fri, 21 Dec 2018 14:46:32 +0100 Subject: mfd: stmpe: Preparations for STMPE ADC driver This prepares the MFD for the STMPE ADC driver. This commit introduces devicetree settings that are used by the ADC and adds an init function. Common ADC settings that are shared with the touchscreen driver can now reside in the overlying MFD. Signed-off-by: Stefan Agner Signed-off-by: Max Krummenacher Signed-off-by: Philippe Schenker Signed-off-by: Lee Jones --- drivers/mfd/Kconfig | 3 ++- drivers/mfd/stmpe.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/stmpe.h | 10 +++++++ 3 files changed, 80 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 8c5dfdce4326..bba159e8eaa4 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1204,7 +1204,7 @@ config MFD_STMPE Currently supported devices are: - STMPE811: GPIO, Touchscreen + STMPE811: GPIO, Touchscreen, ADC STMPE1601: GPIO, Keypad STMPE1801: GPIO, Keypad STMPE2401: GPIO, Keypad @@ -1217,6 +1217,7 @@ config MFD_STMPE GPIO: stmpe-gpio Keypad: stmpe-keypad Touchscreen: stmpe-ts + ADC: stmpe-adc menu "STMicroelectronics STMPE Interface Drivers" depends on MFD_STMPE diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c index 566caca4efd8..f582531a8f3e 100644 --- a/drivers/mfd/stmpe.c +++ b/drivers/mfd/stmpe.c @@ -463,6 +463,28 @@ static const struct mfd_cell stmpe_ts_cell = { .num_resources = ARRAY_SIZE(stmpe_ts_resources), }; +/* + * ADC (STMPE811) + */ + +static struct resource stmpe_adc_resources[] = { + { + .name = "STMPE_TEMP_SENS", + .flags = IORESOURCE_IRQ, + }, + { + .name = "STMPE_ADC", + .flags = IORESOURCE_IRQ, + }, +}; + +static const struct mfd_cell stmpe_adc_cell = { + .name = "stmpe-adc", + .of_compatible = "st,stmpe-adc", + .resources = stmpe_adc_resources, + .num_resources = ARRAY_SIZE(stmpe_adc_resources), +}; + /* * STMPE811 or STMPE610 */ @@ -497,6 +519,11 @@ static struct stmpe_variant_block stmpe811_blocks[] = { .irq = STMPE811_IRQ_TOUCH_DET, .block = STMPE_BLOCK_TOUCHSCREEN, }, + { + .cell = &stmpe_adc_cell, + .irq = STMPE811_IRQ_TEMP_SENS, + .block = STMPE_BLOCK_ADC, + }, }; static int stmpe811_enable(struct stmpe *stmpe, unsigned int blocks, @@ -517,6 +544,35 @@ static int stmpe811_enable(struct stmpe *stmpe, unsigned int blocks, enable ? 0 : mask); } +int stmpe811_adc_common_init(struct stmpe *stmpe) +{ + int ret; + u8 adc_ctrl1, adc_ctrl1_mask; + + adc_ctrl1 = STMPE_SAMPLE_TIME(stmpe->sample_time) | + STMPE_MOD_12B(stmpe->mod_12b) | + STMPE_REF_SEL(stmpe->ref_sel); + adc_ctrl1_mask = STMPE_SAMPLE_TIME(0xff) | STMPE_MOD_12B(0xff) | + STMPE_REF_SEL(0xff); + + ret = stmpe_set_bits(stmpe, STMPE811_REG_ADC_CTRL1, + adc_ctrl1_mask, adc_ctrl1); + if (ret) { + dev_err(stmpe->dev, "Could not setup ADC\n"); + return ret; + } + + ret = stmpe_set_bits(stmpe, STMPE811_REG_ADC_CTRL2, + STMPE_ADC_FREQ(0xff), STMPE_ADC_FREQ(stmpe->adc_freq)); + if (ret) { + dev_err(stmpe->dev, "Could not setup ADC\n"); + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(stmpe811_adc_common_init); + static int stmpe811_get_altfunc(struct stmpe *stmpe, enum stmpe_block block) { /* 0 for touchscreen, 1 for GPIO */ @@ -1325,6 +1381,7 @@ int stmpe_probe(struct stmpe_client_info *ci, enum stmpe_partnum partnum) struct device_node *np = ci->dev->of_node; struct stmpe *stmpe; int ret; + u32 val; pdata = devm_kzalloc(ci->dev, sizeof(*pdata), GFP_KERNEL); if (!pdata) @@ -1342,6 +1399,15 @@ int stmpe_probe(struct stmpe_client_info *ci, enum stmpe_partnum partnum) mutex_init(&stmpe->irq_lock); mutex_init(&stmpe->lock); + if (!of_property_read_u32(np, "st,sample-time", &val)) + stmpe->sample_time = val; + if (!of_property_read_u32(np, "st,mod-12b", &val)) + stmpe->mod_12b = val; + if (!of_property_read_u32(np, "st,ref-sel", &val)) + stmpe->ref_sel = val; + if (!of_property_read_u32(np, "st,adc-freq", &val)) + stmpe->adc_freq = val; + stmpe->dev = ci->dev; stmpe->client = ci->client; stmpe->pdata = pdata; @@ -1433,6 +1499,8 @@ int stmpe_remove(struct stmpe *stmpe) if (!IS_ERR(stmpe->vcc)) regulator_disable(stmpe->vcc); + __stmpe_disable(stmpe, STMPE_BLOCK_ADC); + mfd_remove_devices(stmpe->dev); return 0; diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index c0353f6431f9..07f55aac9390 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -21,6 +21,9 @@ #define STMPE_I_DRIVE(x) (x & 0x1) #define STMPE_OP_MODE(x) ((x & 0x7) << 1) +#define STMPE811_REG_ADC_CTRL1 0x20 +#define STMPE811_REG_ADC_CTRL2 0x21 + struct device; struct regulator; @@ -134,6 +137,12 @@ struct stmpe { u8 ier[2]; u8 oldier[2]; struct stmpe_platform_data *pdata; + + /* For devices that use an ADC */ + u8 sample_time; + u8 mod_12b; + u8 ref_sel; + u8 adc_freq; }; extern int stmpe_reg_write(struct stmpe *stmpe, u8 reg, u8 data); @@ -147,6 +156,7 @@ extern int stmpe_set_altfunc(struct stmpe *stmpe, u32 pins, enum stmpe_block block); extern int stmpe_enable(struct stmpe *stmpe, unsigned int blocks); extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks); +extern int stmpe811_adc_common_init(struct stmpe *stmpe); #define STMPE_GPIO_NOREQ_811_TOUCH (0xf0) -- cgit v1.2.3 From 1d7ae53b152dbc5ba0a4f6a83ecc42ac66f52d11 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 12 Dec 2018 23:38:47 +0300 Subject: iommu: Introduce iotlb_sync_map callback Introduce iotlb_sync_map() callback that is invoked in the end of iommu_map(). This new callback allows IOMMU drivers to avoid syncing after mapping of each contiguous chunk and sync only when the whole mapping is completed, optimizing performance of the mapping operation. Signed-off-by: Dmitry Osipenko Reviewed-by: Robin Murphy Reviewed-by: Thierry Reding Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 8 ++++++-- include/linux/iommu.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 3ed4db334341..ed0e63f2cd9b 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1585,13 +1585,14 @@ static size_t iommu_pgsize(struct iommu_domain *domain, int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot) { + const struct iommu_ops *ops = domain->ops; unsigned long orig_iova = iova; unsigned int min_pagesz; size_t orig_size = size; phys_addr_t orig_paddr = paddr; int ret = 0; - if (unlikely(domain->ops->map == NULL || + if (unlikely(ops->map == NULL || domain->pgsize_bitmap == 0UL)) return -ENODEV; @@ -1620,7 +1621,7 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n", iova, &paddr, pgsize); - ret = domain->ops->map(domain, iova, paddr, pgsize, prot); + ret = ops->map(domain, iova, paddr, pgsize, prot); if (ret) break; @@ -1629,6 +1630,9 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, size -= pgsize; } + if (ops->iotlb_sync_map) + ops->iotlb_sync_map(domain); + /* unroll mapping in case something went wrong */ if (ret) iommu_unmap(domain, orig_iova, orig_size - size); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e90da6b6f3d1..477ef47c357c 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -201,6 +201,7 @@ struct iommu_ops { void (*flush_iotlb_all)(struct iommu_domain *domain); void (*iotlb_range_add)(struct iommu_domain *domain, unsigned long iova, size_t size); + void (*iotlb_sync_map)(struct iommu_domain *domain); void (*iotlb_sync)(struct iommu_domain *domain); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*add_device)(struct device *dev); -- cgit v1.2.3 From 96efa118c03648fdc76acad9ca8fe018a6be7145 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 12 Dec 2018 23:38:52 +0300 Subject: memory: tegra: Adapt to Tegra20 device-tree binding changes The tegra20-mc device-tree binding has been changed, GART has been squashed into Memory Controller and now the clock property is mandatory for Tegra20, the DT compatible has been changed as well. Adapt driver to the DT changes. Signed-off-by: Dmitry Osipenko Acked-by: Thierry Reding Signed-off-by: Joerg Roedel --- drivers/memory/tegra/mc.c | 21 ++++++++------------- drivers/memory/tegra/mc.h | 6 ------ include/soc/tegra/mc.h | 2 +- 3 files changed, 9 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c index b99f3c620f6c..59db13287b47 100644 --- a/drivers/memory/tegra/mc.c +++ b/drivers/memory/tegra/mc.c @@ -51,7 +51,7 @@ static const struct of_device_id tegra_mc_of_match[] = { #ifdef CONFIG_ARCH_TEGRA_2x_SOC - { .compatible = "nvidia,tegra20-mc", .data = &tegra20_mc_soc }, + { .compatible = "nvidia,tegra20-mc-gart", .data = &tegra20_mc_soc }, #endif #ifdef CONFIG_ARCH_TEGRA_3x_SOC { .compatible = "nvidia,tegra30-mc", .data = &tegra30_mc_soc }, @@ -638,24 +638,19 @@ static int tegra_mc_probe(struct platform_device *pdev) if (IS_ERR(mc->regs)) return PTR_ERR(mc->regs); + mc->clk = devm_clk_get(&pdev->dev, "mc"); + if (IS_ERR(mc->clk)) { + dev_err(&pdev->dev, "failed to get MC clock: %ld\n", + PTR_ERR(mc->clk)); + return PTR_ERR(mc->clk); + } + #ifdef CONFIG_ARCH_TEGRA_2x_SOC if (mc->soc == &tegra20_mc_soc) { - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - mc->regs2 = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(mc->regs2)) - return PTR_ERR(mc->regs2); - isr = tegra20_mc_irq; } else #endif { - mc->clk = devm_clk_get(&pdev->dev, "mc"); - if (IS_ERR(mc->clk)) { - dev_err(&pdev->dev, "failed to get MC clock: %ld\n", - PTR_ERR(mc->clk)); - return PTR_ERR(mc->clk); - } - err = tegra_mc_setup_latency_allowance(mc); if (err < 0) { dev_err(&pdev->dev, "failed to setup latency allowance: %d\n", diff --git a/drivers/memory/tegra/mc.h b/drivers/memory/tegra/mc.h index 01065f12ebeb..9856f085e487 100644 --- a/drivers/memory/tegra/mc.h +++ b/drivers/memory/tegra/mc.h @@ -26,18 +26,12 @@ static inline u32 mc_readl(struct tegra_mc *mc, unsigned long offset) { - if (mc->regs2 && offset >= 0x24) - return readl(mc->regs2 + offset - 0x3c); - return readl(mc->regs + offset); } static inline void mc_writel(struct tegra_mc *mc, u32 value, unsigned long offset) { - if (mc->regs2 && offset >= 0x24) - return writel(value, mc->regs2 + offset - 0x3c); - writel(value, mc->regs + offset); } diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index b43f37fea096..db5bfdf589b4 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -144,7 +144,7 @@ struct tegra_mc_soc { struct tegra_mc { struct device *dev; struct tegra_smmu *smmu; - void __iomem *regs, *regs2; + void __iomem *regs; struct clk *clk; int irq; -- cgit v1.2.3 From ce2785a75dbca27375f3723f4e697a2a8dc096ee Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 12 Dec 2018 23:38:56 +0300 Subject: iommu/tegra: gart: Integrate with Memory Controller driver The device-tree binding has been changed. There is no separate GART device anymore, it is squashed into the Memory Controller. Integrate GART module with the MC in a way it is done for the SMMU on Tegra30+. Signed-off-by: Dmitry Osipenko Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 1 + drivers/iommu/tegra-gart.c | 71 ++++++++++++---------------------------------- drivers/memory/tegra/mc.c | 43 ++++++++++++++++++++++++++++ include/soc/tegra/mc.h | 25 ++++++++++++++++ 4 files changed, 87 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index d9a25715650e..83c099bb7288 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -282,6 +282,7 @@ config ROCKCHIP_IOMMU config TEGRA_IOMMU_GART bool "Tegra GART IOMMU Support" depends on ARCH_TEGRA_2x_SOC + depends on TEGRA_MC select IOMMU_API help Enables support for remapping discontiguous physical memory diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 835fea461c59..b35ffa312a83 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -19,16 +19,17 @@ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. */ -#include #include #include #include #include -#include +#include #include #include #include +#include + /* bitmap of the page sizes currently supported */ #define GART_IOMMU_PGSIZES (SZ_4K) @@ -397,9 +398,8 @@ static const struct iommu_ops gart_iommu_ops = { .iotlb_sync = gart_iommu_sync, }; -static int tegra_gart_suspend(struct device *dev) +int tegra_gart_suspend(struct gart_device *gart) { - struct gart_device *gart = dev_get_drvdata(dev); unsigned long iova; u32 *data = gart->savedata; unsigned long flags; @@ -411,9 +411,8 @@ static int tegra_gart_suspend(struct device *dev) return 0; } -static int tegra_gart_resume(struct device *dev) +int tegra_gart_resume(struct gart_device *gart) { - struct gart_device *gart = dev_get_drvdata(dev); unsigned long flags; spin_lock_irqsave(&gart->pte_lock, flags); @@ -422,41 +421,33 @@ static int tegra_gart_resume(struct device *dev) return 0; } -static int tegra_gart_probe(struct platform_device *pdev) +struct gart_device *tegra_gart_probe(struct device *dev, struct tegra_mc *mc) { struct gart_device *gart; - struct resource *res, *res_remap; + struct resource *res_remap; void __iomem *gart_regs; - struct device *dev = &pdev->dev; int ret; BUILD_BUG_ON(PAGE_SHIFT != GART_PAGE_SHIFT); /* the GART memory aperture is required */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - res_remap = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (!res || !res_remap) { + res_remap = platform_get_resource(to_platform_device(dev), + IORESOURCE_MEM, 1); + if (!res_remap) { dev_err(dev, "GART memory aperture expected\n"); - return -ENXIO; + return ERR_PTR(-ENXIO); } gart = devm_kzalloc(dev, sizeof(*gart), GFP_KERNEL); if (!gart) { dev_err(dev, "failed to allocate gart_device\n"); - return -ENOMEM; - } - - gart_regs = devm_ioremap(dev, res->start, resource_size(res)); - if (!gart_regs) { - dev_err(dev, "failed to remap GART registers\n"); - return -ENXIO; + return ERR_PTR(-ENOMEM); } - ret = iommu_device_sysfs_add(&gart->iommu, &pdev->dev, NULL, - dev_name(&pdev->dev)); + ret = iommu_device_sysfs_add(&gart->iommu, dev, NULL, "gart"); if (ret) { dev_err(dev, "Failed to register IOMMU in sysfs\n"); - return ret; + return ERR_PTR(ret); } iommu_device_set_ops(&gart->iommu, &gart_iommu_ops); @@ -468,7 +459,8 @@ static int tegra_gart_probe(struct platform_device *pdev) goto remove_sysfs; } - gart->dev = &pdev->dev; + gart->dev = dev; + gart_regs = mc->regs + GART_REG_BASE; spin_lock_init(&gart->pte_lock); spin_lock_init(&gart->client_lock); INIT_LIST_HEAD(&gart->client); @@ -483,46 +475,19 @@ static int tegra_gart_probe(struct platform_device *pdev) goto unregister_iommu; } - platform_set_drvdata(pdev, gart); do_gart_setup(gart, NULL); gart_handle = gart; - return 0; + return gart; unregister_iommu: iommu_device_unregister(&gart->iommu); remove_sysfs: iommu_device_sysfs_remove(&gart->iommu); - return ret; -} - -static const struct dev_pm_ops tegra_gart_pm_ops = { - .suspend = tegra_gart_suspend, - .resume = tegra_gart_resume, -}; - -static const struct of_device_id tegra_gart_of_match[] = { - { .compatible = "nvidia,tegra20-gart", }, - { }, -}; - -static struct platform_driver tegra_gart_driver = { - .probe = tegra_gart_probe, - .driver = { - .name = "tegra-gart", - .pm = &tegra_gart_pm_ops, - .of_match_table = tegra_gart_of_match, - .suppress_bind_attrs = true, - }, -}; - -static int __init tegra_gart_init(void) -{ - return platform_driver_register(&tegra_gart_driver); + return ERR_PTR(ret); } -subsys_initcall(tegra_gart_init); module_param(gart_debug, bool, 0644); MODULE_PARM_DESC(gart_debug, "Enable GART debugging"); diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c index 55ecfb2d8cfd..e684e234361a 100644 --- a/drivers/memory/tegra/mc.c +++ b/drivers/memory/tegra/mc.c @@ -702,13 +702,56 @@ static int tegra_mc_probe(struct platform_device *pdev) PTR_ERR(mc->smmu)); } + if (IS_ENABLED(CONFIG_TEGRA_IOMMU_GART) && !mc->soc->smmu) { + mc->gart = tegra_gart_probe(&pdev->dev, mc); + if (IS_ERR(mc->gart)) { + dev_err(&pdev->dev, "failed to probe GART: %ld\n", + PTR_ERR(mc->gart)); + mc->gart = NULL; + } + } + + return 0; +} + +static int tegra_mc_suspend(struct device *dev) +{ + struct tegra_mc *mc = dev_get_drvdata(dev); + int err; + + if (IS_ENABLED(CONFIG_TEGRA_IOMMU_GART) && mc->gart) { + err = tegra_gart_suspend(mc->gart); + if (err) + return err; + } + return 0; } +static int tegra_mc_resume(struct device *dev) +{ + struct tegra_mc *mc = dev_get_drvdata(dev); + int err; + + if (IS_ENABLED(CONFIG_TEGRA_IOMMU_GART) && mc->gart) { + err = tegra_gart_resume(mc->gart); + if (err) + return err; + } + + return 0; +} + +static const struct dev_pm_ops tegra_mc_pm_ops = { + .suspend = tegra_mc_suspend, + .resume = tegra_mc_resume, +}; + static struct platform_driver tegra_mc_driver = { .driver = { .name = "tegra-mc", .of_match_table = tegra_mc_of_match, + .pm = &tegra_mc_pm_ops, .suppress_bind_attrs = true, }, .prevent_deferred_probe = true, diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index db5bfdf589b4..e489a028ec9f 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -9,6 +9,7 @@ #ifndef __SOC_TEGRA_MC_H__ #define __SOC_TEGRA_MC_H__ +#include #include #include @@ -77,6 +78,7 @@ struct tegra_smmu_soc { struct tegra_mc; struct tegra_smmu; +struct gart_device; #ifdef CONFIG_TEGRA_IOMMU_SMMU struct tegra_smmu *tegra_smmu_probe(struct device *dev, @@ -96,6 +98,28 @@ static inline void tegra_smmu_remove(struct tegra_smmu *smmu) } #endif +#ifdef CONFIG_TEGRA_IOMMU_GART +struct gart_device *tegra_gart_probe(struct device *dev, struct tegra_mc *mc); +int tegra_gart_suspend(struct gart_device *gart); +int tegra_gart_resume(struct gart_device *gart); +#else +static inline struct gart_device * +tegra_gart_probe(struct device *dev, struct tegra_mc *mc) +{ + return ERR_PTR(-ENODEV); +} + +static inline int tegra_gart_suspend(struct gart_device *gart) +{ + return -ENODEV; +} + +static inline int tegra_gart_resume(struct gart_device *gart) +{ + return -ENODEV; +} +#endif + struct tegra_mc_reset { const char *name; unsigned long id; @@ -144,6 +168,7 @@ struct tegra_mc_soc { struct tegra_mc { struct device *dev; struct tegra_smmu *smmu; + struct gart_device *gart; void __iomem *regs; struct clk *clk; int irq; -- cgit v1.2.3 From 3eafbd3a7745e1579665cbb8c3959a74a666b8c9 Mon Sep 17 00:00:00 2001 From: Pascal PAILLET-LME Date: Mon, 14 Jan 2019 10:05:15 +0000 Subject: dt-bindings: mfd: Document STPMIC1 STPMIC1 is a PMIC from STMicroelectronics. The STPMIC1 integrates 10 regulators, 3 power switches, a watchdog and an input for a power on key. Signed-off-by: Pascal Paillet Reviewed-by: Rob Herring Signed-off-by: Lee Jones --- .../devicetree/bindings/mfd/st,stpmic1.txt | 61 ++++++++++++++++++++++ include/dt-bindings/mfd/st,stpmic1.h | 50 ++++++++++++++++++ 2 files changed, 111 insertions(+) create mode 100644 Documentation/devicetree/bindings/mfd/st,stpmic1.txt create mode 100644 include/dt-bindings/mfd/st,stpmic1.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/mfd/st,stpmic1.txt b/Documentation/devicetree/bindings/mfd/st,stpmic1.txt new file mode 100644 index 000000000000..afd45c089585 --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/st,stpmic1.txt @@ -0,0 +1,61 @@ +* STMicroelectronics STPMIC1 Power Management IC + +Required properties: +- compatible: : "st,stpmic1" +- reg: : The I2C slave address for the STPMIC1 chip. +- interrupts: : The interrupt line the device is connected to. +- #interrupt-cells: : Should be 1. +- interrupt-controller: : Marks the device node as an interrupt controller. + Interrupt numbers are defined at + dt-bindings/mfd/st,stpmic1.h. + +STPMIC1 consists in a varied group of sub-devices. +Each sub-device binding is be described in own documentation file. + +Device Description +------ ------------ +st,stpmic1-onkey : Power on key, see ../input/st,stpmic1-onkey.txt +st,stpmic1-regulators : Regulators, see ../regulator/st,stpmic1-regulator.txt +st,stpmic1-wdt : Watchdog, see ../watchdog/st,stpmic1-wdt.txt + +Example: + +#include + +pmic: pmic@33 { + compatible = "st,stpmic1"; + reg = <0x33>; + interrupt-parent = <&gpioa>; + interrupts = <0 2>; + + interrupt-controller; + #interrupt-cells = <2>; + + onkey { + compatible = "st,stpmic1-onkey"; + interrupts = ,; + interrupt-names = "onkey-falling", "onkey-rising"; + power-off-time-sec = <10>; + }; + + watchdog { + compatible = "st,stpmic1-wdt"; + }; + + regulators { + compatible = "st,stpmic1-regulators"; + + vdd_core: buck1 { + regulator-name = "vdd_core"; + regulator-boot-on; + regulator-min-microvolt = <700000>; + regulator-max-microvolt = <1200000>; + }; + vdd: buck3 { + regulator-name = "vdd"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-pull-down; + }; + }; diff --git a/include/dt-bindings/mfd/st,stpmic1.h b/include/dt-bindings/mfd/st,stpmic1.h new file mode 100644 index 000000000000..321cd08797d9 --- /dev/null +++ b/include/dt-bindings/mfd/st,stpmic1.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) STMicroelectronics 2018 - All Rights Reserved + * Author: Philippe Peurichard , + * Pascal Paillet for STMicroelectronics. + */ + +#ifndef __DT_BINDINGS_STPMIC1_H__ +#define __DT_BINDINGS_STPMIC1_H__ + +/* IRQ definitions */ +#define IT_PONKEY_F 0 +#define IT_PONKEY_R 1 +#define IT_WAKEUP_F 2 +#define IT_WAKEUP_R 3 +#define IT_VBUS_OTG_F 4 +#define IT_VBUS_OTG_R 5 +#define IT_SWOUT_F 6 +#define IT_SWOUT_R 7 + +#define IT_CURLIM_BUCK1 8 +#define IT_CURLIM_BUCK2 9 +#define IT_CURLIM_BUCK3 10 +#define IT_CURLIM_BUCK4 11 +#define IT_OCP_OTG 12 +#define IT_OCP_SWOUT 13 +#define IT_OCP_BOOST 14 +#define IT_OVP_BOOST 15 + +#define IT_CURLIM_LDO1 16 +#define IT_CURLIM_LDO2 17 +#define IT_CURLIM_LDO3 18 +#define IT_CURLIM_LDO4 19 +#define IT_CURLIM_LDO5 20 +#define IT_CURLIM_LDO6 21 +#define IT_SHORT_SWOTG 22 +#define IT_SHORT_SWOUT 23 + +#define IT_TWARN_F 24 +#define IT_TWARN_R 25 +#define IT_VINLOW_F 26 +#define IT_VINLOW_R 27 +#define IT_SWIN_F 30 +#define IT_SWIN_R 31 + +/* BUCK MODES definitions */ +#define STPMIC1_BUCK_MODE_NORMAL 0 +#define STPMIC1_BUCK_MODE_LP 2 + +#endif /* __DT_BINDINGS_STPMIC1_H__ */ -- cgit v1.2.3 From 51908d2e9b7c7730608a19f24fc8718af745bb2f Mon Sep 17 00:00:00 2001 From: Pascal PAILLET-LME Date: Mon, 14 Jan 2019 10:05:16 +0000 Subject: mfd: stpmic1: Add STPMIC1 driver STPMIC1 is a PMIC from STMicroelectronics. The STPMIC1 integrates 10 regulators, 3 power switches, a watchdog and an input for a power on key. Signed-off-by: Pascal Paillet Signed-off-by: Lee Jones --- drivers/mfd/Kconfig | 16 ++++ drivers/mfd/Makefile | 1 + drivers/mfd/stpmic1.c | 213 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/stpmic1.h | 212 +++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 442 insertions(+) create mode 100644 drivers/mfd/stpmic1.c create mode 100644 include/linux/mfd/stpmic1.h (limited to 'include') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 8c5dfdce4326..0761cb83d174 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1871,6 +1871,22 @@ config MFD_STM32_TIMERS for PWM and IIO Timer. This driver allow to share the registers between the others drivers. +config MFD_STPMIC1 + tristate "Support for STPMIC1 PMIC" + depends on (I2C=y && OF) + select REGMAP_I2C + select REGMAP_IRQ + select MFD_CORE + help + Support for ST Microelectronics STPMIC1 PMIC. STPMIC1 has power on + key, watchdog and regulator functionalities which are supported via + the relevant subsystems. This driver provides core support for the + STPMIC1. In order to use the actual functionaltiy of the device other + drivers must be enabled. + + To compile this driver as a module, choose M here: the + module will be called stpmic1. + menu "Multimedia Capabilities Port drivers" depends on ARCH_SA1100 diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 12980a4ad460..a62fb0112d9f 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -233,6 +233,7 @@ obj-$(CONFIG_INTEL_SOC_PMIC_CHTDC_TI) += intel_soc_pmic_chtdc_ti.o obj-$(CONFIG_MFD_MT6397) += mt6397-core.o obj-$(CONFIG_MFD_ALTERA_A10SR) += altera-a10sr.o +obj-$(CONFIG_MFD_STPMIC1) += stpmic1.o obj-$(CONFIG_MFD_SUN4I_GPADC) += sun4i-gpadc.o obj-$(CONFIG_MFD_STM32_LPTIMER) += stm32-lptimer.o diff --git a/drivers/mfd/stpmic1.c b/drivers/mfd/stpmic1.c new file mode 100644 index 000000000000..7dfbe8906cb8 --- /dev/null +++ b/drivers/mfd/stpmic1.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) STMicroelectronics 2018 +// Author: Pascal Paillet + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define STPMIC1_MAIN_IRQ 0 + +static const struct regmap_range stpmic1_readable_ranges[] = { + regmap_reg_range(TURN_ON_SR, VERSION_SR), + regmap_reg_range(SWOFF_PWRCTRL_CR, LDO6_STDBY_CR), + regmap_reg_range(BST_SW_CR, BST_SW_CR), + regmap_reg_range(INT_PENDING_R1, INT_PENDING_R4), + regmap_reg_range(INT_CLEAR_R1, INT_CLEAR_R4), + regmap_reg_range(INT_MASK_R1, INT_MASK_R4), + regmap_reg_range(INT_SET_MASK_R1, INT_SET_MASK_R4), + regmap_reg_range(INT_CLEAR_MASK_R1, INT_CLEAR_MASK_R4), + regmap_reg_range(INT_SRC_R1, INT_SRC_R1), +}; + +static const struct regmap_range stpmic1_writeable_ranges[] = { + regmap_reg_range(SWOFF_PWRCTRL_CR, LDO6_STDBY_CR), + regmap_reg_range(BST_SW_CR, BST_SW_CR), + regmap_reg_range(INT_CLEAR_R1, INT_CLEAR_R4), + regmap_reg_range(INT_SET_MASK_R1, INT_SET_MASK_R4), + regmap_reg_range(INT_CLEAR_MASK_R1, INT_CLEAR_MASK_R4), +}; + +static const struct regmap_range stpmic1_volatile_ranges[] = { + regmap_reg_range(TURN_ON_SR, VERSION_SR), + regmap_reg_range(WCHDG_CR, WCHDG_CR), + regmap_reg_range(INT_PENDING_R1, INT_PENDING_R4), + regmap_reg_range(INT_SRC_R1, INT_SRC_R4), +}; + +static const struct regmap_access_table stpmic1_readable_table = { + .yes_ranges = stpmic1_readable_ranges, + .n_yes_ranges = ARRAY_SIZE(stpmic1_readable_ranges), +}; + +static const struct regmap_access_table stpmic1_writeable_table = { + .yes_ranges = stpmic1_writeable_ranges, + .n_yes_ranges = ARRAY_SIZE(stpmic1_writeable_ranges), +}; + +static const struct regmap_access_table stpmic1_volatile_table = { + .yes_ranges = stpmic1_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(stpmic1_volatile_ranges), +}; + +const struct regmap_config stpmic1_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .cache_type = REGCACHE_RBTREE, + .max_register = PMIC_MAX_REGISTER_ADDRESS, + .rd_table = &stpmic1_readable_table, + .wr_table = &stpmic1_writeable_table, + .volatile_table = &stpmic1_volatile_table, +}; + +static const struct regmap_irq stpmic1_irqs[] = { + REGMAP_IRQ_REG(IT_PONKEY_F, 0, 0x01), + REGMAP_IRQ_REG(IT_PONKEY_R, 0, 0x02), + REGMAP_IRQ_REG(IT_WAKEUP_F, 0, 0x04), + REGMAP_IRQ_REG(IT_WAKEUP_R, 0, 0x08), + REGMAP_IRQ_REG(IT_VBUS_OTG_F, 0, 0x10), + REGMAP_IRQ_REG(IT_VBUS_OTG_R, 0, 0x20), + REGMAP_IRQ_REG(IT_SWOUT_F, 0, 0x40), + REGMAP_IRQ_REG(IT_SWOUT_R, 0, 0x80), + + REGMAP_IRQ_REG(IT_CURLIM_BUCK1, 1, 0x01), + REGMAP_IRQ_REG(IT_CURLIM_BUCK2, 1, 0x02), + REGMAP_IRQ_REG(IT_CURLIM_BUCK3, 1, 0x04), + REGMAP_IRQ_REG(IT_CURLIM_BUCK4, 1, 0x08), + REGMAP_IRQ_REG(IT_OCP_OTG, 1, 0x10), + REGMAP_IRQ_REG(IT_OCP_SWOUT, 1, 0x20), + REGMAP_IRQ_REG(IT_OCP_BOOST, 1, 0x40), + REGMAP_IRQ_REG(IT_OVP_BOOST, 1, 0x80), + + REGMAP_IRQ_REG(IT_CURLIM_LDO1, 2, 0x01), + REGMAP_IRQ_REG(IT_CURLIM_LDO2, 2, 0x02), + REGMAP_IRQ_REG(IT_CURLIM_LDO3, 2, 0x04), + REGMAP_IRQ_REG(IT_CURLIM_LDO4, 2, 0x08), + REGMAP_IRQ_REG(IT_CURLIM_LDO5, 2, 0x10), + REGMAP_IRQ_REG(IT_CURLIM_LDO6, 2, 0x20), + REGMAP_IRQ_REG(IT_SHORT_SWOTG, 2, 0x40), + REGMAP_IRQ_REG(IT_SHORT_SWOUT, 2, 0x80), + + REGMAP_IRQ_REG(IT_TWARN_F, 3, 0x01), + REGMAP_IRQ_REG(IT_TWARN_R, 3, 0x02), + REGMAP_IRQ_REG(IT_VINLOW_F, 3, 0x04), + REGMAP_IRQ_REG(IT_VINLOW_R, 3, 0x08), + REGMAP_IRQ_REG(IT_SWIN_F, 3, 0x40), + REGMAP_IRQ_REG(IT_SWIN_R, 3, 0x80), +}; + +static const struct regmap_irq_chip stpmic1_regmap_irq_chip = { + .name = "pmic_irq", + .status_base = INT_PENDING_R1, + .mask_base = INT_CLEAR_MASK_R1, + .unmask_base = INT_SET_MASK_R1, + .ack_base = INT_CLEAR_R1, + .num_regs = STPMIC1_PMIC_NUM_IRQ_REGS, + .irqs = stpmic1_irqs, + .num_irqs = ARRAY_SIZE(stpmic1_irqs), +}; + +static int stpmic1_probe(struct i2c_client *i2c, + const struct i2c_device_id *id) +{ + struct stpmic1 *ddata; + struct device *dev = &i2c->dev; + int ret; + struct device_node *np = dev->of_node; + u32 reg; + + ddata = devm_kzalloc(dev, sizeof(struct stpmic1), GFP_KERNEL); + if (!ddata) + return -ENOMEM; + + i2c_set_clientdata(i2c, ddata); + ddata->dev = dev; + + ddata->regmap = devm_regmap_init_i2c(i2c, &stpmic1_regmap_config); + if (IS_ERR(ddata->regmap)) + return PTR_ERR(ddata->regmap); + + ddata->irq = of_irq_get(np, STPMIC1_MAIN_IRQ); + if (ddata->irq < 0) { + dev_err(dev, "Failed to get main IRQ: %d\n", ddata->irq); + return ddata->irq; + } + + ret = regmap_read(ddata->regmap, VERSION_SR, ®); + if (ret) { + dev_err(dev, "Unable to read PMIC version\n"); + return ret; + } + dev_info(dev, "PMIC Chip Version: 0x%x\n", reg); + + /* Initialize PMIC IRQ Chip & associated IRQ domains */ + ret = devm_regmap_add_irq_chip(dev, ddata->regmap, ddata->irq, + IRQF_ONESHOT | IRQF_SHARED, + 0, &stpmic1_regmap_irq_chip, + &ddata->irq_data); + if (ret) { + dev_err(dev, "IRQ Chip registration failed: %d\n", ret); + return ret; + } + + return devm_of_platform_populate(dev); +} + +#ifdef CONFIG_PM_SLEEP +static int stpmic1_suspend(struct device *dev) +{ + struct i2c_client *i2c = to_i2c_client(dev); + struct stpmic1 *pmic_dev = i2c_get_clientdata(i2c); + + disable_irq(pmic_dev->irq); + + return 0; +} + +static int stpmic1_resume(struct device *dev) +{ + struct i2c_client *i2c = to_i2c_client(dev); + struct stpmic1 *pmic_dev = i2c_get_clientdata(i2c); + int ret; + + ret = regcache_sync(pmic_dev->regmap); + if (ret) + return ret; + + enable_irq(pmic_dev->irq); + + return 0; +} +#endif + +static SIMPLE_DEV_PM_OPS(stpmic1_pm, stpmic1_suspend, stpmic1_resume); + +static const struct of_device_id stpmic1_of_match[] = { + { .compatible = "st,stpmic1", }, + {}, +}; +MODULE_DEVICE_TABLE(of, stpmic1_of_match); + +static struct i2c_driver stpmic1_driver = { + .driver = { + .name = "stpmic1", + .of_match_table = of_match_ptr(stpmic1_of_match), + .pm = &stpmic1_pm, + }, + .probe = stpmic1_probe, +}; + +module_i2c_driver(stpmic1_driver); + +MODULE_DESCRIPTION("STPMIC1 PMIC Driver"); +MODULE_AUTHOR("Pascal Paillet "); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/mfd/stpmic1.h b/include/linux/mfd/stpmic1.h new file mode 100644 index 000000000000..fa3f99f7e9a1 --- /dev/null +++ b/include/linux/mfd/stpmic1.h @@ -0,0 +1,212 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) STMicroelectronics 2018 - All Rights Reserved + * Author: Philippe Peurichard , + * Pascal Paillet for STMicroelectronics. + */ + +#ifndef __LINUX_MFD_STPMIC1_H +#define __LINUX_MFD_STPMIC1_H + +#define TURN_ON_SR 0x1 +#define TURN_OFF_SR 0x2 +#define ICC_LDO_TURN_OFF_SR 0x3 +#define ICC_BUCK_TURN_OFF_SR 0x4 +#define RREQ_STATE_SR 0x5 +#define VERSION_SR 0x6 + +#define SWOFF_PWRCTRL_CR 0x10 +#define PADS_PULL_CR 0x11 +#define BUCKS_PD_CR 0x12 +#define LDO14_PD_CR 0x13 +#define LDO56_VREF_PD_CR 0x14 +#define VBUS_DET_VIN_CR 0x15 +#define PKEY_TURNOFF_CR 0x16 +#define BUCKS_MASK_RANK_CR 0x17 +#define BUCKS_MASK_RESET_CR 0x18 +#define LDOS_MASK_RANK_CR 0x19 +#define LDOS_MASK_RESET_CR 0x1A +#define WCHDG_CR 0x1B +#define WCHDG_TIMER_CR 0x1C +#define BUCKS_ICCTO_CR 0x1D +#define LDOS_ICCTO_CR 0x1E + +#define BUCK1_ACTIVE_CR 0x20 +#define BUCK2_ACTIVE_CR 0x21 +#define BUCK3_ACTIVE_CR 0x22 +#define BUCK4_ACTIVE_CR 0x23 +#define VREF_DDR_ACTIVE_CR 0x24 +#define LDO1_ACTIVE_CR 0x25 +#define LDO2_ACTIVE_CR 0x26 +#define LDO3_ACTIVE_CR 0x27 +#define LDO4_ACTIVE_CR 0x28 +#define LDO5_ACTIVE_CR 0x29 +#define LDO6_ACTIVE_CR 0x2A + +#define BUCK1_STDBY_CR 0x30 +#define BUCK2_STDBY_CR 0x31 +#define BUCK3_STDBY_CR 0x32 +#define BUCK4_STDBY_CR 0x33 +#define VREF_DDR_STDBY_CR 0x34 +#define LDO1_STDBY_CR 0x35 +#define LDO2_STDBY_CR 0x36 +#define LDO3_STDBY_CR 0x37 +#define LDO4_STDBY_CR 0x38 +#define LDO5_STDBY_CR 0x39 +#define LDO6_STDBY_CR 0x3A + +#define BST_SW_CR 0x40 + +#define INT_PENDING_R1 0x50 +#define INT_PENDING_R2 0x51 +#define INT_PENDING_R3 0x52 +#define INT_PENDING_R4 0x53 + +#define INT_DBG_LATCH_R1 0x60 +#define INT_DBG_LATCH_R2 0x61 +#define INT_DBG_LATCH_R3 0x62 +#define INT_DBG_LATCH_R4 0x63 + +#define INT_CLEAR_R1 0x70 +#define INT_CLEAR_R2 0x71 +#define INT_CLEAR_R3 0x72 +#define INT_CLEAR_R4 0x73 + +#define INT_MASK_R1 0x80 +#define INT_MASK_R2 0x81 +#define INT_MASK_R3 0x82 +#define INT_MASK_R4 0x83 + +#define INT_SET_MASK_R1 0x90 +#define INT_SET_MASK_R2 0x91 +#define INT_SET_MASK_R3 0x92 +#define INT_SET_MASK_R4 0x93 + +#define INT_CLEAR_MASK_R1 0xA0 +#define INT_CLEAR_MASK_R2 0xA1 +#define INT_CLEAR_MASK_R3 0xA2 +#define INT_CLEAR_MASK_R4 0xA3 + +#define INT_SRC_R1 0xB0 +#define INT_SRC_R2 0xB1 +#define INT_SRC_R3 0xB2 +#define INT_SRC_R4 0xB3 + +#define PMIC_MAX_REGISTER_ADDRESS INT_SRC_R4 + +#define STPMIC1_PMIC_NUM_IRQ_REGS 4 + +#define TURN_OFF_SR_ICC_EVENT 0x08 + +#define LDO_VOLTAGE_MASK GENMASK(6, 2) +#define BUCK_VOLTAGE_MASK GENMASK(7, 2) +#define LDO_BUCK_VOLTAGE_SHIFT 2 + +#define LDO_ENABLE_MASK BIT(0) +#define BUCK_ENABLE_MASK BIT(0) + +#define BUCK_HPLP_ENABLE_MASK BIT(1) +#define BUCK_HPLP_SHIFT 1 + +#define STDBY_ENABLE_MASK BIT(0) + +#define BUCKS_PD_CR_REG_MASK GENMASK(7, 0) +#define BUCK_MASK_RANK_REGISTER_MASK GENMASK(3, 0) +#define BUCK_MASK_RESET_REGISTER_MASK GENMASK(3, 0) +#define LDO1234_PULL_DOWN_REGISTER_MASK GENMASK(7, 0) +#define LDO56_VREF_PD_CR_REG_MASK GENMASK(5, 0) +#define LDO_MASK_RANK_REGISTER_MASK GENMASK(5, 0) +#define LDO_MASK_RESET_REGISTER_MASK GENMASK(5, 0) + +#define BUCK1_PULL_DOWN_REG BUCKS_PD_CR +#define BUCK1_PULL_DOWN_MASK BIT(0) +#define BUCK2_PULL_DOWN_REG BUCKS_PD_CR +#define BUCK2_PULL_DOWN_MASK BIT(2) +#define BUCK3_PULL_DOWN_REG BUCKS_PD_CR +#define BUCK3_PULL_DOWN_MASK BIT(4) +#define BUCK4_PULL_DOWN_REG BUCKS_PD_CR +#define BUCK4_PULL_DOWN_MASK BIT(6) + +#define LDO1_PULL_DOWN_REG LDO14_PD_CR +#define LDO1_PULL_DOWN_MASK BIT(0) +#define LDO2_PULL_DOWN_REG LDO14_PD_CR +#define LDO2_PULL_DOWN_MASK BIT(2) +#define LDO3_PULL_DOWN_REG LDO14_PD_CR +#define LDO3_PULL_DOWN_MASK BIT(4) +#define LDO4_PULL_DOWN_REG LDO14_PD_CR +#define LDO4_PULL_DOWN_MASK BIT(6) +#define LDO5_PULL_DOWN_REG LDO56_VREF_PD_CR +#define LDO5_PULL_DOWN_MASK BIT(0) +#define LDO6_PULL_DOWN_REG LDO56_VREF_PD_CR +#define LDO6_PULL_DOWN_MASK BIT(2) +#define VREF_DDR_PULL_DOWN_REG LDO56_VREF_PD_CR +#define VREF_DDR_PULL_DOWN_MASK BIT(4) + +#define BUCKS_ICCTO_CR_REG_MASK GENMASK(6, 0) +#define LDOS_ICCTO_CR_REG_MASK GENMASK(5, 0) + +#define LDO_BYPASS_MASK BIT(7) + +/* Main PMIC Control Register + * SWOFF_PWRCTRL_CR + * Address : 0x10 + */ +#define ICC_EVENT_ENABLED BIT(4) +#define PWRCTRL_POLARITY_HIGH BIT(3) +#define PWRCTRL_PIN_VALID BIT(2) +#define RESTART_REQUEST_ENABLED BIT(1) +#define SOFTWARE_SWITCH_OFF_ENABLED BIT(0) + +/* Main PMIC PADS Control Register + * PADS_PULL_CR + * Address : 0x11 + */ +#define WAKEUP_DETECTOR_DISABLED BIT(4) +#define PWRCTRL_PD_ACTIVE BIT(3) +#define PWRCTRL_PU_ACTIVE BIT(2) +#define WAKEUP_PD_ACTIVE BIT(1) +#define PONKEY_PU_INACTIVE BIT(0) + +/* Main PMIC VINLOW Control Register + * VBUS_DET_VIN_CRC DMSC + * Address : 0x15 + */ +#define SWIN_DETECTOR_ENABLED BIT(7) +#define SWOUT_DETECTOR_ENABLED BIT(6) +#define VINLOW_ENABLED BIT(0) +#define VINLOW_CTRL_REG_MASK GENMASK(7, 0) + +/* USB Control Register + * Address : 0x40 + */ +#define BOOST_OVP_DISABLED BIT(7) +#define VBUS_OTG_DETECTION_DISABLED BIT(6) +#define SW_OUT_DISCHARGE BIT(5) +#define VBUS_OTG_DISCHARGE BIT(4) +#define OCP_LIMIT_HIGH BIT(3) +#define SWIN_SWOUT_ENABLED BIT(2) +#define USBSW_OTG_SWITCH_ENABLED BIT(1) +#define BOOST_ENABLED BIT(0) + +/* PKEY_TURNOFF_CR + * Address : 0x16 + */ +#define PONKEY_PWR_OFF BIT(7) +#define PONKEY_CC_FLAG_CLEAR BIT(6) +#define PONKEY_TURNOFF_TIMER_MASK GENMASK(3, 0) +#define PONKEY_TURNOFF_MASK GENMASK(7, 0) + +/* + * struct stpmic1 - stpmic1 master device for sub-drivers + * @dev: master device of the chip (can be used to access platform data) + * @irq: main IRQ number + * @regmap_irq_chip_data: irq chip data + */ +struct stpmic1 { + struct device *dev; + struct regmap *regmap; + int irq; + struct regmap_irq_chip_data *irq_data; +}; + +#endif /* __LINUX_MFD_STPMIC1_H */ -- cgit v1.2.3 From c1d5fb019f65e1093c77734356f97b6e7ac4d629 Mon Sep 17 00:00:00 2001 From: "Matwey V. Kornilov" Date: Fri, 9 Nov 2018 14:03:26 -0500 Subject: media: usb: pwc: Introduce TRACE_EVENTs for pwc_isoc_handler() There were reports that PWC-based webcams don't work at some embedded ARM platforms. [1] Isochronous transfer handler seems to work too long leading to the issues in MUSB USB host subsystem. Also note, that urb->giveback() handlers are still called with disabled interrupts. In order to be able to measure performance of PWC driver, traces are introduced in URB handler section. [1] https://www.spinics.net/lists/linux-usb/msg165735.html Signed-off-by: Matwey V. Kornilov Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/pwc/pwc-if.c | 7 +++++ include/trace/events/pwc.h | 65 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 72 insertions(+) create mode 100644 include/trace/events/pwc.h (limited to 'include') diff --git a/drivers/media/usb/pwc/pwc-if.c b/drivers/media/usb/pwc/pwc-if.c index 72704f4d5330..53c111bd5a22 100644 --- a/drivers/media/usb/pwc/pwc-if.c +++ b/drivers/media/usb/pwc/pwc-if.c @@ -76,6 +76,9 @@ #include "pwc-dec23.h" #include "pwc-dec1.h" +#define CREATE_TRACE_POINTS +#include + /* Function prototypes and driver templates */ /* hotplug device table support */ @@ -260,6 +263,8 @@ static void pwc_isoc_handler(struct urb *urb) int i, fst, flen; unsigned char *iso_buf = NULL; + trace_pwc_handler_enter(urb, pdev); + if (urb->status == -ENOENT || urb->status == -ECONNRESET || urb->status == -ESHUTDOWN) { PWC_DEBUG_OPEN("URB (%p) unlinked %ssynchronously.\n", @@ -348,6 +353,8 @@ static void pwc_isoc_handler(struct urb *urb) } handler_end: + trace_pwc_handler_exit(urb, pdev); + i = usb_submit_urb(urb, GFP_ATOMIC); if (i != 0) PWC_ERROR("Error (%d) re-submitting urb in pwc_isoc_handler.\n", i); diff --git a/include/trace/events/pwc.h b/include/trace/events/pwc.h new file mode 100644 index 000000000000..a2da764a3b41 --- /dev/null +++ b/include/trace/events/pwc.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if !defined(_TRACE_PWC_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PWC_H + +#include +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM pwc + +TRACE_EVENT(pwc_handler_enter, + TP_PROTO(struct urb *urb, struct pwc_device *pdev), + TP_ARGS(urb, pdev), + TP_STRUCT__entry( + __field(struct urb*, urb) + __field(struct pwc_frame_buf*, fbuf) + __field(int, urb__status) + __field(u32, urb__actual_length) + __field(int, fbuf__filled) + __string(name, pdev->v4l2_dev.name) + ), + TP_fast_assign( + __entry->urb = urb; + __entry->fbuf = pdev->fill_buf; + __entry->urb__status = urb->status; + __entry->urb__actual_length = urb->actual_length; + __entry->fbuf__filled = (pdev->fill_buf + ? pdev->fill_buf->filled : 0); + __assign_str(name, pdev->v4l2_dev.name); + ), + TP_printk("dev=%s (fbuf=%p filled=%d) urb=%p (status=%d actual_length=%u)", + __get_str(name), + __entry->fbuf, + __entry->fbuf__filled, + __entry->urb, + __entry->urb__status, + __entry->urb__actual_length) +); + +TRACE_EVENT(pwc_handler_exit, + TP_PROTO(struct urb *urb, struct pwc_device *pdev), + TP_ARGS(urb, pdev), + TP_STRUCT__entry( + __field(struct urb*, urb) + __field(struct pwc_frame_buf*, fbuf) + __field(int, fbuf__filled) + __string(name, pdev->v4l2_dev.name) + ), + TP_fast_assign( + __entry->urb = urb; + __entry->fbuf = pdev->fill_buf; + __entry->fbuf__filled = pdev->fill_buf->filled; + __assign_str(name, pdev->v4l2_dev.name); + ), + TP_printk(" dev=%s (fbuf=%p filled=%d) urb=%p", + __get_str(name), + __entry->fbuf, + __entry->fbuf__filled, + __entry->urb) +); + +#endif /* _TRACE_PWC_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 66e988e96b31d0c06471234cabb0a77316841fc3 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Thu, 13 Dec 2018 08:31:07 -0500 Subject: media: Change Andrzej Pietrasiewicz's e-mail address My @samsung.com address is going to cease existing soon, so change it to an address which can actually be used to contact me. Signed-off-by: Andrzej Pietrasiewicz Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-dma-sg.c | 2 +- drivers/media/platform/s5p-jpeg/jpeg-core.c | 4 ++-- drivers/media/platform/s5p-jpeg/jpeg-core.h | 2 +- drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c | 2 +- drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.h | 2 +- drivers/media/platform/s5p-jpeg/jpeg-regs.h | 2 +- include/media/videobuf2-dma-sg.h | 2 +- 7 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index 015e737095cd..f02876d971d7 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -3,7 +3,7 @@ * * Copyright (C) 2010 Samsung Electronics * - * Author: Andrzej Pietrasiewicz + * Author: Andrzej Pietrasiewicz * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c index 3f9000b70385..580d6d02557b 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-core.c +++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c @@ -3,7 +3,7 @@ * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd. * http://www.samsung.com * - * Author: Andrzej Pietrasiewicz + * Author: Andrzej Pietrasiewicz * Author: Jacek Anaszewski * * This program is free software; you can redistribute it and/or modify @@ -3220,7 +3220,7 @@ static struct platform_driver s5p_jpeg_driver = { module_platform_driver(s5p_jpeg_driver); -MODULE_AUTHOR("Andrzej Pietrasiewicz "); +MODULE_AUTHOR("Andrzej Pietrasiewicz "); MODULE_AUTHOR("Jacek Anaszewski "); MODULE_DESCRIPTION("Samsung JPEG codec driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.h b/drivers/media/platform/s5p-jpeg/jpeg-core.h index a46465e10351..90fda4b720eb 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-core.h +++ b/drivers/media/platform/s5p-jpeg/jpeg-core.h @@ -3,7 +3,7 @@ * Copyright (c) 2011 Samsung Electronics Co., Ltd. * http://www.samsung.com * - * Author: Andrzej Pietrasiewicz + * Author: Andrzej Pietrasiewicz * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as diff --git a/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c b/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c index b5f20e722b63..59c6263a71bf 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c +++ b/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c @@ -3,7 +3,7 @@ * Copyright (c) 2011 Samsung Electronics Co., Ltd. * http://www.samsung.com * - * Author: Andrzej Pietrasiewicz + * Author: Andrzej Pietrasiewicz * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as diff --git a/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.h b/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.h index f208fa3ed738..bfe746f8f750 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.h +++ b/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.h @@ -3,7 +3,7 @@ * Copyright (c) 2011 Samsung Electronics Co., Ltd. * http://www.samsung.com * - * Author: Andrzej Pietrasiewicz + * Author: Andrzej Pietrasiewicz * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as diff --git a/drivers/media/platform/s5p-jpeg/jpeg-regs.h b/drivers/media/platform/s5p-jpeg/jpeg-regs.h index df790b10140c..574f0e8021e5 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-regs.h +++ b/drivers/media/platform/s5p-jpeg/jpeg-regs.h @@ -5,7 +5,7 @@ * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd. * http://www.samsung.com * - * Author: Andrzej Pietrasiewicz + * Author: Andrzej Pietrasiewicz * Author: Jacek Anaszewski * * This program is free software; you can redistribute it and/or modify diff --git a/include/media/videobuf2-dma-sg.h b/include/media/videobuf2-dma-sg.h index 52afa0e2bb17..f28fcb0cfac7 100644 --- a/include/media/videobuf2-dma-sg.h +++ b/include/media/videobuf2-dma-sg.h @@ -3,7 +3,7 @@ * * Copyright (C) 2010 Samsung Electronics * - * Author: Andrzej Pietrasiewicz + * Author: Andrzej Pietrasiewicz * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by -- cgit v1.2.3 From 4b837c6d7ee771f68a30f362c9f68171a95be222 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 14 Jan 2019 09:01:54 -0500 Subject: media: v4l: uAPI: V4L2_BUF_TYPE_META_OUTPUT is an output buffer type V4L2_BUF_TYPE_META_OUTPUT was added by commit 72148d1a57e7 ("media: v4l: Add support for V4L2_BUF_TYPE_META_OUTPUT") but the patch missed adding the type to the macro telling whether a given type is an output type or not. Do that now. Getting this wrong leads to handling the buffer as a capture buffer in a lot of places. Fixes: 72148d1a57e7 ("media: v4l: Add support for V4L2_BUF_TYPE_META_OUTPUT") Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index d6eed479c3a6..c0c36c165bf4 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -161,7 +161,8 @@ enum v4l2_buf_type { || (type) == V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY \ || (type) == V4L2_BUF_TYPE_VBI_OUTPUT \ || (type) == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT \ - || (type) == V4L2_BUF_TYPE_SDR_OUTPUT) + || (type) == V4L2_BUF_TYPE_SDR_OUTPUT \ + || (type) == V4L2_BUF_TYPE_META_OUTPUT) enum v4l2_tuner_type { V4L2_TUNER_RADIO = 1, -- cgit v1.2.3 From 50656bad786d001b294764e9f047c5d5b3e4db75 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 10 Jan 2019 11:56:09 -0500 Subject: media: v4l2-ctrl: Add control to enable h.264 constrained intra prediction Allow to enable h.264 constrained intra prediction (macroblocks using intra prediction modes are not allowed to use residual data and decoded samples of neighboring macroblocks coded using inter prediction modes). This control directly corresponds to the constrained_intra_pred_flag field in the h.264 picture parameter set. Signed-off-by: Philipp Zabel Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/extended-controls.rst | 4 ++++ drivers/media/v4l2-core/v4l2-ctrls.c | 2 ++ include/uapi/linux/v4l2-controls.h | 1 + 3 files changed, 7 insertions(+) (limited to 'include') diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst index af4273aa5e85..235d0c293983 100644 --- a/Documentation/media/uapi/v4l/extended-controls.rst +++ b/Documentation/media/uapi/v4l/extended-controls.rst @@ -1154,6 +1154,10 @@ enum v4l2_mpeg_video_h264_entropy_mode - ``V4L2_CID_MPEG_VIDEO_H264_8X8_TRANSFORM (boolean)`` Enable 8X8 transform for H264. Applicable to the H264 encoder. +``V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION (boolean)`` + Enable constrained intra prediction for H264. Applicable to the H264 + encoder. + ``V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB (integer)`` Cyclic intra macroblock refresh. This is the number of continuous macroblocks refreshed every frame. Each frame a successive set of diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 8c47d8f00429..50b56185c02e 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -825,6 +825,8 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER:return "H264 Number of HC Layers"; case V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER_QP: return "H264 Set QP Value for HC Layers"; + case V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION: + return "H264 Constrained Intra Pred"; case V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP: return "MPEG4 I-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP: return "MPEG4 P-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP: return "MPEG4 B-Frame QP Value"; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 3dcfc6148f99..fd65c710b144 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -533,6 +533,7 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type { }; #define V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER (V4L2_CID_MPEG_BASE+381) #define V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER_QP (V4L2_CID_MPEG_BASE+382) +#define V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION (V4L2_CID_MPEG_BASE+383) #define V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP (V4L2_CID_MPEG_BASE+400) #define V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP (V4L2_CID_MPEG_BASE+401) #define V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP (V4L2_CID_MPEG_BASE+402) -- cgit v1.2.3 From d034696cbe5a6e00f76ca4b7869c6cdef66aebd5 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 10 Jan 2019 11:56:10 -0500 Subject: media: v4l2-ctrl: Add control for h.264 chroma qp offset Allow to add fixed quantization parameter offset between luma and chroma quantization parameters. This control directly corresponds to the chroma_qp_index_offset field of the h.264 picture parameter set. Signed-off-by: Philipp Zabel Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/extended-controls.rst | 5 +++++ drivers/media/v4l2-core/v4l2-ctrls.c | 1 + include/uapi/linux/v4l2-controls.h | 1 + 3 files changed, 7 insertions(+) (limited to 'include') diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst index 235d0c293983..00934efdc9e4 100644 --- a/Documentation/media/uapi/v4l/extended-controls.rst +++ b/Documentation/media/uapi/v4l/extended-controls.rst @@ -1158,6 +1158,11 @@ enum v4l2_mpeg_video_h264_entropy_mode - Enable constrained intra prediction for H264. Applicable to the H264 encoder. +``V4L2_CID_MPEG_VIDEO_H264_CHROMA_QP_INDEX_OFFSET (integer)`` + Specify the offset that should be added to the luma quantization + parameter to determine the chroma quantization parameter. Applicable + to the H264 encoder. + ``V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB (integer)`` Cyclic intra macroblock refresh. This is the number of continuous macroblocks refreshed every frame. Each frame a successive set of diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 50b56185c02e..99308dac2daa 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -827,6 +827,7 @@ const char *v4l2_ctrl_get_name(u32 id) return "H264 Set QP Value for HC Layers"; case V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION: return "H264 Constrained Intra Pred"; + case V4L2_CID_MPEG_VIDEO_H264_CHROMA_QP_INDEX_OFFSET: return "H264 Chroma QP Index Offset"; case V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP: return "MPEG4 I-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP: return "MPEG4 P-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP: return "MPEG4 B-Frame QP Value"; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index fd65c710b144..06479f2fb3ae 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -534,6 +534,7 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type { #define V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER (V4L2_CID_MPEG_BASE+381) #define V4L2_CID_MPEG_VIDEO_H264_HIERARCHICAL_CODING_LAYER_QP (V4L2_CID_MPEG_BASE+382) #define V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION (V4L2_CID_MPEG_BASE+383) +#define V4L2_CID_MPEG_VIDEO_H264_CHROMA_QP_INDEX_OFFSET (V4L2_CID_MPEG_BASE+384) #define V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP (V4L2_CID_MPEG_BASE+400) #define V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP (V4L2_CID_MPEG_BASE+401) #define V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP (V4L2_CID_MPEG_BASE+402) -- cgit v1.2.3 From 1c3721b1f22286033abeda30b7e12439b083ed0f Mon Sep 17 00:00:00 2001 From: Steve Longerbeam Date: Wed, 9 Jan 2019 13:30:04 -0500 Subject: media: videodev2.h: Add more field helper macros Adds two helper macros: V4L2_FIELD_IS_SEQUENTIAL: returns true if the given field type is 'sequential', that is a full frame is transmitted, or exists in memory, as all top field lines followed by all bottom field lines, or vice-versa. V4L2_FIELD_IS_INTERLACED: returns true if the given field type is 'interlaced', that is a full frame is transmitted, or exists in memory, as top field lines interlaced with bottom field lines. Signed-off-by: Steve Longerbeam Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c0c36c165bf4..9a920f071ff9 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -130,6 +130,13 @@ enum v4l2_field { ((field) == V4L2_FIELD_BOTTOM ||\ (field) == V4L2_FIELD_TOP ||\ (field) == V4L2_FIELD_ALTERNATE) +#define V4L2_FIELD_IS_INTERLACED(field) \ + ((field) == V4L2_FIELD_INTERLACED ||\ + (field) == V4L2_FIELD_INTERLACED_TB ||\ + (field) == V4L2_FIELD_INTERLACED_BT) +#define V4L2_FIELD_IS_SEQUENTIAL(field) \ + ((field) == V4L2_FIELD_SEQ_TB ||\ + (field) == V4L2_FIELD_SEQ_BT) enum v4l2_buf_type { V4L2_BUF_TYPE_VIDEO_CAPTURE = 1, -- cgit v1.2.3 From fc8c723852380b0f4349bb06cf553a6bba47462e Mon Sep 17 00:00:00 2001 From: Steve Longerbeam Date: Wed, 9 Jan 2019 13:30:05 -0500 Subject: media: gpu: ipu-csi: Swap fields according to input/output field types The function ipu_csi_init_interface() was inverting the F-bit for NTSC case, in the CCIR_CODE_1/2 registers. The result being that for NTSC bottom-top field order, the CSI would swap fields and capture in top-bottom order. Instead, base field swap on the field order of the input to the CSI, and the field order of the requested output. If the input/output fields are sequential but different, swap fields, otherwise do not swap. This requires passing both the input and output mbus frame formats to ipu_csi_init_interface(). Move this code to a new private function ipu_csi_set_bt_interlaced_codes() that programs the CCIR_CODE_1/2 registers for interlaced BT.656 (and possibly interlaced BT.1120 in the future). When detecting input video standard from the input frame width/height, make sure to double height if input field type is alternate, since in that case input height only includes lines for one field. Signed-off-by: Steve Longerbeam Reviewed-by: Philipp Zabel Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/gpu/ipu-v3/ipu-csi.c | 126 ++++++++++++++++++++---------- drivers/staging/media/imx/imx-media-csi.c | 7 +- include/video/imx-ipu-v3.h | 5 +- 3 files changed, 89 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c index aa0e30a2ba18..d1e575571a8d 100644 --- a/drivers/gpu/ipu-v3/ipu-csi.c +++ b/drivers/gpu/ipu-v3/ipu-csi.c @@ -325,12 +325,21 @@ static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code, return 0; } +/* translate alternate field mode based on given standard */ +static inline enum v4l2_field +ipu_csi_translate_field(enum v4l2_field field, v4l2_std_id std) +{ + return (field != V4L2_FIELD_ALTERNATE) ? field : + ((std & V4L2_STD_525_60) ? + V4L2_FIELD_SEQ_BT : V4L2_FIELD_SEQ_TB); +} + /* * Fill a CSI bus config struct from mbus_config and mbus_framefmt. */ static int fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg, - struct v4l2_mbus_config *mbus_cfg, - struct v4l2_mbus_framefmt *mbus_fmt) + const struct v4l2_mbus_config *mbus_cfg, + const struct v4l2_mbus_framefmt *mbus_fmt) { int ret; @@ -374,22 +383,76 @@ static int fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg, return 0; } +static int +ipu_csi_set_bt_interlaced_codes(struct ipu_csi *csi, + const struct v4l2_mbus_framefmt *infmt, + const struct v4l2_mbus_framefmt *outfmt, + v4l2_std_id std) +{ + enum v4l2_field infield, outfield; + bool swap_fields; + + /* get translated field type of input and output */ + infield = ipu_csi_translate_field(infmt->field, std); + outfield = ipu_csi_translate_field(outfmt->field, std); + + /* + * Write the H-V-F codes the CSI will match against the + * incoming data for start/end of active and blanking + * field intervals. If input and output field types are + * sequential but not the same (one is SEQ_BT and the other + * is SEQ_TB), swap the F-bit so that the CSI will capture + * field 1 lines before field 0 lines. + */ + swap_fields = (V4L2_FIELD_IS_SEQUENTIAL(infield) && + V4L2_FIELD_IS_SEQUENTIAL(outfield) && + infield != outfield); + + if (!swap_fields) { + /* + * Field0BlankEnd = 110, Field0BlankStart = 010 + * Field0ActiveEnd = 100, Field0ActiveStart = 000 + * Field1BlankEnd = 111, Field1BlankStart = 011 + * Field1ActiveEnd = 101, Field1ActiveStart = 001 + */ + ipu_csi_write(csi, 0x40596 | CSI_CCIR_ERR_DET_EN, + CSI_CCIR_CODE_1); + ipu_csi_write(csi, 0xD07DF, CSI_CCIR_CODE_2); + } else { + dev_dbg(csi->ipu->dev, "capture field swap\n"); + + /* same as above but with F-bit inverted */ + ipu_csi_write(csi, 0xD07DF | CSI_CCIR_ERR_DET_EN, + CSI_CCIR_CODE_1); + ipu_csi_write(csi, 0x40596, CSI_CCIR_CODE_2); + } + + ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3); + + return 0; +} + + int ipu_csi_init_interface(struct ipu_csi *csi, - struct v4l2_mbus_config *mbus_cfg, - struct v4l2_mbus_framefmt *mbus_fmt) + const struct v4l2_mbus_config *mbus_cfg, + const struct v4l2_mbus_framefmt *infmt, + const struct v4l2_mbus_framefmt *outfmt) { struct ipu_csi_bus_config cfg; unsigned long flags; u32 width, height, data = 0; + v4l2_std_id std; int ret; - ret = fill_csi_bus_cfg(&cfg, mbus_cfg, mbus_fmt); + ret = fill_csi_bus_cfg(&cfg, mbus_cfg, infmt); if (ret < 0) return ret; /* set default sensor frame width and height */ - width = mbus_fmt->width; - height = mbus_fmt->height; + width = infmt->width; + height = infmt->height; + if (infmt->field == V4L2_FIELD_ALTERNATE) + height *= 2; /* Set the CSI_SENS_CONF register remaining fields */ data |= cfg.data_width << CSI_SENS_CONF_DATA_WIDTH_SHIFT | @@ -416,42 +479,22 @@ int ipu_csi_init_interface(struct ipu_csi *csi, ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3); break; case IPU_CSI_CLK_MODE_CCIR656_INTERLACED: - if (mbus_fmt->width == 720 && mbus_fmt->height == 576) { - /* - * PAL case - * - * Field0BlankEnd = 0x6, Field0BlankStart = 0x2, - * Field0ActiveEnd = 0x4, Field0ActiveStart = 0 - * Field1BlankEnd = 0x7, Field1BlankStart = 0x3, - * Field1ActiveEnd = 0x5, Field1ActiveStart = 0x1 - */ - height = 625; /* framelines for PAL */ - - ipu_csi_write(csi, 0x40596 | CSI_CCIR_ERR_DET_EN, - CSI_CCIR_CODE_1); - ipu_csi_write(csi, 0xD07DF, CSI_CCIR_CODE_2); - ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3); - } else if (mbus_fmt->width == 720 && mbus_fmt->height == 480) { - /* - * NTSC case - * - * Field0BlankEnd = 0x7, Field0BlankStart = 0x3, - * Field0ActiveEnd = 0x5, Field0ActiveStart = 0x1 - * Field1BlankEnd = 0x6, Field1BlankStart = 0x2, - * Field1ActiveEnd = 0x4, Field1ActiveStart = 0 - */ - height = 525; /* framelines for NTSC */ - - ipu_csi_write(csi, 0xD07DF | CSI_CCIR_ERR_DET_EN, - CSI_CCIR_CODE_1); - ipu_csi_write(csi, 0x40596, CSI_CCIR_CODE_2); - ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3); + if (width == 720 && height == 480) { + std = V4L2_STD_NTSC; + height = 525; + } else if (width == 720 && height == 576) { + std = V4L2_STD_PAL; + height = 625; } else { dev_err(csi->ipu->dev, - "Unsupported CCIR656 interlaced video mode\n"); - spin_unlock_irqrestore(&csi->lock, flags); - return -EINVAL; + "Unsupported interlaced video mode\n"); + ret = -EINVAL; + goto out_unlock; } + + ret = ipu_csi_set_bt_interlaced_codes(csi, infmt, outfmt, std); + if (ret) + goto out_unlock; break; case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_DDR: case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_SDR: @@ -476,9 +519,10 @@ int ipu_csi_init_interface(struct ipu_csi *csi, dev_dbg(csi->ipu->dev, "CSI_ACT_FRM_SIZE = 0x%08X\n", ipu_csi_read(csi, CSI_ACT_FRM_SIZE)); +out_unlock: spin_unlock_irqrestore(&csi->lock, flags); - return 0; + return ret; } EXPORT_SYMBOL_GPL(ipu_csi_init_interface); diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c index 4223f8d418ae..c2a8d9cd31b7 100644 --- a/drivers/staging/media/imx/imx-media-csi.c +++ b/drivers/staging/media/imx/imx-media-csi.c @@ -679,12 +679,7 @@ static int csi_setup(struct csi_priv *priv) priv->upstream_ep.bus.parallel.flags : priv->upstream_ep.bus.mipi_csi2.flags; - /* - * we need to pass input frame to CSI interface, but - * with translated field type from output format - */ if_fmt = *infmt; - if_fmt.field = outfmt->field; crop = priv->crop; /* @@ -702,7 +697,7 @@ static int csi_setup(struct csi_priv *priv) priv->crop.width == 2 * priv->compose.width, priv->crop.height == 2 * priv->compose.height); - ipu_csi_init_interface(priv->csi, &mbus_cfg, &if_fmt); + ipu_csi_init_interface(priv->csi, &mbus_cfg, &if_fmt, outfmt); ipu_csi_set_dest(priv->csi, priv->dest); diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index e582e8e7527a..bbc8481f567d 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -354,8 +354,9 @@ int ipu_prg_channel_configure(struct ipuv3_channel *ipu_chan, */ struct ipu_csi; int ipu_csi_init_interface(struct ipu_csi *csi, - struct v4l2_mbus_config *mbus_cfg, - struct v4l2_mbus_framefmt *mbus_fmt); + const struct v4l2_mbus_config *mbus_cfg, + const struct v4l2_mbus_framefmt *infmt, + const struct v4l2_mbus_framefmt *outfmt); bool ipu_csi_is_interlaced(struct ipu_csi *csi); void ipu_csi_get_window(struct ipu_csi *csi, struct v4l2_rect *w); void ipu_csi_set_window(struct ipu_csi *csi, struct v4l2_rect *w); -- cgit v1.2.3 From 9b5c8d5ffb20cc4f4b1476cb1ad57e0f9b934788 Mon Sep 17 00:00:00 2001 From: Steve Longerbeam Date: Wed, 9 Jan 2019 13:30:06 -0500 Subject: media: gpu: ipu-v3: Add planar support to interlaced scan To support interlaced scan with planar formats, cpmem SLUV must be programmed with the correct chroma line stride. For full and partial planar 4:2:2 (YUV422P, NV16), chroma line stride must be doubled. For full and partial planar 4:2:0 (YUV420, YVU420, NV12), chroma line stride must _not_ be doubled, since a single chroma line is shared by two luma lines. Signed-off-by: Steve Longerbeam Reviewed-by: Philipp Zabel Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/gpu/ipu-v3/ipu-cpmem.c | 26 ++++++++++++++++++++++++-- drivers/staging/media/imx/imx-ic-prpencvf.c | 3 ++- drivers/staging/media/imx/imx-media-csi.c | 3 ++- include/video/imx-ipu-v3.h | 3 ++- 4 files changed, 30 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c index 163fadb8a33a..d047a6867c59 100644 --- a/drivers/gpu/ipu-v3/ipu-cpmem.c +++ b/drivers/gpu/ipu-v3/ipu-cpmem.c @@ -277,9 +277,10 @@ void ipu_cpmem_set_uv_offset(struct ipuv3_channel *ch, u32 u_off, u32 v_off) } EXPORT_SYMBOL_GPL(ipu_cpmem_set_uv_offset); -void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride) +void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride, + u32 pixelformat) { - u32 ilo, sly; + u32 ilo, sly, sluv; if (stride < 0) { stride = -stride; @@ -290,9 +291,30 @@ void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride) sly = (stride * 2) - 1; + switch (pixelformat) { + case V4L2_PIX_FMT_YUV420: + case V4L2_PIX_FMT_YVU420: + sluv = stride / 2 - 1; + break; + case V4L2_PIX_FMT_NV12: + sluv = stride - 1; + break; + case V4L2_PIX_FMT_YUV422P: + sluv = stride - 1; + break; + case V4L2_PIX_FMT_NV16: + sluv = stride * 2 - 1; + break; + default: + sluv = 0; + break; + } + ipu_ch_param_write_field(ch, IPU_FIELD_SO, 1); ipu_ch_param_write_field(ch, IPU_FIELD_ILO, ilo); ipu_ch_param_write_field(ch, IPU_FIELD_SLY, sly); + if (sluv) + ipu_ch_param_write_field(ch, IPU_FIELD_SLUV, sluv); }; EXPORT_SYMBOL_GPL(ipu_cpmem_interlaced_scan); diff --git a/drivers/staging/media/imx/imx-ic-prpencvf.c b/drivers/staging/media/imx/imx-ic-prpencvf.c index 28f41caba05d..af7224846bd5 100644 --- a/drivers/staging/media/imx/imx-ic-prpencvf.c +++ b/drivers/staging/media/imx/imx-ic-prpencvf.c @@ -412,7 +412,8 @@ static int prp_setup_channel(struct prp_priv *priv, if (image.pix.field == V4L2_FIELD_NONE && V4L2_FIELD_HAS_BOTH(infmt->field) && channel == priv->out_ch) - ipu_cpmem_interlaced_scan(channel, image.pix.bytesperline); + ipu_cpmem_interlaced_scan(channel, image.pix.bytesperline, + image.pix.pixelformat); ret = ipu_ic_task_idma_init(priv->ic, channel, image.pix.width, image.pix.height, diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c index c2a8d9cd31b7..da4808348845 100644 --- a/drivers/staging/media/imx/imx-media-csi.c +++ b/drivers/staging/media/imx/imx-media-csi.c @@ -512,7 +512,8 @@ static int csi_idmac_setup_channel(struct csi_priv *priv) if (image.pix.field == V4L2_FIELD_NONE && V4L2_FIELD_HAS_BOTH(infmt->field)) ipu_cpmem_interlaced_scan(priv->idmac_ch, - image.pix.bytesperline); + image.pix.bytesperline, + image.pix.pixelformat); ipu_idmac_set_double_buffer(priv->idmac_ch, true); diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index bbc8481f567d..c887f4bee5f8 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -258,7 +258,8 @@ void ipu_cpmem_set_stride(struct ipuv3_channel *ch, int stride); void ipu_cpmem_set_high_priority(struct ipuv3_channel *ch); void ipu_cpmem_set_buffer(struct ipuv3_channel *ch, int bufnum, dma_addr_t buf); void ipu_cpmem_set_uv_offset(struct ipuv3_channel *ch, u32 u_off, u32 v_off); -void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride); +void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride, + u32 pixelformat); void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id); int ipu_cpmem_get_burstsize(struct ipuv3_channel *ch); void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize); -- cgit v1.2.3 From 8e1f456129e61371fb190c71ea182a9f6e21282e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 9 Jan 2019 15:44:46 +0100 Subject: leds: Add helper for getting default pattern from Device Tree Multiple LED triggers might need to access default pattern so add a helper for that. Signed-off-by: Krzysztof Kozlowski Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- drivers/leds/led-core.c | 30 ++++++++++++++++++++++++++++++ include/linux/leds.h | 13 +++++++++++++ 2 files changed, 43 insertions(+) (limited to 'include') diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index ede4fa0ac2cc..e3da7c03da1b 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -16,7 +16,9 @@ #include #include #include +#include #include +#include #include "leds.h" DECLARE_RWSEM(leds_list_lock); @@ -310,6 +312,34 @@ int led_update_brightness(struct led_classdev *led_cdev) } EXPORT_SYMBOL_GPL(led_update_brightness); +u32 *led_get_default_pattern(struct led_classdev *led_cdev, unsigned int *size) +{ + struct device_node *np = dev_of_node(led_cdev->dev); + u32 *pattern; + int count; + + if (!np) + return NULL; + + count = of_property_count_u32_elems(np, "led-pattern"); + if (count < 0) + return NULL; + + pattern = kcalloc(count, sizeof(*pattern), GFP_KERNEL); + if (!pattern) + return NULL; + + if (of_property_read_u32_array(np, "led-pattern", pattern, count)) { + kfree(pattern); + return NULL; + } + + *size = count; + + return pattern; +} +EXPORT_SYMBOL_GPL(led_get_default_pattern); + /* Caller must ensure led_cdev->led_access held */ void led_sysfs_disable(struct led_classdev *led_cdev) { diff --git a/include/linux/leds.h b/include/linux/leds.h index 5263f87e1d2c..78204650fe2a 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -218,6 +218,19 @@ extern int led_set_brightness_sync(struct led_classdev *led_cdev, */ extern int led_update_brightness(struct led_classdev *led_cdev); +/** + * led_get_default_pattern - return default pattern + * + * @led_cdev: the LED to get default pattern for + * @size: pointer for storing the number of elements in returned array, + * modified only if return != NULL + * + * Return: Allocated array of integers with default pattern from device tree + * or NULL. Caller is responsible for kfree(). + */ +extern u32 *led_get_default_pattern(struct led_classdev *led_cdev, + unsigned int *size); + /** * led_sysfs_disable - disable LED sysfs interface * @led_cdev: the LED to set -- cgit v1.2.3 From da7b9e9b00d4859d0fa563d7fe9a2b2dff59e852 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 15 Jan 2019 14:43:04 -0800 Subject: net: dsa: Add ndo_get_phys_port_name() for CPU port There is not currently way to infer the port number through sysfs that is being used as the CPU port number. Overlay a ndo_get_phys_port_name() operation onto the DSA master network device in order to retrieve that information. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 5 +++++ net/dsa/master.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 60 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index b3eefe8e18fd..2f1daf29131a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -208,6 +208,11 @@ struct dsa_port { * Original copy of the master netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; + + /* + * Original copy of the master netdev net_device_ops + */ + const struct net_device_ops *orig_ndo_ops; }; struct dsa_switch { diff --git a/net/dsa/master.c b/net/dsa/master.c index 71bb15f491c8..79e97d2f2d9b 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -126,6 +126,17 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, } } +static int dsa_master_get_phys_port_name(struct net_device *dev, + char *name, size_t len) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + + if (snprintf(name, len, "p%d", cpu_dp->index) >= len) + return -EINVAL; + + return 0; +} + static int dsa_master_ethtool_setup(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -158,6 +169,38 @@ static void dsa_master_ethtool_teardown(struct net_device *dev) cpu_dp->orig_ethtool_ops = NULL; } +static int dsa_master_ndo_setup(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch *ds = cpu_dp->ds; + struct net_device_ops *ops; + + if (dev->netdev_ops->ndo_get_phys_port_name) + return 0; + + ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + cpu_dp->orig_ndo_ops = dev->netdev_ops; + if (cpu_dp->orig_ndo_ops) + memcpy(ops, cpu_dp->orig_ndo_ops, sizeof(*ops)); + + ops->ndo_get_phys_port_name = dsa_master_get_phys_port_name; + + dev->netdev_ops = ops; + + return 0; +} + +static void dsa_master_ndo_teardown(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + + dev->netdev_ops = cpu_dp->orig_ndo_ops; + cpu_dp->orig_ndo_ops = NULL; +} + static ssize_t tagging_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -223,16 +266,27 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) if (ret) return ret; + ret = dsa_master_ndo_setup(dev); + if (ret) + goto out_err_ethtool_teardown; + ret = sysfs_create_group(&dev->dev.kobj, &dsa_group); if (ret) - dsa_master_ethtool_teardown(dev); + goto out_err_ndo_teardown; + + return ret; +out_err_ndo_teardown: + dsa_master_ndo_teardown(dev); +out_err_ethtool_teardown: + dsa_master_ethtool_teardown(dev); return ret; } void dsa_master_teardown(struct net_device *dev) { sysfs_remove_group(&dev->dev.kobj, &dsa_group); + dsa_master_ndo_teardown(dev); dsa_master_ethtool_teardown(dev); dsa_master_reset_mtu(dev); -- cgit v1.2.3 From fcd44b64b1eb0a33f6cc14f21dcb927ffd664af3 Mon Sep 17 00:00:00 2001 From: Yogesh Narayan Gaur Date: Tue, 15 Jan 2019 10:05:10 +0000 Subject: mtd: spi-nor: add opcodes for octal Read/Write commands - Add opcodes for octal I/O commands * Read : 1-1-8 and 1-8-8 protocol * Write : 1-1-8 and 1-8-8 protocol * opcodes for 4-byte address mode command - Entry of macros in _convert_3to4_xxx function - Add flag SPI_NOR_OCTAL_READ specifying flash support octal read commands. This flag is required for flashes which didn't provides support for auto detection of Octal mode capabilities i.e. not seems to support newer JESD216C standard. Signed-off-by: Vignesh R Signed-off-by: Yogesh Narayan Gaur Reviewed-by: Tudor Ambarus Signed-off-by: Boris Brezillon --- drivers/mtd/spi-nor/spi-nor.c | 16 ++++++++++++++-- include/linux/mtd/spi-nor.h | 16 ++++++++++++---- 2 files changed, 26 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 6e13bbd1aaa5..872d70722672 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -68,7 +68,7 @@ enum spi_nor_read_command_index { SNOR_CMD_READ_4_4_4, SNOR_CMD_READ_1_4_4_DTR, - /* Octo SPI */ + /* Octal SPI */ SNOR_CMD_READ_1_1_8, SNOR_CMD_READ_1_8_8, SNOR_CMD_READ_8_8_8, @@ -85,7 +85,7 @@ enum spi_nor_pp_command_index { SNOR_CMD_PP_1_4_4, SNOR_CMD_PP_4_4_4, - /* Octo SPI */ + /* Octal SPI */ SNOR_CMD_PP_1_1_8, SNOR_CMD_PP_1_8_8, SNOR_CMD_PP_8_8_8, @@ -278,6 +278,7 @@ struct flash_info { #define NO_CHIP_ERASE BIT(12) /* Chip does not support chip erase */ #define SPI_NOR_SKIP_SFDP BIT(13) /* Skip parsing of SFDP tables */ #define USE_CLSR BIT(14) /* use CLSR command */ +#define SPI_NOR_OCTAL_READ BIT(15) /* Flash supports Octal Read */ /* Part specific fixup hooks. */ const struct spi_nor_fixups *fixups; @@ -398,6 +399,8 @@ static u8 spi_nor_convert_3to4_read(u8 opcode) { SPINOR_OP_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B }, { SPINOR_OP_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B }, { SPINOR_OP_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B }, + { SPINOR_OP_READ_1_1_8, SPINOR_OP_READ_1_1_8_4B }, + { SPINOR_OP_READ_1_8_8, SPINOR_OP_READ_1_8_8_4B }, { SPINOR_OP_READ_1_1_1_DTR, SPINOR_OP_READ_1_1_1_DTR_4B }, { SPINOR_OP_READ_1_2_2_DTR, SPINOR_OP_READ_1_2_2_DTR_4B }, @@ -414,6 +417,8 @@ static u8 spi_nor_convert_3to4_program(u8 opcode) { SPINOR_OP_PP, SPINOR_OP_PP_4B }, { SPINOR_OP_PP_1_1_4, SPINOR_OP_PP_1_1_4_4B }, { SPINOR_OP_PP_1_4_4, SPINOR_OP_PP_1_4_4_4B }, + { SPINOR_OP_PP_1_1_8, SPINOR_OP_PP_1_1_8_4B }, + { SPINOR_OP_PP_1_8_8, SPINOR_OP_PP_1_8_8_4B }, }; return spi_nor_convert_opcode(opcode, spi_nor_3to4_program, @@ -3591,6 +3596,13 @@ static int spi_nor_init_params(struct spi_nor *nor, SNOR_PROTO_1_1_4); } + if (info->flags & SPI_NOR_OCTAL_READ) { + params->hwcaps.mask |= SNOR_HWCAPS_READ_1_1_8; + spi_nor_set_read_settings(¶ms->reads[SNOR_CMD_READ_1_1_8], + 0, 8, SPINOR_OP_READ_1_1_8, + SNOR_PROTO_1_1_8); + } + /* Page Program settings. */ params->hwcaps.mask |= SNOR_HWCAPS_PP; spi_nor_set_pp_settings(¶ms->page_programs[SNOR_CMD_PP], diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index fa2d89e38e40..2353af8bac99 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -46,9 +46,13 @@ #define SPINOR_OP_READ_1_2_2 0xbb /* Read data bytes (Dual I/O SPI) */ #define SPINOR_OP_READ_1_1_4 0x6b /* Read data bytes (Quad Output SPI) */ #define SPINOR_OP_READ_1_4_4 0xeb /* Read data bytes (Quad I/O SPI) */ +#define SPINOR_OP_READ_1_1_8 0x8b /* Read data bytes (Octal Output SPI) */ +#define SPINOR_OP_READ_1_8_8 0xcb /* Read data bytes (Octal I/O SPI) */ #define SPINOR_OP_PP 0x02 /* Page program (up to 256 bytes) */ #define SPINOR_OP_PP_1_1_4 0x32 /* Quad page program */ #define SPINOR_OP_PP_1_4_4 0x38 /* Quad page program */ +#define SPINOR_OP_PP_1_1_8 0x82 /* Octal page program */ +#define SPINOR_OP_PP_1_8_8 0xc2 /* Octal page program */ #define SPINOR_OP_BE_4K 0x20 /* Erase 4KiB block */ #define SPINOR_OP_BE_4K_PMC 0xd7 /* Erase 4KiB block on PMC chips */ #define SPINOR_OP_BE_32K 0x52 /* Erase 32KiB block */ @@ -69,9 +73,13 @@ #define SPINOR_OP_READ_1_2_2_4B 0xbc /* Read data bytes (Dual I/O SPI) */ #define SPINOR_OP_READ_1_1_4_4B 0x6c /* Read data bytes (Quad Output SPI) */ #define SPINOR_OP_READ_1_4_4_4B 0xec /* Read data bytes (Quad I/O SPI) */ +#define SPINOR_OP_READ_1_1_8_4B 0x7c /* Read data bytes (Octal Output SPI) */ +#define SPINOR_OP_READ_1_8_8_4B 0xcc /* Read data bytes (Octal I/O SPI) */ #define SPINOR_OP_PP_4B 0x12 /* Page program (up to 256 bytes) */ #define SPINOR_OP_PP_1_1_4_4B 0x34 /* Quad page program */ #define SPINOR_OP_PP_1_4_4_4B 0x3e /* Quad page program */ +#define SPINOR_OP_PP_1_1_8_4B 0x84 /* Octal page program */ +#define SPINOR_OP_PP_1_8_8_4B 0x8e /* Octal page program */ #define SPINOR_OP_BE_4K_4B 0x21 /* Erase 4KiB block */ #define SPINOR_OP_BE_32K_4B 0x5c /* Erase 32KiB block */ #define SPINOR_OP_SE_4B 0xdc /* Sector erase (usually 64KiB) */ @@ -458,7 +466,7 @@ struct spi_nor_hwcaps { /* *(Fast) Read capabilities. * MUST be ordered by priority: the higher bit position, the higher priority. - * As a matter of performances, it is relevant to use Octo SPI protocols first, + * As a matter of performances, it is relevant to use Octal SPI protocols first, * then Quad SPI protocols before Dual SPI protocols, Fast Read and lastly * (Slow) Read. */ @@ -479,7 +487,7 @@ struct spi_nor_hwcaps { #define SNOR_HWCAPS_READ_4_4_4 BIT(9) #define SNOR_HWCAPS_READ_1_4_4_DTR BIT(10) -#define SNOR_HWCPAS_READ_OCTO GENMASK(14, 11) +#define SNOR_HWCPAS_READ_OCTAL GENMASK(14, 11) #define SNOR_HWCAPS_READ_1_1_8 BIT(11) #define SNOR_HWCAPS_READ_1_8_8 BIT(12) #define SNOR_HWCAPS_READ_8_8_8 BIT(13) @@ -488,7 +496,7 @@ struct spi_nor_hwcaps { /* * Page Program capabilities. * MUST be ordered by priority: the higher bit position, the higher priority. - * Like (Fast) Read capabilities, Octo/Quad SPI protocols are preferred to the + * Like (Fast) Read capabilities, Octal/Quad SPI protocols are preferred to the * legacy SPI 1-1-1 protocol. * Note that Dual Page Programs are not supported because there is no existing * JEDEC/SFDP standard to define them. Also at this moment no SPI flash memory @@ -502,7 +510,7 @@ struct spi_nor_hwcaps { #define SNOR_HWCAPS_PP_1_4_4 BIT(18) #define SNOR_HWCAPS_PP_4_4_4 BIT(19) -#define SNOR_HWCAPS_PP_OCTO GENMASK(22, 20) +#define SNOR_HWCAPS_PP_OCTAL GENMASK(22, 20) #define SNOR_HWCAPS_PP_1_1_8 BIT(20) #define SNOR_HWCAPS_PP_1_8_8 BIT(21) #define SNOR_HWCAPS_PP_8_8_8 BIT(22) -- cgit v1.2.3 From b172fd0c898022c47161a99cb40be5304b0d3fd0 Mon Sep 17 00:00:00 2001 From: Alban Bedel Date: Wed, 16 Jan 2019 19:55:46 +0100 Subject: spi: ath79: Enable support for compile test To allow building this driver in compile test we need to remove all dependency on headers from arch/mips/include. To allow this we explicitly define all the registers locally instead of using ar71xx_regs.h and we move the platform data struct definition to include/linux/platform_data/spi-ath79.h. Signed-off-by: Alban Bedel Signed-off-by: Mark Brown --- arch/mips/ath79/dev-spi.h | 2 +- arch/mips/include/asm/mach-ath79/ath79_spi_platform.h | 19 ------------------- drivers/spi/Kconfig | 2 +- drivers/spi/spi-ath79.c | 15 ++++++++++++--- include/linux/platform_data/spi-ath79.h | 19 +++++++++++++++++++ 5 files changed, 33 insertions(+), 24 deletions(-) delete mode 100644 arch/mips/include/asm/mach-ath79/ath79_spi_platform.h create mode 100644 include/linux/platform_data/spi-ath79.h (limited to 'include') diff --git a/arch/mips/ath79/dev-spi.h b/arch/mips/ath79/dev-spi.h index d732565ca736..6e15bc8651be 100644 --- a/arch/mips/ath79/dev-spi.h +++ b/arch/mips/ath79/dev-spi.h @@ -13,7 +13,7 @@ #define _ATH79_DEV_SPI_H #include -#include +#include void ath79_register_spi(struct ath79_spi_platform_data *pdata, struct spi_board_info const *info, diff --git a/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h b/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h deleted file mode 100644 index aa71216edf99..000000000000 --- a/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * Platform data definition for Atheros AR71XX/AR724X/AR913X SPI controller - * - * Copyright (C) 2008-2010 Gabor Juhos - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. - */ - -#ifndef _ATH79_SPI_PLATFORM_H -#define _ATH79_SPI_PLATFORM_H - -struct ath79_spi_platform_data { - unsigned bus_num; - unsigned num_chipselect; -}; - -#endif /* _ATH79_SPI_PLATFORM_H */ diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index 128892c7e21e..71d3d2d5e5d1 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -63,7 +63,7 @@ config SPI_ALTERA config SPI_ATH79 tristate "Atheros AR71XX/AR724X/AR913X SPI controller driver" - depends on ATH79 + depends on ATH79 || COMPILE_TEST select SPI_BITBANG help This enables support for the SPI controller present on the diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c index edf695a359f4..09c4fb7fcf7a 100644 --- a/drivers/spi/spi-ath79.c +++ b/drivers/spi/spi-ath79.c @@ -23,15 +23,24 @@ #include #include #include - -#include -#include +#include #define DRV_NAME "ath79-spi" #define ATH79_SPI_RRW_DELAY_FACTOR 12000 #define MHZ (1000 * 1000) +#define AR71XX_SPI_REG_FS 0x00 /* Function Select */ +#define AR71XX_SPI_REG_CTRL 0x04 /* SPI Control */ +#define AR71XX_SPI_REG_IOC 0x08 /* SPI I/O Control */ +#define AR71XX_SPI_REG_RDS 0x0c /* Read Data Shift */ + +#define AR71XX_SPI_FS_GPIO BIT(0) /* Enable GPIO mode */ + +#define AR71XX_SPI_IOC_DO BIT(0) /* Data Out pin */ +#define AR71XX_SPI_IOC_CLK BIT(8) /* CLK pin */ +#define AR71XX_SPI_IOC_CS(n) BIT(16 + (n)) + struct ath79_spi { struct spi_bitbang bitbang; u32 ioc_base; diff --git a/include/linux/platform_data/spi-ath79.h b/include/linux/platform_data/spi-ath79.h new file mode 100644 index 000000000000..aa71216edf99 --- /dev/null +++ b/include/linux/platform_data/spi-ath79.h @@ -0,0 +1,19 @@ +/* + * Platform data definition for Atheros AR71XX/AR724X/AR913X SPI controller + * + * Copyright (C) 2008-2010 Gabor Juhos + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#ifndef _ATH79_SPI_PLATFORM_H +#define _ATH79_SPI_PLATFORM_H + +struct ath79_spi_platform_data { + unsigned bus_num; + unsigned num_chipselect; +}; + +#endif /* _ATH79_SPI_PLATFORM_H */ -- cgit v1.2.3 From adbb78e1104a006275e0e8e37526f617bb2a3d91 Mon Sep 17 00:00:00 2001 From: Ulrich Hecht Date: Thu, 10 Jan 2019 16:32:32 +0100 Subject: ARM: dts: r8a7778: Add HSCIF0/1 support Add HSCIF0/1 clocks and device nodes, based on Rev. 1.00 of the R-Car M1A datasheet. Signed-off-by: Ulrich Hecht [geert: Squashed two patches] [geert: Correct HSCIF1 module clock index] [geert: Correct reg properties for non-LPAE] Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm/boot/dts/r8a7778.dtsi | 28 ++++++++++++++++++++++++++++ include/dt-bindings/clock/r8a7778-clock.h | 2 ++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/arch/arm/boot/dts/r8a7778.dtsi b/arch/arm/boot/dts/r8a7778.dtsi index 05db0ccad7a6..10d996d2941f 100644 --- a/arch/arm/boot/dts/r8a7778.dtsi +++ b/arch/arm/boot/dts/r8a7778.dtsi @@ -367,6 +367,30 @@ status = "disabled"; }; + hscif0: serial@ffe48000 { + compatible = "renesas,hscif-r8a7778", + "renesas,rcar-gen1-hscif", "renesas,hscif"; + reg = <0xffe48000 96>; + interrupts = ; + clocks = <&mstp0_clks R8A7778_CLK_HSCIF0>, + <&cpg_clocks R8A7778_CLK_S>, <&scif_clk>; + clock-names = "fck", "brg_int", "scif_clk"; + power-domains = <&cpg_clocks>; + status = "disabled"; + }; + + hscif1: serial@ffe49000 { + compatible = "renesas,hscif-r8a7778", + "renesas,rcar-gen1-hscif", "renesas,hscif"; + reg = <0xffe49000 96>; + interrupts = ; + clocks = <&mstp0_clks R8A7778_CLK_HSCIF1>, + <&cpg_clocks R8A7778_CLK_S>, <&scif_clk>; + clock-names = "fck", "brg_int", "scif_clk"; + power-domains = <&cpg_clocks>; + status = "disabled"; + }; + mmcif: mmc@ffe4e000 { compatible = "renesas,mmcif-r8a7778", "renesas,sh-mmcif"; reg = <0xffe4e000 0x100>; @@ -535,6 +559,8 @@ <&cpg_clocks R8A7778_CLK_P>, <&cpg_clocks R8A7778_CLK_P>, <&cpg_clocks R8A7778_CLK_P>, + <&cpg_clocks R8A7778_CLK_S>, + <&cpg_clocks R8A7778_CLK_S>, <&cpg_clocks R8A7778_CLK_P>, <&cpg_clocks R8A7778_CLK_P>, <&cpg_clocks R8A7778_CLK_P>, @@ -551,6 +577,7 @@ R8A7778_CLK_SCIF0 R8A7778_CLK_SCIF1 R8A7778_CLK_SCIF2 R8A7778_CLK_SCIF3 R8A7778_CLK_SCIF4 R8A7778_CLK_SCIF5 + R8A7778_CLK_HSCIF0 R8A7778_CLK_HSCIF1 R8A7778_CLK_TMU0 R8A7778_CLK_TMU1 R8A7778_CLK_TMU2 R8A7778_CLK_SSI0 R8A7778_CLK_SSI1 R8A7778_CLK_SSI2 @@ -560,6 +587,7 @@ clock-output-names = "i2c0", "i2c1", "i2c2", "i2c3", "scif0", "scif1", "scif2", "scif3", "scif4", "scif5", + "hscif0", "hscif1", "tmu0", "tmu1", "tmu2", "ssi0", "ssi1", "ssi2", "ssi3", "sru", "hspi"; }; diff --git a/include/dt-bindings/clock/r8a7778-clock.h b/include/dt-bindings/clock/r8a7778-clock.h index f6b07c5399de..d0bff9ec5c66 100644 --- a/include/dt-bindings/clock/r8a7778-clock.h +++ b/include/dt-bindings/clock/r8a7778-clock.h @@ -30,6 +30,8 @@ #define R8A7778_CLK_SCIF3 23 #define R8A7778_CLK_SCIF4 22 #define R8A7778_CLK_SCIF5 21 +#define R8A7778_CLK_HSCIF0 19 +#define R8A7778_CLK_HSCIF1 18 #define R8A7778_CLK_TMU0 16 #define R8A7778_CLK_TMU1 15 #define R8A7778_CLK_TMU2 14 -- cgit v1.2.3 From 6d7fbce7da0cd06ff3f3f30e009a15a6243f0bc0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Jan 2019 12:02:57 -0500 Subject: kill kernfs_pin_sb() unused now and impossible to use safely anyway. Signed-off-by: Al Viro --- fs/kernfs/mount.c | 30 ------------------------------ include/linux/kernfs.h | 1 - 2 files changed, 31 deletions(-) (limited to 'include') diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index d71c9405874a..4d303047a4f8 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -377,36 +377,6 @@ void kernfs_kill_sb(struct super_block *sb) kfree(info); } -/** - * kernfs_pin_sb: try to pin the superblock associated with a kernfs_root - * @kernfs_root: the kernfs_root in question - * @ns: the namespace tag - * - * Pin the superblock so the superblock won't be destroyed in subsequent - * operations. This can be used to block ->kill_sb() which may be useful - * for kernfs users which dynamically manage superblocks. - * - * Returns NULL if there's no superblock associated to this kernfs_root, or - * -EINVAL if the superblock is being freed. - */ -struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns) -{ - struct kernfs_super_info *info; - struct super_block *sb = NULL; - - mutex_lock(&kernfs_mutex); - list_for_each_entry(info, &root->supers, node) { - if (info->ns == ns) { - sb = info->sb; - if (!atomic_inc_not_zero(&info->sb->s_active)) - sb = ERR_PTR(-EINVAL); - break; - } - } - mutex_unlock(&kernfs_mutex); - return sb; -} - void __init kernfs_init(void) { diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5b36b1287a5a..44acb4c3659c 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -357,7 +357,6 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, struct kernfs_root *root, unsigned long magic, bool *new_sb_created, const void *ns); void kernfs_kill_sb(struct super_block *sb); -struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns); void kernfs_init(void); -- cgit v1.2.3 From ecfc937210e5fdc6554e49b2a735ff22e72ae3f0 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 15 Jan 2019 15:06:11 -0800 Subject: net: dsa: Split platform data to header file Instead of having net/dsa.h contain both the internal switch tree/driver structures, split the relevant platform_data parts into include/linux/platform_data/dsa.h and make that header be included by net/dsa.h in order not to break any setup. A subsequent set of patches will update code including net/dsa.h to include only the platform_data header. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- MAINTAINERS | 1 + include/linux/platform_data/dsa.h | 68 +++++++++++++++++++++++++++++++++++++++ include/net/dsa.h | 61 +---------------------------------- 3 files changed, 70 insertions(+), 60 deletions(-) create mode 100644 include/linux/platform_data/dsa.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 4d04cebb4a71..a592b9992b46 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10576,6 +10576,7 @@ F: Documentation/devicetree/bindings/net/dsa/ F: net/dsa/ F: include/net/dsa.h F: include/linux/dsa/ +F: include/linux/platform_data/dsa.h F: drivers/net/dsa/ NETWORKING [GENERAL] diff --git a/include/linux/platform_data/dsa.h b/include/linux/platform_data/dsa.h new file mode 100644 index 000000000000..d4d9bf2060a6 --- /dev/null +++ b/include/linux/platform_data/dsa.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DSA_PDATA_H +#define __DSA_PDATA_H + +struct device; +struct net_device; + +#define DSA_MAX_SWITCHES 4 +#define DSA_MAX_PORTS 12 +#define DSA_RTABLE_NONE -1 + +struct dsa_chip_data { + /* + * How to access the switch configuration registers. + */ + struct device *host_dev; + int sw_addr; + + /* + * Reference to network devices + */ + struct device *netdev[DSA_MAX_PORTS]; + + /* set to size of eeprom if supported by the switch */ + int eeprom_len; + + /* Device tree node pointer for this specific switch chip + * used during switch setup in case additional properties + * and resources needs to be used + */ + struct device_node *of_node; + + /* + * The names of the switch's ports. Use "cpu" to + * designate the switch port that the cpu is connected to, + * "dsa" to indicate that this port is a DSA link to + * another switch, NULL to indicate the port is unused, + * or any other string to indicate this is a physical port. + */ + char *port_names[DSA_MAX_PORTS]; + struct device_node *port_dn[DSA_MAX_PORTS]; + + /* + * An array of which element [a] indicates which port on this + * switch should be used to send packets to that are destined + * for switch a. Can be NULL if there is only one switch chip. + */ + s8 rtable[DSA_MAX_SWITCHES]; +}; + +struct dsa_platform_data { + /* + * Reference to a Linux network interface that connects + * to the root switch chip of the tree. + */ + struct device *netdev; + struct net_device *of_netdev; + + /* + * Info structs describing each of the switch chips + * connected via this network interface. + */ + int nr_chips; + struct dsa_chip_data *chip; +}; + + +#endif /* __DSA_PDATA_H */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 2f1daf29131a..7f2a668ef2cc 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -44,66 +45,6 @@ enum dsa_tag_protocol { DSA_TAG_LAST, /* MUST BE LAST */ }; -#define DSA_MAX_SWITCHES 4 -#define DSA_MAX_PORTS 12 - -#define DSA_RTABLE_NONE -1 - -struct dsa_chip_data { - /* - * How to access the switch configuration registers. - */ - struct device *host_dev; - int sw_addr; - - /* - * Reference to network devices - */ - struct device *netdev[DSA_MAX_PORTS]; - - /* set to size of eeprom if supported by the switch */ - int eeprom_len; - - /* Device tree node pointer for this specific switch chip - * used during switch setup in case additional properties - * and resources needs to be used - */ - struct device_node *of_node; - - /* - * The names of the switch's ports. Use "cpu" to - * designate the switch port that the cpu is connected to, - * "dsa" to indicate that this port is a DSA link to - * another switch, NULL to indicate the port is unused, - * or any other string to indicate this is a physical port. - */ - char *port_names[DSA_MAX_PORTS]; - struct device_node *port_dn[DSA_MAX_PORTS]; - - /* - * An array of which element [a] indicates which port on this - * switch should be used to send packets to that are destined - * for switch a. Can be NULL if there is only one switch chip. - */ - s8 rtable[DSA_MAX_SWITCHES]; -}; - -struct dsa_platform_data { - /* - * Reference to a Linux network interface that connects - * to the root switch chip of the tree. - */ - struct device *netdev; - struct net_device *of_netdev; - - /* - * Info structs describing each of the switch chips - * connected via this network interface. - */ - int nr_chips; - struct dsa_chip_data *chip; -}; - struct packet_type; struct dsa_switch; -- cgit v1.2.3 From 8cfb5faf32e85b62f08cfe242ce80b2864d0b8f3 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 15 Jan 2019 15:06:13 -0800 Subject: net: dsa: Include platform_data header file b53 and mv88e6xxx support passing platform_data, and now that we have split the platform_data portion from the main net/dsa.h header file, include only the relevant parts. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/b53.h | 2 +- include/linux/platform_data/mv88e6xxx.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/b53.h b/include/linux/platform_data/b53.h index 8eaef2f2b691..c3b61ead41f2 100644 --- a/include/linux/platform_data/b53.h +++ b/include/linux/platform_data/b53.h @@ -20,7 +20,7 @@ #define __B53_H #include -#include +#include struct b53_platform_data { /* Must be first such that dsa_register_switch() can access it */ diff --git a/include/linux/platform_data/mv88e6xxx.h b/include/linux/platform_data/mv88e6xxx.h index f63af2955ea0..963730b44aea 100644 --- a/include/linux/platform_data/mv88e6xxx.h +++ b/include/linux/platform_data/mv88e6xxx.h @@ -2,7 +2,7 @@ #ifndef __DSA_MV88E6XXX_H #define __DSA_MV88E6XXX_H -#include +#include struct dsa_mv88e6xxx_pdata { /* Must be first, such that dsa_register_switch() can access this -- cgit v1.2.3 From 5db5ea995fc2fa89fdef61ef3a658cbb41a24222 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 15 Jan 2019 15:09:35 -0800 Subject: net: phy: Add helpers to determine if PHY driver is generic We are already checking in phy_detach() that the PHY driver is of generic kind (1G or 10G) and we are going to make use of that in the SFP layer as well for 1000BaseT SFP modules, so expose helper functions to return that information. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 34 ++++++++++++++++++++++++++++++++-- include/linux/phy.h | 3 +++ 2 files changed, 35 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index bb1410821ce4..c02669270c41 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1277,6 +1277,36 @@ struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, } EXPORT_SYMBOL(phy_attach); +static bool phy_driver_is_genphy_kind(struct phy_device *phydev, + struct device_driver *driver) +{ + struct device *d = &phydev->mdio.dev; + bool ret = false; + + if (!phydev->drv) + return ret; + + get_device(d); + ret = d->driver == driver; + put_device(d); + + return ret; +} + +bool phy_driver_is_genphy(struct phy_device *phydev) +{ + return phy_driver_is_genphy_kind(phydev, + &genphy_driver.mdiodrv.driver); +} +EXPORT_SYMBOL_GPL(phy_driver_is_genphy); + +bool phy_driver_is_genphy_10g(struct phy_device *phydev) +{ + return phy_driver_is_genphy_kind(phydev, + &genphy_10g_driver.mdiodrv.driver); +} +EXPORT_SYMBOL_GPL(phy_driver_is_genphy_10g); + /** * phy_detach - detach a PHY device from its network device * @phydev: target phy_device struct @@ -1308,8 +1338,8 @@ void phy_detach(struct phy_device *phydev) * from the generic driver so that there's a chance a * real driver could be loaded */ - if (phydev->mdio.dev.driver == &genphy_10g_driver.mdiodrv.driver || - phydev->mdio.dev.driver == &genphy_driver.mdiodrv.driver) + if (phy_driver_is_genphy(phydev) || + phy_driver_is_genphy_10g(phydev)) device_release_driver(&phydev->mdio.dev); /* diff --git a/include/linux/phy.h b/include/linux/phy.h index 3b051f761450..f1c19bf8c658 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1183,4 +1183,7 @@ module_exit(phy_module_exit) #define module_phy_driver(__phy_drivers) \ phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers)) +bool phy_driver_is_genphy(struct phy_device *phydev); +bool phy_driver_is_genphy_10g(struct phy_device *phydev); + #endif /* __PHY_H */ -- cgit v1.2.3 From 44021606298870e4adc641ef3927e7bb47ca8236 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Tue, 15 Jan 2019 12:22:10 -0500 Subject: cpuidle: use BIT() for idle state flags and remove CPUIDLE_DRIVER_FLAGS_MASK Use BIT() macro to do a small tidy-up. CPUIDLE_DRIVER_FLAGS_MASK is not used, so remove it. Signed-off-by: Yangtao Li Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 4dff74f48d4b..3b39472324a3 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -69,11 +69,9 @@ struct cpuidle_state { /* Idle State Flags */ #define CPUIDLE_FLAG_NONE (0x00) -#define CPUIDLE_FLAG_POLLING (0x01) /* polling state */ -#define CPUIDLE_FLAG_COUPLED (0x02) /* state applies to multiple cpus */ -#define CPUIDLE_FLAG_TIMER_STOP (0x04) /* timer is stopped on this state */ - -#define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) +#define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ +#define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ +#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; -- cgit v1.2.3 From 692d7b5d1f9125a1cf0595e979e3b5fb7210547e Mon Sep 17 00:00:00 2001 From: Vakul Garg Date: Wed, 16 Jan 2019 10:40:16 +0000 Subject: tls: Fix recvmsg() to be able to peek across multiple records This fixes recvmsg() to be able to peek across multiple tls records. Without this patch, the tls's selftests test case 'recv_peek_large_buf_mult_recs' fails. Each tls receive context now maintains a 'rx_list' to retain incoming skb carrying tls records. If a tls record needs to be retained e.g. for peek case or for the case when the buffer passed to recvmsg() has a length smaller than decrypted record length, then it is added to 'rx_list'. Additionally, records are added in 'rx_list' if the crypto operation runs in async mode. The records are dequeued from 'rx_list' after the decrypted data is consumed by copying into the buffer passed to recvmsg(). In case, the MSG_PEEK flag is used in recvmsg(), then records are not consumed or removed from the 'rx_list'. Signed-off-by: Vakul Garg Signed-off-by: David S. Miller --- include/net/tls.h | 3 +- net/tls/tls_sw.c | 266 ++++++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 198 insertions(+), 71 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 2a6ac8d642af..90bf52db573e 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -145,12 +145,13 @@ struct tls_sw_context_tx { struct tls_sw_context_rx { struct crypto_aead *aead_recv; struct crypto_wait async_wait; - struct strparser strp; + struct sk_buff_head rx_list; /* list of decrypted 'data' records */ void (*saved_data_ready)(struct sock *sk); struct sk_buff *recv_pkt; u8 control; + int async_capable; bool decrypted; atomic_t decrypt_pending; bool async_notify; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index b8e50e22b777..86b9527c4826 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -124,6 +124,7 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err) { struct aead_request *aead_req = (struct aead_request *)req; struct scatterlist *sgout = aead_req->dst; + struct scatterlist *sgin = aead_req->src; struct tls_sw_context_rx *ctx; struct tls_context *tls_ctx; struct scatterlist *sg; @@ -134,12 +135,16 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err) skb = (struct sk_buff *)req->data; tls_ctx = tls_get_ctx(skb->sk); ctx = tls_sw_ctx_rx(tls_ctx); - pending = atomic_dec_return(&ctx->decrypt_pending); /* Propagate if there was an err */ if (err) { ctx->async_wait.err = err; tls_err_abort(skb->sk, err); + } else { + struct strp_msg *rxm = strp_msg(skb); + + rxm->offset += tls_ctx->rx.prepend_size; + rxm->full_len -= tls_ctx->rx.overhead_size; } /* After using skb->sk to propagate sk through crypto async callback @@ -147,18 +152,21 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err) */ skb->sk = NULL; - /* Release the skb, pages and memory allocated for crypto req */ - kfree_skb(skb); - /* Skip the first S/G entry as it points to AAD */ - for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { - if (!sg) - break; - put_page(sg_page(sg)); + /* Free the destination pages if skb was not decrypted inplace */ + if (sgout != sgin) { + /* Skip the first S/G entry as it points to AAD */ + for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { + if (!sg) + break; + put_page(sg_page(sg)); + } } kfree(aead_req); + pending = atomic_dec_return(&ctx->decrypt_pending); + if (!pending && READ_ONCE(ctx->async_notify)) complete(&ctx->async_wait.completion); } @@ -1271,7 +1279,7 @@ out: static int decrypt_internal(struct sock *sk, struct sk_buff *skb, struct iov_iter *out_iov, struct scatterlist *out_sg, - int *chunk, bool *zc) + int *chunk, bool *zc, bool async) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -1371,13 +1379,13 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, fallback_to_reg_recv: sgout = sgin; pages = 0; - *chunk = 0; + *chunk = data_len; *zc = false; } /* Prepare and submit AEAD request */ err = tls_do_decryption(sk, skb, sgin, sgout, iv, - data_len, aead_req, *zc); + data_len, aead_req, async); if (err == -EINPROGRESS) return err; @@ -1390,7 +1398,8 @@ fallback_to_reg_recv: } static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, - struct iov_iter *dest, int *chunk, bool *zc) + struct iov_iter *dest, int *chunk, bool *zc, + bool async) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -1403,7 +1412,7 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, return err; #endif if (!ctx->decrypted) { - err = decrypt_internal(sk, skb, dest, NULL, chunk, zc); + err = decrypt_internal(sk, skb, dest, NULL, chunk, zc, async); if (err < 0) { if (err == -EINPROGRESS) tls_advance_record_sn(sk, &tls_ctx->rx); @@ -1429,7 +1438,7 @@ int decrypt_skb(struct sock *sk, struct sk_buff *skb, bool zc = true; int chunk; - return decrypt_internal(sk, skb, NULL, sgout, &chunk, &zc); + return decrypt_internal(sk, skb, NULL, sgout, &chunk, &zc, false); } static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb, @@ -1456,6 +1465,77 @@ static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb, return true; } +/* This function traverses the rx_list in tls receive context to copies the + * decrypted data records into the buffer provided by caller zero copy is not + * true. Further, the records are removed from the rx_list if it is not a peek + * case and the record has been consumed completely. + */ +static int process_rx_list(struct tls_sw_context_rx *ctx, + struct msghdr *msg, + size_t skip, + size_t len, + bool zc, + bool is_peek) +{ + struct sk_buff *skb = skb_peek(&ctx->rx_list); + ssize_t copied = 0; + + while (skip && skb) { + struct strp_msg *rxm = strp_msg(skb); + + if (skip < rxm->full_len) + break; + + skip = skip - rxm->full_len; + skb = skb_peek_next(skb, &ctx->rx_list); + } + + while (len && skb) { + struct sk_buff *next_skb; + struct strp_msg *rxm = strp_msg(skb); + int chunk = min_t(unsigned int, rxm->full_len - skip, len); + + if (!zc || (rxm->full_len - skip) > len) { + int err = skb_copy_datagram_msg(skb, rxm->offset + skip, + msg, chunk); + if (err < 0) + return err; + } + + len = len - chunk; + copied = copied + chunk; + + /* Consume the data from record if it is non-peek case*/ + if (!is_peek) { + rxm->offset = rxm->offset + chunk; + rxm->full_len = rxm->full_len - chunk; + + /* Return if there is unconsumed data in the record */ + if (rxm->full_len - skip) + break; + } + + /* The remaining skip-bytes must lie in 1st record in rx_list. + * So from the 2nd record, 'skip' should be 0. + */ + skip = 0; + + if (msg) + msg->msg_flags |= MSG_EOR; + + next_skb = skb_peek_next(skb, &ctx->rx_list); + + if (!is_peek) { + skb_unlink(skb, &ctx->rx_list); + kfree_skb(skb); + } + + skb = next_skb; + } + + return copied; +} + int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, @@ -1466,7 +1546,8 @@ int tls_sw_recvmsg(struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct sk_psock *psock; - unsigned char control; + unsigned char control = 0; + ssize_t decrypted = 0; struct strp_msg *rxm; struct sk_buff *skb; ssize_t copied = 0; @@ -1474,6 +1555,7 @@ int tls_sw_recvmsg(struct sock *sk, int target, err = 0; long timeo; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); + bool is_peek = flags & MSG_PEEK; int num_async = 0; flags |= nonblock; @@ -1484,11 +1566,28 @@ int tls_sw_recvmsg(struct sock *sk, psock = sk_psock_get(sk); lock_sock(sk); - target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + /* Process pending decrypted records. It must be non-zero-copy */ + err = process_rx_list(ctx, msg, 0, len, false, is_peek); + if (err < 0) { + tls_err_abort(sk, err); + goto end; + } else { + copied = err; + } + + len = len - copied; + if (len) { + target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + } else { + goto recv_end; + } + do { - bool zc = false; + bool retain_skb = false; bool async = false; + bool zc = false; + int to_decrypt; int chunk = 0; skb = tls_wait_data(sk, psock, flags, timeo, &err); @@ -1498,7 +1597,7 @@ int tls_sw_recvmsg(struct sock *sk, msg, len, flags); if (ret > 0) { - copied += ret; + decrypted += ret; len -= ret; continue; } @@ -1525,70 +1624,70 @@ int tls_sw_recvmsg(struct sock *sk, goto recv_end; } - if (!ctx->decrypted) { - int to_copy = rxm->full_len - tls_ctx->rx.overhead_size; + to_decrypt = rxm->full_len - tls_ctx->rx.overhead_size; - if (!is_kvec && to_copy <= len && - likely(!(flags & MSG_PEEK))) - zc = true; + if (to_decrypt <= len && !is_kvec && !is_peek) + zc = true; - err = decrypt_skb_update(sk, skb, &msg->msg_iter, - &chunk, &zc); - if (err < 0 && err != -EINPROGRESS) { - tls_err_abort(sk, EBADMSG); - goto recv_end; - } - - if (err == -EINPROGRESS) { - async = true; - num_async++; - goto pick_next_record; - } - - ctx->decrypted = true; + err = decrypt_skb_update(sk, skb, &msg->msg_iter, + &chunk, &zc, ctx->async_capable); + if (err < 0 && err != -EINPROGRESS) { + tls_err_abort(sk, EBADMSG); + goto recv_end; } - if (!zc) { - chunk = min_t(unsigned int, rxm->full_len, len); + if (err == -EINPROGRESS) { + async = true; + num_async++; + goto pick_next_record; + } else { + if (!zc) { + if (rxm->full_len > len) { + retain_skb = true; + chunk = len; + } else { + chunk = rxm->full_len; + } + + err = skb_copy_datagram_msg(skb, rxm->offset, + msg, chunk); + if (err < 0) + goto recv_end; - err = skb_copy_datagram_msg(skb, rxm->offset, msg, - chunk); - if (err < 0) - goto recv_end; + if (!is_peek) { + rxm->offset = rxm->offset + chunk; + rxm->full_len = rxm->full_len - chunk; + } + } } pick_next_record: - copied += chunk; + if (chunk > len) + chunk = len; + + decrypted += chunk; len -= chunk; - if (likely(!(flags & MSG_PEEK))) { - u8 control = ctx->control; - - /* For async, drop current skb reference */ - if (async) - skb = NULL; - - if (tls_sw_advance_skb(sk, skb, chunk)) { - /* Return full control message to - * userspace before trying to parse - * another message type - */ - msg->msg_flags |= MSG_EOR; - if (control != TLS_RECORD_TYPE_DATA) - goto recv_end; - } else { - break; - } - } else { - /* MSG_PEEK right now cannot look beyond current skb - * from strparser, meaning we cannot advance skb here - * and thus unpause strparser since we'd loose original - * one. + + /* For async or peek case, queue the current skb */ + if (async || is_peek || retain_skb) { + skb_queue_tail(&ctx->rx_list, skb); + skb = NULL; + } + + if (tls_sw_advance_skb(sk, skb, chunk)) { + /* Return full control message to + * userspace before trying to parse + * another message type */ + msg->msg_flags |= MSG_EOR; + if (ctx->control != TLS_RECORD_TYPE_DATA) + goto recv_end; + } else { break; } /* If we have a new message from strparser, continue now. */ - if (copied >= target && !ctx->recv_pkt) + if (decrypted >= target && !ctx->recv_pkt) break; } while (len); @@ -1602,13 +1701,33 @@ recv_end: /* one of async decrypt failed */ tls_err_abort(sk, err); copied = 0; + decrypted = 0; + goto end; } } else { reinit_completion(&ctx->async_wait.completion); } WRITE_ONCE(ctx->async_notify, false); + + /* Drain records from the rx_list & copy if required */ + if (is_peek || is_kvec) + err = process_rx_list(ctx, msg, copied, + decrypted, false, is_peek); + else + err = process_rx_list(ctx, msg, 0, + decrypted, true, is_peek); + if (err < 0) { + tls_err_abort(sk, err); + copied = 0; + goto end; + } + + WARN_ON(decrypted != err); } + copied += decrypted; + +end: release_sock(sk); if (psock) sk_psock_put(sk, psock); @@ -1645,7 +1764,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, } if (!ctx->decrypted) { - err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc); + err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); if (err < 0) { tls_err_abort(sk, EBADMSG); @@ -1832,6 +1951,7 @@ void tls_sw_release_resources_rx(struct sock *sk) if (ctx->aead_recv) { kfree_skb(ctx->recv_pkt); ctx->recv_pkt = NULL; + skb_queue_purge(&ctx->rx_list); crypto_free_aead(ctx->aead_recv); strp_stop(&ctx->strp); write_lock_bh(&sk->sk_callback_lock); @@ -1881,6 +2001,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) struct crypto_aead **aead; struct strp_callbacks cb; u16 nonce_size, tag_size, iv_size, rec_seq_size; + struct crypto_tfm *tfm; char *iv, *rec_seq; int rc = 0; @@ -1927,6 +2048,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) crypto_init_wait(&sw_ctx_rx->async_wait); crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; + skb_queue_head_init(&sw_ctx_rx->rx_list); aead = &sw_ctx_rx->aead_recv; } @@ -1994,6 +2116,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto free_aead; if (sw_ctx_rx) { + tfm = crypto_aead_tfm(sw_ctx_rx->aead_recv); + sw_ctx_rx->async_capable = + tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; + /* Set up strparser */ memset(&cb, 0, sizeof(cb)); cb.rcv_msg = tls_queue; -- cgit v1.2.3 From f5dd3d0c9638a9d9a02b5964c4ad636f06cf7e2c Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Tue, 15 Jan 2019 14:42:14 +0100 Subject: net: introduce SO_BINDTOIFINDEX sockopt This introduces a new generic SOL_SOCKET-level socket option called SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a network interface index as argument, rather than the network interface name. User-space often refers to network-interfaces via their index, but has to temporarily resolve it to a name for a call into SO_BINDTODEVICE. This might pose problems when the network-device is renamed asynchronously by other parts of the system. When this happens, the SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong device. In most cases user-space only ever operates on devices which they either manage themselves, or otherwise have a guarantee that the device name will not change (e.g., devices that are UP cannot be renamed). However, particularly in libraries this guarantee is non-obvious and it would be nice if that race-condition would simply not exist. It would make it easier for those libraries to operate even in situations where the device-name might change under the hood. A real use-case that we recently hit is trying to start the network stack early in the initrd but make it survive into the real system. Existing distributions rename network-interfaces during the transition from initrd into the real system. This, obviously, cannot affect devices that are up and running (unless you also consider moving them between network-namespaces). However, the network manager now has to make sure its management engine for dormant devices will not run in parallel to these renames. Particularly, when you offload operations like DHCP into separate processes, these might setup their sockets early, and thus have to resolve the device-name possibly running into this race-condition. By avoiding a call to resolve the device-name, we no longer depend on the name and can run network setup of dormant devices in parallel to the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this race. Reviewed-by: Tom Gundersen Signed-off-by: David Herrmann Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 2 ++ arch/ia64/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/s390/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ arch/xtensa/include/uapi/asm/socket.h | 2 ++ include/uapi/asm-generic/socket.h | 2 ++ net/core/sock.c | 46 +++++++++++++++++++++++++++-------- 9 files changed, 52 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 065fb372e355..b1c9b542c021 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -115,4 +115,6 @@ #define SO_TXTIME 61 #define SCM_TXTIME SO_TXTIME +#define SO_BINDTOIFINDEX 62 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index c872c4e6bafb..ba0d245f9576 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -117,4 +117,6 @@ #define SO_TXTIME 61 #define SCM_TXTIME SO_TXTIME +#define SO_BINDTOIFINDEX 62 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 71370fb3ceef..73e25e35d803 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -126,4 +126,6 @@ #define SO_TXTIME 61 #define SCM_TXTIME SO_TXTIME +#define SO_BINDTOIFINDEX 62 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 061b9cf2a779..52bed5976cbe 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -107,4 +107,6 @@ #define SO_TXTIME 0x4036 #define SCM_TXTIME SO_TXTIME +#define SO_BINDTOIFINDEX 0x4037 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 39d901476ee5..49c971587087 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -114,4 +114,6 @@ #define SO_TXTIME 61 #define SCM_TXTIME SO_TXTIME +#define SO_BINDTOIFINDEX 62 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 7ea35e5601b6..bbdb81594dd4 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -104,6 +104,8 @@ #define SO_TXTIME 0x003f #define SCM_TXTIME SO_TXTIME +#define SO_BINDTOIFINDEX 0x0041 + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 1de07a7f7680..b434217783d0 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -119,4 +119,6 @@ #define SO_TXTIME 61 #define SCM_TXTIME SO_TXTIME +#define SO_BINDTOIFINDEX 62 + #endif /* _XTENSA_SOCKET_H */ diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index a12692e5f7a8..3066ab3853a8 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -110,4 +110,6 @@ #define SO_TXTIME 61 #define SCM_TXTIME SO_TXTIME +#define SO_BINDTOIFINDEX 62 + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/net/core/sock.c b/net/core/sock.c index 6aa2e7e0b4fb..b53764ebb973 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -520,20 +520,43 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) } EXPORT_SYMBOL(sk_dst_check); -static int sock_setbindtodevice(struct sock *sk, char __user *optval, - int optlen) +static int sock_setbindtodevice_locked(struct sock *sk, int ifindex) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); - char devname[IFNAMSIZ]; - int index; /* Sorry... */ ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_RAW)) goto out; + ret = -EINVAL; + if (ifindex < 0) + goto out; + + sk->sk_bound_dev_if = ifindex; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + sk_dst_reset(sk); + + ret = 0; + +out: +#endif + + return ret; +} + +static int sock_setbindtodevice(struct sock *sk, char __user *optval, + int optlen) +{ + int ret = -ENOPROTOOPT; +#ifdef CONFIG_NETDEVICES + struct net *net = sock_net(sk); + char devname[IFNAMSIZ]; + int index; + ret = -EINVAL; if (optlen < 0) goto out; @@ -566,14 +589,9 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval, } lock_sock(sk); - sk->sk_bound_dev_if = index; - if (sk->sk_prot->rehash) - sk->sk_prot->rehash(sk); - sk_dst_reset(sk); + ret = sock_setbindtodevice_locked(sk, index); release_sock(sk); - ret = 0; - out: #endif @@ -1055,6 +1073,10 @@ set_rcvbuf: } break; + case SO_BINDTOIFINDEX: + ret = sock_setbindtodevice_locked(sk, val); + break; + default: ret = -ENOPROTOOPT; break; @@ -1399,6 +1421,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, SOF_TXTIME_REPORT_ERRORS : 0; break; + case SO_BINDTOIFINDEX: + v.val = sk->sk_bound_dev_if; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). -- cgit v1.2.3 From 87b0984ebfabafcfe959e52ca5cdab5eeb2d60c0 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 16 Jan 2019 23:06:50 +0000 Subject: net: Add extack argument to ndo_fdb_add() Drivers may not be able to support certain FDB entries, and an error code is insufficient to give clear hints as to the reasons of rejection. In order to make it possible to communicate the rejection reason, extend ndo_fdb_add() with an extack argument. Adapt the existing implementations of ndo_fdb_add() to take the parameter (and ignore it). Pass the extack parameter when invoking ndo_fdb_add() from rtnl_fdb_add(). Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/i40e/i40e_main.c | 3 ++- drivers/net/ethernet/intel/ice/ice_main.c | 3 ++- drivers/net/ethernet/intel/igb/igb_main.c | 3 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++- drivers/net/ethernet/mscc/ocelot.c | 3 ++- drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 3 ++- drivers/net/macvlan.c | 3 ++- drivers/net/vxlan.c | 3 ++- include/linux/netdevice.h | 6 ++++-- net/bridge/br_fdb.c | 3 ++- net/bridge/br_private.h | 3 ++- net/core/rtnetlink.c | 5 +++-- net/dsa/dsa_priv.h | 3 ++- net/dsa/slave.c | 3 ++- 14 files changed, 31 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f52e2c46e6a7..0ee641c41be4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11644,7 +11644,8 @@ static int i40e_get_phys_port_id(struct net_device *netdev, static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags) + u16 flags, + struct netlink_ext_ack *extack) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_pf *pf = np->vsi->back; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f4bf6bda32a9..48f033928aa2 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2438,7 +2438,8 @@ static void ice_set_rx_mode(struct net_device *netdev) */ static int ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[], struct net_device *dev, const unsigned char *addr, - u16 vid, u16 flags) + u16 vid, u16 flags, + struct netlink_ext_ack *extack) { int err; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 87bdf1604ae2..3615e2e52399 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2486,7 +2486,8 @@ static int igb_set_features(struct net_device *netdev, static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags) + u16 flags, + struct netlink_ext_ack *extack) { /* guarantee we can provide a unique filter for the unicast address */ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index daff8183534b..b53087a980ef 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9910,7 +9910,8 @@ static void ixgbe_del_udp_tunnel_port(struct net_device *dev, static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags) + u16 flags, + struct netlink_ext_ack *extack) { /* guarantee we can provide a unique filter for the unicast address */ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) { diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 215a45374d7b..c6a575eb0ff5 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -721,7 +721,8 @@ static void ocelot_get_stats64(struct net_device *dev, static int ocelot_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - u16 vid, u16 flags) + u16 vid, u16 flags, + struct netlink_ext_ack *extack) { struct ocelot_port *port = netdev_priv(dev); struct ocelot *ocelot = port->ocelot; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 16d0479f6891..7a873002e626 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -396,7 +396,8 @@ static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], static int qlcnic_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *netdev, - const unsigned char *addr, u16 vid, u16 flags) + const unsigned char *addr, u16 vid, u16 flags, + struct netlink_ext_ack *extack) { struct qlcnic_adapter *adapter = netdev_priv(netdev); int err = 0; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index fc726ce4c164..084a1b3fbc80 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -963,7 +963,8 @@ static int macvlan_vlan_rx_kill_vid(struct net_device *dev, static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags) + u16 flags, + struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 83f65eb3085f..11f38fd71678 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1087,7 +1087,8 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, /* Add static entry (via netlink) */ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, u16 vid, u16 flags) + const unsigned char *addr, u16 vid, u16 flags, + struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); /* struct net *net = dev_net(vxlan->dev); */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1377d085ef99..a57b9a853aab 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1152,7 +1152,8 @@ struct dev_ifalias { * * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, - * const unsigned char *addr, u16 vid, u16 flags) + * const unsigned char *addr, u16 vid, u16 flags, + * struct netlink_ext_ack *extack); * Adds an FDB entry to dev for addr. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, @@ -1376,7 +1377,8 @@ struct net_device_ops { struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags); + u16 flags, + struct netlink_ext_ack *extack); int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index fe3c758791ca..6664cb8590f8 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -915,7 +915,8 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, /* Add new permanent fdb entry with RTM_NEWNEIGH */ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, u16 vid, u16 nlh_flags) + const unsigned char *addr, u16 vid, u16 nlh_flags, + struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index eabf8bf28a3f..00deef7fc1f3 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -573,7 +573,8 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid); int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, u16 vid, u16 nlh_flags); + const unsigned char *addr, u16 vid, u16 nlh_flags, + struct netlink_ext_ack *extack); int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *fdev, int *idx); int br_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5ea1bed08ede..b302df0cd5ae 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3639,7 +3639,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, const struct net_device_ops *ops = br_dev->netdev_ops; err = ops->ndo_fdb_add(ndm, tb, dev, addr, vid, - nlh->nlmsg_flags); + nlh->nlmsg_flags, extack); if (err) goto out; else @@ -3651,7 +3651,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (dev->netdev_ops->ndo_fdb_add) err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr, vid, - nlh->nlmsg_flags); + nlh->nlmsg_flags, + extack); else err = ndo_dflt_fdb_add(ndm, tb, dev, addr, vid, nlh->nlmsg_flags); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 026a05774bf7..1f4972dab9f2 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -103,7 +103,8 @@ static inline void dsa_legacy_unregister(void) { } int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags); + u16 flags, + struct netlink_ext_ack *extack); int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a3fcc1d01615..d5680a98a7f0 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1009,7 +1009,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags) + u16 flags, + struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); -- cgit v1.2.3 From 4c59b7d16096e5e2cfbc7f8cba972eb72f6b96c0 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 16 Jan 2019 23:06:54 +0000 Subject: vxlan: Add extack to switchdev operations There are four sources of VXLAN switchdev notifier calls: - the changelink() link operation, which already supports extack, - ndo_fdb_add() which got extack support in a previous patch, - FDB updates due to packet forwarding, - and vxlan_fdb_replay(). Extend vxlan_fdb_switchdev_call_notifiers() to include extack in the switchdev message that it sends, and propagate the argument upwards to the callers. For the first two cases, pass in the extack gotten through the operation. For case #3, pass in NULL. To cover the last case, extend vxlan_fdb_replay() to take extack argument, which might come from whatever operation necessitated the FDB replay. Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c | 3 +- drivers/net/vxlan.c | 68 +++++++++++++--------- include/net/vxlan.h | 6 +- 3 files changed, 46 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c index bc565f2aa121..9ba0b83bd949 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c @@ -217,7 +217,8 @@ mlxsw_sp_nve_vxlan_fdb_replay(const struct net_device *nve_dev, __be32 vni, { if (WARN_ON(!netif_is_vxlan(nve_dev))) return -EINVAL; - return vxlan_fdb_replay(nve_dev, vni, &mlxsw_sp_switchdev_notifier); + return vxlan_fdb_replay(nve_dev, vni, &mlxsw_sp_switchdev_notifier, + extack); } static void diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 11f38fd71678..a9e90159bb61 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -361,10 +361,11 @@ errout: static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, const struct vxlan_rdst *rd, + struct netlink_ext_ack *extack, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { fdb_info->info.dev = vxlan->dev; - fdb_info->info.extack = NULL; + fdb_info->info.extack = extack; fdb_info->remote_ip = rd->remote_ip; fdb_info->remote_port = rd->remote_port; fdb_info->remote_vni = rd->remote_vni; @@ -378,7 +379,8 @@ static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, - bool adding) + bool adding, + struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info info; enum switchdev_notifier_type notifier_type; @@ -389,14 +391,15 @@ static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan, notifier_type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE; - vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, &info); + vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, NULL, &info); ret = call_switchdev_notifiers(notifier_type, vxlan->dev, &info.info); return notifier_to_errno(ret); } static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, - struct vxlan_rdst *rd, int type, bool swdev_notify) + struct vxlan_rdst *rd, int type, bool swdev_notify, + struct netlink_ext_ack *extack) { int err; @@ -404,13 +407,13 @@ static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, switch (type) { case RTM_NEWNEIGH: err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, - true); + true, extack); if (err) return err; break; case RTM_DELNEIGH: vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, - false); + false, extack); break; } } @@ -430,7 +433,7 @@ static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa) .remote_vni = cpu_to_be32(VXLAN_N_VID), }; - vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true); + vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN]) @@ -442,7 +445,7 @@ static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN]) memcpy(f.eth_addr, eth_addr, ETH_ALEN); - vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true); + vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } /* Hash Ethernet address */ @@ -552,7 +555,7 @@ int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, } rdst = first_remote_rcu(f); - vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, fdb_info); + vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, NULL, fdb_info); out: rcu_read_unlock(); @@ -563,19 +566,21 @@ EXPORT_SYMBOL_GPL(vxlan_fdb_find_uc); static int vxlan_fdb_notify_one(struct notifier_block *nb, const struct vxlan_dev *vxlan, const struct vxlan_fdb *f, - const struct vxlan_rdst *rdst) + const struct vxlan_rdst *rdst, + struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info fdb_info; int rc; - vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, &fdb_info); + vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, extack, &fdb_info); rc = nb->notifier_call(nb, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, &fdb_info); return notifier_to_errno(rc); } int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, - struct notifier_block *nb) + struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; @@ -593,7 +598,8 @@ int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, if (f->vni == vni) { list_for_each_entry(rdst, &f->remotes, list) { rc = vxlan_fdb_notify_one(nb, vxlan, - f, rdst); + f, rdst, + extack); if (rc) goto out; } @@ -857,7 +863,7 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, if (do_notify) list_for_each_entry(rd, &f->remotes, list) vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, - swdev_notify); + swdev_notify, NULL); hlist_del_rcu(&f->hlist); call_rcu(&f->rcu, vxlan_fdb_free); @@ -869,7 +875,8 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, __be16 port, __be32 vni, __u32 ifindex, __u16 ndm_flags, struct vxlan_fdb *f, - bool swdev_notify) + bool swdev_notify, + struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_rdst *rd = NULL; @@ -924,7 +931,7 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, rd = first_remote_rtnl(f); err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH, - swdev_notify); + swdev_notify, extack); if (err) goto err_notify; } @@ -944,7 +951,8 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, - bool swdev_notify) + bool swdev_notify, + struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_fdb *f; @@ -962,7 +970,7 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, return rc; rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, - swdev_notify); + swdev_notify, extack); if (rc) goto err_notify; @@ -979,7 +987,8 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, - bool swdev_notify) + bool swdev_notify, + struct netlink_ext_ack *extack) { struct vxlan_fdb *f; @@ -993,14 +1002,14 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan, return vxlan_fdb_update_existing(vxlan, ip, state, flags, port, vni, ifindex, ndm_flags, f, - swdev_notify); + swdev_notify, extack); } else { if (!(flags & NLM_F_CREATE)) return -ENOENT; return vxlan_fdb_update_create(vxlan, mac, ip, state, flags, port, src_vni, vni, ifindex, - ndm_flags, swdev_notify); + ndm_flags, swdev_notify, extack); } } @@ -1016,7 +1025,7 @@ static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, struct vxlan_rdst *rd, bool swdev_notify) { list_del_rcu(&rd->list); - vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify); + vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); call_rcu(&rd->rcu, vxlan_dst_free); } @@ -1118,7 +1127,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER, - true); + true, extack); spin_unlock_bh(&vxlan->hash_lock); return err; @@ -1286,7 +1295,7 @@ static bool vxlan_snoop(struct net_device *dev, rdst->remote_ip = *src_ip; f->updated = jiffies; - vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true); + vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL); } else { /* learned new entry */ spin_lock(&vxlan->hash_lock); @@ -1299,7 +1308,7 @@ static bool vxlan_snoop(struct net_device *dev, vxlan->cfg.dst_port, vni, vxlan->default_dst.remote_vni, - ifindex, NTF_SELF, true); + ifindex, NTF_SELF, true, NULL); spin_unlock(&vxlan->hash_lock); } @@ -3543,7 +3552,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, /* notify default fdb entry */ if (f) { err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), - RTM_NEWNEIGH, true); + RTM_NEWNEIGH, true, extack); if (err) goto errout; } @@ -3818,7 +3827,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], vxlan->cfg.dst_port, conf.vni, conf.vni, conf.remote_ifindex, - NTF_SELF, true); + NTF_SELF, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock); return err; @@ -4113,8 +4122,11 @@ vxlan_fdb_external_learn_add(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); + struct netlink_ext_ack *extack; int err; + extack = switchdev_notifier_info_to_extack(&fdb_info->info); + spin_lock_bh(&vxlan->hash_lock); err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip, NUD_REACHABLE, @@ -4124,7 +4136,7 @@ vxlan_fdb_external_learn_add(struct net_device *dev, fdb_info->remote_vni, fdb_info->remote_ifindex, NTF_USE | NTF_SELF | NTF_EXT_LEARNED, - false); + false, extack); spin_unlock_bh(&vxlan->hash_lock); return err; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 236403eb5ba6..09767819c3d4 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -428,7 +428,8 @@ struct switchdev_notifier_vxlan_fdb_info { int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info); int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, - struct notifier_block *nb); + struct notifier_block *nb, + struct netlink_ext_ack *extack); void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni); #else @@ -440,7 +441,8 @@ vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, } static inline int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, - struct notifier_block *nb) + struct notifier_block *nb, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } -- cgit v1.2.3 From 6685987c29582afc79b7fa3998dfbf36b4295791 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 16 Jan 2019 23:06:56 +0000 Subject: switchdev: Add extack argument to call_switchdev_notifiers() A follow-up patch will enable vetoing of FDB entries. Make it possible to communicate details of why an FDB entry is not acceptable back to the user. Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 2 +- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 6 ++++-- drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 12 ++++++------ drivers/net/ethernet/rocker/rocker_main.c | 2 +- drivers/net/ethernet/rocker/rocker_ofdpa.c | 4 ++-- drivers/net/vxlan.c | 2 +- include/net/switchdev.h | 6 ++++-- net/bridge/br_switchdev.c | 2 +- net/dsa/slave.c | 2 +- net/switchdev/switchdev.c | 5 +++-- 10 files changed, 24 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 82236a17b5e6..f3244d87512a 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -196,7 +196,7 @@ The switch device will learn/forget source MAC address/VLAN on ingress packets and notify the switch driver of the mac/vlan/port tuples. The switch driver, in turn, will notify the bridge driver using the switchdev notifier call: - err = call_switchdev_notifiers(val, dev, info); + err = call_switchdev_notifiers(val, dev, info, extack); Where val is SWITCHDEV_FDB_ADD when learning and SWITCHDEV_FDB_DEL when forgetting, and info points to a struct switchdev_notifier_fdb_info. On diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 98e5ffd71b91..042341c7f6b9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -7294,7 +7294,8 @@ static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) info.addr = mac; info.vid = vid; - call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info); + call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info, + NULL); } static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_vlan_ops = { @@ -7381,7 +7382,8 @@ static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) info.addr = mac; info.vid = 0; - call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info); + call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info, + NULL); } static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 0abbaa0fbf14..71aad9d4e160 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -2443,7 +2443,7 @@ static void mlxsw_sp_fdb_vxlan_call_notifiers(struct net_device *dev, ether_addr_copy(info.eth_addr, mac); info.vni = vni; info.offloaded = adding; - call_switchdev_notifiers(type, dev, &info.info); + call_switchdev_notifiers(type, dev, &info.info, NULL); } static void mlxsw_sp_fdb_nve_call_notifiers(struct net_device *dev, @@ -2468,7 +2468,7 @@ mlxsw_sp_fdb_call_notifiers(enum switchdev_notifier_type type, info.addr = mac; info.vid = vid; info.offloaded = offloaded; - call_switchdev_notifiers(type, dev, &info.info); + call_switchdev_notifiers(type, dev, &info.info, NULL); } static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, @@ -2819,7 +2819,7 @@ mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp, return; vxlan_fdb_info.offloaded = true; call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev, - &vxlan_fdb_info.info); + &vxlan_fdb_info.info, NULL); mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, vxlan_fdb_info.eth_addr, fdb_info->vid, dev, true); @@ -2832,7 +2832,7 @@ mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp, false); vxlan_fdb_info.offloaded = false; call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev, - &vxlan_fdb_info.info); + &vxlan_fdb_info.info, NULL); break; } } @@ -2977,7 +2977,7 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp, } vxlan_fdb_info->offloaded = true; call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev, - &vxlan_fdb_info->info); + &vxlan_fdb_info->info, NULL); mlxsw_sp_fid_put(fid); return; } @@ -2998,7 +2998,7 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp, goto err_fdb_tunnel_uc_op; vxlan_fdb_info->offloaded = true; call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev, - &vxlan_fdb_info->info); + &vxlan_fdb_info->info, NULL); mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, vxlan_fdb_info->eth_addr, vid, dev, true); diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 6213827e3956..62a205eba9f7 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2725,7 +2725,7 @@ rocker_fdb_offload_notify(struct rocker_port *rocker_port, info.vid = recv_info->vid; info.offloaded = true; call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, - rocker_port->dev, &info.info); + rocker_port->dev, &info.info, NULL); } static void rocker_switchdev_event_work(struct work_struct *work) diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 6473cc68c2d5..bea7895930f6 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -1833,10 +1833,10 @@ static void ofdpa_port_fdb_learn_work(struct work_struct *work) rtnl_lock(); if (learned && removing) call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, - lw->ofdpa_port->dev, &info.info); + lw->ofdpa_port->dev, &info.info, NULL); else if (learned && !removing) call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, - lw->ofdpa_port->dev, &info.info); + lw->ofdpa_port->dev, &info.info, NULL); rtnl_unlock(); kfree(work); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index a9e90159bb61..ef45c3c925be 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -393,7 +393,7 @@ static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan, : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE; vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, NULL, &info); ret = call_switchdev_notifiers(notifier_type, vxlan->dev, - &info.info); + &info.info, extack); return notifier_to_errno(ret); } diff --git a/include/net/switchdev.h b/include/net/switchdev.h index a7fdab5ee6c3..63843ae5dc81 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -195,7 +195,8 @@ int switchdev_port_obj_del(struct net_device *dev, int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, - struct switchdev_notifier_info *info); + struct switchdev_notifier_info *info, + struct netlink_ext_ack *extack); int register_switchdev_blocking_notifier(struct notifier_block *nb); int unregister_switchdev_blocking_notifier(struct notifier_block *nb); @@ -267,7 +268,8 @@ static inline int unregister_switchdev_notifier(struct notifier_block *nb) static inline int call_switchdev_notifiers(unsigned long val, struct net_device *dev, - struct switchdev_notifier_info *info) + struct switchdev_notifier_info *info, + struct netlink_ext_ack *extack) { return NOTIFY_DONE; } diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 035ff59d9cbd..4d2b9eb7604a 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -113,7 +113,7 @@ br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac, info.added_by_user = added_by_user; info.offloaded = offloaded; notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_DEVICE : SWITCHDEV_FDB_DEL_TO_DEVICE; - call_switchdev_notifiers(notifier_type, dev, &info.info); + call_switchdev_notifiers(notifier_type, dev, &info.info, NULL); } void diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d5680a98a7f0..91de3a663226 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1451,7 +1451,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) } fdb_info->offloaded = true; call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev, - &fdb_info->info); + &fdb_info->info, NULL); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 5df9d1138ac9..cd78253de31d 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -556,10 +556,11 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); * Call all network notifier blocks. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, - struct switchdev_notifier_info *info) + struct switchdev_notifier_info *info, + struct netlink_ext_ack *extack) { info->dev = dev; - info->extack = NULL; + info->extack = extack; return atomic_notifier_call_chain(&switchdev_notif_chain, val, info); } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); -- cgit v1.2.3 From 8b59bfe83cf15f755024e88812e057af7341f525 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 17 Jan 2019 15:22:20 +0800 Subject: qed: remove duplicated include from qed_if.h Remove duplicated include. Signed-off-by: YueHaibing Acked-by: Denis Bolotin Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 91c536a01b56..5f818fda96bd 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -38,7 +38,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 58fa4a410fc31afe08d0d0c6b6d8860c22ec17c2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 16 Jan 2019 14:15:20 +0100 Subject: ipc: introduce ksys_ipc()/compat_ksys_ipc() for s390 The sys_ipc() and compat_ksys_ipc() functions are meant to only be used from the system call table, not called by another function. Introduce ksys_*() interfaces for this purpose, as we have done for many other system calls. Link: https://lore.kernel.org/lkml/20190116131527.2071570-3-arnd@arndb.de Signed-off-by: Arnd Bergmann Reviewed-by: Heiko Carstens [heiko.carstens@de.ibm.com: compile fix for !CONFIG_COMPAT] Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/compat_linux.c | 2 +- arch/s390/kernel/sys_s390.c | 4 +++- include/linux/syscalls.h | 4 ++++ ipc/syscall.c | 20 ++++++++++++++++---- kernel/sys_ni.c | 1 + 5 files changed, 25 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 8ac38d51ed7d..a47f6d3c6d5b 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -296,7 +296,7 @@ COMPAT_SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, compat_ulong_t, second, { if (call >> 16) /* hack for backward compatibility */ return -EINVAL; - return compat_sys_ipc(call, first, second, third, ptr, third); + return compat_ksys_ipc(call, first, second, third, ptr, third); } #endif diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index 560bdaf8a74f..fd0cbbed4d9f 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -58,6 +58,7 @@ out: return error; } +#ifdef CONFIG_SYSVIPC /* * sys_ipc() is the de-multiplexer for the SysV IPC calls. */ @@ -74,8 +75,9 @@ SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second, * Therefore we can call the generic variant by simply passing the * third parameter also as fifth parameter. */ - return sys_ipc(call, first, second, third, ptr, third); + return ksys_ipc(call, first, second, third, ptr, third); } +#endif /* CONFIG_SYSVIPC */ SYSCALL_DEFINE1(s390_personality, unsigned int, personality) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 257cccba3062..fb63045a0fb6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1185,6 +1185,10 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); ssize_t ksys_readahead(int fd, loff_t offset, size_t count); +int ksys_ipc(unsigned int call, int first, unsigned long second, + unsigned long third, void __user * ptr, long fifth); +int compat_ksys_ipc(u32 call, int first, int second, + u32 third, u32 ptr, u32 fifth); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/ipc/syscall.c b/ipc/syscall.c index 1ac06e3983c0..3cf8ad703a4d 100644 --- a/ipc/syscall.c +++ b/ipc/syscall.c @@ -17,8 +17,8 @@ #include #include -SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second, - unsigned long, third, void __user *, ptr, long, fifth) +int ksys_ipc(unsigned int call, int first, unsigned long second, + unsigned long third, void __user * ptr, long fifth) { int version, ret; @@ -106,6 +106,12 @@ SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second, return -ENOSYS; } } + +SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second, + unsigned long, third, void __user *, ptr, long, fifth) +{ + return ksys_ipc(call, first, second, third, ptr, fifth); +} #endif #ifdef CONFIG_COMPAT @@ -121,8 +127,8 @@ struct compat_ipc_kludge { }; #ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC -COMPAT_SYSCALL_DEFINE6(ipc, u32, call, int, first, int, second, - u32, third, compat_uptr_t, ptr, u32, fifth) +int compat_ksys_ipc(u32 call, int first, int second, + u32 third, compat_uptr_t ptr, u32 fifth) { int version; u32 pad; @@ -195,5 +201,11 @@ COMPAT_SYSCALL_DEFINE6(ipc, u32, call, int, first, int, second, return -ENOSYS; } + +COMPAT_SYSCALL_DEFINE6(ipc, u32, call, int, first, int, second, + u32, third, compat_uptr_t, ptr, u32, fifth) +{ + return compat_ksys_ipc(call, first, second, third, ptr, fifth); +} #endif #endif diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index ab9d0e3c6d50..bc934f31ab10 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -366,6 +366,7 @@ COND_SYSCALL(kexec_file_load); /* s390 */ COND_SYSCALL(s390_pci_mmio_read); COND_SYSCALL(s390_pci_mmio_write); +COND_SYSCALL(s390_ipc); COND_SYSCALL_COMPAT(s390_ipc); /* powerpc */ -- cgit v1.2.3 From 5f620bb6439ea8f354cfe4c7d47887df9d3acaf0 Mon Sep 17 00:00:00 2001 From: Ran Wang Date: Thu, 17 Jan 2019 09:10:55 +0000 Subject: drivers: usb :fsl: Remove USB Errata checking code Remove USB errata checking code from driver. Applicability of erratum is retrieved by reading corresponding property in device tree. This property is written during device tree fixup. Besides, replace spaces with tabs to make code aligned. Signed-off-by: Ramneek Mehresh Signed-off-by: Nikhil Badola Signed-off-by: Yinbo Zhu Signed-off-by: Ran Wang Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/ehci-fsl.c | 7 +------ drivers/usb/host/fsl-mph-dr-of.c | 6 ++++++ include/linux/fsl_devices.h | 7 ++++--- 3 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c index 0a867d96c126..e3d0c1c25160 100644 --- a/drivers/usb/host/ehci-fsl.c +++ b/drivers/usb/host/ehci-fsl.c @@ -304,14 +304,9 @@ static int ehci_fsl_usb_setup(struct ehci_hcd *ehci) return -EINVAL; if (pdata->operating_mode == FSL_USB2_MPH_HOST) { - unsigned int chip, rev, svr; - - svr = mfspr(SPRN_SVR); - chip = svr >> 16; - rev = (svr >> 4) & 0xf; /* Deal with USB Erratum #14 on MPC834x Rev 1.0 & 1.1 chips */ - if ((rev == 1) && (chip >= 0x8050) && (chip <= 0x8055)) + if (pdata->has_fsl_erratum_14 == 1) ehci->has_fsl_port_bug = 1; if (pdata->port_enables & FSL_USB2_PORT0_ENABLED) diff --git a/drivers/usb/host/fsl-mph-dr-of.c b/drivers/usb/host/fsl-mph-dr-of.c index 677f9d592109..4f8b8a08c914 100644 --- a/drivers/usb/host/fsl-mph-dr-of.c +++ b/drivers/usb/host/fsl-mph-dr-of.c @@ -225,6 +225,12 @@ static int fsl_usb2_mph_dr_of_probe(struct platform_device *ofdev) pdata->has_fsl_erratum_a005697 = of_property_read_bool(np, "fsl,usb_erratum-a005697"); + if (of_get_property(np, "fsl,usb_erratum_14", NULL)) + pdata->has_fsl_erratum_14 = 1; + else + pdata->has_fsl_erratum_14 = 0; + + /* * Determine whether phy_clk_valid needs to be checked * by reading property in device tree diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index 60cef8227534..5da56a674f2f 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -98,10 +98,11 @@ struct fsl_usb2_platform_data { unsigned suspended:1; unsigned already_suspended:1; - unsigned has_fsl_erratum_a007792:1; - unsigned has_fsl_erratum_a005275:1; + unsigned has_fsl_erratum_a007792:1; + unsigned has_fsl_erratum_14:1; + unsigned has_fsl_erratum_a005275:1; unsigned has_fsl_erratum_a005697:1; - unsigned check_phy_clk_valid:1; + unsigned check_phy_clk_valid:1; /* register save area for suspend/resume */ u32 pm_command; -- cgit v1.2.3 From 73381da5f9ec333b1fbe38a156e7764a90e36a74 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 10 Jan 2019 12:17:54 -0800 Subject: crypto: streebog - use correct endianness type streebog_uint512::qword needs to be __le64, not u64. This fixes a large number of sparse warnings: crypto/streebog_generic.c:25:9: warning: incorrect type in initializer (different base types) crypto/streebog_generic.c:25:9: expected unsigned long long crypto/streebog_generic.c:25:9: got restricted __le64 [usertype] [omitted many similar warnings] No actual change in behavior. Cc: Vitaly Chikunov Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- crypto/streebog_generic.c | 2 +- include/crypto/streebog.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/crypto/streebog_generic.c b/crypto/streebog_generic.c index 03272a22afce..5a2eafed9c29 100644 --- a/crypto/streebog_generic.c +++ b/crypto/streebog_generic.c @@ -960,7 +960,7 @@ static int streebog_init(struct shash_desc *desc) memset(ctx, 0, sizeof(struct streebog_state)); for (i = 0; i < 8; i++) { if (digest_size == STREEBOG256_DIGEST_SIZE) - ctx->h.qword[i] = 0x0101010101010101ULL; + ctx->h.qword[i] = cpu_to_le64(0x0101010101010101ULL); } return 0; } diff --git a/include/crypto/streebog.h b/include/crypto/streebog.h index 4af119f7e07b..856e32af8657 100644 --- a/include/crypto/streebog.h +++ b/include/crypto/streebog.h @@ -19,7 +19,7 @@ #define STREEBOG_BLOCK_SIZE 64 struct streebog_uint512 { - u64 qword[8]; + __le64 qword[8]; }; struct streebog_state { -- cgit v1.2.3 From e17568e15830c6d158f6492b5b60ccdeb0b7b20b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 10 Jan 2019 12:17:56 -0800 Subject: crypto: user - forward declare crypto_nlsk Move the declaration of crypto_nlsk into internal/cryptouser.h. This fixes the following sparse warning: crypto/crypto_user_base.c:41:13: warning: symbol 'crypto_nlsk' was not declared. Should it be static? Cc: Corentin Labbe Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- crypto/crypto_user_stat.c | 2 -- include/crypto/internal/cryptouser.h | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/crypto/crypto_user_stat.c b/crypto/crypto_user_stat.c index 3e9a53233d80..d4d1cb2bedd7 100644 --- a/crypto/crypto_user_stat.c +++ b/crypto/crypto_user_stat.c @@ -22,8 +22,6 @@ static DEFINE_MUTEX(crypto_cfg_mutex); -extern struct sock *crypto_nlsk; - struct crypto_dump_info { struct sk_buff *in_skb; struct sk_buff *out_skb; diff --git a/include/crypto/internal/cryptouser.h b/include/crypto/internal/cryptouser.h index 40623f4457df..8c602b187c58 100644 --- a/include/crypto/internal/cryptouser.h +++ b/include/crypto/internal/cryptouser.h @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include +extern struct sock *crypto_nlsk; + struct crypto_alg *crypto_alg_match(struct crypto_user_alg *p, int exact); #ifdef CONFIG_CRYPTO_STATS -- cgit v1.2.3 From 466e0759269d31485074126700574230bfff3b1c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 10 Jan 2019 12:18:00 -0800 Subject: crypto: af_alg - make some functions static Some exported functions in af_alg.c aren't used outside of that file. Therefore, un-export them and make them 'static'. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- crypto/af_alg.c | 20 +++++++------------- include/crypto/if_alg.h | 7 ------- 2 files changed, 7 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 17eb09d222ff..ccae4a7ada8a 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -425,12 +425,12 @@ int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len) } EXPORT_SYMBOL_GPL(af_alg_make_sg); -void af_alg_link_sg(struct af_alg_sgl *sgl_prev, struct af_alg_sgl *sgl_new) +static void af_alg_link_sg(struct af_alg_sgl *sgl_prev, + struct af_alg_sgl *sgl_new) { sg_unmark_end(sgl_prev->sg + sgl_prev->npages - 1); sg_chain(sgl_prev->sg, sgl_prev->npages + 1, sgl_new->sg); } -EXPORT_SYMBOL_GPL(af_alg_link_sg); void af_alg_free_sg(struct af_alg_sgl *sgl) { @@ -441,7 +441,7 @@ void af_alg_free_sg(struct af_alg_sgl *sgl) } EXPORT_SYMBOL_GPL(af_alg_free_sg); -int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con) +static int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con) { struct cmsghdr *cmsg; @@ -480,7 +480,6 @@ int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con) return 0; } -EXPORT_SYMBOL_GPL(af_alg_cmsg_send); /** * af_alg_alloc_tsgl - allocate the TX SGL @@ -488,7 +487,7 @@ EXPORT_SYMBOL_GPL(af_alg_cmsg_send); * @sk socket of connection to user space * @return: 0 upon success, < 0 upon error */ -int af_alg_alloc_tsgl(struct sock *sk) +static int af_alg_alloc_tsgl(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct af_alg_ctx *ctx = ask->private; @@ -517,7 +516,6 @@ int af_alg_alloc_tsgl(struct sock *sk) return 0; } -EXPORT_SYMBOL_GPL(af_alg_alloc_tsgl); /** * aead_count_tsgl - Count number of TX SG entries @@ -654,7 +652,7 @@ EXPORT_SYMBOL_GPL(af_alg_pull_tsgl); * * @areq Request holding the TX and RX SGL */ -void af_alg_free_areq_sgls(struct af_alg_async_req *areq) +static void af_alg_free_areq_sgls(struct af_alg_async_req *areq) { struct sock *sk = areq->sk; struct alg_sock *ask = alg_sk(sk); @@ -683,7 +681,6 @@ void af_alg_free_areq_sgls(struct af_alg_async_req *areq) sock_kfree_s(sk, tsgl, areq->tsgl_entries * sizeof(*tsgl)); } } -EXPORT_SYMBOL_GPL(af_alg_free_areq_sgls); /** * af_alg_wait_for_wmem - wait for availability of writable memory @@ -692,7 +689,7 @@ EXPORT_SYMBOL_GPL(af_alg_free_areq_sgls); * @flags If MSG_DONTWAIT is set, then only report if function would sleep * @return 0 when writable memory is available, < 0 upon error */ -int af_alg_wait_for_wmem(struct sock *sk, unsigned int flags) +static int af_alg_wait_for_wmem(struct sock *sk, unsigned int flags) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int err = -ERESTARTSYS; @@ -717,7 +714,6 @@ int af_alg_wait_for_wmem(struct sock *sk, unsigned int flags) return err; } -EXPORT_SYMBOL_GPL(af_alg_wait_for_wmem); /** * af_alg_wmem_wakeup - wakeup caller when writable memory is available @@ -786,8 +782,7 @@ EXPORT_SYMBOL_GPL(af_alg_wait_for_data); * * @sk socket of connection to user space */ - -void af_alg_data_wakeup(struct sock *sk) +static void af_alg_data_wakeup(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct af_alg_ctx *ctx = ask->private; @@ -805,7 +800,6 @@ void af_alg_data_wakeup(struct sock *sk) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } -EXPORT_SYMBOL_GPL(af_alg_data_wakeup); /** * af_alg_sendmsg - implementation of sendmsg system call handler diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 482461d8931d..0d464db74bf5 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -169,9 +169,6 @@ int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern); int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); void af_alg_free_sg(struct af_alg_sgl *sgl); -void af_alg_link_sg(struct af_alg_sgl *sgl_prev, struct af_alg_sgl *sgl_new); - -int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con); static inline struct alg_sock *alg_sk(struct sock *sk) { @@ -230,15 +227,11 @@ static inline bool af_alg_readable(struct sock *sk) return PAGE_SIZE <= af_alg_rcvbuf(sk); } -int af_alg_alloc_tsgl(struct sock *sk); unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset); void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst, size_t dst_offset); -void af_alg_free_areq_sgls(struct af_alg_async_req *areq); -int af_alg_wait_for_wmem(struct sock *sk, unsigned int flags); void af_alg_wmem_wakeup(struct sock *sk); int af_alg_wait_for_data(struct sock *sk, unsigned flags); -void af_alg_data_wakeup(struct sock *sk); int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, unsigned int ivsize); ssize_t af_alg_sendpage(struct socket *sock, struct page *page, -- cgit v1.2.3 From 2ff5c5a1dc6e6c502e0a3e49db4e792804e43693 Mon Sep 17 00:00:00 2001 From: Martin Hostettler Date: Sat, 15 Dec 2018 15:34:20 +0100 Subject: vt: refactor vc_ques to allow of other private sequences. The vc_ques keeps track if a csi sequence is a private DEC control function beginning with '?'. Nowadays some private control functions begin with '>' and '='. Switch the code to instead use a new 3-bit vc_priv that allows for all private use parameter prefixes. Signed-off-by: Martin Hostettler Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 20 +++++++++++--------- include/linux/console_struct.h | 2 +- 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index ec55336abf95..b59feeaaf02b 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1341,6 +1341,8 @@ struct vc_data *vc_deallocate(unsigned int currcons) * VT102 emulator */ +enum { EPecma = 0, EPdec, EPeq, EPgt, EPlt}; + #define set_kbd(vc, x) vt_set_kbd_mode_bit((vc)->vc_num, (x)) #define clr_kbd(vc, x) vt_clr_kbd_mode_bit((vc)->vc_num, (x)) #define is_kbd(vc, x) vt_get_kbd_mode_bit((vc)->vc_num, (x)) @@ -1814,7 +1816,7 @@ static void set_mode(struct vc_data *vc, int on_off) int i; for (i = 0; i <= vc->vc_npar; i++) - if (vc->vc_ques) { + if (vc->vc_priv == EPdec) { switch(vc->vc_par[i]) { /* DEC private modes set/reset */ case 1: /* Cursor keys send ^[Ox/^[[x */ if (on_off) @@ -2030,7 +2032,7 @@ static void reset_terminal(struct vc_data *vc, int do_clear) vc->vc_top = 0; vc->vc_bottom = vc->vc_rows; vc->vc_state = ESnormal; - vc->vc_ques = 0; + vc->vc_priv = EPecma; vc->vc_translate = set_translate(LAT1_MAP, vc); vc->vc_G0_charset = LAT1_MAP; vc->vc_G1_charset = GRAF_MAP; @@ -2234,8 +2236,8 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) vc->vc_state=ESfunckey; return; } - vc->vc_ques = (c == '?'); - if (vc->vc_ques) + vc->vc_priv = (c == '?') ? EPdec : EPecma; + if (vc->vc_priv != EPecma) return; /* fall through */ case ESgetpars: @@ -2256,7 +2258,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) set_mode(vc, 0); return; case 'c': - if (vc->vc_ques) { + if (vc->vc_priv == EPdec) { if (vc->vc_par[0]) vc->vc_cursor_type = vc->vc_par[0] | (vc->vc_par[1] << 8) | (vc->vc_par[2] << 16); else @@ -2265,7 +2267,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) } break; case 'm': - if (vc->vc_ques) { + if (vc->vc_priv == EPdec) { clear_selection(); if (vc->vc_par[0]) vc->vc_complement_mask = vc->vc_par[0] << 8 | vc->vc_par[1]; @@ -2275,7 +2277,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) } break; case 'n': - if (!vc->vc_ques) { + if (vc->vc_priv == EPecma) { if (vc->vc_par[0] == 5) status_report(tty); else if (vc->vc_par[0] == 6) @@ -2283,8 +2285,8 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) } return; } - if (vc->vc_ques) { - vc->vc_ques = 0; + if (vc->vc_priv != EPecma) { + vc->vc_priv = EPecma; return; } switch(c) { diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index ab137f97ecbd..ed798e114663 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -119,7 +119,7 @@ struct vc_data { unsigned int vc_s_blink : 1; unsigned int vc_s_reverse : 1; /* misc */ - unsigned int vc_ques : 1; + unsigned int vc_priv : 3; unsigned int vc_need_wrap : 1; unsigned int vc_can_do_color : 1; unsigned int vc_report_mouse : 2; -- cgit v1.2.3 From d152159b89118841ebc0f7be2aadf79a22c6c501 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Jan 2019 15:45:58 +0100 Subject: netfilter: nf_tables: prepare nft_object for lookups via hashtable Add a 'key' structure for object, so we can look them up by name + table combination (the name can be the same in each table). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 19 ++++++++++++++----- net/netfilter/nf_tables_api.c | 27 ++++++++++++++++----------- net/netfilter/nft_objref.c | 2 +- net/netfilter/nft_quota.c | 2 +- 4 files changed, 32 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 841835a387e1..325d0a6b808b 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1011,12 +1011,22 @@ void nft_unregister_expr(struct nft_expr_type *); int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v); +/** + * struct nft_object_hash_key - key to lookup nft_object + * + * @name: name of the stateful object to look up + * @table: table the object belongs to + */ +struct nft_object_hash_key { + const char *name; + const struct nft_table *table; +}; + /** * struct nft_object - nf_tables stateful object * * @list: table stateful object list node - * @table: table this object belongs to - * @name: name of this stateful object + * @key: keys that identify this object * @genmask: generation mask * @use: number of references to this stateful object * @handle: unique object handle @@ -1025,8 +1035,7 @@ int nft_verdict_dump(struct sk_buff *skb, int type, */ struct nft_object { struct list_head list; - char *name; - struct nft_table *table; + struct nft_object_hash_key key; u32 genmask:2, use:30; u64 handle; @@ -1047,7 +1056,7 @@ struct nft_object *nft_obj_lookup(const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask); -void nft_obj_notify(struct net *net, struct nft_table *table, +void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, int family, int report, gfp_t gfp); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2b0a93300dd7..5e213941e85b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3853,7 +3853,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && nla_put_string(skb, NFTA_SET_ELEM_OBJREF, - (*nft_set_ext_obj(ext))->name) < 0) + (*nft_set_ext_obj(ext))->key.name) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && @@ -4826,7 +4826,7 @@ struct nft_object *nft_obj_lookup(const struct nft_table *table, struct nft_object *obj; list_for_each_entry_rcu(obj, &table->objects, list) { - if (!nla_strcmp(nla, obj->name) && + if (!nla_strcmp(nla, obj->key.name) && objtype == obj->ops->type->type && nft_active_genmask(obj, genmask)) return obj; @@ -5014,11 +5014,11 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, err = PTR_ERR(obj); goto err1; } - obj->table = table; + obj->key.table = table; obj->handle = nf_tables_alloc_handle(table); - obj->name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL); - if (!obj->name) { + obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL); + if (!obj->key.name) { err = -ENOMEM; goto err2; } @@ -5031,7 +5031,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, table->use++; return 0; err3: - kfree(obj->name); + kfree(obj->key.name); err2: if (obj->ops->destroy) obj->ops->destroy(&ctx, obj); @@ -5060,7 +5060,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, nfmsg->res_id = htons(net->nft.base_seq & 0xffff); if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || - nla_put_string(skb, NFTA_OBJ_NAME, obj->name) || + nla_put_string(skb, NFTA_OBJ_NAME, obj->key.name) || nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) || nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset) || @@ -5246,7 +5246,7 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) obj->ops->destroy(ctx, obj); module_put(obj->ops->type->owner); - kfree(obj->name); + kfree(obj->key.name); kfree(obj); } @@ -5297,7 +5297,7 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, return nft_delobj(&ctx, obj); } -void nft_obj_notify(struct net *net, struct nft_table *table, +void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, int family, int report, gfp_t gfp) { @@ -6404,6 +6404,11 @@ static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) nf_tables_commit_chain_free_rules_old(g0); } +static void nft_obj_del(struct nft_object *obj) +{ + list_del_rcu(&obj->list); +} + static void nft_chain_del(struct nft_chain *chain) { struct nft_table *table = chain->table; @@ -6580,7 +6585,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELOBJ: - list_del_rcu(&nft_trans_obj(trans)->list); + nft_obj_del(nft_trans_obj(trans)); nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), NFT_MSG_DELOBJ); break; @@ -7330,7 +7335,7 @@ static void __nft_release_tables(struct net *net) nft_set_destroy(set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { - list_del(&obj->list); + nft_obj_del(obj); table->use--; nft_obj_destroy(&ctx, obj); } diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index a3185ca2a3a9..58eb75ad61bf 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -53,7 +53,7 @@ static int nft_objref_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_object *obj = nft_objref_priv(expr); - if (nla_put_string(skb, NFTA_OBJREF_IMM_NAME, obj->name) || + if (nla_put_string(skb, NFTA_OBJREF_IMM_NAME, obj->key.name) || nla_put_be32(skb, NFTA_OBJREF_IMM_TYPE, htonl(obj->ops->type->type))) goto nla_put_failure; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 0ed124a93fcf..354cde67bca9 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -61,7 +61,7 @@ static void nft_quota_obj_eval(struct nft_object *obj, if (overquota && !test_and_set_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) - nft_obj_notify(nft_net(pkt), obj->table, obj, 0, 0, + nft_obj_notify(nft_net(pkt), obj->key.table, obj, 0, 0, NFT_MSG_NEWOBJ, nft_pf(pkt), 0, GFP_ATOMIC); } -- cgit v1.2.3 From 4d44175aa5bb5f68772b1eb0306554812294ca52 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Jan 2019 15:45:59 +0100 Subject: netfilter: nf_tables: handle nft_object lookups via rhltable Instead of linear search, use rhlist interface to look up the objects. This fixes rulesets with thousands of named objects (quota, counters and the like). We only use a single table for this and consider the address of the table we're doing the lookup in as a part of the key. This reduces restore time of a sample ruleset with ~20k named counters from 37 seconds to 0.8 seconds. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 7 ++- net/netfilter/nf_tables_api.c | 103 +++++++++++++++++++++++++++++++++----- net/netfilter/nft_objref.c | 3 +- 3 files changed, 98 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 325d0a6b808b..45eba7d7ab38 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1027,14 +1027,16 @@ struct nft_object_hash_key { * * @list: table stateful object list node * @key: keys that identify this object + * @rhlhead: nft_objname_ht node * @genmask: generation mask * @use: number of references to this stateful object * @handle: unique object handle * @ops: object operations - * @data: object data, layout depends on type + * @data: object data, layout depends on type */ struct nft_object { struct list_head list; + struct rhlist_head rhlhead; struct nft_object_hash_key key; u32 genmask:2, use:30; @@ -1052,7 +1054,8 @@ static inline void *nft_obj_data(const struct nft_object *obj) #define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) -struct nft_object *nft_obj_lookup(const struct nft_table *table, +struct nft_object *nft_obj_lookup(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5e213941e85b..621ff834d3a4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -37,10 +37,16 @@ enum { NFT_VALIDATE_DO, }; +static struct rhltable nft_objname_ht; + static u32 nft_chain_hash(const void *data, u32 len, u32 seed); static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed); static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *); +static u32 nft_objname_hash(const void *data, u32 len, u32 seed); +static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed); +static int nft_objname_hash_cmp(struct rhashtable_compare_arg *, const void *); + static const struct rhashtable_params nft_chain_ht_params = { .head_offset = offsetof(struct nft_chain, rhlhead), .key_offset = offsetof(struct nft_chain, name), @@ -51,6 +57,15 @@ static const struct rhashtable_params nft_chain_ht_params = { .automatic_shrinking = true, }; +static const struct rhashtable_params nft_objname_ht_params = { + .head_offset = offsetof(struct nft_object, rhlhead), + .key_offset = offsetof(struct nft_object, key), + .hashfn = nft_objname_hash, + .obj_hashfn = nft_objname_hash_obj, + .obj_cmpfn = nft_objname_hash_cmp, + .automatic_shrinking = true, +}; + static void nft_validate_state_update(struct net *net, u8 new_validate_state) { switch (net->nft.validate_state) { @@ -814,6 +829,34 @@ static int nft_chain_hash_cmp(struct rhashtable_compare_arg *arg, return strcmp(chain->name, name); } +static u32 nft_objname_hash(const void *data, u32 len, u32 seed) +{ + const struct nft_object_hash_key *k = data; + + seed ^= hash_ptr(k->table, 32); + + return jhash(k->name, strlen(k->name), seed); +} + +static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct nft_object *obj = data; + + return nft_objname_hash(&obj->key, 0, seed); +} + +static int nft_objname_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct nft_object_hash_key *k = arg->key; + const struct nft_object *obj = ptr; + + if (obj->key.table != k->table) + return -1; + + return strcmp(obj->key.name, k->name); +} + static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -1070,7 +1113,7 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) return ERR_PTR(-ENOENT); } -static bool lockdep_commit_lock_is_held(struct net *net) +static bool lockdep_commit_lock_is_held(const struct net *net) { #ifdef CONFIG_PROVE_LOCKING return lockdep_is_held(&net->nft.commit_mutex); @@ -4386,7 +4429,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -EINVAL; goto err2; } - obj = nft_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF], + obj = nft_obj_lookup(ctx->net, ctx->table, + nla[NFTA_SET_ELEM_OBJREF], set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); @@ -4819,18 +4863,36 @@ void nft_unregister_obj(struct nft_object_type *obj_type) } EXPORT_SYMBOL_GPL(nft_unregister_obj); -struct nft_object *nft_obj_lookup(const struct nft_table *table, +struct nft_object *nft_obj_lookup(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask) { + struct nft_object_hash_key k = { .table = table }; + char search[NFT_OBJ_MAXNAMELEN]; + struct rhlist_head *tmp, *list; struct nft_object *obj; - list_for_each_entry_rcu(obj, &table->objects, list) { - if (!nla_strcmp(nla, obj->key.name) && - objtype == obj->ops->type->type && - nft_active_genmask(obj, genmask)) + nla_strlcpy(search, nla, sizeof(search)); + k.name = search; + + WARN_ON_ONCE(!rcu_read_lock_held() && + !lockdep_commit_lock_is_held(net)); + + rcu_read_lock(); + list = rhltable_lookup(&nft_objname_ht, &k, nft_objname_ht_params); + if (!list) + goto out; + + rhl_for_each_entry_rcu(obj, tmp, list, rhlhead) { + if (objtype == obj->ops->type->type && + nft_active_genmask(obj, genmask)) { + rcu_read_unlock(); return obj; + } } +out: + rcu_read_unlock(); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(nft_obj_lookup); @@ -4988,7 +5050,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); if (err != -ENOENT) { @@ -5027,9 +5089,18 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (err < 0) goto err3; + err = rhltable_insert(&nft_objname_ht, &obj->rhlhead, + nft_objname_ht_params); + if (err < 0) + goto err4; + list_add_tail_rcu(&obj->list, &table->objects); table->use++; return 0; +err4: + /* queued in transaction log */ + INIT_LIST_HEAD(&obj->list); + return err; err3: kfree(obj->key.name); err2: @@ -5215,7 +5286,7 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return PTR_ERR(obj); @@ -5280,7 +5351,7 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, obj = nft_obj_lookup_byhandle(table, attr, objtype, genmask); } else { attr = nla[NFTA_OBJ_NAME]; - obj = nft_obj_lookup(table, attr, objtype, genmask); + obj = nft_obj_lookup(net, table, attr, objtype, genmask); } if (IS_ERR(obj)) { @@ -6406,6 +6477,7 @@ static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) static void nft_obj_del(struct nft_object *obj) { + rhltable_remove(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); list_del_rcu(&obj->list); } @@ -6721,7 +6793,7 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWOBJ: trans->ctx.table->use--; - list_del_rcu(&nft_trans_obj(trans)->list); + nft_obj_del(nft_trans_obj(trans)); break; case NFT_MSG_DELOBJ: trans->ctx.table->use++; @@ -7397,12 +7469,18 @@ static int __init nf_tables_module_init(void) if (err < 0) goto err3; + err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params); + if (err < 0) + goto err4; + /* must be last */ err = nfnetlink_subsys_register(&nf_tables_subsys); if (err < 0) - goto err4; + goto err5; return err; +err5: + rhltable_destroy(&nft_objname_ht); err4: unregister_netdevice_notifier(&nf_tables_flowtable_notifier); err3: @@ -7422,6 +7500,7 @@ static void __exit nf_tables_module_exit(void) unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_destroy_work); rcu_barrier(); + rhltable_destroy(&nft_objname_ht); nf_tables_core_module_exit(); } diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 58eb75ad61bf..c1f2adf198a0 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -38,7 +38,8 @@ static int nft_objref_init(const struct nft_ctx *ctx, return -EINVAL; objtype = ntohl(nla_get_be32(tb[NFTA_OBJREF_IMM_TYPE])); - obj = nft_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype, + obj = nft_obj_lookup(ctx->net, ctx->table, + tb[NFTA_OBJREF_IMM_NAME], objtype, genmask); if (IS_ERR(obj)) return -ENOENT; -- cgit v1.2.3 From 10870dd89e956d911d1a39474c0bf4a18c72cffc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Jan 2019 17:35:34 +0100 Subject: netfilter: nf_tables: add direct calls for all builtin expressions With CONFIG_RETPOLINE its faster to add an if (ptr == &foo_func) check and and use direct calls for all the built-in expressions. ~15% improvement in pathological cases. checkpatch doesn't like the X macro due to the embedded return statement, but the macro has a very limited scope so I don't think its a problem. I would like to avoid bugs of the form If (e->ops->eval == (unsigned long)nft_foo_eval) nft_bar_eval(); and open-coded if ()/else if()/else cascade, thus the macro. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 16 ++++++++++++++++ net/netfilter/nf_tables_core.c | 25 ++++++++++++++++++------- net/netfilter/nft_bitwise.c | 5 ++--- net/netfilter/nft_byteorder.c | 6 +++--- net/netfilter/nft_cmp.c | 6 +++--- net/netfilter/nft_dynset.c | 5 ++--- net/netfilter/nft_immediate.c | 6 +++--- net/netfilter/nft_payload.c | 6 +++--- net/netfilter/nft_range.c | 5 ++--- net/netfilter/nft_rt.c | 6 +++--- 10 files changed, 55 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 2046d104f323..7281895fa6d9 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -80,6 +80,22 @@ struct nft_regs; struct nft_pktinfo; void nft_meta_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_cmp_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); void nft_lookup_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_payload_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_immediate_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_bitwise_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_range_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_byteorder_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_dynset_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_rt_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index a50500232b0a..2a00aef7b6d4 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -124,14 +124,25 @@ static void expr_call_ops_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nft_pktinfo *pkt) { +#ifdef CONFIG_RETPOLINE unsigned long e = (unsigned long)expr->ops->eval; - - if (e == (unsigned long)nft_meta_get_eval) - nft_meta_get_eval(expr, regs, pkt); - else if (e == (unsigned long)nft_lookup_eval) - nft_lookup_eval(expr, regs, pkt); - else - expr->ops->eval(expr, regs, pkt); +#define X(e, fun) \ + do { if ((e) == (unsigned long)(fun)) \ + return fun(expr, regs, pkt); } while (0) + + X(e, nft_payload_eval); + X(e, nft_cmp_eval); + X(e, nft_meta_get_eval); + X(e, nft_lookup_eval); + X(e, nft_range_eval); + X(e, nft_immediate_eval); + X(e, nft_byteorder_eval); + X(e, nft_dynset_eval); + X(e, nft_rt_get_eval); + X(e, nft_bitwise_eval); +#undef X +#endif /* CONFIG_RETPOLINE */ + expr->ops->eval(expr, regs, pkt); } unsigned int diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index fff8073e2a56..2c75b9e0474e 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -25,9 +25,8 @@ struct nft_bitwise { struct nft_data xor; }; -static void nft_bitwise_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_bitwise_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_bitwise *priv = nft_expr_priv(expr); const u32 *src = ®s->data[priv->sreg]; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 13d4e421a6b3..19dbc34cc75e 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -26,9 +26,9 @@ struct nft_byteorder { u8 size; }; -static void nft_byteorder_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_byteorder_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_byteorder *priv = nft_expr_priv(expr); u32 *src = ®s->data[priv->sreg]; diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 79d48c1d06f4..f9f1fa66a16e 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -24,9 +24,9 @@ struct nft_cmp_expr { enum nft_cmp_ops op:8; }; -static void nft_cmp_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_cmp_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_cmp_expr *priv = nft_expr_priv(expr); int d; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 07d4efd3d851..9658493d37d4 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -62,9 +62,8 @@ err1: return NULL; } -static void nft_dynset_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_dynset_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_dynset *priv = nft_expr_priv(expr); struct nft_set *set = priv->set; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 0777a93211e2..3e5ed787b1d4 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -17,9 +17,9 @@ #include #include -static void nft_immediate_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_immediate_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index e110b0ebbf58..54e15de4b79a 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -70,9 +70,9 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; } -static void nft_payload_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_payload_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_payload *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index cedb96c3619f..529ac8acb19d 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -23,9 +23,8 @@ struct nft_range_expr { enum nft_range_ops op:8; }; -static void nft_range_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_range_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_range_expr *priv = nft_expr_priv(expr); int d1, d2; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index f35fa33913ae..c48daed5c46b 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -53,9 +53,9 @@ static u16 get_tcpmss(const struct nft_pktinfo *pkt, const struct dst_entry *skb return mtu - minlen; } -static void nft_rt_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_rt_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_rt *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; -- cgit v1.2.3 From 8e2f311a68494a6677c1724bdcb10bada21af37c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 11 Jan 2019 14:46:15 +0100 Subject: netfilter: physdev: relax br_netfilter dependency Following command: iptables -D FORWARD -m physdev ... causes connectivity loss in some setups. Reason is that iptables userspace will probe kernel for the module revision of the physdev patch, and physdev has an artificial dependency on br_netfilter (xt_physdev use makes no sense unless a br_netfilter module is loaded). This causes the "phydev" module to be loaded, which in turn enables the "call-iptables" infrastructure. bridged packets might then get dropped by the iptables ruleset. The better fix would be to change the "call-iptables" defaults to 0 and enforce explicit setting to 1, but that breaks backwards compatibility. This does the next best thing: add a request_module call to checkentry. This was a stray '-D ... -m physdev' won't activate br_netfilter anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/br_netfilter.h | 1 - net/bridge/br_netfilter_hooks.c | 5 ----- net/netfilter/xt_physdev.c | 9 +++++++-- 3 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 4cd56808ac4e..89808ce293c4 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -43,7 +43,6 @@ static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) } struct net_device *setup_pre_routing(struct sk_buff *skb); -void br_netfilter_enable(void); #if IS_ENABLED(CONFIG_IPV6) int br_validate_ipv6(struct net *net, struct sk_buff *skb); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index c93c35bb73dd..40d058378b52 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -881,11 +881,6 @@ static const struct nf_br_ops br_ops = { .br_dev_xmit_hook = br_nf_dev_xmit, }; -void br_netfilter_enable(void) -{ -} -EXPORT_SYMBOL_GPL(br_netfilter_enable); - /* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because * br_dev_queue_push_xmit is called afterwards */ static const struct nf_hook_ops br_nf_ops[] = { diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index 4034d70bff39..b2e39cb6a590 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -96,8 +96,7 @@ match_outdev: static int physdev_mt_check(const struct xt_mtchk_param *par) { const struct xt_physdev_info *info = par->matchinfo; - - br_netfilter_enable(); + static bool brnf_probed __read_mostly; if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || info->bitmask & ~XT_PHYSDEV_OP_MASK) @@ -111,6 +110,12 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) if (par->hook_mask & (1 << NF_INET_LOCAL_OUT)) return -EINVAL; } + + if (!brnf_probed) { + brnf_probed = true; + request_module("br_netfilter"); + } + return 0; } -- cgit v1.2.3 From 75dd48e2e420a3cbbe56dd7adfcc6f142c948272 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Mon, 14 Jan 2019 18:41:35 +0100 Subject: netfilter: nf_tables: Support RULE_ID reference in new rule To allow for a batch to contain rules in arbitrary ordering, introduce NFTA_RULE_POSITION_ID attribute which works just like NFTA_RULE_POSITION but contains the ID of another rule within the same batch. This helps iptables-nft-restore handling dumps with mixed insert/append commands correctly. Note that NFTA_RULE_POSITION takes precedence over NFTA_RULE_POSITION_ID, so if the former is present, the latter is ignored. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nf_tables_api.c | 9 +++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 7de4f1bdaf06..99ca95b830b6 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -219,6 +219,7 @@ enum nft_chain_attributes { * @NFTA_RULE_POSITION: numeric handle of the previous rule (NLA_U64) * @NFTA_RULE_USERDATA: user data (NLA_BINARY, NFT_USERDATA_MAXLEN) * @NFTA_RULE_ID: uniquely identifies a rule in a transaction (NLA_U32) + * @NFTA_RULE_POSITION_ID: transaction unique identifier of the previous rule (NLA_U32) */ enum nft_rule_attributes { NFTA_RULE_UNSPEC, @@ -231,6 +232,7 @@ enum nft_rule_attributes { NFTA_RULE_USERDATA, NFTA_RULE_PAD, NFTA_RULE_ID, + NFTA_RULE_POSITION_ID, __NFTA_RULE_MAX }; #define NFTA_RULE_MAX (__NFTA_RULE_MAX - 1) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 621ff834d3a4..d88c86c5b433 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2610,6 +2610,9 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) return 0; } +static struct nft_rule *nft_rule_lookup_byid(const struct net *net, + const struct nlattr *nla); + #define NFT_RULE_MAXEXPRS 128 static int nf_tables_newrule(struct net *net, struct sock *nlsk, @@ -2679,6 +2682,12 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); return PTR_ERR(old_rule); } + } else if (nla[NFTA_RULE_POSITION_ID]) { + old_rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_POSITION_ID]); + if (IS_ERR(old_rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION_ID]); + return PTR_ERR(old_rule); + } } } -- cgit v1.2.3 From a47c5404816254d6cc4787f335c4720066a538e6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:32 +0100 Subject: netfilter: conntrack: handle builtin l4proto packet functions via direct calls The l4 protocol trackers are invoked via indirect call: l4proto->packet(). With one exception (gre), all l4trackers are builtin, so we can make .packet optional and use a direct call for most protocols. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 37 +++++++++++++++++++++++ net/netfilter/nf_conntrack_core.c | 45 +++++++++++++++++++++++++++- net/netfilter/nf_conntrack_proto_dccp.c | 8 ++--- net/netfilter/nf_conntrack_proto_icmp.c | 12 +++----- net/netfilter/nf_conntrack_proto_icmpv6.c | 10 +++---- net/netfilter/nf_conntrack_proto_sctp.c | 12 ++++---- net/netfilter/nf_conntrack_proto_tcp.c | 11 ++++--- net/netfilter/nf_conntrack_proto_udp.c | 22 +++++++------- 8 files changed, 113 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index ae7b86f587f2..6ca4355ae3dc 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -99,6 +99,43 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state); + +int nf_conntrack_icmp_packet(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); + +int nf_conntrack_icmpv6_packet(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); + +int nf_conntrack_udp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); +int nf_conntrack_udplite_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); +int nf_conntrack_tcp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); +int nf_conntrack_dccp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); +int nf_conntrack_sctp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); + /* Existing built-in generic protocol */ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 741b533148ba..5dfd95ae510d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1522,6 +1522,45 @@ nf_conntrack_handle_icmp(struct nf_conn *tmpl, return ret; } +/* Returns verdict for packet, or -1 for invalid. */ +static int nf_conntrack_handle_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) +{ + switch (nf_ct_protonum(ct)) { + case IPPROTO_TCP: + return nf_conntrack_tcp_packet(ct, skb, dataoff, + ctinfo, state); + case IPPROTO_UDP: + return nf_conntrack_udp_packet(ct, skb, dataoff, + ctinfo, state); + case IPPROTO_ICMP: + return nf_conntrack_icmp_packet(ct, skb, ctinfo, state); + case IPPROTO_ICMPV6: + return nf_conntrack_icmpv6_packet(ct, skb, ctinfo, state); +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + case IPPROTO_UDPLITE: + return nf_conntrack_udplite_packet(ct, skb, dataoff, + ctinfo, state); +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + case IPPROTO_SCTP: + return nf_conntrack_sctp_packet(ct, skb, dataoff, + ctinfo, state); +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP + case IPPROTO_DCCP: + return nf_conntrack_dccp_packet(ct, skb, dataoff, + ctinfo, state); +#endif + } + + WARN_ON_ONCE(1); + return -NF_ACCEPT; +} + unsigned int nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) { @@ -1583,7 +1622,11 @@ repeat: goto out; } - ret = l4proto->packet(ct, skb, dataoff, ctinfo, state); + if (l4proto->packet) + ret = l4proto->packet(ct, skb, dataoff, ctinfo, state); + else + ret = nf_conntrack_handle_packet(ct, skb, dataoff, ctinfo, state); + if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 023c1445bc39..84408ec80624 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -472,9 +472,10 @@ out_invalid: return true; } -static int dccp_packet(struct nf_conn *ct, struct sk_buff *skb, - unsigned int dataoff, enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct dccp_hdr _dh, *dh; @@ -839,7 +840,6 @@ static struct nf_proto_net *dccp_get_net_proto(struct net *net) const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp = { .l4proto = IPPROTO_DCCP, - .packet = dccp_packet, .can_early_drop = dccp_can_early_drop, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = dccp_print_conntrack, diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index de64d8a5fdfd..381a7f3ea68a 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -68,11 +68,10 @@ static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, } /* Returns verdict for packet, or -1 for invalid. */ -static int icmp_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_icmp_packet(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic @@ -350,9 +349,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .l4proto = IPPROTO_ICMP, .pkt_to_tuple = icmp_pkt_to_tuple, .invert_tuple = icmp_invert_tuple, - .packet = icmp_packet, - .destroy = NULL, - .me = NULL, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmp_tuple_to_nlattr, .nlattr_tuple_size = icmp_nlattr_tuple_size, diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index a15eefb8e317..93f27d0bcb75 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -86,11 +86,10 @@ static unsigned int *icmpv6_get_timeouts(struct net *net) } /* Returns verdict for packet, or -1 for invalid. */ -static int icmpv6_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_icmpv6_packet(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { unsigned int *timeout = nf_ct_timeout_lookup(ct); static const u8 valid_new[] = { @@ -361,7 +360,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .l4proto = IPPROTO_ICMPV6, .pkt_to_tuple = icmpv6_pkt_to_tuple, .invert_tuple = icmpv6_invert_tuple, - .packet = icmpv6_packet, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmpv6_tuple_to_nlattr, .nlattr_tuple_size = icmpv6_nlattr_tuple_size, diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index d53e3e78f605..952f2cc0fd74 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -357,11 +357,11 @@ out_invalid: } /* Returns verdict for packet, or -NF_ACCEPT for invalid. */ -static int sctp_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_sctp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { enum sctp_conntrack new_state, old_state; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -759,9 +759,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp = { #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = sctp_print_conntrack, #endif - .packet = sctp_packet, .can_early_drop = sctp_can_early_drop, - .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_size = SCTP_NLATTR_SIZE, .to_nlattr = sctp_to_nlattr, diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 4dcbd51a8e97..32aac9a835d4 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -829,11 +829,11 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, } /* Returns verdict for packet, or -1 for invalid. */ -static int tcp_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_tcp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); @@ -1535,7 +1535,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = tcp_print_conntrack, #endif - .packet = tcp_packet, .can_early_drop = tcp_can_early_drop, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .to_nlattr = tcp_to_nlattr, diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index b4f5d5e82031..e1f409aa0006 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -85,11 +85,11 @@ static bool udp_error(struct sk_buff *skb, } /* Returns verdict for packet, and may modify conntracktype */ -static int udp_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_udp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { unsigned int *timeouts; @@ -177,11 +177,11 @@ static bool udplite_error(struct sk_buff *skb, } /* Returns verdict for packet, and may modify conntracktype */ -static int udplite_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_udplite_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { unsigned int *timeouts; @@ -319,7 +319,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp = { .l4proto = IPPROTO_UDP, .allow_clash = true, - .packet = udp_packet, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, @@ -344,7 +343,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite = { .l4proto = IPPROTO_UDPLITE, .allow_clash = true, - .packet = udplite_packet, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, -- cgit v1.2.3 From e2e48b471634faa6958718c27208d366b13fe878 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:33 +0100 Subject: netfilter: conntrack: handle icmp pkt_to_tuple helper via direct calls rather than handling them via indirect call, use a direct one instead. This leaves GRE as the last user of this indirect call facility. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 10 ++++++++++ net/netfilter/nf_conntrack_core.c | 6 ++++++ net/netfilter/nf_conntrack_proto_icmp.c | 5 ++--- net/netfilter/nf_conntrack_proto_icmpv6.c | 9 ++++----- 4 files changed, 22 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 6ca4355ae3dc..46d554806eb3 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -90,6 +90,16 @@ struct nf_conntrack_l4proto { struct module *me; }; +bool icmp_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct net *net, + struct nf_conntrack_tuple *tuple); + +bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct net *net, + struct nf_conntrack_tuple *tuple); + int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 5dfd95ae510d..b3840d36c3a6 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -274,6 +274,12 @@ nf_ct_get_tuple(const struct sk_buff *skb, tuple->dst.protonum = protonum; tuple->dst.dir = IP_CT_DIR_ORIGINAL; + switch (protonum) { + case IPPROTO_ICMPV6: + return icmpv6_pkt_to_tuple(skb, dataoff, net, tuple); + case IPPROTO_ICMP: + return icmp_pkt_to_tuple(skb, dataoff, net, tuple); + } if (unlikely(l4proto->pkt_to_tuple)) return l4proto->pkt_to_tuple(skb, dataoff, net, tuple); diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 381a7f3ea68a..805c1fe5b837 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -25,8 +25,8 @@ static const unsigned int nf_ct_icmp_timeout = 30*HZ; -static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct net *net, struct nf_conntrack_tuple *tuple) +bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmphdr *hp; struct icmphdr _hdr; @@ -347,7 +347,6 @@ static struct nf_proto_net *icmp_get_net_proto(struct net *net) const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = { .l4proto = IPPROTO_ICMP, - .pkt_to_tuple = icmp_pkt_to_tuple, .invert_tuple = icmp_invert_tuple, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmp_tuple_to_nlattr, diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 93f27d0bcb75..20cd55e55e41 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -30,10 +30,10 @@ static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; -static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, - unsigned int dataoff, - struct net *net, - struct nf_conntrack_tuple *tuple) +bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct net *net, + struct nf_conntrack_tuple *tuple) { const struct icmp6hdr *hp; struct icmp6hdr _hdr; @@ -358,7 +358,6 @@ static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = { .l4proto = IPPROTO_ICMPV6, - .pkt_to_tuple = icmpv6_pkt_to_tuple, .invert_tuple = icmpv6_invert_tuple, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmpv6_tuple_to_nlattr, -- cgit v1.2.3 From 202e651cd43c69a43f75b445e90f55b59f9af0ad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:34 +0100 Subject: netfilter: conntrack: gre: convert rwlock to rcu We can use gre. Lock is only needed when a new expectation is added. In case a single spinlock proves to be problematic we can either add one per netns or use an array of locks combined with net_hash_mix() or similar to pick the 'correct' one. But given this is only needed for an expectation rather than per packet a single one should be ok. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 1 + net/netfilter/nf_conntrack_proto_gre.c | 37 ++++++++++-------------- 2 files changed, 16 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index 6989e2e4eabf..222c9d3d453f 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -19,6 +19,7 @@ struct nf_conn; struct nf_ct_gre_keymap { struct list_head list; struct nf_conntrack_tuple tuple; + struct rcu_head rcu; }; enum grep_conntrack { diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 8899b51aad44..34dd89485be2 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -49,6 +49,8 @@ static const unsigned int gre_timeouts[GRE_CT_MAX] = { }; static unsigned int proto_gre_net_id __read_mostly; +/* used when expectation is added */ +static DEFINE_SPINLOCK(keymap_lock); static inline struct netns_proto_gre *gre_pernet(struct net *net) { @@ -60,12 +62,12 @@ static void nf_ct_gre_keymap_flush(struct net *net) struct netns_proto_gre *net_gre = gre_pernet(net); struct nf_ct_gre_keymap *km, *tmp; - write_lock_bh(&net_gre->keymap_lock); + spin_lock_bh(&keymap_lock); list_for_each_entry_safe(km, tmp, &net_gre->keymap_list, list) { - list_del(&km->list); - kfree(km); + list_del_rcu(&km->list); + kfree_rcu(km, rcu); } - write_unlock_bh(&net_gre->keymap_lock); + spin_unlock_bh(&keymap_lock); } static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, @@ -85,14 +87,12 @@ static __be16 gre_keymap_lookup(struct net *net, struct nf_conntrack_tuple *t) struct nf_ct_gre_keymap *km; __be16 key = 0; - read_lock_bh(&net_gre->keymap_lock); - list_for_each_entry(km, &net_gre->keymap_list, list) { + list_for_each_entry_rcu(km, &net_gre->keymap_list, list) { if (gre_key_cmpfn(km, t)) { key = km->tuple.src.u.gre.key; break; } } - read_unlock_bh(&net_gre->keymap_lock); pr_debug("lookup src key 0x%x for ", key); nf_ct_dump_tuple(t); @@ -112,14 +112,10 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, kmp = &ct_pptp_info->keymap[dir]; if (*kmp) { /* check whether it's a retransmission */ - read_lock_bh(&net_gre->keymap_lock); - list_for_each_entry(km, &net_gre->keymap_list, list) { - if (gre_key_cmpfn(km, t) && km == *kmp) { - read_unlock_bh(&net_gre->keymap_lock); + list_for_each_entry_rcu(km, &net_gre->keymap_list, list) { + if (gre_key_cmpfn(km, t) && km == *kmp) return 0; - } } - read_unlock_bh(&net_gre->keymap_lock); pr_debug("trying to override keymap_%s for ct %p\n", dir == IP_CT_DIR_REPLY ? "reply" : "orig", ct); return -EEXIST; @@ -134,9 +130,9 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, pr_debug("adding new entry %p: ", km); nf_ct_dump_tuple(&km->tuple); - write_lock_bh(&net_gre->keymap_lock); + spin_lock_bh(&keymap_lock); list_add_tail(&km->list, &net_gre->keymap_list); - write_unlock_bh(&net_gre->keymap_lock); + spin_unlock_bh(&keymap_lock); return 0; } @@ -145,24 +141,22 @@ EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_add); /* destroy the keymap entries associated with specified master ct */ void nf_ct_gre_keymap_destroy(struct nf_conn *ct) { - struct net *net = nf_ct_net(ct); - struct netns_proto_gre *net_gre = gre_pernet(net); struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); enum ip_conntrack_dir dir; pr_debug("entering for ct %p\n", ct); - write_lock_bh(&net_gre->keymap_lock); + spin_lock_bh(&keymap_lock); for (dir = IP_CT_DIR_ORIGINAL; dir < IP_CT_DIR_MAX; dir++) { if (ct_pptp_info->keymap[dir]) { pr_debug("removing %p from list\n", ct_pptp_info->keymap[dir]); - list_del(&ct_pptp_info->keymap[dir]->list); - kfree(ct_pptp_info->keymap[dir]); + list_del_rcu(&ct_pptp_info->keymap[dir]->list); + kfree_rcu(ct_pptp_info->keymap[dir], rcu); ct_pptp_info->keymap[dir] = NULL; } } - write_unlock_bh(&net_gre->keymap_lock); + spin_unlock_bh(&keymap_lock); } EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_destroy); @@ -365,7 +359,6 @@ static int gre_init_net(struct net *net) struct nf_proto_net *nf = &net_gre->nf; int i; - rwlock_init(&net_gre->keymap_lock); INIT_LIST_HEAD(&net_gre->keymap_list); for (i = 0; i < GRE_CT_MAX; i++) net_gre->gre_timeouts[i] = gre_timeouts[i]; -- cgit v1.2.3 From 22fc4c4c9fd60427bcda00878cee94e7622cfa7a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:35 +0100 Subject: netfilter: conntrack: gre: switch module to be built-in This makes the last of the modular l4 trackers 'bool'. After this, all infrastructure to handle dynamic l4 protocol registration becomes obsolete and can be removed in followup patches. Old: 302824 net/netfilter/nf_conntrack.ko 21504 net/netfilter/nf_conntrack_proto_gre.ko New: 313728 net/netfilter/nf_conntrack.ko Old: text data bss dec hex filename 6281 1732 4 8017 1f51 nf_conntrack_proto_gre.ko 108356 20613 236 129205 1f8b5 nf_conntrack.ko New: 112095 21381 240 133716 20a54 nf_conntrack.ko The size increase is only temporary. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 14 +--- include/net/netfilter/ipv4/nf_conntrack_ipv4.h | 3 + include/net/netfilter/nf_conntrack_l4proto.h | 7 ++ include/net/netns/conntrack.h | 17 +++++ net/netfilter/Kconfig | 2 +- net/netfilter/Makefile | 3 +- net/netfilter/nf_conntrack_proto.c | 7 +- net/netfilter/nf_conntrack_proto_gre.c | 93 +++++------------------- net/netfilter/nfnetlink_cttimeout.c | 7 +- 9 files changed, 55 insertions(+), 98 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index 222c9d3d453f..59714e9ee4ef 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -22,23 +22,11 @@ struct nf_ct_gre_keymap { struct rcu_head rcu; }; -enum grep_conntrack { - GRE_CT_UNREPLIED, - GRE_CT_REPLIED, - GRE_CT_MAX -}; - -struct netns_proto_gre { - struct nf_proto_net nf; - rwlock_t keymap_lock; - struct list_head keymap_list; - unsigned int gre_timeouts[GRE_CT_MAX]; -}; - /* add new tuple->key_reply pair to keymap */ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t); +void nf_ct_gre_keymap_flush(struct net *net); /* delete keymap entries */ void nf_ct_gre_keymap_destroy(struct nf_conn *ct); diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h index 135ee702c7b0..2c8c2b023848 100644 --- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h +++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h @@ -22,5 +22,8 @@ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp; #ifdef CONFIG_NF_CT_PROTO_UDPLITE extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite; #endif +#ifdef CONFIG_NF_CT_PROTO_GRE +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre; +#endif #endif /*_NF_CONNTRACK_IPV4_H*/ diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 46d554806eb3..fded3f164dcc 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -239,4 +239,11 @@ static inline struct nf_sctp_net *nf_sctp_pernet(struct net *net) } #endif +#ifdef CONFIG_NF_CT_PROTO_GRE +static inline struct nf_gre_net *nf_gre_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.gre; +} +#endif + #endif /*_NF_CONNTRACK_PROTOCOL_H*/ diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 51cba0b8adf5..c72f413a2d4d 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -70,6 +70,20 @@ struct nf_sctp_net { }; #endif +#ifdef CONFIG_NF_CT_PROTO_GRE +enum gre_conntrack { + GRE_CT_UNREPLIED, + GRE_CT_REPLIED, + GRE_CT_MAX +}; + +struct nf_gre_net { + struct nf_proto_net nf; + struct list_head keymap_list; + unsigned int timeouts[GRE_CT_MAX]; +}; +#endif + struct nf_ip_net { struct nf_generic_net generic; struct nf_tcp_net tcp; @@ -82,6 +96,9 @@ struct nf_ip_net { #ifdef CONFIG_NF_CT_PROTO_SCTP struct nf_sctp_net sctp; #endif +#ifdef CONFIG_NF_CT_PROTO_GRE + struct nf_gre_net gre; +#endif }; struct ct_pcpu { diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index beb3a69ce1d4..fefd63a243f2 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -174,7 +174,7 @@ config NF_CT_PROTO_DCCP If unsure, say Y. config NF_CT_PROTO_GRE - tristate + bool config NF_CT_PROTO_SCTP bool 'SCTP protocol connection tracking support' diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 1ae65a314d7a..e66067befa42 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -13,6 +13,7 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o +nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o obj-$(CONFIG_NETFILTER) = netfilter.o @@ -25,8 +26,6 @@ obj-$(CONFIG_NETFILTER_NETLINK_OSF) += nfnetlink_osf.o # connection tracking obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o -obj-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o - # netlink interface for nf_conntrack obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o obj-$(CONFIG_NF_CT_NETLINK_TIMEOUT) += nfnetlink_cttimeout.o diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 2bbc32d939e4..e113bb2dc88d 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -817,6 +817,9 @@ static const struct nf_conntrack_l4proto * const builtin_l4proto[] = { #ifdef CONFIG_NF_CT_PROTO_UDPLITE &nf_conntrack_l4proto_udplite, #endif +#ifdef CONFIG_NF_CT_PROTO_GRE + &nf_conntrack_l4proto_gre, +#endif #if IS_ENABLED(CONFIG_IPV6) &nf_conntrack_l4proto_icmpv6, #endif /* CONFIG_IPV6 */ @@ -897,9 +900,11 @@ void nf_conntrack_proto_pernet_fini(struct net *net) ARRAY_SIZE(builtin_l4proto)); pn->users--; nf_ct_l4proto_unregister_sysctl(pn); +#ifdef CONFIG_NF_CT_PROTO_GRE + nf_ct_gre_keymap_flush(net); +#endif } - module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, &nf_conntrack_htable_size, 0600); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 34dd89485be2..68f9bfb79c4e 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -48,18 +48,17 @@ static const unsigned int gre_timeouts[GRE_CT_MAX] = { [GRE_CT_REPLIED] = 180*HZ, }; -static unsigned int proto_gre_net_id __read_mostly; /* used when expectation is added */ static DEFINE_SPINLOCK(keymap_lock); -static inline struct netns_proto_gre *gre_pernet(struct net *net) +static inline struct nf_gre_net *gre_pernet(struct net *net) { - return net_generic(net, proto_gre_net_id); + return &net->ct.nf_ct_proto.gre; } -static void nf_ct_gre_keymap_flush(struct net *net) +void nf_ct_gre_keymap_flush(struct net *net) { - struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_gre_net *net_gre = gre_pernet(net); struct nf_ct_gre_keymap *km, *tmp; spin_lock_bh(&keymap_lock); @@ -83,7 +82,7 @@ static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, /* look up the source key for a given tuple */ static __be16 gre_keymap_lookup(struct net *net, struct nf_conntrack_tuple *t) { - struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_gre_net *net_gre = gre_pernet(net); struct nf_ct_gre_keymap *km; __be16 key = 0; @@ -105,7 +104,7 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t) { struct net *net = nf_ct_net(ct); - struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_gre_net *net_gre = gre_pernet(net); struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); struct nf_ct_gre_keymap **kmp, *km; @@ -210,7 +209,7 @@ static void gre_print_conntrack(struct seq_file *s, struct nf_conn *ct) static unsigned int *gre_get_timeouts(struct net *net) { - return gre_pernet(net)->gre_timeouts; + return gre_pernet(net)->timeouts; } /* Returns verdict for packet, and may modify conntrack */ @@ -272,13 +271,13 @@ static int gre_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_gre_net *net_gre = gre_pernet(net); if (!timeouts) timeouts = gre_get_timeouts(net); /* set default timeouts for GRE. */ - timeouts[GRE_CT_UNREPLIED] = net_gre->gre_timeouts[GRE_CT_UNREPLIED]; - timeouts[GRE_CT_REPLIED] = net_gre->gre_timeouts[GRE_CT_REPLIED]; + timeouts[GRE_CT_UNREPLIED] = net_gre->timeouts[GRE_CT_UNREPLIED]; + timeouts[GRE_CT_REPLIED] = net_gre->timeouts[GRE_CT_REPLIED]; if (tb[CTA_TIMEOUT_GRE_UNREPLIED]) { timeouts[GRE_CT_UNREPLIED] = @@ -332,10 +331,11 @@ static struct ctl_table gre_sysctl_table[] = { }; #endif -static int gre_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *nf, - struct netns_proto_gre *net_gre) +static int gre_kmemdup_sysctl_table(struct net *net) { #ifdef CONFIG_SYSCTL + struct nf_gre_net *net_gre = gre_pernet(net); + struct nf_proto_net *nf = &net_gre->nf; int i; if (nf->ctl_table) @@ -348,26 +348,25 @@ static int gre_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *nf, return -ENOMEM; for (i = 0; i < GRE_CT_MAX; i++) - nf->ctl_table[i].data = &net_gre->gre_timeouts[i]; + nf->ctl_table[i].data = &net_gre->timeouts[i]; #endif return 0; } static int gre_init_net(struct net *net) { - struct netns_proto_gre *net_gre = gre_pernet(net); - struct nf_proto_net *nf = &net_gre->nf; + struct nf_gre_net *net_gre = gre_pernet(net); int i; INIT_LIST_HEAD(&net_gre->keymap_list); for (i = 0; i < GRE_CT_MAX; i++) - net_gre->gre_timeouts[i] = gre_timeouts[i]; + net_gre->timeouts[i] = gre_timeouts[i]; - return gre_kmemdup_sysctl_table(net, nf, net_gre); + return gre_kmemdup_sysctl_table(net); } /* protocol helper struct */ -static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { +const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = { .l4proto = IPPROTO_GRE, .pkt_to_tuple = gre_pkt_to_tuple, #ifdef CONFIG_NF_CONNTRACK_PROCFS @@ -391,61 +390,5 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .nla_policy = gre_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .net_id = &proto_gre_net_id, .init_net = gre_init_net, }; - -static int proto_gre_net_init(struct net *net) -{ - int ret = 0; - - ret = nf_ct_l4proto_pernet_register_one(net, - &nf_conntrack_l4proto_gre4); - if (ret < 0) - pr_err("nf_conntrack_gre4: pernet registration failed.\n"); - return ret; -} - -static void proto_gre_net_exit(struct net *net) -{ - nf_ct_l4proto_pernet_unregister_one(net, &nf_conntrack_l4proto_gre4); - nf_ct_gre_keymap_flush(net); -} - -static struct pernet_operations proto_gre_net_ops = { - .init = proto_gre_net_init, - .exit = proto_gre_net_exit, - .id = &proto_gre_net_id, - .size = sizeof(struct netns_proto_gre), -}; - -static int __init nf_ct_proto_gre_init(void) -{ - int ret; - - BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0); - - ret = register_pernet_subsys(&proto_gre_net_ops); - if (ret < 0) - goto out_pernet; - ret = nf_ct_l4proto_register_one(&nf_conntrack_l4proto_gre4); - if (ret < 0) - goto out_gre4; - - return 0; -out_gre4: - unregister_pernet_subsys(&proto_gre_net_ops); -out_pernet: - return ret; -} - -static void __exit nf_ct_proto_gre_fini(void) -{ - nf_ct_l4proto_unregister_one(&nf_conntrack_l4proto_gre4); - unregister_pernet_subsys(&proto_gre_net_ops); -} - -module_init(nf_ct_proto_gre_init); -module_exit(nf_ct_proto_gre_fini); - -MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 109b0d27345a..0e3e1a018206 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -474,12 +474,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, break; case IPPROTO_GRE: #ifdef CONFIG_NF_CT_PROTO_GRE - if (l4proto->net_id) { - struct netns_proto_gre *net_gre; - - net_gre = net_generic(net, *l4proto->net_id); - timeouts = net_gre->gre_timeouts; - } + timeouts = nf_gre_pernet(net)->timeouts; #endif break; case 255: -- cgit v1.2.3 From 751fc301ecbd0fc08d4d6c388f170e2081df26e6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:36 +0100 Subject: netfilter: conntrack: remove net_id No users anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 2 +- net/netfilter/nf_conntrack_proto.c | 8 ++------ 2 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index fded3f164dcc..3585f8666fc0 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -79,7 +79,7 @@ struct nf_conntrack_l4proto { /* Print out the private part of the conntrack. */ void (*print_conntrack)(struct seq_file *s, struct nf_conn *); #endif - unsigned int *net_id; + /* Init l4proto pernet data */ int (*init_net)(struct net *net); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index e113bb2dc88d..47b9294a86f7 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -163,13 +163,9 @@ static int kill_l4proto(struct nf_conn *i, void *data) static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, const struct nf_conntrack_l4proto *l4proto) { - if (l4proto->get_net_proto) { - /* statically built-in protocols use static per-net */ + if (l4proto->get_net_proto) return l4proto->get_net_proto(net); - } else if (l4proto->net_id) { - /* ... and loadable protocols use dynamic per-net */ - return net_generic(net, *l4proto->net_id); - } + return NULL; } -- cgit v1.2.3 From df5e1629087a45ca915fa0f69ea662175261855e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:37 +0100 Subject: netfilter: conntrack: remove pkt_to_tuple callback GRE is now builtin, so we can handle it via direct call and remove the callback. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 2 ++ include/net/netfilter/nf_conntrack_l4proto.h | 5 ----- net/netfilter/nf_conntrack_core.c | 6 ++++-- net/netfilter/nf_conntrack_proto_generic.c | 11 ----------- net/netfilter/nf_conntrack_proto_gre.c | 5 ++--- 5 files changed, 8 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index 59714e9ee4ef..25f9a770fb84 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -30,5 +30,7 @@ void nf_ct_gre_keymap_flush(struct net *net); /* delete keymap entries */ void nf_ct_gre_keymap_destroy(struct nf_conn *ct); +bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple); #endif /* __KERNEL__ */ #endif /* _CONNTRACK_PROTO_GRE_H */ diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 3585f8666fc0..0d4b0398aeb9 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -27,11 +27,6 @@ struct nf_conntrack_l4proto { /* protoinfo nlattr size, closes a hole */ u16 nlattr_size; - /* Try to fill in the third arg: dataoff is offset past network protocol - hdr. Return true if possible. */ - bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int dataoff, - struct net *net, struct nf_conntrack_tuple *tuple); - /* Invert the per-proto part of the tuple: ie. turn xmit into reply. * Only used by icmp, most protocols use a generic version. */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index b3840d36c3a6..b71e271f2b44 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -279,9 +279,11 @@ nf_ct_get_tuple(const struct sk_buff *skb, return icmpv6_pkt_to_tuple(skb, dataoff, net, tuple); case IPPROTO_ICMP: return icmp_pkt_to_tuple(skb, dataoff, net, tuple); +#ifdef CONFIG_NF_CT_PROTO_GRE + case IPPROTO_GRE: + return gre_pkt_to_tuple(skb, dataoff, net, tuple); +#endif } - if (unlikely(l4proto->pkt_to_tuple)) - return l4proto->pkt_to_tuple(skb, dataoff, net, tuple); /* Actually only need first 4 bytes to get ports. */ inet_hdr = skb_header_pointer(skb, dataoff, sizeof(_inet_hdr), &_inet_hdr); diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 5da19d5fbc76..5a5bf7cb6508 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -27,16 +27,6 @@ static bool nf_generic_should_process(u8 proto) } } -static bool generic_pkt_to_tuple(const struct sk_buff *skb, - unsigned int dataoff, - struct net *net, struct nf_conntrack_tuple *tuple) -{ - tuple->src.u.all = 0; - tuple->dst.u.all = 0; - - return true; -} - /* Returns verdict for packet, or -1 for invalid. */ static int generic_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -149,7 +139,6 @@ static struct nf_proto_net *generic_get_net_proto(struct net *net) const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = { .l4proto = 255, - .pkt_to_tuple = generic_pkt_to_tuple, .packet = generic_packet, #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 68f9bfb79c4e..04bc982b274d 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -162,8 +162,8 @@ EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_destroy); /* PUBLIC CONNTRACK PROTO HELPER FUNCTIONS */ /* gre hdr info to tuple */ -static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct net *net, struct nf_conntrack_tuple *tuple) +bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct pptp_gre_header *pgrehdr; struct pptp_gre_header _pgrehdr; @@ -368,7 +368,6 @@ static int gre_init_net(struct net *net) /* protocol helper struct */ const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = { .l4proto = IPPROTO_GRE, - .pkt_to_tuple = gre_pkt_to_tuple, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = gre_print_conntrack, #endif -- cgit v1.2.3 From 197c4300aec09b7cd2df124cea92f9f5a82efe42 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:38 +0100 Subject: netfilter: conntrack: remove invert_tuple callback Only used by icmp(v6). Prefer a direct call and remove this function from the l4proto struct. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 11 +++++------ net/netfilter/nf_conntrack_core.c | 8 ++++++-- net/netfilter/nf_conntrack_proto_icmp.c | 5 ++--- net/netfilter/nf_conntrack_proto_icmpv6.c | 5 ++--- 4 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 0d4b0398aeb9..6cec8337e684 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -27,12 +27,6 @@ struct nf_conntrack_l4proto { /* protoinfo nlattr size, closes a hole */ u16 nlattr_size; - /* Invert the per-proto part of the tuple: ie. turn xmit into reply. - * Only used by icmp, most protocols use a generic version. - */ - bool (*invert_tuple)(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig); - /* Returns verdict for packet, or -1 for invalid. */ int (*packet)(struct nf_conn *ct, struct sk_buff *skb, @@ -95,6 +89,11 @@ bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, struct net *net, struct nf_conntrack_tuple *tuple); +bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig); +bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig); + int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index b71e271f2b44..d56cb0fc82b6 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -423,8 +423,12 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, inverse->dst.protonum = orig->dst.protonum; - if (unlikely(l4proto->invert_tuple)) - return l4proto->invert_tuple(inverse, orig); + switch (orig->dst.protonum) { + case IPPROTO_ICMP: + return nf_conntrack_invert_icmp_tuple(inverse, orig); + case IPPROTO_ICMPV6: + return nf_conntrack_invert_icmpv6_tuple(inverse, orig); + } inverse->src.u.all = orig->dst.u.all; inverse->dst.u.all = orig->src.u.all; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 805c1fe5b837..d28c1d7633b2 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -54,8 +54,8 @@ static const u_int8_t invmap[] = { [ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1 }; -static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) +bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) { if (orig->dst.u.icmp.type >= sizeof(invmap) || !invmap[orig->dst.u.icmp.type]) @@ -347,7 +347,6 @@ static struct nf_proto_net *icmp_get_net_proto(struct net *net) const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = { .l4proto = IPPROTO_ICMP, - .invert_tuple = icmp_invert_tuple, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmp_tuple_to_nlattr, .nlattr_tuple_size = icmp_nlattr_tuple_size, diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 20cd55e55e41..2910dcdea134 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -67,8 +67,8 @@ static const u_int8_t noct_valid_new[] = { [ICMPV6_MLD2_REPORT - 130] = 1 }; -static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) +bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) { int type = orig->dst.u.icmp.type - 128; if (type < 0 || type >= sizeof(invmap) || !invmap[type]) @@ -358,7 +358,6 @@ static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = { .l4proto = IPPROTO_ICMPV6, - .invert_tuple = icmpv6_invert_tuple, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmpv6_tuple_to_nlattr, .nlattr_tuple_size = icmpv6_nlattr_tuple_size, -- cgit v1.2.3 From b184356d0a003ac5e82b4adf37f2d334df1d213c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:39 +0100 Subject: netfilter: conntrack: remove module owner field No need to get/put module owner reference, none of these can be removed anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 4 ---- net/netfilter/nf_conntrack_proto.c | 8 -------- net/netfilter/nf_conntrack_proto_gre.c | 1 - net/netfilter/nfnetlink_cttimeout.c | 6 ------ net/netfilter/nft_ct.c | 2 -- 5 files changed, 21 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 6cec8337e684..fd8954429e87 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -74,9 +74,6 @@ struct nf_conntrack_l4proto { /* Return the per-net protocol part. */ struct nf_proto_net *(*get_net_proto)(struct net *net); - - /* Module (if any) which this is connected to. */ - struct module *me; }; bool icmp_pkt_to_tuple(const struct sk_buff *skb, @@ -148,7 +145,6 @@ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u8 l4proto); const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4proto); -void nf_ct_l4proto_put(const struct nf_conntrack_l4proto *p); /* Protocol pernet registration. */ int nf_ct_l4proto_pernet_register_one(struct net *net, diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 47b9294a86f7..3455f993cc68 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -139,20 +139,12 @@ const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4num) rcu_read_lock(); p = __nf_ct_l4proto_find(l4num); - if (!try_module_get(p->me)) - p = &nf_conntrack_l4proto_generic; rcu_read_unlock(); return p; } EXPORT_SYMBOL_GPL(nf_ct_l4proto_find_get); -void nf_ct_l4proto_put(const struct nf_conntrack_l4proto *p) -{ - module_put(p->me); -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_put); - static int kill_l4proto(struct nf_conn *i, void *data) { const struct nf_conntrack_l4proto *l4proto; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 04bc982b274d..0c26cfd5d29f 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -373,7 +373,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = { #endif .packet = gre_packet, .destroy = gre_destroy, - .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 0e3e1a018206..37b4f84ac153 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -152,7 +152,6 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, err: kfree(timeout); err_proto_put: - nf_ct_l4proto_put(l4proto); return ret; } @@ -302,7 +301,6 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) if (refcount_dec_if_one(&timeout->refcnt)) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); - nf_ct_l4proto_put(timeout->timeout.l4proto); nf_ct_untimeout(net, &timeout->timeout); kfree_rcu(timeout, rcu_head); } else { @@ -372,10 +370,8 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl, if (ret < 0) goto err; - nf_ct_l4proto_put(l4proto); return 0; err: - nf_ct_l4proto_put(l4proto); return ret; } @@ -511,7 +507,6 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, /* this avoids a loop in nfnetlink. */ return ret == -EAGAIN ? -ENOBUFS : ret; err: - nf_ct_l4proto_put(l4proto); return err; } @@ -592,7 +587,6 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { list_del_rcu(&cur->head); - nf_ct_l4proto_put(cur->timeout.l4proto); if (refcount_dec_and_test(&cur->refcnt)) kfree_rcu(cur, rcu_head); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 586627c361df..3249cc059048 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -902,7 +902,6 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, err_free_timeout: kfree(timeout); err_proto_put: - nf_ct_l4proto_put(l4proto); return ret; } @@ -913,7 +912,6 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx, struct nf_ct_timeout *timeout = priv->timeout; nf_ct_untimeout(ctx->net, timeout); - nf_ct_l4proto_put(timeout->l4proto); nf_ct_netns_put(ctx->net, ctx->family); kfree(priv->timeout); } -- cgit v1.2.3 From 44fb87f6351d04fafae2b17df5f46f1ce22c6f93 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:40 +0100 Subject: netfilter: conntrack: remove remaining l4proto indirect packet calls Now that all l4trackers are builtin, no need to use a mix of direct and indirect calls. This removes the last two users: gre and the generic l4 protocol tracker. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 12 ++++------ net/netfilter/nf_conntrack_core.c | 26 +++++++++++++++------ net/netfilter/nf_conntrack_proto_generic.c | 35 ---------------------------- net/netfilter/nf_conntrack_proto_gre.c | 11 ++++----- 4 files changed, 29 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index fd8954429e87..dda028996559 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -27,13 +27,6 @@ struct nf_conntrack_l4proto { /* protoinfo nlattr size, closes a hole */ u16 nlattr_size; - /* Returns verdict for packet, or -1 for invalid. */ - int (*packet)(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state); - /* Called when a conntrack entry is destroyed */ void (*destroy)(struct nf_conn *ct); @@ -136,6 +129,11 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); +int nf_conntrack_gre_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); /* Existing built-in generic protocol */ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d56cb0fc82b6..264074f04615 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1534,6 +1534,18 @@ nf_conntrack_handle_icmp(struct nf_conn *tmpl, return ret; } +static int generic_packet(struct nf_conn *ct, struct sk_buff *skb, + enum ip_conntrack_info ctinfo) +{ + const unsigned int *timeout = nf_ct_timeout_lookup(ct); + + if (!timeout) + timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout; + + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); + return NF_ACCEPT; +} + /* Returns verdict for packet, or -1 for invalid. */ static int nf_conntrack_handle_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -1566,11 +1578,15 @@ static int nf_conntrack_handle_packet(struct nf_conn *ct, case IPPROTO_DCCP: return nf_conntrack_dccp_packet(ct, skb, dataoff, ctinfo, state); +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE + case IPPROTO_GRE: + return nf_conntrack_gre_packet(ct, skb, dataoff, + ctinfo, state); #endif } - WARN_ON_ONCE(1); - return -NF_ACCEPT; + return generic_packet(ct, skb, ctinfo); } unsigned int @@ -1634,11 +1650,7 @@ repeat: goto out; } - if (l4proto->packet) - ret = l4proto->packet(ct, skb, dataoff, ctinfo, state); - else - ret = nf_conntrack_handle_packet(ct, skb, dataoff, ctinfo, state); - + ret = nf_conntrack_handle_packet(ct, skb, dataoff, ctinfo, state); if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 5a5bf7cb6508..78358d192c60 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -15,40 +15,6 @@ static const unsigned int nf_ct_generic_timeout = 600*HZ; -static bool nf_generic_should_process(u8 proto) -{ - switch (proto) { -#ifdef CONFIG_NF_CT_PROTO_GRE_MODULE - case IPPROTO_GRE: - return false; -#endif - default: - return true; - } -} - -/* Returns verdict for packet, or -1 for invalid. */ -static int generic_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) -{ - const unsigned int *timeout = nf_ct_timeout_lookup(ct); - - if (!nf_generic_should_process(nf_ct_protonum(ct))) { - pr_warn_once("conntrack: generic helper won't handle protocol %d. Please consider loading the specific helper module.\n", - nf_ct_protonum(ct)); - return -NF_ACCEPT; - } - - if (!timeout) - timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout; - - nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); - return NF_ACCEPT; -} - #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include @@ -139,7 +105,6 @@ static struct nf_proto_net *generic_get_net_proto(struct net *net) const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = { .l4proto = 255, - .packet = generic_packet, #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = generic_timeout_nlattr_to_obj, diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 0c26cfd5d29f..f6391991bcf6 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -213,11 +213,11 @@ static unsigned int *gre_get_timeouts(struct net *net) } /* Returns verdict for packet, and may modify conntrack */ -static int gre_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_gre_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { if (state->pf != NFPROTO_IPV4) return -NF_ACCEPT; @@ -371,7 +371,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = { #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = gre_print_conntrack, #endif - .packet = gre_packet, .destroy = gre_destroy, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, -- cgit v1.2.3 From edf0338dabf0f330873f7a9f84ea9f9ac431c0a8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:41 +0100 Subject: netfilter: conntrack: remove pernet l4 proto register interface No used anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 12 ------------ net/netfilter/nf_conntrack_proto.c | 28 ++++++++++++---------------- 2 files changed, 12 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index dda028996559..87d9c198c05e 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -144,18 +144,6 @@ const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u8 l4proto); const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4proto); -/* Protocol pernet registration. */ -int nf_ct_l4proto_pernet_register_one(struct net *net, - const struct nf_conntrack_l4proto *proto); -void nf_ct_l4proto_pernet_unregister_one(struct net *net, - const struct nf_conntrack_l4proto *proto); -int nf_ct_l4proto_pernet_register(struct net *net, - const struct nf_conntrack_l4proto *const proto[], - unsigned int num_proto); -void nf_ct_l4proto_pernet_unregister(struct net *net, - const struct nf_conntrack_l4proto *const proto[], - unsigned int num_proto); - /* Protocol global registration. */ int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *proto); void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *proto); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 3455f993cc68..13b782cc6a7a 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -221,8 +221,8 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_ct_l4proto_register_one); -int nf_ct_l4proto_pernet_register_one(struct net *net, - const struct nf_conntrack_l4proto *l4proto) +static int nf_ct_l4proto_pernet_register_one(struct net *net, + const struct nf_conntrack_l4proto *l4proto) { int ret = 0; struct nf_proto_net *pn = NULL; @@ -245,7 +245,6 @@ int nf_ct_l4proto_pernet_register_one(struct net *net, out: return ret; } -EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register_one); static void __nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto) @@ -272,7 +271,7 @@ void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto) } EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister_one); -void nf_ct_l4proto_pernet_unregister_one(struct net *net, +static void nf_ct_l4proto_pernet_unregister_one(struct net *net, const struct nf_conntrack_l4proto *l4proto) { struct nf_proto_net *pn = nf_ct_l4proto_net(net, l4proto); @@ -283,7 +282,6 @@ void nf_ct_l4proto_pernet_unregister_one(struct net *net, pn->users--; nf_ct_l4proto_unregister_sysctl(pn); } -EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one); static void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[], @@ -322,7 +320,15 @@ nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], return ret; } -int nf_ct_l4proto_pernet_register(struct net *net, +static void nf_ct_l4proto_pernet_unregister(struct net *net, + const struct nf_conntrack_l4proto *const l4proto[], + unsigned int num_proto) +{ + while (num_proto-- != 0) + nf_ct_l4proto_pernet_unregister_one(net, l4proto[num_proto]); +} + +static int nf_ct_l4proto_pernet_register(struct net *net, const struct nf_conntrack_l4proto *const l4proto[], unsigned int num_proto) { @@ -341,16 +347,6 @@ int nf_ct_l4proto_pernet_register(struct net *net, } return ret; } -EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register); - -void nf_ct_l4proto_pernet_unregister(struct net *net, - const struct nf_conntrack_l4proto *const l4proto[], - unsigned int num_proto) -{ - while (num_proto-- != 0) - nf_ct_l4proto_pernet_unregister_one(net, l4proto[num_proto]); -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister); static unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, -- cgit v1.2.3 From 303e0c5589592e4f623bfcaf4292a1ed816328ad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:42 +0100 Subject: netfilter: conntrack: avoid unneeded nf_conntrack_l4proto lookups after removal of the packet and invert function pointers, several places do not need to lookup the l4proto structure anymore. Remove those lookups. The function nf_ct_invert_tuplepr becomes redundant, replace it with nf_ct_invert_tuple everywhere. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 2 -- include/net/netfilter/nf_conntrack_core.h | 3 +- net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 2 +- net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 2 +- net/netfilter/nf_conntrack_core.c | 53 ++++++------------------------- net/netfilter/nf_conntrack_pptp.c | 2 +- net/netfilter/nf_conntrack_proto_icmp.c | 6 +--- net/netfilter/nf_conntrack_proto_icmpv6.c | 6 +--- net/netfilter/nf_nat_core.c | 12 +++---- net/openvswitch/conntrack.c | 2 +- 10 files changed, 22 insertions(+), 68 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 249d0a5b12b8..b5aac5ae5129 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -187,8 +187,6 @@ bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, u_int16_t l3num, struct net *net, struct nf_conntrack_tuple *tuple); -bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig); void __nf_ct_refresh_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct sk_buff *skb, diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index afc9b3620473..235c182022b2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -39,8 +39,7 @@ void nf_conntrack_init_end(void); void nf_conntrack_cleanup_end(void); bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig, - const struct nf_conntrack_l4proto *l4proto); + const struct nf_conntrack_tuple *orig); /* Find a connection corresponding to a tuple. */ struct nf_conntrack_tuple_hash * diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 2687db015b6f..e26165af45cb 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -214,7 +214,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, } /* Change outer to look like the reply to an incoming packet */ - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 23022447eb49..9c914db44bec 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -225,7 +225,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, skb->len - hdrlen, 0)); } - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 264074f04615..728d2b5bdb1a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -229,8 +229,7 @@ nf_ct_get_tuple(const struct sk_buff *skb, u_int16_t l3num, u_int8_t protonum, struct net *net, - struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l4proto *l4proto) + struct nf_conntrack_tuple *tuple) { unsigned int size; const __be32 *ap; @@ -374,33 +373,20 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, u_int16_t l3num, struct net *net, struct nf_conntrack_tuple *tuple) { - const struct nf_conntrack_l4proto *l4proto; u8 protonum; int protoff; - int ret; - - rcu_read_lock(); protoff = get_l4proto(skb, nhoff, l3num, &protonum); - if (protoff <= 0) { - rcu_read_unlock(); + if (protoff <= 0) return false; - } - l4proto = __nf_ct_l4proto_find(protonum); - - ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple, - l4proto); - - rcu_read_unlock(); - return ret; + return nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple); } EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr); bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig, - const struct nf_conntrack_l4proto *l4proto) + const struct nf_conntrack_tuple *orig) { memset(inverse, 0, sizeof(*inverse)); @@ -1354,7 +1340,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free); static noinline struct nf_conntrack_tuple_hash * init_conntrack(struct net *net, struct nf_conn *tmpl, const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l4proto *l4proto, struct sk_buff *skb, unsigned int dataoff, u32 hash) { @@ -1367,7 +1352,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conn_timeout *timeout_ext; struct nf_conntrack_zone tmp; - if (!nf_ct_invert_tuple(&repl_tuple, tuple, l4proto)) { + if (!nf_ct_invert_tuple(&repl_tuple, tuple)) { pr_debug("Can't invert tuple.\n"); return NULL; } @@ -1449,7 +1434,6 @@ resolve_normal_ct(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, u_int8_t protonum, - const struct nf_conntrack_l4proto *l4proto, const struct nf_hook_state *state) { const struct nf_conntrack_zone *zone; @@ -1462,7 +1446,7 @@ resolve_normal_ct(struct nf_conn *tmpl, if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, state->pf, protonum, state->net, - &tuple, l4proto)) { + &tuple)) { pr_debug("Can't get tuple\n"); return 0; } @@ -1472,7 +1456,7 @@ resolve_normal_ct(struct nf_conn *tmpl, hash = hash_conntrack_raw(&tuple, state->net); h = __nf_conntrack_find_get(state->net, zone, &tuple, hash); if (!h) { - h = init_conntrack(state->net, tmpl, &tuple, l4proto, + h = init_conntrack(state->net, tmpl, &tuple, skb, dataoff, hash); if (!h) return 0; @@ -1592,7 +1576,6 @@ static int nf_conntrack_handle_packet(struct nf_conn *ct, unsigned int nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) { - const struct nf_conntrack_l4proto *l4proto; enum ip_conntrack_info ctinfo; struct nf_conn *ct, *tmpl; u_int8_t protonum; @@ -1619,8 +1602,6 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) goto out; } - l4proto = __nf_ct_l4proto_find(protonum); - if (protonum == IPPROTO_ICMP || protonum == IPPROTO_ICMPV6) { ret = nf_conntrack_handle_icmp(tmpl, skb, dataoff, protonum, state); @@ -1634,7 +1615,7 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) } repeat: ret = resolve_normal_ct(tmpl, skb, dataoff, - protonum, l4proto, state); + protonum, state); if (ret < 0) { /* Too stressed to deal. */ NF_CT_STAT_INC_ATOMIC(state->net, drop); @@ -1681,19 +1662,6 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_in); -bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig) -{ - bool ret; - - rcu_read_lock(); - ret = nf_ct_invert_tuple(inverse, orig, - __nf_ct_l4proto_find(orig->dst.protonum)); - rcu_read_unlock(); - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_invert_tuplepr); - /* Alter reply tuple (maybe alter helper). This is for NAT, and is implicitly racy: see __nf_conntrack_confirm */ void nf_conntrack_alter_reply(struct nf_conn *ct, @@ -1824,7 +1792,6 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) static int nf_conntrack_update(struct net *net, struct sk_buff *skb) { - const struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; enum ip_conntrack_info ctinfo; @@ -1845,10 +1812,8 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) if (dataoff <= 0) return -1; - l4proto = nf_ct_l4proto_find_get(l4num); - if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, - l4num, net, &tuple, l4proto)) + l4num, net, &tuple)) return -1; if (ct->status & IPS_SRC_NAT) { diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 11562f2a08bb..976f1dcb97f0 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -121,7 +121,7 @@ static void pptp_expectfn(struct nf_conn *ct, struct nf_conntrack_expect *exp_other; /* obviously this tuple inversion only works until you do NAT */ - nf_ct_invert_tuplepr(&inv_t, &exp->tuple); + nf_ct_invert_tuple(&inv_t, &exp->tuple); pr_debug("trying to unexpect other dir: "); nf_ct_dump_tuple(&inv_t); diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index d28c1d7633b2..1007efae741d 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -109,7 +109,6 @@ icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conntrack_tuple innertuple, origtuple; - const struct nf_conntrack_l4proto *innerproto; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_zone *zone; enum ip_conntrack_info ctinfo; @@ -127,12 +126,9 @@ icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb, return -NF_ACCEPT; } - /* rcu_read_lock()ed by nf_hook_thresh */ - innerproto = __nf_ct_l4proto_find(origtuple.dst.protonum); - /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) { + if (!nf_ct_invert_tuple(&innertuple, &origtuple)) { pr_debug("icmp_error_message: no match\n"); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 2910dcdea134..6c93c091a8dd 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -130,7 +130,6 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, { struct nf_conntrack_tuple intuple, origtuple; const struct nf_conntrack_tuple_hash *h; - const struct nf_conntrack_l4proto *inproto; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; @@ -146,12 +145,9 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, return -NF_ACCEPT; } - /* rcu_read_lock()ed by nf_hook_thresh */ - inproto = __nf_ct_l4proto_find(origtuple.dst.protonum); - /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) { + if (!nf_ct_invert_tuple(&intuple, &origtuple)) { pr_debug("icmpv6_error: Can't invert tuple\n"); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d159e9e7835b..44f97b3a215a 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -158,7 +158,7 @@ nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, */ struct nf_conntrack_tuple reply; - nf_ct_invert_tuplepr(&reply, tuple); + nf_ct_invert_tuple(&reply, tuple); return nf_conntrack_tuple_taken(&reply, ignored_conntrack); } EXPORT_SYMBOL(nf_nat_used_tuple); @@ -253,7 +253,7 @@ find_appropriate_src(struct net *net, net_eq(net, nf_ct_net(ct)) && nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) { /* Copy source part from reply tuple. */ - nf_ct_invert_tuplepr(result, + nf_ct_invert_tuple(result, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); result->dst = tuple->dst; @@ -560,8 +560,8 @@ nf_nat_setup_info(struct nf_conn *ct, * manipulations (future optimization: if num_manips == 0, * orig_tp = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple) */ - nf_ct_invert_tuplepr(&curr_tuple, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + nf_ct_invert_tuple(&curr_tuple, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype); @@ -569,7 +569,7 @@ nf_nat_setup_info(struct nf_conn *ct, struct nf_conntrack_tuple reply; /* Alter conntrack table so will recognize replies. */ - nf_ct_invert_tuplepr(&reply, &new_tuple); + nf_ct_invert_tuple(&reply, &new_tuple); nf_conntrack_alter_reply(ct, &reply); /* Non-atomic: we own this at the moment. */ @@ -640,7 +640,7 @@ static unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, struct nf_conntrack_tuple target; /* We are aiming to look like inverse of other direction. */ - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); l3proto = __nf_nat_l3proto_find(target.src.l3num); if (!l3proto->manip_pkt(skb, 0, &target, mtype)) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index cd94f925495a..35884f836260 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -622,7 +622,7 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, if (natted) { struct nf_conntrack_tuple inverse; - if (!nf_ct_invert_tuplepr(&inverse, &tuple)) { + if (!nf_ct_invert_tuple(&inverse, &tuple)) { pr_debug("ovs_ct_find_existing: Inversion failed!\n"); return NULL; } -- cgit v1.2.3 From 70aed4647cbd63e3371386ddfaeb195413f38d99 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:44 +0100 Subject: netfilter: conntrack: remove sysctl registration helpers After previous patch these are not used anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netns/conntrack.h | 4 -- net/netfilter/nf_conntrack_proto.c | 77 +------------------------------------- 2 files changed, 1 insertion(+), 80 deletions(-) (limited to 'include') diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index c72f413a2d4d..b8faa72e0f5b 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -19,10 +19,6 @@ struct ctl_table_header; struct nf_conntrack_ecache; struct nf_proto_net { -#ifdef CONFIG_SYSCTL - struct ctl_table_header *ctl_table_header; - struct ctl_table *ctl_table; -#endif unsigned int users; }; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 13b782cc6a7a..c8f024d731c8 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -48,35 +48,6 @@ static struct nf_conntrack_l4proto __rcu *nf_ct_protos[MAX_NF_CT_PROTO + 1] __re static DEFINE_MUTEX(nf_ct_proto_mutex); #ifdef CONFIG_SYSCTL -static int -nf_ct_register_sysctl(struct net *net, - struct ctl_table_header **header, - const char *path, - struct ctl_table *table) -{ - if (*header == NULL) { - *header = register_net_sysctl(net, path, table); - if (*header == NULL) - return -ENOMEM; - } - - return 0; -} - -static void -nf_ct_unregister_sysctl(struct ctl_table_header **header, - struct ctl_table **table, - unsigned int users) -{ - if (users > 0) - return; - - unregister_net_sysctl_table(*header); - kfree(*table); - *header = NULL; - *table = NULL; -} - __printf(5, 6) void nf_l4proto_log_invalid(const struct sk_buff *skb, struct net *net, @@ -161,40 +132,6 @@ static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, return NULL; } -static -int nf_ct_l4proto_register_sysctl(struct net *net, - struct nf_proto_net *pn) -{ - int err = 0; - -#ifdef CONFIG_SYSCTL - if (pn->ctl_table != NULL) { - err = nf_ct_register_sysctl(net, - &pn->ctl_table_header, - "net/netfilter", - pn->ctl_table); - if (err < 0) { - if (!pn->users) { - kfree(pn->ctl_table); - pn->ctl_table = NULL; - } - } - } -#endif /* CONFIG_SYSCTL */ - return err; -} - -static -void nf_ct_l4proto_unregister_sysctl(struct nf_proto_net *pn) -{ -#ifdef CONFIG_SYSCTL - if (pn->ctl_table_header != NULL) - nf_ct_unregister_sysctl(&pn->ctl_table_header, - &pn->ctl_table, - pn->users); -#endif /* CONFIG_SYSCTL */ -} - /* FIXME: Allow NULL functions and sub in pointers to generic for them. --RR */ int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *l4proto) @@ -237,10 +174,6 @@ static int nf_ct_l4proto_pernet_register_one(struct net *net, if (pn == NULL) goto out; - ret = nf_ct_l4proto_register_sysctl(net, pn); - if (ret < 0) - goto out; - pn->users++; out: return ret; @@ -280,7 +213,6 @@ static void nf_ct_l4proto_pernet_unregister_one(struct net *net, return; pn->users--; - nf_ct_l4proto_unregister_sysctl(pn); } static void @@ -859,17 +791,11 @@ int nf_conntrack_proto_pernet_init(struct net *net) err = nf_conntrack_l4proto_generic.init_net(net); if (err < 0) return err; - err = nf_ct_l4proto_register_sysctl(net, - pn); - if (err < 0) - return err; err = nf_ct_l4proto_pernet_register(net, builtin_l4proto, ARRAY_SIZE(builtin_l4proto)); - if (err < 0) { - nf_ct_l4proto_unregister_sysctl(pn); + if (err < 0) return err; - } pn->users++; return 0; @@ -883,7 +809,6 @@ void nf_conntrack_proto_pernet_fini(struct net *net) nf_ct_l4proto_pernet_unregister(net, builtin_l4proto, ARRAY_SIZE(builtin_l4proto)); pn->users--; - nf_ct_l4proto_unregister_sysctl(pn); #ifdef CONFIG_NF_CT_PROTO_GRE nf_ct_gre_keymap_flush(net); #endif -- cgit v1.2.3 From 2a389de86e4a5d0bd3abed9e6fee27050652d339 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:45 +0100 Subject: netfilter: conntrack: remove l4proto init and get_net callbacks Those were needed we still had modular trackers. As we don't have those anymore, prefer direct calls and remove all the (un)register infrastructure associated with this. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 15 ++-- include/net/netns/conntrack.h | 11 --- net/netfilter/nf_conntrack_proto.c | 103 ++++----------------------- net/netfilter/nf_conntrack_proto_dccp.c | 42 ++++------- net/netfilter/nf_conntrack_proto_generic.c | 11 +-- net/netfilter/nf_conntrack_proto_gre.c | 5 +- net/netfilter/nf_conntrack_proto_icmp.c | 12 +--- net/netfilter/nf_conntrack_proto_icmpv6.c | 12 +--- net/netfilter/nf_conntrack_proto_sctp.c | 29 +++----- net/netfilter/nf_conntrack_proto_tcp.c | 35 +++------ net/netfilter/nf_conntrack_proto_udp.c | 24 ++----- 11 files changed, 65 insertions(+), 234 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 87d9c198c05e..d5909e51ca92 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -61,12 +61,6 @@ struct nf_conntrack_l4proto { /* Print out the private part of the conntrack. */ void (*print_conntrack)(struct seq_file *s, struct nf_conn *); #endif - - /* Init l4proto pernet data */ - int (*init_net)(struct net *net); - - /* Return the per-net protocol part. */ - struct nf_proto_net *(*get_net_proto)(struct net *net); }; bool icmp_pkt_to_tuple(const struct sk_buff *skb, @@ -135,6 +129,15 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); +void nf_conntrack_generic_init_net(struct net *net); +void nf_conntrack_tcp_init_net(struct net *net); +void nf_conntrack_udp_init_net(struct net *net); +void nf_conntrack_gre_init_net(struct net *net); +void nf_conntrack_dccp_init_net(struct net *net); +void nf_conntrack_sctp_init_net(struct net *net); +void nf_conntrack_icmp_init_net(struct net *net); +void nf_conntrack_icmpv6_init_net(struct net *net); + /* Existing built-in generic protocol */ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index b8faa72e0f5b..f19b53130bf7 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -18,17 +18,11 @@ struct ctl_table_header; struct nf_conntrack_ecache; -struct nf_proto_net { - unsigned int users; -}; - struct nf_generic_net { - struct nf_proto_net pn; unsigned int timeout; }; struct nf_tcp_net { - struct nf_proto_net pn; unsigned int timeouts[TCP_CONNTRACK_TIMEOUT_MAX]; unsigned int tcp_loose; unsigned int tcp_be_liberal; @@ -42,18 +36,15 @@ enum udp_conntrack { }; struct nf_udp_net { - struct nf_proto_net pn; unsigned int timeouts[UDP_CT_MAX]; }; struct nf_icmp_net { - struct nf_proto_net pn; unsigned int timeout; }; #ifdef CONFIG_NF_CT_PROTO_DCCP struct nf_dccp_net { - struct nf_proto_net pn; int dccp_loose; unsigned int dccp_timeout[CT_DCCP_MAX + 1]; }; @@ -61,7 +52,6 @@ struct nf_dccp_net { #ifdef CONFIG_NF_CT_PROTO_SCTP struct nf_sctp_net { - struct nf_proto_net pn; unsigned int timeouts[SCTP_CONNTRACK_MAX]; }; #endif @@ -74,7 +64,6 @@ enum gre_conntrack { }; struct nf_gre_net { - struct nf_proto_net nf; struct list_head keymap_list; unsigned int timeouts[GRE_CT_MAX]; }; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index c8f024d731c8..e6bc02c13f0f 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -123,15 +123,6 @@ static int kill_l4proto(struct nf_conn *i, void *data) return nf_ct_protonum(i) == l4proto->l4proto; } -static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, - const struct nf_conntrack_l4proto *l4proto) -{ - if (l4proto->get_net_proto) - return l4proto->get_net_proto(net); - - return NULL; -} - /* FIXME: Allow NULL functions and sub in pointers to generic for them. --RR */ int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *l4proto) @@ -158,27 +149,6 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_ct_l4proto_register_one); -static int nf_ct_l4proto_pernet_register_one(struct net *net, - const struct nf_conntrack_l4proto *l4proto) -{ - int ret = 0; - struct nf_proto_net *pn = NULL; - - if (l4proto->init_net) { - ret = l4proto->init_net(net); - if (ret < 0) - goto out; - } - - pn = nf_ct_l4proto_net(net, l4proto); - if (pn == NULL) - goto out; - - pn->users++; -out: - return ret; -} - static void __nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto) { @@ -204,17 +174,6 @@ void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto) } EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister_one); -static void nf_ct_l4proto_pernet_unregister_one(struct net *net, - const struct nf_conntrack_l4proto *l4proto) -{ - struct nf_proto_net *pn = nf_ct_l4proto_net(net, l4proto); - - if (pn == NULL) - return; - - pn->users--; -} - static void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[], unsigned int num_proto) @@ -252,34 +211,6 @@ nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], return ret; } -static void nf_ct_l4proto_pernet_unregister(struct net *net, - const struct nf_conntrack_l4proto *const l4proto[], - unsigned int num_proto) -{ - while (num_proto-- != 0) - nf_ct_l4proto_pernet_unregister_one(net, l4proto[num_proto]); -} - -static int nf_ct_l4proto_pernet_register(struct net *net, - const struct nf_conntrack_l4proto *const l4proto[], - unsigned int num_proto) -{ - int ret = -EINVAL; - unsigned int i; - - for (i = 0; i < num_proto; i++) { - ret = nf_ct_l4proto_pernet_register_one(net, l4proto[i]); - if (ret < 0) - break; - } - if (i != num_proto) { - pr_err("nf_conntrack %d: pernet registration failed\n", - l4proto[i]->l4proto); - nf_ct_l4proto_pernet_unregister(net, l4proto, i); - } - return ret; -} - static unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, @@ -784,31 +715,25 @@ void nf_conntrack_proto_fini(void) int nf_conntrack_proto_pernet_init(struct net *net) { - int err; - struct nf_proto_net *pn = nf_ct_l4proto_net(net, - &nf_conntrack_l4proto_generic); - - err = nf_conntrack_l4proto_generic.init_net(net); - if (err < 0) - return err; - - err = nf_ct_l4proto_pernet_register(net, builtin_l4proto, - ARRAY_SIZE(builtin_l4proto)); - if (err < 0) - return err; - - pn->users++; + nf_conntrack_generic_init_net(net); + nf_conntrack_udp_init_net(net); + nf_conntrack_tcp_init_net(net); + nf_conntrack_icmp_init_net(net); + nf_conntrack_icmpv6_init_net(net); +#ifdef CONFIG_NF_CT_PROTO_DCCP + nf_conntrack_dccp_init_net(net); +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + nf_conntrack_sctp_init_net(net); +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE + nf_conntrack_gre_init_net(net); +#endif return 0; } void nf_conntrack_proto_pernet_fini(struct net *net) { - struct nf_proto_net *pn = nf_ct_l4proto_net(net, - &nf_conntrack_l4proto_generic); - - nf_ct_l4proto_pernet_unregister(net, builtin_l4proto, - ARRAY_SIZE(builtin_l4proto)); - pn->users--; #ifdef CONFIG_NF_CT_PROTO_GRE nf_ct_gre_keymap_flush(net); #endif diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 31ba88311bc4..6fca80587505 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -724,34 +724,24 @@ dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -static int dccp_init_net(struct net *net) +void nf_conntrack_dccp_init_net(struct net *net) { struct nf_dccp_net *dn = nf_dccp_pernet(net); - struct nf_proto_net *pn = &dn->pn; - - if (!pn->users) { - /* default values */ - dn->dccp_loose = 1; - dn->dccp_timeout[CT_DCCP_REQUEST] = 2 * DCCP_MSL; - dn->dccp_timeout[CT_DCCP_RESPOND] = 4 * DCCP_MSL; - dn->dccp_timeout[CT_DCCP_PARTOPEN] = 4 * DCCP_MSL; - dn->dccp_timeout[CT_DCCP_OPEN] = 12 * 3600 * HZ; - dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; - dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; - dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; - - /* timeouts[0] is unused, make it same as SYN_SENT so - * ->timeouts[0] contains 'new' timeout, like udp or icmp. - */ - dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; - } - - return 0; -} -static struct nf_proto_net *dccp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.dccp.pn; + /* default values */ + dn->dccp_loose = 1; + dn->dccp_timeout[CT_DCCP_REQUEST] = 2 * DCCP_MSL; + dn->dccp_timeout[CT_DCCP_RESPOND] = 4 * DCCP_MSL; + dn->dccp_timeout[CT_DCCP_PARTOPEN] = 4 * DCCP_MSL; + dn->dccp_timeout[CT_DCCP_OPEN] = 12 * 3600 * HZ; + dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; + dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; + dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; + + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp = { @@ -778,6 +768,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp = { .nla_policy = dccp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = dccp_init_net, - .get_net_proto = dccp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 0edbf82594d0..0f526fafecae 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -60,18 +60,11 @@ generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -static int generic_init_net(struct net *net) +void nf_conntrack_generic_init_net(struct net *net) { struct nf_generic_net *gn = nf_generic_pernet(net); gn->timeout = nf_ct_generic_timeout; - - return 0; -} - -static struct nf_proto_net *generic_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.generic.pn; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = @@ -86,6 +79,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .nla_policy = generic_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = generic_init_net, - .get_net_proto = generic_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index e573ec0fa12b..fa765d2fd586 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -313,7 +313,7 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -static int gre_init_net(struct net *net) +void nf_conntrack_gre_init_net(struct net *net) { struct nf_gre_net *net_gre = gre_pernet(net); int i; @@ -321,8 +321,6 @@ static int gre_init_net(struct net *net) INIT_LIST_HEAD(&net_gre->keymap_list); for (i = 0; i < GRE_CT_MAX; i++) net_gre->timeouts[i] = gre_timeouts[i]; - - return 0; } /* protocol helper struct */ @@ -347,5 +345,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = { .nla_policy = gre_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = gre_init_net, }; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index eb77f747759f..7df477996b16 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -298,19 +298,11 @@ icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - -static int icmp_init_net(struct net *net) +void nf_conntrack_icmp_init_net(struct net *net) { struct nf_icmp_net *in = nf_icmp_pernet(net); in->timeout = nf_ct_icmp_timeout; - - return 0; -} - -static struct nf_proto_net *icmp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.icmp.pn; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = @@ -331,6 +323,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .nla_policy = icmp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = icmp_init_net, - .get_net_proto = icmp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index d243ef8a128e..bec4a3211658 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -309,19 +309,11 @@ icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - -static int icmpv6_init_net(struct net *net) +void nf_conntrack_icmpv6_init_net(struct net *net) { struct nf_icmp_net *in = nf_icmpv6_pernet(net); in->timeout = nf_ct_icmpv6_timeout; - - return 0; -} - -static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.icmpv6.pn; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = @@ -342,6 +334,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .nla_policy = icmpv6_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = icmpv6_init_net, - .get_net_proto = icmpv6_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 31130f218d8f..a7818101ad80 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -642,29 +642,18 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -static int sctp_init_net(struct net *net) +void nf_conntrack_sctp_init_net(struct net *net) { struct nf_sctp_net *sn = nf_sctp_pernet(net); - struct nf_proto_net *pn = &sn->pn; - - if (!pn->users) { - int i; - - for (i = 0; i < SCTP_CONNTRACK_MAX; i++) - sn->timeouts[i] = sctp_timeouts[i]; - - /* timeouts[0] is unused, init it so ->timeouts[0] contains - * 'new' timeout, like udp or icmp. - */ - sn->timeouts[0] = sctp_timeouts[SCTP_CONNTRACK_CLOSED]; - } + int i; - return 0; -} + for (i = 0; i < SCTP_CONNTRACK_MAX; i++) + sn->timeouts[i] = sctp_timeouts[i]; -static struct nf_proto_net *sctp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.sctp.pn; + /* timeouts[0] is unused, init it so ->timeouts[0] contains + * 'new' timeout, like udp or icmp. + */ + sn->timeouts[0] = sctp_timeouts[SCTP_CONNTRACK_CLOSED]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp = { @@ -691,6 +680,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp = { .nla_policy = sctp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = sctp_init_net, - .get_net_proto = sctp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 422bdedac0ed..01c748fa8913 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1387,32 +1387,21 @@ static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -static int tcp_init_net(struct net *net) +void nf_conntrack_tcp_init_net(struct net *net) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - struct nf_proto_net *pn = &tn->pn; - - if (!pn->users) { - int i; - - for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) - tn->timeouts[i] = tcp_timeouts[i]; - - /* timeouts[0] is unused, make it same as SYN_SENT so - * ->timeouts[0] contains 'new' timeout, like udp or icmp. - */ - tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; - tn->tcp_loose = nf_ct_tcp_loose; - tn->tcp_be_liberal = nf_ct_tcp_be_liberal; - tn->tcp_max_retrans = nf_ct_tcp_max_retrans; - } + int i; - return 0; -} + for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) + tn->timeouts[i] = tcp_timeouts[i]; -static struct nf_proto_net *tcp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.tcp.pn; + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; + tn->tcp_loose = nf_ct_tcp_loose; + tn->tcp_be_liberal = nf_ct_tcp_be_liberal; + tn->tcp_max_retrans = nf_ct_tcp_max_retrans; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = @@ -1441,6 +1430,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = .nla_policy = tcp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = tcp_init_net, - .get_net_proto = tcp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 6e81e79844d7..951366dfbec3 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -260,25 +260,13 @@ udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - -static int udp_init_net(struct net *net) +void nf_conntrack_udp_init_net(struct net *net) { struct nf_udp_net *un = nf_udp_pernet(net); - struct nf_proto_net *pn = &un->pn; - - if (!pn->users) { - int i; - - for (i = 0; i < UDP_CT_MAX; i++) - un->timeouts[i] = udp_timeouts[i]; - } + int i; - return 0; -} - -static struct nf_proto_net *udp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.udp.pn; + for (i = 0; i < UDP_CT_MAX; i++) + un->timeouts[i] = udp_timeouts[i]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp = @@ -300,8 +288,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp = .nla_policy = udp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = udp_init_net, - .get_net_proto = udp_get_net_proto, }; #ifdef CONFIG_NF_CT_PROTO_UDPLITE @@ -324,7 +310,5 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite = .nla_policy = udp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = udp_init_net, - .get_net_proto = udp_get_net_proto, }; #endif -- cgit v1.2.3 From e56894356f60f9d11bdf53ee5a050a235f6d2b48 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:46 +0100 Subject: netfilter: conntrack: remove l4proto destroy hook Only one user (gre), add a direct call and remove this facility. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 3 --- net/netfilter/nf_conntrack_core.c | 15 +++++++++++---- net/netfilter/nf_conntrack_proto_gre.c | 14 -------------- 3 files changed, 11 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index d5909e51ca92..5d1419ac6a38 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -27,9 +27,6 @@ struct nf_conntrack_l4proto { /* protoinfo nlattr size, closes a hole */ u16 nlattr_size; - /* Called when a conntrack entry is destroyed */ - void (*destroy)(struct nf_conn *ct); - /* called by gc worker if table is full */ bool (*can_early_drop)(const struct nf_conn *ct); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 728d2b5bdb1a..52e6c5c6f202 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -524,11 +524,18 @@ void nf_ct_tmpl_free(struct nf_conn *tmpl) } EXPORT_SYMBOL_GPL(nf_ct_tmpl_free); +static void destroy_gre_conntrack(struct nf_conn *ct) +{ + struct nf_conn *master = ct->master; + + if (master) + nf_ct_gre_keymap_destroy(master); +} + static void destroy_conntrack(struct nf_conntrack *nfct) { struct nf_conn *ct = (struct nf_conn *)nfct; - const struct nf_conntrack_l4proto *l4proto; pr_debug("destroy_conntrack(%p)\n", ct); WARN_ON(atomic_read(&nfct->use) != 0); @@ -537,9 +544,9 @@ destroy_conntrack(struct nf_conntrack *nfct) nf_ct_tmpl_free(ct); return; } - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); - if (l4proto->destroy) - l4proto->destroy(ct); + + if (unlikely(nf_ct_protonum(ct) == IPPROTO_GRE)) + destroy_gre_conntrack(ct); local_bh_disable(); /* Expectations will have been removed in clean_from_lists, diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index fa765d2fd586..ee9ab10a32e4 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -249,19 +249,6 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, return NF_ACCEPT; } -/* Called when a conntrack entry has already been removed from the hashes - * and is about to be deleted from memory */ -static void gre_destroy(struct nf_conn *ct) -{ - struct nf_conn *master = ct->master; - pr_debug(" entering\n"); - - if (!master) - pr_debug("no master !?!\n"); - else - nf_ct_gre_keymap_destroy(master); -} - #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include @@ -329,7 +316,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = { #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = gre_print_conntrack, #endif - .destroy = gre_destroy, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, -- cgit v1.2.3 From 4a60dc748d121b52533a2956567df4f87a3835b1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:47 +0100 Subject: netfilter: conntrack: remove nf_ct_l4proto_find_get Its now same as __nf_ct_l4proto_find(), so rename that to nf_ct_l4proto_find and use it everywhere. It never returns NULL and doesn't need locks or reference counts. Before this series: 302824 net/netfilter/nf_conntrack.ko 21504 net/netfilter/nf_conntrack_proto_gre.ko text data bss dec hex filename 6281 1732 4 8017 1f51 nf_conntrack_proto_gre.ko 108356 20613 236 129205 1f8b5 nf_conntrack.ko After: 294864 net/netfilter/nf_conntrack.ko text data bss dec hex filename 106979 19557 240 126776 1ef38 nf_conntrack.ko so, even with builtin gre, total size got reduced. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 2 +- include/net/netfilter/nf_conntrack_l4proto.h | 8 +- net/netfilter/nf_conntrack_core.c | 11 +- net/netfilter/nf_conntrack_expect.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 14 +-- net/netfilter/nf_conntrack_proto.c | 175 ++++----------------------- net/netfilter/nf_conntrack_standalone.c | 3 +- net/netfilter/nf_flow_table_core.c | 2 +- net/netfilter/nfnetlink_cttimeout.c | 6 +- net/netfilter/nft_ct.c | 2 +- net/netfilter/xt_CT.c | 2 +- 11 files changed, 45 insertions(+), 182 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 235c182022b2..ae41e92251dd 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -26,7 +26,7 @@ int nf_conntrack_init_net(struct net *net); void nf_conntrack_cleanup_net(struct net *net); void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list); -int nf_conntrack_proto_pernet_init(struct net *net); +void nf_conntrack_proto_pernet_init(struct net *net); void nf_conntrack_proto_pernet_fini(struct net *net); int nf_conntrack_proto_init(void); diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 5d1419ac6a38..778087591983 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -140,13 +140,7 @@ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; #define MAX_NF_CT_PROTO IPPROTO_UDPLITE -const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u8 l4proto); - -const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4proto); - -/* Protocol global registration. */ -int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *proto); -void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *proto); +const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto); /* Generic netlink helpers */ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 52e6c5c6f202..171659aa69a1 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -845,7 +845,7 @@ static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, enum ip_conntrack_info oldinfo; struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo); - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->allow_clash && !nf_ct_is_dying(ct) && atomic_inc_not_zero(&ct->ct_general.use)) { @@ -1117,7 +1117,7 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct) if (!test_bit(IPS_ASSURED_BIT, &ct->status)) return true; - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->can_early_drop && l4proto->can_early_drop(ct)) return true; @@ -2452,15 +2452,10 @@ int nf_conntrack_init_net(struct net *net) nf_conntrack_tstamp_pernet_init(net); nf_conntrack_ecache_pernet_init(net); nf_conntrack_helper_pernet_init(net); + nf_conntrack_proto_pernet_init(net); - ret = nf_conntrack_proto_pernet_init(net); - if (ret < 0) - goto err_proto; return 0; -err_proto: - nf_conntrack_ecache_pernet_fini(net); - nf_conntrack_expect_pernet_fini(net); err_expect: free_percpu(net->ct.stat); err_pcpu_lists: diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 3034038bfdf0..334d6e5b7762 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -610,7 +610,7 @@ static int exp_seq_show(struct seq_file *s, void *v) expect->tuple.src.l3num, expect->tuple.dst.protonum); print_tuple(s, &expect->tuple, - __nf_ct_l4proto_find(expect->tuple.dst.protonum)); + nf_ct_l4proto_find(expect->tuple.dst.protonum)); if (expect->flags & NF_CT_EXPECT_PERMANENT) { seq_puts(s, "PERMANENT"); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1213beb5a714..8071bb04a849 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -134,7 +134,7 @@ static int ctnetlink_dump_tuples(struct sk_buff *skb, ret = ctnetlink_dump_tuples_ip(skb, tuple); if (ret >= 0) { - l4proto = __nf_ct_l4proto_find(tuple->dst.protonum); + l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); } rcu_read_unlock(); @@ -182,7 +182,7 @@ static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct) struct nlattr *nest_proto; int ret; - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (!l4proto->to_nlattr) return 0; @@ -590,7 +590,7 @@ static size_t ctnetlink_proto_size(const struct nf_conn *ct) len = nla_policy_len(cta_ip_nla_policy, CTA_IP_MAX + 1); len *= 3u; /* ORIG, REPLY, MASTER */ - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); len += l4proto->nlattr_size; if (l4proto->nlattr_tuple_size) { len4 = l4proto->nlattr_tuple_size(); @@ -1059,7 +1059,7 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr, tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]); rcu_read_lock(); - l4proto = __nf_ct_l4proto_find(tuple->dst.protonum); + l4proto = nf_ct_l4proto_find(tuple->dst.protonum); if (likely(l4proto->nlattr_to_tuple)) { ret = nla_validate_nested(attr, CTA_PROTO_MAX, @@ -1722,11 +1722,9 @@ static int ctnetlink_change_protoinfo(struct nf_conn *ct, if (err < 0) return err; - rcu_read_lock(); - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->from_nlattr) err = l4proto->from_nlattr(tb, ct); - rcu_read_unlock(); return err; } @@ -2676,7 +2674,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, &m); if (ret >= 0) { - l4proto = __nf_ct_l4proto_find(tuple->dst.protonum); + l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto); } rcu_read_unlock(); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index e6bc02c13f0f..aa8d3fe0b37f 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -43,8 +43,6 @@ extern unsigned int nf_conntrack_net_id; -static struct nf_conntrack_l4proto __rcu *nf_ct_protos[MAX_NF_CT_PROTO + 1] __read_mostly; - static DEFINE_MUTEX(nf_ct_proto_mutex); #ifdef CONFIG_SYSCTL @@ -95,121 +93,32 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_ct_l4proto_log_invalid); #endif -const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u8 l4proto) -{ - if (unlikely(l4proto >= ARRAY_SIZE(nf_ct_protos))) - return &nf_conntrack_l4proto_generic; - - return rcu_dereference(nf_ct_protos[l4proto]); -} -EXPORT_SYMBOL_GPL(__nf_ct_l4proto_find); - -const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4num) -{ - const struct nf_conntrack_l4proto *p; - - rcu_read_lock(); - p = __nf_ct_l4proto_find(l4num); - rcu_read_unlock(); - - return p; -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_find_get); - -static int kill_l4proto(struct nf_conn *i, void *data) +const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto) { - const struct nf_conntrack_l4proto *l4proto; - l4proto = data; - return nf_ct_protonum(i) == l4proto->l4proto; -} - -/* FIXME: Allow NULL functions and sub in pointers to generic for - them. --RR */ -int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *l4proto) -{ - int ret = 0; - - if ((l4proto->to_nlattr && l4proto->nlattr_size == 0) || - (l4proto->tuple_to_nlattr && !l4proto->nlattr_tuple_size)) - return -EINVAL; - - mutex_lock(&nf_ct_proto_mutex); - if (rcu_dereference_protected( - nf_ct_protos[l4proto->l4proto], - lockdep_is_held(&nf_ct_proto_mutex) - ) != &nf_conntrack_l4proto_generic) { - ret = -EBUSY; - goto out_unlock; + switch (l4proto) { + case IPPROTO_UDP: return &nf_conntrack_l4proto_udp; + case IPPROTO_TCP: return &nf_conntrack_l4proto_tcp; + case IPPROTO_ICMP: return &nf_conntrack_l4proto_icmp; +#ifdef CONFIG_NF_CT_PROTO_DCCP + case IPPROTO_DCCP: return &nf_conntrack_l4proto_dccp; +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + case IPPROTO_SCTP: return &nf_conntrack_l4proto_sctp; +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + case IPPROTO_UDPLITE: return &nf_conntrack_l4proto_udplite; +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE + case IPPROTO_GRE: return &nf_conntrack_l4proto_gre; +#endif +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ICMPV6: return &nf_conntrack_l4proto_icmpv6; +#endif /* CONFIG_IPV6 */ } - rcu_assign_pointer(nf_ct_protos[l4proto->l4proto], l4proto); -out_unlock: - mutex_unlock(&nf_ct_proto_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_register_one); - -static void __nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto) - -{ - BUG_ON(l4proto->l4proto >= ARRAY_SIZE(nf_ct_protos)); - - BUG_ON(rcu_dereference_protected( - nf_ct_protos[l4proto->l4proto], - lockdep_is_held(&nf_ct_proto_mutex) - ) != l4proto); - rcu_assign_pointer(nf_ct_protos[l4proto->l4proto], - &nf_conntrack_l4proto_generic); -} - -void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto) -{ - mutex_lock(&nf_ct_proto_mutex); - __nf_ct_l4proto_unregister_one(l4proto); - mutex_unlock(&nf_ct_proto_mutex); - - synchronize_net(); - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto); -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister_one); - -static void -nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[], - unsigned int num_proto) -{ - int i; - - mutex_lock(&nf_ct_proto_mutex); - for (i = 0; i < num_proto; i++) - __nf_ct_l4proto_unregister_one(l4proto[i]); - mutex_unlock(&nf_ct_proto_mutex); - - synchronize_net(); - - for (i = 0; i < num_proto; i++) - nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto[i]); -} - -static int -nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], - unsigned int num_proto) -{ - int ret = -EINVAL; - unsigned int i; - - for (i = 0; i < num_proto; i++) { - ret = nf_ct_l4proto_register_one(l4proto[i]); - if (ret < 0) - break; - } - if (i != num_proto) { - pr_err("nf_conntrack: can't register l4 %d proto.\n", - l4proto[i]->l4proto); - nf_ct_l4proto_unregister(l4proto, i); - } - return ret; -} + return &nf_conntrack_l4proto_generic; +}; +EXPORT_SYMBOL_GPL(nf_ct_l4proto_find); static unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, @@ -651,30 +560,9 @@ void nf_ct_netns_put(struct net *net, uint8_t nfproto) } EXPORT_SYMBOL_GPL(nf_ct_netns_put); -static const struct nf_conntrack_l4proto * const builtin_l4proto[] = { - &nf_conntrack_l4proto_tcp, - &nf_conntrack_l4proto_udp, - &nf_conntrack_l4proto_icmp, -#ifdef CONFIG_NF_CT_PROTO_DCCP - &nf_conntrack_l4proto_dccp, -#endif -#ifdef CONFIG_NF_CT_PROTO_SCTP - &nf_conntrack_l4proto_sctp, -#endif -#ifdef CONFIG_NF_CT_PROTO_UDPLITE - &nf_conntrack_l4proto_udplite, -#endif -#ifdef CONFIG_NF_CT_PROTO_GRE - &nf_conntrack_l4proto_gre, -#endif -#if IS_ENABLED(CONFIG_IPV6) - &nf_conntrack_l4proto_icmpv6, -#endif /* CONFIG_IPV6 */ -}; - int nf_conntrack_proto_init(void) { - int ret = 0, i; + int ret; ret = nf_register_sockopt(&so_getorigdst); if (ret < 0) @@ -686,18 +574,8 @@ int nf_conntrack_proto_init(void) goto cleanup_sockopt; #endif - for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) - RCU_INIT_POINTER(nf_ct_protos[i], - &nf_conntrack_l4proto_generic); - - ret = nf_ct_l4proto_register(builtin_l4proto, - ARRAY_SIZE(builtin_l4proto)); - if (ret < 0) - goto cleanup_sockopt2; - return ret; -cleanup_sockopt2: - nf_unregister_sockopt(&so_getorigdst); + #if IS_ENABLED(CONFIG_IPV6) cleanup_sockopt: nf_unregister_sockopt(&so_getorigdst6); @@ -713,7 +591,7 @@ void nf_conntrack_proto_fini(void) #endif } -int nf_conntrack_proto_pernet_init(struct net *net) +void nf_conntrack_proto_pernet_init(struct net *net) { nf_conntrack_generic_init_net(net); nf_conntrack_udp_init_net(net); @@ -729,7 +607,6 @@ int nf_conntrack_proto_pernet_init(struct net *net) #ifdef CONFIG_NF_CT_PROTO_GRE nf_conntrack_gre_init_net(net); #endif - return 0; } void nf_conntrack_proto_pernet_fini(struct net *net) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index d848de713dc0..ddfca5f1784c 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -310,8 +310,7 @@ static int ct_seq_show(struct seq_file *s, void *v) if (!net_eq(nf_ct_net(ct), net)) goto release; - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); - WARN_ON(!l4proto); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); ret = -ENOSPC; seq_printf(s, "%-8s %u %-8s %u ", diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index fa0844e2a68d..8099f0f778ab 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -120,7 +120,7 @@ static void flow_offload_fixup_ct_state(struct nf_conn *ct) if (l4num == IPPROTO_TCP) flow_offload_fixup_tcp(&ct->proto.tcp); - l4proto = __nf_ct_l4proto_find(l4num); + l4proto = nf_ct_l4proto_find(l4num); if (!l4proto) return; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 37b4f84ac153..c69b11ca5aad 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -122,7 +122,7 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, return -EBUSY; } - l4proto = nf_ct_l4proto_find_get(l4num); + l4proto = nf_ct_l4proto_find(l4num); /* This protocol is not supportted, skip. */ if (l4proto->l4proto != l4num) { @@ -357,7 +357,7 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl, return -EINVAL; l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); - l4proto = nf_ct_l4proto_find_get(l4num); + l4proto = nf_ct_l4proto_find(l4num); /* This protocol is not supported, skip. */ if (l4proto->l4proto != l4num) { @@ -438,7 +438,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO])); l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); - l4proto = nf_ct_l4proto_find_get(l4num); + l4proto = nf_ct_l4proto_find(l4num); err = -EOPNOTSUPP; if (l4proto->l4proto != l4num) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 3249cc059048..7b717fad6cdc 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -870,7 +870,7 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, l4num = nla_get_u8(tb[NFTA_CT_TIMEOUT_L4PROTO]); priv->l4proto = l4num; - l4proto = nf_ct_l4proto_find_get(l4num); + l4proto = nf_ct_l4proto_find(l4num); if (l4proto->l4proto != l4num) { ret = -EOPNOTSUPP; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 2c7a4b80206f..0fa863f57575 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -159,7 +159,7 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, /* Make sure the timeout policy matches any existing protocol tracker, * otherwise default to generic. */ - l4proto = __nf_ct_l4proto_find(proto); + l4proto = nf_ct_l4proto_find(proto); if (timeout->l4proto->l4proto != l4proto->l4proto) { ret = -EINVAL; pr_info_ratelimited("Timeout policy `%s' can only be used by L%d protocol number %d\n", -- cgit v1.2.3 From 0fb4d21956f4a9af225594a46857ccf29bd747bc Mon Sep 17 00:00:00 2001 From: wenxu Date: Wed, 16 Jan 2019 07:53:51 +0800 Subject: netfilter: nft_meta: Add NFT_META_I/OIFKIND meta type In the ip_rcv the skb goes through the PREROUTING hook first, then kicks in vrf device and go through the same hook again. When conntrack dnat works with vrf, there will be some conflict with rules because the packet goes through the hook twice with different nf status. ip link add user1 type vrf table 1 ip link add user2 type vrf table 2 ip l set dev tun1 master user1 ip l set dev tun2 master user2 nft add table firewall nft add chain firewall zones { type filter hook prerouting priority - 300 \; } nft add rule firewall zones counter ct zone set iif map { "tun1" : 1, "tun2" : 2 } nft add chain firewall rule-1000-ingress nft add rule firewall rule-1000-ingress ct zone 1 tcp dport 22 ct state new counter accept nft add rule firewall rule-1000-ingress counter drop nft add chain firewall rule-1000-egress nft add rule firewall rule-1000-egress tcp dport 22 ct state new counter drop nft add rule firewall rule-1000-egress counter accept nft add chain firewall rules-all { type filter hook prerouting priority - 150 \; } nft add rule firewall rules-all ip daddr vmap { "2.2.2.11" : jump rule-1000-ingress } nft add rule firewall rules-all ct zone vmap { 1 : jump rule-1000-egress } nft add rule firewall dnat-all ct zone vmap { 1 : jump dnat-1000 } nft add rule firewall dnat-1000 ip daddr 2.2.2.11 counter dnat to 10.0.0.7 For a package with ip daddr 2.2.2.11 and tcp dport 22, first time accept in the rule-1000-ingress and dnat to 10.0.0.7. Then second time the packet goto the wrong chain rule-1000-egress which leads the packet drop With this patch, userspace can add the 'don't re-do entire ruleset for vrf' policy itself via: nft add rule firewall rules-all meta iifkind "vrf" counter accept Signed-off-by: wenxu Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 ++++ net/netfilter/nft_meta.c | 12 ++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 99ca95b830b6..0ba8f48bdf0b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -791,6 +791,8 @@ enum nft_exthdr_attributes { * @NFT_META_CGROUP: socket control group (skb->sk->sk_classid) * @NFT_META_PRANDOM: a 32bit pseudo-random number * @NFT_META_SECPATH: boolean, secpath_exists (!!skb->sp) + * @NFT_META_IIFKIND: packet input interface kind name (dev->rtnl_link_ops->kind) + * @NFT_META_OIFKIND: packet output interface kind name (dev->rtnl_link_ops->kind) */ enum nft_meta_keys { NFT_META_LEN, @@ -819,6 +821,8 @@ enum nft_meta_keys { NFT_META_CGROUP, NFT_META_PRANDOM, NFT_META_SECPATH, + NFT_META_IIFKIND, + NFT_META_OIFKIND, }; /** diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 6df486c5ebd3..987d2d6ce624 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -244,6 +244,16 @@ void nft_meta_get_eval(const struct nft_expr *expr, strncpy((char *)dest, p->br->dev->name, IFNAMSIZ); return; #endif + case NFT_META_IIFKIND: + if (in == NULL || in->rtnl_link_ops == NULL) + goto err; + strncpy((char *)dest, in->rtnl_link_ops->kind, IFNAMSIZ); + break; + case NFT_META_OIFKIND: + if (out == NULL || out->rtnl_link_ops == NULL) + goto err; + strncpy((char *)dest, out->rtnl_link_ops->kind, IFNAMSIZ); + break; default: WARN_ON(1); goto err; @@ -340,6 +350,8 @@ static int nft_meta_get_init(const struct nft_ctx *ctx, break; case NFT_META_IIFNAME: case NFT_META_OIFNAME: + case NFT_META_IIFKIND: + case NFT_META_OIFKIND: len = IFNAMSIZ; break; case NFT_META_PRANDOM: -- cgit v1.2.3 From 472caa69183f7eaf30ecb34451826dd5b98d7b3a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 17 Jan 2019 00:11:43 +0100 Subject: netfilter: nat: un-export nf_nat_used_tuple Not used since 203f2e78200c27e ("netfilter: nat: remove l4proto->unique_tuple") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_nat.h | 4 ---- net/netfilter/nf_nat_core.c | 3 +-- 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index a17eb2f8d40e..8aff77cafb8b 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -47,10 +47,6 @@ extern unsigned int nf_nat_alloc_null_binding(struct nf_conn *ct, struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct); -/* Is this tuple already taken? (not by us)*/ -int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, - const struct nf_conn *ignored_conntrack); - static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct) { #if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 44f97b3a215a..35e61038ae96 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -146,7 +146,7 @@ hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) } /* Is this tuple already taken? (not by us) */ -int +static int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack) { @@ -161,7 +161,6 @@ nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, nf_ct_invert_tuple(&reply, tuple); return nf_conntrack_tuple_taken(&reply, ignored_conntrack); } -EXPORT_SYMBOL(nf_nat_used_tuple); static bool nf_nat_inet_in_range(const struct nf_conntrack_tuple *t, const struct nf_nat_range2 *range) -- cgit v1.2.3 From 0123a75e1d57c3df31e536868339c98c02c14917 Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Fri, 18 Jan 2019 14:36:29 +0100 Subject: Revert "netfilter: nft_hash: add map lookups for hashing operations" A better way to implement this from userspace has been found without specific code in the kernel side, revert this. Fixes: b9ccc07e3f31 ("netfilter: nft_hash: add map lookups for hashing operations") Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 +- net/netfilter/nft_hash.c | 121 ------------------------------- 2 files changed, 2 insertions(+), 123 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 0ba8f48bdf0b..030302893d96 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -877,8 +877,8 @@ enum nft_hash_attributes { NFTA_HASH_SEED, NFTA_HASH_OFFSET, NFTA_HASH_TYPE, - NFTA_HASH_SET_NAME, - NFTA_HASH_SET_ID, + NFTA_HASH_SET_NAME, /* deprecated */ + NFTA_HASH_SET_ID, /* deprecated */ __NFTA_HASH_MAX, }; #define NFTA_HASH_MAX (__NFTA_HASH_MAX - 1) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index c2d237144f74..ea658e6c53e3 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -25,7 +25,6 @@ struct nft_jhash { u32 modulus; u32 seed; u32 offset; - struct nft_set *map; }; static void nft_jhash_eval(const struct nft_expr *expr, @@ -42,33 +41,10 @@ static void nft_jhash_eval(const struct nft_expr *expr, regs->data[priv->dreg] = h + priv->offset; } -static void nft_jhash_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_jhash *priv = nft_expr_priv(expr); - const void *data = ®s->data[priv->sreg]; - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = reciprocal_scale(jhash(data, priv->len, priv->seed), - priv->modulus) + priv->offset; - - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - struct nft_symhash { enum nft_registers dreg:8; u32 modulus; u32 offset; - struct nft_set *map; }; static void nft_symhash_eval(const struct nft_expr *expr, @@ -84,28 +60,6 @@ static void nft_symhash_eval(const struct nft_expr *expr, regs->data[priv->dreg] = h + priv->offset; } -static void nft_symhash_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_symhash *priv = nft_expr_priv(expr); - struct sk_buff *skb = pkt->skb; - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = reciprocal_scale(__skb_get_hash_symmetric(skb), - priv->modulus) + priv->offset; - - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SREG] = { .type = NLA_U32 }, [NFTA_HASH_DREG] = { .type = NLA_U32 }, @@ -114,9 +68,6 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SEED] = { .type = NLA_U32 }, [NFTA_HASH_OFFSET] = { .type = NLA_U32 }, [NFTA_HASH_TYPE] = { .type = NLA_U32 }, - [NFTA_HASH_SET_NAME] = { .type = NLA_STRING, - .len = NFT_SET_MAXNAMELEN - 1 }, - [NFTA_HASH_SET_ID] = { .type = NLA_U32 }, }; static int nft_jhash_init(const struct nft_ctx *ctx, @@ -166,20 +117,6 @@ static int nft_jhash_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_jhash_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_jhash *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_jhash_init(ctx, expr, tb); - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_HASH_SET_NAME], - tb[NFTA_HASH_SET_ID], genmask); - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_symhash_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -206,20 +143,6 @@ static int nft_symhash_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_symhash_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_jhash *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_symhash_init(ctx, expr, tb); - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_HASH_SET_NAME], - tb[NFTA_HASH_SET_ID], genmask); - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_jhash_dump(struct sk_buff *skb, const struct nft_expr *expr) { @@ -247,18 +170,6 @@ nla_put_failure: return -1; } -static int nft_jhash_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_jhash *priv = nft_expr_priv(expr); - - if (nft_jhash_dump(skb, expr) || - nla_put_string(skb, NFTA_HASH_SET_NAME, priv->map->name)) - return -1; - - return 0; -} - static int nft_symhash_dump(struct sk_buff *skb, const struct nft_expr *expr) { @@ -279,18 +190,6 @@ nla_put_failure: return -1; } -static int nft_symhash_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_symhash *priv = nft_expr_priv(expr); - - if (nft_symhash_dump(skb, expr) || - nla_put_string(skb, NFTA_HASH_SET_NAME, priv->map->name)) - return -1; - - return 0; -} - static struct nft_expr_type nft_hash_type; static const struct nft_expr_ops nft_jhash_ops = { .type = &nft_hash_type, @@ -300,14 +199,6 @@ static const struct nft_expr_ops nft_jhash_ops = { .dump = nft_jhash_dump, }; -static const struct nft_expr_ops nft_jhash_map_ops = { - .type = &nft_hash_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_jhash)), - .eval = nft_jhash_map_eval, - .init = nft_jhash_map_init, - .dump = nft_jhash_map_dump, -}; - static const struct nft_expr_ops nft_symhash_ops = { .type = &nft_hash_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), @@ -316,14 +207,6 @@ static const struct nft_expr_ops nft_symhash_ops = { .dump = nft_symhash_dump, }; -static const struct nft_expr_ops nft_symhash_map_ops = { - .type = &nft_hash_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), - .eval = nft_symhash_map_eval, - .init = nft_symhash_map_init, - .dump = nft_symhash_map_dump, -}; - static const struct nft_expr_ops * nft_hash_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -336,12 +219,8 @@ nft_hash_select_ops(const struct nft_ctx *ctx, type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE])); switch (type) { case NFT_HASH_SYM: - if (tb[NFTA_HASH_SET_NAME]) - return &nft_symhash_map_ops; return &nft_symhash_ops; case NFT_HASH_JENKINS: - if (tb[NFTA_HASH_SET_NAME]) - return &nft_jhash_map_ops; return &nft_jhash_ops; default: break; -- cgit v1.2.3 From 570d0200123fb4f809aa2f6226e93a458d664d70 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Fri, 18 Jan 2019 10:34:59 +0800 Subject: driver core: move device->knode_class to device_private As the description of struct device_private says, it stores data which is private to driver core. And it already has similar fields like: knode_parent, knode_driver, knode_driver and knode_bus. This look it is more proper to put knode_class together with those fields to make it private to driver core. This patch move device->knode_class to device_private to make it comply with code convention. Signed-off-by: Wei Yang Reviewed-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 4 ++++ drivers/base/class.c | 14 ++++++++++---- drivers/base/core.c | 4 ++-- include/linux/device.h | 1 - 4 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/base/base.h b/drivers/base/base.h index 7a419a7a6235..37329a668935 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -60,6 +60,7 @@ struct driver_private { * @knode_parent - node in sibling list * @knode_driver - node in driver list * @knode_bus - node in bus list + * @knode_class - node in class list * @deferred_probe - entry in deferred_probe_list which is used to retry the * binding of drivers which were unable to get all the resources needed by * the device; typically because it depends on another driver getting @@ -74,6 +75,7 @@ struct device_private { struct klist_node knode_parent; struct klist_node knode_driver; struct klist_node knode_bus; + struct klist_node knode_class; struct list_head deferred_probe; struct device *device; }; @@ -83,6 +85,8 @@ struct device_private { container_of(obj, struct device_private, knode_driver) #define to_device_private_bus(obj) \ container_of(obj, struct device_private, knode_bus) +#define to_device_private_class(obj) \ + container_of(obj, struct device_private, knode_class) /* initialisation functions */ extern int devices_init(void); diff --git a/drivers/base/class.c b/drivers/base/class.c index 54def4e02f00..d8a6a5864c2e 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -117,16 +117,22 @@ static void class_put(struct class *cls) kset_put(&cls->p->subsys); } +static struct device *klist_class_to_dev(struct klist_node *n) +{ + struct device_private *p = to_device_private_class(n); + return p->device; +} + static void klist_class_dev_get(struct klist_node *n) { - struct device *dev = container_of(n, struct device, knode_class); + struct device *dev = klist_class_to_dev(n); get_device(dev); } static void klist_class_dev_put(struct klist_node *n) { - struct device *dev = container_of(n, struct device, knode_class); + struct device *dev = klist_class_to_dev(n); put_device(dev); } @@ -277,7 +283,7 @@ void class_dev_iter_init(struct class_dev_iter *iter, struct class *class, struct klist_node *start_knode = NULL; if (start) - start_knode = &start->knode_class; + start_knode = &start->p->knode_class; klist_iter_init_node(&class->p->klist_devices, &iter->ki, start_knode); iter->type = type; } @@ -304,7 +310,7 @@ struct device *class_dev_iter_next(struct class_dev_iter *iter) knode = klist_next(&iter->ki); if (!knode) return NULL; - dev = container_of(knode, struct device, knode_class); + dev = klist_class_to_dev(knode); if (!iter->type || iter->type == dev->type) return dev; } diff --git a/drivers/base/core.c b/drivers/base/core.c index 0073b09bb99f..4a4b6f8cbc4f 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1966,7 +1966,7 @@ int device_add(struct device *dev) if (dev->class) { mutex_lock(&dev->class->p->mutex); /* tie the class to the device */ - klist_add_tail(&dev->knode_class, + klist_add_tail(&dev->p->knode_class, &dev->class->p->klist_devices); /* notify any interfaces that the device is here */ @@ -2105,7 +2105,7 @@ void device_del(struct device *dev) if (class_intf->remove_dev) class_intf->remove_dev(dev, class_intf); /* remove the device from the class list */ - klist_del(&dev->knode_class); + klist_del(&dev->p->knode_class); mutex_unlock(&dev->class->p->mutex); } device_remove_file(dev, &dev_attr_uevent); diff --git a/include/linux/device.h b/include/linux/device.h index 6cb4640b6160..d0e452fd0bff 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1035,7 +1035,6 @@ struct device { spinlock_t devres_lock; struct list_head devres_head; - struct klist_node knode_class; struct class *class; const struct attribute_group **groups; /* optional groups */ -- cgit v1.2.3 From 62bc79d35ebb55451112979babea864975cfd16d Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 18 Jan 2019 11:20:41 +0900 Subject: ASoC: soc.h: add explanation of legacy/modern style of dai_link Current ALSA SoC is assuming 1 CPU 1 Platform (= DMA) style system. Because of this background, it is directly using xxx_name / xxx_of_node / xxx_dai_name on dai_link. Let's call it as legacy style here. More complex style system like multi CPU multi Platform (= DMA) will coming. To supporting it, we can use snd_soc_dai_link_component on dai_link. Let's call it as modern style here. But current ALSA SoC can't support it so far. Thus, we need to have multi CPU / multi Codec / multi Platform style in the future on ALSA SoC. Currently we already have multi Codec support. Platform is starting to use modern style on dai_link, but still style only. Multi Platform is not yet implemented. And we still don't have multi CPU support on ALSA SoC, and not have modern style either. Currently, if driver is using legacy style Codec/Platform, it will be converted to modern style on soc-core. This means, we are using glue code for legacy vs modern style so far on ALSA SoC. We can fully switch to modern style on all drivers if ALSA SoC supported modern style for CPU, and then, legacy style code will be removed from ALSA SoC. Untile then, we need to keep both legacy/modern style and its glue code. This patch adds such future plan and background on soc.h Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/soc.h | 36 ++++++++++++++++++++++++++++++++++++ sound/soc/soc-core.c | 20 ++++++++++++++++++-- 2 files changed, 54 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index e665f111b0d2..c31b6d122ff6 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -891,6 +891,18 @@ struct snd_soc_dai_link { /* config - must be set by machine driver */ const char *name; /* Codec name */ const char *stream_name; /* Stream name */ + + /* + * cpu_name + * cpu_of_node + * cpu_dai_name + * + * These are legacy style, and will be replaced to + * modern style (= snd_soc_dai_link_component) in the future, + * but, not yet supported so far. + * If modern style was supported for CPU, all driver will switch + * to use it, and, legacy style code will be removed from ALSA SoC. + */ /* * You MAY specify the link's CPU-side device, either by device name, * or by DT/OF node, but not both. If this information is omitted, @@ -906,6 +918,19 @@ struct snd_soc_dai_link { * only, which only works well when that device exposes a single DAI. */ const char *cpu_dai_name; + + /* + * codec_name + * codec_of_node + * codec_dai_name + * + * These are legacy style, it will be converted to modern style + * (= snd_soc_dai_link_component) automatically in soc-core + * if driver is using legacy style. + * Driver shouldn't use both legacy and modern style in the same time. + * If modern style was supported for CPU, all driver will switch + * to use it, and, legacy style code will be removed from ALSA SoC. + */ /* * You MUST specify the link's codec, either by device name, or by * DT/OF node, but not both. @@ -918,6 +943,17 @@ struct snd_soc_dai_link { struct snd_soc_dai_link_component *codecs; unsigned int num_codecs; + /* + * platform_name + * platform_of_node + * + * These are legacy style, it will be converted to modern style + * (= snd_soc_dai_link_component) automatically in soc-core + * if driver is using legacy style. + * Driver shouldn't use both legacy and modern style in the same time. + * If modern style was supported for CPU, all driver will switch + * to use it, and, legacy style code will be removed from ALSA SoC. + */ /* * You MAY specify the link's platform/PCM/DMA driver, either by * device name, or by DT/OF node, but not both. Some forms of link diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 890d6c9c2752..de2851f1b3df 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1029,9 +1029,14 @@ static int snd_soc_init_platform(struct snd_soc_card *card, struct snd_soc_dai_link_component *platform = dai_link->platform; /* - * FIXME + * REMOVE ME * - * this function should be removed in the future + * This is glue code for Legacy vs Modern dai_link. + * This function will be removed if all derivers are switched to + * modern style dai_link. + * Driver shouldn't use both legacy and modern style in the same time. + * see + * soc.h :: struct snd_soc_dai_link */ /* convert Legacy platform link */ if (!platform || dai_link->legacy_platform) { @@ -1059,6 +1064,17 @@ static int snd_soc_init_platform(struct snd_soc_card *card, static int snd_soc_init_multicodec(struct snd_soc_card *card, struct snd_soc_dai_link *dai_link) { + /* + * REMOVE ME + * + * This is glue code for Legacy vs Modern dai_link. + * This function will be removed if all derivers are switched to + * modern style dai_link. + * Driver shouldn't use both legacy and modern style in the same time. + * see + * soc.h :: struct snd_soc_dai_link + */ + /* Legacy codec/codec_dai link is a single entry in multicodec */ if (dai_link->codec_name || dai_link->codec_of_node || dai_link->codec_dai_name) { -- cgit v1.2.3 From 1cfb2a512e74e577bb0ed7c8d76df90a41a83f6a Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 18 Jan 2019 19:15:59 +0900 Subject: LSM: Make lsm_early_cred() and lsm_early_task() local functions. Since current->cred == current->real_cred when ordered_lsm_init() is called, and lsm_early_cred()/lsm_early_task() need to be called between the amount of required bytes is determined and module specific initialization function is called, we can move these calls from individual modules to ordered_lsm_init(). Signed-off-by: Tetsuo Handa Acked-by: Casey Schaufler Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 5 ----- security/apparmor/lsm.c | 2 -- security/security.c | 27 +++++++++++---------------- security/selinux/hooks.c | 1 - security/smack/smack_lsm.c | 2 -- security/tomoyo/tomoyo.c | 1 - 6 files changed, 11 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 195707210975..22fc786d723a 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2112,9 +2112,4 @@ static inline void security_delete_hooks(struct security_hook_list *hooks, extern int lsm_inode_alloc(struct inode *inode); -#ifdef CONFIG_SECURITY -void __init lsm_early_cred(struct cred *cred); -void __init lsm_early_task(struct task_struct *task); -#endif - #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index b6c395e2acd0..bb5a02d2439f 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1484,8 +1484,6 @@ static int __init set_init_ctx(void) { struct cred *cred = (struct cred *)current->real_cred; - lsm_early_cred(cred); - lsm_early_task(current); set_cred_label(cred, aa_get_label(ns_unconfined(root_ns))); return 0; diff --git a/security/security.c b/security/security.c index a618e22df5c6..992b612c819a 100644 --- a/security/security.c +++ b/security/security.c @@ -278,6 +278,9 @@ static void __init ordered_lsm_parse(const char *order, const char *origin) kfree(sep); } +static void __init lsm_early_cred(struct cred *cred); +static void __init lsm_early_task(struct task_struct *task); + static void __init ordered_lsm_init(void) { struct lsm_info **lsm; @@ -312,6 +315,8 @@ static void __init ordered_lsm_init(void) blob_sizes.lbs_inode, 0, SLAB_PANIC, NULL); + lsm_early_cred((struct cred *) current->cred); + lsm_early_task(current); for (lsm = ordered_lsms; *lsm; lsm++) initialize_lsm(*lsm); @@ -465,17 +470,12 @@ static int lsm_cred_alloc(struct cred *cred, gfp_t gfp) * lsm_early_cred - during initialization allocate a composite cred blob * @cred: the cred that needs a blob * - * Allocate the cred blob for all the modules if it's not already there + * Allocate the cred blob for all the modules */ -void __init lsm_early_cred(struct cred *cred) +static void __init lsm_early_cred(struct cred *cred) { - int rc; + int rc = lsm_cred_alloc(cred, GFP_KERNEL); - if (cred == NULL) - panic("%s: NULL cred.\n", __func__); - if (cred->security != NULL) - return; - rc = lsm_cred_alloc(cred, GFP_KERNEL); if (rc) panic("%s: Early cred alloc failed.\n", __func__); } @@ -589,17 +589,12 @@ int lsm_msg_msg_alloc(struct msg_msg *mp) * lsm_early_task - during initialization allocate a composite task blob * @task: the task that needs a blob * - * Allocate the task blob for all the modules if it's not already there + * Allocate the task blob for all the modules */ -void __init lsm_early_task(struct task_struct *task) +static void __init lsm_early_task(struct task_struct *task) { - int rc; + int rc = lsm_task_alloc(task); - if (task == NULL) - panic("%s: task cred.\n", __func__); - if (task->security != NULL) - return; - rc = lsm_task_alloc(task); if (rc) panic("%s: Early task alloc failed.\n", __func__); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index b2ee49f938f1..5d92167dbe05 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -207,7 +207,6 @@ static void cred_init_security(void) struct cred *cred = (struct cred *) current->real_cred; struct task_security_struct *tsec; - lsm_early_cred(cred); tsec = selinux_cred(cred); tsec->osid = tsec->sid = SECINITSID_KERNEL; } diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 0b848b1f6366..79d6d2a6a0bc 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4671,8 +4671,6 @@ static __init int smack_init(void) if (!smack_inode_cache) return -ENOMEM; - lsm_early_cred(cred); - /* * Set the security state for the initial task. */ diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 066c0daf0efc..2b3eee06004b 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -566,7 +566,6 @@ static int __init tomoyo_init(void) /* register ourselves with the security framework */ security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), "tomoyo"); printk(KERN_INFO "TOMOYO Linux initialized\n"); - lsm_early_cred(cred); blob = tomoyo_cred(cred); *blob = &tomoyo_kernel_domain; tomoyo_mm_init(); -- cgit v1.2.3 From 7527a7b157d1191b23562ed70154ae93bd65f845 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 17 Jan 2019 20:14:15 +0200 Subject: IB/core: Simplify rdma cgroup registration RDMA cgroup registration routine always returns success, so simplify function to be void and run clang formatter over whole CONFIG_CGROUP_RDMA art of core_priv.h. This reduces unwinding error path for regular registration and future net namespace change functionality for rdma device. Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Acked-by: Tejun Heo Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cgroup.c | 5 ++--- drivers/infiniband/core/core_priv.h | 17 +++++++++++------ drivers/infiniband/core/device.c | 8 +------- include/linux/cgroup_rdma.h | 2 +- kernel/cgroup/rdma.c | 5 +---- 5 files changed, 16 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/cgroup.c b/drivers/infiniband/core/cgroup.c index 126ac5f99db7..388fd04e5f63 100644 --- a/drivers/infiniband/core/cgroup.c +++ b/drivers/infiniband/core/cgroup.c @@ -21,12 +21,11 @@ * Register with the rdma cgroup. Should be called before * exposing rdma device to user space applications to avoid * resource accounting leak. - * Returns 0 on success or otherwise failure code. */ -int ib_device_register_rdmacg(struct ib_device *device) +void ib_device_register_rdmacg(struct ib_device *device) { device->cg_device.name = device->name; - return rdmacg_register_device(&device->cg_device); + rdmacg_register_device(&device->cg_device); } /** diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index aca75c74e451..42a49982f66e 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -115,7 +115,7 @@ void ib_cache_cleanup_one(struct ib_device *device); void ib_cache_release_one(struct ib_device *device); #ifdef CONFIG_CGROUP_RDMA -int ib_device_register_rdmacg(struct ib_device *device); +void ib_device_register_rdmacg(struct ib_device *device); void ib_device_unregister_rdmacg(struct ib_device *device); int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj, @@ -126,21 +126,26 @@ void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index); #else -static inline int ib_device_register_rdmacg(struct ib_device *device) -{ return 0; } +static inline void ib_device_register_rdmacg(struct ib_device *device) +{ +} static inline void ib_device_unregister_rdmacg(struct ib_device *device) -{ } +{ +} static inline int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index) -{ return 0; } +{ + return 0; +} static inline void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index) -{ } +{ +} #endif static inline bool rdma_is_upper_dev_rcu(struct net_device *dev, diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 4a9aa6d10c5e..200431c540f2 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -599,12 +599,7 @@ int ib_register_device(struct ib_device *device, const char *name) device->index = __dev_new_index(); - ret = ib_device_register_rdmacg(device); - if (ret) { - dev_warn(&device->dev, - "Couldn't register device with rdma cgroup\n"); - goto dev_cleanup; - } + ib_device_register_rdmacg(device); ret = ib_device_register_sysfs(device); if (ret) { @@ -627,7 +622,6 @@ int ib_register_device(struct ib_device *device, const char *name) cg_cleanup: ib_device_unregister_rdmacg(device); -dev_cleanup: cleanup_device(device); out: mutex_unlock(&device_mutex); diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h index e94290b29e99..ef1bae2983f3 100644 --- a/include/linux/cgroup_rdma.h +++ b/include/linux/cgroup_rdma.h @@ -39,7 +39,7 @@ struct rdmacg_device { * APIs for RDMA/IB stack to publish when a device wants to * participate in resource accounting */ -int rdmacg_register_device(struct rdmacg_device *device); +void rdmacg_register_device(struct rdmacg_device *device); void rdmacg_unregister_device(struct rdmacg_device *device); /* APIs for RDMA/IB stack to charge/uncharge pool specific resources */ diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c index d3bbb757ee49..1d75ae7f1cb7 100644 --- a/kernel/cgroup/rdma.c +++ b/kernel/cgroup/rdma.c @@ -313,10 +313,8 @@ EXPORT_SYMBOL(rdmacg_try_charge); * If IB stack wish a device to participate in rdma cgroup resource * tracking, it must invoke this API to register with rdma cgroup before * any user space application can start using the RDMA resources. - * Returns 0 on success or EINVAL when table length given is beyond - * supported size. */ -int rdmacg_register_device(struct rdmacg_device *device) +void rdmacg_register_device(struct rdmacg_device *device) { INIT_LIST_HEAD(&device->dev_node); INIT_LIST_HEAD(&device->rpools); @@ -324,7 +322,6 @@ int rdmacg_register_device(struct rdmacg_device *device) mutex_lock(&rdmacg_mutex); list_add_tail(&device->dev_node, &rdmacg_devices); mutex_unlock(&rdmacg_mutex); - return 0; } EXPORT_SYMBOL(rdmacg_register_device); -- cgit v1.2.3 From e302c2a5fe0ca63b8fcc93389917625f486e0670 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 16 Jan 2019 19:47:57 +0100 Subject: net: phy: remove state PHY_CHANGELINK Since recent changes to the phylib state machine state PHY_CHANGELINK isn't used any longer. Therefore let's remove it. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 2 -- include/linux/phy.h | 6 ------ 2 files changed, 8 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 241fb83ef4de..b0632e859564 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -47,7 +47,6 @@ static const char *phy_state_to_str(enum phy_state st) PHY_STATE_STR(RUNNING) PHY_STATE_STR(NOLINK) PHY_STATE_STR(FORCING) - PHY_STATE_STR(CHANGELINK) PHY_STATE_STR(HALTED) PHY_STATE_STR(RESUMING) } @@ -939,7 +938,6 @@ void phy_state_machine(struct work_struct *work) break; case PHY_NOLINK: case PHY_RUNNING: - case PHY_CHANGELINK: case PHY_RESUMING: err = phy_check_link_status(phydev); break; diff --git a/include/linux/phy.h b/include/linux/phy.h index f1c19bf8c658..232d93b9cea4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -304,11 +304,6 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * - irq or timer will set NOLINK if link goes down * - phy_stop moves to HALTED * - * CHANGELINK: PHY experienced a change in link state - * - timer moves to RUNNING if link - * - timer moves to NOLINK if the link is down - * - phy_stop moves to HALTED - * * HALTED: PHY is up, but no polling or interrupts are done. Or * PHY is in an error state. * @@ -327,7 +322,6 @@ enum phy_state { PHY_RUNNING, PHY_NOLINK, PHY_FORCING, - PHY_CHANGELINK, PHY_RESUMING }; -- cgit v1.2.3 From 340a6f3d2d52a1b72f3454818e53293807f8f127 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Thu, 17 Jan 2019 18:03:14 +0800 Subject: tcp: declare tcp_mmap() only when CONFIG_MMU is set Since tcp_mmap() is defined when CONFIG_MMU is set. Signed-off-by: Yafang Shao Signed-off-by: David S. Miller --- include/net/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index e0a65c067662..5c950180d61b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -406,8 +406,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); void tcp_data_ready(struct sock *sk); +#ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); +#endif void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); -- cgit v1.2.3 From bb658ab7b8f2828b35c207a95cb0c05965721022 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 17 Jan 2019 20:09:21 +0100 Subject: net: phy: remove phy_stop_interrupts Interrupts have been disabled in phy_stop() already. So we can remove phy_stop_interrupts() and free the interrupt in phy_disconnect() directly. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 17 ----------------- drivers/net/phy/phy_device.c | 4 ++-- include/linux/phy.h | 1 - 3 files changed, 2 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 37cf39fdcc91..f7a92e7edff7 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -818,23 +818,6 @@ int phy_start_interrupts(struct phy_device *phydev) } EXPORT_SYMBOL(phy_start_interrupts); -/** - * phy_stop_interrupts - disable interrupts from a PHY device - * @phydev: target phy_device struct - */ -int phy_stop_interrupts(struct phy_device *phydev) -{ - int err = phy_disable_interrupts(phydev); - - if (err) - phy_error(phydev); - - free_irq(phydev->irq, phydev); - - return err; -} -EXPORT_SYMBOL(phy_stop_interrupts); - /** * phy_stop - Bring down the PHY link, and stop checking the status * @phydev: target phy_device struct diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index e269a355012d..7b3164174251 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1002,8 +1002,8 @@ void phy_disconnect(struct phy_device *phydev) if (phy_is_started(phydev)) phy_stop(phydev); - if (phydev->irq > 0) - phy_stop_interrupts(phydev); + if (phy_interrupt_is_valid(phydev)) + free_irq(phydev->irq, phydev); phydev->adjust_link = NULL; diff --git a/include/linux/phy.h b/include/linux/phy.h index 232d93b9cea4..0990f913d649 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -951,7 +951,6 @@ int phy_aneg_done(struct phy_device *phydev); int phy_speed_down(struct phy_device *phydev, bool sync); int phy_speed_up(struct phy_device *phydev); -int phy_stop_interrupts(struct phy_device *phydev); int phy_restart_aneg(struct phy_device *phydev); int phy_reset_after_clk_enable(struct phy_device *phydev); -- cgit v1.2.3 From f88c19aab5f34835f1ba467c5b508ec4f782f07f Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 17 Jan 2019 12:44:25 -0800 Subject: net_sched: add hit counter for matchall Although matchall always matches packets, however, it still relies on a protocol match first. So it is still useful to have such a counter for matchall. Of course, unlike u32, every time we hit a matchall filter, it is always a success, so we don't have to distinguish them. Sample output: filter protocol 802.1Q pref 100 matchall chain 0 filter protocol 802.1Q pref 100 matchall chain 0 handle 0x1 not_in_hw (rule hit 10) action order 1: vlan pop continue index 1 ref 1 bind 1 installed 40 sec used 1 sec Action statistics: Sent 836 bytes 10 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Reported-by: Martin Olsson Cc: Jamal Hadi Salim Cc: Jiri Pirko Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 6 ++++++ net/sched/cls_matchall.c | 24 ++++++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 95d0db2a8350..32a3416b51c3 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -527,11 +527,17 @@ enum { /* Match-all classifier */ +struct tc_matchall_pcnt { + __u64 rhit; +}; + enum { TCA_MATCHALL_UNSPEC, TCA_MATCHALL_CLASSID, TCA_MATCHALL_ACT, TCA_MATCHALL_FLAGS, + TCA_MATCHALL_PCNT, + TCA_MATCHALL_PAD, __TCA_MATCHALL_MAX, }; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 0e408ee9dcec..a1b803fd372e 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -22,6 +23,7 @@ struct cls_mall_head { u32 handle; u32 flags; unsigned int in_hw_count; + struct tc_matchall_pcnt __percpu *pf; struct rcu_work rwork; }; @@ -34,6 +36,7 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; *res = head->res; + __this_cpu_inc(head->pf->rhit); return tcf_exts_exec(skb, &head->exts, res); } @@ -46,6 +49,7 @@ static void __mall_destroy(struct cls_mall_head *head) { tcf_exts_destroy(&head->exts); tcf_exts_put_net(&head->exts); + free_percpu(head->pf); kfree(head); } @@ -192,6 +196,11 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, handle = 1; new->handle = handle; new->flags = flags; + new->pf = alloc_percpu(struct tc_matchall_pcnt); + if (!new->pf) { + err = -ENOMEM; + goto err_alloc_percpu; + } err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr, extack); @@ -214,6 +223,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, err_replace_hw_filter: err_set_parms: + free_percpu(new->pf); +err_alloc_percpu: tcf_exts_destroy(&new->exts); err_exts_init: kfree(new); @@ -270,8 +281,10 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { + struct tc_matchall_pcnt gpf = {}; struct cls_mall_head *head = fh; struct nlattr *nest; + int cpu; if (!head) return skb->len; @@ -289,6 +302,17 @@ static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, if (head->flags && nla_put_u32(skb, TCA_MATCHALL_FLAGS, head->flags)) goto nla_put_failure; + for_each_possible_cpu(cpu) { + struct tc_matchall_pcnt *pf = per_cpu_ptr(head->pf, cpu); + + gpf.rhit += pf->rhit; + } + + if (nla_put_64bit(skb, TCA_MATCHALL_PCNT, + sizeof(struct tc_matchall_pcnt), + &gpf, TCA_MATCHALL_PAD)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &head->exts)) goto nla_put_failure; -- cgit v1.2.3 From cb5ccfbe73b389470e1dc11061bb185ef4bc9aec Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 17 Jan 2019 23:59:10 +0200 Subject: devlink: Add health buffer support Devlink health buffer is a mechanism to pass descriptors between drivers and devlink. The API allows the driver to add objects, object pair, value array (nested attributes), value and name. Driver can use this API to fill the buffers in a format which can be translated by the devlink to the netlink message. In order to fulfill it, an internal buffer descriptor is defined. This will hold the data and metadata per each attribute and by used to pass actual commands to the netlink. This mechanism will be later used in devlink health for dump and diagnose data store by the drivers. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/net/devlink.h | 76 +++++++ include/uapi/linux/devlink.h | 8 + net/core/devlink.c | 501 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 585 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 67f4293bc970..77c77319290a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -423,6 +423,8 @@ struct devlink_region; typedef void devlink_snapshot_data_dest_t(const void *data); +struct devlink_health_buffer; + struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -584,6 +586,22 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); +int devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, + int attrtype); +void devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer); +void devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer); +int devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, + char *name); +int devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, + u8 value); +int devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, + u32 value); +int devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, + u64 value); +int devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, + char *name); +int devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, + void *data, int len); #else static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, @@ -844,6 +862,64 @@ devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, return 0; } +static inline int +devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, + int attrtype) +{ + return 0; +} + +static inline void +devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer) +{ +} + +static inline void +devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer) +{ +} + +static inline int +devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, + char *name) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, + u8 value) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, + u32 value) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, + u64 value) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, + char *name) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, + void *data, int len) +{ + return 0; +} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6e52d3660654..cff0e0cb5ac2 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -285,6 +285,14 @@ enum devlink_attr { DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */ DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT, /* nested */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR, /* nested */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME, /* string */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE, /* nested */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY, /* nested */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, /* u8 */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, /* dynamic */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index abb0da9d7b4b..8984501edade 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3597,6 +3597,507 @@ out: return 0; } +#define DEVLINK_HEALTH_BUFFER_SIZE (4096 - GENL_HDRLEN) +#define DEVLINK_HEALTH_BUFFER_DATA_SIZE (DEVLINK_HEALTH_BUFFER_SIZE / 2) +#define DEVLINK_HEALTH_SIZE_TO_BUFFERS(size) DIV_ROUND_UP(size, DEVLINK_HEALTH_BUFFER_DATA_SIZE) +#define DEVLINK_HEALTH_BUFFER_MAX_CHUNK 1024 + +struct devlink_health_buffer { + void *data; + u64 offset; + u64 bytes_left; + u64 bytes_left_metadata; + u64 max_nested_depth; + u64 curr_nest; +}; + +struct devlink_health_buffer_desc { + int attrtype; + u16 len; + u8 nla_type; + u8 nest_end; + int value[0]; +}; + +static void +devlink_health_buffers_reset(struct devlink_health_buffer **buffers_list, + u64 num_of_buffers) +{ + u64 i; + + for (i = 0; i < num_of_buffers; i++) { + memset(buffers_list[i]->data, 0, DEVLINK_HEALTH_BUFFER_SIZE); + buffers_list[i]->offset = 0; + buffers_list[i]->bytes_left = DEVLINK_HEALTH_BUFFER_DATA_SIZE; + buffers_list[i]->bytes_left_metadata = + DEVLINK_HEALTH_BUFFER_DATA_SIZE; + buffers_list[i]->max_nested_depth = 0; + buffers_list[i]->curr_nest = 0; + } +} + +static void +devlink_health_buffers_destroy(struct devlink_health_buffer **buffers_list, + u64 size); + +static struct devlink_health_buffer ** +devlink_health_buffers_create(u64 size) +{ + struct devlink_health_buffer **buffers_list; + u64 num_of_buffers = DEVLINK_HEALTH_SIZE_TO_BUFFERS(size); + u64 i; + + buffers_list = kcalloc(num_of_buffers, + sizeof(struct devlink_health_buffer *), + GFP_KERNEL); + if (!buffers_list) + return NULL; + + for (i = 0; i < num_of_buffers; i++) { + struct devlink_health_buffer *buffer; + void *data; + + buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); + data = kzalloc(DEVLINK_HEALTH_BUFFER_SIZE, GFP_KERNEL); + if (!buffer || !data) { + kfree(buffer); + kfree(data); + goto buffers_cleanup; + } + buffers_list[i] = buffer; + buffer->data = data; + } + devlink_health_buffers_reset(buffers_list, num_of_buffers); + + return buffers_list; + +buffers_cleanup: + devlink_health_buffers_destroy(buffers_list, --i); + kfree(buffers_list); + return NULL; +} + +static void +devlink_health_buffers_destroy(struct devlink_health_buffer **buffers_list, + u64 num_of_buffers) +{ + u64 i; + + for (i = 0; i < num_of_buffers; i++) { + kfree(buffers_list[i]->data); + kfree(buffers_list[i]); + } +} + +void +devlink_health_buffer_offset_inc(struct devlink_health_buffer *buffer, + int len) +{ + buffer->offset += len; +} + +/* In order to store a nest, need two descriptors, for start and end */ +#define DEVLINK_HEALTH_BUFFER_NEST_SIZE (sizeof(struct devlink_health_buffer_desc) * 2) + +int devlink_health_buffer_verify_len(struct devlink_health_buffer *buffer, + int len, int metadata_len) +{ + if (len > DEVLINK_HEALTH_BUFFER_DATA_SIZE) + return -EINVAL; + + if (buffer->bytes_left < len || + buffer->bytes_left_metadata < metadata_len) + return -ENOMEM; + + return 0; +} + +static struct devlink_health_buffer_desc * +devlink_health_buffer_get_desc_from_offset(struct devlink_health_buffer *buffer) +{ + return buffer->data + buffer->offset; +} + +int +devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, + int attrtype) +{ + struct devlink_health_buffer_desc *desc; + int err; + + err = devlink_health_buffer_verify_len(buffer, 0, + DEVLINK_HEALTH_BUFFER_NEST_SIZE); + if (err) + return err; + + if (attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT && + attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR && + attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE && + attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY) + return -EINVAL; + + desc = devlink_health_buffer_get_desc_from_offset(buffer); + + desc->attrtype = attrtype; + buffer->bytes_left_metadata -= DEVLINK_HEALTH_BUFFER_NEST_SIZE; + devlink_health_buffer_offset_inc(buffer, sizeof(*desc)); + + buffer->curr_nest++; + buffer->max_nested_depth = max(buffer->max_nested_depth, + buffer->curr_nest); + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_nest_start); + +enum devlink_health_buffer_nest_end_cancel { + DEVLINK_HEALTH_BUFFER_NEST_END = 1, + DEVLINK_HEALTH_BUFFER_NEST_CANCEL, +}; + +static void +devlink_health_buffer_nest_end_cancel(struct devlink_health_buffer *buffer, + enum devlink_health_buffer_nest_end_cancel nest) +{ + struct devlink_health_buffer_desc *desc; + + WARN_ON(!buffer->curr_nest); + buffer->curr_nest--; + + desc = devlink_health_buffer_get_desc_from_offset(buffer); + desc->nest_end = nest; + devlink_health_buffer_offset_inc(buffer, sizeof(*desc)); +} + +void devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer) +{ + devlink_health_buffer_nest_end_cancel(buffer, + DEVLINK_HEALTH_BUFFER_NEST_END); +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_nest_end); + +void devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer) +{ + devlink_health_buffer_nest_end_cancel(buffer, + DEVLINK_HEALTH_BUFFER_NEST_CANCEL); +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_nest_cancel); + +int +devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, + char *name) +{ + struct devlink_health_buffer_desc *desc; + int err; + + err = devlink_health_buffer_verify_len(buffer, strlen(name) + 1, + sizeof(*desc)); + if (err) + return err; + + desc = devlink_health_buffer_get_desc_from_offset(buffer); + desc->attrtype = DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME; + desc->nla_type = NLA_NUL_STRING; + desc->len = strlen(name) + 1; + memcpy(&desc->value, name, desc->len); + devlink_health_buffer_offset_inc(buffer, sizeof(*desc) + desc->len); + + buffer->bytes_left_metadata -= sizeof(*desc); + buffer->bytes_left -= (strlen(name) + 1); + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_object_name); + +static int +devlink_health_buffer_put_value(struct devlink_health_buffer *buffer, + u8 nla_type, void *value, int len) +{ + struct devlink_health_buffer_desc *desc; + int err; + + err = devlink_health_buffer_verify_len(buffer, len, sizeof(*desc)); + if (err) + return err; + + desc = devlink_health_buffer_get_desc_from_offset(buffer); + desc->attrtype = DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA; + desc->nla_type = nla_type; + desc->len = len; + memcpy(&desc->value, value, len); + devlink_health_buffer_offset_inc(buffer, sizeof(*desc) + desc->len); + + buffer->bytes_left_metadata -= sizeof(*desc); + buffer->bytes_left -= len; + + return 0; +} + +int +devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, + u8 value) +{ + int err; + + err = devlink_health_buffer_put_value(buffer, NLA_U8, &value, + sizeof(value)); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_u8); + +int +devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, + u32 value) +{ + int err; + + err = devlink_health_buffer_put_value(buffer, NLA_U32, &value, + sizeof(value)); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_u32); + +int +devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, + u64 value) +{ + int err; + + err = devlink_health_buffer_put_value(buffer, NLA_U64, &value, + sizeof(value)); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_u64); + +int +devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, + char *name) +{ + int err; + + if (strlen(name) + 1 > DEVLINK_HEALTH_BUFFER_MAX_CHUNK) + return -EINVAL; + + err = devlink_health_buffer_put_value(buffer, NLA_NUL_STRING, name, + strlen(name) + 1); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_string); + +int +devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, + void *data, int len) +{ + int err; + + if (len > DEVLINK_HEALTH_BUFFER_MAX_CHUNK) + return -EINVAL; + + err = devlink_health_buffer_put_value(buffer, NLA_BINARY, data, len); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_data); + +static int +devlink_health_buffer_fill_data(struct sk_buff *skb, + struct devlink_health_buffer_desc *desc) +{ + int err = -EINVAL; + + switch (desc->nla_type) { + case NLA_U8: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + *(u8 *)desc->value); + break; + case NLA_U32: + err = nla_put_u32(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + *(u32 *)desc->value); + break; + case NLA_U64: + err = nla_put_u64_64bit(skb, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + *(u64 *)desc->value, DEVLINK_ATTR_PAD); + break; + case NLA_NUL_STRING: + err = nla_put_string(skb, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + (char *)&desc->value); + break; + case NLA_BINARY: + err = nla_put(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + desc->len, (void *)&desc->value); + break; + } + + return err; +} + +static int +devlink_health_buffer_fill_type(struct sk_buff *skb, + struct devlink_health_buffer_desc *desc) +{ + int err = -EINVAL; + + switch (desc->nla_type) { + case NLA_U8: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_U8); + break; + case NLA_U32: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_U32); + break; + case NLA_U64: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_U64); + break; + case NLA_NUL_STRING: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_NUL_STRING); + break; + case NLA_BINARY: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_BINARY); + break; + } + + return err; +} + +static inline struct devlink_health_buffer_desc * +devlink_health_buffer_get_next_desc(struct devlink_health_buffer_desc *desc) +{ + return (void *)&desc->value + desc->len; +} + +static int +devlink_health_buffer_prepare_skb(struct sk_buff *skb, + struct devlink_health_buffer *buffer) +{ + struct devlink_health_buffer_desc *last_desc, *desc; + struct nlattr **buffer_nlattr; + int err; + int i = 0; + + buffer_nlattr = kcalloc(buffer->max_nested_depth, + sizeof(*buffer_nlattr), GFP_KERNEL); + if (!buffer_nlattr) + return -EINVAL; + + last_desc = devlink_health_buffer_get_desc_from_offset(buffer); + desc = buffer->data; + while (desc != last_desc) { + switch (desc->attrtype) { + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT: + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR: + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE: + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY: + buffer_nlattr[i] = nla_nest_start(skb, desc->attrtype); + if (!buffer_nlattr[i]) + goto nla_put_failure; + i++; + break; + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA: + err = devlink_health_buffer_fill_data(skb, desc); + if (err) + goto nla_put_failure; + err = devlink_health_buffer_fill_type(skb, desc); + if (err) + goto nla_put_failure; + break; + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME: + err = nla_put_string(skb, desc->attrtype, + (char *)&desc->value); + if (err) + goto nla_put_failure; + break; + default: + WARN_ON(!desc->nest_end); + WARN_ON(i <= 0); + if (desc->nest_end == DEVLINK_HEALTH_BUFFER_NEST_END) + nla_nest_end(skb, buffer_nlattr[--i]); + else + nla_nest_cancel(skb, buffer_nlattr[--i]); + break; + } + desc = devlink_health_buffer_get_next_desc(desc); + } + + return 0; + +nla_put_failure: + kfree(buffer_nlattr); + return err; +} + +static int +devlink_health_buffer_snd(struct genl_info *info, + enum devlink_command cmd, int flags, + struct devlink_health_buffer **buffers_array, + u64 num_of_buffers) +{ + struct sk_buff *skb; + struct nlmsghdr *nlh; + void *hdr; + int err; + u64 i; + + for (i = 0; i < num_of_buffers; i++) { + /* Skip buffer if driver did not fill it up with any data */ + if (!buffers_array[i]->offset) + continue; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, NLM_F_MULTI, cmd); + if (!hdr) + goto nla_put_failure; + + err = devlink_health_buffer_prepare_skb(skb, buffers_array[i]); + if (err) + goto nla_put_failure; + + genlmsg_end(skb, hdr); + err = genlmsg_reply(skb, info); + if (err) + return err; + } + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + err = genlmsg_reply(skb, info); + if (err) + return err; + + return 0; + +nla_put_failure: + err = -EIO; + nlmsg_free(skb); + return err; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, -- cgit v1.2.3 From 880ee82f0313453ec5a6cb122866ac057263066b Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 17 Jan 2019 23:59:11 +0200 Subject: devlink: Add health reporter create/destroy functionality Devlink health reporter is an instance for reporting, diagnosing and recovering from run time errors discovered by the reporters. Define it's data structure and supported operations. In addition, expose devlink API to create and destroy a reporter. Each devlink instance will hold it's own reporters list. As part of the allocation, driver shall provide a set of callbacks which will be used the devlink in order to handle health reports and user commands related to this reporter. In addition, driver is entitled to provide some priv pointer, which can be fetched from the reporter by devlink_health_reporter_priv function. For each reporter, devlink will hold a metadata of statistics, buffers and status. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/net/devlink.h | 59 +++++++++++++++++++++++ net/core/devlink.c | 127 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 186 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 77c77319290a..7fe30d67678a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -30,6 +30,7 @@ struct devlink { struct list_head param_list; struct list_head region_list; u32 snapshot_id; + struct list_head reporter_list; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; @@ -424,6 +425,34 @@ struct devlink_region; typedef void devlink_snapshot_data_dest_t(const void *data); struct devlink_health_buffer; +struct devlink_health_reporter; + +/** + * struct devlink_health_reporter_ops - Reporter operations + * @name: reporter name + * dump_size: dump buffer size allocated by the devlink + * diagnose_size: diagnose buffer size allocated by the devlink + * recover: callback to recover from reported error + * if priv_ctx is NULL, run a full recover + * dump: callback to dump an object + * if priv_ctx is NULL, run a full dump + * diagnose: callback to diagnose the current status + */ + +struct devlink_health_reporter_ops { + char *name; + unsigned int dump_size; + unsigned int diagnose_size; + int (*recover)(struct devlink_health_reporter *reporter, + void *priv_ctx); + int (*dump)(struct devlink_health_reporter *reporter, + struct devlink_health_buffer **buffers_array, + unsigned int buffer_size, unsigned int num_buffers, + void *priv_ctx); + int (*diagnose)(struct devlink_health_reporter *reporter, + struct devlink_health_buffer **buffers_array, + unsigned int buffer_size, unsigned int num_buffers); +}; struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); @@ -602,6 +631,16 @@ int devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, char *name); int devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, void *data, int len); +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv); +void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter); + +void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter); #else static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, @@ -920,6 +959,26 @@ devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, { return 0; } + +static inline struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv) +{ + return NULL; +} + +static inline void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ +} + +static inline void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter) +{ + return NULL; +} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 8984501edade..fec169a28dba 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4098,6 +4098,132 @@ nla_put_failure: return err; } +struct devlink_health_reporter { + struct list_head list; + struct devlink_health_buffer **dump_buffers_array; + struct mutex dump_lock; /* lock parallel read/write from dump buffers */ + struct devlink_health_buffer **diagnose_buffers_array; + struct mutex diagnose_lock; /* lock parallel read/write from diagnose buffers */ + void *priv; + const struct devlink_health_reporter_ops *ops; + struct devlink *devlink; + u64 graceful_period; + bool auto_recover; + u8 health_state; +}; + +void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter) +{ + return reporter->priv; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); + +static struct devlink_health_reporter * +devlink_health_reporter_find_by_name(struct devlink *devlink, + const char *reporter_name) +{ + struct devlink_health_reporter *reporter; + + list_for_each_entry(reporter, &devlink->reporter_list, list) + if (!strcmp(reporter->ops->name, reporter_name)) + return reporter; + return NULL; +} + +/** + * devlink_health_reporter_create - create devlink health reporter + * + * @devlink: devlink + * @ops: ops + * @graceful_period: to avoid recovery loops, in msecs + * @auto_recover: auto recover when error occurs + * @priv: priv + */ +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv) +{ + struct devlink_health_reporter *reporter; + + mutex_lock(&devlink->lock); + if (devlink_health_reporter_find_by_name(devlink, ops->name)) { + reporter = ERR_PTR(-EEXIST); + goto unlock; + } + + if (WARN_ON(ops->dump && !ops->dump_size) || + WARN_ON(ops->diagnose && !ops->diagnose_size) || + WARN_ON(auto_recover && !ops->recover) || + WARN_ON(graceful_period && !ops->recover)) { + reporter = ERR_PTR(-EINVAL); + goto unlock; + } + + reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); + if (!reporter) { + reporter = ERR_PTR(-ENOMEM); + goto unlock; + } + + if (ops->dump) { + reporter->dump_buffers_array = + devlink_health_buffers_create(ops->dump_size); + if (!reporter->dump_buffers_array) { + kfree(reporter); + reporter = ERR_PTR(-ENOMEM); + goto unlock; + } + } + + if (ops->diagnose) { + reporter->diagnose_buffers_array = + devlink_health_buffers_create(ops->diagnose_size); + if (!reporter->diagnose_buffers_array) { + devlink_health_buffers_destroy(reporter->dump_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(ops->dump_size)); + kfree(reporter); + reporter = ERR_PTR(-ENOMEM); + goto unlock; + } + } + + list_add_tail(&reporter->list, &devlink->reporter_list); + mutex_init(&reporter->dump_lock); + mutex_init(&reporter->diagnose_lock); + + reporter->priv = priv; + reporter->ops = ops; + reporter->devlink = devlink; + reporter->graceful_period = graceful_period; + reporter->auto_recover = auto_recover; +unlock: + mutex_unlock(&devlink->lock); + return reporter; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_create); + +/** + * devlink_health_reporter_destroy - destroy devlink health reporter + * + * @reporter: devlink health reporter to destroy + */ +void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ + mutex_lock(&reporter->devlink->lock); + list_del(&reporter->list); + devlink_health_buffers_destroy(reporter->dump_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size)); + devlink_health_buffers_destroy(reporter->diagnose_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->diagnose_size)); + kfree(reporter); + mutex_unlock(&reporter->devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -4383,6 +4509,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD(&devlink->resource_list); INIT_LIST_HEAD(&devlink->param_list); INIT_LIST_HEAD(&devlink->region_list); + INIT_LIST_HEAD(&devlink->reporter_list); mutex_init(&devlink->lock); return devlink; } -- cgit v1.2.3 From c7af343b4e33578b7de91786a3f639c8cfa0d97b Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 17 Jan 2019 23:59:12 +0200 Subject: devlink: Add health report functionality Upon error discover, every driver can report it to the devlink health mechanism via devlink_health_report function, using the appropriate reporter registered to it. Driver can pass error specific context which will be delivered to it as part of the dump / recovery callbacks. Once an error is reported, devlink health will do the following actions: * A log is being send to the kernel trace events buffer * Health status and statistics are being updated for the reporter instance * Object dump is being taken and stored at the reporter instance (as long as there is no other dump which is already stored) * Auto recovery attempt is being done. depends on: - Auto Recovery configuration - Grace period vs. time since last recover Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/net/devlink.h | 9 ++++ include/trace/events/devlink.h | 62 ++++++++++++++++++++++++++++ net/core/devlink.c | 93 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 164 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7fe30d67678a..a81a1b7a67d7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -641,6 +641,8 @@ devlink_health_reporter_destroy(struct devlink_health_reporter *reporter); void * devlink_health_reporter_priv(struct devlink_health_reporter *reporter); +int devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx); #else static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, @@ -979,6 +981,13 @@ devlink_health_reporter_priv(struct devlink_health_reporter *reporter) { return NULL; } + +static inline int +devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + return 0; +} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 44acfbca1266..7e39d2fc7c75 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -46,6 +46,65 @@ TRACE_EVENT(devlink_hwmsg, (int) __entry->len, __get_dynamic_array(buf), __entry->len) ); +TRACE_EVENT(devlink_health_report, + TP_PROTO(const struct devlink *devlink, const char *reporter_name, + const char *msg), + + TP_ARGS(devlink, reporter_name, msg), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(driver_name, devlink->dev->driver->name) + __string(reporter_name, msg) + __string(msg, msg) + ), + + TP_fast_assign( + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(reporter_name, reporter_name); + __assign_str(msg, msg); + ), + + TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s", + __get_str(bus_name), __get_str(dev_name), + __get_str(driver_name), __get_str(reporter_name), + __get_str(msg)) +); + +TRACE_EVENT(devlink_health_recover_aborted, + TP_PROTO(const struct devlink *devlink, const char *reporter_name, + bool health_state, u64 time_since_last_recover), + + TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(driver_name, devlink->dev->driver->name) + __string(reporter_name, reporter_name) + __field(bool, health_state) + __field(u64, time_since_last_recover) + ), + + TP_fast_assign( + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(reporter_name, reporter_name); + __entry->health_state = health_state; + __entry->time_since_last_recover = time_since_last_recover; + ), + + TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover = %llu recover aborted", + __get_str(bus_name), __get_str(dev_name), + __get_str(driver_name), __get_str(reporter_name), + __entry->health_state, + __entry->time_since_last_recover) +); + #endif /* _TRACE_DEVLINK_H */ /* This part must be outside protection */ @@ -64,6 +123,9 @@ static inline void trace_devlink_hwmsg(const struct devlink *devlink, { } +static inline void trace_devlink_health(const char *msg) +{ +} #endif /* _TRACE_DEVLINK_H */ #endif diff --git a/net/core/devlink.c b/net/core/devlink.c index fec169a28dba..943d3e7dea6a 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4110,6 +4110,16 @@ struct devlink_health_reporter { u64 graceful_period; bool auto_recover; u8 health_state; + u8 dump_avail; + u64 dump_ts; + u64 error_count; + u64 recovery_count; + u64 last_recovery_ts; +}; + +enum devlink_health_reporter_state { + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY, + DEVLINK_HEALTH_REPORTER_STATE_ERROR, }; void * @@ -4224,6 +4234,89 @@ devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) } EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); +static int +devlink_health_reporter_recover(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + int err; + + if (!reporter->ops->recover) + return -EOPNOTSUPP; + + err = reporter->ops->recover(reporter, priv_ctx); + if (err) + return err; + + reporter->recovery_count++; + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; + reporter->last_recovery_ts = jiffies; + + return 0; +} + +static int devlink_health_do_dump(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + int err; + + if (!reporter->ops->dump) + return 0; + + if (reporter->dump_avail) + return 0; + + devlink_health_buffers_reset(reporter->dump_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size)); + err = reporter->ops->dump(reporter, reporter->dump_buffers_array, + DEVLINK_HEALTH_BUFFER_SIZE, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size), + priv_ctx); + if (!err) { + reporter->dump_avail = true; + reporter->dump_ts = jiffies; + } + + return err; +} + +int devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + struct devlink *devlink = reporter->devlink; + int err = 0; + + /* write a log message of the current error */ + WARN_ON(!msg); + trace_devlink_health_report(devlink, reporter->ops->name, msg); + reporter->error_count++; + + /* abort if the previous error wasn't recovered */ + if (reporter->auto_recover && + (reporter->health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || + jiffies - reporter->last_recovery_ts < + msecs_to_jiffies(reporter->graceful_period))) { + trace_devlink_health_recover_aborted(devlink, + reporter->ops->name, + reporter->health_state, + jiffies - + reporter->last_recovery_ts); + return -ECANCELED; + } + + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; + + mutex_lock(&reporter->dump_lock); + /* store current dump of current error, for later analysis */ + devlink_health_do_dump(reporter, priv_ctx); + mutex_unlock(&reporter->dump_lock); + + if (reporter->auto_recover) + err = devlink_health_reporter_recover(reporter, priv_ctx); + + return err; +} +EXPORT_SYMBOL_GPL(devlink_health_report); + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, -- cgit v1.2.3 From ff253fedab961b22117a73ab808fcfa9e6852b50 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 17 Jan 2019 23:59:13 +0200 Subject: devlink: Add health get command Add devlink health get command to provide reporter/s data for user space. Add the ability to get data per reporter or dump data from all available reporters. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 12 ++++ net/core/devlink.c | 152 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 164 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cff0e0cb5ac2..c05470578b99 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -89,6 +89,8 @@ enum devlink_command { DEVLINK_CMD_REGION_DEL, DEVLINK_CMD_REGION_READ, + DEVLINK_CMD_HEALTH_REPORTER_GET, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -293,6 +295,16 @@ enum devlink_attr { DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, /* u8 */ DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, /* dynamic */ + DEVLINK_ATTR_HEALTH_REPORTER, /* nested */ + DEVLINK_ATTR_HEALTH_REPORTER_NAME, /* string */ + DEVLINK_ATTR_HEALTH_REPORTER_STATE, /* u8 */ + DEVLINK_ATTR_HEALTH_REPORTER_ERR, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL, /* u8 */ + DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, /* u8 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 943d3e7dea6a..2ba9275449c2 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4317,6 +4317,149 @@ int devlink_health_report(struct devlink_health_reporter *reporter, } EXPORT_SYMBOL_GPL(devlink_health_report); +static struct devlink_health_reporter * +devlink_health_reporter_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + char *reporter_name; + + if (!info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]) + return NULL; + + reporter_name = + nla_data(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); + return devlink_health_reporter_find_by_name(devlink, reporter_name); +} + +static int +devlink_nl_health_reporter_fill(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_health_reporter *reporter, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + struct nlattr *reporter_attr; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + reporter_attr = nla_nest_start(msg, DEVLINK_ATTR_HEALTH_REPORTER); + if (!reporter_attr) + goto genlmsg_cancel; + if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, + reporter->ops->name)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, + reporter->health_state)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR, + reporter->error_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, + reporter->recovery_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, + reporter->graceful_period, + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, + reporter->auto_recover)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL, + reporter->dump_avail)) + goto reporter_nest_cancel; + if (reporter->dump_avail && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, + jiffies_to_msecs(reporter->dump_ts), + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + + nla_nest_end(msg, reporter_attr); + genlmsg_end(msg, hdr); + return 0; + +reporter_nest_cancel: + nla_nest_end(msg, reporter_attr); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + struct sk_buff *msg; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_health_reporter_fill(msg, devlink, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + info->snd_portid, info->snd_seq, + 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_health_reporter *reporter; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(reporter, &devlink->reporter_list, + list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_health_reporter_fill(msg, devlink, + reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -4342,6 +4485,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -4562,6 +4706,14 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, + .doit = devlink_nl_cmd_health_reporter_get_doit, + .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From 6f9d56132eb6d2603d4273cfc65bed914ec47acb Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 17 Jan 2019 23:59:14 +0200 Subject: devlink: Add health set command Add devlink health set command, in order to set configuration parameters for a specific reporter. Supported parameters are: - graceful_period: Time interval between auto recoveries (in msec) - auto_recover: Determines if the devlink shall execute recover upon receiving error for the reporter Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 1 + net/core/devlink.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index c05470578b99..49ad5a76b121 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -90,6 +90,7 @@ enum devlink_command { DEVLINK_CMD_REGION_READ, DEVLINK_CMD_HEALTH_REPORTER_GET, + DEVLINK_CMD_HEALTH_REPORTER_SET, /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 2ba9275449c2..a34414bf1c27 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4460,6 +4460,33 @@ out: return msg->len; } +static int +devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->recover && + (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) + return -EINVAL; + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) + reporter->graceful_period = + nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]); + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]) + reporter->auto_recover = + nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]); + + return 0; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -4486,6 +4513,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -4714,6 +4743,13 @@ static const struct genl_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, + .doit = devlink_nl_cmd_health_reporter_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From fcd852c69d776c0f46c8f79e8e431e5cc6ddc7b7 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 17 Jan 2019 23:59:15 +0200 Subject: devlink: Add health recover command Add devlink health recover command to the uapi, in order to allow the user to execute a recover operation over a specific reporter. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 1 + net/core/devlink.c | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 49ad5a76b121..1c186fd77343 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -91,6 +91,7 @@ enum devlink_command { DEVLINK_CMD_HEALTH_REPORTER_GET, DEVLINK_CMD_HEALTH_REPORTER_SET, + DEVLINK_CMD_HEALTH_REPORTER_RECOVER, /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index a34414bf1c27..b224d0d31c0c 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4487,6 +4487,19 @@ devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, return 0; } +static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + return devlink_health_reporter_recover(reporter, NULL); +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -4750,6 +4763,13 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + .doit = devlink_nl_cmd_health_reporter_recover_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From 8a66704a13d9713593342e29b4f0c19762f5746b Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 17 Jan 2019 23:59:16 +0200 Subject: devlink: Add health diagnose command Add devlink health diagnose command, in order to run a diagnose operation over a specific reporter. It is expected from driver's callback for diagnose command to fill it via the buffer descriptors API. Devlink will parse it and convert it to netlink nla API in order to pass it to the user. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 1 + net/core/devlink.c | 51 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 1c186fd77343..51b4d7612cf8 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -92,6 +92,7 @@ enum devlink_command { DEVLINK_CMD_HEALTH_REPORTER_GET, DEVLINK_CMD_HEALTH_REPORTER_SET, DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index b224d0d31c0c..57252ca31e1e 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4500,6 +4500,50 @@ static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, return devlink_health_reporter_recover(reporter, NULL); } +static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + u64 num_of_buffers; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->diagnose) + return -EOPNOTSUPP; + + num_of_buffers = + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->diagnose_size); + + mutex_lock(&reporter->diagnose_lock); + devlink_health_buffers_reset(reporter->diagnose_buffers_array, + num_of_buffers); + + err = reporter->ops->diagnose(reporter, + reporter->diagnose_buffers_array, + DEVLINK_HEALTH_BUFFER_SIZE, + num_of_buffers); + if (err) + goto out; + + err = devlink_health_buffer_snd(info, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + 0, reporter->diagnose_buffers_array, + num_of_buffers); + if (err) + goto out; + + mutex_unlock(&reporter->diagnose_lock); + return 0; + +out: + mutex_unlock(&reporter->diagnose_lock); + return err; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -4770,6 +4814,13 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + .doit = devlink_nl_cmd_health_reporter_diagnose_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From 12bd0dcefe88782ac1c9fff632958dd1b71d27e5 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 17 Jan 2019 23:59:17 +0200 Subject: devlink: Add health dump {get,clear} commands Add devlink health dump commands, in order to run an dump operation over a specific reporter. The supported operations are dump_get in order to get last saved dump (if not exist, dump now) and dump_clear to clear last saved dump. It is expected from driver's callback for diagnose command to fill it via the buffer descriptors API. Devlink will parse it and convert it to netlink nla API in order to pass it to the user. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 75 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 51b4d7612cf8..6b26bb2ce4dc 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -93,6 +93,8 @@ enum devlink_command { DEVLINK_CMD_HEALTH_REPORTER_SET, DEVLINK_CMD_HEALTH_REPORTER_RECOVER, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 57252ca31e1e..60248a53c0ad 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4544,6 +4544,65 @@ out: return err; } +static void +devlink_health_dump_clear(struct devlink_health_reporter *reporter) +{ + reporter->dump_avail = false; + reporter->dump_ts = 0; + devlink_health_buffers_reset(reporter->dump_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size)); +} + +static int devlink_nl_cmd_health_reporter_dump_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + u64 num_of_buffers; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->dump) + return -EOPNOTSUPP; + + num_of_buffers = + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size); + + mutex_lock(&reporter->dump_lock); + err = devlink_health_do_dump(reporter, NULL); + if (err) + goto out; + + err = devlink_health_buffer_snd(info, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + 0, reporter->dump_buffers_array, + num_of_buffers); + +out: + mutex_unlock(&reporter->dump_lock); + return err; +} + +static int +devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + mutex_lock(&reporter->dump_lock); + devlink_health_dump_clear(reporter); + mutex_unlock(&reporter->dump_lock); + return 0; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -4821,6 +4880,22 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + .doit = devlink_nl_cmd_health_reporter_dump_get_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + DEVLINK_NL_FLAG_NO_LOCK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, + .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + DEVLINK_NL_FLAG_NO_LOCK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From 1866760096bf40bcf6977a9076b3026598bc12ee Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 18 Dec 2018 17:02:06 -0800 Subject: mac80211: Add TXQ scheduling API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds an API to mac80211 to handle scheduling of TXQs. The interface between driver and mac80211 for TXQ handling is changed by adding two new functions: ieee80211_next_txq(), which will return the next TXQ to schedule in the current round-robin rotation, and ieee80211_return_txq(), which the driver uses to indicate that it has finished scheduling a TXQ (which will then be put back in the scheduling rotation if it isn't empty). The driver must call ieee80211_txq_schedule_start() at the start of each scheduling session, and ieee80211_txq_schedule_end() at the end. The API then guarantees that the same TXQ is not returned twice in the same session (so a driver can loop on ieee80211_next_txq() without worrying about breaking the loop. Usage of the new API is optional, so drivers can be ported one at a time. In this patch, the actual scheduling performed by mac80211 is simple round-robin, but a subsequent commit adds airtime fairness awareness to the scheduler. Signed-off-by: Toke Høiland-Jørgensen [minor kernel-doc fix, propagate sparse locking checks out] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 63 +++++++++++++++++++++++++++++++++++++++++++--- net/mac80211/agg-tx.c | 2 +- net/mac80211/driver-ops.h | 9 +++++++ net/mac80211/ieee80211_i.h | 9 +++++++ net/mac80211/main.c | 5 ++++ net/mac80211/sta_info.c | 2 +- net/mac80211/tx.c | 60 ++++++++++++++++++++++++++++++++++++++++++- 7 files changed, 143 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 88219cc137c3..e8a057f071c4 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -108,9 +108,15 @@ * The driver is expected to initialize its private per-queue data for stations * and interfaces in the .add_interface and .sta_add ops. * - * The driver can't access the queue directly. To dequeue a frame, it calls - * ieee80211_tx_dequeue(). Whenever mac80211 adds a new frame to a queue, it - * calls the .wake_tx_queue driver op. + * The driver can't access the queue directly. To dequeue a frame from a + * txq, it calls ieee80211_tx_dequeue(). Whenever mac80211 adds a new frame to a + * queue, it calls the .wake_tx_queue driver op. + * + * Drivers can optionally delegate responsibility for scheduling queues to + * mac80211, to take advantage of airtime fairness accounting. In this case, to + * obtain the next queue to pull frames from, the driver calls + * ieee80211_next_txq(). The driver is then expected to return the txq using + * ieee80211_return_txq(). * * For AP powersave TIM handling, the driver only needs to indicate if it has * buffered packets in the driver specific data structures by calling @@ -6103,7 +6109,8 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); * ieee80211_tx_dequeue - dequeue a packet from a software tx queue * * @hw: pointer as obtained from ieee80211_alloc_hw() - * @txq: pointer obtained from station or virtual interface + * @txq: pointer obtained from station or virtual interface, or from + * ieee80211_next_txq() * * Returns the skb if successful, %NULL if no frame was available. * @@ -6118,6 +6125,54 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *txq); +/** + * ieee80211_next_txq - get next tx queue to pull packets from + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @ac: AC number to return packets from. + * + * Should only be called between calls to ieee80211_txq_schedule_start() + * and ieee80211_txq_schedule_end(). + * Returns the next txq if successful, %NULL if no queue is eligible. If a txq + * is returned, it should be returned with ieee80211_return_txq() after the + * driver has finished scheduling it. + */ +struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac); + +/** + * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @txq: pointer obtained from station or virtual interface + * + * Should only be called between calls to ieee80211_txq_schedule_start() + * and ieee80211_txq_schedule_end(). + */ +void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); + +/** + * ieee80211_txq_schedule_start - acquire locks for safe scheduling of an AC + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @ac: AC number to acquire locks for + * + * Acquire locks needed to schedule TXQs from the given AC. Should be called + * before ieee80211_next_txq() or ieee80211_return_txq(). + */ +void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) + __acquires(txq_lock); + +/** + * ieee80211_txq_schedule_end - release locks for safe scheduling of an AC + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @ac: AC number to acquire locks for + * + * Release locks previously acquired by ieee80211_txq_schedule_end(). + */ +void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) + __releases(txq_lock); + /** * ieee80211_txq_get_depth - get pending frame/byte count of given txq * diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 69e831bc317b..e94b1a0407af 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -229,7 +229,7 @@ ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable) clear_bit(IEEE80211_TXQ_STOP, &txqi->flags); local_bh_disable(); rcu_read_lock(); - drv_wake_tx_queue(sta->sdata->local, txqi); + schedule_and_wake_txq(sta->sdata->local, txqi); rcu_read_unlock(); local_bh_enable(); } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 3e0d5922a440..1aab1734b26f 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1173,6 +1173,15 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, local->ops->wake_tx_queue(&local->hw, &txq->txq); } +static inline void schedule_and_wake_txq(struct ieee80211_local *local, + struct txq_info *txqi) +{ + spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]); + ieee80211_return_txq(&local->hw, &txqi->txq); + spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]); + drv_wake_tx_queue(local, txqi); +} + static inline int drv_can_aggregate_in_amsdu(struct ieee80211_local *local, struct sk_buff *head, struct sk_buff *skb) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 7dfb4e2f98b2..d1db27b1e989 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -831,6 +831,8 @@ enum txq_info_flags { * a fq_flow which is already owned by a different tin * @def_cvars: codel vars for @def_flow * @frags: used to keep fragments created after dequeue + * @schedule_order: used with ieee80211_local->active_txqs + * @schedule_round: counter to prevent infinite loops on TXQ scheduling */ struct txq_info { struct fq_tin tin; @@ -838,6 +840,8 @@ struct txq_info { struct codel_vars def_cvars; struct codel_stats cstats; struct sk_buff_head frags; + struct list_head schedule_order; + u16 schedule_round; unsigned long flags; /* keep last! */ @@ -1129,6 +1133,11 @@ struct ieee80211_local { struct codel_vars *cvars; struct codel_params cparams; + /* protects active_txqs and txqi->schedule_order */ + spinlock_t active_txq_lock[IEEE80211_NUM_ACS]; + struct list_head active_txqs[IEEE80211_NUM_ACS]; + u16 schedule_round[IEEE80211_NUM_ACS]; + const struct ieee80211_ops *ops; /* diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 87a729926734..9b9d6cadf56e 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -663,6 +663,11 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, spin_lock_init(&local->rx_path_lock); spin_lock_init(&local->queue_stop_reason_lock); + for (i = 0; i < IEEE80211_NUM_ACS; i++) { + INIT_LIST_HEAD(&local->active_txqs[i]); + spin_lock_init(&local->active_txq_lock[i]); + } + INIT_LIST_HEAD(&local->chanctx_list); mutex_init(&local->chanctx_mtx); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index c4a8f115ed33..83e1c316a29e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1249,7 +1249,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) if (!sta->sta.txq[i] || !txq_has_queue(sta->sta.txq[i])) continue; - drv_wake_tx_queue(local, to_txq_info(sta->sta.txq[i])); + schedule_and_wake_txq(local, to_txq_info(sta->sta.txq[i])); } skb_queue_head_init(&pending); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f170d6c6629a..544da6411620 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1449,6 +1449,7 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, codel_vars_init(&txqi->def_cvars); codel_stats_init(&txqi->cstats); __skb_queue_head_init(&txqi->frags); + INIT_LIST_HEAD(&txqi->schedule_order); txqi->txq.vif = &sdata->vif; @@ -1489,6 +1490,9 @@ void ieee80211_txq_purge(struct ieee80211_local *local, fq_tin_reset(fq, tin, fq_skb_free_func); ieee80211_purge_tx_queue(&local->hw, &txqi->frags); + spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]); + list_del_init(&txqi->schedule_order); + spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]); } void ieee80211_txq_set_params(struct ieee80211_local *local) @@ -1605,7 +1609,7 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, ieee80211_txq_enqueue(local, txqi, skb); spin_unlock_bh(&fq->lock); - drv_wake_tx_queue(local, txqi); + schedule_and_wake_txq(local, txqi); return true; } @@ -3630,6 +3634,60 @@ out: } EXPORT_SYMBOL(ieee80211_tx_dequeue); +struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = NULL; + + lockdep_assert_held(&local->active_txq_lock[ac]); + + txqi = list_first_entry_or_null(&local->active_txqs[ac], + struct txq_info, + schedule_order); + + if (!txqi || txqi->schedule_round == local->schedule_round[ac]) + return NULL; + + list_del_init(&txqi->schedule_order); + txqi->schedule_round = local->schedule_round[ac]; + return &txqi->txq; +} +EXPORT_SYMBOL(ieee80211_next_txq); + +void ieee80211_return_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + + lockdep_assert_held(&local->active_txq_lock[txq->ac]); + + if (list_empty(&txqi->schedule_order) && + (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) + list_add_tail(&txqi->schedule_order, + &local->active_txqs[txq->ac]); +} +EXPORT_SYMBOL(ieee80211_return_txq); + +void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) + __acquires(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_lock_bh(&local->active_txq_lock[ac]); + local->schedule_round[ac]++; +} +EXPORT_SYMBOL(ieee80211_txq_schedule_start); + +void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) + __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_unlock_bh(&local->active_txq_lock[ac]); +} +EXPORT_SYMBOL(ieee80211_txq_schedule_end); + void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags) -- cgit v1.2.3 From 36647055b37ec78e9068f470f14e7cd75c001c22 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 18 Dec 2018 17:02:07 -0800 Subject: cfg80211: Add airtime statistics and settings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds TX airtime statistics to the cfg80211 station dump (to go along with the RX info already present), and adds a new parameter to set the airtime weight of each station. The latter allows userspace to implement policies for different stations by varying their weights. Signed-off-by: Toke Høiland-Jørgensen [rmanohar@codeaurora.org: fixed checkpatch warnings] Signed-off-by: Rajkumar Manoharan [move airtime weight != 0 check into policy] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 11 ++++++++++- include/uapi/linux/nl80211.h | 15 +++++++++++++++ net/wireless/nl80211.c | 24 ++++++++++++++++++++++++ 3 files changed, 49 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e0c41eb1c860..1691f52fcc80 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1003,6 +1003,7 @@ enum station_parameters_apply_mask { * @support_p2p_ps: information if station supports P2P PS mechanism * @he_capa: HE capabilities of station * @he_capa_len: the length of the HE capabilities + * @airtime_weight: airtime scheduler weight for this station */ struct station_parameters { const u8 *supported_rates; @@ -1032,6 +1033,7 @@ struct station_parameters { int support_p2p_ps; const struct ieee80211_he_cap_elem *he_capa; u8 he_capa_len; + u16 airtime_weight; }; /** @@ -1300,6 +1302,8 @@ struct cfg80211_tid_stats { * from this peer * @connected_to_gate: true if mesh STA has a path to mesh gate * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer + * @tx_duration: aggregate PPDU duration(usecs) for all the frames to a peer + * @airtime_weight: current airtime scheduling weight * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last * (IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs. * Note that this doesn't use the @filled bit, but is used if non-NULL. @@ -1350,8 +1354,9 @@ struct station_info { u32 expected_throughput; - u64 rx_beacon; + u64 tx_duration; u64 rx_duration; + u64 rx_beacon; u8 rx_beacon_signal_avg; u8 connected_to_gate; @@ -1359,6 +1364,8 @@ struct station_info { s8 ack_signal; s8 avg_ack_signal; + u16 airtime_weight; + u32 rx_mpdu_count; u32 fcs_err_count; }; @@ -2391,6 +2398,8 @@ enum wiphy_params_flags { WIPHY_PARAM_TXQ_QUANTUM = 1 << 8, }; +#define IEEE80211_DEFAULT_AIRTIME_WEIGHT 256 + /** * struct cfg80211_pmksa - PMK Security Association * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 31ae5c7f10e3..ebe79e12c82e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2299,6 +2299,9 @@ enum nl80211_commands { * This is also used for capability advertisement in the wiphy information, * with the appropriate sub-attributes. * + * @NL80211_ATTR_AIRTIME_WEIGHT: Station's weight when scheduled by the airtime + * scheduler. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2748,6 +2751,8 @@ enum nl80211_attrs { NL80211_ATTR_PEER_MEASUREMENTS, + NL80211_ATTR_AIRTIME_WEIGHT, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3125,6 +3130,9 @@ enum nl80211_sta_bss_param { * might not be fully accurate. * @NL80211_STA_INFO_CONNECTED_TO_GATE: set to true if STA has a path to a * mesh gate (u8, 0 or 1) + * @NL80211_STA_INFO_TX_DURATION: aggregate PPDU duration for all frames + * sent to the station (u64, usec) + * @NL80211_STA_INFO_AIRTIME_WEIGHT: current airtime weight for station (u16) * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute */ @@ -3168,6 +3176,8 @@ enum nl80211_sta_info { NL80211_STA_INFO_RX_MPDUS, NL80211_STA_INFO_FCS_ERROR_COUNT, NL80211_STA_INFO_CONNECTED_TO_GATE, + NL80211_STA_INFO_TX_DURATION, + NL80211_STA_INFO_AIRTIME_WEIGHT, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, @@ -5316,6 +5326,10 @@ enum nl80211_feature_flags { * if this flag is not set. Ignoring this can leak clear text packets and/or * freeze the connection. * + * @NL80211_EXT_FEATURE_AIRTIME_FAIRNESS: Driver supports getting airtime + * fairness for transmitted packets and has enabled airtime fairness + * scheduling. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5355,6 +5369,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0, NL80211_EXT_FEATURE_ENABLE_FTM_RESPONDER, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5e49492d5911..a89688929b16 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -557,6 +557,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_PEER_MEASUREMENTS] = NLA_POLICY_NESTED(NL80211_PMSR_FTM_REQ_ATTR_MAX, nl80211_pmsr_attr_policy), + [NL80211_ATTR_AIRTIME_WEIGHT] = NLA_POLICY_MIN(NLA_U16, 1), }; /* policy for the key attributes */ @@ -4851,6 +4852,11 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO(PLID, plid, u16); PUT_SINFO(PLINK_STATE, plink_state, u8); PUT_SINFO_U64(RX_DURATION, rx_duration); + PUT_SINFO_U64(TX_DURATION, tx_duration); + + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + PUT_SINFO(AIRTIME_WEIGHT, airtime_weight, u16); switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: @@ -5470,6 +5476,15 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]); } + if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) + params.airtime_weight = + nla_get_u16(info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]); + + if (params.airtime_weight && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + return -EOPNOTSUPP; + /* Include parameters for TDLS peer (will check later) */ err = nl80211_set_station_tdls(info, ¶ms); if (err) @@ -5598,6 +5613,15 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.plink_action = nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]); + if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) + params.airtime_weight = + nla_get_u16(info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]); + + if (params.airtime_weight && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + return -EOPNOTSUPP; + err = nl80211_parse_sta_channel_info(info, ¶ms); if (err) return err; -- cgit v1.2.3 From b4809e9484da147dc82a31b961df111eee72201a Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 18 Dec 2018 17:02:08 -0800 Subject: mac80211: Add airtime accounting and scheduling to TXQs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds airtime accounting and scheduling to the mac80211 TXQ scheduler. A new callback, ieee80211_sta_register_airtime(), is added that drivers can call to report airtime usage for stations. When airtime information is present, mac80211 will schedule TXQs (through ieee80211_next_txq()) in a way that enforces airtime fairness between active stations. This scheduling works the same way as the ath9k in-driver airtime fairness scheduling. If no airtime usage is reported by the driver, the scheduler will default to round-robin scheduling. For drivers that don't control TXQ scheduling in software, a new API function, ieee80211_txq_may_transmit(), is added which the driver can use to check if the TXQ is eligible for transmission, or should be throttled to enforce fairness. Calls to this function must also be enclosed in ieee80211_txq_schedule_{start,end}() calls to ensure proper locking. The API ieee80211_txq_may_transmit() also ensures that TXQ list will be aligned aginst driver's own round-robin scheduler list. i.e it rotates the TXQ list till it makes the requested node becomes the first entry in TXQ list. Thus both the TXQ list and driver's list are in sync. Co-developed-by: Rajkumar Manoharan Signed-off-by: Louie Lu [added debugfs write op to reset airtime counter] Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Rajkumar Manoharan Signed-off-by: Johannes Berg --- include/net/mac80211.h | 59 ++++++++++++++++++++++++++++++ net/mac80211/cfg.c | 3 ++ net/mac80211/debugfs.c | 3 ++ net/mac80211/debugfs_sta.c | 68 +++++++++++++++++++++++++++++++++-- net/mac80211/ieee80211_i.h | 2 ++ net/mac80211/main.c | 4 +++ net/mac80211/sta_info.c | 44 +++++++++++++++++++++-- net/mac80211/sta_info.h | 13 +++++++ net/mac80211/status.c | 6 ++++ net/mac80211/tx.c | 90 +++++++++++++++++++++++++++++++++++++++++++--- 10 files changed, 282 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e8a057f071c4..5d36eacf401e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2360,6 +2360,9 @@ enum ieee80211_hw_flags { * @tx_sk_pacing_shift: Pacing shift to set on TCP sockets when frames from * them are encountered. The default should typically not be changed, * unless the driver has good reasons for needing more buffers. + * + * @weight_multipler: Driver specific airtime weight multiplier used while + * refilling deficit of each TXQ. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2396,6 +2399,7 @@ struct ieee80211_hw { const struct ieee80211_cipher_scheme *cipher_schemes; u8 max_nan_de_entries; u8 tx_sk_pacing_shift; + u8 weight_multiplier; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, @@ -5407,6 +5411,34 @@ void ieee80211_sta_eosp(struct ieee80211_sta *pubsta); */ void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid); +/** + * ieee80211_sta_register_airtime - register airtime usage for a sta/tid + * + * Register airtime usage for a given sta on a given tid. The driver can call + * this function to notify mac80211 that a station used a certain amount of + * airtime. This information will be used by the TXQ scheduler to schedule + * stations in a way that ensures airtime fairness. + * + * The reported airtime should as a minimum include all time that is spent + * transmitting to the remote station, including overhead and padding, but not + * including time spent waiting for a TXOP. If the time is not reported by the + * hardware it can in some cases be calculated from the rate and known frame + * composition. When possible, the time should include any failed transmission + * attempts. + * + * The driver can either call this function synchronously for every packet or + * aggregate, or asynchronously as airtime usage information becomes available. + * TX and RX airtime can be reported together, or separately by setting one of + * them to 0. + * + * @pubsta: the station + * @tid: the TID to register airtime for + * @tx_airtime: airtime used during TX (in usec) + * @rx_airtime: airtime used during RX (in usec) + */ +void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, + u32 tx_airtime, u32 rx_airtime); + /** * ieee80211_iter_keys - iterate keys programmed into the device * @hw: pointer obtained from ieee80211_alloc_hw() @@ -6173,6 +6205,33 @@ void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) __releases(txq_lock); +/** + * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit + * + * This function is used to check whether given txq is allowed to transmit by + * the airtime scheduler, and can be used by drivers to access the airtime + * fairness accounting without going using the scheduling order enfored by + * next_txq(). + * + * Returns %true if the airtime scheduler thinks the TXQ should be allowed to + * transmit, and %false if it should be throttled. This function can also have + * the side effect of rotating the TXQ in the scheduler rotation, which will + * eventually bring the deficit to positive and allow the station to transmit + * again. + * + * The API ieee80211_txq_may_transmit() also ensures that TXQ list will be + * aligned aginst driver's own round-robin scheduler list. i.e it rotates + * the TXQ list till it makes the requested node becomes the first entry + * in TXQ list. Thus both the TXQ list and driver's list are in sync. If this + * function returns %true, the driver is expected to schedule packets + * for transmission, and then return the TXQ through ieee80211_return_txq(). + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @txq: pointer obtained from station or virtual interface + */ +bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, + struct ieee80211_txq *txq); + /** * ieee80211_txq_get_depth - get pending frame/byte count of given txq * diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index de65fe3ed9cc..83ee573b1804 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1447,6 +1447,9 @@ static int sta_apply_parameters(struct ieee80211_local *local, if (ieee80211_vif_is_mesh(&sdata->vif)) sta_apply_mesh_params(local, sta, params); + if (params->airtime_weight) + sta->airtime_weight = params->airtime_weight; + /* set the STA state after all sta info from usermode has been set */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) || set & BIT(NL80211_STA_FLAG_ASSOCIATED)) { diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 3fe541e358f3..81c5fec2eae7 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -383,6 +383,9 @@ void debugfs_hw_add(struct ieee80211_local *local) if (local->ops->wake_tx_queue) DEBUGFS_ADD_MODE(aqm, 0600); + debugfs_create_u16("airtime_flags", 0600, + phyd, &local->airtime_flags); + statsd = debugfs_create_dir("statistics", phyd); /* if the dir failed, don't put all the other things into the root! */ diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index b753194710ad..3aa618dcc58e 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -181,9 +181,9 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, txqi->tin.tx_bytes, txqi->tin.tx_packets, txqi->flags, - txqi->flags & (1<flags & (1<flags & (1<flags) ? "STOP" : "RUN", + test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags) ? " AMPDU" : "", + test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : ""); } rcu_read_unlock(); @@ -195,6 +195,64 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, } STA_OPS(aqm); +static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + size_t bufsz = 200; + char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; + u64 rx_airtime = 0, tx_airtime = 0; + s64 deficit[IEEE80211_NUM_ACS]; + ssize_t rv; + int ac; + + if (!buf) + return -ENOMEM; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + rx_airtime += sta->airtime[ac].rx_airtime; + tx_airtime += sta->airtime[ac].tx_airtime; + deficit[ac] = sta->airtime[ac].deficit; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + p += scnprintf(p, bufsz + buf - p, + "RX: %llu us\nTX: %llu us\nWeight: %u\n" + "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", + rx_airtime, + tx_airtime, + sta->airtime_weight, + deficit[0], + deficit[1], + deficit[2], + deficit[3]); + + rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return rv; +} + +static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + int ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].rx_airtime = 0; + sta->airtime[ac].tx_airtime = 0; + sta->airtime[ac].deficit = sta->airtime_weight; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + return count; +} +STA_OPS_RW(airtime); + static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -906,6 +964,10 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) if (local->ops->wake_tx_queue) DEBUGFS_ADD(aqm); + if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + DEBUGFS_ADD(airtime); + if (sizeof(sta->driver_buffered_tids) == sizeof(u32)) debugfs_create_x32("driver_buffered_tids", 0400, sta->debugfs_dir, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index d1db27b1e989..056b16bce3b0 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1138,6 +1138,8 @@ struct ieee80211_local { struct list_head active_txqs[IEEE80211_NUM_ACS]; u16 schedule_round[IEEE80211_NUM_ACS]; + u16 airtime_flags; + const struct ieee80211_ops *ops; /* diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 9b9d6cadf56e..896f17d726d0 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -667,6 +667,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, INIT_LIST_HEAD(&local->active_txqs[i]); spin_lock_init(&local->active_txq_lock[i]); } + local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX; INIT_LIST_HEAD(&local->chanctx_list); mutex_init(&local->chanctx_mtx); @@ -1153,6 +1154,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!local->hw.max_nan_de_entries) local->hw.max_nan_de_entries = IEEE80211_MAX_NAN_INSTANCE_ID; + if (!local->hw.weight_multiplier) + local->hw.weight_multiplier = 1; + result = ieee80211_wep_init(local); if (result < 0) wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n", diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 83e1c316a29e..11f058987a54 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -90,7 +90,6 @@ static void __cleanup_single_sta(struct sta_info *sta) struct tid_ampdu_tx *tid_tx; struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - struct fq *fq = &local->fq; struct ps_data *ps; if (test_sta_flag(sta, WLAN_STA_PS_STA) || @@ -120,9 +119,7 @@ static void __cleanup_single_sta(struct sta_info *sta) txqi = to_txq_info(sta->sta.txq[i]); - spin_lock_bh(&fq->lock); ieee80211_txq_purge(local, txqi); - spin_unlock_bh(&fq->lock); } } @@ -387,9 +384,12 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, if (sta_prepare_rate_control(local, sta, gfp)) goto free_txq; + sta->airtime_weight = IEEE80211_DEFAULT_AIRTIME_WEIGHT; + for (i = 0; i < IEEE80211_NUM_ACS; i++) { skb_queue_head_init(&sta->ps_tx_buf[i]); skb_queue_head_init(&sta->tx_filtered[i]); + sta->airtime[i].deficit = sta->airtime_weight; } for (i = 0; i < IEEE80211_NUM_TIDS; i++) @@ -1826,6 +1826,27 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(ieee80211_sta_set_buffered); +void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, + u32 tx_airtime, u32 rx_airtime) +{ + struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + struct ieee80211_local *local = sta->sdata->local; + u8 ac = ieee80211_ac_from_tid(tid); + u32 airtime = 0; + + if (sta->local->airtime_flags & AIRTIME_USE_TX) + airtime += tx_airtime; + if (sta->local->airtime_flags & AIRTIME_USE_RX) + airtime += rx_airtime; + + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].tx_airtime += tx_airtime; + sta->airtime[ac].rx_airtime += rx_airtime; + sta->airtime[ac].deficit -= airtime; + spin_unlock_bh(&local->active_txq_lock[ac]); +} +EXPORT_SYMBOL(ieee80211_sta_register_airtime); + int sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state) { @@ -2188,6 +2209,23 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED); } + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_DURATION))) { + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + sinfo->rx_duration += sta->airtime[ac].rx_airtime; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DURATION); + } + + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_DURATION))) { + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + sinfo->tx_duration += sta->airtime[ac].tx_airtime; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_DURATION); + } + + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT))) { + sinfo->airtime_weight = sta->airtime_weight; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT); + } + sinfo->rx_dropped_misc = sta->rx_stats.dropped; if (sta->pcpu_rx_stats) { for_each_possible_cpu(cpu) { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 8eb29041be54..9a380803e597 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -127,6 +127,16 @@ enum ieee80211_agg_stop_reason { AGG_STOP_DESTROY_STA, }; +/* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */ +#define AIRTIME_USE_TX BIT(0) +#define AIRTIME_USE_RX BIT(1) + +struct airtime_info { + u64 rx_airtime; + u64 tx_airtime; + s64 deficit; +}; + struct sta_info; /** @@ -565,6 +575,9 @@ struct sta_info { } tx_stats; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; + struct airtime_info airtime[IEEE80211_NUM_ACS]; + u16 airtime_weight; + /* * Aggregation information, locked with lock. */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 3f0b96e1e02f..5b9952b1caf3 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -823,6 +823,12 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data, acked, info->status.tx_time); + if (info->status.tx_time && + wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + ieee80211_sta_register_airtime(&sta->sta, tid, + info->status.tx_time, 0); + if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { if (info->flags & IEEE80211_TX_STAT_ACK) { if (sta->status_stats.lost_packets) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 544da6411620..f46d8d822f86 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1488,8 +1488,11 @@ void ieee80211_txq_purge(struct ieee80211_local *local, struct fq *fq = &local->fq; struct fq_tin *tin = &txqi->tin; + spin_lock_bh(&fq->lock); fq_tin_reset(fq, tin, fq_skb_free_func); ieee80211_purge_tx_queue(&local->hw, &txqi->frags); + spin_unlock_bh(&fq->lock); + spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]); list_del_init(&txqi->schedule_order); spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]); @@ -3641,11 +3644,28 @@ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac) lockdep_assert_held(&local->active_txq_lock[ac]); + begin: txqi = list_first_entry_or_null(&local->active_txqs[ac], struct txq_info, schedule_order); + if (!txqi) + return NULL; + + if (txqi->txq.sta) { + struct sta_info *sta = container_of(txqi->txq.sta, + struct sta_info, sta); + + if (sta->airtime[txqi->txq.ac].deficit < 0) { + sta->airtime[txqi->txq.ac].deficit += + sta->airtime_weight; + list_move_tail(&txqi->schedule_order, + &local->active_txqs[txqi->txq.ac]); + goto begin; + } + } + - if (!txqi || txqi->schedule_round == local->schedule_round[ac]) + if (txqi->schedule_round == local->schedule_round[ac]) return NULL; list_del_init(&txqi->schedule_order); @@ -3663,12 +3683,74 @@ void ieee80211_return_txq(struct ieee80211_hw *hw, lockdep_assert_held(&local->active_txq_lock[txq->ac]); if (list_empty(&txqi->schedule_order) && - (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) - list_add_tail(&txqi->schedule_order, - &local->active_txqs[txq->ac]); + (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) { + /* If airtime accounting is active, always enqueue STAs at the + * head of the list to ensure that they only get moved to the + * back by the airtime DRR scheduler once they have a negative + * deficit. A station that already has a negative deficit will + * get immediately moved to the back of the list on the next + * call to ieee80211_next_txq(). + */ + if (txqi->txq.sta && + wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + list_add(&txqi->schedule_order, + &local->active_txqs[txq->ac]); + else + list_add_tail(&txqi->schedule_order, + &local->active_txqs[txq->ac]); + } } EXPORT_SYMBOL(ieee80211_return_txq); +bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *iter, *tmp, *txqi = to_txq_info(txq); + struct sta_info *sta; + u8 ac = txq->ac; + + lockdep_assert_held(&local->active_txq_lock[ac]); + + if (!txqi->txq.sta) + goto out; + + if (list_empty(&txqi->schedule_order)) + goto out; + + list_for_each_entry_safe(iter, tmp, &local->active_txqs[ac], + schedule_order) { + if (iter == txqi) + break; + + if (!iter->txq.sta) { + list_move_tail(&iter->schedule_order, + &local->active_txqs[ac]); + continue; + } + sta = container_of(iter->txq.sta, struct sta_info, sta); + if (sta->airtime[ac].deficit < 0) + sta->airtime[ac].deficit += sta->airtime_weight; + list_move_tail(&iter->schedule_order, &local->active_txqs[ac]); + } + + sta = container_of(txqi->txq.sta, struct sta_info, sta); + if (sta->airtime[ac].deficit >= 0) + goto out; + + sta->airtime[ac].deficit += sta->airtime_weight; + list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]); + + return false; +out: + if (!list_empty(&txqi->schedule_order)) + list_del_init(&txqi->schedule_order); + + return true; +} +EXPORT_SYMBOL(ieee80211_txq_may_transmit); + void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) __acquires(txq_lock) { -- cgit v1.2.3 From cc24163690997c685641d84e77ff6f1c592b06fe Mon Sep 17 00:00:00 2001 From: Julan Hsu Date: Tue, 15 Jan 2019 15:28:42 -0800 Subject: nl80211/mac80211: mesh: add hop count to mpath info Expose hop count to destination information in mpath info Signed-off-by: Julan Hsu Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 2 ++ net/mac80211/cfg.c | 4 +++- net/mac80211/mesh_hwmp.c | 5 +++++ net/wireless/nl80211.c | 5 ++++- 5 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1691f52fcc80..37816786d3e1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1429,6 +1429,7 @@ enum monitor_flags { * @MPATH_INFO_DISCOVERY_TIMEOUT: @discovery_timeout filled * @MPATH_INFO_DISCOVERY_RETRIES: @discovery_retries filled * @MPATH_INFO_FLAGS: @flags filled + * @MPATH_INFO_HOP_COUNT: @hop_count filled */ enum mpath_info_flags { MPATH_INFO_FRAME_QLEN = BIT(0), @@ -1438,6 +1439,7 @@ enum mpath_info_flags { MPATH_INFO_DISCOVERY_TIMEOUT = BIT(4), MPATH_INFO_DISCOVERY_RETRIES = BIT(5), MPATH_INFO_FLAGS = BIT(6), + MPATH_INFO_HOP_COUNT = BIT(7) }; /** @@ -1457,6 +1459,7 @@ enum mpath_info_flags { * This number should increase every time the list of mesh paths * changes, i.e. when a station is added or removed, so that * userspace can tell whether it got a consistent snapshot. + * @hop_count: hops to destination */ struct mpath_info { u32 filled; @@ -1467,6 +1470,7 @@ struct mpath_info { u32 discovery_timeout; u8 discovery_retries; u8 flags; + u8 hop_count; int generation; }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index ebe79e12c82e..213a1d7c1063 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3287,6 +3287,7 @@ enum nl80211_mpath_flags { * &enum nl80211_mpath_flags; * @NL80211_MPATH_INFO_DISCOVERY_TIMEOUT: total path discovery timeout, in msec * @NL80211_MPATH_INFO_DISCOVERY_RETRIES: mesh path discovery retries + * @NL80211_MPATH_INFO_HOP_COUNT: hop count to destination * @NL80211_MPATH_INFO_MAX: highest mesh path information attribute number * currently defind * @__NL80211_MPATH_INFO_AFTER_LAST: internal use @@ -3300,6 +3301,7 @@ enum nl80211_mpath_info { NL80211_MPATH_INFO_FLAGS, NL80211_MPATH_INFO_DISCOVERY_TIMEOUT, NL80211_MPATH_INFO_DISCOVERY_RETRIES, + NL80211_MPATH_INFO_HOP_COUNT, /* keep last */ __NL80211_MPATH_INFO_AFTER_LAST, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 83ee573b1804..52cbaaf5caea 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1745,7 +1745,8 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, MPATH_INFO_EXPTIME | MPATH_INFO_DISCOVERY_TIMEOUT | MPATH_INFO_DISCOVERY_RETRIES | - MPATH_INFO_FLAGS; + MPATH_INFO_FLAGS | + MPATH_INFO_HOP_COUNT; pinfo->frame_qlen = mpath->frame_queue.qlen; pinfo->sn = mpath->sn; @@ -1765,6 +1766,7 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, pinfo->flags |= NL80211_MPATH_FLAG_FIXED; if (mpath->flags & MESH_PATH_RESOLVED) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVED; + pinfo->hop_count = mpath->hop_count; } static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev, diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 6950cd0bf594..6d1190b3332f 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -386,6 +386,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, unsigned long orig_lifetime, exp_time; u32 last_hop_metric, new_metric; bool process = true; + u8 hopcount; rcu_read_lock(); sta = sta_info_get(sdata, mgmt->sa); @@ -404,6 +405,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, orig_sn = PREQ_IE_ORIG_SN(hwmp_ie); orig_lifetime = PREQ_IE_LIFETIME(hwmp_ie); orig_metric = PREQ_IE_METRIC(hwmp_ie); + hopcount = PREQ_IE_HOPCOUNT(hwmp_ie) + 1; break; case MPATH_PREP: /* Originator here refers to the MP that was the target in the @@ -415,6 +417,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, orig_sn = PREP_IE_TARGET_SN(hwmp_ie); orig_lifetime = PREP_IE_LIFETIME(hwmp_ie); orig_metric = PREP_IE_METRIC(hwmp_ie); + hopcount = PREP_IE_HOPCOUNT(hwmp_ie) + 1; break; default: rcu_read_unlock(); @@ -482,6 +485,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, mpath->sn = orig_sn; mpath->exp_time = time_after(mpath->exp_time, exp_time) ? mpath->exp_time : exp_time; + mpath->hop_count = hopcount; mesh_path_activate(mpath); spin_unlock_bh(&mpath->state_lock); ewma_mesh_fail_avg_init(&sta->mesh->fail_avg); @@ -523,6 +527,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, mpath->metric = last_hop_metric; mpath->exp_time = time_after(mpath->exp_time, exp_time) ? mpath->exp_time : exp_time; + mpath->hop_count = 1; mesh_path_activate(mpath); spin_unlock_bh(&mpath->state_lock); ewma_mesh_fail_avg_init(&sta->mesh->fail_avg); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index a89688929b16..159125e16c79 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5827,7 +5827,10 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq, pinfo->discovery_timeout)) || ((pinfo->filled & MPATH_INFO_DISCOVERY_RETRIES) && nla_put_u8(msg, NL80211_MPATH_INFO_DISCOVERY_RETRIES, - pinfo->discovery_retries))) + pinfo->discovery_retries)) || + ((pinfo->filled & MPATH_INFO_HOP_COUNT) && + nla_put_u8(msg, NL80211_MPATH_INFO_HOP_COUNT, + pinfo->hop_count))) goto nla_put_failure; nla_nest_end(msg, pinfoattr); -- cgit v1.2.3 From 540bbcb930ed2fc9d6a57e0babea00027a7ecc67 Mon Sep 17 00:00:00 2001 From: Julan Hsu Date: Tue, 15 Jan 2019 15:28:43 -0800 Subject: nl80211/mac80211: mesh: add mesh path change count to mpath info Expose path change count to destination in mpath info Signed-off-by: Julan Hsu Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 5 ++++- include/uapi/linux/nl80211.h | 4 +++- net/mac80211/cfg.c | 4 +++- net/mac80211/mesh.h | 2 ++ net/mac80211/mesh_hwmp.c | 4 ++++ net/wireless/nl80211.c | 5 ++++- 6 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 37816786d3e1..9c1d7979c200 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1439,7 +1439,8 @@ enum mpath_info_flags { MPATH_INFO_DISCOVERY_TIMEOUT = BIT(4), MPATH_INFO_DISCOVERY_RETRIES = BIT(5), MPATH_INFO_FLAGS = BIT(6), - MPATH_INFO_HOP_COUNT = BIT(7) + MPATH_INFO_HOP_COUNT = BIT(7), + MPATH_INFO_PATH_CHANGE = BIT(8), }; /** @@ -1460,6 +1461,7 @@ enum mpath_info_flags { * changes, i.e. when a station is added or removed, so that * userspace can tell whether it got a consistent snapshot. * @hop_count: hops to destination + * @path_change_count: total number of path changes to destination */ struct mpath_info { u32 filled; @@ -1471,6 +1473,7 @@ struct mpath_info { u8 discovery_retries; u8 flags; u8 hop_count; + u32 path_change_count; int generation; }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 213a1d7c1063..426db4d8f71c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3288,8 +3288,9 @@ enum nl80211_mpath_flags { * @NL80211_MPATH_INFO_DISCOVERY_TIMEOUT: total path discovery timeout, in msec * @NL80211_MPATH_INFO_DISCOVERY_RETRIES: mesh path discovery retries * @NL80211_MPATH_INFO_HOP_COUNT: hop count to destination + * @NL80211_MPATH_INFO_PATH_CHANGE: total number of path changes to destination * @NL80211_MPATH_INFO_MAX: highest mesh path information attribute number - * currently defind + * currently defined * @__NL80211_MPATH_INFO_AFTER_LAST: internal use */ enum nl80211_mpath_info { @@ -3302,6 +3303,7 @@ enum nl80211_mpath_info { NL80211_MPATH_INFO_DISCOVERY_TIMEOUT, NL80211_MPATH_INFO_DISCOVERY_RETRIES, NL80211_MPATH_INFO_HOP_COUNT, + NL80211_MPATH_INFO_PATH_CHANGE, /* keep last */ __NL80211_MPATH_INFO_AFTER_LAST, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 52cbaaf5caea..e5e0f100389c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1746,7 +1746,8 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, MPATH_INFO_DISCOVERY_TIMEOUT | MPATH_INFO_DISCOVERY_RETRIES | MPATH_INFO_FLAGS | - MPATH_INFO_HOP_COUNT; + MPATH_INFO_HOP_COUNT | + MPATH_INFO_PATH_CHANGE; pinfo->frame_qlen = mpath->frame_queue.qlen; pinfo->sn = mpath->sn; @@ -1767,6 +1768,7 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, if (mpath->flags & MESH_PATH_RESOLVED) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVED; pinfo->hop_count = mpath->hop_count; + pinfo->path_change_count = mpath->path_change_count; } static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev, diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index cad6592c52a1..8b26858ab4d5 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -94,6 +94,7 @@ enum mesh_deferred_task_flags { * @last_preq_to_root: Timestamp of last PREQ sent to root * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate + * @path_change_count: the number of path changes to destination * * * The dst address is unique in the mesh path table. Since the mesh_path is @@ -124,6 +125,7 @@ struct mesh_path { unsigned long last_preq_to_root; bool is_root; bool is_gate; + u32 path_change_count; }; /** diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 6d1190b3332f..a0aebf44493f 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -479,6 +479,8 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, } if (fresh_info) { + if (rcu_access_pointer(mpath->next_hop) != sta) + mpath->path_change_count++; mesh_path_assign_nexthop(mpath, sta); mpath->flags |= MESH_PATH_SN_VALID; mpath->metric = new_metric; @@ -523,6 +525,8 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, } if (fresh_info) { + if (rcu_access_pointer(mpath->next_hop) != sta) + mpath->path_change_count++; mesh_path_assign_nexthop(mpath, sta); mpath->metric = last_hop_metric; mpath->exp_time = time_after(mpath->exp_time, exp_time) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 159125e16c79..e5f9c9ceb6c9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5830,7 +5830,10 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq, pinfo->discovery_retries)) || ((pinfo->filled & MPATH_INFO_HOP_COUNT) && nla_put_u8(msg, NL80211_MPATH_INFO_HOP_COUNT, - pinfo->hop_count))) + pinfo->hop_count)) || + ((pinfo->filled & MPATH_INFO_PATH_CHANGE) && + nla_put_u32(msg, NL80211_MPATH_INFO_PATH_CHANGE, + pinfo->path_change_count))) goto nla_put_failure; nla_nest_end(msg, pinfoattr); -- cgit v1.2.3 From 77f7ffdc335de8541a2a40618781ed0b76cee9f7 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 16 Jan 2019 22:32:12 +0100 Subject: mac80211: minstrel_ht: add flag to indicate missing/inaccurate tx A-MPDU length Some hardware (e.g. MediaTek MT7603) cannot report A-MPDU length in tx status information. Add support for a flag to indicate that, to allow minstrel_ht to use a fixed value in its internal calculation (which gives better results than just defaulting to 1). Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ net/mac80211/debugfs.c | 1 + net/mac80211/rc80211_minstrel_ht.c | 25 ++++++++++++++++++++----- net/mac80211/rc80211_minstrel_ht_debugfs.c | 7 ++++--- 4 files changed, 29 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5d36eacf401e..a285c2bfd14e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2190,6 +2190,9 @@ struct ieee80211_txq { * MMPDUs on station interfaces. This of course requires the driver to use * TXQs to start with. * + * @IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN: Driver does not report accurate A-MPDU + * length in tx status information + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2238,6 +2241,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_BUFF_MMPDU_TXQ, IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW, IEEE80211_HW_STA_MMPDU_TXQ, + IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 81c5fec2eae7..343ad0a915e4 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -218,6 +218,7 @@ static const char *hw_flag_names[] = { FLAG(BUFF_MMPDU_TXQ), FLAG(SUPPORTS_VHT_EXT_NSS_BW), FLAG(STA_MMPDU_TXQ), + FLAG(TX_STATUS_NO_AMPDU_LEN), #undef FLAG }; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index f466ec37d161..ccaf951e4e31 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -294,6 +294,15 @@ minstrel_get_ratestats(struct minstrel_ht_sta *mi, int index) return &mi->groups[index / MCS_GROUP_RATES].rates[index % MCS_GROUP_RATES]; } +static unsigned int +minstrel_ht_avg_ampdu_len(struct minstrel_ht_sta *mi) +{ + if (!mi->avg_ampdu_len) + return AVG_AMPDU_SIZE; + + return MINSTREL_TRUNC(mi->avg_ampdu_len); +} + /* * Return current throughput based on the average A-MPDU length, taking into * account the expected number of retransmissions and their expected length @@ -309,7 +318,7 @@ minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, return 0; if (group != MINSTREL_CCK_GROUP) - nsecs = 1000 * mi->overhead / MINSTREL_TRUNC(mi->avg_ampdu_len); + nsecs = 1000 * mi->overhead / minstrel_ht_avg_ampdu_len(mi); nsecs += minstrel_mcs_groups[group].duration[rate] << minstrel_mcs_groups[group].shift; @@ -503,8 +512,12 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) u16 tmp_cck_tp_rate[MAX_THR_RATES], index; if (mi->ampdu_packets > 0) { - mi->avg_ampdu_len = minstrel_ewma(mi->avg_ampdu_len, - MINSTREL_FRAC(mi->ampdu_len, mi->ampdu_packets), EWMA_LEVEL); + if (!ieee80211_hw_check(mp->hw, TX_STATUS_NO_AMPDU_LEN)) + mi->avg_ampdu_len = minstrel_ewma(mi->avg_ampdu_len, + MINSTREL_FRAC(mi->ampdu_len, mi->ampdu_packets), + EWMA_LEVEL); + else + mi->avg_ampdu_len = 0; mi->ampdu_len = 0; mi->ampdu_packets = 0; } @@ -709,7 +722,9 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, mi->ampdu_len += info->status.ampdu_len; if (!mi->sample_wait && !mi->sample_tries && mi->sample_count > 0) { - mi->sample_wait = 16 + 2 * MINSTREL_TRUNC(mi->avg_ampdu_len); + int avg_ampdu_len = minstrel_ht_avg_ampdu_len(mi); + + mi->sample_wait = 16 + 2 * avg_ampdu_len; mi->sample_tries = 1; mi->sample_count--; } @@ -777,7 +792,7 @@ minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, unsigned int cw = mp->cw_min; unsigned int ctime = 0; unsigned int t_slot = 9; /* FIXME */ - unsigned int ampdu_len = MINSTREL_TRUNC(mi->avg_ampdu_len); + unsigned int ampdu_len = minstrel_ht_avg_ampdu_len(mi); unsigned int overhead = 0, overhead_rtscts = 0; mrs = minstrel_get_ratestats(mi, index); diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c index 57820a5f2c16..31641d0b0f5c 100644 --- a/net/mac80211/rc80211_minstrel_ht_debugfs.c +++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c @@ -160,9 +160,10 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file) "lookaround %d\n", max(0, (int) mi->total_packets - (int) mi->sample_packets), mi->sample_packets); - p += sprintf(p, "Average # of aggregated frames per A-MPDU: %d.%d\n", - MINSTREL_TRUNC(mi->avg_ampdu_len), - MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10); + if (mi->avg_ampdu_len) + p += sprintf(p, "Average # of aggregated frames per A-MPDU: %d.%d\n", + MINSTREL_TRUNC(mi->avg_ampdu_len), + MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10); ms->len = p - ms->buf; WARN_ON(ms->len + sizeof(*ms) > 32768); -- cgit v1.2.3 From 5f2939d933e9616b8b779fa46963689000f1a8f4 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Wed, 9 Jan 2019 17:10:57 +0100 Subject: sch_api: Change signature of qdisc_tree_reduce_backlog() to use ints MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are now several places where qdisc_tree_reduce_backlog() is called with a negative number of packets (to signal an increase in number of packets in the queue). Rather than rely on overflow behaviour, change the function signature to use signed integers to communicate this usage to people reading the code. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/net/sch_generic.h | 3 +-- net/sched/sch_api.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9481f2c142e2..7a4957599874 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -580,8 +580,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, void qdisc_reset(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); -void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, - unsigned int len); +void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len); #ifdef CONFIG_NET_SCHED int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, void *type_data); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 7e4d1ccf4c87..03e26e8d0ec9 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -758,8 +758,7 @@ static u32 qdisc_alloc_handle(struct net_device *dev) return 0; } -void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, - unsigned int len) +void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; const struct Qdisc_class_ops *cops; -- cgit v1.2.3 From 59c28058fa7bb1cc7ab8b2c5607093cbbefafeb4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 18 Jan 2019 10:46:13 -0800 Subject: net: netlink: add helper to retrieve NETLINK_F_STRICT_CHK Dumps can read state of the NETLINK_F_STRICT_CHK flag from a field in the callback structure. For non-dump GET requests we need a way to access the state of that flag from a socket. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + net/netlink/af_netlink.c | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 4e8add270200..593d1b9c33a8 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -126,6 +126,7 @@ void __netlink_clear_multicast_users(struct sock *sk, unsigned int group); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack); int netlink_has_listeners(struct sock *sk, unsigned int group); +bool netlink_strict_get_check(struct sk_buff *skb); int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3c023d6120f6..8fa35df94c07 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1371,6 +1371,14 @@ int netlink_has_listeners(struct sock *sk, unsigned int group) } EXPORT_SYMBOL_GPL(netlink_has_listeners); +bool netlink_strict_get_check(struct sk_buff *skb) +{ + const struct netlink_sock *nlk = nlk_sk(NETLINK_CB(skb).sk); + + return nlk->flags & NETLINK_F_STRICT_CHK; +} +EXPORT_SYMBOL_GPL(netlink_strict_get_check); + static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); -- cgit v1.2.3 From 5954894ba3723995fbeab77bef62bb4878a654bb Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 17 Jan 2019 17:14:01 -0800 Subject: net_sched: add performance counters for basic filter Similar to u32 filter, it is useful to know how many times we reach each basic filter and how many times we pass the ematch attached to it. Sample output: filter protocol arp pref 49152 basic chain 0 filter protocol arp pref 49152 basic chain 0 handle 0x1 (rule hit 3 success 3) action order 1: gact action pass random type none pass val 0 index 1 ref 1 bind 1 installed 81 sec used 4 sec Action statistics: Sent 126 bytes 3 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Cc: Jamal Hadi Salim Cc: Jiri Pirko Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 7 +++++++ net/sched/cls_basic.c | 25 +++++++++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 32a3416b51c3..02ac251be8c4 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -333,12 +333,19 @@ enum { /* Basic filter */ +struct tc_basic_pcnt { + __u64 rcnt; + __u64 rhit; +}; + enum { TCA_BASIC_UNSPEC, TCA_BASIC_CLASSID, TCA_BASIC_EMATCHES, TCA_BASIC_ACT, TCA_BASIC_POLICE, + TCA_BASIC_PCNT, + TCA_BASIC_PAD, __TCA_BASIC_MAX }; diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 6a5dce8baf19..4a57fec6f306 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -35,6 +36,7 @@ struct basic_filter { struct tcf_result res; struct tcf_proto *tp; struct list_head link; + struct tc_basic_pcnt __percpu *pf; struct rcu_work rwork; }; @@ -46,8 +48,10 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct basic_filter *f; list_for_each_entry_rcu(f, &head->flist, link) { + __this_cpu_inc(f->pf->rcnt); if (!tcf_em_tree_match(skb, &f->ematches, NULL)) continue; + __this_cpu_inc(f->pf->rhit); *res = f->res; r = tcf_exts_exec(skb, &f->exts, res); if (r < 0) @@ -89,6 +93,7 @@ static void __basic_delete_filter(struct basic_filter *f) tcf_exts_destroy(&f->exts); tcf_em_tree_destroy(&f->ematches); tcf_exts_put_net(&f->exts); + free_percpu(f->pf); kfree(f); } @@ -208,6 +213,11 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (err) goto errout; fnew->handle = handle; + fnew->pf = alloc_percpu(struct tc_basic_pcnt); + if (!fnew->pf) { + err = -ENOMEM; + goto errout; + } err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr, extack); @@ -231,6 +241,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, return 0; errout: + free_percpu(fnew->pf); tcf_exts_destroy(&fnew->exts); kfree(fnew); return err; @@ -265,8 +276,10 @@ static void basic_bind_class(void *fh, u32 classid, unsigned long cl) static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { + struct tc_basic_pcnt gpf = {}; struct basic_filter *f = fh; struct nlattr *nest; + int cpu; if (f == NULL) return skb->len; @@ -281,6 +294,18 @@ static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, nla_put_u32(skb, TCA_BASIC_CLASSID, f->res.classid)) goto nla_put_failure; + for_each_possible_cpu(cpu) { + struct tc_basic_pcnt *pf = per_cpu_ptr(f->pf, cpu); + + gpf.rcnt += pf->rcnt; + gpf.rhit += pf->rhit; + } + + if (nla_put_64bit(skb, TCA_BASIC_PCNT, + sizeof(struct tc_basic_pcnt), + &gpf, TCA_BASIC_PAD)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &f->exts) < 0 || tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0) goto nla_put_failure; -- cgit v1.2.3 From f5d782d46aa5d4dd369e6560ce5227136b58926f Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Thu, 13 Dec 2018 02:38:58 +0100 Subject: power: supply: isp1704: switch to gpiod API This migrates isp1704 driver from old GPIO API to new descriptor based GPIO API and drops useless platform data as a side-effect. Migration is simple, since all mainline users are DT based and DT API does not change. Out of tree users of the platform data need to migrate to gpiod_lookup_table as described here: Documentation/driver-api/gpio/board.rst Reviewed-by: Linus Walleij Acked-by: Pavel Machek Signed-off-by: Sebastian Reichel --- drivers/power/supply/isp1704_charger.c | 60 +++++++--------------------------- include/linux/power/isp1704_charger.h | 30 ----------------- 2 files changed, 12 insertions(+), 78 deletions(-) delete mode 100644 include/linux/power/isp1704_charger.h (limited to 'include') diff --git a/drivers/power/supply/isp1704_charger.c b/drivers/power/supply/isp1704_charger.c index 95af5f305838..a63cb5dcfa08 100644 --- a/drivers/power/supply/isp1704_charger.c +++ b/drivers/power/supply/isp1704_charger.c @@ -30,13 +30,12 @@ #include #include #include -#include +#include #include #include #include #include -#include /* Vendor specific Power Control register */ #define ISP1704_PWR_CTRL 0x3d @@ -60,6 +59,7 @@ struct isp1704_charger { struct device *dev; struct power_supply *psy; struct power_supply_desc psy_desc; + struct gpio_desc *enable_gpio; struct usb_phy *phy; struct notifier_block nb; struct work_struct work; @@ -81,18 +81,9 @@ static inline int isp1704_write(struct isp1704_charger *isp, u32 reg, u32 val) return usb_phy_io_write(isp->phy, val, reg); } -/* - * Disable/enable the power from the isp1704 if a function for it - * has been provided with platform data. - */ static void isp1704_charger_set_power(struct isp1704_charger *isp, bool on) { - struct isp1704_charger_data *board = isp->dev->platform_data; - - if (board && board->set_power) - board->set_power(on); - else if (board) - gpio_set_value(board->enable_gpio, on); + gpiod_set_value(isp->enable_gpio, on); } /* @@ -405,46 +396,19 @@ static int isp1704_charger_probe(struct platform_device *pdev) int ret = -ENODEV; struct power_supply_config psy_cfg = {}; - struct isp1704_charger_data *pdata = dev_get_platdata(&pdev->dev); - struct device_node *np = pdev->dev.of_node; - - if (np) { - int gpio = of_get_named_gpio(np, "nxp,enable-gpio", 0); - - if (gpio < 0) { - dev_err(&pdev->dev, "missing DT GPIO nxp,enable-gpio\n"); - return gpio; - } - - pdata = devm_kzalloc(&pdev->dev, - sizeof(struct isp1704_charger_data), GFP_KERNEL); - if (!pdata) { - ret = -ENOMEM; - goto fail0; - } - pdata->enable_gpio = gpio; - - dev_info(&pdev->dev, "init gpio %d\n", pdata->enable_gpio); - - ret = devm_gpio_request_one(&pdev->dev, pdata->enable_gpio, - GPIOF_OUT_INIT_HIGH, "isp1704_reset"); - if (ret) { - dev_err(&pdev->dev, "gpio request failed\n"); - goto fail0; - } - } - - if (!pdata) { - dev_err(&pdev->dev, "missing platform data!\n"); - return -ENODEV; - } - - isp = devm_kzalloc(&pdev->dev, sizeof(*isp), GFP_KERNEL); if (!isp) return -ENOMEM; - if (np) + isp->enable_gpio = devm_gpiod_get(&pdev->dev, "nxp,enable", + GPIOD_OUT_HIGH); + if (IS_ERR(isp->enable_gpio)) { + ret = PTR_ERR(isp->enable_gpio); + dev_err(&pdev->dev, "Could not get reset gpio: %d\n", ret); + return ret; + } + + if (pdev->dev.of_node) isp->phy = devm_usb_get_phy_by_phandle(&pdev->dev, "usb-phy", 0); else isp->phy = devm_usb_get_phy(&pdev->dev, USB_PHY_TYPE_USB2); diff --git a/include/linux/power/isp1704_charger.h b/include/linux/power/isp1704_charger.h deleted file mode 100644 index 0105d9e7af85..000000000000 --- a/include/linux/power/isp1704_charger.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * ISP1704 USB Charger Detection driver - * - * Copyright (C) 2011 Nokia Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - - -#ifndef __ISP1704_CHARGER_H -#define __ISP1704_CHARGER_H - -struct isp1704_charger_data { - void (*set_power)(bool on); - int enable_gpio; -}; - -#endif -- cgit v1.2.3 From 486efe9f8e30bac1e236f867df164f4966f3e207 Mon Sep 17 00:00:00 2001 From: Andrew Murray Date: Thu, 10 Jan 2019 13:53:24 +0000 Subject: perf/core: Add function to test for event exclusion flags Add a function that tests if any of the perf event exclusion flags are set on a given event. Signed-off-by: Andrew Murray Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Ivan Kokshaysky Cc: Linus Torvalds Cc: Mark Rutland Cc: Matt Turner Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Richard Henderson Cc: Russell King Cc: Sascha Hauer Cc: Shawn Guo Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Cc: robin.murphy@arm.com Cc: suzuki.poulose@arm.com Link: https://lkml.kernel.org/r/1547128414-50693-3-git-send-email-andrew.murray@arm.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1d5c551a5add..54a78d22f0a6 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1004,6 +1004,15 @@ perf_event__output_id_sample(struct perf_event *event, extern void perf_log_lost_samples(struct perf_event *event, u64 lost); +static inline bool event_has_any_exclude_flag(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + + return attr->exclude_idle || attr->exclude_user || + attr->exclude_kernel || attr->exclude_hv || + attr->exclude_guest || attr->exclude_host; +} + static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; -- cgit v1.2.3 From cc6795aeffea0a80d0baf9ad31ba926a6c42cef5 Mon Sep 17 00:00:00 2001 From: Andrew Murray Date: Thu, 10 Jan 2019 13:53:25 +0000 Subject: perf/core: Add PERF_PMU_CAP_NO_EXCLUDE for exclusion incapable PMUs Many PMU drivers do not have the capability to exclude counting events that occur in specific contexts such as idle, kernel, guest, etc. These drivers indicate this by returning an error in their event_init upon testing the events attribute flags. This approach is error prone and often inconsistent. Let's instead allow PMU drivers to advertise their inability to exclude based on context via a new capability: PERF_PMU_CAP_NO_EXCLUDE. This allows the perf core to reject requests for exclusion events where there is no support in the PMU. Signed-off-by: Andrew Murray Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Ivan Kokshaysky Cc: Linus Torvalds Cc: Mark Rutland Cc: Matt Turner Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Richard Henderson Cc: Russell King Cc: Sascha Hauer Cc: Shawn Guo Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Cc: robin.murphy@arm.com Cc: suzuki.poulose@arm.com Link: https://lkml.kernel.org/r/1547128414-50693-4-git-send-email-andrew.murray@arm.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + kernel/events/core.c | 9 +++++++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 54a78d22f0a6..cec02dc63b51 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -244,6 +244,7 @@ struct perf_event; #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 +#define PERF_PMU_CAP_NO_EXCLUDE 0x80 /** * struct pmu - generic performance monitoring unit diff --git a/kernel/events/core.c b/kernel/events/core.c index 3cd13a30f732..fbe59b793b36 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9772,6 +9772,15 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) if (ctx) perf_event_ctx_unlock(event->group_leader, ctx); + if (!ret) { + if (pmu->capabilities & PERF_PMU_CAP_NO_EXCLUDE && + event_has_any_exclude_flag(event)) { + if (event->destroy) + event->destroy(event); + ret = -EINVAL; + } + } + if (ret) module_put(pmu->module); -- cgit v1.2.3 From ad07c8ceb6631a83b62d405a61448bba92adac68 Mon Sep 17 00:00:00 2001 From: Andrew Murray Date: Thu, 10 Jan 2019 13:53:34 +0000 Subject: perf/core: Remove unused perf_flags Now that perf_flags is not used we remove it. Signed-off-by: Andrew Murray Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Ivan Kokshaysky Cc: Linus Torvalds Cc: Mark Rutland Cc: Matt Turner Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Richard Henderson Cc: Russell King Cc: Sascha Hauer Cc: Shawn Guo Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Cc: robin.murphy@arm.com Cc: suzuki.poulose@arm.com Link: https://lkml.kernel.org/r/1547128414-50693-13-git-send-email-andrew.murray@arm.com Signed-off-by: Ingo Molnar --- include/uapi/linux/perf_event.h | 2 -- tools/include/uapi/linux/perf_event.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 9de8780ac8d9..ea19b5d491bf 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -445,8 +445,6 @@ struct perf_event_query_bpf { __u32 ids[0]; }; -#define perf_flags(attr) (*(&(attr)->read_format + 1)) - /* * Ioctls that can be done on a perf event fd: */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 9de8780ac8d9..ea19b5d491bf 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -445,8 +445,6 @@ struct perf_event_query_bpf { __u32 ids[0]; }; -#define perf_flags(attr) (*(&(attr)->read_format + 1)) - /* * Ioctls that can be done on a perf event fd: */ -- cgit v1.2.3 From 8321be6a9df5c5cfbf3fb5f716caf8698a5a7016 Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Mon, 21 Jan 2019 14:17:37 +0530 Subject: cpufreq: Replace open-coded << with BIT() Minor clean-up to use BIT() and keep checkpatch happy. Clean up the comment formatting while we're at it to make it easier to read. Signed-off-by: Amit Kucheria Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c86d6d8bdfed..bd7fbd6a4478 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -346,14 +346,15 @@ struct cpufreq_driver { }; /* flags */ -#define CPUFREQ_STICKY (1 << 0) /* driver isn't removed even if - all ->init() calls failed */ -#define CPUFREQ_CONST_LOOPS (1 << 1) /* loops_per_jiffy or other - kernel "constants" aren't - affected by frequency - transitions */ -#define CPUFREQ_PM_NO_WARN (1 << 2) /* don't warn on suspend/resume - speed mismatches */ + +/* driver isn't removed even if all ->init() calls failed */ +#define CPUFREQ_STICKY BIT(0) + +/* loops_per_jiffy or other kernel "constants" aren't affected by frequency transitions */ +#define CPUFREQ_CONST_LOOPS BIT(1) + +/* don't warn on suspend/resume speed mismatches */ +#define CPUFREQ_PM_NO_WARN BIT(2) /* * This should be set by platforms having multiple clock-domains, i.e. @@ -361,14 +362,14 @@ struct cpufreq_driver { * be created in cpu/cpu/cpufreq/ directory and so they can use the same * governor with different tunables for different clusters. */ -#define CPUFREQ_HAVE_GOVERNOR_PER_POLICY (1 << 3) +#define CPUFREQ_HAVE_GOVERNOR_PER_POLICY BIT(3) /* * Driver will do POSTCHANGE notifications from outside of their ->target() * routine and so must set cpufreq_driver->flags with this flag, so that core * can handle them specially. */ -#define CPUFREQ_ASYNC_NOTIFICATION (1 << 4) +#define CPUFREQ_ASYNC_NOTIFICATION BIT(4) /* * Set by drivers which want cpufreq core to check if CPU is running at a @@ -377,13 +378,13 @@ struct cpufreq_driver { * from the table. And if that fails, we will stop further boot process by * issuing a BUG_ON(). */ -#define CPUFREQ_NEED_INITIAL_FREQ_CHECK (1 << 5) +#define CPUFREQ_NEED_INITIAL_FREQ_CHECK BIT(5) /* * Set by drivers to disallow use of governors with "dynamic_switching" flag * set. */ -#define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING (1 << 6) +#define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING BIT(6) int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -- cgit v1.2.3 From 2a6efbc6da5d248c4fbe7fdb7de7f3eff1de95a4 Mon Sep 17 00:00:00 2001 From: Fabrizio Castro Date: Wed, 16 Jan 2019 19:45:45 +0000 Subject: clk: renesas: r8a774c0: Add missing CANFD clock This patch adds the missing CANFD clock to the r8a774c0 specific clock driver. Signed-off-by: Fabrizio Castro Reviewed-by: Chris Paterson Reviewed-by: Simon Horman Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r8a774c0-cpg-mssr.c | 4 ++++ include/dt-bindings/clock/r8a774c0-cpg-mssr.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/drivers/clk/renesas/r8a774c0-cpg-mssr.c b/drivers/clk/renesas/r8a774c0-cpg-mssr.c index 10b96895d452..28bcc8105d57 100644 --- a/drivers/clk/renesas/r8a774c0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a774c0-cpg-mssr.c @@ -33,6 +33,7 @@ enum clk_ids { CLK_PLL1, CLK_PLL3, CLK_PLL0D4, + CLK_PLL0D6, CLK_PLL0D8, CLK_PLL0D20, CLK_PLL0D24, @@ -61,6 +62,7 @@ static const struct cpg_core_clk r8a774c0_core_clks[] __initconst = { DEF_FIXED(".pll0", CLK_PLL0, CLK_MAIN, 1, 100), DEF_FIXED(".pll0d4", CLK_PLL0D4, CLK_PLL0, 4, 1), + DEF_FIXED(".pll0d6", CLK_PLL0D6, CLK_PLL0, 6, 1), DEF_FIXED(".pll0d8", CLK_PLL0D8, CLK_PLL0, 8, 1), DEF_FIXED(".pll0d20", CLK_PLL0D20, CLK_PLL0, 20, 1), DEF_FIXED(".pll0d24", CLK_PLL0D24, CLK_PLL0, 24, 1), @@ -112,6 +114,7 @@ static const struct cpg_core_clk r8a774c0_core_clks[] __initconst = { DEF_GEN3_PE("s3d2c", R8A774C0_CLK_S3D2C, CLK_S3, 2, CLK_PE, 2), DEF_GEN3_PE("s3d4c", R8A774C0_CLK_S3D4C, CLK_S3, 4, CLK_PE, 4), + DEF_DIV6P1("canfd", R8A774C0_CLK_CANFD, CLK_PLL0D6, 0x244), DEF_DIV6P1("csi0", R8A774C0_CLK_CSI0, CLK_PLL1D2, 0x00c), DEF_DIV6P1("mso", R8A774C0_CLK_MSO, CLK_PLL1D2, 0x014), @@ -187,6 +190,7 @@ static const struct mssr_mod_clk r8a774c0_mod_clks[] __initconst = { DEF_MOD("gpio2", 910, R8A774C0_CLK_S3D4), DEF_MOD("gpio1", 911, R8A774C0_CLK_S3D4), DEF_MOD("gpio0", 912, R8A774C0_CLK_S3D4), + DEF_MOD("can-fd", 914, R8A774C0_CLK_S3D2), DEF_MOD("can-if1", 915, R8A774C0_CLK_S3D4), DEF_MOD("can-if0", 916, R8A774C0_CLK_S3D4), DEF_MOD("i2c6", 918, R8A774C0_CLK_S3D2), diff --git a/include/dt-bindings/clock/r8a774c0-cpg-mssr.h b/include/dt-bindings/clock/r8a774c0-cpg-mssr.h index 8fe51b6aca28..8ad9cd6be8e9 100644 --- a/include/dt-bindings/clock/r8a774c0-cpg-mssr.h +++ b/include/dt-bindings/clock/r8a774c0-cpg-mssr.h @@ -56,5 +56,6 @@ #define R8A774C0_CLK_CSI0 45 #define R8A774C0_CLK_CP 46 #define R8A774C0_CLK_CPEX 47 +#define R8A774C0_CLK_CANFD 48 #endif /* __DT_BINDINGS_CLOCK_R8A774C0_CPG_MSSR_H__ */ -- cgit v1.2.3 From 9d034e151b407cbd2c66bc4c48b423f814533374 Mon Sep 17 00:00:00 2001 From: Fabrizio Castro Date: Thu, 17 Jan 2019 14:54:14 +0000 Subject: clk: renesas: r8a774a1: Add missing CANFD clock This patch adds the missing CANFD clock to the r8a774a1 specific clock driver. Signed-off-by: Fabrizio Castro Reviewed-by: Chris Paterson Reviewed-by: Simon Horman Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r8a774a1-cpg-mssr.c | 2 ++ include/dt-bindings/clock/r8a774a1-cpg-mssr.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/drivers/clk/renesas/r8a774a1-cpg-mssr.c b/drivers/clk/renesas/r8a774a1-cpg-mssr.c index 10e852518870..e10374119a91 100644 --- a/drivers/clk/renesas/r8a774a1-cpg-mssr.c +++ b/drivers/clk/renesas/r8a774a1-cpg-mssr.c @@ -102,6 +102,7 @@ static const struct cpg_core_clk r8a774a1_core_clks[] __initconst = { DEF_FIXED("cp", R8A774A1_CLK_CP, CLK_EXTAL, 2, 1), DEF_FIXED("cpex", R8A774A1_CLK_CPEX, CLK_EXTAL, 2, 1), + DEF_DIV6P1("canfd", R8A774A1_CLK_CANFD, CLK_PLL1_DIV4, 0x244), DEF_DIV6P1("csi0", R8A774A1_CLK_CSI0, CLK_PLL1_DIV4, 0x00c), DEF_DIV6P1("mso", R8A774A1_CLK_MSO, CLK_PLL1_DIV4, 0x014), DEF_DIV6P1("hdmi", R8A774A1_CLK_HDMI, CLK_PLL1_DIV4, 0x250), @@ -191,6 +192,7 @@ static const struct mssr_mod_clk r8a774a1_mod_clks[] __initconst = { DEF_MOD("gpio2", 910, R8A774A1_CLK_S3D4), DEF_MOD("gpio1", 911, R8A774A1_CLK_S3D4), DEF_MOD("gpio0", 912, R8A774A1_CLK_S3D4), + DEF_MOD("can-fd", 914, R8A774A1_CLK_S3D2), DEF_MOD("can-if1", 915, R8A774A1_CLK_S3D4), DEF_MOD("can-if0", 916, R8A774A1_CLK_S3D4), DEF_MOD("i2c6", 918, R8A774A1_CLK_S0D6), diff --git a/include/dt-bindings/clock/r8a774a1-cpg-mssr.h b/include/dt-bindings/clock/r8a774a1-cpg-mssr.h index 9bc5d45ff4b5..e355363f40c2 100644 --- a/include/dt-bindings/clock/r8a774a1-cpg-mssr.h +++ b/include/dt-bindings/clock/r8a774a1-cpg-mssr.h @@ -54,5 +54,6 @@ #define R8A774A1_CLK_CPEX 43 #define R8A774A1_CLK_R 44 #define R8A774A1_CLK_OSC 45 +#define R8A774A1_CLK_CANFD 46 #endif /* __DT_BINDINGS_CLOCK_R8A774A1_CPG_MSSR_H__ */ -- cgit v1.2.3 From a41c4cb913b53bf74f1ec66a4b96057626c87009 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 13 Jan 2019 09:40:21 +0100 Subject: ALSA: pcm: Make PCM linked list consistent while re-grouping Make a common helper to re-assign the PCM link using list_move() instead of open code with manual list_del() and list_add_tail(). This assures the consistency and we can get rid of snd_pcm_group.count field -- its purpose is only to check whether the list is singular, and we can know it by list_is_singular() call now. Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 1 - sound/core/pcm_native.c | 34 ++++++++++++++++++++-------------- 2 files changed, 20 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index d6bd3caf6878..e1c747c70883 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -439,7 +439,6 @@ struct snd_pcm_group { /* keep linked substreams */ spinlock_t lock; struct mutex mutex; struct list_head substreams; - int count; }; struct pid; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 9e4e289e5703..1a56bb1ad780 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1131,6 +1131,13 @@ static int snd_pcm_action_single(const struct action_ops *ops, return res; } +static void snd_pcm_group_assign(struct snd_pcm_substream *substream, + struct snd_pcm_group *new_group) +{ + substream->group = new_group; + list_move(&substream->link_list, &new_group->substreams); +} + /* * Note: call with stream lock */ @@ -1995,14 +2002,10 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) goto _end; } if (!snd_pcm_stream_linked(substream)) { - substream->group = group; + snd_pcm_group_assign(substream, group); group = NULL; - list_add_tail(&substream->link_list, &substream->group->substreams); - substream->group->count = 1; } - list_add_tail(&substream1->link_list, &substream->group->substreams); - substream->group->count++; - substream1->group = substream->group; + snd_pcm_group_assign(substream1, substream->group); _end: write_unlock_irq(&snd_pcm_link_rwlock); up_write(&snd_pcm_link_rwsem); @@ -2015,14 +2018,13 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) static void relink_to_local(struct snd_pcm_substream *substream) { - substream->group = &substream->self_group; - INIT_LIST_HEAD(&substream->self_group.substreams); - list_add_tail(&substream->link_list, &substream->self_group.substreams); + snd_pcm_group_assign(substream, &substream->self_group); } static int snd_pcm_unlink(struct snd_pcm_substream *substream) { struct snd_pcm_substream *s; + struct snd_pcm_group *group; int res = 0; down_write_nonfifo(&snd_pcm_link_rwsem); @@ -2031,16 +2033,20 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) res = -EALREADY; goto _end; } - list_del(&substream->link_list); - substream->group->count--; - if (substream->group->count == 1) { /* detach the last stream, too */ + + group = substream->group; + + relink_to_local(substream); + + /* detach the last stream, too */ + if (list_is_singular(&group->substreams)) { snd_pcm_group_for_each_entry(s, substream) { relink_to_local(s); break; } - kfree(substream->group); + kfree(group); } - relink_to_local(substream); + _end: write_unlock_irq(&snd_pcm_link_rwlock); up_write(&snd_pcm_link_rwsem); -- cgit v1.2.3 From bbe7449e2599b58cf7b995461e2189998111f907 Mon Sep 17 00:00:00 2001 From: Phillip Potter Date: Mon, 21 Jan 2019 00:54:27 +0000 Subject: fs: common implementation of file type Many file systems use a copy&paste implementation of dirent to on-disk file type conversions. Create a common implementation to be used by file systems with some useful conversion helpers to reduce open coded file type conversions in file system code. Signed-off-by: Amir Goldstein Signed-off-by: Phillip Potter Signed-off-by: Jan Kara --- MAINTAINERS | 1 + fs/Makefile | 3 +- fs/fs_types.c | 105 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 17 +------- include/linux/fs_types.h | 75 +++++++++++++++++++++++++++++++++ 5 files changed, 184 insertions(+), 17 deletions(-) create mode 100644 fs/fs_types.c create mode 100644 include/linux/fs_types.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 51029a425dbe..0afaaf0aa6be 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5881,6 +5881,7 @@ L: linux-fsdevel@vger.kernel.org S: Maintained F: fs/* F: include/linux/fs.h +F: include/linux/fs_types.h F: include/uapi/linux/fs.h FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER diff --git a/fs/Makefile b/fs/Makefile index 293733f61594..23fcd8c164a3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -12,7 +12,8 @@ obj-y := open.o read_write.o file_table.o super.o \ attr.o bad_inode.o file.o filesystems.o namespace.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o splice.o sync.o utimes.o d_path.o \ - stack.o fs_struct.o statfs.o fs_pin.o nsfs.o + stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \ + fs_types.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o block_dev.o direct-io.o mpage.o diff --git a/fs/fs_types.c b/fs/fs_types.c new file mode 100644 index 000000000000..78365e5dc08c --- /dev/null +++ b/fs/fs_types.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include + +/* + * fs on-disk file type to dirent file type conversion + */ +static const unsigned char fs_dtype_by_ftype[FT_MAX] = { + [FT_UNKNOWN] = DT_UNKNOWN, + [FT_REG_FILE] = DT_REG, + [FT_DIR] = DT_DIR, + [FT_CHRDEV] = DT_CHR, + [FT_BLKDEV] = DT_BLK, + [FT_FIFO] = DT_FIFO, + [FT_SOCK] = DT_SOCK, + [FT_SYMLINK] = DT_LNK +}; + +/** + * fs_ftype_to_dtype() - fs on-disk file type to dirent type. + * @filetype: The on-disk file type to convert. + * + * This function converts the on-disk file type value (FT_*) to the directory + * entry type (DT_*). + * + * Context: Any context. + * Return: + * * DT_UNKNOWN - Unknown type + * * DT_FIFO - FIFO + * * DT_CHR - Character device + * * DT_DIR - Directory + * * DT_BLK - Block device + * * DT_REG - Regular file + * * DT_LNK - Symbolic link + * * DT_SOCK - Local-domain socket + */ +unsigned char fs_ftype_to_dtype(unsigned int filetype) +{ + if (filetype >= FT_MAX) + return DT_UNKNOWN; + + return fs_dtype_by_ftype[filetype]; +} +EXPORT_SYMBOL_GPL(fs_ftype_to_dtype); + +/* + * dirent file type to fs on-disk file type conversion + * Values not initialized explicitly are FT_UNKNOWN (0). + */ +static const unsigned char fs_ftype_by_dtype[DT_MAX] = { + [DT_REG] = FT_REG_FILE, + [DT_DIR] = FT_DIR, + [DT_LNK] = FT_SYMLINK, + [DT_CHR] = FT_CHRDEV, + [DT_BLK] = FT_BLKDEV, + [DT_FIFO] = FT_FIFO, + [DT_SOCK] = FT_SOCK, +}; + +/** + * fs_umode_to_ftype() - file mode to on-disk file type. + * @mode: The file mode to convert. + * + * This function converts the file mode value to the on-disk file type (FT_*). + * + * Context: Any context. + * Return: + * * FT_UNKNOWN - Unknown type + * * FT_REG_FILE - Regular file + * * FT_DIR - Directory + * * FT_CHRDEV - Character device + * * FT_BLKDEV - Block device + * * FT_FIFO - FIFO + * * FT_SOCK - Local-domain socket + * * FT_SYMLINK - Symbolic link + */ +unsigned char fs_umode_to_ftype(umode_t mode) +{ + return fs_ftype_by_dtype[S_DT(mode)]; +} +EXPORT_SYMBOL_GPL(fs_umode_to_ftype); + +/** + * fs_umode_to_dtype() - file mode to dirent file type. + * @mode: The file mode to convert. + * + * This function converts the file mode value to the directory + * entry type (DT_*). + * + * Context: Any context. + * Return: + * * DT_UNKNOWN - Unknown type + * * DT_FIFO - FIFO + * * DT_CHR - Character device + * * DT_DIR - Directory + * * DT_BLK - Block device + * * DT_REG - Regular file + * * DT_LNK - Symbolic link + * * DT_SOCK - Local-domain socket + */ +unsigned char fs_umode_to_dtype(umode_t mode) +{ + return fs_ftype_to_dtype(fs_umode_to_ftype(mode)); +} +EXPORT_SYMBOL_GPL(fs_umode_to_dtype); diff --git a/include/linux/fs.h b/include/linux/fs.h index 811c77743dad..92966678539d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -1699,22 +1700,6 @@ int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, u64 phys, u64 len, u32 flags); int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); -/* - * File types - * - * NOTE! These match bits 12..15 of stat.st_mode - * (ie "(i_mode >> 12) & 15"). - */ -#define DT_UNKNOWN 0 -#define DT_FIFO 1 -#define DT_CHR 2 -#define DT_DIR 4 -#define DT_BLK 6 -#define DT_REG 8 -#define DT_LNK 10 -#define DT_SOCK 12 -#define DT_WHT 14 - /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. diff --git a/include/linux/fs_types.h b/include/linux/fs_types.h new file mode 100644 index 000000000000..54816791196f --- /dev/null +++ b/include/linux/fs_types.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FS_TYPES_H +#define _LINUX_FS_TYPES_H + +/* + * This is a header for the common implementation of dirent + * to fs on-disk file type conversion. Although the fs on-disk + * bits are specific to every file system, in practice, many + * file systems use the exact same on-disk format to describe + * the lower 3 file type bits that represent the 7 POSIX file + * types. + * + * It is important to note that the definitions in this + * header MUST NOT change. This would break both the + * userspace ABI and the on-disk format of filesystems + * using this code. + * + * All those file systems can use this generic code for the + * conversions. + */ + +/* + * struct dirent file types + * exposed to user via getdents(2), readdir(3) + * + * These match bits 12..15 of stat.st_mode + * (ie "(i_mode >> 12) & 15"). + */ +#define S_DT_SHIFT 12 +#define S_DT(mode) (((mode) & S_IFMT) >> S_DT_SHIFT) +#define S_DT_MASK (S_IFMT >> S_DT_SHIFT) + +/* these are defined by POSIX and also present in glibc's dirent.h */ +#define DT_UNKNOWN 0 +#define DT_FIFO 1 +#define DT_CHR 2 +#define DT_DIR 4 +#define DT_BLK 6 +#define DT_REG 8 +#define DT_LNK 10 +#define DT_SOCK 12 +#define DT_WHT 14 + +#define DT_MAX (S_DT_MASK + 1) /* 16 */ + +/* + * fs on-disk file types. + * Only the low 3 bits are used for the POSIX file types. + * Other bits are reserved for fs private use. + * These definitions are shared and used by multiple filesystems, + * and MUST NOT change under any circumstances. + * + * Note that no fs currently stores the whiteout type on-disk, + * so whiteout dirents are exposed to user as DT_CHR. + */ +#define FT_UNKNOWN 0 +#define FT_REG_FILE 1 +#define FT_DIR 2 +#define FT_CHRDEV 3 +#define FT_BLKDEV 4 +#define FT_FIFO 5 +#define FT_SOCK 6 +#define FT_SYMLINK 7 + +#define FT_MAX 8 + +/* + * declarations for helper functions, accompanying implementation + * is in fs/fs_types.c + */ +extern unsigned char fs_ftype_to_dtype(unsigned int filetype); +extern unsigned char fs_umode_to_ftype(umode_t mode); +extern unsigned char fs_umode_to_dtype(umode_t mode); + +#endif -- cgit v1.2.3 From 386a35eb70569b3158392eb573fe42589a669da4 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 17 Jan 2019 11:33:42 -0200 Subject: media: tw9910.h: remove obsolete soc_camera.h include. This include isn't use anymore, so drop it. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/i2c/tw9910.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/media/i2c/tw9910.h b/include/media/i2c/tw9910.h index bec8f7bce745..2f93799d5a21 100644 --- a/include/media/i2c/tw9910.h +++ b/include/media/i2c/tw9910.h @@ -16,8 +16,6 @@ #ifndef __TW9910_H__ #define __TW9910_H__ -#include - /** * tw9910_mpout_pin - MPOUT (multi-purpose output) pin functions */ -- cgit v1.2.3 From 43a445f188e1a4d58e1be052b23afc9aacccbdd8 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 17 Jan 2019 11:41:23 -0200 Subject: media: sh_mobile_ceu_camera: remove obsolete soc_camera driver This driver got converted to not depend on soc_camera in commit 32e5a70dc8f4 ("media: platform: Add Renesas CEU driver"). There's no sense in keeping the old version there. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/soc_camera/Kconfig | 9 - drivers/media/platform/soc_camera/Makefile | 3 - .../platform/soc_camera/sh_mobile_ceu_camera.c | 1810 -------------------- include/media/drv-intf/sh_mobile_ceu.h | 29 - 4 files changed, 1851 deletions(-) delete mode 100644 drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c delete mode 100644 include/media/drv-intf/sh_mobile_ceu.h (limited to 'include') diff --git a/drivers/media/platform/soc_camera/Kconfig b/drivers/media/platform/soc_camera/Kconfig index 669d116b8f09..94907d0611d6 100644 --- a/drivers/media/platform/soc_camera/Kconfig +++ b/drivers/media/platform/soc_camera/Kconfig @@ -15,12 +15,3 @@ config SOC_CAMERA_PLATFORM depends on SOC_CAMERA help This is a generic SoC camera platform driver, useful for testing - -config VIDEO_SH_MOBILE_CEU - tristate "SuperH Mobile CEU Interface driver" - depends on VIDEO_DEV && SOC_CAMERA && HAVE_CLK - depends on ARCH_SHMOBILE || COMPILE_TEST - select VIDEOBUF2_DMA_CONTIG - select SOC_CAMERA_SCALE_CROP - ---help--- - This is a v4l2 driver for the SuperH Mobile CEU Interface diff --git a/drivers/media/platform/soc_camera/Makefile b/drivers/media/platform/soc_camera/Makefile index 07a451e8b228..aa4b855a0882 100644 --- a/drivers/media/platform/soc_camera/Makefile +++ b/drivers/media/platform/soc_camera/Makefile @@ -4,6 +4,3 @@ obj-$(CONFIG_SOC_CAMERA_SCALE_CROP) += soc_scale_crop.o # a platform subdevice driver stub, allowing to support cameras by adding a # couple of callback functions to the board code obj-$(CONFIG_SOC_CAMERA_PLATFORM) += soc_camera_platform.o - -# soc-camera host drivers have to be linked after camera drivers -obj-$(CONFIG_VIDEO_SH_MOBILE_CEU) += sh_mobile_ceu_camera.o diff --git a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c deleted file mode 100644 index 6803f744e307..000000000000 --- a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c +++ /dev/null @@ -1,1810 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * V4L2 Driver for SuperH Mobile CEU interface - * - * Copyright (C) 2008 Magnus Damm - * - * Based on V4L2 Driver for PXA camera host - "pxa_camera.c", - * - * Copyright (C) 2006, Sascha Hauer, Pengutronix - * Copyright (C) 2008, Guennadi Liakhovetski - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include - -#include "soc_scale_crop.h" - -/* register offsets for sh7722 / sh7723 */ - -#define CAPSR 0x00 /* Capture start register */ -#define CAPCR 0x04 /* Capture control register */ -#define CAMCR 0x08 /* Capture interface control register */ -#define CMCYR 0x0c /* Capture interface cycle register */ -#define CAMOR 0x10 /* Capture interface offset register */ -#define CAPWR 0x14 /* Capture interface width register */ -#define CAIFR 0x18 /* Capture interface input format register */ -#define CSTCR 0x20 /* Camera strobe control register (<= sh7722) */ -#define CSECR 0x24 /* Camera strobe emission count register (<= sh7722) */ -#define CRCNTR 0x28 /* CEU register control register */ -#define CRCMPR 0x2c /* CEU register forcible control register */ -#define CFLCR 0x30 /* Capture filter control register */ -#define CFSZR 0x34 /* Capture filter size clip register */ -#define CDWDR 0x38 /* Capture destination width register */ -#define CDAYR 0x3c /* Capture data address Y register */ -#define CDACR 0x40 /* Capture data address C register */ -#define CDBYR 0x44 /* Capture data bottom-field address Y register */ -#define CDBCR 0x48 /* Capture data bottom-field address C register */ -#define CBDSR 0x4c /* Capture bundle destination size register */ -#define CFWCR 0x5c /* Firewall operation control register */ -#define CLFCR 0x60 /* Capture low-pass filter control register */ -#define CDOCR 0x64 /* Capture data output control register */ -#define CDDCR 0x68 /* Capture data complexity level register */ -#define CDDAR 0x6c /* Capture data complexity level address register */ -#define CEIER 0x70 /* Capture event interrupt enable register */ -#define CETCR 0x74 /* Capture event flag clear register */ -#define CSTSR 0x7c /* Capture status register */ -#define CSRTR 0x80 /* Capture software reset register */ -#define CDSSR 0x84 /* Capture data size register */ -#define CDAYR2 0x90 /* Capture data address Y register 2 */ -#define CDACR2 0x94 /* Capture data address C register 2 */ -#define CDBYR2 0x98 /* Capture data bottom-field address Y register 2 */ -#define CDBCR2 0x9c /* Capture data bottom-field address C register 2 */ - -#undef DEBUG_GEOMETRY -#ifdef DEBUG_GEOMETRY -#define dev_geo dev_info -#else -#define dev_geo dev_dbg -#endif - -/* per video frame buffer */ -struct sh_mobile_ceu_buffer { - struct vb2_v4l2_buffer vb; /* v4l buffer must be first */ - struct list_head queue; -}; - -struct sh_mobile_ceu_dev { - struct soc_camera_host ici; - - unsigned int irq; - void __iomem *base; - size_t video_limit; - size_t buf_total; - - spinlock_t lock; /* Protects video buffer lists */ - struct list_head capture; - struct vb2_v4l2_buffer *active; - - struct sh_mobile_ceu_info *pdata; - struct completion complete; - - u32 cflcr; - - /* static max sizes either from platform data or default */ - int max_width; - int max_height; - - enum v4l2_field field; - int sequence; - unsigned long flags; - - unsigned int image_mode:1; - unsigned int is_16bit:1; - unsigned int frozen:1; -}; - -struct sh_mobile_ceu_cam { - /* CEU offsets within the camera output, before the CEU scaler */ - unsigned int ceu_left; - unsigned int ceu_top; - /* Client output, as seen by the CEU */ - unsigned int width; - unsigned int height; - /* - * User window from S_SELECTION / G_SELECTION, produced by client cropping and - * scaling, CEU scaling and CEU cropping, mapped back onto the client - * input window - */ - struct v4l2_rect subrect; - /* Camera cropping rectangle */ - struct v4l2_rect rect; - const struct soc_mbus_pixelfmt *extra_fmt; - u32 code; -}; - -static struct sh_mobile_ceu_buffer *to_ceu_vb(struct vb2_v4l2_buffer *vbuf) -{ - return container_of(vbuf, struct sh_mobile_ceu_buffer, vb); -} - -static void ceu_write(struct sh_mobile_ceu_dev *priv, - unsigned long reg_offs, u32 data) -{ - iowrite32(data, priv->base + reg_offs); -} - -static u32 ceu_read(struct sh_mobile_ceu_dev *priv, unsigned long reg_offs) -{ - return ioread32(priv->base + reg_offs); -} - -static int sh_mobile_ceu_soft_reset(struct sh_mobile_ceu_dev *pcdev) -{ - int i, success = 0; - - ceu_write(pcdev, CAPSR, 1 << 16); /* reset */ - - /* wait CSTSR.CPTON bit */ - for (i = 0; i < 1000; i++) { - if (!(ceu_read(pcdev, CSTSR) & 1)) { - success++; - break; - } - udelay(1); - } - - /* wait CAPSR.CPKIL bit */ - for (i = 0; i < 1000; i++) { - if (!(ceu_read(pcdev, CAPSR) & (1 << 16))) { - success++; - break; - } - udelay(1); - } - - if (2 != success) { - dev_warn(pcdev->ici.v4l2_dev.dev, "soft reset time out\n"); - return -EIO; - } - - return 0; -} - -/* - * Videobuf operations - */ - -/* - * .queue_setup() is called to check, whether the driver can accept the - * requested number of buffers and to fill in plane sizes - * for the current frame format if required - */ -static int sh_mobile_ceu_videobuf_setup(struct vb2_queue *vq, - unsigned int *count, unsigned int *num_planes, - unsigned int sizes[], struct device *alloc_devs[]) -{ - struct soc_camera_device *icd = soc_camera_from_vb2q(vq); - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - - if (!vq->num_buffers) - pcdev->sequence = 0; - - if (!*count) - *count = 2; - - /* Called from VIDIOC_REQBUFS or in compatibility mode */ - if (!*num_planes) - sizes[0] = icd->sizeimage; - else if (sizes[0] < icd->sizeimage) - return -EINVAL; - - /* If *num_planes != 0, we have already verified *count. */ - if (pcdev->video_limit) { - size_t size = PAGE_ALIGN(sizes[0]) * *count; - - if (size + pcdev->buf_total > pcdev->video_limit) - *count = (pcdev->video_limit - pcdev->buf_total) / - PAGE_ALIGN(sizes[0]); - } - - *num_planes = 1; - - dev_dbg(icd->parent, "count=%d, size=%u\n", *count, sizes[0]); - - return 0; -} - -#define CEU_CETCR_MAGIC 0x0317f313 /* acknowledge magical interrupt sources */ -#define CEU_CETCR_IGRW (1 << 4) /* prohibited register access interrupt bit */ -#define CEU_CEIER_CPEIE (1 << 0) /* one-frame capture end interrupt */ -#define CEU_CEIER_VBP (1 << 20) /* vbp error */ -#define CEU_CAPCR_CTNCP (1 << 16) /* continuous capture mode (if set) */ -#define CEU_CEIER_MASK (CEU_CEIER_CPEIE | CEU_CEIER_VBP) - - -/* - * return value doesn't reflex the success/failure to queue the new buffer, - * but rather the status of the previous buffer. - */ -static int sh_mobile_ceu_capture(struct sh_mobile_ceu_dev *pcdev) -{ - struct soc_camera_device *icd = pcdev->ici.icd; - dma_addr_t phys_addr_top, phys_addr_bottom; - unsigned long top1, top2; - unsigned long bottom1, bottom2; - u32 status; - bool planar; - int ret = 0; - - /* - * The hardware is _very_ picky about this sequence. Especially - * the CEU_CETCR_MAGIC value. It seems like we need to acknowledge - * several not-so-well documented interrupt sources in CETCR. - */ - ceu_write(pcdev, CEIER, ceu_read(pcdev, CEIER) & ~CEU_CEIER_MASK); - status = ceu_read(pcdev, CETCR); - ceu_write(pcdev, CETCR, ~status & CEU_CETCR_MAGIC); - if (!pcdev->frozen) - ceu_write(pcdev, CEIER, ceu_read(pcdev, CEIER) | CEU_CEIER_MASK); - ceu_write(pcdev, CAPCR, ceu_read(pcdev, CAPCR) & ~CEU_CAPCR_CTNCP); - ceu_write(pcdev, CETCR, CEU_CETCR_MAGIC ^ CEU_CETCR_IGRW); - - /* - * When a VBP interrupt occurs, a capture end interrupt does not occur - * and the image of that frame is not captured correctly. So, soft reset - * is needed here. - */ - if (status & CEU_CEIER_VBP) { - sh_mobile_ceu_soft_reset(pcdev); - ret = -EIO; - } - - if (pcdev->frozen) { - complete(&pcdev->complete); - return ret; - } - - if (!pcdev->active) - return ret; - - if (V4L2_FIELD_INTERLACED_BT == pcdev->field) { - top1 = CDBYR; - top2 = CDBCR; - bottom1 = CDAYR; - bottom2 = CDACR; - } else { - top1 = CDAYR; - top2 = CDACR; - bottom1 = CDBYR; - bottom2 = CDBCR; - } - - phys_addr_top = - vb2_dma_contig_plane_dma_addr(&pcdev->active->vb2_buf, 0); - - switch (icd->current_fmt->host_fmt->fourcc) { - case V4L2_PIX_FMT_NV12: - case V4L2_PIX_FMT_NV21: - case V4L2_PIX_FMT_NV16: - case V4L2_PIX_FMT_NV61: - planar = true; - break; - default: - planar = false; - } - - ceu_write(pcdev, top1, phys_addr_top); - if (V4L2_FIELD_NONE != pcdev->field) { - phys_addr_bottom = phys_addr_top + icd->bytesperline; - ceu_write(pcdev, bottom1, phys_addr_bottom); - } - - if (planar) { - phys_addr_top += icd->bytesperline * icd->user_height; - ceu_write(pcdev, top2, phys_addr_top); - if (V4L2_FIELD_NONE != pcdev->field) { - phys_addr_bottom = phys_addr_top + icd->bytesperline; - ceu_write(pcdev, bottom2, phys_addr_bottom); - } - } - - ceu_write(pcdev, CAPSR, 0x1); /* start capture */ - - return ret; -} - -static int sh_mobile_ceu_videobuf_prepare(struct vb2_buffer *vb) -{ - struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); - struct sh_mobile_ceu_buffer *buf = to_ceu_vb(vbuf); - - /* Added list head initialization on alloc */ - WARN(!list_empty(&buf->queue), "Buffer %p on queue!\n", vb); - - return 0; -} - -static void sh_mobile_ceu_videobuf_queue(struct vb2_buffer *vb) -{ - struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); - struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue); - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - struct sh_mobile_ceu_buffer *buf = to_ceu_vb(vbuf); - unsigned long size; - - size = icd->sizeimage; - - if (vb2_plane_size(vb, 0) < size) { - dev_err(icd->parent, "Buffer #%d too small (%lu < %lu)\n", - vb->index, vb2_plane_size(vb, 0), size); - goto error; - } - - vb2_set_plane_payload(vb, 0, size); - - dev_dbg(icd->parent, "%s (vb=0x%p) 0x%p %lu\n", __func__, - vb, vb2_plane_vaddr(vb, 0), vb2_get_plane_payload(vb, 0)); - -#ifdef DEBUG - /* - * This can be useful if you want to see if we actually fill - * the buffer with something - */ - if (vb2_plane_vaddr(vb, 0)) - memset(vb2_plane_vaddr(vb, 0), 0xaa, vb2_get_plane_payload(vb, 0)); -#endif - - spin_lock_irq(&pcdev->lock); - list_add_tail(&buf->queue, &pcdev->capture); - - if (!pcdev->active) { - /* - * Because there were no active buffer at this moment, - * we are not interested in the return value of - * sh_mobile_ceu_capture here. - */ - pcdev->active = vbuf; - sh_mobile_ceu_capture(pcdev); - } - spin_unlock_irq(&pcdev->lock); - - return; - -error: - vb2_buffer_done(vb, VB2_BUF_STATE_ERROR); -} - -static void sh_mobile_ceu_videobuf_release(struct vb2_buffer *vb) -{ - struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); - struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue); - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_buffer *buf = to_ceu_vb(vbuf); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - - spin_lock_irq(&pcdev->lock); - - if (pcdev->active == vbuf) { - /* disable capture (release DMA buffer), reset */ - ceu_write(pcdev, CAPSR, 1 << 16); - pcdev->active = NULL; - } - - /* - * Doesn't hurt also if the list is empty, but it hurts, if queuing the - * buffer failed, and .buf_init() hasn't been called - */ - if (buf->queue.next) - list_del_init(&buf->queue); - - pcdev->buf_total -= PAGE_ALIGN(vb2_plane_size(vb, 0)); - dev_dbg(icd->parent, "%s() %zu bytes buffers\n", __func__, - pcdev->buf_total); - - spin_unlock_irq(&pcdev->lock); -} - -static int sh_mobile_ceu_videobuf_init(struct vb2_buffer *vb) -{ - struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); - struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue); - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - - pcdev->buf_total += PAGE_ALIGN(vb2_plane_size(vb, 0)); - dev_dbg(icd->parent, "%s() %zu bytes buffers\n", __func__, - pcdev->buf_total); - - /* This is for locking debugging only */ - INIT_LIST_HEAD(&to_ceu_vb(vbuf)->queue); - return 0; -} - -static void sh_mobile_ceu_stop_streaming(struct vb2_queue *q) -{ - struct soc_camera_device *icd = soc_camera_from_vb2q(q); - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - struct list_head *buf_head, *tmp; - struct vb2_v4l2_buffer *vbuf; - - spin_lock_irq(&pcdev->lock); - - pcdev->active = NULL; - - list_for_each_safe(buf_head, tmp, &pcdev->capture) { - vbuf = &list_entry(buf_head, struct sh_mobile_ceu_buffer, - queue)->vb; - vb2_buffer_done(&vbuf->vb2_buf, VB2_BUF_STATE_DONE); - list_del_init(buf_head); - } - - spin_unlock_irq(&pcdev->lock); - - sh_mobile_ceu_soft_reset(pcdev); -} - -static const struct vb2_ops sh_mobile_ceu_videobuf_ops = { - .queue_setup = sh_mobile_ceu_videobuf_setup, - .buf_prepare = sh_mobile_ceu_videobuf_prepare, - .buf_queue = sh_mobile_ceu_videobuf_queue, - .buf_cleanup = sh_mobile_ceu_videobuf_release, - .buf_init = sh_mobile_ceu_videobuf_init, - .wait_prepare = vb2_ops_wait_prepare, - .wait_finish = vb2_ops_wait_finish, - .stop_streaming = sh_mobile_ceu_stop_streaming, -}; - -static irqreturn_t sh_mobile_ceu_irq(int irq, void *data) -{ - struct sh_mobile_ceu_dev *pcdev = data; - struct vb2_v4l2_buffer *vbuf; - int ret; - - spin_lock(&pcdev->lock); - - vbuf = pcdev->active; - if (!vbuf) - /* Stale interrupt from a released buffer */ - goto out; - - list_del_init(&to_ceu_vb(vbuf)->queue); - - if (!list_empty(&pcdev->capture)) - pcdev->active = &list_entry(pcdev->capture.next, - struct sh_mobile_ceu_buffer, queue)->vb; - else - pcdev->active = NULL; - - ret = sh_mobile_ceu_capture(pcdev); - vbuf->vb2_buf.timestamp = ktime_get_ns(); - if (!ret) { - vbuf->field = pcdev->field; - vbuf->sequence = pcdev->sequence++; - } - vb2_buffer_done(&vbuf->vb2_buf, - ret < 0 ? VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE); - -out: - spin_unlock(&pcdev->lock); - - return IRQ_HANDLED; -} - -static int sh_mobile_ceu_add_device(struct soc_camera_device *icd) -{ - dev_info(icd->parent, - "SuperH Mobile CEU driver attached to camera %d\n", - icd->devnum); - - return 0; -} - -static void sh_mobile_ceu_remove_device(struct soc_camera_device *icd) -{ - dev_info(icd->parent, - "SuperH Mobile CEU driver detached from camera %d\n", - icd->devnum); -} - -/* Called with .host_lock held */ -static int sh_mobile_ceu_clock_start(struct soc_camera_host *ici) -{ - struct sh_mobile_ceu_dev *pcdev = ici->priv; - - pm_runtime_get_sync(ici->v4l2_dev.dev); - - pcdev->buf_total = 0; - - sh_mobile_ceu_soft_reset(pcdev); - - return 0; -} - -/* Called with .host_lock held */ -static void sh_mobile_ceu_clock_stop(struct soc_camera_host *ici) -{ - struct sh_mobile_ceu_dev *pcdev = ici->priv; - - /* disable capture, disable interrupts */ - ceu_write(pcdev, CEIER, 0); - sh_mobile_ceu_soft_reset(pcdev); - - /* make sure active buffer is canceled */ - spin_lock_irq(&pcdev->lock); - if (pcdev->active) { - list_del_init(&to_ceu_vb(pcdev->active)->queue); - vb2_buffer_done(&pcdev->active->vb2_buf, VB2_BUF_STATE_ERROR); - pcdev->active = NULL; - } - spin_unlock_irq(&pcdev->lock); - - pm_runtime_put(ici->v4l2_dev.dev); -} - -/* - * See chapter 29.4.12 "Capture Filter Control Register (CFLCR)" - * in SH7722 Hardware Manual - */ -static unsigned int size_dst(unsigned int src, unsigned int scale) -{ - unsigned int mant_pre = scale >> 12; - if (!src || !scale) - return src; - return ((mant_pre + 2 * (src - 1)) / (2 * mant_pre) - 1) * - mant_pre * 4096 / scale + 1; -} - -static u16 calc_scale(unsigned int src, unsigned int *dst) -{ - u16 scale; - - if (src == *dst) - return 0; - - scale = (src * 4096 / *dst) & ~7; - - while (scale > 4096 && size_dst(src, scale) < *dst) - scale -= 8; - - *dst = size_dst(src, scale); - - return scale; -} - -/* rect is guaranteed to not exceed the scaled camera rectangle */ -static void sh_mobile_ceu_set_rect(struct soc_camera_device *icd) -{ - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_cam *cam = icd->host_priv; - struct sh_mobile_ceu_dev *pcdev = ici->priv; - unsigned int height, width, cdwdr_width, in_width, in_height; - unsigned int left_offset, top_offset; - u32 camor; - - dev_geo(icd->parent, "Crop %ux%u@%u:%u\n", - icd->user_width, icd->user_height, cam->ceu_left, cam->ceu_top); - - left_offset = cam->ceu_left; - top_offset = cam->ceu_top; - - WARN_ON(icd->user_width & 3 || icd->user_height & 3); - - width = icd->user_width; - - if (pcdev->image_mode) { - in_width = cam->width; - if (!pcdev->is_16bit) { - in_width *= 2; - left_offset *= 2; - } - } else { - unsigned int w_factor; - - switch (icd->current_fmt->host_fmt->packing) { - case SOC_MBUS_PACKING_2X8_PADHI: - w_factor = 2; - break; - default: - w_factor = 1; - } - - in_width = cam->width * w_factor; - left_offset *= w_factor; - } - - cdwdr_width = icd->bytesperline; - - height = icd->user_height; - in_height = cam->height; - if (V4L2_FIELD_NONE != pcdev->field) { - height = (height / 2) & ~3; - in_height /= 2; - top_offset /= 2; - cdwdr_width *= 2; - } - - /* Set CAMOR, CAPWR, CFSZR, take care of CDWDR */ - camor = left_offset | (top_offset << 16); - - dev_geo(icd->parent, - "CAMOR 0x%x, CAPWR 0x%x, CFSZR 0x%x, CDWDR 0x%x\n", camor, - (in_height << 16) | in_width, (height << 16) | width, - cdwdr_width); - - ceu_write(pcdev, CAMOR, camor); - ceu_write(pcdev, CAPWR, (in_height << 16) | in_width); - /* CFSZR clipping is applied _after_ the scaling filter (CFLCR) */ - ceu_write(pcdev, CFSZR, (height << 16) | width); - ceu_write(pcdev, CDWDR, cdwdr_width); -} - -static u32 capture_save_reset(struct sh_mobile_ceu_dev *pcdev) -{ - u32 capsr = ceu_read(pcdev, CAPSR); - ceu_write(pcdev, CAPSR, 1 << 16); /* reset, stop capture */ - return capsr; -} - -static void capture_restore(struct sh_mobile_ceu_dev *pcdev, u32 capsr) -{ - unsigned long timeout = jiffies + 10 * HZ; - - /* - * Wait until the end of the current frame. It can take a long time, - * but if it has been aborted by a CAPSR reset, it shoule exit sooner. - */ - while ((ceu_read(pcdev, CSTSR) & 1) && time_before(jiffies, timeout)) - msleep(1); - - if (time_after(jiffies, timeout)) { - dev_err(pcdev->ici.v4l2_dev.dev, - "Timeout waiting for frame end! Interface problem?\n"); - return; - } - - /* Wait until reset clears, this shall not hang... */ - while (ceu_read(pcdev, CAPSR) & (1 << 16)) - udelay(10); - - /* Anything to restore? */ - if (capsr & ~(1 << 16)) - ceu_write(pcdev, CAPSR, capsr); -} - -#define CEU_BUS_FLAGS (V4L2_MBUS_MASTER | \ - V4L2_MBUS_PCLK_SAMPLE_RISING | \ - V4L2_MBUS_HSYNC_ACTIVE_HIGH | \ - V4L2_MBUS_HSYNC_ACTIVE_LOW | \ - V4L2_MBUS_VSYNC_ACTIVE_HIGH | \ - V4L2_MBUS_VSYNC_ACTIVE_LOW | \ - V4L2_MBUS_DATA_ACTIVE_HIGH) - -/* Capture is not running, no interrupts, no locking needed */ -static int sh_mobile_ceu_set_bus_param(struct soc_camera_device *icd) -{ - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - struct v4l2_subdev *sd = soc_camera_to_subdev(icd); - struct sh_mobile_ceu_cam *cam = icd->host_priv; - struct v4l2_mbus_config cfg = {.type = V4L2_MBUS_PARALLEL,}; - unsigned long value, common_flags = CEU_BUS_FLAGS; - u32 capsr = capture_save_reset(pcdev); - unsigned int yuv_lineskip; - int ret; - - /* - * If the client doesn't implement g_mbus_config, we just use our - * platform data - */ - ret = v4l2_subdev_call(sd, video, g_mbus_config, &cfg); - if (!ret) { - common_flags = soc_mbus_config_compatible(&cfg, - common_flags); - if (!common_flags) - return -EINVAL; - } else if (ret != -ENOIOCTLCMD) { - return ret; - } - - /* Make choises, based on platform preferences */ - if ((common_flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH) && - (common_flags & V4L2_MBUS_HSYNC_ACTIVE_LOW)) { - if (pcdev->flags & SH_CEU_FLAG_HSYNC_LOW) - common_flags &= ~V4L2_MBUS_HSYNC_ACTIVE_HIGH; - else - common_flags &= ~V4L2_MBUS_HSYNC_ACTIVE_LOW; - } - - if ((common_flags & V4L2_MBUS_VSYNC_ACTIVE_HIGH) && - (common_flags & V4L2_MBUS_VSYNC_ACTIVE_LOW)) { - if (pcdev->flags & SH_CEU_FLAG_VSYNC_LOW) - common_flags &= ~V4L2_MBUS_VSYNC_ACTIVE_HIGH; - else - common_flags &= ~V4L2_MBUS_VSYNC_ACTIVE_LOW; - } - - cfg.flags = common_flags; - ret = v4l2_subdev_call(sd, video, s_mbus_config, &cfg); - if (ret < 0 && ret != -ENOIOCTLCMD) - return ret; - - if (icd->current_fmt->host_fmt->bits_per_sample > 8) - pcdev->is_16bit = 1; - else - pcdev->is_16bit = 0; - - ceu_write(pcdev, CRCNTR, 0); - ceu_write(pcdev, CRCMPR, 0); - - value = 0x00000010; /* data fetch by default */ - yuv_lineskip = 0x10; - - switch (icd->current_fmt->host_fmt->fourcc) { - case V4L2_PIX_FMT_NV12: - case V4L2_PIX_FMT_NV21: - /* convert 4:2:2 -> 4:2:0 */ - yuv_lineskip = 0; /* skip for NV12/21, no skip for NV16/61 */ - /* fall-through */ - case V4L2_PIX_FMT_NV16: - case V4L2_PIX_FMT_NV61: - switch (cam->code) { - case MEDIA_BUS_FMT_UYVY8_2X8: - value = 0x00000000; /* Cb0, Y0, Cr0, Y1 */ - break; - case MEDIA_BUS_FMT_VYUY8_2X8: - value = 0x00000100; /* Cr0, Y0, Cb0, Y1 */ - break; - case MEDIA_BUS_FMT_YUYV8_2X8: - value = 0x00000200; /* Y0, Cb0, Y1, Cr0 */ - break; - case MEDIA_BUS_FMT_YVYU8_2X8: - value = 0x00000300; /* Y0, Cr0, Y1, Cb0 */ - break; - default: - BUG(); - } - } - - if (icd->current_fmt->host_fmt->fourcc == V4L2_PIX_FMT_NV21 || - icd->current_fmt->host_fmt->fourcc == V4L2_PIX_FMT_NV61) - value ^= 0x00000100; /* swap U, V to change from NV1x->NVx1 */ - - value |= common_flags & V4L2_MBUS_VSYNC_ACTIVE_LOW ? 1 << 1 : 0; - value |= common_flags & V4L2_MBUS_HSYNC_ACTIVE_LOW ? 1 << 0 : 0; - - if (pcdev->is_16bit) - value |= 1 << 12; - else if (pcdev->flags & SH_CEU_FLAG_LOWER_8BIT) - value |= 2 << 12; - - ceu_write(pcdev, CAMCR, value); - - ceu_write(pcdev, CAPCR, 0x00300000); - - switch (pcdev->field) { - case V4L2_FIELD_INTERLACED_TB: - value = 0x101; - break; - case V4L2_FIELD_INTERLACED_BT: - value = 0x102; - break; - default: - value = 0; - break; - } - ceu_write(pcdev, CAIFR, value); - - sh_mobile_ceu_set_rect(icd); - mdelay(1); - - dev_geo(icd->parent, "CFLCR 0x%x\n", pcdev->cflcr); - ceu_write(pcdev, CFLCR, pcdev->cflcr); - - /* - * A few words about byte order (observed in Big Endian mode) - * - * In data fetch mode bytes are received in chunks of 8 bytes. - * D0, D1, D2, D3, D4, D5, D6, D7 (D0 received first) - * - * The data is however by default written to memory in reverse order: - * D7, D6, D5, D4, D3, D2, D1, D0 (D7 written to lowest byte) - * - * The lowest three bits of CDOCR allows us to do swapping, - * using 7 we swap the data bytes to match the incoming order: - * D0, D1, D2, D3, D4, D5, D6, D7 - */ - value = 0x00000007 | yuv_lineskip; - - ceu_write(pcdev, CDOCR, value); - ceu_write(pcdev, CFWCR, 0); /* keep "datafetch firewall" disabled */ - - capture_restore(pcdev, capsr); - - /* not in bundle mode: skip CBDSR, CDAYR2, CDACR2, CDBYR2, CDBCR2 */ - return 0; -} - -static int sh_mobile_ceu_try_bus_param(struct soc_camera_device *icd, - unsigned char buswidth) -{ - struct v4l2_subdev *sd = soc_camera_to_subdev(icd); - unsigned long common_flags = CEU_BUS_FLAGS; - struct v4l2_mbus_config cfg = {.type = V4L2_MBUS_PARALLEL,}; - int ret; - - ret = v4l2_subdev_call(sd, video, g_mbus_config, &cfg); - if (!ret) - common_flags = soc_mbus_config_compatible(&cfg, - common_flags); - else if (ret != -ENOIOCTLCMD) - return ret; - - if (!common_flags || buswidth > 16) - return -EINVAL; - - return 0; -} - -static const struct soc_mbus_pixelfmt sh_mobile_ceu_formats[] = { - { - .fourcc = V4L2_PIX_FMT_NV12, - .name = "NV12", - .bits_per_sample = 8, - .packing = SOC_MBUS_PACKING_1_5X8, - .order = SOC_MBUS_ORDER_LE, - .layout = SOC_MBUS_LAYOUT_PLANAR_2Y_C, - }, { - .fourcc = V4L2_PIX_FMT_NV21, - .name = "NV21", - .bits_per_sample = 8, - .packing = SOC_MBUS_PACKING_1_5X8, - .order = SOC_MBUS_ORDER_LE, - .layout = SOC_MBUS_LAYOUT_PLANAR_2Y_C, - }, { - .fourcc = V4L2_PIX_FMT_NV16, - .name = "NV16", - .bits_per_sample = 8, - .packing = SOC_MBUS_PACKING_2X8_PADHI, - .order = SOC_MBUS_ORDER_LE, - .layout = SOC_MBUS_LAYOUT_PLANAR_Y_C, - }, { - .fourcc = V4L2_PIX_FMT_NV61, - .name = "NV61", - .bits_per_sample = 8, - .packing = SOC_MBUS_PACKING_2X8_PADHI, - .order = SOC_MBUS_ORDER_LE, - .layout = SOC_MBUS_LAYOUT_PLANAR_Y_C, - }, -}; - -/* This will be corrected as we get more formats */ -static bool sh_mobile_ceu_packing_supported(const struct soc_mbus_pixelfmt *fmt) -{ - return fmt->packing == SOC_MBUS_PACKING_NONE || - (fmt->bits_per_sample == 8 && - fmt->packing == SOC_MBUS_PACKING_1_5X8) || - (fmt->bits_per_sample == 8 && - fmt->packing == SOC_MBUS_PACKING_2X8_PADHI) || - (fmt->bits_per_sample > 8 && - fmt->packing == SOC_MBUS_PACKING_EXTEND16); -} - -static struct soc_camera_device *ctrl_to_icd(struct v4l2_ctrl *ctrl) -{ - return container_of(ctrl->handler, struct soc_camera_device, - ctrl_handler); -} - -static int sh_mobile_ceu_s_ctrl(struct v4l2_ctrl *ctrl) -{ - struct soc_camera_device *icd = ctrl_to_icd(ctrl); - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - - switch (ctrl->id) { - case V4L2_CID_SHARPNESS: - switch (icd->current_fmt->host_fmt->fourcc) { - case V4L2_PIX_FMT_NV12: - case V4L2_PIX_FMT_NV21: - case V4L2_PIX_FMT_NV16: - case V4L2_PIX_FMT_NV61: - ceu_write(pcdev, CLFCR, !ctrl->val); - return 0; - } - break; - } - - return -EINVAL; -} - -static const struct v4l2_ctrl_ops sh_mobile_ceu_ctrl_ops = { - .s_ctrl = sh_mobile_ceu_s_ctrl, -}; - -static int sh_mobile_ceu_get_formats(struct soc_camera_device *icd, unsigned int idx, - struct soc_camera_format_xlate *xlate) -{ - struct v4l2_subdev *sd = soc_camera_to_subdev(icd); - struct device *dev = icd->parent; - struct soc_camera_host *ici = to_soc_camera_host(dev); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - int ret, k, n; - int formats = 0; - struct sh_mobile_ceu_cam *cam; - struct v4l2_subdev_mbus_code_enum code = { - .which = V4L2_SUBDEV_FORMAT_ACTIVE, - .index = idx, - }; - const struct soc_mbus_pixelfmt *fmt; - - ret = v4l2_subdev_call(sd, pad, enum_mbus_code, NULL, &code); - if (ret < 0) - /* No more formats */ - return 0; - - fmt = soc_mbus_get_fmtdesc(code.code); - if (!fmt) { - dev_warn(dev, "unsupported format code #%u: %d\n", idx, code.code); - return 0; - } - - ret = sh_mobile_ceu_try_bus_param(icd, fmt->bits_per_sample); - if (ret < 0) - return 0; - - if (!icd->host_priv) { - struct v4l2_subdev_format fmt = { - .which = V4L2_SUBDEV_FORMAT_ACTIVE, - }; - struct v4l2_mbus_framefmt *mf = &fmt.format; - struct v4l2_rect rect; - int shift = 0; - - /* Add our control */ - v4l2_ctrl_new_std(&icd->ctrl_handler, &sh_mobile_ceu_ctrl_ops, - V4L2_CID_SHARPNESS, 0, 1, 1, 1); - if (icd->ctrl_handler.error) - return icd->ctrl_handler.error; - - /* FIXME: subwindow is lost between close / open */ - - /* Cache current client geometry */ - ret = soc_camera_client_g_rect(sd, &rect); - if (ret < 0) - return ret; - - /* First time */ - ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt); - if (ret < 0) - return ret; - - /* - * All currently existing CEU implementations support 2560x1920 - * or larger frames. If the sensor is proposing too big a frame, - * don't bother with possibly supportred by the CEU larger - * sizes, just try VGA multiples. If needed, this can be - * adjusted in the future. - */ - while ((mf->width > pcdev->max_width || - mf->height > pcdev->max_height) && shift < 4) { - /* Try 2560x1920, 1280x960, 640x480, 320x240 */ - mf->width = 2560 >> shift; - mf->height = 1920 >> shift; - ret = v4l2_device_call_until_err(sd->v4l2_dev, - soc_camera_grp_id(icd), pad, - set_fmt, NULL, &fmt); - if (ret < 0) - return ret; - shift++; - } - - if (shift == 4) { - dev_err(dev, "Failed to configure the client below %ux%x\n", - mf->width, mf->height); - return -EIO; - } - - dev_geo(dev, "camera fmt %ux%u\n", mf->width, mf->height); - - cam = kzalloc(sizeof(*cam), GFP_KERNEL); - if (!cam) - return -ENOMEM; - - /* We are called with current camera crop, initialise subrect with it */ - cam->rect = rect; - cam->subrect = rect; - - cam->width = mf->width; - cam->height = mf->height; - - icd->host_priv = cam; - } else { - cam = icd->host_priv; - } - - /* Beginning of a pass */ - if (!idx) - cam->extra_fmt = NULL; - - switch (code.code) { - case MEDIA_BUS_FMT_UYVY8_2X8: - case MEDIA_BUS_FMT_VYUY8_2X8: - case MEDIA_BUS_FMT_YUYV8_2X8: - case MEDIA_BUS_FMT_YVYU8_2X8: - if (cam->extra_fmt) - break; - - /* - * Our case is simple so far: for any of the above four camera - * formats we add all our four synthesized NV* formats, so, - * just marking the device with a single flag suffices. If - * the format generation rules are more complex, you would have - * to actually hang your already added / counted formats onto - * the host_priv pointer and check whether the format you're - * going to add now is already there. - */ - cam->extra_fmt = sh_mobile_ceu_formats; - - n = ARRAY_SIZE(sh_mobile_ceu_formats); - formats += n; - for (k = 0; xlate && k < n; k++) { - xlate->host_fmt = &sh_mobile_ceu_formats[k]; - xlate->code = code.code; - xlate++; - dev_dbg(dev, "Providing format %s using code %d\n", - sh_mobile_ceu_formats[k].name, code.code); - } - break; - default: - if (!sh_mobile_ceu_packing_supported(fmt)) - return 0; - } - - /* Generic pass-through */ - formats++; - if (xlate) { - xlate->host_fmt = fmt; - xlate->code = code.code; - xlate++; - dev_dbg(dev, "Providing format %s in pass-through mode\n", - fmt->name); - } - - return formats; -} - -static void sh_mobile_ceu_put_formats(struct soc_camera_device *icd) -{ - kfree(icd->host_priv); - icd->host_priv = NULL; -} - -#define scale_down(size, scale) soc_camera_shift_scale(size, 12, scale) -#define calc_generic_scale(in, out) soc_camera_calc_scale(in, 12, out) - -/* - * CEU can scale and crop, but we don't want to waste bandwidth and kill the - * framerate by always requesting the maximum image from the client. See - * Documentation/media/v4l-drivers/sh_mobile_ceu_camera.rst for a description of - * scaling and cropping algorithms and for the meaning of referenced here steps. - */ -static int sh_mobile_ceu_set_selection(struct soc_camera_device *icd, - struct v4l2_selection *sel) -{ - struct v4l2_rect *rect = &sel->r; - struct device *dev = icd->parent; - struct soc_camera_host *ici = to_soc_camera_host(dev); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - struct v4l2_selection cam_sel; - struct sh_mobile_ceu_cam *cam = icd->host_priv; - struct v4l2_rect *cam_rect = &cam_sel.r; - struct v4l2_subdev *sd = soc_camera_to_subdev(icd); - struct v4l2_subdev_format fmt = { - .which = V4L2_SUBDEV_FORMAT_ACTIVE, - }; - struct v4l2_mbus_framefmt *mf = &fmt.format; - unsigned int scale_cam_h, scale_cam_v, scale_ceu_h, scale_ceu_v, - out_width, out_height; - int interm_width, interm_height; - u32 capsr, cflcr; - int ret; - - dev_geo(dev, "S_SELECTION(%ux%u@%u:%u)\n", rect->width, rect->height, - rect->left, rect->top); - - /* During camera cropping its output window can change too, stop CEU */ - capsr = capture_save_reset(pcdev); - dev_dbg(dev, "CAPSR 0x%x, CFLCR 0x%x\n", capsr, pcdev->cflcr); - - /* - * 1. - 2. Apply iterative camera S_SELECTION for new input window, read back - * actual camera rectangle. - */ - ret = soc_camera_client_s_selection(sd, sel, &cam_sel, - &cam->rect, &cam->subrect); - if (ret < 0) - return ret; - - dev_geo(dev, "1-2: camera cropped to %ux%u@%u:%u\n", - cam_rect->width, cam_rect->height, - cam_rect->left, cam_rect->top); - - /* On success cam_crop contains current camera crop */ - - /* 3. Retrieve camera output window */ - ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt); - if (ret < 0) - return ret; - - if (mf->width > pcdev->max_width || mf->height > pcdev->max_height) - return -EINVAL; - - /* 4. Calculate camera scales */ - scale_cam_h = calc_generic_scale(cam_rect->width, mf->width); - scale_cam_v = calc_generic_scale(cam_rect->height, mf->height); - - /* Calculate intermediate window */ - interm_width = scale_down(rect->width, scale_cam_h); - interm_height = scale_down(rect->height, scale_cam_v); - - if (interm_width < icd->user_width) { - u32 new_scale_h; - - new_scale_h = calc_generic_scale(rect->width, icd->user_width); - - mf->width = scale_down(cam_rect->width, new_scale_h); - } - - if (interm_height < icd->user_height) { - u32 new_scale_v; - - new_scale_v = calc_generic_scale(rect->height, icd->user_height); - - mf->height = scale_down(cam_rect->height, new_scale_v); - } - - if (interm_width < icd->user_width || interm_height < icd->user_height) { - ret = v4l2_device_call_until_err(sd->v4l2_dev, - soc_camera_grp_id(icd), pad, - set_fmt, NULL, &fmt); - if (ret < 0) - return ret; - - dev_geo(dev, "New camera output %ux%u\n", mf->width, mf->height); - scale_cam_h = calc_generic_scale(cam_rect->width, mf->width); - scale_cam_v = calc_generic_scale(cam_rect->height, mf->height); - interm_width = scale_down(rect->width, scale_cam_h); - interm_height = scale_down(rect->height, scale_cam_v); - } - - /* Cache camera output window */ - cam->width = mf->width; - cam->height = mf->height; - - if (pcdev->image_mode) { - out_width = min(interm_width, icd->user_width); - out_height = min(interm_height, icd->user_height); - } else { - out_width = interm_width; - out_height = interm_height; - } - - /* - * 5. Calculate CEU scales from camera scales from results of (5) and - * the user window - */ - scale_ceu_h = calc_scale(interm_width, &out_width); - scale_ceu_v = calc_scale(interm_height, &out_height); - - dev_geo(dev, "5: CEU scales %u:%u\n", scale_ceu_h, scale_ceu_v); - - /* Apply CEU scales. */ - cflcr = scale_ceu_h | (scale_ceu_v << 16); - if (cflcr != pcdev->cflcr) { - pcdev->cflcr = cflcr; - ceu_write(pcdev, CFLCR, cflcr); - } - - icd->user_width = out_width & ~3; - icd->user_height = out_height & ~3; - /* Offsets are applied at the CEU scaling filter input */ - cam->ceu_left = scale_down(rect->left - cam_rect->left, scale_cam_h) & ~1; - cam->ceu_top = scale_down(rect->top - cam_rect->top, scale_cam_v) & ~1; - - /* 6. Use CEU cropping to crop to the new window. */ - sh_mobile_ceu_set_rect(icd); - - cam->subrect = *rect; - - dev_geo(dev, "6: CEU cropped to %ux%u@%u:%u\n", - icd->user_width, icd->user_height, - cam->ceu_left, cam->ceu_top); - - /* Restore capture. The CE bit can be cleared by the hardware */ - if (pcdev->active) - capsr |= 1; - capture_restore(pcdev, capsr); - - /* Even if only camera cropping succeeded */ - return ret; -} - -static int sh_mobile_ceu_get_selection(struct soc_camera_device *icd, - struct v4l2_selection *sel) -{ - struct sh_mobile_ceu_cam *cam = icd->host_priv; - - sel->r = cam->subrect; - - return 0; -} - -/* Similar to set_crop multistage iterative algorithm */ -static int sh_mobile_ceu_set_fmt(struct soc_camera_device *icd, - struct v4l2_format *f) -{ - struct device *dev = icd->parent; - struct soc_camera_host *ici = to_soc_camera_host(dev); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - struct sh_mobile_ceu_cam *cam = icd->host_priv; - struct v4l2_pix_format *pix = &f->fmt.pix; - struct v4l2_mbus_framefmt mf; - __u32 pixfmt = pix->pixelformat; - const struct soc_camera_format_xlate *xlate; - unsigned int ceu_sub_width = pcdev->max_width, - ceu_sub_height = pcdev->max_height; - u16 scale_v, scale_h; - int ret; - bool image_mode; - enum v4l2_field field; - - switch (pix->field) { - default: - pix->field = V4L2_FIELD_NONE; - /* fall-through */ - case V4L2_FIELD_INTERLACED_TB: - case V4L2_FIELD_INTERLACED_BT: - case V4L2_FIELD_NONE: - field = pix->field; - break; - case V4L2_FIELD_INTERLACED: - field = V4L2_FIELD_INTERLACED_TB; - break; - } - - xlate = soc_camera_xlate_by_fourcc(icd, pixfmt); - if (!xlate) { - dev_warn(dev, "Format %x not found\n", pixfmt); - return -EINVAL; - } - - /* 1.-4. Calculate desired client output geometry */ - soc_camera_calc_client_output(icd, &cam->rect, &cam->subrect, pix, &mf, 12); - mf.field = pix->field; - mf.colorspace = pix->colorspace; - mf.code = xlate->code; - - switch (pixfmt) { - case V4L2_PIX_FMT_NV12: - case V4L2_PIX_FMT_NV21: - case V4L2_PIX_FMT_NV16: - case V4L2_PIX_FMT_NV61: - image_mode = true; - break; - default: - image_mode = false; - } - - dev_geo(dev, "S_FMT(pix=0x%x, fld 0x%x, code 0x%x, %ux%u)\n", pixfmt, mf.field, mf.code, - pix->width, pix->height); - - dev_geo(dev, "4: request camera output %ux%u\n", mf.width, mf.height); - - /* 5. - 9. */ - ret = soc_camera_client_scale(icd, &cam->rect, &cam->subrect, - &mf, &ceu_sub_width, &ceu_sub_height, - image_mode && V4L2_FIELD_NONE == field, 12); - - dev_geo(dev, "5-9: client scale return %d\n", ret); - - /* Done with the camera. Now see if we can improve the result */ - - dev_geo(dev, "fmt %ux%u, requested %ux%u\n", - mf.width, mf.height, pix->width, pix->height); - if (ret < 0) - return ret; - - if (mf.code != xlate->code) - return -EINVAL; - - /* 9. Prepare CEU crop */ - cam->width = mf.width; - cam->height = mf.height; - - /* 10. Use CEU scaling to scale to the requested user window. */ - - /* We cannot scale up */ - if (pix->width > ceu_sub_width) - ceu_sub_width = pix->width; - - if (pix->height > ceu_sub_height) - ceu_sub_height = pix->height; - - pix->colorspace = mf.colorspace; - - if (image_mode) { - /* Scale pix->{width x height} down to width x height */ - scale_h = calc_scale(ceu_sub_width, &pix->width); - scale_v = calc_scale(ceu_sub_height, &pix->height); - } else { - pix->width = ceu_sub_width; - pix->height = ceu_sub_height; - scale_h = 0; - scale_v = 0; - } - - pcdev->cflcr = scale_h | (scale_v << 16); - - /* - * We have calculated CFLCR, the actual configuration will be performed - * in sh_mobile_ceu_set_bus_param() - */ - - dev_geo(dev, "10: W: %u : 0x%x = %u, H: %u : 0x%x = %u\n", - ceu_sub_width, scale_h, pix->width, - ceu_sub_height, scale_v, pix->height); - - cam->code = xlate->code; - icd->current_fmt = xlate; - - pcdev->field = field; - pcdev->image_mode = image_mode; - - /* CFSZR requirement */ - pix->width &= ~3; - pix->height &= ~3; - - return 0; -} - -#define CEU_CHDW_MAX 8188U /* Maximum line stride */ - -static int sh_mobile_ceu_try_fmt(struct soc_camera_device *icd, - struct v4l2_format *f) -{ - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - const struct soc_camera_format_xlate *xlate; - struct v4l2_pix_format *pix = &f->fmt.pix; - struct v4l2_subdev *sd = soc_camera_to_subdev(icd); - struct v4l2_subdev_pad_config pad_cfg; - struct v4l2_subdev_format format = { - .which = V4L2_SUBDEV_FORMAT_TRY, - }; - struct v4l2_mbus_framefmt *mf = &format.format; - __u32 pixfmt = pix->pixelformat; - int width, height; - int ret; - - dev_geo(icd->parent, "TRY_FMT(pix=0x%x, %ux%u)\n", - pixfmt, pix->width, pix->height); - - xlate = soc_camera_xlate_by_fourcc(icd, pixfmt); - if (!xlate) { - xlate = icd->current_fmt; - dev_dbg(icd->parent, "Format %x not found, keeping %x\n", - pixfmt, xlate->host_fmt->fourcc); - pixfmt = xlate->host_fmt->fourcc; - pix->pixelformat = pixfmt; - pix->colorspace = icd->colorspace; - } - - /* FIXME: calculate using depth and bus width */ - - /* CFSZR requires height and width to be 4-pixel aligned */ - v4l_bound_align_image(&pix->width, 2, pcdev->max_width, 2, - &pix->height, 4, pcdev->max_height, 2, 0); - - width = pix->width; - height = pix->height; - - /* limit to sensor capabilities */ - mf->width = pix->width; - mf->height = pix->height; - mf->field = pix->field; - mf->code = xlate->code; - mf->colorspace = pix->colorspace; - - ret = v4l2_device_call_until_err(sd->v4l2_dev, soc_camera_grp_id(icd), - pad, set_fmt, &pad_cfg, &format); - if (ret < 0) - return ret; - - pix->width = mf->width; - pix->height = mf->height; - pix->field = mf->field; - pix->colorspace = mf->colorspace; - - switch (pixfmt) { - case V4L2_PIX_FMT_NV12: - case V4L2_PIX_FMT_NV21: - case V4L2_PIX_FMT_NV16: - case V4L2_PIX_FMT_NV61: - /* FIXME: check against rect_max after converting soc-camera */ - /* We can scale precisely, need a bigger image from camera */ - if (pix->width < width || pix->height < height) { - /* - * We presume, the sensor behaves sanely, i.e., if - * requested a bigger rectangle, it will not return a - * smaller one. - */ - mf->width = pcdev->max_width; - mf->height = pcdev->max_height; - ret = v4l2_device_call_until_err(sd->v4l2_dev, - soc_camera_grp_id(icd), pad, - set_fmt, &pad_cfg, &format); - if (ret < 0) { - /* Shouldn't actually happen... */ - dev_err(icd->parent, - "FIXME: client try_fmt() = %d\n", ret); - return ret; - } - } - /* We will scale exactly */ - if (mf->width > width) - pix->width = width; - if (mf->height > height) - pix->height = height; - - pix->bytesperline = max(pix->bytesperline, pix->width); - pix->bytesperline = min(pix->bytesperline, CEU_CHDW_MAX); - pix->bytesperline &= ~3; - break; - - default: - /* Configurable stride isn't supported in pass-through mode. */ - pix->bytesperline = 0; - } - - pix->width &= ~3; - pix->height &= ~3; - pix->sizeimage = 0; - - dev_geo(icd->parent, "%s(): return %d, fmt 0x%x, %ux%u\n", - __func__, ret, pix->pixelformat, pix->width, pix->height); - - return ret; -} - -static int sh_mobile_ceu_set_liveselection(struct soc_camera_device *icd, - struct v4l2_selection *sel) -{ - struct v4l2_subdev *sd = soc_camera_to_subdev(icd); - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - struct sh_mobile_ceu_dev *pcdev = ici->priv; - u32 out_width = icd->user_width, out_height = icd->user_height; - int ret; - - /* Freeze queue */ - pcdev->frozen = 1; - /* Wait for frame */ - ret = wait_for_completion_interruptible(&pcdev->complete); - /* Stop the client */ - ret = v4l2_subdev_call(sd, video, s_stream, 0); - if (ret < 0) - dev_warn(icd->parent, - "Client failed to stop the stream: %d\n", ret); - else - /* Do the crop, if it fails, there's nothing more we can do */ - sh_mobile_ceu_set_selection(icd, sel); - - dev_geo(icd->parent, "Output after crop: %ux%u\n", icd->user_width, icd->user_height); - - if (icd->user_width != out_width || icd->user_height != out_height) { - struct v4l2_format f = { - .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, - .fmt.pix = { - .width = out_width, - .height = out_height, - .pixelformat = icd->current_fmt->host_fmt->fourcc, - .field = pcdev->field, - .colorspace = icd->colorspace, - }, - }; - ret = sh_mobile_ceu_set_fmt(icd, &f); - if (!ret && (out_width != f.fmt.pix.width || - out_height != f.fmt.pix.height)) - ret = -EINVAL; - if (!ret) { - icd->user_width = out_width & ~3; - icd->user_height = out_height & ~3; - ret = sh_mobile_ceu_set_bus_param(icd); - } - } - - /* Thaw the queue */ - pcdev->frozen = 0; - spin_lock_irq(&pcdev->lock); - sh_mobile_ceu_capture(pcdev); - spin_unlock_irq(&pcdev->lock); - /* Start the client */ - ret = v4l2_subdev_call(sd, video, s_stream, 1); - return ret; -} - -static __poll_t sh_mobile_ceu_poll(struct file *file, poll_table *pt) -{ - struct soc_camera_device *icd = file->private_data; - - return vb2_poll(&icd->vb2_vidq, file, pt); -} - -static int sh_mobile_ceu_querycap(struct soc_camera_host *ici, - struct v4l2_capability *cap) -{ - strscpy(cap->card, "SuperH_Mobile_CEU", sizeof(cap->card)); - strscpy(cap->driver, "sh_mobile_ceu", sizeof(cap->driver)); - strscpy(cap->bus_info, "platform:sh_mobile_ceu", sizeof(cap->bus_info)); - cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING; - cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS; - - return 0; -} - -static int sh_mobile_ceu_init_videobuf(struct vb2_queue *q, - struct soc_camera_device *icd) -{ - struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - - q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE; - q->io_modes = VB2_MMAP | VB2_USERPTR; - q->drv_priv = icd; - q->ops = &sh_mobile_ceu_videobuf_ops; - q->mem_ops = &vb2_dma_contig_memops; - q->buf_struct_size = sizeof(struct sh_mobile_ceu_buffer); - q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; - q->lock = &ici->host_lock; - q->dev = ici->v4l2_dev.dev; - - return vb2_queue_init(q); -} - -static struct soc_camera_host_ops sh_mobile_ceu_host_ops = { - .owner = THIS_MODULE, - .add = sh_mobile_ceu_add_device, - .remove = sh_mobile_ceu_remove_device, - .clock_start = sh_mobile_ceu_clock_start, - .clock_stop = sh_mobile_ceu_clock_stop, - .get_formats = sh_mobile_ceu_get_formats, - .put_formats = sh_mobile_ceu_put_formats, - .get_selection = sh_mobile_ceu_get_selection, - .set_selection = sh_mobile_ceu_set_selection, - .set_liveselection = sh_mobile_ceu_set_liveselection, - .set_fmt = sh_mobile_ceu_set_fmt, - .try_fmt = sh_mobile_ceu_try_fmt, - .poll = sh_mobile_ceu_poll, - .querycap = sh_mobile_ceu_querycap, - .set_bus_param = sh_mobile_ceu_set_bus_param, - .init_videobuf2 = sh_mobile_ceu_init_videobuf, -}; - -struct bus_wait { - struct notifier_block notifier; - struct completion completion; - struct device *dev; -}; - -static int bus_notify(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - struct bus_wait *wait = container_of(nb, struct bus_wait, notifier); - - if (wait->dev != dev) - return NOTIFY_DONE; - - switch (action) { - case BUS_NOTIFY_UNBOUND_DRIVER: - /* Protect from module unloading */ - wait_for_completion(&wait->completion); - return NOTIFY_OK; - } - return NOTIFY_DONE; -} - -static int sh_mobile_ceu_probe(struct platform_device *pdev) -{ - struct sh_mobile_ceu_dev *pcdev; - struct resource *res; - void __iomem *base; - unsigned int irq; - int err; - struct bus_wait wait = { - .completion = COMPLETION_INITIALIZER_ONSTACK(wait.completion), - .notifier.notifier_call = bus_notify, - }; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - irq = platform_get_irq(pdev, 0); - if (!res || (int)irq <= 0) { - dev_err(&pdev->dev, "Not enough CEU platform resources.\n"); - return -ENODEV; - } - - pcdev = devm_kzalloc(&pdev->dev, sizeof(*pcdev), GFP_KERNEL); - if (!pcdev) { - dev_err(&pdev->dev, "Could not allocate pcdev\n"); - return -ENOMEM; - } - - INIT_LIST_HEAD(&pcdev->capture); - spin_lock_init(&pcdev->lock); - init_completion(&pcdev->complete); - - pcdev->pdata = pdev->dev.platform_data; - if (!pcdev->pdata && !pdev->dev.of_node) { - dev_err(&pdev->dev, "CEU platform data not set.\n"); - return -EINVAL; - } - - /* TODO: implement per-device bus flags */ - if (pcdev->pdata) { - pcdev->max_width = pcdev->pdata->max_width; - pcdev->max_height = pcdev->pdata->max_height; - pcdev->flags = pcdev->pdata->flags; - } - pcdev->field = V4L2_FIELD_NONE; - - if (!pcdev->max_width) { - unsigned int v; - err = of_property_read_u32(pdev->dev.of_node, "renesas,max-width", &v); - if (!err) - pcdev->max_width = v; - - if (!pcdev->max_width) - pcdev->max_width = 2560; - } - if (!pcdev->max_height) { - unsigned int v; - err = of_property_read_u32(pdev->dev.of_node, "renesas,max-height", &v); - if (!err) - pcdev->max_height = v; - - if (!pcdev->max_height) - pcdev->max_height = 1920; - } - - base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(base)) - return PTR_ERR(base); - - pcdev->irq = irq; - pcdev->base = base; - pcdev->video_limit = 0; /* only enabled if second resource exists */ - - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (res) { - err = dma_declare_coherent_memory(&pdev->dev, res->start, - res->start, - resource_size(res), - DMA_MEMORY_EXCLUSIVE); - if (err) { - dev_err(&pdev->dev, "Unable to declare CEU memory.\n"); - return err; - } - - pcdev->video_limit = resource_size(res); - } - - /* request irq */ - err = devm_request_irq(&pdev->dev, pcdev->irq, sh_mobile_ceu_irq, - 0, dev_name(&pdev->dev), pcdev); - if (err) { - dev_err(&pdev->dev, "Unable to register CEU interrupt.\n"); - goto exit_release_mem; - } - - pm_suspend_ignore_children(&pdev->dev, true); - pm_runtime_enable(&pdev->dev); - pm_runtime_resume(&pdev->dev); - - pcdev->ici.priv = pcdev; - pcdev->ici.v4l2_dev.dev = &pdev->dev; - pcdev->ici.nr = pdev->id; - pcdev->ici.drv_name = dev_name(&pdev->dev); - pcdev->ici.ops = &sh_mobile_ceu_host_ops; - pcdev->ici.capabilities = SOCAM_HOST_CAP_STRIDE; - - if (pcdev->pdata && pcdev->pdata->asd_sizes) { - pcdev->ici.asd = pcdev->pdata->asd; - pcdev->ici.asd_sizes = pcdev->pdata->asd_sizes; - } - - err = soc_camera_host_register(&pcdev->ici); - if (err) - goto exit_free_clk; - - return 0; - -exit_free_clk: - pm_runtime_disable(&pdev->dev); -exit_release_mem: - if (platform_get_resource(pdev, IORESOURCE_MEM, 1)) - dma_release_declared_memory(&pdev->dev); - return err; -} - -static int sh_mobile_ceu_remove(struct platform_device *pdev) -{ - struct soc_camera_host *soc_host = to_soc_camera_host(&pdev->dev); - - soc_camera_host_unregister(soc_host); - pm_runtime_disable(&pdev->dev); - if (platform_get_resource(pdev, IORESOURCE_MEM, 1)) - dma_release_declared_memory(&pdev->dev); - - return 0; -} - -static int sh_mobile_ceu_runtime_nop(struct device *dev) -{ - /* Runtime PM callback shared between ->runtime_suspend() - * and ->runtime_resume(). Simply returns success. - * - * This driver re-initializes all registers after - * pm_runtime_get_sync() anyway so there is no need - * to save and restore registers here. - */ - return 0; -} - -static const struct dev_pm_ops sh_mobile_ceu_dev_pm_ops = { - .runtime_suspend = sh_mobile_ceu_runtime_nop, - .runtime_resume = sh_mobile_ceu_runtime_nop, -}; - -static const struct of_device_id sh_mobile_ceu_of_match[] = { - { .compatible = "renesas,sh-mobile-ceu" }, - { } -}; -MODULE_DEVICE_TABLE(of, sh_mobile_ceu_of_match); - -static struct platform_driver sh_mobile_ceu_driver = { - .driver = { - .name = "sh_mobile_ceu", - .pm = &sh_mobile_ceu_dev_pm_ops, - .of_match_table = sh_mobile_ceu_of_match, - }, - .probe = sh_mobile_ceu_probe, - .remove = sh_mobile_ceu_remove, -}; - -module_platform_driver(sh_mobile_ceu_driver); - -MODULE_DESCRIPTION("SuperH Mobile CEU driver"); -MODULE_AUTHOR("Magnus Damm"); -MODULE_LICENSE("GPL"); -MODULE_VERSION("0.1.0"); -MODULE_ALIAS("platform:sh_mobile_ceu"); diff --git a/include/media/drv-intf/sh_mobile_ceu.h b/include/media/drv-intf/sh_mobile_ceu.h deleted file mode 100644 index 555f0ecc0fde..000000000000 --- a/include/media/drv-intf/sh_mobile_ceu.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_SH_MOBILE_CEU_H__ -#define __ASM_SH_MOBILE_CEU_H__ - -#define SH_CEU_FLAG_USE_8BIT_BUS (1 << 0) /* use 8bit bus width */ -#define SH_CEU_FLAG_USE_16BIT_BUS (1 << 1) /* use 16bit bus width */ -#define SH_CEU_FLAG_HSYNC_LOW (1 << 2) /* default High if possible */ -#define SH_CEU_FLAG_VSYNC_LOW (1 << 3) /* default High if possible */ -#define SH_CEU_FLAG_LOWER_8BIT (1 << 4) /* default upper 8bit */ - -struct device; -struct resource; - -struct sh_mobile_ceu_companion { - u32 num_resources; - struct resource *resource; - int id; - void *platform_data; -}; - -struct sh_mobile_ceu_info { - unsigned long flags; - int max_width; - int max_height; - struct v4l2_async_subdev **asd; /* Flat array, arranged in groups */ - unsigned int *asd_sizes; /* 0-terminated array pf asd group sizes */ -}; - -#endif /* __ASM_SH_MOBILE_CEU_H__ */ -- cgit v1.2.3 From dc60a4cfb77c891f67f31953025208067b05883c Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 17 Jan 2019 11:47:55 -0200 Subject: media: soc_camera_platform: remove obsolete soc_camera test driver This is a test stub driver for soc_camera. Since soc_camera is being deprecated (and in fact, nobody is using it anymore) there's no sense in keeping this test driver. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/soc_camera/Kconfig | 6 - drivers/media/platform/soc_camera/Makefile | 4 - .../platform/soc_camera/soc_camera_platform.c | 188 --------------------- .../platform_data/media/soc_camera_platform.h | 83 --------- 4 files changed, 281 deletions(-) delete mode 100644 drivers/media/platform/soc_camera/soc_camera_platform.c delete mode 100644 include/linux/platform_data/media/soc_camera_platform.h (limited to 'include') diff --git a/drivers/media/platform/soc_camera/Kconfig b/drivers/media/platform/soc_camera/Kconfig index d471d34b884c..8f9b3bac5450 100644 --- a/drivers/media/platform/soc_camera/Kconfig +++ b/drivers/media/platform/soc_camera/Kconfig @@ -6,9 +6,3 @@ config SOC_CAMERA SoC Camera is a common API to several cameras, not connecting over a bus like PCI or USB. For example some i2c camera connected directly to the data bus of an SoC. - -config SOC_CAMERA_PLATFORM - tristate "platform camera support" - depends on SOC_CAMERA - help - This is a generic SoC camera platform driver, useful for testing diff --git a/drivers/media/platform/soc_camera/Makefile b/drivers/media/platform/soc_camera/Makefile index 2cb7022e073b..85d5e74f3b2b 100644 --- a/drivers/media/platform/soc_camera/Makefile +++ b/drivers/media/platform/soc_camera/Makefile @@ -1,5 +1 @@ obj-$(CONFIG_SOC_CAMERA) += soc_camera.o soc_mediabus.o - -# a platform subdevice driver stub, allowing to support cameras by adding a -# couple of callback functions to the board code -obj-$(CONFIG_SOC_CAMERA_PLATFORM) += soc_camera_platform.o diff --git a/drivers/media/platform/soc_camera/soc_camera_platform.c b/drivers/media/platform/soc_camera/soc_camera_platform.c deleted file mode 100644 index 79fbe1fea95f..000000000000 --- a/drivers/media/platform/soc_camera/soc_camera_platform.c +++ /dev/null @@ -1,188 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Generic Platform Camera Driver - * - * Copyright (C) 2008 Magnus Damm - * Based on mt9m001 driver, - * Copyright (C) 2008, Guennadi Liakhovetski - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -struct soc_camera_platform_priv { - struct v4l2_subdev subdev; -}; - -static struct soc_camera_platform_priv *get_priv(struct platform_device *pdev) -{ - struct v4l2_subdev *subdev = platform_get_drvdata(pdev); - return container_of(subdev, struct soc_camera_platform_priv, subdev); -} - -static int soc_camera_platform_s_stream(struct v4l2_subdev *sd, int enable) -{ - struct soc_camera_platform_info *p = v4l2_get_subdevdata(sd); - return p->set_capture(p, enable); -} - -static int soc_camera_platform_fill_fmt(struct v4l2_subdev *sd, - struct v4l2_subdev_pad_config *cfg, - struct v4l2_subdev_format *format) -{ - struct soc_camera_platform_info *p = v4l2_get_subdevdata(sd); - struct v4l2_mbus_framefmt *mf = &format->format; - - mf->width = p->format.width; - mf->height = p->format.height; - mf->code = p->format.code; - mf->colorspace = p->format.colorspace; - mf->field = p->format.field; - - return 0; -} - -static int soc_camera_platform_s_power(struct v4l2_subdev *sd, int on) -{ - struct soc_camera_platform_info *p = v4l2_get_subdevdata(sd); - - return soc_camera_set_power(p->icd->control, &p->icd->sdesc->subdev_desc, NULL, on); -} - -static const struct v4l2_subdev_core_ops platform_subdev_core_ops = { - .s_power = soc_camera_platform_s_power, -}; - -static int soc_camera_platform_enum_mbus_code(struct v4l2_subdev *sd, - struct v4l2_subdev_pad_config *cfg, - struct v4l2_subdev_mbus_code_enum *code) -{ - struct soc_camera_platform_info *p = v4l2_get_subdevdata(sd); - - if (code->pad || code->index) - return -EINVAL; - - code->code = p->format.code; - return 0; -} - -static int soc_camera_platform_get_selection(struct v4l2_subdev *sd, - struct v4l2_subdev_pad_config *cfg, - struct v4l2_subdev_selection *sel) -{ - struct soc_camera_platform_info *p = v4l2_get_subdevdata(sd); - - if (sel->which != V4L2_SUBDEV_FORMAT_ACTIVE) - return -EINVAL; - - switch (sel->target) { - case V4L2_SEL_TGT_CROP_BOUNDS: - case V4L2_SEL_TGT_CROP_DEFAULT: - case V4L2_SEL_TGT_CROP: - sel->r.left = 0; - sel->r.top = 0; - sel->r.width = p->format.width; - sel->r.height = p->format.height; - return 0; - default: - return -EINVAL; - } -} - -static int soc_camera_platform_g_mbus_config(struct v4l2_subdev *sd, - struct v4l2_mbus_config *cfg) -{ - struct soc_camera_platform_info *p = v4l2_get_subdevdata(sd); - - cfg->flags = p->mbus_param; - cfg->type = p->mbus_type; - - return 0; -} - -static const struct v4l2_subdev_video_ops platform_subdev_video_ops = { - .s_stream = soc_camera_platform_s_stream, - .g_mbus_config = soc_camera_platform_g_mbus_config, -}; - -static const struct v4l2_subdev_pad_ops platform_subdev_pad_ops = { - .enum_mbus_code = soc_camera_platform_enum_mbus_code, - .get_selection = soc_camera_platform_get_selection, - .get_fmt = soc_camera_platform_fill_fmt, - .set_fmt = soc_camera_platform_fill_fmt, -}; - -static const struct v4l2_subdev_ops platform_subdev_ops = { - .core = &platform_subdev_core_ops, - .video = &platform_subdev_video_ops, - .pad = &platform_subdev_pad_ops, -}; - -static int soc_camera_platform_probe(struct platform_device *pdev) -{ - struct soc_camera_host *ici; - struct soc_camera_platform_priv *priv; - struct soc_camera_platform_info *p = pdev->dev.platform_data; - struct soc_camera_device *icd; - - if (!p) - return -EINVAL; - - if (!p->icd) { - dev_err(&pdev->dev, - "Platform has not set soc_camera_device pointer!\n"); - return -EINVAL; - } - - priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - - icd = p->icd; - - /* soc-camera convention: control's drvdata points to the subdev */ - platform_set_drvdata(pdev, &priv->subdev); - /* Set the control device reference */ - icd->control = &pdev->dev; - - ici = to_soc_camera_host(icd->parent); - - v4l2_subdev_init(&priv->subdev, &platform_subdev_ops); - v4l2_set_subdevdata(&priv->subdev, p); - strscpy(priv->subdev.name, dev_name(&pdev->dev), - sizeof(priv->subdev.name)); - - return v4l2_device_register_subdev(&ici->v4l2_dev, &priv->subdev); -} - -static int soc_camera_platform_remove(struct platform_device *pdev) -{ - struct soc_camera_platform_priv *priv = get_priv(pdev); - struct soc_camera_platform_info *p = v4l2_get_subdevdata(&priv->subdev); - - p->icd->control = NULL; - v4l2_device_unregister_subdev(&priv->subdev); - return 0; -} - -static struct platform_driver soc_camera_platform_driver = { - .driver = { - .name = "soc_camera_platform", - }, - .probe = soc_camera_platform_probe, - .remove = soc_camera_platform_remove, -}; - -module_platform_driver(soc_camera_platform_driver); - -MODULE_DESCRIPTION("SoC Camera Platform driver"); -MODULE_AUTHOR("Magnus Damm"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("platform:soc_camera_platform"); diff --git a/include/linux/platform_data/media/soc_camera_platform.h b/include/linux/platform_data/media/soc_camera_platform.h deleted file mode 100644 index 1e5065dab430..000000000000 --- a/include/linux/platform_data/media/soc_camera_platform.h +++ /dev/null @@ -1,83 +0,0 @@ -/* - * Generic Platform Camera Driver Header - * - * Copyright (C) 2008 Magnus Damm - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __SOC_CAMERA_H__ -#define __SOC_CAMERA_H__ - -#include -#include -#include - -struct device; - -struct soc_camera_platform_info { - const char *format_name; - unsigned long format_depth; - struct v4l2_mbus_framefmt format; - unsigned long mbus_param; - enum v4l2_mbus_type mbus_type; - struct soc_camera_device *icd; - int (*set_capture)(struct soc_camera_platform_info *info, int enable); -}; - -static inline void soc_camera_platform_release(struct platform_device **pdev) -{ - *pdev = NULL; -} - -static inline int soc_camera_platform_add(struct soc_camera_device *icd, - struct platform_device **pdev, - struct soc_camera_link *plink, - void (*release)(struct device *dev), - int id) -{ - struct soc_camera_subdev_desc *ssdd = - (struct soc_camera_subdev_desc *)plink; - struct soc_camera_platform_info *info = ssdd->drv_priv; - int ret; - - if (&icd->sdesc->subdev_desc != ssdd) - return -ENODEV; - - if (*pdev) - return -EBUSY; - - *pdev = platform_device_alloc("soc_camera_platform", id); - if (!*pdev) - return -ENOMEM; - - info->icd = icd; - - (*pdev)->dev.platform_data = info; - (*pdev)->dev.release = release; - - ret = platform_device_add(*pdev); - if (ret < 0) { - platform_device_put(*pdev); - *pdev = NULL; - info->icd = NULL; - } - - return ret; -} - -static inline void soc_camera_platform_del(const struct soc_camera_device *icd, - struct platform_device *pdev, - const struct soc_camera_link *plink) -{ - const struct soc_camera_subdev_desc *ssdd = - (const struct soc_camera_subdev_desc *)plink; - if (&icd->sdesc->subdev_desc != ssdd || !pdev) - return; - - platform_device_unregister(pdev); -} - -#endif /* __SOC_CAMERA_H__ */ -- cgit v1.2.3 From 1fc1b63638da1accb27264a507b23aa6863c3852 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sat, 19 Jan 2019 16:04:12 +0100 Subject: spi: spi-mem: Add devm_spi_mem_dirmap_{create,destroy}() Since direct mapping descriptors usually the same lifetime as the SPI MEM device adding devm_ variants of the spi_mem_dirmap_{create,destroy}() should greatly simplify error/remove path of spi-mem drivers making use of the direct mapping API. Signed-off-by: Boris Brezillon Signed-off-by: Mark Brown --- drivers/spi/spi-mem.c | 69 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/spi/spi-mem.h | 5 ++++ 2 files changed, 74 insertions(+) (limited to 'include') diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index 5217a5628be2..08e326a124cc 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -551,6 +551,75 @@ void spi_mem_dirmap_destroy(struct spi_mem_dirmap_desc *desc) } EXPORT_SYMBOL_GPL(spi_mem_dirmap_destroy); +static void devm_spi_mem_dirmap_release(struct device *dev, void *res) +{ + struct spi_mem_dirmap_desc *desc = *(struct spi_mem_dirmap_desc **)res; + + spi_mem_dirmap_destroy(desc); +} + +/** + * devm_spi_mem_dirmap_create() - Create a direct mapping descriptor and attach + * it to a device + * @dev: device the dirmap desc will be attached to + * @mem: SPI mem device this direct mapping should be created for + * @info: direct mapping information + * + * devm_ variant of the spi_mem_dirmap_create() function. See + * spi_mem_dirmap_create() for more details. + * + * Return: a valid pointer in case of success, and ERR_PTR() otherwise. + */ +struct spi_mem_dirmap_desc * +devm_spi_mem_dirmap_create(struct device *dev, struct spi_mem *mem, + const struct spi_mem_dirmap_info *info) +{ + struct spi_mem_dirmap_desc **ptr, *desc; + + ptr = devres_alloc(devm_spi_mem_dirmap_release, sizeof(*ptr), + GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + desc = spi_mem_dirmap_create(mem, info); + if (IS_ERR(desc)) { + devres_free(ptr); + } else { + *ptr = desc; + devres_add(dev, ptr); + } + + return desc; +} +EXPORT_SYMBOL_GPL(devm_spi_mem_dirmap_create); + +static int devm_spi_mem_dirmap_match(struct device *dev, void *res, void *data) +{ + struct spi_mem_dirmap_desc **ptr = res; + + if (WARN_ON(!ptr || !*ptr)) + return 0; + + return *ptr == data; +} + +/** + * devm_spi_mem_dirmap_destroy() - Destroy a direct mapping descriptor attached + * to a device + * @dev: device the dirmap desc is attached to + * @desc: the direct mapping descriptor to destroy + * + * devm_ variant of the spi_mem_dirmap_destroy() function. See + * spi_mem_dirmap_destroy() for more details. + */ +void devm_spi_mem_dirmap_destroy(struct device *dev, + struct spi_mem_dirmap_desc *desc) +{ + devres_release(dev, devm_spi_mem_dirmap_release, + devm_spi_mem_dirmap_match, desc); +} +EXPORT_SYMBOL_GPL(devm_spi_mem_dirmap_destroy); + /** * spi_mem_dirmap_dirmap_read() - Read data through a direct mapping * @desc: direct mapping descriptor diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 3fe24500c5ee..3703d0dcac2e 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -330,6 +330,11 @@ ssize_t spi_mem_dirmap_read(struct spi_mem_dirmap_desc *desc, u64 offs, size_t len, void *buf); ssize_t spi_mem_dirmap_write(struct spi_mem_dirmap_desc *desc, u64 offs, size_t len, const void *buf); +struct spi_mem_dirmap_desc * +devm_spi_mem_dirmap_create(struct device *dev, struct spi_mem *mem, + const struct spi_mem_dirmap_info *info); +void devm_spi_mem_dirmap_destroy(struct device *dev, + struct spi_mem_dirmap_desc *desc); int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv, struct module *owner); -- cgit v1.2.3 From 910fdcabedd2354d161b1beab6ad7dc7e859651d Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 21 Jan 2019 09:32:32 +0900 Subject: ASoC: soc-core: add .num_platform for dai_link Current snd_soc_dai_link is starting to use snd_soc_dai_link_component (= modern) style for Platform, but it is still assuming single Platform so far. We will need to have multi Platform support in the not far future. Currently only simple card is using it as sound card driver, and other drivers are converted to it from legacy style by snd_soc_init_platform(). To avoid future problem of multi Platform support, let's add num_platforms before it is too late. In the same time, to make it same naming mothed, "platform" should be "platforms". This patch fixup it too. Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 2 +- include/sound/soc.h | 3 ++- sound/soc/generic/audio-graph-card.c | 5 +++-- sound/soc/generic/simple-card-utils.c | 4 ++-- sound/soc/generic/simple-card.c | 7 ++++--- sound/soc/soc-core.c | 23 ++++++++++++++++------- 6 files changed, 28 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index 6d69ed2bd7b1..ab5a2ba09c07 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -75,7 +75,7 @@ void asoc_simple_card_clk_disable(struct asoc_simple_dai *dai); &dai_link->codec_dai_name, \ list_name, cells_name, NULL) #define asoc_simple_card_parse_platform(node, dai_link, list_name, cells_name) \ - asoc_simple_card_parse_dai(node, dai_link->platform, \ + asoc_simple_card_parse_dai(node, dai_link->platforms, \ &dai_link->platform_of_node, \ NULL, list_name, cells_name, NULL) int asoc_simple_card_parse_dai(struct device_node *node, diff --git a/include/sound/soc.h b/include/sound/soc.h index c31b6d122ff6..3089257ead95 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -961,7 +961,8 @@ struct snd_soc_dai_link { */ const char *platform_name; struct device_node *platform_of_node; - struct snd_soc_dai_link_component *platform; + struct snd_soc_dai_link_component *platforms; + unsigned int num_platforms; int id; /* optional ID for machine driver link identification */ diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c index 3ec96cdc683b..42b077c6be4c 100644 --- a/sound/soc/generic/audio-graph-card.c +++ b/sound/soc/generic/audio-graph-card.c @@ -26,7 +26,7 @@ struct graph_priv { struct asoc_simple_dai *cpu_dai; struct asoc_simple_dai *codec_dai; struct snd_soc_dai_link_component codecs; /* single codec */ - struct snd_soc_dai_link_component platform; + struct snd_soc_dai_link_component platforms; struct asoc_simple_card_data adata; struct snd_soc_codec_conf *codec_conf; unsigned int mclk_fs; @@ -687,7 +687,8 @@ static int graph_probe(struct platform_device *pdev) for (i = 0; i < li.link; i++) { dai_link[i].codecs = &dai_props[i].codecs; dai_link[i].num_codecs = 1; - dai_link[i].platform = &dai_props[i].platform; + dai_link[i].platforms = &dai_props[i].platforms; + dai_link[i].num_platforms = 1; } priv->pa_gpio = devm_gpiod_get_optional(dev, "pa", GPIOD_OUT_LOW); diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 336895f7fd1e..3c0901df5796 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -397,8 +397,8 @@ EXPORT_SYMBOL_GPL(asoc_simple_card_init_dai); int asoc_simple_card_canonicalize_dailink(struct snd_soc_dai_link *dai_link) { /* Assumes platform == cpu */ - if (!dai_link->platform->of_node) - dai_link->platform->of_node = dai_link->cpu_of_node; + if (!dai_link->platforms->of_node) + dai_link->platforms->of_node = dai_link->cpu_of_node; return 0; diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index 479de236e694..d8a0d1ec256e 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -21,7 +21,7 @@ struct simple_priv { struct asoc_simple_dai *cpu_dai; struct asoc_simple_dai *codec_dai; struct snd_soc_dai_link_component codecs; /* single codec */ - struct snd_soc_dai_link_component platform; + struct snd_soc_dai_link_component platforms; struct asoc_simple_card_data adata; struct snd_soc_codec_conf *codec_conf; unsigned int mclk_fs; @@ -732,7 +732,8 @@ static int simple_probe(struct platform_device *pdev) for (i = 0; i < li.link; i++) { dai_link[i].codecs = &dai_props[i].codecs; dai_link[i].num_codecs = 1; - dai_link[i].platform = &dai_props[i].platform; + dai_link[i].platforms = &dai_props[i].platforms; + dai_link[i].num_platforms = 1; } priv->dai_props = dai_props; @@ -782,7 +783,7 @@ static int simple_probe(struct platform_device *pdev) codecs->name = cinfo->codec; codecs->dai_name = cinfo->codec_dai.name; - platform = dai_link->platform; + platform = dai_link->platforms; platform->name = cinfo->platform; card->name = (cinfo->card) ? cinfo->card : cinfo->name; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index de2851f1b3df..2c63921675d5 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -915,7 +915,7 @@ static int soc_bind_dai_link(struct snd_soc_card *card, /* find one from the set of registered platforms */ for_each_component(component) { - if (!snd_soc_is_matching_component(dai_link->platform, + if (!snd_soc_is_matching_component(dai_link->platforms, component)) continue; @@ -1026,7 +1026,7 @@ static void soc_remove_dai_links(struct snd_soc_card *card) static int snd_soc_init_platform(struct snd_soc_card *card, struct snd_soc_dai_link *dai_link) { - struct snd_soc_dai_link_component *platform = dai_link->platform; + struct snd_soc_dai_link_component *platform = dai_link->platforms; /* * REMOVE ME @@ -1046,7 +1046,8 @@ static int snd_soc_init_platform(struct snd_soc_card *card, if (!platform) return -ENOMEM; - dai_link->platform = platform; + dai_link->platforms = platform; + dai_link->num_platforms = 1; dai_link->legacy_platform = 1; platform->name = dai_link->platform_name; platform->of_node = dai_link->platform_of_node; @@ -1136,11 +1137,19 @@ static int soc_init_dai_link(struct snd_soc_card *card, } } + /* FIXME */ + if (link->num_platforms > 1) { + dev_err(card->dev, + "ASoC: multi platform is not yet supported %s\n", + link->name); + return -EINVAL; + } + /* * Platform may be specified by either name or OF node, but * can be left unspecified, and a dummy platform will be used. */ - if (link->platform->name && link->platform->of_node) { + if (link->platforms->name && link->platforms->of_node) { dev_err(card->dev, "ASoC: Both platform name/of_node are set for %s\n", link->name); @@ -1151,8 +1160,8 @@ static int soc_init_dai_link(struct snd_soc_card *card, * Defer card registartion if platform dai component is not added to * component list. */ - if ((link->platform->of_node || link->platform->name) && - !soc_find_component(link->platform->of_node, link->platform->name)) + if ((link->platforms->of_node || link->platforms->name) && + !soc_find_component(link->platforms->of_node, link->platforms->name)) return -EPROBE_DEFER; /* @@ -1956,7 +1965,7 @@ static void soc_check_tplg_fes(struct snd_soc_card *card) dev_err(card->dev, "init platform error"); continue; } - dai_link->platform->name = component->name; + dai_link->platforms->name = component->name; /* convert non BE into BE */ dai_link->no_pcm = 1; -- cgit v1.2.3 From fe7ed4dec2e6289eab81dd18c0d613c0851d85a1 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 21 Jan 2019 16:40:59 +0900 Subject: ASoC: simple-card: rename to asoc_simple_card_canonicalize_platform() Current simple-card is using asoc_simple_card_canonicalize_dailink(). Its naming is "dailink", but is for "platform". We already have asoc_simple_card_canonicalize_cpu() for "cpu", let's follow same naming rule. It never return error, so, void function is better idea. Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 2 +- sound/soc/generic/audio-graph-card.c | 11 +++-------- sound/soc/generic/simple-card-utils.c | 7 ++----- sound/soc/generic/simple-card.c | 11 +++-------- 4 files changed, 9 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index ab5a2ba09c07..7afe45389972 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -108,7 +108,7 @@ int asoc_simple_card_parse_graph_dai(struct device_node *ep, int asoc_simple_card_init_dai(struct snd_soc_dai *dai, struct asoc_simple_dai *simple_dai); -int asoc_simple_card_canonicalize_dailink(struct snd_soc_dai_link *dai_link); +void asoc_simple_card_canonicalize_platform(struct snd_soc_dai_link *dai_link); void asoc_simple_card_canonicalize_cpu(struct snd_soc_dai_link *dai_link, int is_single_links); diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c index 42b077c6be4c..bb12351330e8 100644 --- a/sound/soc/generic/audio-graph-card.c +++ b/sound/soc/generic/audio-graph-card.c @@ -307,14 +307,12 @@ static int graph_dai_link_of_dpcm(struct graph_priv *priv, "prefix"); } + asoc_simple_card_canonicalize_platform(dai_link); + ret = asoc_simple_card_of_parse_tdm(ep, dai); if (ret) return ret; - ret = asoc_simple_card_canonicalize_dailink(dai_link); - if (ret < 0) - return ret; - ret = asoc_simple_card_parse_daifmt(dev, cpu_ep, codec_ep, NULL, &dai_link->dai_fmt); if (ret < 0) @@ -405,10 +403,6 @@ static int graph_dai_link_of(struct graph_priv *priv, if (ret < 0) return ret; - ret = asoc_simple_card_canonicalize_dailink(dai_link); - if (ret < 0) - return ret; - ret = asoc_simple_card_set_dailink_name(dev, dai_link, "%s-%s", dai_link->cpu_dai_name, @@ -419,6 +413,7 @@ static int graph_dai_link_of(struct graph_priv *priv, dai_link->ops = &graph_ops; dai_link->init = graph_dai_init; + asoc_simple_card_canonicalize_platform(dai_link); asoc_simple_card_canonicalize_cpu(dai_link, of_graph_get_endpoint_count(dai_link->cpu_of_node) == 1); diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 3c0901df5796..5c1424f03620 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -394,16 +394,13 @@ int asoc_simple_card_init_dai(struct snd_soc_dai *dai, } EXPORT_SYMBOL_GPL(asoc_simple_card_init_dai); -int asoc_simple_card_canonicalize_dailink(struct snd_soc_dai_link *dai_link) +void asoc_simple_card_canonicalize_platform(struct snd_soc_dai_link *dai_link) { /* Assumes platform == cpu */ if (!dai_link->platforms->of_node) dai_link->platforms->of_node = dai_link->cpu_of_node; - - return 0; - } -EXPORT_SYMBOL_GPL(asoc_simple_card_canonicalize_dailink); +EXPORT_SYMBOL_GPL(asoc_simple_card_canonicalize_platform); void asoc_simple_card_canonicalize_cpu(struct snd_soc_dai_link *dai_link, int is_single_links) diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index d8a0d1ec256e..08df261024cf 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -297,14 +297,12 @@ static int simple_dai_link_of_dpcm(struct simple_priv *priv, simple_get_conversion(dev, np, &dai_props->adata); + asoc_simple_card_canonicalize_platform(dai_link); + ret = asoc_simple_card_of_parse_tdm(np, dai); if (ret) return ret; - ret = asoc_simple_card_canonicalize_dailink(dai_link); - if (ret < 0) - return ret; - snprintf(prop, sizeof(prop), "%smclk-fs", prefix); of_property_read_u32(top, PREFIX "mclk-fs", &dai_props->mclk_fs); of_property_read_u32(node, prop, &dai_props->mclk_fs); @@ -409,10 +407,6 @@ static int simple_dai_link_of(struct simple_priv *priv, if (ret < 0) goto dai_link_of_err; - ret = asoc_simple_card_canonicalize_dailink(dai_link); - if (ret < 0) - goto dai_link_of_err; - ret = asoc_simple_card_set_dailink_name(dev, dai_link, "%s-%s", dai_link->cpu_dai_name, @@ -424,6 +418,7 @@ static int simple_dai_link_of(struct simple_priv *priv, dai_link->init = simple_dai_init; asoc_simple_card_canonicalize_cpu(dai_link, single_cpu); + asoc_simple_card_canonicalize_platform(dai_link); dai_link_of_err: of_node_put(node); -- cgit v1.2.3 From cf5c6c211b7e9eb4f4219f83671432c9ef257187 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 17 Jan 2019 15:25:04 +0800 Subject: perf: Remove duplicated workqueue.h include from perf_event.h It is already included a little bit higher up in that file. Signed-off-by: YueHaibing Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20190117072504.14428-1-yuehaibing@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index cec02dc63b51..f8ec36197718 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -53,7 +53,6 @@ struct perf_guest_info_callbacks { #include #include #include -#include #include #include -- cgit v1.2.3 From 5620196951192f7cd2da0a04e7c0113f40bfc14e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 11 Jan 2019 13:20:20 -0300 Subject: perf: Make perf_event_output() propagate the output() return For the original mode of operation it isn't needed, since we report back errors via PERF_RECORD_LOST records in the ring buffer, but for use in bpf_perf_event_output() it is convenient to return the errors, basically -ENOSPC. Currently bpf_perf_event_output() returns an error indication, the last thing it does, which is to push it to the ring buffer is that can fail and if so, this failure won't be reported back to its users, fix it. Reported-by: Jamal Hadi Salim Tested-by: Jamal Hadi Salim Acked-by: Peter Zijlstra (Intel) Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/r/20190118150938.GN5823@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 6 +++--- kernel/events/core.c | 11 +++++++---- kernel/trace/bpf_trace.c | 3 +-- tools/perf/examples/bpf/augmented_raw_syscalls.c | 4 ++-- tools/perf/examples/bpf/augmented_syscalls.c | 14 +++++++------- tools/perf/examples/bpf/etcsnoop.c | 10 +++++----- 6 files changed, 25 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f8ec36197718..4eb88065a9b5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -978,9 +978,9 @@ extern void perf_event_output_forward(struct perf_event *event, extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); -extern void perf_event_output(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs); +extern int perf_event_output(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs); static inline bool is_default_overflow_handler(struct perf_event *event) diff --git a/kernel/events/core.c b/kernel/events/core.c index fbe59b793b36..bc525cd1615c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6489,7 +6489,7 @@ void perf_prepare_sample(struct perf_event_header *header, data->phys_addr = perf_virt_to_phys(data->addr); } -static __always_inline void +static __always_inline int __perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs, @@ -6499,13 +6499,15 @@ __perf_event_output(struct perf_event *event, { struct perf_output_handle handle; struct perf_event_header header; + int err; /* protect the callchain buffers */ rcu_read_lock(); perf_prepare_sample(&header, data, event, regs); - if (output_begin(&handle, event, header.size)) + err = output_begin(&handle, event, header.size); + if (err) goto exit; perf_output_sample(&handle, &header, data, event); @@ -6514,6 +6516,7 @@ __perf_event_output(struct perf_event *event, exit: rcu_read_unlock(); + return err; } void @@ -6532,12 +6535,12 @@ perf_event_output_backward(struct perf_event *event, __perf_event_output(event, data, regs, perf_output_begin_backward); } -void +int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { - __perf_event_output(event, data, regs, perf_output_begin); + return __perf_event_output(event, data, regs, perf_output_begin); } /* diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8b068adb9da1..088c2032ceaf 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -431,8 +431,7 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; - perf_event_output(event, sd, regs); - return 0; + return perf_event_output(event, sd, regs); } BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c index 53c233370fae..9e9d4c66e53c 100644 --- a/tools/perf/examples/bpf/augmented_raw_syscalls.c +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -141,8 +141,8 @@ int sys_enter(struct syscall_enter_args *args) len = sizeof(augmented_args.args); } - perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); - return 0; + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); } SEC("raw_syscalls:sys_exit") diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c index 2ae44813ef2d..b7dba114e36c 100644 --- a/tools/perf/examples/bpf/augmented_syscalls.c +++ b/tools/perf/examples/bpf/augmented_syscalls.c @@ -55,9 +55,9 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; \ len &= sizeof(augmented_args.filename.value) - 1; \ } \ - perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ - &augmented_args, len); \ - return 0; \ + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ \ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ + &augmented_args, len); \ } \ int syscall_exit(syscall)(struct syscall_exit_args *args) \ { \ @@ -125,10 +125,10 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ /* addrlen = augmented_args.args.addrlen; */ \ /* */ \ probe_read(&augmented_args.addr, addrlen, args->addr_ptr); \ - perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ - &augmented_args, \ - sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen); \ - return 0; \ + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ \ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ + &augmented_args, \ + sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);\ } \ int syscall_exit(syscall)(struct syscall_exit_args *args) \ { \ diff --git a/tools/perf/examples/bpf/etcsnoop.c b/tools/perf/examples/bpf/etcsnoop.c index b59e8812ee8c..550e69c2e8d1 100644 --- a/tools/perf/examples/bpf/etcsnoop.c +++ b/tools/perf/examples/bpf/etcsnoop.c @@ -49,11 +49,11 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ args->filename_ptr); \ if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0) \ return 0; \ - perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ - &augmented_args, \ - (sizeof(augmented_args) - sizeof(augmented_args.filename.value) + \ - augmented_args.filename.size)); \ - return 0; \ + /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ \ + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \ + &augmented_args, \ + (sizeof(augmented_args) - sizeof(augmented_args.filename.value) + \ + augmented_args.filename.size)); \ } struct syscall_enter_openat_args { -- cgit v1.2.3 From 76193a94522f1d4edf2447a536f3f796ce56343b Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 17 Jan 2019 08:15:13 -0800 Subject: perf, bpf: Introduce PERF_RECORD_KSYMBOL For better performance analysis of dynamically JITed and loaded kernel functions, such as BPF programs, this patch introduces PERF_RECORD_KSYMBOL, a new perf_event_type that exposes kernel symbol register/unregister information to user space. The following data structure is used for PERF_RECORD_KSYMBOL. /* * struct { * struct perf_event_header header; * u64 addr; * u32 len; * u16 ksym_type; * u16 flags; * char name[]; * struct sample_id sample_id; * }; */ Signed-off-by: Song Liu Reviewed-by: Arnaldo Carvalho de Melo Tested-by: Arnaldo Carvalho de Melo Acked-by: Peter Zijlstra Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Peter Zijlstra Cc: kernel-team@fb.com Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/20190117161521.1341602-2-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 8 ++++ include/uapi/linux/perf_event.h | 26 ++++++++++- kernel/events/core.c | 98 ++++++++++++++++++++++++++++++++++++++++- 3 files changed, 130 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 4eb88065a9b5..136fe0495374 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1122,6 +1122,10 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, } extern void perf_event_mmap(struct vm_area_struct *vma); + +extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, + bool unregister, const char *sym); + extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); @@ -1342,6 +1346,10 @@ static inline int perf_unregister_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline void perf_event_mmap(struct vm_area_struct *vma) { } + +typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); +static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, + bool unregister, const char *sym) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index ea19b5d491bf..1dee5c8f166b 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -372,7 +372,8 @@ struct perf_event_attr { context_switch : 1, /* context switch data */ write_backward : 1, /* Write ring buffer from end to beginning */ namespaces : 1, /* include namespaces data */ - __reserved_1 : 35; + ksymbol : 1, /* include ksymbol events */ + __reserved_1 : 34; union { __u32 wakeup_events; /* wakeup every n events */ @@ -963,9 +964,32 @@ enum perf_event_type { */ PERF_RECORD_NAMESPACES = 16, + /* + * Record ksymbol register/unregister events: + * + * struct { + * struct perf_event_header header; + * u64 addr; + * u32 len; + * u16 ksym_type; + * u16 flags; + * char name[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_KSYMBOL = 17, + PERF_RECORD_MAX, /* non-ABI */ }; +enum perf_record_ksymbol_type { + PERF_RECORD_KSYMBOL_TYPE_UNKNOWN = 0, + PERF_RECORD_KSYMBOL_TYPE_BPF = 1, + PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */ +}; + +#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) + #define PERF_MAX_STACK_DEPTH 127 #define PERF_MAX_CONTEXTS_PER_STACK 8 diff --git a/kernel/events/core.c b/kernel/events/core.c index bc525cd1615c..e04ab5f325cf 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -385,6 +385,7 @@ static atomic_t nr_namespaces_events __read_mostly; static atomic_t nr_task_events __read_mostly; static atomic_t nr_freq_events __read_mostly; static atomic_t nr_switch_events __read_mostly; +static atomic_t nr_ksymbol_events __read_mostly; static LIST_HEAD(pmus); static DEFINE_MUTEX(pmus_lock); @@ -4235,7 +4236,7 @@ static bool is_sb_event(struct perf_event *event) if (attr->mmap || attr->mmap_data || attr->mmap2 || attr->comm || attr->comm_exec || - attr->task || + attr->task || attr->ksymbol || attr->context_switch) return true; return false; @@ -4305,6 +4306,8 @@ static void unaccount_event(struct perf_event *event) dec = true; if (has_branch_stack(event)) dec = true; + if (event->attr.ksymbol) + atomic_dec(&nr_ksymbol_events); if (dec) { if (!atomic_add_unless(&perf_sched_count, -1, 1)) @@ -7653,6 +7656,97 @@ static void perf_log_throttle(struct perf_event *event, int enable) perf_output_end(&handle); } +/* + * ksymbol register/unregister tracking + */ + +struct perf_ksymbol_event { + const char *name; + int name_len; + struct { + struct perf_event_header header; + u64 addr; + u32 len; + u16 ksym_type; + u16 flags; + } event_id; +}; + +static int perf_event_ksymbol_match(struct perf_event *event) +{ + return event->attr.ksymbol; +} + +static void perf_event_ksymbol_output(struct perf_event *event, void *data) +{ + struct perf_ksymbol_event *ksymbol_event = data; + struct perf_output_handle handle; + struct perf_sample_data sample; + int ret; + + if (!perf_event_ksymbol_match(event)) + return; + + perf_event_header__init_id(&ksymbol_event->event_id.header, + &sample, event); + ret = perf_output_begin(&handle, event, + ksymbol_event->event_id.header.size); + if (ret) + return; + + perf_output_put(&handle, ksymbol_event->event_id); + __output_copy(&handle, ksymbol_event->name, ksymbol_event->name_len); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + +void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, + const char *sym) +{ + struct perf_ksymbol_event ksymbol_event; + char name[KSYM_NAME_LEN]; + u16 flags = 0; + int name_len; + + if (!atomic_read(&nr_ksymbol_events)) + return; + + if (ksym_type >= PERF_RECORD_KSYMBOL_TYPE_MAX || + ksym_type == PERF_RECORD_KSYMBOL_TYPE_UNKNOWN) + goto err; + + strlcpy(name, sym, KSYM_NAME_LEN); + name_len = strlen(name) + 1; + while (!IS_ALIGNED(name_len, sizeof(u64))) + name[name_len++] = '\0'; + BUILD_BUG_ON(KSYM_NAME_LEN % sizeof(u64)); + + if (unregister) + flags |= PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER; + + ksymbol_event = (struct perf_ksymbol_event){ + .name = name, + .name_len = name_len, + .event_id = { + .header = { + .type = PERF_RECORD_KSYMBOL, + .size = sizeof(ksymbol_event.event_id) + + name_len, + }, + .addr = addr, + .len = len, + .ksym_type = ksym_type, + .flags = flags, + }, + }; + + perf_iterate_sb(perf_event_ksymbol_output, &ksymbol_event, NULL); + return; +err: + WARN_ONCE(1, "%s: Invalid KSYMBOL type 0x%x\n", __func__, ksym_type); +} + void perf_event_itrace_started(struct perf_event *event) { event->attach_state |= PERF_ATTACH_ITRACE; @@ -9912,6 +10006,8 @@ static void account_event(struct perf_event *event) inc = true; if (is_cgroup_event(event)) inc = true; + if (event->attr.ksymbol) + atomic_inc(&nr_ksymbol_events); if (inc) { /* -- cgit v1.2.3 From 6ee52e2a3fe4ea35520720736e6791df1fb67106 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 17 Jan 2019 08:15:15 -0800 Subject: perf, bpf: Introduce PERF_RECORD_BPF_EVENT For better performance analysis of BPF programs, this patch introduces PERF_RECORD_BPF_EVENT, a new perf_event_type that exposes BPF program load/unload information to user space. Each BPF program may contain up to BPF_MAX_SUBPROGS (256) sub programs. The following example shows kernel symbols for a BPF program with 7 sub programs: ffffffffa0257cf9 t bpf_prog_b07ccb89267cf242_F ffffffffa02592e1 t bpf_prog_2dcecc18072623fc_F ffffffffa025b0e9 t bpf_prog_bb7a405ebaec5d5c_F ffffffffa025dd2c t bpf_prog_a7540d4a39ec1fc7_F ffffffffa025fcca t bpf_prog_05762d4ade0e3737_F ffffffffa026108f t bpf_prog_db4bd11e35df90d4_F ffffffffa0263f00 t bpf_prog_89d64e4abf0f0126_F ffffffffa0257cf9 t bpf_prog_ae31629322c4b018__dummy_tracepoi When a bpf program is loaded, PERF_RECORD_KSYMBOL is generated for each of these sub programs. Therefore, PERF_RECORD_BPF_EVENT is not needed for simple profiling. For annotation, user space need to listen to PERF_RECORD_BPF_EVENT and gather more information about these (sub) programs via sys_bpf. Signed-off-by: Song Liu Reviewed-by: Arnaldo Carvalho de Melo Acked-by: Alexei Starovoitov Acked-by: Peter Zijlstra (Intel) Tested-by: Arnaldo Carvalho de Melo Cc: Daniel Borkmann Cc: Peter Zijlstra Cc: kernel-team@fb.com Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/20190117161521.1341602-4-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/filter.h | 7 +++ include/linux/perf_event.h | 6 +++ include/uapi/linux/perf_event.h | 29 +++++++++- kernel/bpf/core.c | 2 +- kernel/bpf/syscall.c | 2 + kernel/events/core.c | 115 ++++++++++++++++++++++++++++++++++++++++ 6 files changed, 159 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..d531d4250bff 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -951,6 +951,7 @@ bpf_address_lookup(unsigned long addr, unsigned long *size, void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); +void bpf_get_prog_name(const struct bpf_prog *prog, char *sym); #else /* CONFIG_BPF_JIT */ @@ -1006,6 +1007,12 @@ static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } + +static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) +{ + sym[0] = '\0'; +} + #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 136fe0495374..a79e59fc3b7d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1125,6 +1125,9 @@ extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); +extern void perf_event_bpf_event(struct bpf_prog *prog, + enum perf_bpf_event_type type, + u16 flags); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); @@ -1350,6 +1353,9 @@ static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } +static inline void perf_event_bpf_event(struct bpf_prog *prog, + enum perf_bpf_event_type type, + u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 1dee5c8f166b..7198ddd0c6b1 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -373,7 +373,8 @@ struct perf_event_attr { write_backward : 1, /* Write ring buffer from end to beginning */ namespaces : 1, /* include namespaces data */ ksymbol : 1, /* include ksymbol events */ - __reserved_1 : 34; + bpf_event : 1, /* include bpf events */ + __reserved_1 : 33; union { __u32 wakeup_events; /* wakeup every n events */ @@ -979,6 +980,25 @@ enum perf_event_type { */ PERF_RECORD_KSYMBOL = 17, + /* + * Record bpf events: + * enum perf_bpf_event_type { + * PERF_BPF_EVENT_UNKNOWN = 0, + * PERF_BPF_EVENT_PROG_LOAD = 1, + * PERF_BPF_EVENT_PROG_UNLOAD = 2, + * }; + * + * struct { + * struct perf_event_header header; + * u16 type; + * u16 flags; + * u32 id; + * u8 tag[BPF_TAG_SIZE]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_BPF_EVENT = 18, + PERF_RECORD_MAX, /* non-ABI */ }; @@ -990,6 +1010,13 @@ enum perf_record_ksymbol_type { #define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) +enum perf_bpf_event_type { + PERF_BPF_EVENT_UNKNOWN = 0, + PERF_BPF_EVENT_PROG_LOAD = 1, + PERF_BPF_EVENT_PROG_UNLOAD = 2, + PERF_BPF_EVENT_MAX, /* non-ABI */ +}; + #define PERF_MAX_STACK_DEPTH 127 #define PERF_MAX_CONTEXTS_PER_STACK 8 diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index f908b9356025..19c49313c709 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -495,7 +495,7 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog, *symbol_end = addr + hdr->pages * PAGE_SIZE; } -static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) +void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) { const char *end = sym + KSYM_NAME_LEN; const struct btf_type *type; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b155cd17c1bd..30ebd085790b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1211,6 +1211,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic_dec_and_test(&prog->aux->refcnt)) { + perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); bpf_prog_kallsyms_del_all(prog); @@ -1554,6 +1555,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) } bpf_prog_kallsyms_add(prog); + perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); return err; free_used_maps: diff --git a/kernel/events/core.c b/kernel/events/core.c index e04ab5f325cf..236bb8ddb7bc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -386,6 +386,7 @@ static atomic_t nr_task_events __read_mostly; static atomic_t nr_freq_events __read_mostly; static atomic_t nr_switch_events __read_mostly; static atomic_t nr_ksymbol_events __read_mostly; +static atomic_t nr_bpf_events __read_mostly; static LIST_HEAD(pmus); static DEFINE_MUTEX(pmus_lock); @@ -4308,6 +4309,8 @@ static void unaccount_event(struct perf_event *event) dec = true; if (event->attr.ksymbol) atomic_dec(&nr_ksymbol_events); + if (event->attr.bpf_event) + atomic_dec(&nr_bpf_events); if (dec) { if (!atomic_add_unless(&perf_sched_count, -1, 1)) @@ -7747,6 +7750,116 @@ err: WARN_ONCE(1, "%s: Invalid KSYMBOL type 0x%x\n", __func__, ksym_type); } +/* + * bpf program load/unload tracking + */ + +struct perf_bpf_event { + struct bpf_prog *prog; + struct { + struct perf_event_header header; + u16 type; + u16 flags; + u32 id; + u8 tag[BPF_TAG_SIZE]; + } event_id; +}; + +static int perf_event_bpf_match(struct perf_event *event) +{ + return event->attr.bpf_event; +} + +static void perf_event_bpf_output(struct perf_event *event, void *data) +{ + struct perf_bpf_event *bpf_event = data; + struct perf_output_handle handle; + struct perf_sample_data sample; + int ret; + + if (!perf_event_bpf_match(event)) + return; + + perf_event_header__init_id(&bpf_event->event_id.header, + &sample, event); + ret = perf_output_begin(&handle, event, + bpf_event->event_id.header.size); + if (ret) + return; + + perf_output_put(&handle, bpf_event->event_id); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + +static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog, + enum perf_bpf_event_type type) +{ + bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD; + char sym[KSYM_NAME_LEN]; + int i; + + if (prog->aux->func_cnt == 0) { + bpf_get_prog_name(prog, sym); + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, + (u64)(unsigned long)prog->bpf_func, + prog->jited_len, unregister, sym); + } else { + for (i = 0; i < prog->aux->func_cnt; i++) { + struct bpf_prog *subprog = prog->aux->func[i]; + + bpf_get_prog_name(subprog, sym); + perf_event_ksymbol( + PERF_RECORD_KSYMBOL_TYPE_BPF, + (u64)(unsigned long)subprog->bpf_func, + subprog->jited_len, unregister, sym); + } + } +} + +void perf_event_bpf_event(struct bpf_prog *prog, + enum perf_bpf_event_type type, + u16 flags) +{ + struct perf_bpf_event bpf_event; + + if (type <= PERF_BPF_EVENT_UNKNOWN || + type >= PERF_BPF_EVENT_MAX) + return; + + switch (type) { + case PERF_BPF_EVENT_PROG_LOAD: + case PERF_BPF_EVENT_PROG_UNLOAD: + if (atomic_read(&nr_ksymbol_events)) + perf_event_bpf_emit_ksymbols(prog, type); + break; + default: + break; + } + + if (!atomic_read(&nr_bpf_events)) + return; + + bpf_event = (struct perf_bpf_event){ + .prog = prog, + .event_id = { + .header = { + .type = PERF_RECORD_BPF_EVENT, + .size = sizeof(bpf_event.event_id), + }, + .type = type, + .flags = flags, + .id = prog->aux->id, + }, + }; + + BUILD_BUG_ON(BPF_TAG_SIZE % sizeof(u64)); + + memcpy(bpf_event.event_id.tag, prog->tag, BPF_TAG_SIZE); + perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL); +} + void perf_event_itrace_started(struct perf_event *event) { event->attach_state |= PERF_ATTACH_ITRACE; @@ -10008,6 +10121,8 @@ static void account_event(struct perf_event *event) inc = true; if (event->attr.ksymbol) atomic_inc(&nr_ksymbol_events); + if (event->attr.bpf_event) + atomic_inc(&nr_bpf_events); if (inc) { /* -- cgit v1.2.3 From 534fd7aac56a7994d16032f32123def9923e339f Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 13 Jan 2019 16:01:17 +0200 Subject: IB/mlx5: Manage indirection mkey upon DEVX flow for ODP Manage indirection mkey upon DEVX flow to support ODP. To support a page fault event on the indirection mkey it needs to be part of the device mkey radix tree. Both the creation and the deletion flows for a DEVX object which is indirection mkey were adapted to handle that. Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/devx.c | 89 +++++++++++++++++++++++++++++++++++- drivers/infiniband/hw/mlx5/main.c | 1 + drivers/infiniband/hw/mlx5/mlx5_ib.h | 6 +++ include/linux/mlx5/driver.h | 1 + 4 files changed, 96 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index b7ff2138ac2a..bbf9a26d8fa6 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -17,12 +17,18 @@ #define UVERBS_MODULE_NAME mlx5_ib #include +enum devx_obj_flags { + DEVX_OBJ_FLAGS_INDIRECT_MKEY = 1 << 0, +}; + #define MLX5_MAX_DESTROY_INBOX_SIZE_DW MLX5_ST_SZ_DW(delete_fte_in) struct devx_obj { struct mlx5_core_dev *mdev; u64 obj_id; u32 dinlen; /* destroy inbox length */ u32 dinbox[MLX5_MAX_DESTROY_INBOX_SIZE_DW]; + u32 flags; + struct mlx5_ib_devx_mr devx_mr; }; struct devx_umem { @@ -1011,6 +1017,36 @@ static void devx_obj_build_destroy_cmd(void *in, void *out, void *din, } } +static int devx_handle_mkey_indirect(struct devx_obj *obj, + struct mlx5_ib_dev *dev, + void *in, void *out) +{ + struct mlx5_mkey_table *table = &dev->mdev->priv.mkey_table; + struct mlx5_ib_devx_mr *devx_mr = &obj->devx_mr; + unsigned long flags; + struct mlx5_core_mkey *mkey; + void *mkc; + u8 key; + int err; + + mkey = &devx_mr->mmkey; + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + key = MLX5_GET(mkc, mkc, mkey_7_0); + mkey->key = mlx5_idx_to_mkey( + MLX5_GET(create_mkey_out, out, mkey_index)) | key; + mkey->type = MLX5_MKEY_INDIRECT_DEVX; + mkey->iova = MLX5_GET64(mkc, mkc, start_addr); + mkey->size = MLX5_GET64(mkc, mkc, len); + mkey->pd = MLX5_GET(mkc, mkc, pd); + devx_mr->ndescs = MLX5_GET(mkc, mkc, translations_octword_size); + + write_lock_irqsave(&table->lock, flags); + err = radix_tree_insert(&table->tree, mlx5_base_mkey(mkey->key), + mkey); + write_unlock_irqrestore(&table->lock, flags); + return err; +} + static int devx_handle_mkey_create(struct mlx5_ib_dev *dev, struct devx_obj *obj, void *in, int in_len) @@ -1030,13 +1066,45 @@ static int devx_handle_mkey_create(struct mlx5_ib_dev *dev, access_mode |= MLX5_GET(mkc, mkc, access_mode_4_2) << 2; if (access_mode == MLX5_MKC_ACCESS_MODE_KLMS || - access_mode == MLX5_MKC_ACCESS_MODE_KSM) + access_mode == MLX5_MKC_ACCESS_MODE_KSM) { + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) + obj->flags |= DEVX_OBJ_FLAGS_INDIRECT_MKEY; return 0; + } MLX5_SET(create_mkey_in, in, mkey_umem_valid, 1); return 0; } +static void devx_free_indirect_mkey(struct rcu_head *rcu) +{ + kfree(container_of(rcu, struct devx_obj, devx_mr.rcu)); +} + +/* This function to delete from the radix tree needs to be called before + * destroying the underlying mkey. Otherwise a race might occur in case that + * other thread will get the same mkey before this one will be deleted, + * in that case it will fail via inserting to the tree its own data. + * + * Note: + * An error in the destroy is not expected unless there is some other indirect + * mkey which points to this one. In a kernel cleanup flow it will be just + * destroyed in the iterative destruction call. In a user flow, in case + * the application didn't close in the expected order it's its own problem, + * the mkey won't be part of the tree, in both cases the kernel is safe. + */ +static void devx_cleanup_mkey(struct devx_obj *obj) +{ + struct mlx5_mkey_table *table = &obj->mdev->priv.mkey_table; + struct mlx5_core_mkey *del_mkey; + unsigned long flags; + + write_lock_irqsave(&table->lock, flags); + del_mkey = radix_tree_delete(&table->tree, + mlx5_base_mkey(obj->devx_mr.mmkey.key)); + write_unlock_irqrestore(&table->lock, flags); +} + static int devx_obj_cleanup(struct ib_uobject *uobject, enum rdma_remove_reason why) { @@ -1044,10 +1112,21 @@ static int devx_obj_cleanup(struct ib_uobject *uobject, struct devx_obj *obj = uobject->object; int ret; + if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) + devx_cleanup_mkey(obj); + ret = mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out, sizeof(out)); if (ib_is_destroy_retryable(ret, why, uobject)) return ret; + if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) { + struct mlx5_ib_dev *dev = to_mdev(uobject->context->device); + + call_srcu(&dev->mr_srcu, &obj->devx_mr.rcu, + devx_free_indirect_mkey); + return ret; + } + kfree(obj); return ret; } @@ -1108,6 +1187,12 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( &obj_id); WARN_ON(obj->dinlen > MLX5_MAX_DESTROY_INBOX_SIZE_DW * sizeof(u32)); + if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) { + err = devx_handle_mkey_indirect(obj, dev, cmd_in, cmd_out); + if (err) + goto obj_destroy; + } + err = uverbs_copy_to(attrs, MLX5_IB_ATTR_DEVX_OBJ_CREATE_CMD_OUT, cmd_out, cmd_out_len); if (err) goto obj_destroy; @@ -1116,6 +1201,8 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( return 0; obj_destroy: + if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) + devx_cleanup_mkey(obj); mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out, sizeof(out)); obj_free: kfree(obj); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 61064b7171fc..ae00f994673b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -5724,6 +5724,7 @@ void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) { mlx5_ib_cleanup_multiport_master(dev); if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { + srcu_barrier(&dev->mr_srcu); cleanup_srcu_struct(&dev->mr_srcu); drain_workqueue(dev->advise_mr_wq); destroy_workqueue(dev->advise_mr_wq); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index b0a37ca2a714..819207190343 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -602,6 +602,12 @@ struct mlx5_ib_mw { int ndescs; }; +struct mlx5_ib_devx_mr { + struct mlx5_core_mkey mmkey; + int ndescs; + struct rcu_head rcu; +}; + struct mlx5_ib_umr_context { struct ib_cqe cqe; enum ib_wc_status status; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index b6f5839f129a..619d6fee96a1 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -364,6 +364,7 @@ struct mlx5_core_sig_ctx { enum { MLX5_MKEY_MR = 1, MLX5_MKEY_MW, + MLX5_MKEY_INDIRECT_DEVX, }; struct mlx5_core_mkey { -- cgit v1.2.3 From c4f5627f7eeecde1bb6b646d8c0907b96dc2b2a6 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Wed, 2 Jan 2019 16:11:20 -0800 Subject: Bluetooth: Fix locking in bt_accept_enqueue() for BH context With commit e16337622016 ("Bluetooth: Handle bt_accept_enqueue() socket atomically") lock_sock[_nested]() is used to acquire the socket lock before manipulating the socket. lock_sock[_nested]() may block, which is problematic since bt_accept_enqueue() can be called in bottom half context (e.g. from rfcomm_connect_ind()): [] __might_sleep+0x4c/0x80 [] lock_sock_nested+0x24/0x58 [] bt_accept_enqueue+0x48/0xd4 [bluetooth] [] rfcomm_connect_ind+0x190/0x218 [rfcomm] Add a parameter to bt_accept_enqueue() to indicate whether the function is called from BH context, and acquire the socket lock with bh_lock_sock_nested() if that's the case. Also adapt all callers of bt_accept_enqueue() to pass the new parameter: - l2cap_sock_new_connection_cb() - uses lock_sock() to lock the parent socket => process context - rfcomm_connect_ind() - acquires the parent socket lock with bh_lock_sock() => BH context - __sco_chan_add() - called from sco_chan_add(), which is called from sco_connect(). parent is NULL, hence bt_accept_enqueue() isn't called in this code path and we can ignore it - also called from sco_conn_ready(). uses bh_lock_sock() to acquire the parent lock => BH context Fixes: e16337622016 ("Bluetooth: Handle bt_accept_enqueue() socket atomically") Signed-off-by: Matthias Kaehlcke Reviewed-by: Douglas Anderson Signed-off-by: Marcel Holtmann Cc: stable@vger.kernel.org --- include/net/bluetooth/bluetooth.h | 2 +- net/bluetooth/af_bluetooth.c | 16 +++++++++++++--- net/bluetooth/l2cap_sock.c | 2 +- net/bluetooth/rfcomm/sock.c | 2 +- net/bluetooth/sco.c | 2 +- 5 files changed, 17 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index ec9d6bc65855..fabee6db0abb 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -276,7 +276,7 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo); int bt_sock_wait_ready(struct sock *sk, unsigned long flags); -void bt_accept_enqueue(struct sock *parent, struct sock *sk); +void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh); void bt_accept_unlink(struct sock *sk); struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock); diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index deacc52d7ff1..8d12198eaa94 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -154,15 +154,25 @@ void bt_sock_unlink(struct bt_sock_list *l, struct sock *sk) } EXPORT_SYMBOL(bt_sock_unlink); -void bt_accept_enqueue(struct sock *parent, struct sock *sk) +void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { BT_DBG("parent %p, sk %p", parent, sk); sock_hold(sk); - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + + if (bh) + bh_lock_sock_nested(sk); + else + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; - release_sock(sk); + + if (bh) + bh_unlock_sock(sk); + else + release_sock(sk); + parent->sk_ack_backlog++; } EXPORT_SYMBOL(bt_accept_enqueue); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 686bdc6b35b0..a3a2cd55e23a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1252,7 +1252,7 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) l2cap_sock_init(sk, parent); - bt_accept_enqueue(parent, sk); + bt_accept_enqueue(parent, sk, false); release_sock(parent); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index aa0db1d1bd9b..b1f49fcc0478 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -988,7 +988,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * rfcomm_pi(sk)->channel = channel; sk->sk_state = BT_CONFIG; - bt_accept_enqueue(parent, sk); + bt_accept_enqueue(parent, sk, true); /* Accept connection and return socket DLC */ *d = rfcomm_pi(sk)->dlc; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 529b38996d8b..9a580999ca57 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -193,7 +193,7 @@ static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, conn->sk = sk; if (parent) - bt_accept_enqueue(parent, sk); + bt_accept_enqueue(parent, sk, true); } static int sco_chan_add(struct sco_conn *conn, struct sock *sk, -- cgit v1.2.3 From 1278cf66cf4b1c3d30e311200b50c45457c92baa Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: nvram: Replace nvram_* function exports with static functions Replace nvram_* functions with static functions in nvram.h. These will become wrappers for struct nvram_ops method calls. This patch effectively disables existing NVRAM functionality so as to allow the rest of the series to be bisected without build failures. That functionality is gradually re-implemented in subsequent patches. Replace the sole validate-checksum-and-read-byte sequence with a call to nvram_read() which will gain the same semantics in subsequent patches. Remove unused exports. Acked-by: Geert Uytterhoeven Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- arch/m68k/atari/nvram.c | 39 +++------------------------------------ drivers/char/nvram.c | 27 +++++---------------------- drivers/scsi/atari_scsi.c | 8 +++++--- include/linux/nvram.h | 32 +++++++++++++++++++++++++------- 4 files changed, 38 insertions(+), 68 deletions(-) (limited to 'include') diff --git a/arch/m68k/atari/nvram.c b/arch/m68k/atari/nvram.c index a8c457e40b0b..1d767847ffa6 100644 --- a/arch/m68k/atari/nvram.c +++ b/arch/m68k/atari/nvram.c @@ -34,38 +34,17 @@ * periodic 11 min sync from kernel/time/ntp.c vs. this driver.) */ -unsigned char __nvram_read_byte(int i) +static unsigned char __nvram_read_byte(int i) { return CMOS_READ(NVRAM_FIRST_BYTE + i); } -unsigned char nvram_read_byte(int i) -{ - unsigned long flags; - unsigned char c; - - spin_lock_irqsave(&rtc_lock, flags); - c = __nvram_read_byte(i); - spin_unlock_irqrestore(&rtc_lock, flags); - return c; -} -EXPORT_SYMBOL(nvram_read_byte); - /* This races nicely with trying to read with checksum checking */ -void __nvram_write_byte(unsigned char c, int i) +static void __nvram_write_byte(unsigned char c, int i) { CMOS_WRITE(c, NVRAM_FIRST_BYTE + i); } -void nvram_write_byte(unsigned char c, int i) -{ - unsigned long flags; - - spin_lock_irqsave(&rtc_lock, flags); - __nvram_write_byte(c, i); - spin_unlock_irqrestore(&rtc_lock, flags); -} - /* On Ataris, the checksum is over all bytes except the checksum bytes * themselves; these are at the very end. */ @@ -73,7 +52,7 @@ void nvram_write_byte(unsigned char c, int i) #define ATARI_CKS_RANGE_END 47 #define ATARI_CKS_LOC 48 -int __nvram_check_checksum(void) +static int __nvram_check_checksum(void) { int i; unsigned char sum = 0; @@ -84,18 +63,6 @@ int __nvram_check_checksum(void) (__nvram_read_byte(ATARI_CKS_LOC + 1) == (sum & 0xff)); } -int nvram_check_checksum(void) -{ - unsigned long flags; - int rv; - - spin_lock_irqsave(&rtc_lock, flags); - rv = __nvram_check_checksum(); - spin_unlock_irqrestore(&rtc_lock, flags); - return rv; -} -EXPORT_SYMBOL(nvram_check_checksum); - static void __nvram_set_checksum(void) { int i; diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c index c660cff9faf4..c98775bfd896 100644 --- a/drivers/char/nvram.c +++ b/drivers/char/nvram.c @@ -74,13 +74,12 @@ static int nvram_open_mode; /* special open modes */ * periodic 11 min sync from kernel/time/ntp.c vs. this driver.) */ -unsigned char __nvram_read_byte(int i) +static unsigned char __nvram_read_byte(int i) { return CMOS_READ(NVRAM_FIRST_BYTE + i); } -EXPORT_SYMBOL(__nvram_read_byte); -unsigned char nvram_read_byte(int i) +static unsigned char pc_nvram_read_byte(int i) { unsigned long flags; unsigned char c; @@ -90,16 +89,14 @@ unsigned char nvram_read_byte(int i) spin_unlock_irqrestore(&rtc_lock, flags); return c; } -EXPORT_SYMBOL(nvram_read_byte); /* This races nicely with trying to read with checksum checking (nvram_read) */ -void __nvram_write_byte(unsigned char c, int i) +static void __nvram_write_byte(unsigned char c, int i) { CMOS_WRITE(c, NVRAM_FIRST_BYTE + i); } -EXPORT_SYMBOL(__nvram_write_byte); -void nvram_write_byte(unsigned char c, int i) +static void pc_nvram_write_byte(unsigned char c, int i) { unsigned long flags; @@ -107,14 +104,13 @@ void nvram_write_byte(unsigned char c, int i) __nvram_write_byte(c, i); spin_unlock_irqrestore(&rtc_lock, flags); } -EXPORT_SYMBOL(nvram_write_byte); /* On PCs, the checksum is built only over bytes 2..31 */ #define PC_CKS_RANGE_START 2 #define PC_CKS_RANGE_END 31 #define PC_CKS_LOC 32 -int __nvram_check_checksum(void) +static int __nvram_check_checksum(void) { int i; unsigned short sum = 0; @@ -126,19 +122,6 @@ int __nvram_check_checksum(void) __nvram_read_byte(PC_CKS_LOC+1); return (sum & 0xffff) == expect; } -EXPORT_SYMBOL(__nvram_check_checksum); - -int nvram_check_checksum(void) -{ - unsigned long flags; - int rv; - - spin_lock_irqsave(&rtc_lock, flags); - rv = __nvram_check_checksum(); - spin_unlock_irqrestore(&rtc_lock, flags); - return rv; -} -EXPORT_SYMBOL(nvram_check_checksum); static void __nvram_set_checksum(void) { diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c index 78b43200c99e..e809493d0d06 100644 --- a/drivers/scsi/atari_scsi.c +++ b/drivers/scsi/atari_scsi.c @@ -759,13 +759,15 @@ static int __init atari_scsi_probe(struct platform_device *pdev) atari_scsi_template.this_id = setup_hostid & 7; } else if (IS_REACHABLE(CONFIG_NVRAM)) { /* Test if a host id is set in the NVRam */ - if (ATARIHW_PRESENT(TT_CLK) && nvram_check_checksum()) { - unsigned char b = nvram_read_byte(16); + if (ATARIHW_PRESENT(TT_CLK)) { + unsigned char b; + loff_t offset = 16; + ssize_t count = nvram_read(&b, 1, &offset); /* Arbitration enabled? (for TOS) * If yes, use configured host ID */ - if (b & 0x80) + if ((count == 1) && (b & 0x80)) atari_scsi_template.this_id = b & 7; } } diff --git a/include/linux/nvram.h b/include/linux/nvram.h index 28bfb9ab94ca..eb5b52a9a747 100644 --- a/include/linux/nvram.h +++ b/include/linux/nvram.h @@ -2,13 +2,31 @@ #ifndef _LINUX_NVRAM_H #define _LINUX_NVRAM_H +#include #include -/* __foo is foo without grabbing the rtc_lock - get it yourself */ -extern unsigned char __nvram_read_byte(int i); -extern unsigned char nvram_read_byte(int i); -extern void __nvram_write_byte(unsigned char c, int i); -extern void nvram_write_byte(unsigned char c, int i); -extern int __nvram_check_checksum(void); -extern int nvram_check_checksum(void); +static inline ssize_t nvram_get_size(void) +{ + return -ENODEV; +} + +static inline unsigned char nvram_read_byte(int addr) +{ + return 0xFF; +} + +static inline void nvram_write_byte(unsigned char val, int addr) +{ +} + +static inline ssize_t nvram_read(char *buf, size_t count, loff_t *ppos) +{ + return -ENODEV; +} + +static inline ssize_t nvram_write(char *buf, size_t count, loff_t *ppos) +{ + return -ENODEV; +} + #endif /* _LINUX_NVRAM_H */ -- cgit v1.2.3 From a084dbf6592c22468eb946014b2e731fb42da7a9 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: m68k/atari: Implement arch_nvram_ops struct By implementing an arch_nvram_ops struct, a platform can re-use the drivers/char/nvram.c module without needing any arch-specific code in that module. Atari does so here. Acked-by: Geert Uytterhoeven Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- arch/m68k/atari/nvram.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nvram.h | 14 ++++++++++++++ 2 files changed, 63 insertions(+) (limited to 'include') diff --git a/arch/m68k/atari/nvram.c b/arch/m68k/atari/nvram.c index 1d767847ffa6..e75adebe6e7d 100644 --- a/arch/m68k/atari/nvram.c +++ b/arch/m68k/atari/nvram.c @@ -74,6 +74,55 @@ static void __nvram_set_checksum(void) __nvram_write_byte(sum, ATARI_CKS_LOC + 1); } +static ssize_t atari_nvram_read(char *buf, size_t count, loff_t *ppos) +{ + char *p = buf; + loff_t i; + + spin_lock_irq(&rtc_lock); + if (!__nvram_check_checksum()) { + spin_unlock_irq(&rtc_lock); + return -EIO; + } + for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) + *p = __nvram_read_byte(i); + spin_unlock_irq(&rtc_lock); + + *ppos = i; + return p - buf; +} + +static ssize_t atari_nvram_write(char *buf, size_t count, loff_t *ppos) +{ + char *p = buf; + loff_t i; + + spin_lock_irq(&rtc_lock); + if (!__nvram_check_checksum()) { + spin_unlock_irq(&rtc_lock); + return -EIO; + } + for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) + __nvram_write_byte(*p, i); + __nvram_set_checksum(); + spin_unlock_irq(&rtc_lock); + + *ppos = i; + return p - buf; +} + +static ssize_t atari_nvram_get_size(void) +{ + return NVRAM_BYTES; +} + +const struct nvram_ops arch_nvram_ops = { + .read = atari_nvram_read, + .write = atari_nvram_write, + .get_size = atari_nvram_get_size, +}; +EXPORT_SYMBOL(arch_nvram_ops); + #ifdef CONFIG_PROC_FS static struct { unsigned char val; diff --git a/include/linux/nvram.h b/include/linux/nvram.h index eb5b52a9a747..a1e01dc89759 100644 --- a/include/linux/nvram.h +++ b/include/linux/nvram.h @@ -5,8 +5,18 @@ #include #include +struct nvram_ops { + ssize_t (*get_size)(void); + ssize_t (*read)(char *, size_t, loff_t *); + ssize_t (*write)(char *, size_t, loff_t *); +}; + +extern const struct nvram_ops arch_nvram_ops; + static inline ssize_t nvram_get_size(void) { + if (arch_nvram_ops.get_size) + return arch_nvram_ops.get_size(); return -ENODEV; } @@ -21,11 +31,15 @@ static inline void nvram_write_byte(unsigned char val, int addr) static inline ssize_t nvram_read(char *buf, size_t count, loff_t *ppos) { + if (arch_nvram_ops.read) + return arch_nvram_ops.read(buf, count, ppos); return -ENODEV; } static inline ssize_t nvram_write(char *buf, size_t count, loff_t *ppos) { + if (arch_nvram_ops.write) + return arch_nvram_ops.write(buf, count, ppos); return -ENODEV; } -- cgit v1.2.3 From a156c7ba669c65b55c7afcc3994e1199cc0cad47 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: powerpc: Replace nvram_* extern declarations with standard header Remove the nvram_read_byte() and nvram_write_byte() declarations in powerpc/include/asm/nvram.h and use the cross-platform static functions in linux/nvram.h instead. Tested-by: Stan Johnson Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/nvram.h | 6 ------ arch/powerpc/kernel/setup_32.c | 25 +------------------------ drivers/char/generic_nvram.c | 1 + drivers/video/fbdev/matrox/matroxfb_base.c | 2 +- include/linux/nvram.h | 3 +++ 5 files changed, 6 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/arch/powerpc/include/asm/nvram.h b/arch/powerpc/include/asm/nvram.h index 09a518bb7c03..56a388da9c4f 100644 --- a/arch/powerpc/include/asm/nvram.h +++ b/arch/powerpc/include/asm/nvram.h @@ -98,10 +98,4 @@ extern int nvram_write_os_partition(struct nvram_os_partition *part, unsigned int err_type, unsigned int error_log_cnt); -/* Determine NVRAM size */ -extern ssize_t nvram_get_size(void); - -/* Normal access to NVRAM */ -extern unsigned char nvram_read_byte(int i); -extern void nvram_write_byte(unsigned char c, int i); #endif /* _ASM_POWERPC_NVRAM_H */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 947f904688b0..f5107796e2d7 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -149,30 +150,6 @@ __setup("l3cr=", ppc_setup_l3cr); #ifdef CONFIG_GENERIC_NVRAM -/* Generic nvram hooks used by drivers/char/gen_nvram.c */ -unsigned char nvram_read_byte(int addr) -{ - if (ppc_md.nvram_read_val) - return ppc_md.nvram_read_val(addr); - return 0xff; -} -EXPORT_SYMBOL(nvram_read_byte); - -void nvram_write_byte(unsigned char val, int addr) -{ - if (ppc_md.nvram_write_val) - ppc_md.nvram_write_val(addr, val); -} -EXPORT_SYMBOL(nvram_write_byte); - -ssize_t nvram_get_size(void) -{ - if (ppc_md.nvram_size) - return ppc_md.nvram_size(); - return -1; -} -EXPORT_SYMBOL(nvram_get_size); - void nvram_sync(void) { if (ppc_md.nvram_sync) diff --git a/drivers/char/generic_nvram.c b/drivers/char/generic_nvram.c index ff5394f47587..0c22b9503e84 100644 --- a/drivers/char/generic_nvram.c +++ b/drivers/char/generic_nvram.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/video/fbdev/matrox/matroxfb_base.c b/drivers/video/fbdev/matrox/matroxfb_base.c index 838869c6490c..0a4e5bad33f4 100644 --- a/drivers/video/fbdev/matrox/matroxfb_base.c +++ b/drivers/video/fbdev/matrox/matroxfb_base.c @@ -111,12 +111,12 @@ #include "matroxfb_g450.h" #include #include +#include #include #include #ifdef CONFIG_PPC_PMAC #include -unsigned char nvram_read_byte(int); static int default_vmode = VMODE_NVRAM; static int default_cmode = CMODE_NVRAM; #endif diff --git a/include/linux/nvram.h b/include/linux/nvram.h index a1e01dc89759..79431dab87a1 100644 --- a/include/linux/nvram.h +++ b/include/linux/nvram.h @@ -15,8 +15,11 @@ extern const struct nvram_ops arch_nvram_ops; static inline ssize_t nvram_get_size(void) { +#ifdef CONFIG_PPC +#else if (arch_nvram_ops.get_size) return arch_nvram_ops.get_size(); +#endif return -ENODEV; } -- cgit v1.2.3 From d5bbb5021ce8d9ff561c7469f5b4589ccb3bc4a6 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: char/nvram: Adopt arch_nvram_ops NVRAMs on different platforms and architectures have different attributes and access methods. E.g. some platforms have byte-at-a-time accessor functions while others have byte-range accessor functions. Some have checksum functionality while others do not. By calling ops struct methods via the common wrapper functions, the nvram module and other drivers can make use of the available NVRAM functionality in a portable way. Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- drivers/char/nvram.c | 30 ++++++++++++++++++++++++------ include/linux/nvram.h | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c index c98775bfd896..2df391f78986 100644 --- a/drivers/char/nvram.c +++ b/drivers/char/nvram.c @@ -52,9 +52,11 @@ static DEFINE_MUTEX(nvram_mutex); static DEFINE_SPINLOCK(nvram_state_lock); static int nvram_open_cnt; /* #times opened */ static int nvram_open_mode; /* special open modes */ +static ssize_t nvram_size; #define NVRAM_WRITE 1 /* opened for writing (exclusive) */ #define NVRAM_EXCL 2 /* opened with O_EXCL */ +#ifdef CONFIG_X86 /* * These functions are provided to be called internally or by other parts of * the kernel. It's up to the caller to ensure correct checksum before reading @@ -145,6 +147,19 @@ void nvram_set_checksum(void) } #endif /* 0 */ +static ssize_t pc_nvram_get_size(void) +{ + return NVRAM_BYTES; +} + +const struct nvram_ops arch_nvram_ops = { + .read_byte = pc_nvram_read_byte, + .write_byte = pc_nvram_write_byte, + .get_size = pc_nvram_get_size, +}; +EXPORT_SYMBOL(arch_nvram_ops); +#endif /* CONFIG_X86 */ + /* * The are the file operation function for user access to /dev/nvram */ @@ -152,7 +167,7 @@ void nvram_set_checksum(void) static loff_t nvram_misc_llseek(struct file *file, loff_t offset, int origin) { return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE, - NVRAM_BYTES); + nvram_size); } static ssize_t nvram_misc_read(struct file *file, char __user *buf, @@ -303,8 +318,7 @@ static int nvram_misc_release(struct inode *inode, struct file *file) return 0; } -#ifdef CONFIG_PROC_FS - +#if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) static const char * const floppy_types[] = { "none", "5.25'' 360k", "5.25'' 1.2M", "3.5'' 720k", "3.5'' 1.44M", "3.5'' 2.88M", "3.5'' 2.88M" @@ -394,7 +408,7 @@ static int nvram_proc_read(struct seq_file *seq, void *offset) return 0; } -#endif /* CONFIG_PROC_FS */ +#endif /* CONFIG_X86 && CONFIG_PROC_FS */ static const struct file_operations nvram_misc_fops = { .owner = THIS_MODULE, @@ -416,13 +430,17 @@ static int __init nvram_module_init(void) { int ret; + nvram_size = nvram_get_size(); + if (nvram_size < 0) + return nvram_size; + ret = misc_register(&nvram_misc); if (ret) { pr_err("nvram: can't misc_register on minor=%d\n", NVRAM_MINOR); return ret; } -#ifdef CONFIG_PROC_FS +#if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) if (!proc_create_single("driver/nvram", 0, NULL, nvram_proc_read)) { pr_err("nvram: can't create /proc/driver/nvram\n"); misc_deregister(&nvram_misc); @@ -436,7 +454,7 @@ static int __init nvram_module_init(void) static void __exit nvram_module_exit(void) { -#ifdef CONFIG_PROC_FS +#if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) remove_proc_entry("driver/nvram", NULL); #endif misc_deregister(&nvram_misc); diff --git a/include/linux/nvram.h b/include/linux/nvram.h index 79431dab87a1..bb4ea8cc6ea6 100644 --- a/include/linux/nvram.h +++ b/include/linux/nvram.h @@ -5,8 +5,30 @@ #include #include +/** + * struct nvram_ops - NVRAM functionality made available to drivers + * @read: validate checksum (if any) then load a range of bytes from NVRAM + * @write: store a range of bytes to NVRAM then update checksum (if any) + * @read_byte: load a single byte from NVRAM + * @write_byte: store a single byte to NVRAM + * @get_size: return the fixed number of bytes in the NVRAM + * + * Architectures which provide an nvram ops struct need not implement all + * of these methods. If the NVRAM hardware can be accessed only one byte + * at a time then it may be sufficient to provide .read_byte and .write_byte. + * If the NVRAM has a checksum (and it is to be checked) the .read and + * .write methods can be used to implement that efficiently. + * + * Portable drivers may use the wrapper functions defined here. + * The nvram_read() and nvram_write() functions call the .read and .write + * methods when available and fall back on the .read_byte and .write_byte + * methods otherwise. + */ + struct nvram_ops { ssize_t (*get_size)(void); + unsigned char (*read_byte)(int); + void (*write_byte)(unsigned char, int); ssize_t (*read)(char *, size_t, loff_t *); ssize_t (*write)(char *, size_t, loff_t *); }; @@ -25,11 +47,21 @@ static inline ssize_t nvram_get_size(void) static inline unsigned char nvram_read_byte(int addr) { +#ifdef CONFIG_PPC +#else + if (arch_nvram_ops.read_byte) + return arch_nvram_ops.read_byte(addr); +#endif return 0xFF; } static inline void nvram_write_byte(unsigned char val, int addr) { +#ifdef CONFIG_PPC +#else + if (arch_nvram_ops.write_byte) + arch_nvram_ops.write_byte(val, addr); +#endif } static inline ssize_t nvram_read(char *buf, size_t count, loff_t *ppos) -- cgit v1.2.3 From 2d58636e0af724f38acad25246c1625efec36122 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: char/nvram: Allow the set_checksum and initialize ioctls to be omitted The drivers/char/nvram.c module has previously supported only RTC "CMOS" NVRAM, for which it provides appropriate checksum ioctls. Make these ioctls optional so the module can be re-used with other kinds of NVRAM. The ops struct methods that implement the ioctls now return error codes so that a multi-platform kernel binary can do the right thing when running on hardware without a suitable NVRAM. Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- drivers/char/nvram.c | 70 +++++++++++++++++++++++++++++---------------------- include/linux/nvram.h | 2 ++ 2 files changed, 42 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c index 2df391f78986..f88ef41d0598 100644 --- a/drivers/char/nvram.c +++ b/drivers/char/nvram.c @@ -136,16 +136,25 @@ static void __nvram_set_checksum(void) __nvram_write_byte(sum & 0xff, PC_CKS_LOC + 1); } -#if 0 -void nvram_set_checksum(void) +static long pc_nvram_set_checksum(void) { - unsigned long flags; + spin_lock_irq(&rtc_lock); + __nvram_set_checksum(); + spin_unlock_irq(&rtc_lock); + return 0; +} - spin_lock_irqsave(&rtc_lock, flags); +static long pc_nvram_initialize(void) +{ + ssize_t i; + + spin_lock_irq(&rtc_lock); + for (i = 0; i < NVRAM_BYTES; ++i) + __nvram_write_byte(0, i); __nvram_set_checksum(); - spin_unlock_irqrestore(&rtc_lock, flags); + spin_unlock_irq(&rtc_lock); + return 0; } -#endif /* 0 */ static ssize_t pc_nvram_get_size(void) { @@ -156,6 +165,8 @@ const struct nvram_ops arch_nvram_ops = { .read_byte = pc_nvram_read_byte, .write_byte = pc_nvram_write_byte, .get_size = pc_nvram_get_size, + .set_checksum = pc_nvram_set_checksum, + .initialize = pc_nvram_initialize, }; EXPORT_SYMBOL(arch_nvram_ops); #endif /* CONFIG_X86 */ @@ -241,51 +252,50 @@ checksum_err: static long nvram_misc_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - int i; + long ret = -ENOTTY; switch (cmd) { - case NVRAM_INIT: /* initialize NVRAM contents and checksum */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; - mutex_lock(&nvram_mutex); - spin_lock_irq(&rtc_lock); - - for (i = 0; i < NVRAM_BYTES; ++i) - __nvram_write_byte(0, i); - __nvram_set_checksum(); - - spin_unlock_irq(&rtc_lock); - mutex_unlock(&nvram_mutex); - return 0; - + if (arch_nvram_ops.initialize != NULL) { + mutex_lock(&nvram_mutex); + ret = arch_nvram_ops.initialize(); + mutex_unlock(&nvram_mutex); + } + break; case NVRAM_SETCKS: /* just set checksum, contents unchanged (maybe useful after * checksum garbaged somehow...) */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; - mutex_lock(&nvram_mutex); - spin_lock_irq(&rtc_lock); - __nvram_set_checksum(); - spin_unlock_irq(&rtc_lock); - mutex_unlock(&nvram_mutex); - return 0; - - default: - return -ENOTTY; + if (arch_nvram_ops.set_checksum != NULL) { + mutex_lock(&nvram_mutex); + ret = arch_nvram_ops.set_checksum(); + mutex_unlock(&nvram_mutex); + } + break; } + return ret; } static int nvram_misc_open(struct inode *inode, struct file *file) { spin_lock(&nvram_state_lock); + /* Prevent multiple readers/writers if desired. */ if ((nvram_open_cnt && (file->f_flags & O_EXCL)) || - (nvram_open_mode & NVRAM_EXCL) || - ((file->f_mode & FMODE_WRITE) && (nvram_open_mode & NVRAM_WRITE))) { + (nvram_open_mode & NVRAM_EXCL)) { + spin_unlock(&nvram_state_lock); + return -EBUSY; + } + + /* Prevent multiple writers if the set_checksum ioctl is implemented. */ + if ((arch_nvram_ops.set_checksum != NULL) && + (file->f_mode & FMODE_WRITE) && (nvram_open_mode & NVRAM_WRITE)) { spin_unlock(&nvram_state_lock); return -EBUSY; } diff --git a/include/linux/nvram.h b/include/linux/nvram.h index bb4ea8cc6ea6..31c763087746 100644 --- a/include/linux/nvram.h +++ b/include/linux/nvram.h @@ -31,6 +31,8 @@ struct nvram_ops { void (*write_byte)(unsigned char, int); ssize_t (*read)(char *, size_t, loff_t *); ssize_t (*write)(char *, size_t, loff_t *); + long (*initialize)(void); + long (*set_checksum)(void); }; extern const struct nvram_ops arch_nvram_ops; -- cgit v1.2.3 From 109b3a89a7c48405d61a05d7a1720581a4f1574c Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: char/nvram: Implement NVRAM read/write methods Refactor the RTC "CMOS" NVRAM functions so that they can be used as arch_nvram_ops methods. Checksumming logic is moved from the misc device operations to the nvram read/write operations. This makes the misc device implementation more generic. This preserves the locking mechanism such that "read if checksum valid" and "write and update checksum" remain atomic operations. Some platforms implement byte-range read/write methods which are similar to file_operations struct methods. Other platforms provide only byte-at-a-time methods. The former are more efficient but may be unavailable so fall back on the latter methods when necessary. Tested-by: Stan Johnson Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- drivers/char/nvram.c | 120 +++++++++++++++++++++++++++++++------------------- include/linux/nvram.h | 32 +++++++++++++- 2 files changed, 104 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c index f88ef41d0598..adcc213c331e 100644 --- a/drivers/char/nvram.c +++ b/drivers/char/nvram.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -161,7 +162,46 @@ static ssize_t pc_nvram_get_size(void) return NVRAM_BYTES; } +static ssize_t pc_nvram_read(char *buf, size_t count, loff_t *ppos) +{ + char *p = buf; + loff_t i; + + spin_lock_irq(&rtc_lock); + if (!__nvram_check_checksum()) { + spin_unlock_irq(&rtc_lock); + return -EIO; + } + for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) + *p = __nvram_read_byte(i); + spin_unlock_irq(&rtc_lock); + + *ppos = i; + return p - buf; +} + +static ssize_t pc_nvram_write(char *buf, size_t count, loff_t *ppos) +{ + char *p = buf; + loff_t i; + + spin_lock_irq(&rtc_lock); + if (!__nvram_check_checksum()) { + spin_unlock_irq(&rtc_lock); + return -EIO; + } + for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) + __nvram_write_byte(*p, i); + __nvram_set_checksum(); + spin_unlock_irq(&rtc_lock); + + *ppos = i; + return p - buf; +} + const struct nvram_ops arch_nvram_ops = { + .read = pc_nvram_read, + .write = pc_nvram_write, .read_byte = pc_nvram_read_byte, .write_byte = pc_nvram_write_byte, .get_size = pc_nvram_get_size, @@ -184,69 +224,57 @@ static loff_t nvram_misc_llseek(struct file *file, loff_t offset, int origin) static ssize_t nvram_misc_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - unsigned char contents[NVRAM_BYTES]; - unsigned i = *ppos; - unsigned char *tmp; - - spin_lock_irq(&rtc_lock); + char *tmp; + ssize_t ret; - if (!__nvram_check_checksum()) - goto checksum_err; - for (tmp = contents; count-- > 0 && i < NVRAM_BYTES; ++i, ++tmp) - *tmp = __nvram_read_byte(i); + if (!access_ok(buf, count)) + return -EFAULT; + if (*ppos >= nvram_size) + return 0; - spin_unlock_irq(&rtc_lock); + count = min_t(size_t, count, nvram_size - *ppos); + count = min_t(size_t, count, PAGE_SIZE); - if (copy_to_user(buf, contents, tmp - contents)) - return -EFAULT; + tmp = kmalloc(count, GFP_KERNEL); + if (!tmp) + return -ENOMEM; - *ppos = i; + ret = nvram_read(tmp, count, ppos); + if (ret <= 0) + goto out; - return tmp - contents; + if (copy_to_user(buf, tmp, ret)) { + *ppos -= ret; + ret = -EFAULT; + } -checksum_err: - spin_unlock_irq(&rtc_lock); - return -EIO; +out: + kfree(tmp); + return ret; } static ssize_t nvram_misc_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - unsigned char contents[NVRAM_BYTES]; - unsigned i = *ppos; - unsigned char *tmp; - - if (i >= NVRAM_BYTES) - return 0; /* Past EOF */ - - if (count > NVRAM_BYTES - i) - count = NVRAM_BYTES - i; - if (count > NVRAM_BYTES) - return -EFAULT; /* Can't happen, but prove it to gcc */ + char *tmp; + ssize_t ret; - if (copy_from_user(contents, buf, count)) + if (!access_ok(buf, count)) return -EFAULT; + if (*ppos >= nvram_size) + return 0; - spin_lock_irq(&rtc_lock); - - if (!__nvram_check_checksum()) - goto checksum_err; - - for (tmp = contents; count--; ++i, ++tmp) - __nvram_write_byte(*tmp, i); + count = min_t(size_t, count, nvram_size - *ppos); + count = min_t(size_t, count, PAGE_SIZE); - __nvram_set_checksum(); - - spin_unlock_irq(&rtc_lock); + tmp = memdup_user(buf, count); + if (IS_ERR(tmp)) + return PTR_ERR(tmp); - *ppos = i; - - return tmp - contents; - -checksum_err: - spin_unlock_irq(&rtc_lock); - return -EIO; + ret = nvram_write(tmp, count, ppos); + kfree(tmp); + return ret; } static long nvram_misc_ioctl(struct file *file, unsigned int cmd, diff --git a/include/linux/nvram.h b/include/linux/nvram.h index 31c763087746..9df85703735c 100644 --- a/include/linux/nvram.h +++ b/include/linux/nvram.h @@ -66,18 +66,46 @@ static inline void nvram_write_byte(unsigned char val, int addr) #endif } +static inline ssize_t nvram_read_bytes(char *buf, size_t count, loff_t *ppos) +{ + ssize_t nvram_size = nvram_get_size(); + loff_t i; + char *p = buf; + + if (nvram_size < 0) + return nvram_size; + for (i = *ppos; count > 0 && i < nvram_size; ++i, ++p, --count) + *p = nvram_read_byte(i); + *ppos = i; + return p - buf; +} + +static inline ssize_t nvram_write_bytes(char *buf, size_t count, loff_t *ppos) +{ + ssize_t nvram_size = nvram_get_size(); + loff_t i; + char *p = buf; + + if (nvram_size < 0) + return nvram_size; + for (i = *ppos; count > 0 && i < nvram_size; ++i, ++p, --count) + nvram_write_byte(*p, i); + *ppos = i; + return p - buf; +} + static inline ssize_t nvram_read(char *buf, size_t count, loff_t *ppos) { if (arch_nvram_ops.read) return arch_nvram_ops.read(buf, count, ppos); - return -ENODEV; + return nvram_read_bytes(buf, count, ppos); } static inline ssize_t nvram_write(char *buf, size_t count, loff_t *ppos) { if (arch_nvram_ops.write) return arch_nvram_ops.write(buf, count, ppos); - return -ENODEV; + return nvram_write_bytes(buf, count, ppos); } #endif /* _LINUX_NVRAM_H */ -- cgit v1.2.3 From aefcb7460e0b5f35f72601b7a98eec5ca1639cf2 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: m68k/mac: Fix PRAM accessors PMU-based m68k Macs pre-date PowerMac-style NVRAM. Use the appropriate PMU commands. Also implement the missing XPRAM accessors for VIA-based Macs. Acked-by: Geert Uytterhoeven Tested-by: Stan Johnson Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- arch/m68k/mac/misc.c | 43 +++++++++++++++++++++++++++++++++---------- include/uapi/linux/pmu.h | 2 ++ 2 files changed, 35 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index af000a015f68..d016ca2e0d10 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -66,23 +66,22 @@ static unsigned char pmu_pram_read_byte(int offset) { struct adb_request req; - if (pmu_request(&req, NULL, 3, PMU_READ_NVRAM, - (offset >> 8) & 0xFF, offset & 0xFF) < 0) + if (pmu_request(&req, NULL, 3, PMU_READ_XPRAM, + offset & 0xFF, 1) < 0) return 0; - while (!req.complete) - pmu_poll(); - return req.reply[3]; + pmu_wait_complete(&req); + + return req.reply[0]; } static void pmu_pram_write_byte(unsigned char data, int offset) { struct adb_request req; - if (pmu_request(&req, NULL, 4, PMU_WRITE_NVRAM, - (offset >> 8) & 0xFF, offset & 0xFF, data) < 0) + if (pmu_request(&req, NULL, 4, PMU_WRITE_XPRAM, + offset & 0xFF, 1, data) < 0) return; - while (!req.complete) - pmu_poll(); + pmu_wait_complete(&req); } #endif /* CONFIG_ADB_PMU */ @@ -151,6 +150,16 @@ static void via_rtc_send(__u8 data) #define RTC_REG_SECONDS_3 3 #define RTC_REG_WRITE_PROTECT 13 +/* + * Inside Mac has no information about two-byte RTC commands but + * the MAME/MESS source code has the essentials. + */ + +#define RTC_REG_XPRAM 14 +#define RTC_CMD_XPRAM_READ (RTC_CMD_READ(RTC_REG_XPRAM) << 8) +#define RTC_CMD_XPRAM_WRITE (RTC_CMD_WRITE(RTC_REG_XPRAM) << 8) +#define RTC_CMD_XPRAM_ARG(a) (((a & 0xE0) << 3) | ((a & 0x1F) << 2)) + /* * Execute a VIA PRAM/RTC command. For read commands * data should point to a one-byte buffer for the @@ -198,11 +207,25 @@ static void via_rtc_command(int command, __u8 *data) static unsigned char via_pram_read_byte(int offset) { - return 0; + unsigned char temp; + + via_rtc_command(RTC_CMD_XPRAM_READ | RTC_CMD_XPRAM_ARG(offset), &temp); + + return temp; } static void via_pram_write_byte(unsigned char data, int offset) { + unsigned char temp; + + temp = 0x55; + via_rtc_command(RTC_CMD_WRITE(RTC_REG_WRITE_PROTECT), &temp); + + temp = data; + via_rtc_command(RTC_CMD_XPRAM_WRITE | RTC_CMD_XPRAM_ARG(offset), &temp); + + temp = 0x55 | RTC_FLG_WRITE_PROTECT; + via_rtc_command(RTC_CMD_WRITE(RTC_REG_WRITE_PROTECT), &temp); } /* diff --git a/include/uapi/linux/pmu.h b/include/uapi/linux/pmu.h index 97256f90e6df..f2fc1bd80017 100644 --- a/include/uapi/linux/pmu.h +++ b/include/uapi/linux/pmu.h @@ -19,7 +19,9 @@ #define PMU_POWER_CTRL 0x11 /* control power of some devices */ #define PMU_ADB_CMD 0x20 /* send ADB packet */ #define PMU_ADB_POLL_OFF 0x21 /* disable ADB auto-poll */ +#define PMU_WRITE_XPRAM 0x32 /* write eXtended Parameter RAM */ #define PMU_WRITE_NVRAM 0x33 /* write non-volatile RAM */ +#define PMU_READ_XPRAM 0x3a /* read eXtended Parameter RAM */ #define PMU_READ_NVRAM 0x3b /* read non-volatile RAM */ #define PMU_SET_RTC 0x30 /* set real-time clock */ #define PMU_READ_RTC 0x38 /* read real-time clock */ -- cgit v1.2.3 From 95ac14b8a32817dcd1f13ae4787891484966d2d5 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: powerpc: Implement nvram ioctls Add the powerpc-specific ioctls to the nvram module. This allows the nvram module to replace the generic_nvram module. Tested-by: Stan Johnson Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- drivers/char/nvram.c | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/nvram.h | 2 ++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c index c9e295d73dc5..944f05fddacd 100644 --- a/drivers/char/nvram.c +++ b/drivers/char/nvram.c @@ -48,6 +48,9 @@ #include #include +#ifdef CONFIG_PPC +#include +#endif static DEFINE_MUTEX(nvram_mutex); static DEFINE_SPINLOCK(nvram_state_lock); @@ -283,6 +286,38 @@ static long nvram_misc_ioctl(struct file *file, unsigned int cmd, long ret = -ENOTTY; switch (cmd) { +#ifdef CONFIG_PPC + case OBSOLETE_PMAC_NVRAM_GET_OFFSET: + pr_warn("nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n"); + /* fall through */ + case IOC_NVRAM_GET_OFFSET: + ret = -EINVAL; +#ifdef CONFIG_PPC_PMAC + if (machine_is(powermac)) { + int part, offset; + + if (copy_from_user(&part, (void __user *)arg, + sizeof(part)) != 0) + return -EFAULT; + if (part < pmac_nvram_OF || part > pmac_nvram_NR) + return -EINVAL; + offset = pmac_get_partition(part); + if (copy_to_user((void __user *)arg, + &offset, sizeof(offset)) != 0) + return -EFAULT; + ret = 0; + } +#endif + break; + case IOC_NVRAM_SYNC: + if (ppc_md.nvram_sync != NULL) { + mutex_lock(&nvram_mutex); + ppc_md.nvram_sync(); + mutex_unlock(&nvram_mutex); + } + ret = 0; + break; +#elif defined(CONFIG_X86) || defined(CONFIG_M68K) case NVRAM_INIT: /* initialize NVRAM contents and checksum */ if (!capable(CAP_SYS_ADMIN)) @@ -306,6 +341,7 @@ static long nvram_misc_ioctl(struct file *file, unsigned int cmd, mutex_unlock(&nvram_mutex); } break; +#endif /* CONFIG_X86 || CONFIG_M68K */ } return ret; } @@ -321,12 +357,14 @@ static int nvram_misc_open(struct inode *inode, struct file *file) return -EBUSY; } +#if defined(CONFIG_X86) || defined(CONFIG_M68K) /* Prevent multiple writers if the set_checksum ioctl is implemented. */ if ((arch_nvram_ops.set_checksum != NULL) && (file->f_mode & FMODE_WRITE) && (nvram_open_mode & NVRAM_WRITE)) { spin_unlock(&nvram_state_lock); return -EBUSY; } +#endif if (file->f_flags & O_EXCL) nvram_open_mode |= NVRAM_EXCL; diff --git a/include/linux/nvram.h b/include/linux/nvram.h index 9df85703735c..9e3a957c8f1f 100644 --- a/include/linux/nvram.h +++ b/include/linux/nvram.h @@ -31,8 +31,10 @@ struct nvram_ops { void (*write_byte)(unsigned char, int); ssize_t (*read)(char *, size_t, loff_t *); ssize_t (*write)(char *, size_t, loff_t *); +#if defined(CONFIG_X86) || defined(CONFIG_M68K) long (*initialize)(void); long (*set_checksum)(void); +#endif }; extern const struct nvram_ops arch_nvram_ops; -- cgit v1.2.3 From f9c3a570f5fc584f2ca2dd222d1b8c8537fc55f6 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 15 Jan 2019 15:18:56 +1100 Subject: powerpc: Enable HAVE_ARCH_NVRAM_OPS and disable GENERIC_NVRAM Switch PPC32 kernels from the generic_nvram module to the nvram module. Also fix a theoretical bug where CHRP omits the chrp_nvram_init() call when CONFIG_NVRAM_MODULE=m. Tested-by: Stan Johnson Signed-off-by: Finn Thain Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/Kconfig | 6 +----- arch/powerpc/include/asm/nvram.h | 3 --- arch/powerpc/kernel/setup_32.c | 11 ----------- arch/powerpc/platforms/chrp/Makefile | 2 +- arch/powerpc/platforms/chrp/setup.c | 2 +- arch/powerpc/platforms/powermac/setup.c | 3 +-- drivers/char/Kconfig | 19 +++++++++---------- include/linux/nvram.h | 20 ++++++++++++++++++++ 8 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2890d36eb531..f62e6a3f9c4e 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -178,6 +178,7 @@ config PPC select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT + select HAVE_ARCH_NVRAM_OPS if PPC32 select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_CBPF_JIT if !PPC64 @@ -274,11 +275,6 @@ config SYSVIPC_COMPAT depends on COMPAT && SYSVIPC default y -# All PPC32s use generic nvram driver through ppc_md -config GENERIC_NVRAM - bool - default y if PPC32 - config SCHED_OMIT_FRAME_POINTER bool default y diff --git a/arch/powerpc/include/asm/nvram.h b/arch/powerpc/include/asm/nvram.h index 56a388da9c4f..629a5cdcc865 100644 --- a/arch/powerpc/include/asm/nvram.h +++ b/arch/powerpc/include/asm/nvram.h @@ -78,9 +78,6 @@ extern int pmac_get_partition(int partition); extern u8 pmac_xpram_read(int xpaddr); extern void pmac_xpram_write(int xpaddr, u8 data); -/* Synchronize NVRAM */ -extern void nvram_sync(void); - /* Initialize NVRAM OS partition */ extern int __init nvram_init_os_partition(struct nvram_os_partition *part); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index f5107796e2d7..c31082233a25 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -148,17 +148,6 @@ static int __init ppc_setup_l3cr(char *str) } __setup("l3cr=", ppc_setup_l3cr); -#ifdef CONFIG_GENERIC_NVRAM - -void nvram_sync(void) -{ - if (ppc_md.nvram_sync) - ppc_md.nvram_sync(); -} -EXPORT_SYMBOL(nvram_sync); - -#endif /* CONFIG_NVRAM */ - static int __init ppc_init(void) { /* clear the progress line */ diff --git a/arch/powerpc/platforms/chrp/Makefile b/arch/powerpc/platforms/chrp/Makefile index 4b3bfadc70fa..dc3465cc8bc6 100644 --- a/arch/powerpc/platforms/chrp/Makefile +++ b/arch/powerpc/platforms/chrp/Makefile @@ -1,3 +1,3 @@ obj-y += setup.o time.o pegasos_eth.o pci.o obj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_NVRAM) += nvram.o +obj-$(CONFIG_NVRAM:m=y) += nvram.o diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index e66644e0fb40..e8e804289c8e 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -550,7 +550,7 @@ static void __init chrp_init_IRQ(void) static void __init chrp_init2(void) { -#ifdef CONFIG_NVRAM +#if IS_ENABLED(CONFIG_NVRAM) chrp_nvram_init(); #endif diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 2e8221e20ee8..b47f49cf9c4d 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -316,8 +316,7 @@ static void __init pmac_setup_arch(void) find_via_pmu(); smu_init(); -#if defined(CONFIG_NVRAM) || defined(CONFIG_NVRAM_MODULE) || \ - defined(CONFIG_PPC64) +#if IS_ENABLED(CONFIG_NVRAM) || defined(CONFIG_PPC64) pmac_nvram_init(); #endif #ifdef CONFIG_PPC32 diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index ce9979529cf3..72866a004f07 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -244,25 +244,24 @@ source "drivers/char/hw_random/Kconfig" config NVRAM tristate "/dev/nvram support" - depends on X86 || GENERIC_NVRAM || HAVE_ARCH_NVRAM_OPS - default M68K + depends on X86 || HAVE_ARCH_NVRAM_OPS + default M68K || PPC ---help--- If you say Y here and create a character special file /dev/nvram with major number 10 and minor number 144 using mknod ("man mknod"), - you get read and write access to the extra bytes of non-volatile - memory in the real time clock (RTC), which is contained in every PC - and most Ataris. The actual number of bytes varies, depending on the - nvram in the system, but is usually 114 (128-14 for the RTC). - - This memory is conventionally called "CMOS RAM" on PCs and "NVRAM" - on Ataris. /dev/nvram may be used to view settings there, or to - change them (with some utility). It could also be used to frequently + you get read and write access to the non-volatile memory. + + /dev/nvram may be used to view settings in NVRAM or to change them + (with some utility). It could also be used to frequently save a few bits of very important data that may not be lost over power-off and for which writing to disk is too insecure. Note however that most NVRAM space in a PC belongs to the BIOS and you should NEVER idly tamper with it. See Ralf Brown's interrupt list for a guide to the use of CMOS bytes by your BIOS. + This memory is conventionally called "NVRAM" on PowerPC machines, + "CMOS RAM" on PCs, "NVRAM" on Ataris and "PRAM" on Macintoshes. + To compile this driver as a module, choose M here: the module will be called nvram. diff --git a/include/linux/nvram.h b/include/linux/nvram.h index 9e3a957c8f1f..d29d9c93a927 100644 --- a/include/linux/nvram.h +++ b/include/linux/nvram.h @@ -5,6 +5,10 @@ #include #include +#ifdef CONFIG_PPC +#include +#endif + /** * struct nvram_ops - NVRAM functionality made available to drivers * @read: validate checksum (if any) then load a range of bytes from NVRAM @@ -42,6 +46,8 @@ extern const struct nvram_ops arch_nvram_ops; static inline ssize_t nvram_get_size(void) { #ifdef CONFIG_PPC + if (ppc_md.nvram_size) + return ppc_md.nvram_size(); #else if (arch_nvram_ops.get_size) return arch_nvram_ops.get_size(); @@ -52,6 +58,8 @@ static inline ssize_t nvram_get_size(void) static inline unsigned char nvram_read_byte(int addr) { #ifdef CONFIG_PPC + if (ppc_md.nvram_read_val) + return ppc_md.nvram_read_val(addr); #else if (arch_nvram_ops.read_byte) return arch_nvram_ops.read_byte(addr); @@ -62,6 +70,8 @@ static inline unsigned char nvram_read_byte(int addr) static inline void nvram_write_byte(unsigned char val, int addr) { #ifdef CONFIG_PPC + if (ppc_md.nvram_write_val) + ppc_md.nvram_write_val(addr, val); #else if (arch_nvram_ops.write_byte) arch_nvram_ops.write_byte(val, addr); @@ -98,15 +108,25 @@ static inline ssize_t nvram_write_bytes(char *buf, size_t count, loff_t *ppos) static inline ssize_t nvram_read(char *buf, size_t count, loff_t *ppos) { +#ifdef CONFIG_PPC + if (ppc_md.nvram_read) + return ppc_md.nvram_read(buf, count, ppos); +#else if (arch_nvram_ops.read) return arch_nvram_ops.read(buf, count, ppos); +#endif return nvram_read_bytes(buf, count, ppos); } static inline ssize_t nvram_write(char *buf, size_t count, loff_t *ppos) { +#ifdef CONFIG_PPC + if (ppc_md.nvram_write) + return ppc_md.nvram_write(buf, count, ppos); +#else if (arch_nvram_ops.write) return arch_nvram_ops.write(buf, count, ppos); +#endif return nvram_write_bytes(buf, count, ppos); } -- cgit v1.2.3 From 8092e79204e7884f4bee3584ecfe6cf4a124d129 Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Thu, 20 Dec 2018 23:28:37 -0800 Subject: ihex: Share code between ihex_validate_fw() and ihex_next_binrec() Convert both ihex_validate_fw() and ihex_next_binrec() to use a helper function to calculate next record offest. This way we only have one place implementing next record offset calculation logic. No functional change intended. Cc: Chris Healy Cc: Kyle McMartin Cc: Andrew Morton Cc: Masahiro Yamada Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: linux-kernel Signed-off-by: Andrey Smirnov Signed-off-by: Greg Kroah-Hartman --- include/linux/ihex.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/ihex.h b/include/linux/ihex.h index 75c194391869..9c701521176b 100644 --- a/include/linux/ihex.h +++ b/include/linux/ihex.h @@ -23,29 +23,34 @@ struct ihex_binrec { /* Find the next record, taking into account the 4-byte alignment */ static inline const struct ihex_binrec * -ihex_next_binrec(const struct ihex_binrec *rec) +__ihex_next_binrec(const struct ihex_binrec *rec) { int next = ((be16_to_cpu(rec->len) + 5) & ~3) - 2; rec = (void *)&rec->data[next]; + return rec; +} + +static inline const struct ihex_binrec * +ihex_next_binrec(const struct ihex_binrec *rec) +{ + rec = __ihex_next_binrec(rec); + return be16_to_cpu(rec->len) ? rec : NULL; } /* Check that ihex_next_binrec() won't take us off the end of the image... */ static inline int ihex_validate_fw(const struct firmware *fw) { - const struct ihex_binrec *rec; - size_t ofs = 0; + const struct ihex_binrec *end, *rec; - while (ofs <= fw->size - sizeof(*rec)) { - rec = (void *)&fw->data[ofs]; + rec = (const void *)fw->data; + end = (const void *)&fw->data[fw->size - sizeof(*end)]; + for (; rec <= end; rec = __ihex_next_binrec(rec)) { /* Zero length marks end of records */ if (!be16_to_cpu(rec->len)) return 0; - - /* Point to next record... */ - ofs += (sizeof(*rec) + be16_to_cpu(rec->len) + 3) & ~3; } return -EINVAL; } -- cgit v1.2.3 From 5158c36ec9d0b3343f58987cec7ebfd866331fd0 Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Thu, 20 Dec 2018 23:28:38 -0800 Subject: ihex: Check if zero-length record is at the end of the blob When verifying the validity of IHEX file we need to make sure that zero-length record we found is located at the end of the file. Not doing that could result in an invalid file with a bogus zero-length in the middle short-circuiting the check and being reported as valid. Cc: Chris Healy Cc: Kyle McMartin Cc: Andrew Morton Cc: Masahiro Yamada Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: linux-kernel Signed-off-by: Andrey Smirnov Signed-off-by: Greg Kroah-Hartman --- include/linux/ihex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ihex.h b/include/linux/ihex.h index 9c701521176b..9130f307a420 100644 --- a/include/linux/ihex.h +++ b/include/linux/ihex.h @@ -49,7 +49,7 @@ static inline int ihex_validate_fw(const struct firmware *fw) for (; rec <= end; rec = __ihex_next_binrec(rec)) { /* Zero length marks end of records */ - if (!be16_to_cpu(rec->len)) + if (rec == end && !be16_to_cpu(rec->len)) return 0; } return -EINVAL; -- cgit v1.2.3 From 9fb4ab4d3dd665a62da9c176a89e7c7feaf5d9e4 Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Thu, 20 Dec 2018 23:28:39 -0800 Subject: ihex: Simplify next record offset calculation Next record calucaltion can be reduced to a much more tivial ALIGN operation as follows: 1. Splitting 5 into 2 + 3 we get next = ((be16_to_cpu(rec->len) + 2 + 3) & ~3) - 2 (1) 2. Using ALIGN macro we reduce (1) to: ALIGN(be16_to_cpu(rec->len) + 2, 4) - 2 (2) 3. Subsituting 'next' in original next record calucation we get: (void *)&rec->data[ALIGN(be16_to_cpu(rec->len) + 2, 4) - 2] (3) 4. Converting array index to pointer arithmetic we convert (3) into: (void *)rec + sizeof(*rec) + ALIGN(be16_to_cpu(rec->len) + 2, 4) - 2 (4) 5. Subsituting sizeof(*rec) with its value, 6, and substracting 2, in (4) we get: (void *)rec + ALIGN(be16_to_cpu(rec->len) + 2, 4) + 4 (5) 6. Since ALIGN(X, 4) + 4 == ALIGN(X + 4, 4), (5) can be converted to: (void *)rec + ALIGN(be16_to_cpu(rec->len) + 6, 4) (6) 5. Subsituting 6 in (6) to sizeof(*rec) we get: (void *)rec + ALIGN(be16_to_cpu(rec->len) + sizeof(*rec), 4) (7) Using expression (7) should make it more clear that next record is located by adding full size of the current record (payload + auxiliary data) aligned to 4 bytes, to the location of the current one. No functional change intended. Cc: Chris Healy Cc: Kyle McMartin Cc: Andrew Morton Cc: Masahiro Yamada Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: linux-kernel Signed-off-by: Andrey Smirnov Signed-off-by: Greg Kroah-Hartman --- include/linux/ihex.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ihex.h b/include/linux/ihex.h index 9130f307a420..98cb5ce0b0a0 100644 --- a/include/linux/ihex.h +++ b/include/linux/ihex.h @@ -21,14 +21,18 @@ struct ihex_binrec { uint8_t data[0]; } __attribute__((packed)); +static inline uint16_t ihex_binrec_size(const struct ihex_binrec *p) +{ + return be16_to_cpu(p->len) + sizeof(*p); +} + /* Find the next record, taking into account the 4-byte alignment */ static inline const struct ihex_binrec * __ihex_next_binrec(const struct ihex_binrec *rec) { - int next = ((be16_to_cpu(rec->len) + 5) & ~3) - 2; - rec = (void *)&rec->data[next]; + const void *p = rec; - return rec; + return p + ALIGN(ihex_binrec_size(rec), 4); } static inline const struct ihex_binrec * -- cgit v1.2.3 From 11f1ceca7031deefc1a34236ab7b94360016b71d Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Wed, 16 Jan 2019 18:10:56 +0200 Subject: interconnect: Add generic on-chip interconnect API This patch introduces a new API to get requirements and configure the interconnect buses across the entire chipset to fit with the current demand. The API is using a consumer/provider-based model, where the providers are the interconnect buses and the consumers could be various drivers. The consumers request interconnect resources (path) between endpoints and set the desired constraints on this data flow path. The providers receive requests from consumers and aggregate these requests for all master-slave pairs on that path. Then the providers configure each node along the path to support a bandwidth that satisfies all bandwidth requests that cross through that node. The topology could be complicated and multi-tiered and is SoC specific. Reviewed-by: Evan Green Signed-off-by: Georgi Djakov Signed-off-by: Greg Kroah-Hartman --- Documentation/interconnect/interconnect.rst | 94 +++++ drivers/Kconfig | 2 + drivers/Makefile | 1 + drivers/interconnect/Kconfig | 10 + drivers/interconnect/Makefile | 5 + drivers/interconnect/core.c | 567 ++++++++++++++++++++++++++++ include/linux/interconnect-provider.h | 125 ++++++ include/linux/interconnect.h | 52 +++ 8 files changed, 856 insertions(+) create mode 100644 Documentation/interconnect/interconnect.rst create mode 100644 drivers/interconnect/Kconfig create mode 100644 drivers/interconnect/Makefile create mode 100644 drivers/interconnect/core.c create mode 100644 include/linux/interconnect-provider.h create mode 100644 include/linux/interconnect.h (limited to 'include') diff --git a/Documentation/interconnect/interconnect.rst b/Documentation/interconnect/interconnect.rst new file mode 100644 index 000000000000..b8107dcc4cd3 --- /dev/null +++ b/Documentation/interconnect/interconnect.rst @@ -0,0 +1,94 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================================== +GENERIC SYSTEM INTERCONNECT SUBSYSTEM +===================================== + +Introduction +------------ + +This framework is designed to provide a standard kernel interface to control +the settings of the interconnects on an SoC. These settings can be throughput, +latency and priority between multiple interconnected devices or functional +blocks. This can be controlled dynamically in order to save power or provide +maximum performance. + +The interconnect bus is hardware with configurable parameters, which can be +set on a data path according to the requests received from various drivers. +An example of interconnect buses are the interconnects between various +components or functional blocks in chipsets. There can be multiple interconnects +on an SoC that can be multi-tiered. + +Below is a simplified diagram of a real-world SoC interconnect bus topology. + +:: + + +----------------+ +----------------+ + | HW Accelerator |--->| M NoC |<---------------+ + +----------------+ +----------------+ | + | | +------------+ + +-----+ +-------------+ V +------+ | | + | DDR | | +--------+ | PCIe | | | + +-----+ | | Slaves | +------+ | | + ^ ^ | +--------+ | | C NoC | + | | V V | | + +------------------+ +------------------------+ | | +-----+ + | |-->| |-->| |-->| CPU | + | |-->| |<--| | +-----+ + | Mem NoC | | S NoC | +------------+ + | |<--| |---------+ | + | |<--| |<------+ | | +--------+ + +------------------+ +------------------------+ | | +-->| Slaves | + ^ ^ ^ ^ ^ | | +--------+ + | | | | | | V + +------+ | +-----+ +-----+ +---------+ +----------------+ +--------+ + | CPUs | | | GPU | | DSP | | Masters |-->| P NoC |-->| Slaves | + +------+ | +-----+ +-----+ +---------+ +----------------+ +--------+ + | + +-------+ + | Modem | + +-------+ + +Terminology +----------- + +Interconnect provider is the software definition of the interconnect hardware. +The interconnect providers on the above diagram are M NoC, S NoC, C NoC, P NoC +and Mem NoC. + +Interconnect node is the software definition of the interconnect hardware +port. Each interconnect provider consists of multiple interconnect nodes, +which are connected to other SoC components including other interconnect +providers. The point on the diagram where the CPUs connect to the memory is +called an interconnect node, which belongs to the Mem NoC interconnect provider. + +Interconnect endpoints are the first or the last element of the path. Every +endpoint is a node, but not every node is an endpoint. + +Interconnect path is everything between two endpoints including all the nodes +that have to be traversed to reach from a source to destination node. It may +include multiple master-slave pairs across several interconnect providers. + +Interconnect consumers are the entities which make use of the data paths exposed +by the providers. The consumers send requests to providers requesting various +throughput, latency and priority. Usually the consumers are device drivers, that +send request based on their needs. An example for a consumer is a video decoder +that supports various formats and image sizes. + +Interconnect providers +---------------------- + +Interconnect provider is an entity that implements methods to initialize and +configure interconnect bus hardware. The interconnect provider drivers should +be registered with the interconnect provider core. + +.. kernel-doc:: include/linux/interconnect-provider.h + +Interconnect consumers +---------------------- + +Interconnect consumers are the clients which use the interconnect APIs to +get paths between endpoints and set their bandwidth/latency/QoS requirements +for these interconnect paths. + +.. kernel-doc:: include/linux/interconnect.h diff --git a/drivers/Kconfig b/drivers/Kconfig index 4f9f99057ff8..45f9decb9848 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -228,4 +228,6 @@ source "drivers/siox/Kconfig" source "drivers/slimbus/Kconfig" +source "drivers/interconnect/Kconfig" + endmenu diff --git a/drivers/Makefile b/drivers/Makefile index e1ce029d28fd..bb15b9d0e793 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -186,3 +186,4 @@ obj-$(CONFIG_MULTIPLEXER) += mux/ obj-$(CONFIG_UNISYS_VISORBUS) += visorbus/ obj-$(CONFIG_SIOX) += siox/ obj-$(CONFIG_GNSS) += gnss/ +obj-$(CONFIG_INTERCONNECT) += interconnect/ diff --git a/drivers/interconnect/Kconfig b/drivers/interconnect/Kconfig new file mode 100644 index 000000000000..a261c7d41deb --- /dev/null +++ b/drivers/interconnect/Kconfig @@ -0,0 +1,10 @@ +menuconfig INTERCONNECT + tristate "On-Chip Interconnect management support" + help + Support for management of the on-chip interconnects. + + This framework is designed to provide a generic interface for + managing the interconnects in a SoC. + + If unsure, say no. + diff --git a/drivers/interconnect/Makefile b/drivers/interconnect/Makefile new file mode 100644 index 000000000000..7a01f33b5593 --- /dev/null +++ b/drivers/interconnect/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +icc-core-objs := core.o + +obj-$(CONFIG_INTERCONNECT) += icc-core.o diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c new file mode 100644 index 000000000000..2b937b4f43c4 --- /dev/null +++ b/drivers/interconnect/core.c @@ -0,0 +1,567 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Interconnect framework core driver + * + * Copyright (c) 2017-2019, Linaro Ltd. + * Author: Georgi Djakov + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_IDR(icc_idr); +static LIST_HEAD(icc_providers); +static DEFINE_MUTEX(icc_lock); + +/** + * struct icc_req - constraints that are attached to each node + * @req_node: entry in list of requests for the particular @node + * @node: the interconnect node to which this constraint applies + * @dev: reference to the device that sets the constraints + * @avg_bw: an integer describing the average bandwidth in kBps + * @peak_bw: an integer describing the peak bandwidth in kBps + */ +struct icc_req { + struct hlist_node req_node; + struct icc_node *node; + struct device *dev; + u32 avg_bw; + u32 peak_bw; +}; + +/** + * struct icc_path - interconnect path structure + * @num_nodes: number of hops (nodes) + * @reqs: array of the requests applicable to this path of nodes + */ +struct icc_path { + size_t num_nodes; + struct icc_req reqs[]; +}; + +static struct icc_node *node_find(const int id) +{ + return idr_find(&icc_idr, id); +} + +static struct icc_path *path_init(struct device *dev, struct icc_node *dst, + ssize_t num_nodes) +{ + struct icc_node *node = dst; + struct icc_path *path; + int i; + + path = kzalloc(struct_size(path, reqs, num_nodes), GFP_KERNEL); + if (!path) + return ERR_PTR(-ENOMEM); + + path->num_nodes = num_nodes; + + for (i = num_nodes - 1; i >= 0; i--) { + node->provider->users++; + hlist_add_head(&path->reqs[i].req_node, &node->req_list); + path->reqs[i].node = node; + path->reqs[i].dev = dev; + /* reference to previous node was saved during path traversal */ + node = node->reverse; + } + + return path; +} + +static struct icc_path *path_find(struct device *dev, struct icc_node *src, + struct icc_node *dst) +{ + struct icc_path *path = ERR_PTR(-EPROBE_DEFER); + struct icc_node *n, *node = NULL; + struct list_head traverse_list; + struct list_head edge_list; + struct list_head visited_list; + size_t i, depth = 1; + bool found = false; + + INIT_LIST_HEAD(&traverse_list); + INIT_LIST_HEAD(&edge_list); + INIT_LIST_HEAD(&visited_list); + + list_add(&src->search_list, &traverse_list); + src->reverse = NULL; + + do { + list_for_each_entry_safe(node, n, &traverse_list, search_list) { + if (node == dst) { + found = true; + list_splice_init(&edge_list, &visited_list); + list_splice_init(&traverse_list, &visited_list); + break; + } + for (i = 0; i < node->num_links; i++) { + struct icc_node *tmp = node->links[i]; + + if (!tmp) { + path = ERR_PTR(-ENOENT); + goto out; + } + + if (tmp->is_traversed) + continue; + + tmp->is_traversed = true; + tmp->reverse = node; + list_add_tail(&tmp->search_list, &edge_list); + } + } + + if (found) + break; + + list_splice_init(&traverse_list, &visited_list); + list_splice_init(&edge_list, &traverse_list); + + /* count the hops including the source */ + depth++; + + } while (!list_empty(&traverse_list)); + +out: + + /* reset the traversed state */ + list_for_each_entry_reverse(n, &visited_list, search_list) + n->is_traversed = false; + + if (found) + path = path_init(dev, dst, depth); + + return path; +} + +/* + * We want the path to honor all bandwidth requests, so the average and peak + * bandwidth requirements from each consumer are aggregated at each node. + * The aggregation is platform specific, so each platform can customize it by + * implementing its own aggregate() function. + */ + +static int aggregate_requests(struct icc_node *node) +{ + struct icc_provider *p = node->provider; + struct icc_req *r; + + node->avg_bw = 0; + node->peak_bw = 0; + + hlist_for_each_entry(r, &node->req_list, req_node) + p->aggregate(node, r->avg_bw, r->peak_bw, + &node->avg_bw, &node->peak_bw); + + return 0; +} + +static int apply_constraints(struct icc_path *path) +{ + struct icc_node *next, *prev = NULL; + int ret = -EINVAL; + int i; + + for (i = 0; i < path->num_nodes; i++) { + next = path->reqs[i].node; + + /* + * Both endpoints should be valid master-slave pairs of the + * same interconnect provider that will be configured. + */ + if (!prev || next->provider != prev->provider) { + prev = next; + continue; + } + + /* set the constraints */ + ret = next->provider->set(prev, next); + if (ret) + goto out; + + prev = next; + } +out: + return ret; +} + +/** + * icc_set_bw() - set bandwidth constraints on an interconnect path + * @path: reference to the path returned by icc_get() + * @avg_bw: average bandwidth in kilobytes per second + * @peak_bw: peak bandwidth in kilobytes per second + * + * This function is used by an interconnect consumer to express its own needs + * in terms of bandwidth for a previously requested path between two endpoints. + * The requests are aggregated and each node is updated accordingly. The entire + * path is locked by a mutex to ensure that the set() is completed. + * The @path can be NULL when the "interconnects" DT properties is missing, + * which will mean that no constraints will be set. + * + * Returns 0 on success, or an appropriate error code otherwise. + */ +int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) +{ + struct icc_node *node; + size_t i; + int ret; + + if (!path) + return 0; + + mutex_lock(&icc_lock); + + for (i = 0; i < path->num_nodes; i++) { + node = path->reqs[i].node; + + /* update the consumer request for this path */ + path->reqs[i].avg_bw = avg_bw; + path->reqs[i].peak_bw = peak_bw; + + /* aggregate requests for this node */ + aggregate_requests(node); + } + + ret = apply_constraints(path); + if (ret) + pr_debug("interconnect: error applying constraints (%d)\n", + ret); + + mutex_unlock(&icc_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(icc_set_bw); + +/** + * icc_get() - return a handle for path between two endpoints + * @dev: the device requesting the path + * @src_id: source device port id + * @dst_id: destination device port id + * + * This function will search for a path between two endpoints and return an + * icc_path handle on success. Use icc_put() to release + * constraints when they are not needed anymore. + * If the interconnect API is disabled, NULL is returned and the consumer + * drivers will still build. Drivers are free to handle this specifically, + * but they don't have to. + * + * Return: icc_path pointer on success, ERR_PTR() on error or NULL if the + * interconnect API is disabled. + */ +struct icc_path *icc_get(struct device *dev, const int src_id, const int dst_id) +{ + struct icc_node *src, *dst; + struct icc_path *path = ERR_PTR(-EPROBE_DEFER); + + mutex_lock(&icc_lock); + + src = node_find(src_id); + if (!src) + goto out; + + dst = node_find(dst_id); + if (!dst) + goto out; + + path = path_find(dev, src, dst); + if (IS_ERR(path)) + dev_err(dev, "%s: invalid path=%ld\n", __func__, PTR_ERR(path)); + +out: + mutex_unlock(&icc_lock); + return path; +} +EXPORT_SYMBOL_GPL(icc_get); + +/** + * icc_put() - release the reference to the icc_path + * @path: interconnect path + * + * Use this function to release the constraints on a path when the path is + * no longer needed. The constraints will be re-aggregated. + */ +void icc_put(struct icc_path *path) +{ + struct icc_node *node; + size_t i; + int ret; + + if (!path || WARN_ON(IS_ERR(path))) + return; + + ret = icc_set_bw(path, 0, 0); + if (ret) + pr_err("%s: error (%d)\n", __func__, ret); + + mutex_lock(&icc_lock); + for (i = 0; i < path->num_nodes; i++) { + node = path->reqs[i].node; + hlist_del(&path->reqs[i].req_node); + if (!WARN_ON(!node->provider->users)) + node->provider->users--; + } + mutex_unlock(&icc_lock); + + kfree(path); +} +EXPORT_SYMBOL_GPL(icc_put); + +static struct icc_node *icc_node_create_nolock(int id) +{ + struct icc_node *node; + + /* check if node already exists */ + node = node_find(id); + if (node) + return node; + + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return ERR_PTR(-ENOMEM); + + id = idr_alloc(&icc_idr, node, id, id + 1, GFP_KERNEL); + if (id < 0) { + WARN(1, "%s: couldn't get idr\n", __func__); + kfree(node); + return ERR_PTR(id); + } + + node->id = id; + + return node; +} + +/** + * icc_node_create() - create a node + * @id: node id + * + * Return: icc_node pointer on success, or ERR_PTR() on error + */ +struct icc_node *icc_node_create(int id) +{ + struct icc_node *node; + + mutex_lock(&icc_lock); + + node = icc_node_create_nolock(id); + + mutex_unlock(&icc_lock); + + return node; +} +EXPORT_SYMBOL_GPL(icc_node_create); + +/** + * icc_node_destroy() - destroy a node + * @id: node id + */ +void icc_node_destroy(int id) +{ + struct icc_node *node; + + mutex_lock(&icc_lock); + + node = node_find(id); + if (node) { + idr_remove(&icc_idr, node->id); + WARN_ON(!hlist_empty(&node->req_list)); + } + + mutex_unlock(&icc_lock); + + kfree(node); +} +EXPORT_SYMBOL_GPL(icc_node_destroy); + +/** + * icc_link_create() - create a link between two nodes + * @node: source node id + * @dst_id: destination node id + * + * Create a link between two nodes. The nodes might belong to different + * interconnect providers and the @dst_id node might not exist (if the + * provider driver has not probed yet). So just create the @dst_id node + * and when the actual provider driver is probed, the rest of the node + * data is filled. + * + * Return: 0 on success, or an error code otherwise + */ +int icc_link_create(struct icc_node *node, const int dst_id) +{ + struct icc_node *dst; + struct icc_node **new; + int ret = 0; + + if (!node->provider) + return -EINVAL; + + mutex_lock(&icc_lock); + + dst = node_find(dst_id); + if (!dst) { + dst = icc_node_create_nolock(dst_id); + + if (IS_ERR(dst)) { + ret = PTR_ERR(dst); + goto out; + } + } + + new = krealloc(node->links, + (node->num_links + 1) * sizeof(*node->links), + GFP_KERNEL); + if (!new) { + ret = -ENOMEM; + goto out; + } + + node->links = new; + node->links[node->num_links++] = dst; + +out: + mutex_unlock(&icc_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(icc_link_create); + +/** + * icc_link_destroy() - destroy a link between two nodes + * @src: pointer to source node + * @dst: pointer to destination node + * + * Return: 0 on success, or an error code otherwise + */ +int icc_link_destroy(struct icc_node *src, struct icc_node *dst) +{ + struct icc_node **new; + size_t slot; + int ret = 0; + + if (IS_ERR_OR_NULL(src)) + return -EINVAL; + + if (IS_ERR_OR_NULL(dst)) + return -EINVAL; + + mutex_lock(&icc_lock); + + for (slot = 0; slot < src->num_links; slot++) + if (src->links[slot] == dst) + break; + + if (WARN_ON(slot == src->num_links)) { + ret = -ENXIO; + goto out; + } + + src->links[slot] = src->links[--src->num_links]; + + new = krealloc(src->links, src->num_links * sizeof(*src->links), + GFP_KERNEL); + if (new) + src->links = new; + +out: + mutex_unlock(&icc_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(icc_link_destroy); + +/** + * icc_node_add() - add interconnect node to interconnect provider + * @node: pointer to the interconnect node + * @provider: pointer to the interconnect provider + */ +void icc_node_add(struct icc_node *node, struct icc_provider *provider) +{ + mutex_lock(&icc_lock); + + node->provider = provider; + list_add_tail(&node->node_list, &provider->nodes); + + mutex_unlock(&icc_lock); +} +EXPORT_SYMBOL_GPL(icc_node_add); + +/** + * icc_node_del() - delete interconnect node from interconnect provider + * @node: pointer to the interconnect node + */ +void icc_node_del(struct icc_node *node) +{ + mutex_lock(&icc_lock); + + list_del(&node->node_list); + + mutex_unlock(&icc_lock); +} +EXPORT_SYMBOL_GPL(icc_node_del); + +/** + * icc_provider_add() - add a new interconnect provider + * @provider: the interconnect provider that will be added into topology + * + * Return: 0 on success, or an error code otherwise + */ +int icc_provider_add(struct icc_provider *provider) +{ + if (WARN_ON(!provider->set)) + return -EINVAL; + + mutex_lock(&icc_lock); + + INIT_LIST_HEAD(&provider->nodes); + list_add_tail(&provider->provider_list, &icc_providers); + + mutex_unlock(&icc_lock); + + dev_dbg(provider->dev, "interconnect provider added to topology\n"); + + return 0; +} +EXPORT_SYMBOL_GPL(icc_provider_add); + +/** + * icc_provider_del() - delete previously added interconnect provider + * @provider: the interconnect provider that will be removed from topology + * + * Return: 0 on success, or an error code otherwise + */ +int icc_provider_del(struct icc_provider *provider) +{ + mutex_lock(&icc_lock); + if (provider->users) { + pr_warn("interconnect provider still has %d users\n", + provider->users); + mutex_unlock(&icc_lock); + return -EBUSY; + } + + if (!list_empty(&provider->nodes)) { + pr_warn("interconnect provider still has nodes\n"); + mutex_unlock(&icc_lock); + return -EBUSY; + } + + list_del(&provider->provider_list); + mutex_unlock(&icc_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(icc_provider_del); + +MODULE_AUTHOR("Georgi Djakov "); +MODULE_DESCRIPTION("Interconnect Driver Core"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h new file mode 100644 index 000000000000..78208a754181 --- /dev/null +++ b/include/linux/interconnect-provider.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018, Linaro Ltd. + * Author: Georgi Djakov + */ + +#ifndef __LINUX_INTERCONNECT_PROVIDER_H +#define __LINUX_INTERCONNECT_PROVIDER_H + +#include + +#define icc_units_to_bps(bw) ((bw) * 1000ULL) + +struct icc_node; + +/** + * struct icc_provider - interconnect provider (controller) entity that might + * provide multiple interconnect controls + * + * @provider_list: list of the registered interconnect providers + * @nodes: internal list of the interconnect provider nodes + * @set: pointer to device specific set operation function + * @aggregate: pointer to device specific aggregate operation function + * @dev: the device this interconnect provider belongs to + * @users: count of active users + * @data: pointer to private data + */ +struct icc_provider { + struct list_head provider_list; + struct list_head nodes; + int (*set)(struct icc_node *src, struct icc_node *dst); + int (*aggregate)(struct icc_node *node, u32 avg_bw, u32 peak_bw, + u32 *agg_avg, u32 *agg_peak); + struct device *dev; + int users; + void *data; +}; + +/** + * struct icc_node - entity that is part of the interconnect topology + * + * @id: platform specific node id + * @name: node name used in debugfs + * @links: a list of targets pointing to where we can go next when traversing + * @num_links: number of links to other interconnect nodes + * @provider: points to the interconnect provider of this node + * @node_list: the list entry in the parent provider's "nodes" list + * @search_list: list used when walking the nodes graph + * @reverse: pointer to previous node when walking the nodes graph + * @is_traversed: flag that is used when walking the nodes graph + * @req_list: a list of QoS constraint requests associated with this node + * @avg_bw: aggregated value of average bandwidth requests from all consumers + * @peak_bw: aggregated value of peak bandwidth requests from all consumers + * @data: pointer to private data + */ +struct icc_node { + int id; + const char *name; + struct icc_node **links; + size_t num_links; + + struct icc_provider *provider; + struct list_head node_list; + struct list_head search_list; + struct icc_node *reverse; + u8 is_traversed:1; + struct hlist_head req_list; + u32 avg_bw; + u32 peak_bw; + void *data; +}; + +#if IS_ENABLED(CONFIG_INTERCONNECT) + +struct icc_node *icc_node_create(int id); +void icc_node_destroy(int id); +int icc_link_create(struct icc_node *node, const int dst_id); +int icc_link_destroy(struct icc_node *src, struct icc_node *dst); +void icc_node_add(struct icc_node *node, struct icc_provider *provider); +void icc_node_del(struct icc_node *node); +int icc_provider_add(struct icc_provider *provider); +int icc_provider_del(struct icc_provider *provider); + +#else + +static inline struct icc_node *icc_node_create(int id) +{ + return ERR_PTR(-ENOTSUPP); +} + +void icc_node_destroy(int id) +{ +} + +static inline int icc_link_create(struct icc_node *node, const int dst_id) +{ + return -ENOTSUPP; +} + +int icc_link_destroy(struct icc_node *src, struct icc_node *dst) +{ + return -ENOTSUPP; +} + +void icc_node_add(struct icc_node *node, struct icc_provider *provider) +{ +} + +void icc_node_del(struct icc_node *node) +{ +} + +static inline int icc_provider_add(struct icc_provider *provider) +{ + return -ENOTSUPP; +} + +static inline int icc_provider_del(struct icc_provider *provider) +{ + return -ENOTSUPP; +} + +#endif /* CONFIG_INTERCONNECT */ + +#endif /* __LINUX_INTERCONNECT_PROVIDER_H */ diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h new file mode 100644 index 000000000000..c331afb3a2c8 --- /dev/null +++ b/include/linux/interconnect.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018-2019, Linaro Ltd. + * Author: Georgi Djakov + */ + +#ifndef __LINUX_INTERCONNECT_H +#define __LINUX_INTERCONNECT_H + +#include +#include + +/* macros for converting to icc units */ +#define Bps_to_icc(x) ((x) / 1000) +#define kBps_to_icc(x) (x) +#define MBps_to_icc(x) ((x) * 1000) +#define GBps_to_icc(x) ((x) * 1000 * 1000) +#define bps_to_icc(x) (1) +#define kbps_to_icc(x) ((x) / 8 + ((x) % 8 ? 1 : 0)) +#define Mbps_to_icc(x) ((x) * 1000 / 8) +#define Gbps_to_icc(x) ((x) * 1000 * 1000 / 8) + +struct icc_path; +struct device; + +#if IS_ENABLED(CONFIG_INTERCONNECT) + +struct icc_path *icc_get(struct device *dev, const int src_id, + const int dst_id); +void icc_put(struct icc_path *path); +int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); + +#else + +static inline struct icc_path *icc_get(struct device *dev, const int src_id, + const int dst_id) +{ + return NULL; +} + +static inline void icc_put(struct icc_path *path) +{ +} + +static inline int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) +{ + return 0; +} + +#endif /* CONFIG_INTERCONNECT */ + +#endif /* __LINUX_INTERCONNECT_H */ -- cgit v1.2.3 From 87e3031b6fbd83ea83adf1bf9602bcce313ee787 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Wed, 16 Jan 2019 18:10:58 +0200 Subject: interconnect: Allow endpoints translation via DT Currently we support only platform data for specifying the interconnect endpoints. As now the endpoints are hard-coded into the consumer driver this may lead to complications when a single driver is used by multiple SoCs, which may have different interconnect topology. To avoid cluttering the consumer drivers, introduce a translation function to help us get the board specific interconnect data from device-tree. Reviewed-by: Evan Green Signed-off-by: Georgi Djakov Signed-off-by: Greg Kroah-Hartman --- drivers/interconnect/core.c | 149 ++++++++++++++++++++++++++++++++++ include/linux/interconnect-provider.h | 17 ++++ include/linux/interconnect.h | 7 ++ 3 files changed, 173 insertions(+) (limited to 'include') diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 2b937b4f43c4..a8c2bd35197f 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -15,6 +15,7 @@ #include #include #include +#include #include static DEFINE_IDR(icc_idr); @@ -194,6 +195,152 @@ out: return ret; } +/* of_icc_xlate_onecell() - Translate function using a single index. + * @spec: OF phandle args to map into an interconnect node. + * @data: private data (pointer to struct icc_onecell_data) + * + * This is a generic translate function that can be used to model simple + * interconnect providers that have one device tree node and provide + * multiple interconnect nodes. A single cell is used as an index into + * an array of icc nodes specified in the icc_onecell_data struct when + * registering the provider. + */ +struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec, + void *data) +{ + struct icc_onecell_data *icc_data = data; + unsigned int idx = spec->args[0]; + + if (idx >= icc_data->num_nodes) { + pr_err("%s: invalid index %u\n", __func__, idx); + return ERR_PTR(-EINVAL); + } + + return icc_data->nodes[idx]; +} +EXPORT_SYMBOL_GPL(of_icc_xlate_onecell); + +/** + * of_icc_get_from_provider() - Look-up interconnect node + * @spec: OF phandle args to use for look-up + * + * Looks for interconnect provider under the node specified by @spec and if + * found, uses xlate function of the provider to map phandle args to node. + * + * Returns a valid pointer to struct icc_node on success or ERR_PTR() + * on failure. + */ +static struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec) +{ + struct icc_node *node = ERR_PTR(-EPROBE_DEFER); + struct icc_provider *provider; + + if (!spec || spec->args_count != 1) + return ERR_PTR(-EINVAL); + + mutex_lock(&icc_lock); + list_for_each_entry(provider, &icc_providers, provider_list) { + if (provider->dev->of_node == spec->np) + node = provider->xlate(spec, provider->data); + if (!IS_ERR(node)) + break; + } + mutex_unlock(&icc_lock); + + return node; +} + +/** + * of_icc_get() - get a path handle from a DT node based on name + * @dev: device pointer for the consumer device + * @name: interconnect path name + * + * This function will search for a path between two endpoints and return an + * icc_path handle on success. Use icc_put() to release constraints when they + * are not needed anymore. + * If the interconnect API is disabled, NULL is returned and the consumer + * drivers will still build. Drivers are free to handle this specifically, + * but they don't have to. + * + * Return: icc_path pointer on success or ERR_PTR() on error. NULL is returned + * when the API is disabled or the "interconnects" DT property is missing. + */ +struct icc_path *of_icc_get(struct device *dev, const char *name) +{ + struct icc_path *path = ERR_PTR(-EPROBE_DEFER); + struct icc_node *src_node, *dst_node; + struct device_node *np = NULL; + struct of_phandle_args src_args, dst_args; + int idx = 0; + int ret; + + if (!dev || !dev->of_node) + return ERR_PTR(-ENODEV); + + np = dev->of_node; + + /* + * When the consumer DT node do not have "interconnects" property + * return a NULL path to skip setting constraints. + */ + if (!of_find_property(np, "interconnects", NULL)) + return NULL; + + /* + * We use a combination of phandle and specifier for endpoint. For now + * lets support only global ids and extend this in the future if needed + * without breaking DT compatibility. + */ + if (name) { + idx = of_property_match_string(np, "interconnect-names", name); + if (idx < 0) + return ERR_PTR(idx); + } + + ret = of_parse_phandle_with_args(np, "interconnects", + "#interconnect-cells", idx * 2, + &src_args); + if (ret) + return ERR_PTR(ret); + + of_node_put(src_args.np); + + ret = of_parse_phandle_with_args(np, "interconnects", + "#interconnect-cells", idx * 2 + 1, + &dst_args); + if (ret) + return ERR_PTR(ret); + + of_node_put(dst_args.np); + + src_node = of_icc_get_from_provider(&src_args); + + if (IS_ERR(src_node)) { + if (PTR_ERR(src_node) != -EPROBE_DEFER) + dev_err(dev, "error finding src node: %ld\n", + PTR_ERR(src_node)); + return ERR_CAST(src_node); + } + + dst_node = of_icc_get_from_provider(&dst_args); + + if (IS_ERR(dst_node)) { + if (PTR_ERR(dst_node) != -EPROBE_DEFER) + dev_err(dev, "error finding dst node: %ld\n", + PTR_ERR(dst_node)); + return ERR_CAST(dst_node); + } + + mutex_lock(&icc_lock); + path = path_find(dev, src_node, dst_node); + if (IS_ERR(path)) + dev_err(dev, "%s: invalid path=%ld\n", __func__, PTR_ERR(path)); + mutex_unlock(&icc_lock); + + return path; +} +EXPORT_SYMBOL_GPL(of_icc_get); + /** * icc_set_bw() - set bandwidth constraints on an interconnect path * @path: reference to the path returned by icc_get() @@ -519,6 +666,8 @@ int icc_provider_add(struct icc_provider *provider) { if (WARN_ON(!provider->set)) return -EINVAL; + if (WARN_ON(!provider->xlate)) + return -EINVAL; mutex_lock(&icc_lock); diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 78208a754181..63caccadc2db 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -12,6 +12,21 @@ #define icc_units_to_bps(bw) ((bw) * 1000ULL) struct icc_node; +struct of_phandle_args; + +/** + * struct icc_onecell_data - driver data for onecell interconnect providers + * + * @num_nodes: number of nodes in this device + * @nodes: array of pointers to the nodes in this device + */ +struct icc_onecell_data { + unsigned int num_nodes; + struct icc_node *nodes[]; +}; + +struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec, + void *data); /** * struct icc_provider - interconnect provider (controller) entity that might @@ -21,6 +36,7 @@ struct icc_node; * @nodes: internal list of the interconnect provider nodes * @set: pointer to device specific set operation function * @aggregate: pointer to device specific aggregate operation function + * @xlate: provider-specific callback for mapping nodes from phandle arguments * @dev: the device this interconnect provider belongs to * @users: count of active users * @data: pointer to private data @@ -31,6 +47,7 @@ struct icc_provider { int (*set)(struct icc_node *src, struct icc_node *dst); int (*aggregate)(struct icc_node *node, u32 avg_bw, u32 peak_bw, u32 *agg_avg, u32 *agg_peak); + struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data); struct device *dev; int users; void *data; diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index c331afb3a2c8..dc25864755ba 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -27,6 +27,7 @@ struct device; struct icc_path *icc_get(struct device *dev, const int src_id, const int dst_id); +struct icc_path *of_icc_get(struct device *dev, const char *name); void icc_put(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); @@ -38,6 +39,12 @@ static inline struct icc_path *icc_get(struct device *dev, const int src_id, return NULL; } +static inline struct icc_path *of_icc_get(struct device *dev, + const char *name) +{ + return NULL; +} + static inline void icc_put(struct icc_path *path) { } -- cgit v1.2.3 From b5d2f741077abc71205e60b5bbd7dfa07b9d6953 Mon Sep 17 00:00:00 2001 From: David Dai Date: Wed, 16 Jan 2019 18:11:00 +0200 Subject: interconnect: qcom: Add sdm845 interconnect provider driver Introduce Qualcomm SDM845 specific provider driver using the interconnect framework. Signed-off-by: David Dai Acked-by: Rob Herring Signed-off-by: Georgi Djakov Signed-off-by: Greg Kroah-Hartman --- .../bindings/interconnect/qcom,sdm845.txt | 24 + drivers/interconnect/Kconfig | 5 + drivers/interconnect/Makefile | 1 + drivers/interconnect/qcom/Kconfig | 13 + drivers/interconnect/qcom/Makefile | 5 + drivers/interconnect/qcom/sdm845.c | 838 +++++++++++++++++++++ include/dt-bindings/interconnect/qcom,sdm845.h | 143 ++++ 7 files changed, 1029 insertions(+) create mode 100644 Documentation/devicetree/bindings/interconnect/qcom,sdm845.txt create mode 100644 drivers/interconnect/qcom/Kconfig create mode 100644 drivers/interconnect/qcom/Makefile create mode 100644 drivers/interconnect/qcom/sdm845.c create mode 100644 include/dt-bindings/interconnect/qcom,sdm845.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sdm845.txt b/Documentation/devicetree/bindings/interconnect/qcom,sdm845.txt new file mode 100644 index 000000000000..5c4f1d911630 --- /dev/null +++ b/Documentation/devicetree/bindings/interconnect/qcom,sdm845.txt @@ -0,0 +1,24 @@ +Qualcomm SDM845 Network-On-Chip interconnect driver binding +----------------------------------------------------------- + +SDM845 interconnect providers support system bandwidth requirements through +RPMh hardware accelerators known as Bus Clock Manager (BCM). The provider is +able to communicate with the BCM through the Resource State Coordinator (RSC) +associated with each execution environment. Provider nodes must reside within +an RPMh device node pertaining to their RSC and each provider maps to a single +RPMh resource. + +Required properties : +- compatible : shall contain only one of the following: + "qcom,sdm845-rsc-hlos" +- #interconnect-cells : should contain 1 + +Examples: + +apps_rsc: rsc { + rsc_hlos: interconnect { + compatible = "qcom,sdm845-rsc-hlos"; + #interconnect-cells = <1>; + }; +}; + diff --git a/drivers/interconnect/Kconfig b/drivers/interconnect/Kconfig index a261c7d41deb..07a8276fa35a 100644 --- a/drivers/interconnect/Kconfig +++ b/drivers/interconnect/Kconfig @@ -8,3 +8,8 @@ menuconfig INTERCONNECT If unsure, say no. +if INTERCONNECT + +source "drivers/interconnect/qcom/Kconfig" + +endif diff --git a/drivers/interconnect/Makefile b/drivers/interconnect/Makefile index 7a01f33b5593..28f2ab0824d5 100644 --- a/drivers/interconnect/Makefile +++ b/drivers/interconnect/Makefile @@ -3,3 +3,4 @@ icc-core-objs := core.o obj-$(CONFIG_INTERCONNECT) += icc-core.o +obj-$(CONFIG_INTERCONNECT_QCOM) += qcom/ diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig new file mode 100644 index 000000000000..290d330abe5a --- /dev/null +++ b/drivers/interconnect/qcom/Kconfig @@ -0,0 +1,13 @@ +config INTERCONNECT_QCOM + bool "Qualcomm Network-on-Chip interconnect drivers" + depends on ARCH_QCOM + help + Support for Qualcomm's Network-on-Chip interconnect hardware. + +config INTERCONNECT_QCOM_SDM845 + tristate "Qualcomm SDM845 interconnect driver" + depends on INTERCONNECT_QCOM + depends on (QCOM_RPMH && QCOM_COMMAND_DB && OF) || COMPILE_TEST + help + This is a driver for the Qualcomm Network-on-Chip on sdm845-based + platforms. diff --git a/drivers/interconnect/qcom/Makefile b/drivers/interconnect/qcom/Makefile new file mode 100644 index 000000000000..1c1cea690f92 --- /dev/null +++ b/drivers/interconnect/qcom/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +qnoc-sdm845-objs := sdm845.o + +obj-$(CONFIG_INTERCONNECT_QCOM_SDM845) += qnoc-sdm845.o diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c new file mode 100644 index 000000000000..4915b78da673 --- /dev/null +++ b/drivers/interconnect/qcom/sdm845.c @@ -0,0 +1,838 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018, The Linux Foundation. All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#define BCM_TCS_CMD_COMMIT_SHFT 30 +#define BCM_TCS_CMD_COMMIT_MASK 0x40000000 +#define BCM_TCS_CMD_VALID_SHFT 29 +#define BCM_TCS_CMD_VALID_MASK 0x20000000 +#define BCM_TCS_CMD_VOTE_X_SHFT 14 +#define BCM_TCS_CMD_VOTE_MASK 0x3fff +#define BCM_TCS_CMD_VOTE_Y_SHFT 0 +#define BCM_TCS_CMD_VOTE_Y_MASK 0xfffc000 + +#define BCM_TCS_CMD(commit, valid, vote_x, vote_y) \ + (((commit) << BCM_TCS_CMD_COMMIT_SHFT) | \ + ((valid) << BCM_TCS_CMD_VALID_SHFT) | \ + ((cpu_to_le32(vote_x) & \ + BCM_TCS_CMD_VOTE_MASK) << BCM_TCS_CMD_VOTE_X_SHFT) | \ + ((cpu_to_le32(vote_y) & \ + BCM_TCS_CMD_VOTE_MASK) << BCM_TCS_CMD_VOTE_Y_SHFT)) + +#define to_qcom_provider(_provider) \ + container_of(_provider, struct qcom_icc_provider, provider) + +struct qcom_icc_provider { + struct icc_provider provider; + struct device *dev; + struct qcom_icc_bcm **bcms; + size_t num_bcms; +}; + +/** + * struct bcm_db - Auxiliary data pertaining to each Bus Clock Manager (BCM) + * @unit: divisor used to convert bytes/sec bw value to an RPMh msg + * @width: multiplier used to convert bytes/sec bw value to an RPMh msg + * @vcd: virtual clock domain that this bcm belongs to + * @reserved: reserved field + */ +struct bcm_db { + __le32 unit; + __le16 width; + u8 vcd; + u8 reserved; +}; + +#define SDM845_MAX_LINKS 43 +#define SDM845_MAX_BCMS 30 +#define SDM845_MAX_BCM_PER_NODE 2 +#define SDM845_MAX_VCD 10 + +/** + * struct qcom_icc_node - Qualcomm specific interconnect nodes + * @name: the node name used in debugfs + * @links: an array of nodes where we can go next while traversing + * @id: a unique node identifier + * @num_links: the total number of @links + * @channels: num of channels at this node + * @buswidth: width of the interconnect between a node and the bus + * @sum_avg: current sum aggregate value of all avg bw requests + * @max_peak: current max aggregate value of all peak bw requests + * @bcms: list of bcms associated with this logical node + * @num_bcms: num of @bcms + */ +struct qcom_icc_node { + const char *name; + u16 links[SDM845_MAX_LINKS]; + u16 id; + u16 num_links; + u16 channels; + u16 buswidth; + u64 sum_avg; + u64 max_peak; + struct qcom_icc_bcm *bcms[SDM845_MAX_BCM_PER_NODE]; + size_t num_bcms; +}; + +/** + * struct qcom_icc_bcm - Qualcomm specific hardware accelerator nodes + * known as Bus Clock Manager (BCM) + * @name: the bcm node name used to fetch BCM data from command db + * @type: latency or bandwidth bcm + * @addr: address offsets used when voting to RPMH + * @vote_x: aggregated threshold values, represents sum_bw when @type is bw bcm + * @vote_y: aggregated threshold values, represents peak_bw when @type is bw bcm + * @dirty: flag used to indicate whether the bcm needs to be committed + * @keepalive: flag used to indicate whether a keepalive is required + * @aux_data: auxiliary data used when calculating threshold values and + * communicating with RPMh + * @list: used to link to other bcms when compiling lists for commit + * @num_nodes: total number of @num_nodes + * @nodes: list of qcom_icc_nodes that this BCM encapsulates + */ +struct qcom_icc_bcm { + const char *name; + u32 type; + u32 addr; + u64 vote_x; + u64 vote_y; + bool dirty; + bool keepalive; + struct bcm_db aux_data; + struct list_head list; + size_t num_nodes; + struct qcom_icc_node *nodes[]; +}; + +struct qcom_icc_fabric { + struct qcom_icc_node **nodes; + size_t num_nodes; +}; + +struct qcom_icc_desc { + struct qcom_icc_node **nodes; + size_t num_nodes; + struct qcom_icc_bcm **bcms; + size_t num_bcms; +}; + +#define DEFINE_QNODE(_name, _id, _channels, _buswidth, \ + _numlinks, ...) \ + static struct qcom_icc_node _name = { \ + .id = _id, \ + .name = #_name, \ + .channels = _channels, \ + .buswidth = _buswidth, \ + .num_links = _numlinks, \ + .links = { __VA_ARGS__ }, \ + } + +DEFINE_QNODE(qhm_a1noc_cfg, MASTER_A1NOC_CFG, 1, 4, 1, SLAVE_SERVICE_A1NOC); +DEFINE_QNODE(qhm_qup1, MASTER_BLSP_1, 1, 4, 1, SLAVE_A1NOC_SNOC); +DEFINE_QNODE(qhm_tsif, MASTER_TSIF, 1, 4, 1, SLAVE_A1NOC_SNOC); +DEFINE_QNODE(xm_sdc2, MASTER_SDCC_2, 1, 8, 1, SLAVE_A1NOC_SNOC); +DEFINE_QNODE(xm_sdc4, MASTER_SDCC_4, 1, 8, 1, SLAVE_A1NOC_SNOC); +DEFINE_QNODE(xm_ufs_card, MASTER_UFS_CARD, 1, 8, 1, SLAVE_A1NOC_SNOC); +DEFINE_QNODE(xm_ufs_mem, MASTER_UFS_MEM, 1, 8, 1, SLAVE_A1NOC_SNOC); +DEFINE_QNODE(xm_pcie_0, MASTER_PCIE_0, 1, 8, 1, SLAVE_ANOC_PCIE_A1NOC_SNOC); +DEFINE_QNODE(qhm_a2noc_cfg, MASTER_A2NOC_CFG, 1, 4, 1, SLAVE_SERVICE_A2NOC); +DEFINE_QNODE(qhm_qdss_bam, MASTER_QDSS_BAM, 1, 4, 1, SLAVE_A2NOC_SNOC); +DEFINE_QNODE(qhm_qup2, MASTER_BLSP_2, 1, 4, 1, SLAVE_A2NOC_SNOC); +DEFINE_QNODE(qnm_cnoc, MASTER_CNOC_A2NOC, 1, 8, 1, SLAVE_A2NOC_SNOC); +DEFINE_QNODE(qxm_crypto, MASTER_CRYPTO, 1, 8, 1, SLAVE_A2NOC_SNOC); +DEFINE_QNODE(qxm_ipa, MASTER_IPA, 1, 8, 1, SLAVE_A2NOC_SNOC); +DEFINE_QNODE(xm_pcie3_1, MASTER_PCIE_1, 1, 8, 1, SLAVE_ANOC_PCIE_SNOC); +DEFINE_QNODE(xm_qdss_etr, MASTER_QDSS_ETR, 1, 8, 1, SLAVE_A2NOC_SNOC); +DEFINE_QNODE(xm_usb3_0, MASTER_USB3_0, 1, 8, 1, SLAVE_A2NOC_SNOC); +DEFINE_QNODE(xm_usb3_1, MASTER_USB3_1, 1, 8, 1, SLAVE_A2NOC_SNOC); +DEFINE_QNODE(qxm_camnoc_hf0_uncomp, MASTER_CAMNOC_HF0_UNCOMP, 1, 32, 1, SLAVE_CAMNOC_UNCOMP); +DEFINE_QNODE(qxm_camnoc_hf1_uncomp, MASTER_CAMNOC_HF1_UNCOMP, 1, 32, 1, SLAVE_CAMNOC_UNCOMP); +DEFINE_QNODE(qxm_camnoc_sf_uncomp, MASTER_CAMNOC_SF_UNCOMP, 1, 32, 1, SLAVE_CAMNOC_UNCOMP); +DEFINE_QNODE(qhm_spdm, MASTER_SPDM, 1, 4, 1, SLAVE_CNOC_A2NOC); +DEFINE_QNODE(qhm_tic, MASTER_TIC, 1, 4, 43, SLAVE_A1NOC_CFG, SLAVE_A2NOC_CFG, SLAVE_AOP, SLAVE_AOSS, SLAVE_CAMERA_CFG, SLAVE_CLK_CTL, SLAVE_CDSP_CFG, SLAVE_RBCPR_CX_CFG, SLAVE_CRYPTO_0_CFG, SLAVE_DCC_CFG, SLAVE_CNOC_DDRSS, SLAVE_DISPLAY_CFG, SLAVE_GLM, SLAVE_GFX3D_CFG, SLAVE_IMEM_CFG, SLAVE_IPA_CFG, SLAVE_CNOC_MNOC_CFG, SLAVE_PCIE_0_CFG, SLAVE_PCIE_1_CFG, SLAVE_PDM, SLAVE_SOUTH_PHY_CFG, SLAVE_PIMEM_CFG, SLAVE_PRNG, SLAVE_QDSS_CFG, SLAVE_BLSP_2, SLAVE_BLSP_1, SLAVE_SDCC_2, SLAVE_SDCC_4, SLAVE_SNOC_CFG, SLAVE_SPDM_WRAPPER, SLAVE_SPSS_CFG, SLAVE_TCSR, SLAVE_TLMM_NORTH, SLAVE_TLMM_SOUTH, SLAVE_TSIF, SLAVE_UFS_CARD_CFG, SLAVE_UFS_MEM_CFG, SLAVE_USB3_0, SLAVE_USB3_1, SLAVE_VENUS_CFG, SLAVE_VSENSE_CTRL_CFG, SLAVE_CNOC_A2NOC, SLAVE_SERVICE_CNOC); +DEFINE_QNODE(qnm_snoc, MASTER_SNOC_CNOC, 1, 8, 42, SLAVE_A1NOC_CFG, SLAVE_A2NOC_CFG, SLAVE_AOP, SLAVE_AOSS, SLAVE_CAMERA_CFG, SLAVE_CLK_CTL, SLAVE_CDSP_CFG, SLAVE_RBCPR_CX_CFG, SLAVE_CRYPTO_0_CFG, SLAVE_DCC_CFG, SLAVE_CNOC_DDRSS, SLAVE_DISPLAY_CFG, SLAVE_GLM, SLAVE_GFX3D_CFG, SLAVE_IMEM_CFG, SLAVE_IPA_CFG, SLAVE_CNOC_MNOC_CFG, SLAVE_PCIE_0_CFG, SLAVE_PCIE_1_CFG, SLAVE_PDM, SLAVE_SOUTH_PHY_CFG, SLAVE_PIMEM_CFG, SLAVE_PRNG, SLAVE_QDSS_CFG, SLAVE_BLSP_2, SLAVE_BLSP_1, SLAVE_SDCC_2, SLAVE_SDCC_4, SLAVE_SNOC_CFG, SLAVE_SPDM_WRAPPER, SLAVE_SPSS_CFG, SLAVE_TCSR, SLAVE_TLMM_NORTH, SLAVE_TLMM_SOUTH, SLAVE_TSIF, SLAVE_UFS_CARD_CFG, SLAVE_UFS_MEM_CFG, SLAVE_USB3_0, SLAVE_USB3_1, SLAVE_VENUS_CFG, SLAVE_VSENSE_CTRL_CFG, SLAVE_SERVICE_CNOC); +DEFINE_QNODE(xm_qdss_dap, MASTER_QDSS_DAP, 1, 8, 43, SLAVE_A1NOC_CFG, SLAVE_A2NOC_CFG, SLAVE_AOP, SLAVE_AOSS, SLAVE_CAMERA_CFG, SLAVE_CLK_CTL, SLAVE_CDSP_CFG, SLAVE_RBCPR_CX_CFG, SLAVE_CRYPTO_0_CFG, SLAVE_DCC_CFG, SLAVE_CNOC_DDRSS, SLAVE_DISPLAY_CFG, SLAVE_GLM, SLAVE_GFX3D_CFG, SLAVE_IMEM_CFG, SLAVE_IPA_CFG, SLAVE_CNOC_MNOC_CFG, SLAVE_PCIE_0_CFG, SLAVE_PCIE_1_CFG, SLAVE_PDM, SLAVE_SOUTH_PHY_CFG, SLAVE_PIMEM_CFG, SLAVE_PRNG, SLAVE_QDSS_CFG, SLAVE_BLSP_2, SLAVE_BLSP_1, SLAVE_SDCC_2, SLAVE_SDCC_4, SLAVE_SNOC_CFG, SLAVE_SPDM_WRAPPER, SLAVE_SPSS_CFG, SLAVE_TCSR, SLAVE_TLMM_NORTH, SLAVE_TLMM_SOUTH, SLAVE_TSIF, SLAVE_UFS_CARD_CFG, SLAVE_UFS_MEM_CFG, SLAVE_USB3_0, SLAVE_USB3_1, SLAVE_VENUS_CFG, SLAVE_VSENSE_CTRL_CFG, SLAVE_CNOC_A2NOC, SLAVE_SERVICE_CNOC); +DEFINE_QNODE(qhm_cnoc, MASTER_CNOC_DC_NOC, 1, 4, 2, SLAVE_LLCC_CFG, SLAVE_MEM_NOC_CFG); +DEFINE_QNODE(acm_l3, MASTER_APPSS_PROC, 1, 16, 3, SLAVE_GNOC_SNOC, SLAVE_GNOC_MEM_NOC, SLAVE_SERVICE_GNOC); +DEFINE_QNODE(pm_gnoc_cfg, MASTER_GNOC_CFG, 1, 4, 1, SLAVE_SERVICE_GNOC); +DEFINE_QNODE(llcc_mc, MASTER_LLCC, 4, 4, 1, SLAVE_EBI1); +DEFINE_QNODE(acm_tcu, MASTER_TCU_0, 1, 8, 3, SLAVE_MEM_NOC_GNOC, SLAVE_LLCC, SLAVE_MEM_NOC_SNOC); +DEFINE_QNODE(qhm_memnoc_cfg, MASTER_MEM_NOC_CFG, 1, 4, 2, SLAVE_MSS_PROC_MS_MPU_CFG, SLAVE_SERVICE_MEM_NOC); +DEFINE_QNODE(qnm_apps, MASTER_GNOC_MEM_NOC, 2, 32, 1, SLAVE_LLCC); +DEFINE_QNODE(qnm_mnoc_hf, MASTER_MNOC_HF_MEM_NOC, 2, 32, 2, SLAVE_MEM_NOC_GNOC, SLAVE_LLCC); +DEFINE_QNODE(qnm_mnoc_sf, MASTER_MNOC_SF_MEM_NOC, 1, 32, 3, SLAVE_MEM_NOC_GNOC, SLAVE_LLCC, SLAVE_MEM_NOC_SNOC); +DEFINE_QNODE(qnm_snoc_gc, MASTER_SNOC_GC_MEM_NOC, 1, 8, 1, SLAVE_LLCC); +DEFINE_QNODE(qnm_snoc_sf, MASTER_SNOC_SF_MEM_NOC, 1, 16, 2, SLAVE_MEM_NOC_GNOC, SLAVE_LLCC); +DEFINE_QNODE(qxm_gpu, MASTER_GFX3D, 2, 32, 3, SLAVE_MEM_NOC_GNOC, SLAVE_LLCC, SLAVE_MEM_NOC_SNOC); +DEFINE_QNODE(qhm_mnoc_cfg, MASTER_CNOC_MNOC_CFG, 1, 4, 1, SLAVE_SERVICE_MNOC); +DEFINE_QNODE(qxm_camnoc_hf0, MASTER_CAMNOC_HF0, 1, 32, 1, SLAVE_MNOC_HF_MEM_NOC); +DEFINE_QNODE(qxm_camnoc_hf1, MASTER_CAMNOC_HF1, 1, 32, 1, SLAVE_MNOC_HF_MEM_NOC); +DEFINE_QNODE(qxm_camnoc_sf, MASTER_CAMNOC_SF, 1, 32, 1, SLAVE_MNOC_SF_MEM_NOC); +DEFINE_QNODE(qxm_mdp0, MASTER_MDP0, 1, 32, 1, SLAVE_MNOC_HF_MEM_NOC); +DEFINE_QNODE(qxm_mdp1, MASTER_MDP1, 1, 32, 1, SLAVE_MNOC_HF_MEM_NOC); +DEFINE_QNODE(qxm_rot, MASTER_ROTATOR, 1, 32, 1, SLAVE_MNOC_SF_MEM_NOC); +DEFINE_QNODE(qxm_venus0, MASTER_VIDEO_P0, 1, 32, 1, SLAVE_MNOC_SF_MEM_NOC); +DEFINE_QNODE(qxm_venus1, MASTER_VIDEO_P1, 1, 32, 1, SLAVE_MNOC_SF_MEM_NOC); +DEFINE_QNODE(qxm_venus_arm9, MASTER_VIDEO_PROC, 1, 8, 1, SLAVE_MNOC_SF_MEM_NOC); +DEFINE_QNODE(qhm_snoc_cfg, MASTER_SNOC_CFG, 1, 4, 1, SLAVE_SERVICE_SNOC); +DEFINE_QNODE(qnm_aggre1_noc, MASTER_A1NOC_SNOC, 1, 16, 6, SLAVE_APPSS, SLAVE_SNOC_CNOC, SLAVE_SNOC_MEM_NOC_SF, SLAVE_IMEM, SLAVE_PIMEM, SLAVE_QDSS_STM); +DEFINE_QNODE(qnm_aggre2_noc, MASTER_A2NOC_SNOC, 1, 16, 9, SLAVE_APPSS, SLAVE_SNOC_CNOC, SLAVE_SNOC_MEM_NOC_SF, SLAVE_IMEM, SLAVE_PCIE_0, SLAVE_PCIE_1, SLAVE_PIMEM, SLAVE_QDSS_STM, SLAVE_TCU); +DEFINE_QNODE(qnm_gladiator_sodv, MASTER_GNOC_SNOC, 1, 8, 8, SLAVE_APPSS, SLAVE_SNOC_CNOC, SLAVE_IMEM, SLAVE_PCIE_0, SLAVE_PCIE_1, SLAVE_PIMEM, SLAVE_QDSS_STM, SLAVE_TCU); +DEFINE_QNODE(qnm_memnoc, MASTER_MEM_NOC_SNOC, 1, 8, 5, SLAVE_APPSS, SLAVE_SNOC_CNOC, SLAVE_IMEM, SLAVE_PIMEM, SLAVE_QDSS_STM); +DEFINE_QNODE(qnm_pcie_anoc, MASTER_ANOC_PCIE_SNOC, 1, 16, 5, SLAVE_APPSS, SLAVE_SNOC_CNOC, SLAVE_SNOC_MEM_NOC_SF, SLAVE_IMEM, SLAVE_QDSS_STM); +DEFINE_QNODE(qxm_pimem, MASTER_PIMEM, 1, 8, 2, SLAVE_SNOC_MEM_NOC_GC, SLAVE_IMEM); +DEFINE_QNODE(xm_gic, MASTER_GIC, 1, 8, 2, SLAVE_SNOC_MEM_NOC_GC, SLAVE_IMEM); +DEFINE_QNODE(qns_a1noc_snoc, SLAVE_A1NOC_SNOC, 1, 16, 1, MASTER_A1NOC_SNOC); +DEFINE_QNODE(srvc_aggre1_noc, SLAVE_SERVICE_A1NOC, 1, 4, 0); +DEFINE_QNODE(qns_pcie_a1noc_snoc, SLAVE_ANOC_PCIE_A1NOC_SNOC, 1, 16, 1, MASTER_ANOC_PCIE_SNOC); +DEFINE_QNODE(qns_a2noc_snoc, SLAVE_A2NOC_SNOC, 1, 16, 1, MASTER_A2NOC_SNOC); +DEFINE_QNODE(qns_pcie_snoc, SLAVE_ANOC_PCIE_SNOC, 1, 16, 1, MASTER_ANOC_PCIE_SNOC); +DEFINE_QNODE(srvc_aggre2_noc, SLAVE_SERVICE_A2NOC, 1, 4, 0); +DEFINE_QNODE(qns_camnoc_uncomp, SLAVE_CAMNOC_UNCOMP, 1, 32, 0); +DEFINE_QNODE(qhs_a1_noc_cfg, SLAVE_A1NOC_CFG, 1, 4, 1, MASTER_A1NOC_CFG); +DEFINE_QNODE(qhs_a2_noc_cfg, SLAVE_A2NOC_CFG, 1, 4, 1, MASTER_A2NOC_CFG); +DEFINE_QNODE(qhs_aop, SLAVE_AOP, 1, 4, 0); +DEFINE_QNODE(qhs_aoss, SLAVE_AOSS, 1, 4, 0); +DEFINE_QNODE(qhs_camera_cfg, SLAVE_CAMERA_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_clk_ctl, SLAVE_CLK_CTL, 1, 4, 0); +DEFINE_QNODE(qhs_compute_dsp_cfg, SLAVE_CDSP_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_cpr_cx, SLAVE_RBCPR_CX_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_crypto0_cfg, SLAVE_CRYPTO_0_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_dcc_cfg, SLAVE_DCC_CFG, 1, 4, 1, MASTER_CNOC_DC_NOC); +DEFINE_QNODE(qhs_ddrss_cfg, SLAVE_CNOC_DDRSS, 1, 4, 0); +DEFINE_QNODE(qhs_display_cfg, SLAVE_DISPLAY_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_glm, SLAVE_GLM, 1, 4, 0); +DEFINE_QNODE(qhs_gpuss_cfg, SLAVE_GFX3D_CFG, 1, 8, 0); +DEFINE_QNODE(qhs_imem_cfg, SLAVE_IMEM_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_ipa, SLAVE_IPA_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_mnoc_cfg, SLAVE_CNOC_MNOC_CFG, 1, 4, 1, MASTER_CNOC_MNOC_CFG); +DEFINE_QNODE(qhs_pcie0_cfg, SLAVE_PCIE_0_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_pcie_gen3_cfg, SLAVE_PCIE_1_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_pdm, SLAVE_PDM, 1, 4, 0); +DEFINE_QNODE(qhs_phy_refgen_south, SLAVE_SOUTH_PHY_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_pimem_cfg, SLAVE_PIMEM_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_prng, SLAVE_PRNG, 1, 4, 0); +DEFINE_QNODE(qhs_qdss_cfg, SLAVE_QDSS_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_qupv3_north, SLAVE_BLSP_2, 1, 4, 0); +DEFINE_QNODE(qhs_qupv3_south, SLAVE_BLSP_1, 1, 4, 0); +DEFINE_QNODE(qhs_sdc2, SLAVE_SDCC_2, 1, 4, 0); +DEFINE_QNODE(qhs_sdc4, SLAVE_SDCC_4, 1, 4, 0); +DEFINE_QNODE(qhs_snoc_cfg, SLAVE_SNOC_CFG, 1, 4, 1, MASTER_SNOC_CFG); +DEFINE_QNODE(qhs_spdm, SLAVE_SPDM_WRAPPER, 1, 4, 0); +DEFINE_QNODE(qhs_spss_cfg, SLAVE_SPSS_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_tcsr, SLAVE_TCSR, 1, 4, 0); +DEFINE_QNODE(qhs_tlmm_north, SLAVE_TLMM_NORTH, 1, 4, 0); +DEFINE_QNODE(qhs_tlmm_south, SLAVE_TLMM_SOUTH, 1, 4, 0); +DEFINE_QNODE(qhs_tsif, SLAVE_TSIF, 1, 4, 0); +DEFINE_QNODE(qhs_ufs_card_cfg, SLAVE_UFS_CARD_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_ufs_mem_cfg, SLAVE_UFS_MEM_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_usb3_0, SLAVE_USB3_0, 1, 4, 0); +DEFINE_QNODE(qhs_usb3_1, SLAVE_USB3_1, 1, 4, 0); +DEFINE_QNODE(qhs_venus_cfg, SLAVE_VENUS_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_vsense_ctrl_cfg, SLAVE_VSENSE_CTRL_CFG, 1, 4, 0); +DEFINE_QNODE(qns_cnoc_a2noc, SLAVE_CNOC_A2NOC, 1, 8, 1, MASTER_CNOC_A2NOC); +DEFINE_QNODE(srvc_cnoc, SLAVE_SERVICE_CNOC, 1, 4, 0); +DEFINE_QNODE(qhs_llcc, SLAVE_LLCC_CFG, 1, 4, 0); +DEFINE_QNODE(qhs_memnoc, SLAVE_MEM_NOC_CFG, 1, 4, 1, MASTER_MEM_NOC_CFG); +DEFINE_QNODE(qns_gladiator_sodv, SLAVE_GNOC_SNOC, 1, 8, 1, MASTER_GNOC_SNOC); +DEFINE_QNODE(qns_gnoc_memnoc, SLAVE_GNOC_MEM_NOC, 2, 32, 1, MASTER_GNOC_MEM_NOC); +DEFINE_QNODE(srvc_gnoc, SLAVE_SERVICE_GNOC, 1, 4, 0); +DEFINE_QNODE(ebi, SLAVE_EBI1, 4, 4, 0); +DEFINE_QNODE(qhs_mdsp_ms_mpu_cfg, SLAVE_MSS_PROC_MS_MPU_CFG, 1, 4, 0); +DEFINE_QNODE(qns_apps_io, SLAVE_MEM_NOC_GNOC, 1, 32, 0); +DEFINE_QNODE(qns_llcc, SLAVE_LLCC, 4, 16, 1, MASTER_LLCC); +DEFINE_QNODE(qns_memnoc_snoc, SLAVE_MEM_NOC_SNOC, 1, 8, 1, MASTER_MEM_NOC_SNOC); +DEFINE_QNODE(srvc_memnoc, SLAVE_SERVICE_MEM_NOC, 1, 4, 0); +DEFINE_QNODE(qns2_mem_noc, SLAVE_MNOC_SF_MEM_NOC, 1, 32, 1, MASTER_MNOC_SF_MEM_NOC); +DEFINE_QNODE(qns_mem_noc_hf, SLAVE_MNOC_HF_MEM_NOC, 2, 32, 1, MASTER_MNOC_HF_MEM_NOC); +DEFINE_QNODE(srvc_mnoc, SLAVE_SERVICE_MNOC, 1, 4, 0); +DEFINE_QNODE(qhs_apss, SLAVE_APPSS, 1, 8, 0); +DEFINE_QNODE(qns_cnoc, SLAVE_SNOC_CNOC, 1, 8, 1, MASTER_SNOC_CNOC); +DEFINE_QNODE(qns_memnoc_gc, SLAVE_SNOC_MEM_NOC_GC, 1, 8, 1, MASTER_SNOC_GC_MEM_NOC); +DEFINE_QNODE(qns_memnoc_sf, SLAVE_SNOC_MEM_NOC_SF, 1, 16, 1, MASTER_SNOC_SF_MEM_NOC); +DEFINE_QNODE(qxs_imem, SLAVE_IMEM, 1, 8, 0); +DEFINE_QNODE(qxs_pcie, SLAVE_PCIE_0, 1, 8, 0); +DEFINE_QNODE(qxs_pcie_gen3, SLAVE_PCIE_1, 1, 8, 0); +DEFINE_QNODE(qxs_pimem, SLAVE_PIMEM, 1, 8, 0); +DEFINE_QNODE(srvc_snoc, SLAVE_SERVICE_SNOC, 1, 4, 0); +DEFINE_QNODE(xs_qdss_stm, SLAVE_QDSS_STM, 1, 4, 0); +DEFINE_QNODE(xs_sys_tcu_cfg, SLAVE_TCU, 1, 8, 0); + +#define DEFINE_QBCM(_name, _bcmname, _keepalive, _numnodes, ...) \ + static struct qcom_icc_bcm _name = { \ + .name = _bcmname, \ + .keepalive = _keepalive, \ + .num_nodes = _numnodes, \ + .nodes = { __VA_ARGS__ }, \ + } + +DEFINE_QBCM(bcm_acv, "ACV", false, 1, &ebi); +DEFINE_QBCM(bcm_mc0, "MC0", true, 1, &ebi); +DEFINE_QBCM(bcm_sh0, "SH0", true, 1, &qns_llcc); +DEFINE_QBCM(bcm_mm0, "MM0", false, 1, &qns_mem_noc_hf); +DEFINE_QBCM(bcm_sh1, "SH1", false, 1, &qns_apps_io); +DEFINE_QBCM(bcm_mm1, "MM1", false, 7, &qxm_camnoc_hf0_uncomp, &qxm_camnoc_hf1_uncomp, &qxm_camnoc_sf_uncomp, &qxm_camnoc_hf0, &qxm_camnoc_hf1, &qxm_mdp0, &qxm_mdp1); +DEFINE_QBCM(bcm_sh2, "SH2", false, 1, &qns_memnoc_snoc); +DEFINE_QBCM(bcm_mm2, "MM2", false, 1, &qns2_mem_noc); +DEFINE_QBCM(bcm_sh3, "SH3", false, 1, &acm_tcu); +DEFINE_QBCM(bcm_mm3, "MM3", false, 5, &qxm_camnoc_sf, &qxm_rot, &qxm_venus0, &qxm_venus1, &qxm_venus_arm9); +DEFINE_QBCM(bcm_sh5, "SH5", false, 1, &qnm_apps); +DEFINE_QBCM(bcm_sn0, "SN0", true, 1, &qns_memnoc_sf); +DEFINE_QBCM(bcm_ce0, "CE0", false, 1, &qxm_crypto); +DEFINE_QBCM(bcm_cn0, "CN0", false, 47, &qhm_spdm, &qhm_tic, &qnm_snoc, &xm_qdss_dap, &qhs_a1_noc_cfg, &qhs_a2_noc_cfg, &qhs_aop, &qhs_aoss, &qhs_camera_cfg, &qhs_clk_ctl, &qhs_compute_dsp_cfg, &qhs_cpr_cx, &qhs_crypto0_cfg, &qhs_dcc_cfg, &qhs_ddrss_cfg, &qhs_display_cfg, &qhs_glm, &qhs_gpuss_cfg, &qhs_imem_cfg, &qhs_ipa, &qhs_mnoc_cfg, &qhs_pcie0_cfg, &qhs_pcie_gen3_cfg, &qhs_pdm, &qhs_phy_refgen_south, &qhs_pimem_cfg, &qhs_prng, &qhs_qdss_cfg, &qhs_qupv3_north, &qhs_qupv3_south, &qhs_sdc2, &qhs_sdc4, &qhs_snoc_cfg, &qhs_spdm, &qhs_spss_cfg, &qhs_tcsr, &qhs_tlmm_north, &qhs_tlmm_south, &qhs_tsif, &qhs_ufs_card_cfg, &qhs_ufs_mem_cfg, &qhs_usb3_0, &qhs_usb3_1, &qhs_venus_cfg, &qhs_vsense_ctrl_cfg, &qns_cnoc_a2noc, &srvc_cnoc); +DEFINE_QBCM(bcm_qup0, "QUP0", false, 2, &qhm_qup1, &qhm_qup2); +DEFINE_QBCM(bcm_sn1, "SN1", false, 1, &qxs_imem); +DEFINE_QBCM(bcm_sn2, "SN2", false, 1, &qns_memnoc_gc); +DEFINE_QBCM(bcm_sn3, "SN3", false, 1, &qns_cnoc); +DEFINE_QBCM(bcm_sn4, "SN4", false, 1, &qxm_pimem); +DEFINE_QBCM(bcm_sn5, "SN5", false, 1, &xs_qdss_stm); +DEFINE_QBCM(bcm_sn6, "SN6", false, 3, &qhs_apss, &srvc_snoc, &xs_sys_tcu_cfg); +DEFINE_QBCM(bcm_sn7, "SN7", false, 1, &qxs_pcie); +DEFINE_QBCM(bcm_sn8, "SN8", false, 1, &qxs_pcie_gen3); +DEFINE_QBCM(bcm_sn9, "SN9", false, 2, &srvc_aggre1_noc, &qnm_aggre1_noc); +DEFINE_QBCM(bcm_sn11, "SN11", false, 2, &srvc_aggre2_noc, &qnm_aggre2_noc); +DEFINE_QBCM(bcm_sn12, "SN12", false, 2, &qnm_gladiator_sodv, &xm_gic); +DEFINE_QBCM(bcm_sn14, "SN14", false, 1, &qnm_pcie_anoc); +DEFINE_QBCM(bcm_sn15, "SN15", false, 1, &qnm_memnoc); + +static struct qcom_icc_node *rsc_hlos_nodes[] = { + [MASTER_APPSS_PROC] = &acm_l3, + [MASTER_TCU_0] = &acm_tcu, + [MASTER_LLCC] = &llcc_mc, + [MASTER_GNOC_CFG] = &pm_gnoc_cfg, + [MASTER_A1NOC_CFG] = &qhm_a1noc_cfg, + [MASTER_A2NOC_CFG] = &qhm_a2noc_cfg, + [MASTER_CNOC_DC_NOC] = &qhm_cnoc, + [MASTER_MEM_NOC_CFG] = &qhm_memnoc_cfg, + [MASTER_CNOC_MNOC_CFG] = &qhm_mnoc_cfg, + [MASTER_QDSS_BAM] = &qhm_qdss_bam, + [MASTER_BLSP_1] = &qhm_qup1, + [MASTER_BLSP_2] = &qhm_qup2, + [MASTER_SNOC_CFG] = &qhm_snoc_cfg, + [MASTER_SPDM] = &qhm_spdm, + [MASTER_TIC] = &qhm_tic, + [MASTER_TSIF] = &qhm_tsif, + [MASTER_A1NOC_SNOC] = &qnm_aggre1_noc, + [MASTER_A2NOC_SNOC] = &qnm_aggre2_noc, + [MASTER_GNOC_MEM_NOC] = &qnm_apps, + [MASTER_CNOC_A2NOC] = &qnm_cnoc, + [MASTER_GNOC_SNOC] = &qnm_gladiator_sodv, + [MASTER_MEM_NOC_SNOC] = &qnm_memnoc, + [MASTER_MNOC_HF_MEM_NOC] = &qnm_mnoc_hf, + [MASTER_MNOC_SF_MEM_NOC] = &qnm_mnoc_sf, + [MASTER_ANOC_PCIE_SNOC] = &qnm_pcie_anoc, + [MASTER_SNOC_CNOC] = &qnm_snoc, + [MASTER_SNOC_GC_MEM_NOC] = &qnm_snoc_gc, + [MASTER_SNOC_SF_MEM_NOC] = &qnm_snoc_sf, + [MASTER_CAMNOC_HF0] = &qxm_camnoc_hf0, + [MASTER_CAMNOC_HF0_UNCOMP] = &qxm_camnoc_hf0_uncomp, + [MASTER_CAMNOC_HF1] = &qxm_camnoc_hf1, + [MASTER_CAMNOC_HF1_UNCOMP] = &qxm_camnoc_hf1_uncomp, + [MASTER_CAMNOC_SF] = &qxm_camnoc_sf, + [MASTER_CAMNOC_SF_UNCOMP] = &qxm_camnoc_sf_uncomp, + [MASTER_CRYPTO] = &qxm_crypto, + [MASTER_GFX3D] = &qxm_gpu, + [MASTER_IPA] = &qxm_ipa, + [MASTER_MDP0] = &qxm_mdp0, + [MASTER_MDP1] = &qxm_mdp1, + [MASTER_PIMEM] = &qxm_pimem, + [MASTER_ROTATOR] = &qxm_rot, + [MASTER_VIDEO_P0] = &qxm_venus0, + [MASTER_VIDEO_P1] = &qxm_venus1, + [MASTER_VIDEO_PROC] = &qxm_venus_arm9, + [MASTER_GIC] = &xm_gic, + [MASTER_PCIE_1] = &xm_pcie3_1, + [MASTER_PCIE_0] = &xm_pcie_0, + [MASTER_QDSS_DAP] = &xm_qdss_dap, + [MASTER_QDSS_ETR] = &xm_qdss_etr, + [MASTER_SDCC_2] = &xm_sdc2, + [MASTER_SDCC_4] = &xm_sdc4, + [MASTER_UFS_CARD] = &xm_ufs_card, + [MASTER_UFS_MEM] = &xm_ufs_mem, + [MASTER_USB3_0] = &xm_usb3_0, + [MASTER_USB3_1] = &xm_usb3_1, + [SLAVE_EBI1] = &ebi, + [SLAVE_A1NOC_CFG] = &qhs_a1_noc_cfg, + [SLAVE_A2NOC_CFG] = &qhs_a2_noc_cfg, + [SLAVE_AOP] = &qhs_aop, + [SLAVE_AOSS] = &qhs_aoss, + [SLAVE_APPSS] = &qhs_apss, + [SLAVE_CAMERA_CFG] = &qhs_camera_cfg, + [SLAVE_CLK_CTL] = &qhs_clk_ctl, + [SLAVE_CDSP_CFG] = &qhs_compute_dsp_cfg, + [SLAVE_RBCPR_CX_CFG] = &qhs_cpr_cx, + [SLAVE_CRYPTO_0_CFG] = &qhs_crypto0_cfg, + [SLAVE_DCC_CFG] = &qhs_dcc_cfg, + [SLAVE_CNOC_DDRSS] = &qhs_ddrss_cfg, + [SLAVE_DISPLAY_CFG] = &qhs_display_cfg, + [SLAVE_GLM] = &qhs_glm, + [SLAVE_GFX3D_CFG] = &qhs_gpuss_cfg, + [SLAVE_IMEM_CFG] = &qhs_imem_cfg, + [SLAVE_IPA_CFG] = &qhs_ipa, + [SLAVE_LLCC_CFG] = &qhs_llcc, + [SLAVE_MSS_PROC_MS_MPU_CFG] = &qhs_mdsp_ms_mpu_cfg, + [SLAVE_MEM_NOC_CFG] = &qhs_memnoc, + [SLAVE_CNOC_MNOC_CFG] = &qhs_mnoc_cfg, + [SLAVE_PCIE_0_CFG] = &qhs_pcie0_cfg, + [SLAVE_PCIE_1_CFG] = &qhs_pcie_gen3_cfg, + [SLAVE_PDM] = &qhs_pdm, + [SLAVE_SOUTH_PHY_CFG] = &qhs_phy_refgen_south, + [SLAVE_PIMEM_CFG] = &qhs_pimem_cfg, + [SLAVE_PRNG] = &qhs_prng, + [SLAVE_QDSS_CFG] = &qhs_qdss_cfg, + [SLAVE_BLSP_2] = &qhs_qupv3_north, + [SLAVE_BLSP_1] = &qhs_qupv3_south, + [SLAVE_SDCC_2] = &qhs_sdc2, + [SLAVE_SDCC_4] = &qhs_sdc4, + [SLAVE_SNOC_CFG] = &qhs_snoc_cfg, + [SLAVE_SPDM_WRAPPER] = &qhs_spdm, + [SLAVE_SPSS_CFG] = &qhs_spss_cfg, + [SLAVE_TCSR] = &qhs_tcsr, + [SLAVE_TLMM_NORTH] = &qhs_tlmm_north, + [SLAVE_TLMM_SOUTH] = &qhs_tlmm_south, + [SLAVE_TSIF] = &qhs_tsif, + [SLAVE_UFS_CARD_CFG] = &qhs_ufs_card_cfg, + [SLAVE_UFS_MEM_CFG] = &qhs_ufs_mem_cfg, + [SLAVE_USB3_0] = &qhs_usb3_0, + [SLAVE_USB3_1] = &qhs_usb3_1, + [SLAVE_VENUS_CFG] = &qhs_venus_cfg, + [SLAVE_VSENSE_CTRL_CFG] = &qhs_vsense_ctrl_cfg, + [SLAVE_MNOC_SF_MEM_NOC] = &qns2_mem_noc, + [SLAVE_A1NOC_SNOC] = &qns_a1noc_snoc, + [SLAVE_A2NOC_SNOC] = &qns_a2noc_snoc, + [SLAVE_MEM_NOC_GNOC] = &qns_apps_io, + [SLAVE_CAMNOC_UNCOMP] = &qns_camnoc_uncomp, + [SLAVE_SNOC_CNOC] = &qns_cnoc, + [SLAVE_CNOC_A2NOC] = &qns_cnoc_a2noc, + [SLAVE_GNOC_SNOC] = &qns_gladiator_sodv, + [SLAVE_GNOC_MEM_NOC] = &qns_gnoc_memnoc, + [SLAVE_LLCC] = &qns_llcc, + [SLAVE_MNOC_HF_MEM_NOC] = &qns_mem_noc_hf, + [SLAVE_SNOC_MEM_NOC_GC] = &qns_memnoc_gc, + [SLAVE_SNOC_MEM_NOC_SF] = &qns_memnoc_sf, + [SLAVE_MEM_NOC_SNOC] = &qns_memnoc_snoc, + [SLAVE_ANOC_PCIE_A1NOC_SNOC] = &qns_pcie_a1noc_snoc, + [SLAVE_ANOC_PCIE_SNOC] = &qns_pcie_snoc, + [SLAVE_IMEM] = &qxs_imem, + [SLAVE_PCIE_0] = &qxs_pcie, + [SLAVE_PCIE_1] = &qxs_pcie_gen3, + [SLAVE_PIMEM] = &qxs_pimem, + [SLAVE_SERVICE_A1NOC] = &srvc_aggre1_noc, + [SLAVE_SERVICE_A2NOC] = &srvc_aggre2_noc, + [SLAVE_SERVICE_CNOC] = &srvc_cnoc, + [SLAVE_SERVICE_GNOC] = &srvc_gnoc, + [SLAVE_SERVICE_MEM_NOC] = &srvc_memnoc, + [SLAVE_SERVICE_MNOC] = &srvc_mnoc, + [SLAVE_SERVICE_SNOC] = &srvc_snoc, + [SLAVE_QDSS_STM] = &xs_qdss_stm, + [SLAVE_TCU] = &xs_sys_tcu_cfg, +}; + +static struct qcom_icc_bcm *rsc_hlos_bcms[] = { + &bcm_acv, + &bcm_mc0, + &bcm_sh0, + &bcm_mm0, + &bcm_sh1, + &bcm_mm1, + &bcm_sh2, + &bcm_mm2, + &bcm_sh3, + &bcm_mm3, + &bcm_sh5, + &bcm_sn0, + &bcm_ce0, + &bcm_cn0, + &bcm_qup0, + &bcm_sn1, + &bcm_sn2, + &bcm_sn3, + &bcm_sn4, + &bcm_sn5, + &bcm_sn6, + &bcm_sn7, + &bcm_sn8, + &bcm_sn9, + &bcm_sn11, + &bcm_sn12, + &bcm_sn14, + &bcm_sn15, +}; + +static struct qcom_icc_desc sdm845_rsc_hlos = { + .nodes = rsc_hlos_nodes, + .num_nodes = ARRAY_SIZE(rsc_hlos_nodes), + .bcms = rsc_hlos_bcms, + .num_bcms = ARRAY_SIZE(rsc_hlos_bcms), +}; + +static int qcom_icc_bcm_init(struct qcom_icc_bcm *bcm, struct device *dev) +{ + struct qcom_icc_node *qn; + const struct bcm_db *data; + size_t data_count; + int i; + + bcm->addr = cmd_db_read_addr(bcm->name); + if (!bcm->addr) { + dev_err(dev, "%s could not find RPMh address\n", + bcm->name); + return -EINVAL; + } + + data = cmd_db_read_aux_data(bcm->name, &data_count); + if (IS_ERR(data)) { + dev_err(dev, "%s command db read error (%ld)\n", + bcm->name, PTR_ERR(data)); + return PTR_ERR(data); + } + if (!data_count) { + dev_err(dev, "%s command db missing or partial aux data\n", + bcm->name); + return -EINVAL; + } + + bcm->aux_data.unit = le32_to_cpu(data->unit); + bcm->aux_data.width = le16_to_cpu(data->width); + bcm->aux_data.vcd = data->vcd; + bcm->aux_data.reserved = data->reserved; + + /* + * Link Qnodes to their respective BCMs + */ + for (i = 0; i < bcm->num_nodes; i++) { + qn = bcm->nodes[i]; + qn->bcms[qn->num_bcms] = bcm; + qn->num_bcms++; + } + + return 0; +} + +inline void tcs_cmd_gen(struct tcs_cmd *cmd, u64 vote_x, u64 vote_y, + u32 addr, bool commit) +{ + bool valid = true; + + if (!cmd) + return; + + if (vote_x == 0 && vote_y == 0) + valid = false; + + if (vote_x > BCM_TCS_CMD_VOTE_MASK) + vote_x = BCM_TCS_CMD_VOTE_MASK; + + if (vote_y > BCM_TCS_CMD_VOTE_MASK) + vote_y = BCM_TCS_CMD_VOTE_MASK; + + cmd->addr = addr; + cmd->data = BCM_TCS_CMD(commit, valid, vote_x, vote_y); + + /* + * Set the wait for completion flag on command that need to be completed + * before the next command. + */ + if (commit) + cmd->wait = true; +} + +static void tcs_list_gen(struct list_head *bcm_list, + struct tcs_cmd tcs_list[SDM845_MAX_VCD], + int n[SDM845_MAX_VCD]) +{ + struct qcom_icc_bcm *bcm; + bool commit; + size_t idx = 0, batch = 0, cur_vcd_size = 0; + + memset(n, 0, sizeof(int) * SDM845_MAX_VCD); + + list_for_each_entry(bcm, bcm_list, list) { + commit = false; + cur_vcd_size++; + if ((list_is_last(&bcm->list, bcm_list)) || + bcm->aux_data.vcd != list_next_entry(bcm, list)->aux_data.vcd) { + commit = true; + cur_vcd_size = 0; + } + tcs_cmd_gen(&tcs_list[idx], bcm->vote_x, bcm->vote_y, + bcm->addr, commit); + idx++; + n[batch]++; + /* + * Batch the BCMs in such a way that we do not split them in + * multiple payloads when they are under the same VCD. This is + * to ensure that every BCM is committed since we only set the + * commit bit on the last BCM request of every VCD. + */ + if (n[batch] >= MAX_RPMH_PAYLOAD) { + if (!commit) { + n[batch] -= cur_vcd_size; + n[batch + 1] = cur_vcd_size; + } + batch++; + } + } +} + +static void bcm_aggregate(struct qcom_icc_bcm *bcm) +{ + size_t i; + u64 agg_avg = 0; + u64 agg_peak = 0; + u64 temp; + + for (i = 0; i < bcm->num_nodes; i++) { + temp = bcm->nodes[i]->sum_avg * bcm->aux_data.width; + do_div(temp, bcm->nodes[i]->buswidth * bcm->nodes[i]->channels); + agg_avg = max(agg_avg, temp); + + temp = bcm->nodes[i]->max_peak * bcm->aux_data.width; + do_div(temp, bcm->nodes[i]->buswidth); + agg_peak = max(agg_peak, temp); + } + + temp = agg_avg * 1000ULL; + do_div(temp, bcm->aux_data.unit); + bcm->vote_x = temp; + + temp = agg_peak * 1000ULL; + do_div(temp, bcm->aux_data.unit); + bcm->vote_y = temp; + + if (bcm->keepalive && bcm->vote_x == 0 && bcm->vote_y == 0) { + bcm->vote_x = 1; + bcm->vote_y = 1; + } + + bcm->dirty = false; +} + +static int qcom_icc_aggregate(struct icc_node *node, u32 avg_bw, + u32 peak_bw, u32 *agg_avg, u32 *agg_peak) +{ + size_t i; + struct qcom_icc_node *qn; + + qn = node->data; + + *agg_avg += avg_bw; + *agg_peak = max_t(u32, *agg_peak, peak_bw); + + qn->sum_avg = *agg_avg; + qn->max_peak = *agg_peak; + + for (i = 0; i < qn->num_bcms; i++) + qn->bcms[i]->dirty = true; + + return 0; +} + +static int qcom_icc_set(struct icc_node *src, struct icc_node *dst) +{ + struct qcom_icc_provider *qp; + struct icc_node *node; + struct tcs_cmd cmds[SDM845_MAX_BCMS]; + struct list_head commit_list; + int commit_idx[SDM845_MAX_VCD]; + int ret = 0, i; + + if (!src) + node = dst; + else + node = src; + + qp = to_qcom_provider(node->provider); + + INIT_LIST_HEAD(&commit_list); + + for (i = 0; i < qp->num_bcms; i++) { + if (qp->bcms[i]->dirty) { + bcm_aggregate(qp->bcms[i]); + list_add_tail(&qp->bcms[i]->list, &commit_list); + } + } + + /* + * Construct the command list based on a pre ordered list of BCMs + * based on VCD. + */ + tcs_list_gen(&commit_list, cmds, commit_idx); + + if (!commit_idx[0]) + return ret; + + ret = rpmh_invalidate(qp->dev); + if (ret) { + pr_err("Error invalidating RPMH client (%d)\n", ret); + return ret; + } + + ret = rpmh_write_batch(qp->dev, RPMH_ACTIVE_ONLY_STATE, + cmds, commit_idx); + if (ret) { + pr_err("Error sending AMC RPMH requests (%d)\n", ret); + return ret; + } + + return ret; +} + +static int cmp_vcd(const void *_l, const void *_r) +{ + const struct qcom_icc_bcm **l = (const struct qcom_icc_bcm **)_l; + const struct qcom_icc_bcm **r = (const struct qcom_icc_bcm **)_r; + + if (l[0]->aux_data.vcd < r[0]->aux_data.vcd) + return -1; + else if (l[0]->aux_data.vcd == r[0]->aux_data.vcd) + return 0; + else + return 1; +} + +static int qnoc_probe(struct platform_device *pdev) +{ + const struct qcom_icc_desc *desc; + struct icc_onecell_data *data; + struct icc_provider *provider; + struct qcom_icc_node **qnodes; + struct qcom_icc_provider *qp; + struct icc_node *node; + size_t num_nodes, i; + int ret; + + desc = of_device_get_match_data(&pdev->dev); + if (!desc) + return -EINVAL; + + qnodes = desc->nodes; + num_nodes = desc->num_nodes; + + qp = devm_kzalloc(&pdev->dev, sizeof(*qp), GFP_KERNEL); + if (!qp) + return -ENOMEM; + + data = devm_kcalloc(&pdev->dev, num_nodes, sizeof(*node), GFP_KERNEL); + if (!data) + return -ENOMEM; + + provider = &qp->provider; + provider->dev = &pdev->dev; + provider->set = qcom_icc_set; + provider->aggregate = qcom_icc_aggregate; + provider->xlate = of_icc_xlate_onecell; + INIT_LIST_HEAD(&provider->nodes); + provider->data = data; + + qp->dev = &pdev->dev; + qp->bcms = desc->bcms; + qp->num_bcms = desc->num_bcms; + + ret = icc_provider_add(provider); + if (ret) { + dev_err(&pdev->dev, "error adding interconnect provider\n"); + return ret; + } + + for (i = 0; i < num_nodes; i++) { + size_t j; + + node = icc_node_create(qnodes[i]->id); + if (IS_ERR(node)) { + ret = PTR_ERR(node); + goto err; + } + + node->name = qnodes[i]->name; + node->data = qnodes[i]; + icc_node_add(node, provider); + + dev_dbg(&pdev->dev, "registered node %p %s %d\n", node, + qnodes[i]->name, node->id); + + /* populate links */ + for (j = 0; j < qnodes[i]->num_links; j++) + icc_link_create(node, qnodes[i]->links[j]); + + data->nodes[i] = node; + } + data->num_nodes = num_nodes; + + for (i = 0; i < qp->num_bcms; i++) + qcom_icc_bcm_init(qp->bcms[i], &pdev->dev); + + /* + * Pre sort the BCMs based on VCD for ease of generating a command list + * that groups the BCMs with the same VCD together. VCDs are numbered + * with lowest being the most expensive time wise, ensuring that + * those commands are being sent the earliest in the queue. + */ + sort(qp->bcms, qp->num_bcms, sizeof(*qp->bcms), cmp_vcd, NULL); + + platform_set_drvdata(pdev, qp); + + dev_dbg(&pdev->dev, "Registered SDM845 ICC\n"); + + return ret; +err: + list_for_each_entry(node, &provider->nodes, node_list) { + icc_node_del(node); + icc_node_destroy(node->id); + } + + icc_provider_del(provider); + return ret; +} + +static int qnoc_remove(struct platform_device *pdev) +{ + struct qcom_icc_provider *qp = platform_get_drvdata(pdev); + struct icc_provider *provider = &qp->provider; + struct icc_node *n; + + list_for_each_entry(n, &provider->nodes, node_list) { + icc_node_del(n); + icc_node_destroy(n->id); + } + + return icc_provider_del(provider); +} + +static const struct of_device_id qnoc_of_match[] = { + { .compatible = "qcom,sdm845-rsc-hlos", .data = &sdm845_rsc_hlos }, + { }, +}; +MODULE_DEVICE_TABLE(of, qnoc_of_match); + +static struct platform_driver qnoc_driver = { + .probe = qnoc_probe, + .remove = qnoc_remove, + .driver = { + .name = "qnoc-sdm845", + .of_match_table = qnoc_of_match, + }, +}; +module_platform_driver(qnoc_driver); + +MODULE_AUTHOR("David Dai "); +MODULE_DESCRIPTION("Qualcomm sdm845 NoC driver"); +MODULE_LICENSE("GPL v2"); diff --git a/include/dt-bindings/interconnect/qcom,sdm845.h b/include/dt-bindings/interconnect/qcom,sdm845.h new file mode 100644 index 000000000000..7b2393be7361 --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,sdm845.h @@ -0,0 +1,143 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Qualcomm SDM845 interconnect IDs + * + * Copyright (c) 2018, Linaro Ltd. + * Author: Georgi Djakov + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SDM845_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_SDM845_H + +#define MASTER_A1NOC_CFG 0 +#define MASTER_BLSP_1 1 +#define MASTER_TSIF 2 +#define MASTER_SDCC_2 3 +#define MASTER_SDCC_4 4 +#define MASTER_UFS_CARD 5 +#define MASTER_UFS_MEM 6 +#define MASTER_PCIE_0 7 +#define MASTER_A2NOC_CFG 8 +#define MASTER_QDSS_BAM 9 +#define MASTER_BLSP_2 10 +#define MASTER_CNOC_A2NOC 11 +#define MASTER_CRYPTO 12 +#define MASTER_IPA 13 +#define MASTER_PCIE_1 14 +#define MASTER_QDSS_ETR 15 +#define MASTER_USB3_0 16 +#define MASTER_USB3_1 17 +#define MASTER_CAMNOC_HF0_UNCOMP 18 +#define MASTER_CAMNOC_HF1_UNCOMP 19 +#define MASTER_CAMNOC_SF_UNCOMP 20 +#define MASTER_SPDM 21 +#define MASTER_TIC 22 +#define MASTER_SNOC_CNOC 23 +#define MASTER_QDSS_DAP 24 +#define MASTER_CNOC_DC_NOC 25 +#define MASTER_APPSS_PROC 26 +#define MASTER_GNOC_CFG 27 +#define MASTER_LLCC 28 +#define MASTER_TCU_0 29 +#define MASTER_MEM_NOC_CFG 30 +#define MASTER_GNOC_MEM_NOC 31 +#define MASTER_MNOC_HF_MEM_NOC 32 +#define MASTER_MNOC_SF_MEM_NOC 33 +#define MASTER_SNOC_GC_MEM_NOC 34 +#define MASTER_SNOC_SF_MEM_NOC 35 +#define MASTER_GFX3D 36 +#define MASTER_CNOC_MNOC_CFG 37 +#define MASTER_CAMNOC_HF0 38 +#define MASTER_CAMNOC_HF1 39 +#define MASTER_CAMNOC_SF 40 +#define MASTER_MDP0 41 +#define MASTER_MDP1 42 +#define MASTER_ROTATOR 43 +#define MASTER_VIDEO_P0 44 +#define MASTER_VIDEO_P1 45 +#define MASTER_VIDEO_PROC 46 +#define MASTER_SNOC_CFG 47 +#define MASTER_A1NOC_SNOC 48 +#define MASTER_A2NOC_SNOC 49 +#define MASTER_GNOC_SNOC 50 +#define MASTER_MEM_NOC_SNOC 51 +#define MASTER_ANOC_PCIE_SNOC 52 +#define MASTER_PIMEM 53 +#define MASTER_GIC 54 +#define SLAVE_A1NOC_SNOC 55 +#define SLAVE_SERVICE_A1NOC 56 +#define SLAVE_ANOC_PCIE_A1NOC_SNOC 57 +#define SLAVE_A2NOC_SNOC 58 +#define SLAVE_ANOC_PCIE_SNOC 59 +#define SLAVE_SERVICE_A2NOC 60 +#define SLAVE_CAMNOC_UNCOMP 61 +#define SLAVE_A1NOC_CFG 62 +#define SLAVE_A2NOC_CFG 63 +#define SLAVE_AOP 64 +#define SLAVE_AOSS 65 +#define SLAVE_CAMERA_CFG 66 +#define SLAVE_CLK_CTL 67 +#define SLAVE_CDSP_CFG 68 +#define SLAVE_RBCPR_CX_CFG 69 +#define SLAVE_CRYPTO_0_CFG 70 +#define SLAVE_DCC_CFG 71 +#define SLAVE_CNOC_DDRSS 72 +#define SLAVE_DISPLAY_CFG 73 +#define SLAVE_GLM 74 +#define SLAVE_GFX3D_CFG 75 +#define SLAVE_IMEM_CFG 76 +#define SLAVE_IPA_CFG 77 +#define SLAVE_CNOC_MNOC_CFG 78 +#define SLAVE_PCIE_0_CFG 79 +#define SLAVE_PCIE_1_CFG 80 +#define SLAVE_PDM 81 +#define SLAVE_SOUTH_PHY_CFG 82 +#define SLAVE_PIMEM_CFG 83 +#define SLAVE_PRNG 84 +#define SLAVE_QDSS_CFG 85 +#define SLAVE_BLSP_2 86 +#define SLAVE_BLSP_1 87 +#define SLAVE_SDCC_2 88 +#define SLAVE_SDCC_4 89 +#define SLAVE_SNOC_CFG 90 +#define SLAVE_SPDM_WRAPPER 91 +#define SLAVE_SPSS_CFG 92 +#define SLAVE_TCSR 93 +#define SLAVE_TLMM_NORTH 94 +#define SLAVE_TLMM_SOUTH 95 +#define SLAVE_TSIF 96 +#define SLAVE_UFS_CARD_CFG 97 +#define SLAVE_UFS_MEM_CFG 98 +#define SLAVE_USB3_0 99 +#define SLAVE_USB3_1 100 +#define SLAVE_VENUS_CFG 101 +#define SLAVE_VSENSE_CTRL_CFG 102 +#define SLAVE_CNOC_A2NOC 103 +#define SLAVE_SERVICE_CNOC 104 +#define SLAVE_LLCC_CFG 105 +#define SLAVE_MEM_NOC_CFG 106 +#define SLAVE_GNOC_SNOC 107 +#define SLAVE_GNOC_MEM_NOC 108 +#define SLAVE_SERVICE_GNOC 109 +#define SLAVE_EBI1 110 +#define SLAVE_MSS_PROC_MS_MPU_CFG 111 +#define SLAVE_MEM_NOC_GNOC 112 +#define SLAVE_LLCC 113 +#define SLAVE_MEM_NOC_SNOC 114 +#define SLAVE_SERVICE_MEM_NOC 115 +#define SLAVE_MNOC_SF_MEM_NOC 116 +#define SLAVE_MNOC_HF_MEM_NOC 117 +#define SLAVE_SERVICE_MNOC 118 +#define SLAVE_APPSS 119 +#define SLAVE_SNOC_CNOC 120 +#define SLAVE_SNOC_MEM_NOC_GC 121 +#define SLAVE_SNOC_MEM_NOC_SF 122 +#define SLAVE_IMEM 123 +#define SLAVE_PCIE_0 124 +#define SLAVE_PCIE_1 125 +#define SLAVE_PIMEM 126 +#define SLAVE_SERVICE_SNOC 127 +#define SLAVE_QDSS_STM 128 +#define SLAVE_TCU 129 + +#endif -- cgit v1.2.3 From 79bf0cbd86ac4887a7ac897fec8f011a763e23ba Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 16 Jan 2019 11:25:20 -0700 Subject: iomap: introduce io{read|write}64_{lo_hi|hi_lo} In order to provide non-atomic functions for io{read|write}64 that will use readq and writeq when appropriate. We define a number of variants of these functions in the generic iomap that will do non-atomic operations on pio but atomic operations on mmio. These functions are only defined if readq and writeq are defined. If they are not, then the wrappers that always use non-atomic operations from include/linux/io-64-nonatomic*.h will be used. Signed-off-by: Logan Gunthorpe Reviewed-by: Andy Shevchenko Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Arnd Bergmann Cc: Suresh Warrier Cc: Nicholas Piggin Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/io.h | 2 + include/asm-generic/iomap.h | 22 +++++++ lib/iomap.c | 132 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 156 insertions(+) (limited to 'include') diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 7f19fbd3ba55..4b73847e9b95 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -783,8 +783,10 @@ extern void __iounmap_at(void *ea, unsigned long size); #define mmio_read16be(addr) readw_be(addr) #define mmio_read32be(addr) readl_be(addr) +#define mmio_read64be(addr) readq_be(addr) #define mmio_write16be(val, addr) writew_be(val, addr) #define mmio_write32be(val, addr) writel_be(val, addr) +#define mmio_write64be(val, addr) writeq_be(val, addr) #define mmio_insb(addr, dst, count) readsb(addr, dst, count) #define mmio_insw(addr, dst, count) readsw(addr, dst, count) #define mmio_insl(addr, dst, count) readsl(addr, dst, count) diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 5b63b94ef6b5..a008f504a2d0 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -36,6 +36,17 @@ extern u64 ioread64(void __iomem *); extern u64 ioread64be(void __iomem *); #endif +#ifdef readq +#define ioread64_lo_hi ioread64_lo_hi +#define ioread64_hi_lo ioread64_hi_lo +#define ioread64be_lo_hi ioread64be_lo_hi +#define ioread64be_hi_lo ioread64be_hi_lo +extern u64 ioread64_lo_hi(void __iomem *addr); +extern u64 ioread64_hi_lo(void __iomem *addr); +extern u64 ioread64be_lo_hi(void __iomem *addr); +extern u64 ioread64be_hi_lo(void __iomem *addr); +#endif + extern void iowrite8(u8, void __iomem *); extern void iowrite16(u16, void __iomem *); extern void iowrite16be(u16, void __iomem *); @@ -46,6 +57,17 @@ extern void iowrite64(u64, void __iomem *); extern void iowrite64be(u64, void __iomem *); #endif +#ifdef writeq +#define iowrite64_lo_hi iowrite64_lo_hi +#define iowrite64_hi_lo iowrite64_hi_lo +#define iowrite64be_lo_hi iowrite64be_lo_hi +#define iowrite64be_hi_lo iowrite64be_hi_lo +extern void iowrite64_lo_hi(u64 val, void __iomem *addr); +extern void iowrite64_hi_lo(u64 val, void __iomem *addr); +extern void iowrite64be_lo_hi(u64 val, void __iomem *addr); +extern void iowrite64be_hi_lo(u64 val, void __iomem *addr); +#endif + /* * "string" versions of the above. Note that they * use native byte ordering for the accesses (on diff --git a/lib/iomap.c b/lib/iomap.c index 2c293b22569f..e909ab71e995 100644 --- a/lib/iomap.c +++ b/lib/iomap.c @@ -67,6 +67,7 @@ static void bad_io_access(unsigned long port, const char *access) #ifndef mmio_read16be #define mmio_read16be(addr) swab16(readw(addr)) #define mmio_read32be(addr) swab32(readl(addr)) +#define mmio_read64be(addr) swab64(readq(addr)) #endif unsigned int ioread8(void __iomem *addr) @@ -100,6 +101,80 @@ EXPORT_SYMBOL(ioread16be); EXPORT_SYMBOL(ioread32); EXPORT_SYMBOL(ioread32be); +#ifdef readq +static u64 pio_read64_lo_hi(unsigned long port) +{ + u64 lo, hi; + + lo = inl(port); + hi = inl(port + sizeof(u32)); + + return lo | (hi << 32); +} + +static u64 pio_read64_hi_lo(unsigned long port) +{ + u64 lo, hi; + + hi = inl(port + sizeof(u32)); + lo = inl(port); + + return lo | (hi << 32); +} + +static u64 pio_read64be_lo_hi(unsigned long port) +{ + u64 lo, hi; + + lo = pio_read32be(port + sizeof(u32)); + hi = pio_read32be(port); + + return lo | (hi << 32); +} + +static u64 pio_read64be_hi_lo(unsigned long port) +{ + u64 lo, hi; + + hi = pio_read32be(port); + lo = pio_read32be(port + sizeof(u32)); + + return lo | (hi << 32); +} + +u64 ioread64_lo_hi(void __iomem *addr) +{ + IO_COND(addr, return pio_read64_lo_hi(port), return readq(addr)); + return 0xffffffffffffffffULL; +} + +u64 ioread64_hi_lo(void __iomem *addr) +{ + IO_COND(addr, return pio_read64_hi_lo(port), return readq(addr)); + return 0xffffffffffffffffULL; +} + +u64 ioread64be_lo_hi(void __iomem *addr) +{ + IO_COND(addr, return pio_read64be_lo_hi(port), + return mmio_read64be(addr)); + return 0xffffffffffffffffULL; +} + +u64 ioread64be_hi_lo(void __iomem *addr) +{ + IO_COND(addr, return pio_read64be_hi_lo(port), + return mmio_read64be(addr)); + return 0xffffffffffffffffULL; +} + +EXPORT_SYMBOL(ioread64_lo_hi); +EXPORT_SYMBOL(ioread64_hi_lo); +EXPORT_SYMBOL(ioread64be_lo_hi); +EXPORT_SYMBOL(ioread64be_hi_lo); + +#endif /* readq */ + #ifndef pio_write16be #define pio_write16be(val,port) outw(swab16(val),port) #define pio_write32be(val,port) outl(swab32(val),port) @@ -108,6 +183,7 @@ EXPORT_SYMBOL(ioread32be); #ifndef mmio_write16be #define mmio_write16be(val,port) writew(swab16(val),port) #define mmio_write32be(val,port) writel(swab32(val),port) +#define mmio_write64be(val,port) writeq(swab64(val),port) #endif void iowrite8(u8 val, void __iomem *addr) @@ -136,6 +212,62 @@ EXPORT_SYMBOL(iowrite16be); EXPORT_SYMBOL(iowrite32); EXPORT_SYMBOL(iowrite32be); +#ifdef writeq +static void pio_write64_lo_hi(u64 val, unsigned long port) +{ + outl(val, port); + outl(val >> 32, port + sizeof(u32)); +} + +static void pio_write64_hi_lo(u64 val, unsigned long port) +{ + outl(val >> 32, port + sizeof(u32)); + outl(val, port); +} + +static void pio_write64be_lo_hi(u64 val, unsigned long port) +{ + pio_write32be(val, port + sizeof(u32)); + pio_write32be(val >> 32, port); +} + +static void pio_write64be_hi_lo(u64 val, unsigned long port) +{ + pio_write32be(val >> 32, port); + pio_write32be(val, port + sizeof(u32)); +} + +void iowrite64_lo_hi(u64 val, void __iomem *addr) +{ + IO_COND(addr, pio_write64_lo_hi(val, port), + writeq(val, addr)); +} + +void iowrite64_hi_lo(u64 val, void __iomem *addr) +{ + IO_COND(addr, pio_write64_hi_lo(val, port), + writeq(val, addr)); +} + +void iowrite64be_lo_hi(u64 val, void __iomem *addr) +{ + IO_COND(addr, pio_write64be_lo_hi(val, port), + mmio_write64be(val, addr)); +} + +void iowrite64be_hi_lo(u64 val, void __iomem *addr) +{ + IO_COND(addr, pio_write64be_hi_lo(val, port), + mmio_write64be(val, addr)); +} + +EXPORT_SYMBOL(iowrite64_lo_hi); +EXPORT_SYMBOL(iowrite64_hi_lo); +EXPORT_SYMBOL(iowrite64be_lo_hi); +EXPORT_SYMBOL(iowrite64be_hi_lo); + +#endif /* readq */ + /* * These are the "repeat MMIO read/write" functions. * Note the "__raw" accesses, since we don't want to -- cgit v1.2.3 From c81d64d3dc1f2decf8f3a9354416b7496b5c389b Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 16 Jan 2019 11:25:21 -0700 Subject: io-64-nonatomic: add io{read|write}64[be]{_lo_hi|_hi_lo} macros This patch adds generic io{read|write}64[be]{_lo_hi|_hi_lo} macros if they are not already defined by the architecture. (As they are provided by the generic iomap library). The patch also points io{read|write}64[be] to the variant specified by the header name. This is because new drivers are encouraged to use ioreadXX, et al instead of readX[1], et al -- and mixing ioreadXX with readq is pretty ugly. [1] LDD3: section 9.4.2 Signed-off-by: Logan Gunthorpe Reviewed-by: Andy Shevchenko Cc: Christoph Hellwig Cc: Arnd Bergmann Cc: Alan Cox Cc: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- include/linux/io-64-nonatomic-hi-lo.h | 64 +++++++++++++++++++++++++++++++++++ include/linux/io-64-nonatomic-lo-hi.h | 64 +++++++++++++++++++++++++++++++++++ 2 files changed, 128 insertions(+) (limited to 'include') diff --git a/include/linux/io-64-nonatomic-hi-lo.h b/include/linux/io-64-nonatomic-hi-lo.h index 862d786a904f..ae21b72cce85 100644 --- a/include/linux/io-64-nonatomic-hi-lo.h +++ b/include/linux/io-64-nonatomic-hi-lo.h @@ -55,4 +55,68 @@ static inline void hi_lo_writeq_relaxed(__u64 val, volatile void __iomem *addr) #define writeq_relaxed hi_lo_writeq_relaxed #endif +#ifndef ioread64_hi_lo +#define ioread64_hi_lo ioread64_hi_lo +static inline u64 ioread64_hi_lo(void __iomem *addr) +{ + u32 low, high; + + high = ioread32(addr + sizeof(u32)); + low = ioread32(addr); + + return low + ((u64)high << 32); +} +#endif + +#ifndef iowrite64_hi_lo +#define iowrite64_hi_lo iowrite64_hi_lo +static inline void iowrite64_hi_lo(u64 val, void __iomem *addr) +{ + iowrite32(val >> 32, addr + sizeof(u32)); + iowrite32(val, addr); +} +#endif + +#ifndef ioread64be_hi_lo +#define ioread64be_hi_lo ioread64be_hi_lo +static inline u64 ioread64be_hi_lo(void __iomem *addr) +{ + u32 low, high; + + high = ioread32be(addr); + low = ioread32be(addr + sizeof(u32)); + + return low + ((u64)high << 32); +} +#endif + +#ifndef iowrite64be_hi_lo +#define iowrite64be_hi_lo iowrite64be_hi_lo +static inline void iowrite64be_hi_lo(u64 val, void __iomem *addr) +{ + iowrite32be(val >> 32, addr); + iowrite32be(val, addr + sizeof(u32)); +} +#endif + +#ifndef ioread64 +#define ioread64_is_nonatomic +#define ioread64 ioread64_hi_lo +#endif + +#ifndef iowrite64 +#define iowrite64_is_nonatomic +#define iowrite64 iowrite64_hi_lo +#endif + +#ifndef ioread64be +#define ioread64be_is_nonatomic +#define ioread64be ioread64be_hi_lo +#endif + +#ifndef iowrite64be +#define iowrite64be_is_nonatomic +#define iowrite64be iowrite64be_hi_lo +#endif + #endif /* _LINUX_IO_64_NONATOMIC_HI_LO_H_ */ diff --git a/include/linux/io-64-nonatomic-lo-hi.h b/include/linux/io-64-nonatomic-lo-hi.h index d042e7bb5adb..faaa842dbdb9 100644 --- a/include/linux/io-64-nonatomic-lo-hi.h +++ b/include/linux/io-64-nonatomic-lo-hi.h @@ -55,4 +55,68 @@ static inline void lo_hi_writeq_relaxed(__u64 val, volatile void __iomem *addr) #define writeq_relaxed lo_hi_writeq_relaxed #endif +#ifndef ioread64_lo_hi +#define ioread64_lo_hi ioread64_lo_hi +static inline u64 ioread64_lo_hi(void __iomem *addr) +{ + u32 low, high; + + low = ioread32(addr); + high = ioread32(addr + sizeof(u32)); + + return low + ((u64)high << 32); +} +#endif + +#ifndef iowrite64_lo_hi +#define iowrite64_lo_hi iowrite64_lo_hi +static inline void iowrite64_lo_hi(u64 val, void __iomem *addr) +{ + iowrite32(val, addr); + iowrite32(val >> 32, addr + sizeof(u32)); +} +#endif + +#ifndef ioread64be_lo_hi +#define ioread64be_lo_hi ioread64be_lo_hi +static inline u64 ioread64be_lo_hi(void __iomem *addr) +{ + u32 low, high; + + low = ioread32be(addr + sizeof(u32)); + high = ioread32be(addr); + + return low + ((u64)high << 32); +} +#endif + +#ifndef iowrite64be_lo_hi +#define iowrite64be_lo_hi iowrite64be_lo_hi +static inline void iowrite64be_lo_hi(u64 val, void __iomem *addr) +{ + iowrite32be(val, addr + sizeof(u32)); + iowrite32be(val >> 32, addr); +} +#endif + +#ifndef ioread64 +#define ioread64_is_nonatomic +#define ioread64 ioread64_lo_hi +#endif + +#ifndef iowrite64 +#define iowrite64_is_nonatomic +#define iowrite64 iowrite64_lo_hi +#endif + +#ifndef ioread64be +#define ioread64be_is_nonatomic +#define ioread64be ioread64be_lo_hi +#endif + +#ifndef iowrite64be +#define iowrite64be_is_nonatomic +#define iowrite64be iowrite64be_lo_hi +#endif + #endif /* _LINUX_IO_64_NONATOMIC_LO_HI_H_ */ -- cgit v1.2.3 From ec74136ded792deed80780a2f8baf3521eeb72f9 Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Mon, 14 Jan 2019 09:10:21 -0800 Subject: binder: create node flag to request sender's security context To allow servers to verify client identity, allow a node flag to be set that causes the sender's security context to be delivered with the transaction. The BR_TRANSACTION command is extended in BR_TRANSACTION_SEC_CTX to contain a pointer to the security context string. Signed-off-by: Todd Kjos Reviewed-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 106 ++++++++++++++++++++++++++++-------- include/uapi/linux/android/binder.h | 19 +++++++ 2 files changed, 102 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index cdfc87629efb..5f6ef5e63b91 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -329,6 +329,8 @@ struct binder_error { * (invariant after initialized) * @min_priority: minimum scheduling priority * (invariant after initialized) + * @txn_security_ctx: require sender's security context + * (invariant after initialized) * @async_todo: list of async work items * (protected by @proc->inner_lock) * @@ -365,6 +367,7 @@ struct binder_node { * invariant after initialization */ u8 accept_fds:1; + u8 txn_security_ctx:1; u8 min_priority; }; bool has_async_transaction; @@ -615,6 +618,7 @@ struct binder_transaction { long saved_priority; kuid_t sender_euid; struct list_head fd_fixups; + binder_uintptr_t security_ctx; /** * @lock: protects @from, @to_proc, and @to_thread * @@ -1152,6 +1156,7 @@ static struct binder_node *binder_init_node_ilocked( node->work.type = BINDER_WORK_NODE; node->min_priority = flags & FLAT_BINDER_FLAG_PRIORITY_MASK; node->accept_fds = !!(flags & FLAT_BINDER_FLAG_ACCEPTS_FDS); + node->txn_security_ctx = !!(flags & FLAT_BINDER_FLAG_TXN_SECURITY_CTX); spin_lock_init(&node->lock); INIT_LIST_HEAD(&node->work.entry); INIT_LIST_HEAD(&node->async_todo); @@ -2778,6 +2783,8 @@ static void binder_transaction(struct binder_proc *proc, binder_size_t last_fixup_min_off = 0; struct binder_context *context = proc->context; int t_debug_id = atomic_inc_return(&binder_last_id); + char *secctx = NULL; + u32 secctx_sz = 0; e = binder_transaction_log_add(&binder_transaction_log); e->debug_id = t_debug_id; @@ -3020,6 +3027,20 @@ static void binder_transaction(struct binder_proc *proc, t->flags = tr->flags; t->priority = task_nice(current); + if (target_node && target_node->txn_security_ctx) { + u32 secid; + + security_task_getsecid(proc->tsk, &secid); + ret = security_secid_to_secctx(secid, &secctx, &secctx_sz); + if (ret) { + return_error = BR_FAILED_REPLY; + return_error_param = ret; + return_error_line = __LINE__; + goto err_get_secctx_failed; + } + extra_buffers_size += ALIGN(secctx_sz, sizeof(u64)); + } + trace_binder_transaction(reply, t, target_node); t->buffer = binder_alloc_new_buf(&target_proc->alloc, tr->data_size, @@ -3036,6 +3057,19 @@ static void binder_transaction(struct binder_proc *proc, t->buffer = NULL; goto err_binder_alloc_buf_failed; } + if (secctx) { + size_t buf_offset = ALIGN(tr->data_size, sizeof(void *)) + + ALIGN(tr->offsets_size, sizeof(void *)) + + ALIGN(extra_buffers_size, sizeof(void *)) - + ALIGN(secctx_sz, sizeof(u64)); + char *kptr = t->buffer->data + buf_offset; + + t->security_ctx = (uintptr_t)kptr + + binder_alloc_get_user_buffer_offset(&target_proc->alloc); + memcpy(kptr, secctx, secctx_sz); + security_release_secctx(secctx, secctx_sz); + secctx = NULL; + } t->buffer->debug_id = t->debug_id; t->buffer->transaction = t; t->buffer->target_node = target_node; @@ -3305,6 +3339,9 @@ err_copy_data_failed: t->buffer->transaction = NULL; binder_alloc_free_buf(&target_proc->alloc, t->buffer); err_binder_alloc_buf_failed: + if (secctx) + security_release_secctx(secctx, secctx_sz); +err_get_secctx_failed: kfree(tcomplete); binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE); err_alloc_tcomplete_failed: @@ -4036,11 +4073,13 @@ retry: while (1) { uint32_t cmd; - struct binder_transaction_data tr; + struct binder_transaction_data_secctx tr; + struct binder_transaction_data *trd = &tr.transaction_data; struct binder_work *w = NULL; struct list_head *list = NULL; struct binder_transaction *t = NULL; struct binder_thread *t_from; + size_t trsize = sizeof(*trd); binder_inner_proc_lock(proc); if (!binder_worklist_empty_ilocked(&thread->todo)) @@ -4240,8 +4279,8 @@ retry: if (t->buffer->target_node) { struct binder_node *target_node = t->buffer->target_node; - tr.target.ptr = target_node->ptr; - tr.cookie = target_node->cookie; + trd->target.ptr = target_node->ptr; + trd->cookie = target_node->cookie; t->saved_priority = task_nice(current); if (t->priority < target_node->min_priority && !(t->flags & TF_ONE_WAY)) @@ -4251,22 +4290,23 @@ retry: binder_set_nice(target_node->min_priority); cmd = BR_TRANSACTION; } else { - tr.target.ptr = 0; - tr.cookie = 0; + trd->target.ptr = 0; + trd->cookie = 0; cmd = BR_REPLY; } - tr.code = t->code; - tr.flags = t->flags; - tr.sender_euid = from_kuid(current_user_ns(), t->sender_euid); + trd->code = t->code; + trd->flags = t->flags; + trd->sender_euid = from_kuid(current_user_ns(), t->sender_euid); t_from = binder_get_txn_from(t); if (t_from) { struct task_struct *sender = t_from->proc->tsk; - tr.sender_pid = task_tgid_nr_ns(sender, - task_active_pid_ns(current)); + trd->sender_pid = + task_tgid_nr_ns(sender, + task_active_pid_ns(current)); } else { - tr.sender_pid = 0; + trd->sender_pid = 0; } ret = binder_apply_fd_fixups(t); @@ -4297,15 +4337,20 @@ retry: } continue; } - tr.data_size = t->buffer->data_size; - tr.offsets_size = t->buffer->offsets_size; - tr.data.ptr.buffer = (binder_uintptr_t) + trd->data_size = t->buffer->data_size; + trd->offsets_size = t->buffer->offsets_size; + trd->data.ptr.buffer = (binder_uintptr_t) ((uintptr_t)t->buffer->data + binder_alloc_get_user_buffer_offset(&proc->alloc)); - tr.data.ptr.offsets = tr.data.ptr.buffer + + trd->data.ptr.offsets = trd->data.ptr.buffer + ALIGN(t->buffer->data_size, sizeof(void *)); + tr.secctx = t->security_ctx; + if (t->security_ctx) { + cmd = BR_TRANSACTION_SEC_CTX; + trsize = sizeof(tr); + } if (put_user(cmd, (uint32_t __user *)ptr)) { if (t_from) binder_thread_dec_tmpref(t_from); @@ -4316,7 +4361,7 @@ retry: return -EFAULT; } ptr += sizeof(uint32_t); - if (copy_to_user(ptr, &tr, sizeof(tr))) { + if (copy_to_user(ptr, &tr, trsize)) { if (t_from) binder_thread_dec_tmpref(t_from); @@ -4325,7 +4370,7 @@ retry: return -EFAULT; } - ptr += sizeof(tr); + ptr += trsize; trace_binder_transaction_received(t); binder_stat_br(proc, thread, cmd); @@ -4333,16 +4378,18 @@ retry: "%d:%d %s %d %d:%d, cmd %d size %zd-%zd ptr %016llx-%016llx\n", proc->pid, thread->pid, (cmd == BR_TRANSACTION) ? "BR_TRANSACTION" : - "BR_REPLY", + (cmd == BR_TRANSACTION_SEC_CTX) ? + "BR_TRANSACTION_SEC_CTX" : "BR_REPLY", t->debug_id, t_from ? t_from->proc->pid : 0, t_from ? t_from->pid : 0, cmd, t->buffer->data_size, t->buffer->offsets_size, - (u64)tr.data.ptr.buffer, (u64)tr.data.ptr.offsets); + (u64)trd->data.ptr.buffer, + (u64)trd->data.ptr.offsets); if (t_from) binder_thread_dec_tmpref(t_from); t->buffer->allow_user_free = 1; - if (cmd == BR_TRANSACTION && !(t->flags & TF_ONE_WAY)) { + if (cmd != BR_REPLY && !(t->flags & TF_ONE_WAY)) { binder_inner_proc_lock(thread->proc); t->to_parent = thread->transaction_stack; t->to_thread = thread; @@ -4690,7 +4737,8 @@ out: return ret; } -static int binder_ioctl_set_ctx_mgr(struct file *filp) +static int binder_ioctl_set_ctx_mgr(struct file *filp, + struct flat_binder_object *fbo) { int ret = 0; struct binder_proc *proc = filp->private_data; @@ -4719,7 +4767,7 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp) } else { context->binder_context_mgr_uid = curr_euid; } - new_node = binder_new_node(proc, NULL); + new_node = binder_new_node(proc, fbo); if (!new_node) { ret = -ENOMEM; goto out; @@ -4842,8 +4890,20 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) binder_inner_proc_unlock(proc); break; } + case BINDER_SET_CONTEXT_MGR_EXT: { + struct flat_binder_object fbo; + + if (copy_from_user(&fbo, ubuf, sizeof(fbo))) { + ret = -EINVAL; + goto err; + } + ret = binder_ioctl_set_ctx_mgr(filp, &fbo); + if (ret) + goto err; + break; + } case BINDER_SET_CONTEXT_MGR: - ret = binder_ioctl_set_ctx_mgr(filp); + ret = binder_ioctl_set_ctx_mgr(filp, NULL); if (ret) goto err; break; diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index b9ba520f7e4b..2832134e5397 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -41,6 +41,14 @@ enum { enum { FLAT_BINDER_FLAG_PRIORITY_MASK = 0xff, FLAT_BINDER_FLAG_ACCEPTS_FDS = 0x100, + + /** + * @FLAT_BINDER_FLAG_TXN_SECURITY_CTX: request security contexts + * + * Only when set, causes senders to include their security + * context + */ + FLAT_BINDER_FLAG_TXN_SECURITY_CTX = 0x1000, }; #ifdef BINDER_IPC_32BIT @@ -218,6 +226,7 @@ struct binder_node_info_for_ref { #define BINDER_VERSION _IOWR('b', 9, struct binder_version) #define BINDER_GET_NODE_DEBUG_INFO _IOWR('b', 11, struct binder_node_debug_info) #define BINDER_GET_NODE_INFO_FOR_REF _IOWR('b', 12, struct binder_node_info_for_ref) +#define BINDER_SET_CONTEXT_MGR_EXT _IOW('b', 13, struct flat_binder_object) /* * NOTE: Two special error codes you should check for when calling @@ -276,6 +285,11 @@ struct binder_transaction_data { } data; }; +struct binder_transaction_data_secctx { + struct binder_transaction_data transaction_data; + binder_uintptr_t secctx; +}; + struct binder_transaction_data_sg { struct binder_transaction_data transaction_data; binder_size_t buffers_size; @@ -311,6 +325,11 @@ enum binder_driver_return_protocol { BR_OK = _IO('r', 1), /* No parameters! */ + BR_TRANSACTION_SEC_CTX = _IOR('r', 2, + struct binder_transaction_data_secctx), + /* + * binder_transaction_data_secctx: the received command. + */ BR_TRANSACTION = _IOR('r', 2, struct binder_transaction_data), BR_REPLY = _IOR('r', 3, struct binder_transaction_data), /* -- cgit v1.2.3 From 51c48b310183ab6ba5419edfc6a8de889cc04521 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Sat, 19 Jan 2019 11:35:04 -0600 Subject: PCI: Probe bridge window attributes once at enumeration-time pci_bridge_check_ranges() determines whether a bridge supports the optional I/O and prefetchable memory windows and sets the flag bits in the bridge resources. This *could* be done once during enumeration except that the resource allocation code completely clears the flag bits, e.g., in the pci_assign_unassigned_bridge_resources() path. The problem with pci_bridge_check_ranges() in the resource allocation path is that we may allocate resources after devices have been claimed by drivers, and pci_bridge_check_ranges() *changes* the window registers to determine whether they're writable. This may break concurrent accesses to devices behind the bridge. Add a new pci_read_bridge_windows() to determine whether a bridge supports the optional windows, call it once during enumeration, remember the results, and change pci_bridge_check_ranges() so it doesn't touch the bridge windows but sets the flag bits based on those remembered results. Link: https://lore.kernel.org/linux-pci/1506151482-113560-1-git-send-email-wangzhou1@hisilicon.com Link: https://lists.gnu.org/archive/html/qemu-devel/2018-12/msg02082.html Reported-by: Yandong Xu Tested-by: Yandong Xu Signed-off-by: Bjorn Helgaas Cc: Michael S. Tsirkin Cc: Sagi Grimberg Cc: Ofer Hayut Cc: Roy Shterman Cc: Keith Busch Cc: Zhou Wang --- drivers/pci/probe.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/setup-bus.c | 45 ++++-------------------------------------- include/linux/pci.h | 3 +++ 3 files changed, 59 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 257b9f6f2ebb..2ef8b954c65a 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -348,6 +348,57 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom) } } +static void pci_read_bridge_windows(struct pci_dev *bridge) +{ + u16 io; + u32 pmem, tmp; + + pci_read_config_word(bridge, PCI_IO_BASE, &io); + if (!io) { + pci_write_config_word(bridge, PCI_IO_BASE, 0xe0f0); + pci_read_config_word(bridge, PCI_IO_BASE, &io); + pci_write_config_word(bridge, PCI_IO_BASE, 0x0); + } + if (io) + bridge->io_window = 1; + + /* + * DECchip 21050 pass 2 errata: the bridge may miss an address + * disconnect boundary by one PCI data phase. Workaround: do not + * use prefetching on this device. + */ + if (bridge->vendor == PCI_VENDOR_ID_DEC && bridge->device == 0x0001) + return; + + pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem); + if (!pmem) { + pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, + 0xffe0fff0); + pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem); + pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, 0x0); + } + if (!pmem) + return; + + bridge->pref_window = 1; + + if ((pmem & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) { + + /* + * Bridge claims to have a 64-bit prefetchable memory + * window; verify that the upper bits are actually + * writable. + */ + pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &pmem); + pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32, + 0xffffffff); + pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &tmp); + pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32, pmem); + if (tmp) + bridge->pref_64_window = 1; + } +} + static void pci_read_bridge_io(struct pci_bus *child) { struct pci_dev *dev = child->self; @@ -1739,6 +1790,7 @@ int pci_setup_device(struct pci_dev *dev) pci_read_irq(dev); dev->transparent = ((dev->class & 0xff) == 1); pci_read_bases(dev, 2, PCI_ROM_ADDRESS1); + pci_read_bridge_windows(dev); set_pcie_hotplug_bridge(dev); pos = pci_find_capability(dev, PCI_CAP_ID_SSVID); if (pos) { diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index ed960436df5e..1941bb0a6c13 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -735,58 +735,21 @@ int pci_claim_bridge_resource(struct pci_dev *bridge, int i) base/limit registers must be read-only and read as 0. */ static void pci_bridge_check_ranges(struct pci_bus *bus) { - u16 io; - u32 pmem; struct pci_dev *bridge = bus->self; - struct resource *b_res; + struct resource *b_res = &bridge->resource[PCI_BRIDGE_RESOURCES]; - b_res = &bridge->resource[PCI_BRIDGE_RESOURCES]; b_res[1].flags |= IORESOURCE_MEM; - pci_read_config_word(bridge, PCI_IO_BASE, &io); - if (!io) { - pci_write_config_word(bridge, PCI_IO_BASE, 0xe0f0); - pci_read_config_word(bridge, PCI_IO_BASE, &io); - pci_write_config_word(bridge, PCI_IO_BASE, 0x0); - } - if (io) + if (bridge->io_window) b_res[0].flags |= IORESOURCE_IO; - /* DECchip 21050 pass 2 errata: the bridge may miss an address - disconnect boundary by one PCI data phase. - Workaround: do not use prefetching on this device. */ - if (bridge->vendor == PCI_VENDOR_ID_DEC && bridge->device == 0x0001) - return; - - pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem); - if (!pmem) { - pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, - 0xffe0fff0); - pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem); - pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, 0x0); - } - if (pmem) { + if (bridge->pref_window) { b_res[2].flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH; - if ((pmem & PCI_PREF_RANGE_TYPE_MASK) == - PCI_PREF_RANGE_TYPE_64) { + if (bridge->pref_64_window) { b_res[2].flags |= IORESOURCE_MEM_64; b_res[2].flags |= PCI_PREF_RANGE_TYPE_64; } } - - /* double check if bridge does support 64 bit pref */ - if (b_res[2].flags & IORESOURCE_MEM_64) { - u32 mem_base_hi, tmp; - pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, - &mem_base_hi); - pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32, - 0xffffffff); - pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &tmp); - if (!tmp) - b_res[2].flags &= ~IORESOURCE_MEM_64; - pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32, - mem_base_hi); - } } /* Helper function for sizing routines: find first available diff --git a/include/linux/pci.h b/include/linux/pci.h index 65f1d8c2f082..40b327b814aa 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -373,6 +373,9 @@ struct pci_dev { bool match_driver; /* Skip attaching driver */ unsigned int transparent:1; /* Subtractive decode bridge */ + unsigned int io_window:1; /* Bridge has I/O window */ + unsigned int pref_window:1; /* Bridge has pref mem window */ + unsigned int pref_64_window:1; /* Pref mem window is 64-bit */ unsigned int multifunction:1; /* Multi-function device */ unsigned int is_busmaster:1; /* Is busmaster */ -- cgit v1.2.3 From 856c395cfa63b94a1d8215182f0243c222f6f927 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 17 Jan 2019 23:27:11 -0800 Subject: net: introduce a knob to control whether to inherit devconf config There have been many people complaining about the inconsistent behaviors of IPv4 and IPv6 devconf when creating new network namespaces. Currently, for IPv4, we inherit all current settings from init_net, but for IPv6 we reset all setting to default. This patch introduces a new /proc file /proc/sys/net/core/devconf_inherit_init_net to control the behavior of whether to inhert sysctl current settings from init_net. This file itself is only available in init_net. As demonstrated below: Initial setup in init_net: # cat /proc/sys/net/ipv4/conf/all/rp_filter 2 # cat /proc/sys/net/ipv6/conf/all/accept_dad 1 Default value 0 (current behavior): # ip netns del test # ip netns add test # ip netns exec test cat /proc/sys/net/ipv4/conf/all/rp_filter 2 # ip netns exec test cat /proc/sys/net/ipv6/conf/all/accept_dad 0 Set to 1 (inherit from init_net): # echo 1 > /proc/sys/net/core/devconf_inherit_init_net # ip netns del test # ip netns add test # ip netns exec test cat /proc/sys/net/ipv4/conf/all/rp_filter 2 # ip netns exec test cat /proc/sys/net/ipv6/conf/all/accept_dad 1 Set to 2 (reset to default): # echo 2 > /proc/sys/net/core/devconf_inherit_init_net # ip netns del test # ip netns add test # ip netns exec test cat /proc/sys/net/ipv4/conf/all/rp_filter 0 # ip netns exec test cat /proc/sys/net/ipv6/conf/all/accept_dad 0 Set to a value out of range (invalid): # echo 3 > /proc/sys/net/core/devconf_inherit_init_net -bash: echo: write error: Invalid argument # echo -1 > /proc/sys/net/core/devconf_inherit_init_net -bash: echo: write error: Invalid argument Reported-by: Zhu Yanjun Reported-by: Tonghao Zhang Cc: Nicolas Dichtel Signed-off-by: Cong Wang Acked-by: Nicolas Dichtel Acked-by: Tonghao Zhang Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 14 ++++++++++++++ include/linux/netdevice.h | 1 + net/core/sysctl_net_core.c | 18 ++++++++++++++++++ net/ipv4/devinet.c | 43 ++++++++++++++++++++----------------------- net/ipv6/addrconf.c | 5 +++++ 5 files changed, 58 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 2793d4eac55f..bc0680706870 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -291,6 +291,20 @@ user space is responsible for creating them if needed. Default : 0 (for compatibility reasons) +devconf_inherit_init_net +---------------------------- + +Controls if a new network namespace should inherit all current +settings under /proc/sys/net/{ipv4,ipv6}/conf/{all,default}/. By +default, we keep the current behavior: for IPv4 we inherit all current +settings from init_net and for IPv6 we reset all settings to default. + +If set to 1, both IPv4 and IPv6 settings are forced to inherit from +current ones in init_net. If set to 2, both IPv4 and IPv6 settings are +forced to reset to their default values. + +Default : 0 (for compatibility reasons) + 2. /proc/sys/net/unix - Parameters for Unix domain sockets ------------------------------------------------------- diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a57b9a853aab..e675ef97a426 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -630,6 +630,7 @@ struct netdev_queue { } ____cacheline_aligned_in_smp; extern int sysctl_fb_tunnels_only_for_init_net; +extern int sysctl_devconf_inherit_init_net; static inline bool net_has_fallback_tunnels(const struct net *net) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index d67ec17f2cc8..84bf2861f45f 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -36,6 +36,15 @@ static int net_msg_warn; /* Unused, but still a sysctl */ int sysctl_fb_tunnels_only_for_init_net __read_mostly = 0; EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net); +/* 0 - Keep current behavior: + * IPv4: inherit all current settings from init_net + * IPv6: reset all settings to default + * 1 - Both inherit all current settings from init_net + * 2 - Both reset all settings to default + */ +int sysctl_devconf_inherit_init_net __read_mostly; +EXPORT_SYMBOL(sysctl_devconf_inherit_init_net); + #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -544,6 +553,15 @@ static struct ctl_table net_core_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "devconf_inherit_init_net", + .data = &sysctl_devconf_inherit_init_net, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, { } }; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cd027639df2f..cd9033245b98 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2591,32 +2591,32 @@ static __net_init int devinet_init_net(struct net *net) int err; struct ipv4_devconf *all, *dflt; #ifdef CONFIG_SYSCTL - struct ctl_table *tbl = ctl_forward_entry; + struct ctl_table *tbl; struct ctl_table_header *forw_hdr; #endif err = -ENOMEM; - all = &ipv4_devconf; - dflt = &ipv4_devconf_dflt; - - if (!net_eq(net, &init_net)) { - all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL); - if (!all) - goto err_alloc_all; + all = kmemdup(&ipv4_devconf, sizeof(ipv4_devconf), GFP_KERNEL); + if (!all) + goto err_alloc_all; - dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); - if (!dflt) - goto err_alloc_dflt; + dflt = kmemdup(&ipv4_devconf_dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); + if (!dflt) + goto err_alloc_dflt; #ifdef CONFIG_SYSCTL - tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL); - if (!tbl) - goto err_alloc_ctl; + tbl = kmemdup(ctl_forward_entry, sizeof(ctl_forward_entry), GFP_KERNEL); + if (!tbl) + goto err_alloc_ctl; - tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; - tbl[0].extra1 = all; - tbl[0].extra2 = net; + tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; + tbl[0].extra1 = all; + tbl[0].extra2 = net; #endif + + if (sysctl_devconf_inherit_init_net != 2 && !net_eq(net, &init_net)) { + memcpy(all, init_net.ipv4.devconf_all, sizeof(ipv4_devconf)); + memcpy(dflt, init_net.ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); } #ifdef CONFIG_SYSCTL @@ -2646,15 +2646,12 @@ err_reg_ctl: err_reg_dflt: __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: - if (tbl != ctl_forward_entry) - kfree(tbl); + kfree(tbl); err_alloc_ctl: #endif - if (dflt != &ipv4_devconf_dflt) - kfree(dflt); + kfree(dflt); err_alloc_dflt: - if (all != &ipv4_devconf) - kfree(all); + kfree(all); err_alloc_all: return err; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 57198b3c86da..48cd36311901 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6902,6 +6902,11 @@ static int __net_init addrconf_init_net(struct net *net) if (!dflt) goto err_alloc_dflt; + if (sysctl_devconf_inherit_init_net == 1 && !net_eq(net, &init_net)) { + memcpy(all, init_net.ipv6.devconf_all, sizeof(ipv6_devconf)); + memcpy(dflt, init_net.ipv6.devconf_dflt, sizeof(ipv6_devconf_dflt)); + } + /* these will be inherited by all namespaces */ dflt->autoconf = ipv6_defaults.autoconf; dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; -- cgit v1.2.3 From 9b56e0d0cc6353865c5bbc41a18161215063fd33 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 11 Jan 2019 15:22:30 +0100 Subject: MIPS: ath79: add helpers for setting clocks and expose the ref clock Preparation for transitioning the legacy clock setup code over to OF. Signed-off-by: Felix Fietkau Signed-off-by: John Crispin Acked-by: Rob Herring Signed-off-by: Paul Burton Cc: Ralf Baechle Cc: James Hogan Cc: Rob Herring Cc: Pengutronix Kernel Team Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: devicetree@vger.kernel.org --- arch/mips/ath79/clock.c | 128 ++++++++++++++++++---------------- include/dt-bindings/clock/ath79-clk.h | 3 +- 2 files changed, 68 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c index cf9158e3c2d9..50bc3b01a4c4 100644 --- a/arch/mips/ath79/clock.c +++ b/arch/mips/ath79/clock.c @@ -37,20 +37,46 @@ static struct clk_onecell_data clk_data = { .clk_num = ARRAY_SIZE(clks), }; -static struct clk *__init ath79_add_sys_clkdev( - const char *id, unsigned long rate) +static const char * const clk_names[ATH79_CLK_END] = { + [ATH79_CLK_CPU] = "cpu", + [ATH79_CLK_DDR] = "ddr", + [ATH79_CLK_AHB] = "ahb", + [ATH79_CLK_REF] = "ref", +}; + +static const char * __init ath79_clk_name(int type) { - struct clk *clk; - int err; + BUG_ON(type >= ARRAY_SIZE(clk_names) || !clk_names[type]); + return clk_names[type]; +} - clk = clk_register_fixed_rate(NULL, id, NULL, 0, rate); +static void __init __ath79_set_clk(int type, const char *name, struct clk *clk) +{ if (IS_ERR(clk)) - panic("failed to allocate %s clock structure", id); + panic("failed to allocate %s clock structure", clk_names[type]); - err = clk_register_clkdev(clk, id, NULL); - if (err) - panic("unable to register %s clock device", id); + clks[type] = clk; + clk_register_clkdev(clk, name, NULL); +} +static struct clk * __init ath79_set_clk(int type, unsigned long rate) +{ + const char *name = ath79_clk_name(type); + struct clk *clk; + + clk = clk_register_fixed_rate(NULL, name, NULL, 0, rate); + __ath79_set_clk(type, name, clk); + return clk; +} + +static struct clk * __init ath79_set_ff_clk(int type, const char *parent, + unsigned int mult, unsigned int div) +{ + const char *name = ath79_clk_name(type); + struct clk *clk; + + clk = clk_register_fixed_factor(NULL, name, parent, 0, mult, div); + __ath79_set_clk(type, name, clk); return clk; } @@ -80,27 +106,15 @@ static void __init ar71xx_clocks_init(void) div = (((pll >> AR71XX_AHB_DIV_SHIFT) & AR71XX_AHB_DIV_MASK) + 1) * 2; ahb_rate = cpu_rate / div; - ath79_add_sys_clkdev("ref", ref_rate); - clks[ATH79_CLK_CPU] = ath79_add_sys_clkdev("cpu", cpu_rate); - clks[ATH79_CLK_DDR] = ath79_add_sys_clkdev("ddr", ddr_rate); - clks[ATH79_CLK_AHB] = ath79_add_sys_clkdev("ahb", ahb_rate); + ath79_set_clk(ATH79_CLK_REF, ref_rate); + ath79_set_clk(ATH79_CLK_CPU, cpu_rate); + ath79_set_clk(ATH79_CLK_DDR, ddr_rate); + ath79_set_clk(ATH79_CLK_AHB, ahb_rate); clk_add_alias("wdt", NULL, "ahb", NULL); clk_add_alias("uart", NULL, "ahb", NULL); } -static struct clk * __init ath79_reg_ffclk(const char *name, - const char *parent_name, unsigned int mult, unsigned int div) -{ - struct clk *clk; - - clk = clk_register_fixed_factor(NULL, name, parent_name, 0, mult, div); - if (IS_ERR(clk)) - panic("failed to allocate %s clock structure", name); - - return clk; -} - static void __init ar724x_clk_init(struct clk *ref_clk, void __iomem *pll_base) { u32 pll; @@ -114,24 +128,19 @@ static void __init ar724x_clk_init(struct clk *ref_clk, void __iomem *pll_base) ddr_div = ((pll >> AR724X_DDR_DIV_SHIFT) & AR724X_DDR_DIV_MASK) + 1; ahb_div = (((pll >> AR724X_AHB_DIV_SHIFT) & AR724X_AHB_DIV_MASK) + 1) * 2; - clks[ATH79_CLK_CPU] = ath79_reg_ffclk("cpu", "ref", mult, div); - clks[ATH79_CLK_DDR] = ath79_reg_ffclk("ddr", "ref", mult, div * ddr_div); - clks[ATH79_CLK_AHB] = ath79_reg_ffclk("ahb", "ref", mult, div * ahb_div); + ath79_set_ff_clk(ATH79_CLK_CPU, "ref", mult, div); + ath79_set_ff_clk(ATH79_CLK_DDR, "ref", mult, div * ddr_div); + ath79_set_ff_clk(ATH79_CLK_AHB, "ref", mult, div * ahb_div); } static void __init ar724x_clocks_init(void) { struct clk *ref_clk; - ref_clk = ath79_add_sys_clkdev("ref", AR724X_BASE_FREQ); + ref_clk = ath79_set_clk(ATH79_CLK_REF, AR724X_BASE_FREQ); ar724x_clk_init(ref_clk, ath79_pll_base); - /* just make happy plat_time_init() from arch/mips/ath79/setup.c */ - clk_register_clkdev(clks[ATH79_CLK_CPU], "cpu", NULL); - clk_register_clkdev(clks[ATH79_CLK_DDR], "ddr", NULL); - clk_register_clkdev(clks[ATH79_CLK_AHB], "ahb", NULL); - clk_add_alias("wdt", NULL, "ahb", NULL); clk_add_alias("uart", NULL, "ahb", NULL); } @@ -186,12 +195,12 @@ static void __init ar9330_clk_init(struct clk *ref_clk, void __iomem *pll_base) AR933X_PLL_CLOCK_CTRL_AHB_DIV_MASK) + 1; } - clks[ATH79_CLK_CPU] = ath79_reg_ffclk("cpu", "ref", - ninit_mul, ref_div * out_div * cpu_div); - clks[ATH79_CLK_DDR] = ath79_reg_ffclk("ddr", "ref", - ninit_mul, ref_div * out_div * ddr_div); - clks[ATH79_CLK_AHB] = ath79_reg_ffclk("ahb", "ref", - ninit_mul, ref_div * out_div * ahb_div); + ath79_set_ff_clk(ATH79_CLK_CPU, "ref", ninit_mul, + ref_div * out_div * cpu_div); + ath79_set_ff_clk(ATH79_CLK_DDR, "ref", ninit_mul, + ref_div * out_div * ddr_div); + ath79_set_ff_clk(ATH79_CLK_AHB, "ref", ninit_mul, + ref_div * out_div * ahb_div); } static void __init ar933x_clocks_init(void) @@ -206,15 +215,10 @@ static void __init ar933x_clocks_init(void) else ref_rate = (25 * 1000 * 1000); - ref_clk = ath79_add_sys_clkdev("ref", ref_rate); + ref_clk = ath79_set_clk(ATH79_CLK_REF, ref_rate); ar9330_clk_init(ref_clk, ath79_pll_base); - /* just make happy plat_time_init() from arch/mips/ath79/setup.c */ - clk_register_clkdev(clks[ATH79_CLK_CPU], "cpu", NULL); - clk_register_clkdev(clks[ATH79_CLK_DDR], "ddr", NULL); - clk_register_clkdev(clks[ATH79_CLK_AHB], "ahb", NULL); - clk_add_alias("wdt", NULL, "ahb", NULL); clk_add_alias("uart", NULL, "ref", NULL); } @@ -344,10 +348,10 @@ static void __init ar934x_clocks_init(void) else ahb_rate = cpu_pll / (postdiv + 1); - ath79_add_sys_clkdev("ref", ref_rate); - clks[ATH79_CLK_CPU] = ath79_add_sys_clkdev("cpu", cpu_rate); - clks[ATH79_CLK_DDR] = ath79_add_sys_clkdev("ddr", ddr_rate); - clks[ATH79_CLK_AHB] = ath79_add_sys_clkdev("ahb", ahb_rate); + ath79_set_clk(ATH79_CLK_REF, ref_rate); + ath79_set_clk(ATH79_CLK_CPU, cpu_rate); + ath79_set_clk(ATH79_CLK_DDR, ddr_rate); + ath79_set_clk(ATH79_CLK_AHB, ahb_rate); clk_add_alias("wdt", NULL, "ref", NULL); clk_add_alias("uart", NULL, "ref", NULL); @@ -431,10 +435,10 @@ static void __init qca953x_clocks_init(void) else ahb_rate = cpu_pll / (postdiv + 1); - ath79_add_sys_clkdev("ref", ref_rate); - ath79_add_sys_clkdev("cpu", cpu_rate); - ath79_add_sys_clkdev("ddr", ddr_rate); - ath79_add_sys_clkdev("ahb", ahb_rate); + ath79_set_clk(ATH79_CLK_REF, ref_rate); + ath79_set_clk(ATH79_CLK_CPU, cpu_rate); + ath79_set_clk(ATH79_CLK_DDR, ddr_rate); + ath79_set_clk(ATH79_CLK_AHB, ahb_rate); clk_add_alias("wdt", NULL, "ref", NULL); clk_add_alias("uart", NULL, "ref", NULL); @@ -516,10 +520,10 @@ static void __init qca955x_clocks_init(void) else ahb_rate = cpu_pll / (postdiv + 1); - ath79_add_sys_clkdev("ref", ref_rate); - clks[ATH79_CLK_CPU] = ath79_add_sys_clkdev("cpu", cpu_rate); - clks[ATH79_CLK_DDR] = ath79_add_sys_clkdev("ddr", ddr_rate); - clks[ATH79_CLK_AHB] = ath79_add_sys_clkdev("ahb", ahb_rate); + ath79_set_clk(ATH79_CLK_REF, ref_rate); + ath79_set_clk(ATH79_CLK_CPU, cpu_rate); + ath79_set_clk(ATH79_CLK_DDR, ddr_rate); + ath79_set_clk(ATH79_CLK_AHB, ahb_rate); clk_add_alias("wdt", NULL, "ref", NULL); clk_add_alias("uart", NULL, "ref", NULL); @@ -620,10 +624,10 @@ static void __init qca956x_clocks_init(void) else ahb_rate = cpu_pll / (postdiv + 1); - ath79_add_sys_clkdev("ref", ref_rate); - ath79_add_sys_clkdev("cpu", cpu_rate); - ath79_add_sys_clkdev("ddr", ddr_rate); - ath79_add_sys_clkdev("ahb", ahb_rate); + ath79_set_clk(ATH79_CLK_REF, ref_rate); + ath79_set_clk(ATH79_CLK_CPU, cpu_rate); + ath79_set_clk(ATH79_CLK_DDR, ddr_rate); + ath79_set_clk(ATH79_CLK_AHB, ahb_rate); clk_add_alias("wdt", NULL, "ref", NULL); clk_add_alias("uart", NULL, "ref", NULL); diff --git a/include/dt-bindings/clock/ath79-clk.h b/include/dt-bindings/clock/ath79-clk.h index 27359ad83904..262d7c5eb248 100644 --- a/include/dt-bindings/clock/ath79-clk.h +++ b/include/dt-bindings/clock/ath79-clk.h @@ -13,7 +13,8 @@ #define ATH79_CLK_CPU 0 #define ATH79_CLK_DDR 1 #define ATH79_CLK_AHB 2 +#define ATH79_CLK_REF 3 -#define ATH79_CLK_END 3 +#define ATH79_CLK_END 4 #endif /* __DT_BINDINGS_ATH79_CLK_H */ -- cgit v1.2.3 From 6810ed320ec621b37c395be67125f1f456f1e55a Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 11 Jan 2019 15:22:35 +0100 Subject: MIPS: ath79: export switch MDIO reference clock On AR934x, the MDIO reference clock can be configured to a fixed 100 MHz clock. If that feature is not used, it defaults to the main reference clock, like on all other SoC. Signed-off-by: Felix Fietkau Signed-off-by: John Crispin Acked-by: Rob Herring Signed-off-by: Paul Burton Cc: Ralf Baechle Cc: James Hogan Cc: Rob Herring Cc: Pengutronix Kernel Team Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: devicetree@vger.kernel.org --- arch/mips/ath79/clock.c | 8 ++++++++ include/dt-bindings/clock/ath79-clk.h | 3 ++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c index c234818b30e1..699f00f096cb 100644 --- a/arch/mips/ath79/clock.c +++ b/arch/mips/ath79/clock.c @@ -42,6 +42,7 @@ static const char * const clk_names[ATH79_CLK_END] = { [ATH79_CLK_DDR] = "ddr", [ATH79_CLK_AHB] = "ahb", [ATH79_CLK_REF] = "ref", + [ATH79_CLK_MDIO] = "mdio", }; static const char * __init ath79_clk_name(int type) @@ -342,6 +343,10 @@ static void __init ar934x_clocks_init(void __iomem *pll_base) ath79_set_clk(ATH79_CLK_DDR, ddr_rate); ath79_set_clk(ATH79_CLK_AHB, ahb_rate); + clk_ctrl = __raw_readl(pll_base + AR934X_PLL_SWITCH_CLOCK_CONTROL_REG); + if (clk_ctrl & AR934X_PLL_SWITCH_CLOCK_CONTROL_MDIO_CLK_SEL) + ath79_set_clk(ATH79_CLK_MDIO, 100 * 1000 * 1000); + iounmap(dpll_base); } @@ -698,6 +703,9 @@ static void __init ath79_clocks_init_dt(struct device_node *np) else if (of_device_is_compatible(np, "qca,qca9560-pll")) qca956x_clocks_init(pll_base); + if (!clks[ATH79_CLK_MDIO]) + clks[ATH79_CLK_MDIO] = clks[ATH79_CLK_REF]; + if (of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data)) { pr_err("%pOF: could not register clk provider\n", np); goto err_iounmap; diff --git a/include/dt-bindings/clock/ath79-clk.h b/include/dt-bindings/clock/ath79-clk.h index 262d7c5eb248..dcc679a7ad85 100644 --- a/include/dt-bindings/clock/ath79-clk.h +++ b/include/dt-bindings/clock/ath79-clk.h @@ -14,7 +14,8 @@ #define ATH79_CLK_DDR 1 #define ATH79_CLK_AHB 2 #define ATH79_CLK_REF 3 +#define ATH79_CLK_MDIO 4 -#define ATH79_CLK_END 4 +#define ATH79_CLK_END 5 #endif /* __DT_BINDINGS_ATH79_CLK_H */ -- cgit v1.2.3 From 267c095aa2d9126059c1f5a65c660d5a71833e3f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 18 Jan 2019 14:30:22 +0200 Subject: bonding: add 3ad stats Count the following types of 3ad packets per slave: - rx/tx lacpdu - rx/tx marker - rx/tx marker response - rx illegal lacpdus (right now counted on wrong length) - rx unknown lacpdu type - rx unknown marker type The counters are using atomic64 since this is not fast path. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 28 +++++++++++++++++++++++++++- include/net/bond_3ad.h | 14 ++++++++++++++ 2 files changed, 41 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index d8ef2350c68d..d1d8cb6b8cdc 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -851,6 +851,8 @@ static int ad_lacpdu_send(struct port *port) if (!skb) return -ENOMEM; + atomic64_inc(&SLAVE_AD_INFO(slave)->stats.lacpdu_tx); + skb->dev = slave->dev; skb_reset_mac_header(skb); skb->network_header = skb->mac_header + ETH_HLEN; @@ -892,6 +894,15 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker) if (!skb) return -ENOMEM; + switch (marker->tlv_type) { + case AD_MARKER_INFORMATION_SUBTYPE: + atomic64_inc(&SLAVE_AD_INFO(slave)->stats.marker_tx); + break; + case AD_MARKER_RESPONSE_SUBTYPE: + atomic64_inc(&SLAVE_AD_INFO(slave)->stats.marker_resp_tx); + break; + } + skb_reserve(skb, 16); skb->dev = slave->dev; @@ -1086,6 +1097,9 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) */ last_state = port->sm_rx_state; + if (lacpdu) + atomic64_inc(&SLAVE_AD_INFO(port->slave)->stats.lacpdu_rx); + /* check if state machine should change state */ /* first, check if port was reinitialized */ @@ -1922,6 +1936,8 @@ static void ad_marker_info_received(struct bond_marker *marker_info, { struct bond_marker marker; + atomic64_inc(&SLAVE_AD_INFO(port->slave)->stats.marker_rx); + /* copy the received marker data to the response marker */ memcpy(&marker, marker_info, sizeof(struct bond_marker)); /* change the marker subtype to marker response */ @@ -1946,6 +1962,8 @@ static void ad_marker_info_received(struct bond_marker *marker_info, static void ad_marker_response_received(struct bond_marker *marker, struct port *port) { + atomic64_inc(&SLAVE_AD_INFO(port->slave)->stats.marker_resp_rx); + /* DO NOTHING, SINCE WE DECIDED NOT TO IMPLEMENT THIS FEATURE FOR NOW */ } @@ -2358,6 +2376,7 @@ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave) int ret = RX_HANDLER_ANOTHER; struct bond_marker *marker; struct port *port; + atomic64_t *stat; port = &(SLAVE_AD_INFO(slave)->port); if (!port->slave) { @@ -2397,7 +2416,12 @@ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave) default: netdev_dbg(slave->bond->dev, "Received an unknown Marker subtype on slot %d\n", port->actor_port_number); + stat = &SLAVE_AD_INFO(slave)->stats.marker_unknown_rx; + atomic64_inc(stat); } + break; + default: + atomic64_inc(&SLAVE_AD_INFO(slave)->stats.lacpdu_unknown_rx); } return ret; @@ -2635,8 +2659,10 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, return RX_HANDLER_ANOTHER; lacpdu = skb_header_pointer(skb, 0, sizeof(_lacpdu), &_lacpdu); - if (!lacpdu) + if (!lacpdu) { + atomic64_inc(&SLAVE_AD_INFO(slave)->stats.lacpdu_illegal_rx); return RX_HANDLER_ANOTHER; + } return bond_3ad_rx_indication(lacpdu, slave); } diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index fc3111515f5c..30e60dba1b2d 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -180,6 +180,19 @@ struct port; #pragma pack(8) #endif +struct bond_3ad_stats { + atomic64_t lacpdu_rx; + atomic64_t lacpdu_tx; + atomic64_t lacpdu_unknown_rx; + atomic64_t lacpdu_illegal_rx; + + atomic64_t marker_rx; + atomic64_t marker_tx; + atomic64_t marker_resp_rx; + atomic64_t marker_resp_tx; + atomic64_t marker_unknown_rx; +}; + /* aggregator structure(43.4.5 in the 802.3ad standard) */ typedef struct aggregator { struct mac_addr aggregator_mac_address; @@ -272,6 +285,7 @@ struct ad_bond_info { struct ad_slave_info { struct aggregator aggregator; /* 802.3ad aggregator structure */ struct port port; /* 802.3ad port structure */ + struct bond_3ad_stats stats; u16 id; }; -- cgit v1.2.3 From a258aeacd7f0dc10bb45caa7e92a3ea3ca1a76e9 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 18 Jan 2019 14:30:23 +0200 Subject: bonding: add support for xstats and export 3ad stats This patch adds support for extended statistics (xstats) call to the bonding. The first user would be the 3ad code which counts the following events: - LACPDU Rx/Tx - LACPDU unknown type Rx - LACPDU illegal Rx - Marker Rx/Tx - Marker response Rx/Tx - Marker unknown type Rx All of these are exported via netlink as separate attributes to be easily extensible as we plan to add more in the future. Similar to how the bridge and other xstats exports, the structure inside is: [ IFLA_STATS_LINK_XSTATS ] -> [ LINK_XSTATS_TYPE_BOND ] -> [ BOND_XSTATS_3AD ] -> [ 3ad stats attributes ] With this structure it's easy to add more stat types later. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 83 ++++++++++++++++++++++++++++++++++++++ drivers/net/bonding/bond_netlink.c | 71 ++++++++++++++++++++++++++++++++ include/net/bond_3ad.h | 3 ++ include/uapi/linux/if_bonding.h | 24 +++++++++++ include/uapi/linux/if_link.h | 1 + 5 files changed, 182 insertions(+) (limited to 'include') diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index d1d8cb6b8cdc..d30c21b34858 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -31,6 +31,7 @@ #include #include #include +#include /* General definitions */ #define AD_SHORT_TIMEOUT 1 @@ -2696,3 +2697,85 @@ void bond_3ad_update_lacp_rate(struct bonding *bond) } spin_unlock_bh(&bond->mode_lock); } + +void bond_3ad_stats_add(struct slave *slave, struct bond_3ad_stats *stats) +{ + struct bond_3ad_stats *rstats = &SLAVE_AD_INFO(slave)->stats; + u64 stat; + + atomic64_add(atomic64_read(&rstats->lacpdu_rx), &stats->lacpdu_rx); + atomic64_add(atomic64_read(&rstats->lacpdu_tx), &stats->lacpdu_tx); + + stat = atomic64_read(&rstats->lacpdu_unknown_rx); + atomic64_add(stat, &stats->lacpdu_unknown_rx); + stat = atomic64_read(&rstats->lacpdu_illegal_rx); + atomic64_add(stat, &stats->lacpdu_illegal_rx); + + atomic64_add(atomic64_read(&rstats->marker_rx), &stats->marker_rx); + atomic64_add(atomic64_read(&rstats->marker_tx), &stats->marker_tx); + + stat = atomic64_read(&rstats->marker_resp_rx); + atomic64_add(stat, &stats->marker_resp_rx); + stat = atomic64_read(&rstats->marker_resp_tx); + atomic64_add(stat, &stats->marker_resp_tx); + stat = atomic64_read(&rstats->marker_unknown_rx); + atomic64_add(stat, &stats->marker_unknown_rx); +} + +size_t bond_3ad_stats_size(void) +{ + return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */ + nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_TX */ + nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_UNKNOWN_RX */ + nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_ILLEGAL_RX */ + nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_MARKER_RX */ + nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_MARKER_TX */ + nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_MARKER_RESP_RX */ + nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_MARKER_RESP_TX */ + nla_total_size_64bit(sizeof(u64)); /* BOND_3AD_STAT_MARKER_UNKNOWN_RX */ +} + +int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats) +{ + u64 val; + + val = atomic64_read(&stats->lacpdu_rx); + if (nla_put_u64_64bit(skb, BOND_3AD_STAT_LACPDU_RX, val, + BOND_3AD_STAT_PAD)) + return -EMSGSIZE; + val = atomic64_read(&stats->lacpdu_tx); + if (nla_put_u64_64bit(skb, BOND_3AD_STAT_LACPDU_TX, val, + BOND_3AD_STAT_PAD)) + return -EMSGSIZE; + val = atomic64_read(&stats->lacpdu_unknown_rx); + if (nla_put_u64_64bit(skb, BOND_3AD_STAT_LACPDU_UNKNOWN_RX, val, + BOND_3AD_STAT_PAD)) + return -EMSGSIZE; + val = atomic64_read(&stats->lacpdu_illegal_rx); + if (nla_put_u64_64bit(skb, BOND_3AD_STAT_LACPDU_ILLEGAL_RX, val, + BOND_3AD_STAT_PAD)) + return -EMSGSIZE; + + val = atomic64_read(&stats->marker_rx); + if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_RX, val, + BOND_3AD_STAT_PAD)) + return -EMSGSIZE; + val = atomic64_read(&stats->marker_tx); + if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_TX, val, + BOND_3AD_STAT_PAD)) + return -EMSGSIZE; + val = atomic64_read(&stats->marker_resp_rx); + if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_RESP_RX, val, + BOND_3AD_STAT_PAD)) + return -EMSGSIZE; + val = atomic64_read(&stats->marker_resp_tx); + if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_RESP_TX, val, + BOND_3AD_STAT_PAD)) + return -EMSGSIZE; + val = atomic64_read(&stats->marker_unknown_rx); + if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_UNKNOWN_RX, val, + BOND_3AD_STAT_PAD)) + return -EMSGSIZE; + + return 0; +} diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 6b9ad8673218..d1338fbe1830 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -675,6 +675,75 @@ nla_put_failure: return -EMSGSIZE; } +static size_t bond_get_linkxstats_size(const struct net_device *dev, int attr) +{ + switch (attr) { + case IFLA_STATS_LINK_XSTATS: + case IFLA_STATS_LINK_XSTATS_SLAVE: + break; + default: + return 0; + } + + return bond_3ad_stats_size() + nla_total_size(0); +} + +static int bond_fill_linkxstats(struct sk_buff *skb, + const struct net_device *dev, + int *prividx, int attr) +{ + struct nlattr *nla __maybe_unused; + struct slave *slave = NULL; + struct nlattr *nest, *nest2; + struct bonding *bond; + + switch (attr) { + case IFLA_STATS_LINK_XSTATS: + bond = netdev_priv(dev); + break; + case IFLA_STATS_LINK_XSTATS_SLAVE: + slave = bond_slave_get_rtnl(dev); + if (!slave) + return 0; + bond = slave->bond; + break; + default: + return -EINVAL; + } + + nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BOND); + if (!nest) + return -EMSGSIZE; + if (BOND_MODE(bond) == BOND_MODE_8023AD) { + struct bond_3ad_stats stats; + struct list_head *iter; + + memset(&stats, 0, sizeof(stats)); + if (slave) { + bond_3ad_stats_add(slave, &stats); + } else { + bond_for_each_slave(bond, slave, iter) + bond_3ad_stats_add(slave, &stats); + } + + nest2 = nla_nest_start(skb, BOND_XSTATS_3AD); + if (!nest2) { + nla_nest_end(skb, nest); + return -EMSGSIZE; + } + + if (bond_3ad_stats_fill(skb, &stats)) { + nla_nest_cancel(skb, nest2); + nla_nest_end(skb, nest); + return -EMSGSIZE; + } + nla_nest_end(skb, nest2); + } + nla_nest_end(skb, nest); + + return 0; +} + struct rtnl_link_ops bond_link_ops __read_mostly = { .kind = "bond", .priv_size = sizeof(struct bonding), @@ -689,6 +758,8 @@ struct rtnl_link_ops bond_link_ops __read_mostly = { .get_num_tx_queues = bond_get_num_tx_queues, .get_num_rx_queues = bond_get_num_tx_queues, /* Use the same number as for TX queues */ + .fill_linkxstats = bond_fill_linkxstats, + .get_linkxstats_size = bond_get_linkxstats_size, .slave_maxtype = IFLA_BOND_SLAVE_MAX, .slave_policy = bond_slave_policy, .slave_changelink = bond_slave_changelink, diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 30e60dba1b2d..25aaf49d19be 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -321,5 +321,8 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); +void bond_3ad_stats_add(struct slave *slave, struct bond_3ad_stats *stats); +int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); +size_t bond_3ad_stats_size(void); #endif /* _NET_BOND_3AD_H */ diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h index 61a1bf6e865e..790585f0e61b 100644 --- a/include/uapi/linux/if_bonding.h +++ b/include/uapi/linux/if_bonding.h @@ -117,6 +117,30 @@ struct ad_info { __u8 partner_system[ETH_ALEN]; }; +/* Embedded inside LINK_XSTATS_TYPE_BOND */ +enum { + BOND_XSTATS_UNSPEC, + BOND_XSTATS_3AD, + __BOND_XSTATS_MAX +}; +#define BOND_XSTATS_MAX (__BOND_XSTATS_MAX - 1) + +/* Embedded inside BOND_XSTATS_3AD */ +enum { + BOND_3AD_STAT_LACPDU_RX, + BOND_3AD_STAT_LACPDU_TX, + BOND_3AD_STAT_LACPDU_UNKNOWN_RX, + BOND_3AD_STAT_LACPDU_ILLEGAL_RX, + BOND_3AD_STAT_MARKER_RX, + BOND_3AD_STAT_MARKER_TX, + BOND_3AD_STAT_MARKER_RESP_RX, + BOND_3AD_STAT_MARKER_RESP_TX, + BOND_3AD_STAT_MARKER_UNKNOWN_RX, + BOND_3AD_STAT_PAD, + __BOND_3AD_STAT_MAX +}; +#define BOND_3AD_STAT_MAX (__BOND_3AD_STAT_MAX - 1) + #endif /* _LINUX_IF_BONDING_H */ /* diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d6533828123a..5b225ff63b48 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -925,6 +925,7 @@ enum { enum { LINK_XSTATS_TYPE_UNSPEC, LINK_XSTATS_TYPE_BRIDGE, + LINK_XSTATS_TYPE_BOND, __LINK_XSTATS_TYPE_MAX }; #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) -- cgit v1.2.3 From 5b93ac542301026eff8954589cf59f801d03db3e Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Thu, 10 Jan 2019 09:32:02 +0530 Subject: OPP: Add support for parsing the 'opp-level' property Now that the OPP bindings are updated to include an optional 'opp-level' property, add support to parse it from device tree and store it as part of dev_pm_opp structure. Also add and export an helper 'dev_pm_opp_get_level()' that can be used to get the level value read from device tree when present. Reviewed-by: Stephen Boyd Acked-by: Viresh Kumar Signed-off-by: Rajendra Nayak Signed-off-by: Bjorn Andersson Signed-off-by: Andy Gross --- drivers/opp/core.c | 18 ++++++++++++++++++ drivers/opp/of.c | 2 ++ drivers/opp/opp.h | 2 ++ include/linux/pm_opp.h | 7 +++++++ 4 files changed, 29 insertions(+) (limited to 'include') diff --git a/drivers/opp/core.c b/drivers/opp/core.c index e5507add8f04..90b78a122be9 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -130,6 +130,24 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp) } EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq); +/** + * dev_pm_opp_get_level() - Gets the level corresponding to an available opp + * @opp: opp for which level value has to be returned for + * + * Return: level read from device tree corresponding to the opp, else + * return 0. + */ +unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp) +{ + if (IS_ERR_OR_NULL(opp) || !opp->available) { + pr_err("%s: Invalid parameters\n", __func__); + return 0; + } + + return opp->level; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_level); + /** * dev_pm_opp_is_turbo() - Returns if opp is turbo OPP or not * @opp: opp for which turbo mode is being verified diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 06f0f632ec47..1779f2c93291 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -594,6 +594,8 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, new_opp->rate = (unsigned long)rate; } + of_property_read_u32(np, "opp-level", &new_opp->level); + /* Check if the OPP supports hardware's hierarchy of versions or not */ if (!_opp_is_supported(dev, opp_table, np)) { dev_dbg(dev, "OPP not supported by hardware: %llu\n", rate); diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h index e24d81497375..4458175aa661 100644 --- a/drivers/opp/opp.h +++ b/drivers/opp/opp.h @@ -60,6 +60,7 @@ extern struct list_head opp_tables; * @suspend: true if suspend OPP * @pstate: Device's power domain's performance state. * @rate: Frequency in hertz + * @level: Performance level * @supplies: Power supplies voltage/current values * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's * frequency from any other OPP's frequency. @@ -80,6 +81,7 @@ struct dev_pm_opp { bool suspend; unsigned int pstate; unsigned long rate; + unsigned int level; struct dev_pm_opp_supply *supplies; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 0a2a88e5a383..473d2c7516f0 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -86,6 +86,8 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp); +unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp); + bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); @@ -157,6 +159,11 @@ static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp) return 0; } +static inline unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp) +{ + return 0; +} + static inline bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp) { return false; -- cgit v1.2.3 From c6e6eff4d48f8b7180f9f94f1615ffe345fd7e5c Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Thu, 10 Jan 2019 09:32:03 +0530 Subject: dt-bindings: power: Add qcom rpm power domain driver bindings Add DT bindings to describe the rpm/rpmh power domains found on Qualcomm Technologies, Inc. SoCs. These power domains communicate a performance state to RPM/RPMh, which then translates it into corresponding voltage on a PMIC rail. Reviewed-by: Ulf Hansson Reviewed-by: Stephen Boyd Reviewed-by: Rob Herring Signed-off-by: Rajendra Nayak Signed-off-by: Viresh Kumar Signed-off-by: Bjorn Andersson Signed-off-by: Andy Gross --- .../devicetree/bindings/power/qcom,rpmpd.txt | 145 +++++++++++++++++++++ include/dt-bindings/power/qcom-rpmpd.h | 39 ++++++ 2 files changed, 184 insertions(+) create mode 100644 Documentation/devicetree/bindings/power/qcom,rpmpd.txt create mode 100644 include/dt-bindings/power/qcom-rpmpd.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/power/qcom,rpmpd.txt b/Documentation/devicetree/bindings/power/qcom,rpmpd.txt new file mode 100644 index 000000000000..980e5413d18f --- /dev/null +++ b/Documentation/devicetree/bindings/power/qcom,rpmpd.txt @@ -0,0 +1,145 @@ +Qualcomm RPM/RPMh Power domains + +For RPM/RPMh Power domains, we communicate a performance state to RPM/RPMh +which then translates it into a corresponding voltage on a rail + +Required Properties: + - compatible: Should be one of the following + * qcom,msm8996-rpmpd: RPM Power domain for the msm8996 family of SoC + * qcom,sdm845-rpmhpd: RPMh Power domain for the sdm845 family of SoC + - #power-domain-cells: number of cells in Power domain specifier + must be 1. + - operating-points-v2: Phandle to the OPP table for the Power domain. + Refer to Documentation/devicetree/bindings/power/power_domain.txt + and Documentation/devicetree/bindings/opp/opp.txt for more details + +Refer to for the level values for +various OPPs for different platforms as well as Power domain indexes + +Example: rpmh power domain controller and OPP table + +#include + +opp-level values specified in the OPP tables for RPMh power domains +should use the RPMH_REGULATOR_LEVEL_* constants from + + + rpmhpd: power-controller { + compatible = "qcom,sdm845-rpmhpd"; + #power-domain-cells = <1>; + operating-points-v2 = <&rpmhpd_opp_table>; + + rpmhpd_opp_table: opp-table { + compatible = "operating-points-v2"; + + rpmhpd_opp_ret: opp1 { + opp-level = ; + }; + + rpmhpd_opp_min_svs: opp2 { + opp-level = ; + }; + + rpmhpd_opp_low_svs: opp3 { + opp-level = ; + }; + + rpmhpd_opp_svs: opp4 { + opp-level = ; + }; + + rpmhpd_opp_svs_l1: opp5 { + opp-level = ; + }; + + rpmhpd_opp_nom: opp6 { + opp-level = ; + }; + + rpmhpd_opp_nom_l1: opp7 { + opp-level = ; + }; + + rpmhpd_opp_nom_l2: opp8 { + opp-level = ; + }; + + rpmhpd_opp_turbo: opp9 { + opp-level = ; + }; + + rpmhpd_opp_turbo_l1: opp10 { + opp-level = ; + }; + }; + }; + +Example: rpm power domain controller and OPP table + + rpmpd: power-controller { + compatible = "qcom,msm8996-rpmpd"; + #power-domain-cells = <1>; + operating-points-v2 = <&rpmpd_opp_table>; + + rpmpd_opp_table: opp-table { + compatible = "operating-points-v2"; + + rpmpd_opp_low: opp1 { + opp-level = <1>; + }; + + rpmpd_opp_ret: opp2 { + opp-level = <2>; + }; + + rpmpd_opp_svs: opp3 { + opp-level = <3>; + }; + + rpmpd_opp_normal: opp4 { + opp-level = <4>; + }; + + rpmpd_opp_high: opp5 { + opp-level = <5>; + }; + + rpmpd_opp_turbo: opp6 { + opp-level = <6>; + }; + }; + }; + +Example: Client/Consumer device using OPP table + + leaky-device0@12350000 { + compatible = "foo,i-leak-current"; + reg = <0x12350000 0x1000>; + power-domains = <&rpmhpd SDM845_MX>; + operating-points-v2 = <&leaky_opp_table>; + }; + + + leaky_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp1 { + opp-hz = /bits/ 64 <144000>; + required-opps = <&rpmhpd_opp_low>; + }; + + opp2 { + opp-hz = /bits/ 64 <400000>; + required-opps = <&rpmhpd_opp_ret>; + }; + + opp3 { + opp-hz = /bits/ 64 <20000000>; + required-opps = <&rpmpd_opp_svs>; + }; + + opp4 { + opp-hz = /bits/ 64 <25000000>; + required-opps = <&rpmpd_opp_normal>; + }; + }; diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h new file mode 100644 index 000000000000..87d9c6611682 --- /dev/null +++ b/include/dt-bindings/power/qcom-rpmpd.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, The Linux Foundation. All rights reserved. */ + +#ifndef _DT_BINDINGS_POWER_QCOM_RPMPD_H +#define _DT_BINDINGS_POWER_QCOM_RPMPD_H + +/* SDM845 Power Domain Indexes */ +#define SDM845_EBI 0 +#define SDM845_MX 1 +#define SDM845_MX_AO 2 +#define SDM845_CX 3 +#define SDM845_CX_AO 4 +#define SDM845_LMX 5 +#define SDM845_LCX 6 +#define SDM845_GFX 7 +#define SDM845_MSS 8 + +/* SDM845 Power Domain performance levels */ +#define RPMH_REGULATOR_LEVEL_RETENTION 16 +#define RPMH_REGULATOR_LEVEL_MIN_SVS 48 +#define RPMH_REGULATOR_LEVEL_LOW_SVS 64 +#define RPMH_REGULATOR_LEVEL_SVS 128 +#define RPMH_REGULATOR_LEVEL_SVS_L1 192 +#define RPMH_REGULATOR_LEVEL_NOM 256 +#define RPMH_REGULATOR_LEVEL_NOM_L1 320 +#define RPMH_REGULATOR_LEVEL_NOM_L2 336 +#define RPMH_REGULATOR_LEVEL_TURBO 384 +#define RPMH_REGULATOR_LEVEL_TURBO_L1 416 + +/* MSM8996 Power Domain Indexes */ +#define MSM8996_VDDCX 0 +#define MSM8996_VDDCX_AO 1 +#define MSM8996_VDDCX_VFC 2 +#define MSM8996_VDDMX 3 +#define MSM8996_VDDMX_AO 4 +#define MSM8996_VDDSSCX 5 +#define MSM8996_VDDSSCX_VFC 6 + +#endif -- cgit v1.2.3 From ba5ea614622dca6d675b4cc8a97270569ae13a23 Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Mon, 21 Jan 2019 07:26:25 +0100 Subject: bridge: simplify ip_mc_check_igmp() and ipv6_mc_check_mld() calls MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch refactors ip_mc_check_igmp(), ipv6_mc_check_mld() and their callers (more precisely, the Linux bridge) to not rely on the skb_trimmed parameter anymore. An skb with its tail trimmed to the IP packet length was initially introduced for the following three reasons: 1) To be able to verify the ICMPv6 checksum. 2) To be able to distinguish the version of an IGMP or MLD query. They are distinguishable only by their size. 3) To avoid parsing data for an IGMPv3 or MLDv2 report that is beyond the IP packet but still within the skb. The first case still uses a cloned and potentially trimmed skb to verfiy. However, there is no need to propagate it to the caller. For the second and third case explicit IP packet length checks were added. This hopefully makes ip_mc_check_igmp() and ipv6_mc_check_mld() easier to read and verfiy, as well as easier to use. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/linux/igmp.h | 11 ++++++++- include/linux/ip.h | 5 ++++ include/linux/ipv6.h | 6 +++++ include/net/addrconf.h | 12 +++++++++- net/batman-adv/multicast.c | 4 ++-- net/bridge/br_multicast.c | 57 +++++++++++++++++++++++----------------------- net/ipv4/igmp.c | 23 ++++--------------- net/ipv6/mcast_snoop.c | 24 ++++--------------- 8 files changed, 70 insertions(+), 72 deletions(-) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 119f53941c12..8b4348f69bc5 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -106,6 +107,14 @@ struct ip_mc_list { #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) +static inline int ip_mc_may_pull(struct sk_buff *skb, unsigned int len) +{ + if (skb_transport_offset(skb) + ip_transport_len(skb) < len) + return -EINVAL; + + return pskb_may_pull(skb, len); +} + extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); @@ -130,6 +139,6 @@ extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); -int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed); +int ip_mc_check_igmp(struct sk_buff *skb); #endif diff --git a/include/linux/ip.h b/include/linux/ip.h index 492bc6513533..482b7b7c9f30 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -34,4 +34,9 @@ static inline struct iphdr *ipip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_transport_header(skb); } + +static inline unsigned int ip_transport_len(const struct sk_buff *skb) +{ + return ntohs(ip_hdr(skb)->tot_len) - skb_network_header_len(skb); +} #endif /* _LINUX_IP_H */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 495e834c1367..6d45ce784bea 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -104,6 +104,12 @@ static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) return (struct ipv6hdr *)skb_transport_header(skb); } +static inline unsigned int ipv6_transport_len(const struct sk_buff *skb) +{ + return ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr) - + skb_network_header_len(skb); +} + /* This structure contains results of exthdrs parsing as offsets from skb->nh. diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 1656c5978498..daf11dcb0f70 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -49,6 +49,7 @@ struct prefix_info { struct in6_addr prefix; }; +#include #include #include #include @@ -201,6 +202,15 @@ u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, /* * multicast prototypes (mcast.c) */ +static inline int ipv6_mc_may_pull(struct sk_buff *skb, + unsigned int len) +{ + if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len) + return -EINVAL; + + return pskb_may_pull(skb, len); +} + int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, @@ -219,7 +229,7 @@ void ipv6_mc_unmap(struct inet6_dev *idev); void ipv6_mc_remap(struct inet6_dev *idev); void ipv6_mc_init_dev(struct inet6_dev *idev); void ipv6_mc_destroy_dev(struct inet6_dev *idev); -int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed); +int ipv6_mc_check_mld(struct sk_buff *skb); void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp); bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 69244e4598f5..1dd70f048e7b 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -674,7 +674,7 @@ static void batadv_mcast_mla_update(struct work_struct *work) */ static bool batadv_mcast_is_report_ipv4(struct sk_buff *skb) { - if (ip_mc_check_igmp(skb, NULL) < 0) + if (ip_mc_check_igmp(skb) < 0) return false; switch (igmp_hdr(skb)->type) { @@ -741,7 +741,7 @@ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv, */ static bool batadv_mcast_is_report_ipv6(struct sk_buff *skb) { - if (ipv6_mc_check_mld(skb, NULL) < 0) + if (ipv6_mc_check_mld(skb) < 0) return false; switch (icmp6_hdr(skb)->icmp6_type) { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3aeff0895669..156c4905639e 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -938,7 +938,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, for (i = 0; i < num; i++) { len += sizeof(*grec); - if (!pskb_may_pull(skb, len)) + if (!ip_mc_may_pull(skb, len)) return -EINVAL; grec = (void *)(skb->data + len - sizeof(*grec)); @@ -946,7 +946,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, type = grec->grec_type; len += ntohs(grec->grec_nsrcs) * 4; - if (!pskb_may_pull(skb, len)) + if (!ip_mc_may_pull(skb, len)) return -EINVAL; /* We treat this as an IGMPv2 report for now. */ @@ -985,15 +985,17 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + unsigned int nsrcs_offset; const unsigned char *src; struct icmp6hdr *icmp6h; struct mld2_grec *grec; + unsigned int grec_len; int i; int len; int num; int err = 0; - if (!pskb_may_pull(skb, sizeof(*icmp6h))) + if (!ipv6_mc_may_pull(skb, sizeof(*icmp6h))) return -EINVAL; icmp6h = icmp6_hdr(skb); @@ -1003,21 +1005,25 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, for (i = 0; i < num; i++) { __be16 *nsrcs, _nsrcs; - nsrcs = skb_header_pointer(skb, - len + offsetof(struct mld2_grec, - grec_nsrcs), + nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs); + + if (skb_transport_offset(skb) + ipv6_transport_len(skb) < + nsrcs_offset + sizeof(_nsrcs)) + return -EINVAL; + + nsrcs = skb_header_pointer(skb, nsrcs_offset, sizeof(_nsrcs), &_nsrcs); if (!nsrcs) return -EINVAL; - if (!pskb_may_pull(skb, - len + sizeof(*grec) + - sizeof(struct in6_addr) * ntohs(*nsrcs))) + grec_len = sizeof(*grec) + + sizeof(struct in6_addr) * ntohs(*nsrcs); + + if (!ipv6_mc_may_pull(skb, len + grec_len)) return -EINVAL; grec = (struct mld2_grec *)(skb->data + len); - len += sizeof(*grec) + - sizeof(struct in6_addr) * ntohs(*nsrcs); + len += grec_len; /* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { @@ -1219,6 +1225,7 @@ static void br_ip4_multicast_query(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + unsigned int transport_len = ip_transport_len(skb); const struct iphdr *iph = ip_hdr(skb); struct igmphdr *ih = igmp_hdr(skb); struct net_bridge_mdb_entry *mp; @@ -1228,7 +1235,6 @@ static void br_ip4_multicast_query(struct net_bridge *br, struct br_ip saddr; unsigned long max_delay; unsigned long now = jiffies; - unsigned int offset = skb_transport_offset(skb); __be32 group; spin_lock(&br->multicast_lock); @@ -1238,14 +1244,14 @@ static void br_ip4_multicast_query(struct net_bridge *br, group = ih->group; - if (skb->len == offset + sizeof(*ih)) { + if (transport_len == sizeof(*ih)) { max_delay = ih->code * (HZ / IGMP_TIMER_SCALE); if (!max_delay) { max_delay = 10 * HZ; group = 0; } - } else if (skb->len >= offset + sizeof(*ih3)) { + } else if (transport_len >= sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) goto out; @@ -1296,6 +1302,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + unsigned int transport_len = ipv6_transport_len(skb); const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct mld_msg *mld; struct net_bridge_mdb_entry *mp; @@ -1315,7 +1322,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; - if (skb->len == offset + sizeof(*mld)) { + if (transport_len == sizeof(*mld)) { if (!pskb_may_pull(skb, offset + sizeof(*mld))) { err = -EINVAL; goto out; @@ -1581,12 +1588,11 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, struct sk_buff *skb, u16 vid) { - struct sk_buff *skb_trimmed = NULL; const unsigned char *src; struct igmphdr *ih; int err; - err = ip_mc_check_igmp(skb, &skb_trimmed); + err = ip_mc_check_igmp(skb); if (err == -ENOMSG) { if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr)) { @@ -1612,19 +1618,16 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = br_ip4_multicast_add_group(br, port, ih->group, vid, src); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: - err = br_ip4_multicast_igmp3_report(br, port, skb_trimmed, vid); + err = br_ip4_multicast_igmp3_report(br, port, skb, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: - br_ip4_multicast_query(br, port, skb_trimmed, vid); + br_ip4_multicast_query(br, port, skb, vid); break; case IGMP_HOST_LEAVE_MESSAGE: br_ip4_multicast_leave_group(br, port, ih->group, vid, src); break; } - if (skb_trimmed && skb_trimmed != skb) - kfree_skb(skb_trimmed); - br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); @@ -1637,12 +1640,11 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, struct sk_buff *skb, u16 vid) { - struct sk_buff *skb_trimmed = NULL; const unsigned char *src; struct mld_msg *mld; int err; - err = ipv6_mc_check_mld(skb, &skb_trimmed); + err = ipv6_mc_check_mld(skb); if (err == -ENOMSG) { if (!ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) @@ -1664,10 +1666,10 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, src); break; case ICMPV6_MLD2_REPORT: - err = br_ip6_multicast_mld2_report(br, port, skb_trimmed, vid); + err = br_ip6_multicast_mld2_report(br, port, skb, vid); break; case ICMPV6_MGM_QUERY: - err = br_ip6_multicast_query(br, port, skb_trimmed, vid); + err = br_ip6_multicast_query(br, port, skb, vid); break; case ICMPV6_MGM_REDUCTION: src = eth_hdr(skb)->h_source; @@ -1675,9 +1677,6 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, break; } - if (skb_trimmed && skb_trimmed != skb) - kfree_skb(skb_trimmed); - br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 765b2b32c4a4..b1f6d93282d7 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1544,7 +1544,7 @@ static inline __sum16 ip_mc_validate_checksum(struct sk_buff *skb) return skb_checksum_simple_validate(skb); } -static int __ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) +static int __ip_mc_check_igmp(struct sk_buff *skb) { struct sk_buff *skb_chk; @@ -1566,16 +1566,10 @@ static int __ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) if (ret) goto err; - if (skb_trimmed) - *skb_trimmed = skb_chk; - /* free now unneeded clone */ - else if (skb_chk != skb) - kfree_skb(skb_chk); - ret = 0; err: - if (ret && skb_chk && skb_chk != skb) + if (skb_chk && skb_chk != skb) kfree_skb(skb_chk); return ret; @@ -1584,7 +1578,6 @@ err: /** * ip_mc_check_igmp - checks whether this is a sane IGMP packet * @skb: the skb to validate - * @skb_trimmed: to store an skb pointer trimmed to IPv4 packet tail (optional) * * Checks whether an IPv4 packet is a valid IGMP packet. If so sets * skb transport header accordingly and returns zero. @@ -1594,18 +1587,10 @@ err: * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. * -ENOMEM: A memory allocation failure happened. * - * Optionally, an skb pointer might be provided via skb_trimmed (or set it - * to NULL): After parsing an IGMP packet successfully it will point to - * an skb which has its tail aligned to the IP packet end. This might - * either be the originally provided skb or a trimmed, cloned version if - * the skb frame had data beyond the IP packet. A cloned skb allows us - * to leave the original skb and its full frame unchanged (which might be - * desirable for layer 2 frame jugglers). - * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ -int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) +int ip_mc_check_igmp(struct sk_buff *skb) { int ret = ip_mc_check_iphdr(skb); @@ -1615,7 +1600,7 @@ int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) if (ip_hdr(skb)->protocol != IPPROTO_IGMP) return -ENOMSG; - return __ip_mc_check_igmp(skb, skb_trimmed); + return __ip_mc_check_igmp(skb); } EXPORT_SYMBOL(ip_mc_check_igmp); diff --git a/net/ipv6/mcast_snoop.c b/net/ipv6/mcast_snoop.c index 9405b04eecc6..1a917dc80d5e 100644 --- a/net/ipv6/mcast_snoop.c +++ b/net/ipv6/mcast_snoop.c @@ -136,8 +136,7 @@ static inline __sum16 ipv6_mc_validate_checksum(struct sk_buff *skb) return skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo); } -static int __ipv6_mc_check_mld(struct sk_buff *skb, - struct sk_buff **skb_trimmed) +static int __ipv6_mc_check_mld(struct sk_buff *skb) { struct sk_buff *skb_chk = NULL; @@ -160,16 +159,10 @@ static int __ipv6_mc_check_mld(struct sk_buff *skb, if (ret) goto err; - if (skb_trimmed) - *skb_trimmed = skb_chk; - /* free now unneeded clone */ - else if (skb_chk != skb) - kfree_skb(skb_chk); - ret = 0; err: - if (ret && skb_chk && skb_chk != skb) + if (skb_chk && skb_chk != skb) kfree_skb(skb_chk); return ret; @@ -178,7 +171,6 @@ err: /** * ipv6_mc_check_mld - checks whether this is a sane MLD packet * @skb: the skb to validate - * @skb_trimmed: to store an skb pointer trimmed to IPv6 packet tail (optional) * * Checks whether an IPv6 packet is a valid MLD packet. If so sets * skb transport header accordingly and returns zero. @@ -188,18 +180,10 @@ err: * -ENOMSG: IP header validation succeeded but it is not an MLD packet. * -ENOMEM: A memory allocation failure happened. * - * Optionally, an skb pointer might be provided via skb_trimmed (or set it - * to NULL): After parsing an MLD packet successfully it will point to - * an skb which has its tail aligned to the IP packet end. This might - * either be the originally provided skb or a trimmed, cloned version if - * the skb frame had data beyond the IP packet. A cloned skb allows us - * to leave the original skb and its full frame unchanged (which might be - * desirable for layer 2 frame jugglers). - * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ -int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed) +int ipv6_mc_check_mld(struct sk_buff *skb) { int ret; @@ -211,6 +195,6 @@ int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed) if (ret < 0) return ret; - return __ipv6_mc_check_mld(skb, skb_trimmed); + return __ipv6_mc_check_mld(skb); } EXPORT_SYMBOL(ipv6_mc_check_mld); -- cgit v1.2.3 From 4effd28c1245303dce7fd290c501ac2c11052114 Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Mon, 21 Jan 2019 07:26:27 +0100 Subject: bridge: join all-snoopers multicast address MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Next to snooping IGMP/MLD queries RFC4541, section 2.1.1.a) recommends to snoop multicast router advertisements to detect multicast routers. Multicast router advertisements are sent to an "all-snoopers" multicast address. To be able to receive them reliably, we need to join this group. Otherwise other snooping switches might refrain from forwarding these advertisements to us. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 9 +++--- net/bridge/br_multicast.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++- net/ipv6/mcast.c | 2 ++ 3 files changed, 78 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index a55cb8b10165..e7ad9d350a28 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -292,10 +292,11 @@ struct sockaddr_in { #define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000) /* Defines for Multicast INADDR */ -#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ -#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ -#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ -#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ +#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ +#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ +#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ +#define INADDR_ALLSNOOPERS_GROUP 0xe000006aU /* 224.0.0.106 */ +#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ #endif /* contains the htonl type stuff.. */ diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 156c4905639e..2366f4a2780e 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1780,6 +1780,68 @@ void br_multicast_init(struct net_bridge *br) INIT_HLIST_HEAD(&br->mdb_list); } +static void br_ip4_multicast_join_snoopers(struct net_bridge *br) +{ + struct in_device *in_dev = in_dev_get(br->dev); + + if (!in_dev) + return; + + ip_mc_inc_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP)); + in_dev_put(in_dev); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_join_snoopers(struct net_bridge *br) +{ + struct in6_addr addr; + + ipv6_addr_set(&addr, htonl(0xff020000), 0, 0, htonl(0x6a)); + ipv6_dev_mc_inc(br->dev, &addr); +} +#else +static inline void br_ip6_multicast_join_snoopers(struct net_bridge *br) +{ +} +#endif + +static void br_multicast_join_snoopers(struct net_bridge *br) +{ + br_ip4_multicast_join_snoopers(br); + br_ip6_multicast_join_snoopers(br); +} + +static void br_ip4_multicast_leave_snoopers(struct net_bridge *br) +{ + struct in_device *in_dev = in_dev_get(br->dev); + + if (WARN_ON(!in_dev)) + return; + + ip_mc_dec_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP)); + in_dev_put(in_dev); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_leave_snoopers(struct net_bridge *br) +{ + struct in6_addr addr; + + ipv6_addr_set(&addr, htonl(0xff020000), 0, 0, htonl(0x6a)); + ipv6_dev_mc_dec(br->dev, &addr); +} +#else +static inline void br_ip6_multicast_leave_snoopers(struct net_bridge *br) +{ +} +#endif + +static void br_multicast_leave_snoopers(struct net_bridge *br) +{ + br_ip4_multicast_leave_snoopers(br); + br_ip6_multicast_leave_snoopers(br); +} + static void __br_multicast_open(struct net_bridge *br, struct bridge_mcast_own_query *query) { @@ -1793,6 +1855,9 @@ static void __br_multicast_open(struct net_bridge *br, void br_multicast_open(struct net_bridge *br) { + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_join_snoopers(br); + __br_multicast_open(br, &br->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) __br_multicast_open(br, &br->ip6_own_query); @@ -1808,6 +1873,9 @@ void br_multicast_stop(struct net_bridge *br) del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif + + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_leave_snoopers(br); } void br_multicast_dev_del(struct net_bridge *br) @@ -1943,8 +2011,10 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) br_mc_disabled_update(br->dev, val); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); - if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) + if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { + br_multicast_leave_snoopers(br); goto unlock; + } if (!netif_running(br->dev)) goto unlock; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 21f6deb2aec9..42f3f5cd349f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -940,6 +940,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) { return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); } +EXPORT_SYMBOL(ipv6_dev_mc_inc); /* * device multicast group del @@ -987,6 +988,7 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) return err; } +EXPORT_SYMBOL(ipv6_dev_mc_dec); /* * check if the interface/address pair is valid -- cgit v1.2.3 From 4b3087c7e37f9e499127201849e33960dc81da11 Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Mon, 21 Jan 2019 07:26:28 +0100 Subject: bridge: Snoop Multicast Router Advertisements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When multiple multicast routers are present in a broadcast domain then only one of them will be detectable via IGMP/MLD query snooping. The multicast router with the lowest IP address will become the selected and active querier while all other multicast routers will then refrain from sending queries. To detect such rather silent multicast routers, too, RFC4286 ("Multicast Router Discovery") provides a standardized protocol to detect multicast routers for multicast snooping switches. This patch implements the necessary MRD Advertisement message parsing and after successful processing adds such routers to the internal multicast router list. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/linux/in.h | 5 +++++ include/net/addrconf.h | 15 +++++++++++++ include/uapi/linux/icmpv6.h | 2 ++ include/uapi/linux/igmp.h | 1 + net/bridge/br_multicast.c | 55 +++++++++++++++++++++++++++++++++++++++++++++ net/ipv6/mcast_snoop.c | 5 ++++- 6 files changed, 82 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/in.h b/include/linux/in.h index 31b493734763..435e7f2a513a 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -60,6 +60,11 @@ static inline bool ipv4_is_lbcast(__be32 addr) return addr == htonl(INADDR_BROADCAST); } +static inline bool ipv4_is_all_snoopers(__be32 addr) +{ + return addr == htonl(INADDR_ALLSNOOPERS_GROUP); +} + static inline bool ipv4_is_zeronet(__be32 addr) { return (addr & htonl(0xff000000)) == htonl(0x00000000); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index daf11dcb0f70..20d523ee2fec 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -229,6 +229,7 @@ void ipv6_mc_unmap(struct inet6_dev *idev); void ipv6_mc_remap(struct inet6_dev *idev); void ipv6_mc_init_dev(struct inet6_dev *idev); void ipv6_mc_destroy_dev(struct inet6_dev *idev); +int ipv6_mc_check_icmpv6(struct sk_buff *skb); int ipv6_mc_check_mld(struct sk_buff *skb); void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp); @@ -499,6 +500,20 @@ static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr) #endif } +static inline bool ipv6_addr_is_all_snoopers(const struct in6_addr *addr) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + __be64 *p = (__be64 *)addr; + + return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | + (p[1] ^ cpu_to_be64(0x6a))) == 0UL; +#else + return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | + addr->s6_addr32[1] | addr->s6_addr32[2] | + (addr->s6_addr32[3] ^ htonl(0x0000006a))) == 0; +#endif +} + #ifdef CONFIG_PROC_FS int if6_proc_init(void); void if6_proc_exit(void); diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index caf8dc019250..325395f56bfa 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -108,6 +108,8 @@ struct icmp6hdr { #define ICMPV6_MOBILE_PREFIX_SOL 146 #define ICMPV6_MOBILE_PREFIX_ADV 147 +#define ICMPV6_MRDISC_ADV 151 + /* * Codes for Destination Unreachable */ diff --git a/include/uapi/linux/igmp.h b/include/uapi/linux/igmp.h index 7e44ac02ca18..90c28bc466c6 100644 --- a/include/uapi/linux/igmp.h +++ b/include/uapi/linux/igmp.h @@ -93,6 +93,7 @@ struct igmpv3_query { #define IGMP_MTRACE_RESP 0x1e #define IGMP_MTRACE 0x1f +#define IGMP_MRDISC_ADV 0x30 /* From RFC4286 */ /* * Use the BSD names for these for compatibility diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 2366f4a2780e..2c46c7aca571 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -29,10 +30,12 @@ #include #include #if IS_ENABLED(CONFIG_IPV6) +#include #include #include #include #include +#include #endif #include "br_private.h" @@ -1583,6 +1586,19 @@ static void br_multicast_pim(struct net_bridge *br, br_multicast_mark_router(br, port); } +static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb) +{ + if (ip_hdr(skb)->protocol != IPPROTO_IGMP || + igmp_hdr(skb)->type != IGMP_MRDISC_ADV) + return -ENOMSG; + + br_multicast_mark_router(br, port); + + return 0; +} + static int br_multicast_ipv4_rcv(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, @@ -1600,7 +1616,15 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, } else if (pim_ipv4_all_pim_routers(ip_hdr(skb)->daddr)) { if (ip_hdr(skb)->protocol == IPPROTO_PIM) br_multicast_pim(br, port, skb); + } else if (ipv4_is_all_snoopers(ip_hdr(skb)->daddr)) { + err = br_ip4_multicast_mrd_rcv(br, port, skb); + + if (err < 0 && err != -ENOMSG) { + br_multicast_err_count(br, port, skb->protocol); + return err; + } } + return 0; } else if (err < 0) { br_multicast_err_count(br, port, skb->protocol); @@ -1635,6 +1659,27 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, } #if IS_ENABLED(CONFIG_IPV6) +static int br_ip6_multicast_mrd_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb) +{ + int ret; + + if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) + return -ENOMSG; + + ret = ipv6_mc_check_icmpv6(skb); + if (ret < 0) + return ret; + + if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) + return -ENOMSG; + + br_multicast_mark_router(br, port); + + return 0; +} + static int br_multicast_ipv6_rcv(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, @@ -1649,6 +1694,16 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, if (err == -ENOMSG) { if (!ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) BR_INPUT_SKB_CB(skb)->mrouters_only = 1; + + if (ipv6_addr_is_all_snoopers(&ipv6_hdr(skb)->daddr)) { + err = br_ip6_multicast_mrd_rcv(br, port, skb); + + if (err < 0 && err != -ENOMSG) { + br_multicast_err_count(br, port, skb->protocol); + return err; + } + } + return 0; } else if (err < 0) { br_multicast_err_count(br, port, skb->protocol); diff --git a/net/ipv6/mcast_snoop.c b/net/ipv6/mcast_snoop.c index a72ddfc40eb3..55e2ac179f28 100644 --- a/net/ipv6/mcast_snoop.c +++ b/net/ipv6/mcast_snoop.c @@ -41,6 +41,8 @@ static int ipv6_mc_check_ip6hdr(struct sk_buff *skb) if (skb->len < len || len <= offset) return -EINVAL; + skb_set_transport_header(skb, offset); + return 0; } @@ -142,7 +144,7 @@ static inline __sum16 ipv6_mc_validate_checksum(struct sk_buff *skb) return skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo); } -static int ipv6_mc_check_icmpv6(struct sk_buff *skb) +int ipv6_mc_check_icmpv6(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct icmp6hdr); unsigned int transport_len = ipv6_transport_len(skb); @@ -161,6 +163,7 @@ static int ipv6_mc_check_icmpv6(struct sk_buff *skb) return 0; } +EXPORT_SYMBOL(ipv6_mc_check_icmpv6); /** * ipv6_mc_check_mld - checks whether this is a sane MLD packet -- cgit v1.2.3 From 6815d8b09282c1df8e016bd2fabf25ada6d4462b Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 21 Jan 2019 18:41:39 +0800 Subject: ptp_qoriq: support external trigger stamp FIFO The external trigger stamp FIFO was introduced as a new feature for QorIQ 1588 timer IP block. This patch is to support it by adding a new dts property "fsl,extts-fifo". Any QorIQ 1588 timer supporting this feature is required to add this property in its dts node. In addition, the FIFO should be cleaned up before enabling external trigger interrupts. Otherwise, there will be interrupts immediately just after enabling external trigger interrupts. Signed-off-by: Yangbo Lu Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/ptp/ptp_qoriq.c | 68 ++++++++++++++++++++++++++++++++++--------- include/linux/fsl/ptp_qoriq.h | 3 ++ 2 files changed, 57 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index 274321471d50..a2e7702db3a4 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -88,6 +88,49 @@ static void set_fipers(struct qoriq_ptp *qoriq_ptp) qoriq_write(®s->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); } +static int extts_clean_up(struct qoriq_ptp *qoriq_ptp, int index, + bool update_event) +{ + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_clock_event event; + void __iomem *reg_etts_l; + void __iomem *reg_etts_h; + u32 valid, stat, lo, hi; + + switch (index) { + case 0: + valid = ETS1_VLD; + reg_etts_l = ®s->etts_regs->tmr_etts1_l; + reg_etts_h = ®s->etts_regs->tmr_etts1_h; + break; + case 1: + valid = ETS2_VLD; + reg_etts_l = ®s->etts_regs->tmr_etts2_l; + reg_etts_h = ®s->etts_regs->tmr_etts2_h; + break; + default: + return -EINVAL; + } + + event.type = PTP_CLOCK_EXTTS; + event.index = index; + + do { + lo = qoriq_read(reg_etts_l); + hi = qoriq_read(reg_etts_h); + + if (update_event) { + event.timestamp = ((u64) hi) << 32; + event.timestamp |= lo; + ptp_clock_event(qoriq_ptp->clock, &event); + } + + stat = qoriq_read(®s->ctrl_regs->tmr_stat); + } while (qoriq_ptp->extts_fifo_support && (stat & valid)); + + return 0; +} + /* * Interrupt service routine */ @@ -111,24 +154,12 @@ static irqreturn_t isr(int irq, void *priv) if (irqs & ETS1) { ack |= ETS1; - hi = qoriq_read(®s->etts_regs->tmr_etts1_h); - lo = qoriq_read(®s->etts_regs->tmr_etts1_l); - event.type = PTP_CLOCK_EXTTS; - event.index = 0; - event.timestamp = ((u64) hi) << 32; - event.timestamp |= lo; - ptp_clock_event(qoriq_ptp->clock, &event); + extts_clean_up(qoriq_ptp, 0, true); } if (irqs & ETS2) { ack |= ETS2; - hi = qoriq_read(®s->etts_regs->tmr_etts2_h); - lo = qoriq_read(®s->etts_regs->tmr_etts2_l); - event.type = PTP_CLOCK_EXTTS; - event.index = 1; - event.timestamp = ((u64) hi) << 32; - event.timestamp |= lo; - ptp_clock_event(qoriq_ptp->clock, &event); + extts_clean_up(qoriq_ptp, 1, true); } if (irqs & ALM2) { @@ -278,6 +309,10 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp, default: return -EINVAL; } + + if (on) + extts_clean_up(qoriq_ptp, rq->extts.index, false); + break; case PTP_CLK_REQ_PPS: bit = PP1EN; @@ -441,6 +476,11 @@ static int qoriq_ptp_probe(struct platform_device *dev) if (of_property_read_u32(node, "fsl,cksel", &qoriq_ptp->cksel)) qoriq_ptp->cksel = DEFAULT_CKSEL; + if (of_property_read_bool(node, "fsl,extts-fifo")) + qoriq_ptp->extts_fifo_support = true; + else + qoriq_ptp->extts_fifo_support = false; + if (of_property_read_u32(node, "fsl,tclk-period", &qoriq_ptp->tclk_period) || of_property_read_u32(node, diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index c1f003aadcce..43b4b442f6a4 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -120,6 +120,8 @@ struct qoriq_ptp_registers { /* Bit definitions for the TMR_STAT register */ #define STAT_VEC_SHIFT (0) /* Timer general purpose status vector */ #define STAT_VEC_MASK (0x3f) +#define ETS1_VLD (1<<24) +#define ETS2_VLD (1<<25) /* Bit definitions for the TMR_PRSC register */ #define PRSC_OCK_SHIFT (0) /* Output clock division/prescale factor. */ @@ -141,6 +143,7 @@ struct qoriq_ptp { struct ptp_clock *clock; struct ptp_clock_info caps; struct resource *rsrc; + bool extts_fifo_support; int irq; int phc_index; u64 alarm_interval; /* for periodic alarm */ -- cgit v1.2.3 From 19df7510d5cf077c2e88a7690fb7617e6d341beb Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 21 Jan 2019 18:41:42 +0800 Subject: ptp: add debugfs support for ptp_qoriq This patch is to add debugfs support for ptp_qoriq. Current debugfs supports to control fiper1/fiper2 loopback mode. If the loopback mode is enabled, the fiper1/fiper2 pulse is looped back into trigger1/ trigger2 input. This is very useful for validating hardware and driver without external hardware. Below is an example to enable fiper1 loopback. echo 1 > /sys/kernel/debug/2d10e00.ptp_clock/fiper1-loopback Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/Kconfig | 2 +- drivers/ptp/Makefile | 4 +- drivers/ptp/ptp_qoriq.c | 3 ++ drivers/ptp/ptp_qoriq_debugfs.c | 101 ++++++++++++++++++++++++++++++++++++++++ include/linux/fsl/ptp_qoriq.h | 12 +++++ 5 files changed, 120 insertions(+), 2 deletions(-) create mode 100644 drivers/ptp/ptp_qoriq_debugfs.c (limited to 'include') diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index d137c480db46..aeb4a8b2e0af 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -53,7 +53,7 @@ config PTP_1588_CLOCK_QORIQ packets using the SO_TIMESTAMPING API. To compile this driver as a module, choose M here: the module - will be called ptp_qoriq. + will be called ptp-qoriq. config PTP_1588_CLOCK_IXP46X tristate "Intel IXP46x as PTP clock" diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile index 19efa9cfa950..677d1d178a3e 100644 --- a/drivers/ptp/Makefile +++ b/drivers/ptp/Makefile @@ -9,4 +9,6 @@ obj-$(CONFIG_PTP_1588_CLOCK_DTE) += ptp_dte.o obj-$(CONFIG_PTP_1588_CLOCK_IXP46X) += ptp_ixp46x.o obj-$(CONFIG_PTP_1588_CLOCK_PCH) += ptp_pch.o obj-$(CONFIG_PTP_1588_CLOCK_KVM) += ptp_kvm.o -obj-$(CONFIG_PTP_1588_CLOCK_QORIQ) += ptp_qoriq.o +obj-$(CONFIG_PTP_1588_CLOCK_QORIQ) += ptp-qoriq.o +ptp-qoriq-y += ptp_qoriq.o +ptp-qoriq-$(CONFIG_DEBUG_FS) += ptp_qoriq_debugfs.o diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index a2e7702db3a4..43416b2e8a13 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -471,6 +471,7 @@ static int qoriq_ptp_probe(struct platform_device *dev) err = -EINVAL; + qoriq_ptp->dev = &dev->dev; qoriq_ptp->caps = ptp_qoriq_caps; if (of_property_read_u32(node, "fsl,cksel", &qoriq_ptp->cksel)) @@ -572,6 +573,7 @@ static int qoriq_ptp_probe(struct platform_device *dev) } qoriq_ptp->phc_index = ptp_clock_index(qoriq_ptp->clock); + ptp_qoriq_create_debugfs(qoriq_ptp); platform_set_drvdata(dev, qoriq_ptp); return 0; @@ -597,6 +599,7 @@ static int qoriq_ptp_remove(struct platform_device *dev) qoriq_write(®s->ctrl_regs->tmr_temask, 0); qoriq_write(®s->ctrl_regs->tmr_ctrl, 0); + ptp_qoriq_remove_debugfs(qoriq_ptp); ptp_clock_unregister(qoriq_ptp->clock); iounmap(qoriq_ptp->base); release_resource(qoriq_ptp->rsrc); diff --git a/drivers/ptp/ptp_qoriq_debugfs.c b/drivers/ptp/ptp_qoriq_debugfs.c new file mode 100644 index 000000000000..d904332b240d --- /dev/null +++ b/drivers/ptp/ptp_qoriq_debugfs.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright 2019 NXP + */ +#include +#include +#include + +static int ptp_qoriq_fiper1_lpbk_get(void *data, u64 *val) +{ + struct qoriq_ptp *qoriq_ptp = data; + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + u32 ctrl; + + ctrl = qoriq_read(®s->ctrl_regs->tmr_ctrl); + *val = ctrl & PP1L ? 1 : 0; + + return 0; +} + +static int ptp_qoriq_fiper1_lpbk_set(void *data, u64 val) +{ + struct qoriq_ptp *qoriq_ptp = data; + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + u32 ctrl; + + ctrl = qoriq_read(®s->ctrl_regs->tmr_ctrl); + if (val == 0) + ctrl &= ~PP1L; + else + ctrl |= PP1L; + + qoriq_write(®s->ctrl_regs->tmr_ctrl, ctrl); + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(ptp_qoriq_fiper1_fops, ptp_qoriq_fiper1_lpbk_get, + ptp_qoriq_fiper1_lpbk_set, "%llu\n"); + +static int ptp_qoriq_fiper2_lpbk_get(void *data, u64 *val) +{ + struct qoriq_ptp *qoriq_ptp = data; + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + u32 ctrl; + + ctrl = qoriq_read(®s->ctrl_regs->tmr_ctrl); + *val = ctrl & PP2L ? 1 : 0; + + return 0; +} + +static int ptp_qoriq_fiper2_lpbk_set(void *data, u64 val) +{ + struct qoriq_ptp *qoriq_ptp = data; + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + u32 ctrl; + + ctrl = qoriq_read(®s->ctrl_regs->tmr_ctrl); + if (val == 0) + ctrl &= ~PP2L; + else + ctrl |= PP2L; + + qoriq_write(®s->ctrl_regs->tmr_ctrl, ctrl); + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(ptp_qoriq_fiper2_fops, ptp_qoriq_fiper2_lpbk_get, + ptp_qoriq_fiper2_lpbk_set, "%llu\n"); + +void ptp_qoriq_create_debugfs(struct qoriq_ptp *qoriq_ptp) +{ + struct dentry *root; + + root = debugfs_create_dir(dev_name(qoriq_ptp->dev), NULL); + if (IS_ERR(root)) + return; + if (!root) + goto err_root; + + qoriq_ptp->debugfs_root = root; + + if (!debugfs_create_file("fiper1-loopback", 0600, root, qoriq_ptp, + &ptp_qoriq_fiper1_fops)) + goto err_node; + if (!debugfs_create_file("fiper2-loopback", 0600, root, qoriq_ptp, + &ptp_qoriq_fiper2_fops)) + goto err_node; + return; + +err_node: + debugfs_remove_recursive(root); + qoriq_ptp->debugfs_root = NULL; +err_root: + dev_err(qoriq_ptp->dev, "failed to initialize debugfs\n"); +} + +void ptp_qoriq_remove_debugfs(struct qoriq_ptp *qoriq_ptp) +{ + debugfs_remove_recursive(qoriq_ptp->debugfs_root); + qoriq_ptp->debugfs_root = NULL; +} diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index 43b4b442f6a4..94e9797e434c 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -143,6 +143,8 @@ struct qoriq_ptp { struct ptp_clock *clock; struct ptp_clock_info caps; struct resource *rsrc; + struct dentry *debugfs_root; + struct device *dev; bool extts_fifo_support; int irq; int phc_index; @@ -169,4 +171,14 @@ static inline void qoriq_write(unsigned __iomem *addr, u32 val) iowrite32be(val, addr); } +#ifdef CONFIG_DEBUG_FS +void ptp_qoriq_create_debugfs(struct qoriq_ptp *qoriq_ptp); +void ptp_qoriq_remove_debugfs(struct qoriq_ptp *qoriq_ptp); +#else +static inline void ptp_qoriq_create_debugfs(struct qoriq_ptp *qoriq_ptp) +{ } +static inline void ptp_qoriq_remove_debugfs(struct qoriq_ptp *qoriq_ptp) +{ } +#endif + #endif -- cgit v1.2.3 From f57f3df03a8e6010e321fa0258d3e054713c3cb7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 13 Jan 2019 09:50:33 +0100 Subject: ALSA: pcm: More fine-grained PCM link locking We have currently two global locks, a rwlock and a rwsem, that are used for managing linking the PCM streams. Due to these global locks, once when a linked stream is used, the lock granularity suffers a lot. This patch attempts to eliminate the former global lock for atomic ops. The latter rwsem needs remaining because of the loosy way of the loop calls in snd_pcm_action_nonatomic(), as well as for avoiding the deadlock at linking. However, these are used far rarely, actually only by two actions (prepare and reset), where both are no timing critical ones. So this can be still seen as a good improvement. The basic strategy to eliminate the rwlock is to assure group->lock at adding or removing a stream to / from the group. Since we already takes the group lock whenever taking the all substream locks under the group, this shouldn't be a big problem. The reference to group pointer in snd_pcm_substream object is protected by the stream lock itself. However, there are still pitfalls: a race window at re-locking and the lifecycle of group object. The former is a small race window for dereferencing the substream group object opened while snd_pcm_action() performs re-locking to avoid ABBA deadlocks. This includes the unlink of group during that window, too. And the latter is the kfree performed after all streams are removed from the group while it's still dereferenced. For addressing these corner cases, two new tricks are introduced: - After re-locking, the group assigned to the stream is checked again; if the group is changed, we retry the whole procedure. - Introduce a refcount to snd_pcm_group object, so that it's freed only when it's empty and really no one refers to it. (Some readers might wonder why not RCU for the latter. RCU in this case would cost more than refcounting, unfortunately. We take the group lock sooner or later, hence the performance improvement by RCU would be negligible. Meanwhile, because we need to deal with schedulable context depending on the pcm->nonatomic flag, it'll become dynamic RCU/SRCU switch, and the grace period may become too long.) Along with these changes, there are a significant amount of code refactoring. The complex group re-lock & ref code is factored out to snd_pcm_stream_group_ref() function, for example. Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 2 + sound/core/pcm_native.c | 166 +++++++++++++++++++++++++++++++++++------------- 2 files changed, 124 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index e1c747c70883..3bde24575a99 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -30,6 +30,7 @@ #include #include #include +#include #define snd_pcm_substream_chip(substream) ((substream)->private_data) #define snd_pcm_chip(pcm) ((pcm)->private_data) @@ -439,6 +440,7 @@ struct snd_pcm_group { /* keep linked substreams */ spinlock_t lock; struct mutex mutex; struct list_head substreams; + refcount_t refs; }; struct pid; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index fb45386270d5..cbde23fc67a9 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -85,7 +85,6 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream); * */ -static DEFINE_RWLOCK(snd_pcm_link_rwlock); static DECLARE_RWSEM(snd_pcm_link_rwsem); /* Writer in rwsem may block readers even during its waiting in queue, @@ -105,8 +104,24 @@ void snd_pcm_group_init(struct snd_pcm_group *group) spin_lock_init(&group->lock); mutex_init(&group->mutex); INIT_LIST_HEAD(&group->substreams); + refcount_set(&group->refs, 0); } +/* define group lock helpers */ +#define DEFINE_PCM_GROUP_LOCK(action, mutex_action) \ +static void snd_pcm_group_ ## action(struct snd_pcm_group *group, bool nonatomic) \ +{ \ + if (nonatomic) \ + mutex_ ## mutex_action(&group->mutex); \ + else \ + spin_ ## action(&group->lock); \ +} + +DEFINE_PCM_GROUP_LOCK(lock, lock); +DEFINE_PCM_GROUP_LOCK(unlock, unlock); +DEFINE_PCM_GROUP_LOCK(lock_irq, lock); +DEFINE_PCM_GROUP_LOCK(unlock_irq, unlock); + #define PCM_LOCK_DEFAULT 0 #define PCM_LOCK_IRQ 1 #define PCM_LOCK_IRQSAVE 2 @@ -116,21 +131,19 @@ static unsigned long __snd_pcm_stream_lock_mode(struct snd_pcm_substream *substr { unsigned long flags = 0; if (substream->pcm->nonatomic) { - down_read_nested(&snd_pcm_link_rwsem, SINGLE_DEPTH_NESTING); mutex_lock(&substream->self_group.mutex); } else { switch (mode) { case PCM_LOCK_DEFAULT: - read_lock(&snd_pcm_link_rwlock); + spin_lock(&substream->self_group.lock); break; case PCM_LOCK_IRQ: - read_lock_irq(&snd_pcm_link_rwlock); + spin_lock_irq(&substream->self_group.lock); break; case PCM_LOCK_IRQSAVE: - read_lock_irqsave(&snd_pcm_link_rwlock, flags); + spin_lock_irqsave(&substream->self_group.lock, flags); break; } - spin_lock(&substream->self_group.lock); } return flags; } @@ -140,19 +153,16 @@ static void __snd_pcm_stream_unlock_mode(struct snd_pcm_substream *substream, { if (substream->pcm->nonatomic) { mutex_unlock(&substream->self_group.mutex); - up_read(&snd_pcm_link_rwsem); } else { - spin_unlock(&substream->self_group.lock); - switch (mode) { case PCM_LOCK_DEFAULT: - read_unlock(&snd_pcm_link_rwlock); + spin_unlock(&substream->self_group.lock); break; case PCM_LOCK_IRQ: - read_unlock_irq(&snd_pcm_link_rwlock); + spin_unlock_irq(&substream->self_group.lock); break; case PCM_LOCK_IRQSAVE: - read_unlock_irqrestore(&snd_pcm_link_rwlock, flags); + spin_unlock_irqrestore(&substream->self_group.lock, flags); break; } } @@ -1138,6 +1148,61 @@ static void snd_pcm_group_assign(struct snd_pcm_substream *substream, list_move(&substream->link_list, &new_group->substreams); } +/* + * Unref and unlock the group, but keep the stream lock; + * when the group becomes empty and no longer referred, destroy itself + */ +static void snd_pcm_group_unref(struct snd_pcm_group *group, + struct snd_pcm_substream *substream) +{ + bool do_free; + + if (!group) + return; + do_free = refcount_dec_and_test(&group->refs) && + list_empty(&group->substreams); + snd_pcm_group_unlock(group, substream->pcm->nonatomic); + if (do_free) + kfree(group); +} + +/* + * Lock the group inside a stream lock and reference it; + * return the locked group object, or NULL if not linked + */ +static struct snd_pcm_group * +snd_pcm_stream_group_ref(struct snd_pcm_substream *substream) +{ + bool nonatomic = substream->pcm->nonatomic; + struct snd_pcm_group *group; + bool trylock; + + for (;;) { + if (!snd_pcm_stream_linked(substream)) + return NULL; + group = substream->group; + /* block freeing the group object */ + refcount_inc(&group->refs); + + trylock = nonatomic ? mutex_trylock(&group->mutex) : + spin_trylock(&group->lock); + if (trylock) + break; /* OK */ + + /* re-lock for avoiding ABBA deadlock */ + snd_pcm_stream_unlock(substream); + snd_pcm_group_lock(group, nonatomic); + snd_pcm_stream_lock(substream); + + /* check the group again; the above opens a small race window */ + if (substream->group == group) + break; /* OK */ + /* group changed, try again */ + snd_pcm_group_unref(group, substream); + } + return group; +} + /* * Note: call with stream lock */ @@ -1145,28 +1210,15 @@ static int snd_pcm_action(const struct action_ops *ops, struct snd_pcm_substream *substream, int state) { + struct snd_pcm_group *group; int res; - if (!snd_pcm_stream_linked(substream)) - return snd_pcm_action_single(ops, substream, state); - - if (substream->pcm->nonatomic) { - if (!mutex_trylock(&substream->group->mutex)) { - mutex_unlock(&substream->self_group.mutex); - mutex_lock(&substream->group->mutex); - mutex_lock(&substream->self_group.mutex); - } + group = snd_pcm_stream_group_ref(substream); + if (group) res = snd_pcm_action_group(ops, substream, state, 1); - mutex_unlock(&substream->group->mutex); - } else { - if (!spin_trylock(&substream->group->lock)) { - spin_unlock(&substream->self_group.lock); - spin_lock(&substream->group->lock); - spin_lock(&substream->self_group.lock); - } - res = snd_pcm_action_group(ops, substream, state, 1); - spin_unlock(&substream->group->lock); - } + else + res = snd_pcm_action_single(ops, substream, state); + snd_pcm_group_unref(group, substream); return res; } @@ -1193,6 +1245,7 @@ static int snd_pcm_action_nonatomic(const struct action_ops *ops, { int res; + /* Guarantee the group members won't change during non-atomic action */ down_read(&snd_pcm_link_rwsem); if (snd_pcm_stream_linked(substream)) res = snd_pcm_action_group(ops, substream, state, 0); @@ -1821,6 +1874,7 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, struct snd_card *card; struct snd_pcm_runtime *runtime; struct snd_pcm_substream *s; + struct snd_pcm_group *group; wait_queue_entry_t wait; int result = 0; int nonblock = 0; @@ -1837,7 +1891,6 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, } else if (substream->f_flags & O_NONBLOCK) nonblock = 1; - down_read(&snd_pcm_link_rwsem); snd_pcm_stream_lock_irq(substream); /* resume pause */ if (runtime->status->state == SNDRV_PCM_STATE_PAUSED) @@ -1862,6 +1915,7 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, } /* find a substream to drain */ to_check = NULL; + group = snd_pcm_stream_group_ref(substream); snd_pcm_group_for_each_entry(s, substream) { if (s->stream != SNDRV_PCM_STREAM_PLAYBACK) continue; @@ -1871,12 +1925,12 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, break; } } + snd_pcm_group_unref(group, substream); if (!to_check) break; /* all drained */ init_waitqueue_entry(&wait, current); add_wait_queue(&to_check->sleep, &wait); snd_pcm_stream_unlock_irq(substream); - up_read(&snd_pcm_link_rwsem); if (runtime->no_period_wakeup) tout = MAX_SCHEDULE_TIMEOUT; else { @@ -1888,9 +1942,17 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, tout = msecs_to_jiffies(tout * 1000); } tout = schedule_timeout_interruptible(tout); - down_read(&snd_pcm_link_rwsem); + snd_pcm_stream_lock_irq(substream); - remove_wait_queue(&to_check->sleep, &wait); + group = snd_pcm_stream_group_ref(substream); + snd_pcm_group_for_each_entry(s, substream) { + if (s->runtime == to_check) { + remove_wait_queue(&to_check->sleep, &wait); + break; + } + } + snd_pcm_group_unref(group, substream); + if (card->shutdown) { result = -ENODEV; break; @@ -1910,7 +1972,6 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, unlock: snd_pcm_stream_unlock_irq(substream); - up_read(&snd_pcm_link_rwsem); return result; } @@ -1972,7 +2033,8 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) int res = 0; struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream1; - struct snd_pcm_group *group; + struct snd_pcm_group *group, *target_group; + bool nonatomic = substream->pcm->nonatomic; struct fd f = fdget(fd); if (!f.file) @@ -1989,8 +2051,8 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) goto _nolock; } snd_pcm_group_init(group); + down_write_nonfifo(&snd_pcm_link_rwsem); - write_lock_irq(&snd_pcm_link_rwlock); if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN || substream->runtime->status->state != substream1->runtime->status->state || substream->pcm->nonatomic != substream1->pcm->nonatomic) { @@ -2001,13 +2063,21 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) res = -EALREADY; goto _end; } + + snd_pcm_stream_lock_irq(substream); if (!snd_pcm_stream_linked(substream)) { snd_pcm_group_assign(substream, group); - group = NULL; + group = NULL; /* assigned, don't free this one below */ } - snd_pcm_group_assign(substream1, substream->group); + target_group = substream->group; + snd_pcm_stream_unlock_irq(substream); + + snd_pcm_group_lock_irq(target_group, nonatomic); + snd_pcm_stream_lock(substream1); + snd_pcm_group_assign(substream1, target_group); + snd_pcm_stream_unlock(substream1); + snd_pcm_group_unlock_irq(target_group, nonatomic); _end: - write_unlock_irq(&snd_pcm_link_rwlock); up_write(&snd_pcm_link_rwsem); _nolock: kfree(group); @@ -2018,22 +2088,27 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) static void relink_to_local(struct snd_pcm_substream *substream) { + snd_pcm_stream_lock(substream); snd_pcm_group_assign(substream, &substream->self_group); + snd_pcm_stream_unlock(substream); } static int snd_pcm_unlink(struct snd_pcm_substream *substream) { struct snd_pcm_group *group; + bool nonatomic = substream->pcm->nonatomic; + bool do_free = false; int res = 0; down_write_nonfifo(&snd_pcm_link_rwsem); - write_lock_irq(&snd_pcm_link_rwlock); + if (!snd_pcm_stream_linked(substream)) { res = -EALREADY; goto _end; } group = substream->group; + snd_pcm_group_lock_irq(group, nonatomic); relink_to_local(substream); @@ -2042,11 +2117,14 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) relink_to_local(list_first_entry(&group->substreams, struct snd_pcm_substream, link_list)); - kfree(group); + do_free = !refcount_read(&group->refs); } + snd_pcm_group_unlock_irq(group, nonatomic); + if (do_free) + kfree(group); + _end: - write_unlock_irq(&snd_pcm_link_rwlock); up_write(&snd_pcm_link_rwsem); return res; } -- cgit v1.2.3 From 51eea52d26d4939b788b7244c28cf47e902b4c4c Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 16 Jan 2019 16:13:31 +0100 Subject: pxa2xx: replace spi_master with spi_controller It's also a slave controller driver now, calling it "master" is slightly misleading. Signed-off-by: Lubomir Rintel Acked-by: Robert Jarzmik Signed-off-by: Mark Brown --- Documentation/spi/pxa2xx | 10 +-- arch/arm/mach-pxa/cm-x255.c | 2 +- arch/arm/mach-pxa/cm-x270.c | 2 +- arch/arm/mach-pxa/corgi.c | 2 +- arch/arm/mach-pxa/devices.c | 2 +- arch/arm/mach-pxa/em-x270.c | 4 +- arch/arm/mach-pxa/hx4700.c | 2 +- arch/arm/mach-pxa/icontrol.c | 4 +- arch/arm/mach-pxa/littleton.c | 2 +- arch/arm/mach-pxa/lubbock.c | 2 +- arch/arm/mach-pxa/magician.c | 2 +- arch/arm/mach-pxa/pcm027.c | 2 +- arch/arm/mach-pxa/poodle.c | 2 +- arch/arm/mach-pxa/spitz.c | 2 +- arch/arm/mach-pxa/stargate2.c | 6 +- arch/arm/mach-pxa/tosa.c | 2 +- arch/arm/mach-pxa/z2.c | 4 +- arch/arm/mach-pxa/zeus.c | 2 +- drivers/spi/spi-pxa2xx-dma.c | 58 +++++++-------- drivers/spi/spi-pxa2xx-pci.c | 4 +- drivers/spi/spi-pxa2xx.c | 156 ++++++++++++++++++++--------------------- drivers/spi/spi-pxa2xx.h | 4 +- include/linux/spi/pxa2xx_spi.h | 4 +- 23 files changed, 140 insertions(+), 140 deletions(-) (limited to 'include') diff --git a/Documentation/spi/pxa2xx b/Documentation/spi/pxa2xx index 13a0b7fb192f..551325b66b23 100644 --- a/Documentation/spi/pxa2xx +++ b/Documentation/spi/pxa2xx @@ -21,15 +21,15 @@ Typically a SPI master is defined in the arch/.../mach-*/board-*.c as a "platform device". The master configuration is passed to the driver via a table found in include/linux/spi/pxa2xx_spi.h: -struct pxa2xx_spi_master { +struct pxa2xx_spi_controller { u16 num_chipselect; u8 enable_dma; }; -The "pxa2xx_spi_master.num_chipselect" field is used to determine the number of +The "pxa2xx_spi_controller.num_chipselect" field is used to determine the number of slave device (chips) attached to this SPI master. -The "pxa2xx_spi_master.enable_dma" field informs the driver that SSP DMA should +The "pxa2xx_spi_controller.enable_dma" field informs the driver that SSP DMA should be used. This caused the driver to acquire two DMA channels: rx_channel and tx_channel. The rx_channel has a higher DMA service priority the tx_channel. See the "PXA2xx Developer Manual" section "DMA Controller". @@ -51,7 +51,7 @@ static struct resource pxa_spi_nssp_resources[] = { }, }; -static struct pxa2xx_spi_master pxa_nssp_master_info = { +static struct pxa2xx_spi_controller pxa_nssp_master_info = { .num_chipselect = 1, /* Matches the number of chips attached to NSSP */ .enable_dma = 1, /* Enables NSSP DMA */ }; @@ -206,7 +206,7 @@ DMA and PIO I/O Support ----------------------- The pxa2xx_spi driver supports both DMA and interrupt driven PIO message transfers. The driver defaults to PIO mode and DMA transfers must be enabled -by setting the "enable_dma" flag in the "pxa2xx_spi_master" structure. The DMA +by setting the "enable_dma" flag in the "pxa2xx_spi_controller" structure. The DMA mode supports both coherent and stream based DMA mappings. The following logic is used to determine the type of I/O to be used on diff --git a/arch/arm/mach-pxa/cm-x255.c b/arch/arm/mach-pxa/cm-x255.c index fa8e7dd4d898..4401dfcd7e68 100644 --- a/arch/arm/mach-pxa/cm-x255.c +++ b/arch/arm/mach-pxa/cm-x255.c @@ -98,7 +98,7 @@ static unsigned long cmx255_pin_config[] = { }; #if defined(CONFIG_SPI_PXA2XX) -static struct pxa2xx_spi_master pxa_ssp_master_info = { +static struct pxa2xx_spi_controller pxa_ssp_master_info = { .num_chipselect = 1, }; diff --git a/arch/arm/mach-pxa/cm-x270.c b/arch/arm/mach-pxa/cm-x270.c index f7081a50dc67..279eeca7add0 100644 --- a/arch/arm/mach-pxa/cm-x270.c +++ b/arch/arm/mach-pxa/cm-x270.c @@ -313,7 +313,7 @@ static inline void cmx270_init_mmc(void) {} #endif #if defined(CONFIG_SPI_PXA2XX) || defined(CONFIG_SPI_PXA2XX_MODULE) -static struct pxa2xx_spi_master cm_x270_spi_info = { +static struct pxa2xx_spi_controller cm_x270_spi_info = { .num_chipselect = 1, .enable_dma = 1, }; diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index c9732cace5e3..7ecf559bd71c 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -530,7 +530,7 @@ static struct pxa2xx_udc_mach_info udc_info __initdata = { }; #if IS_ENABLED(CONFIG_SPI_PXA2XX) -static struct pxa2xx_spi_master corgi_spi_info = { +static struct pxa2xx_spi_controller corgi_spi_info = { .num_chipselect = 3, }; diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c index a24783a03827..524d6093e0c7 100644 --- a/arch/arm/mach-pxa/devices.c +++ b/arch/arm/mach-pxa/devices.c @@ -1065,7 +1065,7 @@ struct platform_device pxa93x_device_gpio = { /* pxa2xx-spi platform-device ID equals respective SSP platform-device ID + 1. * See comment in arch/arm/mach-pxa/ssp.c::ssp_probe() */ -void __init pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info) +void __init pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info) { struct platform_device *pd; diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c index 32c1edeb3f14..5e372760f16e 100644 --- a/arch/arm/mach-pxa/em-x270.c +++ b/arch/arm/mach-pxa/em-x270.c @@ -689,7 +689,7 @@ static inline void em_x270_init_lcd(void) {} #endif #if defined(CONFIG_SPI_PXA2XX) || defined(CONFIG_SPI_PXA2XX_MODULE) -static struct pxa2xx_spi_master em_x270_spi_info = { +static struct pxa2xx_spi_controller em_x270_spi_info = { .num_chipselect = 1, }; @@ -703,7 +703,7 @@ static struct tdo24m_platform_data em_x270_tdo24m_pdata = { .model = TDO35S, }; -static struct pxa2xx_spi_master em_x270_spi_2_info = { +static struct pxa2xx_spi_controller em_x270_spi_2_info = { .num_chipselect = 1, .enable_dma = 1, }; diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c index b79b757fdd41..c3b47557b3f2 100644 --- a/arch/arm/mach-pxa/hx4700.c +++ b/arch/arm/mach-pxa/hx4700.c @@ -629,7 +629,7 @@ static struct spi_board_info tsc2046_board_info[] __initdata = { }, }; -static struct pxa2xx_spi_master pxa_ssp2_master_info = { +static struct pxa2xx_spi_controller pxa_ssp2_master_info = { .num_chipselect = 1, .enable_dma = 1, }; diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c index cbaf4f6edcda..7e30452e3840 100644 --- a/arch/arm/mach-pxa/icontrol.c +++ b/arch/arm/mach-pxa/icontrol.c @@ -115,12 +115,12 @@ static struct spi_board_info mcp251x_board_info[] = { } }; -static struct pxa2xx_spi_master pxa_ssp3_spi_master_info = { +static struct pxa2xx_spi_controller pxa_ssp3_spi_master_info = { .num_chipselect = 2, .enable_dma = 1 }; -static struct pxa2xx_spi_master pxa_ssp4_spi_master_info = { +static struct pxa2xx_spi_controller pxa_ssp4_spi_master_info = { .num_chipselect = 2, .enable_dma = 1 }; diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c index 39db4898dc4a..464b8bd2bcb9 100644 --- a/arch/arm/mach-pxa/littleton.c +++ b/arch/arm/mach-pxa/littleton.c @@ -191,7 +191,7 @@ static inline void littleton_init_lcd(void) {}; #endif /* CONFIG_FB_PXA || CONFIG_FB_PXA_MODULE */ #if defined(CONFIG_SPI_PXA2XX) || defined(CONFIG_SPI_PXA2XX_MODULE) -static struct pxa2xx_spi_master littleton_spi_info = { +static struct pxa2xx_spi_controller littleton_spi_info = { .num_chipselect = 1, }; diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c index a1391e113ef4..c1bd0d544981 100644 --- a/arch/arm/mach-pxa/lubbock.c +++ b/arch/arm/mach-pxa/lubbock.c @@ -197,7 +197,7 @@ static struct platform_device sa1111_device = { * (to J5) and poking board registers (as done below). Else it's only useful * for the temperature sensors. */ -static struct pxa2xx_spi_master pxa_ssp_master_info = { +static struct pxa2xx_spi_controller pxa_ssp_master_info = { .num_chipselect = 1, }; diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c index 08b079653c3f..618bcff4cdc9 100644 --- a/arch/arm/mach-pxa/magician.c +++ b/arch/arm/mach-pxa/magician.c @@ -932,7 +932,7 @@ struct pxa2xx_spi_chip tsc2046_chip_info = { .gpio_cs = GPIO14_MAGICIAN_TSC2046_CS, }; -static struct pxa2xx_spi_master magician_spi_info = { +static struct pxa2xx_spi_controller magician_spi_info = { .num_chipselect = 1, .enable_dma = 1, }; diff --git a/arch/arm/mach-pxa/pcm027.c b/arch/arm/mach-pxa/pcm027.c index ccca9f7575c3..e2e613449660 100644 --- a/arch/arm/mach-pxa/pcm027.c +++ b/arch/arm/mach-pxa/pcm027.c @@ -132,7 +132,7 @@ static struct platform_device smc91x_device = { /* * SPI host and devices */ -static struct pxa2xx_spi_master pxa_ssp_master_info = { +static struct pxa2xx_spi_controller pxa_ssp_master_info = { .num_chipselect = 1, }; diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c index c2a43d4cfd3e..9450a523cd0b 100644 --- a/arch/arm/mach-pxa/poodle.c +++ b/arch/arm/mach-pxa/poodle.c @@ -196,7 +196,7 @@ struct platform_device poodle_locomo_device = { EXPORT_SYMBOL(poodle_locomo_device); #if defined(CONFIG_SPI_PXA2XX) || defined(CONFIG_SPI_PXA2XX_MODULE) -static struct pxa2xx_spi_master poodle_spi_info = { +static struct pxa2xx_spi_controller poodle_spi_info = { .num_chipselect = 1, }; diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 306818e2cf54..8dac824a85df 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -572,7 +572,7 @@ static struct spi_board_info spitz_spi_devices[] = { }, }; -static struct pxa2xx_spi_master spitz_spi_info = { +static struct pxa2xx_spi_controller spitz_spi_info = { .num_chipselect = 3, }; diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c index e0d6c872270a..c28d19b126a7 100644 --- a/arch/arm/mach-pxa/stargate2.c +++ b/arch/arm/mach-pxa/stargate2.c @@ -337,15 +337,15 @@ static struct platform_device stargate2_flash_device = { .num_resources = 1, }; -static struct pxa2xx_spi_master pxa_ssp_master_0_info = { +static struct pxa2xx_spi_controller pxa_ssp_master_0_info = { .num_chipselect = 1, }; -static struct pxa2xx_spi_master pxa_ssp_master_1_info = { +static struct pxa2xx_spi_controller pxa_ssp_master_1_info = { .num_chipselect = 1, }; -static struct pxa2xx_spi_master pxa_ssp_master_2_info = { +static struct pxa2xx_spi_controller pxa_ssp_master_2_info = { .num_chipselect = 1, }; diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c index e8a93c088c35..7439798d58e4 100644 --- a/arch/arm/mach-pxa/tosa.c +++ b/arch/arm/mach-pxa/tosa.c @@ -813,7 +813,7 @@ static struct platform_device tosa_bt_device = { .dev.platform_data = &tosa_bt_data, }; -static struct pxa2xx_spi_master pxa_ssp_master_info = { +static struct pxa2xx_spi_controller pxa_ssp_master_info = { .num_chipselect = 1, }; diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c index e2353e75bb28..ad082e11e2a4 100644 --- a/arch/arm/mach-pxa/z2.c +++ b/arch/arm/mach-pxa/z2.c @@ -607,12 +607,12 @@ static struct spi_board_info spi_board_info[] __initdata = { }, }; -static struct pxa2xx_spi_master pxa_ssp1_master_info = { +static struct pxa2xx_spi_controller pxa_ssp1_master_info = { .num_chipselect = 1, .enable_dma = 1, }; -static struct pxa2xx_spi_master pxa_ssp2_master_info = { +static struct pxa2xx_spi_controller pxa_ssp2_master_info = { .num_chipselect = 1, }; diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c index c411f79d4cb5..bdbcf46595f9 100644 --- a/arch/arm/mach-pxa/zeus.c +++ b/arch/arm/mach-pxa/zeus.c @@ -391,7 +391,7 @@ static struct platform_device zeus_sram_device = { }; /* SPI interface on SSP3 */ -static struct pxa2xx_spi_master pxa2xx_spi_ssp3_master_info = { +static struct pxa2xx_spi_controller pxa2xx_spi_ssp3_master_info = { .num_chipselect = 1, .enable_dma = 1, }; diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c index 2fa7f4b43492..15592598273e 100644 --- a/drivers/spi/spi-pxa2xx-dma.c +++ b/drivers/spi/spi-pxa2xx-dma.c @@ -23,7 +23,7 @@ static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data, bool error) { - struct spi_message *msg = drv_data->master->cur_msg; + struct spi_message *msg = drv_data->controller->cur_msg; /* * It is possible that one CPU is handling ROR interrupt and other @@ -59,7 +59,7 @@ static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data, msg->status = -EIO; } - spi_finalize_current_transfer(drv_data->master); + spi_finalize_current_transfer(drv_data->controller); } } @@ -74,7 +74,7 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data, struct spi_transfer *xfer) { struct chip_data *chip = - spi_get_ctldata(drv_data->master->cur_msg->spi); + spi_get_ctldata(drv_data->controller->cur_msg->spi); enum dma_slave_buswidth width; struct dma_slave_config cfg; struct dma_chan *chan; @@ -102,14 +102,14 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data, cfg.dst_maxburst = chip->dma_burst_size; sgt = &xfer->tx_sg; - chan = drv_data->master->dma_tx; + chan = drv_data->controller->dma_tx; } else { cfg.src_addr = drv_data->ssdr_physical; cfg.src_addr_width = width; cfg.src_maxburst = chip->dma_burst_size; sgt = &xfer->rx_sg; - chan = drv_data->master->dma_rx; + chan = drv_data->controller->dma_rx; } ret = dmaengine_slave_config(chan, &cfg); @@ -130,8 +130,8 @@ irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data) if (status & SSSR_ROR) { dev_err(&drv_data->pdev->dev, "FIFO overrun\n"); - dmaengine_terminate_async(drv_data->master->dma_rx); - dmaengine_terminate_async(drv_data->master->dma_tx); + dmaengine_terminate_async(drv_data->controller->dma_rx); + dmaengine_terminate_async(drv_data->controller->dma_tx); pxa2xx_spi_dma_transfer_complete(drv_data, true); return IRQ_HANDLED; @@ -171,15 +171,15 @@ int pxa2xx_spi_dma_prepare(struct driver_data *drv_data, return 0; err_rx: - dmaengine_terminate_async(drv_data->master->dma_tx); + dmaengine_terminate_async(drv_data->controller->dma_tx); err_tx: return err; } void pxa2xx_spi_dma_start(struct driver_data *drv_data) { - dma_async_issue_pending(drv_data->master->dma_rx); - dma_async_issue_pending(drv_data->master->dma_tx); + dma_async_issue_pending(drv_data->controller->dma_rx); + dma_async_issue_pending(drv_data->controller->dma_tx); atomic_set(&drv_data->dma_running, 1); } @@ -187,30 +187,30 @@ void pxa2xx_spi_dma_start(struct driver_data *drv_data) void pxa2xx_spi_dma_stop(struct driver_data *drv_data) { atomic_set(&drv_data->dma_running, 0); - dmaengine_terminate_sync(drv_data->master->dma_rx); - dmaengine_terminate_sync(drv_data->master->dma_tx); + dmaengine_terminate_sync(drv_data->controller->dma_rx); + dmaengine_terminate_sync(drv_data->controller->dma_tx); } int pxa2xx_spi_dma_setup(struct driver_data *drv_data) { - struct pxa2xx_spi_master *pdata = drv_data->master_info; + struct pxa2xx_spi_controller *pdata = drv_data->controller_info; struct device *dev = &drv_data->pdev->dev; - struct spi_controller *master = drv_data->master; + struct spi_controller *controller = drv_data->controller; dma_cap_mask_t mask; dma_cap_zero(mask); dma_cap_set(DMA_SLAVE, mask); - master->dma_tx = dma_request_slave_channel_compat(mask, + controller->dma_tx = dma_request_slave_channel_compat(mask, pdata->dma_filter, pdata->tx_param, dev, "tx"); - if (!master->dma_tx) + if (!controller->dma_tx) return -ENODEV; - master->dma_rx = dma_request_slave_channel_compat(mask, + controller->dma_rx = dma_request_slave_channel_compat(mask, pdata->dma_filter, pdata->rx_param, dev, "rx"); - if (!master->dma_rx) { - dma_release_channel(master->dma_tx); - master->dma_tx = NULL; + if (!controller->dma_rx) { + dma_release_channel(controller->dma_tx); + controller->dma_tx = NULL; return -ENODEV; } @@ -219,17 +219,17 @@ int pxa2xx_spi_dma_setup(struct driver_data *drv_data) void pxa2xx_spi_dma_release(struct driver_data *drv_data) { - struct spi_controller *master = drv_data->master; + struct spi_controller *controller = drv_data->controller; - if (master->dma_rx) { - dmaengine_terminate_sync(master->dma_rx); - dma_release_channel(master->dma_rx); - master->dma_rx = NULL; + if (controller->dma_rx) { + dmaengine_terminate_sync(controller->dma_rx); + dma_release_channel(controller->dma_rx); + controller->dma_rx = NULL; } - if (master->dma_tx) { - dmaengine_terminate_sync(master->dma_tx); - dma_release_channel(master->dma_tx); - master->dma_tx = NULL; + if (controller->dma_tx) { + dmaengine_terminate_sync(controller->dma_tx); + dma_release_channel(controller->dma_tx); + controller->dma_tx = NULL; } } diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c index 869f188b02eb..1727fdfbac28 100644 --- a/drivers/spi/spi-pxa2xx-pci.c +++ b/drivers/spi/spi-pxa2xx-pci.c @@ -197,7 +197,7 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev, struct platform_device_info pi; int ret; struct platform_device *pdev; - struct pxa2xx_spi_master spi_pdata; + struct pxa2xx_spi_controller spi_pdata; struct ssp_device *ssp; struct pxa_spi_info *c; char buf[40]; @@ -265,7 +265,7 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev, static void pxa2xx_spi_pci_remove(struct pci_dev *dev) { struct platform_device *pdev = pci_get_drvdata(dev); - struct pxa2xx_spi_master *spi_pdata; + struct pxa2xx_spi_controller *spi_pdata; spi_pdata = dev_get_platdata(&pdev->dev); diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index d84b893a64d7..69e874a2ad1e 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -328,7 +328,7 @@ static void lpss_ssp_setup(struct driver_data *drv_data) __lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value); /* Enable multiblock DMA transfers */ - if (drv_data->master_info->enable_dma) { + if (drv_data->controller_info->enable_dma) { __lpss_ssp_write_priv(drv_data, config->reg_ssp, 1); if (config->reg_general >= 0) { @@ -368,7 +368,7 @@ static void lpss_ssp_select_cs(struct spi_device *spi, __lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value); ndelay(1000000000 / - (drv_data->master->max_speed_hz / 2)); + (drv_data->controller->max_speed_hz / 2)); } } @@ -567,7 +567,7 @@ static int u32_reader(struct driver_data *drv_data) static void reset_sccr1(struct driver_data *drv_data) { struct chip_data *chip = - spi_get_ctldata(drv_data->master->cur_msg->spi); + spi_get_ctldata(drv_data->controller->cur_msg->spi); u32 sccr1_reg; sccr1_reg = pxa2xx_spi_read(drv_data, SSCR1) & ~drv_data->int_cr1; @@ -599,8 +599,8 @@ static void int_error_stop(struct driver_data *drv_data, const char* msg) dev_err(&drv_data->pdev->dev, "%s\n", msg); - drv_data->master->cur_msg->status = -EIO; - spi_finalize_current_transfer(drv_data->master); + drv_data->controller->cur_msg->status = -EIO; + spi_finalize_current_transfer(drv_data->controller); } static void int_transfer_complete(struct driver_data *drv_data) @@ -611,7 +611,7 @@ static void int_transfer_complete(struct driver_data *drv_data) if (!pxa25x_ssp_comp(drv_data)) pxa2xx_spi_write(drv_data, SSTO, 0); - spi_finalize_current_transfer(drv_data->master); + spi_finalize_current_transfer(drv_data->controller); } static irqreturn_t interrupt_transfer(struct driver_data *drv_data) @@ -747,7 +747,7 @@ static irqreturn_t ssp_int(int irq, void *dev_id) pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg & ~drv_data->int_cr1); pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg); - if (!drv_data->master->cur_msg) { + if (!drv_data->controller->cur_msg) { handle_bad_msg(drv_data); /* Never fail */ return IRQ_HANDLED; @@ -879,7 +879,7 @@ static unsigned int quark_x1000_get_clk_div(int rate, u32 *dds) static unsigned int ssp_get_clk_div(struct driver_data *drv_data, int rate) { - unsigned long ssp_clk = drv_data->master->max_speed_hz; + unsigned long ssp_clk = drv_data->controller->max_speed_hz; const struct ssp_device *ssp = drv_data->ssp; rate = min_t(int, ssp_clk, rate); @@ -894,7 +894,7 @@ static unsigned int pxa2xx_ssp_get_clk_div(struct driver_data *drv_data, int rate) { struct chip_data *chip = - spi_get_ctldata(drv_data->master->cur_msg->spi); + spi_get_ctldata(drv_data->controller->cur_msg->spi); unsigned int clk_div; switch (drv_data->ssp_type) { @@ -908,7 +908,7 @@ static unsigned int pxa2xx_ssp_get_clk_div(struct driver_data *drv_data, return clk_div << 8; } -static bool pxa2xx_spi_can_dma(struct spi_controller *master, +static bool pxa2xx_spi_can_dma(struct spi_controller *controller, struct spi_device *spi, struct spi_transfer *xfer) { @@ -919,12 +919,12 @@ static bool pxa2xx_spi_can_dma(struct spi_controller *master, xfer->len >= chip->dma_burst_size; } -static int pxa2xx_spi_transfer_one(struct spi_controller *master, +static int pxa2xx_spi_transfer_one(struct spi_controller *controller, struct spi_device *spi, struct spi_transfer *transfer) { - struct driver_data *drv_data = spi_controller_get_devdata(master); - struct spi_message *message = master->cur_msg; + struct driver_data *drv_data = spi_controller_get_devdata(controller); + struct spi_message *message = controller->cur_msg; struct chip_data *chip = spi_get_ctldata(message->spi); u32 dma_thresh = chip->dma_threshold; u32 dma_burst = chip->dma_burst_size; @@ -1006,9 +1006,9 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *master, "DMA burst size reduced to match bits_per_word\n"); } - dma_mapped = master->can_dma && - master->can_dma(master, message->spi, transfer) && - master->cur_msg_mapped; + dma_mapped = controller->can_dma && + controller->can_dma(controller, message->spi, transfer) && + controller->cur_msg_mapped; if (dma_mapped) { /* Ensure we have the correct interrupt handler */ @@ -1036,12 +1036,12 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *master, cr0 = pxa2xx_configure_sscr0(drv_data, clk_div, bits); if (!pxa25x_ssp_comp(drv_data)) dev_dbg(&message->spi->dev, "%u Hz actual, %s\n", - master->max_speed_hz + controller->max_speed_hz / (1 + ((cr0 & SSCR0_SCR(0xfff)) >> 8)), dma_mapped ? "DMA" : "PIO"); else dev_dbg(&message->spi->dev, "%u Hz actual, %s\n", - master->max_speed_hz / 2 + controller->max_speed_hz / 2 / (1 + ((cr0 & SSCR0_SCR(0x0ff)) >> 8)), dma_mapped ? "DMA" : "PIO"); @@ -1092,7 +1092,7 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *master, } } - if (spi_controller_is_slave(master)) { + if (spi_controller_is_slave(controller)) { while (drv_data->write(drv_data)) ; if (drv_data->gpiod_ready) { @@ -1111,9 +1111,9 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *master, return 1; } -static int pxa2xx_spi_slave_abort(struct spi_master *master) +static int pxa2xx_spi_slave_abort(struct spi_controller *controller) { - struct driver_data *drv_data = spi_controller_get_devdata(master); + struct driver_data *drv_data = spi_controller_get_devdata(controller); /* Stop and reset SSP */ write_SSSR_CS(drv_data, drv_data->clear_sr); @@ -1126,16 +1126,16 @@ static int pxa2xx_spi_slave_abort(struct spi_master *master) dev_dbg(&drv_data->pdev->dev, "transfer aborted\n"); - drv_data->master->cur_msg->status = -EINTR; - spi_finalize_current_transfer(drv_data->master); + drv_data->controller->cur_msg->status = -EINTR; + spi_finalize_current_transfer(drv_data->controller); return 0; } -static void pxa2xx_spi_handle_err(struct spi_controller *master, +static void pxa2xx_spi_handle_err(struct spi_controller *controller, struct spi_message *msg) { - struct driver_data *drv_data = spi_controller_get_devdata(master); + struct driver_data *drv_data = spi_controller_get_devdata(controller); /* Disable the SSP */ pxa2xx_spi_write(drv_data, SSCR0, @@ -1159,9 +1159,9 @@ static void pxa2xx_spi_handle_err(struct spi_controller *master, pxa2xx_spi_dma_stop(drv_data); } -static int pxa2xx_spi_unprepare_transfer(struct spi_controller *master) +static int pxa2xx_spi_unprepare_transfer(struct spi_controller *controller) { - struct driver_data *drv_data = spi_controller_get_devdata(master); + struct driver_data *drv_data = spi_controller_get_devdata(controller); /* Disable the SSP now */ pxa2xx_spi_write(drv_data, SSCR0, @@ -1260,7 +1260,7 @@ static int setup(struct spi_device *spi) break; default: tx_hi_thres = 0; - if (spi_controller_is_slave(drv_data->master)) { + if (spi_controller_is_slave(drv_data->controller)) { tx_thres = 1; rx_thres = 2; } else { @@ -1287,7 +1287,7 @@ static int setup(struct spi_device *spi) chip->frm = spi->chip_select; } - chip->enable_dma = drv_data->master_info->enable_dma; + chip->enable_dma = drv_data->controller_info->enable_dma; chip->timeout = TIMOUT_DFLT; } @@ -1310,7 +1310,7 @@ static int setup(struct spi_device *spi) if (chip_info->enable_loopback) chip->cr1 = SSCR1_LBM; } - if (spi_controller_is_slave(drv_data->master)) { + if (spi_controller_is_slave(drv_data->controller)) { chip->cr1 |= SSCR1_SCFR; chip->cr1 |= SSCR1_SCLKDIR; chip->cr1 |= SSCR1_SFRMDIR; @@ -1497,10 +1497,10 @@ static bool pxa2xx_spi_idma_filter(struct dma_chan *chan, void *param) #endif /* CONFIG_PCI */ -static struct pxa2xx_spi_master * +static struct pxa2xx_spi_controller * pxa2xx_spi_init_pdata(struct platform_device *pdev) { - struct pxa2xx_spi_master *pdata; + struct pxa2xx_spi_controller *pdata; struct acpi_device *adev; struct ssp_device *ssp; struct resource *res; @@ -1568,10 +1568,10 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev) return pdata; } -static int pxa2xx_spi_fw_translate_cs(struct spi_controller *master, +static int pxa2xx_spi_fw_translate_cs(struct spi_controller *controller, unsigned int cs) { - struct driver_data *drv_data = spi_controller_get_devdata(master); + struct driver_data *drv_data = spi_controller_get_devdata(controller); if (has_acpi_companion(&drv_data->pdev->dev)) { switch (drv_data->ssp_type) { @@ -1595,8 +1595,8 @@ static int pxa2xx_spi_fw_translate_cs(struct spi_controller *master, static int pxa2xx_spi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct pxa2xx_spi_master *platform_info; - struct spi_controller *master; + struct pxa2xx_spi_controller *platform_info; + struct spi_controller *controller; struct driver_data *drv_data; struct ssp_device *ssp; const struct lpss_config *config; @@ -1622,37 +1622,37 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) } if (platform_info->is_slave) - master = spi_alloc_slave(dev, sizeof(struct driver_data)); + controller = spi_alloc_slave(dev, sizeof(struct driver_data)); else - master = spi_alloc_master(dev, sizeof(struct driver_data)); + controller = spi_alloc_master(dev, sizeof(struct driver_data)); - if (!master) { - dev_err(&pdev->dev, "cannot alloc spi_master\n"); + if (!controller) { + dev_err(&pdev->dev, "cannot alloc spi_controller\n"); pxa_ssp_free(ssp); return -ENOMEM; } - drv_data = spi_controller_get_devdata(master); - drv_data->master = master; - drv_data->master_info = platform_info; + drv_data = spi_controller_get_devdata(controller); + drv_data->controller = controller; + drv_data->controller_info = platform_info; drv_data->pdev = pdev; drv_data->ssp = ssp; - master->dev.of_node = pdev->dev.of_node; + controller->dev.of_node = pdev->dev.of_node; /* the spi->mode bits understood by this driver: */ - master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP; - - master->bus_num = ssp->port_id; - master->dma_alignment = DMA_ALIGNMENT; - master->cleanup = cleanup; - master->setup = setup; - master->set_cs = pxa2xx_spi_set_cs; - master->transfer_one = pxa2xx_spi_transfer_one; - master->slave_abort = pxa2xx_spi_slave_abort; - master->handle_err = pxa2xx_spi_handle_err; - master->unprepare_transfer_hardware = pxa2xx_spi_unprepare_transfer; - master->fw_translate_cs = pxa2xx_spi_fw_translate_cs; - master->auto_runtime_pm = true; - master->flags = SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX; + controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP; + + controller->bus_num = ssp->port_id; + controller->dma_alignment = DMA_ALIGNMENT; + controller->cleanup = cleanup; + controller->setup = setup; + controller->set_cs = pxa2xx_spi_set_cs; + controller->transfer_one = pxa2xx_spi_transfer_one; + controller->slave_abort = pxa2xx_spi_slave_abort; + controller->handle_err = pxa2xx_spi_handle_err; + controller->unprepare_transfer_hardware = pxa2xx_spi_unprepare_transfer; + controller->fw_translate_cs = pxa2xx_spi_fw_translate_cs; + controller->auto_runtime_pm = true; + controller->flags = SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX; drv_data->ssp_type = ssp->type; @@ -1661,10 +1661,10 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) if (pxa25x_ssp_comp(drv_data)) { switch (drv_data->ssp_type) { case QUARK_X1000_SSP: - master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32); + controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32); break; default: - master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16); + controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16); break; } @@ -1673,7 +1673,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) drv_data->clear_sr = SSSR_ROR; drv_data->mask_sr = SSSR_RFS | SSSR_TFS | SSSR_ROR; } else { - master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32); + controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32); drv_data->int_cr1 = SSCR1_TIE | SSCR1_RIE | SSCR1_TINTE; drv_data->dma_cr1 = DEFAULT_DMA_CR1; drv_data->clear_sr = SSSR_ROR | SSSR_TINT; @@ -1685,7 +1685,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) drv_data); if (status < 0) { dev_err(&pdev->dev, "cannot get IRQ %d\n", ssp->irq); - goto out_error_master_alloc; + goto out_error_controller_alloc; } /* Setup DMA if requested */ @@ -1695,7 +1695,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) dev_dbg(dev, "no DMA channels available, using PIO\n"); platform_info->enable_dma = false; } else { - master->can_dma = pxa2xx_spi_can_dma; + controller->can_dma = pxa2xx_spi_can_dma; } } @@ -1704,7 +1704,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) if (status) goto out_error_dma_irq_alloc; - master->max_speed_hz = clk_get_rate(ssp->clk); + controller->max_speed_hz = clk_get_rate(ssp->clk); /* Load default SSP configuration */ pxa2xx_spi_write(drv_data, SSCR0, 0); @@ -1727,7 +1727,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) break; default: - if (spi_controller_is_slave(master)) { + if (spi_controller_is_slave(controller)) { tmp = SSCR1_SCFR | SSCR1_SCLKDIR | SSCR1_SFRMDIR | @@ -1740,7 +1740,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) } pxa2xx_spi_write(drv_data, SSCR1, tmp); tmp = SSCR0_Motorola | SSCR0_DataSize(8); - if (!spi_controller_is_slave(master)) + if (!spi_controller_is_slave(controller)) tmp |= SSCR0_SCR(2); pxa2xx_spi_write(drv_data, SSCR0, tmp); break; @@ -1765,24 +1765,24 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) platform_info->num_chipselect = config->cs_num; } } - master->num_chipselect = platform_info->num_chipselect; + controller->num_chipselect = platform_info->num_chipselect; count = gpiod_count(&pdev->dev, "cs"); if (count > 0) { int i; - master->num_chipselect = max_t(int, count, - master->num_chipselect); + controller->num_chipselect = max_t(int, count, + controller->num_chipselect); drv_data->cs_gpiods = devm_kcalloc(&pdev->dev, - master->num_chipselect, sizeof(struct gpio_desc *), + controller->num_chipselect, sizeof(struct gpio_desc *), GFP_KERNEL); if (!drv_data->cs_gpiods) { status = -ENOMEM; goto out_error_clock_enabled; } - for (i = 0; i < master->num_chipselect; i++) { + for (i = 0; i < controller->num_chipselect; i++) { struct gpio_desc *gpiod; gpiod = devm_gpiod_get_index(dev, "cs", i, GPIOD_ASIS); @@ -1815,9 +1815,9 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) /* Register with the SPI framework */ platform_set_drvdata(pdev, drv_data); - status = devm_spi_register_controller(&pdev->dev, master); + status = devm_spi_register_controller(&pdev->dev, controller); if (status != 0) { - dev_err(&pdev->dev, "problem registering spi master\n"); + dev_err(&pdev->dev, "problem registering spi controller\n"); goto out_error_clock_enabled; } @@ -1832,8 +1832,8 @@ out_error_dma_irq_alloc: pxa2xx_spi_dma_release(drv_data); free_irq(ssp->irq, drv_data); -out_error_master_alloc: - spi_controller_put(master); +out_error_controller_alloc: + spi_controller_put(controller); pxa_ssp_free(ssp); return status; } @@ -1854,7 +1854,7 @@ static int pxa2xx_spi_remove(struct platform_device *pdev) clk_disable_unprepare(ssp->clk); /* Release DMA */ - if (drv_data->master_info->enable_dma) + if (drv_data->controller_info->enable_dma) pxa2xx_spi_dma_release(drv_data); pm_runtime_put_noidle(&pdev->dev); @@ -1876,7 +1876,7 @@ static int pxa2xx_spi_suspend(struct device *dev) struct ssp_device *ssp = drv_data->ssp; int status; - status = spi_controller_suspend(drv_data->master); + status = spi_controller_suspend(drv_data->controller); if (status != 0) return status; pxa2xx_spi_write(drv_data, SSCR0, 0); @@ -1901,7 +1901,7 @@ static int pxa2xx_spi_resume(struct device *dev) } /* Start the queue running */ - return spi_controller_resume(drv_data->master); + return spi_controller_resume(drv_data->controller); } #endif diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h index 4e324da66ef7..aba777b4502d 100644 --- a/drivers/spi/spi-pxa2xx.h +++ b/drivers/spi/spi-pxa2xx.h @@ -31,10 +31,10 @@ struct driver_data { /* SPI framework hookup */ enum pxa_ssp_type ssp_type; - struct spi_controller *master; + struct spi_controller *controller; /* PXA hookup */ - struct pxa2xx_spi_master *master_info; + struct pxa2xx_spi_controller *controller_info; /* SSP register addresses */ void __iomem *ioaddr; diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index b0674e330ef6..c1c59473cef9 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -22,7 +22,7 @@ struct dma_chan; /* device.platform_data for SSP controller devices */ -struct pxa2xx_spi_master { +struct pxa2xx_spi_controller { u16 num_chipselect; u8 enable_dma; bool is_slave; @@ -54,7 +54,7 @@ struct pxa2xx_spi_chip { #include -extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info); +extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info); #endif #endif -- cgit v1.2.3 From a2d21848d9211dad5e786aa7368709ca8938834e Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Tue, 22 Jan 2019 11:42:24 +0200 Subject: regmap: regmap-irq: Add main status register support There is bunch of devices with multiple logical blocks which can generate interrupts. It's not a rare case that the interrupt reason registers are arranged so that there is own status/ack/mask register for each logical block. In some devices there is also a 'main interrupt register(s)' which can indicate what sub blocks have interrupts pending. When such a device is connected via slow bus like i2c the main part of interrupt handling latency can be caused by bus accesses. On systems where it is expected that only one (or few) sub blocks have active interrupts we can reduce the latency by only reading the main register and those sub registers which have active interrupts. Support this with regmap-irq for simple cases where main register does not require acking or masking. Signed-off-by: Matti Vaittinen Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-irq.c | 99 ++++++++++++++++++++++++++++++++++++++-- include/linux/regmap.h | 31 +++++++++++++ 2 files changed, 126 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 1bd1145ad8b5..22778e9501ff 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -35,6 +35,7 @@ struct regmap_irq_chip_data { int wake_count; void *status_reg_buf; + unsigned int *main_status_buf; unsigned int *status_buf; unsigned int *mask_buf; unsigned int *mask_buf_def; @@ -326,6 +327,33 @@ static const struct irq_chip regmap_irq_chip = { .irq_set_wake = regmap_irq_set_wake, }; +static inline int read_sub_irq_data(struct regmap_irq_chip_data *data, + unsigned int b) +{ + const struct regmap_irq_chip *chip = data->chip; + struct regmap *map = data->map; + struct regmap_irq_sub_irq_map *subreg; + int i, ret = 0; + + if (!chip->sub_reg_offsets) { + /* Assume linear mapping */ + ret = regmap_read(map, chip->status_base + + (b * map->reg_stride * data->irq_reg_stride), + &data->status_buf[b]); + } else { + subreg = &chip->sub_reg_offsets[b]; + for (i = 0; i < subreg->num_regs; i++) { + unsigned int offset = subreg->offset[i]; + + ret = regmap_read(map, chip->status_base + offset, + &data->status_buf[offset]); + if (ret) + break; + } + } + return ret; +} + static irqreturn_t regmap_irq_thread(int irq, void *d) { struct regmap_irq_chip_data *data = d; @@ -349,11 +377,65 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) } /* - * Read in the statuses, using a single bulk read if possible - * in order to reduce the I/O overheads. + * Read only registers with active IRQs if the chip has 'main status + * register'. Else read in the statuses, using a single bulk read if + * possible in order to reduce the I/O overheads. */ - if (!map->use_single_read && map->reg_stride == 1 && - data->irq_reg_stride == 1) { + + if (chip->num_main_regs) { + unsigned int max_main_bits; + unsigned long size; + + size = chip->num_regs * sizeof(unsigned int); + + max_main_bits = (chip->num_main_status_bits) ? + chip->num_main_status_bits : chip->num_regs; + /* Clear the status buf as we don't read all status regs */ + memset(data->status_buf, 0, size); + + /* We could support bulk read for main status registers + * but I don't expect to see devices with really many main + * status registers so let's only support single reads for the + * sake of simplicity. and add bulk reads only if needed + */ + for (i = 0; i < chip->num_main_regs; i++) { + ret = regmap_read(map, chip->main_status + + (i * map->reg_stride + * data->irq_reg_stride), + &data->main_status_buf[i]); + if (ret) { + dev_err(map->dev, + "Failed to read IRQ status %d\n", + ret); + goto exit; + } + } + + /* Read sub registers with active IRQs */ + for (i = 0; i < chip->num_main_regs; i++) { + unsigned int b; + const unsigned long mreg = data->main_status_buf[i]; + + for_each_set_bit(b, &mreg, map->format.val_bytes * 8) { + if (i * map->format.val_bytes * 8 + b > + max_main_bits) + break; + ret = read_sub_irq_data(data, b); + + if (ret != 0) { + dev_err(map->dev, + "Failed to read IRQ status %d\n", + ret); + if (chip->runtime_pm) + pm_runtime_put(map->dev); + goto exit; + } + } + + } + } else if (!map->use_single_read && map->reg_stride == 1 && + data->irq_reg_stride == 1) { + u8 *buf8 = data->status_reg_buf; u16 *buf16 = data->status_reg_buf; u32 *buf32 = data->status_reg_buf; @@ -518,6 +600,15 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, if (!d) return -ENOMEM; + if (chip->num_main_regs) { + d->main_status_buf = kcalloc(chip->num_main_regs, + sizeof(unsigned int), + GFP_KERNEL); + + if (!d->main_status_buf) + goto err_alloc; + } + d->status_buf = kcalloc(chip->num_regs, sizeof(unsigned int), GFP_KERNEL); if (!d->status_buf) diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 1781b6cb793c..daeec7dbd65c 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1131,11 +1131,37 @@ struct regmap_irq { .reg_offset = (_id) / (_reg_bits), \ } +#define REGMAP_IRQ_MAIN_REG_OFFSET(arr) \ + { .num_regs = ARRAY_SIZE((arr)), .offset = &(arr)[0] } + +struct regmap_irq_sub_irq_map { + unsigned int num_regs; + unsigned int *offset; +}; + /** * struct regmap_irq_chip - Description of a generic regmap irq_chip. * * @name: Descriptive name for IRQ controller. * + * @main_status: Base main status register address. For chips which have + * interrupts arranged in separate sub-irq blocks with own IRQ + * registers and which have a main IRQ registers indicating + * sub-irq blocks with unhandled interrupts. For such chips fill + * sub-irq register information in status_base, mask_base and + * ack_base. + * @num_main_status_bits: Should be given to chips where number of meaningfull + * main status bits differs from num_regs. + * @sub_reg_offsets: arrays of mappings from main register bits to sub irq + * registers. First item in array describes the registers + * for first main status bit. Second array for second bit etc. + * Offset is given as sub register status offset to + * status_base. Should contain num_regs arrays. + * Can be provided for chips with more complex mapping than + * 1.st bit to 1.st sub-reg, 2.nd bit to 2.nd sub-reg, ... + * @num_main_regs: Number of 'main status' irq registers for chips which have + * main_status set. + * * @status_base: Base status register address. * @mask_base: Base mask register address. * @mask_writeonly: Base mask register is write only. @@ -1181,6 +1207,11 @@ struct regmap_irq { struct regmap_irq_chip { const char *name; + unsigned int main_status; + unsigned int num_main_status_bits; + struct regmap_irq_sub_irq_map *sub_reg_offsets; + int num_main_regs; + unsigned int status_base; unsigned int mask_base; unsigned int unmask_base; -- cgit v1.2.3 From f0125f1a559be1033055f44e511174aaa75b60cc Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 23 Jan 2019 17:29:53 +0000 Subject: spi: Go back to immediate teardown Commit 412e6037324 ("spi: core: avoid waking pump thread from spi_sync instead run teardown delayed") introduced regressions on some boards, apparently connected to spi_mem not triggering shutdown properly any more. Since we've thus far been unable to figure out exactly where the breakage is revert the optimisation for now. Reported-by: Jon Hunter Signed-off-by: Mark Brown Cc: kernel@martin.sperl.org --- drivers/spi/spi.c | 122 +++++++++++++----------------------------------- include/linux/spi/spi.h | 2 - 2 files changed, 33 insertions(+), 91 deletions(-) (limited to 'include') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 06b9139664a3..13f447a67d67 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1225,7 +1225,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) return; } - /* If another context is idling the device then defer to kthread */ + /* If another context is idling the device then defer */ if (ctlr->idling) { kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages); spin_unlock_irqrestore(&ctlr->queue_lock, flags); @@ -1239,10 +1239,34 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) return; } - /* schedule idle teardown with a delay of 1 second */ - kthread_mod_delayed_work(&ctlr->kworker, - &ctlr->pump_idle_teardown, - HZ); + /* Only do teardown in the thread */ + if (!in_kthread) { + kthread_queue_work(&ctlr->kworker, + &ctlr->pump_messages); + spin_unlock_irqrestore(&ctlr->queue_lock, flags); + return; + } + + ctlr->busy = false; + ctlr->idling = true; + spin_unlock_irqrestore(&ctlr->queue_lock, flags); + + kfree(ctlr->dummy_rx); + ctlr->dummy_rx = NULL; + kfree(ctlr->dummy_tx); + ctlr->dummy_tx = NULL; + if (ctlr->unprepare_transfer_hardware && + ctlr->unprepare_transfer_hardware(ctlr)) + dev_err(&ctlr->dev, + "failed to unprepare transfer hardware\n"); + if (ctlr->auto_runtime_pm) { + pm_runtime_mark_last_busy(ctlr->dev.parent); + pm_runtime_put_autosuspend(ctlr->dev.parent); + } + trace_spi_controller_idle(ctlr); + + spin_lock_irqsave(&ctlr->queue_lock, flags); + ctlr->idling = false; spin_unlock_irqrestore(&ctlr->queue_lock, flags); return; } @@ -1335,77 +1359,6 @@ static void spi_pump_messages(struct kthread_work *work) __spi_pump_messages(ctlr, true); } -/** - * spi_pump_idle_teardown - kthread delayed work function which tears down - * the controller settings after some delay - * @work: pointer to kthread work struct contained in the controller struct - */ -static void spi_pump_idle_teardown(struct kthread_work *work) -{ - struct spi_controller *ctlr = - container_of(work, struct spi_controller, - pump_idle_teardown.work); - unsigned long flags; - - /* Lock queue */ - spin_lock_irqsave(&ctlr->queue_lock, flags); - - /* Make sure we are not already running a message */ - if (ctlr->cur_msg) - goto out; - - /* if there is anything in the list then exit */ - if (!list_empty(&ctlr->queue)) - goto out; - - /* if the controller is running then exit */ - if (ctlr->running) - goto out; - - /* if the controller is busy then exit */ - if (ctlr->busy) - goto out; - - /* if the controller is idling then exit - * this is actually a bit strange and would indicate that - * this function is scheduled twice, which should not happen - */ - if (ctlr->idling) - goto out; - - /* set up the initial states */ - ctlr->busy = false; - ctlr->idling = true; - spin_unlock_irqrestore(&ctlr->queue_lock, flags); - - /* free dummy receive buffers */ - kfree(ctlr->dummy_rx); - ctlr->dummy_rx = NULL; - kfree(ctlr->dummy_tx); - ctlr->dummy_tx = NULL; - - /* unprepare hardware */ - if (ctlr->unprepare_transfer_hardware && - ctlr->unprepare_transfer_hardware(ctlr)) - dev_err(&ctlr->dev, - "failed to unprepare transfer hardware\n"); - /* handle pm */ - if (ctlr->auto_runtime_pm) { - pm_runtime_mark_last_busy(ctlr->dev.parent); - pm_runtime_put_autosuspend(ctlr->dev.parent); - } - - /* mark controller as idle */ - trace_spi_controller_idle(ctlr); - - /* finally put us from idling into stopped */ - spin_lock_irqsave(&ctlr->queue_lock, flags); - ctlr->idling = false; - -out: - spin_unlock_irqrestore(&ctlr->queue_lock, flags); -} - static int spi_init_queue(struct spi_controller *ctlr) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; @@ -1421,8 +1374,7 @@ static int spi_init_queue(struct spi_controller *ctlr) return PTR_ERR(ctlr->kworker_task); } kthread_init_work(&ctlr->pump_messages, spi_pump_messages); - kthread_init_delayed_work(&ctlr->pump_idle_teardown, - spi_pump_idle_teardown); + /* * Controller config will indicate if this controller should run the * message pump with high (realtime) priority to reduce the transfer @@ -1494,16 +1446,7 @@ void spi_finalize_current_message(struct spi_controller *ctlr) spin_lock_irqsave(&ctlr->queue_lock, flags); ctlr->cur_msg = NULL; ctlr->cur_msg_prepared = false; - - /* if there is something queued, then wake the queue */ - if (!list_empty(&ctlr->queue)) - kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages); - else - /* otherwise schedule delayed teardown */ - kthread_mod_delayed_work(&ctlr->kworker, - &ctlr->pump_idle_teardown, - HZ); - + kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages); spin_unlock_irqrestore(&ctlr->queue_lock, flags); trace_spi_message_done(mesg); @@ -1608,7 +1551,7 @@ static int __spi_queued_transfer(struct spi_device *spi, msg->status = -EINPROGRESS; list_add_tail(&msg->queue, &ctlr->queue); - if (need_pump) + if (!ctlr->busy && need_pump) kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages); spin_unlock_irqrestore(&ctlr->queue_lock, flags); @@ -3783,3 +3726,4 @@ err0: * include needing to have boardinfo data structures be much more public. */ postcore_initcall(spi_init); + diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 79ad62e2487c..916bba47d156 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -334,7 +334,6 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @kworker: thread struct for message pump * @kworker_task: pointer to task for message pump kworker thread * @pump_messages: work struct for scheduling work to the message pump - * @pump_idle_teardown: work structure for scheduling a teardown delayed * @queue_lock: spinlock to syncronise access to message queue * @queue: message queue * @idling: the device is entering idle state @@ -533,7 +532,6 @@ struct spi_controller { struct kthread_worker kworker; struct task_struct *kworker_task; struct kthread_work pump_messages; - struct kthread_delayed_work pump_idle_teardown; spinlock_t queue_lock; struct list_head queue; struct spi_message *cur_msg; -- cgit v1.2.3 From 52875a04f4b26e7ef30a288ea096f7cfec0e93cd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 22 Jan 2019 22:45:20 -0800 Subject: bpf: verifier: remove dead code Instead of overwriting dead code with jmp -1 instructions remove it completely for root. Adjust verifier state and line info appropriately. v2: - adjust func_info (Alexei); - make sure first instruction retains line info (Alexei). v4: (Yonghong) - remove unnecessary if (!insn to remove) checks; - always keep last line info if first live instruction lacks one. v5: (Martin Lau) - improve and clarify comments. Signed-off-by: Jakub Kicinski Acked-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 1 + kernel/bpf/core.c | 12 ++++ kernel/bpf/verifier.c | 176 ++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 186 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..be9af6b4a9e4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -778,6 +778,7 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); void bpf_clear_redirect_map(struct bpf_map *map); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ad08ba341197..2a81b8af3748 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -462,6 +462,18 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, return prog_adj; } +int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) +{ + /* Branch offsets can't overflow when program is shrinking, no need + * to call bpf_adj_branches(..., true) here + */ + memmove(prog->insnsi + off, prog->insnsi + off + cnt, + sizeof(struct bpf_insn) * (prog->len - off - cnt)); + prog->len -= cnt; + + return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false)); +} + void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { int i; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bf1f98e8beb6..099b2541f87f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6432,6 +6432,150 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of return new_prog; } +static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env, + u32 off, u32 cnt) +{ + int i, j; + + /* find first prog starting at or after off (first to remove) */ + for (i = 0; i < env->subprog_cnt; i++) + if (env->subprog_info[i].start >= off) + break; + /* find first prog starting at or after off + cnt (first to stay) */ + for (j = i; j < env->subprog_cnt; j++) + if (env->subprog_info[j].start >= off + cnt) + break; + /* if j doesn't start exactly at off + cnt, we are just removing + * the front of previous prog + */ + if (env->subprog_info[j].start != off + cnt) + j--; + + if (j > i) { + struct bpf_prog_aux *aux = env->prog->aux; + int move; + + /* move fake 'exit' subprog as well */ + move = env->subprog_cnt + 1 - j; + + memmove(env->subprog_info + i, + env->subprog_info + j, + sizeof(*env->subprog_info) * move); + env->subprog_cnt -= j - i; + + /* remove func_info */ + if (aux->func_info) { + move = aux->func_info_cnt - j; + + memmove(aux->func_info + i, + aux->func_info + j, + sizeof(*aux->func_info) * move); + aux->func_info_cnt -= j - i; + /* func_info->insn_off is set after all code rewrites, + * in adjust_btf_func() - no need to adjust + */ + } + } else { + /* convert i from "first prog to remove" to "first to adjust" */ + if (env->subprog_info[i].start == off) + i++; + } + + /* update fake 'exit' subprog as well */ + for (; i <= env->subprog_cnt; i++) + env->subprog_info[i].start -= cnt; + + return 0; +} + +static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off, + u32 cnt) +{ + struct bpf_prog *prog = env->prog; + u32 i, l_off, l_cnt, nr_linfo; + struct bpf_line_info *linfo; + + nr_linfo = prog->aux->nr_linfo; + if (!nr_linfo) + return 0; + + linfo = prog->aux->linfo; + + /* find first line info to remove, count lines to be removed */ + for (i = 0; i < nr_linfo; i++) + if (linfo[i].insn_off >= off) + break; + + l_off = i; + l_cnt = 0; + for (; i < nr_linfo; i++) + if (linfo[i].insn_off < off + cnt) + l_cnt++; + else + break; + + /* First live insn doesn't match first live linfo, it needs to "inherit" + * last removed linfo. prog is already modified, so prog->len == off + * means no live instructions after (tail of the program was removed). + */ + if (prog->len != off && l_cnt && + (i == nr_linfo || linfo[i].insn_off != off + cnt)) { + l_cnt--; + linfo[--i].insn_off = off + cnt; + } + + /* remove the line info which refer to the removed instructions */ + if (l_cnt) { + memmove(linfo + l_off, linfo + i, + sizeof(*linfo) * (nr_linfo - i)); + + prog->aux->nr_linfo -= l_cnt; + nr_linfo = prog->aux->nr_linfo; + } + + /* pull all linfo[i].insn_off >= off + cnt in by cnt */ + for (i = l_off; i < nr_linfo; i++) + linfo[i].insn_off -= cnt; + + /* fix up all subprogs (incl. 'exit') which start >= off */ + for (i = 0; i <= env->subprog_cnt; i++) + if (env->subprog_info[i].linfo_idx > l_off) { + /* program may have started in the removed region but + * may not be fully removed + */ + if (env->subprog_info[i].linfo_idx >= l_off + l_cnt) + env->subprog_info[i].linfo_idx -= l_cnt; + else + env->subprog_info[i].linfo_idx = l_off; + } + + return 0; +} + +static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) +{ + struct bpf_insn_aux_data *aux_data = env->insn_aux_data; + unsigned int orig_prog_len = env->prog->len; + int err; + + err = bpf_remove_insns(env->prog, off, cnt); + if (err) + return err; + + err = adjust_subprog_starts_after_remove(env, off, cnt); + if (err) + return err; + + err = bpf_adj_linfo_after_remove(env, off, cnt); + if (err) + return err; + + memmove(aux_data + off, aux_data + off + cnt, + sizeof(*aux_data) * (orig_prog_len - off - cnt)); + + return 0; +} + /* The verifier does more data flow analysis than llvm and will not * explore branches that are dead at run time. Malicious programs can * have dead code too. Therefore replace all dead at-run-time code @@ -6492,6 +6636,30 @@ static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env) } } +static int opt_remove_dead_code(struct bpf_verifier_env *env) +{ + struct bpf_insn_aux_data *aux_data = env->insn_aux_data; + int insn_cnt = env->prog->len; + int i, err; + + for (i = 0; i < insn_cnt; i++) { + int j; + + j = 0; + while (i + j < insn_cnt && !aux_data[i + j].seen) + j++; + if (!j) + continue; + + err = verifier_remove_insns(env, i, j); + if (err) + return err; + insn_cnt = env->prog->len; + } + + return 0; +} + /* convert load instructions that access fields of a context type into a * sequence of instructions that access fields of the underlying structure: * struct __sk_buff -> struct sk_buff @@ -7282,11 +7450,13 @@ skip_full_check: if (is_priv) { if (ret == 0) opt_hard_wire_dead_code_branches(env); + if (ret == 0) + ret = opt_remove_dead_code(env); + } else { + if (ret == 0) + sanitize_dead_code(env); } - if (ret == 0) - sanitize_dead_code(env); - if (ret == 0) /* program is valid, convert *(u32*)(ctx + off) accesses */ ret = convert_ctx_accesses(env); -- cgit v1.2.3 From 9e4c24e7ee7dfd3898269519103e823892b730d8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 22 Jan 2019 22:45:23 -0800 Subject: bpf: verifier: record original instruction index The communication between the verifier and advanced JITs is based on instruction indexes. We have to keep them stable throughout the optimizations otherwise referring to a particular instruction gets messy quickly. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + kernel/bpf/verifier.c | 8 +++++--- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 573cca00a0e6..f3ae00ee5516 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -187,6 +187,7 @@ struct bpf_insn_aux_data { int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ u8 alu_state; /* used in combination with alu_limit */ + unsigned int orig_idx; /* original instruction index */ }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f39bca188a5c..f2c49b4235df 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7371,7 +7371,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, { struct bpf_verifier_env *env; struct bpf_verifier_log *log; - int ret = -EINVAL; + int i, len, ret = -EINVAL; bool is_priv; /* no program is valid */ @@ -7386,12 +7386,14 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, return -ENOMEM; log = &env->log; + len = (*prog)->len; env->insn_aux_data = - vzalloc(array_size(sizeof(struct bpf_insn_aux_data), - (*prog)->len)); + vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len)); ret = -ENOMEM; if (!env->insn_aux_data) goto err_free_env; + for (i = 0; i < len; i++) + env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; -- cgit v1.2.3 From 08ca90afba255d05dc3253caa44056e7aecbe8c5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 22 Jan 2019 22:45:24 -0800 Subject: bpf: notify offload JITs about optimizations Let offload JITs know when instructions are replaced and optimized out, so they can update their state appropriately. The optimizations are best effort, if JIT returns an error from any callback verifier will stop notifying it as state may now be out of sync, but the verifier continues making progress. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 +++++++ include/linux/bpf_verifier.h | 5 +++++ kernel/bpf/offload.c | 35 +++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 6 ++++++ 4 files changed, 53 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e734f163bd0b..3851529062ec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -268,9 +268,15 @@ struct bpf_verifier_ops { }; struct bpf_prog_offload_ops { + /* verifier basic callbacks */ int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); + /* verifier optimization callbacks (called after .finalize) */ + int (*replace_insn)(struct bpf_verifier_env *env, u32 off, + struct bpf_insn *insn); + int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt); + /* program management callbacks */ int (*prepare)(struct bpf_prog *prog); int (*translate)(struct bpf_prog *prog); void (*destroy)(struct bpf_prog *prog); @@ -283,6 +289,7 @@ struct bpf_prog_offload { void *dev_priv; struct list_head offloads; bool dev_state; + bool opt_failed; void *jited_image; u32 jited_len; }; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f3ae00ee5516..0620e418dde5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -266,5 +266,10 @@ int bpf_prog_offload_verifier_prep(struct bpf_prog *prog); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int bpf_prog_offload_finalize(struct bpf_verifier_env *env); +void +bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, + struct bpf_insn *insn); +void +bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 54cf2b9c44a4..39dba8c90331 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -173,6 +173,41 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env) return ret; } +void +bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, + struct bpf_insn *insn) +{ + const struct bpf_prog_offload_ops *ops; + struct bpf_prog_offload *offload; + int ret = -EOPNOTSUPP; + + down_read(&bpf_devs_lock); + offload = env->prog->aux->offload; + if (offload) { + ops = offload->offdev->ops; + if (!offload->opt_failed && ops->replace_insn) + ret = ops->replace_insn(env, off, insn); + offload->opt_failed |= ret; + } + up_read(&bpf_devs_lock); +} + +void +bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) +{ + struct bpf_prog_offload *offload; + int ret = -EOPNOTSUPP; + + down_read(&bpf_devs_lock); + offload = env->prog->aux->offload; + if (offload) { + if (!offload->opt_failed && offload->offdev->ops->remove_insns) + ret = offload->offdev->ops->remove_insns(env, off, cnt); + offload->opt_failed |= ret; + } + up_read(&bpf_devs_lock); +} + static void __bpf_prog_offload_destroy(struct bpf_prog *prog) { struct bpf_prog_offload *offload = prog->aux->offload; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f2c49b4235df..8cfe39ef770f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6558,6 +6558,9 @@ static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) unsigned int orig_prog_len = env->prog->len; int err; + if (bpf_prog_is_dev_bound(env->prog->aux)) + bpf_prog_offload_remove_insns(env, off, cnt); + err = bpf_remove_insns(env->prog, off, cnt); if (err) return err; @@ -6632,6 +6635,9 @@ static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env) else continue; + if (bpf_prog_is_dev_bound(env->prog->aux)) + bpf_prog_offload_replace_insn(env, i, &ja); + memcpy(insn, &ja, sizeof(ja)); } } -- cgit v1.2.3 From 643fa9612bf1a29153eee46fd398117632f93cbe Mon Sep 17 00:00:00 2001 From: Chandan Rajendra Date: Wed, 12 Dec 2018 15:20:12 +0530 Subject: fscrypt: remove filesystem specific build config option In order to have a common code base for fscrypt "post read" processing for all filesystems which support encryption, this commit removes filesystem specific build config option (e.g. CONFIG_EXT4_FS_ENCRYPTION) and replaces it with a build option (i.e. CONFIG_FS_ENCRYPTION) whose value affects all the filesystems making use of fscrypt. Reviewed-by: Eric Biggers Signed-off-by: Chandan Rajendra Signed-off-by: Eric Biggers --- Documentation/filesystems/fscrypt.rst | 4 +- arch/mips/configs/generic_defconfig | 2 +- arch/nds32/configs/defconfig | 2 +- arch/s390/configs/debug_defconfig | 2 +- arch/s390/configs/performance_defconfig | 2 +- fs/crypto/Kconfig | 5 +- fs/crypto/fscrypt_private.h | 1 - fs/ext4/Kconfig | 15 -- fs/ext4/dir.c | 2 - fs/ext4/ext4.h | 7 +- fs/ext4/inode.c | 8 +- fs/ext4/ioctl.c | 4 +- fs/ext4/namei.c | 10 +- fs/ext4/page-io.c | 6 +- fs/ext4/readpage.c | 2 +- fs/ext4/super.c | 6 +- fs/ext4/sysfs.c | 4 +- fs/f2fs/Kconfig | 12 +- fs/f2fs/f2fs.h | 7 +- fs/f2fs/super.c | 8 +- fs/f2fs/sysfs.c | 4 +- fs/ubifs/Kconfig | 12 +- fs/ubifs/Makefile | 2 +- fs/ubifs/ioctl.c | 4 +- fs/ubifs/sb.c | 2 +- fs/ubifs/super.c | 2 +- fs/ubifs/ubifs.h | 5 +- include/linux/fs.h | 4 +- include/linux/fscrypt.h | 416 +++++++++++++++++++++++++++++++- include/linux/fscrypt_notsupp.h | 231 ------------------ include/linux/fscrypt_supp.h | 204 ---------------- 31 files changed, 460 insertions(+), 535 deletions(-) delete mode 100644 include/linux/fscrypt_notsupp.h delete mode 100644 include/linux/fscrypt_supp.h (limited to 'include') diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index 3a7b60521b94..43dd989e2a3f 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -343,9 +343,9 @@ FS_IOC_SET_ENCRYPTION_POLICY can fail with the following errors: - ``ENOTEMPTY``: the file is unencrypted and is a nonempty directory - ``ENOTTY``: this type of filesystem does not implement encryption - ``EOPNOTSUPP``: the kernel was not configured with encryption - support for this filesystem, or the filesystem superblock has not + support for filesystems, or the filesystem superblock has not had encryption enabled on it. (For example, to use encryption on an - ext4 filesystem, CONFIG_EXT4_ENCRYPTION must be enabled in the + ext4 filesystem, CONFIG_FS_ENCRYPTION must be enabled in the kernel config, and the superblock must have had the "encrypt" feature flag enabled using ``tune2fs -O encrypt`` or ``mkfs.ext4 -O encrypt``.) diff --git a/arch/mips/configs/generic_defconfig b/arch/mips/configs/generic_defconfig index 7c138dab87df..5d80521e5d5a 100644 --- a/arch/mips/configs/generic_defconfig +++ b/arch/mips/configs/generic_defconfig @@ -59,7 +59,7 @@ CONFIG_HID_MONTEREY=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_EXT4_ENCRYPTION=y +CONFIG_FS_ENCRYPTION=y CONFIG_FANOTIFY=y CONFIG_FUSE_FS=y CONFIG_CUSE=y diff --git a/arch/nds32/configs/defconfig b/arch/nds32/configs/defconfig index 2546d8770785..65ce9259081b 100644 --- a/arch/nds32/configs/defconfig +++ b/arch/nds32/configs/defconfig @@ -74,7 +74,7 @@ CONFIG_GENERIC_PHY=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_EXT4_ENCRYPTION=y +CONFIG_FS_ENCRYPTION=y CONFIG_FUSE_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index c69cb04b7a59..9824c7bad9d4 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -500,7 +500,6 @@ CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_EXT4_ENCRYPTION=y CONFIG_JBD2_DEBUG=y CONFIG_JFS_FS=m CONFIG_JFS_POSIX_ACL=y @@ -520,6 +519,7 @@ CONFIG_BTRFS_DEBUG=y CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y +CONFIG_FS_ENCRYPTION=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 32f539dc9c19..4fcbe5792744 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -497,7 +497,6 @@ CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_EXT4_ENCRYPTION=y CONFIG_JBD2_DEBUG=y CONFIG_JFS_FS=m CONFIG_JFS_POSIX_ACL=y @@ -515,6 +514,7 @@ CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y +CONFIG_FS_ENCRYPTION=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig index 284b589b4774..f0de238000c0 100644 --- a/fs/crypto/Kconfig +++ b/fs/crypto/Kconfig @@ -1,5 +1,5 @@ config FS_ENCRYPTION - tristate "FS Encryption (Per-file encryption)" + bool "FS Encryption (Per-file encryption)" select CRYPTO select CRYPTO_AES select CRYPTO_CBC @@ -12,4 +12,5 @@ config FS_ENCRYPTION Enable encryption of files and directories. This feature is similar to ecryptfs, but it is more memory efficient since it avoids caching the encrypted and - decrypted pages in the page cache. + decrypted pages in the page cache. Currently Ext4, + F2FS and UBIFS make use of this feature. diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 7424f851eb5c..7da276159593 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -12,7 +12,6 @@ #ifndef _FSCRYPT_PRIVATE_H #define _FSCRYPT_PRIVATE_H -#define __FS_HAS_ENCRYPTION 1 #include #include diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index a453cc87082b..031e5a82d556 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -96,21 +96,6 @@ config EXT4_FS_SECURITY If you are not using a security module that requires using extended attributes for file security labels, say N. -config EXT4_ENCRYPTION - bool "Ext4 Encryption" - depends on EXT4_FS - select FS_ENCRYPTION - help - Enable encryption of ext4 files and directories. This - feature is similar to ecryptfs, but it is more memory - efficient since it avoids caching the encrypted and - decrypted pages in the page cache. - -config EXT4_FS_ENCRYPTION - bool - default y - depends on EXT4_ENCRYPTION - config EXT4_DEBUG bool "EXT4 debugging support" depends on EXT4_FS diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index fb7a64ea5679..0ccd51f72048 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -283,9 +283,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) done: err = 0; errout: -#ifdef CONFIG_EXT4_FS_ENCRYPTION fscrypt_fname_free_buffer(&fstr); -#endif brelse(bh); return err; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index afdb9ad8be0e..5012ddb6daf9 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -40,7 +40,6 @@ #include #endif -#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_EXT4_FS_ENCRYPTION) #include #include @@ -1326,7 +1325,7 @@ struct ext4_super_block { #define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ #define EXT4_MF_TEST_DUMMY_ENCRYPTION 0x0004 -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION #define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely((sbi)->s_mount_flags & \ EXT4_MF_TEST_DUMMY_ENCRYPTION)) #else @@ -2051,7 +2050,7 @@ struct ext4_filename { const struct qstr *usr_fname; struct fscrypt_str disk_name; struct dx_hash_info hinfo; -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION struct fscrypt_str crypto_buf; #endif }; @@ -2279,7 +2278,7 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION static inline int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct ext4_filename *fname) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 71bd2d28f58d..4356ef6d728e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1150,7 +1150,7 @@ int do_journal_get_write_access(handle_t *handle, return ret; } -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { @@ -1302,7 +1302,7 @@ retry_journal: /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION if (ext4_should_dioread_nolock(inode)) ret = ext4_block_write_begin(page, pos, len, ext4_get_block_unwritten); @@ -3104,7 +3104,7 @@ retry_journal: /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION ret = ext4_block_write_begin(page, pos, len, ext4_da_get_block_prep); #else @@ -3879,7 +3879,7 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter) loff_t offset = iocb->ki_pos; ssize_t ret; -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) return 0; #endif diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index d37dafa1d133..d26bcac291bb 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -210,7 +210,7 @@ journal_err_out: return err; } -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION static int uuid_is_zero(__u8 u[16]) { int i; @@ -978,7 +978,7 @@ resizefs_out: return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); case EXT4_IOC_GET_ENCRYPTION_PWSALT: { -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION int err, err2; struct ext4_sb_info *sbi = EXT4_SB(sb); handle_t *handle; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index be6cb69beb12..980166a8122a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -612,7 +612,7 @@ static struct stats dx_show_leaf(struct inode *dir, { if (show_names) { -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION int len; char *name; struct fscrypt_str fname_crypto_str = @@ -984,7 +984,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, top = (struct ext4_dir_entry_2 *) ((char *) de + dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0)); -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION /* Check if the directory is encrypted */ if (IS_ENCRYPTED(dir)) { err = fscrypt_get_encryption_info(dir); @@ -1047,7 +1047,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, } errout: brelse(bh); -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION fscrypt_fname_free_buffer(&fname_crypto_str); #endif return count; @@ -1267,7 +1267,7 @@ static inline bool ext4_match(const struct ext4_filename *fname, f.usr_fname = fname->usr_fname; f.disk_name = fname->disk_name; -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION f.crypto_buf = fname->crypto_buf; #endif return fscrypt_match_name(&f, de->name, de->name_len); @@ -1498,7 +1498,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, ext4_lblk_t block; int retval; -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION *res_dir = NULL; #endif frame = dx_probe(fname, dir, NULL, frames); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index c398b55da854..b9d6cabe2ea8 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -66,7 +66,7 @@ static void ext4_finish_bio(struct bio *bio) bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION struct page *data_page = NULL; #endif struct buffer_head *bh, *head; @@ -78,7 +78,7 @@ static void ext4_finish_bio(struct bio *bio) if (!page) continue; -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION if (!page->mapping) { /* The bounce data pages are unmapped. */ data_page = page; @@ -111,7 +111,7 @@ static void ext4_finish_bio(struct bio *bio) bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); local_irq_restore(flags); if (!under_io) { -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION if (data_page) fscrypt_restore_control_page(data_page); #endif diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 52d3ff5a9db1..b18881eb8da6 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -49,7 +49,7 @@ static inline bool ext4_bio_encrypted(struct bio *bio) { -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION return unlikely(bio->bi_private != NULL); #else return false; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index fb12d3c17c1b..60da0a6e4d86 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1232,7 +1232,7 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, return try_to_free_buffers(page); } -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION static int ext4_get_context(struct inode *inode, void *ctx, size_t len) { return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, @@ -1922,7 +1922,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg); } else if (token == Opt_test_dummy_encryption) { -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION sbi->s_mount_flags |= EXT4_MF_TEST_DUMMY_ENCRYPTION; ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled"); @@ -4167,7 +4167,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &ext4_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION sb->s_cop = &ext4_cryptops; #endif #ifdef CONFIG_QUOTA diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 9212a026a1f1..5e4e78fc0b3a 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -224,7 +224,7 @@ static struct attribute *ext4_attrs[] = { EXT4_ATTR_FEATURE(lazy_itable_init); EXT4_ATTR_FEATURE(batched_discard); EXT4_ATTR_FEATURE(meta_bg_resize); -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION EXT4_ATTR_FEATURE(encryption); #endif EXT4_ATTR_FEATURE(metadata_csum_seed); @@ -233,7 +233,7 @@ static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(lazy_itable_init), ATTR_LIST(batched_discard), ATTR_LIST(meta_bg_resize), -#ifdef CONFIG_EXT4_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION ATTR_LIST(encryption), #endif ATTR_LIST(metadata_csum_seed), diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index 9a20ef42fadd..e57cc754d543 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -3,6 +3,7 @@ config F2FS_FS depends on BLOCK select CRYPTO select CRYPTO_CRC32 + select F2FS_FS_XATTR if FS_ENCRYPTION help F2FS is based on Log-structured File System (LFS), which supports versatile "flash-friendly" features. The design has been focused on @@ -70,17 +71,6 @@ config F2FS_CHECK_FS If you want to improve the performance, say N. -config F2FS_FS_ENCRYPTION - bool "F2FS Encryption" - depends on F2FS_FS - depends on F2FS_FS_XATTR - select FS_ENCRYPTION - help - Enable encryption of f2fs files and directories. This - feature is similar to ecryptfs, but it is more memory - efficient since it avoids caching the encrypted and - decrypted pages in the page cache. - config F2FS_IO_TRACE bool "F2FS IO tracer" depends on F2FS_FS diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9ef6f38e51cc..95cc885ccb2f 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -24,7 +24,6 @@ #include #include -#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_F2FS_FS_ENCRYPTION) #include #ifdef CONFIG_F2FS_CHECK_FS @@ -1137,7 +1136,7 @@ enum fsync_mode { FSYNC_MODE_NOBARRIER, /* fsync behaves nobarrier based on posix */ }; -#ifdef CONFIG_F2FS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION #define DUMMY_ENCRYPTION_ENABLED(sbi) \ (unlikely(F2FS_OPTION(sbi).test_dummy_encryption)) #else @@ -3470,7 +3469,7 @@ static inline bool f2fs_encrypted_file(struct inode *inode) static inline void f2fs_set_encrypted_inode(struct inode *inode) { -#ifdef CONFIG_F2FS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION file_set_encrypt(inode); f2fs_set_inode_flags(inode); #endif @@ -3549,7 +3548,7 @@ static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) static inline bool f2fs_may_encrypt(struct inode *inode) { -#ifdef CONFIG_F2FS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION umode_t mode = inode->i_mode; return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index c46a1d4318d4..0f3db3a8e5cb 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -757,7 +757,7 @@ static int parse_options(struct super_block *sb, char *options) kvfree(name); break; case Opt_test_dummy_encryption: -#ifdef CONFIG_F2FS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION if (!f2fs_sb_has_encrypt(sbi)) { f2fs_msg(sb, KERN_ERR, "Encrypt feature is off"); return -EINVAL; @@ -1390,7 +1390,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_printf(seq, ",whint_mode=%s", "user-based"); else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) seq_printf(seq, ",whint_mode=%s", "fs-based"); -#ifdef CONFIG_F2FS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION if (F2FS_OPTION(sbi).test_dummy_encryption) seq_puts(seq, ",test_dummy_encryption"); #endif @@ -2154,7 +2154,7 @@ static const struct super_operations f2fs_sops = { .remount_fs = f2fs_remount, }; -#ifdef CONFIG_F2FS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION static int f2fs_get_context(struct inode *inode, void *ctx, size_t len) { return f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, @@ -3116,7 +3116,7 @@ try_onemore: #endif sb->s_op = &f2fs_sops; -#ifdef CONFIG_F2FS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION sb->s_cop = &f2fs_cryptops; #endif sb->s_xattr = f2fs_xattr_handlers; diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 0575edbe3ed6..70da6801c86f 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -431,7 +431,7 @@ F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); F2FS_GENERAL_RO_ATTR(features); F2FS_GENERAL_RO_ATTR(current_reserved_blocks); -#ifdef CONFIG_F2FS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); #endif #ifdef CONFIG_BLK_DEV_ZONED @@ -492,7 +492,7 @@ static struct attribute *f2fs_attrs[] = { }; static struct attribute *f2fs_feat_attrs[] = { -#ifdef CONFIG_F2FS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION ATTR_LIST(encryption), #endif #ifdef CONFIG_BLK_DEV_ZONED diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig index bc1e082d921d..9da2f135121b 100644 --- a/fs/ubifs/Kconfig +++ b/fs/ubifs/Kconfig @@ -8,6 +8,7 @@ config UBIFS_FS select CRYPTO_LZO if UBIFS_FS_LZO select CRYPTO_DEFLATE if UBIFS_FS_ZLIB select CRYPTO_HASH_INFO + select UBIFS_FS_XATTR if FS_ENCRYPTION depends on MTD_UBI help UBIFS is a file system for flash devices which works on top of UBI. @@ -60,17 +61,6 @@ config UBIFS_FS_XATTR If unsure, say Y. -config UBIFS_FS_ENCRYPTION - bool "UBIFS Encryption" - depends on UBIFS_FS_XATTR && BLOCK - select FS_ENCRYPTION - default n - help - Enable encryption of UBIFS files and directories. This - feature is similar to ecryptfs, but it is more memory - efficient since it avoids caching the encrypted and - decrypted pages in the page cache. - config UBIFS_FS_SECURITY bool "UBIFS Security Labels" depends on UBIFS_FS_XATTR diff --git a/fs/ubifs/Makefile b/fs/ubifs/Makefile index 5f838319c8d5..5c4b845754a7 100644 --- a/fs/ubifs/Makefile +++ b/fs/ubifs/Makefile @@ -6,6 +6,6 @@ ubifs-y += tnc.o master.o scan.o replay.o log.o commit.o gc.o orphan.o ubifs-y += budget.o find.o tnc_commit.o compress.o lpt.o lprops.o ubifs-y += recovery.o ioctl.o lpt_commit.o tnc_misc.o debug.o ubifs-y += misc.o -ubifs-$(CONFIG_UBIFS_FS_ENCRYPTION) += crypto.o +ubifs-$(CONFIG_FS_ENCRYPTION) += crypto.o ubifs-$(CONFIG_UBIFS_FS_XATTR) += xattr.o ubifs-$(CONFIG_UBIFS_FS_AUTHENTICATION) += auth.o diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index 0164bcc827f8..0f9c362a3402 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -185,7 +185,7 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return err; } case FS_IOC_SET_ENCRYPTION_POLICY: { -#ifdef CONFIG_UBIFS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION struct ubifs_info *c = inode->i_sb->s_fs_info; err = ubifs_enable_encryption(c); @@ -198,7 +198,7 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) #endif } case FS_IOC_GET_ENCRYPTION_POLICY: { -#ifdef CONFIG_UBIFS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION return fscrypt_ioctl_get_policy(file, (void __user *)arg); #else return -EOPNOTSUPP; diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index 3da90c951c23..67fac1e8adfb 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -748,7 +748,7 @@ int ubifs_read_superblock(struct ubifs_info *c) goto out; } -#ifndef CONFIG_UBIFS_FS_ENCRYPTION +#ifndef CONFIG_FS_ENCRYPTION if (c->encrypted) { ubifs_err(c, "file system contains encrypted files but UBIFS" " was built without crypto support."); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 1fac1133dadd..8dc2818fdd84 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2146,7 +2146,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_UBIFS_FS_XATTR sb->s_xattr = ubifs_xattr_handlers; #endif -#ifdef CONFIG_UBIFS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION sb->s_cop = &ubifs_crypt_operations; #endif diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 38401adaa00d..1ae12900e01d 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -43,7 +43,6 @@ #include #include -#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_UBIFS_FS_ENCRYPTION) #include #include "ubifs-media.h" @@ -142,7 +141,7 @@ */ #define WORST_COMPR_FACTOR 2 -#ifdef CONFIG_UBIFS_FS_ENCRYPTION +#ifdef CONFIG_FS_ENCRYPTION #define UBIFS_CIPHER_BLOCK_SIZE FS_CRYPTO_BLOCK_SIZE #else #define UBIFS_CIPHER_BLOCK_SIZE 0 @@ -2072,7 +2071,7 @@ int ubifs_decompress(const struct ubifs_info *c, const void *buf, int len, #include "misc.h" #include "key.h" -#ifndef CONFIG_UBIFS_FS_ENCRYPTION +#ifndef CONFIG_FS_ENCRYPTION static inline int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn, unsigned int in_len, unsigned int *out_len, diff --git a/include/linux/fs.h b/include/linux/fs.h index 811c77743dad..ba7889bb9ef6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -698,7 +698,7 @@ struct inode { struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) +#ifdef CONFIG_FS_ENCRYPTION struct fscrypt_info *i_crypt_info; #endif @@ -1403,7 +1403,7 @@ struct super_block { void *s_security; #endif const struct xattr_handler **s_xattr; -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) +#ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 952ab97af325..eec604840568 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -2,9 +2,8 @@ /* * fscrypt.h: declarations for per-file encryption * - * Filesystems that implement per-file encryption include this header - * file with the __FS_HAS_ENCRYPTION set according to whether that filesystem - * is being built with encryption support or not. + * Filesystems that implement per-file encryption must include this header + * file. * * Copyright (C) 2015, Google, Inc. * @@ -15,6 +14,8 @@ #define _LINUX_FSCRYPT_H #include +#include +#include #define FS_CRYPTO_BLOCK_SIZE 16 @@ -42,11 +43,410 @@ struct fscrypt_name { /* Maximum value for the third parameter of fscrypt_operations.set_context(). */ #define FSCRYPT_SET_CONTEXT_MAX_SIZE 28 -#if __FS_HAS_ENCRYPTION -#include -#else -#include -#endif +#ifdef CONFIG_FS_ENCRYPTION +/* + * fscrypt superblock flags + */ +#define FS_CFLG_OWN_PAGES (1U << 1) + +/* + * crypto operations for filesystems + */ +struct fscrypt_operations { + unsigned int flags; + const char *key_prefix; + int (*get_context)(struct inode *, void *, size_t); + int (*set_context)(struct inode *, const void *, size_t, void *); + bool (*dummy_context)(struct inode *); + bool (*empty_dir)(struct inode *); + unsigned int max_namelen; +}; + +struct fscrypt_ctx { + union { + struct { + struct page *bounce_page; /* Ciphertext page */ + struct page *control_page; /* Original page */ + } w; + struct { + struct bio *bio; + struct work_struct work; + } r; + struct list_head free_list; /* Free list */ + }; + u8 flags; /* Flags */ +}; + +static inline bool fscrypt_has_encryption_key(const struct inode *inode) +{ + return (inode->i_crypt_info != NULL); +} + +static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +{ + return inode->i_sb->s_cop->dummy_context && + inode->i_sb->s_cop->dummy_context(inode); +} + +/* crypto.c */ +extern void fscrypt_enqueue_decrypt_work(struct work_struct *); +extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); +extern void fscrypt_release_ctx(struct fscrypt_ctx *); +extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, + unsigned int, unsigned int, + u64, gfp_t); +extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int, + unsigned int, u64); + +static inline struct page *fscrypt_control_page(struct page *page) +{ + return ((struct fscrypt_ctx *)page_private(page))->w.control_page; +} + +extern void fscrypt_restore_control_page(struct page *); + +/* policy.c */ +extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); +extern int fscrypt_ioctl_get_policy(struct file *, void __user *); +extern int fscrypt_has_permitted_context(struct inode *, struct inode *); +extern int fscrypt_inherit_context(struct inode *, struct inode *, + void *, bool); +/* keyinfo.c */ +extern int fscrypt_get_encryption_info(struct inode *); +extern void fscrypt_put_encryption_info(struct inode *); + +/* fname.c */ +extern int fscrypt_setup_filename(struct inode *, const struct qstr *, + int lookup, struct fscrypt_name *); + +static inline void fscrypt_free_filename(struct fscrypt_name *fname) +{ + kfree(fname->crypto_buf.name); +} + +extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, + struct fscrypt_str *); +extern void fscrypt_fname_free_buffer(struct fscrypt_str *); +extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, + const struct fscrypt_str *, struct fscrypt_str *); + +#define FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE 32 + +/* Extracts the second-to-last ciphertext block; see explanation below */ +#define FSCRYPT_FNAME_DIGEST(name, len) \ + ((name) + round_down((len) - FS_CRYPTO_BLOCK_SIZE - 1, \ + FS_CRYPTO_BLOCK_SIZE)) + +#define FSCRYPT_FNAME_DIGEST_SIZE FS_CRYPTO_BLOCK_SIZE + +/** + * fscrypt_digested_name - alternate identifier for an on-disk filename + * + * When userspace lists an encrypted directory without access to the key, + * filenames whose ciphertext is longer than FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE + * bytes are shown in this abbreviated form (base64-encoded) rather than as the + * full ciphertext (base64-encoded). This is necessary to allow supporting + * filenames up to NAME_MAX bytes, since base64 encoding expands the length. + * + * To make it possible for filesystems to still find the correct directory entry + * despite not knowing the full on-disk name, we encode any filesystem-specific + * 'hash' and/or 'minor_hash' which the filesystem may need for its lookups, + * followed by the second-to-last ciphertext block of the filename. Due to the + * use of the CBC-CTS encryption mode, the second-to-last ciphertext block + * depends on the full plaintext. (Note that ciphertext stealing causes the + * last two blocks to appear "flipped".) This makes accidental collisions very + * unlikely: just a 1 in 2^128 chance for two filenames to collide even if they + * share the same filesystem-specific hashes. + * + * However, this scheme isn't immune to intentional collisions, which can be + * created by anyone able to create arbitrary plaintext filenames and view them + * without the key. Making the "digest" be a real cryptographic hash like + * SHA-256 over the full ciphertext would prevent this, although it would be + * less efficient and harder to implement, especially since the filesystem would + * need to calculate it for each directory entry examined during a search. + */ +struct fscrypt_digested_name { + u32 hash; + u32 minor_hash; + u8 digest[FSCRYPT_FNAME_DIGEST_SIZE]; +}; + +/** + * fscrypt_match_name() - test whether the given name matches a directory entry + * @fname: the name being searched for + * @de_name: the name from the directory entry + * @de_name_len: the length of @de_name in bytes + * + * Normally @fname->disk_name will be set, and in that case we simply compare + * that to the name stored in the directory entry. The only exception is that + * if we don't have the key for an encrypted directory and a filename in it is + * very long, then we won't have the full disk_name and we'll instead need to + * match against the fscrypt_digested_name. + * + * Return: %true if the name matches, otherwise %false. + */ +static inline bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len) +{ + if (unlikely(!fname->disk_name.name)) { + const struct fscrypt_digested_name *n = + (const void *)fname->crypto_buf.name; + if (WARN_ON_ONCE(fname->usr_fname->name[0] != '_')) + return false; + if (de_name_len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) + return false; + return !memcmp(FSCRYPT_FNAME_DIGEST(de_name, de_name_len), + n->digest, FSCRYPT_FNAME_DIGEST_SIZE); + } + + if (de_name_len != fname->disk_name.len) + return false; + return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); +} + +/* bio.c */ +extern void fscrypt_decrypt_bio(struct bio *); +extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, + struct bio *bio); +extern void fscrypt_pullback_bio_page(struct page **, bool); +extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, + unsigned int); + +/* hooks.c */ +extern int fscrypt_file_open(struct inode *inode, struct file *filp); +extern int __fscrypt_prepare_link(struct inode *inode, struct inode *dir); +extern int __fscrypt_prepare_rename(struct inode *old_dir, + struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry, + unsigned int flags); +extern int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry); +extern int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link); +extern int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, + unsigned int len, + struct fscrypt_str *disk_link); +extern const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, + unsigned int max_size, + struct delayed_call *done); +#else /* !CONFIG_FS_ENCRYPTION */ + +static inline bool fscrypt_has_encryption_key(const struct inode *inode) +{ + return false; +} + +static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +{ + return false; +} + +/* crypto.c */ +static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) +{ +} + +static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, + gfp_t gfp_flags) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx) +{ + return; +} + +static inline struct page *fscrypt_encrypt_page(const struct inode *inode, + struct page *page, + unsigned int len, + unsigned int offs, + u64 lblk_num, gfp_t gfp_flags) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline int fscrypt_decrypt_page(const struct inode *inode, + struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num) +{ + return -EOPNOTSUPP; +} + +static inline struct page *fscrypt_control_page(struct page *page) +{ + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); +} + +static inline void fscrypt_restore_control_page(struct page *page) +{ + return; +} + +/* policy.c */ +static inline int fscrypt_ioctl_set_policy(struct file *filp, + const void __user *arg) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_has_permitted_context(struct inode *parent, + struct inode *child) +{ + return 0; +} + +static inline int fscrypt_inherit_context(struct inode *parent, + struct inode *child, + void *fs_data, bool preload) +{ + return -EOPNOTSUPP; +} + +/* keyinfo.c */ +static inline int fscrypt_get_encryption_info(struct inode *inode) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_put_encryption_info(struct inode *inode) +{ + return; +} + + /* fname.c */ +static inline int fscrypt_setup_filename(struct inode *dir, + const struct qstr *iname, + int lookup, struct fscrypt_name *fname) +{ + if (IS_ENCRYPTED(dir)) + return -EOPNOTSUPP; + + memset(fname, 0, sizeof(struct fscrypt_name)); + fname->usr_fname = iname; + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; +} + +static inline void fscrypt_free_filename(struct fscrypt_name *fname) +{ + return; +} + +static inline int fscrypt_fname_alloc_buffer(const struct inode *inode, + u32 max_encrypted_len, + struct fscrypt_str *crypto_str) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) +{ + return; +} + +static inline int fscrypt_fname_disk_to_usr(struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname) +{ + return -EOPNOTSUPP; +} + +static inline bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len) +{ + /* Encryption support disabled; use standard comparison */ + if (de_name_len != fname->disk_name.len) + return false; + return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); +} + +/* bio.c */ +static inline void fscrypt_decrypt_bio(struct bio *bio) +{ +} + +static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, + struct bio *bio) +{ +} + +static inline void fscrypt_pullback_bio_page(struct page **page, bool restore) +{ + return; +} + +static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len) +{ + return -EOPNOTSUPP; +} + +/* hooks.c */ + +static inline int fscrypt_file_open(struct inode *inode, struct file *filp) +{ + if (IS_ENCRYPTED(inode)) + return -EOPNOTSUPP; + return 0; +} + +static inline int __fscrypt_prepare_link(struct inode *inode, + struct inode *dir) +{ + return -EOPNOTSUPP; +} + +static inline int __fscrypt_prepare_rename(struct inode *old_dir, + struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry, + unsigned int flags) +{ + return -EOPNOTSUPP; +} + +static inline int __fscrypt_prepare_lookup(struct inode *dir, + struct dentry *dentry) +{ + return -EOPNOTSUPP; +} + +static inline int __fscrypt_prepare_symlink(struct inode *dir, + unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link) +{ + return -EOPNOTSUPP; +} + + +static inline int __fscrypt_encrypt_symlink(struct inode *inode, + const char *target, + unsigned int len, + struct fscrypt_str *disk_link) +{ + return -EOPNOTSUPP; +} + +static inline const char *fscrypt_get_symlink(struct inode *inode, + const void *caddr, + unsigned int max_size, + struct delayed_call *done) +{ + return ERR_PTR(-EOPNOTSUPP); +} +#endif /* !CONFIG_FS_ENCRYPTION */ /** * fscrypt_require_key - require an inode's encryption key diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h deleted file mode 100644 index ee8b43e4c15a..000000000000 --- a/include/linux/fscrypt_notsupp.h +++ /dev/null @@ -1,231 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * fscrypt_notsupp.h - * - * This stubs out the fscrypt functions for filesystems configured without - * encryption support. - * - * Do not include this file directly. Use fscrypt.h instead! - */ -#ifndef _LINUX_FSCRYPT_H -#error "Incorrect include of linux/fscrypt_notsupp.h!" -#endif - -#ifndef _LINUX_FSCRYPT_NOTSUPP_H -#define _LINUX_FSCRYPT_NOTSUPP_H - -static inline bool fscrypt_has_encryption_key(const struct inode *inode) -{ - return false; -} - -static inline bool fscrypt_dummy_context_enabled(struct inode *inode) -{ - return false; -} - -/* crypto.c */ -static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) -{ -} - -static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, - gfp_t gfp_flags) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx) -{ - return; -} - -static inline struct page *fscrypt_encrypt_page(const struct inode *inode, - struct page *page, - unsigned int len, - unsigned int offs, - u64 lblk_num, gfp_t gfp_flags) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline int fscrypt_decrypt_page(const struct inode *inode, - struct page *page, - unsigned int len, unsigned int offs, - u64 lblk_num) -{ - return -EOPNOTSUPP; -} - -static inline struct page *fscrypt_control_page(struct page *page) -{ - WARN_ON_ONCE(1); - return ERR_PTR(-EINVAL); -} - -static inline void fscrypt_restore_control_page(struct page *page) -{ - return; -} - -/* policy.c */ -static inline int fscrypt_ioctl_set_policy(struct file *filp, - const void __user *arg) -{ - return -EOPNOTSUPP; -} - -static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg) -{ - return -EOPNOTSUPP; -} - -static inline int fscrypt_has_permitted_context(struct inode *parent, - struct inode *child) -{ - return 0; -} - -static inline int fscrypt_inherit_context(struct inode *parent, - struct inode *child, - void *fs_data, bool preload) -{ - return -EOPNOTSUPP; -} - -/* keyinfo.c */ -static inline int fscrypt_get_encryption_info(struct inode *inode) -{ - return -EOPNOTSUPP; -} - -static inline void fscrypt_put_encryption_info(struct inode *inode) -{ - return; -} - - /* fname.c */ -static inline int fscrypt_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, struct fscrypt_name *fname) -{ - if (IS_ENCRYPTED(dir)) - return -EOPNOTSUPP; - - memset(fname, 0, sizeof(struct fscrypt_name)); - fname->usr_fname = iname; - fname->disk_name.name = (unsigned char *)iname->name; - fname->disk_name.len = iname->len; - return 0; -} - -static inline void fscrypt_free_filename(struct fscrypt_name *fname) -{ - return; -} - -static inline int fscrypt_fname_alloc_buffer(const struct inode *inode, - u32 max_encrypted_len, - struct fscrypt_str *crypto_str) -{ - return -EOPNOTSUPP; -} - -static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) -{ - return; -} - -static inline int fscrypt_fname_disk_to_usr(struct inode *inode, - u32 hash, u32 minor_hash, - const struct fscrypt_str *iname, - struct fscrypt_str *oname) -{ - return -EOPNOTSUPP; -} - -static inline bool fscrypt_match_name(const struct fscrypt_name *fname, - const u8 *de_name, u32 de_name_len) -{ - /* Encryption support disabled; use standard comparison */ - if (de_name_len != fname->disk_name.len) - return false; - return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); -} - -/* bio.c */ -static inline void fscrypt_decrypt_bio(struct bio *bio) -{ -} - -static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, - struct bio *bio) -{ -} - -static inline void fscrypt_pullback_bio_page(struct page **page, bool restore) -{ - return; -} - -static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, - sector_t pblk, unsigned int len) -{ - return -EOPNOTSUPP; -} - -/* hooks.c */ - -static inline int fscrypt_file_open(struct inode *inode, struct file *filp) -{ - if (IS_ENCRYPTED(inode)) - return -EOPNOTSUPP; - return 0; -} - -static inline int __fscrypt_prepare_link(struct inode *inode, - struct inode *dir) -{ - return -EOPNOTSUPP; -} - -static inline int __fscrypt_prepare_rename(struct inode *old_dir, - struct dentry *old_dentry, - struct inode *new_dir, - struct dentry *new_dentry, - unsigned int flags) -{ - return -EOPNOTSUPP; -} - -static inline int __fscrypt_prepare_lookup(struct inode *dir, - struct dentry *dentry) -{ - return -EOPNOTSUPP; -} - -static inline int __fscrypt_prepare_symlink(struct inode *dir, - unsigned int len, - unsigned int max_len, - struct fscrypt_str *disk_link) -{ - return -EOPNOTSUPP; -} - -static inline int __fscrypt_encrypt_symlink(struct inode *inode, - const char *target, - unsigned int len, - struct fscrypt_str *disk_link) -{ - return -EOPNOTSUPP; -} - -static inline const char *fscrypt_get_symlink(struct inode *inode, - const void *caddr, - unsigned int max_size, - struct delayed_call *done) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -#endif /* _LINUX_FSCRYPT_NOTSUPP_H */ diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h deleted file mode 100644 index 6456c6b2005f..000000000000 --- a/include/linux/fscrypt_supp.h +++ /dev/null @@ -1,204 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * fscrypt_supp.h - * - * Do not include this file directly. Use fscrypt.h instead! - */ -#ifndef _LINUX_FSCRYPT_H -#error "Incorrect include of linux/fscrypt_supp.h!" -#endif - -#ifndef _LINUX_FSCRYPT_SUPP_H -#define _LINUX_FSCRYPT_SUPP_H - -#include -#include - -/* - * fscrypt superblock flags - */ -#define FS_CFLG_OWN_PAGES (1U << 1) - -/* - * crypto operations for filesystems - */ -struct fscrypt_operations { - unsigned int flags; - const char *key_prefix; - int (*get_context)(struct inode *, void *, size_t); - int (*set_context)(struct inode *, const void *, size_t, void *); - bool (*dummy_context)(struct inode *); - bool (*empty_dir)(struct inode *); - unsigned int max_namelen; -}; - -struct fscrypt_ctx { - union { - struct { - struct page *bounce_page; /* Ciphertext page */ - struct page *control_page; /* Original page */ - } w; - struct { - struct bio *bio; - struct work_struct work; - } r; - struct list_head free_list; /* Free list */ - }; - u8 flags; /* Flags */ -}; - -static inline bool fscrypt_has_encryption_key(const struct inode *inode) -{ - return (inode->i_crypt_info != NULL); -} - -static inline bool fscrypt_dummy_context_enabled(struct inode *inode) -{ - return inode->i_sb->s_cop->dummy_context && - inode->i_sb->s_cop->dummy_context(inode); -} - -/* crypto.c */ -extern void fscrypt_enqueue_decrypt_work(struct work_struct *); -extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); -extern void fscrypt_release_ctx(struct fscrypt_ctx *); -extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, - unsigned int, unsigned int, - u64, gfp_t); -extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int, - unsigned int, u64); - -static inline struct page *fscrypt_control_page(struct page *page) -{ - return ((struct fscrypt_ctx *)page_private(page))->w.control_page; -} - -extern void fscrypt_restore_control_page(struct page *); - -/* policy.c */ -extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); -extern int fscrypt_ioctl_get_policy(struct file *, void __user *); -extern int fscrypt_has_permitted_context(struct inode *, struct inode *); -extern int fscrypt_inherit_context(struct inode *, struct inode *, - void *, bool); -/* keyinfo.c */ -extern int fscrypt_get_encryption_info(struct inode *); -extern void fscrypt_put_encryption_info(struct inode *); - -/* fname.c */ -extern int fscrypt_setup_filename(struct inode *, const struct qstr *, - int lookup, struct fscrypt_name *); - -static inline void fscrypt_free_filename(struct fscrypt_name *fname) -{ - kfree(fname->crypto_buf.name); -} - -extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, - struct fscrypt_str *); -extern void fscrypt_fname_free_buffer(struct fscrypt_str *); -extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, - const struct fscrypt_str *, struct fscrypt_str *); - -#define FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE 32 - -/* Extracts the second-to-last ciphertext block; see explanation below */ -#define FSCRYPT_FNAME_DIGEST(name, len) \ - ((name) + round_down((len) - FS_CRYPTO_BLOCK_SIZE - 1, \ - FS_CRYPTO_BLOCK_SIZE)) - -#define FSCRYPT_FNAME_DIGEST_SIZE FS_CRYPTO_BLOCK_SIZE - -/** - * fscrypt_digested_name - alternate identifier for an on-disk filename - * - * When userspace lists an encrypted directory without access to the key, - * filenames whose ciphertext is longer than FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE - * bytes are shown in this abbreviated form (base64-encoded) rather than as the - * full ciphertext (base64-encoded). This is necessary to allow supporting - * filenames up to NAME_MAX bytes, since base64 encoding expands the length. - * - * To make it possible for filesystems to still find the correct directory entry - * despite not knowing the full on-disk name, we encode any filesystem-specific - * 'hash' and/or 'minor_hash' which the filesystem may need for its lookups, - * followed by the second-to-last ciphertext block of the filename. Due to the - * use of the CBC-CTS encryption mode, the second-to-last ciphertext block - * depends on the full plaintext. (Note that ciphertext stealing causes the - * last two blocks to appear "flipped".) This makes accidental collisions very - * unlikely: just a 1 in 2^128 chance for two filenames to collide even if they - * share the same filesystem-specific hashes. - * - * However, this scheme isn't immune to intentional collisions, which can be - * created by anyone able to create arbitrary plaintext filenames and view them - * without the key. Making the "digest" be a real cryptographic hash like - * SHA-256 over the full ciphertext would prevent this, although it would be - * less efficient and harder to implement, especially since the filesystem would - * need to calculate it for each directory entry examined during a search. - */ -struct fscrypt_digested_name { - u32 hash; - u32 minor_hash; - u8 digest[FSCRYPT_FNAME_DIGEST_SIZE]; -}; - -/** - * fscrypt_match_name() - test whether the given name matches a directory entry - * @fname: the name being searched for - * @de_name: the name from the directory entry - * @de_name_len: the length of @de_name in bytes - * - * Normally @fname->disk_name will be set, and in that case we simply compare - * that to the name stored in the directory entry. The only exception is that - * if we don't have the key for an encrypted directory and a filename in it is - * very long, then we won't have the full disk_name and we'll instead need to - * match against the fscrypt_digested_name. - * - * Return: %true if the name matches, otherwise %false. - */ -static inline bool fscrypt_match_name(const struct fscrypt_name *fname, - const u8 *de_name, u32 de_name_len) -{ - if (unlikely(!fname->disk_name.name)) { - const struct fscrypt_digested_name *n = - (const void *)fname->crypto_buf.name; - if (WARN_ON_ONCE(fname->usr_fname->name[0] != '_')) - return false; - if (de_name_len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) - return false; - return !memcmp(FSCRYPT_FNAME_DIGEST(de_name, de_name_len), - n->digest, FSCRYPT_FNAME_DIGEST_SIZE); - } - - if (de_name_len != fname->disk_name.len) - return false; - return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); -} - -/* bio.c */ -extern void fscrypt_decrypt_bio(struct bio *); -extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, - struct bio *bio); -extern void fscrypt_pullback_bio_page(struct page **, bool); -extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, - unsigned int); - -/* hooks.c */ -extern int fscrypt_file_open(struct inode *inode, struct file *filp); -extern int __fscrypt_prepare_link(struct inode *inode, struct inode *dir); -extern int __fscrypt_prepare_rename(struct inode *old_dir, - struct dentry *old_dentry, - struct inode *new_dir, - struct dentry *new_dentry, - unsigned int flags); -extern int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry); -extern int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, - unsigned int max_len, - struct fscrypt_str *disk_link); -extern int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, - unsigned int len, - struct fscrypt_str *disk_link); -extern const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, - unsigned int max_size, - struct delayed_call *done); - -#endif /* _LINUX_FSCRYPT_SUPP_H */ -- cgit v1.2.3 From f5e55e777cc93eae1416f0fa4908e8846b6d7825 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 22 Jan 2019 16:20:21 -0800 Subject: fscrypt: return -EXDEV for incompatible rename or link into encrypted dir Currently, trying to rename or link a regular file, directory, or symlink into an encrypted directory fails with EPERM when the source file is unencrypted or is encrypted with a different encryption policy, and is on the same mountpoint. It is correct for the operation to fail, but the choice of EPERM breaks tools like 'mv' that know to copy rather than rename if they see EXDEV, but don't know what to do with EPERM. Our original motivation for EPERM was to encourage users to securely handle their data. Encrypting files by "moving" them into an encrypted directory can be insecure because the unencrypted data may remain in free space on disk, where it can later be recovered by an attacker. It's much better to encrypt the data from the start, or at least try to securely delete the source data e.g. using the 'shred' program. However, the current behavior hasn't been effective at achieving its goal because users tend to be confused, hack around it, and complain; see e.g. https://github.com/google/fscrypt/issues/76. And in some cases it's actually inconsistent or unnecessary. For example, 'mv'-ing files between differently encrypted directories doesn't work even in cases where it can be secure, such as when in userspace the same passphrase protects both directories. Yet, you *can* already 'mv' unencrypted files into an encrypted directory if the source files are on a different mountpoint, even though doing so is often insecure. There are probably better ways to teach users to securely handle their files. For example, the 'fscrypt' userspace tool could provide a command that migrates unencrypted files into an encrypted directory, acting like 'shred' on the source files and providing appropriate warnings depending on the type of the source filesystem and disk. Receiving errors on unimportant files might also force some users to disable encryption, thus making the behavior counterproductive. It's desirable to make encryption as unobtrusive as possible. Therefore, change the error code from EPERM to EXDEV so that tools looking for EXDEV will fall back to a copy. This, of course, doesn't prevent users from still doing the right things to securely manage their files. Note that this also matches the behavior when a file is renamed between two project quota hierarchies; so there's precedent for using EXDEV for things other than mountpoints. xfstests generic/398 will require an update with this change. [Rewritten from an earlier patch series by Michael Halcrow.] Cc: Michael Halcrow Cc: Joe Richey Signed-off-by: Eric Biggers --- Documentation/filesystems/fscrypt.rst | 12 ++++++++++-- fs/crypto/hooks.c | 6 +++--- fs/crypto/policy.c | 3 +-- include/linux/fscrypt.h | 4 ++-- 4 files changed, 16 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index 43dd989e2a3f..08c23b60e016 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -451,10 +451,18 @@ astute users may notice some differences in behavior: - Unencrypted files, or files encrypted with a different encryption policy (i.e. different key, modes, or flags), cannot be renamed or linked into an encrypted directory; see `Encryption policy - enforcement`_. Attempts to do so will fail with EPERM. However, + enforcement`_. Attempts to do so will fail with EXDEV. However, encrypted files can be renamed within an encrypted directory, or into an unencrypted directory. + Note: "moving" an unencrypted file into an encrypted directory, e.g. + with the `mv` program, is implemented in userspace by a copy + followed by a delete. Be aware that the original unencrypted data + may remain recoverable from free space on the disk; prefer to keep + all files encrypted from the very beginning. The `shred` program + may be used to overwrite the source files but isn't guaranteed to be + effective on all filesystems and storage devices. + - Direct I/O is not supported on encrypted files. Attempts to use direct I/O on such files will fall back to buffered I/O. @@ -541,7 +549,7 @@ not be encrypted. Except for those special files, it is forbidden to have unencrypted files, or files encrypted with a different encryption policy, in an encrypted directory tree. Attempts to link or rename such a file into -an encrypted directory will fail with EPERM. This is also enforced +an encrypted directory will fail with EXDEV. This is also enforced during ->lookup() to provide limited protection against offline attacks that try to disable or downgrade encryption in known locations where applications may later write sensitive data. It is recommended diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 926e5df20ec3..56debb1fcf5e 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -58,7 +58,7 @@ int __fscrypt_prepare_link(struct inode *inode, struct inode *dir) return err; if (!fscrypt_has_permitted_context(dir, inode)) - return -EPERM; + return -EXDEV; return 0; } @@ -82,13 +82,13 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, if (IS_ENCRYPTED(new_dir) && !fscrypt_has_permitted_context(new_dir, d_inode(old_dentry))) - return -EPERM; + return -EXDEV; if ((flags & RENAME_EXCHANGE) && IS_ENCRYPTED(old_dir) && !fscrypt_has_permitted_context(old_dir, d_inode(new_dentry))) - return -EPERM; + return -EXDEV; } return 0; } diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index f490de921ce8..bd7eaf9b3f00 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -151,8 +151,7 @@ EXPORT_SYMBOL(fscrypt_ioctl_get_policy); * malicious offline violations of this constraint, while the link and rename * checks are needed to prevent online violations of this constraint. * - * Return: 1 if permitted, 0 if forbidden. If forbidden, the caller must fail - * the filesystem operation with EPERM. + * Return: 1 if permitted, 0 if forbidden. */ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) { diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index eec604840568..e5194fc3983e 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -489,7 +489,7 @@ static inline int fscrypt_require_key(struct inode *inode) * in an encrypted directory tree use the same encryption policy. * * Return: 0 on success, -ENOKEY if the directory's encryption key is missing, - * -EPERM if the link would result in an inconsistent encryption policy, or + * -EXDEV if the link would result in an inconsistent encryption policy, or * another -errno code. */ static inline int fscrypt_prepare_link(struct dentry *old_dentry, @@ -519,7 +519,7 @@ static inline int fscrypt_prepare_link(struct dentry *old_dentry, * We also verify that the rename will not violate the constraint that all files * in an encrypted directory tree use the same encryption policy. * - * Return: 0 on success, -ENOKEY if an encryption key is missing, -EPERM if the + * Return: 0 on success, -ENOKEY if an encryption key is missing, -EXDEV if the * rename would cause inconsistent encryption policies, or another -errno code. */ static inline int fscrypt_prepare_rename(struct inode *old_dir, -- cgit v1.2.3 From d9ff286a0f59fa7843549e49bd240393dd7d8b87 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 23 Jan 2019 09:22:27 -0800 Subject: bpf: allow BPF programs access skb_shared_info->gso_segs field This adds the ability to read gso_segs from a BPF program. v3: Use BPF_REG_AX instead of BPF_REG_TMP for the temporary register, as suggested by Martin. v2: refined Eddie Hao patch to address Alexei feedback. Signed-off-by: Eric Dumazet Cc: Eddie Hao Cc: Martin KaFai Lau Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 21 +++++++++++++++++ tools/include/uapi/linux/bpf.h | 1 + tools/testing/selftests/bpf/test_verifier.c | 36 +++++++++++++++++++++++++++++ 4 files changed, 59 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 91c43884f295..2940a9854f6d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2540,6 +2540,7 @@ struct __sk_buff { __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); __u64 tstamp; __u32 wire_len; + __u32 gso_segs; }; struct bpf_tunnel_key { diff --git a/net/core/filter.c b/net/core/filter.c index 2b3b436ef545..8e587dd1da20 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6700,6 +6700,27 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, target_size)); break; + case offsetof(struct __sk_buff, gso_segs): + /* si->dst_reg = skb_shinfo(SKB); */ +#ifdef NET_SKBUFF_DATA_USES_OFFSET + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, head)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), + BPF_REG_AX, si->src_reg, + offsetof(struct sk_buff, end)); + *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); +#else + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, end)); +#endif + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), + si->dst_reg, si->dst_reg, + bpf_target_off(struct skb_shared_info, + gso_segs, 2, + target_size)); + break; case offsetof(struct __sk_buff, wire_len): BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 91c43884f295..2940a9854f6d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2540,6 +2540,7 @@ struct __sk_buff { __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); __u64 tstamp; __u32 wire_len; + __u32 gso_segs; }; struct bpf_tunnel_key { diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 4f67afeec8d9..e4fef6ca8071 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -5663,6 +5663,42 @@ static struct bpf_test tests[] = { .result = ACCEPT, .prog_type = BPF_PROG_TYPE_CGROUP_SKB, }, + { + "read gso_segs from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, gso_segs)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + }, + { + "write gso_segs from CGROUP_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, gso_segs)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .result_unpriv = REJECT, + .errstr = "invalid bpf_context access off=164 size=4", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + }, + { + "read gso_segs from CLS", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, gso_segs)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, { "multiple registers share map_lookup_elem result", .insns = { -- cgit v1.2.3 From e355477ed9e4f401e3931043df97325d38552d54 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 18 Jan 2019 16:33:10 -0800 Subject: net/mlx5: Make mlx5_cmd_exec_cb() a safe API APIs that have deferred callbacks should have some kind of cleanup function that callers can use to fence the callbacks. Otherwise things like module unloading can lead to dangling function pointers, or worse. The IB MR code is the only place that calls this function and had a really poor attempt at creating this fence. Provide a good version in the core code as future patches will add more places that need this fence. Signed-off-by: Jason Gunthorpe Signed-off-by: Yishai Hadas Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 + drivers/infiniband/hw/mlx5/mr.c | 39 ++++--------------- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 55 ++++++++++++++++++++++++--- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 11 +++--- include/linux/mlx5/driver.h | 32 +++++++++++++--- 5 files changed, 91 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index efe383c0ac86..eedba0d2ec4b 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -587,6 +587,7 @@ struct mlx5_ib_mr { struct mlx5_ib_mr *parent; atomic_t num_leaf_free; wait_queue_head_t q_leaf_free; + struct mlx5_async_work cb_work; }; struct mlx5_ib_mw { @@ -944,6 +945,7 @@ struct mlx5_ib_dev { struct mlx5_memic memic; u16 devx_whitelist_uid; struct mlx5_srq_table srq_table; + struct mlx5_async_ctx async_ctx; }; static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index fd6ea1f75085..bf2b6ea23851 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -123,9 +123,10 @@ static void update_odp_mr(struct mlx5_ib_mr *mr) } #endif -static void reg_mr_callback(int status, void *context) +static void reg_mr_callback(int status, struct mlx5_async_work *context) { - struct mlx5_ib_mr *mr = context; + struct mlx5_ib_mr *mr = + container_of(context, struct mlx5_ib_mr, cb_work); struct mlx5_ib_dev *dev = mr->dev; struct mlx5_mr_cache *cache = &dev->cache; int c = order2idx(dev, mr->order); @@ -216,9 +217,9 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num) ent->pending++; spin_unlock_irq(&ent->lock); err = mlx5_core_create_mkey_cb(dev->mdev, &mr->mmkey, - in, inlen, + &dev->async_ctx, in, inlen, mr->out, sizeof(mr->out), - reg_mr_callback, mr); + reg_mr_callback, &mr->cb_work); if (err) { spin_lock_irq(&ent->lock); ent->pending--; @@ -679,6 +680,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) return -ENOMEM; } + mlx5_cmd_init_async_ctx(dev->mdev, &dev->async_ctx); timer_setup(&dev->delay_timer, delay_time_func, 0); for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) { ent = &cache->ent[i]; @@ -725,33 +727,6 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) return 0; } -static void wait_for_async_commands(struct mlx5_ib_dev *dev) -{ - struct mlx5_mr_cache *cache = &dev->cache; - struct mlx5_cache_ent *ent; - int total = 0; - int i; - int j; - - for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) { - ent = &cache->ent[i]; - for (j = 0 ; j < 1000; j++) { - if (!ent->pending) - break; - msleep(50); - } - } - for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) { - ent = &cache->ent[i]; - total += ent->pending; - } - - if (total) - mlx5_ib_warn(dev, "aborted while there are %d pending mr requests\n", total); - else - mlx5_ib_warn(dev, "done with all pending requests\n"); -} - int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev) { int i; @@ -763,12 +738,12 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev) flush_workqueue(dev->cache.wq); mlx5_mr_cache_debugfs_cleanup(dev); + mlx5_cmd_cleanup_async_ctx(&dev->async_ctx); for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) clean_keys(dev, i); destroy_workqueue(dev->cache.wq); - wait_for_async_commands(dev); del_timer_sync(&dev->delay_timer); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 3e0fa8a8077b..a25a8c6f938e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1711,12 +1711,57 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, } EXPORT_SYMBOL(mlx5_cmd_exec); -int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, - void *out, int out_size, mlx5_cmd_cbk_t callback, - void *context) +void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, + struct mlx5_async_ctx *ctx) { - return cmd_exec(dev, in, in_size, out, out_size, callback, context, - false); + ctx->dev = dev; + /* Starts at 1 to avoid doing wake_up if we are not cleaning up */ + atomic_set(&ctx->num_inflight, 1); + init_waitqueue_head(&ctx->wait); +} +EXPORT_SYMBOL(mlx5_cmd_init_async_ctx); + +/** + * mlx5_cmd_cleanup_async_ctx - Clean up an async_ctx + * @ctx: The ctx to clean + * + * Upon return all callbacks given to mlx5_cmd_exec_cb() have been called. The + * caller must ensure that mlx5_cmd_exec_cb() is not called during or after + * the call mlx5_cleanup_async_ctx(). + */ +void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx) +{ + atomic_dec(&ctx->num_inflight); + wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0); +} +EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx); + +static void mlx5_cmd_exec_cb_handler(int status, void *_work) +{ + struct mlx5_async_work *work = _work; + struct mlx5_async_ctx *ctx = work->ctx; + + work->user_callback(status, work); + if (atomic_dec_and_test(&ctx->num_inflight)) + wake_up(&ctx->wait); +} + +int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, + void *out, int out_size, mlx5_async_cbk_t callback, + struct mlx5_async_work *work) +{ + int ret; + + work->ctx = ctx; + work->user_callback = callback; + if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) + return -EIO; + ret = cmd_exec(ctx->dev, in, in_size, out, out_size, + mlx5_cmd_exec_cb_handler, work, false); + if (ret && atomic_dec_and_test(&ctx->num_inflight)) + wake_up(&ctx->wait); + + return ret; } EXPORT_SYMBOL(mlx5_cmd_exec_cb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 0670165afd5f..ea744d8466ea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -51,9 +51,10 @@ void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev) int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, - u32 *in, int inlen, - u32 *out, int outlen, - mlx5_cmd_cbk_t callback, void *context) + struct mlx5_async_ctx *async_ctx, u32 *in, + int inlen, u32 *out, int outlen, + mlx5_async_cbk_t callback, + struct mlx5_async_work *context) { struct mlx5_mkey_table *table = &dev->priv.mkey_table; u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {0}; @@ -71,7 +72,7 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, MLX5_SET(mkc, mkc, mkey_7_0, key); if (callback) - return mlx5_cmd_exec_cb(dev, in, inlen, out, outlen, + return mlx5_cmd_exec_cb(async_ctx, in, inlen, out, outlen, callback, context); err = mlx5_cmd_exec(dev, in, inlen, lout, sizeof(lout)); @@ -105,7 +106,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, u32 *in, int inlen) { - return mlx5_core_create_mkey_cb(dev, mkey, in, inlen, + return mlx5_core_create_mkey_cb(dev, mkey, NULL, in, inlen, NULL, 0, NULL, NULL); } EXPORT_SYMBOL(mlx5_core_create_mkey); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4e444863054a..039c9398614c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -850,11 +850,30 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev); void mlx5_cmd_use_events(struct mlx5_core_dev *dev); void mlx5_cmd_use_polling(struct mlx5_core_dev *dev); +struct mlx5_async_ctx { + struct mlx5_core_dev *dev; + atomic_t num_inflight; + struct wait_queue_head wait; +}; + +struct mlx5_async_work; + +typedef void (*mlx5_async_cbk_t)(int status, struct mlx5_async_work *context); + +struct mlx5_async_work { + struct mlx5_async_ctx *ctx; + mlx5_async_cbk_t user_callback; +}; + +void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, + struct mlx5_async_ctx *ctx); +void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx); +int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, + void *out, int out_size, mlx5_async_cbk_t callback, + struct mlx5_async_work *work); + int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); -int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, - void *out, int out_size, mlx5_cmd_cbk_t callback, - void *context); int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); @@ -885,9 +904,10 @@ void mlx5_init_mkey_table(struct mlx5_core_dev *dev); void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev); int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, - u32 *in, int inlen, - u32 *out, int outlen, - mlx5_cmd_cbk_t callback, void *context); + struct mlx5_async_ctx *async_ctx, u32 *in, + int inlen, u32 *out, int outlen, + mlx5_async_cbk_t callback, + struct mlx5_async_work *context); int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, u32 *in, int inlen); -- cgit v1.2.3 From de89750c56f4bf2f04492c6ce298911381a7597a Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 23 Jan 2019 12:47:34 +0100 Subject: ALSA: pcm: Drop unused snd_pcm_substream.file field It's assigned but nowhere used. Let's remove it. Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 1 - sound/core/oss/pcm_oss.c | 1 - sound/core/pcm_native.c | 4 +--- 3 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 2c30c1ad1b0d..a20d3a48df00 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -470,7 +470,6 @@ struct snd_pcm_substream { struct snd_pcm_group self_group; /* fake group for non linked substream (with substream lock inside) */ struct snd_pcm_group *group; /* pointer to current group */ /* -- assigned files -- */ - void *file; int ref_count; atomic_t mmap_count; unsigned int f_flags; diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 467039b342b5..d5b0d7ba83c4 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -2427,7 +2427,6 @@ static int snd_pcm_oss_open_file(struct file *file, } pcm_oss_file->streams[idx] = substream; - substream->file = pcm_oss_file; snd_pcm_oss_init_substream(substream, &setup[idx], minor); } diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 26afb6b0889a..63640d3af9db 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2452,10 +2452,8 @@ static int snd_pcm_open_file(struct file *file, return -ENOMEM; } pcm_file->substream = substream; - if (substream->ref_count == 1) { - substream->file = pcm_file; + if (substream->ref_count == 1) substream->pcm_release = pcm_release_private; - } file->private_data = pcm_file; return 0; -- cgit v1.2.3 From 480e32ebd524ffdf3d50cc5cac179fb9e44a552d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 23 Jan 2019 16:44:38 +0100 Subject: ALSA: pcm: Simplify proc file destruction The proc files are recursively freed by calling with the root snd_info_entry object, so we don't have to keep each object for releasing one by one. Move the release of the PCM stream proc root at the beginning, so that we can remove the redundant code and resource. Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 11 --------- sound/core/pcm.c | 66 +++++++++---------------------------------------- sound/core/pcm_memory.c | 16 ++---------- 3 files changed, 13 insertions(+), 80 deletions(-) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index a20d3a48df00..eae6d2b82d7a 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -481,15 +481,6 @@ struct snd_pcm_substream { #endif #ifdef CONFIG_SND_VERBOSE_PROCFS struct snd_info_entry *proc_root; - struct snd_info_entry *proc_info_entry; - struct snd_info_entry *proc_hw_params_entry; - struct snd_info_entry *proc_sw_params_entry; - struct snd_info_entry *proc_status_entry; - struct snd_info_entry *proc_prealloc_entry; - struct snd_info_entry *proc_prealloc_max_entry; -#ifdef CONFIG_SND_PCM_XRUN_DEBUG - struct snd_info_entry *proc_xrun_injection_entry; -#endif #endif /* CONFIG_SND_VERBOSE_PROCFS */ /* misc flags */ unsigned int hw_opened: 1; @@ -511,10 +502,8 @@ struct snd_pcm_str { #endif #ifdef CONFIG_SND_VERBOSE_PROCFS struct snd_info_entry *proc_root; - struct snd_info_entry *proc_info_entry; #ifdef CONFIG_SND_PCM_XRUN_DEBUG unsigned int xrun_debug; /* 0 = disabled, 1 = verbose, 2 = stacktrace */ - struct snd_info_entry *proc_xrun_debug_entry; #endif #endif struct snd_kcontrol *chmap_kctl; /* channel-mapping controls */ diff --git a/sound/core/pcm.c b/sound/core/pcm.c index ca1ea3cf9350..bca0bdf3e33c 100644 --- a/sound/core/pcm.c +++ b/sound/core/pcm.c @@ -536,12 +536,9 @@ static int snd_pcm_stream_proc_init(struct snd_pcm_str *pstr) entry = snd_info_create_card_entry(pcm->card, "info", pstr->proc_root); if (entry) { snd_info_set_text_ops(entry, pstr, snd_pcm_stream_proc_info_read); - if (snd_info_register(entry) < 0) { + if (snd_info_register(entry) < 0) snd_info_free_entry(entry); - entry = NULL; - } } - pstr->proc_info_entry = entry; #ifdef CONFIG_SND_PCM_XRUN_DEBUG entry = snd_info_create_card_entry(pcm->card, "xrun_debug", @@ -551,24 +548,15 @@ static int snd_pcm_stream_proc_init(struct snd_pcm_str *pstr) entry->c.text.write = snd_pcm_xrun_debug_write; entry->mode |= 0200; entry->private_data = pstr; - if (snd_info_register(entry) < 0) { + if (snd_info_register(entry) < 0) snd_info_free_entry(entry); - entry = NULL; - } } - pstr->proc_xrun_debug_entry = entry; #endif return 0; } static int snd_pcm_stream_proc_done(struct snd_pcm_str *pstr) { -#ifdef CONFIG_SND_PCM_XRUN_DEBUG - snd_info_free_entry(pstr->proc_xrun_debug_entry); - pstr->proc_xrun_debug_entry = NULL; -#endif - snd_info_free_entry(pstr->proc_info_entry); - pstr->proc_info_entry = NULL; snd_info_free_entry(pstr->proc_root); pstr->proc_root = NULL; return 0; @@ -597,45 +585,33 @@ static int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream) if (entry) { snd_info_set_text_ops(entry, substream, snd_pcm_substream_proc_info_read); - if (snd_info_register(entry) < 0) { + if (snd_info_register(entry) < 0) snd_info_free_entry(entry); - entry = NULL; - } } - substream->proc_info_entry = entry; entry = snd_info_create_card_entry(card, "hw_params", substream->proc_root); if (entry) { snd_info_set_text_ops(entry, substream, snd_pcm_substream_proc_hw_params_read); - if (snd_info_register(entry) < 0) { + if (snd_info_register(entry) < 0) snd_info_free_entry(entry); - entry = NULL; - } } - substream->proc_hw_params_entry = entry; entry = snd_info_create_card_entry(card, "sw_params", substream->proc_root); if (entry) { snd_info_set_text_ops(entry, substream, snd_pcm_substream_proc_sw_params_read); - if (snd_info_register(entry) < 0) { + if (snd_info_register(entry) < 0) snd_info_free_entry(entry); - entry = NULL; - } } - substream->proc_sw_params_entry = entry; entry = snd_info_create_card_entry(card, "status", substream->proc_root); if (entry) { snd_info_set_text_ops(entry, substream, snd_pcm_substream_proc_status_read); - if (snd_info_register(entry) < 0) { + if (snd_info_register(entry) < 0) snd_info_free_entry(entry); - entry = NULL; - } } - substream->proc_status_entry = entry; #ifdef CONFIG_SND_PCM_XRUN_DEBUG entry = snd_info_create_card_entry(card, "xrun_injection", @@ -645,40 +621,18 @@ static int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream) entry->c.text.read = NULL; entry->c.text.write = snd_pcm_xrun_injection_write; entry->mode = S_IFREG | 0200; - if (snd_info_register(entry) < 0) { + if (snd_info_register(entry) < 0) snd_info_free_entry(entry); - entry = NULL; - } } - substream->proc_xrun_injection_entry = entry; #endif /* CONFIG_SND_PCM_XRUN_DEBUG */ return 0; } -static int snd_pcm_substream_proc_done(struct snd_pcm_substream *substream) -{ - snd_info_free_entry(substream->proc_info_entry); - substream->proc_info_entry = NULL; - snd_info_free_entry(substream->proc_hw_params_entry); - substream->proc_hw_params_entry = NULL; - snd_info_free_entry(substream->proc_sw_params_entry); - substream->proc_sw_params_entry = NULL; - snd_info_free_entry(substream->proc_status_entry); - substream->proc_status_entry = NULL; -#ifdef CONFIG_SND_PCM_XRUN_DEBUG - snd_info_free_entry(substream->proc_xrun_injection_entry); - substream->proc_xrun_injection_entry = NULL; -#endif - snd_info_free_entry(substream->proc_root); - substream->proc_root = NULL; - return 0; -} #else /* !CONFIG_SND_VERBOSE_PROCFS */ static inline int snd_pcm_stream_proc_init(struct snd_pcm_str *pstr) { return 0; } static inline int snd_pcm_stream_proc_done(struct snd_pcm_str *pstr) { return 0; } static inline int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream) { return 0; } -static inline int snd_pcm_substream_proc_done(struct snd_pcm_substream *substream) { return 0; } #endif /* CONFIG_SND_VERBOSE_PROCFS */ static const struct attribute_group *pcm_dev_attr_groups[]; @@ -911,15 +865,17 @@ static void snd_pcm_free_stream(struct snd_pcm_str * pstr) #if IS_ENABLED(CONFIG_SND_PCM_OSS) struct snd_pcm_oss_setup *setup, *setupn; #endif + + /* free all proc files under the stream */ + snd_pcm_stream_proc_done(pstr); + substream = pstr->substream; while (substream) { substream_next = substream->next; snd_pcm_timer_done(substream); - snd_pcm_substream_proc_done(substream); kfree(substream); substream = substream_next; } - snd_pcm_stream_proc_done(pstr); #if IS_ENABLED(CONFIG_SND_PCM_OSS) for (setup = pstr->oss.setup_list; setup; setup = setupn) { setupn = setup->next; diff --git a/sound/core/pcm_memory.c b/sound/core/pcm_memory.c index 4b5356a10315..9a98bc61461f 100644 --- a/sound/core/pcm_memory.c +++ b/sound/core/pcm_memory.c @@ -93,12 +93,6 @@ static void snd_pcm_lib_preallocate_dma_free(struct snd_pcm_substream *substream int snd_pcm_lib_preallocate_free(struct snd_pcm_substream *substream) { snd_pcm_lib_preallocate_dma_free(substream); -#ifdef CONFIG_SND_VERBOSE_PROCFS - snd_info_free_entry(substream->proc_prealloc_max_entry); - substream->proc_prealloc_max_entry = NULL; - snd_info_free_entry(substream->proc_prealloc_entry); - substream->proc_prealloc_entry = NULL; -#endif return 0; } @@ -203,21 +197,15 @@ static inline void preallocate_info_init(struct snd_pcm_substream *substream) entry->c.text.write = snd_pcm_lib_preallocate_proc_write; entry->mode |= 0200; entry->private_data = substream; - if (snd_info_register(entry) < 0) { + if (snd_info_register(entry) < 0) snd_info_free_entry(entry); - entry = NULL; - } } - substream->proc_prealloc_entry = entry; if ((entry = snd_info_create_card_entry(substream->pcm->card, "prealloc_max", substream->proc_root)) != NULL) { entry->c.text.read = snd_pcm_lib_preallocate_max_proc_read; entry->private_data = substream; - if (snd_info_register(entry) < 0) { + if (snd_info_register(entry) < 0) snd_info_free_entry(entry); - entry = NULL; - } } - substream->proc_prealloc_max_entry = entry; } #else /* !CONFIG_SND_VERBOSE_PROCFS */ -- cgit v1.2.3 From ef74f70e5a10cc2a78cc5529e564170cabcda9af Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Sat, 19 Jan 2019 15:42:42 -0500 Subject: gpio: add irq domain activate/deactivate functions This adds the two new functions gpiochip_irq_domain_activate and gpiochip_irq_domain_deactivate that can be used as the activate and deactivate functions in the struct irq_domain_ops. This is for situations where only gpiochip_{lock,unlock}_as_irq needs to be called. SPMI and SSBI GPIO are two users that will initially use these functions. Signed-off-by: Brian Masney Suggested-by: Stephen Boyd Reviewed-by: Stephen Boyd Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib.c | 37 +++++++++++++++++++++++++++++++++++++ include/linux/gpio/driver.h | 5 +++++ 2 files changed, 42 insertions(+) (limited to 'include') diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 1651d7f0a303..361a09c8138a 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1775,6 +1775,43 @@ static const struct irq_domain_ops gpiochip_domain_ops = { .xlate = irq_domain_xlate_twocell, }; +/** + * gpiochip_irq_domain_activate() - Lock a GPIO to be used as an IRQ + * @domain: The IRQ domain used by this IRQ chip + * @data: Outermost irq_data associated with the IRQ + * @reserve: If set, only reserve an interrupt vector instead of assigning one + * + * This function is a wrapper that calls gpiochip_lock_as_irq() and is to be + * used as the activate function for the &struct irq_domain_ops. The host_data + * for the IRQ domain must be the &struct gpio_chip. + */ +int gpiochip_irq_domain_activate(struct irq_domain *domain, + struct irq_data *data, bool reserve) +{ + struct gpio_chip *chip = domain->host_data; + + return gpiochip_lock_as_irq(chip, data->hwirq); +} +EXPORT_SYMBOL_GPL(gpiochip_irq_domain_activate); + +/** + * gpiochip_irq_domain_deactivate() - Unlock a GPIO used as an IRQ + * @domain: The IRQ domain used by this IRQ chip + * @data: Outermost irq_data associated with the IRQ + * + * This function is a wrapper that will call gpiochip_unlock_as_irq() and is to + * be used as the deactivate function for the &struct irq_domain_ops. The + * host_data for the IRQ domain must be the &struct gpio_chip. + */ +void gpiochip_irq_domain_deactivate(struct irq_domain *domain, + struct irq_data *data) +{ + struct gpio_chip *chip = domain->host_data; + + return gpiochip_unlock_as_irq(chip, data->hwirq); +} +EXPORT_SYMBOL_GPL(gpiochip_irq_domain_deactivate); + static int gpiochip_to_irq(struct gpio_chip *chip, unsigned offset) { if (!gpiochip_irqchip_irq_valid(chip, offset)) diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 07cddbf45186..01497910f023 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -472,6 +472,11 @@ int gpiochip_irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq); void gpiochip_irq_unmap(struct irq_domain *d, unsigned int irq); +int gpiochip_irq_domain_activate(struct irq_domain *domain, + struct irq_data *data, bool reserve); +void gpiochip_irq_domain_deactivate(struct irq_domain *domain, + struct irq_data *data); + void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip, struct irq_chip *irqchip, unsigned int parent_irq, -- cgit v1.2.3 From da6a496a34f2fdcab14362cdc5068aac385e7b47 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 22 Jan 2019 09:16:08 +0200 Subject: IB/mlx5: Ranges in implicit ODP MR inherit its write access A sub-range in ODP implicit MR should take its write permission from the MR and not be set always to allow. Fixes: d07d1d70ce1a ("IB/umem: Update on demand page (ODP) support") Signed-off-by: Moni Shoua Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/umem_odp.c | 5 +++-- drivers/infiniband/hw/mlx5/odp.c | 2 +- include/rdma/ib_umem_odp.h | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index dc1d7cb15cfa..eb8a5eb65bfa 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -332,9 +332,10 @@ static void put_per_mm(struct ib_umem_odp *umem_odp) mmu_notifier_call_srcu(&per_mm->rcu, free_per_mm); } -struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm, +struct ib_umem_odp *ib_alloc_odp_umem(struct ib_umem_odp *root, unsigned long addr, size_t size) { + struct ib_ucontext_per_mm *per_mm = root->per_mm; struct ib_ucontext *ctx = per_mm->context; struct ib_umem_odp *odp_data; struct ib_umem *umem; @@ -349,7 +350,7 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm, umem->length = size; umem->address = addr; umem->page_shift = PAGE_SHIFT; - umem->writable = 1; + umem->writable = root->umem.writable; umem->is_odp = 1; odp_data->per_mm = per_mm; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 3abdfc3584c0..3e0d5885c026 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -439,7 +439,7 @@ next_mr: if (nentries) nentries++; } else { - odp = ib_alloc_odp_umem(odp_mr->per_mm, addr, + odp = ib_alloc_odp_umem(odp_mr, addr, MLX5_IMR_MTT_SIZE); if (IS_ERR(odp)) { mutex_unlock(&odp_mr->umem_mutex); diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h index d3725cf13ecd..d0024f53626e 100644 --- a/include/rdma/ib_umem_odp.h +++ b/include/rdma/ib_umem_odp.h @@ -116,7 +116,7 @@ struct ib_ucontext_per_mm { }; int ib_umem_odp_get(struct ib_umem_odp *umem_odp, int access); -struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm, +struct ib_umem_odp *ib_alloc_odp_umem(struct ib_umem_odp *root_umem, unsigned long addr, size_t size); void ib_umem_odp_release(struct ib_umem_odp *umem_odp); -- cgit v1.2.3 From 61b2fe3c62e5269408e264b2348f96467246d537 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 22 Jan 2019 09:16:09 +0200 Subject: IB/mlx5: Remove dead code When CONFIG_INFINIBAND_ON_DEMAND_PAGING is not set there is no caller to ib_alloc_odp_umem() so let's remove it. Signed-off-by: Moni Shoua Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_umem_odp.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h index d0024f53626e..dadc96dea39c 100644 --- a/include/rdma/ib_umem_odp.h +++ b/include/rdma/ib_umem_odp.h @@ -169,12 +169,6 @@ static inline int ib_umem_odp_get(struct ib_umem_odp *umem_odp, int access) return -EINVAL; } -static inline struct ib_umem_odp * -ib_alloc_odp_umem(struct ib_ucontext *context, unsigned long addr, size_t size) -{ - return ERR_PTR(-EINVAL); -} - static inline void ib_umem_odp_release(struct ib_umem_odp *umem_odp) {} #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */ -- cgit v1.2.3 From 1d0dc06930a917eaca4156193c6c49f798b95ce7 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Thu, 24 Jan 2019 19:59:37 +0100 Subject: net: xsk: track AF_XDP sockets on a per-netns list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Track each AF_XDP socket in a per-netns list. This will be used later by the sock_diag interface for querying sockets from userspace. Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/net/net_namespace.h | 4 ++++ include/net/netns/xdp.h | 13 +++++++++++++ net/xdp/xsk.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 47 insertions(+) create mode 100644 include/net/netns/xdp.h (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 99d4148e0f90..a68ced28d8f4 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -160,6 +161,9 @@ struct net { #endif #if IS_ENABLED(CONFIG_CAN) struct netns_can can; +#endif +#ifdef CONFIG_XDP_SOCKETS + struct netns_xdp xdp; #endif struct sock *diag_nlsk; atomic_t fnhe_genid; diff --git a/include/net/netns/xdp.h b/include/net/netns/xdp.h new file mode 100644 index 000000000000..e5734261ba0a --- /dev/null +++ b/include/net/netns/xdp.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NETNS_XDP_H__ +#define __NETNS_XDP_H__ + +#include +#include + +struct netns_xdp { + struct mutex lock; + struct hlist_head list; +}; + +#endif /* __NETNS_XDP_H__ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index a03268454a27..80ca48cefc42 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -350,6 +350,10 @@ static int xsk_release(struct socket *sock) net = sock_net(sk); + mutex_lock(&net->xdp.lock); + sk_del_node_init_rcu(sk); + mutex_unlock(&net->xdp.lock); + local_bh_disable(); sock_prot_inuse_add(net, sk->sk_prot, -1); local_bh_enable(); @@ -746,6 +750,10 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, mutex_init(&xs->mutex); spin_lock_init(&xs->tx_completion_lock); + mutex_lock(&net->xdp.lock); + sk_add_node_rcu(sk, &net->xdp.list); + mutex_unlock(&net->xdp.lock); + local_bh_disable(); sock_prot_inuse_add(net, &xsk_proto, 1); local_bh_enable(); @@ -759,6 +767,23 @@ static const struct net_proto_family xsk_family_ops = { .owner = THIS_MODULE, }; +static int __net_init xsk_net_init(struct net *net) +{ + mutex_init(&net->xdp.lock); + INIT_HLIST_HEAD(&net->xdp.list); + return 0; +} + +static void __net_exit xsk_net_exit(struct net *net) +{ + WARN_ON_ONCE(!hlist_empty(&net->xdp.list)); +} + +static struct pernet_operations xsk_net_ops = { + .init = xsk_net_init, + .exit = xsk_net_exit, +}; + static int __init xsk_init(void) { int err; @@ -771,8 +796,13 @@ static int __init xsk_init(void) if (err) goto out_proto; + err = register_pernet_subsys(&xsk_net_ops); + if (err) + goto out_sk; return 0; +out_sk: + sock_unregister(PF_XDP); out_proto: proto_unregister(&xsk_proto); out: -- cgit v1.2.3 From 50e74c0131a5b3a3e387798a5705158c04fb3bd0 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Thu, 24 Jan 2019 19:59:38 +0100 Subject: xsk: add id to umem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit adds an id to the umem structure. The id uniquely identifies a umem instance, and will be exposed to user-space via the socket monitoring interface. Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/net/xdp_sock.h | 1 + net/xdp/xdp_umem.c | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 13acb9803a6d..61cf7dbb6782 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -42,6 +42,7 @@ struct xdp_umem { struct work_struct work; struct page **pgs; u32 npgs; + int id; struct net_device *dev; struct xdp_umem_fq_reuse *fq_reuse; u16 queue_id; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index a264cf2accd0..eabdb0f59031 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -13,12 +13,15 @@ #include #include #include +#include #include "xdp_umem.h" #include "xsk_queue.h" #define XDP_UMEM_MIN_CHUNK_SIZE 2048 +static DEFINE_IDA(umem_ida); + void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) { unsigned long flags; @@ -183,6 +186,8 @@ static void xdp_umem_release(struct xdp_umem *umem) xdp_umem_clear_dev(umem); + ida_simple_remove(&umem_ida, umem->id); + if (umem->fq) { xskq_destroy(umem->fq); umem->fq = NULL; @@ -389,8 +394,16 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) if (!umem) return ERR_PTR(-ENOMEM); + err = ida_simple_get(&umem_ida, 0, 0, GFP_KERNEL); + if (err < 0) { + kfree(umem); + return ERR_PTR(err); + } + umem->id = err; + err = xdp_umem_reg(umem, mr); if (err) { + ida_simple_remove(&umem_ida, umem->id); kfree(umem); return ERR_PTR(err); } -- cgit v1.2.3 From a36b38aa2af61146ea80980a01cf6e952ab021c1 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Thu, 24 Jan 2019 19:59:39 +0100 Subject: xsk: add sock_diag interface for AF_XDP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds the sock_diag interface for querying sockets from user space. Tools like iproute2 ss(8) can use this interface to list open AF_XDP sockets. The user-space ABI is defined in linux/xdp_diag.h and includes netlink request and response structs. The request can query sockets and the response contains socket information about the rings, umems, inode and more. Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/uapi/linux/xdp_diag.h | 72 ++++++++++++++++ net/xdp/Kconfig | 8 ++ net/xdp/Makefile | 1 + net/xdp/xsk.c | 6 +- net/xdp/xsk.h | 12 +++ net/xdp/xsk_diag.c | 191 ++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 285 insertions(+), 5 deletions(-) create mode 100644 include/uapi/linux/xdp_diag.h create mode 100644 net/xdp/xsk.h create mode 100644 net/xdp/xsk_diag.c (limited to 'include') diff --git a/include/uapi/linux/xdp_diag.h b/include/uapi/linux/xdp_diag.h new file mode 100644 index 000000000000..78b2591a7782 --- /dev/null +++ b/include/uapi/linux/xdp_diag.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * xdp_diag: interface for query/monitor XDP sockets + * Copyright(c) 2019 Intel Corporation. + */ + +#ifndef _LINUX_XDP_DIAG_H +#define _LINUX_XDP_DIAG_H + +#include + +struct xdp_diag_req { + __u8 sdiag_family; + __u8 sdiag_protocol; + __u16 pad; + __u32 xdiag_ino; + __u32 xdiag_show; + __u32 xdiag_cookie[2]; +}; + +struct xdp_diag_msg { + __u8 xdiag_family; + __u8 xdiag_type; + __u16 pad; + __u32 xdiag_ino; + __u32 xdiag_cookie[2]; +}; + +#define XDP_SHOW_INFO (1 << 0) /* Basic information */ +#define XDP_SHOW_RING_CFG (1 << 1) +#define XDP_SHOW_UMEM (1 << 2) +#define XDP_SHOW_MEMINFO (1 << 3) + +enum { + XDP_DIAG_NONE, + XDP_DIAG_INFO, + XDP_DIAG_UID, + XDP_DIAG_RX_RING, + XDP_DIAG_TX_RING, + XDP_DIAG_UMEM, + XDP_DIAG_UMEM_FILL_RING, + XDP_DIAG_UMEM_COMPLETION_RING, + XDP_DIAG_MEMINFO, + __XDP_DIAG_MAX, +}; + +#define XDP_DIAG_MAX (__XDP_DIAG_MAX - 1) + +struct xdp_diag_info { + __u32 ifindex; + __u32 queue_id; +}; + +struct xdp_diag_ring { + __u32 entries; /*num descs */ +}; + +#define XDP_DU_F_ZEROCOPY (1 << 0) + +struct xdp_diag_umem { + __u64 size; + __u32 id; + __u32 num_pages; + __u32 chunk_size; + __u32 headroom; + __u32 ifindex; + __u32 queue_id; + __u32 flags; + __u32 refs; +}; + +#endif /* _LINUX_XDP_DIAG_H */ diff --git a/net/xdp/Kconfig b/net/xdp/Kconfig index 90e4a7152854..0255b33cff4b 100644 --- a/net/xdp/Kconfig +++ b/net/xdp/Kconfig @@ -5,3 +5,11 @@ config XDP_SOCKETS help XDP sockets allows a channel between XDP programs and userspace applications. + +config XDP_SOCKETS_DIAG + tristate "XDP sockets: monitoring interface" + depends on XDP_SOCKETS + default n + help + Support for PF_XDP sockets monitoring interface used by the ss tool. + If unsure, say Y. diff --git a/net/xdp/Makefile b/net/xdp/Makefile index 04f073146256..59dbfdf93dca 100644 --- a/net/xdp/Makefile +++ b/net/xdp/Makefile @@ -1 +1,2 @@ obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o +obj-$(CONFIG_XDP_SOCKETS_DIAG) += xsk_diag.o diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 80ca48cefc42..949d3bbccb2f 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -27,14 +27,10 @@ #include "xsk_queue.h" #include "xdp_umem.h" +#include "xsk.h" #define TX_BATCH_SIZE 16 -static struct xdp_sock *xdp_sk(struct sock *sk) -{ - return (struct xdp_sock *)sk; -} - bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return READ_ONCE(xs->rx) && READ_ONCE(xs->umem) && diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h new file mode 100644 index 000000000000..ba8120610426 --- /dev/null +++ b/net/xdp/xsk.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2019 Intel Corporation. */ + +#ifndef XSK_H_ +#define XSK_H_ + +static inline struct xdp_sock *xdp_sk(struct sock *sk) +{ + return (struct xdp_sock *)sk; +} + +#endif /* XSK_H_ */ diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c new file mode 100644 index 000000000000..661d007c3b28 --- /dev/null +++ b/net/xdp/xsk_diag.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP sockets monitoring support + * + * Copyright(c) 2019 Intel Corporation. + * + * Author: Björn Töpel + */ + +#include +#include +#include +#include + +#include "xsk_queue.h" +#include "xsk.h" + +static int xsk_diag_put_info(const struct xdp_sock *xs, struct sk_buff *nlskb) +{ + struct xdp_diag_info di = {}; + + di.ifindex = xs->dev ? xs->dev->ifindex : 0; + di.queue_id = xs->queue_id; + return nla_put(nlskb, XDP_DIAG_INFO, sizeof(di), &di); +} + +static int xsk_diag_put_ring(const struct xsk_queue *queue, int nl_type, + struct sk_buff *nlskb) +{ + struct xdp_diag_ring dr = {}; + + dr.entries = queue->nentries; + return nla_put(nlskb, nl_type, sizeof(dr), &dr); +} + +static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs, + struct sk_buff *nlskb) +{ + int err = 0; + + if (xs->rx) + err = xsk_diag_put_ring(xs->rx, XDP_DIAG_RX_RING, nlskb); + if (!err && xs->tx) + err = xsk_diag_put_ring(xs->tx, XDP_DIAG_TX_RING, nlskb); + return err; +} + +static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) +{ + struct xdp_umem *umem = xs->umem; + struct xdp_diag_umem du = {}; + int err; + + if (!umem) + return 0; + + du.id = umem->id; + du.size = umem->size; + du.num_pages = umem->npgs; + du.chunk_size = (__u32)(~umem->chunk_mask + 1); + du.headroom = umem->headroom; + du.ifindex = umem->dev ? umem->dev->ifindex : 0; + du.queue_id = umem->queue_id; + du.flags = 0; + if (umem->zc) + du.flags |= XDP_DU_F_ZEROCOPY; + du.refs = refcount_read(&umem->users); + + err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du); + + if (!err && umem->fq) + err = xsk_diag_put_ring(xs->tx, XDP_DIAG_UMEM_FILL_RING, nlskb); + if (!err && umem->cq) { + err = xsk_diag_put_ring(xs->tx, XDP_DIAG_UMEM_COMPLETION_RING, + nlskb); + } + return err; +} + +static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb, + struct xdp_diag_req *req, + struct user_namespace *user_ns, + u32 portid, u32 seq, u32 flags, int sk_ino) +{ + struct xdp_sock *xs = xdp_sk(sk); + struct xdp_diag_msg *msg; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(nlskb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*msg), + flags); + if (!nlh) + return -EMSGSIZE; + + msg = nlmsg_data(nlh); + memset(msg, 0, sizeof(*msg)); + msg->xdiag_family = AF_XDP; + msg->xdiag_type = sk->sk_type; + msg->xdiag_ino = sk_ino; + sock_diag_save_cookie(sk, msg->xdiag_cookie); + + if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb)) + goto out_nlmsg_trim; + + if ((req->xdiag_show & XDP_SHOW_INFO) && + nla_put_u32(nlskb, XDP_DIAG_UID, + from_kuid_munged(user_ns, sock_i_uid(sk)))) + goto out_nlmsg_trim; + + if ((req->xdiag_show & XDP_SHOW_RING_CFG) && + xsk_diag_put_rings_cfg(xs, nlskb)) + goto out_nlmsg_trim; + + if ((req->xdiag_show & XDP_SHOW_UMEM) && + xsk_diag_put_umem(xs, nlskb)) + goto out_nlmsg_trim; + + if ((req->xdiag_show & XDP_SHOW_MEMINFO) && + sock_diag_put_meminfo(sk, nlskb, XDP_DIAG_MEMINFO)) + goto out_nlmsg_trim; + + nlmsg_end(nlskb, nlh); + return 0; + +out_nlmsg_trim: + nlmsg_cancel(nlskb, nlh); + return -EMSGSIZE; +} + +static int xsk_diag_dump(struct sk_buff *nlskb, struct netlink_callback *cb) +{ + struct xdp_diag_req *req = nlmsg_data(cb->nlh); + struct net *net = sock_net(nlskb->sk); + int num = 0, s_num = cb->args[0]; + struct sock *sk; + + mutex_lock(&net->xdp.lock); + + sk_for_each(sk, &net->xdp.list) { + if (!net_eq(sock_net(sk), net)) + continue; + if (num++ < s_num) + continue; + + if (xsk_diag_fill(sk, nlskb, req, + sk_user_ns(NETLINK_CB(cb->skb).sk), + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + sock_i_ino(sk)) < 0) { + num--; + break; + } + } + + mutex_unlock(&net->xdp.lock); + cb->args[0] = num; + return nlskb->len; +} + +static int xsk_diag_handler_dump(struct sk_buff *nlskb, struct nlmsghdr *hdr) +{ + struct netlink_dump_control c = { .dump = xsk_diag_dump }; + int hdrlen = sizeof(struct xdp_diag_req); + struct net *net = sock_net(nlskb->sk); + + if (nlmsg_len(hdr) < hdrlen) + return -EINVAL; + + if (!(hdr->nlmsg_flags & NLM_F_DUMP)) + return -EOPNOTSUPP; + + return netlink_dump_start(net->diag_nlsk, nlskb, hdr, &c); +} + +static const struct sock_diag_handler xsk_diag_handler = { + .family = AF_XDP, + .dump = xsk_diag_handler_dump, +}; + +static int __init xsk_diag_init(void) +{ + return sock_diag_register(&xsk_diag_handler); +} + +static void __exit xsk_diag_exit(void) +{ + sock_diag_unregister(&xsk_diag_handler); +} + +module_init(xsk_diag_init); +module_exit(xsk_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP); -- cgit v1.2.3 From 434a4315b9617bf1742bc64712bf44a208502f7f Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 23 Jan 2019 07:31:58 +0100 Subject: net: phy: change phy_start_interrupts to phy_request_interrupt Now that we enable the interrupts in phy_start() we don't have to do it before. Therefore remove enabling interrupts from phy_start_interrupts() and rename this function to reflect the changed functionality. v2: - improve warning to clearly state that we fall back to polling Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 23 +++++++++++------------ drivers/net/phy/phy_device.c | 4 ++-- drivers/net/phy/phylink.c | 4 ++-- include/linux/phy.h | 2 +- 4 files changed, 16 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 079b6a617fc8..d12aa512b7f5 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -785,28 +785,27 @@ static int phy_enable_interrupts(struct phy_device *phydev) } /** - * phy_start_interrupts - request and enable interrupts for a PHY device + * phy_request_interrupt - request interrupt for a PHY device * @phydev: target phy_device struct * * Description: Request the interrupt for the given PHY. * If this fails, then we set irq to PHY_POLL. - * Otherwise, we enable the interrupts in the PHY. * This should only be called with a valid IRQ number. - * Returns 0 on success or < 0 on error. */ -int phy_start_interrupts(struct phy_device *phydev) +void phy_request_interrupt(struct phy_device *phydev) { - if (request_threaded_irq(phydev->irq, NULL, phy_interrupt, - IRQF_ONESHOT | IRQF_SHARED, - phydev_name(phydev), phydev) < 0) { - phydev_warn(phydev, "Can't get IRQ %d\n", phydev->irq); + int err; + + err = request_threaded_irq(phydev->irq, NULL, phy_interrupt, + IRQF_ONESHOT | IRQF_SHARED, + phydev_name(phydev), phydev); + if (err) { + phydev_warn(phydev, "Error %d requesting IRQ %d, falling back to polling\n", + err, phydev->irq); phydev->irq = PHY_POLL; - return 0; } - - return phy_enable_interrupts(phydev); } -EXPORT_SYMBOL(phy_start_interrupts); +EXPORT_SYMBOL(phy_request_interrupt); /** * phy_stop - Bring down the PHY link, and stop checking the status diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 64c25a0684ac..891e0178b97f 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -951,8 +951,8 @@ int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, return rc; phy_prepare_link(phydev, handler); - if (phydev->irq > 0) - phy_start_interrupts(phydev); + if (phy_interrupt_is_valid(phydev)) + phy_request_interrupt(phydev); return 0; } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index c1b6e05ba60c..2e21ce42e388 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -676,8 +676,8 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy) __ETHTOOL_LINK_MODE_MASK_NBITS, pl->supported, __ETHTOOL_LINK_MODE_MASK_NBITS, phy->advertising); - if (phy->irq > 0) - phy_start_interrupts(phy); + if (phy_interrupt_is_valid(phy)) + phy_request_interrupt(phy); return 0; } diff --git a/include/linux/phy.h b/include/linux/phy.h index 1f3873a2ff29..70f83d0d7469 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1047,7 +1047,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); -int phy_start_interrupts(struct phy_device *phydev); +void phy_request_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); -- cgit v1.2.3 From 949e7cea0cbccd7e2afc4b374e2be998b8fcef78 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 23 Jan 2019 19:14:50 +0200 Subject: bonding: count master 3ad stats separately I made a dumb mistake when I summed up the slave stats, obviously slaves can come and go which would make the master stats unreliable. Count and export the master stats separately. Fixes: a258aeacd7f0 ("bonding: add support for xstats and export 3ad stats") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 39 +++++++++++++------------------------- drivers/net/bonding/bond_netlink.c | 18 +++++++----------- include/net/bond_3ad.h | 2 +- 3 files changed, 21 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index d30c21b34858..9274dcc6e9b0 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -853,6 +853,7 @@ static int ad_lacpdu_send(struct port *port) return -ENOMEM; atomic64_inc(&SLAVE_AD_INFO(slave)->stats.lacpdu_tx); + atomic64_inc(&BOND_AD_INFO(slave->bond).stats.lacpdu_tx); skb->dev = slave->dev; skb_reset_mac_header(skb); @@ -898,9 +899,11 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker) switch (marker->tlv_type) { case AD_MARKER_INFORMATION_SUBTYPE: atomic64_inc(&SLAVE_AD_INFO(slave)->stats.marker_tx); + atomic64_inc(&BOND_AD_INFO(slave->bond).stats.marker_tx); break; case AD_MARKER_RESPONSE_SUBTYPE: atomic64_inc(&SLAVE_AD_INFO(slave)->stats.marker_resp_tx); + atomic64_inc(&BOND_AD_INFO(slave->bond).stats.marker_resp_tx); break; } @@ -1098,9 +1101,10 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) */ last_state = port->sm_rx_state; - if (lacpdu) + if (lacpdu) { atomic64_inc(&SLAVE_AD_INFO(port->slave)->stats.lacpdu_rx); - + atomic64_inc(&BOND_AD_INFO(port->slave->bond).stats.lacpdu_rx); + } /* check if state machine should change state */ /* first, check if port was reinitialized */ @@ -1938,6 +1942,7 @@ static void ad_marker_info_received(struct bond_marker *marker_info, struct bond_marker marker; atomic64_inc(&SLAVE_AD_INFO(port->slave)->stats.marker_rx); + atomic64_inc(&BOND_AD_INFO(port->slave->bond).stats.marker_rx); /* copy the received marker data to the response marker */ memcpy(&marker, marker_info, sizeof(struct bond_marker)); @@ -1964,6 +1969,7 @@ static void ad_marker_response_received(struct bond_marker *marker, struct port *port) { atomic64_inc(&SLAVE_AD_INFO(port->slave)->stats.marker_resp_rx); + atomic64_inc(&BOND_AD_INFO(port->slave->bond).stats.marker_resp_rx); /* DO NOTHING, SINCE WE DECIDED NOT TO IMPLEMENT THIS FEATURE FOR NOW */ } @@ -2374,6 +2380,7 @@ re_arm: */ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave) { + struct bonding *bond = slave->bond; int ret = RX_HANDLER_ANOTHER; struct bond_marker *marker; struct port *port; @@ -2419,10 +2426,13 @@ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave) port->actor_port_number); stat = &SLAVE_AD_INFO(slave)->stats.marker_unknown_rx; atomic64_inc(stat); + stat = &BOND_AD_INFO(bond).stats.marker_unknown_rx; + atomic64_inc(stat); } break; default: atomic64_inc(&SLAVE_AD_INFO(slave)->stats.lacpdu_unknown_rx); + atomic64_inc(&BOND_AD_INFO(bond).stats.lacpdu_unknown_rx); } return ret; @@ -2662,6 +2672,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, lacpdu = skb_header_pointer(skb, 0, sizeof(_lacpdu), &_lacpdu); if (!lacpdu) { atomic64_inc(&SLAVE_AD_INFO(slave)->stats.lacpdu_illegal_rx); + atomic64_inc(&BOND_AD_INFO(bond).stats.lacpdu_illegal_rx); return RX_HANDLER_ANOTHER; } @@ -2698,30 +2709,6 @@ void bond_3ad_update_lacp_rate(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); } -void bond_3ad_stats_add(struct slave *slave, struct bond_3ad_stats *stats) -{ - struct bond_3ad_stats *rstats = &SLAVE_AD_INFO(slave)->stats; - u64 stat; - - atomic64_add(atomic64_read(&rstats->lacpdu_rx), &stats->lacpdu_rx); - atomic64_add(atomic64_read(&rstats->lacpdu_tx), &stats->lacpdu_tx); - - stat = atomic64_read(&rstats->lacpdu_unknown_rx); - atomic64_add(stat, &stats->lacpdu_unknown_rx); - stat = atomic64_read(&rstats->lacpdu_illegal_rx); - atomic64_add(stat, &stats->lacpdu_illegal_rx); - - atomic64_add(atomic64_read(&rstats->marker_rx), &stats->marker_rx); - atomic64_add(atomic64_read(&rstats->marker_tx), &stats->marker_tx); - - stat = atomic64_read(&rstats->marker_resp_rx); - atomic64_add(stat, &stats->marker_resp_rx); - stat = atomic64_read(&rstats->marker_resp_tx); - atomic64_add(stat, &stats->marker_resp_tx); - stat = atomic64_read(&rstats->marker_unknown_rx); - atomic64_add(stat, &stats->marker_unknown_rx); -} - size_t bond_3ad_stats_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */ diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index d1338fbe1830..b286f591242e 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -715,16 +715,12 @@ static int bond_fill_linkxstats(struct sk_buff *skb, if (!nest) return -EMSGSIZE; if (BOND_MODE(bond) == BOND_MODE_8023AD) { - struct bond_3ad_stats stats; - struct list_head *iter; - - memset(&stats, 0, sizeof(stats)); - if (slave) { - bond_3ad_stats_add(slave, &stats); - } else { - bond_for_each_slave(bond, slave, iter) - bond_3ad_stats_add(slave, &stats); - } + struct bond_3ad_stats *stats; + + if (slave) + stats = &SLAVE_AD_INFO(slave)->stats; + else + stats = &BOND_AD_INFO(bond).stats; nest2 = nla_nest_start(skb, BOND_XSTATS_3AD); if (!nest2) { @@ -732,7 +728,7 @@ static int bond_fill_linkxstats(struct sk_buff *skb, return -EMSGSIZE; } - if (bond_3ad_stats_fill(skb, &stats)) { + if (bond_3ad_stats_fill(skb, stats)) { nla_nest_cancel(skb, nest2); nla_nest_end(skb, nest); return -EMSGSIZE; diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 25aaf49d19be..c781e1afd683 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -278,6 +278,7 @@ struct ad_system { struct ad_bond_info { struct ad_system system; /* 802.3ad system structure */ + struct bond_3ad_stats stats; u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ u16 aggregator_identifier; }; @@ -321,7 +322,6 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); -void bond_3ad_stats_add(struct slave *slave, struct bond_3ad_stats *stats); int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); size_t bond_3ad_stats_size(void); #endif /* _NET_BOND_3AD_H */ -- cgit v1.2.3 From 78dc70ebaa38aa303274e333be6c98eef87619e2 Mon Sep 17 00:00:00 2001 From: Priyaranjan Jha Date: Wed, 23 Jan 2019 12:04:54 -0800 Subject: tcp_bbr: adapt cwnd based on ack aggregation estimation Aggregation effects are extremely common with wifi, cellular, and cable modem link technologies, ACK decimation in middleboxes, and LRO and GRO in receiving hosts. The aggregation can happen in either direction, data or ACKs, but in either case the aggregation effect is visible to the sender in the ACK stream. Previously BBR's sending was often limited by cwnd under severe ACK aggregation/decimation because BBR sized the cwnd at 2*BDP. If packets were acked in bursts after long delays (e.g. one ACK acking 5*BDP after 5*RTT), BBR's sending was halted after sending 2*BDP over 2*RTT, leaving the bottleneck idle for potentially long periods. Note that loss-based congestion control does not have this issue because when facing aggregation it continues increasing cwnd after bursts of ACKs, growing cwnd until the buffer is full. To achieve good throughput in the presence of aggregation effects, this algorithm allows the BBR sender to put extra data in flight to keep the bottleneck utilized during silences in the ACK stream that it has evidence to suggest were caused by aggregation. A summary of the algorithm: when a burst of packets are acked by a stretched ACK or a burst of ACKs or both, BBR first estimates the expected amount of data that should have been acked, based on its estimated bandwidth. Then the surplus ("extra_acked") is recorded in a windowed-max filter to estimate the recent level of observed ACK aggregation. Then cwnd is increased by the ACK aggregation estimate. The larger cwnd avoids BBR being cwnd-limited in the face of ACK silences that recent history suggests were caused by aggregation. As a sanity check, the ACK aggregation degree is upper-bounded by the cwnd (at the time of measurement) and a global max of BW * 100ms. The algorithm is further described by the following presentation: https://datatracker.ietf.org/meeting/101/materials/slides-101-iccrg-an-update-on-bbr-work-at-google-00 In our internal testing, we observed a significant increase in BBR throughput (measured using netperf), in a basic wifi setup. - Host1 (sender on ethernet) -> AP -> Host2 (receiver on wifi) - 2.4 GHz -> BBR before: ~73 Mbps; BBR after: ~102 Mbps; CUBIC: ~100 Mbps - 5.0 GHz -> BBR before: ~362 Mbps; BBR after: ~593 Mbps; CUBIC: ~601 Mbps Also, this code is running globally on YouTube TCP connections and produced significant bandwidth increases for YouTube traffic. This is based on Ian Swett's max_ack_height_ algorithm from the QUIC BBR implementation. Signed-off-by: Priyaranjan Jha Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 4 +- net/ipv4/tcp_bbr.c | 122 ++++++++++++++++++++++++++++++++++++- 2 files changed, 123 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 371b3b45fd5c..fe0d9b44d6fc 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -139,8 +139,8 @@ struct inet_connection_sock { } icsk_mtup; u32 icsk_user_timeout; - u64 icsk_ca_priv[88 / sizeof(u64)]; -#define ICSK_CA_PRIV_SIZE (11 * sizeof(u64)) + u64 icsk_ca_priv[104 / sizeof(u64)]; +#define ICSK_CA_PRIV_SIZE (13 * sizeof(u64)) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6b6c7f14ccf9..56be7d27f208 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -115,6 +115,14 @@ struct bbr { unused_b:5; u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ u32 full_bw; /* recent bw, to estimate if pipe is full */ + + /* For tracking ACK aggregation: */ + u64 ack_epoch_mstamp; /* start of ACK sampling epoch */ + u16 extra_acked[2]; /* max excess data ACKed in epoch */ + u32 ack_epoch_acked:20, /* packets (S)ACKed in sampling epoch */ + extra_acked_win_rtts:5, /* age of extra_acked, in round trips */ + extra_acked_win_idx:1, /* current index in extra_acked array */ + unused_c:6; }; #define CYCLE_LEN 8 /* number of phases in a pacing gain cycle */ @@ -182,6 +190,15 @@ static const u32 bbr_lt_bw_diff = 4000 / 8; /* If we estimate we're policed, use lt_bw for this many round trips: */ static const u32 bbr_lt_bw_max_rtts = 48; +/* Gain factor for adding extra_acked to target cwnd: */ +static const int bbr_extra_acked_gain = BBR_UNIT; +/* Window length of extra_acked window. */ +static const u32 bbr_extra_acked_win_rtts = 5; +/* Max allowed val for ack_epoch_acked, after which sampling epoch is reset */ +static const u32 bbr_ack_epoch_acked_reset_thresh = 1U << 20; +/* Time period for clamping cwnd increment due to ack aggregation */ +static const u32 bbr_extra_acked_max_us = 100 * 1000; + static void bbr_check_probe_rtt_done(struct sock *sk); /* Do we estimate that STARTUP filled the pipe? */ @@ -208,6 +225,16 @@ static u32 bbr_bw(const struct sock *sk) return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk); } +/* Return maximum extra acked in past k-2k round trips, + * where k = bbr_extra_acked_win_rtts. + */ +static u16 bbr_extra_acked(const struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return max(bbr->extra_acked[0], bbr->extra_acked[1]); +} + /* Return rate in bytes per second, optionally with a gain. * The order here is chosen carefully to avoid overflow of u64. This should * work for input rates of up to 2.9Tbit/sec and gain of 2.89x. @@ -305,6 +332,8 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) if (event == CA_EVENT_TX_START && tp->app_limited) { bbr->idle_restart = 1; + bbr->ack_epoch_mstamp = tp->tcp_mstamp; + bbr->ack_epoch_acked = 0; /* Avoid pointless buffer overflows: pace at est. bw if we don't * need more speed (we're restarting from idle and app-limited). */ @@ -418,6 +447,22 @@ static u32 bbr_packets_in_net_at_edt(struct sock *sk, u32 inflight_now) return inflight_at_edt - interval_delivered; } +/* Find the cwnd increment based on estimate of ack aggregation */ +static u32 bbr_ack_aggregation_cwnd(struct sock *sk) +{ + u32 max_aggr_cwnd, aggr_cwnd = 0; + + if (bbr_extra_acked_gain && bbr_full_bw_reached(sk)) { + max_aggr_cwnd = ((u64)bbr_bw(sk) * bbr_extra_acked_max_us) + / BW_UNIT; + aggr_cwnd = (bbr_extra_acked_gain * bbr_extra_acked(sk)) + >> BBR_SCALE; + aggr_cwnd = min(aggr_cwnd, max_aggr_cwnd); + } + + return aggr_cwnd; +} + /* An optimization in BBR to reduce losses: On the first round of recovery, we * follow the packet conservation principle: send P packets per P packets acked. * After that, we slow-start and send at most 2*P packets per P packets acked. @@ -478,9 +523,15 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) goto done; - /* If we're below target cwnd, slow start cwnd toward target cwnd. */ target_cwnd = bbr_bdp(sk, bw, gain); + + /* Increment the cwnd to account for excess ACKed data that seems + * due to aggregation (of data and/or ACKs) visible in the ACK stream. + */ + target_cwnd += bbr_ack_aggregation_cwnd(sk); target_cwnd = bbr_quantization_budget(sk, target_cwnd, gain); + + /* If we're below target cwnd, slow start cwnd toward target cwnd. */ if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ cwnd = min(cwnd + acked, target_cwnd); else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND) @@ -745,6 +796,67 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) } } +/* Estimates the windowed max degree of ack aggregation. + * This is used to provision extra in-flight data to keep sending during + * inter-ACK silences. + * + * Degree of ack aggregation is estimated as extra data acked beyond expected. + * + * max_extra_acked = "maximum recent excess data ACKed beyond max_bw * interval" + * cwnd += max_extra_acked + * + * Max extra_acked is clamped by cwnd and bw * bbr_extra_acked_max_us (100 ms). + * Max filter is an approximate sliding window of 5-10 (packet timed) round + * trips. + */ +static void bbr_update_ack_aggregation(struct sock *sk, + const struct rate_sample *rs) +{ + u32 epoch_us, expected_acked, extra_acked; + struct bbr *bbr = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + if (!bbr_extra_acked_gain || rs->acked_sacked <= 0 || + rs->delivered < 0 || rs->interval_us <= 0) + return; + + if (bbr->round_start) { + bbr->extra_acked_win_rtts = min(0x1F, + bbr->extra_acked_win_rtts + 1); + if (bbr->extra_acked_win_rtts >= bbr_extra_acked_win_rtts) { + bbr->extra_acked_win_rtts = 0; + bbr->extra_acked_win_idx = bbr->extra_acked_win_idx ? + 0 : 1; + bbr->extra_acked[bbr->extra_acked_win_idx] = 0; + } + } + + /* Compute how many packets we expected to be delivered over epoch. */ + epoch_us = tcp_stamp_us_delta(tp->delivered_mstamp, + bbr->ack_epoch_mstamp); + expected_acked = ((u64)bbr_bw(sk) * epoch_us) / BW_UNIT; + + /* Reset the aggregation epoch if ACK rate is below expected rate or + * significantly large no. of ack received since epoch (potentially + * quite old epoch). + */ + if (bbr->ack_epoch_acked <= expected_acked || + (bbr->ack_epoch_acked + rs->acked_sacked >= + bbr_ack_epoch_acked_reset_thresh)) { + bbr->ack_epoch_acked = 0; + bbr->ack_epoch_mstamp = tp->delivered_mstamp; + expected_acked = 0; + } + + /* Compute excess data delivered, beyond what was expected. */ + bbr->ack_epoch_acked = min_t(u32, 0xFFFFF, + bbr->ack_epoch_acked + rs->acked_sacked); + extra_acked = bbr->ack_epoch_acked - expected_acked; + extra_acked = min(extra_acked, tp->snd_cwnd); + if (extra_acked > bbr->extra_acked[bbr->extra_acked_win_idx]) + bbr->extra_acked[bbr->extra_acked_win_idx] = extra_acked; +} + /* Estimate when the pipe is full, using the change in delivery rate: BBR * estimates that STARTUP filled the pipe if the estimated bw hasn't changed by * at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited @@ -899,6 +1011,7 @@ static void bbr_update_gains(struct sock *sk) static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) { bbr_update_bw(sk, rs); + bbr_update_ack_aggregation(sk, rs); bbr_update_cycle_phase(sk, rs); bbr_check_full_bw_reached(sk, rs); bbr_check_drain(sk, rs); @@ -950,6 +1063,13 @@ static void bbr_init(struct sock *sk) bbr_reset_lt_bw_sampling(sk); bbr_reset_startup_mode(sk); + bbr->ack_epoch_mstamp = tp->tcp_mstamp; + bbr->ack_epoch_acked = 0; + bbr->extra_acked_win_rtts = 0; + bbr->extra_acked_win_idx = 0; + bbr->extra_acked[0] = 0; + bbr->extra_acked[1] = 0; + cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); } -- cgit v1.2.3 From e2bef3847e3d0d57dcf316de50c4b1a5a91816b7 Mon Sep 17 00:00:00 2001 From: Rajat Jain Date: Thu, 24 Jan 2019 15:28:13 -0800 Subject: Bluetooth: Allow driver specific cmd timeout handling Add a hook to allow the BT driver to do device or command specific handling in case of timeouts. This is to be used by Intel driver to reset the device after certain number of timeouts. Signed-off-by: Rajat Jain Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_core.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e5ea633ea368..094e61e07030 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -437,6 +437,7 @@ struct hci_dev { int (*post_init)(struct hci_dev *hdev); int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); + void (*cmd_timeout)(struct hci_dev *hdev); }; #define HCI_PHY_HANDLE(handle) (handle & 0xff) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 7352fe85674b..75793265ba9e 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2578,6 +2578,9 @@ static void hci_cmd_timeout(struct work_struct *work) bt_dev_err(hdev, "command tx timeout"); } + if (hdev->cmd_timeout) + hdev->cmd_timeout(hdev); + atomic_set(&hdev->cmd_cnt, 1); queue_work(hdev->workqueue, &hdev->cmd_work); } -- cgit v1.2.3 From 12ea20f61637539dfac6e6e41beb07c21ba890d8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 18 Jan 2019 00:14:19 +0100 Subject: crypto: morus - Cleanup license mess Precise and non-ambiguous license information is important. The recently added morus header files have a SPDX license identifier, which is nice, but at the same time they have a contradictionary license boiler plate text. SPDX-License-Identifier: GPL-2.0 versus * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) * any later version Oh well. As the other morus related files are licensed under the GPL v2 or later, it's assumed that the boiler plate code is correct, but the SPDX license identifier is wrong. Fix the SPDX identifier and remove the boiler plate as it is redundant. Fixes: 56e8e57fc3a7 ("crypto: morus - Add common SIMD glue code for MORUS") Fixes: 396be41f16fd ("crypto: morus - Add generic MORUS AEAD implementations") Signed-off-by: Thomas Gleixner Cc: Ondrej Mosnacek Cc: Herbert Xu Cc: "David S. Miller" Cc: linux-crypto@vger.kernel.org Acked-by: Ondrej Mosnacek Signed-off-by: Herbert Xu --- include/crypto/morus1280_glue.h | 7 +------ include/crypto/morus640_glue.h | 7 +------ include/crypto/morus_common.h | 7 +------ 3 files changed, 3 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/crypto/morus1280_glue.h b/include/crypto/morus1280_glue.h index ba782e10065e..ad2aa743dd99 100644 --- a/include/crypto/morus1280_glue.h +++ b/include/crypto/morus1280_glue.h @@ -1,15 +1,10 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * The MORUS-1280 Authenticated-Encryption Algorithm * Common glue skeleton -- header file * * Copyright (c) 2016-2018 Ondrej Mosnacek * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. */ #ifndef _CRYPTO_MORUS1280_GLUE_H diff --git a/include/crypto/morus640_glue.h b/include/crypto/morus640_glue.h index 27fa790a2362..df8e1103ff94 100644 --- a/include/crypto/morus640_glue.h +++ b/include/crypto/morus640_glue.h @@ -1,15 +1,10 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * The MORUS-640 Authenticated-Encryption Algorithm * Common glue skeleton -- header file * * Copyright (c) 2016-2018 Ondrej Mosnacek * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. */ #ifndef _CRYPTO_MORUS640_GLUE_H diff --git a/include/crypto/morus_common.h b/include/crypto/morus_common.h index 39f28c749951..969510a9a56c 100644 --- a/include/crypto/morus_common.h +++ b/include/crypto/morus_common.h @@ -1,15 +1,10 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * The MORUS Authenticated-Encryption Algorithm * Common definitions * * Copyright (c) 2016-2018 Ondrej Mosnacek * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. */ #ifndef _CRYPTO_MORUS_COMMON_H -- cgit v1.2.3 From 9572442dcf487e534e70b30f43e21a364cf483e9 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Fri, 18 Jan 2019 13:58:11 +0800 Subject: crypto: api - add a helper to (un)register a array of templates This patch add a helper to (un)register a array of templates. The following patches will use this helper to simplify the code. Signed-off-by: Xiongfeng Wang Reviewed-by: Eric Biggers Signed-off-by: Herbert Xu --- crypto/algapi.c | 27 +++++++++++++++++++++++++++ include/crypto/algapi.h | 2 ++ 2 files changed, 29 insertions(+) (limited to 'include') diff --git a/crypto/algapi.c b/crypto/algapi.c index 713baabeb643..4c9c86b55738 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -494,6 +494,24 @@ out: } EXPORT_SYMBOL_GPL(crypto_register_template); +int crypto_register_templates(struct crypto_template *tmpls, int count) +{ + int i, err; + + for (i = 0; i < count; i++) { + err = crypto_register_template(&tmpls[i]); + if (err) + goto out; + } + return 0; + +out: + for (--i; i >= 0; --i) + crypto_unregister_template(&tmpls[i]); + return err; +} +EXPORT_SYMBOL_GPL(crypto_register_templates); + void crypto_unregister_template(struct crypto_template *tmpl) { struct crypto_instance *inst; @@ -523,6 +541,15 @@ void crypto_unregister_template(struct crypto_template *tmpl) } EXPORT_SYMBOL_GPL(crypto_unregister_template); +void crypto_unregister_templates(struct crypto_template *tmpls, int count) +{ + int i; + + for (i = count - 1; i >= 0; --i) + crypto_unregister_template(&tmpls[i]); +} +EXPORT_SYMBOL_GPL(crypto_unregister_templates); + static struct crypto_template *__crypto_lookup_template(const char *name) { struct crypto_template *q, *tmpl = NULL; diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 093869f175d6..4be38cd0b8d5 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -143,7 +143,9 @@ extern const struct crypto_type crypto_blkcipher_type; void crypto_mod_put(struct crypto_alg *alg); int crypto_register_template(struct crypto_template *tmpl); +int crypto_register_templates(struct crypto_template *tmpls, int count); void crypto_unregister_template(struct crypto_template *tmpl); +void crypto_unregister_templates(struct crypto_template *tmpls, int count); struct crypto_template *crypto_lookup_template(const char *name); int crypto_register_instance(struct crypto_template *tmpl, -- cgit v1.2.3 From 231baecdef7a906579925ccf1bd45aa734f32320 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 18 Jan 2019 22:48:00 -0800 Subject: crypto: clarify name of WEAK_KEY request flag CRYPTO_TFM_REQ_WEAK_KEY confuses newcomers to the crypto API because it sounds like it is requesting a weak key. Actually, it is requesting that weak keys be forbidden (for algorithms that have the notion of "weak keys"; currently only DES and XTS do). Also it is only one letter away from CRYPTO_TFM_RES_WEAK_KEY, with which it can be easily confused. (This in fact happened in the UX500 driver, though just in some debugging messages.) Therefore, make the intent clear by renaming it to CRYPTO_TFM_REQ_FORBID_WEAK_KEYS. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- arch/s390/crypto/des_s390.c | 4 ++-- arch/sparc/crypto/des_glue.c | 4 ++-- crypto/des_generic.c | 4 ++-- crypto/testmgr.c | 14 +++++++------- crypto/testmgr.h | 4 ++-- drivers/crypto/atmel-tdes.c | 2 +- drivers/crypto/bcm/cipher.c | 4 ++-- drivers/crypto/ccp/ccp-crypto-des3.c | 2 +- drivers/crypto/ccree/cc_cipher.c | 3 ++- drivers/crypto/hifn_795x.c | 3 ++- drivers/crypto/inside-secure/safexcel_cipher.c | 2 +- drivers/crypto/ixp4xx_crypto.c | 4 ++-- drivers/crypto/marvell/cipher.c | 2 +- drivers/crypto/n2_core.c | 2 +- drivers/crypto/omap-des.c | 2 +- drivers/crypto/picoxcell_crypto.c | 3 ++- drivers/crypto/qce/ablkcipher.c | 4 ++-- drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c | 2 +- drivers/crypto/sunxi-ss/sun4i-ss-cipher.c | 2 +- drivers/crypto/talitos.c | 2 +- drivers/crypto/ux500/cryp/cryp_core.c | 20 +++++++++++--------- fs/crypto/keyinfo.c | 4 ++-- fs/ecryptfs/crypto.c | 5 +++-- include/crypto/xts.h | 4 ++-- include/linux/crypto.h | 2 +- 25 files changed, 55 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 5346b5a80bb6..0d15383d0ff1 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -38,7 +38,7 @@ static int des_setkey(struct crypto_tfm *tfm, const u8 *key, /* check for weak keys */ if (!des_ekey(tmp, key) && - (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } @@ -228,7 +228,7 @@ static int des3_setkey(struct crypto_tfm *tfm, const u8 *key, if (!(crypto_memneq(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) && crypto_memneq(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2], DES_KEY_SIZE)) && - (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c index 56499ea39fd3..4884315daff4 100644 --- a/arch/sparc/crypto/des_glue.c +++ b/arch/sparc/crypto/des_glue.c @@ -53,7 +53,7 @@ static int des_set_key(struct crypto_tfm *tfm, const u8 *key, * weak key detection code. */ ret = des_ekey(tmp, key); - if (unlikely(ret == 0) && (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (unlikely(ret == 0) && (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { *flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } @@ -209,7 +209,7 @@ static int des3_ede_set_key(struct crypto_tfm *tfm, const u8 *key, if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) || !((K[2] ^ K[4]) | (K[3] ^ K[5]))) && - (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { *flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/crypto/des_generic.c b/crypto/des_generic.c index a71720544d11..1e6621665dd9 100644 --- a/crypto/des_generic.c +++ b/crypto/des_generic.c @@ -789,7 +789,7 @@ static int des_setkey(struct crypto_tfm *tfm, const u8 *key, /* Expand to tmp */ ret = des_ekey(tmp, key); - if (unlikely(ret == 0) && (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (unlikely(ret == 0) && (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { *flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } @@ -866,7 +866,7 @@ int __des3_ede_setkey(u32 *expkey, u32 *flags, const u8 *key, if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) || !((K[2] ^ K[4]) | (K[3] ^ K[5]))) && - (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { *flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/crypto/testmgr.c b/crypto/testmgr.c index e4f3f5f688e7..4ac3d22256c3 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -706,7 +706,8 @@ static int __test_aead(struct crypto_aead *tfm, int enc, crypto_aead_clear_flags(tfm, ~0); if (template[i].wk) - crypto_aead_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_aead_set_flags(tfm, + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); if (template[i].klen > MAX_KEYLEN) { pr_err("alg: aead%s: setkey failed on test %d for %s: key size %d > %d\n", @@ -820,7 +821,8 @@ static int __test_aead(struct crypto_aead *tfm, int enc, crypto_aead_clear_flags(tfm, ~0); if (template[i].wk) - crypto_aead_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_aead_set_flags(tfm, + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); if (template[i].klen > MAX_KEYLEN) { pr_err("alg: aead%s: setkey failed on test %d for %s: key size %d > %d\n", d, j, algo, template[i].klen, MAX_KEYLEN); @@ -1078,7 +1080,7 @@ static int test_cipher(struct crypto_cipher *tfm, int enc, crypto_cipher_clear_flags(tfm, ~0); if (template[i].wk) - crypto_cipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_cipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); ret = crypto_cipher_setkey(tfm, template[i].key, template[i].klen); @@ -1194,8 +1196,7 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc, crypto_skcipher_clear_flags(tfm, ~0); if (template[i].wk) - crypto_skcipher_set_flags(tfm, - CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); ret = crypto_skcipher_setkey(tfm, template[i].key, template[i].klen); @@ -1265,8 +1266,7 @@ static int __test_skcipher(struct crypto_skcipher *tfm, int enc, j++; crypto_skcipher_clear_flags(tfm, ~0); if (template[i].wk) - crypto_skcipher_set_flags(tfm, - CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); ret = crypto_skcipher_setkey(tfm, template[i].key, template[i].klen); diff --git a/crypto/testmgr.h b/crypto/testmgr.h index 95297240b0f1..d8f6035c7ff2 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -50,7 +50,7 @@ struct hash_testvec { * @ctext: Pointer to ciphertext * @len: Length of @ptext and @ctext in bytes * @fail: If set to one, the test need to fail - * @wk: Does the test need CRYPTO_TFM_REQ_WEAK_KEY + * @wk: Does the test need CRYPTO_TFM_REQ_FORBID_WEAK_KEYS? * ( e.g. test needs to fail due to a weak key ) * @np: numbers of SG to distribute data in (from 1 to MAX_TAP) * @tap: How to distribute data in @np SGs @@ -91,7 +91,7 @@ struct cipher_testvec { * @anp: Numbers of SG to distribute assoc data in * @fail: setkey() failure expected? * @novrfy: Decryption verification failure expected? - * @wk: Does the test need CRYPTO_TFM_REQ_WEAK_KEY? + * @wk: Does the test need CRYPTO_TFM_REQ_FORBID_WEAK_KEYS? * (e.g. setkey() needs to fail due to a weak key) * @klen: Length of @key in bytes * @plen: Length of @ptext in bytes diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c index 438e1ffb2ec0..65bf1a299562 100644 --- a/drivers/crypto/atmel-tdes.c +++ b/drivers/crypto/atmel-tdes.c @@ -785,7 +785,7 @@ static int atmel_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key, } err = des_ekey(tmp, key); - if (err == 0 && (ctfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (err == 0 && (ctfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { ctfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c index 2099d7bcfd44..28f592f7e1b7 100644 --- a/drivers/crypto/bcm/cipher.c +++ b/drivers/crypto/bcm/cipher.c @@ -1818,7 +1818,7 @@ static int des_setkey(struct crypto_ablkcipher *cipher, const u8 *key, if (keylen == DES_KEY_SIZE) { if (des_ekey(tmp, key) == 0) { if (crypto_ablkcipher_get_flags(cipher) & - CRYPTO_TFM_REQ_WEAK_KEY) { + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) { u32 flags = CRYPTO_TFM_RES_WEAK_KEY; crypto_ablkcipher_set_flags(cipher, flags); @@ -2872,7 +2872,7 @@ static int aead_authenc_setkey(struct crypto_aead *cipher, if (des_ekey(tmp, keys.enckey) == 0) { if (crypto_aead_get_flags(cipher) & - CRYPTO_TFM_REQ_WEAK_KEY) { + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) { crypto_aead_set_flags(cipher, flags); return -EINVAL; } diff --git a/drivers/crypto/ccp/ccp-crypto-des3.c b/drivers/crypto/ccp/ccp-crypto-des3.c index ae87b741f9d5..c2ff551d215b 100644 --- a/drivers/crypto/ccp/ccp-crypto-des3.c +++ b/drivers/crypto/ccp/ccp-crypto-des3.c @@ -57,7 +57,7 @@ static int ccp_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key, if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) || !((K[2] ^ K[4]) | (K[3] ^ K[5]))) && - (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { *flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c index e202d7c7ea00..5e3361a363b5 100644 --- a/drivers/crypto/ccree/cc_cipher.c +++ b/drivers/crypto/ccree/cc_cipher.c @@ -352,7 +352,8 @@ static int cc_cipher_setkey(struct crypto_skcipher *sktfm, const u8 *key, dev_dbg(dev, "weak 3DES key"); return -EINVAL; } else if (!des_ekey(tmp, key) && - (crypto_tfm_get_flags(tfm) & CRYPTO_TFM_REQ_WEAK_KEY)) { + (crypto_tfm_get_flags(tfm) & + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; dev_dbg(dev, "weak DES key"); return -EINVAL; diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c index a5a36fe7bf2c..dad212cabe63 100644 --- a/drivers/crypto/hifn_795x.c +++ b/drivers/crypto/hifn_795x.c @@ -1961,7 +1961,8 @@ static int hifn_setkey(struct crypto_ablkcipher *cipher, const u8 *key, u32 tmp[DES_EXPKEY_WORDS]; int ret = des_ekey(tmp, key); - if (unlikely(ret == 0) && (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (unlikely(ret == 0) && + (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c index d531c14020dc..7ef30a98cb24 100644 --- a/drivers/crypto/inside-secure/safexcel_cipher.c +++ b/drivers/crypto/inside-secure/safexcel_cipher.c @@ -940,7 +940,7 @@ static int safexcel_des_setkey(struct crypto_skcipher *ctfm, const u8 *key, } ret = des_ekey(tmp, key); - if (!ret && (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (!ret && (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 19fba998b86b..95c1af227bd5 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -847,7 +847,7 @@ static int ablk_setkey(struct crypto_ablkcipher *tfm, const u8 *key, goto out; if (*flags & CRYPTO_TFM_RES_WEAK_KEY) { - if (*flags & CRYPTO_TFM_REQ_WEAK_KEY) { + if (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) { ret = -EINVAL; } else { *flags &= ~CRYPTO_TFM_RES_WEAK_KEY; @@ -1125,7 +1125,7 @@ static int aead_setup(struct crypto_aead *tfm, unsigned int authsize) goto out; if (*flags & CRYPTO_TFM_RES_WEAK_KEY) { - if (*flags & CRYPTO_TFM_REQ_WEAK_KEY) { + if (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) { ret = -EINVAL; goto out; } else { diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c index 0ae84ec9e21c..066830dcc53e 100644 --- a/drivers/crypto/marvell/cipher.c +++ b/drivers/crypto/marvell/cipher.c @@ -286,7 +286,7 @@ static int mv_cesa_des_setkey(struct crypto_skcipher *cipher, const u8 *key, } ret = des_ekey(tmp, key); - if (!ret && (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (!ret && (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c index 55f34cfc43ff..9450c41211b2 100644 --- a/drivers/crypto/n2_core.c +++ b/drivers/crypto/n2_core.c @@ -772,7 +772,7 @@ static int n2_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key, } err = des_ekey(tmp, key); - if (err == 0 && (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (err == 0 && (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c index 6369019219d4..1ba2633e90d6 100644 --- a/drivers/crypto/omap-des.c +++ b/drivers/crypto/omap-des.c @@ -662,7 +662,7 @@ static int omap_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key, pr_debug("enter, keylen: %d\n", keylen); /* Do we need to test against weak key? */ - if (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY) { + if (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) { u32 tmp[DES_EXPKEY_WORDS]; int ret = des_ekey(tmp, key); diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c index 17068b55fea5..1b3acdeffede 100644 --- a/drivers/crypto/picoxcell_crypto.c +++ b/drivers/crypto/picoxcell_crypto.c @@ -759,7 +759,8 @@ static int spacc_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key, } if (unlikely(!des_ekey(tmp, key)) && - (crypto_ablkcipher_get_flags(cipher) & CRYPTO_TFM_REQ_WEAK_KEY)) { + (crypto_ablkcipher_get_flags(cipher) & + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/drivers/crypto/qce/ablkcipher.c b/drivers/crypto/qce/ablkcipher.c index 25c13e26d012..154b6baa124e 100644 --- a/drivers/crypto/qce/ablkcipher.c +++ b/drivers/crypto/qce/ablkcipher.c @@ -180,8 +180,8 @@ static int qce_ablkcipher_setkey(struct crypto_ablkcipher *ablk, const u8 *key, u32 tmp[DES_EXPKEY_WORDS]; ret = des_ekey(tmp, key); - if (!ret && crypto_ablkcipher_get_flags(ablk) & - CRYPTO_TFM_REQ_WEAK_KEY) + if (!ret && (crypto_ablkcipher_get_flags(ablk) & + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) goto weakkey; } diff --git a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c index 639c15c5364b..87dd571466c1 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c @@ -60,7 +60,7 @@ static int rk_tdes_setkey(struct crypto_ablkcipher *cipher, if (keylen == DES_KEY_SIZE) { if (!des_ekey(tmp, key) && - (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY; return -EINVAL; } diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c index 5cf64746731a..54fd714d53ca 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c @@ -517,7 +517,7 @@ int sun4i_ss_des_setkey(struct crypto_skcipher *tfm, const u8 *key, flags = crypto_skcipher_get_flags(tfm); ret = des_ekey(tmp, key); - if (unlikely(!ret) && (flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (unlikely(!ret) && (flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_WEAK_KEY); dev_dbg(ss->dev, "Weak key %u\n", keylen); return -EINVAL; diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index f8e2c5c3f4eb..de78b54bcfb1 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -1535,7 +1535,7 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher, } if (unlikely(crypto_ablkcipher_get_flags(cipher) & - CRYPTO_TFM_REQ_WEAK_KEY) && + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) && !des_ekey(tmp, key)) { crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_WEAK_KEY); return -EINVAL; diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index db94f89d8d11..3235611928f2 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -1000,10 +1000,11 @@ static int des_ablkcipher_setkey(struct crypto_ablkcipher *cipher, } ret = des_ekey(tmp, key); - if (unlikely(ret == 0) && (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (unlikely(ret == 0) && + (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { *flags |= CRYPTO_TFM_RES_WEAK_KEY; - pr_debug(DEV_DBG_NAME " [%s]: CRYPTO_TFM_REQ_WEAK_KEY", - __func__); + pr_debug(DEV_DBG_NAME " [%s]: CRYPTO_TFM_RES_WEAK_KEY", + __func__); return -EINVAL; } @@ -1034,18 +1035,19 @@ static int des3_ablkcipher_setkey(struct crypto_ablkcipher *cipher, /* Checking key interdependency for weak key detection. */ if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) || !((K[2] ^ K[4]) | (K[3] ^ K[5]))) && - (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { *flags |= CRYPTO_TFM_RES_WEAK_KEY; - pr_debug(DEV_DBG_NAME " [%s]: CRYPTO_TFM_REQ_WEAK_KEY", - __func__); + pr_debug(DEV_DBG_NAME " [%s]: CRYPTO_TFM_RES_WEAK_KEY", + __func__); return -EINVAL; } for (i = 0; i < 3; i++) { ret = des_ekey(tmp, key + i*DES_KEY_SIZE); - if (unlikely(ret == 0) && (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) { + if (unlikely(ret == 0) && + (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) { *flags |= CRYPTO_TFM_RES_WEAK_KEY; - pr_debug(DEV_DBG_NAME " [%s]: " - "CRYPTO_TFM_REQ_WEAK_KEY", __func__); + pr_debug(DEV_DBG_NAME " [%s]: CRYPTO_TFM_RES_WEAK_KEY", + __func__); return -EINVAL; } } diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 1e11a683f63d..322ce9686bdb 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -47,7 +47,7 @@ static int derive_key_aes(const u8 *master_key, tfm = NULL; goto out; } - crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); req = skcipher_request_alloc(tfm, GFP_NOFS); if (!req) { res = -ENOMEM; @@ -257,7 +257,7 @@ allocate_skcipher_for_mode(struct fscrypt_mode *mode, const u8 *raw_key, mode->friendly_name, crypto_skcipher_alg(tfm)->base.cra_driver_name); } - crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); err = crypto_skcipher_setkey(tfm, raw_key, mode->keysize); if (err) goto err_free_tfm; diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 4dd842f72846..f664da55234e 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -610,7 +610,8 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat) full_alg_name); goto out_free; } - crypto_skcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(crypt_stat->tfm, + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); rc = 0; out_free: kfree(full_alg_name); @@ -1590,7 +1591,7 @@ ecryptfs_process_key_cipher(struct crypto_skcipher **key_tfm, "[%s]; rc = [%d]\n", full_alg_name, rc); goto out; } - crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); if (*key_size == 0) *key_size = crypto_skcipher_default_keysize(*key_tfm); get_random_bytes(dummy_key, *key_size); diff --git a/include/crypto/xts.h b/include/crypto/xts.h index 34d94c95445a..75fd96ff976b 100644 --- a/include/crypto/xts.h +++ b/include/crypto/xts.h @@ -47,8 +47,8 @@ static inline int xts_verify_key(struct crypto_skcipher *tfm, } /* ensure that the AES and tweak key are not identical */ - if ((fips_enabled || crypto_skcipher_get_flags(tfm) & - CRYPTO_TFM_REQ_WEAK_KEY) && + if ((fips_enabled || (crypto_skcipher_get_flags(tfm) & + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) && !crypto_memneq(key, key + (keylen / 2), keylen / 2)) { crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_WEAK_KEY); return -EINVAL; diff --git a/include/linux/crypto.h b/include/linux/crypto.h index c3c98a62e503..f2565a103158 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -118,7 +118,7 @@ #define CRYPTO_TFM_REQ_MASK 0x000fff00 #define CRYPTO_TFM_RES_MASK 0xfff00000 -#define CRYPTO_TFM_REQ_WEAK_KEY 0x00000100 +#define CRYPTO_TFM_REQ_FORBID_WEAK_KEYS 0x00000100 #define CRYPTO_TFM_REQ_MAY_SLEEP 0x00000200 #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 #define CRYPTO_TFM_RES_WEAK_KEY 0x00100000 -- cgit v1.2.3 From 390298e86f8a2e8b428ffb259a323667229ff822 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 22 Jan 2019 15:20:16 +0100 Subject: mac80211: Expose ieee80211_schedule_txq() function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since we reworked ieee80211_return_txq() so it assumes that the caller takes care of logging, we need another function that can be called without holding any locks. Introduce ieee80211_schedule_txq() which serves this purpose. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Johannes Berg --- include/net/mac80211.h | 13 +++++++++++++ net/mac80211/driver-ops.h | 4 +--- net/mac80211/tx.c | 13 +++++++++++++ 3 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index a285c2bfd14e..294a8a36012a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6209,6 +6209,19 @@ void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) __releases(txq_lock); +/** + * ieee80211_schedule_txq - schedule a TXQ for transmission + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @txq: pointer obtained from station or virtual interface + * + * Schedules a TXQ for transmission if it is not already scheduled. Takes a + * lock, which means it must *not* be called between + * ieee80211_txq_schedule_start() and ieee80211_txq_schedule_end() + */ +void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) + __acquires(txq_lock) __releases(txq_lock); + /** * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit * diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 1aab1734b26f..ba3c07b10cd0 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1176,9 +1176,7 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, static inline void schedule_and_wake_txq(struct ieee80211_local *local, struct txq_info *txqi) { - spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]); - ieee80211_return_txq(&local->hw, &txqi->txq); - spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]); + ieee80211_schedule_txq(&local->hw, &txqi->txq); drv_wake_tx_queue(local, txqi); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f46d8d822f86..037f95e39a45 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3703,6 +3703,19 @@ void ieee80211_return_txq(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_return_txq); +void ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) + __acquires(txq_lock) __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + + spin_lock_bh(&local->active_txq_lock[txq->ac]); + ieee80211_return_txq(hw, txq); + spin_unlock_bh(&local->active_txq_lock[txq->ac]); +} +EXPORT_SYMBOL(ieee80211_schedule_txq); + bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq) { -- cgit v1.2.3 From ab4dfa20534e32e48de6b761b42d943518fb26f7 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Wed, 19 Dec 2018 22:52:25 +0530 Subject: cfg80211: Allow drivers to advertise supported AKM suites There was no such capability advertisement from the driver and thus the current user space has to assume the driver to support all the AKMs. While that may be the case with some drivers (e.g., mac80211-based ones), there are cfg80211-based drivers that implement SME and have constraints on which AKMs can be supported (e.g., such drivers may need an update to support SAE AKM using NL80211_CMD_EXTERNAL_AUTH). Allow such drivers to advertise the exact set of supported AKMs so that user space tools can determine what network profile options should be allowed to be configured. Signed-off-by: Veerendranath Jakkam [pmsr data might be big, start a new netlink message section] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 5 +++++ include/uapi/linux/nl80211.h | 6 ++++++ net/wireless/nl80211.c | 9 +++++++++ 3 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9c1d7979c200..b61ac6e9de08 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4128,6 +4128,8 @@ struct cfg80211_pmsr_capabilities { * @signal_type: signal type reported in &struct cfg80211_bss. * @cipher_suites: supported cipher suites * @n_cipher_suites: number of supported cipher suites + * @akm_suites: supported AKM suites + * @n_akm_suites: number of supported AKM suites * @retry_short: Retry limit for short frames (dot11ShortRetryLimit) * @retry_long: Retry limit for long frames (dot11LongRetryLimit) * @frag_threshold: Fragmentation threshold (dot11FragmentationThreshold); @@ -4326,6 +4328,9 @@ struct wiphy { int n_cipher_suites; const u32 *cipher_suites; + int n_akm_suites; + const u32 *akm_suites; + u8 retry_short; u8 retry_long; u32 frag_threshold; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 426db4d8f71c..5f9d5cd458a1 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1565,6 +1565,12 @@ enum nl80211_commands { * (a u32 with flags from &enum nl80211_wpa_versions). * @NL80211_ATTR_AKM_SUITES: Used with CONNECT, ASSOCIATE, and NEW_BEACON to * indicate which key management algorithm(s) to use (an array of u32). + * This attribute is also sent in response to @NL80211_CMD_GET_WIPHY, + * indicating the supported AKM suites, intended for specific drivers which + * implement SME and have constraints on which AKMs are supported and also + * the cases where an AKM support is offloaded to the driver/firmware. + * If there is no such notification from the driver, user space should + * assume the driver supports all the AKM suites. * * @NL80211_ATTR_REQ_IE: (Re)association request information elements as * sent out by the card, for ROAM and successful CONNECT events. diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e5f9c9ceb6c9..eb4437fa0539 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2279,6 +2279,15 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (nl80211_send_pmsr_capa(rdev, msg)) goto nla_put_failure; + state->split_start++; + break; + case 15: + if (rdev->wiphy.akm_suites && + nla_put(msg, NL80211_ATTR_AKM_SUITES, + sizeof(u32) * rdev->wiphy.n_akm_suites, + rdev->wiphy.akm_suites)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; -- cgit v1.2.3 From d32dde2c5a110f2d69add70d7a9f1c20d82d0ef1 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 25 Jan 2019 11:22:51 +0100 Subject: soc/tegra: pmc: Make tegra_powergate_is_powered() a local function Now there are no more external users of tegra_powergate_is_powered(), make this a local function. Signed-off-by: Jon Hunter Signed-off-by: Thierry Reding --- drivers/soc/tegra/pmc.c | 2 +- include/soc/tegra/pmc.h | 6 ------ 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c index 50ebf98e04ee..986f2171ff38 100644 --- a/drivers/soc/tegra/pmc.c +++ b/drivers/soc/tegra/pmc.c @@ -637,7 +637,7 @@ EXPORT_SYMBOL(tegra_powergate_power_off); * tegra_powergate_is_powered() - check if partition is powered * @id: partition ID */ -int tegra_powergate_is_powered(unsigned int id) +static int tegra_powergate_is_powered(unsigned int id) { if (!tegra_powergate_is_valid(id)) return -EINVAL; diff --git a/include/soc/tegra/pmc.h b/include/soc/tegra/pmc.h index a9db1b501de1..b32ee5d82dd4 100644 --- a/include/soc/tegra/pmc.h +++ b/include/soc/tegra/pmc.h @@ -161,7 +161,6 @@ enum tegra_io_pad { #define TEGRA_IO_RAIL_LVDS TEGRA_IO_PAD_LVDS #ifdef CONFIG_SOC_TEGRA_PMC -int tegra_powergate_is_powered(unsigned int id); int tegra_powergate_power_on(unsigned int id); int tegra_powergate_power_off(unsigned int id); int tegra_powergate_remove_clamping(unsigned int id); @@ -182,11 +181,6 @@ void tegra_pmc_set_suspend_mode(enum tegra_suspend_mode mode); void tegra_pmc_enter_suspend_mode(enum tegra_suspend_mode mode); #else -static inline int tegra_powergate_is_powered(unsigned int id) -{ - return -ENOSYS; -} - static inline int tegra_powergate_power_on(unsigned int id) { return -ENOSYS; -- cgit v1.2.3 From cdfa358b248efd36c6a9cb4d4d0a3ba7509f8387 Mon Sep 17 00:00:00 2001 From: Timo Alho Date: Thu, 24 Jan 2019 19:03:53 +0200 Subject: firmware: tegra: Refactor BPMP driver Split BPMP driver into common and chip specific parts to facilitate adding support for previous and future Tegra chips that are using BPMP as co-processor. Signed-off-by: Timo Alho Acked-by: Jon Hunter Signed-off-by: Thierry Reding --- drivers/firmware/tegra/Makefile | 1 + drivers/firmware/tegra/bpmp-private.h | 28 +++ drivers/firmware/tegra/bpmp-tegra186.c | 310 +++++++++++++++++++++++++++++++++ drivers/firmware/tegra/bpmp.c | 257 ++++++--------------------- include/soc/tegra/bpmp.h | 12 +- 5 files changed, 400 insertions(+), 208 deletions(-) create mode 100644 drivers/firmware/tegra/bpmp-private.h create mode 100644 drivers/firmware/tegra/bpmp-tegra186.c (limited to 'include') diff --git a/drivers/firmware/tegra/Makefile b/drivers/firmware/tegra/Makefile index 1b826dcca719..559355674bca 100644 --- a/drivers/firmware/tegra/Makefile +++ b/drivers/firmware/tegra/Makefile @@ -1,4 +1,5 @@ tegra-bpmp-y = bpmp.o +tegra-bpmp-$(CONFIG_ARCH_TEGRA_186_SOC) += bpmp-tegra186.o tegra-bpmp-$(CONFIG_DEBUG_FS) += bpmp-debugfs.o obj-$(CONFIG_TEGRA_BPMP) += tegra-bpmp.o obj-$(CONFIG_TEGRA_IVC) += ivc.o diff --git a/drivers/firmware/tegra/bpmp-private.h b/drivers/firmware/tegra/bpmp-private.h new file mode 100644 index 000000000000..6fb10f1cfb8f --- /dev/null +++ b/drivers/firmware/tegra/bpmp-private.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018, NVIDIA CORPORATION. + */ + +#ifndef __FIRMWARE_TEGRA_BPMP_PRIVATE_H +#define __FIRMWARE_TEGRA_BPMP_PRIVATE_H + +#include + +struct tegra_bpmp_ops { + int (*init)(struct tegra_bpmp *bpmp); + void (*deinit)(struct tegra_bpmp *bpmp); + bool (*is_response_ready)(struct tegra_bpmp_channel *channel); + bool (*is_request_ready)(struct tegra_bpmp_channel *channel); + int (*ack_response)(struct tegra_bpmp_channel *channel); + int (*ack_request)(struct tegra_bpmp_channel *channel); + bool (*is_response_channel_free)(struct tegra_bpmp_channel *channel); + bool (*is_request_channel_free)(struct tegra_bpmp_channel *channel); + int (*post_response)(struct tegra_bpmp_channel *channel); + int (*post_request)(struct tegra_bpmp_channel *channel); + int (*ring_doorbell)(struct tegra_bpmp *bpmp); + int (*resume)(struct tegra_bpmp *bpmp); +}; + +extern const struct tegra_bpmp_ops tegra186_bpmp_ops; + +#endif diff --git a/drivers/firmware/tegra/bpmp-tegra186.c b/drivers/firmware/tegra/bpmp-tegra186.c new file mode 100644 index 000000000000..89bb32b97345 --- /dev/null +++ b/drivers/firmware/tegra/bpmp-tegra186.c @@ -0,0 +1,310 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018, NVIDIA CORPORATION. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "bpmp-private.h" + +struct tegra186_bpmp { + struct tegra_bpmp *parent; + + struct { + struct gen_pool *pool; + dma_addr_t phys; + void *virt; + } tx, rx; + + struct { + struct mbox_client client; + struct mbox_chan *channel; + } mbox; +}; + +static inline struct tegra_bpmp * +mbox_client_to_bpmp(struct mbox_client *client) +{ + struct tegra186_bpmp *priv; + + priv = container_of(client, struct tegra186_bpmp, mbox.client); + + return priv->parent; +} + +static bool tegra186_bpmp_is_message_ready(struct tegra_bpmp_channel *channel) +{ + void *frame; + + frame = tegra_ivc_read_get_next_frame(channel->ivc); + if (IS_ERR(frame)) { + channel->ib = NULL; + return false; + } + + channel->ib = frame; + + return true; +} + +static bool tegra186_bpmp_is_channel_free(struct tegra_bpmp_channel *channel) +{ + void *frame; + + frame = tegra_ivc_write_get_next_frame(channel->ivc); + if (IS_ERR(frame)) { + channel->ob = NULL; + return false; + } + + channel->ob = frame; + + return true; +} + +static int tegra186_bpmp_ack_message(struct tegra_bpmp_channel *channel) +{ + return tegra_ivc_read_advance(channel->ivc); +} + +static int tegra186_bpmp_post_message(struct tegra_bpmp_channel *channel) +{ + return tegra_ivc_write_advance(channel->ivc); +} + +static int tegra186_bpmp_ring_doorbell(struct tegra_bpmp *bpmp) +{ + struct tegra186_bpmp *priv = bpmp->priv; + int err; + + err = mbox_send_message(priv->mbox.channel, NULL); + if (err < 0) + return err; + + mbox_client_txdone(priv->mbox.channel, 0); + + return 0; +} + +static void tegra186_bpmp_ivc_notify(struct tegra_ivc *ivc, void *data) +{ + struct tegra_bpmp *bpmp = data; + struct tegra186_bpmp *priv = bpmp->priv; + + if (WARN_ON(priv->mbox.channel == NULL)) + return; + + tegra186_bpmp_ring_doorbell(bpmp); +} + +static int tegra186_bpmp_channel_init(struct tegra_bpmp_channel *channel, + struct tegra_bpmp *bpmp, + unsigned int index) +{ + struct tegra186_bpmp *priv = bpmp->priv; + size_t message_size, queue_size; + unsigned int offset; + int err; + + channel->ivc = devm_kzalloc(bpmp->dev, sizeof(*channel->ivc), + GFP_KERNEL); + if (!channel->ivc) + return -ENOMEM; + + message_size = tegra_ivc_align(MSG_MIN_SZ); + queue_size = tegra_ivc_total_queue_size(message_size); + offset = queue_size * index; + + err = tegra_ivc_init(channel->ivc, NULL, + priv->rx.virt + offset, priv->rx.phys + offset, + priv->tx.virt + offset, priv->tx.phys + offset, + 1, message_size, tegra186_bpmp_ivc_notify, + bpmp); + if (err < 0) { + dev_err(bpmp->dev, "failed to setup IVC for channel %u: %d\n", + index, err); + return err; + } + + init_completion(&channel->completion); + channel->bpmp = bpmp; + + return 0; +} + +static void tegra186_bpmp_channel_reset(struct tegra_bpmp_channel *channel) +{ + /* reset the channel state */ + tegra_ivc_reset(channel->ivc); + + /* sync the channel state with BPMP */ + while (tegra_ivc_notified(channel->ivc)) + ; +} + +static void tegra186_bpmp_channel_cleanup(struct tegra_bpmp_channel *channel) +{ + tegra_ivc_cleanup(channel->ivc); +} + +static void mbox_handle_rx(struct mbox_client *client, void *data) +{ + struct tegra_bpmp *bpmp = mbox_client_to_bpmp(client); + + tegra_bpmp_handle_rx(bpmp); +} + +static int tegra186_bpmp_init(struct tegra_bpmp *bpmp) +{ + struct tegra186_bpmp *priv; + unsigned int i; + int err; + + priv = devm_kzalloc(bpmp->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + bpmp->priv = priv; + priv->parent = bpmp; + + priv->tx.pool = of_gen_pool_get(bpmp->dev->of_node, "shmem", 0); + if (!priv->tx.pool) { + dev_err(bpmp->dev, "TX shmem pool not found\n"); + return -ENOMEM; + } + + priv->tx.virt = gen_pool_dma_alloc(priv->tx.pool, 4096, &priv->tx.phys); + if (!priv->tx.virt) { + dev_err(bpmp->dev, "failed to allocate from TX pool\n"); + return -ENOMEM; + } + + priv->rx.pool = of_gen_pool_get(bpmp->dev->of_node, "shmem", 1); + if (!priv->rx.pool) { + dev_err(bpmp->dev, "RX shmem pool not found\n"); + err = -ENOMEM; + goto free_tx; + } + + priv->rx.virt = gen_pool_dma_alloc(priv->rx.pool, 4096, &priv->rx.phys); + if (!priv->rx.virt) { + dev_err(bpmp->dev, "failed to allocate from RX pool\n"); + err = -ENOMEM; + goto free_tx; + } + + err = tegra186_bpmp_channel_init(bpmp->tx_channel, bpmp, + bpmp->soc->channels.cpu_tx.offset); + if (err < 0) + goto free_rx; + + err = tegra186_bpmp_channel_init(bpmp->rx_channel, bpmp, + bpmp->soc->channels.cpu_rx.offset); + if (err < 0) + goto cleanup_tx_channel; + + for (i = 0; i < bpmp->threaded.count; i++) { + unsigned int index = bpmp->soc->channels.thread.offset + i; + + err = tegra186_bpmp_channel_init(&bpmp->threaded_channels[i], + bpmp, index); + if (err < 0) + goto cleanup_channels; + } + + /* mbox registration */ + priv->mbox.client.dev = bpmp->dev; + priv->mbox.client.rx_callback = mbox_handle_rx; + priv->mbox.client.tx_block = false; + priv->mbox.client.knows_txdone = false; + + priv->mbox.channel = mbox_request_channel(&priv->mbox.client, 0); + if (IS_ERR(priv->mbox.channel)) { + err = PTR_ERR(priv->mbox.channel); + dev_err(bpmp->dev, "failed to get HSP mailbox: %d\n", err); + goto cleanup_channels; + } + + tegra186_bpmp_channel_reset(bpmp->tx_channel); + tegra186_bpmp_channel_reset(bpmp->rx_channel); + + for (i = 0; i < bpmp->threaded.count; i++) + tegra186_bpmp_channel_reset(&bpmp->threaded_channels[i]); + + return 0; + +cleanup_channels: + for (i = 0; i < bpmp->threaded.count; i++) { + if (!bpmp->threaded_channels[i].bpmp) + continue; + + tegra186_bpmp_channel_cleanup(&bpmp->threaded_channels[i]); + } + + tegra186_bpmp_channel_cleanup(bpmp->rx_channel); +cleanup_tx_channel: + tegra186_bpmp_channel_cleanup(bpmp->tx_channel); +free_rx: + gen_pool_free(priv->rx.pool, (unsigned long)priv->rx.virt, 4096); +free_tx: + gen_pool_free(priv->tx.pool, (unsigned long)priv->tx.virt, 4096); + + return err; +} + +static void tegra186_bpmp_deinit(struct tegra_bpmp *bpmp) +{ + struct tegra186_bpmp *priv = bpmp->priv; + unsigned int i; + + mbox_free_channel(priv->mbox.channel); + + for (i = 0; i < bpmp->threaded.count; i++) + tegra186_bpmp_channel_cleanup(&bpmp->threaded_channels[i]); + + tegra186_bpmp_channel_cleanup(bpmp->rx_channel); + tegra186_bpmp_channel_cleanup(bpmp->tx_channel); + + gen_pool_free(priv->rx.pool, (unsigned long)priv->rx.virt, 4096); + gen_pool_free(priv->tx.pool, (unsigned long)priv->tx.virt, 4096); +} + +static int tegra186_bpmp_resume(struct tegra_bpmp *bpmp) +{ + unsigned int i; + + /* reset message channels */ + tegra186_bpmp_channel_reset(bpmp->tx_channel); + tegra186_bpmp_channel_reset(bpmp->rx_channel); + + for (i = 0; i < bpmp->threaded.count; i++) + tegra186_bpmp_channel_reset(&bpmp->threaded_channels[i]); + + return 0; +} + +const struct tegra_bpmp_ops tegra186_bpmp_ops = { + .init = tegra186_bpmp_init, + .deinit = tegra186_bpmp_deinit, + .is_response_ready = tegra186_bpmp_is_message_ready, + .is_request_ready = tegra186_bpmp_is_message_ready, + .ack_response = tegra186_bpmp_ack_message, + .ack_request = tegra186_bpmp_ack_message, + .is_response_channel_free = tegra186_bpmp_is_channel_free, + .is_request_channel_free = tegra186_bpmp_is_channel_free, + .post_response = tegra186_bpmp_post_message, + .post_request = tegra186_bpmp_post_message, + .ring_doorbell = tegra186_bpmp_ring_doorbell, + .resume = tegra186_bpmp_resume, +}; diff --git a/drivers/firmware/tegra/bpmp.c b/drivers/firmware/tegra/bpmp.c index e7fd68ebedd0..2b498deacdbc 100644 --- a/drivers/firmware/tegra/bpmp.c +++ b/drivers/firmware/tegra/bpmp.c @@ -26,6 +26,8 @@ #include #include +#include "bpmp-private.h" + #define MSG_ACK BIT(0) #define MSG_RING BIT(1) #define TAG_SZ 32 @@ -36,6 +38,14 @@ mbox_client_to_bpmp(struct mbox_client *client) return container_of(client, struct tegra_bpmp, mbox.client); } +static inline const struct tegra_bpmp_ops * +channel_to_ops(struct tegra_bpmp_channel *channel) +{ + struct tegra_bpmp *bpmp = channel->bpmp; + + return bpmp->soc->ops; +} + struct tegra_bpmp *tegra_bpmp_get(struct device *dev) { struct platform_device *pdev; @@ -98,22 +108,16 @@ static bool tegra_bpmp_message_valid(const struct tegra_bpmp_message *msg) static bool tegra_bpmp_is_response_ready(struct tegra_bpmp_channel *channel) { - void *frame; + const struct tegra_bpmp_ops *ops = channel_to_ops(channel); - frame = tegra_ivc_read_get_next_frame(channel->ivc); - if (IS_ERR(frame)) { - channel->ib = NULL; - return false; - } - - channel->ib = frame; - - return true; + return ops->is_response_ready(channel); } static bool tegra_bpmp_is_request_ready(struct tegra_bpmp_channel *channel) { - return tegra_bpmp_is_response_ready(channel); + const struct tegra_bpmp_ops *ops = channel_to_ops(channel); + + return ops->is_request_ready(channel); } static int tegra_bpmp_wait_response(struct tegra_bpmp_channel *channel) @@ -133,34 +137,32 @@ static int tegra_bpmp_wait_response(struct tegra_bpmp_channel *channel) static int tegra_bpmp_ack_response(struct tegra_bpmp_channel *channel) { - return tegra_ivc_read_advance(channel->ivc); + const struct tegra_bpmp_ops *ops = channel_to_ops(channel); + + return ops->ack_response(channel); } static int tegra_bpmp_ack_request(struct tegra_bpmp_channel *channel) { - return tegra_ivc_read_advance(channel->ivc); + const struct tegra_bpmp_ops *ops = channel_to_ops(channel); + + return ops->ack_request(channel); } static bool tegra_bpmp_is_request_channel_free(struct tegra_bpmp_channel *channel) { - void *frame; - - frame = tegra_ivc_write_get_next_frame(channel->ivc); - if (IS_ERR(frame)) { - channel->ob = NULL; - return false; - } - - channel->ob = frame; + const struct tegra_bpmp_ops *ops = channel_to_ops(channel); - return true; + return ops->is_request_channel_free(channel); } static bool tegra_bpmp_is_response_channel_free(struct tegra_bpmp_channel *channel) { - return tegra_bpmp_is_request_channel_free(channel); + const struct tegra_bpmp_ops *ops = channel_to_ops(channel); + + return ops->is_response_channel_free(channel); } static int @@ -183,28 +185,21 @@ tegra_bpmp_wait_request_channel_free(struct tegra_bpmp_channel *channel) static int tegra_bpmp_post_request(struct tegra_bpmp_channel *channel) { - return tegra_ivc_write_advance(channel->ivc); + const struct tegra_bpmp_ops *ops = channel_to_ops(channel); + + return ops->post_request(channel); } static int tegra_bpmp_post_response(struct tegra_bpmp_channel *channel) { - return tegra_ivc_write_advance(channel->ivc); + const struct tegra_bpmp_ops *ops = channel_to_ops(channel); + + return ops->post_response(channel); } static int tegra_bpmp_ring_doorbell(struct tegra_bpmp *bpmp) { - int err; - - if (WARN_ON(bpmp->mbox.channel == NULL)) - return -EINVAL; - - err = mbox_send_message(bpmp->mbox.channel, NULL); - if (err < 0) - return err; - - mbox_client_txdone(bpmp->mbox.channel, 0); - - return 0; + return bpmp->soc->ops->ring_doorbell(bpmp); } static ssize_t __tegra_bpmp_channel_read(struct tegra_bpmp_channel *channel, @@ -668,9 +663,8 @@ static void tegra_bpmp_channel_signal(struct tegra_bpmp_channel *channel) complete(&channel->completion); } -static void tegra_bpmp_handle_rx(struct mbox_client *client, void *data) +void tegra_bpmp_handle_rx(struct tegra_bpmp *bpmp) { - struct tegra_bpmp *bpmp = mbox_client_to_bpmp(client); struct tegra_bpmp_channel *channel; unsigned int i, count; unsigned long *busy; @@ -698,66 +692,9 @@ static void tegra_bpmp_handle_rx(struct mbox_client *client, void *data) spin_unlock(&bpmp->lock); } -static void tegra_bpmp_ivc_notify(struct tegra_ivc *ivc, void *data) -{ - struct tegra_bpmp *bpmp = data; - - WARN_ON(tegra_bpmp_ring_doorbell(bpmp)); -} - -static int tegra_bpmp_channel_init(struct tegra_bpmp_channel *channel, - struct tegra_bpmp *bpmp, - unsigned int index) -{ - size_t message_size, queue_size; - unsigned int offset; - int err; - - channel->ivc = devm_kzalloc(bpmp->dev, sizeof(*channel->ivc), - GFP_KERNEL); - if (!channel->ivc) - return -ENOMEM; - - message_size = tegra_ivc_align(MSG_MIN_SZ); - queue_size = tegra_ivc_total_queue_size(message_size); - offset = queue_size * index; - - err = tegra_ivc_init(channel->ivc, NULL, - bpmp->rx.virt + offset, bpmp->rx.phys + offset, - bpmp->tx.virt + offset, bpmp->tx.phys + offset, - 1, message_size, tegra_bpmp_ivc_notify, - bpmp); - if (err < 0) { - dev_err(bpmp->dev, "failed to setup IVC for channel %u: %d\n", - index, err); - return err; - } - - init_completion(&channel->completion); - channel->bpmp = bpmp; - - return 0; -} - -static void tegra_bpmp_channel_reset(struct tegra_bpmp_channel *channel) -{ - /* reset the channel state */ - tegra_ivc_reset(channel->ivc); - - /* sync the channel state with BPMP */ - while (tegra_ivc_notified(channel->ivc)) - ; -} - -static void tegra_bpmp_channel_cleanup(struct tegra_bpmp_channel *channel) -{ - tegra_ivc_cleanup(channel->ivc); -} - static int tegra_bpmp_probe(struct platform_device *pdev) { struct tegra_bpmp *bpmp; - unsigned int i; char tag[TAG_SZ]; size_t size; int err; @@ -769,32 +706,6 @@ static int tegra_bpmp_probe(struct platform_device *pdev) bpmp->soc = of_device_get_match_data(&pdev->dev); bpmp->dev = &pdev->dev; - bpmp->tx.pool = of_gen_pool_get(pdev->dev.of_node, "shmem", 0); - if (!bpmp->tx.pool) { - dev_err(&pdev->dev, "TX shmem pool not found\n"); - return -ENOMEM; - } - - bpmp->tx.virt = gen_pool_dma_alloc(bpmp->tx.pool, 4096, &bpmp->tx.phys); - if (!bpmp->tx.virt) { - dev_err(&pdev->dev, "failed to allocate from TX pool\n"); - return -ENOMEM; - } - - bpmp->rx.pool = of_gen_pool_get(pdev->dev.of_node, "shmem", 1); - if (!bpmp->rx.pool) { - dev_err(&pdev->dev, "RX shmem pool not found\n"); - err = -ENOMEM; - goto free_tx; - } - - bpmp->rx.virt = gen_pool_dma_alloc(bpmp->rx.pool, 4096, &bpmp->rx.phys); - if (!bpmp->rx.virt) { - dev_err(&pdev->dev, "failed to allocate from RX pool\n"); - err = -ENOMEM; - goto free_tx; - } - INIT_LIST_HEAD(&bpmp->mrqs); spin_lock_init(&bpmp->lock); @@ -804,81 +715,38 @@ static int tegra_bpmp_probe(struct platform_device *pdev) size = BITS_TO_LONGS(bpmp->threaded.count) * sizeof(long); bpmp->threaded.allocated = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); - if (!bpmp->threaded.allocated) { - err = -ENOMEM; - goto free_rx; - } + if (!bpmp->threaded.allocated) + return -ENOMEM; bpmp->threaded.busy = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); - if (!bpmp->threaded.busy) { - err = -ENOMEM; - goto free_rx; - } + if (!bpmp->threaded.busy) + return -ENOMEM; spin_lock_init(&bpmp->atomic_tx_lock); bpmp->tx_channel = devm_kzalloc(&pdev->dev, sizeof(*bpmp->tx_channel), GFP_KERNEL); - if (!bpmp->tx_channel) { - err = -ENOMEM; - goto free_rx; - } + if (!bpmp->tx_channel) + return -ENOMEM; bpmp->rx_channel = devm_kzalloc(&pdev->dev, sizeof(*bpmp->rx_channel), GFP_KERNEL); - if (!bpmp->rx_channel) { - err = -ENOMEM; - goto free_rx; - } + if (!bpmp->rx_channel) + return -ENOMEM; bpmp->threaded_channels = devm_kcalloc(&pdev->dev, bpmp->threaded.count, sizeof(*bpmp->threaded_channels), GFP_KERNEL); - if (!bpmp->threaded_channels) { - err = -ENOMEM; - goto free_rx; - } - - err = tegra_bpmp_channel_init(bpmp->tx_channel, bpmp, - bpmp->soc->channels.cpu_tx.offset); - if (err < 0) - goto free_rx; + if (!bpmp->threaded_channels) + return -ENOMEM; - err = tegra_bpmp_channel_init(bpmp->rx_channel, bpmp, - bpmp->soc->channels.cpu_rx.offset); + err = bpmp->soc->ops->init(bpmp); if (err < 0) - goto cleanup_tx_channel; - - for (i = 0; i < bpmp->threaded.count; i++) { - err = tegra_bpmp_channel_init( - &bpmp->threaded_channels[i], bpmp, - bpmp->soc->channels.thread.offset + i); - if (err < 0) - goto cleanup_threaded_channels; - } - - /* mbox registration */ - bpmp->mbox.client.dev = &pdev->dev; - bpmp->mbox.client.rx_callback = tegra_bpmp_handle_rx; - bpmp->mbox.client.tx_block = false; - bpmp->mbox.client.knows_txdone = false; - - bpmp->mbox.channel = mbox_request_channel(&bpmp->mbox.client, 0); - if (IS_ERR(bpmp->mbox.channel)) { - err = PTR_ERR(bpmp->mbox.channel); - dev_err(&pdev->dev, "failed to get HSP mailbox: %d\n", err); - goto cleanup_threaded_channels; - } - - /* reset message channels */ - tegra_bpmp_channel_reset(bpmp->tx_channel); - tegra_bpmp_channel_reset(bpmp->rx_channel); - for (i = 0; i < bpmp->threaded.count; i++) - tegra_bpmp_channel_reset(&bpmp->threaded_channels[i]); + return err; err = tegra_bpmp_request_mrq(bpmp, MRQ_PING, tegra_bpmp_mrq_handle_ping, bpmp); if (err < 0) - goto free_mbox; + goto deinit; err = tegra_bpmp_ping(bpmp); if (err < 0) { @@ -920,37 +788,21 @@ static int tegra_bpmp_probe(struct platform_device *pdev) free_mrq: tegra_bpmp_free_mrq(bpmp, MRQ_PING, bpmp); -free_mbox: - mbox_free_channel(bpmp->mbox.channel); -cleanup_threaded_channels: - for (i = 0; i < bpmp->threaded.count; i++) { - if (bpmp->threaded_channels[i].bpmp) - tegra_bpmp_channel_cleanup(&bpmp->threaded_channels[i]); - } +deinit: + if (bpmp->soc->ops->deinit) + bpmp->soc->ops->deinit(bpmp); - tegra_bpmp_channel_cleanup(bpmp->rx_channel); -cleanup_tx_channel: - tegra_bpmp_channel_cleanup(bpmp->tx_channel); -free_rx: - gen_pool_free(bpmp->rx.pool, (unsigned long)bpmp->rx.virt, 4096); -free_tx: - gen_pool_free(bpmp->tx.pool, (unsigned long)bpmp->tx.virt, 4096); return err; } static int __maybe_unused tegra_bpmp_resume(struct device *dev) { struct tegra_bpmp *bpmp = dev_get_drvdata(dev); - unsigned int i; - - /* reset message channels */ - tegra_bpmp_channel_reset(bpmp->tx_channel); - tegra_bpmp_channel_reset(bpmp->rx_channel); - - for (i = 0; i < bpmp->threaded.count; i++) - tegra_bpmp_channel_reset(&bpmp->threaded_channels[i]); - return 0; + if (bpmp->soc->ops->resume) + return bpmp->soc->ops->resume(bpmp); + else + return 0; } static SIMPLE_DEV_PM_OPS(tegra_bpmp_pm_ops, NULL, tegra_bpmp_resume); @@ -971,6 +823,7 @@ static const struct tegra_bpmp_soc tegra186_soc = { .timeout = 0, }, }, + .ops = &tegra186_bpmp_ops, .num_resets = 193, }; diff --git a/include/soc/tegra/bpmp.h b/include/soc/tegra/bpmp.h index b02f926a0216..bdd1bd107aba 100644 --- a/include/soc/tegra/bpmp.h +++ b/include/soc/tegra/bpmp.h @@ -23,6 +23,7 @@ #include struct tegra_bpmp_clk; +struct tegra_bpmp_ops; struct tegra_bpmp_soc { struct { @@ -32,6 +33,8 @@ struct tegra_bpmp_soc { unsigned int timeout; } cpu_tx, thread, cpu_rx; } channels; + + const struct tegra_bpmp_ops *ops; unsigned int num_resets; }; @@ -63,12 +66,7 @@ struct tegra_bpmp_mrq { struct tegra_bpmp { const struct tegra_bpmp_soc *soc; struct device *dev; - - struct { - struct gen_pool *pool; - dma_addr_t phys; - void *virt; - } tx, rx; + void *priv; struct { struct mbox_client client; @@ -173,6 +171,8 @@ static inline bool tegra_bpmp_mrq_is_supported(struct tegra_bpmp *bpmp, } #endif +void tegra_bpmp_handle_rx(struct tegra_bpmp *bpmp); + #if IS_ENABLED(CONFIG_CLK_TEGRA_BPMP) int tegra_bpmp_init_clocks(struct tegra_bpmp *bpmp); #else -- cgit v1.2.3 From 139251fc220830cc49b71331d281a8ad03a08ab7 Mon Sep 17 00:00:00 2001 From: Timo Alho Date: Thu, 24 Jan 2019 19:03:54 +0200 Subject: firmware: tegra: add bpmp driver for Tegra210 This patch adds driver for Tegra210 BPMP firmware. The BPMP is a specific processor in Tegra210 chip, which runs firmware for assisting in entering deep low power states (suspend to ram), and offloading DRAM memory clock scaling on some platforms. Based on work by Sivaram Nair Signed-off-by: Timo Alho Acked-by: Jon Hunter Signed-off-by: Thierry Reding --- drivers/firmware/tegra/Makefile | 1 + drivers/firmware/tegra/bpmp-private.h | 1 + drivers/firmware/tegra/bpmp-tegra210.c | 243 +++++++++++++++++++++++++++++++++ drivers/firmware/tegra/bpmp.c | 46 +++++-- include/soc/tegra/bpmp.h | 1 + 5 files changed, 283 insertions(+), 9 deletions(-) create mode 100644 drivers/firmware/tegra/bpmp-tegra210.c (limited to 'include') diff --git a/drivers/firmware/tegra/Makefile b/drivers/firmware/tegra/Makefile index 559355674bca..ba45e58f7647 100644 --- a/drivers/firmware/tegra/Makefile +++ b/drivers/firmware/tegra/Makefile @@ -1,4 +1,5 @@ tegra-bpmp-y = bpmp.o +tegra-bpmp-$(CONFIG_ARCH_TEGRA_210_SOC) += bpmp-tegra210.o tegra-bpmp-$(CONFIG_ARCH_TEGRA_186_SOC) += bpmp-tegra186.o tegra-bpmp-$(CONFIG_DEBUG_FS) += bpmp-debugfs.o obj-$(CONFIG_TEGRA_BPMP) += tegra-bpmp.o diff --git a/drivers/firmware/tegra/bpmp-private.h b/drivers/firmware/tegra/bpmp-private.h index 6fb10f1cfb8f..07c3d46abb87 100644 --- a/drivers/firmware/tegra/bpmp-private.h +++ b/drivers/firmware/tegra/bpmp-private.h @@ -24,5 +24,6 @@ struct tegra_bpmp_ops { }; extern const struct tegra_bpmp_ops tegra186_bpmp_ops; +extern const struct tegra_bpmp_ops tegra210_bpmp_ops; #endif diff --git a/drivers/firmware/tegra/bpmp-tegra210.c b/drivers/firmware/tegra/bpmp-tegra210.c new file mode 100644 index 000000000000..ae15940a078e --- /dev/null +++ b/drivers/firmware/tegra/bpmp-tegra210.c @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018, NVIDIA CORPORATION. + */ + +#include +#include +#include +#include +#include + +#include + +#include "bpmp-private.h" + +#define TRIGGER_OFFSET 0x000 +#define RESULT_OFFSET(id) (0xc00 + id * 4) +#define TRIGGER_ID_SHIFT 16 +#define TRIGGER_CMD_GET 4 + +#define STA_OFFSET 0 +#define SET_OFFSET 4 +#define CLR_OFFSET 8 + +#define CH_MASK(ch) (0x3 << ((ch) * 2)) +#define SL_SIGL(ch) (0x0 << ((ch) * 2)) +#define SL_QUED(ch) (0x1 << ((ch) * 2)) +#define MA_FREE(ch) (0x2 << ((ch) * 2)) +#define MA_ACKD(ch) (0x3 << ((ch) * 2)) + +struct tegra210_bpmp { + void __iomem *atomics; + void __iomem *arb_sema; + struct irq_data *tx_irq_data; +}; + +static u32 bpmp_channel_status(struct tegra_bpmp *bpmp, unsigned int index) +{ + struct tegra210_bpmp *priv = bpmp->priv; + + return __raw_readl(priv->arb_sema + STA_OFFSET) & CH_MASK(index); +} + +static bool tegra210_bpmp_is_response_ready(struct tegra_bpmp_channel *channel) +{ + unsigned int index = channel->index; + + return bpmp_channel_status(channel->bpmp, index) == MA_ACKD(index); +} + +static bool tegra210_bpmp_is_request_ready(struct tegra_bpmp_channel *channel) +{ + unsigned int index = channel->index; + + return bpmp_channel_status(channel->bpmp, index) == SL_SIGL(index); +} + +static bool +tegra210_bpmp_is_request_channel_free(struct tegra_bpmp_channel *channel) +{ + unsigned int index = channel->index; + + return bpmp_channel_status(channel->bpmp, index) == MA_FREE(index); +} + +static bool +tegra210_bpmp_is_response_channel_free(struct tegra_bpmp_channel *channel) +{ + unsigned int index = channel->index; + + return bpmp_channel_status(channel->bpmp, index) == SL_QUED(index); +} + +static int tegra210_bpmp_post_request(struct tegra_bpmp_channel *channel) +{ + struct tegra210_bpmp *priv = channel->bpmp->priv; + + __raw_writel(CH_MASK(channel->index), priv->arb_sema + CLR_OFFSET); + + return 0; +} + +static int tegra210_bpmp_post_response(struct tegra_bpmp_channel *channel) +{ + struct tegra210_bpmp *priv = channel->bpmp->priv; + + __raw_writel(MA_ACKD(channel->index), priv->arb_sema + SET_OFFSET); + + return 0; +} + +static int tegra210_bpmp_ack_response(struct tegra_bpmp_channel *channel) +{ + struct tegra210_bpmp *priv = channel->bpmp->priv; + + __raw_writel(MA_ACKD(channel->index) ^ MA_FREE(channel->index), + priv->arb_sema + CLR_OFFSET); + + return 0; +} + +static int tegra210_bpmp_ack_request(struct tegra_bpmp_channel *channel) +{ + struct tegra210_bpmp *priv = channel->bpmp->priv; + + __raw_writel(SL_QUED(channel->index), priv->arb_sema + SET_OFFSET); + + return 0; +} + +static int tegra210_bpmp_ring_doorbell(struct tegra_bpmp *bpmp) +{ + struct tegra210_bpmp *priv = bpmp->priv; + struct irq_data *irq_data = priv->tx_irq_data; + + /* + * Tegra Legacy Interrupt Controller (LIC) is used to notify BPMP of + * available messages + */ + if (irq_data->chip->irq_retrigger) + return irq_data->chip->irq_retrigger(irq_data); + + return -EINVAL; +} + +static irqreturn_t rx_irq(int irq, void *data) +{ + struct tegra_bpmp *bpmp = data; + + tegra_bpmp_handle_rx(bpmp); + + return IRQ_HANDLED; +} + +static int tegra210_bpmp_channel_init(struct tegra_bpmp_channel *channel, + struct tegra_bpmp *bpmp, + unsigned int index) +{ + struct tegra210_bpmp *priv = bpmp->priv; + u32 address; + void *p; + + /* Retrieve channel base address from BPMP */ + writel(index << TRIGGER_ID_SHIFT | TRIGGER_CMD_GET, + priv->atomics + TRIGGER_OFFSET); + address = readl(priv->atomics + RESULT_OFFSET(index)); + + p = devm_ioremap(bpmp->dev, address, 0x80); + if (!p) + return -ENOMEM; + + channel->ib = p; + channel->ob = p; + channel->index = index; + init_completion(&channel->completion); + channel->bpmp = bpmp; + + return 0; +} + +static int tegra210_bpmp_init(struct tegra_bpmp *bpmp) +{ + struct platform_device *pdev = to_platform_device(bpmp->dev); + struct tegra210_bpmp *priv; + struct resource *res; + unsigned int i; + int err; + + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + bpmp->priv = priv; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + priv->atomics = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->atomics)) + return PTR_ERR(priv->atomics); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + priv->arb_sema = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->arb_sema)) + return PTR_ERR(priv->arb_sema); + + err = tegra210_bpmp_channel_init(bpmp->tx_channel, bpmp, + bpmp->soc->channels.cpu_tx.offset); + if (err < 0) + return err; + + err = tegra210_bpmp_channel_init(bpmp->rx_channel, bpmp, + bpmp->soc->channels.cpu_rx.offset); + if (err < 0) + return err; + + for (i = 0; i < bpmp->threaded.count; i++) { + unsigned int index = bpmp->soc->channels.thread.offset + i; + + err = tegra210_bpmp_channel_init(&bpmp->threaded_channels[i], + bpmp, index); + if (err < 0) + return err; + } + + err = platform_get_irq_byname(pdev, "tx"); + if (err < 0) { + dev_err(&pdev->dev, "failed to get TX IRQ: %d\n", err); + return err; + } + + priv->tx_irq_data = irq_get_irq_data(err); + if (!priv->tx_irq_data) { + dev_err(&pdev->dev, "failed to get IRQ data for TX IRQ\n"); + return err; + } + + err = platform_get_irq_byname(pdev, "rx"); + if (err < 0) { + dev_err(&pdev->dev, "failed to get rx IRQ: %d\n", err); + return err; + } + + err = devm_request_irq(&pdev->dev, err, rx_irq, + IRQF_NO_SUSPEND, dev_name(&pdev->dev), bpmp); + if (err < 0) { + dev_err(&pdev->dev, "failed to request IRQ: %d\n", err); + return err; + } + + return 0; +} + +const struct tegra_bpmp_ops tegra210_bpmp_ops = { + .init = tegra210_bpmp_init, + .is_response_ready = tegra210_bpmp_is_response_ready, + .is_request_ready = tegra210_bpmp_is_request_ready, + .ack_response = tegra210_bpmp_ack_response, + .ack_request = tegra210_bpmp_ack_request, + .is_response_channel_free = tegra210_bpmp_is_response_channel_free, + .is_request_channel_free = tegra210_bpmp_is_request_channel_free, + .post_response = tegra210_bpmp_post_response, + .post_request = tegra210_bpmp_post_request, + .ring_doorbell = tegra210_bpmp_ring_doorbell, +}; diff --git a/drivers/firmware/tegra/bpmp.c b/drivers/firmware/tegra/bpmp.c index 2b498deacdbc..8e3f79959d48 100644 --- a/drivers/firmware/tegra/bpmp.c +++ b/drivers/firmware/tegra/bpmp.c @@ -768,17 +768,23 @@ static int tegra_bpmp_probe(struct platform_device *pdev) if (err < 0) goto free_mrq; - err = tegra_bpmp_init_clocks(bpmp); - if (err < 0) - goto free_mrq; + if (of_find_property(pdev->dev.of_node, "#clock-cells", NULL)) { + err = tegra_bpmp_init_clocks(bpmp); + if (err < 0) + goto free_mrq; + } - err = tegra_bpmp_init_resets(bpmp); - if (err < 0) - goto free_mrq; + if (of_find_property(pdev->dev.of_node, "#reset-cells", NULL)) { + err = tegra_bpmp_init_resets(bpmp); + if (err < 0) + goto free_mrq; + } - err = tegra_bpmp_init_powergates(bpmp); - if (err < 0) - goto free_mrq; + if (of_find_property(pdev->dev.of_node, "#power-domain-cells", NULL)) { + err = tegra_bpmp_init_powergates(bpmp); + if (err < 0) + goto free_mrq; + } err = tegra_bpmp_init_debugfs(bpmp); if (err < 0) @@ -827,8 +833,30 @@ static const struct tegra_bpmp_soc tegra186_soc = { .num_resets = 193, }; +static const struct tegra_bpmp_soc tegra210_soc = { + .channels = { + .cpu_tx = { + .offset = 0, + .count = 1, + .timeout = 60 * USEC_PER_SEC, + }, + .thread = { + .offset = 4, + .count = 1, + .timeout = 600 * USEC_PER_SEC, + }, + .cpu_rx = { + .offset = 8, + .count = 1, + .timeout = 0, + }, + }, + .ops = &tegra210_bpmp_ops, +}; + static const struct of_device_id tegra_bpmp_match[] = { { .compatible = "nvidia,tegra186-bpmp", .data = &tegra186_soc }, + { .compatible = "nvidia,tegra210-bpmp", .data = &tegra210_soc }, { } }; diff --git a/include/soc/tegra/bpmp.h b/include/soc/tegra/bpmp.h index bdd1bd107aba..45960aa08f4a 100644 --- a/include/soc/tegra/bpmp.h +++ b/include/soc/tegra/bpmp.h @@ -50,6 +50,7 @@ struct tegra_bpmp_channel { struct tegra_bpmp_mb_data *ob; struct completion completion; struct tegra_ivc *ivc; + unsigned int index; }; typedef void (*tegra_bpmp_mrq_handler_t)(unsigned int mrq, -- cgit v1.2.3 From 9359a8cbcc77d4afb07444f341e39015d232bd55 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 25 Jan 2019 16:30:35 +0200 Subject: RAS: Use consistent types for UUIDs The commit 297b64c74385 ("ras: acpi / apei: generate trace event for unrecognized CPER section") brought inconsistency in UUID types which are used across the RAS subsystem. Fix this by using guid_t everywhere. Signed-off-by: Andy Shevchenko Signed-off-by: Borislav Petkov Reviewed-by: Christoph Hellwig Cc: "Rafael J. Wysocki" Cc: "Steven Rostedt (VMware)" Cc: Bjorn Helgaas Cc: Thomas Tai Cc: Tony Luck Cc: Tyler Baicar Link: https://lkml.kernel.org/r/20190125143035.81589-1-andriy.shevchenko@linux.intel.com --- drivers/ras/ras.c | 2 +- include/ras/ras_event.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c index 3f38907320dc..95540ea8dd9d 100644 --- a/drivers/ras/ras.c +++ b/drivers/ras/ras.c @@ -14,7 +14,7 @@ #define TRACE_INCLUDE_PATH ../../include/ras #include -void log_non_standard_event(const uuid_le *sec_type, const uuid_le *fru_id, +void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id, const char *fru_text, const u8 sev, const u8 *err, const u32 len) { diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index a0794632fd01..36c5c5e38c1d 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -27,7 +27,7 @@ TRACE_EVENT(extlog_mem_event, TP_PROTO(struct cper_sec_mem_err *mem, u32 err_seq, - const uuid_le *fru_id, + const guid_t *fru_id, const char *fru_text, u8 sev), @@ -39,7 +39,7 @@ TRACE_EVENT(extlog_mem_event, __field(u8, sev) __field(u64, pa) __field(u8, pa_mask_lsb) - __field_struct(uuid_le, fru_id) + __field_struct(guid_t, fru_id) __string(fru_text, fru_text) __field_struct(struct cper_mem_err_compact, data) ), @@ -218,8 +218,8 @@ TRACE_EVENT(arm_event, */ TRACE_EVENT(non_standard_event, - TP_PROTO(const uuid_le *sec_type, - const uuid_le *fru_id, + TP_PROTO(const guid_t *sec_type, + const guid_t *fru_id, const char *fru_text, const u8 sev, const u8 *err, -- cgit v1.2.3 From 275f22148e8720e84b180d9e0cdf8abfd69bac5b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 31 Dec 2018 22:22:40 +0100 Subject: ipc: rename old-style shmctl/semctl/msgctl syscalls The behavior of these system calls is slightly different between architectures, as determined by the CONFIG_ARCH_WANT_IPC_PARSE_VERSION symbol. Most architectures that implement the split IPC syscalls don't set that symbol and only get the modern version, but alpha, arm, microblaze, mips-n32, mips-n64 and xtensa expect the caller to pass the IPC_64 flag. For the architectures that so far only implement sys_ipc(), i.e. m68k, mips-o32, powerpc, s390, sh, sparc, and x86-32, we want the new behavior when adding the split syscalls, so we need to distinguish between the two groups of architectures. The method I picked for this distinction is to have a separate system call entry point: sys_old_*ctl() now uses ipc_parse_version, while sys_*ctl() does not. The system call tables of the five architectures are changed accordingly. As an additional benefit, we no longer need the configuration specific definition for ipc_parse_version(), it always does the same thing now, but simply won't get called on architectures with the modern interface. A small downside is that on architectures that do set ARCH_WANT_IPC_PARSE_VERSION, we now have an extra set of entry points that are never called. They only add a few bytes of bloat, so it seems better to keep them compared to adding yet another Kconfig symbol. I considered adding new syscall numbers for the IPC_64 variants for consistency, but decided against that for now. Signed-off-by: Arnd Bergmann --- arch/alpha/kernel/syscalls/syscall.tbl | 6 ++--- arch/arm/tools/syscall.tbl | 6 ++--- arch/arm64/include/asm/unistd32.h | 6 ++--- arch/microblaze/kernel/syscalls/syscall.tbl | 6 ++--- arch/mips/kernel/syscalls/syscall_n32.tbl | 6 ++--- arch/mips/kernel/syscalls/syscall_n64.tbl | 6 ++--- arch/xtensa/kernel/syscalls/syscall.tbl | 6 ++--- include/linux/syscalls.h | 3 +++ ipc/msg.c | 39 +++++++++++++++++++++++----- ipc/sem.c | 39 +++++++++++++++++++++++----- ipc/shm.c | 40 ++++++++++++++++++++++++----- ipc/syscall.c | 12 ++++----- ipc/util.h | 21 +++++---------- kernel/sys_ni.c | 3 +++ 14 files changed, 137 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index f920b65e8c49..b0e247287908 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -174,17 +174,17 @@ 187 common osf_alt_sigpending sys_ni_syscall 188 common osf_alt_setsid sys_ni_syscall 199 common osf_swapon sys_swapon -200 common msgctl sys_msgctl +200 common msgctl sys_old_msgctl 201 common msgget sys_msgget 202 common msgrcv sys_msgrcv 203 common msgsnd sys_msgsnd -204 common semctl sys_semctl +204 common semctl sys_old_semctl 205 common semget sys_semget 206 common semop sys_semop 207 common osf_utsname sys_osf_utsname 208 common lchown sys_lchown 209 common shmat sys_shmat -210 common shmctl sys_shmctl +210 common shmctl sys_old_shmctl 211 common shmdt sys_shmdt 212 common shmget sys_shmget 213 common osf_mvalid sys_ni_syscall diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 20ed7e026723..b54b7f2bc24a 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -314,15 +314,15 @@ 297 common recvmsg sys_recvmsg 298 common semop sys_semop sys_oabi_semop 299 common semget sys_semget -300 common semctl sys_semctl +300 common semctl sys_old_semctl 301 common msgsnd sys_msgsnd 302 common msgrcv sys_msgrcv 303 common msgget sys_msgget -304 common msgctl sys_msgctl +304 common msgctl sys_old_msgctl 305 common shmat sys_shmat 306 common shmdt sys_shmdt 307 common shmget sys_shmget -308 common shmctl sys_shmctl +308 common shmctl sys_old_shmctl 309 common add_key sys_add_key 310 common request_key sys_request_key 311 common keyctl sys_keyctl diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 8ca1d4c304f4..d10cce69a4b0 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -622,7 +622,7 @@ __SYSCALL(__NR_semop, sys_semop) #define __NR_semget 299 __SYSCALL(__NR_semget, sys_semget) #define __NR_semctl 300 -__SYSCALL(__NR_semctl, compat_sys_semctl) +__SYSCALL(__NR_semctl, compat_sys_old_semctl) #define __NR_msgsnd 301 __SYSCALL(__NR_msgsnd, compat_sys_msgsnd) #define __NR_msgrcv 302 @@ -630,7 +630,7 @@ __SYSCALL(__NR_msgrcv, compat_sys_msgrcv) #define __NR_msgget 303 __SYSCALL(__NR_msgget, sys_msgget) #define __NR_msgctl 304 -__SYSCALL(__NR_msgctl, compat_sys_msgctl) +__SYSCALL(__NR_msgctl, compat_sys_old_msgctl) #define __NR_shmat 305 __SYSCALL(__NR_shmat, compat_sys_shmat) #define __NR_shmdt 306 @@ -638,7 +638,7 @@ __SYSCALL(__NR_shmdt, sys_shmdt) #define __NR_shmget 307 __SYSCALL(__NR_shmget, sys_shmget) #define __NR_shmctl 308 -__SYSCALL(__NR_shmctl, compat_sys_shmctl) +__SYSCALL(__NR_shmctl, compat_sys_old_shmctl) #define __NR_add_key 309 __SYSCALL(__NR_add_key, sys_add_key) #define __NR_request_key 310 diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index a24d09e937dd..7cc0f9554da3 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -335,15 +335,15 @@ 325 common semtimedop sys_semtimedop 326 common timerfd_settime sys_timerfd_settime 327 common timerfd_gettime sys_timerfd_gettime -328 common semctl sys_semctl +328 common semctl sys_old_semctl 329 common semget sys_semget 330 common semop sys_semop -331 common msgctl sys_msgctl +331 common msgctl sys_old_msgctl 332 common msgget sys_msgget 333 common msgrcv sys_msgrcv 334 common msgsnd sys_msgsnd 335 common shmat sys_shmat -336 common shmctl sys_shmctl +336 common shmctl sys_old_shmctl 337 common shmdt sys_shmdt 338 common shmget sys_shmget 339 common signalfd4 sys_signalfd4 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 53d5862649ae..cc134b1211aa 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -37,7 +37,7 @@ 27 n32 madvise sys_madvise 28 n32 shmget sys_shmget 29 n32 shmat sys_shmat -30 n32 shmctl compat_sys_shmctl +30 n32 shmctl compat_sys_old_shmctl 31 n32 dup sys_dup 32 n32 dup2 sys_dup2 33 n32 pause sys_pause @@ -71,12 +71,12 @@ 61 n32 uname sys_newuname 62 n32 semget sys_semget 63 n32 semop sys_semop -64 n32 semctl compat_sys_semctl +64 n32 semctl compat_sys_old_semctl 65 n32 shmdt sys_shmdt 66 n32 msgget sys_msgget 67 n32 msgsnd compat_sys_msgsnd 68 n32 msgrcv compat_sys_msgrcv -69 n32 msgctl compat_sys_msgctl +69 n32 msgctl compat_sys_old_msgctl 70 n32 fcntl compat_sys_fcntl 71 n32 flock sys_flock 72 n32 fsync sys_fsync diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index a8286ccbb66c..af0da757a7b2 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -37,7 +37,7 @@ 27 n64 madvise sys_madvise 28 n64 shmget sys_shmget 29 n64 shmat sys_shmat -30 n64 shmctl sys_shmctl +30 n64 shmctl sys_old_shmctl 31 n64 dup sys_dup 32 n64 dup2 sys_dup2 33 n64 pause sys_pause @@ -71,12 +71,12 @@ 61 n64 uname sys_newuname 62 n64 semget sys_semget 63 n64 semop sys_semop -64 n64 semctl sys_semctl +64 n64 semctl sys_old_semctl 65 n64 shmdt sys_shmdt 66 n64 msgget sys_msgget 67 n64 msgsnd sys_msgsnd 68 n64 msgrcv sys_msgrcv -69 n64 msgctl sys_msgctl +69 n64 msgctl sys_old_msgctl 70 n64 fcntl sys_fcntl 71 n64 flock sys_flock 72 n64 fsync sys_fsync diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 69cf91b03b26..f8befa11b0c4 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -103,7 +103,7 @@ 91 common madvise sys_madvise 92 common shmget sys_shmget 93 common shmat xtensa_shmat -94 common shmctl sys_shmctl +94 common shmctl sys_old_shmctl 95 common shmdt sys_shmdt # Socket Operations 96 common socket sys_socket @@ -177,12 +177,12 @@ 161 common semtimedop sys_semtimedop 162 common semget sys_semget 163 common semop sys_semop -164 common semctl sys_semctl +164 common semctl sys_old_semctl 165 common available165 sys_ni_syscall 166 common msgget sys_msgget 167 common msgsnd sys_msgsnd 168 common msgrcv sys_msgrcv -169 common msgctl sys_msgctl +169 common msgctl sys_old_msgctl 170 common available170 sys_ni_syscall # File System 171 common umount2 sys_umount diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index fb63045a0fb6..938d8908b9e0 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -717,6 +717,7 @@ asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqst /* ipc/msg.c */ asmlinkage long sys_msgget(key_t key, int msgflg); +asmlinkage long sys_old_msgctl(int msqid, int cmd, struct msqid_ds __user *buf); asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf); asmlinkage long sys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, long msgtyp, int msgflg); @@ -726,6 +727,7 @@ asmlinkage long sys_msgsnd(int msqid, struct msgbuf __user *msgp, /* ipc/sem.c */ asmlinkage long sys_semget(key_t key, int nsems, int semflg); asmlinkage long sys_semctl(int semid, int semnum, int cmd, unsigned long arg); +asmlinkage long sys_old_semctl(int semid, int semnum, int cmd, unsigned long arg); asmlinkage long sys_semtimedop(int semid, struct sembuf __user *sops, unsigned nsops, const struct __kernel_timespec __user *timeout); @@ -734,6 +736,7 @@ asmlinkage long sys_semop(int semid, struct sembuf __user *sops, /* ipc/shm.c */ asmlinkage long sys_shmget(key_t key, size_t size, int flag); +asmlinkage long sys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg); asmlinkage long sys_shmdt(char __user *shmaddr); diff --git a/ipc/msg.c b/ipc/msg.c index 0833c6405915..8dec945fa030 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -567,9 +567,8 @@ out_unlock: return err; } -long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) +static long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf, int version) { - int version; struct ipc_namespace *ns; struct msqid64_ds msqid64; int err; @@ -577,7 +576,6 @@ long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) if (msqid < 0 || cmd < 0) return -EINVAL; - version = ipc_parse_version(&cmd); ns = current->nsproxy->ipc_ns; switch (cmd) { @@ -613,9 +611,23 @@ long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) { - return ksys_msgctl(msqid, cmd, buf); + return ksys_msgctl(msqid, cmd, buf, IPC_64); } +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION +long ksys_old_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) +{ + int version = ipc_parse_version(&cmd); + + return ksys_msgctl(msqid, cmd, buf, version); +} + +SYSCALL_DEFINE3(old_msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) +{ + return ksys_old_msgctl(msqid, cmd, buf); +} +#endif + #ifdef CONFIG_COMPAT struct compat_msqid_ds { @@ -689,12 +701,11 @@ static int copy_compat_msqid_to_user(void __user *buf, struct msqid64_ds *in, } } -long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr) +static long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr, int version) { struct ipc_namespace *ns; int err; struct msqid64_ds msqid64; - int version = compat_ipc_parse_version(&cmd); ns = current->nsproxy->ipc_ns; @@ -734,8 +745,22 @@ long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr) COMPAT_SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, void __user *, uptr) { - return compat_ksys_msgctl(msqid, cmd, uptr); + return compat_ksys_msgctl(msqid, cmd, uptr, IPC_64); } + +#ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION +long compat_ksys_old_msgctl(int msqid, int cmd, void __user *uptr) +{ + int version = compat_ipc_parse_version(&cmd); + + return compat_ksys_msgctl(msqid, cmd, uptr, version); +} + +COMPAT_SYSCALL_DEFINE3(old_msgctl, int, msqid, int, cmd, void __user *, uptr) +{ + return compat_ksys_old_msgctl(msqid, cmd, uptr); +} +#endif #endif static int testmsg(struct msg_msg *msg, long type, int mode) diff --git a/ipc/sem.c b/ipc/sem.c index 745dc6187e84..d1efff3a81bb 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1634,9 +1634,8 @@ out_up: return err; } -long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg) +static long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg, int version) { - int version; struct ipc_namespace *ns; void __user *p = (void __user *)arg; struct semid64_ds semid64; @@ -1645,7 +1644,6 @@ long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg) if (semid < 0) return -EINVAL; - version = ipc_parse_version(&cmd); ns = current->nsproxy->ipc_ns; switch (cmd) { @@ -1691,9 +1689,23 @@ long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg) SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) { - return ksys_semctl(semid, semnum, cmd, arg); + return ksys_semctl(semid, semnum, cmd, arg, IPC_64); } +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION +long ksys_old_semctl(int semid, int semnum, int cmd, unsigned long arg) +{ + int version = ipc_parse_version(&cmd); + + return ksys_semctl(semid, semnum, cmd, arg, version); +} + +SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) +{ + return ksys_old_semctl(semid, semnum, cmd, arg); +} +#endif + #ifdef CONFIG_COMPAT struct compat_semid_ds { @@ -1744,12 +1756,11 @@ static int copy_compat_semid_to_user(void __user *buf, struct semid64_ds *in, } } -long compat_ksys_semctl(int semid, int semnum, int cmd, int arg) +static long compat_ksys_semctl(int semid, int semnum, int cmd, int arg, int version) { void __user *p = compat_ptr(arg); struct ipc_namespace *ns; struct semid64_ds semid64; - int version = compat_ipc_parse_version(&cmd); int err; ns = current->nsproxy->ipc_ns; @@ -1792,8 +1803,22 @@ long compat_ksys_semctl(int semid, int semnum, int cmd, int arg) COMPAT_SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, int, arg) { - return compat_ksys_semctl(semid, semnum, cmd, arg); + return compat_ksys_semctl(semid, semnum, cmd, arg, IPC_64); } + +#ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION +long compat_ksys_old_semctl(int semid, int semnum, int cmd, int arg) +{ + int version = compat_ipc_parse_version(&cmd); + + return compat_ksys_semctl(semid, semnum, cmd, arg, version); +} + +COMPAT_SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, int, arg) +{ + return compat_ksys_old_semctl(semid, semnum, cmd, arg); +} +#endif #endif /* If the task doesn't already have a undo_list, then allocate one diff --git a/ipc/shm.c b/ipc/shm.c index 0842411cb0e9..ce1ca9f7c6e9 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1137,16 +1137,15 @@ out_unlock1: return err; } -long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) +static long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf, int version) { - int err, version; + int err; struct ipc_namespace *ns; struct shmid64_ds sem64; if (cmd < 0 || shmid < 0) return -EINVAL; - version = ipc_parse_version(&cmd); ns = current->nsproxy->ipc_ns; switch (cmd) { @@ -1194,8 +1193,22 @@ long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { - return ksys_shmctl(shmid, cmd, buf); + return ksys_shmctl(shmid, cmd, buf, IPC_64); +} + +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION +long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) +{ + int version = ipc_parse_version(&cmd); + + return ksys_shmctl(shmid, cmd, buf, version); +} + +SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) +{ + return ksys_old_shmctl(shmid, cmd, buf); } +#endif #ifdef CONFIG_COMPAT @@ -1319,11 +1332,10 @@ static int copy_compat_shmid_from_user(struct shmid64_ds *out, void __user *buf, } } -long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr) +long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int version) { struct ipc_namespace *ns; struct shmid64_ds sem64; - int version = compat_ipc_parse_version(&cmd); int err; ns = current->nsproxy->ipc_ns; @@ -1378,8 +1390,22 @@ long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr) COMPAT_SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, void __user *, uptr) { - return compat_ksys_shmctl(shmid, cmd, uptr); + return compat_ksys_shmctl(shmid, cmd, uptr, IPC_64); } + +#ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION +long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr) +{ + int version = compat_ipc_parse_version(&cmd); + + return compat_ksys_shmctl(shmid, cmd, uptr, version); +} + +COMPAT_SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, void __user *, uptr) +{ + return compat_ksys_old_shmctl(shmid, cmd, uptr); +} +#endif #endif /* diff --git a/ipc/syscall.c b/ipc/syscall.c index 3cf8ad703a4d..581bdff4e7c5 100644 --- a/ipc/syscall.c +++ b/ipc/syscall.c @@ -47,7 +47,7 @@ int ksys_ipc(unsigned int call, int first, unsigned long second, return -EINVAL; if (get_user(arg, (unsigned long __user *) ptr)) return -EFAULT; - return ksys_semctl(first, second, third, arg); + return ksys_old_semctl(first, second, third, arg); } case MSGSND: @@ -75,7 +75,7 @@ int ksys_ipc(unsigned int call, int first, unsigned long second, case MSGGET: return ksys_msgget((key_t) first, second); case MSGCTL: - return ksys_msgctl(first, second, + return ksys_old_msgctl(first, second, (struct msqid_ds __user *)ptr); case SHMAT: @@ -100,7 +100,7 @@ int ksys_ipc(unsigned int call, int first, unsigned long second, case SHMGET: return ksys_shmget(first, second, third); case SHMCTL: - return ksys_shmctl(first, second, + return ksys_old_shmctl(first, second, (struct shmid_ds __user *) ptr); default: return -ENOSYS; @@ -152,7 +152,7 @@ int compat_ksys_ipc(u32 call, int first, int second, return -EINVAL; if (get_user(pad, (u32 __user *) compat_ptr(ptr))) return -EFAULT; - return compat_ksys_semctl(first, second, third, pad); + return compat_ksys_old_semctl(first, second, third, pad); case MSGSND: return compat_ksys_msgsnd(first, ptr, second, third); @@ -177,7 +177,7 @@ int compat_ksys_ipc(u32 call, int first, int second, case MSGGET: return ksys_msgget(first, second); case MSGCTL: - return compat_ksys_msgctl(first, second, compat_ptr(ptr)); + return compat_ksys_old_msgctl(first, second, compat_ptr(ptr)); case SHMAT: { int err; @@ -196,7 +196,7 @@ int compat_ksys_ipc(u32 call, int first, int second, case SHMGET: return ksys_shmget(first, (unsigned int)second, third); case SHMCTL: - return compat_ksys_shmctl(first, second, compat_ptr(ptr)); + return compat_ksys_old_shmctl(first, second, compat_ptr(ptr)); } return -ENOSYS; diff --git a/ipc/util.h b/ipc/util.h index d768fdbed515..e272be622ae7 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -160,10 +160,7 @@ static inline void ipc_update_pid(struct pid **pos, struct pid *pid) } } -#ifndef CONFIG_ARCH_WANT_IPC_PARSE_VERSION -/* On IA-64, we always use the "64-bit version" of the IPC structures. */ -# define ipc_parse_version(cmd) IPC_64 -#else +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION int ipc_parse_version(int *cmd); #endif @@ -246,13 +243,9 @@ int get_compat_ipc64_perm(struct ipc64_perm *, static inline int compat_ipc_parse_version(int *cmd) { -#ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION int version = *cmd & IPC_64; *cmd &= ~IPC_64; return version; -#else - return IPC_64; -#endif } #endif @@ -261,29 +254,29 @@ long ksys_semtimedop(int semid, struct sembuf __user *tsops, unsigned int nsops, const struct __kernel_timespec __user *timeout); long ksys_semget(key_t key, int nsems, int semflg); -long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg); +long ksys_old_semctl(int semid, int semnum, int cmd, unsigned long arg); long ksys_msgget(key_t key, int msgflg); -long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf); +long ksys_old_msgctl(int msqid, int cmd, struct msqid_ds __user *buf); long ksys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, long msgtyp, int msgflg); long ksys_msgsnd(int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg); long ksys_shmget(key_t key, size_t size, int shmflg); long ksys_shmdt(char __user *shmaddr); -long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); +long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); /* for CONFIG_ARCH_WANT_OLD_COMPAT_IPC */ long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, unsigned int nsops, const struct old_timespec32 __user *timeout); #ifdef CONFIG_COMPAT -long compat_ksys_semctl(int semid, int semnum, int cmd, int arg); -long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr); +long compat_ksys_old_semctl(int semid, int semnum, int cmd, int arg); +long compat_ksys_old_msgctl(int msqid, int cmd, void __user *uptr); long compat_ksys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg); long compat_ksys_msgsnd(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, int msgflg); -long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr); +long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr); #endif /* CONFIG_COMPAT */ #endif diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index bc934f31ab10..ce04431a40d1 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -197,6 +197,7 @@ COND_SYSCALL_COMPAT(mq_getsetattr); /* ipc/msg.c */ COND_SYSCALL(msgget); +COND_SYSCALL(old_msgctl); COND_SYSCALL(msgctl); COND_SYSCALL_COMPAT(msgctl); COND_SYSCALL(msgrcv); @@ -206,6 +207,7 @@ COND_SYSCALL_COMPAT(msgsnd); /* ipc/sem.c */ COND_SYSCALL(semget); +COND_SYSCALL(old_semctl); COND_SYSCALL(semctl); COND_SYSCALL_COMPAT(semctl); COND_SYSCALL(semtimedop); @@ -214,6 +216,7 @@ COND_SYSCALL(semop); /* ipc/shm.c */ COND_SYSCALL(shmget); +COND_SYSCALL(old_shmctl); COND_SYSCALL(shmctl); COND_SYSCALL_COMPAT(shmctl); COND_SYSCALL(shmat); -- cgit v1.2.3 From 0d6040d4681735dfc47565de288525de405a5c99 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 31 Dec 2018 14:38:26 +0100 Subject: arch: add split IPC system calls where needed The IPC system call handling is highly inconsistent across architectures, some use sys_ipc, some use separate calls, and some use both. We also have some architectures that require passing IPC_64 in the flags, and others that set it implicitly. For the addition of a y2038 safe semtimedop() system call, I chose to only support the separate entry points, but that requires first supporting the regular ones with their own syscall numbers. The IPC_64 is now implied by the new semctl/shmctl/msgctl system calls even on the architectures that require passing it with the ipc() multiplexer. I'm not adding the new semtimedop() or semop() on 32-bit architectures, those will get implemented using the new semtimedop_time64() version that gets added along with the other time64 calls. Three 64-bit architectures (powerpc, s390 and sparc) get semtimedop(). Signed-off-by: Arnd Bergmann Acked-by: Geert Uytterhoeven Acked-by: Heiko Carstens --- arch/m68k/kernel/syscalls/syscall.tbl | 11 +++++++++++ arch/mips/kernel/syscalls/syscall_o32.tbl | 11 +++++++++++ arch/powerpc/kernel/syscalls/syscall.tbl | 13 +++++++++++++ arch/s390/kernel/syscalls/syscall.tbl | 12 ++++++++++++ arch/sh/kernel/syscalls/syscall.tbl | 11 +++++++++++ arch/sparc/kernel/syscalls/syscall.tbl | 12 ++++++++++++ arch/x86/entry/syscalls/syscall_32.tbl | 11 +++++++++++ arch/x86/entry/syscalls/syscall_64.tbl | 2 ++ include/uapi/asm-generic/unistd.h | 1 + 9 files changed, 84 insertions(+) (limited to 'include') diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 85779d6ef935..5354ba02eed2 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -388,3 +388,14 @@ 378 common pwritev2 sys_pwritev2 379 common statx sys_statx 380 common seccomp sys_seccomp +# room for arch specific calls +393 common semget sys_semget +394 common semctl sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl +397 common shmat sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd +401 common msgrcv sys_msgrcv +402 common msgctl sys_msgctl diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 3d5a47b80d2b..fa47ea8cc6ef 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -380,3 +380,14 @@ 366 o32 statx sys_statx 367 o32 rseq sys_rseq 368 o32 io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +# room for arch specific calls +393 o32 semget sys_semget +394 o32 semctl sys_semctl compat_sys_semctl +395 o32 shmget sys_shmget +396 o32 shmctl sys_shmctl compat_sys_shmctl +397 o32 shmat sys_shmat compat_sys_shmat +398 o32 shmdt sys_shmdt +399 o32 msgget sys_msgget +400 o32 msgsnd sys_msgsnd compat_sys_msgsnd +401 o32 msgrcv sys_msgrcv compat_sys_msgrcv +402 o32 msgctl sys_msgctl compat_sys_msgctl diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index db3bbb8744af..7555874ce39c 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -414,6 +414,7 @@ 363 spu switch_endian sys_ni_syscall 364 common userfaultfd sys_userfaultfd 365 common membarrier sys_membarrier +# 366-377 originally left for IPC, now unused 378 nospu mlock2 sys_mlock2 379 nospu copy_file_range sys_copy_file_range 380 common preadv2 sys_preadv2 compat_sys_preadv2 @@ -425,3 +426,15 @@ 386 nospu pkey_mprotect sys_pkey_mprotect 387 nospu rseq sys_rseq 388 nospu io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +# room for arch specific syscalls +392 64 semtimedop sys_semtimedop +393 common semget sys_semget +394 common semctl sys_semctl compat_sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl compat_sys_shmctl +397 common shmat sys_shmat compat_sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd compat_sys_msgsnd +401 common msgrcv sys_msgrcv compat_sys_msgrcv +402 common msgctl sys_msgctl compat_sys_msgctl diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 7413fd318e2a..0bccb01c6202 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -391,3 +391,15 @@ 381 common kexec_file_load sys_kexec_file_load sys_kexec_file_load 382 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents 383 common rseq sys_rseq sys_rseq +# room for arch specific syscalls +392 64 semtimedop sys_semtimedop - +393 common semget sys_semget sys_semget +394 common semctl sys_semctl compat_sys_semctl +395 common shmget sys_shmget sys_shmget +396 common shmctl sys_shmctl compat_sys_shmctl +397 common shmat sys_shmat compat_sys_shmat +398 common shmdt sys_shmdt sys_shmdt +399 common msgget sys_msgget sys_msgget +400 common msgsnd sys_msgsnd compat_sys_msgsnd +401 common msgrcv sys_msgrcv compat_sys_msgrcv +402 common msgctl sys_msgctl compat_sys_msgctl diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index a70db013dbc7..6d0b84e3ef2d 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -391,3 +391,14 @@ 381 common preadv2 sys_preadv2 382 common pwritev2 sys_pwritev2 383 common statx sys_statx +# room for arch specific syscalls +393 common semget sys_semget +394 common semctl sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl +397 common shmat sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd +401 common msgrcv sys_msgrcv +402 common msgctl sys_msgctl diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index c8c77c05ea97..8c9580302422 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -407,3 +407,15 @@ 359 common pwritev2 sys_pwritev2 compat_sys_pwritev2 360 common statx sys_statx 361 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +# room for arch specific syscalls +392 64 semtimedop sys_semtimedop +393 common semget sys_semget +394 common semctl sys_semctl compat_sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl compat_sys_shmctl +397 common shmat sys_shmat compat_sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd compat_sys_msgsnd +401 common msgrcv sys_msgrcv compat_sys_msgrcv +402 common msgctl sys_msgctl compat_sys_msgctl diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 3cf7b533b3d1..2be1d0eb7754 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -398,3 +398,14 @@ 384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl 385 i386 io_pgetevents sys_io_pgetevents __ia32_compat_sys_io_pgetevents 386 i386 rseq sys_rseq __ia32_sys_rseq +# don't use numbers 387 through 392, add new calls at the end +393 i386 semget sys_semget __ia32_sys_semget +394 i386 semctl sys_semctl __ia32_compat_sys_semctl +395 i386 shmget sys_shmget __ia32_sys_shmget +396 i386 shmctl sys_shmctl __ia32_compat_sys_shmctl +397 i386 shmat sys_shmat __ia32_compat_sys_shmat +398 i386 shmdt sys_shmdt __ia32_sys_shmdt +399 i386 msgget sys_msgget __ia32_sys_msgget +400 i386 msgsnd sys_msgsnd __ia32_compat_sys_msgsnd +401 i386 msgrcv sys_msgrcv __ia32_compat_sys_msgrcv +402 i386 msgctl sys_msgctl __ia32_compat_sys_msgctl diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index f0b1709a5ffb..9d8128ef50a9 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -343,6 +343,8 @@ 332 common statx __x64_sys_statx 333 common io_pgetevents __x64_sys_io_pgetevents 334 common rseq __x64_sys_rseq +# don't use numbers 387 through 423, add new calls after the last +# 'common' entry # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index d90127298f12..509484dbfd5d 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -740,6 +740,7 @@ __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) __SYSCALL(__NR_rseq, sys_rseq) #define __NR_kexec_file_load 294 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) +/* 295 through 402 are unassigned to sync up with generic numbers, don't use */ #undef __NR_syscalls #define __NR_syscalls 295 -- cgit v1.2.3 From 4b7d248b3a1de483ffe9d05c1debbf32a544164d Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 22 Jan 2019 17:06:39 -0500 Subject: audit: move loginuid and sessionid from CONFIG_AUDITSYSCALL to CONFIG_AUDIT loginuid and sessionid (and audit_log_session_info) should be part of CONFIG_AUDIT scope and not CONFIG_AUDITSYSCALL since it is used in CONFIG_CHANGE, ANOM_LINK, FEATURE_CHANGE (and INTEGRITY_RULE), none of which are otherwise dependent on AUDITSYSCALL. Please see github issue https://github.com/linux-audit/audit-kernel/issues/104 Signed-off-by: Richard Guy Briggs [PM: tweaked subject line for better grep'ing] Signed-off-by: Paul Moore --- fs/proc/base.c | 6 ++-- include/linux/audit.h | 42 +++++++++++++------------ include/linux/sched.h | 2 +- init/init_task.c | 2 +- kernel/audit.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++++++ kernel/auditsc.c | 84 -------------------------------------------------- 6 files changed, 113 insertions(+), 108 deletions(-) (limited to 'include') diff --git a/fs/proc/base.c b/fs/proc/base.c index 633a63462573..a23651ce6960 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1210,7 +1210,7 @@ static const struct file_operations proc_oom_score_adj_operations = { .llseek = default_llseek, }; -#ifdef CONFIG_AUDITSYSCALL +#ifdef CONFIG_AUDIT #define TMPBUFLEN 11 static ssize_t proc_loginuid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) @@ -3002,7 +3002,7 @@ static const struct pid_entry tgid_base_stuff[] = { ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), -#ifdef CONFIG_AUDITSYSCALL +#ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif @@ -3390,7 +3390,7 @@ static const struct pid_entry tid_base_stuff[] = { ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), -#ifdef CONFIG_AUDITSYSCALL +#ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif diff --git a/include/linux/audit.h b/include/linux/audit.h index a625c29a2ea2..ecb5d317d6a2 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -159,6 +159,18 @@ extern int audit_update_lsm_rules(void); extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); +extern int audit_set_loginuid(kuid_t loginuid); + +static inline kuid_t audit_get_loginuid(struct task_struct *tsk) +{ + return tsk->loginuid; +} + +static inline unsigned int audit_get_sessionid(struct task_struct *tsk) +{ + return tsk->sessionid; +} + extern u32 audit_enabled; #else /* CONFIG_AUDIT */ static inline __printf(4, 5) @@ -201,6 +213,17 @@ static inline int audit_log_task_context(struct audit_buffer *ab) } static inline void audit_log_task_info(struct audit_buffer *ab) { } + +static inline kuid_t audit_get_loginuid(struct task_struct *tsk) +{ + return INVALID_UID; +} + +static inline unsigned int audit_get_sessionid(struct task_struct *tsk) +{ + return AUDIT_SID_UNSET; +} + #define audit_enabled AUDIT_OFF #endif /* CONFIG_AUDIT */ @@ -323,17 +346,6 @@ static inline void audit_ptrace(struct task_struct *t) extern unsigned int audit_serial(void); extern int auditsc_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial); -extern int audit_set_loginuid(kuid_t loginuid); - -static inline kuid_t audit_get_loginuid(struct task_struct *tsk) -{ - return tsk->loginuid; -} - -static inline unsigned int audit_get_sessionid(struct task_struct *tsk) -{ - return tsk->sessionid; -} extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); @@ -519,14 +531,6 @@ static inline int auditsc_get_stamp(struct audit_context *ctx, { return 0; } -static inline kuid_t audit_get_loginuid(struct task_struct *tsk) -{ - return INVALID_UID; -} -static inline unsigned int audit_get_sessionid(struct task_struct *tsk) -{ - return AUDIT_SID_UNSET; -} static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, diff --git a/include/linux/sched.h b/include/linux/sched.h index 89541d248893..f9788bb122c5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -886,7 +886,7 @@ struct task_struct { struct callback_head *task_works; struct audit_context *audit_context; -#ifdef CONFIG_AUDITSYSCALL +#ifdef CONFIG_AUDIT kuid_t loginuid; unsigned int sessionid; #endif diff --git a/init/init_task.c b/init/init_task.c index 5aebe3be4d7c..39c3109acc1a 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -121,7 +121,7 @@ struct task_struct init_task .thread_pid = &init_struct_pid, .thread_group = LIST_HEAD_INIT(init_task.thread_group), .thread_node = LIST_HEAD_INIT(init_signals.thread_head), -#ifdef CONFIG_AUDITSYSCALL +#ifdef CONFIG_AUDIT .loginuid = INVALID_UID, .sessionid = AUDIT_SID_UNSET, #endif diff --git a/kernel/audit.c b/kernel/audit.c index c2a7662cc254..2a32f304223d 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -2335,6 +2335,91 @@ void audit_log_link_denied(const char *operation) audit_log_end(ab); } +/* global counter which is incremented every time something logs in */ +static atomic_t session_id = ATOMIC_INIT(0); + +static int audit_set_loginuid_perm(kuid_t loginuid) +{ + /* if we are unset, we don't need privs */ + if (!audit_loginuid_set(current)) + return 0; + /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/ + if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE)) + return -EPERM; + /* it is set, you need permission */ + if (!capable(CAP_AUDIT_CONTROL)) + return -EPERM; + /* reject if this is not an unset and we don't allow that */ + if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) + && uid_valid(loginuid)) + return -EPERM; + return 0; +} + +static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, + unsigned int oldsessionid, + unsigned int sessionid, int rc) +{ + struct audit_buffer *ab; + uid_t uid, oldloginuid, loginuid; + struct tty_struct *tty; + + if (!audit_enabled) + return; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); + if (!ab) + return; + + uid = from_kuid(&init_user_ns, task_uid(current)); + oldloginuid = from_kuid(&init_user_ns, koldloginuid); + loginuid = from_kuid(&init_user_ns, kloginuid), + tty = audit_get_tty(); + + audit_log_format(ab, "pid=%d uid=%u", task_tgid_nr(current), uid); + audit_log_task_context(ab); + audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d", + oldloginuid, loginuid, tty ? tty_name(tty) : "(none)", + oldsessionid, sessionid, !rc); + audit_put_tty(tty); + audit_log_end(ab); +} + +/** + * audit_set_loginuid - set current task's loginuid + * @loginuid: loginuid value + * + * Returns 0. + * + * Called (set) from fs/proc/base.c::proc_loginuid_write(). + */ +int audit_set_loginuid(kuid_t loginuid) +{ + unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET; + kuid_t oldloginuid; + int rc; + + oldloginuid = audit_get_loginuid(current); + oldsessionid = audit_get_sessionid(current); + + rc = audit_set_loginuid_perm(loginuid); + if (rc) + goto out; + + /* are we setting or clearing? */ + if (uid_valid(loginuid)) { + sessionid = (unsigned int)atomic_inc_return(&session_id); + if (unlikely(sessionid == AUDIT_SID_UNSET)) + sessionid = (unsigned int)atomic_inc_return(&session_id); + } + + current->sessionid = sessionid; + current->loginuid = loginuid; +out: + audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc); + return rc; +} + /** * audit_log_end - end one audit record * @ab: the audit_buffer diff --git a/kernel/auditsc.c b/kernel/auditsc.c index b585ceb2f7a2..572d247957fb 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1983,90 +1983,6 @@ int auditsc_get_stamp(struct audit_context *ctx, return 1; } -/* global counter which is incremented every time something logs in */ -static atomic_t session_id = ATOMIC_INIT(0); - -static int audit_set_loginuid_perm(kuid_t loginuid) -{ - /* if we are unset, we don't need privs */ - if (!audit_loginuid_set(current)) - return 0; - /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/ - if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE)) - return -EPERM; - /* it is set, you need permission */ - if (!capable(CAP_AUDIT_CONTROL)) - return -EPERM; - /* reject if this is not an unset and we don't allow that */ - if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid)) - return -EPERM; - return 0; -} - -static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, - unsigned int oldsessionid, unsigned int sessionid, - int rc) -{ - struct audit_buffer *ab; - uid_t uid, oldloginuid, loginuid; - struct tty_struct *tty; - - if (!audit_enabled) - return; - - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); - if (!ab) - return; - - uid = from_kuid(&init_user_ns, task_uid(current)); - oldloginuid = from_kuid(&init_user_ns, koldloginuid); - loginuid = from_kuid(&init_user_ns, kloginuid), - tty = audit_get_tty(); - - audit_log_format(ab, "pid=%d uid=%u", task_tgid_nr(current), uid); - audit_log_task_context(ab); - audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d", - oldloginuid, loginuid, tty ? tty_name(tty) : "(none)", - oldsessionid, sessionid, !rc); - audit_put_tty(tty); - audit_log_end(ab); -} - -/** - * audit_set_loginuid - set current task's audit_context loginuid - * @loginuid: loginuid value - * - * Returns 0. - * - * Called (set) from fs/proc/base.c::proc_loginuid_write(). - */ -int audit_set_loginuid(kuid_t loginuid) -{ - unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET; - kuid_t oldloginuid; - int rc; - - oldloginuid = audit_get_loginuid(current); - oldsessionid = audit_get_sessionid(current); - - rc = audit_set_loginuid_perm(loginuid); - if (rc) - goto out; - - /* are we setting or clearing? */ - if (uid_valid(loginuid)) { - sessionid = (unsigned int)atomic_inc_return(&session_id); - if (unlikely(sessionid == AUDIT_SID_UNSET)) - sessionid = (unsigned int)atomic_inc_return(&session_id); - } - - current->sessionid = sessionid; - current->loginuid = loginuid; -out: - audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc); - return rc; -} - /** * __audit_mq_open - record audit data for a POSIX MQ open * @oflag: open flag -- cgit v1.2.3 From 2fec30e245a3b46fef89c4cb1f74eefc5fbb29a6 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 23 Jan 2019 21:36:25 -0500 Subject: audit: add support for fcaps v3 V3 namespaced file capabilities were introduced in commit 8db6c34f1dbc ("Introduce v3 namespaced file capabilities") Add support for these by adding the "frootid" field to the existing fcaps fields in the NAME and BPRM_FCAPS records. Please see github issue https://github.com/linux-audit/audit-kernel/issues/103 Signed-off-by: Richard Guy Briggs Acked-by: Serge Hallyn [PM: comment tweak to fit an 80 char line width] Signed-off-by: Paul Moore --- include/linux/capability.h | 5 +++-- kernel/audit.c | 6 ++++-- kernel/audit.h | 1 + kernel/auditsc.c | 4 ++++ security/commoncap.c | 2 ++ 5 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/capability.h b/include/linux/capability.h index f640dcbc880c..b769330e9380 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -14,7 +14,7 @@ #define _LINUX_CAPABILITY_H #include - +#include #define _KERNEL_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_3 #define _KERNEL_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3 @@ -25,11 +25,12 @@ typedef struct kernel_cap_struct { __u32 cap[_KERNEL_CAPABILITY_U32S]; } kernel_cap_t; -/* exact same as vfs_cap_data but in cpu endian and always filled completely */ +/* same as vfs_ns_cap_data but in cpu endian and always filled completely */ struct cpu_vfs_cap_data { __u32 magic_etc; kernel_cap_t permitted; kernel_cap_t inheritable; + kuid_t rootid; }; #define _USER_CAP_HEADER_SIZE (sizeof(struct __user_cap_header_struct)) diff --git a/kernel/audit.c b/kernel/audit.c index 2a32f304223d..3f3f1888cac7 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -2084,8 +2084,9 @@ static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) { audit_log_cap(ab, "cap_fp", &name->fcap.permitted); audit_log_cap(ab, "cap_fi", &name->fcap.inheritable); - audit_log_format(ab, " cap_fe=%d cap_fver=%x", - name->fcap.fE, name->fcap_ver); + audit_log_format(ab, " cap_fe=%d cap_fver=%x cap_frootid=%d", + name->fcap.fE, name->fcap_ver, + from_kuid(&init_user_ns, name->fcap.rootid)); } static inline int audit_copy_fcaps(struct audit_names *name, @@ -2104,6 +2105,7 @@ static inline int audit_copy_fcaps(struct audit_names *name, name->fcap.permitted = caps.permitted; name->fcap.inheritable = caps.inheritable; name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); + name->fcap.rootid = caps.rootid; name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT; diff --git a/kernel/audit.h b/kernel/audit.h index 6ffb70575082..deefdbe61a47 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -69,6 +69,7 @@ struct audit_cap_data { kernel_cap_t effective; /* effective set of process */ }; kernel_cap_t ambient; + kuid_t rootid; }; /* When fs/namei.c:getname() is called, we store the pointer in name and bump diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 572d247957fb..c16beb25fd0a 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1358,6 +1358,9 @@ static void audit_log_exit(void) audit_log_cap(ab, "pi", &axs->new_pcap.inheritable); audit_log_cap(ab, "pe", &axs->new_pcap.effective); audit_log_cap(ab, "pa", &axs->new_pcap.ambient); + audit_log_format(ab, " frootid=%d", + from_kuid(&init_user_ns, + axs->fcap.rootid)); break; } } @@ -2271,6 +2274,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, ax->fcap.permitted = vcaps.permitted; ax->fcap.inheritable = vcaps.inheritable; ax->fcap.fE = !!(vcaps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); + ax->fcap.rootid = vcaps.rootid; ax->fcap_ver = (vcaps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT; ax->old_pcap.permitted = old->cap_permitted; diff --git a/security/commoncap.c b/security/commoncap.c index 232db019f051..c097f3568001 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -643,6 +643,8 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + cpu_caps->rootid = rootkuid; + return 0; } -- cgit v1.2.3 From 30e5c2c6bf285d93dee4c45f23da95d7d50b125a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 25 Jan 2019 10:53:23 -0800 Subject: net: Revert devlink health changes. This reverts the devlink health changes from 9/17/2019, Jiri wants things to be designed differently and it was agreed that the easiest way to do this is start from the beginning again. Commits reverted: cb5ccfbe73b389470e1dc11061bb185ef4bc9aec 880ee82f0313453ec5a6cb122866ac057263066b c7af343b4e33578b7de91786a3f639c8cfa0d97b ff253fedab961b22117a73ab808fcfa9e6852b50 6f9d56132eb6d2603d4273cfc65bed914ec47acb fcd852c69d776c0f46c8f79e8e431e5cc6ddc7b7 8a66704a13d9713593342e29b4f0c19762f5746b 12bd0dcefe88782ac1c9fff632958dd1b71d27e5 aba25279c10094c5c97d09c3491ca86d00b4ad5e ce019faa70f81555fa17ebc1d5a03651f2e7e15a b8c45a033acc607201588f7665ba84207e5149e0 And the follow-on build fix: o33a0efa4baecd689da9474ce0e8b673eb6931c60 Signed-off-by: David S. Miller --- Documentation/networking/devlink-health.txt | 86 -- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en.h | 18 +- .../net/ethernet/mellanox/mlx5/core/en/reporter.h | 15 - .../ethernet/mellanox/mlx5/core/en/reporter_tx.c | 356 ------- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 186 +++- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +- include/net/devlink.h | 144 --- include/trace/events/devlink.h | 62 -- include/uapi/linux/devlink.h | 25 - net/core/devlink.c | 1058 -------------------- 11 files changed, 169 insertions(+), 1785 deletions(-) delete mode 100644 Documentation/networking/devlink-health.txt delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c (limited to 'include') diff --git a/Documentation/networking/devlink-health.txt b/Documentation/networking/devlink-health.txt deleted file mode 100644 index 1db3fbea0831..000000000000 --- a/Documentation/networking/devlink-health.txt +++ /dev/null @@ -1,86 +0,0 @@ -The health mechanism is targeted for Real Time Alerting, in order to know when -something bad had happened to a PCI device -- Provide alert debug information -- Self healing -- If problem needs vendor support, provide a way to gather all needed debugging - information. - -The main idea is to unify and centralize driver health reports in the -generic devlink instance and allow the user to set different -attributes of the health reporting and recovery procedures. - -The devlink health reporter: -Device driver creates a "health reporter" per each error/health type. -Error/Health type can be a known/generic (eg pci error, fw error, rx/tx error) -or unknown (driver specific). -For each registered health reporter a driver can issue error/health reports -asynchronously. All health reports handling is done by devlink. -Device driver can provide specific callbacks for each "health reporter", e.g. - - Recovery procedures - - Diagnostics and object dump procedures - - OOB initial parameters -Different parts of the driver can register different types of health reporters -with different handlers. - -Once an error is reported, devlink health will do the following actions: - * A log is being send to the kernel trace events buffer - * Health status and statistics are being updated for the reporter instance - * Object dump is being taken and saved at the reporter instance (as long as - there is no other dump which is already stored) - * Auto recovery attempt is being done. Depends on: - - Auto-recovery configuration - - Grace period vs. time passed since last recover - -The user interface: -User can access/change each reporter's parameters and driver specific callbacks -via devlink, e.g per error type (per health reporter) - - Configure reporter's generic parameters (like: disable/enable auto recovery) - - Invoke recovery procedure - - Run diagnostics - - Object dump - -The devlink health interface (via netlink): -DEVLINK_CMD_HEALTH_REPORTER_GET - Retrieves status and configuration info per DEV and reporter. -DEVLINK_CMD_HEALTH_REPORTER_SET - Allows reporter-related configuration setting. -DEVLINK_CMD_HEALTH_REPORTER_RECOVER - Triggers a reporter's recovery procedure. -DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - Retrieves diagnostics data from a reporter on a device. -DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - Retrieves the last stored dump. Devlink health - saves a single dump. If an dump is not already stored by the devlink - for this reporter, devlink generates a new dump. - dump output is defined by the reporter. -DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - Clears the last saved dump file for the specified reporter. - - - netlink - +--------------------------+ - | | - | + | - | | | - +--------------------------+ - |request for ops - |(diagnose, - mlx5_core devlink |recover, - |dump) -+--------+ +--------------------------+ -| | | reporter| | -| | | +---------v----------+ | -| | ops execution | | | | -| <----------------------------------+ | | -| | | | | | -| | | + ^------------------+ | -| | | | request for ops | -| | | | (recover, dump) | -| | | | | -| | | +-+------------------+ | -| | health report | | health handler | | -| +-------------------------------> | | -| | | +--------------------+ | -| | health reporter create | | -| +----------------------------> | -+--------+ +--------------------------+ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 6bb2a860b15b..9de9abacf7f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -22,7 +22,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ # mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ - en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o + en_selftest.o en/port.o en/monitor_stats.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 27e276c9bf84..8fa8fdd30b85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -388,7 +388,10 @@ struct mlx5e_txqsq { struct mlx5e_channel *channel; int txq_ix; u32 rate_limit; - struct work_struct recover_work; + struct mlx5e_txqsq_recover { + struct work_struct recover_work; + u64 last_recover; + } recover; } ____cacheline_aligned_in_smp; struct mlx5e_dma_info { @@ -679,13 +682,6 @@ struct mlx5e_rss_params { u8 hfunc; }; -struct mlx5e_modify_sq_param { - int curr_state; - int next_state; - int rl_update; - int rl_index; -}; - struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; @@ -741,7 +737,6 @@ struct mlx5e_priv { #ifdef CONFIG_MLX5_EN_TLS struct mlx5e_tls *tls; #endif - struct devlink_health_reporter *tx_reporter; }; struct mlx5e_profile { @@ -871,11 +866,6 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); -int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, - struct mlx5e_modify_sq_param *p); -void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq); -void mlx5e_tx_disable_queue(struct netdev_queue *txq); - static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) { return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h deleted file mode 100644 index 2335c5b48820..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ -/* Copyright (c) 2018 Mellanox Technologies. */ - -#ifndef __MLX5E_EN_REPORTER_H -#define __MLX5E_EN_REPORTER_H - -#include -#include "en.h" - -int mlx5e_tx_reporter_create(struct mlx5e_priv *priv); -void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv); -void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq); -void mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq); - -#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c deleted file mode 100644 index d9675afbb924..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ /dev/null @@ -1,356 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ -/* Copyright (c) 2018 Mellanox Technologies. */ - -#include -#include "reporter.h" -#include "lib/eq.h" - -#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256 - -struct mlx5e_tx_err_ctx { - int (*recover)(struct mlx5e_txqsq *sq); - struct mlx5e_txqsq *sq; -}; - -static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) -{ - unsigned long exp_time = jiffies + msecs_to_jiffies(2000); - - while (time_before(jiffies, exp_time)) { - if (sq->cc == sq->pc) - return 0; - - msleep(20); - } - - netdev_err(sq->channel->netdev, - "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", - sq->sqn, sq->cc, sq->pc); - - return -ETIMEDOUT; -} - -static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) -{ - WARN_ONCE(sq->cc != sq->pc, - "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", - sq->sqn, sq->cc, sq->pc); - sq->cc = 0; - sq->dma_fifo_cc = 0; - sq->pc = 0; -} - -static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) -{ - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - struct mlx5e_modify_sq_param msp = {0}; - int err; - - msp.curr_state = curr_state; - msp.next_state = MLX5_SQC_STATE_RST; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); - return err; - } - - memset(&msp, 0, sizeof(msp)); - msp.curr_state = MLX5_SQC_STATE_RST; - msp.next_state = MLX5_SQC_STATE_RDY; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); - return err; - } - - return 0; -} - -static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq) -{ - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - u8 state; - int err; - - if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) - return 0; - - err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); - if (err) { - netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", - sq->sqn, err); - return err; - } - - if (state != MLX5_RQC_STATE_ERR) { - netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn); - return -EINVAL; - } - - mlx5e_tx_disable_queue(sq->txq); - - err = mlx5e_wait_for_sq_flush(sq); - if (err) - return err; - - /* At this point, no new packets will arrive from the stack as TXQ is - * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all - * pending WQEs. SQ can safely reset the SQ. - */ - - err = mlx5e_sq_to_ready(sq, state); - if (err) - return err; - - mlx5e_reset_txqsq_cc_pc(sq); - sq->stats->recover++; - mlx5e_activate_txqsq(sq); - - return 0; -} - -void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq) -{ - char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; - struct mlx5e_tx_err_ctx err_ctx = {0}; - - err_ctx.sq = sq; - err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover; - sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn); - - devlink_health_report(sq->channel->priv->tx_reporter, err_str, - &err_ctx); -} - -static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq) -{ - struct mlx5_eq_comp *eq = sq->cq.mcq.eq; - u32 eqe_count; - - netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", - eq->core.eqn, eq->core.cons_index, eq->core.irqn); - - eqe_count = mlx5_eq_poll_irq_disabled(eq); - if (!eqe_count) { - clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - return 1; - } - - netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n", - eqe_count, eq->core.eqn); - sq->channel->stats->eq_rearm++; - return 0; -} - -void mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq) -{ - struct mlx5e_tx_err_ctx err_ctx; - char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; - - err_ctx.sq = sq; - err_ctx.recover = mlx5e_tx_reporter_timeout_recover; - sprintf(err_str, - "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", - sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, - jiffies_to_usecs(jiffies - sq->txq->trans_start)); - devlink_health_report(sq->channel->priv->tx_reporter, err_str, - &err_ctx); -} - -/* state lock cannot be grabbed within this function. - * It can cause a dead lock or a read-after-free. - */ -int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx) -{ - return err_ctx->recover(err_ctx->sq); -} - -static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv) -{ - int err; - - mutex_lock(&priv->state_lock); - mlx5e_close_locked(priv->netdev); - err = mlx5e_open_locked(priv->netdev); - mutex_unlock(&priv->state_lock); - - return err; -} - -static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter, - void *context) -{ - struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); - struct mlx5e_tx_err_ctx *err_ctx = context; - - return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) : - mlx5e_tx_reporter_recover_all(priv); -} - -static int -mlx5e_tx_reporter_build_diagnose_output(struct devlink_health_buffer *buffer, - u32 sqn, u8 state, u8 stopped) -{ - int err, i; - int nest = 0; - char name[20]; - - err = devlink_health_buffer_nest_start(buffer, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT); - if (err) - goto buffer_error; - nest++; - - err = devlink_health_buffer_nest_start(buffer, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR); - if (err) - goto buffer_error; - nest++; - - sprintf(name, "SQ 0x%x", sqn); - err = devlink_health_buffer_put_object_name(buffer, name); - if (err) - goto buffer_error; - - err = devlink_health_buffer_nest_start(buffer, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE); - if (err) - goto buffer_error; - nest++; - - err = devlink_health_buffer_nest_start(buffer, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT); - if (err) - goto buffer_error; - nest++; - - err = devlink_health_buffer_nest_start(buffer, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR); - if (err) - goto buffer_error; - nest++; - - err = devlink_health_buffer_put_object_name(buffer, "HW state"); - if (err) - goto buffer_error; - - err = devlink_health_buffer_nest_start(buffer, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE); - if (err) - goto buffer_error; - nest++; - - err = devlink_health_buffer_put_value_u8(buffer, state); - if (err) - goto buffer_error; - - devlink_health_buffer_nest_end(buffer); /* DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE */ - nest--; - - devlink_health_buffer_nest_end(buffer); /* DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR */ - nest--; - - err = devlink_health_buffer_nest_start(buffer, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR); - if (err) - goto buffer_error; - nest++; - - err = devlink_health_buffer_put_object_name(buffer, "stopped"); - if (err) - goto buffer_error; - - err = devlink_health_buffer_nest_start(buffer, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE); - if (err) - goto buffer_error; - nest++; - - err = devlink_health_buffer_put_value_u8(buffer, stopped); - if (err) - goto buffer_error; - - for (i = 0; i < nest; i++) - devlink_health_buffer_nest_end(buffer); - - return 0; - -buffer_error: - for (i = 0; i < nest; i++) - devlink_health_buffer_nest_cancel(buffer); - return err; -} - -static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_health_buffer **buffers_array, - unsigned int buffer_size, - unsigned int num_buffers) -{ - struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); - unsigned int buff = 0; - int i = 0, err = 0; - - if (buffer_size < MLX5E_TX_REPORTER_PER_SQ_MAX_LEN) - return -ENOMEM; - - mutex_lock(&priv->state_lock); - - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - mutex_unlock(&priv->state_lock); - return 0; - } - - while (i < priv->channels.num * priv->channels.params.num_tc) { - struct mlx5e_txqsq *sq = priv->txq2sq[i]; - u8 state; - - err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); - if (err) - break; - - err = mlx5e_tx_reporter_build_diagnose_output(buffers_array[buff], - sq->sqn, state, - netif_xmit_stopped(sq->txq)); - if (err) { - if (++buff == num_buffers) - break; - } else { - i++; - } - } - - mutex_unlock(&priv->state_lock); - return err; -} - -static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { - .name = "TX", - .recover = mlx5e_tx_reporter_recover, - .diagnose_size = MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC * - MLX5E_TX_REPORTER_PER_SQ_MAX_LEN, - .diagnose = mlx5e_tx_reporter_diagnose, - .dump_size = 0, - .dump = NULL, -}; - -#define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500 -int mlx5e_tx_reporter_create(struct mlx5e_priv *priv) -{ - struct mlx5_core_dev *mdev = priv->mdev; - struct devlink *devlink = priv_to_devlink(mdev); - - priv->tx_reporter = - devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops, - MLX5_REPORTER_TX_GRACEFUL_PERIOD, - true, priv); - return PTR_ERR_OR_ZERO(priv->tx_reporter); -} - -void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv) -{ - devlink_health_reporter_destroy(priv->tx_reporter); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dee0c8f3d4e9..8cfd2ec7c0a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -51,7 +51,6 @@ #include "en/xdp.h" #include "lib/eq.h" #include "en/monitor_stats.h" -#include "en/reporter.h" struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; @@ -1161,7 +1160,7 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) return 0; } -static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work); +static void mlx5e_sq_recover(struct work_struct *work); static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, int txq_ix, struct mlx5e_params *params, @@ -1183,7 +1182,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; - INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); + INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); if (mlx5_accel_is_tls_device(c->priv->mdev)) @@ -1271,8 +1270,15 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev, return err; } -int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, - struct mlx5e_modify_sq_param *p) +struct mlx5e_modify_sq_param { + int curr_state; + int next_state; + bool rl_update; + int rl_index; +}; + +static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, + struct mlx5e_modify_sq_param *p) { void *in; void *sqc; @@ -1370,7 +1376,17 @@ err_free_txqsq: return err; } -void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) +static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) +{ + WARN_ONCE(sq->cc != sq->pc, + "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", + sq->sqn, sq->cc, sq->pc); + sq->cc = 0; + sq->dma_fifo_cc = 0; + sq->pc = 0; +} + +static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) { sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix); clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); @@ -1379,7 +1395,7 @@ void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) netif_tx_start_queue(sq->txq); } -void mlx5e_tx_disable_queue(struct netdev_queue *txq) +static inline void netif_tx_disable_queue(struct netdev_queue *txq) { __netif_tx_lock_bh(txq); netif_tx_stop_queue(txq); @@ -1395,7 +1411,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) /* prevent netif_tx_wake_queue */ napi_synchronize(&c->napi); - mlx5e_tx_disable_queue(sq->txq); + netif_tx_disable_queue(sq->txq); /* last doorbell out, godspeed .. */ if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) { @@ -1415,7 +1431,6 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) struct mlx5_rate_limit rl = {0}; cancel_work_sync(&sq->dim.work); - cancel_work_sync(&sq->recover_work); mlx5e_destroy_sq(mdev, sq->sqn); if (sq->rate_limit) { rl.rate = sq->rate_limit; @@ -1425,15 +1440,105 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) mlx5e_free_txqsq(sq); } -static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) +static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) +{ + unsigned long exp_time = jiffies + msecs_to_jiffies(2000); + + while (time_before(jiffies, exp_time)) { + if (sq->cc == sq->pc) + return 0; + + msleep(20); + } + + netdev_err(sq->channel->netdev, + "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", + sq->sqn, sq->cc, sq->pc); + + return -ETIMEDOUT; +} + +static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) { - struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq, - recover_work); + struct mlx5_core_dev *mdev = sq->channel->mdev; + struct net_device *dev = sq->channel->netdev; + struct mlx5e_modify_sq_param msp = {0}; + int err; - if (!sq->channel->priv->tx_reporter) + msp.curr_state = curr_state; + msp.next_state = MLX5_SQC_STATE_RST; + + err = mlx5e_modify_sq(mdev, sq->sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); + return err; + } + + memset(&msp, 0, sizeof(msp)); + msp.curr_state = MLX5_SQC_STATE_RST; + msp.next_state = MLX5_SQC_STATE_RDY; + + err = mlx5e_modify_sq(mdev, sq->sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); + return err; + } + + return 0; +} + +static void mlx5e_sq_recover(struct work_struct *work) +{ + struct mlx5e_txqsq_recover *recover = + container_of(work, struct mlx5e_txqsq_recover, + recover_work); + struct mlx5e_txqsq *sq = container_of(recover, struct mlx5e_txqsq, + recover); + struct mlx5_core_dev *mdev = sq->channel->mdev; + struct net_device *dev = sq->channel->netdev; + u8 state; + int err; + + err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); + if (err) { + netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", + sq->sqn, err); + return; + } + + if (state != MLX5_RQC_STATE_ERR) { + netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn); + return; + } + + netif_tx_disable_queue(sq->txq); + + if (mlx5e_wait_for_sq_flush(sq)) return; - mlx5e_tx_reporter_err_cqe(sq); + /* If the interval between two consecutive recovers per SQ is too + * short, don't recover to avoid infinite loop of ERR_CQE -> recover. + * If we reached this state, there is probably a bug that needs to be + * fixed. let's keep the queue close and let tx timeout cleanup. + */ + if (jiffies_to_msecs(jiffies - recover->last_recover) < + MLX5E_SQ_RECOVER_MIN_INTERVAL) { + netdev_err(dev, "Recover SQ 0x%x canceled, too many error CQEs\n", + sq->sqn); + return; + } + + /* At this point, no new packets will arrive from the stack as TXQ is + * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all + * pending WQEs. SQ can safely reset the SQ. + */ + if (mlx5e_sq_to_ready(sq, state)) + return; + + mlx5e_reset_txqsq_cc_pc(sq); + sq->stats->recover++; + recover->last_recover = jiffies; + mlx5e_activate_txqsq(sq); } static int mlx5e_open_icosq(struct mlx5e_channel *c, @@ -3102,7 +3207,6 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) { int tc; - mlx5e_tx_reporter_destroy(priv); for (tc = 0; tc < priv->profile->max_tc; tc++) mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); } @@ -4074,14 +4178,31 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb, return features; } +static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev, + struct mlx5e_txqsq *sq) +{ + struct mlx5_eq_comp *eq = sq->cq.mcq.eq; + u32 eqe_count; + + netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", + eq->core.eqn, eq->core.cons_index, eq->core.irqn); + + eqe_count = mlx5_eq_poll_irq_disabled(eq); + if (!eqe_count) + return false; + + netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn); + sq->channel->stats->eq_rearm++; + return true; +} + static void mlx5e_tx_timeout_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, tx_timeout_work); - int i; - - if (!priv->tx_reporter) - return; + struct net_device *dev = priv->netdev; + bool reopen_channels = false; + int i, err; rtnl_lock(); mutex_lock(&priv->state_lock); @@ -4090,16 +4211,36 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) goto unlock; for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) { - struct netdev_queue *dev_queue = - netdev_get_tx_queue(priv->netdev, i); + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i); struct mlx5e_txqsq *sq = priv->txq2sq[i]; if (!netif_xmit_stopped(dev_queue)) continue; - mlx5e_tx_reporter_timeout(sq); + netdev_err(dev, + "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", + i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, + jiffies_to_usecs(jiffies - dev_queue->trans_start)); + + /* If we recover a lost interrupt, most likely TX timeout will + * be resolved, skip reopening channels + */ + if (!mlx5e_tx_timeout_eq_recover(dev, sq)) { + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); + reopen_channels = true; + } } + if (!reopen_channels) + goto unlock; + + mlx5e_close_locked(dev); + err = mlx5e_open_locked(dev); + if (err) + netdev_err(priv->netdev, + "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n", + err); + unlock: mutex_unlock(&priv->state_lock); rtnl_unlock(); @@ -4767,7 +4908,6 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_initialize(priv); #endif - mlx5e_tx_reporter_create(priv); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index a8e052a5ce36..598ad7e4d5c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -514,7 +514,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) mlx5e_dump_error_cqe(sq, (struct mlx5_err_cqe *)cqe); queue_work(cq->channel->priv->wq, - &sq->recover_work); + &sq->recover.recover_work); } stats->cqe_err++; } diff --git a/include/net/devlink.h b/include/net/devlink.h index a81a1b7a67d7..67f4293bc970 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -30,7 +30,6 @@ struct devlink { struct list_head param_list; struct list_head region_list; u32 snapshot_id; - struct list_head reporter_list; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; @@ -424,36 +423,6 @@ struct devlink_region; typedef void devlink_snapshot_data_dest_t(const void *data); -struct devlink_health_buffer; -struct devlink_health_reporter; - -/** - * struct devlink_health_reporter_ops - Reporter operations - * @name: reporter name - * dump_size: dump buffer size allocated by the devlink - * diagnose_size: diagnose buffer size allocated by the devlink - * recover: callback to recover from reported error - * if priv_ctx is NULL, run a full recover - * dump: callback to dump an object - * if priv_ctx is NULL, run a full dump - * diagnose: callback to diagnose the current status - */ - -struct devlink_health_reporter_ops { - char *name; - unsigned int dump_size; - unsigned int diagnose_size; - int (*recover)(struct devlink_health_reporter *reporter, - void *priv_ctx); - int (*dump)(struct devlink_health_reporter *reporter, - struct devlink_health_buffer **buffers_array, - unsigned int buffer_size, unsigned int num_buffers, - void *priv_ctx); - int (*diagnose)(struct devlink_health_reporter *reporter, - struct devlink_health_buffer **buffers_array, - unsigned int buffer_size, unsigned int num_buffers); -}; - struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -615,34 +584,6 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); -int devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, - int attrtype); -void devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer); -void devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer); -int devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, - char *name); -int devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, - u8 value); -int devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, - u32 value); -int devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, - u64 value); -int devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, - char *name); -int devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, - void *data, int len); -struct devlink_health_reporter * -devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, bool auto_recover, - void *priv); -void -devlink_health_reporter_destroy(struct devlink_health_reporter *reporter); - -void * -devlink_health_reporter_priv(struct devlink_health_reporter *reporter); -int devlink_health_report(struct devlink_health_reporter *reporter, - const char *msg, void *priv_ctx); #else static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, @@ -903,91 +844,6 @@ devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, return 0; } -static inline int -devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, - int attrtype) -{ - return 0; -} - -static inline void -devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer) -{ -} - -static inline void -devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer) -{ -} - -static inline int -devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, - char *name) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, - u8 value) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, - u32 value) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, - u64 value) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, - char *name) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, - void *data, int len) -{ - return 0; -} - -static inline struct devlink_health_reporter * -devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, bool auto_recover, - void *priv) -{ - return NULL; -} - -static inline void -devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) -{ -} - -static inline void * -devlink_health_reporter_priv(struct devlink_health_reporter *reporter) -{ - return NULL; -} - -static inline int -devlink_health_report(struct devlink_health_reporter *reporter, - const char *msg, void *priv_ctx) -{ - return 0; -} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 7e39d2fc7c75..44acfbca1266 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -46,65 +46,6 @@ TRACE_EVENT(devlink_hwmsg, (int) __entry->len, __get_dynamic_array(buf), __entry->len) ); -TRACE_EVENT(devlink_health_report, - TP_PROTO(const struct devlink *devlink, const char *reporter_name, - const char *msg), - - TP_ARGS(devlink, reporter_name, msg), - - TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) - __string(reporter_name, msg) - __string(msg, msg) - ), - - TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); - __assign_str(reporter_name, reporter_name); - __assign_str(msg, msg); - ), - - TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s", - __get_str(bus_name), __get_str(dev_name), - __get_str(driver_name), __get_str(reporter_name), - __get_str(msg)) -); - -TRACE_EVENT(devlink_health_recover_aborted, - TP_PROTO(const struct devlink *devlink, const char *reporter_name, - bool health_state, u64 time_since_last_recover), - - TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover), - - TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) - __string(reporter_name, reporter_name) - __field(bool, health_state) - __field(u64, time_since_last_recover) - ), - - TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); - __assign_str(reporter_name, reporter_name); - __entry->health_state = health_state; - __entry->time_since_last_recover = time_since_last_recover; - ), - - TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover = %llu recover aborted", - __get_str(bus_name), __get_str(dev_name), - __get_str(driver_name), __get_str(reporter_name), - __entry->health_state, - __entry->time_since_last_recover) -); - #endif /* _TRACE_DEVLINK_H */ /* This part must be outside protection */ @@ -123,9 +64,6 @@ static inline void trace_devlink_hwmsg(const struct devlink *devlink, { } -static inline void trace_devlink_health(const char *msg) -{ -} #endif /* _TRACE_DEVLINK_H */ #endif diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6b26bb2ce4dc..6e52d3660654 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -89,13 +89,6 @@ enum devlink_command { DEVLINK_CMD_REGION_DEL, DEVLINK_CMD_REGION_READ, - DEVLINK_CMD_HEALTH_REPORTER_GET, - DEVLINK_CMD_HEALTH_REPORTER_SET, - DEVLINK_CMD_HEALTH_REPORTER_RECOVER, - DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, - DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, - DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, - /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -292,24 +285,6 @@ enum devlink_attr { DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */ DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT, /* nested */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR, /* nested */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME, /* string */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE, /* nested */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY, /* nested */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, /* u8 */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, /* dynamic */ - - DEVLINK_ATTR_HEALTH_REPORTER, /* nested */ - DEVLINK_ATTR_HEALTH_REPORTER_NAME, /* string */ - DEVLINK_ATTR_HEALTH_REPORTER_STATE, /* u8 */ - DEVLINK_ATTR_HEALTH_REPORTER_ERR, /* u64 */ - DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, /* u64 */ - DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL, /* u8 */ - DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, /* u64 */ - DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, /* u64 */ - DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, /* u8 */ - /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 24f266468ca5..abb0da9d7b4b 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3597,1015 +3597,6 @@ out: return 0; } -#define DEVLINK_HEALTH_BUFFER_SIZE (4096 - GENL_HDRLEN) -#define DEVLINK_HEALTH_BUFFER_DATA_SIZE (DEVLINK_HEALTH_BUFFER_SIZE / 2) -#define DEVLINK_HEALTH_SIZE_TO_BUFFERS(size) DIV_ROUND_UP_ULL(size, DEVLINK_HEALTH_BUFFER_DATA_SIZE) -#define DEVLINK_HEALTH_BUFFER_MAX_CHUNK 1024 - -struct devlink_health_buffer { - void *data; - u64 offset; - u64 bytes_left; - u64 bytes_left_metadata; - u64 max_nested_depth; - u64 curr_nest; -}; - -struct devlink_health_buffer_desc { - int attrtype; - u16 len; - u8 nla_type; - u8 nest_end; - int value[0]; -}; - -static void -devlink_health_buffers_reset(struct devlink_health_buffer **buffers_list, - u64 num_of_buffers) -{ - u64 i; - - for (i = 0; i < num_of_buffers; i++) { - memset(buffers_list[i]->data, 0, DEVLINK_HEALTH_BUFFER_SIZE); - buffers_list[i]->offset = 0; - buffers_list[i]->bytes_left = DEVLINK_HEALTH_BUFFER_DATA_SIZE; - buffers_list[i]->bytes_left_metadata = - DEVLINK_HEALTH_BUFFER_DATA_SIZE; - buffers_list[i]->max_nested_depth = 0; - buffers_list[i]->curr_nest = 0; - } -} - -static void -devlink_health_buffers_destroy(struct devlink_health_buffer **buffers_list, - u64 size); - -static struct devlink_health_buffer ** -devlink_health_buffers_create(u64 size) -{ - struct devlink_health_buffer **buffers_list; - u64 num_of_buffers = DEVLINK_HEALTH_SIZE_TO_BUFFERS(size); - u64 i; - - buffers_list = kcalloc(num_of_buffers, - sizeof(struct devlink_health_buffer *), - GFP_KERNEL); - if (!buffers_list) - return NULL; - - for (i = 0; i < num_of_buffers; i++) { - struct devlink_health_buffer *buffer; - void *data; - - buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); - data = kzalloc(DEVLINK_HEALTH_BUFFER_SIZE, GFP_KERNEL); - if (!buffer || !data) { - kfree(buffer); - kfree(data); - goto buffers_cleanup; - } - buffers_list[i] = buffer; - buffer->data = data; - } - devlink_health_buffers_reset(buffers_list, num_of_buffers); - - return buffers_list; - -buffers_cleanup: - devlink_health_buffers_destroy(buffers_list, --i); - kfree(buffers_list); - return NULL; -} - -static void -devlink_health_buffers_destroy(struct devlink_health_buffer **buffers_list, - u64 num_of_buffers) -{ - u64 i; - - for (i = 0; i < num_of_buffers; i++) { - kfree(buffers_list[i]->data); - kfree(buffers_list[i]); - } -} - -void -devlink_health_buffer_offset_inc(struct devlink_health_buffer *buffer, - int len) -{ - buffer->offset += len; -} - -/* In order to store a nest, need two descriptors, for start and end */ -#define DEVLINK_HEALTH_BUFFER_NEST_SIZE (sizeof(struct devlink_health_buffer_desc) * 2) - -int devlink_health_buffer_verify_len(struct devlink_health_buffer *buffer, - int len, int metadata_len) -{ - if (len > DEVLINK_HEALTH_BUFFER_DATA_SIZE) - return -EINVAL; - - if (buffer->bytes_left < len || - buffer->bytes_left_metadata < metadata_len) - return -ENOMEM; - - return 0; -} - -static struct devlink_health_buffer_desc * -devlink_health_buffer_get_desc_from_offset(struct devlink_health_buffer *buffer) -{ - return buffer->data + buffer->offset; -} - -int -devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, - int attrtype) -{ - struct devlink_health_buffer_desc *desc; - int err; - - err = devlink_health_buffer_verify_len(buffer, 0, - DEVLINK_HEALTH_BUFFER_NEST_SIZE); - if (err) - return err; - - if (attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT && - attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR && - attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE && - attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY) - return -EINVAL; - - desc = devlink_health_buffer_get_desc_from_offset(buffer); - - desc->attrtype = attrtype; - buffer->bytes_left_metadata -= DEVLINK_HEALTH_BUFFER_NEST_SIZE; - devlink_health_buffer_offset_inc(buffer, sizeof(*desc)); - - buffer->curr_nest++; - buffer->max_nested_depth = max(buffer->max_nested_depth, - buffer->curr_nest); - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_health_buffer_nest_start); - -enum devlink_health_buffer_nest_end_cancel { - DEVLINK_HEALTH_BUFFER_NEST_END = 1, - DEVLINK_HEALTH_BUFFER_NEST_CANCEL, -}; - -static void -devlink_health_buffer_nest_end_cancel(struct devlink_health_buffer *buffer, - enum devlink_health_buffer_nest_end_cancel nest) -{ - struct devlink_health_buffer_desc *desc; - - WARN_ON(!buffer->curr_nest); - buffer->curr_nest--; - - desc = devlink_health_buffer_get_desc_from_offset(buffer); - desc->nest_end = nest; - devlink_health_buffer_offset_inc(buffer, sizeof(*desc)); -} - -void devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer) -{ - devlink_health_buffer_nest_end_cancel(buffer, - DEVLINK_HEALTH_BUFFER_NEST_END); -} -EXPORT_SYMBOL_GPL(devlink_health_buffer_nest_end); - -void devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer) -{ - devlink_health_buffer_nest_end_cancel(buffer, - DEVLINK_HEALTH_BUFFER_NEST_CANCEL); -} -EXPORT_SYMBOL_GPL(devlink_health_buffer_nest_cancel); - -int -devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, - char *name) -{ - struct devlink_health_buffer_desc *desc; - int err; - - err = devlink_health_buffer_verify_len(buffer, strlen(name) + 1, - sizeof(*desc)); - if (err) - return err; - - desc = devlink_health_buffer_get_desc_from_offset(buffer); - desc->attrtype = DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME; - desc->nla_type = NLA_NUL_STRING; - desc->len = strlen(name) + 1; - memcpy(&desc->value, name, desc->len); - devlink_health_buffer_offset_inc(buffer, sizeof(*desc) + desc->len); - - buffer->bytes_left_metadata -= sizeof(*desc); - buffer->bytes_left -= (strlen(name) + 1); - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_health_buffer_put_object_name); - -static int -devlink_health_buffer_put_value(struct devlink_health_buffer *buffer, - u8 nla_type, void *value, int len) -{ - struct devlink_health_buffer_desc *desc; - int err; - - err = devlink_health_buffer_verify_len(buffer, len, sizeof(*desc)); - if (err) - return err; - - desc = devlink_health_buffer_get_desc_from_offset(buffer); - desc->attrtype = DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA; - desc->nla_type = nla_type; - desc->len = len; - memcpy(&desc->value, value, len); - devlink_health_buffer_offset_inc(buffer, sizeof(*desc) + desc->len); - - buffer->bytes_left_metadata -= sizeof(*desc); - buffer->bytes_left -= len; - - return 0; -} - -int -devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, - u8 value) -{ - int err; - - err = devlink_health_buffer_put_value(buffer, NLA_U8, &value, - sizeof(value)); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_u8); - -int -devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, - u32 value) -{ - int err; - - err = devlink_health_buffer_put_value(buffer, NLA_U32, &value, - sizeof(value)); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_u32); - -int -devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, - u64 value) -{ - int err; - - err = devlink_health_buffer_put_value(buffer, NLA_U64, &value, - sizeof(value)); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_u64); - -int -devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, - char *name) -{ - int err; - - if (strlen(name) + 1 > DEVLINK_HEALTH_BUFFER_MAX_CHUNK) - return -EINVAL; - - err = devlink_health_buffer_put_value(buffer, NLA_NUL_STRING, name, - strlen(name) + 1); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_string); - -int -devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, - void *data, int len) -{ - int err; - - if (len > DEVLINK_HEALTH_BUFFER_MAX_CHUNK) - return -EINVAL; - - err = devlink_health_buffer_put_value(buffer, NLA_BINARY, data, len); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_data); - -static int -devlink_health_buffer_fill_data(struct sk_buff *skb, - struct devlink_health_buffer_desc *desc) -{ - int err = -EINVAL; - - switch (desc->nla_type) { - case NLA_U8: - err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, - *(u8 *)desc->value); - break; - case NLA_U32: - err = nla_put_u32(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, - *(u32 *)desc->value); - break; - case NLA_U64: - err = nla_put_u64_64bit(skb, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, - *(u64 *)desc->value, DEVLINK_ATTR_PAD); - break; - case NLA_NUL_STRING: - err = nla_put_string(skb, - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, - (char *)&desc->value); - break; - case NLA_BINARY: - err = nla_put(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, - desc->len, (void *)&desc->value); - break; - } - - return err; -} - -static int -devlink_health_buffer_fill_type(struct sk_buff *skb, - struct devlink_health_buffer_desc *desc) -{ - int err = -EINVAL; - - switch (desc->nla_type) { - case NLA_U8: - err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, - NLA_U8); - break; - case NLA_U32: - err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, - NLA_U32); - break; - case NLA_U64: - err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, - NLA_U64); - break; - case NLA_NUL_STRING: - err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, - NLA_NUL_STRING); - break; - case NLA_BINARY: - err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, - NLA_BINARY); - break; - } - - return err; -} - -static inline struct devlink_health_buffer_desc * -devlink_health_buffer_get_next_desc(struct devlink_health_buffer_desc *desc) -{ - return (void *)&desc->value + desc->len; -} - -static int -devlink_health_buffer_prepare_skb(struct sk_buff *skb, - struct devlink_health_buffer *buffer) -{ - struct devlink_health_buffer_desc *last_desc, *desc; - struct nlattr **buffer_nlattr; - int err; - int i = 0; - - buffer_nlattr = kcalloc(buffer->max_nested_depth, - sizeof(*buffer_nlattr), GFP_KERNEL); - if (!buffer_nlattr) - return -EINVAL; - - last_desc = devlink_health_buffer_get_desc_from_offset(buffer); - desc = buffer->data; - while (desc != last_desc) { - switch (desc->attrtype) { - case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT: - case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR: - case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE: - case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY: - buffer_nlattr[i] = nla_nest_start(skb, desc->attrtype); - if (!buffer_nlattr[i]) - goto nla_put_failure; - i++; - break; - case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA: - err = devlink_health_buffer_fill_data(skb, desc); - if (err) - goto nla_put_failure; - err = devlink_health_buffer_fill_type(skb, desc); - if (err) - goto nla_put_failure; - break; - case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME: - err = nla_put_string(skb, desc->attrtype, - (char *)&desc->value); - if (err) - goto nla_put_failure; - break; - default: - WARN_ON(!desc->nest_end); - WARN_ON(i <= 0); - if (desc->nest_end == DEVLINK_HEALTH_BUFFER_NEST_END) - nla_nest_end(skb, buffer_nlattr[--i]); - else - nla_nest_cancel(skb, buffer_nlattr[--i]); - break; - } - desc = devlink_health_buffer_get_next_desc(desc); - } - - return 0; - -nla_put_failure: - kfree(buffer_nlattr); - return err; -} - -static int -devlink_health_buffer_snd(struct genl_info *info, - enum devlink_command cmd, int flags, - struct devlink_health_buffer **buffers_array, - u64 num_of_buffers) -{ - struct sk_buff *skb; - struct nlmsghdr *nlh; - void *hdr; - int err; - u64 i; - - for (i = 0; i < num_of_buffers; i++) { - /* Skip buffer if driver did not fill it up with any data */ - if (!buffers_array[i]->offset) - continue; - - skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - return -ENOMEM; - - hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, - &devlink_nl_family, NLM_F_MULTI, cmd); - if (!hdr) - goto nla_put_failure; - - err = devlink_health_buffer_prepare_skb(skb, buffers_array[i]); - if (err) - goto nla_put_failure; - - genlmsg_end(skb, hdr); - err = genlmsg_reply(skb, info); - if (err) - return err; - } - - skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - return -ENOMEM; - nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, - NLMSG_DONE, 0, flags | NLM_F_MULTI); - if (!nlh) - goto nla_put_failure; - - err = genlmsg_reply(skb, info); - if (err) - return err; - - return 0; - -nla_put_failure: - err = -EIO; - nlmsg_free(skb); - return err; -} - -struct devlink_health_reporter { - struct list_head list; - struct devlink_health_buffer **dump_buffers_array; - struct mutex dump_lock; /* lock parallel read/write from dump buffers */ - struct devlink_health_buffer **diagnose_buffers_array; - struct mutex diagnose_lock; /* lock parallel read/write from diagnose buffers */ - void *priv; - const struct devlink_health_reporter_ops *ops; - struct devlink *devlink; - u64 graceful_period; - bool auto_recover; - u8 health_state; - u8 dump_avail; - u64 dump_ts; - u64 error_count; - u64 recovery_count; - u64 last_recovery_ts; -}; - -enum devlink_health_reporter_state { - DEVLINK_HEALTH_REPORTER_STATE_HEALTHY, - DEVLINK_HEALTH_REPORTER_STATE_ERROR, -}; - -void * -devlink_health_reporter_priv(struct devlink_health_reporter *reporter) -{ - return reporter->priv; -} -EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); - -static struct devlink_health_reporter * -devlink_health_reporter_find_by_name(struct devlink *devlink, - const char *reporter_name) -{ - struct devlink_health_reporter *reporter; - - list_for_each_entry(reporter, &devlink->reporter_list, list) - if (!strcmp(reporter->ops->name, reporter_name)) - return reporter; - return NULL; -} - -/** - * devlink_health_reporter_create - create devlink health reporter - * - * @devlink: devlink - * @ops: ops - * @graceful_period: to avoid recovery loops, in msecs - * @auto_recover: auto recover when error occurs - * @priv: priv - */ -struct devlink_health_reporter * -devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, bool auto_recover, - void *priv) -{ - struct devlink_health_reporter *reporter; - - mutex_lock(&devlink->lock); - if (devlink_health_reporter_find_by_name(devlink, ops->name)) { - reporter = ERR_PTR(-EEXIST); - goto unlock; - } - - if (WARN_ON(ops->dump && !ops->dump_size) || - WARN_ON(ops->diagnose && !ops->diagnose_size) || - WARN_ON(auto_recover && !ops->recover) || - WARN_ON(graceful_period && !ops->recover)) { - reporter = ERR_PTR(-EINVAL); - goto unlock; - } - - reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); - if (!reporter) { - reporter = ERR_PTR(-ENOMEM); - goto unlock; - } - - if (ops->dump) { - reporter->dump_buffers_array = - devlink_health_buffers_create(ops->dump_size); - if (!reporter->dump_buffers_array) { - kfree(reporter); - reporter = ERR_PTR(-ENOMEM); - goto unlock; - } - } - - if (ops->diagnose) { - reporter->diagnose_buffers_array = - devlink_health_buffers_create(ops->diagnose_size); - if (!reporter->diagnose_buffers_array) { - devlink_health_buffers_destroy(reporter->dump_buffers_array, - DEVLINK_HEALTH_SIZE_TO_BUFFERS(ops->dump_size)); - kfree(reporter); - reporter = ERR_PTR(-ENOMEM); - goto unlock; - } - } - - list_add_tail(&reporter->list, &devlink->reporter_list); - mutex_init(&reporter->dump_lock); - mutex_init(&reporter->diagnose_lock); - - reporter->priv = priv; - reporter->ops = ops; - reporter->devlink = devlink; - reporter->graceful_period = graceful_period; - reporter->auto_recover = auto_recover; -unlock: - mutex_unlock(&devlink->lock); - return reporter; -} -EXPORT_SYMBOL_GPL(devlink_health_reporter_create); - -/** - * devlink_health_reporter_destroy - destroy devlink health reporter - * - * @reporter: devlink health reporter to destroy - */ -void -devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) -{ - mutex_lock(&reporter->devlink->lock); - list_del(&reporter->list); - devlink_health_buffers_destroy(reporter->dump_buffers_array, - DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size)); - devlink_health_buffers_destroy(reporter->diagnose_buffers_array, - DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->diagnose_size)); - kfree(reporter); - mutex_unlock(&reporter->devlink->lock); -} -EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); - -static int -devlink_health_reporter_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) -{ - int err; - - if (!reporter->ops->recover) - return -EOPNOTSUPP; - - err = reporter->ops->recover(reporter, priv_ctx); - if (err) - return err; - - reporter->recovery_count++; - reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; - reporter->last_recovery_ts = jiffies; - - return 0; -} - -static int devlink_health_do_dump(struct devlink_health_reporter *reporter, - void *priv_ctx) -{ - int err; - - if (!reporter->ops->dump) - return 0; - - if (reporter->dump_avail) - return 0; - - devlink_health_buffers_reset(reporter->dump_buffers_array, - DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size)); - err = reporter->ops->dump(reporter, reporter->dump_buffers_array, - DEVLINK_HEALTH_BUFFER_SIZE, - DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size), - priv_ctx); - if (!err) { - reporter->dump_avail = true; - reporter->dump_ts = jiffies; - } - - return err; -} - -int devlink_health_report(struct devlink_health_reporter *reporter, - const char *msg, void *priv_ctx) -{ - struct devlink *devlink = reporter->devlink; - int err = 0; - - /* write a log message of the current error */ - WARN_ON(!msg); - trace_devlink_health_report(devlink, reporter->ops->name, msg); - reporter->error_count++; - - /* abort if the previous error wasn't recovered */ - if (reporter->auto_recover && - (reporter->health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || - jiffies - reporter->last_recovery_ts < - msecs_to_jiffies(reporter->graceful_period))) { - trace_devlink_health_recover_aborted(devlink, - reporter->ops->name, - reporter->health_state, - jiffies - - reporter->last_recovery_ts); - return -ECANCELED; - } - - reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; - - mutex_lock(&reporter->dump_lock); - /* store current dump of current error, for later analysis */ - devlink_health_do_dump(reporter, priv_ctx); - mutex_unlock(&reporter->dump_lock); - - if (reporter->auto_recover) - err = devlink_health_reporter_recover(reporter, priv_ctx); - - return err; -} -EXPORT_SYMBOL_GPL(devlink_health_report); - -static struct devlink_health_reporter * -devlink_health_reporter_get_from_info(struct devlink *devlink, - struct genl_info *info) -{ - char *reporter_name; - - if (!info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]) - return NULL; - - reporter_name = - nla_data(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); - return devlink_health_reporter_find_by_name(devlink, reporter_name); -} - -static int -devlink_nl_health_reporter_fill(struct sk_buff *msg, - struct devlink *devlink, - struct devlink_health_reporter *reporter, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - struct nlattr *reporter_attr; - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto genlmsg_cancel; - - reporter_attr = nla_nest_start(msg, DEVLINK_ATTR_HEALTH_REPORTER); - if (!reporter_attr) - goto genlmsg_cancel; - if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, - reporter->ops->name)) - goto reporter_nest_cancel; - if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, - reporter->health_state)) - goto reporter_nest_cancel; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR, - reporter->error_count, DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, - reporter->recovery_count, DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, - reporter->graceful_period, - DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, - reporter->auto_recover)) - goto reporter_nest_cancel; - if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL, - reporter->dump_avail)) - goto reporter_nest_cancel; - if (reporter->dump_avail && - nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, - jiffies_to_msecs(reporter->dump_ts), - DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - - nla_nest_end(msg, reporter_attr); - genlmsg_end(msg, hdr); - return 0; - -reporter_nest_cancel: - nla_nest_end(msg, reporter_attr); -genlmsg_cancel: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - struct sk_buff *msg; - int err; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_health_reporter_fill(msg, devlink, reporter, - DEVLINK_CMD_HEALTH_REPORTER_GET, - info->snd_portid, info->snd_seq, - 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink_health_reporter *reporter; - struct devlink *devlink; - int start = cb->args[0]; - int idx = 0; - int err; - - mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) - continue; - mutex_lock(&devlink->lock); - list_for_each_entry(reporter, &devlink->reporter_list, - list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_health_reporter_fill(msg, devlink, - reporter, - DEVLINK_CMD_HEALTH_REPORTER_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - mutex_unlock(&devlink->lock); - goto out; - } - idx++; - } - mutex_unlock(&devlink->lock); - } -out: - mutex_unlock(&devlink_mutex); - - cb->args[0] = idx; - return msg->len; -} - -static int -devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - if (!reporter->ops->recover && - (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || - info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) - return -EINVAL; - - if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) - reporter->graceful_period = - nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]); - - if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]) - reporter->auto_recover = - nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]); - - return 0; -} - -static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - return devlink_health_reporter_recover(reporter, NULL); -} - -static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - u64 num_of_buffers; - int err; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - if (!reporter->ops->diagnose) - return -EOPNOTSUPP; - - num_of_buffers = - DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->diagnose_size); - - mutex_lock(&reporter->diagnose_lock); - devlink_health_buffers_reset(reporter->diagnose_buffers_array, - num_of_buffers); - - err = reporter->ops->diagnose(reporter, - reporter->diagnose_buffers_array, - DEVLINK_HEALTH_BUFFER_SIZE, - num_of_buffers); - if (err) - goto out; - - err = devlink_health_buffer_snd(info, - DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, - 0, reporter->diagnose_buffers_array, - num_of_buffers); - if (err) - goto out; - - mutex_unlock(&reporter->diagnose_lock); - return 0; - -out: - mutex_unlock(&reporter->diagnose_lock); - return err; -} - -static void -devlink_health_dump_clear(struct devlink_health_reporter *reporter) -{ - reporter->dump_avail = false; - reporter->dump_ts = 0; - devlink_health_buffers_reset(reporter->dump_buffers_array, - DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size)); -} - -static int devlink_nl_cmd_health_reporter_dump_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - u64 num_of_buffers; - int err; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - if (!reporter->ops->dump) - return -EOPNOTSUPP; - - num_of_buffers = - DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size); - - mutex_lock(&reporter->dump_lock); - err = devlink_health_do_dump(reporter, NULL); - if (err) - goto out; - - err = devlink_health_buffer_snd(info, - DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, - 0, reporter->dump_buffers_array, - num_of_buffers); - -out: - mutex_unlock(&reporter->dump_lock); - return err; -} - -static int -devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - mutex_lock(&reporter->dump_lock); - devlink_health_dump_clear(reporter); - mutex_unlock(&reporter->dump_lock); - return 0; -} - static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -4631,9 +3622,6 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, - [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -4854,51 +3842,6 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, - .doit = devlink_nl_cmd_health_reporter_get_doit, - .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, - .policy = devlink_nl_policy, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, - .doit = devlink_nl_cmd_health_reporter_set_doit, - .policy = devlink_nl_policy, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, - .doit = devlink_nl_cmd_health_reporter_recover_doit, - .policy = devlink_nl_policy, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, - .doit = devlink_nl_cmd_health_reporter_diagnose_doit, - .policy = devlink_nl_policy, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, - .doit = devlink_nl_cmd_health_reporter_dump_get_doit, - .policy = devlink_nl_policy, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | - DEVLINK_NL_FLAG_NO_LOCK, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, - .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, - .policy = devlink_nl_policy, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | - DEVLINK_NL_FLAG_NO_LOCK, - }, }; static struct genl_family devlink_nl_family __ro_after_init = { @@ -4939,7 +3882,6 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD(&devlink->resource_list); INIT_LIST_HEAD(&devlink->param_list); INIT_LIST_HEAD(&devlink->region_list); - INIT_LIST_HEAD(&devlink->reporter_list); mutex_init(&devlink->lock); return devlink; } -- cgit v1.2.3 From 40852275a94afb3e836be9248399e036982d1a79 Mon Sep 17 00:00:00 2001 From: Micah Morton Date: Tue, 22 Jan 2019 14:42:09 -0800 Subject: LSM: add SafeSetID module that gates setid calls This change ensures that the set*uid family of syscalls in kernel/sys.c (setreuid, setuid, setresuid, setfsuid) all call ns_capable_common with the CAP_OPT_INSETID flag, so capability checks in the security_capable hook can know whether they are being called from within a set*uid syscall. This change is a no-op by itself, but is needed for the proposed SafeSetID LSM. Signed-off-by: Micah Morton Acked-by: Kees Cook Signed-off-by: James Morris --- include/linux/capability.h | 5 +++++ kernel/capability.c | 19 +++++++++++++++++++ kernel/sys.c | 10 +++++----- 3 files changed, 29 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/capability.h b/include/linux/capability.h index f640dcbc880c..c3f9a4d558a0 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -209,6 +209,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t, extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool ns_capable_noaudit(struct user_namespace *ns, int cap); +extern bool ns_capable_setid(struct user_namespace *ns, int cap); #else static inline bool has_capability(struct task_struct *t, int cap) { @@ -240,6 +241,10 @@ static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return true; } +static inline bool ns_capable_setid(struct user_namespace *ns, int cap) +{ + return true; +} #endif /* CONFIG_MULTIUSER */ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode); extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); diff --git a/kernel/capability.c b/kernel/capability.c index cfbbcb68e11e..1444f3954d75 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -415,6 +415,25 @@ bool ns_capable_noaudit(struct user_namespace *ns, int cap) } EXPORT_SYMBOL(ns_capable_noaudit); +/** + * ns_capable_setid - Determine if the current task has a superior capability + * in effect, while signalling that this check is being done from within a + * setid syscall. + * @ns: The usernamespace we want the capability in + * @cap: The capability to be tested for + * + * Return true if the current task has the given superior capability currently + * available for use, false if not. + * + * This sets PF_SUPERPRIV on the task if the capability is available on the + * assumption that it's about to be used. + */ +bool ns_capable_setid(struct user_namespace *ns, int cap) +{ + return ns_capable_common(ns, cap, CAP_OPT_INSETID); +} +EXPORT_SYMBOL(ns_capable_setid); + /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for diff --git a/kernel/sys.c b/kernel/sys.c index f7eb62eceb24..c5f875048aef 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -516,7 +516,7 @@ long __sys_setreuid(uid_t ruid, uid_t euid) new->uid = kruid; if (!uid_eq(old->uid, kruid) && !uid_eq(old->euid, kruid) && - !ns_capable(old->user_ns, CAP_SETUID)) + !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } @@ -525,7 +525,7 @@ long __sys_setreuid(uid_t ruid, uid_t euid) if (!uid_eq(old->uid, keuid) && !uid_eq(old->euid, keuid) && !uid_eq(old->suid, keuid) && - !ns_capable(old->user_ns, CAP_SETUID)) + !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } @@ -584,7 +584,7 @@ long __sys_setuid(uid_t uid) old = current_cred(); retval = -EPERM; - if (ns_capable(old->user_ns, CAP_SETUID)) { + if (ns_capable_setid(old->user_ns, CAP_SETUID)) { new->suid = new->uid = kuid; if (!uid_eq(kuid, old->uid)) { retval = set_user(new); @@ -646,7 +646,7 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) old = current_cred(); retval = -EPERM; - if (!ns_capable(old->user_ns, CAP_SETUID)) { + if (!ns_capable_setid(old->user_ns, CAP_SETUID)) { if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) goto error; @@ -814,7 +814,7 @@ long __sys_setfsuid(uid_t uid) if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || - ns_capable(old->user_ns, CAP_SETUID)) { + ns_capable_setid(old->user_ns, CAP_SETUID)) { if (!uid_eq(kuid, old->fsuid)) { new->fsuid = kuid; if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) -- cgit v1.2.3 From fe4943702c850fa07f963eaa6f1530d9d4c2da78 Mon Sep 17 00:00:00 2001 From: Srinivas Dasari Date: Wed, 23 Jan 2019 18:06:56 +0530 Subject: cfg80211: Authentication offload to user space in AP mode commit 40cbfa90218b ("cfg80211/nl80211: Optional authentication offload to userspace")' introduced authentication offload to user space by the host drivers in station mode. This commit extends the same for the AP mode too. Extend NL80211_ATTR_EXTERNAL_AUTH_SUPPORT to also claim the support of external authentication from the user space in AP mode. A new flag parameter is introduced in cfg80211_ap_settings to intend the same while "start ap". Host driver to use NL80211_CMD_FRAME interface to transmit and receive the authentication frames to / from the user space. Host driver to indicate the flag NL80211_RXMGMT_FLAG_EXTERNAL_AUTH while sending the authentication frame to the user space. This intends to the user space that the driver wishes it to process the authentication frame for certain protocols, though it had initially advertised the support for SME functionality. User space shall accordingly do the authentication and indicate its final status through the command NL80211_CMD_EXTERNAL_AUTH. Allow the command even if userspace doesn't include the attribute NL80211_ATTR_SSID for AP interface. Host driver shall continue with the association sequence and indicate the STA connection status through cfg80211_new_sta. To facilitate the host drivers in AP mode for matching the pmkid by the stations during the association, NL80211_CMD_EXTERNAL_AUTH is also enhanced to include the pmkid to drivers after the authentication. This pmkid can also be used in the STA mode to include in the association request. Also modify nl80211_external_auth to not mandate SSID in AP mode. Signed-off-by: Srinivas Dasari [remove useless nla_get_flag() usage] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 15 +++++++++++++++ include/uapi/linux/nl80211.h | 13 +++++++++---- net/wireless/nl80211.c | 25 ++++++++++++++++++------- 3 files changed, 42 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b61ac6e9de08..7033c90850b0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -835,6 +835,17 @@ struct cfg80211_bitrate_mask { } control[NUM_NL80211_BANDS]; }; +/** + * enum cfg80211_ap_settings_flags - AP settings flags + * + * Used by cfg80211_ap_settings + * + * @AP_SETTINGS_EXTERNAL_AUTH_SUPPORT: AP supports external authentication + */ +enum cfg80211_ap_settings_flags { + AP_SETTINGS_EXTERNAL_AUTH_SUPPORT = BIT(0), +}; + /** * struct cfg80211_ap_settings - AP configuration * @@ -865,6 +876,7 @@ struct cfg80211_bitrate_mask { * @he_cap: HE capabilities (or %NULL if HE isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT + * @flags: flags, as defined in enum cfg80211_ap_settings_flags */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -890,6 +902,7 @@ struct cfg80211_ap_settings { const struct ieee80211_vht_cap *vht_cap; const struct ieee80211_he_cap_elem *he_cap; bool ht_required, vht_required; + u32 flags; }; /** @@ -2831,6 +2844,7 @@ struct cfg80211_pmk_conf { * use %WLAN_STATUS_UNSPECIFIED_FAILURE if user space cannot give you * the real status code for failures. Used only for the authentication * response command interface (user space to driver). + * @pmkid: The identifier to refer a PMKSA. */ struct cfg80211_external_auth_params { enum nl80211_external_auth_action action; @@ -2838,6 +2852,7 @@ struct cfg80211_external_auth_params { struct cfg80211_ssid ssid; unsigned int key_mgmt_suite; u16 status; + const u8 *pmkid; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5f9d5cd458a1..8b0fdb9e133b 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2266,10 +2266,10 @@ enum nl80211_commands { * &enum nl80211_external_auth_action value). This is used with the * %NL80211_CMD_EXTERNAL_AUTH request event. * @NL80211_ATTR_EXTERNAL_AUTH_SUPPORT: Flag attribute indicating that the user - * space supports external authentication. This attribute shall be used - * only with %NL80211_CMD_CONNECT request. The driver may offload - * authentication processing to user space if this capability is indicated - * in NL80211_CMD_CONNECT requests from the user space. + * space supports external authentication. This attribute shall be used + * with %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP request. The driver + * may offload authentication processing to user space if this capability + * is indicated in the respective requests from the user space. * * @NL80211_ATTR_NSS: Station's New/updated RX_NSS value notified using this * u8 attribute. This is used with %NL80211_CMD_STA_OPMODE_CHANGED. @@ -5631,9 +5631,14 @@ enum nl80211_crit_proto_id { * Used by cfg80211_rx_mgmt() * * @NL80211_RXMGMT_FLAG_ANSWERED: frame was answered by device/driver. + * @NL80211_RXMGMT_FLAG_EXTERNAL_AUTH: Host driver intends to offload + * the authentication. Exclusively defined for host drivers that + * advertises the SME functionality but would like the userspace + * to handle certain authentication algorithms (e.g. SAE). */ enum nl80211_rxmgmt_flags { NL80211_RXMGMT_FLAG_ANSWERED = 1 << 0, + NL80211_RXMGMT_FLAG_EXTERNAL_AUTH = 1 << 1, }; /* diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index eb4437fa0539..dc96077afe5e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4550,6 +4550,9 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) nl80211_calculate_ap_params(¶ms); + if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) + params.flags |= AP_SETTINGS_EXTERNAL_AUTH_SUPPORT; + wdev_lock(wdev); err = rdev_start_ap(rdev, dev, ¶ms); if (!err) { @@ -13086,7 +13089,9 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->external_auth) return -EOPNOTSUPP; - if (!info->attrs[NL80211_ATTR_SSID]) + if (!info->attrs[NL80211_ATTR_SSID] && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EINVAL; if (!info->attrs[NL80211_ATTR_BSSID]) @@ -13097,18 +13102,24 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) memset(¶ms, 0, sizeof(params)); - params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid.ssid_len == 0 || - params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) - return -EINVAL; - memcpy(params.ssid.ssid, nla_data(info->attrs[NL80211_ATTR_SSID]), - params.ssid.ssid_len); + if (info->attrs[NL80211_ATTR_SSID]) { + params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + if (params.ssid.ssid_len == 0 || + params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) + return -EINVAL; + memcpy(params.ssid.ssid, + nla_data(info->attrs[NL80211_ATTR_SSID]), + params.ssid.ssid_len); + } memcpy(params.bssid, nla_data(info->attrs[NL80211_ATTR_BSSID]), ETH_ALEN); params.status = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); + if (info->attrs[NL80211_ATTR_PMKID]) + params.pmkid = nla_data(info->attrs[NL80211_ATTR_PMKID]); + return rdev_external_auth(rdev, dev, ¶ms); } -- cgit v1.2.3 From 6c900360e7c0df6a4846ac97d7b548d72cd801b0 Mon Sep 17 00:00:00 2001 From: Liangwei Dong Date: Fri, 18 Jan 2019 16:54:38 +0530 Subject: nl80211: Allow set/del pmksa operations for AP Host drivers may offload authentication to the user space through the commit ("cfg80211: Authentication offload to user space in AP mode"). This interface can be used to implement SAE by having the userspace do authentication/PMKID key derivation and driver handle the association. A step ahead, this interface can get further optimized if the PMKID is passed to the host driver and also have it respond to the association request by the STA on a valid PMKID. This commit enables the userspace to pass the PMKID to the host drivers through the set/del pmksa operations in AP mode. Set/Del pmksa is now restricted to STA/P2P client mode only and thus the drivers might not expect them in any other(AP) mode. This commit also introduces a feature flag NL80211_EXT_FEATURE_AP_PMKSA_CACHING (johannes: renamed) to maintain the backward compatibility of such an expectation by the host drivers. These operations are allowed in AP mode only when the drivers advertize the capability through this flag. Signed-off-by: Liangwei Dong Signed-off-by: Srinivas Dasari [rename flag to NL80211_EXT_FEATURE_AP_PMKSA_CACHING] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 ++++ net/wireless/nl80211.c | 5 ++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8b0fdb9e133b..dd4f86ee286e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5340,6 +5340,9 @@ enum nl80211_feature_flags { * fairness for transmitted packets and has enabled airtime fairness * scheduling. * + * @NL80211_EXT_FEATURE_AP_PMKSA_CACHING: Driver/device supports PMKSA caching + * (set/del PMKSA operations) in AP mode. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5380,6 +5383,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_CAN_REPLACE_PTK0, NL80211_EXT_FEATURE_ENABLE_FTM_RESPONDER, NL80211_EXT_FEATURE_AIRTIME_FAIRNESS, + NL80211_EXT_FEATURE_AP_PMKSA_CACHING, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index dc96077afe5e..af89e5c9fd0a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9899,7 +9899,10 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) } if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && + !(dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP && + wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AP_PMKSA_CACHING))) return -EOPNOTSUPP; switch (info->genlhdr->cmd) { -- cgit v1.2.3 From 6ba7d681aca22e53385bdb35b1d7662e61905760 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 9 Jan 2019 15:22:03 -0800 Subject: rcu: Remove wrapper definitions for obsolete RCU update functions None of synchronize_rcu_bh, synchronize_rcu_bh_expedited, call_rcu_bh, rcu_barrier_bh, synchronize_sched, synchronize_sched_expedited, call_rcu_sched, rcu_barrier_sched, get_state_synchronize_sched, and cond_synchronize_sched are actually used. This commit therefore removes their trivial wrapper-function definitions. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 53 ------------------------------------------------ 1 file changed, 53 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 4db8bcacc51a..0e39e0d2629e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -896,57 +896,4 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) return false; } - -/* Transitional pre-consolidation compatibility definitions. */ - -static inline void synchronize_rcu_bh(void) -{ - synchronize_rcu(); -} - -static inline void synchronize_rcu_bh_expedited(void) -{ - synchronize_rcu_expedited(); -} - -static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) -{ - call_rcu(head, func); -} - -static inline void rcu_barrier_bh(void) -{ - rcu_barrier(); -} - -static inline void synchronize_sched(void) -{ - synchronize_rcu(); -} - -static inline void synchronize_sched_expedited(void) -{ - synchronize_rcu_expedited(); -} - -static inline void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) -{ - call_rcu(head, func); -} - -static inline void rcu_barrier_sched(void) -{ - rcu_barrier(); -} - -static inline unsigned long get_state_synchronize_sched(void) -{ - return get_state_synchronize_rcu(); -} - -static inline void cond_synchronize_sched(unsigned long oldstate) -{ - cond_synchronize_rcu(oldstate); -} - #endif /* __LINUX_RCUPDATE_H */ -- cgit v1.2.3 From 2aa5503026ceaa8860697b93c9e5bbbcd025ba89 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 20 Nov 2018 08:29:35 -0800 Subject: rcu: Docbook for rcu_head_init() and rcu_head_after_call_rcu() This commit adds the missing asterisks required to make Sphinx pick up the current header comments for these two functions. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0e39e0d2629e..632113946757 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -859,7 +859,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /* Has the specified rcu_head structure been handed to call_rcu()? */ -/* +/** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * @@ -874,10 +874,10 @@ static inline void rcu_head_init(struct rcu_head *rhp) rhp->func = (rcu_callback_t)~0L; } -/* +/** * rcu_head_after_call_rcu - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. - * @func: The function passed to call_rcu() along with @rhp. + * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including -- cgit v1.2.3 From c98cac603f1ce7d00e2a802b5640bced3bc3c1f2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 21 Nov 2018 11:35:03 -0800 Subject: rcu: Rename rcu_check_callbacks() to rcu_sched_clock_irq() The name rcu_check_callbacks() arguably made sense back in the early 2000s when RCU was quite a bit simpler than it is today, but it has become quite misleading, especially with the advent of dyntick-idle and NO_HZ_FULL. The rcu_check_callbacks() function is RCU's hook into the scheduling-clock interrupt, and is now but one of many ways that callbacks get promoted to invocable state. This commit therefore changes the name to rcu_sched_clock_irq(), which is the same number of characters and clearly indicates this function's relation to the rest of the Linux kernel. In addition, for the sake of consistency, rcu_flavor_check_callbacks() is also renamed to rcu_flavor_sched_clock_irq(). While in the area, the header comments for both functions are reworked. Signed-off-by: Paul E. McKenney --- .../Memory-Ordering/Tree-RCU-Memory-Ordering.html | 4 ++-- .../TreeRCU-callback-invocation.svg | 2 +- .../RCU/Design/Memory-Ordering/TreeRCU-gp.svg | 4 ++-- .../RCU/Design/Memory-Ordering/TreeRCU-qs.svg | 2 +- include/linux/rcupdate.h | 2 +- kernel/rcu/tiny.c | 2 +- kernel/rcu/tree.c | 18 ++++++++-------- kernel/rcu/tree.h | 2 +- kernel/rcu/tree_plugin.h | 24 +++++++++------------- kernel/time/timer.c | 2 +- 10 files changed, 29 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html index e4d94fba6c89..a3acfd49255f 100644 --- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html +++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html @@ -485,7 +485,7 @@ section that the grace period must wait on. noted by rcu_node_context_switch() on the left. On the other hand, if the CPU takes a scheduler-clock interrupt while executing in usermode, a quiescent state will be noted by -rcu_check_callbacks() on the right. +rcu_sched_clock_irq() on the right. Either way, the passage through a quiescent state will be noted in a per-CPU variable. @@ -651,7 +651,7 @@ to end. These callbacks are identified by rcu_advance_cbs(), which is usually invoked by __note_gp_changes(). As shown in the diagram below, this invocation can be triggered by -the scheduling-clock interrupt (rcu_check_callbacks() on +the scheduling-clock interrupt (rcu_sched_clock_irq() on the left) or by idle entry (rcu_cleanup_after_idle() on the right, but only for kernels build with CONFIG_RCU_FAST_NO_HZ=y). diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-invocation.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-invocation.svg index 832408313d93..3fcf0c17cef2 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-invocation.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-invocation.svg @@ -349,7 +349,7 @@ font-weight="bold" font-size="192" id="text202-7-5" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_check_callbacks() + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_sched_clock_irq() rcu_check_callbacks() + xml:space="preserve">rcu_sched_clock_irq() rcu_check_callbacks() + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_sched_clock_irq() rcu_check_callbacks() + xml:space="preserve">rcu_sched_clock_irq() rcu_read_unlock_special.b.need_qs = false; } } @@ -778,13 +778,13 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) } /* - * Check for a quiescent state from the current CPU. When a task blocks, - * the task is recorded in the corresponding CPU's rcu_node structure, - * which is checked elsewhere. - * - * Caller must disable hard irqs. + * Check for a quiescent state from the current CPU, including voluntary + * context switches for Tasks RCU. When a task blocks, the task is + * recorded in the corresponding CPU's rcu_node structure, which is checked + * elsewhere, hence this function need only check for quiescent states + * related to the current CPU, not to those related to tasks. */ -static void rcu_flavor_check_callbacks(int user) +static void rcu_flavor_sched_clock_irq(int user) { struct task_struct *t = current; @@ -1030,14 +1030,10 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) } /* - * Check to see if this CPU is in a non-context-switch quiescent state - * (user mode or idle loop for rcu, non-softirq execution for rcu_bh). - * Also schedule RCU core processing. - * - * This function must be called from hardirq context. It is normally - * invoked from the scheduling-clock interrupt. + * Check to see if this CPU is in a non-context-switch quiescent state, + * namely user mode and idle loop. */ -static void rcu_flavor_check_callbacks(int user) +static void rcu_flavor_sched_clock_irq(int user) { if (user || rcu_is_cpu_rrupt_from_idle()) { diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 444156debfa0..6eb7cc4b6d52 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1632,7 +1632,7 @@ void update_process_times(int user_tick) /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); - rcu_check_callbacks(user_tick); + rcu_sched_clock_irq(user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_tick(); -- cgit v1.2.3 From 423a86a610cad121742ebe698ef98a3b4c87b5dd Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Wed, 12 Dec 2018 14:37:10 -0800 Subject: rcu: Add sparse check to rcu_assign_pointer() The rcu_assign_pointer() function currently doesn't do any sparse checking on the assigned-to pointer. So its possible that a pointer that is not __rcu annotated is assigned with rcu_assign_pointer without sparse complaints. Because rcu_dereference() already does such checking, this commit makes rcu_assign_pointer() to do the same. The extra error could be helpful in cases where an RCU pointer is assigned with rcu_assign_pointer() but not annotated with __rcu. This doesn't generate any code in the normal case because __CHECKER__ is defined only in the context of sparse. This commit also renames rcu_dereference_sparse() to rcu_check_parse() since the checking now happens not only during derereferencing but also during assignment. Test: Introduced an rcu_assign_pointer in code and checked the output of sparse with and without this change. The change correctly causes sparse to throw an error. Signed-off-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 6f8f047c4068..4a2cce4d4bd9 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -309,16 +309,16 @@ static inline void rcu_preempt_sleep_check(void) { } */ #ifdef __CHECKER__ -#define rcu_dereference_sparse(p, space) \ +#define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ -#define rcu_dereference_sparse(p, space) +#define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ - rcu_dereference_sparse(p, space); \ + rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_check(p, c, space) \ @@ -326,13 +326,13 @@ static inline void rcu_preempt_sleep_check(void) { } /* Dependency order vs. p above. */ \ typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ - rcu_dereference_sparse(p, space); \ + rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ - rcu_dereference_sparse(p, space); \ + rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define rcu_dereference_raw(p) \ @@ -382,6 +382,7 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_assign_pointer(p, v) \ ({ \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ + rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ @@ -785,7 +786,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) */ #define RCU_INIT_POINTER(p, v) \ do { \ - rcu_dereference_sparse(p, __rcu); \ + rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) -- cgit v1.2.3 From 728e3e6178aa5790066b642dd2ebc9e9bdacff1b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 8 Jan 2019 10:13:44 -0800 Subject: include/asm-generic: Remove spin_is_locked() comment The WARN_ON_SMP() comment header suggests using spin_is_locked() to check for locks being held. But these days we prefer lockdep_assert_held(), so this commit removes that suggestion. Signed-off-by: Paul E. McKenney Cc: Arnd Bergmann Cc: --- include/asm-generic/bug.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 20561a60db9c..0e9bd9c83870 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -211,9 +211,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint, /* * WARN_ON_SMP() is for cases that the warning is either * meaningless for !SMP or may even cause failures. - * This is usually used for cases that we have - * WARN_ON(!spin_is_locked(&lock)) checks, as spin_is_locked() - * returns 0 for uniprocessor settings. * It can also be used with values that are only defined * on SMP: * -- cgit v1.2.3 From c8ca1aa774b20f182733d1661f3b6aa3105338e7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 30 Nov 2018 10:06:46 -0800 Subject: srcu: Check for invalid idx argument in srcu_read_unlock() The current SRCU implementation has an idx argument of zero or one, and never anything else. This commit therefore adds a WARN_ON_ONCE() to complain if this restriction is violated. Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index c614375cd264..33cf83b9bda8 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -223,6 +223,7 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { + WARN_ON_ONCE(idx & ~0x1); rcu_lock_release(&(ssp)->dep_map); __srcu_read_unlock(ssp, idx); } -- cgit v1.2.3 From e81baf4cb19a9b428ba477fd0423f81672a58817 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 11 Dec 2018 12:12:38 +0100 Subject: srcu: Remove srcu_queue_delayed_work_on() srcu_queue_delayed_work_on() disables preemption (and therefore CPU hotplug in RCU's case) and then checks based on its own accounting if a CPU is online. If the CPU is online it uses queue_delayed_work_on() otherwise it fallbacks to queue_delayed_work(). The problem here is that queue_work() on -RT does not work with disabled preemption. queue_work_on() works also on an offlined CPU. queue_delayed_work_on() has the problem that it is possible to program a timer on an offlined CPU. This timer will fire once the CPU is online again. But until then, the timer remains programmed and nothing will happen. Add a local timer which will fire (as requested per delay) on the local CPU and then enqueue the work on the specific CPU. RCUtorture testing with SRCU-P for 24h showed no problems. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 3 ++- kernel/rcu/srcutree.c | 55 +++++++++++++++++++++--------------------------- kernel/rcu/tree.c | 4 ---- kernel/rcu/tree.h | 8 ------- 4 files changed, 26 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 6f292bd3e7db..0faa978c9880 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -45,7 +45,8 @@ struct srcu_data { unsigned long srcu_gp_seq_needed; /* Furthest future GP needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ bool srcu_cblist_invoking; /* Invoking these CBs? */ - struct delayed_work work; /* Context for CB invoking. */ + struct timer_list delay_work; /* Delay for CB invoking */ + struct work_struct work; /* Context for CB invoking. */ struct rcu_head srcu_barrier_head; /* For srcu_barrier() use. */ struct srcu_node *mynode; /* Leaf srcu_node. */ unsigned long grpmask; /* Mask for leaf srcu_node */ diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 3600d88d8956..7f041f2435df 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -58,6 +58,7 @@ static bool __read_mostly srcu_init_done; static void srcu_invoke_callbacks(struct work_struct *work); static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay); static void process_srcu(struct work_struct *work); +static void srcu_delay_timer(struct timer_list *t); /* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */ #define spin_lock_rcu_node(p) \ @@ -156,7 +157,8 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp, bool is_static) snp->grphi = cpu; } sdp->cpu = cpu; - INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks); + INIT_WORK(&sdp->work, srcu_invoke_callbacks); + timer_setup(&sdp->delay_work, srcu_delay_timer, 0); sdp->ssp = ssp; sdp->grpmask = 1 << (cpu - sdp->mynode->grplo); if (is_static) @@ -386,13 +388,19 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced) } else { flush_delayed_work(&ssp->work); } - for_each_possible_cpu(cpu) + for_each_possible_cpu(cpu) { + struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu); + if (quiesced) { - if (WARN_ON(delayed_work_pending(&per_cpu_ptr(ssp->sda, cpu)->work))) + if (WARN_ON(timer_pending(&sdp->delay_work))) + return; /* Just leak it! */ + if (WARN_ON(work_pending(&sdp->work))) return; /* Just leak it! */ } else { - flush_delayed_work(&per_cpu_ptr(ssp->sda, cpu)->work); + del_timer_sync(&sdp->delay_work); + flush_work(&sdp->work); } + } if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) || WARN_ON(srcu_readers_active(ssp))) { pr_info("%s: Active srcu_struct %p state: %d\n", @@ -463,39 +471,23 @@ static void srcu_gp_start(struct srcu_struct *ssp) WARN_ON_ONCE(state != SRCU_STATE_SCAN1); } -/* - * Track online CPUs to guide callback workqueue placement. - */ -DEFINE_PER_CPU(bool, srcu_online); -void srcu_online_cpu(unsigned int cpu) +static void srcu_delay_timer(struct timer_list *t) { - WRITE_ONCE(per_cpu(srcu_online, cpu), true); -} + struct srcu_data *sdp = container_of(t, struct srcu_data, delay_work); -void srcu_offline_cpu(unsigned int cpu) -{ - WRITE_ONCE(per_cpu(srcu_online, cpu), false); + queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work); } -/* - * Place the workqueue handler on the specified CPU if online, otherwise - * just run it whereever. This is useful for placing workqueue handlers - * that are to invoke the specified CPU's callbacks. - */ -static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq, - struct delayed_work *dwork, +static void srcu_queue_delayed_work_on(struct srcu_data *sdp, unsigned long delay) { - bool ret; + if (!delay) { + queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work); + return; + } - preempt_disable(); - if (READ_ONCE(per_cpu(srcu_online, cpu))) - ret = queue_delayed_work_on(cpu, wq, dwork, delay); - else - ret = queue_delayed_work(wq, dwork, delay); - preempt_enable(); - return ret; + timer_reduce(&sdp->delay_work, jiffies + delay); } /* @@ -504,7 +496,7 @@ static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq, */ static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay) { - srcu_queue_delayed_work_on(sdp->cpu, rcu_gp_wq, &sdp->work, delay); + srcu_queue_delayed_work_on(sdp, delay); } /* @@ -1186,7 +1178,8 @@ static void srcu_invoke_callbacks(struct work_struct *work) struct srcu_data *sdp; struct srcu_struct *ssp; - sdp = container_of(work, struct srcu_data, work.work); + sdp = container_of(work, struct srcu_data, work); + ssp = sdp->ssp; rcu_cblist_init(&ready_cbs); spin_lock_irq_rcu_node(sdp); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1c4add096078..127255795859 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3408,8 +3408,6 @@ int rcutree_online_cpu(unsigned int cpu) raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->ffmask |= rdp->grpmask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (IS_ENABLED(CONFIG_TREE_SRCU)) - srcu_online_cpu(cpu); if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) return 0; /* Too early in boot for scheduler work. */ sync_sched_exp_online_cleanup(cpu); @@ -3434,8 +3432,6 @@ int rcutree_offline_cpu(unsigned int cpu) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); rcutree_affinity_setting(cpu, cpu); - if (IS_ENABLED(CONFIG_TREE_SRCU)) - srcu_offline_cpu(cpu); return 0; } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 149557b7c39c..4bba017c703c 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -458,11 +458,3 @@ static void rcu_bind_gp_kthread(void); static bool rcu_nohz_full_cpu(void); static void rcu_dynticks_task_enter(void); static void rcu_dynticks_task_exit(void); - -#ifdef CONFIG_SRCU -void srcu_online_cpu(unsigned int cpu); -void srcu_offline_cpu(unsigned int cpu); -#else /* #ifdef CONFIG_SRCU */ -void srcu_online_cpu(unsigned int cpu) { } -void srcu_offline_cpu(unsigned int cpu) { } -#endif /* #else #ifdef CONFIG_SRCU */ -- cgit v1.2.3 From 3a6cb58f159e64241b2af9374acad41a70939349 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 10 Dec 2018 09:44:52 -0800 Subject: rcutorture: Add grace period after CPU offline Beyond a certain point in the CPU-hotplug offline process, timers get stranded on the outgoing CPU, and won't fire until that CPU comes back online, which might well be never. This commit therefore adds a hook in torture_onoff_init() that is invoked from torture_offline(), which rcutorture uses to occasionally wait for a grace period. This should result in failures for RCU implementations that rely on stranded timers eventually firing in the absence of the CPU coming back online. Reported-by: Sebastian Andrzej Siewior Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 3 ++- kernel/locking/locktorture.c | 2 +- kernel/rcu/rcutorture.c | 11 ++++++++++- kernel/torture.c | 6 +++++- 4 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/torture.h b/include/linux/torture.h index 48fad21109fc..f2d3bcbf4337 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -50,11 +50,12 @@ do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0) /* Definitions for online/offline exerciser. */ +typedef void torture_ofl_func(void); bool torture_offline(int cpu, long *n_onl_attempts, long *n_onl_successes, unsigned long *sum_offl, int *min_onl, int *max_onl); bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, unsigned long *sum_onl, int *min_onl, int *max_onl); -int torture_onoff_init(long ooholdoff, long oointerval); +int torture_onoff_init(long ooholdoff, long oointerval, torture_ofl_func *f); void torture_onoff_stats(void); bool torture_onoff_failures(void); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 7d0b0ed74404..c8b348097bb5 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -970,7 +970,7 @@ static int __init lock_torture_init(void) /* Prepare torture context. */ if (onoff_interval > 0) { firsterr = torture_onoff_init(onoff_holdoff * HZ, - onoff_interval * HZ); + onoff_interval * HZ, NULL); if (firsterr) goto unwind; } diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 0955f3a20952..9eb9235c1ec9 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -2243,6 +2243,14 @@ static void rcu_test_debug_objects(void) #endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ } +static void rcutorture_sync(void) +{ + static unsigned long n; + + if (cur_ops->sync && !(++n & 0xfff)) + cur_ops->sync(); +} + static int __init rcu_torture_init(void) { @@ -2404,7 +2412,8 @@ rcu_torture_init(void) firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup); if (firsterr) goto unwind; - firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval); + firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval, + rcutorture_sync); if (firsterr) goto unwind; firsterr = rcu_torture_stall_init(); diff --git a/kernel/torture.c b/kernel/torture.c index bbf6d473e50c..a03ff722352b 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -75,6 +75,7 @@ static DEFINE_MUTEX(fullstop_mutex); static struct task_struct *onoff_task; static long onoff_holdoff; static long onoff_interval; +static torture_ofl_func *onoff_f; static long n_offline_attempts; static long n_offline_successes; static unsigned long sum_offline; @@ -118,6 +119,8 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, pr_alert("%s" TORTURE_FLAG "torture_onoff task: offlined %d\n", torture_type, cpu); + if (onoff_f) + onoff_f(); (*n_offl_successes)++; delta = jiffies - starttime; *sum_offl += delta; @@ -243,11 +246,12 @@ stop: /* * Initiate online-offline handling. */ -int torture_onoff_init(long ooholdoff, long oointerval) +int torture_onoff_init(long ooholdoff, long oointerval, torture_ofl_func *f) { #ifdef CONFIG_HOTPLUG_CPU onoff_holdoff = ooholdoff; onoff_interval = oointerval; + onoff_f = f; if (onoff_interval <= 0) return 0; return torture_create_kthread(torture_onoff, NULL, onoff_task); -- cgit v1.2.3 From c23f35d19db3b36ffb9e04b08f1d91565d15f84f Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Tue, 22 Jan 2019 10:02:50 -0800 Subject: net: IP defrag: encapsulate rbtree defrag code into callable functions This is a refactoring patch: without changing runtime behavior, it moves rbtree-related code from IPv4-specific files/functions into .h/.c defrag files shared with IPv6 defragmentation code. Signed-off-by: Peter Oskolkov Cc: Eric Dumazet Cc: Florian Westphal Cc: Tom Herbert Signed-off-by: David S. Miller --- include/net/inet_frag.h | 16 ++- net/ipv4/inet_fragment.c | 293 +++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/ip_fragment.c | 289 +++++----------------------------------------- 3 files changed, 334 insertions(+), 264 deletions(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 1662cbc0b46b..b02bf737d019 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -77,8 +77,8 @@ struct inet_frag_queue { struct timer_list timer; spinlock_t lock; refcount_t refcnt; - struct sk_buff *fragments; /* Used in IPv6. */ - struct rb_root rb_fragments; /* Used in IPv4. */ + struct sk_buff *fragments; /* used in 6lopwpan IPv6. */ + struct rb_root rb_fragments; /* Used in IPv4/IPv6. */ struct sk_buff *fragments_tail; struct sk_buff *last_run_head; ktime_t stamp; @@ -153,4 +153,16 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, long val) extern const u8 ip_frag_ecn_table[16]; +/* Return values of inet_frag_queue_insert() */ +#define IPFRAG_OK 0 +#define IPFRAG_DUP 1 +#define IPFRAG_OVERLAP 2 +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end); +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent); +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data); +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q); + #endif diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 760a9e52e02b..9f69411251d0 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -25,6 +25,62 @@ #include #include #include +#include +#include + +/* Use skb->cb to track consecutive/adjacent fragments coming at + * the end of the queue. Nodes in the rb-tree queue will + * contain "runs" of one or more adjacent fragments. + * + * Invariants: + * - next_frag is NULL at the tail of a "run"; + * - the head of a "run" has the sum of all fragment lengths in frag_run_len. + */ +struct ipfrag_skb_cb { + union { + struct inet_skb_parm h4; + struct inet6_skb_parm h6; + }; + struct sk_buff *next_frag; + int frag_run_len; +}; + +#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) + +static void fragcb_clear(struct sk_buff *skb) +{ + RB_CLEAR_NODE(&skb->rbnode); + FRAG_CB(skb)->next_frag = NULL; + FRAG_CB(skb)->frag_run_len = skb->len; +} + +/* Append skb to the last "run". */ +static void fragrun_append_to_last(struct inet_frag_queue *q, + struct sk_buff *skb) +{ + fragcb_clear(skb); + + FRAG_CB(q->last_run_head)->frag_run_len += skb->len; + FRAG_CB(q->fragments_tail)->next_frag = skb; + q->fragments_tail = skb; +} + +/* Create a new "run" with the skb. */ +static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); + fragcb_clear(skb); + + if (q->last_run_head) + rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, + &q->last_run_head->rbnode.rb_right); + else + rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + + q->fragments_tail = skb; + q->last_run_head = skb; +} /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. @@ -123,6 +179,28 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) kmem_cache_free(f->frags_cachep, q); } +unsigned int inet_frag_rbtree_purge(struct rb_root *root) +{ + struct rb_node *p = rb_first(root); + unsigned int sum = 0; + + while (p) { + struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); + + p = rb_next(p); + rb_erase(&skb->rbnode, root); + while (skb) { + struct sk_buff *next = FRAG_CB(skb)->next_frag; + + sum += skb->truesize; + kfree_skb(skb); + skb = next; + } + } + return sum; +} +EXPORT_SYMBOL(inet_frag_rbtree_purge); + void inet_frag_destroy(struct inet_frag_queue *q) { struct sk_buff *fp; @@ -224,3 +302,218 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) return fq; } EXPORT_SYMBOL(inet_frag_find); + +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end) +{ + struct sk_buff *last = q->fragments_tail; + + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments) MUST be silently discarded. + * + * Duplicates, however, should be ignored (i.e. skb dropped, but the + * queue/fragments kept for later reassembly). + */ + if (!last) + fragrun_create(q, skb); /* First fragment. */ + else if (last->ip_defrag_offset + last->len < end) { + /* This is the common case: skb goes to the end. */ + /* Detect and discard overlaps. */ + if (offset < last->ip_defrag_offset + last->len) + return IPFRAG_OVERLAP; + if (offset == last->ip_defrag_offset + last->len) + fragrun_append_to_last(q, skb); + else + fragrun_create(q, skb); + } else { + /* Binary search. Note that skb can become the first fragment, + * but not the last (covered above). + */ + struct rb_node **rbn, *parent; + + rbn = &q->rb_fragments.rb_node; + do { + struct sk_buff *curr; + int curr_run_end; + + parent = *rbn; + curr = rb_to_skb(parent); + curr_run_end = curr->ip_defrag_offset + + FRAG_CB(curr)->frag_run_len; + if (end <= curr->ip_defrag_offset) + rbn = &parent->rb_left; + else if (offset >= curr_run_end) + rbn = &parent->rb_right; + else if (offset >= curr->ip_defrag_offset && + end <= curr_run_end) + return IPFRAG_DUP; + else + return IPFRAG_OVERLAP; + } while (*rbn); + /* Here we have parent properly set, and rbn pointing to + * one of its NULL left/right children. Insert skb. + */ + fragcb_clear(skb); + rb_link_node(&skb->rbnode, parent, rbn); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + } + + skb->ip_defrag_offset = offset; + + return IPFRAG_OK; +} +EXPORT_SYMBOL(inet_frag_queue_insert); + +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent) +{ + struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); + struct sk_buff **nextp; + int delta; + + if (head != skb) { + fp = skb_clone(skb, GFP_ATOMIC); + if (!fp) + return NULL; + FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; + if (RB_EMPTY_NODE(&skb->rbnode)) + FRAG_CB(parent)->next_frag = fp; + else + rb_replace_node(&skb->rbnode, &fp->rbnode, + &q->rb_fragments); + if (q->fragments_tail == skb) + q->fragments_tail = fp; + skb_morph(skb, head); + FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + consume_skb(head); + head = skb; + } + WARN_ON(head->ip_defrag_offset != 0); + + delta = -head->truesize; + + /* Head of list must not be cloned. */ + if (skb_unclone(head, GFP_ATOMIC)) + return NULL; + + delta += head->truesize; + if (delta) + add_frag_mem_limit(q->net, delta); + + /* If the first fragment is fragmented itself, we split + * it to two chunks: the first with data and paged part + * and the second, holding only fragments. + */ + if (skb_has_frag_list(head)) { + struct sk_buff *clone; + int i, plen = 0; + + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) + return NULL; + skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; + skb_frag_list_init(head); + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); + clone->data_len = head->data_len - plen; + clone->len = clone->data_len; + head->truesize += clone->truesize; + clone->csum = 0; + clone->ip_summed = head->ip_summed; + add_frag_mem_limit(q->net, clone->truesize); + skb_shinfo(head)->frag_list = clone; + nextp = &clone->next; + } else { + nextp = &skb_shinfo(head)->frag_list; + } + + return nextp; +} +EXPORT_SYMBOL(inet_frag_reasm_prepare); + +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data) +{ + struct sk_buff **nextp = (struct sk_buff **)reasm_data; + struct rb_node *rbn; + struct sk_buff *fp; + + skb_push(head, head->data - skb_network_header(head)); + + /* Traverse the tree in order, to build frag_list. */ + fp = FRAG_CB(head)->next_frag; + rbn = rb_next(&head->rbnode); + rb_erase(&head->rbnode, &q->rb_fragments); + while (rbn || fp) { + /* fp points to the next sk_buff in the current run; + * rbn points to the next run. + */ + /* Go through the current run. */ + while (fp) { + *nextp = fp; + nextp = &fp->next; + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; + head->data_len += fp->len; + head->len += fp->len; + if (head->ip_summed != fp->ip_summed) + head->ip_summed = CHECKSUM_NONE; + else if (head->ip_summed == CHECKSUM_COMPLETE) + head->csum = csum_add(head->csum, fp->csum); + head->truesize += fp->truesize; + fp = FRAG_CB(fp)->next_frag; + } + /* Move to the next run. */ + if (rbn) { + struct rb_node *rbnext = rb_next(rbn); + + fp = rb_to_skb(rbn); + rb_erase(rbn, &q->rb_fragments); + rbn = rbnext; + } + } + sub_frag_mem_limit(q->net, head->truesize); + + *nextp = NULL; + skb_mark_not_on_list(head); + head->prev = NULL; + head->tstamp = q->stamp; +} +EXPORT_SYMBOL(inet_frag_reasm_finish); + +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) +{ + struct sk_buff *head; + + if (q->fragments) { + head = q->fragments; + q->fragments = head->next; + } else { + struct sk_buff *skb; + + head = skb_rb_first(&q->rb_fragments); + if (!head) + return NULL; + skb = FRAG_CB(head)->next_frag; + if (skb) + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + else + rb_erase(&head->rbnode, &q->rb_fragments); + memset(&head->rbnode, 0, sizeof(head->rbnode)); + barrier(); + } + if (head == q->fragments_tail) + q->fragments_tail = NULL; + + sub_frag_mem_limit(q->net, head->truesize); + + return head; +} +EXPORT_SYMBOL(inet_frag_pull_head); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 867be8f7f1fa..486ecb0aeb87 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -57,57 +57,6 @@ */ static const char ip_frag_cache_name[] = "ip4-frags"; -/* Use skb->cb to track consecutive/adjacent fragments coming at - * the end of the queue. Nodes in the rb-tree queue will - * contain "runs" of one or more adjacent fragments. - * - * Invariants: - * - next_frag is NULL at the tail of a "run"; - * - the head of a "run" has the sum of all fragment lengths in frag_run_len. - */ -struct ipfrag_skb_cb { - struct inet_skb_parm h; - struct sk_buff *next_frag; - int frag_run_len; -}; - -#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) - -static void ip4_frag_init_run(struct sk_buff *skb) -{ - BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); - - FRAG_CB(skb)->next_frag = NULL; - FRAG_CB(skb)->frag_run_len = skb->len; -} - -/* Append skb to the last "run". */ -static void ip4_frag_append_to_last_run(struct inet_frag_queue *q, - struct sk_buff *skb) -{ - RB_CLEAR_NODE(&skb->rbnode); - FRAG_CB(skb)->next_frag = NULL; - - FRAG_CB(q->last_run_head)->frag_run_len += skb->len; - FRAG_CB(q->fragments_tail)->next_frag = skb; - q->fragments_tail = skb; -} - -/* Create a new "run" with the skb. */ -static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb) -{ - if (q->last_run_head) - rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, - &q->last_run_head->rbnode.rb_right); - else - rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); - rb_insert_color(&skb->rbnode, &q->rb_fragments); - - ip4_frag_init_run(skb); - q->fragments_tail = skb; - q->last_run_head = skb; -} - /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; @@ -212,27 +161,9 @@ static void ip_expire(struct timer_list *t) * pull the head out of the tree in order to be able to * deal with head->dev. */ - if (qp->q.fragments) { - head = qp->q.fragments; - qp->q.fragments = head->next; - } else { - head = skb_rb_first(&qp->q.rb_fragments); - if (!head) - goto out; - if (FRAG_CB(head)->next_frag) - rb_replace_node(&head->rbnode, - &FRAG_CB(head)->next_frag->rbnode, - &qp->q.rb_fragments); - else - rb_erase(&head->rbnode, &qp->q.rb_fragments); - memset(&head->rbnode, 0, sizeof(head->rbnode)); - barrier(); - } - if (head == qp->q.fragments_tail) - qp->q.fragments_tail = NULL; - - sub_frag_mem_limit(qp->q.net, head->truesize); - + head = inet_frag_pull_head(&qp->q); + if (!head) + goto out; head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; @@ -344,12 +275,10 @@ static int ip_frag_reinit(struct ipq *qp) static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); - struct rb_node **rbn, *parent; - struct sk_buff *skb1, *prev_tail; - int ihl, end, skb1_run_end; + int ihl, end, flags, offset; + struct sk_buff *prev_tail; struct net_device *dev; unsigned int fragsize; - int flags, offset; int err = -ENOENT; u8 ecn; @@ -413,62 +342,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) /* Makes sure compiler wont do silly aliasing games */ barrier(); - /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - * - * We do the same here for IPv4 (and increment an snmp counter) but - * we do not want to drop the whole queue in response to a duplicate - * fragment. - */ - - err = -EINVAL; - /* Find out where to put this fragment. */ prev_tail = qp->q.fragments_tail; - if (!prev_tail) - ip4_frag_create_run(&qp->q, skb); /* First fragment. */ - else if (prev_tail->ip_defrag_offset + prev_tail->len < end) { - /* This is the common case: skb goes to the end. */ - /* Detect and discard overlaps. */ - if (offset < prev_tail->ip_defrag_offset + prev_tail->len) - goto overlap; - if (offset == prev_tail->ip_defrag_offset + prev_tail->len) - ip4_frag_append_to_last_run(&qp->q, skb); - else - ip4_frag_create_run(&qp->q, skb); - } else { - /* Binary search. Note that skb can become the first fragment, - * but not the last (covered above). - */ - rbn = &qp->q.rb_fragments.rb_node; - do { - parent = *rbn; - skb1 = rb_to_skb(parent); - skb1_run_end = skb1->ip_defrag_offset + - FRAG_CB(skb1)->frag_run_len; - if (end <= skb1->ip_defrag_offset) - rbn = &parent->rb_left; - else if (offset >= skb1_run_end) - rbn = &parent->rb_right; - else if (offset >= skb1->ip_defrag_offset && - end <= skb1_run_end) - goto err; /* No new data, potential duplicate */ - else - goto overlap; /* Found an overlap */ - } while (*rbn); - /* Here we have parent properly set, and rbn pointing to - * one of its NULL left/right children. Insert skb. - */ - ip4_frag_init_run(skb); - rb_link_node(&skb->rbnode, parent, rbn); - rb_insert_color(&skb->rbnode, &qp->q.rb_fragments); - } + err = inet_frag_queue_insert(&qp->q, skb, offset, end); + if (err) + goto insert_error; if (dev) qp->iif = dev->ifindex; - skb->ip_defrag_offset = offset; qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; @@ -501,10 +381,16 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) skb_dst_drop(skb); return -EINPROGRESS; -overlap: +insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q); + __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb(skb); return err; @@ -516,13 +402,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct iphdr *iph; - struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments); - struct sk_buff **nextp; /* To build frag_list. */ - struct rb_node *rbn; - int len; - int ihlen; - int delta; - int err; + void *reasm_data; + int len, err; u8 ecn; ipq_kill(qp); @@ -532,117 +413,23 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, err = -EINVAL; goto out_fail; } - /* Make the one we just received the head. */ - if (head != skb) { - fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - goto out_nomem; - FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; - if (RB_EMPTY_NODE(&skb->rbnode)) - FRAG_CB(prev_tail)->next_frag = fp; - else - rb_replace_node(&skb->rbnode, &fp->rbnode, - &qp->q.rb_fragments); - if (qp->q.fragments_tail == skb) - qp->q.fragments_tail = fp; - skb_morph(skb, head); - FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; - rb_replace_node(&head->rbnode, &skb->rbnode, - &qp->q.rb_fragments); - consume_skb(head); - head = skb; - } - WARN_ON(head->ip_defrag_offset != 0); - - /* Allocate a new buffer for the datagram. */ - ihlen = ip_hdrlen(head); - len = ihlen + qp->q.len; + /* Make the one we just received the head. */ + reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); + if (!reasm_data) + goto out_nomem; + len = ip_hdrlen(skb) + qp->q.len; err = -E2BIG; if (len > 65535) goto out_oversize; - delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_nomem; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(qp->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_nomem; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->truesize += clone->truesize; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(qp->q.net, clone->truesize); - skb_shinfo(head)->frag_list = clone; - nextp = &clone->next; - } else { - nextp = &skb_shinfo(head)->frag_list; - } - - skb_push(head, head->data - skb_network_header(head)); + inet_frag_reasm_finish(&qp->q, skb, reasm_data); - /* Traverse the tree in order, to build frag_list. */ - fp = FRAG_CB(head)->next_frag; - rbn = rb_next(&head->rbnode); - rb_erase(&head->rbnode, &qp->q.rb_fragments); - while (rbn || fp) { - /* fp points to the next sk_buff in the current run; - * rbn points to the next run. - */ - /* Go through the current run. */ - while (fp) { - *nextp = fp; - nextp = &fp->next; - fp->prev = NULL; - memset(&fp->rbnode, 0, sizeof(fp->rbnode)); - fp->sk = NULL; - head->data_len += fp->len; - head->len += fp->len; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp = FRAG_CB(fp)->next_frag; - } - /* Move to the next run. */ - if (rbn) { - struct rb_node *rbnext = rb_next(rbn); - - fp = rb_to_skb(rbn); - rb_erase(rbn, &qp->q.rb_fragments); - rbn = rbnext; - } - } - sub_frag_mem_limit(qp->q.net, head->truesize); - - *nextp = NULL; - skb_mark_not_on_list(head); - head->prev = NULL; - head->dev = dev; - head->tstamp = qp->q.stamp; - IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); + skb->dev = dev; + IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); - iph = ip_hdr(head); + iph = ip_hdr(skb); iph->tot_len = htons(len); iph->tos |= ecn; @@ -655,7 +442,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, * from one very small df-fragment and one large non-df frag. */ if (qp->max_df_size == qp->q.max_size) { - IPCB(head)->flags |= IPSKB_FRAG_PMTU; + IPCB(skb)->flags |= IPSKB_FRAG_PMTU; iph->frag_off = htons(IP_DF); } else { iph->frag_off = 0; @@ -753,28 +540,6 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) } EXPORT_SYMBOL(ip_check_defrag); -unsigned int inet_frag_rbtree_purge(struct rb_root *root) -{ - struct rb_node *p = rb_first(root); - unsigned int sum = 0; - - while (p) { - struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); - - p = rb_next(p); - rb_erase(&skb->rbnode, root); - while (skb) { - struct sk_buff *next = FRAG_CB(skb)->next_frag; - - sum += skb->truesize; - kfree_skb(skb); - skb = next; - } - } - return sum; -} -EXPORT_SYMBOL(inet_frag_rbtree_purge); - #ifdef CONFIG_SYSCTL static int dist_min; -- cgit v1.2.3 From d4289fcc9b16b89619ee1c54f829e05e56de8b9a Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Tue, 22 Jan 2019 10:02:51 -0800 Subject: net: IP6 defrag: use rbtrees for IPv6 defrag Currently, IPv6 defragmentation code drops non-last fragments that are smaller than 1280 bytes: see commit 0ed4229b08c1 ("ipv6: defrag: drop non-last frags smaller than min mtu") This behavior is not specified in IPv6 RFCs and appears to break compatibility with some IPv6 implemenations, as reported here: https://www.spinics.net/lists/netdev/msg543846.html This patch re-uses common IP defragmentation queueing and reassembly code in IPv6, removing the 1280 byte restriction. Signed-off-by: Peter Oskolkov Reported-by: Tom Herbert Cc: Eric Dumazet Cc: Florian Westphal Signed-off-by: David S. Miller --- include/net/ipv6_frag.h | 11 ++- net/ipv6/reassembly.c | 233 +++++++++++++----------------------------------- 2 files changed, 71 insertions(+), 173 deletions(-) (limited to 'include') diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 6ced1e6899b6..28aa9b30aece 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -82,8 +82,15 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); /* Don't send error if the first segment did not arrive. */ - head = fq->q.fragments; - if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head) + if (!(fq->q.flags & INET_FRAG_FIRST_IN)) + goto out; + + /* sk_buff::dev and sk_buff::rbnode are unionized. So we + * pull the head out of the tree in order to be able to + * deal with head->dev. + */ + head = inet_frag_pull_head(&fq->q); + if (!head) goto out; head->dev = dev; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 36a3d8dc61f5..24264d0a4b85 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -69,8 +69,8 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) static struct inet_frags ip6_frags; -static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev); +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev); static void ip6_frag_expire(struct timer_list *t) { @@ -111,21 +111,26 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct frag_hdr *fhdr, int nhoff, u32 *prob_offset) { - struct sk_buff *prev, *next; - struct net_device *dev; - int offset, end, fragsize; struct net *net = dev_net(skb_dst(skb)->dev); + int offset, end, fragsize; + struct sk_buff *prev_tail; + struct net_device *dev; + int err = -ENOENT; u8 ecn; if (fq->q.flags & INET_FRAG_COMPLETE) goto err; + err = -EINVAL; offset = ntohs(fhdr->frag_off) & ~0x7; end = offset + (ntohs(ipv6_hdr(skb)->payload_len) - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb); + /* note that if prob_offset is set, the skb is freed elsewhere, + * we do not free it here. + */ return -1; } @@ -170,62 +175,27 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, if (end == offset) goto discard_fq; + err = -ENOMEM; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) goto discard_fq; - if (pskb_trim_rcsum(skb, end - offset)) + err = pskb_trim_rcsum(skb, end - offset); + if (err) goto discard_fq; - /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ - prev = fq->q.fragments_tail; - if (!prev || prev->ip_defrag_offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = fq->q.fragments; next != NULL; next = next->next) { - if (next->ip_defrag_offset >= offset) - break; /* bingo! */ - prev = next; - } - -found: - /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - */ - - /* Check for overlap with preceding fragment. */ - if (prev && - (prev->ip_defrag_offset + prev->len) > offset) - goto discard_fq; - - /* Look for overlap with succeeding segment. */ - if (next && next->ip_defrag_offset < end) - goto discard_fq; - - /* Note : skb->ip_defrag_offset and skb->sk share the same location */ + /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; - if (dev) - fq->iif = dev->ifindex; /* Makes sure compiler wont do silly aliasing games */ barrier(); - skb->ip_defrag_offset = offset; - /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - fq->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - fq->q.fragments = skb; + prev_tail = fq->q.fragments_tail; + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) + goto insert_error; + + if (dev) + fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; @@ -246,44 +216,48 @@ found: if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { - int res; unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; - res = ip6_frag_reasm(fq, prev, dev); + err = ip6_frag_reasm(fq, skb, prev_tail, dev); skb->_skb_refdst = orefdst; - return res; + return err; } skb_dst_drop(skb); - return -1; + return -EINPROGRESS; +insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASM_OVERLAPS); discard_fq: inet_frag_kill(&fq->q); -err: __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); +err: kfree_skb(skb); - return -1; + return err; } /* * Check if this packet is complete. - * Returns NULL on failure by any reason, and pointer - * to current nexthdr field in reassembled frame. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ -static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev) +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev) { struct net *net = container_of(fq->q.net, struct net, ipv6.frags); - struct sk_buff *fp, *head = fq->q.fragments; - int payload_len, delta; unsigned int nhoff; - int sum_truesize; + void *reasm_data; + int payload_len; u8 ecn; inet_frag_kill(&fq->q); @@ -292,121 +266,40 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, if (unlikely(ecn == 0xff)) goto out_fail; - /* Make the one we just received the head. */ - if (prev) { - head = prev->next; - fp = skb_clone(head, GFP_ATOMIC); - - if (!fp) - goto out_oom; - - fp->next = head->next; - if (!fp->next) - fq->q.fragments_tail = fp; - prev->next = fp; - - skb_morph(head, fq->q.fragments); - head->next = fq->q.fragments->next; - - consume_skb(fq->q.fragments); - fq->q.fragments = head; - } - - WARN_ON(head == NULL); - WARN_ON(head->ip_defrag_offset != 0); + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto out_oom; - /* Unfragmented part is taken from the first segment. */ - payload_len = ((head->data - skb_network_header(head)) - + payload_len = ((skb->data - skb_network_header(skb)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) goto out_oversize; - delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_oom; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(fq->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_oom; - clone->next = head->next; - head->next = clone; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(fq->q.net, clone->truesize); - } - /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ nhoff = fq->nhoffset; - skb_network_header(head)[nhoff] = skb_transport_header(head)[0]; - memmove(head->head + sizeof(struct frag_hdr), head->head, - (head->data - head->head) - sizeof(struct frag_hdr)); - if (skb_mac_header_was_set(head)) - head->mac_header += sizeof(struct frag_hdr); - head->network_header += sizeof(struct frag_hdr); - - skb_reset_transport_header(head); - skb_push(head, head->data - skb_network_header(head)); - - sum_truesize = head->truesize; - for (fp = head->next; fp;) { - bool headstolen; - int delta; - struct sk_buff *next = fp->next; - - sum_truesize += fp->truesize; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - - if (skb_try_coalesce(head, fp, &headstolen, &delta)) { - kfree_skb_partial(fp, headstolen); - } else { - fp->sk = NULL; - if (!skb_shinfo(head)->frag_list) - skb_shinfo(head)->frag_list = fp; - head->data_len += fp->len; - head->len += fp->len; - head->truesize += fp->truesize; - } - fp = next; - } - sub_frag_mem_limit(fq->q.net, sum_truesize); + skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0]; + memmove(skb->head + sizeof(struct frag_hdr), skb->head, + (skb->data - skb->head) - sizeof(struct frag_hdr)); + if (skb_mac_header_was_set(skb)) + skb->mac_header += sizeof(struct frag_hdr); + skb->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(skb); + + inet_frag_reasm_finish(&fq->q, skb, reasm_data); - skb_mark_not_on_list(head); - head->dev = dev; - head->tstamp = fq->q.stamp; - ipv6_hdr(head)->payload_len = htons(payload_len); - ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); - IP6CB(head)->nhoff = nhoff; - IP6CB(head)->flags |= IP6SKB_FRAGMENTED; - IP6CB(head)->frag_max_size = fq->q.max_size; + skb->dev = dev; + ipv6_hdr(skb)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); + IP6CB(skb)->nhoff = nhoff; + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + IP6CB(skb)->frag_max_size = fq->q.max_size; /* Yes, and fold redundant checksum back. 8) */ - skb_postpush_rcsum(head, skb_network_header(head), - skb_network_header_len(head)); + skb_postpush_rcsum(skb, skb_network_header(skb), + skb_network_header_len(skb)); rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); @@ -414,6 +307,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; return 1; out_oversize: @@ -464,10 +358,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } - if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && - fhdr->frag_off & htons(IP6_MF)) - goto fail_hdr; - iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { @@ -485,6 +375,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) if (prob_offset) { __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INHDRERRORS); + /* icmpv6_param_prob() calls kfree_skb(skb) */ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset); } return ret; -- cgit v1.2.3 From f859a448470304135f7a1af0083b99e188873bb4 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 25 Jan 2019 11:17:23 -0500 Subject: tcp: allow zerocopy with fastopen Accept MSG_ZEROCOPY in all the TCP states that allow sendmsg. Remove the explicit check for ESTABLISHED and CLOSE_WAIT states. This requires correctly handling zerocopy state (uarg, sk_zckey) in all paths reachable from other TCP states. Such as the EPIPE case in sk_stream_wait_connect, which a sendmsg() in incorrect state will now hit. Most paths are already safe. Only extension needed is for TCP Fastopen active open. This can build an skb with data in tcp_send_syn_data. Pass the uarg along with other fastopen state, so that this skb also generates a zerocopy notification on release. Tested with active and passive tcp fastopen packetdrill scripts at https://github.com/wdebruij/packetdrill/commit/1747eef03d25a2404e8132817d0f1244fd6f129d Signed-off-by: Willem de Bruijn Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + net/ipv4/tcp.c | 11 ++++------- net/ipv4/tcp_output.c | 1 + 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 5c950180d61b..a6e0355921e1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1608,6 +1608,7 @@ struct tcp_fastopen_request { struct msghdr *data; /* data in MSG_FASTOPEN */ size_t size; int copied; /* queued in tcp_connect() */ + struct ubuf_info *uarg; }; void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5f099c9d04e5..12ba21433dd0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1127,7 +1127,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, - int *copied, size_t size) + int *copied, size_t size, + struct ubuf_info *uarg) { struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); @@ -1147,6 +1148,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, return -ENOBUFS; tp->fastopen_req->data = msg; tp->fastopen_req->size = size; + tp->fastopen_req->uarg = uarg; if (inet->defer_connect) { err = tcp_connect(sk); @@ -1186,11 +1188,6 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { - if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { - err = -EINVAL; - goto out_err; - } - skb = tcp_write_queue_tail(sk); uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { @@ -1205,7 +1202,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && !tp->repair) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6527f61f59ff..26a2948dca95 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3455,6 +3455,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) skb_trim(syn_data, copied); space = copied; } + skb_zcopy_set(syn_data, fo->uarg, NULL); } /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) -- cgit v1.2.3 From c8b34e680a090ab8dc42f8331020e31052b49a70 Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 22 Jan 2019 18:39:50 +0800 Subject: ip_tunnel: Add tnl_update_pmtu in ip_md_tunnel_xmit Add tnl_update_pmtu in ip_md_tunnel_xmit to dynamic modify the pmtu which packet send through collect_metadata mode ip tunnel Signed-off-by: wenxu Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 2 +- net/ipv4/ip_tunnel.c | 37 +++++++++++++++++++++++++++---------- net/ipv4/ipip.c | 2 +- 3 files changed, 29 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 34f019650941..f069f64ebf29 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -267,7 +267,7 @@ void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id, void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, - const u8 proto); + const u8 proto, int tunnel_hlen); int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index f98fc4c983a5..6233a7c434b1 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -501,15 +501,19 @@ EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup); static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rtable *rt, __be16 df, - const struct iphdr *inner_iph) + const struct iphdr *inner_iph, + int tunnel_hlen, __be32 dst, bool md) { struct ip_tunnel *tunnel = netdev_priv(dev); - int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len; + int pkt_size; int mtu; + tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; + pkt_size = skb->len - tunnel_hlen - dev->hard_header_len; + if (df) mtu = dst_mtu(&rt->dst) - dev->hard_header_len - - sizeof(struct iphdr) - tunnel->hlen; + - sizeof(struct iphdr) - tunnel_hlen; else mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; @@ -527,11 +531,13 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); + __be32 daddr; + + daddr = md ? dst : tunnel->parms.iph.daddr; if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) { - if ((tunnel->parms.iph.daddr && - !ipv4_is_multicast(tunnel->parms.iph.daddr)) || + if ((daddr && !ipv4_is_multicast(daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); @@ -548,7 +554,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } -void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) +void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, + u8 proto, int tunnel_hlen) { struct ip_tunnel *tunnel = netdev_priv(dev); u32 headroom = sizeof(struct iphdr); @@ -598,6 +605,15 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) dev->stats.collisions++; goto tx_error; } + + if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, + key->u.ipv4.dst, true)) { + ip_rt_put(rt); + goto tx_error; + } + tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = key->ttl; if (ttl == 0) { @@ -608,10 +624,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) else ttl = ip4_dst_hoplimit(&rt->dst); } - if (key->tun_flags & TUNNEL_DONT_FRAGMENT) - df = htons(IP_DF); - else if (skb->protocol == htons(ETH_P_IP)) + + if (!df && skb->protocol == htons(ETH_P_IP)) df = inner_iph->frag_off & htons(IP_DF); + headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (headroom > dev->needed_headroom) dev->needed_headroom = headroom; @@ -741,7 +757,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) { + if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph, + 0, 0, false)) { ip_rt_put(rt); goto tx_error; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 57c5dd283a2c..fe10b9a2efc8 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -302,7 +302,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, skb_set_inner_ipproto(skb, ipproto); if (tunnel->collect_md) - ip_md_tunnel_xmit(skb, dev, ipproto); + ip_md_tunnel_xmit(skb, dev, ipproto, 0); else ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; -- cgit v1.2.3 From 9b28aa1d0eae1be1016c8f4ba504545caff01da3 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Wed, 12 Dec 2018 23:59:13 +0000 Subject: platform_data/mlxreg: Document fixes for core platform data Remove "led" from the description, since the structure "mlxreg_core_platform_data" is used not only for led data. Signed-off-by: Vadim Pasternak Signed-off-by: Darren Hart (VMware) --- include/linux/platform_data/mlxreg.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 19f5cb618c55..d823713f94ec 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -107,9 +107,9 @@ struct mlxreg_core_item { /** * struct mlxreg_core_platform_data - platform data: * - * @led_data: led private data; + * @data: instance private data; * @regmap: register map of parent device; - * @counter: number of led instances; + * @counter: number of instances; */ struct mlxreg_core_platform_data { struct mlxreg_core_data *data; -- cgit v1.2.3 From 946e4e02b11889cb161b15ff4712a8ba21a50eb6 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Wed, 12 Dec 2018 23:59:14 +0000 Subject: platform_data/mlxreg: Add capability field to core platform data Add capability field to "mlxreg_core_platform_data" structure. The purpose of this register is to provide additional info to platform driver through the atribute related capability register. Signed-off-by: Vadim Pasternak Signed-off-by: Darren Hart (VMware) --- include/linux/platform_data/mlxreg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index d823713f94ec..1b2f86f96743 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -61,6 +61,7 @@ struct mlxreg_hotplug_device { * @reg: attribute register; * @mask: attribute access mask; * @bit: attribute effective bit; + * @capability: attribute capability register; * @mode: access mode; * @np - pointer to node platform associated with attribute; * @hpdev - hotplug device data; @@ -72,6 +73,7 @@ struct mlxreg_core_data { u32 reg; u32 mask; u32 bit; + u32 capability; umode_t mode; struct device_node *np; struct mlxreg_hotplug_device hpdev; -- cgit v1.2.3 From d405c7407a5468d4fc11724d76063e0647d80106 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Sat, 26 Jan 2019 12:25:59 -0500 Subject: bpf: allocate 0x06 to new eBPF instruction class JMP32 The new eBPF instruction class JMP32 uses the reserved class number 0x6. Kernel BPF ISA documentation updated accordingly. Reviewed-by: Jakub Kicinski Signed-off-by: Jiong Wang Signed-off-by: Alexei Starovoitov --- Documentation/networking/filter.txt | 15 ++++++++------- include/uapi/linux/bpf.h | 1 + tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index 2196b824e96c..01603bc2eff1 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -865,7 +865,7 @@ Three LSB bits store instruction class which is one of: BPF_STX 0x03 BPF_STX 0x03 BPF_ALU 0x04 BPF_ALU 0x04 BPF_JMP 0x05 BPF_JMP 0x05 - BPF_RET 0x06 [ class 6 unused, for future if needed ] + BPF_RET 0x06 BPF_JMP32 0x06 BPF_MISC 0x07 BPF_ALU64 0x07 When BPF_CLASS(code) == BPF_ALU or BPF_JMP, 4th bit encodes source operand ... @@ -902,9 +902,9 @@ If BPF_CLASS(code) == BPF_ALU or BPF_ALU64 [ in eBPF ], BPF_OP(code) is one of: BPF_ARSH 0xc0 /* eBPF only: sign extending shift right */ BPF_END 0xd0 /* eBPF only: endianness conversion */ -If BPF_CLASS(code) == BPF_JMP, BPF_OP(code) is one of: +If BPF_CLASS(code) == BPF_JMP or BPF_JMP32 [ in eBPF ], BPF_OP(code) is one of: - BPF_JA 0x00 + BPF_JA 0x00 /* BPF_JMP only */ BPF_JEQ 0x10 BPF_JGT 0x20 BPF_JGE 0x30 @@ -912,8 +912,8 @@ If BPF_CLASS(code) == BPF_JMP, BPF_OP(code) is one of: BPF_JNE 0x50 /* eBPF only: jump != */ BPF_JSGT 0x60 /* eBPF only: signed '>' */ BPF_JSGE 0x70 /* eBPF only: signed '>=' */ - BPF_CALL 0x80 /* eBPF only: function call */ - BPF_EXIT 0x90 /* eBPF only: function return */ + BPF_CALL 0x80 /* eBPF BPF_JMP only: function call */ + BPF_EXIT 0x90 /* eBPF BPF_JMP only: function return */ BPF_JLT 0xa0 /* eBPF only: unsigned '<' */ BPF_JLE 0xb0 /* eBPF only: unsigned '<=' */ BPF_JSLT 0xc0 /* eBPF only: signed '<' */ @@ -936,8 +936,9 @@ Classic BPF wastes the whole BPF_RET class to represent a single 'ret' operation. Classic BPF_RET | BPF_K means copy imm32 into return register and perform function exit. eBPF is modeled to match CPU, so BPF_JMP | BPF_EXIT in eBPF means function exit only. The eBPF program needs to store return -value into register R0 before doing a BPF_EXIT. Class 6 in eBPF is currently -unused and reserved for future use. +value into register R0 before doing a BPF_EXIT. Class 6 in eBPF is used as +BPF_JMP32 to mean exactly the same operations as BPF_JMP, but with 32-bit wide +operands for the comparisons instead. For load and store instructions the 8-bit 'code' field is divided as: diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2940a9854f6d..60b99b730a41 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -14,6 +14,7 @@ /* Extended instruction set based on top of classic BPF */ /* instruction classes */ +#define BPF_JMP32 0x06 /* jmp mode in word width */ #define BPF_ALU64 0x07 /* alu mode in double word width */ /* ld/ldx fields */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 2940a9854f6d..60b99b730a41 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -14,6 +14,7 @@ /* Extended instruction set based on top of classic BPF */ /* instruction classes */ +#define BPF_JMP32 0x06 /* jmp mode in word width */ #define BPF_ALU64 0x07 /* alu mode in double word width */ /* ld/ldx fields */ -- cgit v1.2.3 From a7b76c8857692b0fce063b94ed83da11c396d341 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Sat, 26 Jan 2019 12:26:05 -0500 Subject: bpf: JIT blinds support JMP32 This patch adds JIT blinds support for JMP32. Like BPF_JMP_REG/IMM, JMP32 version are needed for building raw bpf insn. They are added to both include/linux/filter.h and tools/include/linux/filter.h. Reviewed-by: Jakub Kicinski Signed-off-by: Jiong Wang Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 20 ++++++++++++++++++++ kernel/bpf/core.c | 21 +++++++++++++++++++++ tools/include/linux/filter.h | 20 ++++++++++++++++++++ 3 files changed, 61 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index be9af6b4a9e4..e4b473f85b46 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -277,6 +277,26 @@ struct sock_reuseport; .off = OFF, \ .imm = IMM }) +/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_REG(OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index bba11c2565ee..a7bcb23bee84 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -949,6 +949,27 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; + case BPF_JMP32 | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_K: + case BPF_JMP32 | BPF_JSET | BPF_K: + /* Accommodate for extra offset in case of a backjump. */ + off = from->off; + if (off < 0) + off -= 2; + *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); + *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); + *to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX, + off); + break; + case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index af55acf73e75..cce0b02c0e28 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -199,6 +199,16 @@ .off = OFF, \ .imm = 0 }) +/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_REG(OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ #define BPF_JMP_IMM(OP, DST, IMM, OFF) \ @@ -209,6 +219,16 @@ .off = OFF, \ .imm = IMM }) +/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ -- cgit v1.2.3 From 8d5d0cfb63cbcb4005e19a332b31d687b1d01e58 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:23 +0000 Subject: sched/topology: Introduce a sysctl for Energy Aware Scheduling In its current state, Energy Aware Scheduling (EAS) starts automatically on asymmetric platforms having an Energy Model (EM). However, there are users who want to have an EM (for thermal management for example), but don't want EAS with it. In order to let users disable EAS explicitly, introduce a new sysctl called 'sched_energy_aware'. It is enabled by default so that EAS can start automatically on platforms where it makes sense. Flipping it to 0 rebuilds the scheduling domains and disables EAS. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-11-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- Documentation/sysctl/kernel.txt | 12 ++++++++++++ include/linux/sched/sysctl.h | 7 +++++++ kernel/sched/topology.c | 29 +++++++++++++++++++++++++++++ kernel/sysctl.c | 11 +++++++++++ 4 files changed, 59 insertions(+) (limited to 'include') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index c0527d8a468a..379063e58326 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -79,6 +79,7 @@ show up in /proc/sys/kernel: - reboot-cmd [ SPARC only ] - rtsig-max - rtsig-nr +- sched_energy_aware - seccomp/ ==> Documentation/userspace-api/seccomp_filter.rst - sem - sem_next_id [ sysv ipc ] @@ -890,6 +891,17 @@ rtsig-nr shows the number of RT signals currently queued. ============================================================== +sched_energy_aware: + +Enables/disables Energy Aware Scheduling (EAS). EAS starts +automatically on platforms where it can run (that is, +platforms with asymmetric CPU topologies and having an Energy +Model available). If your platform happens to meet the +requirements for EAS but you do not want to use it, change +this value to 0. + +============================================================== + sched_schedstats: Enables/disables scheduler statistics. Enabling this feature diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index a9c32daeb9d8..99ce6d728df7 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -83,4 +83,11 @@ extern int sysctl_schedstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) +extern unsigned int sysctl_sched_energy_aware; +extern int sched_energy_aware_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); +#endif + #endif /* _LINUX_SCHED_SYSCTL_H */ diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 3f35ba1d8fde..50c3fc316c54 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -203,9 +203,35 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) DEFINE_STATIC_KEY_FALSE(sched_energy_present); #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) +unsigned int sysctl_sched_energy_aware = 1; DEFINE_MUTEX(sched_energy_mutex); bool sched_energy_update; +#ifdef CONFIG_PROC_SYSCTL +int sched_energy_aware_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, state; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (!ret && write) { + state = static_branch_unlikely(&sched_energy_present); + if (state != sysctl_sched_energy_aware) { + mutex_lock(&sched_energy_mutex); + sched_energy_update = 1; + rebuild_sched_domains(); + sched_energy_update = 0; + mutex_unlock(&sched_energy_mutex); + } + } + + return ret; +} +#endif + static void free_pd(struct perf_domain *pd) { struct perf_domain *tmp; @@ -322,6 +348,9 @@ static bool build_perf_domains(const struct cpumask *cpu_map) struct cpufreq_policy *policy; struct cpufreq_governor *gov; + if (!sysctl_sched_energy_aware) + goto free; + /* EAS is enabled for asymmetric CPU capacity topologies. */ if (!per_cpu(sd_asym_cpucapacity, cpu)) { if (sched_debug()) { diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ba4d9e85feb8..987ae08147bf 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -467,6 +467,17 @@ static struct ctl_table kern_table[] = { .extra1 = &one, }, #endif +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) + { + .procname = "sched_energy_aware", + .data = &sysctl_sched_energy_aware, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_energy_aware_handler, + .extra1 = &zero, + .extra2 = &one, + }, +#endif #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", -- cgit v1.2.3 From 31954cd8bb667030b1c0d3d77f28fe71f06999f9 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 25 Jan 2019 10:53:19 -0800 Subject: tcp: Refactor pingpong code Instead of using pingpong as a single bit information, we refactor the code to treat it as a counter. When interactive session is detected, we set pingpong count to TCP_PINGPONG_THRESH. And when pingpong count is >= TCP_PINGPONG_THRESH, we consider the session in pingpong mode. This patch is a pure refactor and sets foundation for the next patch. This patch itself does not change any pingpong logic. Signed-off-by: Wei Wang Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 17 +++++++++++++++++ net/dccp/input.c | 2 +- net/dccp/timer.c | 4 ++-- net/ipv4/tcp.c | 10 +++++----- net/ipv4/tcp_input.c | 8 ++++---- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_output.c | 4 ++-- net/ipv4/tcp_timer.c | 4 ++-- net/ipv6/tcp_ipv6.c | 2 +- 9 files changed, 35 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index fe0d9b44d6fc..179609d1d1ea 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -314,4 +314,21 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); + +#define TCP_PINGPONG_THRESH 1 + +static inline void inet_csk_enter_pingpong_mode(struct sock *sk) +{ + inet_csk(sk)->icsk_ack.pingpong = TCP_PINGPONG_THRESH; +} + +static inline void inet_csk_exit_pingpong_mode(struct sock *sk) +{ + inet_csk(sk)->icsk_ack.pingpong = 0; +} + +static inline bool inet_csk_in_pingpong_mode(struct sock *sk) +{ + return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; +} #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/net/dccp/input.c b/net/dccp/input.c index 85d6c879383d..8d03707abdac 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -480,7 +480,7 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); } - if (sk->sk_write_pending || icsk->icsk_ack.pingpong || + if (sk->sk_write_pending || inet_csk_in_pingpong_mode(sk) || icsk->icsk_accept_queue.rskq_defer_accept) { /* Save one ACK. Data will be ready after * several ticks, if write_pending is set. diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 1501a20a94ca..74e138495d67 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -199,7 +199,7 @@ static void dccp_delack_timer(struct timer_list *t) icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { - if (!icsk->icsk_ack.pingpong) { + if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto); @@ -207,7 +207,7 @@ static void dccp_delack_timer(struct timer_list *t) /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ - icsk->icsk_ack.pingpong = 0; + inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } dccp_send_ack(sk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 12ba21433dd0..6f8d292ad501 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1551,7 +1551,7 @@ static void tcp_cleanup_rbuf(struct sock *sk, int copied) (copied > 0 && ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && - !icsk->icsk_ack.pingpong)) && + !inet_csk_in_pingpong_mode(sk))) && !atomic_read(&sk->sk_rmem_alloc))) time_to_ack = true; } @@ -2984,16 +2984,16 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_QUICKACK: if (!val) { - icsk->icsk_ack.pingpong = 1; + inet_csk_enter_pingpong_mode(sk); } else { - icsk->icsk_ack.pingpong = 0; + inet_csk_exit_pingpong_mode(sk); if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && inet_csk_ack_scheduled(sk)) { icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; tcp_cleanup_rbuf(sk, 1); if (!(val & 1)) - icsk->icsk_ack.pingpong = 1; + inet_csk_enter_pingpong_mode(sk); } } break; @@ -3407,7 +3407,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return 0; } case TCP_QUICKACK: - val = !icsk->icsk_ack.pingpong; + val = !inet_csk_in_pingpong_mode(sk); break; case TCP_CONGESTION: diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 76858b14ebe9..7a027dec649b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -221,7 +221,7 @@ void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) struct inet_connection_sock *icsk = inet_csk(sk); tcp_incr_quickack(sk, max_quickacks); - icsk->icsk_ack.pingpong = 0; + inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } EXPORT_SYMBOL(tcp_enter_quickack_mode); @@ -236,7 +236,7 @@ static bool tcp_in_quickack_mode(struct sock *sk) const struct dst_entry *dst = __sk_dst_get(sk); return (dst && dst_metric(dst, RTAX_QUICKACK)) || - (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong); + (icsk->icsk_ack.quick && !inet_csk_in_pingpong_mode(sk)); } static void tcp_ecn_queue_cwr(struct tcp_sock *tp) @@ -4094,7 +4094,7 @@ void tcp_fin(struct sock *sk) case TCP_ESTABLISHED: /* Move to CLOSE_WAIT */ tcp_set_state(sk, TCP_CLOSE_WAIT); - inet_csk(sk)->icsk_ack.pingpong = 1; + inet_csk_enter_pingpong_mode(sk); break; case TCP_CLOSE_WAIT: @@ -5889,7 +5889,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, return -1; if (sk->sk_write_pending || icsk->icsk_accept_queue.rskq_defer_accept || - icsk->icsk_ack.pingpong) { + inet_csk_in_pingpong_mode(sk)) { /* Save one ACK. Data will be ready after * several ticks, if write_pending is set. * diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index efc6fef692ff..662b034f1795 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2437,7 +2437,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), - (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sk), tp->snd_cwnd, state == TCP_LISTEN ? fastopenq->max_qlen : diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 26a2948dca95..06228e2d010e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -171,7 +171,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, * packet, enter pingpong mode. */ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) - icsk->icsk_ack.pingpong = 1; + inet_csk_enter_pingpong_mode(sk); } /* Account for an ACK we sent. */ @@ -3569,7 +3569,7 @@ void tcp_send_delayed_ack(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; - if (icsk->icsk_ack.pingpong || + if (inet_csk_in_pingpong_mode(sk) || (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)) max_ato = TCP_DELACK_MAX; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d7399a89469d..f0c86398e6a7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -277,14 +277,14 @@ void tcp_delack_timer_handler(struct sock *sk) icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { - if (!icsk->icsk_ack.pingpong) { + if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ - icsk->icsk_ack.pingpong = 0; + inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } tcp_mstamp_refresh(tcp_sk(sk)); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b81eb7cb815e..e51cda79f0cc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1864,7 +1864,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) refcount_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), - (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp), tp->snd_cwnd, state == TCP_LISTEN ? fastopenq->max_qlen : -- cgit v1.2.3 From 4a41f453bedfd5e9cd040bad509d9da49feb3e2c Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 25 Jan 2019 10:53:20 -0800 Subject: tcp: change pingpong threshold to 3 In order to be more confident about an on-going interactive session, we increment pingpong count by 1 for every interactive transaction and we adjust TCP_PINGPONG_THRESH to 3. This means, we only consider a session in pingpong mode after we see 3 interactive transactions, and start to activate delayed acks in quick ack mode. And in order to not over-count the credits, we only increase pingpong count for the first packet sent in response for the previous received packet. This is mainly to prevent delaying the ack immediately after some handshake protocol but no real interactive traffic pattern afterwards. Signed-off-by: Wei Wang Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 10 +++++++++- net/ipv4/tcp_output.c | 15 +++++++++------ 2 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 179609d1d1ea..ff40e1d08157 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -315,7 +315,7 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); -#define TCP_PINGPONG_THRESH 1 +#define TCP_PINGPONG_THRESH 3 static inline void inet_csk_enter_pingpong_mode(struct sock *sk) { @@ -331,4 +331,12 @@ static inline bool inet_csk_in_pingpong_mode(struct sock *sk) { return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; } + +static inline void inet_csk_inc_pingpong_cnt(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ack.pingpong < U8_MAX) + icsk->icsk_ack.pingpong++; +} #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 06228e2d010e..96bdb8eae9bb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -165,13 +165,16 @@ static void tcp_event_data_sent(struct tcp_sock *tp, if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); - tp->lsndtime = now; - - /* If it is a reply for ato after last received - * packet, enter pingpong mode. + /* If this is the first data packet sent in response to the + * previous received data, + * and it is a reply for ato after last received packet, + * increase pingpong count. */ - if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) - inet_csk_enter_pingpong_mode(sk); + if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) && + (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) + inet_csk_inc_pingpong_cnt(sk); + + tp->lsndtime = now; } /* Account for an ACK we sent. */ -- cgit v1.2.3 From fe19a8fea7cb59f202ddd30ec2fa9f5bd907b3d2 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Sat, 19 Jan 2019 15:22:38 +0100 Subject: ipvs: avoid indirect calls when calculating checksums The function pointer ip_vs_protocol->csum_check is only used in protocol specific code, and never in the generic one. Remove the function pointer from struct ip_vs_protocol and call the checksum functions directly. This reduces the performance impact of the Spectre mitigation, and should give a small improvement even with RETPOLINES disabled. Signed-off-by: Matteo Croce Acked-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 3 --- net/netfilter/ipvs/ip_vs_proto_ah_esp.c | 2 -- net/netfilter/ipvs/ip_vs_proto_sctp.c | 8 +++++--- net/netfilter/ipvs/ip_vs_proto_tcp.c | 12 +++++++----- net/netfilter/ipvs/ip_vs_proto_udp.c | 12 +++++++----- 5 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a0d2e0bb9a94..047f9a5ccaad 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -453,9 +453,6 @@ struct ip_vs_protocol { int (*dnat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph); - int (*csum_check)(int af, struct sk_buff *skb, - struct ip_vs_protocol *pp); - const char *(*state_name)(int state); void (*state_transition)(struct ip_vs_conn *cp, int direction, diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 5320d39976e1..480598cb0f05 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -129,7 +129,6 @@ struct ip_vs_protocol ip_vs_protocol_ah = { .conn_out_get = ah_esp_conn_out_get, .snat_handler = NULL, .dnat_handler = NULL, - .csum_check = NULL, .state_transition = NULL, .register_app = NULL, .unregister_app = NULL, @@ -152,7 +151,6 @@ struct ip_vs_protocol ip_vs_protocol_esp = { .conn_out_get = ah_esp_conn_out_get, .snat_handler = NULL, .dnat_handler = NULL, - .csum_check = NULL, .state_transition = NULL, .register_app = NULL, .unregister_app = NULL, diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index b0cd7d08f2a7..bc3d1625ecc8 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -9,6 +9,9 @@ #include #include +static int +sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); + static int sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, @@ -105,7 +108,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!sctp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ @@ -152,7 +155,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!sctp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ @@ -587,7 +590,6 @@ struct ip_vs_protocol ip_vs_protocol_sctp = { .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = sctp_snat_handler, .dnat_handler = sctp_dnat_handler, - .csum_check = sctp_csum_check, .state_name = sctp_state_name, .state_transition = sctp_state_transition, .app_conn_bind = sctp_app_conn_bind, diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 1770fc6ce960..6a275f989085 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -31,6 +31,9 @@ #include +static int +tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); + static int tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, @@ -166,7 +169,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ @@ -192,7 +195,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = (cp->app && pp->csum_check) ? + skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -244,7 +247,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* @@ -275,7 +278,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = (cp->app && pp->csum_check) ? + skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -736,7 +739,6 @@ struct ip_vs_protocol ip_vs_protocol_tcp = { .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = tcp_snat_handler, .dnat_handler = tcp_dnat_handler, - .csum_check = tcp_csum_check, .state_name = tcp_state_name, .state_transition = tcp_state_transition, .app_conn_bind = tcp_app_conn_bind, diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 0f53c49025f8..3285718264d5 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -28,6 +28,9 @@ #include #include +static int +udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); + static int udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, @@ -156,7 +159,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!udp_csum_check(cp->af, skb, pp)) return 0; /* @@ -186,7 +189,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, udp_fast_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = (cp->app && pp->csum_check) ? + skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -239,7 +242,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!udp_csum_check(cp->af, skb, pp)) return 0; /* @@ -270,7 +273,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, udp_fast_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = (cp->app && pp->csum_check) ? + skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -494,7 +497,6 @@ struct ip_vs_protocol ip_vs_protocol_udp = { .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = udp_snat_handler, .dnat_handler = udp_dnat_handler, - .csum_check = udp_csum_check, .state_transition = udp_state_transition, .state_name = udp_state_name, .register_app = udp_register_app, -- cgit v1.2.3 From 4cab5bf616f6513b2111ce80f634a9a07c037a0a Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Mon, 21 Jan 2019 18:10:42 -0800 Subject: dt-bindings: reset: imx7: Document usage on i.MX8MQ SoCs The driver now supports i.MX8MQ, so update bindings accordingly. Cc: p.zabel@pengutronix.de Cc: Fabio Estevam Cc: cphealy@gmail.com Cc: l.stach@pengutronix.de Cc: Leonard Crestez Cc: "A.s. Dong" Cc: Richard Zhu Cc: linux-imx@nxp.com Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Rob Herring Signed-off-by: Andrey Smirnov Signed-off-by: Philipp Zabel --- .../devicetree/bindings/reset/fsl,imx7-src.txt | 7 ++- include/dt-bindings/reset/imx8mq-reset.h | 64 ++++++++++++++++++++++ 2 files changed, 69 insertions(+), 2 deletions(-) create mode 100644 include/dt-bindings/reset/imx8mq-reset.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/reset/fsl,imx7-src.txt b/Documentation/devicetree/bindings/reset/fsl,imx7-src.txt index 1ab1d109318e..2ecf33815d18 100644 --- a/Documentation/devicetree/bindings/reset/fsl,imx7-src.txt +++ b/Documentation/devicetree/bindings/reset/fsl,imx7-src.txt @@ -5,7 +5,9 @@ Please also refer to reset.txt in this directory for common reset controller binding usage. Required properties: -- compatible: Should be "fsl,imx7d-src", "syscon" +- compatible: + - For i.MX7 SoCs should be "fsl,imx7d-src", "syscon" + - For i.MX8MQ SoCs should be "fsl,imx8mq-src", "syscon" - reg: should be register base and length as documented in the datasheet - interrupts: Should contain SRC interrupt @@ -44,4 +46,5 @@ Example: For list of all valid reset indicies see - + for i.MX7 and + for i.MX8MQ diff --git a/include/dt-bindings/reset/imx8mq-reset.h b/include/dt-bindings/reset/imx8mq-reset.h new file mode 100644 index 000000000000..57c592498aa0 --- /dev/null +++ b/include/dt-bindings/reset/imx8mq-reset.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 Zodiac Inflight Innovations + * + * Author: Andrey Smirnov + */ + +#ifndef DT_BINDING_RESET_IMX8MQ_H +#define DT_BINDING_RESET_IMX8MQ_H + +#define IMX8MQ_RESET_A53_CORE_POR_RESET0 0 +#define IMX8MQ_RESET_A53_CORE_POR_RESET1 1 +#define IMX8MQ_RESET_A53_CORE_POR_RESET2 2 +#define IMX8MQ_RESET_A53_CORE_POR_RESET3 3 +#define IMX8MQ_RESET_A53_CORE_RESET0 4 +#define IMX8MQ_RESET_A53_CORE_RESET1 5 +#define IMX8MQ_RESET_A53_CORE_RESET2 6 +#define IMX8MQ_RESET_A53_CORE_RESET3 7 +#define IMX8MQ_RESET_A53_DBG_RESET0 8 +#define IMX8MQ_RESET_A53_DBG_RESET1 9 +#define IMX8MQ_RESET_A53_DBG_RESET2 10 +#define IMX8MQ_RESET_A53_DBG_RESET3 11 +#define IMX8MQ_RESET_A53_ETM_RESET0 12 +#define IMX8MQ_RESET_A53_ETM_RESET1 13 +#define IMX8MQ_RESET_A53_ETM_RESET2 14 +#define IMX8MQ_RESET_A53_ETM_RESET3 15 +#define IMX8MQ_RESET_A53_SOC_DBG_RESET 16 +#define IMX8MQ_RESET_A53_L2RESET 17 +#define IMX8MQ_RESET_SW_NON_SCLR_M4C_RST 18 +#define IMX8MQ_RESET_OTG1_PHY_RESET 19 +#define IMX8MQ_RESET_OTG2_PHY_RESET 20 +#define IMX8MQ_RESET_MIPI_DSI_RESET_BYTE_N 21 +#define IMX8MQ_RESET_MIPI_DSI_RESET_N 22 +#define IMX8MQ_RESET_MIPI_DIS_DPI_RESET_N 23 +#define IMX8MQ_RESET_MIPI_DIS_ESC_RESET_N 24 +#define IMX8MQ_RESET_MIPI_DIS_PCLK_RESET_N 25 +#define IMX8MQ_RESET_PCIEPHY 26 +#define IMX8MQ_RESET_PCIEPHY_PERST 27 +#define IMX8MQ_RESET_PCIE_CTRL_APPS_EN 28 +#define IMX8MQ_RESET_PCIE_CTRL_APPS_TURNOFF 29 +#define IMX8MQ_RESET_HDMI_PHY_APB_RESET 30 +#define IMX8MQ_RESET_DISP_RESET 31 +#define IMX8MQ_RESET_GPU_RESET 32 +#define IMX8MQ_RESET_VPU_RESET 33 +#define IMX8MQ_RESET_PCIEPHY2 34 +#define IMX8MQ_RESET_PCIEPHY2_PERST 35 +#define IMX8MQ_RESET_PCIE2_CTRL_APPS_EN 36 +#define IMX8MQ_RESET_PCIE2_CTRL_APPS_TURNOFF 37 +#define IMX8MQ_RESET_MIPI_CSI1_CORE_RESET 38 +#define IMX8MQ_RESET_MIPI_CSI1_PHY_REF_RESET 39 +#define IMX8MQ_RESET_MIPI_CSI1_ESC_RESET 40 +#define IMX8MQ_RESET_MIPI_CSI2_CORE_RESET 41 +#define IMX8MQ_RESET_MIPI_CSI2_PHY_REF_RESET 42 +#define IMX8MQ_RESET_MIPI_CSI2_ESC_RESET 43 +#define IMX8MQ_RESET_DDRC1_PRST 44 +#define IMX8MQ_RESET_DDRC1_CORE_RESET 45 +#define IMX8MQ_RESET_DDRC1_PHY_RESET 46 +#define IMX8MQ_RESET_DDRC2_PRST 47 +#define IMX8MQ_RESET_DDRC2_CORE_RESET 48 +#define IMX8MQ_RESET_DDRC2_PHY_RESET 49 + +#define IMX8MQ_RESET_NUM 50 + +#endif -- cgit v1.2.3 From fdce60787f6215607dc7ac910cbaf4416684b589 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 13 Dec 2018 12:22:32 +0100 Subject: reset: sunxi: declare sun6i_reset_init in a header file Avoid declaring extern functions in c files. To make sure function definition and usage don't get out of sync, declare sun6i_reset_init in a common header. Suggested-by: Stephen Rothwell Signed-off-by: Philipp Zabel --- arch/arm/mach-sunxi/sunxi.c | 2 +- drivers/reset/reset-sunxi.c | 1 + include/linux/reset/sunxi.h | 7 +++++++ 3 files changed, 9 insertions(+), 1 deletion(-) create mode 100644 include/linux/reset/sunxi.h (limited to 'include') diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c index 8a7f301839c2..933b6930f024 100644 --- a/arch/arm/mach-sunxi/sunxi.c +++ b/arch/arm/mach-sunxi/sunxi.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -37,7 +38,6 @@ static const char * const sun6i_board_dt_compat[] = { NULL, }; -extern void __init sun6i_reset_init(void); static void __init sun6i_timer_init(void) { of_clk_init(NULL); diff --git a/drivers/reset/reset-sunxi.c b/drivers/reset/reset-sunxi.c index db9a1a75523f..b06d724d8f21 100644 --- a/drivers/reset/reset-sunxi.c +++ b/drivers/reset/reset-sunxi.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/reset/sunxi.h b/include/linux/reset/sunxi.h new file mode 100644 index 000000000000..1ad7fffb413e --- /dev/null +++ b/include/linux/reset/sunxi.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_RESET_SUNXI_H__ +#define __LINUX_RESET_SUNXI_H__ + +void __init sun6i_reset_init(void); + +#endif /* __LINUX_RESET_SUNXI_H__ */ -- cgit v1.2.3 From cdbeb315ed8dcc142a68054899cedd6e4f1fea3f Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 13 Dec 2018 12:24:36 +0100 Subject: reset: socfpga: declare socfpga_reset_init in a header file Avoid declaring extern functions in c files. To make sure function definition and usage don't get out of sync, declare socfpga_reset_init in a common header. Suggested-by: Stephen Rothwell Signed-off-by: Philipp Zabel Acked-by: Dinh Nguyen --- arch/arm/mach-socfpga/socfpga.c | 3 +-- drivers/reset/reset-socfpga.c | 2 +- include/linux/reset/socfpga.h | 7 +++++++ 3 files changed, 9 insertions(+), 3 deletions(-) create mode 100644 include/linux/reset/socfpga.h (limited to 'include') diff --git a/arch/arm/mach-socfpga/socfpga.c b/arch/arm/mach-socfpga/socfpga.c index afd98971d903..816da0eb6616 100644 --- a/arch/arm/mach-socfpga/socfpga.c +++ b/arch/arm/mach-socfpga/socfpga.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -32,8 +33,6 @@ void __iomem *rst_manager_base_addr; void __iomem *sdr_ctl_base_addr; unsigned long socfpga_cpu1start_addr; -extern void __init socfpga_reset_init(void); - static void __init socfpga_sysmgr_init(void) { struct device_node *np; diff --git a/drivers/reset/reset-socfpga.c b/drivers/reset/reset-socfpga.c index 318cfc51c441..96953992c2bb 100644 --- a/drivers/reset/reset-socfpga.c +++ b/drivers/reset/reset-socfpga.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -18,7 +19,6 @@ #include "reset-simple.h" #define SOCFPGA_NR_BANKS 8 -void __init socfpga_reset_init(void); static int a10_reset_init(struct device_node *np) { diff --git a/include/linux/reset/socfpga.h b/include/linux/reset/socfpga.h new file mode 100644 index 000000000000..b11a2047c342 --- /dev/null +++ b/include/linux/reset/socfpga.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_RESET_SOCFPGA_H__ +#define __LINUX_RESET_SOCFPGA_H__ + +void __init socfpga_reset_init(void); + +#endif /* __LINUX_RESET_SOCFPGA_H__ */ -- cgit v1.2.3 From 83f529281d7aa42b10c2c5cb64fcbd2c7cab4409 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 27 Jan 2019 19:18:57 +0100 Subject: netfilter: ipv4: remove useless export_symbol Only one caller; place it where needed and get rid of the EXPORT_SYMBOL. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4.h | 6 ------ net/ipv4/netfilter.c | 18 ------------------ net/netfilter/utils.c | 19 +++++++++++++++++++ 3 files changed, 19 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 95ab5cc64422..082e2c41b7ff 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -25,7 +25,6 @@ __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); -int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry); #else static inline __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol) @@ -37,11 +36,6 @@ static inline int nf_ip_route(struct net *net, struct dst_entry **dst, { return -EOPNOTSUPP; } -static inline int nf_ip_reroute(struct sk_buff *skb, - const struct nf_queue_entry *entry) -{ - return -EOPNOTSUPP; -} #endif /* CONFIG_INET */ #endif /*__LINUX_IP_NETFILTER_H*/ diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 8d2e5dc9a827..a058213b77a7 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -80,24 +80,6 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t } EXPORT_SYMBOL(ip_route_me_harder); -int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) -{ - const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); - - if (entry->state.hook == NF_INET_LOCAL_OUT) { - const struct iphdr *iph = ip_hdr(skb); - - if (!(iph->tos == rt_info->tos && - skb->mark == rt_info->mark && - iph->daddr == rt_info->daddr && - iph->saddr == rt_info->saddr)) - return ip_route_me_harder(entry->state.net, skb, - RTN_UNSPEC); - } - return 0; -} -EXPORT_SYMBOL_GPL(nf_ip_reroute); - int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict __always_unused) { diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index e8da9a9bba73..55af9f247993 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -180,6 +180,25 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, } EXPORT_SYMBOL_GPL(nf_route); +static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) +{ +#ifdef CONFIG_INET + const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); + + if (entry->state.hook == NF_INET_LOCAL_OUT) { + const struct iphdr *iph = ip_hdr(skb); + + if (!(iph->tos == rt_info->tos && + skb->mark == rt_info->mark && + iph->daddr == rt_info->daddr && + iph->saddr == rt_info->saddr)) + return ip_route_me_harder(entry->state.net, skb, + RTN_UNSPEC); + } +#endif + return 0; +} + int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) { const struct nf_ipv6_ops *v6ops; -- cgit v1.2.3 From 5e484ec1758b95e6420787fc17f0e8c5e152c264 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 25 Jan 2019 14:16:17 -0600 Subject: ASoC: soc-acpi: add static inline fallbacks when CONFIG_ACPI=n Fix compilation issues reported by 0day-Kbuild with sparc64 w/ SOF. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index 266e64e3c24c..6cbbeed9cdd0 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -22,20 +22,37 @@ struct snd_soc_acpi_package_context { #define SND_ACPI_I2C_ID_LEN (4 + ACPI_ID_LEN + 3 + 1) #if IS_ENABLED(CONFIG_ACPI) +/* acpi match */ +struct snd_soc_acpi_mach * +snd_soc_acpi_find_machine(struct snd_soc_acpi_mach *machines); + bool snd_soc_acpi_find_package_from_hid(const u8 hid[ACPI_ID_LEN], struct snd_soc_acpi_package_context *ctx); + +/* check all codecs */ +struct snd_soc_acpi_mach *snd_soc_acpi_codec_list(void *arg); + #else +/* acpi match */ +static inline struct snd_soc_acpi_mach * +snd_soc_acpi_find_machine(struct snd_soc_acpi_mach *machines) +{ + return NULL; +} + static inline bool snd_soc_acpi_find_package_from_hid(const u8 hid[ACPI_ID_LEN], struct snd_soc_acpi_package_context *ctx) { return false; } -#endif -/* acpi match */ -struct snd_soc_acpi_mach * -snd_soc_acpi_find_machine(struct snd_soc_acpi_mach *machines); +/* check all codecs */ +static inline struct snd_soc_acpi_mach *snd_soc_acpi_codec_list(void *arg) +{ + return NULL; +} +#endif /** * snd_soc_acpi_mach_params: interface for machine driver configuration @@ -105,7 +122,4 @@ struct snd_soc_acpi_codecs { u8 codecs[SND_SOC_ACPI_MAX_CODECS][ACPI_ID_LEN]; }; -/* check all codecs */ -struct snd_soc_acpi_mach *snd_soc_acpi_codec_list(void *arg); - #endif -- cgit v1.2.3 From 87eff9af7efb154cc4a940ed12efc803a0bf3fba Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Tue, 22 Jan 2019 23:18:21 +0200 Subject: pinctrl: remove pinctrl/machine.h inclusion from pinctrl/pinconf.h The change adds explicit inclusion of linux/pinctrl/machine.h header to the only needed pinctrl-madera-core.c file, and therefore inclusion of pinctrl/machine.h header from pinctrl/pinconf.h can be removed. The change is preparatory to a follow-up reversal of commit f07512e615dd ("pinctrl/pinconfig: add debug interface"). Signed-off-by: Vladimir Zapolskiy Cc: Charles Keepax Reviewed-by Richard Fitzgerald Signed-off-by: Linus Walleij --- drivers/pinctrl/cirrus/pinctrl-madera-core.c | 1 + include/linux/pinctrl/pinconf.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/pinctrl/cirrus/pinctrl-madera-core.c b/drivers/pinctrl/cirrus/pinctrl-madera-core.c index a5dda832024a..7c9694593f79 100644 --- a/drivers/pinctrl/cirrus/pinctrl-madera-core.c +++ b/drivers/pinctrl/cirrus/pinctrl-madera-core.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h index 8dd85d302b90..109468d9d849 100644 --- a/include/linux/pinctrl/pinconf.h +++ b/include/linux/pinctrl/pinconf.h @@ -14,8 +14,6 @@ #ifdef CONFIG_PINCONF -#include - struct pinctrl_dev; struct seq_file; -- cgit v1.2.3 From e73339037f6b6d65e84f5fd42e56dd3cdf0d9e9c Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Tue, 22 Jan 2019 23:18:22 +0200 Subject: pinctrl: remove unused 'pinconf-config' debugfs interface The main goal of the change is to remove .pin_config_dbg_parse_modify callback before a driver with its support appears. So far the in-kernel interface did not attract any users since its introduction 5 years ago. Originally .pin_config_dbg_parse_modify callback and the associated 'pinconf-config' debugfs file were introduced in commit f07512e615dd ("pinctrl/pinconfig: add debug interface"), a short description of 'pinconf-config' usage for debugging can be expressed this way: Write to 'pinconf-config' (see pinconf_dbg_config_write() function): % echo -n modify $map_type $device_name $state_name $pin_name $config > \ /sys/kernel/debug/pinctrl/$pinctrl/pinconf-config It supposes to update a global (therefore single!) 'pinconf_dbg_conf' variable with an alternative setting, the arguments should match an existing pinconf device and some registered pinctrl mapping 'map': * $map_type is either 'config_pin' or 'config_group', it should match 'map->type' value of PIN_MAP_TYPE_CONFIGS_PIN or PIN_MAP_TYPE_CONFIGS_GROUP accordingly, * $device_name should match 'map->dev_name' string value, * $state_name should match 'map->name' string value, * $pin_name should match 'map->data.configs.group_or_pin' string value, If all above has matched, then $config is a new value to be set by calling pinconfops->pin_config_dbg_parse_modify(pctldev, config, matched_config). After a successful write into 'pinconf-config' a user can read the file to get information about that single modified pin configuration. The fact is .pin_config_dbg_parse_modify callback has never been defined in 'struct pinconf_ops' of any pinconf driver, thus an actual modification of a pin or group state on any present pinconf controller does not happen, and it declares that all related code is no more than dead code. I discovered the issue while attempting to add .pin_config_dbg_parse_modify support in some drivers and found that too short 'MAX_NAME_LEN' set by drivers/pinctrl/pinconf.c:372:#define MAX_NAME_LEN 15 is practically insufficient to store a regular pinctrl device name, which are like 'e6060000.pin-controller-sh-pfc' or pin names like 'MX6QDL_PAD_ENET_REF_CLK', thus it is another indicator that the code is barely usable, insufficiently tested and unprepossessing. Of course it might be possible to increase MAX_NAME_LEN, and then add .pin_config_dbg_parse_modify callbacks to the drivers, but the whole idea of such a limited debug option looks inviable. A more flexible way to functionally substitute the original approach is to implicitly or explicitly use pinctrl_select_state() function whenever needed. Signed-off-by: Vladimir Zapolskiy Cc: Laurent Meunier Cc: Masahiro Yamada Cc: Russell King Signed-off-by: Linus Walleij --- drivers/pinctrl/pinconf.c | 222 ---------------------------------------- include/linux/pinctrl/pinconf.h | 4 - 2 files changed, 226 deletions(-) (limited to 'include') diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c index 2c7229380f08..2678603df14b 100644 --- a/drivers/pinctrl/pinconf.c +++ b/drivers/pinctrl/pinconf.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -369,225 +368,6 @@ static int pinconf_groups_show(struct seq_file *s, void *what) DEFINE_SHOW_ATTRIBUTE(pinconf_pins); DEFINE_SHOW_ATTRIBUTE(pinconf_groups); -#define MAX_NAME_LEN 15 - -struct dbg_cfg { - enum pinctrl_map_type map_type; - char dev_name[MAX_NAME_LEN + 1]; - char state_name[MAX_NAME_LEN + 1]; - char pin_name[MAX_NAME_LEN + 1]; -}; - -/* - * Goal is to keep this structure as global in order to simply read the - * pinconf-config file after a write to check config is as expected - */ -static struct dbg_cfg pinconf_dbg_conf; - -/** - * pinconf_dbg_config_print() - display the pinctrl config from the pinctrl - * map, of the dev/pin/state that was last written to pinconf-config file. - * @s: string filled in with config description - * @d: not used - */ -static int pinconf_dbg_config_print(struct seq_file *s, void *d) -{ - struct pinctrl_maps *maps_node; - const struct pinctrl_map *map; - const struct pinctrl_map *found = NULL; - struct pinctrl_dev *pctldev; - struct dbg_cfg *dbg = &pinconf_dbg_conf; - int i; - - mutex_lock(&pinctrl_maps_mutex); - - /* Parse the pinctrl map and look for the elected pin/state */ - for_each_maps(maps_node, i, map) { - if (map->type != dbg->map_type) - continue; - if (strcmp(map->dev_name, dbg->dev_name)) - continue; - if (strcmp(map->name, dbg->state_name)) - continue; - - if (!strcmp(map->data.configs.group_or_pin, dbg->pin_name)) { - /* We found the right pin */ - found = map; - break; - } - } - - if (!found) { - seq_printf(s, "No config found for dev/state/pin, expected:\n"); - seq_printf(s, "Searched dev:%s\n", dbg->dev_name); - seq_printf(s, "Searched state:%s\n", dbg->state_name); - seq_printf(s, "Searched pin:%s\n", dbg->pin_name); - seq_printf(s, "Use: modify config_pin "\ - " \n"); - goto exit; - } - - pctldev = get_pinctrl_dev_from_devname(found->ctrl_dev_name); - seq_printf(s, "Dev %s has config of %s in state %s:\n", - dbg->dev_name, dbg->pin_name, dbg->state_name); - pinconf_show_config(s, pctldev, found->data.configs.configs, - found->data.configs.num_configs); - -exit: - mutex_unlock(&pinctrl_maps_mutex); - - return 0; -} - -/** - * pinconf_dbg_config_write() - modify the pinctrl config in the pinctrl - * map, of a dev/pin/state entry based on user entries to pinconf-config - * @user_buf: contains the modification request with expected format: - * modify - * modify is literal string, alternatives like add/delete not supported yet - * is the configuration to be changed. Supported configs are - * "config_pin" or "config_group", alternatives like config_mux are not - * supported yet. - * are values that should match the pinctrl-maps - * reflects the new config and is driver dependent - */ -static ssize_t pinconf_dbg_config_write(struct file *file, - const char __user *user_buf, size_t count, loff_t *ppos) -{ - struct pinctrl_maps *maps_node; - const struct pinctrl_map *map; - const struct pinctrl_map *found = NULL; - struct pinctrl_dev *pctldev; - const struct pinconf_ops *confops = NULL; - struct dbg_cfg *dbg = &pinconf_dbg_conf; - const struct pinctrl_map_configs *configs; - char config[MAX_NAME_LEN + 1]; - char buf[128]; - char *b = &buf[0]; - int buf_size; - char *token; - int i; - - /* Get userspace string and assure termination */ - buf_size = min(count, sizeof(buf) - 1); - if (copy_from_user(buf, user_buf, buf_size)) - return -EFAULT; - buf[buf_size] = 0; - - /* - * need to parse entry and extract parameters: - * modify configs_pin devicename state pinname newvalue - */ - - /* Get arg: 'modify' */ - token = strsep(&b, " "); - if (!token) - return -EINVAL; - if (strcmp(token, "modify")) - return -EINVAL; - - /* - * Get arg type: "config_pin" and "config_group" - * types are supported so far - */ - token = strsep(&b, " "); - if (!token) - return -EINVAL; - if (!strcmp(token, "config_pin")) - dbg->map_type = PIN_MAP_TYPE_CONFIGS_PIN; - else if (!strcmp(token, "config_group")) - dbg->map_type = PIN_MAP_TYPE_CONFIGS_GROUP; - else - return -EINVAL; - - /* get arg 'device_name' */ - token = strsep(&b, " "); - if (!token) - return -EINVAL; - if (strlen(token) >= MAX_NAME_LEN) - return -EINVAL; - strncpy(dbg->dev_name, token, MAX_NAME_LEN); - - /* get arg 'state_name' */ - token = strsep(&b, " "); - if (!token) - return -EINVAL; - if (strlen(token) >= MAX_NAME_LEN) - return -EINVAL; - strncpy(dbg->state_name, token, MAX_NAME_LEN); - - /* get arg 'pin_name' */ - token = strsep(&b, " "); - if (!token) - return -EINVAL; - if (strlen(token) >= MAX_NAME_LEN) - return -EINVAL; - strncpy(dbg->pin_name, token, MAX_NAME_LEN); - - /* get new_value of config' */ - token = strsep(&b, " "); - if (!token) - return -EINVAL; - if (strlen(token) >= MAX_NAME_LEN) - return -EINVAL; - strncpy(config, token, MAX_NAME_LEN); - - mutex_lock(&pinctrl_maps_mutex); - - /* Parse the pinctrl map and look for the selected dev/state/pin */ - for_each_maps(maps_node, i, map) { - if (strcmp(map->dev_name, dbg->dev_name)) - continue; - if (map->type != dbg->map_type) - continue; - if (strcmp(map->name, dbg->state_name)) - continue; - - /* we found the right pin / state, so overwrite config */ - if (!strcmp(map->data.configs.group_or_pin, dbg->pin_name)) { - found = map; - break; - } - } - - if (!found) { - count = -EINVAL; - goto exit; - } - - pctldev = get_pinctrl_dev_from_devname(found->ctrl_dev_name); - if (pctldev) - confops = pctldev->desc->confops; - - if (confops && confops->pin_config_dbg_parse_modify) { - configs = &found->data.configs; - for (i = 0; i < configs->num_configs; i++) { - confops->pin_config_dbg_parse_modify(pctldev, - config, - &configs->configs[i]); - } - } - -exit: - mutex_unlock(&pinctrl_maps_mutex); - - return count; -} - -static int pinconf_dbg_config_open(struct inode *inode, struct file *file) -{ - return single_open(file, pinconf_dbg_config_print, inode->i_private); -} - -static const struct file_operations pinconf_dbg_pinconfig_fops = { - .open = pinconf_dbg_config_open, - .write = pinconf_dbg_config_write, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; - void pinconf_init_device_debugfs(struct dentry *devroot, struct pinctrl_dev *pctldev) { @@ -595,8 +375,6 @@ void pinconf_init_device_debugfs(struct dentry *devroot, devroot, pctldev, &pinconf_pins_fops); debugfs_create_file("pinconf-groups", S_IFREG | S_IRUGO, devroot, pctldev, &pinconf_groups_fops); - debugfs_create_file("pinconf-config", (S_IRUGO | S_IWUSR | S_IWGRP), - devroot, pctldev, &pinconf_dbg_pinconfig_fops); } #endif diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h index 109468d9d849..93c9dd133e9d 100644 --- a/include/linux/pinctrl/pinconf.h +++ b/include/linux/pinctrl/pinconf.h @@ -29,7 +29,6 @@ struct seq_file; * @pin_config_group_get: get configurations for an entire pin group; should * return -ENOTSUPP and -EINVAL using the same rules as pin_config_get. * @pin_config_group_set: configure all pins in a group - * @pin_config_dbg_parse_modify: optional debugfs to modify a pin configuration * @pin_config_dbg_show: optional debugfs display hook that will provide * per-device info for a certain pin in debugfs * @pin_config_group_dbg_show: optional debugfs display hook that will provide @@ -55,9 +54,6 @@ struct pinconf_ops { unsigned selector, unsigned long *configs, unsigned num_configs); - int (*pin_config_dbg_parse_modify) (struct pinctrl_dev *pctldev, - const char *arg, - unsigned long *config); void (*pin_config_dbg_show) (struct pinctrl_dev *pctldev, struct seq_file *s, unsigned offset); -- cgit v1.2.3 From cb50358b83846e4dcb37137c431327c4dd68561b Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 25 Jan 2019 14:34:55 -0600 Subject: ASoC: add helper to change platform name for all dailinks To reuse the same machine drivers with Atom/SST, Skylake and SOF, we need to change the default platform_name (or platforms->name in the "modern" representation). So far, this override was done with an automatic override, which was broken by a set of changes for DT platforms related to deferred probe handling. This automatic override is actually not really needed, the machine driver can already receive the platform name as a platform_data parameter. This is used e.g. for HDaudio support where we have different PCI aliases used for different platforms. We can reuse the same mechanism and modify the machine drivers to override the dailinks prior to registrating the card. This will require additional work for SOF, but with this helper it'll be just two lines of additional code per machine driver which is reused, not the end of the world. This helper can be simplified when all drivers have transitioned to the "modern" representation of dailinks. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Mark Brown --- include/sound/soc.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 3089257ead95..95689680336b 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1580,6 +1580,37 @@ struct snd_soc_dai *snd_soc_card_get_codec_dai(struct snd_soc_card *card, return NULL; } +static inline +int snd_soc_fixup_dai_links_platform_name(struct snd_soc_card *card, + const char *platform_name) +{ + struct snd_soc_dai_link *dai_link; + const char *name; + int i; + + if (!platform_name) /* nothing to do */ + return 0; + + /* set platform name for each dailink */ + for_each_card_prelinks(card, i, dai_link) { + name = devm_kstrdup(card->dev, platform_name, GFP_KERNEL); + if (!name) + return -ENOMEM; + + if (dai_link->platforms) + /* only single platform is supported for now */ + dai_link->platforms->name = name; + else + /* + * legacy mode, this case will be removed when all + * derivers are switched to modern style dai_link. + */ + dai_link->platform_name = name; + } + + return 0; +} + #ifdef CONFIG_DEBUG_FS extern struct dentry *snd_soc_debugfs_root; #endif -- cgit v1.2.3 From 64515dc899df898991b2b7e56f69f56f014ea888 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Mon, 28 Jan 2019 19:27:55 +0200 Subject: qed: Add infrastructure for error detection and recovery This patch adds the detection and handling of a parity error ("process kill event"), including the update of the protocol drivers, and the prevention of any HW access that will lead to device access towards the host while recovery is in progress. It also provides the means for the protocol drivers to trigger a recovery process on their decision. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed.h | 4 ++ drivers/net/ethernet/qlogic/qed/qed_dev.c | 41 +++++++---- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_hw.c | 11 +++ drivers/net/ethernet/qlogic/qed/qed_main.c | 30 ++++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.c | 94 ++++++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.h | 32 +++++++++ drivers/net/ethernet/qlogic/qed/qed_reg_addr.h | 2 + drivers/net/ethernet/qlogic/qed/qed_spq.c | 22 ++++++ drivers/net/ethernet/qlogic/qed/qed_sriov.c | 9 ++- include/linux/qed/qed_if.h | 20 ++++++ 11 files changed, 251 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index b352e313e1f6..3b0955d34716 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -804,6 +804,9 @@ struct qed_dev { u32 mcp_nvm_resp; + /* Recovery */ + bool recov_in_prog; + /* Linux specific here */ struct qede_dev *edev; struct pci_dev *pdev; @@ -943,6 +946,7 @@ void qed_link_update(struct qed_hwfn *hwfn, struct qed_ptt *ptt); u32 qed_unzip_data(struct qed_hwfn *p_hwfn, u32 input_len, u8 *input_buf, u32 max_size, u8 *unzip_buf); +void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn); void qed_get_protocol_stats(struct qed_dev *cdev, enum qed_mcp_protocol_type type, union qed_mcp_protocol_stats *stats); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index fa5f07e65672..b17003d9066c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -2140,6 +2140,11 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) "Load request was sent. Load code: 0x%x\n", load_code); + /* Only relevant for recovery: + * Clear the indication after LOAD_REQ is responded by the MFW. + */ + cdev->recov_in_prog = false; + qed_mcp_set_capabilities(p_hwfn, p_hwfn->p_main_ptt); qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt); @@ -2291,6 +2296,9 @@ static void qed_hw_timers_stop(struct qed_dev *cdev, qed_wr(p_hwfn, p_ptt, TM_REG_PF_ENABLE_CONN, 0x0); qed_wr(p_hwfn, p_ptt, TM_REG_PF_ENABLE_TASK, 0x0); + if (cdev->recov_in_prog) + return; + for (i = 0; i < QED_HW_STOP_RETRY_LIMIT; i++) { if ((!qed_rd(p_hwfn, p_ptt, TM_REG_PF_SCAN_ACTIVE_CONN)) && @@ -2353,12 +2361,14 @@ int qed_hw_stop(struct qed_dev *cdev) p_hwfn->hw_init_done = false; /* Send unload command to MCP */ - rc = qed_mcp_unload_req(p_hwfn, p_ptt); - if (rc) { - DP_NOTICE(p_hwfn, - "Failed sending a UNLOAD_REQ command. rc = %d.\n", - rc); - rc2 = -EINVAL; + if (!cdev->recov_in_prog) { + rc = qed_mcp_unload_req(p_hwfn, p_ptt); + if (rc) { + DP_NOTICE(p_hwfn, + "Failed sending a UNLOAD_REQ command. rc = %d.\n", + rc); + rc2 = -EINVAL; + } } qed_slowpath_irq_sync(p_hwfn); @@ -2400,16 +2410,18 @@ int qed_hw_stop(struct qed_dev *cdev) qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_DB_ENABLE, 0); qed_wr(p_hwfn, p_ptt, QM_REG_PF_EN, 0); - qed_mcp_unload_done(p_hwfn, p_ptt); - if (rc) { - DP_NOTICE(p_hwfn, - "Failed sending a UNLOAD_DONE command. rc = %d.\n", - rc); - rc2 = -EINVAL; + if (!cdev->recov_in_prog) { + rc = qed_mcp_unload_done(p_hwfn, p_ptt); + if (rc) { + DP_NOTICE(p_hwfn, + "Failed sending a UNLOAD_DONE command. rc = %d.\n", + rc); + rc2 = -EINVAL; + } } } - if (IS_PF(cdev)) { + if (IS_PF(cdev) && !cdev->recov_in_prog) { p_hwfn = QED_LEADING_HWFN(cdev); p_ptt = QED_LEADING_HWFN(cdev)->p_main_ptt; @@ -3459,6 +3471,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn, void __iomem *p_doorbells, enum qed_pci_personality personality) { + struct qed_dev *cdev = p_hwfn->cdev; int rc = 0; /* Split PCI bars evenly between hwfns */ @@ -3511,7 +3524,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn, /* Sending a mailbox to the MFW should be done after qed_get_hw_info() * is called as it sets the ports number in an engine. */ - if (IS_LEAD_HWFN(p_hwfn)) { + if (IS_LEAD_HWFN(p_hwfn) && !cdev->recov_in_prog) { rc = qed_mcp_initiate_pf_flr(p_hwfn, p_hwfn->p_main_ptt); if (rc) DP_NOTICE(p_hwfn, "Failed to initiate PF FLR\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index b13cfb449d8f..417121e74ee9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -12827,7 +12827,7 @@ enum MFW_DRV_MSG_TYPE { MFW_DRV_MSG_LLDP_DATA_UPDATED, MFW_DRV_MSG_DCBX_REMOTE_MIB_UPDATED, MFW_DRV_MSG_DCBX_OPERATIONAL_MIB_UPDATED, - MFW_DRV_MSG_RESERVED4, + MFW_DRV_MSG_ERROR_RECOVERY, MFW_DRV_MSG_BW_UPDATE, MFW_DRV_MSG_S_TAG_UPDATE, MFW_DRV_MSG_GET_LAN_STATS, diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c index 70504dcf4087..72ec1c6bdf70 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hw.c +++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c @@ -703,6 +703,17 @@ static int qed_dmae_execute_command(struct qed_hwfn *p_hwfn, int qed_status = 0; u32 offset = 0; + if (p_hwfn->cdev->recov_in_prog) { + DP_VERBOSE(p_hwfn, + NETIF_MSG_HW, + "Recovery is in progress. Avoid DMAE transaction [{src: addr 0x%llx, type %d}, {dst: addr 0x%llx, type %d}, size %d].\n", + src_addr, src_type, dst_addr, dst_type, + size_in_dwords); + + /* Let the flow complete w/o any error handling */ + return 0; + } + qed_dmae_opcode(p_hwfn, (src_type == QED_DMAE_ADDRESS_GRC), (dst_type == QED_DMAE_ADDRESS_GRC), diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 6adf5bda9811..b47352643fb5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -359,6 +359,8 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev, qed_init_dp(cdev, params->dp_module, params->dp_level); + cdev->recov_in_prog = params->recov_in_prog; + rc = qed_init_pci(cdev, pdev); if (rc) { DP_ERR(cdev, "init pci failed\n"); @@ -2203,6 +2205,15 @@ static int qed_nvm_get_image(struct qed_dev *cdev, enum qed_nvm_images type, return qed_mcp_get_nvm_image(hwfn, type, buf, len); } +void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn) +{ + struct qed_common_cb_ops *ops = p_hwfn->cdev->protocol_ops.common; + void *cookie = p_hwfn->cdev->ops_cookie; + + if (ops && ops->schedule_recovery_handler) + ops->schedule_recovery_handler(cookie); +} + static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, void *handle) { @@ -2226,6 +2237,23 @@ static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode) return status; } +static int qed_recovery_process(struct qed_dev *cdev) +{ + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *p_ptt; + int rc = 0; + + p_ptt = qed_ptt_acquire(p_hwfn); + if (!p_ptt) + return -EAGAIN; + + rc = qed_start_recovery_process(p_hwfn, p_ptt); + + qed_ptt_release(p_hwfn, p_ptt); + + return rc; +} + static int qed_update_wol(struct qed_dev *cdev, bool enabled) { struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); @@ -2380,6 +2408,8 @@ const struct qed_common_ops qed_common_ops_pass = { .nvm_get_image = &qed_nvm_get_image, .set_coalesce = &qed_set_coalesce, .set_led = &qed_set_led, + .recovery_process = &qed_recovery_process, + .recovery_prolog = &qed_recovery_prolog, .update_drv_state = &qed_update_drv_state, .update_mac = &qed_update_mac, .update_mtu = &qed_update_mtu, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 1024484d7dd8..bb8541847aa5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1549,6 +1549,60 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up) return 0; } +u32 qed_get_process_kill_counter(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + u32 path_offsize_addr, path_offsize, path_addr, proc_kill_cnt; + + if (IS_VF(p_hwfn->cdev)) + return -EINVAL; + + path_offsize_addr = SECTION_OFFSIZE_ADDR(p_hwfn->mcp_info->public_base, + PUBLIC_PATH); + path_offsize = qed_rd(p_hwfn, p_ptt, path_offsize_addr); + path_addr = SECTION_ADDR(path_offsize, QED_PATH_ID(p_hwfn)); + + proc_kill_cnt = qed_rd(p_hwfn, p_ptt, + path_addr + + offsetof(struct public_path, process_kill)) & + PROCESS_KILL_COUNTER_MASK; + + return proc_kill_cnt; +} + +static void qed_mcp_handle_process_kill(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + struct qed_dev *cdev = p_hwfn->cdev; + u32 proc_kill_cnt; + + /* Prevent possible attentions/interrupts during the recovery handling + * and till its load phase, during which they will be re-enabled. + */ + qed_int_igu_disable_int(p_hwfn, p_ptt); + + DP_NOTICE(p_hwfn, "Received a process kill indication\n"); + + /* The following operations should be done once, and thus in CMT mode + * are carried out by only the first HW function. + */ + if (p_hwfn != QED_LEADING_HWFN(cdev)) + return; + + if (cdev->recov_in_prog) { + DP_NOTICE(p_hwfn, + "Ignoring the indication since a recovery process is already in progress\n"); + return; + } + + cdev->recov_in_prog = true; + + proc_kill_cnt = qed_get_process_kill_counter(p_hwfn, p_ptt); + DP_NOTICE(p_hwfn, "Process kill counter: %d\n", proc_kill_cnt); + + qed_schedule_recovery_handler(p_hwfn); +} + static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, enum MFW_DRV_MSG_TYPE type) @@ -1779,6 +1833,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn, case MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE: qed_mcp_handle_transceiver_change(p_hwfn, p_ptt); break; + case MFW_DRV_MSG_ERROR_RECOVERY: + qed_mcp_handle_process_kill(p_hwfn, p_ptt); + break; case MFW_DRV_MSG_GET_LAN_STATS: case MFW_DRV_MSG_GET_FCOE_STATS: case MFW_DRV_MSG_GET_ISCSI_STATS: @@ -2324,6 +2381,43 @@ int qed_mcp_get_flash_size(struct qed_hwfn *p_hwfn, return 0; } +int qed_start_recovery_process(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) +{ + struct qed_dev *cdev = p_hwfn->cdev; + + if (cdev->recov_in_prog) { + DP_NOTICE(p_hwfn, + "Avoid triggering a recovery since such a process is already in progress\n"); + return -EAGAIN; + } + + DP_NOTICE(p_hwfn, "Triggering a recovery process\n"); + qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_GENERAL_ATTN_35, 0x1); + + return 0; +} + +#define QED_RECOVERY_PROLOG_SLEEP_MS 100 + +int qed_recovery_prolog(struct qed_dev *cdev) +{ + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *p_ptt = p_hwfn->p_main_ptt; + int rc; + + /* Allow ongoing PCIe transactions to complete */ + msleep(QED_RECOVERY_PROLOG_SLEEP_MS); + + /* Clear the PF's internal FID_enable in the PXP */ + rc = qed_pglueb_set_pfid_enable(p_hwfn, p_ptt, false); + if (rc) + DP_NOTICE(p_hwfn, + "qed_pglueb_set_pfid_enable() failed. rc = %d.\n", + rc); + + return rc; +} + static int qed_mcp_config_vf_msix_bb(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u8 vf_id, u8 num) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 387c5e649136..6e1d72a669ae 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -440,6 +440,38 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_mcp_drv_version *p_ver); +/** + * @brief Read the MFW process kill counter + * + * @param p_hwfn + * @param p_ptt + * + * @return u32 + */ +u32 qed_get_process_kill_counter(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt); + +/** + * @brief Trigger a recovery process + * + * @param p_hwfn + * @param p_ptt + * + * @return int + */ +int qed_start_recovery_process(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); + +/** + * @brief A recovery handler must call this function as its first step. + * It is assumed that the handler is not run from an interrupt context. + * + * @param cdev + * @param p_ptt + * + * @return int + */ +int qed_recovery_prolog(struct qed_dev *cdev); + /** * @brief Notify MFW about the change in base device properties * diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index 8939ed6e08b7..5ce825ca5f24 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -518,6 +518,8 @@ 0x180824UL #define MISC_REG_AEU_GENERAL_ATTN_0 \ 0x008400UL +#define MISC_REG_AEU_GENERAL_ATTN_35 \ + 0x00848cUL #define CAU_REG_SB_ADDR_MEMORY \ 0x1c8000UL #define CAU_REG_SB_VAR_MEMORY \ diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index eb88bbc6b193..3e0f7c46bb1b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -790,6 +790,17 @@ static int qed_spq_pend_post(struct qed_hwfn *p_hwfn) SPQ_HIGH_PRI_RESERVE_DEFAULT); } +static void qed_spq_recov_set_ret_code(struct qed_spq_entry *p_ent, + u8 *fw_return_code) +{ + if (!fw_return_code) + return; + + if (p_ent->elem.hdr.protocol_id == PROTOCOLID_ROCE || + p_ent->elem.hdr.protocol_id == PROTOCOLID_IWARP) + *fw_return_code = RDMA_RETURN_OK; +} + /* Avoid overriding of SPQ entries when getting out-of-order completions, by * marking the completions in a bitmap and increasing the chain consumer only * for the first successive completed entries. @@ -825,6 +836,17 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, return -EINVAL; } + if (p_hwfn->cdev->recov_in_prog) { + DP_VERBOSE(p_hwfn, + QED_MSG_SPQ, + "Recovery is in progress. Skip spq post [cmd %02x protocol %02x]\n", + p_ent->elem.hdr.cmd_id, p_ent->elem.hdr.protocol_id); + + /* Let the flow complete w/o any error handling */ + qed_spq_recov_set_ret_code(p_ent, fw_return_code); + return 0; + } + /* Complete the entry */ rc = qed_spq_fill_entry(p_hwfn, p_ent); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index ca6290fa0f30..71e28be58102 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -4447,6 +4447,13 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled) if (cdev->p_iov_info && cdev->p_iov_info->num_vfs && pci_enabled) pci_disable_sriov(cdev->pdev); + if (cdev->recov_in_prog) { + DP_VERBOSE(cdev, + QED_MSG_IOV, + "Skip SRIOV disable operations in the device since a recovery is in progress\n"); + goto out; + } + for_each_hwfn(cdev, i) { struct qed_hwfn *hwfn = &cdev->hwfns[i]; struct qed_ptt *ptt = qed_ptt_acquire(hwfn); @@ -4486,7 +4493,7 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled) qed_ptt_release(hwfn, ptt); } - +out: qed_iov_set_vfs_to_disable(cdev, false); return 0; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 5f818fda96bd..35170f74ed80 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -763,6 +763,7 @@ struct qed_probe_params { u32 dp_module; u8 dp_level; bool is_vf; + bool recov_in_prog; }; #define QED_DRV_VER_STR_SIZE 12 @@ -809,6 +810,7 @@ struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); + void (*schedule_recovery_handler)(void *dev); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); @@ -1056,6 +1058,24 @@ struct qed_common_ops { int (*db_recovery_del)(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); +/** + * @brief recovery_process - Trigger a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_process)(struct qed_dev *cdev); + +/** + * @brief recovery_prolog - Execute the prolog operations of a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_prolog)(struct qed_dev *cdev); + /** * @brief update_drv_state - API to inform the change in the driver state. * -- cgit v1.2.3 From ccc67ef50b9085b895738d7720840eb6fe98745e Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Mon, 28 Jan 2019 19:27:56 +0200 Subject: qede: Error recovery process This patch adds the error recovery process in the qede driver. The process includes a partial/customized driver unload and load, which allows it to look like a short suspend period to the kernel while preserving the net devices' state. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qede/qede.h | 3 + drivers/net/ethernet/qlogic/qede/qede_main.c | 292 ++++++++++++++++++++++----- drivers/net/ethernet/qlogic/qede/qede_rdma.c | 63 ++++-- include/linux/qed/qede_rdma.h | 10 +- 4 files changed, 294 insertions(+), 74 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 613249d1e967..843416404aeb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -162,6 +162,7 @@ struct qede_rdma_dev { struct list_head entry; struct list_head rdma_event_list; struct workqueue_struct *rdma_wq; + bool exp_recovery; }; struct qede_ptp; @@ -264,6 +265,7 @@ struct qede_dev { enum QEDE_STATE { QEDE_STATE_CLOSED, QEDE_STATE_OPEN, + QEDE_STATE_RECOVERY, }; #define HILO_U64(hi, lo) ((((u64)(hi)) << 32) + (lo)) @@ -462,6 +464,7 @@ struct qede_fastpath { #define QEDE_CSUM_UNNECESSARY BIT(1) #define QEDE_TUNN_CSUM_UNNECESSARY BIT(2) +#define QEDE_SP_RECOVERY 0 #define QEDE_SP_RX_MODE 1 #ifdef CONFIG_RFS_ACCEL diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 5a74fcbdbc2b..6b4d96635238 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -133,23 +133,12 @@ static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id); static void qede_remove(struct pci_dev *pdev); static void qede_shutdown(struct pci_dev *pdev); static void qede_link_update(void *dev, struct qed_link_output *link); +static void qede_schedule_recovery_handler(void *dev); +static void qede_recovery_handler(struct qede_dev *edev); static void qede_get_eth_tlv_data(void *edev, void *data); static void qede_get_generic_tlv_data(void *edev, struct qed_generic_tlvs *data); -/* The qede lock is used to protect driver state change and driver flows that - * are not reentrant. - */ -void __qede_lock(struct qede_dev *edev) -{ - mutex_lock(&edev->qede_lock); -} - -void __qede_unlock(struct qede_dev *edev) -{ - mutex_unlock(&edev->qede_lock); -} - #ifdef CONFIG_QED_SRIOV static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos, __be16 vlan_proto) @@ -231,6 +220,7 @@ static struct qed_eth_cb_ops qede_ll_ops = { .arfs_filter_op = qede_arfs_filter_op, #endif .link_update = qede_link_update, + .schedule_recovery_handler = qede_schedule_recovery_handler, .get_generic_tlv_data = qede_get_generic_tlv_data, .get_protocol_tlv_data = qede_get_eth_tlv_data, }, @@ -950,11 +940,57 @@ err: return -ENOMEM; } +/* The qede lock is used to protect driver state change and driver flows that + * are not reentrant. + */ +void __qede_lock(struct qede_dev *edev) +{ + mutex_lock(&edev->qede_lock); +} + +void __qede_unlock(struct qede_dev *edev) +{ + mutex_unlock(&edev->qede_lock); +} + +/* This version of the lock should be used when acquiring the RTNL lock is also + * needed in addition to the internal qede lock. + */ +void qede_lock(struct qede_dev *edev) +{ + rtnl_lock(); + __qede_lock(edev); +} + +void qede_unlock(struct qede_dev *edev) +{ + __qede_unlock(edev); + rtnl_unlock(); +} + static void qede_sp_task(struct work_struct *work) { struct qede_dev *edev = container_of(work, struct qede_dev, sp_task.work); + /* The locking scheme depends on the specific flag: + * In case of QEDE_SP_RECOVERY, acquiring the RTNL lock is required to + * ensure that ongoing flows are ended and new ones are not started. + * In other cases - only the internal qede lock should be acquired. + */ + + if (test_and_clear_bit(QEDE_SP_RECOVERY, &edev->sp_flags)) { +#ifdef CONFIG_QED_SRIOV + /* SRIOV must be disabled outside the lock to avoid a deadlock. + * The recovery of the active VFs is currently not supported. + */ + qede_sriov_configure(edev->pdev, 0); +#endif + qede_lock(edev); + qede_recovery_handler(edev); + qede_unlock(edev); + } + __qede_lock(edev); if (test_and_clear_bit(QEDE_SP_RX_MODE, &edev->sp_flags)) @@ -1031,6 +1067,7 @@ static void qede_log_probe(struct qede_dev *edev) enum qede_probe_mode { QEDE_PROBE_NORMAL, + QEDE_PROBE_RECOVERY, }; static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, @@ -1051,6 +1088,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, probe_params.dp_module = dp_module; probe_params.dp_level = dp_level; probe_params.is_vf = is_vf; + probe_params.recov_in_prog = (mode == QEDE_PROBE_RECOVERY); cdev = qed_ops->common->probe(pdev, &probe_params); if (!cdev) { rc = -ENODEV; @@ -1078,11 +1116,20 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, if (rc) goto err2; - edev = qede_alloc_etherdev(cdev, pdev, &dev_info, dp_module, - dp_level); - if (!edev) { - rc = -ENOMEM; - goto err2; + if (mode != QEDE_PROBE_RECOVERY) { + edev = qede_alloc_etherdev(cdev, pdev, &dev_info, dp_module, + dp_level); + if (!edev) { + rc = -ENOMEM; + goto err2; + } + } else { + struct net_device *ndev = pci_get_drvdata(pdev); + + edev = netdev_priv(ndev); + edev->cdev = cdev; + memset(&edev->stats, 0, sizeof(edev->stats)); + memcpy(&edev->dev_info, &dev_info, sizeof(dev_info)); } if (is_vf) @@ -1090,28 +1137,31 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, qede_init_ndev(edev); - rc = qede_rdma_dev_add(edev); + rc = qede_rdma_dev_add(edev, (mode == QEDE_PROBE_RECOVERY)); if (rc) goto err3; - /* Prepare the lock prior to the registration of the netdev, - * as once it's registered we might reach flows requiring it - * [it's even possible to reach a flow needing it directly - * from there, although it's unlikely]. - */ - INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task); - mutex_init(&edev->qede_lock); - rc = register_netdev(edev->ndev); - if (rc) { - DP_NOTICE(edev, "Cannot register net-device\n"); - goto err4; + if (mode != QEDE_PROBE_RECOVERY) { + /* Prepare the lock prior to the registration of the netdev, + * as once it's registered we might reach flows requiring it + * [it's even possible to reach a flow needing it directly + * from there, although it's unlikely]. + */ + INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task); + mutex_init(&edev->qede_lock); + + rc = register_netdev(edev->ndev); + if (rc) { + DP_NOTICE(edev, "Cannot register net-device\n"); + goto err4; + } } edev->ops->common->set_name(cdev, edev->ndev->name); /* PTP not supported on VFs */ if (!is_vf) - qede_ptp_enable(edev, true); + qede_ptp_enable(edev, (mode == QEDE_PROBE_NORMAL)); edev->ops->register_ops(cdev, &qede_ll_ops, edev); @@ -1126,7 +1176,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, return 0; err4: - qede_rdma_dev_remove(edev); + qede_rdma_dev_remove(edev, (mode == QEDE_PROBE_RECOVERY)); err3: free_netdev(edev->ndev); err2: @@ -1162,6 +1212,7 @@ static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id) enum qede_remove_mode { QEDE_REMOVE_NORMAL, + QEDE_REMOVE_RECOVERY, }; static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) @@ -1172,15 +1223,19 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) DP_INFO(edev, "Starting qede_remove\n"); - qede_rdma_dev_remove(edev); - unregister_netdev(ndev); - cancel_delayed_work_sync(&edev->sp_task); + qede_rdma_dev_remove(edev, (mode == QEDE_REMOVE_RECOVERY)); - qede_ptp_disable(edev); + if (mode != QEDE_REMOVE_RECOVERY) { + unregister_netdev(ndev); - edev->ops->common->set_power_state(cdev, PCI_D0); + cancel_delayed_work_sync(&edev->sp_task); - pci_set_drvdata(pdev, NULL); + edev->ops->common->set_power_state(cdev, PCI_D0); + + pci_set_drvdata(pdev, NULL); + } + + qede_ptp_disable(edev); /* Use global ops since we've freed edev */ qed_ops->common->slowpath_stop(cdev); @@ -1194,7 +1249,8 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) * [e.g., QED register callbacks] won't break anything when * accessing the netdevice. */ - free_netdev(ndev); + if (mode != QEDE_REMOVE_RECOVERY) + free_netdev(ndev); dev_info(&pdev->dev, "Ending qede_remove successfully\n"); } @@ -1539,6 +1595,58 @@ static int qede_alloc_mem_load(struct qede_dev *edev) return 0; } +static void qede_empty_tx_queue(struct qede_dev *edev, + struct qede_tx_queue *txq) +{ + unsigned int pkts_compl = 0, bytes_compl = 0; + struct netdev_queue *netdev_txq; + int rc, len = 0; + + netdev_txq = netdev_get_tx_queue(edev->ndev, txq->ndev_txq_id); + + while (qed_chain_get_cons_idx(&txq->tx_pbl) != + qed_chain_get_prod_idx(&txq->tx_pbl)) { + DP_VERBOSE(edev, NETIF_MSG_IFDOWN, + "Freeing a packet on tx queue[%d]: chain_cons 0x%x, chain_prod 0x%x\n", + txq->index, qed_chain_get_cons_idx(&txq->tx_pbl), + qed_chain_get_prod_idx(&txq->tx_pbl)); + + rc = qede_free_tx_pkt(edev, txq, &len); + if (rc) { + DP_NOTICE(edev, + "Failed to free a packet on tx queue[%d]: chain_cons 0x%x, chain_prod 0x%x\n", + txq->index, + qed_chain_get_cons_idx(&txq->tx_pbl), + qed_chain_get_prod_idx(&txq->tx_pbl)); + break; + } + + bytes_compl += len; + pkts_compl++; + txq->sw_tx_cons++; + } + + netdev_tx_completed_queue(netdev_txq, pkts_compl, bytes_compl); +} + +static void qede_empty_tx_queues(struct qede_dev *edev) +{ + int i; + + for_each_queue(i) + if (edev->fp_array[i].type & QEDE_FASTPATH_TX) { + int cos; + + for_each_cos_in_txq(edev, cos) { + struct qede_fastpath *fp; + + fp = &edev->fp_array[i]; + qede_empty_tx_queue(edev, + &fp->txq[cos]); + } + } +} + /* This function inits fp content and resets the SB, RXQ and TXQ structures */ static void qede_init_fp(struct qede_dev *edev) { @@ -2053,6 +2161,7 @@ out: enum qede_unload_mode { QEDE_UNLOAD_NORMAL, + QEDE_UNLOAD_RECOVERY, }; static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, @@ -2068,7 +2177,8 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, clear_bit(QEDE_FLAGS_LINK_REQUESTED, &edev->flags); - edev->state = QEDE_STATE_CLOSED; + if (mode != QEDE_UNLOAD_RECOVERY) + edev->state = QEDE_STATE_CLOSED; qede_rdma_dev_event_close(edev); @@ -2076,17 +2186,20 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, netif_tx_disable(edev->ndev); netif_carrier_off(edev->ndev); - /* Reset the link */ - memset(&link_params, 0, sizeof(link_params)); - link_params.link_up = false; - edev->ops->common->set_link(edev->cdev, &link_params); - rc = qede_stop_queues(edev); - if (rc) { - qede_sync_free_irqs(edev); - goto out; - } + if (mode != QEDE_UNLOAD_RECOVERY) { + /* Reset the link */ + memset(&link_params, 0, sizeof(link_params)); + link_params.link_up = false; + edev->ops->common->set_link(edev->cdev, &link_params); - DP_INFO(edev, "Stopped Queues\n"); + rc = qede_stop_queues(edev); + if (rc) { + qede_sync_free_irqs(edev); + goto out; + } + + DP_INFO(edev, "Stopped Queues\n"); + } qede_vlan_mark_nonconfigured(edev); edev->ops->fastpath_stop(edev->cdev); @@ -2102,18 +2215,26 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, qede_napi_disable_remove(edev); + if (mode == QEDE_UNLOAD_RECOVERY) + qede_empty_tx_queues(edev); + qede_free_mem_load(edev); qede_free_fp_array(edev); out: if (!is_locked) __qede_unlock(edev); + + if (mode != QEDE_UNLOAD_RECOVERY) + DP_NOTICE(edev, "Link is down\n"); + DP_INFO(edev, "Ending qede unload\n"); } enum qede_load_mode { QEDE_LOAD_NORMAL, QEDE_LOAD_RELOAD, + QEDE_LOAD_RECOVERY, }; static int qede_load(struct qede_dev *edev, enum qede_load_mode mode, @@ -2293,6 +2414,77 @@ static void qede_link_update(void *dev, struct qed_link_output *link) } } +static void qede_schedule_recovery_handler(void *dev) +{ + struct qede_dev *edev = dev; + + if (edev->state == QEDE_STATE_RECOVERY) { + DP_NOTICE(edev, + "Avoid scheduling a recovery handling since already in recovery state\n"); + return; + } + + set_bit(QEDE_SP_RECOVERY, &edev->sp_flags); + schedule_delayed_work(&edev->sp_task, 0); + + DP_INFO(edev, "Scheduled a recovery handler\n"); +} + +static void qede_recovery_failed(struct qede_dev *edev) +{ + netdev_err(edev->ndev, "Recovery handling has failed. Power cycle is needed.\n"); + + netif_device_detach(edev->ndev); + + if (edev->cdev) + edev->ops->common->set_power_state(edev->cdev, PCI_D3hot); +} + +static void qede_recovery_handler(struct qede_dev *edev) +{ + u32 curr_state = edev->state; + int rc; + + DP_NOTICE(edev, "Starting a recovery process\n"); + + /* No need to acquire first the qede_lock since is done by qede_sp_task + * before calling this function. + */ + edev->state = QEDE_STATE_RECOVERY; + + edev->ops->common->recovery_prolog(edev->cdev); + + if (curr_state == QEDE_STATE_OPEN) + qede_unload(edev, QEDE_UNLOAD_RECOVERY, true); + + __qede_remove(edev->pdev, QEDE_REMOVE_RECOVERY); + + rc = __qede_probe(edev->pdev, edev->dp_module, edev->dp_level, + IS_VF(edev), QEDE_PROBE_RECOVERY); + if (rc) { + edev->cdev = NULL; + goto err; + } + + if (curr_state == QEDE_STATE_OPEN) { + rc = qede_load(edev, QEDE_LOAD_RECOVERY, true); + if (rc) + goto err; + + qede_config_rx_mode(edev->ndev); + udp_tunnel_get_rx_info(edev->ndev); + } + + edev->state = curr_state; + + DP_NOTICE(edev, "Recovery handling is done\n"); + + return; + +err: + qede_recovery_failed(edev); +} + static bool qede_is_txq_full(struct qede_dev *edev, struct qede_tx_queue *txq) { struct netdev_queue *netdev_txq; diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c index 1900bf7e67d1..ffabc2d2f082 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c +++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c @@ -50,6 +50,8 @@ static void _qede_rdma_dev_add(struct qede_dev *edev) if (!qedr_drv) return; + /* Leftovers from previous error recovery */ + edev->rdma_info.exp_recovery = false; edev->rdma_info.qedr_dev = qedr_drv->add(edev->cdev, edev->pdev, edev->ndev); } @@ -87,21 +89,26 @@ static void qede_rdma_destroy_wq(struct qede_dev *edev) destroy_workqueue(edev->rdma_info.rdma_wq); } -int qede_rdma_dev_add(struct qede_dev *edev) +int qede_rdma_dev_add(struct qede_dev *edev, bool recovery) { - int rc = 0; + int rc; - if (qede_rdma_supported(edev)) { - rc = qede_rdma_create_wq(edev); - if (rc) - return rc; + if (!qede_rdma_supported(edev)) + return 0; - INIT_LIST_HEAD(&edev->rdma_info.entry); - mutex_lock(&qedr_dev_list_lock); - list_add_tail(&edev->rdma_info.entry, &qedr_dev_list); - _qede_rdma_dev_add(edev); - mutex_unlock(&qedr_dev_list_lock); - } + /* Cannot start qedr while recovering since it wasn't fully stopped */ + if (recovery) + return 0; + + rc = qede_rdma_create_wq(edev); + if (rc) + return rc; + + INIT_LIST_HEAD(&edev->rdma_info.entry); + mutex_lock(&qedr_dev_list_lock); + list_add_tail(&edev->rdma_info.entry, &qedr_dev_list); + _qede_rdma_dev_add(edev); + mutex_unlock(&qedr_dev_list_lock); return rc; } @@ -110,19 +117,30 @@ static void _qede_rdma_dev_remove(struct qede_dev *edev) { if (qedr_drv && qedr_drv->remove && edev->rdma_info.qedr_dev) qedr_drv->remove(edev->rdma_info.qedr_dev); - edev->rdma_info.qedr_dev = NULL; } -void qede_rdma_dev_remove(struct qede_dev *edev) +void qede_rdma_dev_remove(struct qede_dev *edev, bool recovery) { if (!qede_rdma_supported(edev)) return; - qede_rdma_destroy_wq(edev); - mutex_lock(&qedr_dev_list_lock); - _qede_rdma_dev_remove(edev); - list_del(&edev->rdma_info.entry); - mutex_unlock(&qedr_dev_list_lock); + /* Cannot remove qedr while recovering since it wasn't fully stopped */ + if (!recovery) { + qede_rdma_destroy_wq(edev); + mutex_lock(&qedr_dev_list_lock); + if (!edev->rdma_info.exp_recovery) + _qede_rdma_dev_remove(edev); + edev->rdma_info.qedr_dev = NULL; + list_del(&edev->rdma_info.entry); + mutex_unlock(&qedr_dev_list_lock); + } else { + if (!edev->rdma_info.exp_recovery) { + mutex_lock(&qedr_dev_list_lock); + _qede_rdma_dev_remove(edev); + mutex_unlock(&qedr_dev_list_lock); + } + edev->rdma_info.exp_recovery = true; + } } static void _qede_rdma_dev_open(struct qede_dev *edev) @@ -204,7 +222,8 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv) mutex_lock(&qedr_dev_list_lock); list_for_each_entry(edev, &qedr_dev_list, rdma_info.entry) { - if (edev->rdma_info.qedr_dev) + /* If device has experienced recovery it was already removed */ + if (edev->rdma_info.qedr_dev && !edev->rdma_info.exp_recovery) _qede_rdma_dev_remove(edev); } qedr_drv = NULL; @@ -284,6 +303,10 @@ static void qede_rdma_add_event(struct qede_dev *edev, { struct qede_rdma_event_work *event_node; + /* If a recovery was experienced avoid adding the event */ + if (edev->rdma_info.exp_recovery) + return; + if (!edev->rdma_info.qedr_dev) return; diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 9904617a9730..5a00c7a473bf 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -74,21 +74,23 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv); bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_rdma_dev_add(struct qede_dev *dev); +int qede_rdma_dev_add(struct qede_dev *dev, bool recovery); void qede_rdma_dev_event_open(struct qede_dev *dev); void qede_rdma_dev_event_close(struct qede_dev *dev); -void qede_rdma_dev_remove(struct qede_dev *dev); +void qede_rdma_dev_remove(struct qede_dev *dev, bool recovery); void qede_rdma_event_changeaddr(struct qede_dev *edr); #else -static inline int qede_rdma_dev_add(struct qede_dev *dev) +static inline int qede_rdma_dev_add(struct qede_dev *dev, + bool recovery) { return 0; } static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} -static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev, + bool recovery) {} static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif -- cgit v1.2.3 From c8aa703822bf811269975cf7251b5eaad4c38e9c Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 28 Jan 2019 08:53:53 -0800 Subject: net/flow_dissector: move bpf case into __skb_flow_bpf_dissect This way, we can reuse it for flow dissector in BPF_PROG_TEST_RUN. No functional changes. Signed-off-by: Stanislav Fomichev Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 5 +++ net/core/flow_dissector.c | 92 +++++++++++++++++++++++++++-------------------- 2 files changed, 59 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 93f56fddd92a..be762fc34ff3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1221,6 +1221,11 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) } #endif +struct bpf_flow_keys; +bool __skb_flow_bpf_dissect(struct bpf_prog *prog, + const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + struct bpf_flow_keys *flow_keys); bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 9f2840510e63..bb1a54747d64 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -683,6 +683,46 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, } } +bool __skb_flow_bpf_dissect(struct bpf_prog *prog, + const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + struct bpf_flow_keys *flow_keys) +{ + struct bpf_skb_data_end cb_saved; + struct bpf_skb_data_end *cb; + u32 result; + + /* Note that even though the const qualifier is discarded + * throughout the execution of the BPF program, all changes(the + * control block) are reverted after the BPF program returns. + * Therefore, __skb_flow_dissect does not alter the skb. + */ + + cb = (struct bpf_skb_data_end *)skb->cb; + + /* Save Control Block */ + memcpy(&cb_saved, cb, sizeof(cb_saved)); + memset(cb, 0, sizeof(*cb)); + + /* Pass parameters to the BPF program */ + memset(flow_keys, 0, sizeof(*flow_keys)); + cb->qdisc_cb.flow_keys = flow_keys; + flow_keys->nhoff = skb_network_offset(skb); + flow_keys->thoff = flow_keys->nhoff; + + bpf_compute_data_pointers((struct sk_buff *)skb); + result = BPF_PROG_RUN(prog, skb); + + /* Restore state */ + memcpy(cb, &cb_saved, sizeof(cb_saved)); + + flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, 0, skb->len); + flow_keys->thoff = clamp_t(u16, flow_keys->thoff, + flow_keys->nhoff, skb->len); + + return result == BPF_OK; +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -714,7 +754,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; - struct bpf_prog *attached = NULL; int num_hdrs = 0; u8 ip_proto = 0; bool ret; @@ -754,53 +793,30 @@ bool __skb_flow_dissect(const struct sk_buff *skb, FLOW_DISSECTOR_KEY_BASIC, target_container); - rcu_read_lock(); if (skb) { + struct bpf_flow_keys flow_keys; + struct bpf_prog *attached = NULL; + + rcu_read_lock(); + if (skb->dev) attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog); else if (skb->sk) attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog); else WARN_ON_ONCE(1); - } - if (attached) { - /* Note that even though the const qualifier is discarded - * throughout the execution of the BPF program, all changes(the - * control block) are reverted after the BPF program returns. - * Therefore, __skb_flow_dissect does not alter the skb. - */ - struct bpf_flow_keys flow_keys = {}; - struct bpf_skb_data_end cb_saved; - struct bpf_skb_data_end *cb; - u32 result; - - cb = (struct bpf_skb_data_end *)skb->cb; - - /* Save Control Block */ - memcpy(&cb_saved, cb, sizeof(cb_saved)); - memset(cb, 0, sizeof(cb_saved)); - /* Pass parameters to the BPF program */ - cb->qdisc_cb.flow_keys = &flow_keys; - flow_keys.nhoff = nhoff; - flow_keys.thoff = nhoff; - - bpf_compute_data_pointers((struct sk_buff *)skb); - result = BPF_PROG_RUN(attached, skb); - - /* Restore state */ - memcpy(cb, &cb_saved, sizeof(cb_saved)); - - flow_keys.nhoff = clamp_t(u16, flow_keys.nhoff, 0, skb->len); - flow_keys.thoff = clamp_t(u16, flow_keys.thoff, - flow_keys.nhoff, skb->len); - - __skb_flow_bpf_to_target(&flow_keys, flow_dissector, - target_container); + if (attached) { + ret = __skb_flow_bpf_dissect(attached, skb, + flow_dissector, + &flow_keys); + __skb_flow_bpf_to_target(&flow_keys, flow_dissector, + target_container); + rcu_read_unlock(); + return ret; + } rcu_read_unlock(); - return result == BPF_OK; } - rcu_read_unlock(); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { -- cgit v1.2.3 From b7a1848e8398b8396c990279e6a10272d818577e Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 28 Jan 2019 08:53:54 -0800 Subject: bpf: add BPF_PROG_TEST_RUN support for flow dissector The input is packet data, the output is struct bpf_flow_key. This should make it easy to test flow dissector programs without elaborate setup. Signed-off-by: Stanislav Fomichev Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 3 ++ net/bpf/test_run.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++++ net/core/filter.c | 1 + 3 files changed, 86 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3851529062ec..0394f1f9213b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -404,6 +404,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); /* an array of programs to be executed under rcu_lock. * diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index fa2644d276ef..2c5172b33209 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -240,3 +240,85 @@ out: kfree(data); return ret; } + +int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + u32 size = kattr->test.data_size_in; + u32 repeat = kattr->test.repeat; + struct bpf_flow_keys flow_keys; + u64 time_start, time_spent = 0; + struct bpf_skb_data_end *cb; + u32 retval, duration; + struct sk_buff *skb; + struct sock *sk; + void *data; + int ret; + u32 i; + + if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) + return -EINVAL; + + data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); + if (IS_ERR(data)) + return PTR_ERR(data); + + sk = kzalloc(sizeof(*sk), GFP_USER); + if (!sk) { + kfree(data); + return -ENOMEM; + } + sock_net_set(sk, current->nsproxy->net_ns); + sock_init_data(NULL, sk); + + skb = build_skb(data, 0); + if (!skb) { + kfree(data); + kfree(sk); + return -ENOMEM; + } + skb->sk = sk; + + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + __skb_put(skb, size); + skb->protocol = eth_type_trans(skb, + current->nsproxy->net_ns->loopback_dev); + skb_reset_network_header(skb); + + cb = (struct bpf_skb_data_end *)skb->cb; + cb->qdisc_cb.flow_keys = &flow_keys; + + if (!repeat) + repeat = 1; + + time_start = ktime_get_ns(); + for (i = 0; i < repeat; i++) { + preempt_disable(); + rcu_read_lock(); + retval = __skb_flow_bpf_dissect(prog, skb, + &flow_keys_dissector, + &flow_keys); + rcu_read_unlock(); + preempt_enable(); + + if (need_resched()) { + if (signal_pending(current)) + break; + time_spent += ktime_get_ns() - time_start; + cond_resched(); + time_start = ktime_get_ns(); + } + } + time_spent += ktime_get_ns() - time_start; + do_div(time_spent, repeat); + duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; + + ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), + retval, duration); + + kfree_skb(skb); + kfree(sk); + return ret; +} diff --git a/net/core/filter.c b/net/core/filter.c index 8e587dd1da20..8ce421796ac6 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7711,6 +7711,7 @@ const struct bpf_verifier_ops flow_dissector_verifier_ops = { }; const struct bpf_prog_ops flow_dissector_prog_ops = { + .test_run = bpf_prog_test_run_flow_dissector, }; int sk_detach_filter(struct sock *sk) -- cgit v1.2.3 From 59abc8cc05856cb31d6e07a8e25f0d749d559233 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 23 Jan 2019 11:08:05 -0800 Subject: scsi: libsas: Remove scsi_to_u32() Since the function scsi_to_u32() is identical to get_unaligned_be32(), change all scsi_to_u32() calls into get_unaligned_be32() calls. Cc: Jian Luo Cc: John Garry Signed-off-by: Bart Van Assche Reviewed-by: John Garry Reviewed-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- drivers/scsi/libsas/sas_expander.c | 9 +++++---- include/scsi/scsi.h | 6 ------ 2 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 83e3715d30e4..b13b245791b0 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "sas_internal.h" @@ -696,10 +697,10 @@ int sas_smp_get_phy_events(struct sas_phy *phy) if (res) goto out; - phy->invalid_dword_count = scsi_to_u32(&resp[12]); - phy->running_disparity_error_count = scsi_to_u32(&resp[16]); - phy->loss_of_dword_sync_count = scsi_to_u32(&resp[20]); - phy->phy_reset_problem_count = scsi_to_u32(&resp[24]); + phy->invalid_dword_count = get_unaligned_be32(&resp[12]); + phy->running_disparity_error_count = get_unaligned_be32(&resp[16]); + phy->loss_of_dword_sync_count = get_unaligned_be32(&resp[20]); + phy->phy_reset_problem_count = get_unaligned_be32(&resp[24]); out: kfree(req); diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index eb7853c1a23b..5339baadc082 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -274,10 +274,4 @@ static inline int scsi_is_wlun(u64 lun) /* Used to obtain the PCI location of a device */ #define SCSI_IOCTL_GET_PCI 0x5387 -/* Pull a u32 out of a SCSI message (using BE SCSI conventions) */ -static inline __u32 scsi_to_u32(__u8 *ptr) -{ - return (ptr[0]<<24) + (ptr[1]<<16) + (ptr[2]<<8) + ptr[3]; -} - #endif /* _SCSI_SCSI_H */ -- cgit v1.2.3 From 2b6e492467c78183bb629bb0a100ea3509b615a5 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 23 Jan 2019 17:44:16 +0300 Subject: device property: Fix the length used in PROPERTY_ENTRY_STRING() With string type property entries we need to use sizeof(const char *) instead of the number of characters as the length of the entry. If the string was shorter then sizeof(const char *), attempts to read it would have failed with -EOVERFLOW. The problem has been hidden because all build-in string properties have had a string longer then 8 characters until now. Fixes: a85f42047533 ("device property: helper macros for property entry creation") Cc: 4.5+ # 4.5+ Signed-off-by: Heikki Krogerus Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 3789ec755fb6..65d3420dd5d1 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -258,7 +258,7 @@ struct property_entry { #define PROPERTY_ENTRY_STRING(_name_, _val_) \ (struct property_entry) { \ .name = _name_, \ - .length = sizeof(_val_), \ + .length = sizeof(const char *), \ .type = DEV_PROP_STRING, \ { .value = { .str = _val_ } }, \ } -- cgit v1.2.3 From 625c85a62cb7d3c79f6e16de3cfa972033658250 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 25 Jan 2019 12:53:07 +0530 Subject: cpufreq: Use struct kobj_attribute instead of struct global_attr The cpufreq_global_kobject is created using kobject_create_and_add() helper, which assigns the kobj_type as dynamic_kobj_ktype and show/store routines are set to kobj_attr_show() and kobj_attr_store(). These routines pass struct kobj_attribute as an argument to the show/store callbacks. But all the cpufreq files created using the cpufreq_global_kobject expect the argument to be of type struct attribute. Things work fine currently as no one accesses the "attr" argument. We may not see issues even if the argument is used, as struct kobj_attribute has struct attribute as its first element and so they will both get same address. But this is logically incorrect and we should rather use struct kobj_attribute instead of struct global_attr in the cpufreq core and drivers and the show/store callbacks should take struct kobj_attribute as argument instead. This bug is caught using CFI CLANG builds in android kernel which catches mismatch in function prototypes for such callbacks. Reported-by: Donghee Han Reported-by: Sangkyu Kim Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 6 +++--- drivers/cpufreq/intel_pstate.c | 23 ++++++++++++----------- include/linux/cpufreq.h | 12 ++---------- 3 files changed, 17 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index a8fa684f5f90..3eff158d9750 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -545,13 +545,13 @@ EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us); * SYSFS INTERFACE * *********************************************************************/ static ssize_t show_boost(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled); } -static ssize_t store_boost(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t count) +static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) { int ret, enable; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index dd66decf2087..5ab6a4fe93aa 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -895,7 +895,7 @@ static void intel_pstate_update_policies(void) /************************** sysfs begin ************************/ #define show_one(file_name, object) \ static ssize_t show_##file_name \ - (struct kobject *kobj, struct attribute *attr, char *buf) \ + (struct kobject *kobj, struct kobj_attribute *attr, char *buf) \ { \ return sprintf(buf, "%u\n", global.object); \ } @@ -904,7 +904,7 @@ static ssize_t intel_pstate_show_status(char *buf); static int intel_pstate_update_status(const char *buf, size_t size); static ssize_t show_status(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { ssize_t ret; @@ -915,7 +915,7 @@ static ssize_t show_status(struct kobject *kobj, return ret; } -static ssize_t store_status(struct kobject *a, struct attribute *b, +static ssize_t store_status(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { char *p = memchr(buf, '\n', count); @@ -929,7 +929,7 @@ static ssize_t store_status(struct kobject *a, struct attribute *b, } static ssize_t show_turbo_pct(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { struct cpudata *cpu; int total, no_turbo, turbo_pct; @@ -955,7 +955,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj, } static ssize_t show_num_pstates(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { struct cpudata *cpu; int total; @@ -976,7 +976,7 @@ static ssize_t show_num_pstates(struct kobject *kobj, } static ssize_t show_no_turbo(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { ssize_t ret; @@ -998,7 +998,7 @@ static ssize_t show_no_turbo(struct kobject *kobj, return ret; } -static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, +static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; @@ -1045,7 +1045,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, return count; } -static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, +static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; @@ -1075,7 +1075,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, return count; } -static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, +static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; @@ -1107,12 +1107,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, } static ssize_t show_hwp_dynamic_boost(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%u\n", hwp_boost); } -static ssize_t store_hwp_dynamic_boost(struct kobject *a, struct attribute *b, +static ssize_t store_hwp_dynamic_boost(struct kobject *a, + struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index bd7fbd6a4478..c19142911554 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -254,20 +254,12 @@ __ATTR(_name, 0644, show_##_name, store_##_name) static struct freq_attr _name = \ __ATTR(_name, 0200, NULL, store_##_name) -struct global_attr { - struct attribute attr; - ssize_t (*show)(struct kobject *kobj, - struct attribute *attr, char *buf); - ssize_t (*store)(struct kobject *a, struct attribute *b, - const char *c, size_t count); -}; - #define define_one_global_ro(_name) \ -static struct global_attr _name = \ +static struct kobj_attribute _name = \ __ATTR(_name, 0444, show_##_name, NULL) #define define_one_global_rw(_name) \ -static struct global_attr _name = \ +static struct kobj_attribute _name = \ __ATTR(_name, 0644, show_##_name, store_##_name) -- cgit v1.2.3 From bc3843d4d357061d92e7800c7da342e2d068772c Mon Sep 17 00:00:00 2001 From: Nava kishore Manne Date: Fri, 25 Jan 2019 13:16:52 +0530 Subject: firmware: xilinx: Add reset API's This Patch Adds reset API's to support release, assert and status functionalities by using firmware interface. Signed-off-by: Nava kishore Manne Signed-off-by: Michal Simek --- drivers/firmware/xilinx/zynqmp.c | 40 +++++++++++ include/linux/firmware/xlnx-zynqmp.h | 136 +++++++++++++++++++++++++++++++++++ 2 files changed, 176 insertions(+) (limited to 'include') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 9a1c72a9280f..70b50377ae5f 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -469,6 +469,44 @@ static int zynqmp_pm_ioctl(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, arg1, arg2, out); } +/** + * zynqmp_pm_reset_assert - Request setting of reset (1 - assert, 0 - release) + * @reset: Reset to be configured + * @assert_flag: Flag stating should reset be asserted (1) or + * released (0) + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, + const enum zynqmp_pm_reset_action assert_flag) +{ + return zynqmp_pm_invoke_fn(PM_RESET_ASSERT, reset, assert_flag, + 0, 0, NULL); +} + +/** + * zynqmp_pm_reset_get_status - Get status of the reset + * @reset: Reset whose status should be returned + * @status: Returned status + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, + u32 *status) +{ + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + if (!status) + return -EINVAL; + + ret = zynqmp_pm_invoke_fn(PM_RESET_GET_STATUS, reset, 0, + 0, 0, ret_payload); + *status = ret_payload[1]; + + return ret; +} + static const struct zynqmp_eemi_ops eemi_ops = { .get_api_version = zynqmp_pm_get_api_version, .query_data = zynqmp_pm_query_data, @@ -482,6 +520,8 @@ static const struct zynqmp_eemi_ops eemi_ops = { .clock_setparent = zynqmp_pm_clock_setparent, .clock_getparent = zynqmp_pm_clock_getparent, .ioctl = zynqmp_pm_ioctl, + .reset_assert = zynqmp_pm_reset_assert, + .reset_get_status = zynqmp_pm_reset_get_status, }; /** diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 3c3c28eff56a..07c587a0b06e 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -34,6 +34,8 @@ enum pm_api_id { PM_GET_API_VERSION = 1, + PM_RESET_ASSERT = 17, + PM_RESET_GET_STATUS, PM_IOCTL = 34, PM_QUERY_DATA, PM_CLOCK_ENABLE, @@ -75,6 +77,137 @@ enum pm_query_id { PM_QID_CLOCK_GET_NUM_CLOCKS = 12, }; +enum zynqmp_pm_reset_action { + PM_RESET_ACTION_RELEASE, + PM_RESET_ACTION_ASSERT, + PM_RESET_ACTION_PULSE, +}; + +enum zynqmp_pm_reset { + ZYNQMP_PM_RESET_START = 1000, + ZYNQMP_PM_RESET_PCIE_CFG = ZYNQMP_PM_RESET_START, + ZYNQMP_PM_RESET_PCIE_BRIDGE, + ZYNQMP_PM_RESET_PCIE_CTRL, + ZYNQMP_PM_RESET_DP, + ZYNQMP_PM_RESET_SWDT_CRF, + ZYNQMP_PM_RESET_AFI_FM5, + ZYNQMP_PM_RESET_AFI_FM4, + ZYNQMP_PM_RESET_AFI_FM3, + ZYNQMP_PM_RESET_AFI_FM2, + ZYNQMP_PM_RESET_AFI_FM1, + ZYNQMP_PM_RESET_AFI_FM0, + ZYNQMP_PM_RESET_GDMA, + ZYNQMP_PM_RESET_GPU_PP1, + ZYNQMP_PM_RESET_GPU_PP0, + ZYNQMP_PM_RESET_GPU, + ZYNQMP_PM_RESET_GT, + ZYNQMP_PM_RESET_SATA, + ZYNQMP_PM_RESET_ACPU3_PWRON, + ZYNQMP_PM_RESET_ACPU2_PWRON, + ZYNQMP_PM_RESET_ACPU1_PWRON, + ZYNQMP_PM_RESET_ACPU0_PWRON, + ZYNQMP_PM_RESET_APU_L2, + ZYNQMP_PM_RESET_ACPU3, + ZYNQMP_PM_RESET_ACPU2, + ZYNQMP_PM_RESET_ACPU1, + ZYNQMP_PM_RESET_ACPU0, + ZYNQMP_PM_RESET_DDR, + ZYNQMP_PM_RESET_APM_FPD, + ZYNQMP_PM_RESET_SOFT, + ZYNQMP_PM_RESET_GEM0, + ZYNQMP_PM_RESET_GEM1, + ZYNQMP_PM_RESET_GEM2, + ZYNQMP_PM_RESET_GEM3, + ZYNQMP_PM_RESET_QSPI, + ZYNQMP_PM_RESET_UART0, + ZYNQMP_PM_RESET_UART1, + ZYNQMP_PM_RESET_SPI0, + ZYNQMP_PM_RESET_SPI1, + ZYNQMP_PM_RESET_SDIO0, + ZYNQMP_PM_RESET_SDIO1, + ZYNQMP_PM_RESET_CAN0, + ZYNQMP_PM_RESET_CAN1, + ZYNQMP_PM_RESET_I2C0, + ZYNQMP_PM_RESET_I2C1, + ZYNQMP_PM_RESET_TTC0, + ZYNQMP_PM_RESET_TTC1, + ZYNQMP_PM_RESET_TTC2, + ZYNQMP_PM_RESET_TTC3, + ZYNQMP_PM_RESET_SWDT_CRL, + ZYNQMP_PM_RESET_NAND, + ZYNQMP_PM_RESET_ADMA, + ZYNQMP_PM_RESET_GPIO, + ZYNQMP_PM_RESET_IOU_CC, + ZYNQMP_PM_RESET_TIMESTAMP, + ZYNQMP_PM_RESET_RPU_R50, + ZYNQMP_PM_RESET_RPU_R51, + ZYNQMP_PM_RESET_RPU_AMBA, + ZYNQMP_PM_RESET_OCM, + ZYNQMP_PM_RESET_RPU_PGE, + ZYNQMP_PM_RESET_USB0_CORERESET, + ZYNQMP_PM_RESET_USB1_CORERESET, + ZYNQMP_PM_RESET_USB0_HIBERRESET, + ZYNQMP_PM_RESET_USB1_HIBERRESET, + ZYNQMP_PM_RESET_USB0_APB, + ZYNQMP_PM_RESET_USB1_APB, + ZYNQMP_PM_RESET_IPI, + ZYNQMP_PM_RESET_APM_LPD, + ZYNQMP_PM_RESET_RTC, + ZYNQMP_PM_RESET_SYSMON, + ZYNQMP_PM_RESET_AFI_FM6, + ZYNQMP_PM_RESET_LPD_SWDT, + ZYNQMP_PM_RESET_FPD, + ZYNQMP_PM_RESET_RPU_DBG1, + ZYNQMP_PM_RESET_RPU_DBG0, + ZYNQMP_PM_RESET_DBG_LPD, + ZYNQMP_PM_RESET_DBG_FPD, + ZYNQMP_PM_RESET_APLL, + ZYNQMP_PM_RESET_DPLL, + ZYNQMP_PM_RESET_VPLL, + ZYNQMP_PM_RESET_IOPLL, + ZYNQMP_PM_RESET_RPLL, + ZYNQMP_PM_RESET_GPO3_PL_0, + ZYNQMP_PM_RESET_GPO3_PL_1, + ZYNQMP_PM_RESET_GPO3_PL_2, + ZYNQMP_PM_RESET_GPO3_PL_3, + ZYNQMP_PM_RESET_GPO3_PL_4, + ZYNQMP_PM_RESET_GPO3_PL_5, + ZYNQMP_PM_RESET_GPO3_PL_6, + ZYNQMP_PM_RESET_GPO3_PL_7, + ZYNQMP_PM_RESET_GPO3_PL_8, + ZYNQMP_PM_RESET_GPO3_PL_9, + ZYNQMP_PM_RESET_GPO3_PL_10, + ZYNQMP_PM_RESET_GPO3_PL_11, + ZYNQMP_PM_RESET_GPO3_PL_12, + ZYNQMP_PM_RESET_GPO3_PL_13, + ZYNQMP_PM_RESET_GPO3_PL_14, + ZYNQMP_PM_RESET_GPO3_PL_15, + ZYNQMP_PM_RESET_GPO3_PL_16, + ZYNQMP_PM_RESET_GPO3_PL_17, + ZYNQMP_PM_RESET_GPO3_PL_18, + ZYNQMP_PM_RESET_GPO3_PL_19, + ZYNQMP_PM_RESET_GPO3_PL_20, + ZYNQMP_PM_RESET_GPO3_PL_21, + ZYNQMP_PM_RESET_GPO3_PL_22, + ZYNQMP_PM_RESET_GPO3_PL_23, + ZYNQMP_PM_RESET_GPO3_PL_24, + ZYNQMP_PM_RESET_GPO3_PL_25, + ZYNQMP_PM_RESET_GPO3_PL_26, + ZYNQMP_PM_RESET_GPO3_PL_27, + ZYNQMP_PM_RESET_GPO3_PL_28, + ZYNQMP_PM_RESET_GPO3_PL_29, + ZYNQMP_PM_RESET_GPO3_PL_30, + ZYNQMP_PM_RESET_GPO3_PL_31, + ZYNQMP_PM_RESET_RPU_LS, + ZYNQMP_PM_RESET_PS_ONLY, + ZYNQMP_PM_RESET_PL, + ZYNQMP_PM_RESET_PS_PL0, + ZYNQMP_PM_RESET_PS_PL1, + ZYNQMP_PM_RESET_PS_PL2, + ZYNQMP_PM_RESET_PS_PL3, + ZYNQMP_PM_RESET_END = ZYNQMP_PM_RESET_PS_PL3 +}; + /** * struct zynqmp_pm_query_data - PM query data * @qid: query ID @@ -102,6 +235,9 @@ struct zynqmp_eemi_ops { int (*clock_setparent)(u32 clock_id, u32 parent_id); int (*clock_getparent)(u32 clock_id, u32 *parent_id); int (*ioctl)(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, u32 *out); + int (*reset_assert)(const enum zynqmp_pm_reset reset, + const enum zynqmp_pm_reset_action assert_flag); + int (*reset_get_status)(const enum zynqmp_pm_reset reset, u32 *status); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3 From 3f1b66be4aaa5dbe0a16197bfdfc355cf1da7701 Mon Sep 17 00:00:00 2001 From: Nava kishore Manne Date: Fri, 25 Jan 2019 13:16:53 +0530 Subject: dt-bindings: reset: Add bindings for ZynqMP reset driver Add documentation to describe Xilinx ZynqMP reset driver bindings. Signed-off-by: Nava kishore Manne Signed-off-by: Jolly Shah Reviewed-by: Rob Herring Signed-off-by: Michal Simek --- .../bindings/reset/xlnx,zynqmp-reset.txt | 52 +++++++++ include/dt-bindings/reset/xlnx-zynqmp-resets.h | 130 +++++++++++++++++++++ 2 files changed, 182 insertions(+) create mode 100644 Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.txt create mode 100644 include/dt-bindings/reset/xlnx-zynqmp-resets.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.txt b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.txt new file mode 100644 index 000000000000..27a45fe5ecf1 --- /dev/null +++ b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.txt @@ -0,0 +1,52 @@ +-------------------------------------------------------------------------- + = Zynq UltraScale+ MPSoC reset driver binding = +-------------------------------------------------------------------------- +The Zynq UltraScale+ MPSoC has several different resets. + +See Chapter 36 of the Zynq UltraScale+ MPSoC TRM (UG) for more information +about zynqmp resets. + +Please also refer to reset.txt in this directory for common reset +controller binding usage. + +Required Properties: +- compatible: "xlnx,zynqmp-reset" +- #reset-cells: Specifies the number of cells needed to encode reset + line, should be 1 + +------- +Example +------- + +firmware { + zynqmp_firmware: zynqmp-firmware { + compatible = "xlnx,zynqmp-firmware"; + method = "smc"; + + zynqmp_reset: reset-controller { + compatible = "xlnx,zynqmp-reset"; + #reset-cells = <1>; + }; + }; +}; + +Specifying reset lines connected to IP modules +============================================== + +Device nodes that need access to reset lines should +specify them as a reset phandle in their corresponding node as +specified in reset.txt. + +For list of all valid reset indicies see + + +Example: + +serdes: zynqmp_phy@fd400000 { + ... + + resets = <&zynqmp_reset ZYNQMP_RESET_SATA>; + reset-names = "sata_rst"; + + ... +}; diff --git a/include/dt-bindings/reset/xlnx-zynqmp-resets.h b/include/dt-bindings/reset/xlnx-zynqmp-resets.h new file mode 100644 index 000000000000..d44525b9f8db --- /dev/null +++ b/include/dt-bindings/reset/xlnx-zynqmp-resets.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 Xilinx, Inc. + */ + +#ifndef _DT_BINDINGS_ZYNQMP_RESETS_H +#define _DT_BINDINGS_ZYNQMP_RESETS_H + +#define ZYNQMP_RESET_PCIE_CFG 0 +#define ZYNQMP_RESET_PCIE_BRIDGE 1 +#define ZYNQMP_RESET_PCIE_CTRL 2 +#define ZYNQMP_RESET_DP 3 +#define ZYNQMP_RESET_SWDT_CRF 4 +#define ZYNQMP_RESET_AFI_FM5 5 +#define ZYNQMP_RESET_AFI_FM4 6 +#define ZYNQMP_RESET_AFI_FM3 7 +#define ZYNQMP_RESET_AFI_FM2 8 +#define ZYNQMP_RESET_AFI_FM1 9 +#define ZYNQMP_RESET_AFI_FM0 10 +#define ZYNQMP_RESET_GDMA 11 +#define ZYNQMP_RESET_GPU_PP1 12 +#define ZYNQMP_RESET_GPU_PP0 13 +#define ZYNQMP_RESET_GPU 14 +#define ZYNQMP_RESET_GT 15 +#define ZYNQMP_RESET_SATA 16 +#define ZYNQMP_RESET_ACPU3_PWRON 17 +#define ZYNQMP_RESET_ACPU2_PWRON 18 +#define ZYNQMP_RESET_ACPU1_PWRON 19 +#define ZYNQMP_RESET_ACPU0_PWRON 20 +#define ZYNQMP_RESET_APU_L2 21 +#define ZYNQMP_RESET_ACPU3 22 +#define ZYNQMP_RESET_ACPU2 23 +#define ZYNQMP_RESET_ACPU1 24 +#define ZYNQMP_RESET_ACPU0 25 +#define ZYNQMP_RESET_DDR 26 +#define ZYNQMP_RESET_APM_FPD 27 +#define ZYNQMP_RESET_SOFT 28 +#define ZYNQMP_RESET_GEM0 29 +#define ZYNQMP_RESET_GEM1 30 +#define ZYNQMP_RESET_GEM2 31 +#define ZYNQMP_RESET_GEM3 32 +#define ZYNQMP_RESET_QSPI 33 +#define ZYNQMP_RESET_UART0 34 +#define ZYNQMP_RESET_UART1 35 +#define ZYNQMP_RESET_SPI0 36 +#define ZYNQMP_RESET_SPI1 37 +#define ZYNQMP_RESET_SDIO0 38 +#define ZYNQMP_RESET_SDIO1 39 +#define ZYNQMP_RESET_CAN0 40 +#define ZYNQMP_RESET_CAN1 41 +#define ZYNQMP_RESET_I2C0 42 +#define ZYNQMP_RESET_I2C1 43 +#define ZYNQMP_RESET_TTC0 44 +#define ZYNQMP_RESET_TTC1 45 +#define ZYNQMP_RESET_TTC2 46 +#define ZYNQMP_RESET_TTC3 47 +#define ZYNQMP_RESET_SWDT_CRL 48 +#define ZYNQMP_RESET_NAND 49 +#define ZYNQMP_RESET_ADMA 50 +#define ZYNQMP_RESET_GPIO 51 +#define ZYNQMP_RESET_IOU_CC 52 +#define ZYNQMP_RESET_TIMESTAMP 53 +#define ZYNQMP_RESET_RPU_R50 54 +#define ZYNQMP_RESET_RPU_R51 55 +#define ZYNQMP_RESET_RPU_AMBA 56 +#define ZYNQMP_RESET_OCM 57 +#define ZYNQMP_RESET_RPU_PGE 58 +#define ZYNQMP_RESET_USB0_CORERESET 59 +#define ZYNQMP_RESET_USB1_CORERESET 60 +#define ZYNQMP_RESET_USB0_HIBERRESET 61 +#define ZYNQMP_RESET_USB1_HIBERRESET 62 +#define ZYNQMP_RESET_USB0_APB 63 +#define ZYNQMP_RESET_USB1_APB 64 +#define ZYNQMP_RESET_IPI 65 +#define ZYNQMP_RESET_APM_LPD 66 +#define ZYNQMP_RESET_RTC 67 +#define ZYNQMP_RESET_SYSMON 68 +#define ZYNQMP_RESET_AFI_FM6 69 +#define ZYNQMP_RESET_LPD_SWDT 70 +#define ZYNQMP_RESET_FPD 71 +#define ZYNQMP_RESET_RPU_DBG1 72 +#define ZYNQMP_RESET_RPU_DBG0 73 +#define ZYNQMP_RESET_DBG_LPD 74 +#define ZYNQMP_RESET_DBG_FPD 75 +#define ZYNQMP_RESET_APLL 76 +#define ZYNQMP_RESET_DPLL 77 +#define ZYNQMP_RESET_VPLL 78 +#define ZYNQMP_RESET_IOPLL 79 +#define ZYNQMP_RESET_RPLL 80 +#define ZYNQMP_RESET_GPO3_PL_0 81 +#define ZYNQMP_RESET_GPO3_PL_1 82 +#define ZYNQMP_RESET_GPO3_PL_2 83 +#define ZYNQMP_RESET_GPO3_PL_3 84 +#define ZYNQMP_RESET_GPO3_PL_4 85 +#define ZYNQMP_RESET_GPO3_PL_5 86 +#define ZYNQMP_RESET_GPO3_PL_6 87 +#define ZYNQMP_RESET_GPO3_PL_7 88 +#define ZYNQMP_RESET_GPO3_PL_8 89 +#define ZYNQMP_RESET_GPO3_PL_9 90 +#define ZYNQMP_RESET_GPO3_PL_10 91 +#define ZYNQMP_RESET_GPO3_PL_11 92 +#define ZYNQMP_RESET_GPO3_PL_12 93 +#define ZYNQMP_RESET_GPO3_PL_13 94 +#define ZYNQMP_RESET_GPO3_PL_14 95 +#define ZYNQMP_RESET_GPO3_PL_15 96 +#define ZYNQMP_RESET_GPO3_PL_16 97 +#define ZYNQMP_RESET_GPO3_PL_17 98 +#define ZYNQMP_RESET_GPO3_PL_18 99 +#define ZYNQMP_RESET_GPO3_PL_19 100 +#define ZYNQMP_RESET_GPO3_PL_20 101 +#define ZYNQMP_RESET_GPO3_PL_21 102 +#define ZYNQMP_RESET_GPO3_PL_22 103 +#define ZYNQMP_RESET_GPO3_PL_23 104 +#define ZYNQMP_RESET_GPO3_PL_24 105 +#define ZYNQMP_RESET_GPO3_PL_25 106 +#define ZYNQMP_RESET_GPO3_PL_26 107 +#define ZYNQMP_RESET_GPO3_PL_27 108 +#define ZYNQMP_RESET_GPO3_PL_28 109 +#define ZYNQMP_RESET_GPO3_PL_29 110 +#define ZYNQMP_RESET_GPO3_PL_30 111 +#define ZYNQMP_RESET_GPO3_PL_31 112 +#define ZYNQMP_RESET_RPU_LS 113 +#define ZYNQMP_RESET_PS_ONLY 114 +#define ZYNQMP_RESET_PL 115 +#define ZYNQMP_RESET_PS_PL0 116 +#define ZYNQMP_RESET_PS_PL1 117 +#define ZYNQMP_RESET_PS_PL2 118 +#define ZYNQMP_RESET_PS_PL3 119 + +#endif -- cgit v1.2.3 From 5c30f43f0625a792c30e465f21dbeb1bb4dfc40b Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Fri, 25 Jan 2019 14:06:46 -0600 Subject: ASoC: topology: add SND_SOC_DOBJ_GRAPH type for dapm routes Add a new dobj type SND_SOC_DOBJ_GRAPH for dapm routes and add snd_soc_dobj member to struct snd_soc_dapm_route. This enables device drivers to save driver specific data pertaining to dapm routes and also be able to clean up the data when the driver module is unloaded. Also, reorder the snd_soc_dobj_type types to align with matching topology header types. Signed-off-by: Ranjani Sridharan Signed-off-by: Pierre-Louis Bossart Signed-off-by: Mark Brown --- include/sound/soc-dapm.h | 2 ++ include/sound/soc-topology.h | 7 ++++--- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index bd8163f151cb..46f2ba3ffcb7 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -540,6 +540,8 @@ struct snd_soc_dapm_route { /* Note: currently only supported for links where source is a supply */ int (*connected)(struct snd_soc_dapm_widget *source, struct snd_soc_dapm_widget *sink); + + struct snd_soc_dobj dobj; }; /* dapm audio path between two widgets */ diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h index fa4b8413d2e2..8c43cfc240fa 100644 --- a/include/sound/soc-topology.h +++ b/include/sound/soc-topology.h @@ -38,12 +38,13 @@ struct snd_soc_dapm_route; enum snd_soc_dobj_type { SND_SOC_DOBJ_NONE = 0, /* object is not dynamic */ SND_SOC_DOBJ_MIXER, - SND_SOC_DOBJ_ENUM, SND_SOC_DOBJ_BYTES, - SND_SOC_DOBJ_PCM, + SND_SOC_DOBJ_ENUM, + SND_SOC_DOBJ_GRAPH, + SND_SOC_DOBJ_WIDGET, SND_SOC_DOBJ_DAI_LINK, + SND_SOC_DOBJ_PCM, SND_SOC_DOBJ_CODEC_LINK, - SND_SOC_DOBJ_WIDGET, }; /* dynamic control object */ -- cgit v1.2.3 From 15917dc02841862840efcbfe1da0830f88078b5c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 19 Dec 2018 13:04:41 +0100 Subject: sched: Remove stale PF_MUTEX_TESTER bit The RTMUTEX tester was removed long ago but the PF bit stayed around. Remove it and free up the space. Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index d2f90fa92468..e2bba022827d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1409,7 +1409,6 @@ extern struct pid *cad_pid; #define PF_UMH 0x02000000 /* I'm an Usermodehelper process */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ -#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ -- cgit v1.2.3 From 6bf8f22aea0ddd93af822aed8afeeee4acdf7694 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 22 Jan 2019 08:29:56 +0200 Subject: IB/mlx5: Introduce MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD Introduce MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD and its initial implementation. This object is from type class FD and will be used to read DEVX async commands completion. The core layer should allow the driver to set object from type FD in a safe mode, this option was added with a matching comment in place. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/rdma_core.c | 1 + drivers/infiniband/core/uverbs_uapi.c | 15 ++++-- drivers/infiniband/hw/mlx5/devx.c | 83 ++++++++++++++++++++++++++++++++ include/rdma/uverbs_types.h | 1 + include/uapi/rdma/mlx5_user_ioctl_cmds.h | 9 ++++ 5 files changed, 104 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 6c4747e61d2b..a260d2f8e0b7 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -801,6 +801,7 @@ void uverbs_close_fd(struct file *f) /* Pairs with filp->private_data in alloc_begin_fd_uobject */ uverbs_uobject_put(uobj); } +EXPORT_SYMBOL(uverbs_close_fd); /* * Drop the ucontext off the ufile and completely disconnect it from the diff --git a/drivers/infiniband/core/uverbs_uapi.c b/drivers/infiniband/core/uverbs_uapi.c index 9ae08e4b78a3..7a987acf0c0b 100644 --- a/drivers/infiniband/core/uverbs_uapi.c +++ b/drivers/infiniband/core/uverbs_uapi.c @@ -188,13 +188,18 @@ static int uapi_merge_obj_tree(struct uverbs_api *uapi, obj_elm->type_attrs = obj->type_attrs; obj_elm->type_class = obj->type_attrs->type_class; /* - * Today drivers are only permitted to use idr_class - * types. They cannot use FD types because we currently have - * no way to revoke the fops pointer after device - * disassociation. + * Today drivers are only permitted to use idr_class and + * fd_class types. We can revoke the IDR types during + * disassociation, and the FD types require the driver to use + * struct file_operations.owner to prevent the driver module + * code from unloading while the file is open. This provides + * enough safety that uverbs_close_fd() will continue to work. + * Drivers using FD are responsible to handle disassociation of + * the device on their own. */ if (WARN_ON(is_driver && - obj->type_attrs->type_class != &uverbs_idr_class)) + obj->type_attrs->type_class != &uverbs_idr_class && + obj->type_attrs->type_class != &uverbs_fd_class)) return -EINVAL; } diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 5a588f3cfb1b..9933bcf83a6b 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1168,6 +1168,38 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_QUERY)( cmd_out, cmd_out_len); } +struct devx_async_event_queue { + spinlock_t lock; + wait_queue_head_t poll_wait; + struct list_head event_list; +}; + +struct devx_async_cmd_event_file { + struct ib_uobject uobj; + struct devx_async_event_queue ev_queue; +}; + +static void devx_init_event_queue(struct devx_async_event_queue *ev_queue) +{ + spin_lock_init(&ev_queue->lock); + INIT_LIST_HEAD(&ev_queue->event_list); + init_waitqueue_head(&ev_queue->poll_wait); +} + +static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_ASYNC_CMD_FD_ALLOC)( + struct uverbs_attr_bundle *attrs) +{ + struct devx_async_cmd_event_file *ev_file; + + struct ib_uobject *uobj = uverbs_attr_get_uobject( + attrs, MLX5_IB_ATTR_DEVX_ASYNC_CMD_FD_ALLOC_HANDLE); + + ev_file = container_of(uobj, struct devx_async_cmd_event_file, + uobj); + devx_init_event_queue(&ev_file->ev_queue); + return 0; +} + static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext, struct uverbs_attr_bundle *attrs, struct devx_umem *obj) @@ -1313,6 +1345,38 @@ static int devx_umem_cleanup(struct ib_uobject *uobject, return 0; } +static ssize_t devx_async_cmd_event_read(struct file *filp, char __user *buf, + size_t count, loff_t *pos) +{ + return -EINVAL; +} + +static int devx_async_cmd_event_close(struct inode *inode, struct file *filp) +{ + uverbs_close_fd(filp); + return 0; +} + +static __poll_t devx_async_cmd_event_poll(struct file *filp, + struct poll_table_struct *wait) +{ + return 0; +} + +const struct file_operations devx_async_cmd_event_fops = { + .owner = THIS_MODULE, + .read = devx_async_cmd_event_read, + .poll = devx_async_cmd_event_poll, + .release = devx_async_cmd_event_close, + .llseek = no_llseek, +}; + +static int devx_hot_unplug_async_cmd_event_file(struct ib_uobject *uobj, + enum rdma_remove_reason why) +{ + return 0; +}; + DECLARE_UVERBS_NAMED_METHOD( MLX5_IB_METHOD_DEVX_UMEM_REG, UVERBS_ATTR_IDR(MLX5_IB_ATTR_DEVX_UMEM_REG_HANDLE, @@ -1440,6 +1504,22 @@ DECLARE_UVERBS_NAMED_OBJECT(MLX5_IB_OBJECT_DEVX_UMEM, &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_UMEM_REG), &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_UMEM_DEREG)); + +DECLARE_UVERBS_NAMED_METHOD( + MLX5_IB_METHOD_DEVX_ASYNC_CMD_FD_ALLOC, + UVERBS_ATTR_FD(MLX5_IB_ATTR_DEVX_ASYNC_CMD_FD_ALLOC_HANDLE, + MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD, + UVERBS_ACCESS_NEW, + UA_MANDATORY)); + +DECLARE_UVERBS_NAMED_OBJECT( + MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD, + UVERBS_TYPE_ALLOC_FD(sizeof(struct devx_async_cmd_event_file), + devx_hot_unplug_async_cmd_event_file, + &devx_async_cmd_event_fops, "[devx_async_cmd]", + O_RDONLY), + &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_ASYNC_CMD_FD_ALLOC)); + static bool devx_is_supported(struct ib_device *device) { struct mlx5_ib_dev *dev = to_mdev(device); @@ -1457,5 +1537,8 @@ const struct uapi_definition mlx5_ib_devx_defs[] = { UAPI_DEF_CHAIN_OBJ_TREE_NAMED( MLX5_IB_OBJECT_DEVX_UMEM, UAPI_DEF_IS_OBJ_SUPPORTED(devx_is_supported)), + UAPI_DEF_CHAIN_OBJ_TREE_NAMED( + MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD, + UAPI_DEF_IS_OBJ_SUPPORTED(devx_is_supported)), {}, }; diff --git a/include/rdma/uverbs_types.h b/include/rdma/uverbs_types.h index acb1bfa3cc99..175d761695e1 100644 --- a/include/rdma/uverbs_types.h +++ b/include/rdma/uverbs_types.h @@ -157,6 +157,7 @@ struct uverbs_obj_fd_type { extern const struct uverbs_obj_type_class uverbs_idr_class; extern const struct uverbs_obj_type_class uverbs_fd_class; +void uverbs_close_fd(struct file *f); #define UVERBS_BUILD_BUG_ON(cond) (sizeof(char[1 - 2 * !!(cond)]) - \ sizeof(char)) diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h index b8d121d457f1..6ceae29d77cd 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h +++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h @@ -113,11 +113,20 @@ enum mlx5_ib_devx_umem_methods { MLX5_IB_METHOD_DEVX_UMEM_DEREG, }; +enum mlx5_ib_devx_async_cmd_fd_alloc_attrs { + MLX5_IB_ATTR_DEVX_ASYNC_CMD_FD_ALLOC_HANDLE = (1U << UVERBS_ID_NS_SHIFT), +}; + +enum mlx5_ib_devx_async_cmd_fd_methods { + MLX5_IB_METHOD_DEVX_ASYNC_CMD_FD_ALLOC = (1U << UVERBS_ID_NS_SHIFT), +}; + enum mlx5_ib_objects { MLX5_IB_OBJECT_DEVX = (1U << UVERBS_ID_NS_SHIFT), MLX5_IB_OBJECT_DEVX_OBJ, MLX5_IB_OBJECT_DEVX_UMEM, MLX5_IB_OBJECT_FLOW_MATCHER, + MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD, }; enum mlx5_ib_flow_matcher_create_attrs { -- cgit v1.2.3 From a124edba26270697540f1058bfcd490c1c65b116 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 22 Jan 2019 08:29:57 +0200 Subject: IB/mlx5: Introduce async DEVX obj query API Introduce async DEVX obj query API to get the command response back to user space once it's ready without blocking when calling the firmware. The event's data includes a header with some meta data then the firmware output command data. The header includes: - The input 'wr_id' to let application recognizing the response. The input FD attribute is used to have the event data ready on. Downstream patches from this series will implement the file ops to let application read it. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/devx.c | 164 +++++++++++++++++++++++++++++- include/uapi/rdma/mlx5_user_ioctl_cmds.h | 9 ++ include/uapi/rdma/mlx5_user_ioctl_verbs.h | 5 + 3 files changed, 177 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 9933bcf83a6b..9ca116155f9c 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -17,6 +18,16 @@ #define UVERBS_MODULE_NAME mlx5_ib #include +struct devx_async_data { + struct mlx5_ib_dev *mdev; + struct list_head list; + struct ib_uobject *fd_uobj; + struct mlx5_async_work cb_work; + u16 cmd_out_len; + /* must be last field in this structure */ + struct mlx5_ib_uapi_devx_async_cmd_hdr hdr; +}; + #define MLX5_MAX_DESTROY_INBOX_SIZE_DW MLX5_ST_SZ_DW(delete_fte_in) struct devx_obj { struct mlx5_core_dev *mdev; @@ -1172,11 +1183,13 @@ struct devx_async_event_queue { spinlock_t lock; wait_queue_head_t poll_wait; struct list_head event_list; + atomic_t bytes_in_use; }; struct devx_async_cmd_event_file { struct ib_uobject uobj; struct devx_async_event_queue ev_queue; + struct mlx5_async_ctx async_ctx; }; static void devx_init_event_queue(struct devx_async_event_queue *ev_queue) @@ -1184,6 +1197,7 @@ static void devx_init_event_queue(struct devx_async_event_queue *ev_queue) spin_lock_init(&ev_queue->lock); INIT_LIST_HEAD(&ev_queue->event_list); init_waitqueue_head(&ev_queue->poll_wait); + atomic_set(&ev_queue->bytes_in_use, 0); } static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_ASYNC_CMD_FD_ALLOC)( @@ -1193,13 +1207,123 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_ASYNC_CMD_FD_ALLOC)( struct ib_uobject *uobj = uverbs_attr_get_uobject( attrs, MLX5_IB_ATTR_DEVX_ASYNC_CMD_FD_ALLOC_HANDLE); + struct mlx5_ib_dev *mdev = to_mdev(uobj->context->device); ev_file = container_of(uobj, struct devx_async_cmd_event_file, uobj); devx_init_event_queue(&ev_file->ev_queue); + mlx5_cmd_init_async_ctx(mdev->mdev, &ev_file->async_ctx); return 0; } +static void devx_query_callback(int status, struct mlx5_async_work *context) +{ + struct devx_async_data *async_data = + container_of(context, struct devx_async_data, cb_work); + struct ib_uobject *fd_uobj = async_data->fd_uobj; + struct devx_async_cmd_event_file *ev_file; + struct devx_async_event_queue *ev_queue; + unsigned long flags; + + ev_file = container_of(fd_uobj, struct devx_async_cmd_event_file, + uobj); + ev_queue = &ev_file->ev_queue; + + spin_lock_irqsave(&ev_queue->lock, flags); + list_add_tail(&async_data->list, &ev_queue->event_list); + spin_unlock_irqrestore(&ev_queue->lock, flags); + + wake_up_interruptible(&ev_queue->poll_wait); + fput(fd_uobj->object); +} + +#define MAX_ASYNC_BYTES_IN_USE (1024 * 1024) /* 1MB */ + +static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_ASYNC_QUERY)( + struct uverbs_attr_bundle *attrs) +{ + void *cmd_in = uverbs_attr_get_alloced_ptr(attrs, + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_CMD_IN); + struct ib_uobject *uobj = uverbs_attr_get_uobject( + attrs, + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_HANDLE); + u16 cmd_out_len; + struct mlx5_ib_ucontext *c = to_mucontext(uobj->context); + struct ib_uobject *fd_uobj; + int err; + int uid; + struct mlx5_ib_dev *mdev = to_mdev(uobj->context->device); + struct devx_async_cmd_event_file *ev_file; + struct devx_async_data *async_data; + + uid = devx_get_uid(c, cmd_in); + if (uid < 0) + return uid; + + if (!devx_is_obj_query_cmd(cmd_in)) + return -EINVAL; + + err = uverbs_get_const(&cmd_out_len, attrs, + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_OUT_LEN); + if (err) + return err; + + if (!devx_is_valid_obj_id(uobj, cmd_in)) + return -EINVAL; + + fd_uobj = uverbs_attr_get_uobject(attrs, + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_FD); + if (IS_ERR(fd_uobj)) + return PTR_ERR(fd_uobj); + + ev_file = container_of(fd_uobj, struct devx_async_cmd_event_file, + uobj); + + if (atomic_add_return(cmd_out_len, &ev_file->ev_queue.bytes_in_use) > + MAX_ASYNC_BYTES_IN_USE) { + atomic_sub(cmd_out_len, &ev_file->ev_queue.bytes_in_use); + return -EAGAIN; + } + + async_data = kvzalloc(struct_size(async_data, hdr.out_data, + cmd_out_len), GFP_KERNEL); + if (!async_data) { + err = -ENOMEM; + goto sub_bytes; + } + + err = uverbs_copy_from(&async_data->hdr.wr_id, attrs, + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_WR_ID); + if (err) + goto free_async; + + async_data->cmd_out_len = cmd_out_len; + async_data->mdev = mdev; + async_data->fd_uobj = fd_uobj; + + get_file(fd_uobj->object); + MLX5_SET(general_obj_in_cmd_hdr, cmd_in, uid, uid); + err = mlx5_cmd_exec_cb(&ev_file->async_ctx, cmd_in, + uverbs_attr_get_len(attrs, + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_CMD_IN), + async_data->hdr.out_data, + async_data->cmd_out_len, + devx_query_callback, &async_data->cb_work); + + if (err) + goto cb_err; + + return 0; + +cb_err: + fput(fd_uobj->object); +free_async: + kvfree(async_data); +sub_bytes: + atomic_sub(cmd_out_len, &ev_file->ev_queue.bytes_in_use); + return err; +} + static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext, struct uverbs_attr_bundle *attrs, struct devx_umem *obj) @@ -1353,6 +1477,17 @@ static ssize_t devx_async_cmd_event_read(struct file *filp, char __user *buf, static int devx_async_cmd_event_close(struct inode *inode, struct file *filp) { + struct ib_uobject *uobj = filp->private_data; + struct devx_async_cmd_event_file *comp_ev_file = container_of( + uobj, struct devx_async_cmd_event_file, uobj); + struct devx_async_data *entry, *tmp; + + spin_lock_irq(&comp_ev_file->ev_queue.lock); + list_for_each_entry_safe(entry, tmp, + &comp_ev_file->ev_queue.event_list, list) + kvfree(entry); + spin_unlock_irq(&comp_ev_file->ev_queue.lock); + uverbs_close_fd(filp); return 0; } @@ -1374,6 +1509,11 @@ const struct file_operations devx_async_cmd_event_fops = { static int devx_hot_unplug_async_cmd_event_file(struct ib_uobject *uobj, enum rdma_remove_reason why) { + struct devx_async_cmd_event_file *comp_ev_file = + container_of(uobj, struct devx_async_cmd_event_file, + uobj); + + mlx5_cmd_cleanup_async_ctx(&comp_ev_file->async_ctx); return 0; }; @@ -1487,6 +1627,27 @@ DECLARE_UVERBS_NAMED_METHOD( UVERBS_ATTR_MIN_SIZE(MLX5_ST_SZ_BYTES(general_obj_out_cmd_hdr)), UA_MANDATORY)); +DECLARE_UVERBS_NAMED_METHOD( + MLX5_IB_METHOD_DEVX_OBJ_ASYNC_QUERY, + UVERBS_ATTR_IDR(MLX5_IB_ATTR_DEVX_OBJ_QUERY_HANDLE, + UVERBS_IDR_ANY_OBJECT, + UVERBS_ACCESS_READ, + UA_MANDATORY), + UVERBS_ATTR_PTR_IN( + MLX5_IB_ATTR_DEVX_OBJ_QUERY_CMD_IN, + UVERBS_ATTR_MIN_SIZE(MLX5_ST_SZ_BYTES(general_obj_in_cmd_hdr)), + UA_MANDATORY, + UA_ALLOC_AND_COPY), + UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_OUT_LEN, + u16, UA_MANDATORY), + UVERBS_ATTR_FD(MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_FD, + MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD, + UVERBS_ACCESS_READ, + UA_MANDATORY), + UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_WR_ID, + UVERBS_ATTR_TYPE(u64), + UA_MANDATORY)); + DECLARE_UVERBS_GLOBAL_METHODS(MLX5_IB_OBJECT_DEVX, &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_OTHER), &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_QUERY_UAR), @@ -1497,7 +1658,8 @@ DECLARE_UVERBS_NAMED_OBJECT(MLX5_IB_OBJECT_DEVX_OBJ, &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_OBJ_CREATE), &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_OBJ_DESTROY), &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_OBJ_MODIFY), - &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_OBJ_QUERY)); + &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_OBJ_QUERY), + &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_OBJ_ASYNC_QUERY)); DECLARE_UVERBS_NAMED_OBJECT(MLX5_IB_OBJECT_DEVX_UMEM, UVERBS_TYPE_ALLOC_IDR(devx_umem_cleanup), diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h index 6ceae29d77cd..8149d224030b 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h +++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h @@ -84,6 +84,14 @@ enum mlx5_ib_devx_obj_query_attrs { MLX5_IB_ATTR_DEVX_OBJ_QUERY_CMD_OUT, }; +enum mlx5_ib_devx_obj_query_async_attrs { + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_HANDLE = (1U << UVERBS_ID_NS_SHIFT), + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_CMD_IN, + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_FD, + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_WR_ID, + MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_OUT_LEN, +}; + enum mlx5_ib_devx_query_eqn_attrs { MLX5_IB_ATTR_DEVX_QUERY_EQN_USER_VEC = (1U << UVERBS_ID_NS_SHIFT), MLX5_IB_ATTR_DEVX_QUERY_EQN_DEV_EQN, @@ -94,6 +102,7 @@ enum mlx5_ib_devx_obj_methods { MLX5_IB_METHOD_DEVX_OBJ_DESTROY, MLX5_IB_METHOD_DEVX_OBJ_MODIFY, MLX5_IB_METHOD_DEVX_OBJ_QUERY, + MLX5_IB_METHOD_DEVX_OBJ_ASYNC_QUERY, }; enum mlx5_ib_devx_umem_reg_attrs { diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h index 4ef62c0e8452..4a701033b93f 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h +++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h @@ -51,5 +51,10 @@ enum mlx5_ib_uapi_flow_action_packet_reformat_type { MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x3, }; +struct mlx5_ib_uapi_devx_async_cmd_hdr { + __aligned_u64 wr_id; + __u8 out_data[]; +}; + #endif -- cgit v1.2.3 From 71368af9027f18fe5d1c6f372cfdff7e4bde8b48 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 16 Jan 2019 17:01:36 -0500 Subject: x86/speculation: Add PR_SPEC_DISABLE_NOEXEC With the default SPEC_STORE_BYPASS_SECCOMP/SPEC_STORE_BYPASS_PRCTL mode, the TIF_SSBD bit will be inherited when a new task is fork'ed or cloned. It will also remain when a new program is execve'ed. Only certain class of applications (like Java) that can run on behalf of multiple users on a single thread will require disabling speculative store bypass for security purposes. Those applications will call prctl(2) at startup time to disable SSB. They won't rely on the fact the SSB might have been disabled. Other applications that don't need SSBD will just move on without checking if SSBD has been turned on or not. The fact that the TIF_SSBD is inherited across execve(2) boundary will cause performance of applications that don't need SSBD but their predecessors have SSBD on to be unwittingly impacted especially if they write to memory a lot. To remedy this problem, a new PR_SPEC_DISABLE_NOEXEC argument for the PR_SET_SPECULATION_CTRL option of prctl(2) is added to allow applications to specify that the SSBD feature bit on the task structure should be cleared whenever a new program is being execve'ed. Suggested-by: Thomas Gleixner Signed-off-by: Waiman Long Signed-off-by: Thomas Gleixner Cc: Borislav Petkov Cc: Jonathan Corbet Cc: linux-doc@vger.kernel.org Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: David Woodhouse Cc: Jiri Kosina Cc: Josh Poimboeuf Cc: Tim Chen Cc: KarimAllah Ahmed Cc: Peter Zijlstra Cc: Konrad Rzeszutek Wilk Link: https://lkml.kernel.org/r/1547676096-3281-1-git-send-email-longman@redhat.com --- Documentation/userspace-api/spec_ctrl.rst | 27 +++++++++++++++------------ arch/x86/kernel/cpu/bugs.c | 12 ++++++++++++ arch/x86/kernel/process.c | 12 ++++++++++++ include/linux/sched.h | 5 +++++ include/uapi/linux/prctl.h | 1 + tools/include/uapi/linux/prctl.h | 1 + 6 files changed, 46 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst index c4dbe6f7cdae..1129c7550a48 100644 --- a/Documentation/userspace-api/spec_ctrl.rst +++ b/Documentation/userspace-api/spec_ctrl.rst @@ -28,18 +28,20 @@ PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature which is selected with arg2 of prctl(2). The return value uses bits 0-3 with the following meaning: -==== ===================== =================================================== -Bit Define Description -==== ===================== =================================================== -0 PR_SPEC_PRCTL Mitigation can be controlled per task by - PR_SET_SPECULATION_CTRL. -1 PR_SPEC_ENABLE The speculation feature is enabled, mitigation is - disabled. -2 PR_SPEC_DISABLE The speculation feature is disabled, mitigation is - enabled. -3 PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A - subsequent prctl(..., PR_SPEC_ENABLE) will fail. -==== ===================== =================================================== +==== ====================== ================================================== +Bit Define Description +==== ====================== ================================================== +0 PR_SPEC_PRCTL Mitigation can be controlled per task by + PR_SET_SPECULATION_CTRL. +1 PR_SPEC_ENABLE The speculation feature is enabled, mitigation is + disabled. +2 PR_SPEC_DISABLE The speculation feature is disabled, mitigation is + enabled. +3 PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A + subsequent prctl(..., PR_SPEC_ENABLE) will fail. +4 PR_SPEC_DISABLE_NOEXEC Same as PR_SPEC_DISABLE, but the state will be + cleared on :manpage:`execve(2)`. +==== ====================== ================================================== If all bits are 0 the CPU is not affected by the speculation misfeature. @@ -92,6 +94,7 @@ Speculation misfeature controls * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE_NOEXEC, 0, 0); - PR_SPEC_INDIR_BRANCH: Indirect Branch Speculation in User Processes (Mitigate Spectre V2 style attacks against user processes) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1de0f4170178..2faeaf46347a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -798,15 +798,25 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) if (task_spec_ssb_force_disable(task)) return -EPERM; task_clear_spec_ssb_disable(task); + task_clear_spec_ssb_noexec(task); task_update_spec_tif(task); break; case PR_SPEC_DISABLE: task_set_spec_ssb_disable(task); + task_clear_spec_ssb_noexec(task); task_update_spec_tif(task); break; case PR_SPEC_FORCE_DISABLE: task_set_spec_ssb_disable(task); task_set_spec_ssb_force_disable(task); + task_clear_spec_ssb_noexec(task); + task_update_spec_tif(task); + break; + case PR_SPEC_DISABLE_NOEXEC: + if (task_spec_ssb_force_disable(task)) + return -EPERM; + task_set_spec_ssb_disable(task); + task_set_spec_ssb_noexec(task); task_update_spec_tif(task); break; default: @@ -885,6 +895,8 @@ static int ssb_prctl_get(struct task_struct *task) case SPEC_STORE_BYPASS_PRCTL: if (task_spec_ssb_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_noexec(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE_NOEXEC; if (task_spec_ssb_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 90ae0ca51083..58ac7be52c7a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -255,6 +255,18 @@ void arch_setup_new_exec(void) /* If cpuid was previously disabled for this task, re-enable it. */ if (test_thread_flag(TIF_NOCPUID)) enable_cpuid(); + + /* + * Don't inherit TIF_SSBD across exec boundary when + * PR_SPEC_DISABLE_NOEXEC is used. + */ + if (test_thread_flag(TIF_SSBD) && + task_spec_ssb_noexec(current)) { + clear_thread_flag(TIF_SSBD); + task_clear_spec_ssb_disable(current); + task_clear_spec_ssb_noexec(current); + speculation_ctrl_update(task_thread_info(current)->flags); + } } static inline void switch_to_bitmap(struct thread_struct *prev, diff --git a/include/linux/sched.h b/include/linux/sched.h index d2f90fa92468..fc836dc71bba 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1459,6 +1459,7 @@ static inline bool is_percpu_thread(void) #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ #define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ +#define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1487,6 +1488,10 @@ TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) +TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec) +TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec) +TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec) + TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index b4875a93363a..094bb03b9cc2 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -219,6 +219,7 @@ struct prctl_mm_map { # define PR_SPEC_ENABLE (1UL << 1) # define PR_SPEC_DISABLE (1UL << 2) # define PR_SPEC_FORCE_DISABLE (1UL << 3) +# define PR_SPEC_DISABLE_NOEXEC (1UL << 4) /* Reset arm64 pointer authentication keys */ #define PR_PAC_RESET_KEYS 54 diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index b4875a93363a..094bb03b9cc2 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -219,6 +219,7 @@ struct prctl_mm_map { # define PR_SPEC_ENABLE (1UL << 1) # define PR_SPEC_DISABLE (1UL << 2) # define PR_SPEC_FORCE_DISABLE (1UL << 3) +# define PR_SPEC_DISABLE_NOEXEC (1UL << 4) /* Reset arm64 pointer authentication keys */ #define PR_PAC_RESET_KEYS 54 -- cgit v1.2.3 From 1194c4133195dfcb6c5fc0935d54bbed872a5285 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Tue, 29 Jan 2019 00:56:17 +0000 Subject: nfit: Add Hyper-V NVDIMM DSM command set to white list Add the Hyper-V _DSM command set to the white list of NVDIMM command sets. This command set is documented at http://www.uefi.org/RFIC_LIST (see "Virtual NVDIMM 0x1901"). Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Signed-off-by: Dan Williams --- drivers/acpi/nfit/core.c | 17 ++++++++++++++--- drivers/acpi/nfit/nfit.h | 6 +++++- include/uapi/linux/ndctl.h | 1 + 3 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 1598e3a121a6..4a7e8b1fa43b 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1846,9 +1846,17 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, dev_set_drvdata(&adev_dimm->dev, nfit_mem); /* - * Until standardization materializes we need to consider 4 - * different command sets. Note, that checking for function0 (bit0) - * tells us if any commands are reachable through this GUID. + * There are 4 "legacy" NVDIMM command sets + * (NVDIMM_FAMILY_{INTEL,MSFT,HPE1,HPE2}) that were created before + * an EFI working group was established to constrain this + * proliferation. The nfit driver probes for the supported command + * set by GUID. Note, if you're a platform developer looking to add + * a new command set to this probe, consider using an existing set, + * or otherwise seek approval to publish the command set at + * http://www.uefi.org/RFIC_LIST. + * + * Note, that checking for function0 (bit0) tells us if any commands + * are reachable through this GUID. */ for (i = 0; i <= NVDIMM_FAMILY_MAX; i++) if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1)) @@ -1871,6 +1879,8 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, dsm_mask &= ~(1 << 8); } else if (nfit_mem->family == NVDIMM_FAMILY_MSFT) { dsm_mask = 0xffffffff; + } else if (nfit_mem->family == NVDIMM_FAMILY_HYPERV) { + dsm_mask = 0x1f; } else { dev_dbg(dev, "unknown dimm command family\n"); nfit_mem->family = -1; @@ -3714,6 +3724,7 @@ static __init int nfit_init(void) guid_parse(UUID_NFIT_DIMM_N_HPE1, &nfit_uuid[NFIT_DEV_DIMM_N_HPE1]); guid_parse(UUID_NFIT_DIMM_N_HPE2, &nfit_uuid[NFIT_DEV_DIMM_N_HPE2]); guid_parse(UUID_NFIT_DIMM_N_MSFT, &nfit_uuid[NFIT_DEV_DIMM_N_MSFT]); + guid_parse(UUID_NFIT_DIMM_N_HYPERV, &nfit_uuid[NFIT_DEV_DIMM_N_HYPERV]); nfit_wq = create_singlethread_workqueue("nfit"); if (!nfit_wq) diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 33691aecfcee..4de167b4f76f 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -34,11 +34,14 @@ /* https://msdn.microsoft.com/library/windows/hardware/mt604741 */ #define UUID_NFIT_DIMM_N_MSFT "1ee68b36-d4bd-4a1a-9a16-4f8e53d46e05" +/* http://www.uefi.org/RFIC_LIST (see "Virtual NVDIMM 0x1901") */ +#define UUID_NFIT_DIMM_N_HYPERV "5746c5f2-a9a2-4264-ad0e-e4ddc9e09e80" + #define ACPI_NFIT_MEM_FAILED_MASK (ACPI_NFIT_MEM_SAVE_FAILED \ | ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \ | ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED) -#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_MSFT +#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_HYPERV #define NVDIMM_STANDARD_CMDMASK \ (1 << ND_CMD_SMART | 1 << ND_CMD_SMART_THRESHOLD | 1 << ND_CMD_DIMM_FLAGS \ @@ -94,6 +97,7 @@ enum nfit_uuids { NFIT_DEV_DIMM_N_HPE1 = NVDIMM_FAMILY_HPE1, NFIT_DEV_DIMM_N_HPE2 = NVDIMM_FAMILY_HPE2, NFIT_DEV_DIMM_N_MSFT = NVDIMM_FAMILY_MSFT, + NFIT_DEV_DIMM_N_HYPERV = NVDIMM_FAMILY_HYPERV, NFIT_SPA_VOLATILE, NFIT_SPA_PM, NFIT_SPA_DCR, diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index f57c9e434d2d..de5d90212409 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -243,6 +243,7 @@ struct nd_cmd_pkg { #define NVDIMM_FAMILY_HPE1 1 #define NVDIMM_FAMILY_HPE2 2 #define NVDIMM_FAMILY_MSFT 3 +#define NVDIMM_FAMILY_HYPERV 4 #define ND_IOCTL_CALL _IOWR(ND_IOCTL, ND_CMD_CALL,\ struct nd_cmd_pkg) -- cgit v1.2.3 From 39e6160e14bd011988e4f88fd3d3f1205c3b9776 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:20 +0530 Subject: devlink: Add devlink_param for port register and unregister Add functions to register and unregister for the driver supported configuration parameters table per port. v7->v8: - Order the definitions following way as suggested by Jiri. __devlink_params_register __devlink_params_unregister devlink_params_register devlink_params_unregister devlink_port_params_register devlink_port_params_unregister - Append with Acked-by: Jiri Pirko . v2->v3: - Add a helper __devlink_params_register() with common code used by both devlink_params_register() and devlink_port_params_register(). Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 22 +++++++++ net/core/devlink.c | 133 +++++++++++++++++++++++++++++++++++--------------- 2 files changed, 117 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 67f4293bc970..7fc0748c58e3 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -48,6 +48,7 @@ struct devlink_port_attrs { struct devlink_port { struct list_head list; + struct list_head param_list; struct devlink *devlink; unsigned index; bool registered; @@ -567,6 +568,12 @@ int devlink_params_register(struct devlink *devlink, void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count); +int devlink_port_params_register(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count); +void devlink_port_params_unregister(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count); int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, @@ -791,6 +798,21 @@ devlink_params_unregister(struct devlink *devlink, } +static inline int +devlink_port_params_register(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ + return 0; +} + +static inline void +devlink_port_params_unregister(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ +} + static inline int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val) diff --git a/net/core/devlink.c b/net/core/devlink.c index abb0da9d7b4b..371481ca2afd 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3147,12 +3147,12 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, } static int devlink_param_register_one(struct devlink *devlink, + struct list_head *param_list, const struct devlink_param *param) { struct devlink_param_item *param_item; - if (devlink_param_find_by_name(&devlink->param_list, - param->name)) + if (devlink_param_find_by_name(param_list, param->name)) return -EEXIST; if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT)) @@ -3165,18 +3165,18 @@ static int devlink_param_register_one(struct devlink *devlink, return -ENOMEM; param_item->param = param; - list_add_tail(¶m_item->list, &devlink->param_list); + list_add_tail(¶m_item->list, param_list); devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); return 0; } static void devlink_param_unregister_one(struct devlink *devlink, + struct list_head *param_list, const struct devlink_param *param) { struct devlink_param_item *param_item; - param_item = devlink_param_find_by_name(&devlink->param_list, - param->name); + param_item = devlink_param_find_by_name(param_list, param->name); WARN_ON(!param_item); devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_DEL); list_del(¶m_item->list); @@ -3954,6 +3954,7 @@ int devlink_port_register(struct devlink *devlink, devlink_port->index = port_index; devlink_port->registered = true; list_add_tail(&devlink_port->list, &devlink->port_list); + INIT_LIST_HEAD(&devlink_port->param_list); mutex_unlock(&devlink->lock); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; @@ -4471,18 +4472,20 @@ out: } EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister); -/** - * devlink_params_register - register configuration parameters - * - * @devlink: devlink - * @params: configuration parameters array - * @params_count: number of parameters provided - * - * Register the configuration parameters supported by the driver. - */ -int devlink_params_register(struct devlink *devlink, - const struct devlink_param *params, - size_t params_count) +static int devlink_param_verify(const struct devlink_param *param) +{ + if (!param || !param->name || !param->supported_cmodes) + return -EINVAL; + if (param->generic) + return devlink_param_generic_verify(param); + else + return devlink_param_driver_verify(param); +} + +static int __devlink_params_register(struct devlink *devlink, + struct list_head *param_list, + const struct devlink_param *params, + size_t params_count) { const struct devlink_param *param = params; int i; @@ -4490,20 +4493,11 @@ int devlink_params_register(struct devlink *devlink, mutex_lock(&devlink->lock); for (i = 0; i < params_count; i++, param++) { - if (!param || !param->name || !param->supported_cmodes) { - err = -EINVAL; + err = devlink_param_verify(param); + if (err) goto rollback; - } - if (param->generic) { - err = devlink_param_generic_verify(param); - if (err) - goto rollback; - } else { - err = devlink_param_driver_verify(param); - if (err) - goto rollback; - } - err = devlink_param_register_one(devlink, param); + + err = devlink_param_register_one(devlink, param_list, param); if (err) goto rollback; } @@ -4515,11 +4509,42 @@ rollback: if (!i) goto unlock; for (param--; i > 0; i--, param--) - devlink_param_unregister_one(devlink, param); + devlink_param_unregister_one(devlink, param_list, param); unlock: mutex_unlock(&devlink->lock); return err; } + +static void __devlink_params_unregister(struct devlink *devlink, + struct list_head *param_list, + const struct devlink_param *params, + size_t params_count) +{ + const struct devlink_param *param = params; + int i; + + mutex_lock(&devlink->lock); + for (i = 0; i < params_count; i++, param++) + devlink_param_unregister_one(devlink, param_list, param); + mutex_unlock(&devlink->lock); +} + +/** + * devlink_params_register - register configuration parameters + * + * @devlink: devlink + * @params: configuration parameters array + * @params_count: number of parameters provided + * + * Register the configuration parameters supported by the driver. + */ +int devlink_params_register(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count) +{ + return __devlink_params_register(devlink, &devlink->param_list, params, + params_count); +} EXPORT_SYMBOL_GPL(devlink_params_register); /** @@ -4532,16 +4557,48 @@ void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count) { - const struct devlink_param *param = params; - int i; - - mutex_lock(&devlink->lock); - for (i = 0; i < params_count; i++, param++) - devlink_param_unregister_one(devlink, param); - mutex_unlock(&devlink->lock); + return __devlink_params_unregister(devlink, &devlink->param_list, + params, params_count); } EXPORT_SYMBOL_GPL(devlink_params_unregister); +/** + * devlink_port_params_register - register port configuration parameters + * + * @devlink_port: devlink port + * @params: configuration parameters array + * @params_count: number of parameters provided + * + * Register the configuration parameters supported by the port. + */ +int devlink_port_params_register(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ + return __devlink_params_register(devlink_port->devlink, + &devlink_port->param_list, params, + params_count); +} +EXPORT_SYMBOL_GPL(devlink_port_params_register); + +/** + * devlink_port_params_unregister - unregister port configuration + * parameters + * + * @devlink_port: devlink port + * @params: configuration parameters array + * @params_count: number of parameters provided + */ +void devlink_port_params_unregister(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ + return __devlink_params_unregister(devlink_port->devlink, + &devlink_port->param_list, + params, params_count); +} +EXPORT_SYMBOL_GPL(devlink_port_params_unregister); + /** * devlink_param_driverinit_value_get - get configuration parameter * value for driver initializing -- cgit v1.2.3 From f4601dee25d5fe8010023552b10879f3d62e45ce Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:21 +0530 Subject: devlink: Add port param get command Add port param get command which gets data per parameter. It also has option to dump the parameters data per port. v7->v8: Append "Acked-by: Jiri Pirko " Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 2 + net/core/devlink.c | 102 ++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 97 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6e52d3660654..448973beac9d 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -89,6 +89,8 @@ enum devlink_command { DEVLINK_CMD_REGION_DEL, DEVLINK_CMD_REGION_READ, + DEVLINK_CMD_PORT_PARAM_GET, /* can dump */ + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 diff --git a/net/core/devlink.c b/net/core/devlink.c index 371481ca2afd..66313dcdbdca 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2843,6 +2843,7 @@ nla_put_failure: } static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, + unsigned int port_index, struct devlink_param_item *param_item, enum devlink_command cmd, u32 portid, u32 seq, int flags) @@ -2880,6 +2881,11 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, if (devlink_nl_put_handle(msg, devlink)) goto genlmsg_cancel; + + if (cmd == DEVLINK_CMD_PORT_PARAM_GET) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index)) + goto genlmsg_cancel; + param_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM); if (!param_attr) goto genlmsg_cancel; @@ -2933,7 +2939,7 @@ static void devlink_param_notify(struct devlink *devlink, msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; - err = devlink_nl_param_fill(msg, devlink, param_item, cmd, 0, 0, 0); + err = devlink_nl_param_fill(msg, devlink, 0, param_item, cmd, 0, 0, 0); if (err) { nlmsg_free(msg); return; @@ -2962,7 +2968,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, idx++; continue; } - err = devlink_nl_param_fill(msg, devlink, param_item, + err = devlink_nl_param_fill(msg, devlink, 0, param_item, DEVLINK_CMD_PARAM_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, @@ -3051,7 +3057,7 @@ devlink_param_value_get_from_info(const struct devlink_param *param, } static struct devlink_param_item * -devlink_param_get_from_info(struct devlink *devlink, +devlink_param_get_from_info(struct list_head *param_list, struct genl_info *info) { char *param_name; @@ -3060,7 +3066,7 @@ devlink_param_get_from_info(struct devlink *devlink, return NULL; param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]); - return devlink_param_find_by_name(&devlink->param_list, param_name); + return devlink_param_find_by_name(param_list, param_name); } static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, @@ -3071,7 +3077,7 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, struct sk_buff *msg; int err; - param_item = devlink_param_get_from_info(devlink, info); + param_item = devlink_param_get_from_info(&devlink->param_list, info); if (!param_item) return -EINVAL; @@ -3079,7 +3085,7 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, if (!msg) return -ENOMEM; - err = devlink_nl_param_fill(msg, devlink, param_item, + err = devlink_nl_param_fill(msg, devlink, 0, param_item, DEVLINK_CMD_PARAM_GET, info->snd_portid, info->snd_seq, 0); if (err) { @@ -3102,7 +3108,7 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, union devlink_param_value value; int err = 0; - param_item = devlink_param_get_from_info(devlink, info); + param_item = devlink_param_get_from_info(&devlink->param_list, info); if (!param_item) return -EINVAL; param = param_item->param; @@ -3183,6 +3189,80 @@ static void devlink_param_unregister_one(struct devlink *devlink, kfree(param_item); } +static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_param_item *param_item; + struct devlink_port *devlink_port; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_port, &devlink->port_list, list) { + list_for_each_entry(param_item, + &devlink_port->param_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_param_fill(msg, + devlink_port->devlink, + devlink_port->index, param_item, + DEVLINK_CMD_PORT_PARAM_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[0]; + struct devlink_param_item *param_item; + struct sk_buff *msg; + int err; + + param_item = devlink_param_get_from_info(&devlink_port->param_list, + info); + if (!param_item) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_param_fill(msg, devlink_port->devlink, + devlink_port->index, param_item, + DEVLINK_CMD_PORT_PARAM_GET, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_snapshot *snapshot) @@ -3820,6 +3900,14 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_GET, + .doit = devlink_nl_cmd_port_param_get_doit, + .dumpit = devlink_nl_cmd_port_param_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, { .cmd = DEVLINK_CMD_REGION_GET, .doit = devlink_nl_cmd_region_get_doit, -- cgit v1.2.3 From 9c54873b4e2ee22507627b1adac9e3a8407741bd Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:22 +0530 Subject: devlink: Add port param set command Add port param set command to set the value for a parameter. Value can be set to any of the supported configuration modes. v7->v8: Append "Acked-by: Jiri Pirko " Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 1 + net/core/devlink.c | 37 ++++++++++++++++++++++++++++++++----- 2 files changed, 33 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 448973beac9d..3658fb20b190 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -90,6 +90,7 @@ enum devlink_command { DEVLINK_CMD_REGION_READ, DEVLINK_CMD_PORT_PARAM_GET, /* can dump */ + DEVLINK_CMD_PORT_PARAM_SET, /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 66313dcdbdca..113ad9f529e1 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3096,10 +3096,11 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, - struct genl_info *info) +static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, + struct list_head *param_list, + struct genl_info *info, + enum devlink_command cmd) { - struct devlink *devlink = info->user_ptr[0]; enum devlink_param_type param_type; struct devlink_param_gset_ctx ctx; enum devlink_param_cmode cmode; @@ -3108,7 +3109,7 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, union devlink_param_value value; int err = 0; - param_item = devlink_param_get_from_info(&devlink->param_list, info); + param_item = devlink_param_get_from_info(param_list, info); if (!param_item) return -EINVAL; param = param_item->param; @@ -3148,10 +3149,19 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, return err; } - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, param_item, cmd); return 0; } +static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + + return __devlink_nl_cmd_param_set_doit(devlink, &devlink->param_list, + info, DEVLINK_CMD_PARAM_NEW); +} + static int devlink_param_register_one(struct devlink *devlink, struct list_head *param_list, const struct devlink_param *param) @@ -3263,6 +3273,16 @@ static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } +static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[0]; + + return __devlink_nl_cmd_param_set_doit(devlink_port->devlink, + &devlink_port->param_list, + info, 0); +} + static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_snapshot *snapshot) @@ -3908,6 +3928,13 @@ static const struct genl_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_SET, + .doit = devlink_nl_cmd_port_param_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, { .cmd = DEVLINK_CMD_REGION_GET, .doit = devlink_nl_cmd_region_get_doit, -- cgit v1.2.3 From ffd19b9a490a6b022b58bada054ee130fff06a1c Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:23 +0530 Subject: devlink: Add support for driverinit get value for devlink_port Add support for "driverinit" configuration mode value for devlink_port configuration parameters. Add devlink_port_param_driverinit_value_get() function to help the driver get the value from devlink_port. Also, move the common code to __devlink_param_driverinit_value_get() to be used by both device and port params. v7->v8: -Add the missing devlink_port_param_driverinit_value_get() declaration. -Also, order devlink_port_param_driverinit_value_get() after devlink_param_driverinit_value_get/set() calls Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 12 +++++++++ net/core/devlink.c | 67 ++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 62 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7fc0748c58e3..3943072d3552 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -578,6 +578,10 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val); +int +devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value *init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src); @@ -827,6 +831,14 @@ devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, return -EOPNOTSUPP; } +static inline int +devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value *init_val) +{ + return -EOPNOTSUPP; +} + static inline void devlink_param_value_changed(struct devlink *devlink, u32 param_id) { diff --git a/net/core/devlink.c b/net/core/devlink.c index 113ad9f529e1..fdfdb9b571a9 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4714,26 +4714,13 @@ void devlink_port_params_unregister(struct devlink_port *devlink_port, } EXPORT_SYMBOL_GPL(devlink_port_params_unregister); -/** - * devlink_param_driverinit_value_get - get configuration parameter - * value for driver initializing - * - * @devlink: devlink - * @param_id: parameter ID - * @init_val: value of parameter in driverinit configuration mode - * - * This function should be used by the driver to get driverinit - * configuration for initialization after reload command. - */ -int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, - union devlink_param_value *init_val) +static int +__devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id, + union devlink_param_value *init_val) { struct devlink_param_item *param_item; - if (!devlink->ops || !devlink->ops->reload) - return -EOPNOTSUPP; - - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); + param_item = devlink_param_find_by_id(param_list, param_id); if (!param_item) return -EINVAL; @@ -4749,6 +4736,27 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, return 0; } + +/** + * devlink_param_driverinit_value_get - get configuration parameter + * value for driver initializing + * + * @devlink: devlink + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode + * + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. + */ +int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, + union devlink_param_value *init_val) +{ + if (!devlink->ops || !devlink->ops->reload) + return -EOPNOTSUPP; + + return __devlink_param_driverinit_value_get(&devlink->param_list, + param_id, init_val); +} EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); /** @@ -4787,6 +4795,31 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, } EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); +/** + * devlink_port_param_driverinit_value_get - get configuration parameter + * value for driver initializing + * + * @devlink_port: devlink_port + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode + * + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. + */ +int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value *init_val) +{ + struct devlink *devlink = devlink_port->devlink; + + if (!devlink->ops || !devlink->ops->reload) + return -EOPNOTSUPP; + + return __devlink_param_driverinit_value_get(&devlink_port->param_list, + param_id, init_val); +} +EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_get); + /** * devlink_param_value_changed - notify devlink on a parameter's value * change. Should be called by the driver -- cgit v1.2.3 From 5473a7bdad78f2efe8ee508e8c7bbb762896e78f Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:24 +0530 Subject: devlink: Add support for driverinit set value for devlink_port Add support for "driverinit" configuration mode value for devlink_port configuration parameters. Add devlink_port_param_driverinit_value_set() function to help the driver set the value to devlink_port. Also, move the common code to __devlink_param_driverinit_value_set() to be used by both device and port params. v7->v8: Re-order the definitions as follows: __devlink_param_driverinit_value_get __devlink_param_driverinit_value_set devlink_param_driverinit_value_get devlink_param_driverinit_value_set devlink_port_param_driverinit_value_get devlink_port_param_driverinit_value_set Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 11 ++++++++ net/core/devlink.c | 70 ++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 63 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 3943072d3552..ae2ccf297946 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -582,6 +582,9 @@ int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, u32 param_id, union devlink_param_value *init_val); +int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src); @@ -839,6 +842,14 @@ devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, return -EOPNOTSUPP; } +static inline int +devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value init_val) +{ + return -EOPNOTSUPP; +} + static inline void devlink_param_value_changed(struct devlink *devlink, u32 param_id) { diff --git a/net/core/devlink.c b/net/core/devlink.c index fdfdb9b571a9..55456cc36833 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4737,6 +4737,32 @@ __devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id, return 0; } +static int +__devlink_param_driverinit_value_set(struct devlink *devlink, + struct list_head *param_list, u32 param_id, + union devlink_param_value init_val, + enum devlink_command cmd) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(param_list, param_id); + if (!param_item) + return -EINVAL; + + if (!devlink_param_cmode_is_supported(param_item->param, + DEVLINK_PARAM_CMODE_DRIVERINIT)) + return -EOPNOTSUPP; + + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, init_val.vstr); + else + param_item->driverinit_value = init_val; + param_item->driverinit_value_valid = true; + + devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + return 0; +} + /** * devlink_param_driverinit_value_get - get configuration parameter * value for driver initializing @@ -4774,24 +4800,10 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val) { - struct devlink_param_item *param_item; - - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); - if (!param_item) - return -EINVAL; - - if (!devlink_param_cmode_is_supported(param_item->param, - DEVLINK_PARAM_CMODE_DRIVERINIT)) - return -EOPNOTSUPP; - - if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) - strcpy(param_item->driverinit_value.vstr, init_val.vstr); - else - param_item->driverinit_value = init_val; - param_item->driverinit_value_valid = true; - - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); - return 0; + return __devlink_param_driverinit_value_set(devlink, + &devlink->param_list, + param_id, init_val, + DEVLINK_CMD_PARAM_NEW); } EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); @@ -4820,6 +4832,28 @@ int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, } EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_get); +/** + * devlink_port_param_driverinit_value_set - set value of configuration + * parameter for driverinit + * configuration mode + * + * @devlink_port: devlink_port + * @param_id: parameter ID + * @init_val: value of parameter to set for driverinit configuration mode + * + * This function should be used by the driver to set driverinit + * configuration mode default value. + */ +int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value init_val) +{ + return __devlink_param_driverinit_value_set(devlink_port->devlink, + &devlink_port->param_list, + param_id, init_val, 0); +} +EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_set); + /** * devlink_param_value_changed - notify devlink on a parameter's value * change. Should be called by the driver -- cgit v1.2.3 From c1e5786d6771c67fe044c3bcaa23e631e0503261 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:25 +0530 Subject: devlink: Add devlink notifications support for port params Add notification call for devlink port param set, register and unregister functions. Add devlink_port_param_value_changed() function to enable the driver notify devlink on value change. Driver should use this function after value was changed on any configuration mode part to driverinit. v7->v8: Order devlink_port_param_value_changed() definitions followed by devlink_param_value_changed() Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++ include/uapi/linux/devlink.h | 2 + net/core/devlink.c | 111 ++++++++++++++++++++++++++++++++----------- 3 files changed, 94 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index ae2ccf297946..ceb5e89d74d6 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -586,6 +586,8 @@ int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, u32 param_id, union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); +void devlink_port_param_value_changed(struct devlink_port *devlink_port, + u32 param_id); void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src); struct devlink_region *devlink_region_create(struct devlink *devlink, @@ -855,6 +857,12 @@ devlink_param_value_changed(struct devlink *devlink, u32 param_id) { } +static inline void +devlink_port_param_value_changed(struct devlink_port *devlink_port, + u32 param_id) +{ +} + static inline void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src) diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 3658fb20b190..61b4447a6c5b 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -91,6 +91,8 @@ enum devlink_command { DEVLINK_CMD_PORT_PARAM_GET, /* can dump */ DEVLINK_CMD_PORT_PARAM_SET, + DEVLINK_CMD_PORT_PARAM_NEW, + DEVLINK_CMD_PORT_PARAM_DEL, /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 55456cc36833..451ab4725340 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2882,7 +2882,9 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, if (devlink_nl_put_handle(msg, devlink)) goto genlmsg_cancel; - if (cmd == DEVLINK_CMD_PORT_PARAM_GET) + if (cmd == DEVLINK_CMD_PORT_PARAM_GET || + cmd == DEVLINK_CMD_PORT_PARAM_NEW || + cmd == DEVLINK_CMD_PORT_PARAM_DEL) if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index)) goto genlmsg_cancel; @@ -2928,18 +2930,22 @@ genlmsg_cancel: } static void devlink_param_notify(struct devlink *devlink, + unsigned int port_index, struct devlink_param_item *param_item, enum devlink_command cmd) { struct sk_buff *msg; int err; - WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL); + WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL && + cmd != DEVLINK_CMD_PORT_PARAM_NEW && + cmd != DEVLINK_CMD_PORT_PARAM_DEL); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; - err = devlink_nl_param_fill(msg, devlink, 0, param_item, cmd, 0, 0, 0); + err = devlink_nl_param_fill(msg, devlink, port_index, param_item, cmd, + 0, 0, 0); if (err) { nlmsg_free(msg); return; @@ -3097,6 +3103,7 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, } static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, + unsigned int port_index, struct list_head *param_list, struct genl_info *info, enum devlink_command cmd) @@ -3149,7 +3156,7 @@ static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, return err; } - devlink_param_notify(devlink, param_item, cmd); + devlink_param_notify(devlink, port_index, param_item, cmd); return 0; } @@ -3158,13 +3165,15 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, { struct devlink *devlink = info->user_ptr[0]; - return __devlink_nl_cmd_param_set_doit(devlink, &devlink->param_list, + return __devlink_nl_cmd_param_set_doit(devlink, 0, &devlink->param_list, info, DEVLINK_CMD_PARAM_NEW); } static int devlink_param_register_one(struct devlink *devlink, + unsigned int port_index, struct list_head *param_list, - const struct devlink_param *param) + const struct devlink_param *param, + enum devlink_command cmd) { struct devlink_param_item *param_item; @@ -3182,19 +3191,21 @@ static int devlink_param_register_one(struct devlink *devlink, param_item->param = param; list_add_tail(¶m_item->list, param_list); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, port_index, param_item, cmd); return 0; } static void devlink_param_unregister_one(struct devlink *devlink, + unsigned int port_index, struct list_head *param_list, - const struct devlink_param *param) + const struct devlink_param *param, + enum devlink_command cmd) { struct devlink_param_item *param_item; param_item = devlink_param_find_by_name(param_list, param->name); WARN_ON(!param_item); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_DEL); + devlink_param_notify(devlink, port_index, param_item, cmd); list_del(¶m_item->list); kfree(param_item); } @@ -3279,8 +3290,9 @@ static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, struct devlink_port *devlink_port = info->user_ptr[0]; return __devlink_nl_cmd_param_set_doit(devlink_port->devlink, - &devlink_port->param_list, - info, 0); + devlink_port->index, + &devlink_port->param_list, info, + DEVLINK_CMD_PORT_PARAM_NEW); } static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, @@ -4598,9 +4610,12 @@ static int devlink_param_verify(const struct devlink_param *param) } static int __devlink_params_register(struct devlink *devlink, + unsigned int port_index, struct list_head *param_list, const struct devlink_param *params, - size_t params_count) + size_t params_count, + enum devlink_command reg_cmd, + enum devlink_command unreg_cmd) { const struct devlink_param *param = params; int i; @@ -4612,7 +4627,8 @@ static int __devlink_params_register(struct devlink *devlink, if (err) goto rollback; - err = devlink_param_register_one(devlink, param_list, param); + err = devlink_param_register_one(devlink, port_index, + param_list, param, reg_cmd); if (err) goto rollback; } @@ -4624,23 +4640,27 @@ rollback: if (!i) goto unlock; for (param--; i > 0; i--, param--) - devlink_param_unregister_one(devlink, param_list, param); + devlink_param_unregister_one(devlink, port_index, param_list, + param, unreg_cmd); unlock: mutex_unlock(&devlink->lock); return err; } static void __devlink_params_unregister(struct devlink *devlink, + unsigned int port_index, struct list_head *param_list, const struct devlink_param *params, - size_t params_count) + size_t params_count, + enum devlink_command cmd) { const struct devlink_param *param = params; int i; mutex_lock(&devlink->lock); for (i = 0; i < params_count; i++, param++) - devlink_param_unregister_one(devlink, param_list, param); + devlink_param_unregister_one(devlink, 0, param_list, param, + cmd); mutex_unlock(&devlink->lock); } @@ -4657,8 +4677,10 @@ int devlink_params_register(struct devlink *devlink, const struct devlink_param *params, size_t params_count) { - return __devlink_params_register(devlink, &devlink->param_list, params, - params_count); + return __devlink_params_register(devlink, 0, &devlink->param_list, + params, params_count, + DEVLINK_CMD_PARAM_NEW, + DEVLINK_CMD_PARAM_DEL); } EXPORT_SYMBOL_GPL(devlink_params_register); @@ -4672,8 +4694,9 @@ void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count) { - return __devlink_params_unregister(devlink, &devlink->param_list, - params, params_count); + return __devlink_params_unregister(devlink, 0, &devlink->param_list, + params, params_count, + DEVLINK_CMD_PARAM_DEL); } EXPORT_SYMBOL_GPL(devlink_params_unregister); @@ -4691,8 +4714,11 @@ int devlink_port_params_register(struct devlink_port *devlink_port, size_t params_count) { return __devlink_params_register(devlink_port->devlink, + devlink_port->index, &devlink_port->param_list, params, - params_count); + params_count, + DEVLINK_CMD_PORT_PARAM_NEW, + DEVLINK_CMD_PORT_PARAM_DEL); } EXPORT_SYMBOL_GPL(devlink_port_params_register); @@ -4709,8 +4735,10 @@ void devlink_port_params_unregister(struct devlink_port *devlink_port, size_t params_count) { return __devlink_params_unregister(devlink_port->devlink, + devlink_port->index, &devlink_port->param_list, - params, params_count); + params, params_count, + DEVLINK_CMD_PORT_PARAM_DEL); } EXPORT_SYMBOL_GPL(devlink_port_params_unregister); @@ -4739,6 +4767,7 @@ __devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id, static int __devlink_param_driverinit_value_set(struct devlink *devlink, + unsigned int port_index, struct list_head *param_list, u32 param_id, union devlink_param_value init_val, enum devlink_command cmd) @@ -4759,7 +4788,7 @@ __devlink_param_driverinit_value_set(struct devlink *devlink, param_item->driverinit_value = init_val; param_item->driverinit_value_valid = true; - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, port_index, param_item, cmd); return 0; } @@ -4800,7 +4829,7 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val) { - return __devlink_param_driverinit_value_set(devlink, + return __devlink_param_driverinit_value_set(devlink, 0, &devlink->param_list, param_id, init_val, DEVLINK_CMD_PARAM_NEW); @@ -4849,8 +4878,10 @@ int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, union devlink_param_value init_val) { return __devlink_param_driverinit_value_set(devlink_port->devlink, + devlink_port->index, &devlink_port->param_list, - param_id, init_val, 0); + param_id, init_val, + DEVLINK_CMD_PORT_PARAM_NEW); } EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_set); @@ -4865,7 +4896,6 @@ EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_set); * This function should be used by the driver to notify devlink on value * change, excluding driverinit configuration mode. * For driverinit configuration mode driver should use the function - * devlink_param_driverinit_value_set() instead. */ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) { @@ -4874,10 +4904,37 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) param_item = devlink_param_find_by_id(&devlink->param_list, param_id); WARN_ON(!param_item); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); } EXPORT_SYMBOL_GPL(devlink_param_value_changed); +/** + * devlink_port_param_value_changed - notify devlink on a parameter's value + * change. Should be called by the driver + * right after the change. + * + * @devlink_port: devlink_port + * @param_id: parameter ID + * + * This function should be used by the driver to notify devlink on value + * change, excluding driverinit configuration mode. + * For driverinit configuration mode driver should use the function + * devlink_port_param_driverinit_value_set() instead. + */ +void devlink_port_param_value_changed(struct devlink_port *devlink_port, + u32 param_id) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(&devlink_port->param_list, + param_id); + WARN_ON(!param_item); + + devlink_param_notify(devlink_port->devlink, devlink_port->index, + param_item, DEVLINK_CMD_PORT_PARAM_NEW); +} +EXPORT_SYMBOL_GPL(devlink_port_param_value_changed); + /** * devlink_param_value_str_fill - Safely fill-up the string preventing * from overflow of the preallocated buffer -- cgit v1.2.3 From b639583f9e36d044ac1b13090ae812266992cbac Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:26 +0530 Subject: devlink: Add a generic wake_on_lan port parameter wake_on_lan - Enables Wake on Lan for this port. If enabled, the controller asserts a wake pin based on the WOL type. v2->v3: - Define only WOL types used now and define them as bitfield, so that mutliple WOL types can be enabled upon power on. - Modify "wake-on-lan" name to "wake_on_lan" to be symmetric with previous definitions. - Rename DEVLINK_PARAM_WOL_XXX to DEVLINK_PARAM_WAKE_XXX to be symmetrical with ethtool WOL definitions. Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++++++ net/core/devlink.c | 5 +++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index ceb5e89d74d6..85c9eabaf056 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -367,12 +367,17 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, + DEVLINK_PARAM_GENERIC_ID_WOL, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, DEVLINK_PARAM_GENERIC_ID_MAX = __DEVLINK_PARAM_GENERIC_ID_MAX - 1, }; +enum devlink_param_wol_types { + DEVLINK_PARAM_WAKE_MAGIC = (1 << 0), +}; + #define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME "internal_error_reset" #define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL @@ -397,6 +402,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME "fw_load_policy" #define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE DEVLINK_PARAM_TYPE_U8 +#define DEVLINK_PARAM_GENERIC_WOL_NAME "wake_on_lan" +#define DEVLINK_PARAM_GENERIC_WOL_TYPE DEVLINK_PARAM_TYPE_U8 + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ diff --git a/net/core/devlink.c b/net/core/devlink.c index 451ab4725340..e6f170caf449 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2697,6 +2697,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME, .type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_WOL, + .name = DEVLINK_PARAM_GENERIC_WOL_NAME, + .type = DEVLINK_PARAM_GENERIC_WOL_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) -- cgit v1.2.3 From 2d908b38d40921a03225d42fd6e48eb51bffd606 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 23 Jan 2019 11:28:19 +0100 Subject: serial: Add Tegra Combined UART driver The Tegra Combined UART (TCU) is a mailbox-based mechanism that allows multiplexing multiple "virtual UARTs" into a single hardware serial port. The TCU is the primary serial port on Tegra194 devices. Add a TCU driver utilizing the mailbox framework, as the used mailboxes are part of Tegra HSP blocks that are already controlled by the Tegra HSP mailbox driver. Based on work by Mikko Perttunen . Signed-off-by: Thierry Reding Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 22 +++ drivers/tty/serial/Makefile | 1 + drivers/tty/serial/tegra-tcu.c | 298 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/serial_core.h | 3 + 4 files changed, 324 insertions(+) create mode 100644 drivers/tty/serial/tegra-tcu.c (limited to 'include') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 089a6f285d5e..72966bc0ac76 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -335,6 +335,28 @@ config SERIAL_TEGRA are enabled). This driver uses the APB DMA to achieve higher baudrate and better performance. +config SERIAL_TEGRA_TCU + tristate "NVIDIA Tegra Combined UART" + depends on ARCH_TEGRA && TEGRA_HSP_MBOX + select SERIAL_CORE + help + Support for the mailbox-based TCU (Tegra Combined UART) serial port. + TCU is a virtual serial port that allows multiplexing multiple data + streams into a single hardware serial port. + +config SERIAL_TEGRA_TCU_CONSOLE + bool "Support for console on a Tegra TCU serial port" + depends on SERIAL_TEGRA_TCU=y + select SERIAL_CORE_CONSOLE + default y + ---help--- + If you say Y here, it will be possible to use a the Tegra TCU as the + system console (the system console is the device which receives all + kernel messages and warnings and which allows logins in single user + mode). + + If unsure, say Y. + config SERIAL_MAX3100 tristate "MAX3100 support" depends on SPI diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index 1511e8a9f856..40b702aaa85e 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -77,6 +77,7 @@ obj-$(CONFIG_SERIAL_LANTIQ) += lantiq.o obj-$(CONFIG_SERIAL_XILINX_PS_UART) += xilinx_uartps.o obj-$(CONFIG_SERIAL_SIRFSOC) += sirfsoc_uart.o obj-$(CONFIG_SERIAL_TEGRA) += serial-tegra.o +obj-$(CONFIG_SERIAL_TEGRA_TCU) += tegra-tcu.o obj-$(CONFIG_SERIAL_AR933X) += ar933x_uart.o obj-$(CONFIG_SERIAL_EFM32_UART) += efm32-uart.o obj-$(CONFIG_SERIAL_ARC) += arc_uart.o diff --git a/drivers/tty/serial/tegra-tcu.c b/drivers/tty/serial/tegra-tcu.c new file mode 100644 index 000000000000..aaf8748a6147 --- /dev/null +++ b/drivers/tty/serial/tegra-tcu.c @@ -0,0 +1,298 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define TCU_MBOX_BYTE(i, x) ((x) << (i * 8)) +#define TCU_MBOX_BYTE_V(x, i) (((x) >> (i * 8)) & 0xff) +#define TCU_MBOX_NUM_BYTES(x) ((x) << 24) +#define TCU_MBOX_NUM_BYTES_V(x) (((x) >> 24) & 0x3) + +struct tegra_tcu { + struct uart_driver driver; +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + struct console console; +#endif + struct uart_port port; + + struct mbox_client tx_client, rx_client; + struct mbox_chan *tx, *rx; +}; + +static unsigned int tegra_tcu_uart_tx_empty(struct uart_port *port) +{ + return TIOCSER_TEMT; +} + +static void tegra_tcu_uart_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ +} + +static unsigned int tegra_tcu_uart_get_mctrl(struct uart_port *port) +{ + return 0; +} + +static void tegra_tcu_uart_stop_tx(struct uart_port *port) +{ +} + +static void tegra_tcu_write_one(struct tegra_tcu *tcu, u32 value, + unsigned int count) +{ + void *msg; + + value |= TCU_MBOX_NUM_BYTES(count); + msg = (void *)(unsigned long)value; + mbox_send_message(tcu->tx, msg); + mbox_flush(tcu->tx, 1000); +} + +static void tegra_tcu_write(struct tegra_tcu *tcu, const char *s, + unsigned int count) +{ + unsigned int written = 0, i = 0; + bool insert_nl = false; + u32 value = 0; + + while (i < count) { + if (insert_nl) { + value |= TCU_MBOX_BYTE(written++, '\n'); + insert_nl = false; + i++; + } else if (s[i] == '\n') { + value |= TCU_MBOX_BYTE(written++, '\r'); + insert_nl = true; + } else { + value |= TCU_MBOX_BYTE(written++, s[i++]); + } + + if (written == 3) { + tegra_tcu_write_one(tcu, value, 3); + value = written = 0; + } + } + + if (written) + tegra_tcu_write_one(tcu, value, written); +} + +static void tegra_tcu_uart_start_tx(struct uart_port *port) +{ + struct tegra_tcu *tcu = port->private_data; + struct circ_buf *xmit = &port->state->xmit; + unsigned long count; + + for (;;) { + count = CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE); + if (!count) + break; + + tegra_tcu_write(tcu, &xmit->buf[xmit->tail], count); + xmit->tail = (xmit->tail + count) & (UART_XMIT_SIZE - 1); + } + + uart_write_wakeup(port); +} + +static void tegra_tcu_uart_stop_rx(struct uart_port *port) +{ +} + +static void tegra_tcu_uart_break_ctl(struct uart_port *port, int ctl) +{ +} + +static int tegra_tcu_uart_startup(struct uart_port *port) +{ + return 0; +} + +static void tegra_tcu_uart_shutdown(struct uart_port *port) +{ +} + +static void tegra_tcu_uart_set_termios(struct uart_port *port, + struct ktermios *new, + struct ktermios *old) +{ +} + +static const struct uart_ops tegra_tcu_uart_ops = { + .tx_empty = tegra_tcu_uart_tx_empty, + .set_mctrl = tegra_tcu_uart_set_mctrl, + .get_mctrl = tegra_tcu_uart_get_mctrl, + .stop_tx = tegra_tcu_uart_stop_tx, + .start_tx = tegra_tcu_uart_start_tx, + .stop_rx = tegra_tcu_uart_stop_rx, + .break_ctl = tegra_tcu_uart_break_ctl, + .startup = tegra_tcu_uart_startup, + .shutdown = tegra_tcu_uart_shutdown, + .set_termios = tegra_tcu_uart_set_termios, +}; + +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) +static void tegra_tcu_console_write(struct console *cons, const char *s, + unsigned int count) +{ + struct tegra_tcu *tcu = container_of(cons, struct tegra_tcu, console); + + tegra_tcu_write(tcu, s, count); +} + +static int tegra_tcu_console_setup(struct console *cons, char *options) +{ + return 0; +} +#endif + +static void tegra_tcu_receive(struct mbox_client *cl, void *msg) +{ + struct tegra_tcu *tcu = container_of(cl, struct tegra_tcu, rx_client); + struct tty_port *port = &tcu->port.state->port; + u32 value = (u32)(unsigned long)msg; + unsigned int num_bytes, i; + + num_bytes = TCU_MBOX_NUM_BYTES_V(value); + + for (i = 0; i < num_bytes; i++) + tty_insert_flip_char(port, TCU_MBOX_BYTE_V(value, i), + TTY_NORMAL); + + tty_flip_buffer_push(port); +} + +static int tegra_tcu_probe(struct platform_device *pdev) +{ + struct uart_port *port; + struct tegra_tcu *tcu; + int err; + + tcu = devm_kzalloc(&pdev->dev, sizeof(*tcu), GFP_KERNEL); + if (!tcu) + return -ENOMEM; + + tcu->tx_client.dev = &pdev->dev; + tcu->rx_client.dev = &pdev->dev; + tcu->rx_client.rx_callback = tegra_tcu_receive; + + tcu->tx = mbox_request_channel_byname(&tcu->tx_client, "tx"); + if (IS_ERR(tcu->tx)) { + err = PTR_ERR(tcu->tx); + dev_err(&pdev->dev, "failed to get tx mailbox: %d\n", err); + return err; + } + + tcu->rx = mbox_request_channel_byname(&tcu->rx_client, "rx"); + if (IS_ERR(tcu->rx)) { + err = PTR_ERR(tcu->rx); + dev_err(&pdev->dev, "failed to get rx mailbox: %d\n", err); + goto free_tx; + } + +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + /* setup the console */ + strcpy(tcu->console.name, "ttyTCU"); + tcu->console.device = uart_console_device; + tcu->console.flags = CON_PRINTBUFFER | CON_ANYTIME; + tcu->console.index = -1; + tcu->console.write = tegra_tcu_console_write; + tcu->console.setup = tegra_tcu_console_setup; + tcu->console.data = &tcu->driver; +#endif + + /* setup the driver */ + tcu->driver.owner = THIS_MODULE; + tcu->driver.driver_name = "tegra-tcu"; + tcu->driver.dev_name = "ttyTCU"; +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + tcu->driver.cons = &tcu->console; +#endif + tcu->driver.nr = 1; + + err = uart_register_driver(&tcu->driver); + if (err) { + dev_err(&pdev->dev, "failed to register UART driver: %d\n", + err); + goto free_rx; + } + + /* setup the port */ + port = &tcu->port; + spin_lock_init(&port->lock); + port->dev = &pdev->dev; + port->type = PORT_TEGRA_TCU; + port->ops = &tegra_tcu_uart_ops; + port->fifosize = 1; + port->iotype = UPIO_MEM; + port->flags = UPF_BOOT_AUTOCONF; + port->private_data = tcu; + + err = uart_add_one_port(&tcu->driver, port); + if (err) { + dev_err(&pdev->dev, "failed to add UART port: %d\n", err); + goto unregister_uart; + } + + platform_set_drvdata(pdev, tcu); +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + register_console(&tcu->console); +#endif + + return 0; + +unregister_uart: + uart_unregister_driver(&tcu->driver); +free_rx: + mbox_free_channel(tcu->rx); +free_tx: + mbox_free_channel(tcu->tx); + + return err; +} + +static int tegra_tcu_remove(struct platform_device *pdev) +{ + struct tegra_tcu *tcu = platform_get_drvdata(pdev); + +#if IS_ENABLED(CONFIG_SERIAL_TEGRA_TCU_CONSOLE) + unregister_console(&tcu->console); +#endif + uart_remove_one_port(&tcu->driver, &tcu->port); + uart_unregister_driver(&tcu->driver); + mbox_free_channel(tcu->rx); + mbox_free_channel(tcu->tx); + + return 0; +} + +static const struct of_device_id tegra_tcu_match[] = { + { .compatible = "nvidia,tegra194-tcu" }, + { } +}; + +static struct platform_driver tegra_tcu_driver = { + .driver = { + .name = "tegra-tcu", + .of_match_table = tegra_tcu_match, + }, + .probe = tegra_tcu_probe, + .remove = tegra_tcu_remove, +}; +module_platform_driver(tegra_tcu_driver); + +MODULE_AUTHOR("Mikko Perttunen "); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("NVIDIA Tegra Combined UART driver"); diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index df4a7534e239..6009ee2c2e99 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -79,6 +79,9 @@ /* Nuvoton UART */ #define PORT_NPCM 40 +/* NVIDIA Tegra Combined UART */ +#define PORT_TEGRA_TCU 41 + /* Intel EG20 */ #define PORT_PCH_8LINE 44 #define PORT_PCH_2LINE 45 -- cgit v1.2.3 From 80df2704a375bb4b3c9c5cce9c00052361b16d61 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 28 Jan 2019 15:08:23 +0800 Subject: sctp: introduce SCTP_FUTURE/CURRENT/ALL_ASSOC This patch is to add 3 constants SCTP_FUTURE_ASSOC, SCTP_CURRENT_ASSOC and SCTP_ALL_ASSOC for reserved assoc_ids, as defined in rfc6458#section-7.2. And add the process for them when doing lookup and inserting in sctp_id2assoc and sctp_assoc_set_id. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 4 ++++ net/sctp/associola.c | 7 +++++-- net/sctp/socket.c | 2 +- 3 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index d584073532b8..b8f2c4d56532 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -59,6 +59,10 @@ typedef __s32 sctp_assoc_t; +#define SCTP_FUTURE_ASSOC 0 +#define SCTP_CURRENT_ASSOC 1 +#define SCTP_ALL_ASSOC 2 + /* The following symbols come from the Sockets API Extensions for * SCTP . */ diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 201c888604e4..b99f163e33ac 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1651,8 +1651,11 @@ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) if (preload) idr_preload(gfp); spin_lock_bh(&sctp_assocs_id_lock); - /* 0 is not a valid assoc_id, must be >= 1 */ - ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, 1, 0, GFP_NOWAIT); + /* 0, 1, 2 are used as SCTP_FUTURE_ASSOC, SCTP_CURRENT_ASSOC and + * SCTP_ALL_ASSOC, so an available id must be > SCTP_ALL_ASSOC. + */ + ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, SCTP_ALL_ASSOC + 1, 0, + GFP_NOWAIT); spin_unlock_bh(&sctp_assocs_id_lock); if (preload) idr_preload_end(); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f93c3cf9e567..a52d132470ea 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -248,7 +248,7 @@ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id) } /* Otherwise this is a UDP-style socket. */ - if (!id || (id == (sctp_assoc_t)-1)) + if (id <= SCTP_ALL_ASSOC) return NULL; spin_lock_bh(&sctp_assocs_id_lock); -- cgit v1.2.3 From 8add543e369d67ccd42f7e67d68866b4d606f632 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 28 Jan 2019 15:08:29 +0800 Subject: sctp: add SCTP_FUTURE_ASSOC for SCTP_PEER_ADDR_THLDS sockopt Check with SCTP_FUTURE_ASSOC instead in sctp_set/getsockopt_paddr_thresholds, it's compatible with 0. It also adds pf_retrans in sctp_sock to support SCTP_FUTURE_ASSOC. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 ++ net/sctp/associola.c | 2 +- net/sctp/socket.c | 58 ++++++++++++++++++++++++++++++++-------------- 3 files changed, 43 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 003020eb6e66..a5a46b1c9261 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -199,6 +199,8 @@ struct sctp_sock { __u32 flowlabel; __u8 dscp; + int pf_retrans; + /* The initial Path MTU to use for new associations. */ __u32 pathmtu; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b99f163e33ac..d2c7d0d2abc1 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -101,7 +101,7 @@ static struct sctp_association *sctp_association_init( * socket values. */ asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt; - asoc->pf_retrans = net->sctp.pf_retrans; + asoc->pf_retrans = sp->pf_retrans; asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial); asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 7df2123ae64c..1d49b7dfcba2 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3888,11 +3888,25 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, sizeof(struct sctp_paddrthlds))) return -EFAULT; - - if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { - asoc = sctp_id2assoc(sk, val.spt_assoc_id); - if (!asoc) + if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { + trans = sctp_addr_id2transport(sk, &val.spt_address, + val.spt_assoc_id); + if (!trans) return -ENOENT; + + if (val.spt_pathmaxrxt) + trans->pathmaxrxt = val.spt_pathmaxrxt; + trans->pf_retrans = val.spt_pathpfthld; + + return 0; + } + + asoc = sctp_id2assoc(sk, val.spt_assoc_id); + if (!asoc && val.spt_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + if (asoc) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { if (val.spt_pathmaxrxt) @@ -3904,14 +3918,11 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, asoc->pathmaxrxt = val.spt_pathmaxrxt; asoc->pf_retrans = val.spt_pathpfthld; } else { - trans = sctp_addr_id2transport(sk, &val.spt_address, - val.spt_assoc_id); - if (!trans) - return -ENOENT; + struct sctp_sock *sp = sctp_sk(sk); if (val.spt_pathmaxrxt) - trans->pathmaxrxt = val.spt_pathmaxrxt; - trans->pf_retrans = val.spt_pathpfthld; + sp->pathmaxrxt = val.spt_pathmaxrxt; + sp->pf_retrans = val.spt_pathpfthld; } return 0; @@ -4781,6 +4792,7 @@ static int sctp_init_sock(struct sock *sk) */ sp->hbinterval = net->sctp.hb_interval; sp->pathmaxrxt = net->sctp.max_retrans_path; + sp->pf_retrans = net->sctp.pf_retrans; sp->pathmtu = 0; /* allow default discovery */ sp->sackdelay = net->sctp.sack_timeout; sp->sackfreq = 2; @@ -6917,14 +6929,7 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, len)) return -EFAULT; - if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { - asoc = sctp_id2assoc(sk, val.spt_assoc_id); - if (!asoc) - return -ENOENT; - - val.spt_pathpfthld = asoc->pf_retrans; - val.spt_pathmaxrxt = asoc->pathmaxrxt; - } else { + if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { trans = sctp_addr_id2transport(sk, &val.spt_address, val.spt_assoc_id); if (!trans) @@ -6932,6 +6937,23 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, val.spt_pathmaxrxt = trans->pathmaxrxt; val.spt_pathpfthld = trans->pf_retrans; + + return 0; + } + + asoc = sctp_id2assoc(sk, val.spt_assoc_id); + if (!asoc && val.spt_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + if (asoc) { + val.spt_pathpfthld = asoc->pf_retrans; + val.spt_pathmaxrxt = asoc->pathmaxrxt; + } else { + struct sctp_sock *sp = sctp_sk(sk); + + val.spt_pathpfthld = sp->pf_retrans; + val.spt_pathmaxrxt = sp->pathmaxrxt; } if (put_user(len, optlen) || copy_to_user(optval, &val, len)) -- cgit v1.2.3 From 7efba10d6bd22030fb5931e50bf97496f932f00e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 28 Jan 2019 15:08:46 +0800 Subject: sctp: add SCTP_FUTURE_ASOC and SCTP_CURRENT_ASSOC for SCTP_STREAM_SCHEDULER sockopt Check with SCTP_ALL_ASSOC instead in sctp_setsockopt_scheduler and check with SCTP_FUTURE_ASSOC instead in sctp_getsockopt_scheduler, it's compatible with 0. SCTP_CURRENT_ASSOC is supported for SCTP_STREAM_SCHEDULER in this patch. It also adds default_ss in sctp_sock to support SCTP_FUTURE_ASSOC. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 ++ net/sctp/outqueue.c | 2 +- net/sctp/socket.c | 44 +++++++++++++++++++++++++++++++------------- 3 files changed, 34 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a5a46b1c9261..58e4b23cecf4 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -211,6 +211,8 @@ struct sctp_sock { /* Flags controlling Heartbeat, SACK delay, and Path MTU Discovery. */ __u32 param_flags; + __u32 default_ss; + struct sctp_rtoinfo rtoinfo; struct sctp_paddrparams paddrparam; struct sctp_assocparams assocparams; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index c37e1c2dec9d..fd33281999b5 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); - sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT); + sctp_sched_set_sched(asoc, sctp_sk(asoc->base.sk)->default_ss); } /* Free the outqueue structure and any related pending chunks. diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 00b0f6659251..9644bdc8e85c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4352,29 +4352,44 @@ static int sctp_setsockopt_scheduler(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_assoc_value params; - int retval = -EINVAL; + int retval = 0; if (optlen < sizeof(params)) - goto out; + return -EINVAL; optlen = sizeof(params); - if (copy_from_user(¶ms, optval, optlen)) { - retval = -EFAULT; - goto out; - } + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; if (params.assoc_value > SCTP_SS_MAX) - goto out; + return -EINVAL; asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) - goto out; + if (!asoc && params.assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - retval = sctp_sched_set_sched(asoc, params.assoc_value); + if (asoc) + return sctp_sched_set_sched(asoc, params.assoc_value); + + if (params.assoc_id == SCTP_FUTURE_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + sp->default_ss = params.assoc_value; + + if (params.assoc_id == SCTP_CURRENT_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + int ret = sctp_sched_set_sched(asoc, + params.assoc_value); + + if (ret && !retval) + retval = ret; + } + } -out: return retval; } @@ -5005,6 +5020,7 @@ static int sctp_init_sock(struct sock *sk) sp->param_flags = SPP_HB_ENABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; + sp->default_ss = SCTP_SS_DEFAULT; /* If enabled no SCTP message fragmentation will be performed. * Configure through SCTP_DISABLE_FRAGMENTS socket option. @@ -7572,12 +7588,14 @@ static int sctp_getsockopt_scheduler(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } - params.assoc_value = sctp_sched_get_sched(asoc); + params.assoc_value = asoc ? sctp_sched_get_sched(asoc) + : sctp_sk(sk)->default_ss; if (put_user(len, optlen)) goto out; -- cgit v1.2.3 From fab940755d1d78377901450b6ee7c77356e06821 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sun, 27 Jan 2019 14:03:57 +0100 Subject: x86/hw_breakpoints, kprobes: Remove kprobes ifdeffery Remove the ifdeffery in the breakpoint parsing arch_build_bp_info() by adding a within_kprobe_blacklist() stub for the !CONFIG_KPROBES case. It is returning true when kprobes are not enabled to mean that any address is within the kprobes blacklist on such kernels and thus not allow kernel breakpoints on non-kprobes kernels. Signed-off-by: Borislav Petkov Acked-by: Masami Hiramatsu Cc: Anil S Keshavamurthy Cc: "David S. Miller" Cc: Frederic Weisbecker Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "Naveen N. Rao" Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190127131237.4557-1-bp@alien8.de --- arch/x86/kernel/hw_breakpoint.c | 4 ---- include/linux/kprobes.h | 5 +++++ 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 7d6f91f2869a..ff9bfd40429e 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -261,12 +261,8 @@ static int arch_build_bp_info(struct perf_event *bp, * allow kernel breakpoints at all. */ if (attr->bp_addr >= TASK_SIZE_MAX) { -#ifdef CONFIG_KPROBES if (within_kprobe_blacklist(attr->bp_addr)) return -EINVAL; -#else - return -EINVAL; -#endif } hw->type = X86_BREAKPOINT_EXECUTE; diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e07e91daaacc..201f0f2683f2 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -442,6 +442,11 @@ static inline int enable_kprobe(struct kprobe *kp) { return -ENOSYS; } + +static inline bool within_kprobe_blacklist(unsigned long addr) +{ + return true; +} #endif /* CONFIG_KPROBES */ static inline int disable_kretprobe(struct kretprobe *rp) { -- cgit v1.2.3 From a97cfe4de1bee89db3286ad0a4201dc6d2b72456 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 30 Jan 2019 08:58:34 +0000 Subject: mlxsw: spectrum_acl: Add C-TCAM spill tracepoint Add some visibility to the rule addition process and trace whenever rule spilled into C-TCAM. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c | 3 ++ include/trace/events/mlxsw.h | 38 ++++++++++++++++++++++ 2 files changed, 41 insertions(+) create mode 100644 include/trace/events/mlxsw.h (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c index cda0a7170c34..a74a390901ac 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c @@ -7,6 +7,8 @@ #include #include #include +#define CREATE_TRACE_POINTS +#include #include "reg.h" #include "core.h" @@ -578,6 +580,7 @@ int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp, /* It is possible we failed to add the rule to the A-TCAM due to * exceeded number of masks. Try to spill into C-TCAM. */ + trace_mlxsw_sp_acl_atcam_entry_add_ctcam_spill(mlxsw_sp, aregion); err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &aregion->cregion, &achunk->cchunk, &aentry->centry, rulei, true); diff --git a/include/trace/events/mlxsw.h b/include/trace/events/mlxsw.h new file mode 100644 index 000000000000..6c2bafcade18 --- /dev/null +++ b/include/trace/events/mlxsw.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlxsw + +#if !defined(_MLXSW_TRACEPOINT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _MLXSW_TRACEPOINT_H + +#include + +struct mlxsw_sp; +struct mlxsw_sp_acl_atcam_region; + +TRACE_EVENT(mlxsw_sp_acl_atcam_entry_add_ctcam_spill, + TP_PROTO(const struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_acl_atcam_region *aregion), + + TP_ARGS(mlxsw_sp, aregion), + + TP_STRUCT__entry( + __field(const void *, mlxsw_sp) + __field(const void *, aregion) + ), + + TP_fast_assign( + __entry->mlxsw_sp = mlxsw_sp; + __entry->aregion = aregion; + ), + + TP_printk("mlxsw_sp %p, aregion %p", + __entry->mlxsw_sp, __entry->aregion) +); + +#endif /* _MLXSW_TRACEPOINT_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 5c238a8b599f1ae25eaeb08ad0e9e13e2b9eb023 Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Wed, 30 Jan 2019 10:52:01 +0530 Subject: cpufreq: Auto-register the driver as a thermal cooling device if asked All cpufreq drivers do similar things to register as a cooling device. Provide a cpufreq driver flag so drivers can just ask the cpufreq core to register the cooling device on their behalf. This allows us to get rid of duplicated code in the drivers. In order to allow this, we add a struct thermal_cooling_device pointer to struct cpufreq_policy so that drivers don't need to store it in a private data structure. Suggested-by: Stephen Boyd Suggested-by: Viresh Kumar Signed-off-by: Amit Kucheria Reviewed-by: Matthias Kaehlcke Tested-by: Matthias Kaehlcke Acked-by: Viresh Kumar Reviewed-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 11 +++++++++++ include/linux/cpufreq.h | 9 +++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 3eff158d9750..96a69c67a545 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -19,6 +19,7 @@ #include #include +#include #include #include #include @@ -1316,6 +1317,10 @@ static int cpufreq_online(unsigned int cpu) if (cpufreq_driver->ready) cpufreq_driver->ready(policy); + if (IS_ENABLED(CONFIG_CPU_THERMAL) && + cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV) + policy->cdev = of_cpufreq_cooling_register(policy); + pr_debug("initialization complete\n"); return 0; @@ -1403,6 +1408,12 @@ static int cpufreq_offline(unsigned int cpu) goto unlock; } + if (IS_ENABLED(CONFIG_CPU_THERMAL) && + cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV) { + cpufreq_cooling_unregister(policy->cdev); + policy->cdev = NULL; + } + if (cpufreq_driver->stop_cpu) cpufreq_driver->stop_cpu(policy); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c19142911554..9db074ecbbd7 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -151,6 +151,9 @@ struct cpufreq_policy { /* For cpufreq driver's internal use */ void *driver_data; + + /* Pointer to the cooling device if used for thermal mitigation */ + struct thermal_cooling_device *cdev; }; /* Only for ACPI */ @@ -378,6 +381,12 @@ struct cpufreq_driver { */ #define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING BIT(6) +/* + * Set by drivers that want the core to automatically register the cpufreq + * driver as a thermal cooling device. + */ +#define CPUFREQ_IS_COOLING_DEV BIT(7) + int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -- cgit v1.2.3 From 0b5cb3300ae59ed7e93b465dfa2384a6a4df8eb4 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 22 Jan 2019 10:25:20 -0800 Subject: RDMA/srp: Increase max_segment_size The default behavior of the SCSI core is to set the block layer request queue parameter max_segment_size to 64 KB. That means that elements of scatterlists are limited to 64 KB. Since RDMA adapters support larger sizes, increase max_segment_size for the SRP initiator. Notes: - The SCSI max_segment_size parameter was introduced in kernel v5.0. See also commit 50c2e9107f17 ("scsi: introduce a max_segment_size host_template parameters"). - Some other block drivers already set max_segment_size to UINT_MAX, e.g. nbd and rbd. Signed-off-by: Bart Van Assche Signed-off-by: Jason Gunthorpe --- drivers/infiniband/ulp/srp/ib_srp.c | 1 + include/rdma/ib_verbs.h | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 0f855294ff3f..29fe46dbdbf1 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -3823,6 +3823,7 @@ static ssize_t srp_create_target(struct device *dev, target_host->max_id = 1; target_host->max_lun = -1LL; target_host->max_cmd_len = sizeof ((struct srp_cmd *) (void *) 0L)->cdb; + target_host->max_segment_size = ib_dma_max_seg_size(ibdev); target = host_to_target(target_host); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 94b6e1dd4dab..71ea144ec823 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -3715,6 +3715,19 @@ static inline unsigned int ib_sg_dma_len(struct ib_device *dev, return sg_dma_len(sg); } +/** + * ib_dma_max_seg_size - Return the size limit of a single DMA transfer + * @dev: The device to query + * + * The returned value represents a size in bytes. + */ +static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev) +{ + struct device_dma_parameters *p = dev->dma_device->dma_parms; + + return p ? p->max_segment_size : UINT_MAX; +} + /** * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU * @dev: The device for which the DMA address was created -- cgit v1.2.3 From 9bc61ab18b1d41f26dc06b9e6d3c203e65f83fe6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sun, 4 Nov 2018 03:19:03 -0500 Subject: vfs: Introduce fs_context, switch vfs_kern_mount() to it. Introduce a filesystem context concept to be used during superblock creation for mount and superblock reconfiguration for remount. This is allocated at the beginning of the mount procedure and into it is placed: (1) Filesystem type. (2) Namespaces. (3) Source/Device names (there may be multiple). (4) Superblock flags (SB_*). (5) Security details. (6) Filesystem-specific data, as set by the mount options. Accessor functions are then provided to set up a context, parameterise it from monolithic mount data (the data page passed to mount(2)) and tear it down again. A legacy wrapper is provided that implements what will be the basic operations, wrapping access to filesystems that aren't yet aware of the fs_context. Finally, vfs_kern_mount() is changed to make use of the fs_context and mount_fs() is replaced by vfs_get_tree(), called from vfs_kern_mount(). [AV -- add missing kstrdup()] [AV -- put_cred() can be unconditional - fc->cred can't be NULL] [AV -- take legacy_validate() contents into legacy_parse_monolithic()] [AV -- merge KERNEL_MOUNT and USER_MOUNT] [AV -- don't unlock superblock on success return from vfs_get_tree()] [AV -- kill 'reference' argument of init_fs_context()] Signed-off-by: David Howells Co-developed-by: Al Viro Signed-off-by: Al Viro --- fs/Makefile | 3 +- fs/fs_context.c | 182 +++++++++++++++++++++++++++++++++++++++++++++ fs/internal.h | 9 ++- fs/namespace.c | 46 ++++++++---- fs/super.c | 50 ++++++------- include/linux/fs_context.h | 64 ++++++++++++++++ 6 files changed, 310 insertions(+), 44 deletions(-) create mode 100644 fs/fs_context.c create mode 100644 include/linux/fs_context.h (limited to 'include') diff --git a/fs/Makefile b/fs/Makefile index 293733f61594..5563cf34f7c2 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -12,7 +12,8 @@ obj-y := open.o read_write.o file_table.o super.o \ attr.o bad_inode.o file.o filesystems.o namespace.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o splice.o sync.o utimes.o d_path.o \ - stack.o fs_struct.o statfs.o fs_pin.o nsfs.o + stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \ + fs_context.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o block_dev.o direct-io.o mpage.o diff --git a/fs/fs_context.c b/fs/fs_context.c new file mode 100644 index 000000000000..4294091b689d --- /dev/null +++ b/fs/fs_context.c @@ -0,0 +1,182 @@ +/* Provide a way to create a superblock configuration context within the kernel + * that allows a superblock to be set up prior to mounting. + * + * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "mount.h" +#include "internal.h" + +struct legacy_fs_context { + char *legacy_data; /* Data page for legacy filesystems */ + size_t data_size; +}; + +static int legacy_init_fs_context(struct fs_context *fc); + +/** + * alloc_fs_context - Create a filesystem context. + * @fs_type: The filesystem type. + * @reference: The dentry from which this one derives (or NULL) + * @sb_flags: Filesystem/superblock flags (SB_*) + * @sb_flags_mask: Applicable members of @sb_flags + * @purpose: The purpose that this configuration shall be used for. + * + * Open a filesystem and create a mount context. The mount context is + * initialised with the supplied flags and, if a submount/automount from + * another superblock (referred to by @reference) is supplied, may have + * parameters such as namespaces copied across from that superblock. + */ +static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, + struct dentry *reference, + unsigned int sb_flags, + unsigned int sb_flags_mask, + enum fs_context_purpose purpose) +{ + struct fs_context *fc; + int ret = -ENOMEM; + + fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL); + if (!fc) + return ERR_PTR(-ENOMEM); + + fc->purpose = purpose; + fc->sb_flags = sb_flags; + fc->sb_flags_mask = sb_flags_mask; + fc->fs_type = get_filesystem(fs_type); + fc->cred = get_current_cred(); + fc->net_ns = get_net(current->nsproxy->net_ns); + + switch (purpose) { + case FS_CONTEXT_FOR_MOUNT: + fc->user_ns = get_user_ns(fc->cred->user_ns); + break; + } + + ret = legacy_init_fs_context(fc); + if (ret < 0) + goto err_fc; + fc->need_free = true; + return fc; + +err_fc: + put_fs_context(fc); + return ERR_PTR(ret); +} + +struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, + unsigned int sb_flags) +{ + return alloc_fs_context(fs_type, NULL, sb_flags, 0, + FS_CONTEXT_FOR_MOUNT); +} +EXPORT_SYMBOL(fs_context_for_mount); + +static void legacy_fs_context_free(struct fs_context *fc); +/** + * put_fs_context - Dispose of a superblock configuration context. + * @fc: The context to dispose of. + */ +void put_fs_context(struct fs_context *fc) +{ + struct super_block *sb; + + if (fc->root) { + sb = fc->root->d_sb; + dput(fc->root); + fc->root = NULL; + deactivate_super(sb); + } + + if (fc->need_free) + legacy_fs_context_free(fc); + + security_free_mnt_opts(&fc->security); + if (fc->net_ns) + put_net(fc->net_ns); + put_user_ns(fc->user_ns); + put_cred(fc->cred); + kfree(fc->subtype); + put_filesystem(fc->fs_type); + kfree(fc->source); + kfree(fc); +} +EXPORT_SYMBOL(put_fs_context); + +/* + * Free the config for a filesystem that doesn't support fs_context. + */ +static void legacy_fs_context_free(struct fs_context *fc) +{ + kfree(fc->fs_private); +} + +/* + * Add monolithic mount data. + */ +static int legacy_parse_monolithic(struct fs_context *fc, void *data) +{ + struct legacy_fs_context *ctx = fc->fs_private; + ctx->legacy_data = data; + if (!ctx->legacy_data) + return 0; + if (fc->fs_type->fs_flags & FS_BINARY_MOUNTDATA) + return 0; + return security_sb_eat_lsm_opts(ctx->legacy_data, &fc->security); +} + +/* + * Get a mountable root with the legacy mount command. + */ +int legacy_get_tree(struct fs_context *fc) +{ + struct legacy_fs_context *ctx = fc->fs_private; + struct super_block *sb; + struct dentry *root; + + root = fc->fs_type->mount(fc->fs_type, fc->sb_flags, + fc->source, ctx->legacy_data); + if (IS_ERR(root)) + return PTR_ERR(root); + + sb = root->d_sb; + BUG_ON(!sb); + + fc->root = root; + return 0; +} + +/* + * Initialise a legacy context for a filesystem that doesn't support + * fs_context. + */ +static int legacy_init_fs_context(struct fs_context *fc) +{ + fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL); + if (!fc->fs_private) + return -ENOMEM; + return 0; +} + +int parse_monolithic_mount_data(struct fs_context *fc, void *data) +{ + return legacy_parse_monolithic(fc, data); +} diff --git a/fs/internal.h b/fs/internal.h index d410186bc369..f85c3212d25d 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -17,6 +17,7 @@ struct linux_binprm; struct path; struct mount; struct shrink_control; +struct fs_context; /* * block_dev.c @@ -51,6 +52,12 @@ int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied, */ extern void __init chrdev_init(void); +/* + * fs_context.c + */ +extern int legacy_get_tree(struct fs_context *fc); +extern int parse_monolithic_mount_data(struct fs_context *, void *); + /* * namei.c */ @@ -101,8 +108,6 @@ extern struct file *alloc_empty_file_noaccount(int, const struct cred *); */ extern int do_remount_sb(struct super_block *, int, void *, int); extern bool trylock_super(struct super_block *sb); -extern struct dentry *mount_fs(struct file_system_type *, - int, const char *, void *); extern struct super_block *user_get_super(dev_t); /* diff --git a/fs/namespace.c b/fs/namespace.c index f0b8a8ca08df..3f2fd7a34733 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "pnode.h" #include "internal.h" @@ -940,36 +941,53 @@ static struct mount *skip_mnt_tree(struct mount *p) return p; } -struct vfsmount * -vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) +struct vfsmount *vfs_kern_mount(struct file_system_type *type, + int flags, const char *name, + void *data) { + struct fs_context *fc; struct mount *mnt; - struct dentry *root; + int ret = 0; if (!type) return ERR_PTR(-ENODEV); + fc = fs_context_for_mount(type, flags); + if (IS_ERR(fc)) + return ERR_CAST(fc); + + if (name) { + fc->source = kstrdup(name, GFP_KERNEL); + if (!fc->source) + ret = -ENOMEM; + } + if (!ret) + ret = parse_monolithic_mount_data(fc, data); + if (!ret) + ret = vfs_get_tree(fc); + if (ret) { + put_fs_context(fc); + return ERR_PTR(ret); + } + up_write(&fc->root->d_sb->s_umount); mnt = alloc_vfsmnt(name); - if (!mnt) + if (!mnt) { + put_fs_context(fc); return ERR_PTR(-ENOMEM); + } if (flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; - root = mount_fs(type, flags, name, data); - if (IS_ERR(root)) { - mnt_free_id(mnt); - free_vfsmnt(mnt); - return ERR_CAST(root); - } - - mnt->mnt.mnt_root = root; - mnt->mnt.mnt_sb = root->d_sb; + atomic_inc(&fc->root->d_sb->s_active); + mnt->mnt.mnt_root = dget(fc->root); + mnt->mnt.mnt_sb = fc->root->d_sb; mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); - list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts); + list_add_tail(&mnt->mnt_instance, &fc->root->d_sb->s_mounts); unlock_mount_hash(); + put_fs_context(fc); return &mnt->mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); diff --git a/fs/super.c b/fs/super.c index 48e25eba8465..fc3887277ad1 100644 --- a/fs/super.c +++ b/fs/super.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include "internal.h" @@ -1241,27 +1242,24 @@ struct dentry *mount_single(struct file_system_type *fs_type, } EXPORT_SYMBOL(mount_single); -struct dentry * -mount_fs(struct file_system_type *type, int flags, const char *name, void *data) +/** + * vfs_get_tree - Get the mountable root + * @fc: The superblock configuration context. + * + * The filesystem is invoked to get or create a superblock which can then later + * be used for mounting. The filesystem places a pointer to the root to be + * used for mounting in @fc->root. + */ +int vfs_get_tree(struct fs_context *fc) { - struct dentry *root; struct super_block *sb; - int error = -ENOMEM; - void *sec_opts = NULL; + int error; - if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) { - error = security_sb_eat_lsm_opts(data, &sec_opts); - if (error) - return ERR_PTR(error); - } + error = legacy_get_tree(fc); + if (error < 0) + return error; - root = type->mount(type, flags, name, data); - if (IS_ERR(root)) { - error = PTR_ERR(root); - goto out_free_secdata; - } - sb = root->d_sb; - BUG_ON(!sb); + sb = fc->root->d_sb; WARN_ON(!sb->s_bdi); /* @@ -1273,11 +1271,11 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) smp_wmb(); sb->s_flags |= SB_BORN; - error = security_sb_set_mnt_opts(sb, sec_opts, 0, NULL); + error = security_sb_set_mnt_opts(sb, fc->security, 0, NULL); if (error) goto out_sb; - if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT))) { + if (!(fc->sb_flags & (MS_KERNMOUNT|MS_SUBMOUNT))) { error = security_sb_kern_mount(sb); if (error) goto out_sb; @@ -1290,18 +1288,16 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) * violate this rule. */ WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to " - "negative value (%lld)\n", type->name, sb->s_maxbytes); + "negative value (%lld)\n", fc->fs_type->name, sb->s_maxbytes); - up_write(&sb->s_umount); - security_free_mnt_opts(&sec_opts); - return root; + return 0; out_sb: - dput(root); + dput(fc->root); + fc->root = NULL; deactivate_locked_super(sb); -out_free_secdata: - security_free_mnt_opts(&sec_opts); - return ERR_PTR(error); + return error; } +EXPORT_SYMBOL(vfs_get_tree); /* * Setup private BDI for given superblock. It gets automatically cleaned up diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h new file mode 100644 index 000000000000..9805514444c9 --- /dev/null +++ b/include/linux/fs_context.h @@ -0,0 +1,64 @@ +/* Filesystem superblock creation and reconfiguration context. + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _LINUX_FS_CONTEXT_H +#define _LINUX_FS_CONTEXT_H + +#include +#include +#include + +struct cred; +struct dentry; +struct file_operations; +struct file_system_type; +struct net; +struct user_namespace; + +enum fs_context_purpose { + FS_CONTEXT_FOR_MOUNT, /* New superblock for explicit mount */ +}; + +/* + * Filesystem context for holding the parameters used in the creation or + * reconfiguration of a superblock. + * + * Superblock creation fills in ->root whereas reconfiguration begins with this + * already set. + * + * See Documentation/filesystems/mounting.txt + */ +struct fs_context { + struct file_system_type *fs_type; + void *fs_private; /* The filesystem's context */ + struct dentry *root; /* The root and superblock */ + struct user_namespace *user_ns; /* The user namespace for this mount */ + struct net *net_ns; /* The network namespace for this mount */ + const struct cred *cred; /* The mounter's credentials */ + const char *source; /* The source name (eg. dev path) */ + const char *subtype; /* The subtype to set on the superblock */ + void *security; /* Linux S&M options */ + unsigned int sb_flags; /* Proposed superblock flags (SB_*) */ + unsigned int sb_flags_mask; /* Superblock flags that were changed */ + enum fs_context_purpose purpose:8; + bool need_free:1; /* Need to call ops->free() */ +}; + +/* + * fs_context manipulation functions. + */ +extern struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, + unsigned int sb_flags); + +extern int vfs_get_tree(struct fs_context *fc); +extern void put_fs_context(struct fs_context *fc); + +#endif /* _LINUX_FS_CONTEXT_H */ -- cgit v1.2.3 From 8f2918898eb5fe25845dde7f4a77bda0e2966e05 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 4 Nov 2018 06:48:34 -0500 Subject: new helpers: vfs_create_mount(), fc_mount() Create a new helper, vfs_create_mount(), that creates a detached vfsmount object from an fs_context that has a superblock attached to it. Almost all uses will be paired with immediately preceding vfs_get_tree(); add a helper for such combination. Switch vfs_kern_mount() to use this. NOTE: mild behaviour change; passing NULL as 'device name' to something like procfs will change /proc/*/mountstats - "device none" instead on "no device". That is consistent with /proc/mounts et.al. [do'h - EXPORT_SYMBOL_GPL slipped in by mistake; removed] [AV -- remove confused comment from vfs_create_mount()] [AV -- removed the second argument] Reviewed-by: David Howells Signed-off-by: Al Viro --- fs/namespace.c | 76 +++++++++++++++++++++++++++++++++++---------------- include/linux/mount.h | 3 ++ 2 files changed, 55 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/fs/namespace.c b/fs/namespace.c index 3f2fd7a34733..156771f5745a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -941,12 +941,59 @@ static struct mount *skip_mnt_tree(struct mount *p) return p; } +/** + * vfs_create_mount - Create a mount for a configured superblock + * @fc: The configuration context with the superblock attached + * + * Create a mount to an already configured superblock. If necessary, the + * caller should invoke vfs_get_tree() before calling this. + * + * Note that this does not attach the mount to anything. + */ +struct vfsmount *vfs_create_mount(struct fs_context *fc) +{ + struct mount *mnt; + + if (!fc->root) + return ERR_PTR(-EINVAL); + + mnt = alloc_vfsmnt(fc->source ?: "none"); + if (!mnt) + return ERR_PTR(-ENOMEM); + + if (fc->sb_flags & SB_KERNMOUNT) + mnt->mnt.mnt_flags = MNT_INTERNAL; + + atomic_inc(&fc->root->d_sb->s_active); + mnt->mnt.mnt_sb = fc->root->d_sb; + mnt->mnt.mnt_root = dget(fc->root); + mnt->mnt_mountpoint = mnt->mnt.mnt_root; + mnt->mnt_parent = mnt; + + lock_mount_hash(); + list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); + unlock_mount_hash(); + return &mnt->mnt; +} +EXPORT_SYMBOL(vfs_create_mount); + +struct vfsmount *fc_mount(struct fs_context *fc) +{ + int err = vfs_get_tree(fc); + if (!err) { + up_write(&fc->root->d_sb->s_umount); + return vfs_create_mount(fc); + } + return ERR_PTR(err); +} +EXPORT_SYMBOL(fc_mount); + struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; - struct mount *mnt; + struct vfsmount *mnt; int ret = 0; if (!type) @@ -964,31 +1011,12 @@ struct vfsmount *vfs_kern_mount(struct file_system_type *type, if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) - ret = vfs_get_tree(fc); - if (ret) { - put_fs_context(fc); - return ERR_PTR(ret); - } - up_write(&fc->root->d_sb->s_umount); - mnt = alloc_vfsmnt(name); - if (!mnt) { - put_fs_context(fc); - return ERR_PTR(-ENOMEM); - } - - if (flags & SB_KERNMOUNT) - mnt->mnt.mnt_flags = MNT_INTERNAL; + mnt = fc_mount(fc); + else + mnt = ERR_PTR(ret); - atomic_inc(&fc->root->d_sb->s_active); - mnt->mnt.mnt_root = dget(fc->root); - mnt->mnt.mnt_sb = fc->root->d_sb; - mnt->mnt_mountpoint = mnt->mnt.mnt_root; - mnt->mnt_parent = mnt; - lock_mount_hash(); - list_add_tail(&mnt->mnt_instance, &fc->root->d_sb->s_mounts); - unlock_mount_hash(); put_fs_context(fc); - return &mnt->mnt; + return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); diff --git a/include/linux/mount.h b/include/linux/mount.h index 037eed52164b..9197ddbf35fb 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -21,6 +21,7 @@ struct super_block; struct vfsmount; struct dentry; struct mnt_namespace; +struct fs_context; #define MNT_NOSUID 0x01 #define MNT_NODEV 0x02 @@ -88,6 +89,8 @@ struct path; extern struct vfsmount *clone_private_mount(const struct path *path); struct file_system_type; +extern struct vfsmount *fc_mount(struct fs_context *fc); +extern struct vfsmount *vfs_create_mount(struct fs_context *fc); extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data); -- cgit v1.2.3 From a0c9a8b8fd9fd572b0d60276beb2142c8f59f9b8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 4 Nov 2018 07:18:51 -0500 Subject: teach vfs_get_tree() to handle subtype, switch do_new_mount() to it Roll the handling of subtypes into do_new_mount() and vfs_get_tree(). The former determines any subtype string and hangs it off the fs_context; the latter applies it. Make do_new_mount() create, parameterise and commit an fs_context and create a mount for itself rather than calling vfs_kern_mount(). [AV -- missing kstrdup()] [AV -- ... and no kstrdup() if we get to setting ->s_submount - we simply transfer it from fc, leaving NULL behind] [AV -- constify ->s_submount, while we are at it] Reviewed-by: David Howells Signed-off-by: Al Viro --- fs/namespace.c | 77 ++++++++++++++++++++++++++++++++---------------------- fs/super.c | 5 ++++ include/linux/fs.h | 2 +- 3 files changed, 52 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/fs/namespace.c b/fs/namespace.c index 156771f5745a..0354cb6ac2d3 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2479,29 +2479,6 @@ out: return err; } -static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype) -{ - int err; - const char *subtype = strchr(fstype, '.'); - if (subtype) { - subtype++; - err = -EINVAL; - if (!subtype[0]) - goto err; - } else - subtype = ""; - - mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL); - err = -ENOMEM; - if (!mnt->mnt_sb->s_subtype) - goto err; - return mnt; - - err: - mntput(mnt); - return ERR_PTR(err); -} - /* * add a mount into a namespace's mount tree */ @@ -2557,7 +2534,9 @@ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, { struct file_system_type *type; struct vfsmount *mnt; - int err; + struct fs_context *fc; + const char *subtype = NULL; + int err = 0; if (!fstype) return -EINVAL; @@ -2566,23 +2545,59 @@ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, if (!type) return -ENODEV; - mnt = vfs_kern_mount(type, sb_flags, name, data); - if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) && - !mnt->mnt_sb->s_subtype) - mnt = fs_set_subtype(mnt, fstype); + if (type->fs_flags & FS_HAS_SUBTYPE) { + subtype = strchr(fstype, '.'); + if (subtype) { + subtype++; + if (!*subtype) { + put_filesystem(type); + return -EINVAL; + } + } else { + subtype = ""; + } + } + fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); - if (IS_ERR(mnt)) - return PTR_ERR(mnt); + if (IS_ERR(fc)) + return PTR_ERR(fc); + + if (subtype) { + fc->subtype = kstrdup(subtype, GFP_KERNEL); + if (!fc->subtype) + err = -ENOMEM; + } + if (!err && name) { + fc->source = kstrdup(name, GFP_KERNEL); + if (!fc->source) + err = -ENOMEM; + } + if (!err) + err = parse_monolithic_mount_data(fc, data); + if (!err) + err = vfs_get_tree(fc); + if (err) + goto out; + + up_write(&fc->root->d_sb->s_umount); + mnt = vfs_create_mount(fc); + if (IS_ERR(mnt)) { + err = PTR_ERR(mnt); + goto out; + } if (mount_too_revealing(mnt, &mnt_flags)) { mntput(mnt); - return -EPERM; + err = -EPERM; + goto out; } err = do_add_mount(real_mount(mnt), path, mnt_flags); if (err) mntput(mnt); +out: + put_fs_context(fc); return err; } diff --git a/fs/super.c b/fs/super.c index fc3887277ad1..b91b6df05b67 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1262,6 +1262,11 @@ int vfs_get_tree(struct fs_context *fc) sb = fc->root->d_sb; WARN_ON(!sb->s_bdi); + if (fc->subtype && !sb->s_subtype) { + sb->s_subtype = fc->subtype; + fc->subtype = NULL; + } + /* * Write barrier is for super_cache_count(). We place it before setting * SB_BORN as the data dependency between the two functions is the diff --git a/include/linux/fs.h b/include/linux/fs.h index 811c77743dad..36fff12ab890 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1447,7 +1447,7 @@ struct super_block { * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ - char *s_subtype; + const char *s_subtype; const struct dentry_operations *s_d_op; /* default d_op for dentries */ -- cgit v1.2.3 From 8d0347f6c3a9d4953ddd636a31c6584da082e084 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sun, 4 Nov 2018 09:28:36 -0500 Subject: convert do_remount_sb() to fs_context Replace do_remount_sb() with a function, reconfigure_super(), that's fs_context aware. The fs_context is expected to be parameterised already and have ->root pointing to the superblock to be reconfigured. A legacy wrapper is provided that is intended to be called from the fs_context ops when those appear, but for now is called directly from reconfigure_super(). This wrapper invokes the ->remount_fs() superblock op for the moment. It is intended that the remount_fs() op will be phased out. The fs_context->purpose is set to FS_CONTEXT_FOR_RECONFIGURE to indicate that the context is being used for reconfiguration. do_umount_root() is provided to consolidate remount-to-R/O for umount and emergency remount by creating a context and invoking reconfiguration. do_remount(), do_umount() and do_emergency_remount_callback() are switched to use the new process. [AV -- fold UMOUNT and EMERGENCY_REMOUNT in; fixes the umount / bug, gets rid of pointless complexity] [AV -- set ->net_ns in all cases; nfs remount will need that] [AV -- shift security_sb_remount() call into reconfigure_super(); the callers that didn't do security_sb_remount() have NULL fc->security anyway, so it's a no-op for them] Signed-off-by: David Howells Co-developed-by: Al Viro Signed-off-by: Al Viro --- fs/fs_context.c | 35 ++++++++++++++- fs/internal.h | 3 +- fs/namespace.c | 61 ++++++++++++++++---------- fs/super.c | 107 +++++++++++++++++++++++++++++++-------------- include/linux/fs.h | 1 + include/linux/fs_context.h | 4 ++ 6 files changed, 152 insertions(+), 59 deletions(-) (limited to 'include') diff --git a/fs/fs_context.c b/fs/fs_context.c index 857cd46a687b..5e2c3aba1dd8 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -69,6 +69,13 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, case FS_CONTEXT_FOR_MOUNT: fc->user_ns = get_user_ns(fc->cred->user_ns); break; + case FS_CONTEXT_FOR_RECONFIGURE: + /* We don't pin any namespaces as the superblock's + * subscriptions cannot be changed at this point. + */ + atomic_inc(&reference->d_sb->s_active); + fc->root = dget(reference); + break; } ret = legacy_init_fs_context(fc); @@ -90,6 +97,15 @@ struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, } EXPORT_SYMBOL(fs_context_for_mount); +struct fs_context *fs_context_for_reconfigure(struct dentry *dentry, + unsigned int sb_flags, + unsigned int sb_flags_mask) +{ + return alloc_fs_context(dentry->d_sb->s_type, dentry, sb_flags, + sb_flags_mask, FS_CONTEXT_FOR_RECONFIGURE); +} +EXPORT_SYMBOL(fs_context_for_reconfigure); + void fc_drop_locked(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; @@ -99,6 +115,7 @@ void fc_drop_locked(struct fs_context *fc) } static void legacy_fs_context_free(struct fs_context *fc); + /** * put_fs_context - Dispose of a superblock configuration context. * @fc: The context to dispose of. @@ -118,8 +135,7 @@ void put_fs_context(struct fs_context *fc) legacy_fs_context_free(fc); security_free_mnt_opts(&fc->security); - if (fc->net_ns) - put_net(fc->net_ns); + put_net(fc->net_ns); put_user_ns(fc->user_ns); put_cred(fc->cred); kfree(fc->subtype); @@ -172,6 +188,21 @@ int legacy_get_tree(struct fs_context *fc) return 0; } +/* + * Handle remount. + */ +int legacy_reconfigure(struct fs_context *fc) +{ + struct legacy_fs_context *ctx = fc->fs_private; + struct super_block *sb = fc->root->d_sb; + + if (!sb->s_op->remount_fs) + return 0; + + return sb->s_op->remount_fs(sb, &fc->sb_flags, + ctx ? ctx->legacy_data : NULL); +} + /* * Initialise a legacy context for a filesystem that doesn't support * fs_context. diff --git a/fs/internal.h b/fs/internal.h index 6af26d897034..016a5b8dd305 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -56,6 +56,7 @@ extern void __init chrdev_init(void); * fs_context.c */ extern int legacy_get_tree(struct fs_context *fc); +extern int legacy_reconfigure(struct fs_context *fc); extern int parse_monolithic_mount_data(struct fs_context *, void *); extern void fc_drop_locked(struct fs_context *); @@ -107,7 +108,7 @@ extern struct file *alloc_empty_file_noaccount(int, const struct cred *); /* * super.c */ -extern int do_remount_sb(struct super_block *, int, void *, int); +extern int reconfigure_super(struct fs_context *); extern bool trylock_super(struct super_block *sb); extern struct super_block *user_get_super(dev_t); diff --git a/fs/namespace.c b/fs/namespace.c index 750500c6c33d..931228d8518a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1489,6 +1489,29 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) static void shrink_submounts(struct mount *mnt); +static int do_umount_root(struct super_block *sb) +{ + int ret = 0; + + down_write(&sb->s_umount); + if (!sb_rdonly(sb)) { + struct fs_context *fc; + + fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, + SB_RDONLY); + if (IS_ERR(fc)) { + ret = PTR_ERR(fc); + } else { + ret = parse_monolithic_mount_data(fc, NULL); + if (!ret) + ret = reconfigure_super(fc); + put_fs_context(fc); + } + } + up_write(&sb->s_umount); + return ret; +} + static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; @@ -1554,11 +1577,7 @@ static int do_umount(struct mount *mnt, int flags) */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; - down_write(&sb->s_umount); - if (!sb_rdonly(sb)) - retval = do_remount_sb(sb, SB_RDONLY, NULL, 0); - up_write(&sb->s_umount); - return retval; + return do_umount_root(sb); } namespace_lock(); @@ -2367,7 +2386,7 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags, int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); - void *sec_opts = NULL; + struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; @@ -2378,24 +2397,22 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags, if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; - if (data && !(sb->s_type->fs_flags & FS_BINARY_MOUNTDATA)) { - err = security_sb_eat_lsm_opts(data, &sec_opts); - if (err) - return err; - } - err = security_sb_remount(sb, sec_opts); - security_free_mnt_opts(&sec_opts); - if (err) - return err; + fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); + if (IS_ERR(fc)) + return PTR_ERR(fc); - down_write(&sb->s_umount); - err = -EPERM; - if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { - err = do_remount_sb(sb, sb_flags, data, 0); - if (!err) - set_mount_attributes(mnt, mnt_flags); + err = parse_monolithic_mount_data(fc, data); + if (!err) { + down_write(&sb->s_umount); + err = -EPERM; + if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { + err = reconfigure_super(fc); + if (!err) + set_mount_attributes(mnt, mnt_flags); + } + up_write(&sb->s_umount); } - up_write(&sb->s_umount); + put_fs_context(fc); return err; } diff --git a/fs/super.c b/fs/super.c index 11e2a6cb3baf..50553233dd15 100644 --- a/fs/super.c +++ b/fs/super.c @@ -836,28 +836,35 @@ rescan: } /** - * do_remount_sb - asks filesystem to change mount options. - * @sb: superblock in question - * @sb_flags: revised superblock flags - * @data: the rest of options - * @force: whether or not to force the change + * reconfigure_super - asks filesystem to change superblock parameters + * @fc: The superblock and configuration * - * Alters the mount options of a mounted file system. + * Alters the configuration parameters of a live superblock. */ -int do_remount_sb(struct super_block *sb, int sb_flags, void *data, int force) +int reconfigure_super(struct fs_context *fc) { + struct super_block *sb = fc->root->d_sb; int retval; - int remount_ro; + bool remount_ro = false; + bool force = fc->sb_flags & SB_FORCE; + if (fc->sb_flags_mask & ~MS_RMT_MASK) + return -EINVAL; if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; + retval = security_sb_remount(sb, fc->security); + if (retval) + return retval; + + if (fc->sb_flags_mask & SB_RDONLY) { #ifdef CONFIG_BLOCK - if (!(sb_flags & SB_RDONLY) && bdev_read_only(sb->s_bdev)) - return -EACCES; + if (!(fc->sb_flags & SB_RDONLY) && bdev_read_only(sb->s_bdev)) + return -EACCES; #endif - remount_ro = (sb_flags & SB_RDONLY) && !sb_rdonly(sb); + remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb); + } if (remount_ro) { if (!hlist_empty(&sb->s_pins)) { @@ -868,13 +875,14 @@ int do_remount_sb(struct super_block *sb, int sb_flags, void *data, int force) return 0; if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; - remount_ro = (sb_flags & SB_RDONLY) && !sb_rdonly(sb); + remount_ro = !sb_rdonly(sb); } } shrink_dcache_sb(sb); - /* If we are remounting RDONLY and current sb is read/write, - make sure there are no rw files opened */ + /* If we are reconfiguring to RDONLY and current sb is read/write, + * make sure there are no files open for writing. + */ if (remount_ro) { if (force) { sb->s_readonly_remount = 1; @@ -886,17 +894,17 @@ int do_remount_sb(struct super_block *sb, int sb_flags, void *data, int force) } } - if (sb->s_op->remount_fs) { - retval = sb->s_op->remount_fs(sb, &sb_flags, data); - if (retval) { - if (!force) - goto cancel_readonly; - /* If forced remount, go ahead despite any errors */ - WARN(1, "forced remount of a %s fs returned %i\n", - sb->s_type->name, retval); - } + retval = legacy_reconfigure(fc); + if (retval) { + if (!force) + goto cancel_readonly; + /* If forced remount, go ahead despite any errors */ + WARN(1, "forced remount of a %s fs returned %i\n", + sb->s_type->name, retval); } - sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (sb_flags & MS_RMT_MASK); + + WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) | + (fc->sb_flags & fc->sb_flags_mask))); /* Needs to be ordered wrt mnt_is_readonly() */ smp_wmb(); sb->s_readonly_remount = 0; @@ -923,10 +931,15 @@ static void do_emergency_remount_callback(struct super_block *sb) down_write(&sb->s_umount); if (sb->s_root && sb->s_bdev && (sb->s_flags & SB_BORN) && !sb_rdonly(sb)) { - /* - * What lock protects sb->s_flags?? - */ - do_remount_sb(sb, SB_RDONLY, NULL, 1); + struct fs_context *fc; + + fc = fs_context_for_reconfigure(sb->s_root, + SB_RDONLY | SB_FORCE, SB_RDONLY); + if (!IS_ERR(fc)) { + if (parse_monolithic_mount_data(fc, NULL) == 0) + (void)reconfigure_super(fc); + put_fs_context(fc); + } } up_write(&sb->s_umount); } @@ -1213,6 +1226,31 @@ struct dentry *mount_nodev(struct file_system_type *fs_type, } EXPORT_SYMBOL(mount_nodev); +static int reconfigure_single(struct super_block *s, + int flags, void *data) +{ + struct fs_context *fc; + int ret; + + /* The caller really need to be passing fc down into mount_single(), + * then a chunk of this can be removed. [Bollocks -- AV] + * Better yet, reconfiguration shouldn't happen, but rather the second + * mount should be rejected if the parameters are not compatible. + */ + fc = fs_context_for_reconfigure(s->s_root, flags, MS_RMT_MASK); + if (IS_ERR(fc)) + return PTR_ERR(fc); + + ret = parse_monolithic_mount_data(fc, data); + if (ret < 0) + goto out; + + ret = reconfigure_super(fc); +out: + put_fs_context(fc); + return ret; +} + static int compare_single(struct super_block *s, void *p) { return 1; @@ -1230,13 +1268,14 @@ struct dentry *mount_single(struct file_system_type *fs_type, return ERR_CAST(s); if (!s->s_root) { error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); - if (error) { - deactivate_locked_super(s); - return ERR_PTR(error); - } - s->s_flags |= SB_ACTIVE; + if (!error) + s->s_flags |= SB_ACTIVE; } else { - do_remount_sb(s, flags, data, 0); + error = reconfigure_single(s, flags, data); + } + if (unlikely(error)) { + deactivate_locked_super(s); + return ERR_PTR(error); } return dget(s->s_root); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 36fff12ab890..c65d02c5c512 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1337,6 +1337,7 @@ extern int send_sigurg(struct fown_struct *fown); /* These sb flags are internal to the kernel */ #define SB_SUBMOUNT (1<<26) +#define SB_FORCE (1<<27) #define SB_NOSEC (1<<28) #define SB_BORN (1<<29) #define SB_ACTIVE (1<<30) diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 9805514444c9..98772f882a3e 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -25,6 +25,7 @@ struct user_namespace; enum fs_context_purpose { FS_CONTEXT_FOR_MOUNT, /* New superblock for explicit mount */ + FS_CONTEXT_FOR_RECONFIGURE, /* Superblock reconfiguration (remount) */ }; /* @@ -57,6 +58,9 @@ struct fs_context { */ extern struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, unsigned int sb_flags); +extern struct fs_context *fs_context_for_reconfigure(struct dentry *dentry, + unsigned int sb_flags, + unsigned int sb_flags_mask); extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); -- cgit v1.2.3 From e1a91586d5da6f879b6dd385a2e7227bf1653570 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 23 Dec 2018 16:25:31 -0500 Subject: fs_context flavour for submounts This is an eventual replacement for vfs_submount() uses. Unlike the "mount" and "remount" cases, the users of that thing are not in VFS - they are buried in various ->d_automount() instances and rather than converting them all at once we introduce the (thankfully small and simple) infrastructure here and deal with the prospective users in afs, nfs, etc. parts of the series. Here we just introduce a new constructor (fs_context_for_submount()) along with the corresponding enum constant to be put into fc->purpose for those. Signed-off-by: Al Viro --- fs/fs_context.c | 10 ++++++++++ include/linux/fs_context.h | 3 +++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/fs/fs_context.c b/fs/fs_context.c index 5e2c3aba1dd8..2bd652b6e848 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -69,6 +69,9 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, case FS_CONTEXT_FOR_MOUNT: fc->user_ns = get_user_ns(fc->cred->user_ns); break; + case FS_CONTEXT_FOR_SUBMOUNT: + fc->user_ns = get_user_ns(reference->d_sb->s_user_ns); + break; case FS_CONTEXT_FOR_RECONFIGURE: /* We don't pin any namespaces as the superblock's * subscriptions cannot be changed at this point. @@ -106,6 +109,13 @@ struct fs_context *fs_context_for_reconfigure(struct dentry *dentry, } EXPORT_SYMBOL(fs_context_for_reconfigure); +struct fs_context *fs_context_for_submount(struct file_system_type *type, + struct dentry *reference) +{ + return alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT); +} +EXPORT_SYMBOL(fs_context_for_submount); + void fc_drop_locked(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 98772f882a3e..7feb018c7a9e 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -25,6 +25,7 @@ struct user_namespace; enum fs_context_purpose { FS_CONTEXT_FOR_MOUNT, /* New superblock for explicit mount */ + FS_CONTEXT_FOR_SUBMOUNT, /* New superblock for automatic submount */ FS_CONTEXT_FOR_RECONFIGURE, /* Superblock reconfiguration (remount) */ }; @@ -61,6 +62,8 @@ extern struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, extern struct fs_context *fs_context_for_reconfigure(struct dentry *dentry, unsigned int sb_flags, unsigned int sb_flags_mask); +extern struct fs_context *fs_context_for_submount(struct file_system_type *fs_type, + struct dentry *reference); extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); -- cgit v1.2.3 From f3a09c92018a91ad0981146a4ac59414f814d801 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 23 Dec 2018 18:55:56 -0500 Subject: introduce fs_context methods Signed-off-by: Al Viro --- fs/fs_context.c | 28 ++++++++++++++++++++++------ fs/internal.h | 2 -- fs/super.c | 36 ++++++++++++++++++++++++++++-------- include/linux/fs.h | 2 ++ include/linux/fs_context.h | 13 +++++++++++++ 5 files changed, 65 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/fs/fs_context.c b/fs/fs_context.c index 2bd652b6e848..825d1b2c8807 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -51,6 +51,7 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, unsigned int sb_flags_mask, enum fs_context_purpose purpose) { + int (*init_fs_context)(struct fs_context *); struct fs_context *fc; int ret = -ENOMEM; @@ -81,7 +82,12 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, break; } - ret = legacy_init_fs_context(fc); + /* TODO: Make all filesystems support this unconditionally */ + init_fs_context = fc->fs_type->init_fs_context; + if (!init_fs_context) + init_fs_context = legacy_init_fs_context; + + ret = init_fs_context(fc); if (ret < 0) goto err_fc; fc->need_free = true; @@ -141,8 +147,8 @@ void put_fs_context(struct fs_context *fc) deactivate_super(sb); } - if (fc->need_free) - legacy_fs_context_free(fc); + if (fc->need_free && fc->ops && fc->ops->free) + fc->ops->free(fc); security_free_mnt_opts(&fc->security); put_net(fc->net_ns); @@ -180,7 +186,7 @@ static int legacy_parse_monolithic(struct fs_context *fc, void *data) /* * Get a mountable root with the legacy mount command. */ -int legacy_get_tree(struct fs_context *fc) +static int legacy_get_tree(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; struct super_block *sb; @@ -201,7 +207,7 @@ int legacy_get_tree(struct fs_context *fc) /* * Handle remount. */ -int legacy_reconfigure(struct fs_context *fc) +static int legacy_reconfigure(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; struct super_block *sb = fc->root->d_sb; @@ -213,6 +219,13 @@ int legacy_reconfigure(struct fs_context *fc) ctx ? ctx->legacy_data : NULL); } +const struct fs_context_operations legacy_fs_context_ops = { + .free = legacy_fs_context_free, + .parse_monolithic = legacy_parse_monolithic, + .get_tree = legacy_get_tree, + .reconfigure = legacy_reconfigure, +}; + /* * Initialise a legacy context for a filesystem that doesn't support * fs_context. @@ -222,10 +235,13 @@ static int legacy_init_fs_context(struct fs_context *fc) fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL); if (!fc->fs_private) return -ENOMEM; + fc->ops = &legacy_fs_context_ops; return 0; } int parse_monolithic_mount_data(struct fs_context *fc, void *data) { - return legacy_parse_monolithic(fc, data); + int (*monolithic_mount_data)(struct fs_context *, void *); + monolithic_mount_data = fc->ops->parse_monolithic; + return monolithic_mount_data(fc, data); } diff --git a/fs/internal.h b/fs/internal.h index 016a5b8dd305..8f8d07cc433f 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -55,8 +55,6 @@ extern void __init chrdev_init(void); /* * fs_context.c */ -extern int legacy_get_tree(struct fs_context *fc); -extern int legacy_reconfigure(struct fs_context *fc); extern int parse_monolithic_mount_data(struct fs_context *, void *); extern void fc_drop_locked(struct fs_context *); diff --git a/fs/super.c b/fs/super.c index 50553233dd15..76b3181c782d 100644 --- a/fs/super.c +++ b/fs/super.c @@ -894,13 +894,15 @@ int reconfigure_super(struct fs_context *fc) } } - retval = legacy_reconfigure(fc); - if (retval) { - if (!force) - goto cancel_readonly; - /* If forced remount, go ahead despite any errors */ - WARN(1, "forced remount of a %s fs returned %i\n", - sb->s_type->name, retval); + if (fc->ops->reconfigure) { + retval = fc->ops->reconfigure(fc); + if (retval) { + if (!force) + goto cancel_readonly; + /* If forced remount, go ahead despite any errors */ + WARN(1, "forced remount of a %s fs returned %i\n", + sb->s_type->name, retval); + } } WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) | @@ -1294,10 +1296,28 @@ int vfs_get_tree(struct fs_context *fc) struct super_block *sb; int error; - error = legacy_get_tree(fc); + if (fc->fs_type->fs_flags & FS_REQUIRES_DEV && !fc->source) + return -ENOENT; + + if (fc->root) + return -EBUSY; + + /* Get the mountable root in fc->root, with a ref on the root and a ref + * on the superblock. + */ + error = fc->ops->get_tree(fc); if (error < 0) return error; + if (!fc->root) { + pr_err("Filesystem %s get_tree() didn't set fc->root\n", + fc->fs_type->name); + /* We don't know what the locking state of the superblock is - + * if there is a superblock. + */ + BUG(); + } + sb = fc->root->d_sb; WARN_ON(!sb->s_bdi); diff --git a/include/linux/fs.h b/include/linux/fs.h index c65d02c5c512..8d578a9e1e8c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -61,6 +61,7 @@ struct workqueue_struct; struct iov_iter; struct fscrypt_info; struct fscrypt_operations; +struct fs_context; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -2173,6 +2174,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ + int (*init_fs_context)(struct fs_context *); struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 7feb018c7a9e..087c12954360 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -20,8 +20,13 @@ struct cred; struct dentry; struct file_operations; struct file_system_type; +struct mnt_namespace; struct net; +struct pid_namespace; +struct super_block; struct user_namespace; +struct vfsmount; +struct path; enum fs_context_purpose { FS_CONTEXT_FOR_MOUNT, /* New superblock for explicit mount */ @@ -39,6 +44,7 @@ enum fs_context_purpose { * See Documentation/filesystems/mounting.txt */ struct fs_context { + const struct fs_context_operations *ops; struct file_system_type *fs_type; void *fs_private; /* The filesystem's context */ struct dentry *root; /* The root and superblock */ @@ -54,6 +60,13 @@ struct fs_context { bool need_free:1; /* Need to call ops->free() */ }; +struct fs_context_operations { + void (*free)(struct fs_context *fc); + int (*parse_monolithic)(struct fs_context *fc, void *data); + int (*get_tree)(struct fs_context *fc); + int (*reconfigure)(struct fs_context *fc); +}; + /* * fs_context manipulation functions. */ -- cgit v1.2.3 From c6b82263f9c6e745eb4c5dfc2578d147c4cd7604 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 1 Nov 2018 23:07:23 +0000 Subject: vfs: Introduce logging functions Introduce a set of logging functions through which informational messages, warnings and error messages incurred by the mount procedure can be logged and, in a future patch, passed to userspace instead by way of the filesystem configuration context file descriptor. There are four functions: (1) infof(const char *fmt, ...); Logs an informational message. (2) warnf(const char *fmt, ...); Logs a warning message. (3) errorf(const char *fmt, ...); Logs an error message. (4) invalf(const char *fmt, ...); As errof(), but returns -EINVAL so can be used on a return statement. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/fs_context.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'include') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 087c12954360..d208cc40b868 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -81,4 +81,46 @@ extern struct fs_context *fs_context_for_submount(struct file_system_type *fs_ty extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); +#define logfc(FC, FMT, ...) pr_notice(FMT, ## __VA_ARGS__) + +/** + * infof - Store supplementary informational message + * @fc: The context in which to log the informational message + * @fmt: The format string + * + * Store the supplementary informational message for the process if the process + * has enabled the facility. + */ +#define infof(fc, fmt, ...) ({ logfc(fc, fmt, ## __VA_ARGS__); }) + +/** + * warnf - Store supplementary warning message + * @fc: The context in which to log the error message + * @fmt: The format string + * + * Store the supplementary warning message for the process if the process has + * enabled the facility. + */ +#define warnf(fc, fmt, ...) ({ logfc(fc, fmt, ## __VA_ARGS__); }) + +/** + * errorf - Store supplementary error message + * @fc: The context in which to log the error message + * @fmt: The format string + * + * Store the supplementary error message for the process if the process has + * enabled the facility. + */ +#define errorf(fc, fmt, ...) ({ logfc(fc, fmt, ## __VA_ARGS__); }) + +/** + * invalf - Store supplementary invalid argument error message + * @fc: The context in which to log the error message + * @fmt: The format string + * + * Store the supplementary error message for the process if the process has + * enabled the facility and return -EINVAL. + */ +#define invalf(fc, fmt, ...) ({ errorf(fc, fmt, ## __VA_ARGS__); -EINVAL; }) + #endif /* _LINUX_FS_CONTEXT_H */ -- cgit v1.2.3 From 459cc69fa4c17caf21de596693d8a07170820a58 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 30 Jan 2019 12:49:11 +0200 Subject: RDMA: Provide safe ib_alloc_device() function All callers to ib_alloc_device() provide a larger size than struct ib_device and rely on the fact that struct ib_device is embedded in their driver specific structure as the first member. Provide a safer variant of ib_alloc_device() that checks and enforces this approach to make sure the drivers are using it right. Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/device.c | 6 +++--- drivers/infiniband/hw/bnxt_re/main.c | 2 +- drivers/infiniband/hw/cxgb3/iwch.c | 2 +- drivers/infiniband/hw/cxgb4/device.c | 2 +- drivers/infiniband/hw/hns/hns_roce_hw_v1.c | 2 +- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 2 +- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 2 +- drivers/infiniband/hw/mlx4/main.c | 2 +- drivers/infiniband/hw/mlx5/ib_rep.c | 2 +- drivers/infiniband/hw/mlx5/main.c | 2 +- drivers/infiniband/hw/mthca/mthca_main.c | 2 +- drivers/infiniband/hw/nes/nes_verbs.c | 2 +- drivers/infiniband/hw/ocrdma/ocrdma_main.c | 2 +- drivers/infiniband/hw/qedr/main.c | 2 +- drivers/infiniband/hw/usnic/usnic_ib_main.c | 2 +- drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c | 2 +- drivers/infiniband/sw/rdmavt/vt.c | 2 +- drivers/infiniband/sw/rxe/rxe_net.c | 2 +- include/rdma/ib_verbs.h | 8 +++++++- 19 files changed, 27 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 200431c540f2..b511cfa00bdb 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -268,7 +268,7 @@ static struct class ib_class = { }; /** - * ib_alloc_device - allocate an IB device struct + * _ib_alloc_device - allocate an IB device struct * @size:size of structure to allocate * * Low-level drivers should use ib_alloc_device() to allocate &struct @@ -277,7 +277,7 @@ static struct class ib_class = { * ib_dealloc_device() must be used to free structures allocated with * ib_alloc_device(). */ -struct ib_device *ib_alloc_device(size_t size) +struct ib_device *_ib_alloc_device(size_t size) { struct ib_device *device; @@ -303,7 +303,7 @@ struct ib_device *ib_alloc_device(size_t size) return device; } -EXPORT_SYMBOL(ib_alloc_device); +EXPORT_SYMBOL(_ib_alloc_device); /** * ib_dealloc_device - free an IB device struct diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 16eecfa5882c..08777506d0b1 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -688,7 +688,7 @@ static struct bnxt_re_dev *bnxt_re_dev_add(struct net_device *netdev, struct bnxt_re_dev *rdev; /* Allocate bnxt_re_dev instance here */ - rdev = (struct bnxt_re_dev *)ib_alloc_device(sizeof(*rdev)); + rdev = ib_alloc_device(bnxt_re_dev, ibdev); if (!rdev) { dev_err(NULL, "%s: bnxt_re_dev allocation failure!", ROCE_DRV_MODULE_NAME); diff --git a/drivers/infiniband/hw/cxgb3/iwch.c b/drivers/infiniband/hw/cxgb3/iwch.c index 591de319c178..fb03bc492ef7 100644 --- a/drivers/infiniband/hw/cxgb3/iwch.c +++ b/drivers/infiniband/hw/cxgb3/iwch.c @@ -146,7 +146,7 @@ static void open_rnic_dev(struct t3cdev *tdev) pr_debug("%s t3cdev %p\n", __func__, tdev); pr_info_once("Chelsio T3 RDMA Driver - version %s\n", DRV_VERSION); - rnicp = (struct iwch_dev *)ib_alloc_device(sizeof(*rnicp)); + rnicp = ib_alloc_device(iwch_dev, ibdev); if (!rnicp) { pr_err("Cannot allocate ib device\n"); return; diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index 9c10fff6dcfb..4b4e2464b705 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -966,7 +966,7 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop) pr_info("%s: On-Chip Queues not supported on this device\n", pci_name(infop->pdev)); - devp = (struct c4iw_dev *)ib_alloc_device(sizeof(*devp)); + devp = ib_alloc_device(c4iw_dev, ibdev); if (!devp) { pr_err("Cannot allocate ib device\n"); return ERR_PTR(-ENOMEM); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index b74c742b000c..fa08c22aad66 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -5002,7 +5002,7 @@ static int hns_roce_probe(struct platform_device *pdev) struct hns_roce_dev *hr_dev; struct device *dev = &pdev->dev; - hr_dev = (struct hns_roce_dev *)ib_alloc_device(sizeof(*hr_dev)); + hr_dev = ib_alloc_device(hns_roce_dev, ib_dev); if (!hr_dev) return -ENOMEM; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 5c483b437bdd..48a5d6548cd4 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -6059,7 +6059,7 @@ static int hns_roce_hw_v2_init_instance(struct hnae3_handle *handle) struct hns_roce_dev *hr_dev; int ret; - hr_dev = (struct hns_roce_dev *)ib_alloc_device(sizeof(*hr_dev)); + hr_dev = ib_alloc_device(hns_roce_dev, ib_dev); if (!hr_dev) return -ENOMEM; diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 12b31a8440be..d4ab46dd9e6c 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -2762,7 +2762,7 @@ static struct i40iw_ib_device *i40iw_init_rdma_device(struct i40iw_device *iwdev struct net_device *netdev = iwdev->netdev; struct pci_dev *pcidev = (struct pci_dev *)iwdev->hw.dev_context; - iwibdev = (struct i40iw_ib_device *)ib_alloc_device(sizeof(*iwibdev)); + iwibdev = ib_alloc_device(i40iw_ib_device, ibdev); if (!iwibdev) { i40iw_pr_err("iwdev == NULL\n"); return NULL; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index dc2ffd293a11..d66002a31000 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -2635,7 +2635,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) if (num_ports == 0) return NULL; - ibdev = (struct mlx4_ib_dev *) ib_alloc_device(sizeof *ibdev); + ibdev = ib_alloc_device(mlx4_ib_dev, ib_dev); if (!ibdev) { dev_err(&dev->persist->pdev->dev, "Device struct alloc failed\n"); diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index 46a9ddc8ca56..6d7b8bad4b61 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -70,7 +70,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { struct mlx5_ib_dev *ibdev; - ibdev = (struct mlx5_ib_dev *)ib_alloc_device(sizeof(*ibdev)); + ibdev = ib_alloc_device(mlx5_ib_dev, ib_dev); if (!ibdev) return -ENOMEM; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 96bf1b2f9dd7..8161acda64e6 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -6508,7 +6508,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) if (mlx5_core_is_mp_slave(mdev) && ll == IB_LINK_LAYER_ETHERNET) return mlx5_ib_add_slave_port(mdev); - dev = (struct mlx5_ib_dev *)ib_alloc_device(sizeof(*dev)); + dev = ib_alloc_device(mlx5_ib_dev, ib_dev); if (!dev) return NULL; diff --git a/drivers/infiniband/hw/mthca/mthca_main.c b/drivers/infiniband/hw/mthca/mthca_main.c index 92c49bff22bc..fe9654a7af71 100644 --- a/drivers/infiniband/hw/mthca/mthca_main.c +++ b/drivers/infiniband/hw/mthca/mthca_main.c @@ -961,7 +961,7 @@ static int __mthca_init_one(struct pci_dev *pdev, int hca_type) /* We can handle large RDMA requests, so allow larger segments. */ dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024); - mdev = (struct mthca_dev *) ib_alloc_device(sizeof *mdev); + mdev = ib_alloc_device(mthca_dev, ib_dev); if (!mdev) { dev_err(&pdev->dev, "Device struct alloc failed, " "aborting.\n"); diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index 034156f7e9ed..6eb991d40035 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -3669,7 +3669,7 @@ struct nes_ib_device *nes_init_ofa_device(struct net_device *netdev) struct nes_vnic *nesvnic = netdev_priv(netdev); struct nes_device *nesdev = nesvnic->nesdev; - nesibdev = (struct nes_ib_device *)ib_alloc_device(sizeof(struct nes_ib_device)); + nesibdev = ib_alloc_device(nes_ib_device, ibdev); if (nesibdev == NULL) { return NULL; } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index b0491b9ecfe4..88970a6bb555 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -297,7 +297,7 @@ static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info) u8 lstate = 0; struct ocrdma_dev *dev; - dev = (struct ocrdma_dev *)ib_alloc_device(sizeof(struct ocrdma_dev)); + dev = ib_alloc_device(ocrdma_dev, ibdev); if (!dev) { pr_err("Unable to allocate ib device\n"); return NULL; diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index f85e72b65a10..878e9e23652b 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -853,7 +853,7 @@ static struct qedr_dev *qedr_add(struct qed_dev *cdev, struct pci_dev *pdev, struct qedr_dev *dev; int rc = 0; - dev = (struct qedr_dev *)ib_alloc_device(sizeof(*dev)); + dev = ib_alloc_device(qedr_dev, ibdev); if (!dev) { pr_err("Unable to allocate ib device\n"); return NULL; diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index 3201dd1899c7..0c0a288cb585 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -372,7 +372,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev) usnic_dbg("\n"); netdev = pci_get_drvdata(dev); - us_ibdev = (struct usnic_ib_dev *)ib_alloc_device(sizeof(*us_ibdev)); + us_ibdev = ib_alloc_device(usnic_ib_dev, ib_dev); if (!us_ibdev) { usnic_err("Device %s context alloc failed\n", netdev_name(pci_get_drvdata(dev))); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index a5f02276d903..e582beaf9430 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -795,7 +795,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev, dev_dbg(&pdev->dev, "initializing driver %s\n", pci_name(pdev)); /* Allocate zero-out device */ - dev = (struct pvrdma_dev *)ib_alloc_device(sizeof(*dev)); + dev = ib_alloc_device(pvrdma_dev, ib_dev); if (!dev) { dev_err(&pdev->dev, "failed to allocate IB device\n"); return -ENOMEM; diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c index 7de7389d0235..b3f0c5578925 100644 --- a/drivers/infiniband/sw/rdmavt/vt.c +++ b/drivers/infiniband/sw/rdmavt/vt.c @@ -91,7 +91,7 @@ struct rvt_dev_info *rvt_alloc_device(size_t size, int nports) { struct rvt_dev_info *rdi; - rdi = (struct rvt_dev_info *)ib_alloc_device(size); + rdi = container_of(_ib_alloc_device(size), struct rvt_dev_info, ibdev); if (!rdi) return rdi; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 8fd03ae20efc..19f3c69916b1 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -555,7 +555,7 @@ struct rxe_dev *rxe_net_add(struct net_device *ndev) int err; struct rxe_dev *rxe = NULL; - rxe = (struct rxe_dev *)ib_alloc_device(sizeof(*rxe)); + rxe = ib_alloc_device(rxe_dev, ib_dev); if (!rxe) return NULL; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 71ea144ec823..a1a1e710642c 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2621,7 +2621,13 @@ struct ib_client { struct list_head list; }; -struct ib_device *ib_alloc_device(size_t size); +struct ib_device *_ib_alloc_device(size_t size); +#define ib_alloc_device(drv_struct, member) \ + container_of(_ib_alloc_device(sizeof(struct drv_struct) + \ + BUILD_BUG_ON_ZERO(offsetof( \ + struct drv_struct, member))), \ + struct drv_struct, member) + void ib_dealloc_device(struct ib_device *device); void ib_get_device_fw_str(struct ib_device *device, char *str); -- cgit v1.2.3 From b7bb367afa4bf9de60830683305c63030c3e581d Mon Sep 17 00:00:00 2001 From: Jonas Bonn Date: Wed, 30 Jan 2019 09:40:04 +0100 Subject: spi: support inter-word delay requirement for devices Some devices are slow and cannot keep up with the SPI bus and therefore require a short delay between words of the SPI transfer. The example of this that I'm looking at is a SAMA5D2 with a minimum SPI clock of 400kHz talking to an AVR-based SPI slave. The AVR cannot put bytes on the bus fast enough to keep up with the SoC's SPI controller even at the lowest bus speed. This patch introduces the ability to specify a required inter-word delay for SPI devices. It is up to the controller driver to configure itself accordingly in order to introduce the requested delay. Note that, for spi_transfer, there is already a field word_delay that provides similar functionality. This field, however, is specified in clock cycles (and worse, SPI controller cycles, not SCK cycles); that makes this value dependent on the master clock instead of the device clock for which the delay is intended to provide some relief. This patch leaves this old word_delay in place and provides a time-based word_delay_us alongside it; the new field fits in the struct padding so struct size is constant. There is only one in-kernel user of the word_delay field and presumably that driver could be reworked to use the time-based value instead. The time-based delay is limited to 8 bits as these delays are intended to be short. The SAMA5D2 that I've tested this on limits delays to a maximum of ~100us, which is already many word-transfer periods even at the minimum transfer speed supported by the controller. Signed-off-by: Jonas Bonn CC: Mark Brown CC: Rob Herring CC: Mark Rutland CC: linux-spi@vger.kernel.org CC: devicetree@vger.kernel.org Signed-off-by: Mark Brown --- drivers/spi/spi.c | 5 +++++ include/linux/spi/spi.h | 6 ++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 0e0f2c62973c..2f7176f07591 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -3050,6 +3050,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) * it is not set for this transfer. * Set transfer tx_nbits and rx_nbits as single transfer default * (SPI_NBITS_SINGLE) if it is not set for this transfer. + * Ensure transfer word_delay is at least as long as that required by + * device itself. */ message->frame_length = 0; list_for_each_entry(xfer, &message->transfers, transfer_list) { @@ -3120,6 +3122,9 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) !(spi->mode & SPI_RX_QUAD)) return -EINVAL; } + + if (xfer->word_delay_usecs < spi->word_delay_usecs) + xfer->word_delay_usecs = spi->word_delay_usecs; } message->status = -EINPROGRESS; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 916bba47d156..662b336aa2e4 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -122,6 +122,8 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, * the spi_master. * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when * not using a GPIO line) + * @word_delay_usecs: microsecond delay to be inserted between consecutive + * words of a transfer * * @statistics: statistics for the spi_device * @@ -169,6 +171,7 @@ struct spi_device { const char *driver_override; int cs_gpio; /* LEGACY: chip select gpio */ struct gpio_desc *cs_gpiod; /* chip select gpio desc */ + uint8_t word_delay_usecs; /* inter-word delay */ /* the statistics */ struct spi_statistics statistics; @@ -721,6 +724,8 @@ extern void spi_res_release(struct spi_controller *ctlr, * @delay_usecs: microseconds to delay after this transfer before * (optionally) changing the chipselect status, then starting * the next transfer or completing this @spi_message. + * @word_delay_usecs: microseconds to inter word delay after each word size + * (set by bits_per_word) transmission. * @word_delay: clock cycles to inter word delay after each word size * (set by bits_per_word) transmission. * @transfer_list: transfers are sequenced through @spi_message.transfers @@ -803,6 +808,7 @@ struct spi_transfer { #define SPI_NBITS_DUAL 0x02 /* 2bits transfer */ #define SPI_NBITS_QUAD 0x04 /* 4bits transfer */ u8 bits_per_word; + u8 word_delay_usecs; u16 delay_usecs; u32 speed_hz; u16 word_delay; -- cgit v1.2.3 From 57d4657716aca81ef4d7ec23e8123d26e3d28954 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 23 Jan 2019 13:35:00 -0500 Subject: audit: ignore fcaps on umount Don't fetch fcaps when umount2 is called to avoid a process hang while it waits for the missing resource to (possibly never) re-appear. Note the comment above user_path_mountpoint_at(): * A umount is a special case for path walking. We're not actually interested * in the inode in this situation, and ESTALE errors can be a problem. We * simply want track down the dentry and vfsmount attached at the mountpoint * and avoid revalidating the last component. This can happen on ceph, cifs, 9p, lustre, fuse (gluster) or NFS. Please see the github issue tracker https://github.com/linux-audit/audit-kernel/issues/100 Signed-off-by: Richard Guy Briggs [PM: merge fuzz in audit_log_fcaps()] Signed-off-by: Paul Moore --- fs/namei.c | 2 +- fs/namespace.c | 2 ++ include/linux/audit.h | 15 ++++++++++----- include/linux/namei.h | 3 +++ kernel/audit.c | 10 +++++++++- kernel/audit.h | 2 +- kernel/auditsc.c | 6 +++--- 7 files changed, 29 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/fs/namei.c b/fs/namei.c index 914178cdbe94..87d7710a2e1d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2720,7 +2720,7 @@ filename_mountpoint(int dfd, struct filename *name, struct path *path, if (unlikely(error == -ESTALE)) error = path_mountpoint(&nd, flags | LOOKUP_REVAL, path); if (likely(!error)) - audit_inode(name, path->dentry, 0); + audit_inode(name, path->dentry, flags & LOOKUP_NO_EVAL); restore_nameidata(); putname(name); return error; diff --git a/fs/namespace.c b/fs/namespace.c index a677b59efd74..e5de0e372df2 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1640,6 +1640,8 @@ int ksys_umount(char __user *name, int flags) if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; + lookup_flags |= LOOKUP_NO_EVAL; + retval = user_path_mountpoint_at(AT_FDCWD, name, lookup_flags, &path); if (retval) goto out; diff --git a/include/linux/audit.h b/include/linux/audit.h index ecb5d317d6a2..29251b18331a 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -25,6 +25,7 @@ #include #include +#include /* LOOKUP_* */ #include #define AUDIT_INO_UNSET ((unsigned long)-1) @@ -248,6 +249,7 @@ extern void __audit_getname(struct filename *name); #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ +#define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); @@ -308,12 +310,15 @@ static inline void audit_getname(struct filename *name) } static inline void audit_inode(struct filename *name, const struct dentry *dentry, - unsigned int parent) { + unsigned int flags) { if (unlikely(!audit_dummy_context())) { - unsigned int flags = 0; - if (parent) - flags |= AUDIT_INODE_PARENT; - __audit_inode(name, dentry, flags); + unsigned int aflags = 0; + + if (flags & LOOKUP_PARENT) + aflags |= AUDIT_INODE_PARENT; + if (flags & LOOKUP_NO_EVAL) + aflags |= AUDIT_INODE_NOEVAL; + __audit_inode(name, dentry, aflags); } } static inline void audit_file(struct file *file) diff --git a/include/linux/namei.h b/include/linux/namei.h index a78606e8e3df..9138b4471dbf 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -24,6 +24,8 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; * - internal "there are more path components" flag * - dentry cache is untrusted; force a real lookup * - suppress terminal automount + * - skip revalidation + * - don't fetch xattrs on audit_inode */ #define LOOKUP_FOLLOW 0x0001 #define LOOKUP_DIRECTORY 0x0002 @@ -33,6 +35,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_REVAL 0x0020 #define LOOKUP_RCU 0x0040 #define LOOKUP_NO_REVAL 0x0080 +#define LOOKUP_NO_EVAL 0x0100 /* * Intent data diff --git a/kernel/audit.c b/kernel/audit.c index 3f3f1888cac7..b7177a8def2e 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -2082,6 +2082,10 @@ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) { + if (name->fcap_ver == -1) { + audit_log_format(ab, " cap_fe=? cap_fver=? cap_fp=? cap_fi=?"); + return; + } audit_log_cap(ab, "cap_fp", &name->fcap.permitted); audit_log_cap(ab, "cap_fi", &name->fcap.inheritable); audit_log_format(ab, " cap_fe=%d cap_fver=%x cap_frootid=%d", @@ -2114,7 +2118,7 @@ static inline int audit_copy_fcaps(struct audit_names *name, /* Copy inode data into an audit_names. */ void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, - struct inode *inode) + struct inode *inode, unsigned int flags) { name->ino = inode->i_ino; name->dev = inode->i_sb->s_dev; @@ -2123,6 +2127,10 @@ void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, name->gid = inode->i_gid; name->rdev = inode->i_rdev; security_inode_getsecid(inode, &name->osid); + if (flags & AUDIT_INODE_NOEVAL) { + name->fcap_ver = -1; + return; + } audit_copy_fcaps(name, dentry); } diff --git a/kernel/audit.h b/kernel/audit.h index 9acb8691ed87..002f0f7ba732 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -215,7 +215,7 @@ extern void audit_log_session_info(struct audit_buffer *ab); extern void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, - struct inode *inode); + struct inode *inode, unsigned int flags); extern void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap); extern void audit_log_name(struct audit_context *context, diff --git a/kernel/auditsc.c b/kernel/auditsc.c index a2696ce790f9..68da71001096 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1856,7 +1856,7 @@ out: n->type = AUDIT_TYPE_NORMAL; } handle_path(dentry); - audit_copy_inode(n, dentry, inode); + audit_copy_inode(n, dentry, inode, flags & AUDIT_INODE_NOEVAL); } void __audit_file(const struct file *file) @@ -1955,7 +1955,7 @@ void __audit_inode_child(struct inode *parent, n = audit_alloc_name(context, AUDIT_TYPE_PARENT); if (!n) return; - audit_copy_inode(n, NULL, parent); + audit_copy_inode(n, NULL, parent, 0); } if (!found_child) { @@ -1974,7 +1974,7 @@ void __audit_inode_child(struct inode *parent, } if (inode) - audit_copy_inode(found_child, dentry, inode); + audit_copy_inode(found_child, dentry, inode, 0); else found_child->ino = AUDIT_INO_UNSET; } -- cgit v1.2.3 From 6780c4fa9d6e091b2f206ac429a40e2e8d2e45f3 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Tue, 22 Jan 2019 10:08:22 +0200 Subject: RDMA: Add indication for in kernel API support to IB device Drivers that do not provide kernel verbs support should not be used by ib kernel clients at all. In case a device does not implement all mandatory verbs for kverbs usage mark it as a non kverbs provider and prevent its usage for all clients except for uverbs. The device is marked as a non kverbs provider using the 'kverbs_provider' flag which should only be set by the core code. The clients can choose whether kverbs are requested for its usage using the 'no_kverbs_req' flag which is currently set for uverbs only. This patch allows drivers to remove mandatory verbs stubs and simply set the callbacks to NULL. The IB device will be registered as a non-kverbs provider. Note that verbs that are required for the device registration process must be implemented. Signed-off-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/device.c | 10 ++++++---- drivers/infiniband/core/uverbs_main.c | 1 + include/rdma/ib_verbs.h | 5 +++++ 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index b511cfa00bdb..9d2e108235e9 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -121,13 +121,12 @@ static int ib_device_check_mandatory(struct ib_device *device) }; int i; + device->kverbs_provider = true; for (i = 0; i < ARRAY_SIZE(mandatory_table); ++i) { if (!*(void **) ((void *) &device->ops + mandatory_table[i].offset)) { - dev_warn(&device->dev, - "Device is missing mandatory function %s\n", - mandatory_table[i].name); - return -EINVAL; + device->kverbs_provider = false; + break; } } @@ -325,6 +324,9 @@ static int add_client_context(struct ib_device *device, struct ib_client *client { struct ib_client_data *context; + if (!device->kverbs_provider && !client->no_kverbs_req) + return -EOPNOTSUPP; + context = kmalloc(sizeof(*context), GFP_KERNEL); if (!context) return -ENOMEM; diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 996f167d1436..d628747e058c 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -1151,6 +1151,7 @@ static const struct file_operations uverbs_mmap_fops = { static struct ib_client uverbs_client = { .name = "uverbs", + .no_kverbs_req = true, .add = ib_uverbs_add_one, .remove = ib_uverbs_remove_one }; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a1a1e710642c..4183a03b46b5 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2565,6 +2565,8 @@ struct ib_device { __be64 node_guid; u32 local_dma_lkey; u16 is_switch:1; + /* Indicates kernel verbs support, should not be used in drivers */ + u16 kverbs_provider:1; u8 node_type; u8 phys_port_cnt; struct ib_device_attr attrs; @@ -2619,6 +2621,9 @@ struct ib_client { const struct sockaddr *addr, void *client_data); struct list_head list; + + /* kverbs are not required by the client */ + u8 no_kverbs_req:1; }; struct ib_device *_ib_alloc_device(size_t size); -- cgit v1.2.3 From 0ad699c0edc97a864177679dd67f2ccd73b07cb7 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 30 Jan 2019 12:48:58 +0200 Subject: RDMA/core: Simplify restrack interface In the current implementation, we have one restrack root per-device and all users are simply providing it directly. Let's simplify the interface and have callers provide the ib_device and internally access the restrack_root. Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/device.c | 4 ++-- drivers/infiniband/core/nldev.c | 4 ++-- drivers/infiniband/core/restrack.c | 26 +++++++++++++++++++++----- include/rdma/restrack.h | 23 ++++------------------- 4 files changed, 29 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 9d2e108235e9..919e94ff4b25 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -287,7 +287,7 @@ struct ib_device *_ib_alloc_device(size_t size) if (!device) return NULL; - rdma_restrack_init(&device->res); + rdma_restrack_init(device); device->dev.class = &ib_class; device_initialize(&device->dev); @@ -315,7 +315,7 @@ void ib_dealloc_device(struct ib_device *device) WARN_ON(!list_empty(&device->client_data_list)); WARN_ON(device->reg_state != IB_DEV_UNREGISTERED && device->reg_state != IB_DEV_UNINITIALIZED); - rdma_restrack_clean(&device->res); + rdma_restrack_clean(device); put_device(&device->dev); } EXPORT_SYMBOL(ib_dealloc_device); diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 1742ff4fbf79..ee98fc9058b1 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -314,7 +314,6 @@ static int fill_res_info(struct sk_buff *msg, struct ib_device *device) [RDMA_RESTRACK_CTX] = "ctx", }; - struct rdma_restrack_root *res = &device->res; struct nlattr *table_attr; int ret, i, curr; @@ -328,7 +327,8 @@ static int fill_res_info(struct sk_buff *msg, struct ib_device *device) for (i = 0; i < RDMA_RESTRACK_MAX; i++) { if (!names[i]) continue; - curr = rdma_restrack_count(res, i, task_active_pid_ns(current)); + curr = rdma_restrack_count(device, i, + task_active_pid_ns(current)); ret = fill_res_info_entry(msg, names[i], curr); if (ret) goto err; diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c index 46a5c553c624..0ade3da0a5c7 100644 --- a/drivers/infiniband/core/restrack.c +++ b/drivers/infiniband/core/restrack.c @@ -18,8 +18,14 @@ static int fill_res_noop(struct sk_buff *msg, return 0; } -void rdma_restrack_init(struct rdma_restrack_root *res) +/** + * rdma_restrack_init() - initialize resource tracking + * @dev: IB device + */ +void rdma_restrack_init(struct ib_device *dev) { + struct rdma_restrack_root *res = &dev->res; + init_rwsem(&res->rwsem); res->fill_res_entry = fill_res_noop; } @@ -38,11 +44,15 @@ static const char *type2str(enum rdma_restrack_type type) return names[type]; }; -void rdma_restrack_clean(struct rdma_restrack_root *res) +/** + * rdma_restrack_clean() - clean resource tracking + * @dev: IB device + */ +void rdma_restrack_clean(struct ib_device *dev) { + struct rdma_restrack_root *res = &dev->res; struct rdma_restrack_entry *e; char buf[TASK_COMM_LEN]; - struct ib_device *dev; const char *owner; int bkt; @@ -72,10 +82,16 @@ void rdma_restrack_clean(struct rdma_restrack_root *res) pr_err("restrack: %s", CUT_HERE); } -int rdma_restrack_count(struct rdma_restrack_root *res, - enum rdma_restrack_type type, +/** + * rdma_restrack_count() - the current usage of specific object + * @dev: IB device + * @type: actual type of object to operate + * @ns: PID namespace + */ +int rdma_restrack_count(struct ib_device *dev, enum rdma_restrack_type type, struct pid_namespace *ns) { + struct rdma_restrack_root *res = &dev->res; struct rdma_restrack_entry *e; u32 cnt = 0; diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h index 8f179be9d9a9..f756fc48eee5 100644 --- a/include/rdma/restrack.h +++ b/include/rdma/restrack.h @@ -49,6 +49,7 @@ enum rdma_restrack_type { }; #define RDMA_RESTRACK_HASH_BITS 8 +struct ib_device; struct rdma_restrack_entry; /** @@ -122,25 +123,9 @@ struct rdma_restrack_entry { bool user; }; -/** - * rdma_restrack_init() - initialize resource tracking - * @res: resource tracking root - */ -void rdma_restrack_init(struct rdma_restrack_root *res); - -/** - * rdma_restrack_clean() - clean resource tracking - * @res: resource tracking root - */ -void rdma_restrack_clean(struct rdma_restrack_root *res); - -/** - * rdma_restrack_count() - the current usage of specific object - * @res: resource entry - * @type: actual type of object to operate - * @ns: PID namespace - */ -int rdma_restrack_count(struct rdma_restrack_root *res, +void rdma_restrack_init(struct ib_device *dev); +void rdma_restrack_clean(struct ib_device *dev); +int rdma_restrack_count(struct ib_device *dev, enum rdma_restrack_type type, struct pid_namespace *ns); -- cgit v1.2.3 From 02da37509705d3ba6a58fe4799a0caf6b4baecb0 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 30 Jan 2019 12:49:02 +0200 Subject: RDMA/core: Use the ops infrastructure to keep all callbacks in one place As preparation to hide rdma_restrack_root, refactor the code to use the ops structure instead of a special callback which is hidden in rdma_restrack_root. Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/device.c | 1 + drivers/infiniband/core/nldev.c | 28 ++++++++++++++++++---------- drivers/infiniband/core/restrack.c | 7 ------- drivers/infiniband/hw/cxgb4/provider.c | 2 +- include/rdma/ib_verbs.h | 5 +++++ include/rdma/restrack.h | 7 ------- 6 files changed, 25 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 919e94ff4b25..b9f725df4195 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1263,6 +1263,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) SET_DEVICE_OP(dev_ops, disassociate_ucontext); SET_DEVICE_OP(dev_ops, drain_rq); SET_DEVICE_OP(dev_ops, drain_sq); + SET_DEVICE_OP(dev_ops, fill_res_entry); SET_DEVICE_OP(dev_ops, get_dev_fw_str); SET_DEVICE_OP(dev_ops, get_dma_mr); SET_DEVICE_OP(dev_ops, get_hw_stats); diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index ee98fc9058b1..25a248847575 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -361,11 +361,19 @@ static int fill_res_name_pid(struct sk_buff *msg, return 0; } +static bool fill_res_entry(struct ib_device *dev, struct sk_buff *msg, + struct rdma_restrack_entry *res) +{ + if (!dev->ops.fill_res_entry) + return false; + return dev->ops.fill_res_entry(msg, res); +} + static int fill_res_qp_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_qp *qp = container_of(res, struct ib_qp, res); - struct rdma_restrack_root *resroot = &qp->device->res; + struct ib_device *dev = qp->device; struct ib_qp_init_attr qp_init_attr; struct nlattr *entry_attr; struct ib_qp_attr qp_attr; @@ -415,7 +423,7 @@ static int fill_res_qp_entry(struct sk_buff *msg, bool has_cap_net_admin, if (fill_res_name_pid(msg, res)) goto err; - if (resroot->fill_res_entry(msg, res)) + if (fill_res_entry(dev, msg, res)) goto err; nla_nest_end(msg, entry_attr); @@ -432,7 +440,7 @@ static int fill_res_cm_id_entry(struct sk_buff *msg, bool has_cap_net_admin, { struct rdma_id_private *id_priv = container_of(res, struct rdma_id_private, res); - struct rdma_restrack_root *resroot = &id_priv->id.device->res; + struct ib_device *dev = id_priv->id.device; struct rdma_cm_id *cm_id = &id_priv->id; struct nlattr *entry_attr; @@ -474,7 +482,7 @@ static int fill_res_cm_id_entry(struct sk_buff *msg, bool has_cap_net_admin, if (fill_res_name_pid(msg, res)) goto err; - if (resroot->fill_res_entry(msg, res)) + if (fill_res_entry(dev, msg, res)) goto err; nla_nest_end(msg, entry_attr); @@ -490,7 +498,7 @@ static int fill_res_cq_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_cq *cq = container_of(res, struct ib_cq, res); - struct rdma_restrack_root *resroot = &cq->device->res; + struct ib_device *dev = cq->device; struct nlattr *entry_attr; entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_CQ_ENTRY); @@ -511,7 +519,7 @@ static int fill_res_cq_entry(struct sk_buff *msg, bool has_cap_net_admin, if (fill_res_name_pid(msg, res)) goto err; - if (resroot->fill_res_entry(msg, res)) + if (fill_res_entry(dev, msg, res)) goto err; nla_nest_end(msg, entry_attr); @@ -527,7 +535,7 @@ static int fill_res_mr_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_mr *mr = container_of(res, struct ib_mr, res); - struct rdma_restrack_root *resroot = &mr->pd->device->res; + struct ib_device *dev = mr->pd->device; struct nlattr *entry_attr; entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_MR_ENTRY); @@ -548,7 +556,7 @@ static int fill_res_mr_entry(struct sk_buff *msg, bool has_cap_net_admin, if (fill_res_name_pid(msg, res)) goto err; - if (resroot->fill_res_entry(msg, res)) + if (fill_res_entry(dev, msg, res)) goto err; nla_nest_end(msg, entry_attr); @@ -564,7 +572,7 @@ static int fill_res_pd_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_pd *pd = container_of(res, struct ib_pd, res); - struct rdma_restrack_root *resroot = &pd->device->res; + struct ib_device *dev = pd->device; struct nlattr *entry_attr; entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_PD_ENTRY); @@ -591,7 +599,7 @@ static int fill_res_pd_entry(struct sk_buff *msg, bool has_cap_net_admin, if (fill_res_name_pid(msg, res)) goto err; - if (resroot->fill_res_entry(msg, res)) + if (fill_res_entry(dev, msg, res)) goto err; nla_nest_end(msg, entry_attr); diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c index bd7770ed4174..f80b37d437ac 100644 --- a/drivers/infiniband/core/restrack.c +++ b/drivers/infiniband/core/restrack.c @@ -12,12 +12,6 @@ #include "cma_priv.h" -static int fill_res_noop(struct sk_buff *msg, - struct rdma_restrack_entry *entry) -{ - return 0; -} - /** * rdma_restrack_init() - initialize resource tracking * @dev: IB device @@ -27,7 +21,6 @@ void rdma_restrack_init(struct ib_device *dev) struct rdma_restrack_root *res = &dev->res; init_rwsem(&res->rwsem); - res->fill_res_entry = fill_res_noop; } static const char *type2str(enum rdma_restrack_type type) diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index f977f8e7e162..cb5b713bbf39 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -549,6 +549,7 @@ static const struct ib_device_ops c4iw_dev_ops = { .destroy_cq = c4iw_destroy_cq, .destroy_qp = c4iw_destroy_qp, .destroy_srq = c4iw_destroy_srq, + .fill_res_entry = fill_res_entry, .get_dev_fw_str = get_dev_fw_str, .get_dma_mr = c4iw_get_dma_mr, .get_hw_stats = c4iw_get_mib, @@ -629,7 +630,6 @@ void c4iw_register_device(struct work_struct *work) dev->ibdev.iwcm->add_ref = c4iw_qp_add_ref; dev->ibdev.iwcm->rem_ref = c4iw_qp_rem_ref; dev->ibdev.iwcm->get_qp = c4iw_get_qp; - dev->ibdev.res.fill_res_entry = fill_res_entry; memcpy(dev->ibdev.iwcm->ifname, dev->rdev.lldi.ports[0]->name, sizeof(dev->ibdev.iwcm->ifname)); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 4183a03b46b5..5fc3be884444 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2510,6 +2510,11 @@ struct ib_device_ops { */ int (*init_port)(struct ib_device *device, u8 port_num, struct kobject *port_sysfs); + /** + * Allows rdma drivers to add their own restrack attributes. + */ + int (*fill_res_entry)(struct sk_buff *msg, + struct rdma_restrack_entry *entry); }; struct ib_device { diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h index f756fc48eee5..cc66cc7a11d3 100644 --- a/include/rdma/restrack.h +++ b/include/rdma/restrack.h @@ -65,13 +65,6 @@ struct rdma_restrack_root { * @hash: global database for all resources per-device */ DECLARE_HASHTABLE(hash, RDMA_RESTRACK_HASH_BITS); - /** - * @fill_res_entry: driver-specific fill function - * - * Allows rdma drivers to add their own restrack attributes. - */ - int (*fill_res_entry)(struct sk_buff *msg, - struct rdma_restrack_entry *entry); }; /** -- cgit v1.2.3 From befa618112a0a4590ce21d70aa35c9d341337774 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 28 Jan 2019 09:21:19 -0800 Subject: bpf: BPF_PROG_TYPE_CGROUP_{SKB, SOCK, SOCK_ADDR} require cgroups enabled There is no way to exercise appropriate attach points without cgroups enabled. This lets test_verifier correctly skip tests for these prog_types if kernel was compiled without BPF cgroup support. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/linux/bpf_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 44d9ab4809bd..08bf2f1fe553 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -6,9 +6,11 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter) BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act) BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act) BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) +#ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr) +#endif BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) -- cgit v1.2.3 From 116bfa96a255123ed209da6544f74a4f2eaca5da Mon Sep 17 00:00:00 2001 From: Valdis Kletnieks Date: Tue, 29 Jan 2019 01:04:25 -0500 Subject: bpf: fix missing prototype warnings Compiling with W=1 generates warnings: CC kernel/bpf/core.o kernel/bpf/core.c:721:12: warning: no previous prototype for ?bpf_jit_alloc_exec_limit? [-Wmissing-prototypes] 721 | u64 __weak bpf_jit_alloc_exec_limit(void) | ^~~~~~~~~~~~~~~~~~~~~~~~ kernel/bpf/core.c:757:14: warning: no previous prototype for ?bpf_jit_alloc_exec? [-Wmissing-prototypes] 757 | void *__weak bpf_jit_alloc_exec(unsigned long size) | ^~~~~~~~~~~~~~~~~~ kernel/bpf/core.c:762:13: warning: no previous prototype for ?bpf_jit_free_exec? [-Wmissing-prototypes] 762 | void __weak bpf_jit_free_exec(void *addr) | ^~~~~~~~~~~~~~~~~ All three are weak functions that archs can override, provide proper prototypes for when a new arch provides their own. Signed-off-by: Valdis Kletnieks Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index e4b473f85b46..7317376734f7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -880,7 +880,9 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_jit_binary_free(struct bpf_binary_header *hdr); - +u64 bpf_jit_alloc_exec_limit(void); +void *bpf_jit_alloc_exec(unsigned long size); +void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); int bpf_jit_get_func_addr(const struct bpf_prog *prog, -- cgit v1.2.3 From 1832f4ef5867fd3898d8a6c6c1978b75d76fc246 Mon Sep 17 00:00:00 2001 From: Valdis Kletnieks Date: Tue, 29 Jan 2019 01:47:06 -0500 Subject: bpf, cgroups: clean up kerneldoc warnings Building with W=1 reveals some bitrot: CC kernel/bpf/cgroup.o kernel/bpf/cgroup.c:238: warning: Function parameter or member 'flags' not described in '__cgroup_bpf_attach' kernel/bpf/cgroup.c:367: warning: Function parameter or member 'unused_flags' not described in '__cgroup_bpf_detach' Add a kerneldoc line for 'flags'. Fixing the warning for 'unused_flags' is best approached by removing the unused parameter on the function call. Signed-off-by: Valdis Kletnieks Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 2 +- kernel/bpf/cgroup.c | 3 ++- kernel/cgroup/cgroup.c | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 588dd5f0bd85..695b2a880d9a 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -78,7 +78,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp); int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, u32 flags); + enum bpf_attach_type type); int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ab612fe9862f..d78cfec5807d 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -230,6 +230,7 @@ cleanup: * @cgrp: The cgroup which descendants to traverse * @prog: A program to attach * @type: Type of attach operation + * @flags: Option flags * * Must be called with cgroup_mutex held. */ @@ -363,7 +364,7 @@ cleanup: * Must be called with cgroup_mutex held. */ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, u32 unused_flags) + enum bpf_attach_type type) { struct list_head *progs = &cgrp->bpf.progs[type]; enum bpf_cgroup_storage_type stype; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index f31bd61c9466..9f617605dacb 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5996,7 +5996,7 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_detach(cgrp, prog, type, flags); + ret = __cgroup_bpf_detach(cgrp, prog, type); mutex_unlock(&cgroup_mutex); return ret; } -- cgit v1.2.3 From a08c2a5a31941131c41feaa0429e4c8854cf48f2 Mon Sep 17 00:00:00 2001 From: Thara Gopinath Date: Wed, 23 Jan 2019 08:50:14 +0100 Subject: PM-runtime: Replace jiffies-based accounting with ktime-based accounting Replace jiffies-based accounting for runtime_active_time and runtime_suspended_time with ktime-based accounting. This makes the runtime debug counters inline with genpd and other PM subsytems which use ktime-based accounting. Timekeeping is initialized before driver_init(). It's only at that time that PM-runtime can be enabled. Signed-off-by: Thara Gopinath [switch from ktime to raw nsec] Signed-off-by: Vincent Guittot Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- drivers/base/power/runtime.c | 17 +++++++++-------- drivers/base/power/sysfs.c | 11 ++++++++--- include/linux/pm.h | 6 +++--- 3 files changed, 20 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index f23b7ecfce3b..eb1a3b878e1e 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -66,8 +66,8 @@ static int rpm_suspend(struct device *dev, int rpmflags); */ void update_pm_runtime_accounting(struct device *dev) { - unsigned long now = jiffies; - unsigned long delta; + u64 now = ktime_to_ns(ktime_get()); + u64 delta; delta = now - dev->power.accounting_timestamp; @@ -77,9 +77,9 @@ void update_pm_runtime_accounting(struct device *dev) return; if (dev->power.runtime_status == RPM_SUSPENDED) - dev->power.suspended_jiffies += delta; + dev->power.suspended_time += delta; else - dev->power.active_jiffies += delta; + dev->power.active_time += delta; } static void __update_runtime_status(struct device *dev, enum rpm_status status) @@ -90,16 +90,17 @@ static void __update_runtime_status(struct device *dev, enum rpm_status status) u64 pm_runtime_suspended_time(struct device *dev) { - unsigned long flags, time; + u64 time; + unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); update_pm_runtime_accounting(dev); - time = dev->power.suspended_jiffies; + time = dev->power.suspended_time; spin_unlock_irqrestore(&dev->power.lock, flags); - return jiffies_to_nsecs(time); + return time; } EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); @@ -1314,7 +1315,7 @@ void pm_runtime_enable(struct device *dev) /* About to enable runtime pm, set accounting_timestamp to now */ if (!dev->power.disable_depth) - dev->power.accounting_timestamp = jiffies; + dev->power.accounting_timestamp = ktime_to_ns(ktime_get()); } else { dev_warn(dev, "Unbalanced %s!\n", __func__); } diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index d713738ce796..96c8a227610a 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -125,9 +125,12 @@ static ssize_t runtime_active_time_show(struct device *dev, struct device_attribute *attr, char *buf) { int ret; + u64 tmp; spin_lock_irq(&dev->power.lock); update_pm_runtime_accounting(dev); - ret = sprintf(buf, "%i\n", jiffies_to_msecs(dev->power.active_jiffies)); + tmp = dev->power.active_time; + do_div(tmp, NSEC_PER_MSEC); + ret = sprintf(buf, "%llu\n", tmp); spin_unlock_irq(&dev->power.lock); return ret; } @@ -138,10 +141,12 @@ static ssize_t runtime_suspended_time_show(struct device *dev, struct device_attribute *attr, char *buf) { int ret; + u64 tmp; spin_lock_irq(&dev->power.lock); update_pm_runtime_accounting(dev); - ret = sprintf(buf, "%i\n", - jiffies_to_msecs(dev->power.suspended_jiffies)); + tmp = dev->power.suspended_time; + do_div(tmp, NSEC_PER_MSEC); + ret = sprintf(buf, "%llu\n", tmp); spin_unlock_irq(&dev->power.lock); return ret; } diff --git a/include/linux/pm.h b/include/linux/pm.h index 0bd9de116826..3d2cbf947768 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -633,9 +633,9 @@ struct dev_pm_info { int runtime_error; int autosuspend_delay; u64 last_busy; - unsigned long active_jiffies; - unsigned long suspended_jiffies; - unsigned long accounting_timestamp; + u64 active_time; + u64 suspended_time; + u64 accounting_timestamp; #endif struct pm_subsys_data *subsys_data; /* Owned by the subsystem. */ void (*set_latency_tolerance)(struct device *, s32); -- cgit v1.2.3 From 03535e7a3a9937da99ee18304309e0574d2504fc Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 24 Jan 2019 06:47:49 -0200 Subject: media: vb2: vb2_find_timestamp: drop restriction on buffer state There really is no reason why vb2_find_timestamp can't just find buffers in any state. Drop that part of the test. This also means that vb->timestamp should only be set to 0 when the driver doesn't copy timestamps. This change allows for more efficient pipelining (i.e. you can use a buffer for a reference frame even when it is queued). Signed-off-by: Hans Verkuil Reviewed-by: Tomasz Figa Reviewed-by: Alexandre Courbot Reviewed-by: Paul Kocialkowski Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-v4l2.c | 11 +++-------- include/media/videobuf2-v4l2.h | 3 +-- 2 files changed, 4 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index 75ea90e795d8..2f3b3ca5bde6 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -567,7 +567,7 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb, struct vb2_plane *planes) struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); unsigned int plane; - if (!vb->vb2_queue->is_output || !vb->vb2_queue->copy_timestamp) + if (!vb->vb2_queue->copy_timestamp) vb->timestamp = 0; for (plane = 0; plane < vb->num_planes; ++plane) { @@ -594,14 +594,9 @@ int vb2_find_timestamp(const struct vb2_queue *q, u64 timestamp, { unsigned int i; - for (i = start_idx; i < q->num_buffers; i++) { - struct vb2_buffer *vb = q->bufs[i]; - - if ((vb->state == VB2_BUF_STATE_DEQUEUED || - vb->state == VB2_BUF_STATE_DONE) && - vb->timestamp == timestamp) + for (i = start_idx; i < q->num_buffers; i++) + if (q->bufs[i]->timestamp == timestamp) return i; - } return -1; } EXPORT_SYMBOL_GPL(vb2_find_timestamp); diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h index a9961bc776dc..8a10889dc2fd 100644 --- a/include/media/videobuf2-v4l2.h +++ b/include/media/videobuf2-v4l2.h @@ -59,8 +59,7 @@ struct vb2_v4l2_buffer { * vb2_find_timestamp() - Find buffer with given timestamp in the queue * * @q: pointer to &struct vb2_queue with videobuf2 queue. - * @timestamp: the timestamp to find. Only buffers in state DEQUEUED or DONE - * are considered. + * @timestamp: the timestamp to find. * @start_idx: the start index (usually 0) in the buffer array to start * searching from. Note that there may be multiple buffers * with the same timestamp value, so you can restart the search -- cgit v1.2.3 From 28d77c21cbeb2c6039d48ef88401b87a56a7a07f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 16 Jan 2019 10:01:13 -0200 Subject: media: vb2: add buf_out_validate callback When queueing a buffer to a request the 'field' value is not validated. That field is only validated when the _buf_prepare() is called, which happens when the request is queued. However, this validation should happen at QBUF time, since you want to know about this as soon as possible. Also, the spec requires that the 'field' value is validated at QBUF time. This patch adds a new buf_out_validate callback to validate the output buffer at buf_prepare time or when QBUF queues an unprepared buffer to a request. This callback is mandatory for output queues that support requests. This issue was found by v4l2-compliance since it failed to replace V4L2_FIELD_ANY by a proper field value when testing the vivid video output in combination with requests. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-core.c | 22 +++++++++++++++++++--- include/media/videobuf2-core.h | 5 +++++ 2 files changed, 24 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index ce9294a635cc..e07b6bdb6982 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -499,9 +499,9 @@ static int __vb2_queue_free(struct vb2_queue *q, unsigned int buffers) pr_info(" buf_init: %u buf_cleanup: %u buf_prepare: %u buf_finish: %u\n", vb->cnt_buf_init, vb->cnt_buf_cleanup, vb->cnt_buf_prepare, vb->cnt_buf_finish); - pr_info(" buf_queue: %u buf_done: %u buf_request_complete: %u\n", - vb->cnt_buf_queue, vb->cnt_buf_done, - vb->cnt_buf_request_complete); + pr_info(" buf_out_validate: %u buf_queue: %u buf_done: %u buf_request_complete: %u\n", + vb->cnt_buf_out_validate, vb->cnt_buf_queue, + vb->cnt_buf_done, vb->cnt_buf_request_complete); pr_info(" alloc: %u put: %u prepare: %u finish: %u mmap: %u\n", vb->cnt_mem_alloc, vb->cnt_mem_put, vb->cnt_mem_prepare, vb->cnt_mem_finish, @@ -1277,6 +1277,14 @@ static int __buf_prepare(struct vb2_buffer *vb) return 0; WARN_ON(vb->synced); + if (q->is_output) { + ret = call_vb_qop(vb, buf_out_validate, vb); + if (ret) { + dprintk(1, "buffer validation failed\n"); + return ret; + } + } + vb->state = VB2_BUF_STATE_PREPARING; switch (q->memory) { @@ -1523,6 +1531,14 @@ int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb, return -EINVAL; } + if (q->is_output && !vb->prepared) { + ret = call_vb_qop(vb, buf_out_validate, vb); + if (ret) { + dprintk(1, "buffer validation failed\n"); + return ret; + } + } + media_request_object_init(&vb->req_obj); /* Make sure the request is in a safe state for updating. */ diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 4a737b2c610b..4849b865b908 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -296,6 +296,7 @@ struct vb2_buffer { u32 cnt_mem_num_users; u32 cnt_mem_mmap; + u32 cnt_buf_out_validate; u32 cnt_buf_init; u32 cnt_buf_prepare; u32 cnt_buf_finish; @@ -342,6 +343,9 @@ struct vb2_buffer { * @wait_finish: reacquire all locks released in the previous callback; * required to continue operation after sleeping while * waiting for a new buffer to arrive. + * @buf_out_validate: called when the output buffer is prepared or queued + * to a request; drivers can use this to validate + * userspace-provided information; optional. * @buf_init: called once after allocating a buffer (in MMAP case) * or after acquiring a new USERPTR buffer; drivers may * perform additional buffer-related initialization; @@ -409,6 +413,7 @@ struct vb2_ops { void (*wait_prepare)(struct vb2_queue *q); void (*wait_finish)(struct vb2_queue *q); + int (*buf_out_validate)(struct vb2_buffer *vb); int (*buf_init)(struct vb2_buffer *vb); int (*buf_prepare)(struct vb2_buffer *vb); void (*buf_finish)(struct vb2_buffer *vb); -- cgit v1.2.3 From 8204e0c1113d6b7f599bcd7ebfbfde72e76c102f Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 22 Jan 2019 10:39:26 -0800 Subject: workqueue: Provide queue_work_node to queue work near a given NUMA node Provide a new function, queue_work_node, which is meant to schedule work on a "random" CPU of the requested NUMA node. The main motivation for this is to help assist asynchronous init to better improve boot times for devices that are local to a specific node. For now we just default to the first CPU that is in the intersection of the cpumask of the node and the online cpumask. The only exception is if the CPU is local to the node we will just use the current CPU. This should work for our purposes as we are currently only using this for unbound work so the CPU will be translated to a node anyway instead of being directly used. As we are only using the first CPU to represent the NUMA node for now I am limiting the scope of the function so that it can only be used with unbound workqueues. Acked-by: Tejun Heo Reviewed-by: Bart Van Assche Acked-by: Dan Williams Signed-off-by: Alexander Duyck Signed-off-by: Greg Kroah-Hartman --- include/linux/workqueue.h | 2 ++ kernel/workqueue.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 86 insertions(+) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 60d673e15632..1f50c1e586e7 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -463,6 +463,8 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); +extern bool queue_work_node(int node, struct workqueue_struct *wq, + struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 392be4b252f6..d5a26e456f7a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1492,6 +1492,90 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL(queue_work_on); +/** + * workqueue_select_cpu_near - Select a CPU based on NUMA node + * @node: NUMA node ID that we want to select a CPU from + * + * This function will attempt to find a "random" cpu available on a given + * node. If there are no CPUs available on the given node it will return + * WORK_CPU_UNBOUND indicating that we should just schedule to any + * available CPU if we need to schedule this work. + */ +static int workqueue_select_cpu_near(int node) +{ + int cpu; + + /* No point in doing this if NUMA isn't enabled for workqueues */ + if (!wq_numa_enabled) + return WORK_CPU_UNBOUND; + + /* Delay binding to CPU if node is not valid or online */ + if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) + return WORK_CPU_UNBOUND; + + /* Use local node/cpu if we are already there */ + cpu = raw_smp_processor_id(); + if (node == cpu_to_node(cpu)) + return cpu; + + /* Use "random" otherwise know as "first" online CPU of node */ + cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); + + /* If CPU is valid return that, otherwise just defer */ + return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; +} + +/** + * queue_work_node - queue work on a "random" cpu for a given NUMA node + * @node: NUMA node that we are targeting the work for + * @wq: workqueue to use + * @work: work to queue + * + * We queue the work to a "random" CPU within a given NUMA node. The basic + * idea here is to provide a way to somehow associate work with a given + * NUMA node. + * + * This function will only make a best effort attempt at getting this onto + * the right NUMA node. If no node is requested or the requested node is + * offline then we just fall back to standard queue_work behavior. + * + * Currently the "random" CPU ends up being the first available CPU in the + * intersection of cpu_online_mask and the cpumask of the node, unless we + * are running on the node. In that case we just use the current CPU. + * + * Return: %false if @work was already on a queue, %true otherwise. + */ +bool queue_work_node(int node, struct workqueue_struct *wq, + struct work_struct *work) +{ + unsigned long flags; + bool ret = false; + + /* + * This current implementation is specific to unbound workqueues. + * Specifically we only return the first available CPU for a given + * node instead of cycling through individual CPUs within the node. + * + * If this is used with a per-cpu workqueue then the logic in + * workqueue_select_cpu_near would need to be updated to allow for + * some round robin type logic. + */ + WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); + + local_irq_save(flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + int cpu = workqueue_select_cpu_near(node); + + __queue_work(cpu, wq, work); + ret = true; + } + + local_irq_restore(flags); + return ret; +} +EXPORT_SYMBOL_GPL(queue_work_node); + void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = from_timer(dwork, t, timer); -- cgit v1.2.3 From 6be9238e5cb64741ff95c3ae440b112753ad93de Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 22 Jan 2019 10:39:31 -0800 Subject: async: Add support for queueing on specific NUMA node Introduce four new variants of the async_schedule_ functions that allow scheduling on a specific NUMA node. The first two functions are async_schedule_near and async_schedule_near_domain end up mapping to async_schedule and async_schedule_domain, but provide NUMA node specific functionality. They replace the original functions which were moved to inline function definitions that call the new functions while passing NUMA_NO_NODE. The second two functions are async_schedule_dev and async_schedule_dev_domain which provide NUMA specific functionality when passing a device as the data member and that device has a NUMA node other than NUMA_NO_NODE. The main motivation behind this is to address the need to be able to schedule device specific init work on specific NUMA nodes in order to improve performance of memory initialization. I have seen a significant improvement in initialziation time for persistent memory as a result of this approach. In the case of 3TB of memory on a single node the initialization time in the worst case went from 36s down to about 26s for a 10s improvement. As such the data shows a general benefit for affinitizing the async work to the node local to the device. Reviewed-by: Bart Van Assche Reviewed-by: Dan Williams Signed-off-by: Alexander Duyck Signed-off-by: Greg Kroah-Hartman --- include/linux/async.h | 82 +++++++++++++++++++++++++++++++++++++++++++++++++-- kernel/async.c | 53 ++++++++++++++++++--------------- 2 files changed, 108 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/async.h b/include/linux/async.h index 6b0226bdaadc..f81d6dbffe68 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -14,6 +14,8 @@ #include #include +#include +#include typedef u64 async_cookie_t; typedef void (*async_func_t) (void *data, async_cookie_t cookie); @@ -37,9 +39,83 @@ struct async_domain { struct async_domain _name = { .pending = LIST_HEAD_INIT(_name.pending), \ .registered = 0 } -extern async_cookie_t async_schedule(async_func_t func, void *data); -extern async_cookie_t async_schedule_domain(async_func_t func, void *data, - struct async_domain *domain); +async_cookie_t async_schedule_node(async_func_t func, void *data, + int node); +async_cookie_t async_schedule_node_domain(async_func_t func, void *data, + int node, + struct async_domain *domain); + +/** + * async_schedule - schedule a function for asynchronous execution + * @func: function to execute asynchronously + * @data: data pointer to pass to the function + * + * Returns an async_cookie_t that may be used for checkpointing later. + * Note: This function may be called from atomic or non-atomic contexts. + */ +static inline async_cookie_t async_schedule(async_func_t func, void *data) +{ + return async_schedule_node(func, data, NUMA_NO_NODE); +} + +/** + * async_schedule_domain - schedule a function for asynchronous execution within a certain domain + * @func: function to execute asynchronously + * @data: data pointer to pass to the function + * @domain: the domain + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @domain may be used in the async_synchronize_*_domain() functions to + * wait within a certain synchronization domain rather than globally. + * Note: This function may be called from atomic or non-atomic contexts. + */ +static inline async_cookie_t +async_schedule_domain(async_func_t func, void *data, + struct async_domain *domain) +{ + return async_schedule_node_domain(func, data, NUMA_NO_NODE, domain); +} + +/** + * async_schedule_dev - A device specific version of async_schedule + * @func: function to execute asynchronously + * @dev: device argument to be passed to function + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @dev is used as both the argument for the function and to provide NUMA + * context for where to run the function. By doing this we can try to + * provide for the best possible outcome by operating on the device on the + * CPUs closest to the device. + * Note: This function may be called from atomic or non-atomic contexts. + */ +static inline async_cookie_t +async_schedule_dev(async_func_t func, struct device *dev) +{ + return async_schedule_node(func, dev, dev_to_node(dev)); +} + +/** + * async_schedule_dev_domain - A device specific version of async_schedule_domain + * @func: function to execute asynchronously + * @dev: device argument to be passed to function + * @domain: the domain + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @dev is used as both the argument for the function and to provide NUMA + * context for where to run the function. By doing this we can try to + * provide for the best possible outcome by operating on the device on the + * CPUs closest to the device. + * @domain may be used in the async_synchronize_*_domain() functions to + * wait within a certain synchronization domain rather than globally. + * Note: This function may be called from atomic or non-atomic contexts. + */ +static inline async_cookie_t +async_schedule_dev_domain(async_func_t func, struct device *dev, + struct async_domain *domain) +{ + return async_schedule_node_domain(func, dev, dev_to_node(dev), domain); +} + void async_unregister_domain(struct async_domain *domain); extern void async_synchronize_full(void); extern void async_synchronize_full_domain(struct async_domain *domain); diff --git a/kernel/async.c b/kernel/async.c index a893d6170944..f6bd0d9885e1 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -149,7 +149,25 @@ static void async_run_entry_fn(struct work_struct *work) wake_up(&async_done); } -static async_cookie_t __async_schedule(async_func_t func, void *data, struct async_domain *domain) +/** + * async_schedule_node_domain - NUMA specific version of async_schedule_domain + * @func: function to execute asynchronously + * @data: data pointer to pass to the function + * @node: NUMA node that we want to schedule this on or close to + * @domain: the domain + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @domain may be used in the async_synchronize_*_domain() functions to + * wait within a certain synchronization domain rather than globally. + * + * Note: This function may be called from atomic or non-atomic contexts. + * + * The node requested will be honored on a best effort basis. If the node + * has no CPUs associated with it then the work is distributed among all + * available CPUs. + */ +async_cookie_t async_schedule_node_domain(async_func_t func, void *data, + int node, struct async_domain *domain) { struct async_entry *entry; unsigned long flags; @@ -195,43 +213,30 @@ static async_cookie_t __async_schedule(async_func_t func, void *data, struct asy current->flags |= PF_USED_ASYNC; /* schedule for execution */ - queue_work(system_unbound_wq, &entry->work); + queue_work_node(node, system_unbound_wq, &entry->work); return newcookie; } +EXPORT_SYMBOL_GPL(async_schedule_node_domain); /** - * async_schedule - schedule a function for asynchronous execution + * async_schedule_node - NUMA specific version of async_schedule * @func: function to execute asynchronously * @data: data pointer to pass to the function + * @node: NUMA node that we want to schedule this on or close to * * Returns an async_cookie_t that may be used for checkpointing later. * Note: This function may be called from atomic or non-atomic contexts. - */ -async_cookie_t async_schedule(async_func_t func, void *data) -{ - return __async_schedule(func, data, &async_dfl_domain); -} -EXPORT_SYMBOL_GPL(async_schedule); - -/** - * async_schedule_domain - schedule a function for asynchronous execution within a certain domain - * @func: function to execute asynchronously - * @data: data pointer to pass to the function - * @domain: the domain * - * Returns an async_cookie_t that may be used for checkpointing later. - * @domain may be used in the async_synchronize_*_domain() functions to - * wait within a certain synchronization domain rather than globally. A - * synchronization domain is specified via @domain. Note: This function - * may be called from atomic or non-atomic contexts. + * The node requested will be honored on a best effort basis. If the node + * has no CPUs associated with it then the work is distributed among all + * available CPUs. */ -async_cookie_t async_schedule_domain(async_func_t func, void *data, - struct async_domain *domain) +async_cookie_t async_schedule_node(async_func_t func, void *data, int node) { - return __async_schedule(func, data, domain); + return async_schedule_node_domain(func, data, node, &async_dfl_domain); } -EXPORT_SYMBOL_GPL(async_schedule_domain); +EXPORT_SYMBOL_GPL(async_schedule_node); /** * async_synchronize_full - synchronize all asynchronous function calls -- cgit v1.2.3 From 51bee5abeab2058ea5813c5615d6197a23dbf041 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 28 Jan 2019 17:00:13 +0100 Subject: cgroup/pids: turn cgroup_subsys->free() into cgroup_subsys->release() to fix the accounting The only user of cgroup_subsys->free() callback is pids_cgrp_subsys which needs pids_free() to uncharge the pid. However, ->free() is called from __put_task_struct()->cgroup_free() and this is too late. Even the trivial program which does for (;;) { int pid = fork(); assert(pid >= 0); if (pid) wait(NULL); else exit(0); } can run out of limits because release_task()->call_rcu(delayed_put_task_struct) implies an RCU gp after the task/pid goes away and before the final put(). Test-case: mkdir -p /tmp/CG mount -t cgroup2 none /tmp/CG echo '+pids' > /tmp/CG/cgroup.subtree_control mkdir /tmp/CG/PID echo 2 > /tmp/CG/PID/pids.max perl -e 'while ($p = fork) { wait; } $p // die "fork failed: $!\n"' & echo $! > /tmp/CG/PID/cgroup.procs Without this patch the forking process fails soon after migration. Rename cgroup_subsys->free() to cgroup_subsys->release() and move the callsite into the new helper, cgroup_release(), called by release_task() which actually frees the pid(s). Reported-by: Herton R. Krzesinski Reported-by: Jan Stancek Signed-off-by: Oleg Nesterov Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 2 +- include/linux/cgroup.h | 2 ++ kernel/cgroup/cgroup.c | 15 +++++++++------ kernel/cgroup/pids.c | 4 ++-- kernel/exit.c | 1 + 5 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8fcbae1b8db0..120d1d40704b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -602,7 +602,7 @@ struct cgroup_subsys { void (*cancel_fork)(struct task_struct *task); void (*fork)(struct task_struct *task); void (*exit)(struct task_struct *task); - void (*free)(struct task_struct *task); + void (*release)(struct task_struct *task); void (*bind)(struct cgroup_subsys_state *root_css); bool early_init:1; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9968332cceed..81f58b4a5418 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -121,6 +121,7 @@ extern int cgroup_can_fork(struct task_struct *p); extern void cgroup_cancel_fork(struct task_struct *p); extern void cgroup_post_fork(struct task_struct *p); void cgroup_exit(struct task_struct *p); +void cgroup_release(struct task_struct *p); void cgroup_free(struct task_struct *p); int cgroup_init_early(void); @@ -697,6 +698,7 @@ static inline int cgroup_can_fork(struct task_struct *p) { return 0; } static inline void cgroup_cancel_fork(struct task_struct *p) {} static inline void cgroup_post_fork(struct task_struct *p) {} static inline void cgroup_exit(struct task_struct *p) {} +static inline void cgroup_release(struct task_struct *p) {} static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index f31bd61c9466..f4418371c83b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -197,7 +197,7 @@ static u64 css_serial_nr_next = 1; */ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; -static u16 have_free_callback __read_mostly; +static u16 have_release_callback __read_mostly; static u16 have_canfork_callback __read_mostly; /* cgroup namespace for init task */ @@ -5313,7 +5313,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) have_fork_callback |= (bool)ss->fork << ss->id; have_exit_callback |= (bool)ss->exit << ss->id; - have_free_callback |= (bool)ss->free << ss->id; + have_release_callback |= (bool)ss->release << ss->id; have_canfork_callback |= (bool)ss->can_fork << ss->id; /* At system boot, before all subsystems have been @@ -5749,16 +5749,19 @@ void cgroup_exit(struct task_struct *tsk) } while_each_subsys_mask(); } -void cgroup_free(struct task_struct *task) +void cgroup_release(struct task_struct *task) { - struct css_set *cset = task_css_set(task); struct cgroup_subsys *ss; int ssid; - do_each_subsys_mask(ss, ssid, have_free_callback) { - ss->free(task); + do_each_subsys_mask(ss, ssid, have_release_callback) { + ss->release(task); } while_each_subsys_mask(); +} +void cgroup_free(struct task_struct *task) +{ + struct css_set *cset = task_css_set(task); put_css_set(cset); } diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index 9829c67ebc0a..c9960baaa14f 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -247,7 +247,7 @@ static void pids_cancel_fork(struct task_struct *task) pids_uncharge(pids, 1); } -static void pids_free(struct task_struct *task) +static void pids_release(struct task_struct *task) { struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id)); @@ -342,7 +342,7 @@ struct cgroup_subsys pids_cgrp_subsys = { .cancel_attach = pids_cancel_attach, .can_fork = pids_can_fork, .cancel_fork = pids_cancel_fork, - .free = pids_free, + .release = pids_release, .legacy_cftypes = pids_files, .dfl_cftypes = pids_files, .threaded = true, diff --git a/kernel/exit.c b/kernel/exit.c index 3fb7be001964..c2b8443f30b4 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -219,6 +219,7 @@ repeat: } write_unlock_irq(&tasklist_lock); + cgroup_release(p); release_thread(p); call_rcu(&p->rcu, delayed_put_task_struct); -- cgit v1.2.3 From ddf922c31fedd19c5b89a269c35e5c8b68c64327 Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Wed, 23 Jan 2019 19:21:01 -0800 Subject: IB/hfi1, IB/rdmavt: Allow for extending of QP's s_ack_queue The OPFN protocol uses the COMPARE_SWAP request to exchange data between the requester and the responder and therefore needs to be stored in the QP's s_ack_queue when the request is received on the responder side. However, because the user does not know anything about the OPFN protocol, this extra entry in the queue cannot be advertised to the user. This patch adds an extra entry in a QP's s_ack_queue. Reviewed-by: Mike Marciniszyn Signed-off-by: Mitko Haralanov Signed-off-by: Kaike Wan Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/rc.c | 13 +++++++------ drivers/infiniband/hw/hfi1/verbs.c | 1 + include/rdma/rdma_vt.h | 10 +++++++++- 3 files changed, 17 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 940e9236c328..8970fc7ffd4b 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -122,7 +122,8 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, * response has been sent instead of only being * constructed. */ - if (++qp->s_tail_ack_queue > HFI1_MAX_RDMA_ATOMIC) + if (++qp->s_tail_ack_queue > + rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) qp->s_tail_ack_queue = 0; /* FALLTHROUGH */ case OP(SEND_ONLY): @@ -1818,7 +1819,7 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data, if (i) prev = i - 1; else - prev = HFI1_MAX_RDMA_ATOMIC; + prev = rvt_size_atomic(ib_to_rvt(qp->ibqp.device)); if (prev == qp->r_head_ack_queue) { e = NULL; break; @@ -1942,7 +1943,7 @@ static inline void update_ack_queue(struct rvt_qp *qp, unsigned n) unsigned next; next = n + 1; - if (next > HFI1_MAX_RDMA_ATOMIC) + if (next > rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) next = 0; qp->s_tail_ack_queue = next; qp->s_ack_state = OP(ACKNOWLEDGE); @@ -2298,8 +2299,8 @@ send_last: if (unlikely(!(qp->qp_access_flags & IB_ACCESS_REMOTE_READ))) goto nack_inv; next = qp->r_head_ack_queue + 1; - /* s_ack_queue is size HFI1_MAX_RDMA_ATOMIC+1 so use > not >= */ - if (next > HFI1_MAX_RDMA_ATOMIC) + /* s_ack_queue is size rvt_size_atomic()+1 so use > not >= */ + if (next > rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) next = 0; spin_lock_irqsave(&qp->s_lock, flags); if (unlikely(next == qp->s_tail_ack_queue)) { @@ -2373,7 +2374,7 @@ send_last: if (unlikely(!(qp->qp_access_flags & IB_ACCESS_REMOTE_ATOMIC))) goto nack_inv; next = qp->r_head_ack_queue + 1; - if (next > HFI1_MAX_RDMA_ATOMIC) + if (next > rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) next = 0; spin_lock_irqsave(&qp->s_lock, flags); if (unlikely(next == qp->s_tail_ack_queue)) { diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index c980345cf1e1..ec3899c0874c 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -1735,6 +1735,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd) dd->verbs_dev.rdi.dparms.sge_copy_mode = sge_copy_mode; dd->verbs_dev.rdi.dparms.wss_threshold = wss_threshold; dd->verbs_dev.rdi.dparms.wss_clean_period = wss_clean_period; + dd->verbs_dev.rdi.dparms.extra_rdma_atomic = 1; /* post send table */ dd->verbs_dev.rdi.post_parms = hfi1_post_parms; diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h index acb3bc96dfa7..168e40be183c 100644 --- a/include/rdma/rdma_vt.h +++ b/include/rdma/rdma_vt.h @@ -182,6 +182,7 @@ struct rvt_driver_params { u32 max_mad_size; u8 qos_shift; u8 max_rdma_atomic; + u8 extra_rdma_atomic; u8 reserved_operations; }; @@ -519,7 +520,14 @@ static inline unsigned rvt_get_npkeys(struct rvt_dev_info *rdi) */ static inline unsigned int rvt_max_atomic(struct rvt_dev_info *rdi) { - return rdi->dparms.max_rdma_atomic + 1; + return rdi->dparms.max_rdma_atomic + + rdi->dparms.extra_rdma_atomic + 1; +} + +static inline unsigned int rvt_size_atomic(struct rvt_dev_info *rdi) +{ + return rdi->dparms.max_rdma_atomic + + rdi->dparms.extra_rdma_atomic; } /* -- cgit v1.2.3 From 90462a5bd30c6ed91c6758e59537d047d7878ff9 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Thu, 31 Jan 2019 11:52:11 -0500 Subject: audit: remove unused actx param from audit_rule_match The audit_rule_match() struct audit_context *actx parameter is not used by any in-tree consumers (selinux, apparmour, integrity, smack). The audit context is an internal audit structure that should only be accessed by audit accessor functions. It was part of commit 03d37d25e0f9 ("LSM/Audit: Introduce generic Audit LSM hooks") but appears to have never been used. Remove it. Please see the github issue https://github.com/linux-audit/audit-kernel/issues/107 Signed-off-by: Richard Guy Briggs [PM: fixed the referenced commit title] Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 4 +--- include/linux/security.h | 5 ++--- kernel/auditfilter.c | 2 +- kernel/auditsc.c | 21 ++++++++++++--------- security/apparmor/audit.c | 3 +-- security/apparmor/include/audit.h | 3 +-- security/integrity/ima/ima.h | 3 +-- security/integrity/ima/ima_policy.c | 6 ++---- security/security.c | 6 ++---- security/selinux/include/audit.h | 4 +--- security/selinux/ss/services.c | 3 +-- security/smack/smack_lsm.c | 4 +--- 12 files changed, 26 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9a0bdf91e646..d0b5c7a05832 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1344,7 +1344,6 @@ * @field contains the field which relates to current LSM. * @op contains the operator that will be used for matching. * @rule points to the audit rule that will be checked against. - * @actx points to the audit context associated with the check. * Return 1 if secid matches the rule, 0 if it does not, -ERRNO on failure. * * @audit_rule_free: @@ -1764,8 +1763,7 @@ union security_list_options { int (*audit_rule_init)(u32 field, u32 op, char *rulestr, void **lsmrule); int (*audit_rule_known)(struct audit_krule *krule); - int (*audit_rule_match)(u32 secid, u32 field, u32 op, void *lsmrule, - struct audit_context *actx); + int (*audit_rule_match)(u32 secid, u32 field, u32 op, void *lsmrule); void (*audit_rule_free)(void *lsmrule); #endif /* CONFIG_AUDIT */ diff --git a/include/linux/security.h b/include/linux/security.h index dbfb5a66babb..e8febec62ffb 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1674,8 +1674,7 @@ static inline int security_key_getsecurity(struct key *key, char **_buffer) #ifdef CONFIG_SECURITY int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule); int security_audit_rule_known(struct audit_krule *krule); -int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule, - struct audit_context *actx); +int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule); void security_audit_rule_free(void *lsmrule); #else @@ -1692,7 +1691,7 @@ static inline int security_audit_rule_known(struct audit_krule *krule) } static inline int security_audit_rule_match(u32 secid, u32 field, u32 op, - void *lsmrule, struct audit_context *actx) + void *lsmrule) { return 0; } diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 26a80a9d43a9..add360b46b38 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1355,7 +1355,7 @@ int audit_filter(int msgtype, unsigned int listtype) if (f->lsm_rule) { security_task_getsecid(current, &sid); result = security_audit_rule_match(sid, - f->type, f->op, f->lsm_rule, NULL); + f->type, f->op, f->lsm_rule); } break; case AUDIT_EXE: diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 68da71001096..7d37cb1e4aef 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -631,9 +631,8 @@ static int audit_filter_rules(struct task_struct *tsk, need_sid = 0; } result = security_audit_rule_match(sid, f->type, - f->op, - f->lsm_rule, - ctx); + f->op, + f->lsm_rule); } break; case AUDIT_OBJ_USER: @@ -647,13 +646,17 @@ static int audit_filter_rules(struct task_struct *tsk, /* Find files that match */ if (name) { result = security_audit_rule_match( - name->osid, f->type, f->op, - f->lsm_rule, ctx); + name->osid, + f->type, + f->op, + f->lsm_rule); } else if (ctx) { list_for_each_entry(n, &ctx->names_list, list) { - if (security_audit_rule_match(n->osid, f->type, - f->op, f->lsm_rule, - ctx)) { + if (security_audit_rule_match( + n->osid, + f->type, + f->op, + f->lsm_rule)) { ++result; break; } @@ -664,7 +667,7 @@ static int audit_filter_rules(struct task_struct *tsk, break; if (security_audit_rule_match(ctx->ipc.osid, f->type, f->op, - f->lsm_rule, ctx)) + f->lsm_rule)) ++result; } break; diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c index eeaddfe0c0fb..5a8b9cded4f2 100644 --- a/security/apparmor/audit.c +++ b/security/apparmor/audit.c @@ -225,8 +225,7 @@ int aa_audit_rule_known(struct audit_krule *rule) return 0; } -int aa_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule, - struct audit_context *actx) +int aa_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) { struct aa_audit_rule *rule = vrule; struct aa_label *label; diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h index b8c8b1066b0a..ee559bc2acb8 100644 --- a/security/apparmor/include/audit.h +++ b/security/apparmor/include/audit.h @@ -192,7 +192,6 @@ static inline int complain_error(int error) void aa_audit_rule_free(void *vrule); int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule); int aa_audit_rule_known(struct audit_krule *rule); -int aa_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule, - struct audit_context *actx); +int aa_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule); #endif /* __AA_AUDIT_H */ diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index cc12f3449a72..026163f37ba1 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -307,8 +307,7 @@ static inline int security_filter_rule_init(u32 field, u32 op, char *rulestr, } static inline int security_filter_rule_match(u32 secid, u32 field, u32 op, - void *lsmrule, - struct audit_context *actx) + void *lsmrule) { return -EINVAL; } diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 8bc8a1c8cb3f..26fa9d9723f6 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -340,8 +340,7 @@ retry: rc = security_filter_rule_match(osid, rule->lsm[i].type, Audit_equal, - rule->lsm[i].rule, - NULL); + rule->lsm[i].rule); break; case LSM_SUBJ_USER: case LSM_SUBJ_ROLE: @@ -349,8 +348,7 @@ retry: rc = security_filter_rule_match(secid, rule->lsm[i].type, Audit_equal, - rule->lsm[i].rule, - NULL); + rule->lsm[i].rule); default: break; } diff --git a/security/security.c b/security/security.c index f1b8d2587639..5f954b179a8e 100644 --- a/security/security.c +++ b/security/security.c @@ -1783,11 +1783,9 @@ void security_audit_rule_free(void *lsmrule) call_void_hook(audit_rule_free, lsmrule); } -int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule, - struct audit_context *actx) +int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule) { - return call_int_hook(audit_rule_match, 0, secid, field, op, lsmrule, - actx); + return call_int_hook(audit_rule_match, 0, secid, field, op, lsmrule); } #endif /* CONFIG_AUDIT */ diff --git a/security/selinux/include/audit.h b/security/selinux/include/audit.h index 1bdf973433cc..e51a81ffb8c9 100644 --- a/security/selinux/include/audit.h +++ b/security/selinux/include/audit.h @@ -46,13 +46,11 @@ void selinux_audit_rule_free(void *rule); * @field: the field this rule refers to * @op: the operater the rule uses * @rule: pointer to the audit rule to check against - * @actx: the audit context (can be NULL) associated with the check * * Returns 1 if the context id matches the rule, 0 if it does not, and * -errno on failure. */ -int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *rule, - struct audit_context *actx); +int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *rule); /** * selinux_audit_rule_known - check to see if rule contains selinux fields. diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index dd44126c8d14..0b7e33f6aa59 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -3376,8 +3376,7 @@ int selinux_audit_rule_known(struct audit_krule *rule) return 0; } -int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule, - struct audit_context *actx) +int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) { struct selinux_state *state = &selinux_state; struct context *ctxt; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 430d4f35e55c..403513df42fc 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4393,13 +4393,11 @@ static int smack_audit_rule_known(struct audit_krule *krule) * @field: audit rule flags given from user-space * @op: required testing operator * @vrule: smack internal rule presentation - * @actx: audit context associated with the check * * The core Audit hook. It's used to take the decision of * whether to audit or not to audit a given object. */ -static int smack_audit_rule_match(u32 secid, u32 field, u32 op, void *vrule, - struct audit_context *actx) +static int smack_audit_rule_match(u32 secid, u32 field, u32 op, void *vrule) { struct smack_known *skp; char *rule = vrule; -- cgit v1.2.3 From a0ce2f0aa6ad97c3d4927bf2ca54bcebdf062d55 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Wed, 23 Jan 2019 15:19:17 +0100 Subject: splice: don't merge into linked buffers Before this patch, it was possible for two pipes to affect each other after data had been transferred between them with tee(): ============ $ cat tee_test.c int main(void) { int pipe_a[2]; if (pipe(pipe_a)) err(1, "pipe"); int pipe_b[2]; if (pipe(pipe_b)) err(1, "pipe"); if (write(pipe_a[1], "abcd", 4) != 4) err(1, "write"); if (tee(pipe_a[0], pipe_b[1], 2, 0) != 2) err(1, "tee"); if (write(pipe_b[1], "xx", 2) != 2) err(1, "write"); char buf[5]; if (read(pipe_a[0], buf, 4) != 4) err(1, "read"); buf[4] = 0; printf("got back: '%s'\n", buf); } $ gcc -o tee_test tee_test.c $ ./tee_test got back: 'abxx' $ ============ As suggested by Al Viro, fix it by creating a separate type for non-mergeable pipe buffers, then changing the types of buffers in splice_pipe_to_pipe() and link_pipe(). Cc: Fixes: 7c77f0b3f920 ("splice: implement pipe to pipe splicing") Fixes: 70524490ee2e ("[PATCH] splice: add support for sys_tee()") Suggested-by: Al Viro Signed-off-by: Jann Horn Signed-off-by: Al Viro --- fs/pipe.c | 14 ++++++++++++++ fs/splice.c | 4 ++++ include/linux/pipe_fs_i.h | 1 + 3 files changed, 19 insertions(+) (limited to 'include') diff --git a/fs/pipe.c b/fs/pipe.c index bdc5d3c0977d..c51750ed4011 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -234,6 +234,14 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = { .get = generic_pipe_buf_get, }; +static const struct pipe_buf_operations anon_pipe_buf_nomerge_ops = { + .can_merge = 0, + .confirm = generic_pipe_buf_confirm, + .release = anon_pipe_buf_release, + .steal = anon_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + static const struct pipe_buf_operations packet_pipe_buf_ops = { .can_merge = 0, .confirm = generic_pipe_buf_confirm, @@ -242,6 +250,12 @@ static const struct pipe_buf_operations packet_pipe_buf_ops = { .get = generic_pipe_buf_get, }; +void pipe_buf_mark_unmergeable(struct pipe_buffer *buf) +{ + if (buf->ops == &anon_pipe_buf_ops) + buf->ops = &anon_pipe_buf_nomerge_ops; +} + static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { diff --git a/fs/splice.c b/fs/splice.c index de2ede048473..90c29675d573 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1597,6 +1597,8 @@ retry: */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; + pipe_buf_mark_unmergeable(obuf); + obuf->len = len; opipe->nrbufs++; ibuf->offset += obuf->len; @@ -1671,6 +1673,8 @@ static int link_pipe(struct pipe_inode_info *ipipe, */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; + pipe_buf_mark_unmergeable(obuf); + if (obuf->len > len) obuf->len = len; diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 5a3bb3b7c9ad..3ecd7ea212ae 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -182,6 +182,7 @@ void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); +void pipe_buf_mark_unmergeable(struct pipe_buffer *buf); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -- cgit v1.2.3 From 01e7187b41191376cee8bea8de9f907b001e87b4 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Wed, 23 Jan 2019 15:19:18 +0100 Subject: pipe: stop using ->can_merge Al Viro pointed out that since there is only one pipe buffer type to which new data can be appended, it isn't necessary to have a ->can_merge field in struct pipe_buf_operations, we can just check for a magic type. Suggested-by: Al Viro Signed-off-by: Jann Horn Signed-off-by: Al Viro --- fs/pipe.c | 20 ++++++++++++++++---- fs/splice.c | 4 ---- include/linux/pipe_fs_i.h | 7 ------- kernel/relay.c | 1 - kernel/trace/trace.c | 2 -- net/smc/smc_rx.c | 1 - 6 files changed, 16 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/fs/pipe.c b/fs/pipe.c index c51750ed4011..0ff09b490ddf 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -226,8 +226,8 @@ void generic_pipe_buf_release(struct pipe_inode_info *pipe, } EXPORT_SYMBOL(generic_pipe_buf_release); +/* New data written to a pipe may be appended to a buffer with this type. */ static const struct pipe_buf_operations anon_pipe_buf_ops = { - .can_merge = 1, .confirm = generic_pipe_buf_confirm, .release = anon_pipe_buf_release, .steal = anon_pipe_buf_steal, @@ -235,7 +235,6 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = { }; static const struct pipe_buf_operations anon_pipe_buf_nomerge_ops = { - .can_merge = 0, .confirm = generic_pipe_buf_confirm, .release = anon_pipe_buf_release, .steal = anon_pipe_buf_steal, @@ -243,19 +242,32 @@ static const struct pipe_buf_operations anon_pipe_buf_nomerge_ops = { }; static const struct pipe_buf_operations packet_pipe_buf_ops = { - .can_merge = 0, .confirm = generic_pipe_buf_confirm, .release = anon_pipe_buf_release, .steal = anon_pipe_buf_steal, .get = generic_pipe_buf_get, }; +/** + * pipe_buf_mark_unmergeable - mark a &struct pipe_buffer as unmergeable + * @buf: the buffer to mark + * + * Description: + * This function ensures that no future writes will be merged into the + * given &struct pipe_buffer. This is necessary when multiple pipe buffers + * share the same backing page. + */ void pipe_buf_mark_unmergeable(struct pipe_buffer *buf) { if (buf->ops == &anon_pipe_buf_ops) buf->ops = &anon_pipe_buf_nomerge_ops; } +static bool pipe_buf_can_merge(struct pipe_buffer *buf) +{ + return buf->ops == &anon_pipe_buf_ops; +} + static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { @@ -393,7 +405,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) struct pipe_buffer *buf = pipe->bufs + lastbuf; int offset = buf->offset + buf->len; - if (buf->ops->can_merge && offset + chars <= PAGE_SIZE) { + if (pipe_buf_can_merge(buf) && offset + chars <= PAGE_SIZE) { ret = pipe_buf_confirm(pipe, buf); if (ret) goto out; diff --git a/fs/splice.c b/fs/splice.c index 90c29675d573..fc71e9733f7a 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -138,7 +138,6 @@ error: } const struct pipe_buf_operations page_cache_pipe_buf_ops = { - .can_merge = 0, .confirm = page_cache_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .steal = page_cache_pipe_buf_steal, @@ -156,7 +155,6 @@ static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe, } static const struct pipe_buf_operations user_page_pipe_buf_ops = { - .can_merge = 0, .confirm = generic_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .steal = user_page_pipe_buf_steal, @@ -326,7 +324,6 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, EXPORT_SYMBOL(generic_file_splice_read); const struct pipe_buf_operations default_pipe_buf_ops = { - .can_merge = 0, .confirm = generic_pipe_buf_confirm, .release = generic_pipe_buf_release, .steal = generic_pipe_buf_steal, @@ -341,7 +338,6 @@ static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, /* Pipe buffer operations for a socket and similar. */ const struct pipe_buf_operations nosteal_pipe_buf_ops = { - .can_merge = 0, .confirm = generic_pipe_buf_confirm, .release = generic_pipe_buf_release, .steal = generic_pipe_buf_nosteal, diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 3ecd7ea212ae..787d224ff43e 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -73,13 +73,6 @@ struct pipe_inode_info { * in fs/pipe.c for the pipe and generic variants of these hooks. */ struct pipe_buf_operations { - /* - * This is set to 1, if the generic pipe read/write may coalesce - * data into an existing buffer. If this is set to 0, a new pipe - * page segment is always used for new data. - */ - int can_merge; - /* * ->confirm() verifies that the data in the pipe buffer is there * and that the contents are good. If the pages in the pipe belong diff --git a/kernel/relay.c b/kernel/relay.c index 04f248644e06..db3e419c25a6 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1175,7 +1175,6 @@ static void relay_pipe_buf_release(struct pipe_inode_info *pipe, } static const struct pipe_buf_operations relay_pipe_buf_ops = { - .can_merge = 0, .confirm = generic_pipe_buf_confirm, .release = relay_pipe_buf_release, .steal = generic_pipe_buf_steal, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c521b7347482..f380139e972c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5823,7 +5823,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd, } static const struct pipe_buf_operations tracing_pipe_buf_ops = { - .can_merge = 0, .confirm = generic_pipe_buf_confirm, .release = generic_pipe_buf_release, .steal = generic_pipe_buf_steal, @@ -6843,7 +6842,6 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { - .can_merge = 0, .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, .steal = generic_pipe_buf_steal, diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index bbcf0fe4ae10..413a6abf227e 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -136,7 +136,6 @@ static int smc_rx_pipe_buf_nosteal(struct pipe_inode_info *pipe, } static const struct pipe_buf_operations smc_pipe_ops = { - .can_merge = 0, .confirm = generic_pipe_buf_confirm, .release = smc_rx_pipe_buf_release, .steal = smc_rx_pipe_buf_nosteal, -- cgit v1.2.3 From 4bc59c2f7e306775f3d2e1bbafaa854dd1e09335 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 12 Dec 2018 18:33:56 +0100 Subject: mfd / platform: cros_ec: Use devm_mfd_add_devices Use devm_mfd_add_devices() for adding cros-ec core MFD child devices. This reduces the need of remove callback from platform/chrome for removing the MFD child devices. Signed-off-by: Enric Balletbo i Serra Reviewed-by: Guenter Roeck Signed-off-by: Lee Jones --- drivers/mfd/cros_ec.c | 14 +++----------- drivers/platform/chrome/cros_ec_i2c.c | 10 ---------- drivers/platform/chrome/cros_ec_lpc.c | 4 ---- drivers/platform/chrome/cros_ec_spi.c | 11 ----------- include/linux/mfd/cros_ec.h | 10 ---------- 5 files changed, 3 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/drivers/mfd/cros_ec.c b/drivers/mfd/cros_ec.c index fe6f83766144..6acfe036d522 100644 --- a/drivers/mfd/cros_ec.c +++ b/drivers/mfd/cros_ec.c @@ -129,8 +129,8 @@ int cros_ec_register(struct cros_ec_device *ec_dev) } } - err = mfd_add_devices(ec_dev->dev, PLATFORM_DEVID_AUTO, &ec_cell, 1, - NULL, ec_dev->irq, NULL); + err = devm_mfd_add_devices(ec_dev->dev, PLATFORM_DEVID_AUTO, &ec_cell, + 1, NULL, ec_dev->irq, NULL); if (err) { dev_err(dev, "Failed to register Embedded Controller subdevice %d\n", @@ -147,7 +147,7 @@ int cros_ec_register(struct cros_ec_device *ec_dev) * - the EC is responsive at init time (it is not true for a * sensor hub. */ - err = mfd_add_devices(ec_dev->dev, PLATFORM_DEVID_AUTO, + err = devm_mfd_add_devices(ec_dev->dev, PLATFORM_DEVID_AUTO, &ec_pd_cell, 1, NULL, ec_dev->irq, NULL); if (err) { dev_err(dev, @@ -181,14 +181,6 @@ int cros_ec_register(struct cros_ec_device *ec_dev) } EXPORT_SYMBOL(cros_ec_register); -int cros_ec_remove(struct cros_ec_device *ec_dev) -{ - mfd_remove_devices(ec_dev->dev); - - return 0; -} -EXPORT_SYMBOL(cros_ec_remove); - #ifdef CONFIG_PM_SLEEP int cros_ec_suspend(struct cros_ec_device *ec_dev) { diff --git a/drivers/platform/chrome/cros_ec_i2c.c b/drivers/platform/chrome/cros_ec_i2c.c index ef9b4763356f..9a009eaa4ada 100644 --- a/drivers/platform/chrome/cros_ec_i2c.c +++ b/drivers/platform/chrome/cros_ec_i2c.c @@ -317,15 +317,6 @@ static int cros_ec_i2c_probe(struct i2c_client *client, return 0; } -static int cros_ec_i2c_remove(struct i2c_client *client) -{ - struct cros_ec_device *ec_dev = i2c_get_clientdata(client); - - cros_ec_remove(ec_dev); - - return 0; -} - #ifdef CONFIG_PM_SLEEP static int cros_ec_i2c_suspend(struct device *dev) { @@ -376,7 +367,6 @@ static struct i2c_driver cros_ec_driver = { .pm = &cros_ec_i2c_pm_ops, }, .probe = cros_ec_i2c_probe, - .remove = cros_ec_i2c_remove, .id_table = cros_ec_i2c_id, }; diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index e1b75775cd4a..14684a56e40f 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -327,7 +327,6 @@ static int cros_ec_lpc_probe(struct platform_device *pdev) static int cros_ec_lpc_remove(struct platform_device *pdev) { - struct cros_ec_device *ec_dev; struct acpi_device *adev; adev = ACPI_COMPANION(&pdev->dev); @@ -335,9 +334,6 @@ static int cros_ec_lpc_remove(struct platform_device *pdev) acpi_remove_notify_handler(adev->handle, ACPI_ALL_NOTIFY, cros_ec_lpc_acpi_notify); - ec_dev = platform_get_drvdata(pdev); - cros_ec_remove(ec_dev); - return 0; } diff --git a/drivers/platform/chrome/cros_ec_spi.c b/drivers/platform/chrome/cros_ec_spi.c index 2060d1483043..6cfbc2835beb 100644 --- a/drivers/platform/chrome/cros_ec_spi.c +++ b/drivers/platform/chrome/cros_ec_spi.c @@ -685,16 +685,6 @@ static int cros_ec_spi_probe(struct spi_device *spi) return 0; } -static int cros_ec_spi_remove(struct spi_device *spi) -{ - struct cros_ec_device *ec_dev; - - ec_dev = spi_get_drvdata(spi); - cros_ec_remove(ec_dev); - - return 0; -} - #ifdef CONFIG_PM_SLEEP static int cros_ec_spi_suspend(struct device *dev) { @@ -733,7 +723,6 @@ static struct spi_driver cros_ec_driver_spi = { .pm = &cros_ec_spi_pm_ops, }, .probe = cros_ec_spi_probe, - .remove = cros_ec_spi_remove, .id_table = cros_ec_spi_id, }; diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index de8b588c8776..977ebaa78e99 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -281,16 +281,6 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -/** - * cros_ec_remove() - Remove a ChromeOS EC. - * @ec_dev: Device to register. - * - * Call this to deregister a ChromeOS EC, then clean up any private data. - * - * Return: 0 on success or negative error code. - */ -int cros_ec_remove(struct cros_ec_device *ec_dev); - /** * cros_ec_register() - Register a new ChromeOS EC, using the provided info. * @ec_dev: Device to register. -- cgit v1.2.3 From ecf8a6cd949ef236ce435ae488ceb6b3354e677e Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 12 Dec 2018 18:33:57 +0100 Subject: mfd / platform: cros_ec: Move lightbar attributes to its own driver The entire way how cros sysfs attibutes are created is broken. cros_ec_lightbar should be its own driver and its attributes should be associated with a lightbar driver not the mfd driver. In order to retain the path, the lightbar attributes are attached to the cros_class. The patch also adds the sysfs documentation. Signed-off-by: Enric Balletbo i Serra Reviewed-by: Guenter Roeck Signed-off-by: Lee Jones --- .../sysfs-class-chromeos-driver-cros-ec-lightbar | 74 +++++++++++++++++ drivers/mfd/cros_ec_dev.c | 24 +++--- drivers/mfd/cros_ec_dev.h | 6 -- drivers/platform/chrome/Kconfig | 11 +++ drivers/platform/chrome/Makefile | 3 +- drivers/platform/chrome/cros_ec_lightbar.c | 95 +++++++++++++++++----- include/linux/mfd/cros_ec.h | 1 - 7 files changed, 173 insertions(+), 41 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-class-chromeos-driver-cros-ec-lightbar (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-class-chromeos-driver-cros-ec-lightbar b/Documentation/ABI/testing/sysfs-class-chromeos-driver-cros-ec-lightbar new file mode 100644 index 000000000000..57a037791403 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-chromeos-driver-cros-ec-lightbar @@ -0,0 +1,74 @@ +What: /sys/class/chromeos//lightbar/brightness +Date: August 2015 +KernelVersion: 4.2 +Description: + Writing to this file adjusts the overall brightness of + the lightbar, separate from any color intensity. The + valid range is 0 (off) to 255 (maximum brightness). + +What: /sys/class/chromeos//lightbar/interval_msec +Date: August 2015 +KernelVersion: 4.2 +Description: + The lightbar is controlled by an embedded controller (EC), + which also manages the keyboard, battery charging, fans, + and other system hardware. To prevent unprivileged users + from interfering with the other EC functions, the rate at + which the lightbar control files can be read or written is + limited. + + Reading this file will return the number of milliseconds + that must elapse between accessing any of the lightbar + functions through this interface. Going faster will simply + block until the necessary interval has lapsed. The interval + applies uniformly to all accesses of any kind by any user. + +What: /sys/class/chromeos//lightbar/led_rgb +Date: August 2015 +KernelVersion: 4.2 +Description: + This allows you to control each LED segment. If the + lightbar is already running one of the automatic + sequences, you probably won’t see anything change because + your color setting will be almost immediately replaced. + To get useful results, you should stop the lightbar + sequence first. + + The values written to this file are sets of four integers, + indicating LED, RED, GREEN, BLUE. The LED number is 0 to 3 + to select a single segment, or 4 to set all four segments + to the same value at once. The RED, GREEN, and BLUE + numbers should be in the range 0 (off) to 255 (maximum). + You can update more than one segment at a time by writing + more than one set of four integers. + +What: /sys/class/chromeos//lightbar/program +Date: August 2015 +KernelVersion: 4.2 +Description: + This allows you to upload and run custom lightbar sequences. + +What: /sys/class/chromeos//lightbar/sequence +Date: August 2015 +KernelVersion: 4.2 +Description: + The Pixel lightbar has a number of built-in sequences + that it displays under various conditions, such as at + power on, shut down, or while running. Reading from this + file displays the current sequence that the lightbar is + displaying. Writing to this file allows you to change the + sequence. + +What: /sys/class/chromeos//lightbar/userspace_control +Date: August 2015 +KernelVersion: 4.2 +Description: + This allows you to take the control of the lightbar. This + prevents the kernel from going through its normal + sequences. + +What: /sys/class/chromeos//lightbar/version +Date: August 2015 +KernelVersion: 4.2 +Description: + Show the information about the lightbar version. diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index 2d0fee488c5a..b227718e0ec2 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -36,7 +36,6 @@ static int ec_major; static const struct attribute_group *cros_ec_groups[] = { &cros_ec_attr_group, - &cros_ec_lightbar_attr_group, &cros_ec_vbc_attr_group, NULL, }; @@ -395,6 +394,10 @@ static const struct mfd_cell cros_usbpd_charger_cells[] = { { .name = "cros-usbpd-charger" } }; +static const struct mfd_cell cros_ec_platform_cells[] = { + { .name = "cros-ec-lightbar" }, +}; + static int ec_device_probe(struct platform_device *pdev) { int retval = -ENOMEM; @@ -470,9 +473,6 @@ static int ec_device_probe(struct platform_device *pdev) retval); } - /* Take control of the lightbar from the EC. */ - lb_manual_suspend_ctrl(ec, 1); - /* We can now add the sysfs class, we know which parameter to show */ retval = cdev_device_add(&ec->cdev, &ec->class_dev); if (retval) { @@ -480,6 +480,15 @@ static int ec_device_probe(struct platform_device *pdev) goto failed; } + retval = mfd_add_devices(ec->dev, PLATFORM_DEVID_AUTO, + cros_ec_platform_cells, + ARRAY_SIZE(cros_ec_platform_cells), + NULL, 0, NULL); + if (retval) + dev_warn(ec->dev, + "failed to add cros-ec platform devices: %d\n", + retval); + if (cros_ec_debugfs_init(ec)) dev_warn(dev, "failed to create debugfs directory\n"); @@ -494,9 +503,6 @@ static int ec_device_remove(struct platform_device *pdev) { struct cros_ec_dev *ec = dev_get_drvdata(&pdev->dev); - /* Let the EC take over the lightbar again. */ - lb_manual_suspend_ctrl(ec, 0); - cros_ec_debugfs_remove(ec); mfd_remove_devices(ec->dev); @@ -525,8 +531,6 @@ static __maybe_unused int ec_device_suspend(struct device *dev) cros_ec_debugfs_suspend(ec); - lb_suspend(ec); - return 0; } @@ -536,8 +540,6 @@ static __maybe_unused int ec_device_resume(struct device *dev) cros_ec_debugfs_resume(ec); - lb_resume(ec); - return 0; } diff --git a/drivers/mfd/cros_ec_dev.h b/drivers/mfd/cros_ec_dev.h index 978d836a0248..ec750433455a 100644 --- a/drivers/mfd/cros_ec_dev.h +++ b/drivers/mfd/cros_ec_dev.h @@ -44,10 +44,4 @@ struct cros_ec_readmem { #define CROS_EC_DEV_IOCXCMD _IOWR(CROS_EC_DEV_IOC, 0, struct cros_ec_command) #define CROS_EC_DEV_IOCRDMEM _IOWR(CROS_EC_DEV_IOC, 1, struct cros_ec_readmem) -/* Lightbar utilities */ -extern bool ec_has_lightbar(struct cros_ec_dev *ec); -extern int lb_manual_suspend_ctrl(struct cros_ec_dev *ec, uint8_t enable); -extern int lb_suspend(struct cros_ec_dev *ec); -extern int lb_resume(struct cros_ec_dev *ec); - #endif /* _CROS_EC_DEV_H_ */ diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index 16b1615958aa..6c05752a3334 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -111,4 +111,15 @@ config CROS_KBD_LED_BACKLIGHT To compile this driver as a module, choose M here: the module will be called cros_kbd_led_backlight. +config CROS_EC_LIGHTBAR + tristate "Chromebook Pixel's lightbar support" + depends on MFD_CROS_EC_CHARDEV + default MFD_CROS_EC_CHARDEV + help + This option exposes the Chromebook Pixel's lightbar to + userspace. + + To compile this driver as a module, choose M here: the + module will be called cros_ec_lightbar. + endif # CHROMEOS_PLATFORMS diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index cd591bf872bb..3c29a4b405d5 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -3,7 +3,7 @@ obj-$(CONFIG_CHROMEOS_LAPTOP) += chromeos_laptop.o obj-$(CONFIG_CHROMEOS_PSTORE) += chromeos_pstore.o obj-$(CONFIG_CHROMEOS_TBMC) += chromeos_tbmc.o -cros_ec_ctl-objs := cros_ec_sysfs.o cros_ec_lightbar.o \ +cros_ec_ctl-objs := cros_ec_sysfs.o \ cros_ec_vbc.o cros_ec_debugfs.o obj-$(CONFIG_CROS_EC_CTL) += cros_ec_ctl.o obj-$(CONFIG_CROS_EC_I2C) += cros_ec_i2c.o @@ -13,3 +13,4 @@ cros_ec_lpcs-$(CONFIG_CROS_EC_LPC_MEC) += cros_ec_lpc_mec.o obj-$(CONFIG_CROS_EC_LPC) += cros_ec_lpcs.o obj-$(CONFIG_CROS_EC_PROTO) += cros_ec_proto.o obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT) += cros_kbd_led_backlight.o +obj-$(CONFIG_CROS_EC_LIGHTBAR) += cros_ec_lightbar.o diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c index 68193bb53383..80eed6317570 100644 --- a/drivers/platform/chrome/cros_ec_lightbar.c +++ b/drivers/platform/chrome/cros_ec_lightbar.c @@ -33,6 +33,8 @@ #include #include +#define DRV_NAME "cros-ec-lightbar" + /* Rate-limit the lightbar interface to prevent DoS. */ static unsigned long lb_interval_jiffies = 50 * HZ / 1000; @@ -373,7 +375,7 @@ error: return ret; } -int lb_manual_suspend_ctrl(struct cros_ec_dev *ec, uint8_t enable) +static int lb_manual_suspend_ctrl(struct cros_ec_dev *ec, uint8_t enable) { struct ec_params_lightbar *param; struct cros_ec_command *msg; @@ -408,25 +410,6 @@ error: return ret; } -EXPORT_SYMBOL(lb_manual_suspend_ctrl); - -int lb_suspend(struct cros_ec_dev *ec) -{ - if (userspace_control || ec != ec_with_lightbar) - return 0; - - return lb_send_empty_cmd(ec, LIGHTBAR_CMD_SUSPEND); -} -EXPORT_SYMBOL(lb_suspend); - -int lb_resume(struct cros_ec_dev *ec) -{ - if (userspace_control || ec != ec_with_lightbar) - return 0; - - return lb_send_empty_cmd(ec, LIGHTBAR_CMD_RESUME); -} -EXPORT_SYMBOL(lb_resume); static ssize_t sequence_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -584,7 +567,7 @@ static struct attribute *__lb_cmds_attrs[] = { NULL, }; -bool ec_has_lightbar(struct cros_ec_dev *ec) +static bool ec_has_lightbar(struct cros_ec_dev *ec) { return !!get_lightbar_version(ec, NULL, NULL); } @@ -616,4 +599,72 @@ struct attribute_group cros_ec_lightbar_attr_group = { .attrs = __lb_cmds_attrs, .is_visible = cros_ec_lightbar_attrs_are_visible, }; -EXPORT_SYMBOL(cros_ec_lightbar_attr_group); + +static int cros_ec_lightbar_probe(struct platform_device *pd) +{ + struct cros_ec_dev *ec_dev = dev_get_drvdata(pd->dev.parent); + struct device *dev = &pd->dev; + int ret; + + /* Take control of the lightbar from the EC. */ + lb_manual_suspend_ctrl(ec_dev, 1); + + ret = sysfs_create_group(&ec_dev->class_dev.kobj, + &cros_ec_lightbar_attr_group); + if (ret < 0) + dev_err(dev, "failed to create %s attributes. err=%d\n", + cros_ec_lightbar_attr_group.name, ret); + + return ret; +} + +static int cros_ec_lightbar_remove(struct platform_device *pd) +{ + struct cros_ec_dev *ec_dev = dev_get_drvdata(pd->dev.parent); + + sysfs_remove_group(&ec_dev->class_dev.kobj, + &cros_ec_lightbar_attr_group); + + /* Let the EC take over the lightbar again. */ + lb_manual_suspend_ctrl(ec_dev, 0); + + return 0; +} + +static int __maybe_unused cros_ec_lightbar_resume(struct device *dev) +{ + struct cros_ec_dev *ec_dev = dev_get_drvdata(dev); + + if (userspace_control || ec_dev != ec_with_lightbar) + return 0; + + return lb_send_empty_cmd(ec_dev, LIGHTBAR_CMD_RESUME); +} + +static int __maybe_unused cros_ec_lightbar_suspend(struct device *dev) +{ + struct cros_ec_dev *ec_dev = dev_get_drvdata(dev); + + if (userspace_control || ec_dev != ec_with_lightbar) + return 0; + + return lb_send_empty_cmd(ec_dev, LIGHTBAR_CMD_SUSPEND); +} + +static SIMPLE_DEV_PM_OPS(cros_ec_lightbar_pm_ops, + cros_ec_lightbar_suspend, cros_ec_lightbar_resume); + +static struct platform_driver cros_ec_lightbar_driver = { + .driver = { + .name = DRV_NAME, + .pm = &cros_ec_lightbar_pm_ops, + }, + .probe = cros_ec_lightbar_probe, + .remove = cros_ec_lightbar_remove, +}; + +module_platform_driver(cros_ec_lightbar_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Expose the Chromebook Pixel's lightbar to userspace"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 977ebaa78e99..1e9b569564ea 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -327,7 +327,6 @@ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); /* sysfs stuff */ extern struct attribute_group cros_ec_attr_group; -extern struct attribute_group cros_ec_lightbar_attr_group; extern struct attribute_group cros_ec_vbc_attr_group; /* debugfs stuff */ -- cgit v1.2.3 From acb9900f9e8074858738f48bee9a705138961258 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 12 Dec 2018 18:33:58 +0100 Subject: mfd / platform: cros_ec: Move vbc attributes to its own driver The entire way how cros sysfs attibutes are created is broken. cros_ec_vbc should be its own driver and its attributes should be associated with a vbc driver not the mfd driver. In order to retain the path, the vbc attributes are attached to the cros_class. The patch also adds the sysfs documentation. Signed-off-by: Enric Balletbo i Serra Reviewed-by: Guenter Roeck Signed-off-by: Lee Jones --- .../sysfs-class-chromeos-driver-cros-ec-vbc | 6 +++ drivers/mfd/cros_ec_dev.c | 2 +- drivers/platform/chrome/Kconfig | 11 ++++++ drivers/platform/chrome/Makefile | 3 +- drivers/platform/chrome/cros_ec_vbc.c | 43 +++++++++++++++++++++- include/linux/mfd/cros_ec.h | 1 - 6 files changed, 62 insertions(+), 4 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-class-chromeos-driver-cros-ec-vbc (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-class-chromeos-driver-cros-ec-vbc b/Documentation/ABI/testing/sysfs-class-chromeos-driver-cros-ec-vbc new file mode 100644 index 000000000000..38c5aaaaa89a --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-chromeos-driver-cros-ec-vbc @@ -0,0 +1,6 @@ +What: /sys/class/chromeos//vbc/vboot_context +Date: October 2015 +KernelVersion: 4.4 +Description: + Read/write the verified boot context data included on a + small nvram space on some EC implementations. diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index b227718e0ec2..40c98808fa1c 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -36,7 +36,6 @@ static int ec_major; static const struct attribute_group *cros_ec_groups[] = { &cros_ec_attr_group, - &cros_ec_vbc_attr_group, NULL, }; @@ -396,6 +395,7 @@ static const struct mfd_cell cros_usbpd_charger_cells[] = { static const struct mfd_cell cros_ec_platform_cells[] = { { .name = "cros-ec-lightbar" }, + { .name = "cros-ec-vbc" }, }; static int ec_device_probe(struct platform_device *pdev) diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index 6c05752a3334..1e9dc9626e84 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -122,4 +122,15 @@ config CROS_EC_LIGHTBAR To compile this driver as a module, choose M here: the module will be called cros_ec_lightbar. +config CROS_EC_VBC + tristate "ChromeOS EC vboot context support" + depends on MFD_CROS_EC_CHARDEV && OF + default MFD_CROS_EC_CHARDEV + help + This option exposes the ChromeOS EC vboot context nvram to + userspace. + + To compile this driver as a module, choose M here: the + module will be called cros_ec_vbc. + endif # CHROMEOS_PLATFORMS diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index 3c29a4b405d5..4081b7179df7 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_CHROMEOS_LAPTOP) += chromeos_laptop.o obj-$(CONFIG_CHROMEOS_PSTORE) += chromeos_pstore.o obj-$(CONFIG_CHROMEOS_TBMC) += chromeos_tbmc.o cros_ec_ctl-objs := cros_ec_sysfs.o \ - cros_ec_vbc.o cros_ec_debugfs.o + cros_ec_debugfs.o obj-$(CONFIG_CROS_EC_CTL) += cros_ec_ctl.o obj-$(CONFIG_CROS_EC_I2C) += cros_ec_i2c.o obj-$(CONFIG_CROS_EC_SPI) += cros_ec_spi.o @@ -14,3 +14,4 @@ obj-$(CONFIG_CROS_EC_LPC) += cros_ec_lpcs.o obj-$(CONFIG_CROS_EC_PROTO) += cros_ec_proto.o obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT) += cros_kbd_led_backlight.o obj-$(CONFIG_CROS_EC_LIGHTBAR) += cros_ec_lightbar.o +obj-$(CONFIG_CROS_EC_VBC) += cros_ec_vbc.o diff --git a/drivers/platform/chrome/cros_ec_vbc.c b/drivers/platform/chrome/cros_ec_vbc.c index 5356f26bc022..da3bbf05e86f 100644 --- a/drivers/platform/chrome/cros_ec_vbc.c +++ b/drivers/platform/chrome/cros_ec_vbc.c @@ -22,8 +22,11 @@ #include #include #include +#include #include +#define DRV_NAME "cros-ec-vbc" + static ssize_t vboot_context_read(struct file *filp, struct kobject *kobj, struct bin_attribute *att, char *buf, loff_t pos, size_t count) @@ -132,4 +135,42 @@ struct attribute_group cros_ec_vbc_attr_group = { .bin_attrs = cros_ec_vbc_bin_attrs, .is_bin_visible = cros_ec_vbc_is_visible, }; -EXPORT_SYMBOL(cros_ec_vbc_attr_group); + +static int cros_ec_vbc_probe(struct platform_device *pd) +{ + struct cros_ec_dev *ec_dev = dev_get_drvdata(pd->dev.parent); + struct device *dev = &pd->dev; + int ret; + + ret = sysfs_create_group(&ec_dev->class_dev.kobj, + &cros_ec_vbc_attr_group); + if (ret < 0) + dev_err(dev, "failed to create %s attributes. err=%d\n", + cros_ec_vbc_attr_group.name, ret); + + return ret; +} + +static int cros_ec_vbc_remove(struct platform_device *pd) +{ + struct cros_ec_dev *ec_dev = dev_get_drvdata(pd->dev.parent); + + sysfs_remove_group(&ec_dev->class_dev.kobj, + &cros_ec_vbc_attr_group); + + return 0; +} + +static struct platform_driver cros_ec_vbc_driver = { + .driver = { + .name = DRV_NAME, + }, + .probe = cros_ec_vbc_probe, + .remove = cros_ec_vbc_remove, +}; + +module_platform_driver(cros_ec_vbc_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Expose the vboot context nvram to userspace"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 1e9b569564ea..fdc3152cca1d 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -327,7 +327,6 @@ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); /* sysfs stuff */ extern struct attribute_group cros_ec_attr_group; -extern struct attribute_group cros_ec_vbc_attr_group; /* debugfs stuff */ int cros_ec_debugfs_init(struct cros_ec_dev *ec); -- cgit v1.2.3 From 6fce0a2cf5a050e8a3326556d7d293e69be303be Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 12 Dec 2018 18:33:59 +0100 Subject: mfd / platform: cros_ec: Move debugfs attributes to its own driver The entire way how cros debugfs attibutes are created is broken. cros_ec_debugfs should be its own driver and its attributes should be associated with a debugfs driver not the mfd driver. Signed-off-by: Enric Balletbo i Serra Reviewed-by: Guenter Roeck Signed-off-by: Lee Jones --- drivers/mfd/cros_ec_dev.c | 41 +------------------- drivers/platform/chrome/Kconfig | 11 ++++++ drivers/platform/chrome/Makefile | 4 +- drivers/platform/chrome/cros_ec_debugfs.c | 62 +++++++++++++++++++++---------- include/linux/mfd/cros_ec.h | 6 --- 5 files changed, 56 insertions(+), 68 deletions(-) (limited to 'include') diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index 40c98808fa1c..9955937b821d 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -394,6 +394,7 @@ static const struct mfd_cell cros_usbpd_charger_cells[] = { }; static const struct mfd_cell cros_ec_platform_cells[] = { + { .name = "cros-ec-debugfs" }, { .name = "cros-ec-lightbar" }, { .name = "cros-ec-vbc" }, }; @@ -489,9 +490,6 @@ static int ec_device_probe(struct platform_device *pdev) "failed to add cros-ec platform devices: %d\n", retval); - if (cros_ec_debugfs_init(ec)) - dev_warn(dev, "failed to create debugfs directory\n"); - return 0; failed: @@ -503,62 +501,25 @@ static int ec_device_remove(struct platform_device *pdev) { struct cros_ec_dev *ec = dev_get_drvdata(&pdev->dev); - cros_ec_debugfs_remove(ec); - mfd_remove_devices(ec->dev); cdev_del(&ec->cdev); device_unregister(&ec->class_dev); return 0; } -static void ec_device_shutdown(struct platform_device *pdev) -{ - struct cros_ec_dev *ec = dev_get_drvdata(&pdev->dev); - - /* Be sure to clear up debugfs delayed works */ - cros_ec_debugfs_remove(ec); -} - static const struct platform_device_id cros_ec_id[] = { { DRV_NAME, 0 }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(platform, cros_ec_id); -static __maybe_unused int ec_device_suspend(struct device *dev) -{ - struct cros_ec_dev *ec = dev_get_drvdata(dev); - - cros_ec_debugfs_suspend(ec); - - return 0; -} - -static __maybe_unused int ec_device_resume(struct device *dev) -{ - struct cros_ec_dev *ec = dev_get_drvdata(dev); - - cros_ec_debugfs_resume(ec); - - return 0; -} - -static const struct dev_pm_ops cros_ec_dev_pm_ops = { -#ifdef CONFIG_PM_SLEEP - .suspend = ec_device_suspend, - .resume = ec_device_resume, -#endif -}; - static struct platform_driver cros_ec_dev_driver = { .driver = { .name = DRV_NAME, - .pm = &cros_ec_dev_pm_ops, }, .id_table = cros_ec_id, .probe = ec_device_probe, .remove = ec_device_remove, - .shutdown = ec_device_shutdown, }; static int __init cros_ec_dev_init(void) diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index 1e9dc9626e84..6cbf5b69d156 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -133,4 +133,15 @@ config CROS_EC_VBC To compile this driver as a module, choose M here: the module will be called cros_ec_vbc. +config CROS_EC_DEBUGFS + tristate "Export ChromeOS EC internals in DebugFS" + depends on MFD_CROS_EC_CHARDEV && DEBUG_FS + default MFD_CROS_EC_CHARDEV + help + This option exposes the ChromeOS EC device internals to + userspace. + + To compile this driver as a module, choose M here: the + module will be called cros_ec_debugfs. + endif # CHROMEOS_PLATFORMS diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index 4081b7179df7..12a5c4d18c17 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -3,8 +3,7 @@ obj-$(CONFIG_CHROMEOS_LAPTOP) += chromeos_laptop.o obj-$(CONFIG_CHROMEOS_PSTORE) += chromeos_pstore.o obj-$(CONFIG_CHROMEOS_TBMC) += chromeos_tbmc.o -cros_ec_ctl-objs := cros_ec_sysfs.o \ - cros_ec_debugfs.o +cros_ec_ctl-objs := cros_ec_sysfs.o obj-$(CONFIG_CROS_EC_CTL) += cros_ec_ctl.o obj-$(CONFIG_CROS_EC_I2C) += cros_ec_i2c.o obj-$(CONFIG_CROS_EC_SPI) += cros_ec_spi.o @@ -15,3 +14,4 @@ obj-$(CONFIG_CROS_EC_PROTO) += cros_ec_proto.o obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT) += cros_kbd_led_backlight.o obj-$(CONFIG_CROS_EC_LIGHTBAR) += cros_ec_lightbar.o obj-$(CONFIG_CROS_EC_VBC) += cros_ec_vbc.o +obj-$(CONFIG_CROS_EC_DEBUGFS) += cros_ec_debugfs.o diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c index c62ee8e610a0..6cacac53dfce 100644 --- a/drivers/platform/chrome/cros_ec_debugfs.c +++ b/drivers/platform/chrome/cros_ec_debugfs.c @@ -23,12 +23,16 @@ #include #include #include +#include #include +#include #include #include #include #include +#define DRV_NAME "cros-ec-debugfs" + #define LOG_SHIFT 14 #define LOG_SIZE (1 << LOG_SHIFT) #define LOG_POLL_SEC 10 @@ -423,8 +427,9 @@ static int cros_ec_create_pdinfo(struct cros_ec_debugfs *debug_info) return 0; } -int cros_ec_debugfs_init(struct cros_ec_dev *ec) +static int cros_ec_debugfs_probe(struct platform_device *pd) { + struct cros_ec_dev *ec = dev_get_drvdata(pd->dev.parent); struct cros_ec_platform *ec_platform = dev_get_platdata(ec->dev); const char *name = ec_platform->ec_name; struct cros_ec_debugfs *debug_info; @@ -453,40 +458,57 @@ int cros_ec_debugfs_init(struct cros_ec_dev *ec) ec->debug_info = debug_info; + dev_set_drvdata(&pd->dev, ec); + return 0; remove_debugfs: debugfs_remove_recursive(debug_info->dir); return ret; } -EXPORT_SYMBOL(cros_ec_debugfs_init); -void cros_ec_debugfs_remove(struct cros_ec_dev *ec) +static int cros_ec_debugfs_remove(struct platform_device *pd) { - if (!ec->debug_info) - return; + struct cros_ec_dev *ec = dev_get_drvdata(pd->dev.parent); debugfs_remove_recursive(ec->debug_info->dir); cros_ec_cleanup_console_log(ec->debug_info); + + return 0; } -EXPORT_SYMBOL(cros_ec_debugfs_remove); -void cros_ec_debugfs_suspend(struct cros_ec_dev *ec) +static int __maybe_unused cros_ec_debugfs_suspend(struct device *dev) { - /* - * cros_ec_debugfs_init() failures are non-fatal; it's also possible - * that we initted things but decided that console log wasn't supported. - * We'll use the same set of checks that cros_ec_debugfs_remove() + - * cros_ec_cleanup_console_log() end up using to handle those cases. - */ - if (ec->debug_info && ec->debug_info->log_buffer.buf) - cancel_delayed_work_sync(&ec->debug_info->log_poll_work); + struct cros_ec_dev *ec = dev_get_drvdata(dev); + + cancel_delayed_work_sync(&ec->debug_info->log_poll_work); + + return 0; } -EXPORT_SYMBOL(cros_ec_debugfs_suspend); -void cros_ec_debugfs_resume(struct cros_ec_dev *ec) +static int __maybe_unused cros_ec_debugfs_resume(struct device *dev) { - if (ec->debug_info && ec->debug_info->log_buffer.buf) - schedule_delayed_work(&ec->debug_info->log_poll_work, 0); + struct cros_ec_dev *ec = dev_get_drvdata(dev); + + schedule_delayed_work(&ec->debug_info->log_poll_work, 0); + + return 0; } -EXPORT_SYMBOL(cros_ec_debugfs_resume); + +static SIMPLE_DEV_PM_OPS(cros_ec_debugfs_pm_ops, + cros_ec_debugfs_suspend, cros_ec_debugfs_resume); + +static struct platform_driver cros_ec_debugfs_driver = { + .driver = { + .name = DRV_NAME, + .pm = &cros_ec_debugfs_pm_ops, + }, + .probe = cros_ec_debugfs_probe, + .remove = cros_ec_debugfs_remove, +}; + +module_platform_driver(cros_ec_debugfs_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Debug logs for ChromeOS EC"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index fdc3152cca1d..e50860d190db 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -328,10 +328,4 @@ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); /* sysfs stuff */ extern struct attribute_group cros_ec_attr_group; -/* debugfs stuff */ -int cros_ec_debugfs_init(struct cros_ec_dev *ec); -void cros_ec_debugfs_remove(struct cros_ec_dev *ec); -void cros_ec_debugfs_suspend(struct cros_ec_dev *ec); -void cros_ec_debugfs_resume(struct cros_ec_dev *ec); - #endif /* __LINUX_MFD_CROS_EC_H */ -- cgit v1.2.3 From 6fd7f2bbd4422e7635bc771cd1ec440378158cb1 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 12 Dec 2018 18:34:00 +0100 Subject: mfd / platform: cros_ec: Move device sysfs attributes to its own driver The entire way how cros debugfs attibutes are created is broken. cros_ec_sysfs should be its own driver and its attributes should be associated with the sysfs driver not the mfd driver. The patch also adds the sysfs documentation. Signed-off-by: Enric Balletbo i Serra Reviewed-by: Guenter Roeck Signed-off-by: Lee Jones --- Documentation/ABI/testing/sysfs-class-chromeos | 32 +++++++++++++++++++++++ drivers/mfd/Kconfig | 1 - drivers/mfd/cros_ec_dev.c | 7 +---- drivers/platform/chrome/Kconfig | 14 +++++++--- drivers/platform/chrome/Makefile | 3 +-- drivers/platform/chrome/cros_ec_lightbar.c | 2 +- drivers/platform/chrome/cros_ec_sysfs.c | 36 +++++++++++++++++++++++++- include/linux/mfd/cros_ec.h | 3 --- 8 files changed, 81 insertions(+), 17 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-class-chromeos (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-class-chromeos b/Documentation/ABI/testing/sysfs-class-chromeos new file mode 100644 index 000000000000..5819699d66ec --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-chromeos @@ -0,0 +1,32 @@ +What: /sys/class/chromeos//flashinfo +Date: August 2015 +KernelVersion: 4.2 +Description: + Show the EC flash information. + +What: /sys/class/chromeos//kb_wake_angle +Date: March 2018 +KernelVersion: 4.17 +Description: + Control the keyboard wake lid angle. Values are between + 0 and 360. This file will also show the keyboard wake lid + angle by querying the hardware. + +What: /sys/class/chromeos//reboot +Date: August 2015 +KernelVersion: 4.2 +Description: + Tell the EC to reboot in various ways. Options are: + "cancel": Cancel a pending reboot. + "ro": Jump to RO without rebooting. + "rw": Jump to RW without rebooting. + "cold": Cold reboot. + "disable-jump": Disable jump until next reboot. + "hibernate": Hibernate the EC. + "at-shutdown": Reboot after an AP shutdown. + +What: /sys/class/chromeos//version +Date: August 2015 +KernelVersion: 4.2 +Description: + Show the information about the EC software and hardware. diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index f461460a2aeb..2acc105e43cc 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -215,7 +215,6 @@ config MFD_CROS_EC config MFD_CROS_EC_CHARDEV tristate "Chrome OS Embedded Controller userspace device interface" depends on MFD_CROS_EC - select CROS_EC_CTL ---help--- This driver adds support to talk with the ChromeOS EC from userspace. diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index 9955937b821d..b9ec2a798dbb 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -34,15 +34,9 @@ #define CROS_MAX_DEV 128 static int ec_major; -static const struct attribute_group *cros_ec_groups[] = { - &cros_ec_attr_group, - NULL, -}; - static struct class cros_class = { .owner = THIS_MODULE, .name = "chromeos", - .dev_groups = cros_ec_groups, }; /* Basic communication */ @@ -396,6 +390,7 @@ static const struct mfd_cell cros_usbpd_charger_cells[] = { static const struct mfd_cell cros_ec_platform_cells[] = { { .name = "cros-ec-debugfs" }, { .name = "cros-ec-lightbar" }, + { .name = "cros-ec-sysfs" }, { .name = "cros-ec-vbc" }, }; diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index 6cbf5b69d156..5e2fde5ff63d 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -49,9 +49,6 @@ config CHROMEOS_TBMC To compile this driver as a module, choose M here: the module will be called chromeos_tbmc. -config CROS_EC_CTL - tristate - config CROS_EC_I2C tristate "ChromeOS Embedded Controller (I2C)" depends on MFD_CROS_EC && I2C @@ -144,4 +141,15 @@ config CROS_EC_DEBUGFS To compile this driver as a module, choose M here: the module will be called cros_ec_debugfs. +config CROS_EC_SYSFS + tristate "ChromeOS EC control and information through sysfs" + depends on MFD_CROS_EC_CHARDEV && SYSFS + default MFD_CROS_EC_CHARDEV + help + This option exposes some sysfs attributes to control and get + information from ChromeOS EC. + + To compile this driver as a module, choose M here: the + module will be called cros_ec_sysfs. + endif # CHROMEOS_PLATFORMS diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index 12a5c4d18c17..fdbee501931b 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -3,8 +3,6 @@ obj-$(CONFIG_CHROMEOS_LAPTOP) += chromeos_laptop.o obj-$(CONFIG_CHROMEOS_PSTORE) += chromeos_pstore.o obj-$(CONFIG_CHROMEOS_TBMC) += chromeos_tbmc.o -cros_ec_ctl-objs := cros_ec_sysfs.o -obj-$(CONFIG_CROS_EC_CTL) += cros_ec_ctl.o obj-$(CONFIG_CROS_EC_I2C) += cros_ec_i2c.o obj-$(CONFIG_CROS_EC_SPI) += cros_ec_spi.o cros_ec_lpcs-objs := cros_ec_lpc.o cros_ec_lpc_reg.o @@ -15,3 +13,4 @@ obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT) += cros_kbd_led_backlight.o obj-$(CONFIG_CROS_EC_LIGHTBAR) += cros_ec_lightbar.o obj-$(CONFIG_CROS_EC_VBC) += cros_ec_vbc.o obj-$(CONFIG_CROS_EC_DEBUGFS) += cros_ec_debugfs.o +obj-$(CONFIG_CROS_EC_SYSFS) += cros_ec_sysfs.o diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c index 80eed6317570..c22318ba93aa 100644 --- a/drivers/platform/chrome/cros_ec_lightbar.c +++ b/drivers/platform/chrome/cros_ec_lightbar.c @@ -594,7 +594,7 @@ static umode_t cros_ec_lightbar_attrs_are_visible(struct kobject *kobj, return 0; } -struct attribute_group cros_ec_lightbar_attr_group = { +static struct attribute_group cros_ec_lightbar_attr_group = { .name = "lightbar", .attrs = __lb_cmds_attrs, .is_visible = cros_ec_lightbar_attrs_are_visible, diff --git a/drivers/platform/chrome/cros_ec_sysfs.c b/drivers/platform/chrome/cros_ec_sysfs.c index f34a50121064..0ff5aa30c070 100644 --- a/drivers/platform/chrome/cros_ec_sysfs.c +++ b/drivers/platform/chrome/cros_ec_sysfs.c @@ -34,6 +34,8 @@ #include #include +#define DRV_NAME "cros-ec-sysfs" + /* Accessor functions */ static ssize_t reboot_show(struct device *dev, @@ -353,7 +355,39 @@ struct attribute_group cros_ec_attr_group = { .attrs = __ec_attrs, .is_visible = cros_ec_ctrl_visible, }; -EXPORT_SYMBOL(cros_ec_attr_group); + +static int cros_ec_sysfs_probe(struct platform_device *pd) +{ + struct cros_ec_dev *ec_dev = dev_get_drvdata(pd->dev.parent); + struct device *dev = &pd->dev; + int ret; + + ret = sysfs_create_group(&ec_dev->class_dev.kobj, &cros_ec_attr_group); + if (ret < 0) + dev_err(dev, "failed to create attributes. err=%d\n", ret); + + return ret; +} + +static int cros_ec_sysfs_remove(struct platform_device *pd) +{ + struct cros_ec_dev *ec_dev = dev_get_drvdata(pd->dev.parent); + + sysfs_remove_group(&ec_dev->class_dev.kobj, &cros_ec_attr_group); + + return 0; +} + +static struct platform_driver cros_ec_sysfs_driver = { + .driver = { + .name = DRV_NAME, + }, + .probe = cros_ec_sysfs_probe, + .remove = cros_ec_sysfs_remove, +}; + +module_platform_driver(cros_ec_sysfs_driver); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ChromeOS EC control driver"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index e50860d190db..8f2a8918bfa3 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -325,7 +325,4 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); -/* sysfs stuff */ -extern struct attribute_group cros_ec_attr_group; - #endif /* __LINUX_MFD_CROS_EC_H */ -- cgit v1.2.3 From efb5a790dfc33b36bc64dd5a41ffc3ae5a709770 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 13 Jan 2019 13:36:46 -0500 Subject: mfd: wm831x-core: Drop unused module infrastructure from non-modular code The Kconfig currently controlling compilation of this code is: drivers/mfd/Kconfig:config MFD_WM831X drivers/mfd/Kconfig: bool ...meaning that it currently is not being built as a module by anyone. Lets remove the couple traces of modular infrastructure use, so that when reading the driver there is no doubt it is builtin-only. We delete the MODULE_LICENSE tag etc. since all that information is already contained at the top of the file in the comments. Previous demodularizaion work has made wm831x_device_exit() no longer used, so it is also removed from the 831x core code. Signed-off-by: Paul Gortmaker Acked-by: Charles Keepax Signed-off-by: Lee Jones --- drivers/mfd/wm831x-core.c | 15 ++------------- include/linux/mfd/wm831x/core.h | 1 - 2 files changed, 2 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/mfd/wm831x-core.c b/drivers/mfd/wm831x-core.c index e70d35ef5c6d..25fbbaf39cb9 100644 --- a/drivers/mfd/wm831x-core.c +++ b/drivers/mfd/wm831x-core.c @@ -13,7 +13,8 @@ */ #include -#include +#include +#include #include #include #include @@ -1892,14 +1893,6 @@ err: return ret; } -void wm831x_device_exit(struct wm831x *wm831x) -{ - wm831x_otp_exit(wm831x); - mfd_remove_devices(wm831x->dev); - free_irq(wm831x_irq(wm831x, WM831X_IRQ_AUXADC_DATA), wm831x); - wm831x_irq_exit(wm831x); -} - int wm831x_device_suspend(struct wm831x *wm831x) { int reg, mask; @@ -1944,7 +1937,3 @@ void wm831x_device_shutdown(struct wm831x *wm831x) } } EXPORT_SYMBOL_GPL(wm831x_device_shutdown); - -MODULE_DESCRIPTION("Core support for the WM831X AudioPlus PMIC"); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Mark Brown"); diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index b49fa67612f1..6fcb8eb00282 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -418,7 +418,6 @@ int wm831x_bulk_read(struct wm831x *wm831x, unsigned short reg, int count, u16 *buf); int wm831x_device_init(struct wm831x *wm831x, int irq); -void wm831x_device_exit(struct wm831x *wm831x); int wm831x_device_suspend(struct wm831x *wm831x); void wm831x_device_shutdown(struct wm831x *wm831x); int wm831x_irq_init(struct wm831x *wm831x, int irq); -- cgit v1.2.3 From 0db88688e1bb0180d6348742bdba8927cd0e5670 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 13 Jan 2019 13:36:48 -0500 Subject: mfd: wm8350-core: Drop unused module infrastructure from non-modular code The Kconfig currently controlling compilation of this code is: drivers/mfd/Kconfig:config MFD_WM8350 drivers/mfd/Kconfig: bool ...meaning that it currently is not being built as a module by anyone. Lets remove the couple traces of modular infrastructure use, so that when reading the driver there is no doubt it is builtin-only. We delete the MODULE_LICENSE tag etc. since all that information is already contained at the top of the file in the comments. We replace module.h with init.h and export.h ; the latter since the file does export some symbols. Previous demodularizaion work has made wm8350_device_exit() no longer used, so it is also removed from the 8350 core code. Signed-off-by: Paul Gortmaker Acked-by: Charles Keepax Signed-off-by: Lee Jones --- drivers/mfd/wm8350-core.c | 30 ++---------------------------- include/linux/mfd/wm8350/core.h | 1 - 2 files changed, 2 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c index 8a07c5634aee..9e1070f26b11 100644 --- a/drivers/mfd/wm8350-core.c +++ b/drivers/mfd/wm8350-core.c @@ -13,7 +13,8 @@ */ #include -#include +#include +#include #include #include #include @@ -442,30 +443,3 @@ err: return ret; } EXPORT_SYMBOL_GPL(wm8350_device_init); - -void wm8350_device_exit(struct wm8350 *wm8350) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(wm8350->pmic.led); i++) - platform_device_unregister(wm8350->pmic.led[i].pdev); - - for (i = 0; i < ARRAY_SIZE(wm8350->pmic.pdev); i++) - platform_device_unregister(wm8350->pmic.pdev[i]); - - platform_device_unregister(wm8350->wdt.pdev); - platform_device_unregister(wm8350->rtc.pdev); - platform_device_unregister(wm8350->power.pdev); - platform_device_unregister(wm8350->hwmon.pdev); - platform_device_unregister(wm8350->gpio.pdev); - platform_device_unregister(wm8350->codec.pdev); - - if (wm8350->irq_base) - free_irq(wm8350->irq_base + WM8350_IRQ_AUXADC_DATARDY, wm8350); - - wm8350_irq_exit(wm8350); -} -EXPORT_SYMBOL_GPL(wm8350_device_exit); - -MODULE_DESCRIPTION("WM8350 AudioPlus PMIC core driver"); -MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h index 509481d9cf19..202d9bde2c7c 100644 --- a/include/linux/mfd/wm8350/core.h +++ b/include/linux/mfd/wm8350/core.h @@ -643,7 +643,6 @@ struct wm8350_platform_data { */ int wm8350_device_init(struct wm8350 *wm8350, int irq, struct wm8350_platform_data *pdata); -void wm8350_device_exit(struct wm8350 *wm8350); /* * WM8350 device IO -- cgit v1.2.3 From d57f72875eed3f26afaca176c0f425f209bc99d7 Mon Sep 17 00:00:00 2001 From: Christian Hohnstaedt Date: Mon, 14 Jan 2019 09:16:34 +0100 Subject: mfd: tps65218.c: Add input voltage options These options apply to all regulators in this chip. ti,strict-supply-voltage-supervision: Set STRICT flag in CONFIG1 ti,under-voltage-limit-microvolt: Select 2.75, 2.95, 3.25 or 3.35 V UVLO in CONFIG1 ti,under-voltage-hyst-microvolt: Select 200mV or 400mV UVLOHYS in CONFIG2 Signed-off-by: Christian Hohnstaedt Tested-by: Keerthy Reviewed-by: Keerthy Signed-off-by: Lee Jones --- drivers/mfd/tps65218.c | 89 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/tps65218.h | 4 ++ 2 files changed, 93 insertions(+) (limited to 'include') diff --git a/drivers/mfd/tps65218.c b/drivers/mfd/tps65218.c index 8bcdecf494d0..a62ea4cb8be7 100644 --- a/drivers/mfd/tps65218.c +++ b/drivers/mfd/tps65218.c @@ -211,6 +211,83 @@ static const struct of_device_id of_tps65218_match_table[] = { }; MODULE_DEVICE_TABLE(of, of_tps65218_match_table); +static int tps65218_voltage_set_strict(struct tps65218 *tps) +{ + u32 strict; + + if (of_property_read_u32(tps->dev->of_node, + "ti,strict-supply-voltage-supervision", + &strict)) + return 0; + + if (strict != 0 && strict != 1) { + dev_err(tps->dev, + "Invalid ti,strict-supply-voltage-supervision value\n"); + return -EINVAL; + } + + tps65218_update_bits(tps, TPS65218_REG_CONFIG1, + TPS65218_CONFIG1_STRICT, + strict ? TPS65218_CONFIG1_STRICT : 0, + TPS65218_PROTECT_L1); + return 0; +} + +static int tps65218_voltage_set_uv_hyst(struct tps65218 *tps) +{ + u32 hyst; + + if (of_property_read_u32(tps->dev->of_node, + "ti,under-voltage-hyst-microvolt", &hyst)) + return 0; + + if (hyst != 400000 && hyst != 200000) { + dev_err(tps->dev, + "Invalid ti,under-voltage-hyst-microvolt value\n"); + return -EINVAL; + } + + tps65218_update_bits(tps, TPS65218_REG_CONFIG2, + TPS65218_CONFIG2_UVLOHYS, + hyst == 400000 ? TPS65218_CONFIG2_UVLOHYS : 0, + TPS65218_PROTECT_L1); + return 0; +} + +static int tps65218_voltage_set_uvlo(struct tps65218 *tps) +{ + u32 uvlo; + int uvloval; + + if (of_property_read_u32(tps->dev->of_node, + "ti,under-voltage-limit-microvolt", &uvlo)) + return 0; + + switch (uvlo) { + case 2750000: + uvloval = TPS65218_CONFIG1_UVLO_2750000; + break; + case 2950000: + uvloval = TPS65218_CONFIG1_UVLO_2950000; + break; + case 3250000: + uvloval = TPS65218_CONFIG1_UVLO_3250000; + break; + case 3350000: + uvloval = TPS65218_CONFIG1_UVLO_3350000; + break; + default: + dev_err(tps->dev, + "Invalid ti,under-voltage-limit-microvolt value\n"); + return -EINVAL; + } + + tps65218_update_bits(tps, TPS65218_REG_CONFIG1, + TPS65218_CONFIG1_UVLO_MASK, uvloval, + TPS65218_PROTECT_L1); + return 0; +} + static int tps65218_probe(struct i2c_client *client, const struct i2c_device_id *ids) { @@ -249,6 +326,18 @@ static int tps65218_probe(struct i2c_client *client, tps->rev = chipid & TPS65218_CHIPID_REV_MASK; + ret = tps65218_voltage_set_strict(tps); + if (ret) + return ret; + + ret = tps65218_voltage_set_uvlo(tps); + if (ret) + return ret; + + ret = tps65218_voltage_set_uv_hyst(tps); + if (ret) + return ret; + ret = mfd_add_devices(tps->dev, PLATFORM_DEVID_AUTO, tps65218_cells, ARRAY_SIZE(tps65218_cells), NULL, 0, regmap_irq_get_domain(tps->irq_data)); diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index c204d9a79436..3cbe103495ab 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -137,6 +137,10 @@ #define TPS65218_CONFIG1_PGDLY_MASK 0x18 #define TPS65218_CONFIG1_STRICT BIT(2) #define TPS65218_CONFIG1_UVLO_MASK 0x3 +#define TPS65218_CONFIG1_UVLO_2750000 0x0 +#define TPS65218_CONFIG1_UVLO_2950000 0x1 +#define TPS65218_CONFIG1_UVLO_3250000 0x2 +#define TPS65218_CONFIG1_UVLO_3350000 0x3 #define TPS65218_CONFIG2_DC12_RST BIT(7) #define TPS65218_CONFIG2_UVLOHYS BIT(6) -- cgit v1.2.3 From cfced786969c2a3e1bca45d7055a00311d93ae6c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jan 2019 18:20:05 +0100 Subject: dma-mapping: remove the default map_resource implementation Instead provide a proper implementation in the direct mapping code, and also wire it up for arm and powerpc, leaving an error return for all the IOMMU or virtual mapping instances for which we'd have to wire up an actual implementation Signed-off-by: Christoph Hellwig Tested-by: Marek Szyprowski --- arch/arm/mm/dma-mapping.c | 2 ++ arch/powerpc/kernel/dma-swiotlb.c | 1 + arch/powerpc/kernel/dma.c | 1 + include/linux/dma-mapping.h | 12 +++++++----- kernel/dma/direct.c | 14 ++++++++++++++ 5 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index f1e2922e447c..3c8534904209 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -188,6 +188,7 @@ const struct dma_map_ops arm_dma_ops = { .unmap_page = arm_dma_unmap_page, .map_sg = arm_dma_map_sg, .unmap_sg = arm_dma_unmap_sg, + .map_resource = dma_direct_map_resource, .sync_single_for_cpu = arm_dma_sync_single_for_cpu, .sync_single_for_device = arm_dma_sync_single_for_device, .sync_sg_for_cpu = arm_dma_sync_sg_for_cpu, @@ -211,6 +212,7 @@ const struct dma_map_ops arm_coherent_dma_ops = { .get_sgtable = arm_dma_get_sgtable, .map_page = arm_coherent_dma_map_page, .map_sg = arm_dma_map_sg, + .map_resource = dma_direct_map_resource, .dma_supported = arm_dma_supported, }; EXPORT_SYMBOL(arm_coherent_dma_ops); diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 7d5fc9751622..fbb2506a414e 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -55,6 +55,7 @@ const struct dma_map_ops powerpc_swiotlb_dma_ops = { .dma_supported = swiotlb_dma_supported, .map_page = dma_direct_map_page, .unmap_page = dma_direct_unmap_page, + .map_resource = dma_direct_map_resource, .sync_single_for_cpu = dma_direct_sync_single_for_cpu, .sync_single_for_device = dma_direct_sync_single_for_device, .sync_sg_for_cpu = dma_direct_sync_sg_for_cpu, diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index b1903ebb2e9c..258b9e8ebb99 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -273,6 +273,7 @@ const struct dma_map_ops dma_nommu_ops = { .dma_supported = dma_nommu_dma_supported, .map_page = dma_nommu_map_page, .unmap_page = dma_nommu_unmap_page, + .map_resource = dma_direct_map_resource, .get_required_mask = dma_nommu_get_required_mask, #ifdef CONFIG_NOT_COHERENT_CACHE .sync_single_for_cpu = dma_nommu_sync_single, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index f6ded992c183..9842085e6774 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -208,6 +208,8 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long attrs); int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs); +dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir, unsigned long attrs); #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_SWIOTLB) @@ -346,19 +348,19 @@ static inline dma_addr_t dma_map_resource(struct device *dev, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); - dma_addr_t addr; + dma_addr_t addr = DMA_MAPPING_ERROR; BUG_ON(!valid_dma_direction(dir)); /* Don't allow RAM to be mapped */ BUG_ON(pfn_valid(PHYS_PFN(phys_addr))); - addr = phys_addr; - if (ops && ops->map_resource) + if (dma_is_direct(ops)) + addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs); + else if (ops->map_resource) addr = ops->map_resource(dev, phys_addr, size, dir, attrs); debug_dma_map_resource(dev, phys_addr, size, dir, addr); - return addr; } @@ -369,7 +371,7 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); - if (ops && ops->unmap_resource) + if (!dma_is_direct(ops) && ops->unmap_resource) ops->unmap_resource(dev, addr, size, dir, attrs); debug_dma_unmap_resource(dev, addr, size, dir); } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 355d16acee6d..25bd19974223 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -356,6 +356,20 @@ out_unmap: } EXPORT_SYMBOL(dma_direct_map_sg); +dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + dma_addr_t dma_addr = paddr; + + if (unlikely(!dma_direct_possible(dev, dma_addr, size))) { + report_addr(dev, dma_addr, size); + return DMA_MAPPING_ERROR; + } + + return dma_addr; +} +EXPORT_SYMBOL(dma_direct_map_resource); + /* * Because 32-bit DMA masks are so common we expect every architecture to be * able to satisfy them - either by not supporting more physical memory, or by -- cgit v1.2.3 From 645386dfe6307dbb28f10a4513792a59beda0efa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jan 2019 17:17:53 +0100 Subject: dma-mapping: don't BUG when calling dma_map_resource on RAM Use WARN_ON_ONCE to print a stack trace and return a proper error code instead. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Tested-by: Marek Szyprowski --- include/linux/dma-mapping.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 9842085e6774..b904d55247ab 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -353,7 +353,8 @@ static inline dma_addr_t dma_map_resource(struct device *dev, BUG_ON(!valid_dma_direction(dir)); /* Don't allow RAM to be mapped */ - BUG_ON(pfn_valid(PHYS_PFN(phys_addr))); + if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr)))) + return DMA_MAPPING_ERROR; if (dma_is_direct(ops)) addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs); -- cgit v1.2.3 From e2f3cd831a280fc226118d9369bf3f77aab58c56 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 1 Feb 2019 01:49:14 +0100 Subject: driver core: Fix handling of runtime PM flags in device_link_add() After commit ead18c23c263 ("driver core: Introduce device links reference counting"), if there is a link between the given supplier and the given consumer already, device_link_add() will refcount it and return it unconditionally without updating its flags. It is possible, however, that the second (or any subsequent) caller of device_link_add() for the same consumer-supplier pair will pass DL_FLAG_PM_RUNTIME, possibly along with DL_FLAG_RPM_ACTIVE, in flags to it and the existing link may not behave as expected then. First, if DL_FLAG_PM_RUNTIME is not set in the existing link's flags at all, it needs to be set like during the original initialization of the link. Second, if DL_FLAG_RPM_ACTIVE is passed to device_link_add() in flags (in addition to DL_FLAG_PM_RUNTIME), the existing link should to be updated to reflect the "active" runtime PM configuration of the consumer-supplier pair and extra care must be taken here to avoid possible destructive races with runtime PM of the consumer. To that end, redefine the rpm_active field in struct device_link as a refcount, initialize it to 1 and make rpm_resume() (for the consumer) and device_link_add() increment it whenever they acquire a runtime PM reference on the supplier device. Accordingly, make rpm_suspend() (for the consumer) and pm_runtime_clean_up_links() decrement it and drop runtime PM references to the supplier device in a loop until rpm_active becones 1 again. Fixes: ead18c23c263 ("driver core: Introduce device links reference counting") Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 45 +++++++++++++++++++++++++++++--------------- drivers/base/power/runtime.c | 26 +++++++++++-------------- include/linux/device.h | 2 +- 3 files changed, 42 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index 50610cd87e71..8611385e44b5 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -165,6 +165,19 @@ void device_pm_move_to_tail(struct device *dev) device_links_read_unlock(idx); } +static void device_link_rpm_prepare(struct device *consumer, + struct device *supplier) +{ + pm_runtime_new_link(consumer); + /* + * If the link is being added by the consumer driver at probe time, + * balance the decrementation of the supplier's runtime PM usage counter + * after consumer probe in driver_probe_device(). + */ + if (consumer->links.status == DL_DEV_PROBING) + pm_runtime_get_noresume(supplier); +} + /** * device_link_add - Create a link between two devices. * @consumer: Consumer end of the link. @@ -201,7 +214,6 @@ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags) { struct device_link *link; - bool rpm_put_supplier = false; if (!consumer || !supplier || (flags & DL_FLAG_STATELESS && @@ -213,7 +225,6 @@ struct device_link *device_link_add(struct device *consumer, pm_runtime_put_noidle(supplier); return NULL; } - rpm_put_supplier = true; } device_links_write_lock(); @@ -249,6 +260,15 @@ struct device_link *device_link_add(struct device *consumer, if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) link->flags |= DL_FLAG_AUTOREMOVE_SUPPLIER; + if (flags & DL_FLAG_PM_RUNTIME) { + if (!(link->flags & DL_FLAG_PM_RUNTIME)) { + device_link_rpm_prepare(consumer, supplier); + link->flags |= DL_FLAG_PM_RUNTIME; + } + if (flags & DL_FLAG_RPM_ACTIVE) + refcount_inc(&link->rpm_active); + } + kref_get(&link->kref); goto out; } @@ -257,20 +277,15 @@ struct device_link *device_link_add(struct device *consumer, if (!link) goto out; + refcount_set(&link->rpm_active, 1); + if (flags & DL_FLAG_PM_RUNTIME) { - if (flags & DL_FLAG_RPM_ACTIVE) { - link->rpm_active = true; - rpm_put_supplier = false; - } - pm_runtime_new_link(consumer); - /* - * If the link is being added by the consumer driver at probe - * time, balance the decrementation of the supplier's runtime PM - * usage counter after consumer probe in driver_probe_device(). - */ - if (consumer->links.status == DL_DEV_PROBING) - pm_runtime_get_noresume(supplier); + if (flags & DL_FLAG_RPM_ACTIVE) + refcount_inc(&link->rpm_active); + + device_link_rpm_prepare(consumer, supplier); } + get_device(supplier); link->supplier = supplier; INIT_LIST_HEAD(&link->s_node); @@ -333,7 +348,7 @@ struct device_link *device_link_add(struct device *consumer, device_pm_unlock(); device_links_write_unlock(); - if (rpm_put_supplier) + if ((flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) && !link) pm_runtime_put(supplier); return link; diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 457be03b744d..8bc9a432de70 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -259,11 +259,8 @@ static int rpm_get_suppliers(struct device *dev) list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) { int retval; - if (!(link->flags & DL_FLAG_PM_RUNTIME)) - continue; - - if (READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND || - link->rpm_active) + if (!(link->flags & DL_FLAG_PM_RUNTIME) || + READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND) continue; retval = pm_runtime_get_sync(link->supplier); @@ -272,7 +269,7 @@ static int rpm_get_suppliers(struct device *dev) pm_runtime_put_noidle(link->supplier); return retval; } - link->rpm_active = true; + refcount_inc(&link->rpm_active); } return 0; } @@ -281,12 +278,13 @@ static void rpm_put_suppliers(struct device *dev) { struct device_link *link; - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) - if (link->rpm_active && - READ_ONCE(link->status) != DL_STATE_SUPPLIER_UNBIND) { + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) { + if (READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND) + continue; + + while (refcount_dec_not_one(&link->rpm_active)) pm_runtime_put(link->supplier); - link->rpm_active = false; - } + } } /** @@ -1539,7 +1537,7 @@ void pm_runtime_remove(struct device *dev) * * Check links from this device to any consumers and if any of them have active * runtime PM references to the device, drop the usage counter of the device - * (once per link). + * (as many times as needed). * * Links with the DL_FLAG_STATELESS flag set are ignored. * @@ -1561,10 +1559,8 @@ void pm_runtime_clean_up_links(struct device *dev) if (link->flags & DL_FLAG_STATELESS) continue; - if (link->rpm_active) { + while (refcount_dec_not_one(&link->rpm_active)) pm_runtime_put_noidle(dev); - link->rpm_active = false; - } } device_links_read_unlock(idx); diff --git a/include/linux/device.h b/include/linux/device.h index d0e452fd0bff..5f49d2eff6ed 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -853,7 +853,7 @@ struct device_link { struct list_head c_node; enum device_link_state status; u32 flags; - bool rpm_active; + refcount_t rpm_active; struct kref kref; #ifdef CONFIG_SRCU struct rcu_head rcu_head; -- cgit v1.2.3 From e7dd40105aac9ba051e44ad711123bc53a5e4c71 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 1 Feb 2019 01:59:42 +0100 Subject: driver core: Add device link flag DL_FLAG_AUTOPROBE_CONSUMER Add a new device link flag, DL_FLAG_AUTOPROBE_CONSUMER, to request the driver core to probe for a consumer driver automatically after binding a driver to the supplier device on a persistent managed device link. As unbinding the supplier driver on a managed device link causes the consumer driver to be detached from its device automatically, this flag provides a complementary mechanism which is needed to address some "composite device" use cases. Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/device_link.rst | 9 +++++++++ drivers/base/core.c | 16 +++++++++++++++- drivers/base/dd.c | 2 +- include/linux/device.h | 3 +++ 4 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst index e249e074a8d2..c764755121c7 100644 --- a/Documentation/driver-api/device_link.rst +++ b/Documentation/driver-api/device_link.rst @@ -94,6 +94,15 @@ Similarly, when the device link is added from supplier's ``->probe`` callback, ``DL_FLAG_AUTOREMOVE_SUPPLIER`` causes the device link to be automatically purged when the supplier fails to probe or later unbinds. +If neither ``DL_FLAG_AUTOREMOVE_CONSUMER`` nor ``DL_FLAG_AUTOREMOVE_SUPPLIER`` +is set, ``DL_FLAG_AUTOPROBE_CONSUMER`` can be used to request the driver core +to probe for a driver for the consumer driver on the link automatically after +a driver has been bound to the supplier device. + +Note, however, that any combinations of ``DL_FLAG_AUTOREMOVE_CONSUMER``, +``DL_FLAG_AUTOREMOVE_SUPPLIER`` or ``DL_FLAG_AUTOPROBE_CONSUMER`` with +``DL_FLAG_STATELESS`` are invalid and cannot be used. + Limitations =========== diff --git a/drivers/base/core.c b/drivers/base/core.c index 9d49b461b1d9..abfce4f613f8 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -208,6 +208,12 @@ static void device_link_rpm_prepare(struct device *consumer, * the link will be maintained until one of the devices pointed to by it (either * the consumer or the supplier) is unregistered. * + * Also, if DL_FLAG_STATELESS, DL_FLAG_AUTOREMOVE_CONSUMER and + * DL_FLAG_AUTOREMOVE_SUPPLIER are not set in @flags (that is, a persistent + * managed device link is being added), the DL_FLAG_AUTOPROBE_CONSUMER flag can + * be used to request the driver core to automaticall probe for a consmer + * driver after successfully binding a driver to the supplier device. + * * The combination of DL_FLAG_STATELESS and either DL_FLAG_AUTOREMOVE_CONSUMER * or DL_FLAG_AUTOREMOVE_SUPPLIER set in @flags at the same time is invalid and * will cause NULL to be returned upfront. @@ -228,7 +234,12 @@ struct device_link *device_link_add(struct device *consumer, if (!consumer || !supplier || (flags & DL_FLAG_STATELESS && - flags & (DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER))) + flags & (DL_FLAG_AUTOREMOVE_CONSUMER | + DL_FLAG_AUTOREMOVE_SUPPLIER | + DL_FLAG_AUTOPROBE_CONSUMER)) || + (flags & DL_FLAG_AUTOPROBE_CONSUMER && + flags & (DL_FLAG_AUTOREMOVE_CONSUMER | + DL_FLAG_AUTOREMOVE_SUPPLIER))) return NULL; if (flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) { @@ -589,6 +600,9 @@ void device_links_driver_bound(struct device *dev) WARN_ON(link->status != DL_STATE_DORMANT); WRITE_ONCE(link->status, DL_STATE_AVAILABLE); + + if (link->flags & DL_FLAG_AUTOPROBE_CONSUMER) + driver_deferred_probe_add(link->consumer); } list_for_each_entry(link, &dev->links.suppliers, c_node) { diff --git a/drivers/base/dd.c b/drivers/base/dd.c index aa6a9c613595..2e898cbba79b 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -116,7 +116,7 @@ static void deferred_probe_work_func(struct work_struct *work) } static DECLARE_WORK(deferred_probe_work, deferred_probe_work_func); -static void driver_deferred_probe_add(struct device *dev) +void driver_deferred_probe_add(struct device *dev) { mutex_lock(&deferred_probe_mutex); if (list_empty(&dev->p->deferred_probe)) { diff --git a/include/linux/device.h b/include/linux/device.h index 5f49d2eff6ed..0ab0a3a80ec3 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -341,6 +341,7 @@ struct device *driver_find_device(struct device_driver *drv, struct device *start, void *data, int (*match)(struct device *dev, void *data)); +void driver_deferred_probe_add(struct device *dev); int driver_deferred_probe_check_state(struct device *dev); /** @@ -827,12 +828,14 @@ enum device_link_state { * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. + * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) +#define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) /** * struct device_link - Device link representation. -- cgit v1.2.3 From cb86880ee493ea41e95476be054a605b3e434035 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 29 Jan 2019 11:31:26 +0100 Subject: mac80211: Fix documentation strings for airtime-related variables MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There was a typo in the documentation for weight_multiplier in mac80211.h, and the doc was missing entirely for airtime and airtime_weight in sta_info.h. Reported-by: kbuild test robot Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 +- net/mac80211/sta_info.h | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 294a8a36012a..396b0c079c3b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2365,7 +2365,7 @@ enum ieee80211_hw_flags { * them are encountered. The default should typically not be changed, * unless the driver has good reasons for needing more buffers. * - * @weight_multipler: Driver specific airtime weight multiplier used while + * @weight_multiplier: Driver specific airtime weight multiplier used while * refilling deficit of each TXQ. */ struct ieee80211_hw { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 90e03ebccd3f..05647d835894 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -473,6 +473,9 @@ struct ieee80211_sta_rx_stats { * @last_seq_ctrl: last received seq/frag number from this STA (per TID * plus one for non-QoS frames) * @tid_seq: per-TID sequence numbers for sending to this STA + * @airtime: per-AC struct airtime_info describing airtime statistics for this + * station + * @airtime_weight: station weight for airtime fairness calculation purposes * @ampdu_mlme: A-MPDU state machine state * @mesh: mesh STA information * @debugfs_dir: debug filesystem directory dentry -- cgit v1.2.3 From 5ac4a12df58121f0cf874b518406ec2a8e2d4ac4 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Tue, 29 Jan 2019 19:25:53 +0100 Subject: cfg80211: fix typo Fix spelling mistake in cfg80211.h: "lenght" -> "length". The typo is also in the special comment block which translates to documentation. Signed-off-by: Matteo Croce Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7033c90850b0..5862f1efb52c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5604,7 +5604,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, * @dev: network device * @macaddr: the MAC address of the new candidate * @ie: information elements advertised by the peer candidate - * @ie_len: lenght of the information elements buffer + * @ie_len: length of the information elements buffer * @gfp: allocation flags * * This function notifies cfg80211 that the mesh peer candidate has been -- cgit v1.2.3 From 23323289b1543b445d1f10aeab1bcfd84f2ca50a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 25 Jan 2019 10:08:28 +0100 Subject: netlink: reduce NLA_POLICY_NESTED{,_ARRAY} arguments In typical cases, there's no need to pass both the maxattr and the policy array pointer, as the maxattr should just be ARRAY_SIZE(policy) - 1. Therefore, to be less error prone, just remove the maxattr argument from the default macros and deduce the size accordingly. Leave the original macros with a leading underscore to use here and in case somebody needs to pass a policy pointer where the policy isn't declared in the same place and thus ARRAY_SIZE() cannot be used. Signed-off-by: Johannes Berg --- include/net/netlink.h | 8 ++++++-- net/wireless/nl80211.c | 15 +++++---------- 2 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 4c1e99303b5a..23f27b0b3cef 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -306,10 +306,14 @@ struct nla_policy { #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) -#define NLA_POLICY_NESTED(maxattr, policy) \ +#define _NLA_POLICY_NESTED(maxattr, policy) \ { .type = NLA_NESTED, .validation_data = policy, .len = maxattr } -#define NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ +#define _NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ { .type = NLA_NESTED_ARRAY, .validation_data = policy, .len = maxattr } +#define NLA_POLICY_NESTED(policy) \ + _NLA_POLICY_NESTED(ARRAY_SIZE(policy) - 1, policy) +#define NLA_POLICY_NESTED_ARRAY(policy) \ + _NLA_POLICY_NESTED_ARRAY(ARRAY_SIZE(policy) - 1, policy) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_INT_TYPE(tp) \ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ed53f8332ec8..a3cc039b9f55 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -259,15 +259,13 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { static const struct nla_policy nl80211_pmsr_req_data_policy[NL80211_PMSR_TYPE_MAX + 1] = { [NL80211_PMSR_TYPE_FTM] = - NLA_POLICY_NESTED(NL80211_PMSR_FTM_REQ_ATTR_MAX, - nl80211_pmsr_ftm_req_attr_policy), + NLA_POLICY_NESTED(nl80211_pmsr_ftm_req_attr_policy), }; static const struct nla_policy nl80211_pmsr_req_attr_policy[NL80211_PMSR_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_REQ_ATTR_DATA] = - NLA_POLICY_NESTED(NL80211_PMSR_TYPE_MAX, - nl80211_pmsr_req_data_policy), + NLA_POLICY_NESTED(nl80211_pmsr_req_data_policy), [NL80211_PMSR_REQ_ATTR_GET_AP_TSF] = { .type = NLA_FLAG }, }; @@ -280,8 +278,7 @@ nl80211_psmr_peer_attr_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = { */ [NL80211_PMSR_PEER_ATTR_CHAN] = { .type = NLA_NESTED }, [NL80211_PMSR_PEER_ATTR_REQ] = - NLA_POLICY_NESTED(NL80211_PMSR_REQ_ATTR_MAX, - nl80211_pmsr_req_attr_policy), + NLA_POLICY_NESTED(nl80211_pmsr_req_attr_policy), [NL80211_PMSR_PEER_ATTR_RESP] = { .type = NLA_REJECT }, }; @@ -292,8 +289,7 @@ nl80211_pmsr_attr_policy[NL80211_PMSR_ATTR_MAX + 1] = { [NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_TYPE_CAPA] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_PEERS] = - NLA_POLICY_NESTED_ARRAY(NL80211_PMSR_PEER_ATTR_MAX, - nl80211_psmr_peer_attr_policy), + NLA_POLICY_NESTED_ARRAY(nl80211_psmr_peer_attr_policy), }; const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { @@ -555,8 +551,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { }, [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PEER_MEASUREMENTS] = - NLA_POLICY_NESTED(NL80211_PMSR_ATTR_MAX, - nl80211_pmsr_attr_policy), + NLA_POLICY_NESTED(nl80211_pmsr_attr_policy), [NL80211_ATTR_AIRTIME_WEIGHT] = NLA_POLICY_MIN(NLA_U16, 1), }; -- cgit v1.2.3 From 9874b71fa19c3ae4d13e02081326975ab2734061 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 1 Feb 2019 11:52:44 +0100 Subject: cfg80211: add missing documentation that kernel-doc warns about Add the missing documentation that kernel-doc continually warns about, to get rid of all that noise. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5862f1efb52c..7f2739a90bdb 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1443,6 +1443,7 @@ enum monitor_flags { * @MPATH_INFO_DISCOVERY_RETRIES: @discovery_retries filled * @MPATH_INFO_FLAGS: @flags filled * @MPATH_INFO_HOP_COUNT: @hop_count filled + * @MPATH_INFO_PATH_CHANGE: @path_change_count filled */ enum mpath_info_flags { MPATH_INFO_FRAME_QLEN = BIT(0), @@ -4609,6 +4610,17 @@ struct cfg80211_cqm_config; * @mesh_id_len: (private) Used by the internal configuration code * @mesh_id_up_len: (private) Used by the internal configuration code * @wext: (private) Used by the internal wireless extensions compat code + * @wext.ibss: (private) IBSS data part of wext handling + * @wext.connect: (private) connection handling data + * @wext.keys: (private) (WEP) key data + * @wext.ie: (private) extra elements for association + * @wext.ie_len: (private) length of extra elements + * @wext.bssid: (private) selected network BSSID + * @wext.ssid: (private) selected network SSID + * @wext.default_key: (private) selected default key index + * @wext.default_mgmt_key: (private) selected default management key index + * @wext.prev_bssid: (private) previous BSSID for reassociation + * @wext.prev_bssid_valid: (private) previous BSSID validity * @use_4addr: indicates 4addr mode is used on this interface, must be * set by driver (if supported) on add_interface BEFORE registering the * netdev and may otherwise be used by driver read-only, will be update @@ -4708,7 +4720,8 @@ struct wireless_dev { struct cfg80211_cached_keys *keys; const u8 *ie; size_t ie_len; - u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; + u8 bssid[ETH_ALEN]; + u8 prev_bssid[ETH_ALEN]; u8 ssid[IEEE80211_MAX_SSID_LEN]; s8 default_key, default_mgmt_key; bool prev_bssid_valid; -- cgit v1.2.3 From 7d4194633b29342d93501b53accebf638da134ad Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 1 Feb 2019 11:53:32 +0100 Subject: mac80211: fix missing/malformed documentation Fix the missing and malformed documentation that kernel-doc and sphinx warn about. While at it, also add some things to the docs to fix missing links. Sadly, the only way I could find to fix this was to add some trailing whitespace. Signed-off-by: Johannes Berg --- Documentation/driver-api/80211/mac80211.rst | 3 ++ include/net/mac80211.h | 44 +++++++++++++++++++++++------ net/mac80211/sta_info.h | 18 ++++++++++++ 3 files changed, 57 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/Documentation/driver-api/80211/mac80211.rst b/Documentation/driver-api/80211/mac80211.rst index 85a8335e80b6..eab40bcf3987 100644 --- a/Documentation/driver-api/80211/mac80211.rst +++ b/Documentation/driver-api/80211/mac80211.rst @@ -125,6 +125,9 @@ functions/definitions .. kernel-doc:: include/net/mac80211.h :functions: ieee80211_rx_status +.. kernel-doc:: include/net/mac80211.h + :functions: mac80211_rx_encoding_flags + .. kernel-doc:: include/net/mac80211.h :functions: mac80211_rx_flags diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 396b0c079c3b..de866a7253c9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -942,8 +942,32 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * @band: the band to transmit on (use for checking for races) * @hw_queue: HW queue to put the frame on, skb_get_queue_mapping() gives the AC * @ack_frame_id: internal frame ID for TX status, used internally - * @control: union for control data - * @status: union for status data + * @control: union part for control data + * @control.rates: TX rates array to try + * @control.rts_cts_rate_idx: rate for RTS or CTS + * @control.use_rts: use RTS + * @control.use_cts_prot: use RTS/CTS + * @control.short_preamble: use short preamble (CCK only) + * @control.skip_table: skip externally configured rate table + * @control.jiffies: timestamp for expiry on powersave clients + * @control.vif: virtual interface (may be NULL) + * @control.hw_key: key to encrypt with (may be NULL) + * @control.flags: control flags, see &enum mac80211_tx_control_flags + * @control.enqueue_time: enqueue time (for iTXQs) + * @driver_rates: alias to @control.rates to reserve space + * @pad: padding + * @rate_driver_data: driver use area if driver needs @control.rates + * @status: union part for status data + * @status.rates: attempted rates + * @status.ack_signal: ACK signal + * @status.ampdu_ack_len: AMPDU ack length + * @status.ampdu_len: AMPDU length + * @status.antenna: (legacy, kept only for iwlegacy) + * @status.tx_time: airtime consumed for transmission + * @status.is_valid_ack_signal: ACK signal is valid + * @status.status_driver_data: driver use area + * @ack: union part for pure ACK data + * @ack.cookie: cookie for the ACK * @driver_data: array of driver_data pointers * @ampdu_ack_len: number of acked aggregated frames. * relevant only if IEEE80211_TX_STAT_AMPDU was set. @@ -1163,6 +1187,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known * @RX_FLAG_RADIOTAP_HE: HE radiotap data is present * (&struct ieee80211_radiotap_he, mac80211 will fill in + * * - DATA3_DATA_MCS * - DATA3_DATA_DCM * - DATA3_CODING @@ -1170,6 +1195,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * - DATA5_DATA_BW_RU_ALLOC * - DATA6_NSTS * - DATA3_STBC + * * from the RX info data, so leave those zeroed when building this data) * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present * (&struct ieee80211_radiotap_he_mu) @@ -1220,7 +1246,7 @@ enum mac80211_rx_flags { * @RX_ENC_FLAG_HT_GF: This frame was received in a HT-greenfield transmission, * if the driver fills this value it should add * %IEEE80211_RADIOTAP_MCS_HAVE_FMT - * to hw.radiotap_mcs_details to advertise that fact + * to @hw.radiotap_mcs_details to advertise that fact. * @RX_ENC_FLAG_LDPC: LDPC was used * @RX_ENC_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3 * @RX_ENC_FLAG_BF: packet was beamformed @@ -2333,12 +2359,14 @@ enum ieee80211_hw_flags { * @radiotap_he: HE radiotap validity flags * * @radiotap_timestamp: Information for the radiotap timestamp field; if the - * 'units_pos' member is set to a non-negative value it must be set to - * a combination of a IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a - * IEEE80211_RADIOTAP_TIMESTAMP_SPOS_* value, and then the timestamp + * @units_pos member is set to a non-negative value then the timestamp * field will be added and populated from the &struct ieee80211_rx_status - * device_timestamp. If the 'accuracy' member is non-negative, it's put - * into the accuracy radiotap field and the accuracy known flag is set. + * device_timestamp. + * @radiotap_timestamp.units_pos: Must be set to a combination of a + * IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a + * IEEE80211_RADIOTAP_TIMESTAMP_SPOS_* value. + * @radiotap_timestamp.accuracy: If non-negative, fills the accuracy in the + * radiotap field and the accuracy known flag will be set. * * @netdev_features: netdev features to be set in each netdev created * from this HW. Note that not all features are usable with mac80211, diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 05647d835894..71f7e4973329 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -497,10 +497,28 @@ struct ieee80211_sta_rx_stats { * @tdls_chandef: a TDLS peer can have a wider chandef that is compatible to * the BSS one. * @tx_stats: TX statistics + * @tx_stats.packets: # of packets transmitted + * @tx_stats.bytes: # of bytes in all packets transmitted + * @tx_stats.last_rate: last TX rate + * @tx_stats.msdu: # of transmitted MSDUs per TID * @rx_stats: RX statistics + * @rx_stats_avg: averaged RX statistics + * @rx_stats_avg.signal: averaged signal + * @rx_stats_avg.chain_signal: averaged per-chain signal * @pcpu_rx_stats: per-CPU RX statistics, assigned only if the driver needs * this (by advertising the USES_RSS hw flag) * @status_stats: TX status statistics + * @status_stats.filtered: # of filtered frames + * @status_stats.retry_failed: # of frames that failed after retry + * @status_stats.retry_count: # of retries attempted + * @status_stats.lost_packets: # of lost packets + * @status_stats.last_tdls_pkt_time: timestamp of last TDLS packet + * @status_stats.msdu_retries: # of MSDU retries + * @status_stats.msdu_failed: # of failed MSDUs + * @status_stats.last_ack: last ack timestamp (jiffies) + * @status_stats.last_ack_signal: last ACK signal + * @status_stats.ack_signal_filled: last ACK signal validity + * @status_stats.avg_ack_signal: average ACK signal */ struct sta_info { /* General information, mostly static */ -- cgit v1.2.3 From 7403e48d7abd9a0114e9056e7615cfbbb5123b15 Mon Sep 17 00:00:00 2001 From: Kamil Konieczny Date: Tue, 22 Jan 2019 10:02:31 +0100 Subject: clk: samsung: dt-bindings: Add Exynos5433 IMEM CMU clock IDs Add DT bindings to describe the IMEM CMU clocks for the SlimSSS (Slim Security SubSystem). Signed-off-by: Kamil Konieczny Reviewed-by: Rob Herring Acked-by: Chanwoo Choi [s.nawrocki@samsung.com: edited commit description] Signed-off-by: Sylwester Nawrocki --- include/dt-bindings/clock/exynos5433.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/exynos5433.h b/include/dt-bindings/clock/exynos5433.h index 98bd85ce1e45..7cfce3a62050 100644 --- a/include/dt-bindings/clock/exynos5433.h +++ b/include/dt-bindings/clock/exynos5433.h @@ -1406,4 +1406,10 @@ #define CAM1_NR_CLK 113 +/* CMU_IMEM */ +#define CLK_ACLK_SLIMSSS 2 +#define CLK_PCLK_SLIMSSS 35 + +#define IMEM_NR_CLK 36 + #endif /* _DT_BINDINGS_CLOCK_EXYNOS5433_H */ -- cgit v1.2.3 From b80a40c659ba38e1295ab7e55b2c781abee64739 Mon Sep 17 00:00:00 2001 From: Kamil Konieczny Date: Tue, 22 Jan 2019 10:02:29 +0100 Subject: clk: samsung: exynos5433: Fix name typo in sssx Fix typo in sssx name, there should be three letters 's'. Acked-by: Rob Herring Reviewed-by: Chanwoo Choi Signed-off-by: Kamil Konieczny Signed-off-by: Sylwester Nawrocki --- drivers/clk/samsung/clk-exynos5433.c | 2 +- include/dt-bindings/clock/exynos5433.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c index ea47f49abc7f..24c3360db65b 100644 --- a/drivers/clk/samsung/clk-exynos5433.c +++ b/drivers/clk/samsung/clk-exynos5433.c @@ -559,7 +559,7 @@ static const struct samsung_gate_clock top_gate_clks[] __initconst = { /* ENABLE_ACLK_TOP */ GATE(CLK_ACLK_G3D_400, "aclk_g3d_400", "div_aclk_g3d_400", ENABLE_ACLK_TOP, 30, CLK_IS_CRITICAL, 0), - GATE(CLK_ACLK_IMEM_SSX_266, "aclk_imem_ssx_266", + GATE(CLK_ACLK_IMEM_SSSX_266, "aclk_imem_sssx_266", "div_aclk_imem_sssx_266", ENABLE_ACLK_TOP, 29, CLK_IGNORE_UNUSED, 0), GATE(CLK_ACLK_BUS0_400, "aclk_bus0_400", "div_aclk_bus0_400", diff --git a/include/dt-bindings/clock/exynos5433.h b/include/dt-bindings/clock/exynos5433.h index 7cfce3a62050..25ffa53573a5 100644 --- a/include/dt-bindings/clock/exynos5433.h +++ b/include/dt-bindings/clock/exynos5433.h @@ -156,7 +156,7 @@ #define CLK_ACLK_G2D_266 220 #define CLK_ACLK_G2D_400 221 #define CLK_ACLK_G3D_400 222 -#define CLK_ACLK_IMEM_SSX_266 223 +#define CLK_ACLK_IMEM_SSSX_266 223 #define CLK_ACLK_BUS0_400 224 #define CLK_ACLK_BUS1_400 225 #define CLK_ACLK_IMEM_200 226 -- cgit v1.2.3 From d0a060be573bfbf8753a15dca35497db5e968bb0 Mon Sep 17 00:00:00 2001 From: Kristina Martsenko Date: Wed, 30 Jan 2019 12:02:44 +0000 Subject: arm64: add ptrace regsets for ptrauth key management Add two new ptrace regsets, which can be used to request and change the pointer authentication keys of a thread. NT_ARM_PACA_KEYS gives access to the instruction/data address keys, and NT_ARM_PACG_KEYS to the generic authentication key. The keys are also part of the core dump file of the process. The regsets are only exposed if the kernel is compiled with CONFIG_CHECKPOINT_RESTORE=y, as the only intended use case is checkpointing and restoring processes that are using pointer authentication. (This can be changed later if there are other use cases.) Reviewed-by: Dave Martin Signed-off-by: Kristina Martsenko Signed-off-by: Catalin Marinas --- Documentation/arm64/pointer-authentication.txt | 5 + arch/arm64/include/uapi/asm/ptrace.h | 13 +++ arch/arm64/kernel/ptrace.c | 147 +++++++++++++++++++++++++ include/uapi/linux/elf.h | 2 + 4 files changed, 167 insertions(+) (limited to 'include') diff --git a/Documentation/arm64/pointer-authentication.txt b/Documentation/arm64/pointer-authentication.txt index a25cd21290e9..5baca42ba146 100644 --- a/Documentation/arm64/pointer-authentication.txt +++ b/Documentation/arm64/pointer-authentication.txt @@ -78,6 +78,11 @@ bits can vary between the two. Note that the masks apply to TTBR0 addresses, and are not valid to apply to TTBR1 addresses (e.g. kernel pointers). +Additionally, when CONFIG_CHECKPOINT_RESTORE is also set, the kernel +will expose the NT_ARM_PACA_KEYS and NT_ARM_PACG_KEYS regsets (struct +user_pac_address_keys and struct user_pac_generic_keys). These can be +used to get and set the keys for a thread. + Virtualization -------------- diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 28d77c9ed531..d78623acb649 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -233,6 +233,19 @@ struct user_pac_mask { __u64 insn_mask; }; +/* pointer authentication keys (NT_ARM_PACA_KEYS, NT_ARM_PACG_KEYS) */ + +struct user_pac_address_keys { + __uint128_t apiakey; + __uint128_t apibkey; + __uint128_t apdakey; + __uint128_t apdbkey; +}; + +struct user_pac_generic_keys { + __uint128_t apgakey; +}; + #endif /* __ASSEMBLY__ */ #endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 9dce33b0e260..a86413be5a2d 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -979,6 +979,131 @@ static int pac_mask_get(struct task_struct *target, return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &uregs, 0, -1); } + +#ifdef CONFIG_CHECKPOINT_RESTORE +static __uint128_t pac_key_to_user(const struct ptrauth_key *key) +{ + return (__uint128_t)key->hi << 64 | key->lo; +} + +static struct ptrauth_key pac_key_from_user(__uint128_t ukey) +{ + struct ptrauth_key key = { + .lo = (unsigned long)ukey, + .hi = (unsigned long)(ukey >> 64), + }; + + return key; +} + +static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys, + const struct ptrauth_keys *keys) +{ + ukeys->apiakey = pac_key_to_user(&keys->apia); + ukeys->apibkey = pac_key_to_user(&keys->apib); + ukeys->apdakey = pac_key_to_user(&keys->apda); + ukeys->apdbkey = pac_key_to_user(&keys->apdb); +} + +static void pac_address_keys_from_user(struct ptrauth_keys *keys, + const struct user_pac_address_keys *ukeys) +{ + keys->apia = pac_key_from_user(ukeys->apiakey); + keys->apib = pac_key_from_user(ukeys->apibkey); + keys->apda = pac_key_from_user(ukeys->apdakey); + keys->apdb = pac_key_from_user(ukeys->apdbkey); +} + +static int pac_address_keys_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct ptrauth_keys *keys = &target->thread.keys_user; + struct user_pac_address_keys user_keys; + + if (!system_supports_address_auth()) + return -EINVAL; + + pac_address_keys_to_user(&user_keys, keys); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &user_keys, 0, -1); +} + +static int pac_address_keys_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct ptrauth_keys *keys = &target->thread.keys_user; + struct user_pac_address_keys user_keys; + int ret; + + if (!system_supports_address_auth()) + return -EINVAL; + + pac_address_keys_to_user(&user_keys, keys); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &user_keys, 0, -1); + if (ret) + return ret; + pac_address_keys_from_user(keys, &user_keys); + + return 0; +} + +static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys, + const struct ptrauth_keys *keys) +{ + ukeys->apgakey = pac_key_to_user(&keys->apga); +} + +static void pac_generic_keys_from_user(struct ptrauth_keys *keys, + const struct user_pac_generic_keys *ukeys) +{ + keys->apga = pac_key_from_user(ukeys->apgakey); +} + +static int pac_generic_keys_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct ptrauth_keys *keys = &target->thread.keys_user; + struct user_pac_generic_keys user_keys; + + if (!system_supports_generic_auth()) + return -EINVAL; + + pac_generic_keys_to_user(&user_keys, keys); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &user_keys, 0, -1); +} + +static int pac_generic_keys_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct ptrauth_keys *keys = &target->thread.keys_user; + struct user_pac_generic_keys user_keys; + int ret; + + if (!system_supports_generic_auth()) + return -EINVAL; + + pac_generic_keys_to_user(&user_keys, keys); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &user_keys, 0, -1); + if (ret) + return ret; + pac_generic_keys_from_user(keys, &user_keys); + + return 0; +} +#endif /* CONFIG_CHECKPOINT_RESTORE */ #endif /* CONFIG_ARM64_PTR_AUTH */ enum aarch64_regset { @@ -995,6 +1120,10 @@ enum aarch64_regset { #endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, +#ifdef CONFIG_CHECKPOINT_RESTORE + REGSET_PACA_KEYS, + REGSET_PACG_KEYS, +#endif #endif }; @@ -1074,6 +1203,24 @@ static const struct user_regset aarch64_regsets[] = { .get = pac_mask_get, /* this cannot be set dynamically */ }, +#ifdef CONFIG_CHECKPOINT_RESTORE + [REGSET_PACA_KEYS] = { + .core_note_type = NT_ARM_PACA_KEYS, + .n = sizeof(struct user_pac_address_keys) / sizeof(__uint128_t), + .size = sizeof(__uint128_t), + .align = sizeof(__uint128_t), + .get = pac_address_keys_get, + .set = pac_address_keys_set, + }, + [REGSET_PACG_KEYS] = { + .core_note_type = NT_ARM_PACG_KEYS, + .n = sizeof(struct user_pac_generic_keys) / sizeof(__uint128_t), + .size = sizeof(__uint128_t), + .align = sizeof(__uint128_t), + .get = pac_generic_keys_get, + .set = pac_generic_keys_set, + }, +#endif #endif }; diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index e4d6ddd93567..34c02e4290fe 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -421,6 +421,8 @@ typedef struct elf64_shdr { #define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */ #define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */ #define NT_ARM_PAC_MASK 0x406 /* ARM pointer authentication code masks */ +#define NT_ARM_PACA_KEYS 0x407 /* ARM pointer authentication address keys */ +#define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit v1.2.3 From 42bf4152d8a79f89f5456dee63a1f364fbce2dd6 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Tue, 29 Jan 2019 11:19:36 +0530 Subject: tee: add supp_nowait flag in tee_context struct This flag indicates that requests in this context should not wait for tee-supplicant daemon to be started if not present and just return with an error code. It is needed for requests which should be non-blocking in nature like ones arising from TEE based kernel drivers or any in kernel api that uses TEE internal client interface. Signed-off-by: Sumit Garg Reviewed-by: Daniel Thompson Signed-off-by: Jens Wiklander --- drivers/tee/optee/supp.c | 10 +++++++++- drivers/tee/tee_core.c | 13 +++++++++++++ include/linux/tee_drv.h | 6 ++++++ 3 files changed, 28 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/tee/optee/supp.c b/drivers/tee/optee/supp.c index 43626e15703a..92f56b8645e3 100644 --- a/drivers/tee/optee/supp.c +++ b/drivers/tee/optee/supp.c @@ -88,10 +88,18 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params, { struct optee *optee = tee_get_drvdata(ctx->teedev); struct optee_supp *supp = &optee->supp; - struct optee_supp_req *req = kzalloc(sizeof(*req), GFP_KERNEL); + struct optee_supp_req *req; bool interruptable; u32 ret; + /* + * Return in case there is no supplicant available and + * non-blocking request. + */ + if (!supp->ctx && ctx->supp_nowait) + return TEEC_ERROR_COMMUNICATION; + + req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return TEEC_ERROR_OUT_OF_MEMORY; diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index 7b2bb4c50058..adf2588282fc 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -106,6 +106,11 @@ static int tee_open(struct inode *inode, struct file *filp) if (IS_ERR(ctx)) return PTR_ERR(ctx); + /* + * Default user-space behaviour is to wait for tee-supplicant + * if not present for any requests in this context. + */ + ctx->supp_nowait = false; filp->private_data = ctx; return 0; } @@ -982,6 +987,14 @@ tee_client_open_context(struct tee_context *start, } while (IS_ERR(ctx) && PTR_ERR(ctx) != -ENOMEM); put_device(put_dev); + /* + * Default behaviour for in kernel client is to not wait for + * tee-supplicant if not present for any requests in this context. + * Also this flag could be configured again before call to + * tee_client_open_session() if any in kernel client requires + * different behaviour. + */ + ctx->supp_nowait = true; return ctx; } EXPORT_SYMBOL_GPL(tee_client_open_context); diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 6cfe05893a76..5076502c07d7 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -47,6 +47,11 @@ struct tee_shm_pool; * @releasing: flag that indicates if context is being released right now. * It is needed to break circular dependency on context during * shared memory release. + * @supp_nowait: flag that indicates that requests in this context should not + * wait for tee-supplicant daemon to be started if not present + * and just return with an error code. It is needed for requests + * that arises from TEE based kernel drivers that should be + * non-blocking in nature. */ struct tee_context { struct tee_device *teedev; @@ -54,6 +59,7 @@ struct tee_context { void *data; struct kref refcount; bool releasing; + bool supp_nowait; }; struct tee_param_memref { -- cgit v1.2.3 From 0fc1db9d105915021260eb241661b8e96f5c0f1a Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Tue, 29 Jan 2019 11:19:35 +0530 Subject: tee: add bus driver framework for TEE based devices Introduce a generic TEE bus driver concept for TEE based kernel drivers which would like to communicate with TEE based devices/services. Also add support in module device table for these new TEE based devices. In this TEE bus concept, devices/services are identified via Universally Unique Identifier (UUID) and drivers register a table of device UUIDs which they can support. So this TEE bus framework registers following apis: - match(): Iterates over the driver UUID table to find a corresponding match for device UUID. If a match is found, then this particular device is probed via corresponding probe api registered by the driver. This process happens whenever a device or a driver is registered with TEE bus. - uevent(): Notifies user-space (udev) whenever a new device is registered on this bus for auto-loading of modularized drivers. Also this framework allows for device enumeration to be specific to corresponding TEE implementation like OP-TEE etc. Signed-off-by: Sumit Garg Reviewed-by: Daniel Thompson Reviewed-by: Bhupesh Sharma Signed-off-by: Jens Wiklander --- drivers/tee/tee_core.c | 54 ++++++++++++++++++++++++++++++++++++--- include/linux/mod_devicetable.h | 9 +++++++ include/linux/tee_drv.h | 32 ++++++++++++++++++++++- scripts/mod/devicetable-offsets.c | 3 +++ scripts/mod/file2alias.c | 19 ++++++++++++++ 5 files changed, 112 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index adf2588282fc..25f3b9cc8908 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -15,7 +15,6 @@ #define pr_fmt(fmt) "%s: " fmt, __func__ #include -#include #include #include #include @@ -1040,6 +1039,39 @@ int tee_client_invoke_func(struct tee_context *ctx, } EXPORT_SYMBOL_GPL(tee_client_invoke_func); +static int tee_client_device_match(struct device *dev, + struct device_driver *drv) +{ + const struct tee_client_device_id *id_table; + struct tee_client_device *tee_device; + + id_table = to_tee_client_driver(drv)->id_table; + tee_device = to_tee_client_device(dev); + + while (!uuid_is_null(&id_table->uuid)) { + if (uuid_equal(&tee_device->id.uuid, &id_table->uuid)) + return 1; + id_table++; + } + + return 0; +} + +static int tee_client_device_uevent(struct device *dev, + struct kobj_uevent_env *env) +{ + uuid_t *dev_id = &to_tee_client_device(dev)->id.uuid; + + return add_uevent_var(env, "MODALIAS=tee:%pUb", dev_id); +} + +struct bus_type tee_bus_type = { + .name = "tee", + .match = tee_client_device_match, + .uevent = tee_client_device_uevent, +}; +EXPORT_SYMBOL_GPL(tee_bus_type); + static int __init tee_init(void) { int rc; @@ -1053,18 +1085,32 @@ static int __init tee_init(void) rc = alloc_chrdev_region(&tee_devt, 0, TEE_NUM_DEVICES, "tee"); if (rc) { pr_err("failed to allocate char dev region\n"); - class_destroy(tee_class); - tee_class = NULL; + goto out_unreg_class; + } + + rc = bus_register(&tee_bus_type); + if (rc) { + pr_err("failed to register tee bus\n"); + goto out_unreg_chrdev; } + return 0; + +out_unreg_chrdev: + unregister_chrdev_region(tee_devt, TEE_NUM_DEVICES); +out_unreg_class: + class_destroy(tee_class); + tee_class = NULL; + return rc; } static void __exit tee_exit(void) { + bus_unregister(&tee_bus_type); + unregister_chrdev_region(tee_devt, TEE_NUM_DEVICES); class_destroy(tee_class); tee_class = NULL; - unregister_chrdev_region(tee_devt, TEE_NUM_DEVICES); } subsys_initcall(tee_init); diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index f9bd2f34b99f..14eaeeb46f41 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -779,4 +779,13 @@ struct typec_device_id { kernel_ulong_t driver_data; }; +/** + * struct tee_client_device_id - tee based device identifier + * @uuid: For TEE based client devices we use the device uuid as + * the identifier. + */ +struct tee_client_device_id { + uuid_t uuid; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 5076502c07d7..56d7f1b4516d 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -15,11 +15,14 @@ #ifndef __TEE_DRV_H #define __TEE_DRV_H -#include +#include #include #include #include +#include #include +#include +#include /* * The file describes the API provided by the generic TEE driver to the @@ -544,4 +547,31 @@ static inline bool tee_param_is_memref(struct tee_param *param) } } +extern struct bus_type tee_bus_type; + +/** + * struct tee_client_device - tee based device + * @id: device identifier + * @dev: device structure + */ +struct tee_client_device { + struct tee_client_device_id id; + struct device dev; +}; + +#define to_tee_client_device(d) container_of(d, struct tee_client_device, dev) + +/** + * struct tee_client_driver - tee client driver + * @id_table: device id table supported by this driver + * @driver: driver structure + */ +struct tee_client_driver { + const struct tee_client_device_id *id_table; + struct device_driver driver; +}; + +#define to_tee_client_driver(d) \ + container_of(d, struct tee_client_driver, driver) + #endif /*__TEE_DRV_H*/ diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index 293004499b4d..160718383a71 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -225,5 +225,8 @@ int main(void) DEVID_FIELD(typec_device_id, svid); DEVID_FIELD(typec_device_id, mode); + DEVID(tee_client_device_id); + DEVID_FIELD(tee_client_device_id, uuid); + return 0; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index a37af7d71973..d0e41723627f 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -37,6 +37,9 @@ typedef unsigned char __u8; typedef struct { __u8 b[16]; } uuid_le; +typedef struct { + __u8 b[16]; +} uuid_t; /* Big exception to the "don't include kernel headers into userspace, which * even potentially has different endianness and word sizes, since @@ -1287,6 +1290,21 @@ static int do_typec_entry(const char *filename, void *symval, char *alias) return 1; } +/* Looks like: tee:uuid */ +static int do_tee_entry(const char *filename, void *symval, char *alias) +{ + DEF_FIELD(symval, tee_client_device_id, uuid); + + sprintf(alias, "tee:%02x%02x%02x%02x-%02x%02x-%02x%02x-%02x%02x-%02x%02x%02x%02x%02x%02x", + uuid.b[0], uuid.b[1], uuid.b[2], uuid.b[3], uuid.b[4], + uuid.b[5], uuid.b[6], uuid.b[7], uuid.b[8], uuid.b[9], + uuid.b[10], uuid.b[11], uuid.b[12], uuid.b[13], uuid.b[14], + uuid.b[15]); + + add_wildcard(alias); + return 1; +} + /* Does namelen bytes of name exactly match the symbol? */ static bool sym_is(const char *name, unsigned namelen, const char *symbol) { @@ -1357,6 +1375,7 @@ static const struct devtable devtable[] = { {"fslmc", SIZE_fsl_mc_device_id, do_fsl_mc_entry}, {"tbsvc", SIZE_tb_service_id, do_tbsvc_entry}, {"typec", SIZE_typec_device_id, do_typec_entry}, + {"tee", SIZE_tee_client_device_id, do_tee_entry}, }; /* Create MODULE_ALIAS() statements. -- cgit v1.2.3 From 0b6a2c9cf4a00f54a0916499ece8a5cf3cced385 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 1 Feb 2019 12:14:53 +0100 Subject: ALSA: isa: Avoid passing NULL to memory allocators We used to pass NULL to memory allocators for ISA devices due to historical reasons. But we prefer rather a proper device object to be assigned, so let's fix it by replacing snd_dma_isa_data() call with card->dev reference, and kill snd_dma_isa_data() definition. Reviewed-by: Christoph Hellwig Signed-off-by: Takashi Iwai --- Documentation/sound/kernel-api/writing-an-alsa-driver.rst | 10 +++++----- include/sound/memalloc.h | 1 - sound/isa/ad1816a/ad1816a_lib.c | 2 +- sound/isa/cmi8330.c | 2 +- sound/isa/es1688/es1688_lib.c | 2 +- sound/isa/es18xx.c | 2 +- sound/isa/gus/gus_pcm.c | 4 ++-- sound/isa/sb/sb16_main.c | 2 +- sound/isa/sb/sb8_main.c | 2 +- sound/isa/sscape.c | 7 ++++--- sound/isa/wss/wss_lib.c | 2 +- 11 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/Documentation/sound/kernel-api/writing-an-alsa-driver.rst b/Documentation/sound/kernel-api/writing-an-alsa-driver.rst index 7c2f2032d30a..6b154dbb02cc 100644 --- a/Documentation/sound/kernel-api/writing-an-alsa-driver.rst +++ b/Documentation/sound/kernel-api/writing-an-alsa-driver.rst @@ -3520,14 +3520,14 @@ allocator will try to get an area as large as possible within the given size. The second argument (type) and the third argument (device pointer) are -dependent on the bus. In the case of the ISA bus, pass -:c:func:`snd_dma_isa_data()` as the third argument with +dependent on the bus. For normal devices, pass the device pointer +(typically identical as ``card->dev``) to the third argument with ``SNDRV_DMA_TYPE_DEV`` type. For the continuous buffer unrelated to the bus can be pre-allocated with ``SNDRV_DMA_TYPE_CONTINUOUS`` type and the ``snd_dma_continuous_data(GFP_KERNEL)`` device pointer, where -``GFP_KERNEL`` is the kernel allocation flag to use. For the PCI -scatter-gather buffers, use ``SNDRV_DMA_TYPE_DEV_SG`` with -``snd_dma_pci_data(pci)`` (see the `Non-Contiguous Buffers`_ +``GFP_KERNEL`` is the kernel allocation flag to use. For the +scatter-gather buffers, use ``SNDRV_DMA_TYPE_DEV_SG`` with the device +pointer (see the `Non-Contiguous Buffers`_ section). Once the buffer is pre-allocated, you can use the allocator in the diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h index af3fa577fa06..1ac0dd82a916 100644 --- a/include/sound/memalloc.h +++ b/include/sound/memalloc.h @@ -37,7 +37,6 @@ struct snd_dma_device { }; #define snd_dma_pci_data(pci) (&(pci)->dev) -#define snd_dma_isa_data() NULL #define snd_dma_continuous_data(x) ((struct device *)(__force unsigned long)(x)) diff --git a/sound/isa/ad1816a/ad1816a_lib.c b/sound/isa/ad1816a/ad1816a_lib.c index 61e8c7e524db..94b381a78e9e 100644 --- a/sound/isa/ad1816a/ad1816a_lib.c +++ b/sound/isa/ad1816a/ad1816a_lib.c @@ -693,7 +693,7 @@ int snd_ad1816a_pcm(struct snd_ad1816a *chip, int device) snd_ad1816a_init(chip); snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, - snd_dma_isa_data(), + chip->card->dev, 64*1024, chip->dma1 > 3 || chip->dma2 > 3 ? 128*1024 : 64*1024); chip->pcm = pcm; diff --git a/sound/isa/cmi8330.c b/sound/isa/cmi8330.c index 7e5aa06414c4..1868b73aa49c 100644 --- a/sound/isa/cmi8330.c +++ b/sound/isa/cmi8330.c @@ -470,7 +470,7 @@ static int snd_cmi8330_pcm(struct snd_card *card, struct snd_cmi8330 *chip) snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &chip->streams[SNDRV_PCM_STREAM_CAPTURE].ops); snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, - snd_dma_isa_data(), + card->dev, 64*1024, 128*1024); chip->pcm = pcm; diff --git a/sound/isa/es1688/es1688_lib.c b/sound/isa/es1688/es1688_lib.c index 50cdce0e8946..da341969e650 100644 --- a/sound/isa/es1688/es1688_lib.c +++ b/sound/isa/es1688/es1688_lib.c @@ -746,7 +746,7 @@ int snd_es1688_pcm(struct snd_card *card, struct snd_es1688 *chip, int device) chip->pcm = pcm; snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, - snd_dma_isa_data(), + card->dev, 64*1024, 64*1024); return 0; } diff --git a/sound/isa/es18xx.c b/sound/isa/es18xx.c index 77aa9a27fb3b..07abc7f7840c 100644 --- a/sound/isa/es18xx.c +++ b/sound/isa/es18xx.c @@ -1717,7 +1717,7 @@ static int snd_es18xx_pcm(struct snd_card *card, int device) chip->pcm = pcm; snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, - snd_dma_isa_data(), + card->dev, 64*1024, chip->dma1 > 3 || chip->dma2 > 3 ? 128*1024 : 64*1024); return 0; diff --git a/sound/isa/gus/gus_pcm.c b/sound/isa/gus/gus_pcm.c index 131b28997e1d..b9efc6dff45d 100644 --- a/sound/isa/gus/gus_pcm.c +++ b/sound/isa/gus/gus_pcm.c @@ -891,7 +891,7 @@ int snd_gf1_pcm_new(struct snd_gus_card *gus, int pcm_dev, int control_index) for (substream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream; substream; substream = substream->next) snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV, - snd_dma_isa_data(), + card->dev, 64*1024, gus->gf1.dma1 > 3 ? 128*1024 : 64*1024); pcm->info_flags = 0; @@ -901,7 +901,7 @@ int snd_gf1_pcm_new(struct snd_gus_card *gus, int pcm_dev, int control_index) if (gus->gf1.dma2 == gus->gf1.dma1) pcm->info_flags |= SNDRV_PCM_INFO_HALF_DUPLEX; snd_pcm_lib_preallocate_pages(pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream, - SNDRV_DMA_TYPE_DEV, snd_dma_isa_data(), + SNDRV_DMA_TYPE_DEV, card->dev, 64*1024, gus->gf1.dma2 > 3 ? 128*1024 : 64*1024); } strcpy(pcm->name, pcm->id); diff --git a/sound/isa/sb/sb16_main.c b/sound/isa/sb/sb16_main.c index 981d65d122b6..473ec74ae48c 100644 --- a/sound/isa/sb/sb16_main.c +++ b/sound/isa/sb/sb16_main.c @@ -889,7 +889,7 @@ int snd_sb16dsp_pcm(struct snd_sb *chip, int device) } snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, - snd_dma_isa_data(), + card->dev, 64*1024, 128*1024); return 0; } diff --git a/sound/isa/sb/sb8_main.c b/sound/isa/sb/sb8_main.c index 8288fae90085..97645a732a71 100644 --- a/sound/isa/sb/sb8_main.c +++ b/sound/isa/sb/sb8_main.c @@ -610,7 +610,7 @@ int snd_sb8dsp_pcm(struct snd_sb *chip, int device) if (chip->dma8 > 3 || chip->dma16 >= 0) max_prealloc = 128 * 1024; snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, - snd_dma_isa_data(), + card->dev, 64*1024, max_prealloc); return 0; diff --git a/sound/isa/sscape.c b/sound/isa/sscape.c index 733adee5afbf..8181db4db019 100644 --- a/sound/isa/sscape.c +++ b/sound/isa/sscape.c @@ -167,12 +167,13 @@ static inline struct soundscape *get_card_soundscape(struct snd_card *c) * I think this means that the memory has to map to * contiguous pages of physical memory. */ -static struct snd_dma_buffer *get_dmabuf(struct snd_dma_buffer *buf, +static struct snd_dma_buffer *get_dmabuf(struct soundscape *s, + struct snd_dma_buffer *buf, unsigned long size) { if (buf) { if (snd_dma_alloc_pages_fallback(SNDRV_DMA_TYPE_DEV, - snd_dma_isa_data(), + s->chip->card->dev, size, buf) < 0) { snd_printk(KERN_ERR "sscape: Failed to allocate " "%lu bytes for DMA\n", @@ -443,7 +444,7 @@ static int upload_dma_data(struct soundscape *s, const unsigned char *data, int ret; unsigned char val; - if (!get_dmabuf(&dma, PAGE_ALIGN(32 * 1024))) + if (!get_dmabuf(s, &dma, PAGE_ALIGN(32 * 1024))) return -ENOMEM; spin_lock_irqsave(&s->lock, flags); diff --git a/sound/isa/wss/wss_lib.c b/sound/isa/wss/wss_lib.c index b11ef97bce1b..0dfb8065b403 100644 --- a/sound/isa/wss/wss_lib.c +++ b/sound/isa/wss/wss_lib.c @@ -1942,7 +1942,7 @@ int snd_wss_pcm(struct snd_wss *chip, int device) strcpy(pcm->name, snd_wss_chip_id(chip)); snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, - snd_dma_isa_data(), + chip->card->dev, 64*1024, chip->dma1 > 3 || chip->dma2 > 3 ? 128*1024 : 64*1024); chip->pcm = pcm; -- cgit v1.2.3 From d83525ca62cf8ebe3271d14c36fb900c294274a2 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 31 Jan 2019 15:40:04 -0800 Subject: bpf: introduce bpf_spin_lock Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let bpf program serialize access to other variables. Example: struct hash_elem { int cnt; struct bpf_spin_lock lock; }; struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key); if (val) { bpf_spin_lock(&val->lock); val->cnt++; bpf_spin_unlock(&val->lock); } Restrictions and safety checks: - bpf_spin_lock is only allowed inside HASH and ARRAY maps. - BTF description of the map is mandatory for safety analysis. - bpf program can take one bpf_spin_lock at a time, since two or more can cause dead locks. - only one 'struct bpf_spin_lock' is allowed per map element. It drastically simplifies implementation yet allows bpf program to use any number of bpf_spin_locks. - when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed. - bpf program must bpf_spin_unlock() before return. - bpf program can access 'struct bpf_spin_lock' only via bpf_spin_lock()/bpf_spin_unlock() helpers. - load/store into 'struct bpf_spin_lock lock;' field is not allowed. - to use bpf_spin_lock() helper the BTF description of map value must be a struct and have 'struct bpf_spin_lock anyname;' field at the top level. Nested lock inside another struct is not allowed. - syscall map_lookup doesn't copy bpf_spin_lock field to user space. - syscall map_update and program map_update do not update bpf_spin_lock field. - bpf_spin_lock cannot be on the stack or inside networking packet. bpf_spin_lock can only be inside HASH or ARRAY map value. - bpf_spin_lock is available to root only and to all program types. - bpf_spin_lock is not allowed in inner maps of map-in-map. - ld_abs is not allowed inside spin_lock-ed region. - tracing progs and socket filter progs cannot use bpf_spin_lock due to insufficient preemption checks Implementation details: - cgroup-bpf class of programs can nest with xdp/tc programs. Hence bpf_spin_lock is equivalent to spin_lock_irqsave. Other solutions to avoid nested bpf_spin_lock are possible. Like making sure that all networking progs run with softirq disabled. spin_lock_irqsave is the simplest and doesn't add overhead to the programs that don't use it. - arch_spinlock_t is used when its implemented as queued_spin_lock - archs can force their own arch_spinlock_t - on architectures where queued_spin_lock is not available and sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used. - presence of bpf_spin_lock inside map value could have been indicated via extra flag during map_create, but specifying it via BTF is cleaner. It provides introspection for map key/value and reduces user mistakes. Next steps: - allow bpf_spin_lock in other map types (like cgroup local storage) - introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper to request kernel to grab bpf_spin_lock before rewriting the value. That will serialize access to map elements. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 37 +++++++++- include/linux/bpf_verifier.h | 1 + include/linux/btf.h | 1 + include/uapi/linux/bpf.h | 7 +- kernel/Kconfig.locks | 3 + kernel/bpf/arraymap.c | 7 +- kernel/bpf/btf.c | 42 +++++++++++ kernel/bpf/core.c | 2 + kernel/bpf/hashtab.c | 21 +++--- kernel/bpf/helpers.c | 80 ++++++++++++++++++++ kernel/bpf/map_in_map.c | 5 ++ kernel/bpf/syscall.c | 21 +++++- kernel/bpf/verifier.c | 169 ++++++++++++++++++++++++++++++++++++++++++- net/core/filter.c | 16 +++- 14 files changed, 386 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0394f1f9213b..2ae615b48bb8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -72,14 +72,15 @@ struct bpf_map { u32 value_size; u32 max_entries; u32 map_flags; - u32 pages; + int spin_lock_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; struct btf *btf; + u32 pages; bool unpriv_array; - /* 55 bytes hole */ + /* 51 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. @@ -91,6 +92,34 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; }; +static inline bool map_value_has_spin_lock(const struct bpf_map *map) +{ + return map->spin_lock_off >= 0; +} + +static inline void check_and_init_map_lock(struct bpf_map *map, void *dst) +{ + if (likely(!map_value_has_spin_lock(map))) + return; + *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = + (struct bpf_spin_lock){}; +} + +/* copy everything but bpf_spin_lock */ +static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) +{ + if (unlikely(map_value_has_spin_lock(map))) { + u32 off = map->spin_lock_off; + + memcpy(dst, src, off); + memcpy(dst + off + sizeof(struct bpf_spin_lock), + src + off + sizeof(struct bpf_spin_lock), + map->value_size - off - sizeof(struct bpf_spin_lock)); + } else { + memcpy(dst, src, map->value_size); + } +} + struct bpf_offload_dev; struct bpf_offloaded_map; @@ -162,6 +191,7 @@ enum bpf_arg_type { ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock */ + ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ }; /* type of values returned from helper functions */ @@ -879,7 +909,8 @@ extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; extern const struct bpf_func_proto bpf_sk_redirect_map_proto; - +extern const struct bpf_func_proto bpf_spin_lock_proto; +extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; /* Shared helpers among cBPF and eBPF. */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 0620e418dde5..69f7a3449eda 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -148,6 +148,7 @@ struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; u32 curframe; + u32 active_spin_lock; bool speculative; }; diff --git a/include/linux/btf.h b/include/linux/btf.h index 12502e25e767..455d31b55828 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -50,6 +50,7 @@ u32 btf_id(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); +int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 60b99b730a41..86f7c438d40f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2422,7 +2422,9 @@ union bpf_attr { FN(map_peek_elem), \ FN(msg_push_data), \ FN(msg_pop_data), \ - FN(rc_pointer_rel), + FN(rc_pointer_rel), \ + FN(spin_lock), \ + FN(spin_unlock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3056,4 +3058,7 @@ struct bpf_line_info { __u32 line_col; }; +struct bpf_spin_lock { + __u32 val; +}; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 84d882f3e299..fbba478ae522 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -242,6 +242,9 @@ config QUEUED_SPINLOCKS def_bool y if ARCH_USE_QUEUED_SPINLOCKS depends on SMP +config BPF_ARCH_SPINLOCK + bool + config ARCH_USE_QUEUED_RWLOCKS bool diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 25632a75d630..d6d979910a2a 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -270,9 +270,10 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]), value, map->value_size); else - memcpy(array->value + - array->elem_size * (index & array->index_mask), - value, map->value_size); + copy_map_value(map, + array->value + + array->elem_size * (index & array->index_mask), + value); return 0; } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 3d661f0606fe..7019c1f05cab 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -355,6 +355,11 @@ static bool btf_type_is_struct(const struct btf_type *t) return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; } +static bool __btf_type_is_struct(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; +} + static bool btf_type_is_array(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; @@ -2045,6 +2050,43 @@ static void btf_struct_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } +/* find 'struct bpf_spin_lock' in map value. + * return >= 0 offset if found + * and < 0 in case of error + */ +int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t) +{ + const struct btf_member *member; + u32 i, off = -ENOENT; + + if (!__btf_type_is_struct(t)) + return -EINVAL; + + for_each_member(i, t, member) { + const struct btf_type *member_type = btf_type_by_id(btf, + member->type); + if (!__btf_type_is_struct(member_type)) + continue; + if (member_type->size != sizeof(struct bpf_spin_lock)) + continue; + if (strcmp(__btf_name_by_offset(btf, member_type->name_off), + "bpf_spin_lock")) + continue; + if (off != -ENOENT) + /* only one 'struct bpf_spin_lock' is allowed */ + return -E2BIG; + off = btf_member_bit_offset(t, member); + if (off % 8) + /* valid C code cannot generate such BTF */ + return -EINVAL; + off /= 8; + if (off % __alignof__(struct bpf_spin_lock)) + /* valid struct bpf_spin_lock will be 4 byte aligned */ + return -EINVAL; + } + return off; +} + static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct seq_file *m) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index f13c543b7b36..ef88b167959d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2002,6 +2002,8 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; +const struct bpf_func_proto bpf_spin_lock_proto __weak; +const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4b7c76765d9d..6d3b22c5ad68 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -718,21 +718,12 @@ static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) BITS_PER_LONG == 64; } -static u32 htab_size_value(const struct bpf_htab *htab, bool percpu) -{ - u32 size = htab->map.value_size; - - if (percpu || fd_htab_map_needs_adjust(htab)) - size = round_up(size, 8); - return size; -} - static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, bool percpu, bool onallcpus, struct htab_elem *old_elem) { - u32 size = htab_size_value(htab, percpu); + u32 size = htab->map.value_size; bool prealloc = htab_is_prealloc(htab); struct htab_elem *l_new, **pl_new; void __percpu *pptr; @@ -770,10 +761,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new = ERR_PTR(-ENOMEM); goto dec_count; } + check_and_init_map_lock(&htab->map, + l_new->key + round_up(key_size, 8)); } memcpy(l_new->key, key, key_size); if (percpu) { + size = round_up(size, 8); if (prealloc) { pptr = htab_elem_get_ptr(l_new, key_size); } else { @@ -791,8 +785,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, if (!prealloc) htab_elem_set_ptr(l_new, key_size, pptr); - } else { + } else if (fd_htab_map_needs_adjust(htab)) { + size = round_up(size, 8); memcpy(l_new->key + round_up(key_size, 8), value, size); + } else { + copy_map_value(&htab->map, + l_new->key + round_up(key_size, 8), + value); } l_new->hash = hash; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a74972b07e74..fbe544761628 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -221,6 +221,86 @@ const struct bpf_func_proto bpf_get_current_comm_proto = { .arg2_type = ARG_CONST_SIZE, }; +#if defined(CONFIG_QUEUED_SPINLOCKS) || defined(CONFIG_BPF_ARCH_SPINLOCK) + +static inline void __bpf_spin_lock(struct bpf_spin_lock *lock) +{ + arch_spinlock_t *l = (void *)lock; + union { + __u32 val; + arch_spinlock_t lock; + } u = { .lock = __ARCH_SPIN_LOCK_UNLOCKED }; + + compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0"); + BUILD_BUG_ON(sizeof(*l) != sizeof(__u32)); + BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32)); + arch_spin_lock(l); +} + +static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) +{ + arch_spinlock_t *l = (void *)lock; + + arch_spin_unlock(l); +} + +#else + +static inline void __bpf_spin_lock(struct bpf_spin_lock *lock) +{ + atomic_t *l = (void *)lock; + + BUILD_BUG_ON(sizeof(*l) != sizeof(*lock)); + do { + atomic_cond_read_relaxed(l, !VAL); + } while (atomic_xchg(l, 1)); +} + +static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) +{ + atomic_t *l = (void *)lock; + + atomic_set_release(l, 0); +} + +#endif + +static DEFINE_PER_CPU(unsigned long, irqsave_flags); + +notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +{ + unsigned long flags; + + local_irq_save(flags); + __bpf_spin_lock(lock); + __this_cpu_write(irqsave_flags, flags); + return 0; +} + +const struct bpf_func_proto bpf_spin_lock_proto = { + .func = bpf_spin_lock, + .gpl_only = false, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_SPIN_LOCK, +}; + +notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +{ + unsigned long flags; + + flags = __this_cpu_read(irqsave_flags); + __bpf_spin_unlock(lock); + local_irq_restore(flags); + return 0; +} + +const struct bpf_func_proto bpf_spin_unlock_proto = { + .func = bpf_spin_unlock, + .gpl_only = false, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_SPIN_LOCK, +}; + #ifdef CONFIG_CGROUPS BPF_CALL_0(bpf_get_current_cgroup_id) { diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 52378d3e34b3..583346a0ab29 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -37,6 +37,11 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) return ERR_PTR(-EINVAL); } + if (map_value_has_spin_lock(inner_map)) { + fdput(f); + return ERR_PTR(-ENOTSUPP); + } + inner_map_meta_size = sizeof(*inner_map_meta); /* In some cases verifier needs to access beyond just base map. */ if (inner_map->ops == &array_map_ops) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b155cd17c1bd..ebf0a673cb83 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -463,7 +463,7 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(const struct bpf_map *map, const struct btf *btf, +static int map_check_btf(struct bpf_map *map, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; @@ -478,6 +478,21 @@ static int map_check_btf(const struct bpf_map *map, const struct btf *btf, if (!value_type || value_size != map->value_size) return -EINVAL; + map->spin_lock_off = btf_find_spin_lock(btf, value_type); + + if (map_value_has_spin_lock(map)) { + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY) + return -ENOTSUPP; + if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > + map->value_size) { + WARN_ONCE(1, + "verifier bug spin_lock_off %d value_size %d\n", + map->spin_lock_off, map->value_size); + return -EFAULT; + } + } + if (map->ops->map_check_btf) ret = map->ops->map_check_btf(map, btf, key_type, value_type); @@ -542,6 +557,8 @@ static int map_create(union bpf_attr *attr) map->btf = btf; map->btf_key_type_id = attr->btf_key_type_id; map->btf_value_type_id = attr->btf_value_type_id; + } else { + map->spin_lock_off = -EINVAL; } err = security_bpf_map_alloc(map); @@ -740,7 +757,7 @@ static int map_lookup_elem(union bpf_attr *attr) err = -ENOENT; } else { err = 0; - memcpy(value, ptr, value_size); + copy_map_value(map, value, ptr); } rcu_read_unlock(); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8c1c21cd50b4..38892bdee651 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -213,6 +213,7 @@ struct bpf_call_arg_meta { s64 msize_smax_value; u64 msize_umax_value; int ptr_id; + int func_id; }; static DEFINE_MUTEX(bpf_verifier_lock); @@ -351,6 +352,12 @@ static bool reg_is_refcounted(const struct bpf_reg_state *reg) return type_is_refcounted(reg->type); } +static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) +{ + return reg->type == PTR_TO_MAP_VALUE && + map_value_has_spin_lock(reg->map_ptr); +} + static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) { return type_is_refcounted_or_null(reg->type); @@ -712,6 +719,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, } dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; + dst_state->active_spin_lock = src->active_spin_lock; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -1483,6 +1491,21 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, if (err) verbose(env, "R%d max value is outside of the array range\n", regno); + + if (map_value_has_spin_lock(reg->map_ptr)) { + u32 lock = reg->map_ptr->spin_lock_off; + + /* if any part of struct bpf_spin_lock can be touched by + * load/store reject this program. + * To check that [x1, x2) overlaps with [y1, y2) + * it is sufficient to check x1 < y2 && y1 < x2. + */ + if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) && + lock < reg->umax_value + off + size) { + verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n"); + return -EACCES; + } + } return err; } @@ -2192,6 +2215,91 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, } } +/* Implementation details: + * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL + * Two bpf_map_lookups (even with the same key) will have different reg->id. + * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after + * value_or_null->value transition, since the verifier only cares about + * the range of access to valid map value pointer and doesn't care about actual + * address of the map element. + * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps + * reg->id > 0 after value_or_null->value transition. By doing so + * two bpf_map_lookups will be considered two different pointers that + * point to different bpf_spin_locks. + * The verifier allows taking only one bpf_spin_lock at a time to avoid + * dead-locks. + * Since only one bpf_spin_lock is allowed the checks are simpler than + * reg_is_refcounted() logic. The verifier needs to remember only + * one spin_lock instead of array of acquired_refs. + * cur_state->active_spin_lock remembers which map value element got locked + * and clears it after bpf_spin_unlock. + */ +static int process_spin_lock(struct bpf_verifier_env *env, int regno, + bool is_lock) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + struct bpf_verifier_state *cur = env->cur_state; + bool is_const = tnum_is_const(reg->var_off); + struct bpf_map *map = reg->map_ptr; + u64 val = reg->var_off.value; + + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "R%d is not a pointer to map_value\n", regno); + return -EINVAL; + } + if (!is_const) { + verbose(env, + "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n", + regno); + return -EINVAL; + } + if (!map->btf) { + verbose(env, + "map '%s' has to have BTF in order to use bpf_spin_lock\n", + map->name); + return -EINVAL; + } + if (!map_value_has_spin_lock(map)) { + if (map->spin_lock_off == -E2BIG) + verbose(env, + "map '%s' has more than one 'struct bpf_spin_lock'\n", + map->name); + else if (map->spin_lock_off == -ENOENT) + verbose(env, + "map '%s' doesn't have 'struct bpf_spin_lock'\n", + map->name); + else + verbose(env, + "map '%s' is not a struct type or bpf_spin_lock is mangled\n", + map->name); + return -EINVAL; + } + if (map->spin_lock_off != val + reg->off) { + verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n", + val + reg->off); + return -EINVAL; + } + if (is_lock) { + if (cur->active_spin_lock) { + verbose(env, + "Locking two bpf_spin_locks are not allowed\n"); + return -EINVAL; + } + cur->active_spin_lock = reg->id; + } else { + if (!cur->active_spin_lock) { + verbose(env, "bpf_spin_unlock without taking a lock\n"); + return -EINVAL; + } + if (cur->active_spin_lock != reg->id) { + verbose(env, "bpf_spin_unlock of different lock\n"); + return -EINVAL; + } + cur->active_spin_lock = 0; + } + return 0; +} + static bool arg_type_is_mem_ptr(enum bpf_arg_type type) { return type == ARG_PTR_TO_MEM || @@ -2268,6 +2376,17 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return -EFAULT; } meta->ptr_id = reg->id; + } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { + if (meta->func_id == BPF_FUNC_spin_lock) { + if (process_spin_lock(env, regno, true)) + return -EACCES; + } else if (meta->func_id == BPF_FUNC_spin_unlock) { + if (process_spin_lock(env, regno, false)) + return -EACCES; + } else { + verbose(env, "verifier internal error\n"); + return -EFAULT; + } } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be @@ -2887,6 +3006,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } + meta.func_id = func_id; /* check args */ err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta); if (err) @@ -4473,7 +4593,8 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { reg->type = PTR_TO_SOCKET; } - if (is_null || !reg_is_refcounted(reg)) { + if (is_null || !(reg_is_refcounted(reg) || + reg_may_point_to_spin_lock(reg))) { /* We don't need id from this point onwards anymore, * thus we should better reset it, so that state * pruning has chances to take effect. @@ -4871,6 +4992,11 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } + if (env->cur_state->active_spin_lock) { + verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); + return -EINVAL; + } + if (regs[BPF_REG_6].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); @@ -5607,8 +5733,11 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_MAP_VALUE: /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. - * We don't care about the 'id' value, because nothing - * uses it for PTR_TO_MAP_VALUE (only for ..._OR_NULL) + * 'id' is not compared, since it's only used for maps with + * bpf_spin_lock inside map element and in such cases if + * the rest of the prog is valid for one map element then + * it's valid for all map elements regardless of the key + * used in bpf_map_lookup() */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && range_within(rold, rcur) && @@ -5811,6 +5940,9 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->speculative && !cur->speculative) return false; + if (old->active_spin_lock != cur->active_spin_lock) + return false; + /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ @@ -6229,6 +6361,12 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } + if (env->cur_state->active_spin_lock && + (insn->src_reg == BPF_PSEUDO_CALL || + insn->imm != BPF_FUNC_spin_unlock)) { + verbose(env, "function calls are not allowed while holding a lock\n"); + return -EINVAL; + } if (insn->src_reg == BPF_PSEUDO_CALL) err = check_func_call(env, insn, &env->insn_idx); else @@ -6259,6 +6397,11 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } + if (env->cur_state->active_spin_lock) { + verbose(env, "bpf_spin_unlock is missing\n"); + return -EINVAL; + } + if (state->curframe) { /* exit from nested function */ env->prev_insn_idx = env->insn_idx; @@ -6356,6 +6499,19 @@ static int check_map_prealloc(struct bpf_map *map) !(map->map_flags & BPF_F_NO_PREALLOC); } +static bool is_tracing_prog_type(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + return true; + default: + return false; + } +} + static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) @@ -6378,6 +6534,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if ((is_tracing_prog_type(prog->type) || + prog->type == BPF_PROG_TYPE_SOCKET_FILTER) && + map_value_has_spin_lock(map)) { + verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); + return -EINVAL; + } + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); diff --git a/net/core/filter.c b/net/core/filter.c index 41984ad4b9b4..3a49f68eda10 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5314,10 +5314,20 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_tail_call_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; + default: + break; + } + + if (!capable(CAP_SYS_ADMIN)) + return NULL; + + switch (func_id) { + case BPF_FUNC_spin_lock: + return &bpf_spin_lock_proto; + case BPF_FUNC_spin_unlock: + return &bpf_spin_unlock_proto; case BPF_FUNC_trace_printk: - if (capable(CAP_SYS_ADMIN)) - return bpf_get_trace_printk_proto(); - /* else, fall through */ + return bpf_get_trace_printk_proto(); default: return NULL; } -- cgit v1.2.3 From 96049f3afd50fe8db69fa0068cdca822e747b1e4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 31 Jan 2019 15:40:09 -0800 Subject: bpf: introduce BPF_F_LOCK flag Introduce BPF_F_LOCK flag for map_lookup and map_update syscall commands and for map_update() helper function. In all these cases take a lock of existing element (which was provided in BTF description) before copying (in or out) the rest of map value. Implementation details that are part of uapi: Array: The array map takes the element lock for lookup/update. Hash: hash map also takes the lock for lookup/update and tries to avoid the bucket lock. If old element exists it takes the element lock and updates the element in place. If element doesn't exist it allocates new one and inserts into hash table while holding the bucket lock. In rare case the hashmap has to take both the bucket lock and the element lock to update old value in place. Cgroup local storage: It is similar to array. update in place and lookup are done with lock taken. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 1 + kernel/bpf/arraymap.c | 24 ++++++++++++++++-------- kernel/bpf/hashtab.c | 42 +++++++++++++++++++++++++++++++++++++++--- kernel/bpf/helpers.c | 16 ++++++++++++++++ kernel/bpf/local_storage.c | 14 +++++++++++++- kernel/bpf/syscall.c | 25 +++++++++++++++++++++++-- 7 files changed, 110 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2ae615b48bb8..bd169a7bcc93 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -119,6 +119,8 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) memcpy(dst, src, map->value_size); } } +void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, + bool lock_src); struct bpf_offload_dev; struct bpf_offloaded_map; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 86f7c438d40f..1777fa0c61e4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -267,6 +267,7 @@ enum bpf_attach_type { #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */ /* flags for BPF_MAP_CREATE command */ #define BPF_F_NO_PREALLOC (1U << 0) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index d6d979910a2a..c72e0d8e1e65 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -253,8 +253,9 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; + char *val; - if (unlikely(map_flags > BPF_EXIST)) + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST)) /* unknown flags */ return -EINVAL; @@ -262,18 +263,25 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, /* all elements were pre-allocated, cannot insert a new one */ return -E2BIG; - if (unlikely(map_flags == BPF_NOEXIST)) + if (unlikely(map_flags & BPF_NOEXIST)) /* all elements already exist */ return -EEXIST; - if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + if (unlikely((map_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map))) + return -EINVAL; + + if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]), value, map->value_size); - else - copy_map_value(map, - array->value + - array->elem_size * (index & array->index_mask), - value); + } else { + val = array->value + + array->elem_size * (index & array->index_mask); + if (map_flags & BPF_F_LOCK) + copy_map_value_locked(map, val, value, false); + else + copy_map_value(map, val, value); + } return 0; } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 6d3b22c5ad68..937776531998 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -804,11 +804,11 @@ dec_count: static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, u64 map_flags) { - if (l_old && map_flags == BPF_NOEXIST) + if (l_old && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) /* elem already exists */ return -EEXIST; - if (!l_old && map_flags == BPF_EXIST) + if (!l_old && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) /* elem doesn't exist, cannot update it */ return -ENOENT; @@ -827,7 +827,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, u32 key_size, hash; int ret; - if (unlikely(map_flags > BPF_EXIST)) + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST)) /* unknown flags */ return -EINVAL; @@ -840,6 +840,28 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, b = __select_bucket(htab, hash); head = &b->head; + if (unlikely(map_flags & BPF_F_LOCK)) { + if (unlikely(!map_value_has_spin_lock(map))) + return -EINVAL; + /* find an element without taking the bucket lock */ + l_old = lookup_nulls_elem_raw(head, hash, key, key_size, + htab->n_buckets); + ret = check_flags(htab, l_old, map_flags); + if (ret) + return ret; + if (l_old) { + /* grab the element lock and update value in place */ + copy_map_value_locked(map, + l_old->key + round_up(key_size, 8), + value, false); + return 0; + } + /* fall through, grab the bucket lock and lookup again. + * 99.9% chance that the element won't be found, + * but second lookup under lock has to be done. + */ + } + /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); @@ -849,6 +871,20 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (ret) goto err; + if (unlikely(l_old && (map_flags & BPF_F_LOCK))) { + /* first lookup without the bucket lock didn't find the element, + * but second lookup with the bucket lock found it. + * This case is highly unlikely, but has to be dealt with: + * grab the element lock in addition to the bucket lock + * and update element in place + */ + copy_map_value_locked(map, + l_old->key + round_up(key_size, 8), + value, false); + ret = 0; + goto err; + } + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false, l_old); if (IS_ERR(l_new)) { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index fbe544761628..a411fc17d265 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -301,6 +301,22 @@ const struct bpf_func_proto bpf_spin_unlock_proto = { .arg1_type = ARG_PTR_TO_SPIN_LOCK, }; +void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, + bool lock_src) +{ + struct bpf_spin_lock *lock; + + if (lock_src) + lock = src + map->spin_lock_off; + else + lock = dst + map->spin_lock_off; + preempt_disable(); + ____bpf_spin_lock(lock); + copy_map_value(map, dst, src); + ____bpf_spin_unlock(lock); + preempt_enable(); +} + #ifdef CONFIG_CGROUPS BPF_CALL_0(bpf_get_current_cgroup_id) { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 0295427f06e2..6b572e2de7fb 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -131,7 +131,14 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, struct bpf_cgroup_storage *storage; struct bpf_storage_buffer *new; - if (flags != BPF_ANY && flags != BPF_EXIST) + if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST | BPF_NOEXIST))) + return -EINVAL; + + if (unlikely(flags & BPF_NOEXIST)) + return -EINVAL; + + if (unlikely((flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map))) return -EINVAL; storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map, @@ -139,6 +146,11 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, if (!storage) return -ENOENT; + if (flags & BPF_F_LOCK) { + copy_map_value_locked(map, storage->buf->data, value, false); + return 0; + } + new = kmalloc_node(sizeof(struct bpf_storage_buffer) + map->value_size, __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b29e6dc44650..0834958f1dc4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -682,7 +682,7 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value +#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags static int map_lookup_elem(union bpf_attr *attr) { @@ -698,6 +698,9 @@ static int map_lookup_elem(union bpf_attr *attr) if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; + if (attr->flags & ~BPF_F_LOCK) + return -EINVAL; + f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) @@ -708,6 +711,12 @@ static int map_lookup_elem(union bpf_attr *attr) goto err_put; } + if ((attr->flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + err = -EINVAL; + goto err_put; + } + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -758,7 +767,13 @@ static int map_lookup_elem(union bpf_attr *attr) err = -ENOENT; } else { err = 0; - copy_map_value(map, value, ptr); + if (attr->flags & BPF_F_LOCK) + /* lock 'ptr' and copy everything but lock */ + copy_map_value_locked(map, value, ptr, true); + else + copy_map_value(map, value, ptr); + /* mask lock, since value wasn't zero inited */ + check_and_init_map_lock(map, value); } rcu_read_unlock(); } @@ -818,6 +833,12 @@ static int map_update_elem(union bpf_attr *attr) goto err_put; } + if ((attr->flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + err = -EINVAL; + goto err_put; + } + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); -- cgit v1.2.3 From fb99bce7120014307dde57b3d7def6977a9a62a1 Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Wed, 30 Jan 2019 21:58:05 +0000 Subject: net: tls: Support 256 bit keys Wire up support for 256 bit keys from the setsockopt to the crypto framework Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- include/net/tls.h | 5 +++- include/uapi/linux/tls.h | 15 ++++++++++ net/tls/tls_main.c | 33 +++++++++++++++++++-- net/tls/tls_sw.c | 29 +++++++++++++++--- tools/testing/selftests/net/tls.c | 62 +++++++++++++++++++++++++++++++++++++++ 5 files changed, 137 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 4592606e136a..da616db48413 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -206,7 +206,10 @@ struct cipher_context { union tls_crypto_context { struct tls_crypto_info info; - struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; + union { + struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; + struct tls12_crypto_info_aes_gcm_256 aes_gcm_256; + }; }; struct tls_context { diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index ff02287495ac..9affceaa3db4 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -59,6 +59,13 @@ #define TLS_CIPHER_AES_GCM_128_TAG_SIZE 16 #define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE 8 +#define TLS_CIPHER_AES_GCM_256 52 +#define TLS_CIPHER_AES_GCM_256_IV_SIZE 8 +#define TLS_CIPHER_AES_GCM_256_KEY_SIZE 32 +#define TLS_CIPHER_AES_GCM_256_SALT_SIZE 4 +#define TLS_CIPHER_AES_GCM_256_TAG_SIZE 16 +#define TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE 8 + #define TLS_SET_RECORD_TYPE 1 #define TLS_GET_RECORD_TYPE 2 @@ -75,4 +82,12 @@ struct tls12_crypto_info_aes_gcm_128 { unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE]; }; +struct tls12_crypto_info_aes_gcm_256 { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_AES_GCM_256_IV_SIZE]; + unsigned char key[TLS_CIPHER_AES_GCM_256_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_AES_GCM_256_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE]; +}; + #endif /* _UAPI_LINUX_TLS_H */ diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index d36d095cbcf0..0f028cfdf835 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -372,6 +372,30 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, rc = -EFAULT; break; } + case TLS_CIPHER_AES_GCM_256: { + struct tls12_crypto_info_aes_gcm_256 * + crypto_info_aes_gcm_256 = + container_of(crypto_info, + struct tls12_crypto_info_aes_gcm_256, + info); + + if (len != sizeof(*crypto_info_aes_gcm_256)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(crypto_info_aes_gcm_256->iv, + ctx->tx.iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, + TLS_CIPHER_AES_GCM_256_IV_SIZE); + memcpy(crypto_info_aes_gcm_256->rec_seq, ctx->tx.rec_seq, + TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE); + release_sock(sk); + if (copy_to_user(optval, + crypto_info_aes_gcm_256, + sizeof(*crypto_info_aes_gcm_256))) + rc = -EFAULT; + break; + } default: rc = -EINVAL; } @@ -412,6 +436,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { struct tls_crypto_info *crypto_info; struct tls_context *ctx = tls_get_ctx(sk); + size_t optsize; int rc = 0; int conf; @@ -444,8 +469,12 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } switch (crypto_info->cipher_type) { - case TLS_CIPHER_AES_GCM_128: { - if (optlen != sizeof(struct tls12_crypto_info_aes_gcm_128)) { + case TLS_CIPHER_AES_GCM_128: + case TLS_CIPHER_AES_GCM_256: { + optsize = crypto_info->cipher_type == TLS_CIPHER_AES_GCM_128 ? + sizeof(struct tls12_crypto_info_aes_gcm_128) : + sizeof(struct tls12_crypto_info_aes_gcm_256); + if (optlen != optsize) { rc = -EINVAL; goto err_crypto_info; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 3f2a6af27e62..9326c06c2ffe 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1999,6 +1999,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; + struct tls12_crypto_info_aes_gcm_256 *gcm_256_info; struct tls_sw_context_tx *sw_ctx_tx = NULL; struct tls_sw_context_rx *sw_ctx_rx = NULL; struct cipher_context *cctx; @@ -2006,7 +2007,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) struct strp_callbacks cb; u16 nonce_size, tag_size, iv_size, rec_seq_size; struct crypto_tfm *tfm; - char *iv, *rec_seq; + char *iv, *rec_seq, *key, *salt; + size_t keysize; int rc = 0; if (!ctx) { @@ -2067,6 +2069,24 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq; gcm_128_info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info; + keysize = TLS_CIPHER_AES_GCM_128_KEY_SIZE; + key = gcm_128_info->key; + salt = gcm_128_info->salt; + break; + } + case TLS_CIPHER_AES_GCM_256: { + nonce_size = TLS_CIPHER_AES_GCM_256_IV_SIZE; + tag_size = TLS_CIPHER_AES_GCM_256_TAG_SIZE; + iv_size = TLS_CIPHER_AES_GCM_256_IV_SIZE; + iv = ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->iv; + rec_seq_size = TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE; + rec_seq = + ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->rec_seq; + gcm_256_info = + (struct tls12_crypto_info_aes_gcm_256 *)crypto_info; + keysize = TLS_CIPHER_AES_GCM_256_KEY_SIZE; + key = gcm_256_info->key; + salt = gcm_256_info->salt; break; } default: @@ -2090,7 +2110,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) rc = -ENOMEM; goto free_priv; } - memcpy(cctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + /* Note: 128 & 256 bit salt are the same size */ + memcpy(cctx->iv, salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); memcpy(cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); cctx->rec_seq_size = rec_seq_size; cctx->rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL); @@ -2110,8 +2131,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ctx->push_pending_record = tls_sw_push_pending_record; - rc = crypto_aead_setkey(*aead, gcm_128_info->key, - TLS_CIPHER_AES_GCM_128_KEY_SIZE); + rc = crypto_aead_setkey(*aead, key, keysize); + if (rc) goto free_aead; diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index ff68ed19c0ef..c356f481de79 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -763,4 +763,66 @@ TEST_F(tls, control_msg) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST(keysizes) { + struct tls12_crypto_info_aes_gcm_256 tls12; + struct sockaddr_in addr; + int sfd, ret, fd, cfd; + socklen_t len; + bool notls; + + notls = false; + len = sizeof(addr); + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_2_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret != 0) { + notls = true; + printf("Failure setting TCP_ULP, testing without tls\n"); + } + + if (!notls) { + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + } + + cfd = accept(sfd, &addr, &len); + ASSERT_GE(cfd, 0); + + if (!notls) { + ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", + sizeof("tls")); + EXPECT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + } + + close(sfd); + close(fd); + close(cfd); +} + TEST_HARNESS_MAIN -- cgit v1.2.3 From a2ef9b6a22bd22841bde53e52cc50476fb4d1a5d Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Wed, 30 Jan 2019 21:58:12 +0000 Subject: net: tls: Refactor tls aad space size calculation TLS 1.3 has a different AAD size, use a variable in the code to make TLS 1.3 support easy. Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- include/net/tls.h | 1 + net/tls/tls_sw.c | 17 +++++++++-------- 2 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index da616db48413..754b130672f0 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -202,6 +202,7 @@ struct cipher_context { char *iv; u16 rec_seq_size; char *rec_seq; + u16 aad_size; }; union tls_crypto_context { diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9326c06c2ffe..7b6386f4c685 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -185,7 +185,7 @@ static int tls_do_decryption(struct sock *sk, int ret; aead_request_set_tfm(aead_req, ctx->aead_recv); - aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); + aead_request_set_ad(aead_req, tls_ctx->rx.aad_size); aead_request_set_crypt(aead_req, sgin, sgout, data_len + tls_ctx->rx.tag_size, (u8 *)iv_recv); @@ -289,12 +289,12 @@ static struct tls_rec *tls_get_rec(struct sock *sk) sg_init_table(rec->sg_aead_in, 2); sg_set_buf(&rec->sg_aead_in[0], rec->aad_space, - sizeof(rec->aad_space)); + tls_ctx->tx.aad_size); sg_unmark_end(&rec->sg_aead_in[1]); sg_init_table(rec->sg_aead_out, 2); sg_set_buf(&rec->sg_aead_out[0], rec->aad_space, - sizeof(rec->aad_space)); + tls_ctx->tx.aad_size); sg_unmark_end(&rec->sg_aead_out[1]); return rec; @@ -455,7 +455,7 @@ static int tls_do_encryption(struct sock *sk, msg_en->sg.curr = start; aead_request_set_tfm(aead_req, ctx->aead_send); - aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); + aead_request_set_ad(aead_req, tls_ctx->tx.aad_size); aead_request_set_crypt(aead_req, rec->sg_aead_in, rec->sg_aead_out, data_len, rec->iv_data); @@ -1317,7 +1317,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, aead_size = sizeof(*aead_req) + crypto_aead_reqsize(ctx->aead_recv); mem_size = aead_size + (nsg * sizeof(struct scatterlist)); - mem_size = mem_size + TLS_AAD_SPACE_SIZE; + mem_size = mem_size + tls_ctx->rx.aad_size; mem_size = mem_size + crypto_aead_ivsize(ctx->aead_recv); /* Allocate a single block of memory which contains @@ -1333,7 +1333,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, sgin = (struct scatterlist *)(mem + aead_size); sgout = sgin + n_sgin; aad = (u8 *)(sgout + n_sgout); - iv = aad + TLS_AAD_SPACE_SIZE; + iv = aad + tls_ctx->rx.aad_size; /* Prepare IV */ err = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE, @@ -1352,7 +1352,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, /* Prepare sgin */ sg_init_table(sgin, n_sgin); - sg_set_buf(&sgin[0], aad, TLS_AAD_SPACE_SIZE); + sg_set_buf(&sgin[0], aad, tls_ctx->rx.aad_size); err = skb_to_sgvec(skb, &sgin[1], rxm->offset + tls_ctx->rx.prepend_size, rxm->full_len - tls_ctx->rx.prepend_size); @@ -1364,7 +1364,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, if (n_sgout) { if (out_iov) { sg_init_table(sgout, n_sgout); - sg_set_buf(&sgout[0], aad, TLS_AAD_SPACE_SIZE); + sg_set_buf(&sgout[0], aad, tls_ctx->rx.aad_size); *chunk = 0; err = tls_setup_from_iter(sk, out_iov, data_len, @@ -2100,6 +2100,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto free_priv; } + cctx->aad_size = TLS_AAD_SPACE_SIZE; cctx->prepend_size = TLS_HEADER_SIZE + nonce_size; cctx->tag_size = tag_size; cctx->overhead_size = cctx->prepend_size + cctx->tag_size; -- cgit v1.2.3 From 130b392c6cd6b2aed1b7eb32253d4920babb4891 Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Wed, 30 Jan 2019 21:58:31 +0000 Subject: net: tls: Add tls 1.3 support TLS 1.3 has minor changes from TLS 1.2 at the record layer. * Header now hardcodes the same version and application content type in the header. * The real content type is appended after the data, before encryption (or after decryption). * The IV is xored with the sequence number, instead of concatinating four bytes of IV with the explicit IV. * Zero-padding: No exlicit length is given, we search backwards from the end of the decrypted data for the first non-zero byte, which is the content type. Currently recv supports reading zero-padding, but there is no way for send to add zero padding. Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- include/net/tls.h | 66 +++++++++++++++++------- include/uapi/linux/tls.h | 4 ++ net/tls/tls_device.c | 5 +- net/tls/tls_device_fallback.c | 3 +- net/tls/tls_main.c | 3 +- net/tls/tls_sw.c | 116 ++++++++++++++++++++++++++++++++++-------- 6 files changed, 154 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 754b130672f0..004bf01ce868 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -119,6 +119,9 @@ struct tls_rec { /* AAD | msg_encrypted.sg.data (data contains overhead for hdr & iv & tag) */ struct scatterlist sg_aead_out[2]; + char content_type; + struct scatterlist sg_content_type; + char aad_space[TLS_AAD_SPACE_SIZE]; u8 iv_data[TLS_CIPHER_AES_GCM_128_IV_SIZE + TLS_CIPHER_AES_GCM_128_SALT_SIZE]; @@ -203,6 +206,7 @@ struct cipher_context { u16 rec_seq_size; char *rec_seq; u16 aad_size; + u16 tail_size; }; union tls_crypto_context { @@ -397,49 +401,77 @@ static inline bool tls_bigint_increment(unsigned char *seq, int len) } static inline void tls_advance_record_sn(struct sock *sk, - struct cipher_context *ctx) + struct cipher_context *ctx, + int version) { if (tls_bigint_increment(ctx->rec_seq, ctx->rec_seq_size)) tls_err_abort(sk, EBADMSG); - tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, - ctx->iv_size); + + if (version != TLS_1_3_VERSION) { + tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + ctx->iv_size); + } } static inline void tls_fill_prepend(struct tls_context *ctx, char *buf, size_t plaintext_len, - unsigned char record_type) + unsigned char record_type, + int version) { size_t pkt_len, iv_size = ctx->tx.iv_size; - pkt_len = plaintext_len + iv_size + ctx->tx.tag_size; + pkt_len = plaintext_len + ctx->tx.tag_size; + if (version != TLS_1_3_VERSION) { + pkt_len += iv_size; + + memcpy(buf + TLS_NONCE_OFFSET, + ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size); + } /* we cover nonce explicit here as well, so buf should be of * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE */ - buf[0] = record_type; - buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.info.version); - buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.info.version); + buf[0] = version == TLS_1_3_VERSION ? + TLS_RECORD_TYPE_DATA : record_type; + /* Note that VERSION must be TLS_1_2 for both TLS1.2 and TLS1.3 */ + buf[1] = TLS_1_2_VERSION_MINOR; + buf[2] = TLS_1_2_VERSION_MAJOR; /* we can use IV for nonce explicit according to spec */ buf[3] = pkt_len >> 8; buf[4] = pkt_len & 0xFF; - memcpy(buf + TLS_NONCE_OFFSET, - ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size); } static inline void tls_make_aad(char *buf, size_t size, char *record_sequence, int record_sequence_size, - unsigned char record_type) + unsigned char record_type, + int version) +{ + if (version != TLS_1_3_VERSION) { + memcpy(buf, record_sequence, record_sequence_size); + buf += 8; + } else { + size += TLS_CIPHER_AES_GCM_128_TAG_SIZE; + } + + buf[0] = version == TLS_1_3_VERSION ? + TLS_RECORD_TYPE_DATA : record_type; + buf[1] = TLS_1_2_VERSION_MAJOR; + buf[2] = TLS_1_2_VERSION_MINOR; + buf[3] = size >> 8; + buf[4] = size & 0xFF; +} + +static inline void xor_iv_with_seq(int version, char *iv, char *seq) { - memcpy(buf, record_sequence, record_sequence_size); + int i; - buf[8] = record_type; - buf[9] = TLS_1_2_VERSION_MAJOR; - buf[10] = TLS_1_2_VERSION_MINOR; - buf[11] = size >> 8; - buf[12] = size & 0xFF; + if (version == TLS_1_3_VERSION) { + for (i = 0; i < 8; i++) + iv[i + 4] ^= seq[i]; + } } static inline struct tls_context *tls_get_ctx(const struct sock *sk) diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index 9affceaa3db4..401d6f01de6a 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -51,6 +51,10 @@ #define TLS_1_2_VERSION_MINOR 0x3 #define TLS_1_2_VERSION TLS_VERSION_NUMBER(TLS_1_2) +#define TLS_1_3_VERSION_MAJOR 0x3 +#define TLS_1_3_VERSION_MINOR 0x4 +#define TLS_1_3_VERSION TLS_VERSION_NUMBER(TLS_1_3) + /* Supported ciphers */ #define TLS_CIPHER_AES_GCM_128 51 #define TLS_CIPHER_AES_GCM_128_IV_SIZE 8 diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index d753e362d2d9..7ee9008b2187 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -257,7 +257,8 @@ static int tls_push_record(struct sock *sk, tls_fill_prepend(ctx, skb_frag_address(frag), record->len - ctx->tx.prepend_size, - record_type); + record_type, + ctx->crypto_send.info.version); /* HW doesn't care about the data in the tag, because it fills it. */ dummy_tag_frag.page = skb_frag_page(frag); @@ -270,7 +271,7 @@ static int tls_push_record(struct sock *sk, spin_unlock_irq(&offload_ctx->lock); offload_ctx->open_record = NULL; set_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); - tls_advance_record_sn(sk, &ctx->tx); + tls_advance_record_sn(sk, &ctx->tx, ctx->crypto_send.info.version); for (i = 0; i < record->num_frags; i++) { frag = &record->frags[i]; diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 450a6dbc5a88..54c3a758f2a7 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -73,7 +73,8 @@ static int tls_enc_record(struct aead_request *aead_req, len -= TLS_CIPHER_AES_GCM_128_IV_SIZE; tls_make_aad(aad, len - TLS_CIPHER_AES_GCM_128_TAG_SIZE, - (char *)&rcd_sn, sizeof(rcd_sn), buf[0]); + (char *)&rcd_sn, sizeof(rcd_sn), buf[0], + TLS_1_2_VERSION); memcpy(iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, buf + TLS_HEADER_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 0f028cfdf835..d1c2fd9a3f63 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -463,7 +463,8 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } /* check version */ - if (crypto_info->version != TLS_1_2_VERSION) { + if (crypto_info->version != TLS_1_2_VERSION && + crypto_info->version != TLS_1_3_VERSION) { rc = -ENOTSUPP; goto err_crypto_info; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 34f3523f668e..06d7ae97b929 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -120,6 +120,34 @@ static int skb_nsg(struct sk_buff *skb, int offset, int len) return __skb_nsg(skb, offset, len, 0); } +static int padding_length(struct tls_sw_context_rx *ctx, + struct tls_context *tls_ctx, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + int sub = 0; + + /* Determine zero-padding length */ + if (tls_ctx->crypto_recv.info.version == TLS_1_3_VERSION) { + char content_type = 0; + int err; + int back = 17; + + while (content_type == 0) { + if (back > rxm->full_len) + return -EBADMSG; + err = skb_copy_bits(skb, + rxm->offset + rxm->full_len - back, + &content_type, 1); + if (content_type) + break; + sub++; + back++; + } + ctx->control = content_type; + } + return sub; +} + static void tls_decrypt_done(struct crypto_async_request *req, int err) { struct aead_request *aead_req = (struct aead_request *)req; @@ -142,7 +170,7 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err) tls_err_abort(skb->sk, err); } else { struct strp_msg *rxm = strp_msg(skb); - + rxm->full_len -= padding_length(ctx, tls_ctx, skb); rxm->offset += tls_ctx->rx.prepend_size; rxm->full_len -= tls_ctx->rx.overhead_size; } @@ -448,6 +476,8 @@ static int tls_do_encryption(struct sock *sk, int rc; memcpy(rec->iv_data, tls_ctx->tx.iv, sizeof(rec->iv_data)); + xor_iv_with_seq(tls_ctx->crypto_send.info.version, rec->iv_data, + tls_ctx->tx.rec_seq); sge->offset += tls_ctx->tx.prepend_size; sge->length -= tls_ctx->tx.prepend_size; @@ -483,7 +513,8 @@ static int tls_do_encryption(struct sock *sk, /* Unhook the record from context if encryption is not failure */ ctx->open_rec = NULL; - tls_advance_record_sn(sk, &tls_ctx->tx); + tls_advance_record_sn(sk, &tls_ctx->tx, + tls_ctx->crypto_send.info.version); return rc; } @@ -640,7 +671,17 @@ static int tls_push_record(struct sock *sk, int flags, i = msg_pl->sg.end; sk_msg_iter_var_prev(i); - sg_mark_end(sk_msg_elem(msg_pl, i)); + + rec->content_type = record_type; + if (tls_ctx->crypto_send.info.version == TLS_1_3_VERSION) { + /* Add content type to end of message. No padding added */ + sg_set_buf(&rec->sg_content_type, &rec->content_type, 1); + sg_mark_end(&rec->sg_content_type); + sg_chain(msg_pl->sg.data, msg_pl->sg.end + 1, + &rec->sg_content_type); + } else { + sg_mark_end(sk_msg_elem(msg_pl, i)); + } i = msg_pl->sg.start; sg_chain(rec->sg_aead_in, 2, rec->inplace_crypto ? @@ -653,18 +694,22 @@ static int tls_push_record(struct sock *sk, int flags, i = msg_en->sg.start; sg_chain(rec->sg_aead_out, 2, &msg_en->sg.data[i]); - tls_make_aad(rec->aad_space, msg_pl->sg.size, + tls_make_aad(rec->aad_space, msg_pl->sg.size + tls_ctx->tx.tail_size, tls_ctx->tx.rec_seq, tls_ctx->tx.rec_seq_size, - record_type); + record_type, + tls_ctx->crypto_send.info.version); tls_fill_prepend(tls_ctx, page_address(sg_page(&msg_en->sg.data[i])) + - msg_en->sg.data[i].offset, msg_pl->sg.size, - record_type); + msg_en->sg.data[i].offset, + msg_pl->sg.size + tls_ctx->tx.tail_size, + record_type, + tls_ctx->crypto_send.info.version); tls_ctx->pending_open_record_frags = false; - rc = tls_do_encryption(sk, tls_ctx, ctx, req, msg_pl->sg.size, i); + rc = tls_do_encryption(sk, tls_ctx, ctx, req, + msg_pl->sg.size + tls_ctx->tx.tail_size, i); if (rc < 0) { if (rc != -EINPROGRESS) { tls_err_abort(sk, EBADMSG); @@ -1292,7 +1337,8 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, u8 *aad, *iv, *mem = NULL; struct scatterlist *sgin = NULL; struct scatterlist *sgout = NULL; - const int data_len = rxm->full_len - tls_ctx->rx.overhead_size; + const int data_len = rxm->full_len - tls_ctx->rx.overhead_size + + tls_ctx->rx.tail_size; if (*zc && (out_iov || out_sg)) { if (out_iov) @@ -1343,12 +1389,20 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, kfree(mem); return err; } - memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + if (tls_ctx->crypto_recv.info.version == TLS_1_3_VERSION) + memcpy(iv, tls_ctx->rx.iv, crypto_aead_ivsize(ctx->aead_recv)); + else + memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + + xor_iv_with_seq(tls_ctx->crypto_recv.info.version, iv, + tls_ctx->rx.rec_seq); /* Prepare AAD */ - tls_make_aad(aad, rxm->full_len - tls_ctx->rx.overhead_size, + tls_make_aad(aad, rxm->full_len - tls_ctx->rx.overhead_size + + tls_ctx->rx.tail_size, tls_ctx->rx.rec_seq, tls_ctx->rx.rec_seq_size, - ctx->control); + ctx->control, + tls_ctx->crypto_recv.info.version); /* Prepare sgin */ sg_init_table(sgin, n_sgin); @@ -1405,6 +1459,7 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + int version = tls_ctx->crypto_recv.info.version; struct strp_msg *rxm = strp_msg(skb); int err = 0; @@ -1417,13 +1472,17 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, err = decrypt_internal(sk, skb, dest, NULL, chunk, zc, async); if (err < 0) { if (err == -EINPROGRESS) - tls_advance_record_sn(sk, &tls_ctx->rx); + tls_advance_record_sn(sk, &tls_ctx->rx, + version); return err; } + + rxm->full_len -= padding_length(ctx, tls_ctx, skb); + rxm->offset += tls_ctx->rx.prepend_size; rxm->full_len -= tls_ctx->rx.overhead_size; - tls_advance_record_sn(sk, &tls_ctx->rx); + tls_advance_record_sn(sk, &tls_ctx->rx, version); ctx->decrypted = true; ctx->saved_data_ready(sk); } else { @@ -1611,7 +1670,8 @@ int tls_sw_recvmsg(struct sock *sk, to_decrypt = rxm->full_len - tls_ctx->rx.overhead_size; if (to_decrypt <= len && !is_kvec && !is_peek && - ctx->control == TLS_RECORD_TYPE_DATA) + ctx->control == TLS_RECORD_TYPE_DATA && + tls_ctx->crypto_recv.info.version != TLS_1_3_VERSION) zc = true; err = decrypt_skb_update(sk, skb, &msg->msg_iter, @@ -1835,9 +1895,12 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) data_len = ((header[4] & 0xFF) | (header[3] << 8)); - cipher_overhead = tls_ctx->rx.tag_size + tls_ctx->rx.iv_size; + cipher_overhead = tls_ctx->rx.tag_size; + if (tls_ctx->crypto_recv.info.version != TLS_1_3_VERSION) + cipher_overhead += tls_ctx->rx.iv_size; - if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead) { + if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead + + tls_ctx->rx.tail_size) { ret = -EMSGSIZE; goto read_failure; } @@ -1846,12 +1909,12 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) goto read_failure; } - if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.info.version) || - header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.info.version)) { + /* Note that both TLS1.3 and TLS1.2 use TLS_1_2 version here */ + if (header[1] != TLS_1_2_VERSION_MINOR || + header[2] != TLS_1_2_VERSION_MAJOR) { ret = -EINVAL; goto read_failure; } - #ifdef CONFIG_TLS_DEVICE handle_device_resync(strp->sk, TCP_SKB_CB(skb)->seq + rxm->offset, *(u64*)tls_ctx->rx.rec_seq); @@ -2100,10 +2163,19 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto free_priv; } - cctx->aad_size = TLS_AAD_SPACE_SIZE; + if (crypto_info->version == TLS_1_3_VERSION) { + nonce_size = 0; + cctx->aad_size = TLS_HEADER_SIZE; + cctx->tail_size = 1; + } else { + cctx->aad_size = TLS_AAD_SPACE_SIZE; + cctx->tail_size = 0; + } + cctx->prepend_size = TLS_HEADER_SIZE + nonce_size; cctx->tag_size = tag_size; - cctx->overhead_size = cctx->prepend_size + cctx->tag_size; + cctx->overhead_size = cctx->prepend_size + cctx->tag_size + + cctx->tail_size; cctx->iv_size = iv_size; cctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, GFP_KERNEL); -- cgit v1.2.3 From 5b053e121ffdec851dc3a7046e9bece287a3c5b1 Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Wed, 30 Jan 2019 22:08:21 +0000 Subject: net: tls: Set async_capable for tls zerocopy only if we see EINPROGRESS Currently we don't zerocopy if the crypto framework async bit is set. However some crypto algorithms (such as x86 AESNI) support async, but in the context of sendmsg, will never run asynchronously. Instead, check for actual EINPROGRESS return code before assuming algorithm is async. Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- include/net/tls.h | 1 + net/tls/tls_sw.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 004bf01ce868..a93a8ed8f716 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -142,6 +142,7 @@ struct tls_sw_context_tx { struct list_head tx_list; atomic_t encrypt_pending; int async_notify; + int async_capable; #define BIT_TX_SCHEDULED 0 unsigned long tx_bitmask; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 06d7ae97b929..8051a9164139 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -718,6 +718,7 @@ static int tls_push_record(struct sock *sk, int flags, tls_merge_open_record(sk, rec, tmp, orig_end); } } + ctx->async_capable = 1; return rc; } else if (split) { msg_pl = &tmp->msg_plaintext; @@ -859,8 +860,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send); - bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; + bool async_capable = ctx->async_capable; unsigned char record_type = TLS_RECORD_TYPE_DATA; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool eor = !(msg->msg_flags & MSG_MORE); -- cgit v1.2.3 From b8580e9de48bf32b884910d22330ef2fa027cf01 Mon Sep 17 00:00:00 2001 From: Shunyong Yang Date: Fri, 1 Feb 2019 17:11:14 -0600 Subject: PCI: Add HXT vendor ID Add the HXT vendor ID to pci_ids.h. Signed-off-by: Shunyong Yang [bhelgaas: split to separate patch] Signed-off-by: Bjorn Helgaas Reviewed-by: Sinan Kaya CC: Joey Zheng --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 5eaf39dbc388..26420e619dd7 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2573,6 +2573,8 @@ #define PCI_VENDOR_ID_HYGON 0x1d94 +#define PCI_VENDOR_ID_HXT 0x1dbf + #define PCI_VENDOR_ID_TEKRAM 0x1de1 #define PCI_DEVICE_ID_TEKRAM_DC290 0xdc29 -- cgit v1.2.3 From 0ce26a1c31ca928df4dfc7504c8898b71ff9f5d5 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Feb 2019 17:24:52 -0600 Subject: PCI: Move Rohm Vendor ID to generic list Move the Rohm Vendor ID to pci_ids.h instead of defining it in several drivers. Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas Acked-by: Mark Brown Acked-by: Linus Walleij --- drivers/dma/pch_dma.c | 1 - drivers/gpio/gpio-ml-ioh.c | 2 -- drivers/gpio/gpio-pch.c | 1 - drivers/i2c/busses/i2c-eg20t.c | 1 - drivers/misc/pch_phub.c | 1 - drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 7 ++----- drivers/spi/spi-topcliff-pch.c | 1 - drivers/tty/serial/pch_uart.c | 2 -- drivers/usb/gadget/udc/pch_udc.c | 1 - include/linux/pci_ids.h | 2 ++ 10 files changed, 4 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c index afd8f27bda96..538b6e0e17bb 100644 --- a/drivers/dma/pch_dma.c +++ b/drivers/dma/pch_dma.c @@ -972,7 +972,6 @@ static void pch_dma_remove(struct pci_dev *pdev) } /* PCI Device ID of DMA device */ -#define PCI_VENDOR_ID_ROHM 0x10DB #define PCI_DEVICE_ID_EG20T_PCH_DMA_8CH 0x8810 #define PCI_DEVICE_ID_EG20T_PCH_DMA_4CH 0x8815 #define PCI_DEVICE_ID_ML7213_DMA1_8CH 0x8026 diff --git a/drivers/gpio/gpio-ml-ioh.c b/drivers/gpio/gpio-ml-ioh.c index 51c7d1b84c2e..0c076dce9e17 100644 --- a/drivers/gpio/gpio-ml-ioh.c +++ b/drivers/gpio/gpio-ml-ioh.c @@ -31,8 +31,6 @@ #define IOH_IRQ_BASE 0 -#define PCI_VENDOR_ID_ROHM 0x10DB - struct ioh_reg_comn { u32 ien; u32 istatus; diff --git a/drivers/gpio/gpio-pch.c b/drivers/gpio/gpio-pch.c index ee79e5f88b5a..1d99293096f2 100644 --- a/drivers/gpio/gpio-pch.c +++ b/drivers/gpio/gpio-pch.c @@ -437,7 +437,6 @@ static int __maybe_unused pch_gpio_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(pch_gpio_pm_ops, pch_gpio_suspend, pch_gpio_resume); -#define PCI_VENDOR_ID_ROHM 0x10DB static const struct pci_device_id pch_gpio_pcidev_id[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x8803) }, { PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x8014) }, diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c index 835d54ac2971..231675b10376 100644 --- a/drivers/i2c/busses/i2c-eg20t.c +++ b/drivers/i2c/busses/i2c-eg20t.c @@ -177,7 +177,6 @@ static wait_queue_head_t pch_event; static DEFINE_MUTEX(pch_mutex); /* Definition for ML7213 by LAPIS Semiconductor */ -#define PCI_VENDOR_ID_ROHM 0x10DB #define PCI_DEVICE_ID_ML7213_I2C 0x802D #define PCI_DEVICE_ID_ML7223_I2C 0x8010 #define PCI_DEVICE_ID_ML7831_I2C 0x8817 diff --git a/drivers/misc/pch_phub.c b/drivers/misc/pch_phub.c index 540845651b8c..309703e9c42e 100644 --- a/drivers/misc/pch_phub.c +++ b/drivers/misc/pch_phub.c @@ -64,7 +64,6 @@ #define CLKCFG_UARTCLKSEL (1 << 18) /* Macros for ML7213 */ -#define PCI_VENDOR_ID_ROHM 0x10db #define PCI_DEVICE_ID_ROHM_ML7213_PHUB 0x801A /* Macros for ML7223 */ diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 43c0c10dfeb7..3a4225837049 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -27,7 +27,6 @@ #define DRV_VERSION "1.01" const char pch_driver_version[] = DRV_VERSION; -#define PCI_DEVICE_ID_INTEL_IOH1_GBE 0x8802 /* Pci device ID */ #define PCH_GBE_MAR_ENTRIES 16 #define PCH_GBE_SHORT_PKT 64 #define DSC_INIT16 0xC000 @@ -37,11 +36,9 @@ const char pch_driver_version[] = DRV_VERSION; #define PCH_GBE_PCI_BAR 1 #define PCH_GBE_RESERVE_MEMORY 0x200000 /* 2MB */ -/* Macros for ML7223 */ -#define PCI_VENDOR_ID_ROHM 0x10db -#define PCI_DEVICE_ID_ROHM_ML7223_GBE 0x8013 +#define PCI_DEVICE_ID_INTEL_IOH1_GBE 0x8802 -/* Macros for ML7831 */ +#define PCI_DEVICE_ID_ROHM_ML7223_GBE 0x8013 #define PCI_DEVICE_ID_ROHM_ML7831_GBE 0x8802 #define PCH_GBE_TX_WEIGHT 64 diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c index 97d137591b18..d794180e83dc 100644 --- a/drivers/spi/spi-topcliff-pch.c +++ b/drivers/spi/spi-topcliff-pch.c @@ -92,7 +92,6 @@ #define PCH_MAX_SPBR 1023 /* Definition for ML7213/ML7223/ML7831 by LAPIS Semiconductor */ -#define PCI_VENDOR_ID_ROHM 0x10DB #define PCI_DEVICE_ID_ML7213_SPI 0x802c #define PCI_DEVICE_ID_ML7223_SPI 0x800F #define PCI_DEVICE_ID_ML7831_SPI 0x8816 diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 9ed121f08a54..6157213a8359 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -192,8 +192,6 @@ enum { #define PCH_UART_HAL_LOOP (PCH_UART_MCR_LOOP) #define PCH_UART_HAL_AFE (PCH_UART_MCR_AFE) -#define PCI_VENDOR_ID_ROHM 0x10DB - #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) #define DEFAULT_UARTCLK 1843200 /* 1.8432 MHz */ diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c index 55c8c8abeacd..cded51f36fc1 100644 --- a/drivers/usb/gadget/udc/pch_udc.c +++ b/drivers/usb/gadget/udc/pch_udc.c @@ -368,7 +368,6 @@ struct pch_udc_dev { #define PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC 0x0939 #define PCI_DEVICE_ID_INTEL_EG20T_UDC 0x8808 -#define PCI_VENDOR_ID_ROHM 0x10DB #define PCI_DEVICE_ID_ML7213_IOH_UDC 0x801D #define PCI_DEVICE_ID_ML7831_IOH_UDC 0x8808 diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 26420e619dd7..70e86148cb1e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1140,6 +1140,8 @@ #define PCI_VENDOR_ID_TCONRAD 0x10da #define PCI_DEVICE_ID_TCONRAD_TOKENRING 0x0508 +#define PCI_VENDOR_ID_ROHM 0x10db + #define PCI_VENDOR_ID_NVIDIA 0x10de #define PCI_DEVICE_ID_NVIDIA_TNT 0x0020 #define PCI_DEVICE_ID_NVIDIA_TNT2 0x0028 -- cgit v1.2.3 From f9cf22882c606f3ffe06f620bb6d03b9eff18d3d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 31 Jan 2019 10:50:40 -0800 Subject: devlink: add device information API ethtool -i has served us well for a long time, but its showing its limitations more and more. The device information should also be reported per device not per-netdev. Lay foundation for a simple devlink-based way of reading device info. Add driver name and device serial number as initial pieces of information exposed via this new API. v3: - rename helpers (Jiri); - rename driver name attr (Jiri); - remove double spacing in commit message (Jiri). RFC v2: - wrap the skb into an opaque structure (Jiri); - allow the serial number of be any length (Jiri & Andrew); - add driver name (Jonathan). Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 18 +++++++ include/uapi/linux/devlink.h | 5 ++ net/core/devlink.c | 112 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 135 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 85c9eabaf056..a6d0a530483d 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -429,6 +429,7 @@ enum devlink_param_wol_types { } struct devlink_region; +struct devlink_info_req; typedef void devlink_snapshot_data_dest_t(const void *data); @@ -484,6 +485,8 @@ struct devlink_ops { int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode); int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode, struct netlink_ext_ack *extack); + int (*info_get)(struct devlink *devlink, struct devlink_info_req *req, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) @@ -607,6 +610,10 @@ u32 devlink_region_shapshot_id_get(struct devlink *devlink); int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); +int devlink_info_serial_number_put(struct devlink_info_req *req, + const char *sn); +int devlink_info_driver_name_put(struct devlink_info_req *req, + const char *name); #else @@ -905,6 +912,17 @@ devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, return 0; } +static inline int +devlink_info_driver_name_put(struct devlink_info_req *req, const char *name) +{ + return 0; +} + +static inline int +devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) +{ + return 0; +} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 61b4447a6c5b..142710d45093 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -94,6 +94,8 @@ enum devlink_command { DEVLINK_CMD_PORT_PARAM_NEW, DEVLINK_CMD_PORT_PARAM_DEL, + DEVLINK_CMD_INFO_GET, /* can dump */ + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -290,6 +292,9 @@ enum devlink_attr { DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */ DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */ + DEVLINK_ATTR_INFO_DRIVER_NAME, /* string */ + DEVLINK_ATTR_INFO_SERIAL_NUMBER, /* string */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index e6f170caf449..f456f6aa3d40 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3714,6 +3714,110 @@ out: return 0; } +struct devlink_info_req { + struct sk_buff *msg; +}; + +int devlink_info_driver_name_put(struct devlink_info_req *req, const char *name) +{ + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, name); +} +EXPORT_SYMBOL_GPL(devlink_info_driver_name_put); + +int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) +{ + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); +} +EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); + +static int +devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, struct netlink_ext_ack *extack) +{ + struct devlink_info_req req; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, extack); + if (err) + goto err_cancel_msg; + + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (!devlink->ops || !devlink->ops->info_get) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + if (idx < start) { + idx++; + continue; + } + + mutex_lock(&devlink->lock); + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + mutex_unlock(&devlink->lock); + if (err) + break; + idx++; + } + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -3974,6 +4078,14 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_INFO_GET, + .doit = devlink_nl_cmd_info_get_doit, + .dumpit = devlink_nl_cmd_info_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From fc6fae7dd987dccce3f322c32dc26b52d69ad00e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 31 Jan 2019 10:50:41 -0800 Subject: devlink: add version reporting to devlink info API ethtool -i has a few fixed-size fields which can be used to report firmware version and expansion ROM version. Unfortunately, modern hardware has more firmware components. There is usually some datapath microcode, management controller, PXE drivers, and a CPLD load. Running ethtool -i on modern controllers reveals the fact that vendors cram multiple values into firmware version field. Here are some examples from systems I could lay my hands on quickly: tg3: "FFV20.2.17 bc 5720-v1.39" i40e: "6.01 0x800034a4 1.1747.0" nfp: "0.0.3.5 0.25 sriov-2.1.16 nic" Add a new devlink API to allow retrieving multiple versions, and provide user-readable name for those versions. While at it break down the versions into three categories: - fixed - this is the board/fixed component version, usually vendors report information like the board version in the PCI VPD, but it will benefit from naming and common API as well; - running - this is the running firmware version; - stored - this is firmware in the flash, after firmware update this value will reflect the flashed version, while the running version may only be updated after reboot. v3: - add per-type helpers instead of using the special argument (Jiri). RFCv2: - remove the nesting in attr DEVLINK_ATTR_INFO_VERSIONS (now versions are mixed with other info attrs)l - have the driver report versions from the same callback as other info. Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 33 +++++++++++++++++++++++++ include/uapi/linux/devlink.h | 5 ++++ net/core/devlink.c | 57 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 95 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index a6d0a530483d..6dc0ef964392 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -614,6 +614,15 @@ int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn); int devlink_info_driver_name_put(struct devlink_info_req *req, const char *name); +int devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value); +int devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value); +int devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value); #else @@ -923,6 +932,30 @@ devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) { return 0; } + +static inline int +devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return 0; +} + +static inline int +devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return 0; +} + +static inline int +devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return 0; +} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 142710d45093..7fffd879c328 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -294,6 +294,11 @@ enum devlink_attr { DEVLINK_ATTR_INFO_DRIVER_NAME, /* string */ DEVLINK_ATTR_INFO_SERIAL_NUMBER, /* string */ + DEVLINK_ATTR_INFO_VERSION_FIXED, /* nested */ + DEVLINK_ATTR_INFO_VERSION_RUNNING, /* nested */ + DEVLINK_ATTR_INFO_VERSION_STORED, /* nested */ + DEVLINK_ATTR_INFO_VERSION_NAME, /* string */ + DEVLINK_ATTR_INFO_VERSION_VALUE, /* string */ /* add new attributes above here, update the policy in devlink.c */ diff --git a/net/core/devlink.c b/net/core/devlink.c index f456f6aa3d40..e31b6d617837 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3730,6 +3730,63 @@ int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) } EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); +static int devlink_info_version_put(struct devlink_info_req *req, int attr, + const char *version_name, + const char *version_value) +{ + struct nlattr *nest; + int err; + + nest = nla_nest_start(req->msg, attr); + if (!nest) + return -EMSGSIZE; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, + version_name); + if (err) + goto nla_put_failure; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, + version_value); + if (err) + goto nla_put_failure; + + nla_nest_end(req->msg, nest); + + return 0; + +nla_put_failure: + nla_nest_cancel(req->msg, nest); + return err; +} + +int devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, + version_name, version_value); +} +EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); + +int devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); + +int devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put); + static int devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, -- cgit v1.2.3 From 785bd550c4fb0e12cb29dd24cf0a0be103f145a0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 31 Jan 2019 10:50:42 -0800 Subject: devlink: add generic info version names Add defines and docs for generic info versions. v3: - add docs; - separate patch (Jiri). Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/devlink-info-versions.rst | 38 ++++++++++++++++++++++ Documentation/networking/index.rst | 1 + include/net/devlink.h | 14 ++++++++ 3 files changed, 53 insertions(+) create mode 100644 Documentation/networking/devlink-info-versions.rst (limited to 'include') diff --git a/Documentation/networking/devlink-info-versions.rst b/Documentation/networking/devlink-info-versions.rst new file mode 100644 index 000000000000..7d4ecf6b6f34 --- /dev/null +++ b/Documentation/networking/devlink-info-versions.rst @@ -0,0 +1,38 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +===================== +Devlink info versions +===================== + +board.id +======== + +Unique identifier of the board design. + +board.rev +========= + +Board design revision. + +fw.mgmt +======= + +Control unit firmware version. This firmware is responsible for house +keeping tasks, PHY control etc. but not the packet-by-packet data path +operation. + +fw.app +====== + +Data path microcode controlling high-speed packet processing. + +fw.undi +======= + +UNDI software, may include the UEFI driver, firmware or both. + +fw.ncsi +======= + +Version of the software responsible for supporting/handling the +Network Controller Sideband Interface. diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index f1627ca2a0ea..9a32451cd201 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -24,6 +24,7 @@ Contents: device_drivers/intel/i40e device_drivers/intel/iavf device_drivers/intel/ice + devlink-info-versions kapi z8530book msg_zerocopy diff --git a/include/net/devlink.h b/include/net/devlink.h index 6dc0ef964392..6b417f141fd6 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -428,6 +428,20 @@ enum devlink_param_wol_types { .validate = _validate, \ } +/* Part number, identifier of board design */ +#define DEVLINK_INFO_VERSION_GENERIC_BOARD_ID "board.id" +/* Revision of board design */ +#define DEVLINK_INFO_VERSION_GENERIC_BOARD_REV "board.rev" + +/* Control processor FW version */ +#define DEVLINK_INFO_VERSION_GENERIC_FW_MGMT "fw.mgmt" +/* Data path microcode controlling high-speed packet processing */ +#define DEVLINK_INFO_VERSION_GENERIC_FW_APP "fw.app" +/* UNDI software version */ +#define DEVLINK_INFO_VERSION_GENERIC_FW_UNDI "fw.undi" +/* NCSI support/handler version */ +#define DEVLINK_INFO_VERSION_GENERIC_FW_NCSI "fw.ncsi" + struct devlink_region; struct devlink_info_req; -- cgit v1.2.3 From ddb6e99e2db14d4b3c22a0dbddc6a09234856bb7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 31 Jan 2019 10:50:47 -0800 Subject: ethtool: add compat for devlink info If driver did not fill the fw_version field, try to call into the new devlink get_info op and collect the versions that way. We assume ethtool was always reporting running versions. v4: - use IS_REACHABLE() to avoid problems with DEVLINK=m (kbuildbot). v3 (Jiri): - do a dump and then parse it instead of special handling; - concatenate all versions (well, all that fit :)). Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 10 ++++++++ net/core/devlink.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++ net/core/ethtool.c | 7 ++++++ 3 files changed, 80 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 6b417f141fd6..1c8523920f66 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -972,4 +972,14 @@ devlink_info_version_running_put(struct devlink_info_req *req, } #endif +#if IS_REACHABLE(CONFIG_NET_DEVLINK) +void devlink_compat_running_version(struct net_device *dev, + char *buf, size_t len); +#else +static inline void +devlink_compat_running_version(struct net_device *dev, char *buf, size_t len) +{ +} +#endif + #endif /* _NET_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index e31b6d617837..eb839d74bcc0 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -5278,6 +5278,69 @@ unlock: } EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); +static void __devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + const struct nlattr *nlattr; + struct devlink_info_req req; + struct sk_buff *msg; + int rem, err; + + if (!devlink->ops->info_get) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, NULL); + if (err) + goto free_msg; + + nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { + const struct nlattr *kv; + int rem_kv; + + if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) + continue; + + nla_for_each_nested(kv, nlattr, rem_kv) { + if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) + continue; + + strlcat(buf, nla_data(kv), len); + strlcat(buf, " ", len); + } + } +free_msg: + nlmsg_free(msg); +} + +void devlink_compat_running_version(struct net_device *dev, + char *buf, size_t len) +{ + struct devlink_port *devlink_port; + struct devlink *devlink; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (devlink_port->type == DEVLINK_PORT_TYPE_ETH || + devlink_port->type_dev == dev) { + __devlink_compat_running_version(devlink, + buf, len); + mutex_unlock(&devlink->lock); + goto out; + } + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); +} + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 3fe6e9da3579..45c0a6e3d6ad 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -27,6 +27,7 @@ #include #include #include +#include #include /* @@ -803,6 +804,12 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); + rtnl_unlock(); + if (!info.fw_version[0]) + devlink_compat_running_version(dev, info.fw_version, + sizeof(info.fw_version)); + rtnl_lock(); + if (copy_to_user(useraddr, &info, sizeof(info))) return -EFAULT; return 0; -- cgit v1.2.3 From f38ab20b749da84e3df1f8c9240ddc791b0d5983 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Thu, 20 Dec 2018 14:59:33 +0800 Subject: iio: st_accel: use ACPI orientation data Platform-specific ST accelerometer mount matrix information can be provided by returning a package of 6 integers from the ACPI _ONT method. This has been seen on Acer products such as Veriton Z4860G, Z6860G and A890, which include a ST SMO8840 sensor. We have also confirmed experimentally that the Windows driver uses such information. The _ONT data format was explained by a ST vendor contact. However, strangely enough, the _ONT transformations must be applied after first applying another mount matrix which we determined experimentally. ST have not commented on why this is the case, but we imagine that perhaps earlier devices (before _ONT was introduced) required this translation and hence it became 'standard.' Interpret the _ONT data and export the equivalent mount matrix to userspace. If no _ONT data is present, no mount matrix is exported. Signed-off-by: Daniel Drake Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_core.c | 171 +++++++++++++++++++++++++++++++++- include/linux/iio/common/st_sensors.h | 1 + 2 files changed, 171 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index f7b471121508..a3c0916479fa 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -918,12 +919,167 @@ static const struct iio_trigger_ops st_accel_trigger_ops = { #define ST_ACCEL_TRIGGER_OPS NULL #endif +static const struct iio_mount_matrix * +get_mount_matrix(const struct iio_dev *indio_dev, + const struct iio_chan_spec *chan) +{ + struct st_sensor_data *adata = iio_priv(indio_dev); + + return adata->mount_matrix; +} + +static const struct iio_chan_spec_ext_info mount_matrix_ext_info[] = { + IIO_MOUNT_MATRIX(IIO_SHARED_BY_ALL, get_mount_matrix), + { }, +}; + +/* Read ST-specific _ONT orientation data from ACPI and generate an + * appropriate mount matrix. + */ +static int apply_acpi_orientation(struct iio_dev *indio_dev, + struct iio_chan_spec *channels) +{ +#ifdef CONFIG_ACPI + struct st_sensor_data *adata = iio_priv(indio_dev); + struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; + struct acpi_device *adev; + union acpi_object *ont; + union acpi_object *elements; + acpi_status status; + int ret = -EINVAL; + unsigned int val; + int i, j; + int final_ont[3][3] = { { 0 }, }; + + /* For some reason, ST's _ONT translation does not apply directly + * to the data read from the sensor. Another translation must be + * performed first, as described by the matrix below. Perhaps + * ST required this specific translation for the first product + * where the device was mounted? + */ + const int default_ont[3][3] = { + { 0, 1, 0 }, + { -1, 0, 0 }, + { 0, 0, -1 }, + }; + + + adev = ACPI_COMPANION(adata->dev); + if (!adev) + return 0; + + /* Read _ONT data, which should be a package of 6 integers. */ + status = acpi_evaluate_object(adev->handle, "_ONT", NULL, &buffer); + if (status == AE_NOT_FOUND) { + return 0; + } else if (ACPI_FAILURE(status)) { + dev_warn(&indio_dev->dev, "failed to execute _ONT: %d\n", + status); + return status; + } + + ont = buffer.pointer; + if (ont->type != ACPI_TYPE_PACKAGE || ont->package.count != 6) + goto out; + + /* The first 3 integers provide axis order information. + * e.g. 0 1 2 would indicate normal X,Y,Z ordering. + * e.g. 1 0 2 indicates that data arrives in order Y,X,Z. + */ + elements = ont->package.elements; + for (i = 0; i < 3; i++) { + if (elements[i].type != ACPI_TYPE_INTEGER) + goto out; + + val = elements[i].integer.value; + if (val < 0 || val > 2) + goto out; + + /* Avoiding full matrix multiplication, we simply reorder the + * columns in the default_ont matrix according to the + * ordering provided by _ONT. + */ + final_ont[0][i] = default_ont[0][val]; + final_ont[1][i] = default_ont[1][val]; + final_ont[2][i] = default_ont[2][val]; + } + + /* The final 3 integers provide sign flip information. + * 0 means no change, 1 means flip. + * e.g. 0 0 1 means that Z data should be sign-flipped. + * This is applied after the axis reordering from above. + */ + elements += 3; + for (i = 0; i < 3; i++) { + if (elements[i].type != ACPI_TYPE_INTEGER) + goto out; + + val = elements[i].integer.value; + if (val != 0 && val != 1) + goto out; + if (!val) + continue; + + /* Flip the values in the indicated column */ + final_ont[0][i] *= -1; + final_ont[1][i] *= -1; + final_ont[2][i] *= -1; + } + + /* Convert our integer matrix to a string-based iio_mount_matrix */ + adata->mount_matrix = devm_kmalloc(&indio_dev->dev, + sizeof(*adata->mount_matrix), + GFP_KERNEL); + if (!adata->mount_matrix) { + ret = -ENOMEM; + goto out; + } + + for (i = 0; i < 3; i++) { + for (j = 0; j < 3; j++) { + int matrix_val = final_ont[i][j]; + char *str_value; + + switch (matrix_val) { + case -1: + str_value = "-1"; + break; + case 0: + str_value = "0"; + break; + case 1: + str_value = "1"; + break; + default: + goto out; + } + adata->mount_matrix->rotation[i * 3 + j] = str_value; + } + } + + /* Expose the mount matrix via ext_info */ + for (i = 0; i < indio_dev->num_channels; i++) + channels[i].ext_info = mount_matrix_ext_info; + + ret = 0; + dev_info(&indio_dev->dev, "computed mount matrix from ACPI\n"); + +out: + kfree(buffer.pointer); + return ret; +#else /* !CONFIG_ACPI */ + return 0; +#endif +} + int st_accel_common_probe(struct iio_dev *indio_dev) { struct st_sensor_data *adata = iio_priv(indio_dev); struct st_sensors_platform_data *pdata = (struct st_sensors_platform_data *)adata->dev->platform_data; int irq = adata->get_irq_data_ready(indio_dev); + struct iio_chan_spec *channels; + size_t channels_size; int err; indio_dev->modes = INDIO_DIRECT_MODE; @@ -942,9 +1098,22 @@ int st_accel_common_probe(struct iio_dev *indio_dev) adata->num_data_channels = ST_ACCEL_NUMBER_DATA_CHANNELS; adata->multiread_bit = adata->sensor_settings->multi_read_bit; - indio_dev->channels = adata->sensor_settings->ch; indio_dev->num_channels = ST_SENSORS_NUMBER_ALL_CHANNELS; + channels_size = indio_dev->num_channels * sizeof(struct iio_chan_spec); + channels = devm_kmemdup(&indio_dev->dev, + adata->sensor_settings->ch, + channels_size, GFP_KERNEL); + if (!channels) { + err = -ENOMEM; + goto st_accel_power_off; + } + + if (apply_acpi_orientation(indio_dev, channels)) + dev_warn(&indio_dev->dev, + "failed to apply ACPI orientation data: %d\n", err); + + indio_dev->channels = channels; adata->current_fullscale = (struct st_sensor_fullscale_avl *) &adata->sensor_settings->fs.fs_avl[0]; adata->odr = adata->sensor_settings->odr.odr_avl[0].hz; diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 8092b8e7f37e..45e9667f0a8c 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -260,6 +260,7 @@ struct st_sensor_settings { struct st_sensor_data { struct device *dev; struct iio_trigger *trig; + struct iio_mount_matrix *mount_matrix; struct st_sensor_settings *sensor_settings; struct st_sensor_fullscale_avl *current_fullscale; struct regulator *vdd; -- cgit v1.2.3 From 078a85f2806f0ffd11289009462a6a390f9adb5c Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Thu, 31 Jan 2019 13:30:18 +0000 Subject: ASoC: dapm: Only power up active channels from a DAI Currently all widgets attached to a DAI link will be powered up when the DAI is active, however this may include routes that are not actually in use if there are unused channels available on the DAI. The macros for creating AIF widgets already include an entry for slot, it is proposed to change that to channel. The effective difference here being respresenting the logical channel index rather than the physical slot index. The CODECs currently using the slot entry on the DAPM_AIF macros are using it in a manner consistent with this, the CODECs not using it just have the field set to zero. A variable is added to snd_soc_dapm_widget to represent this channel index and then for each AIF widget attached to a DAI this is compared against the number of channels on the stream. Enabling the links for those which will be in use. This has the nice property that the CODECs which haven't used the slot/channel entry in the macro will function exactly as before due to all the AIF widgets having a channel of zero and a stream by definition having at least one channel. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- include/sound/soc-dapm.h | 22 +++++++++----- sound/soc/soc-dapm.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++ sound/soc/soc-pcm.c | 4 +++ 3 files changed, 94 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 46f2ba3ffcb7..79b4ddfb8e9e 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -214,21 +214,21 @@ struct device; .event_flags = SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD} /* stream domain */ -#define SND_SOC_DAPM_AIF_IN(wname, stname, wslot, wreg, wshift, winvert) \ +#define SND_SOC_DAPM_AIF_IN(wname, stname, wchan, wreg, wshift, winvert) \ { .id = snd_soc_dapm_aif_in, .name = wname, .sname = stname, \ - SND_SOC_DAPM_INIT_REG_VAL(wreg, wshift, winvert), } -#define SND_SOC_DAPM_AIF_IN_E(wname, stname, wslot, wreg, wshift, winvert, \ + .channel = wchan, SND_SOC_DAPM_INIT_REG_VAL(wreg, wshift, winvert), } +#define SND_SOC_DAPM_AIF_IN_E(wname, stname, wchan, wreg, wshift, winvert, \ wevent, wflags) \ { .id = snd_soc_dapm_aif_in, .name = wname, .sname = stname, \ - SND_SOC_DAPM_INIT_REG_VAL(wreg, wshift, winvert), \ + .channel = wchan, SND_SOC_DAPM_INIT_REG_VAL(wreg, wshift, winvert), \ .event = wevent, .event_flags = wflags } -#define SND_SOC_DAPM_AIF_OUT(wname, stname, wslot, wreg, wshift, winvert) \ +#define SND_SOC_DAPM_AIF_OUT(wname, stname, wchan, wreg, wshift, winvert) \ { .id = snd_soc_dapm_aif_out, .name = wname, .sname = stname, \ - SND_SOC_DAPM_INIT_REG_VAL(wreg, wshift, winvert), } -#define SND_SOC_DAPM_AIF_OUT_E(wname, stname, wslot, wreg, wshift, winvert, \ + .channel = wchan, SND_SOC_DAPM_INIT_REG_VAL(wreg, wshift, winvert), } +#define SND_SOC_DAPM_AIF_OUT_E(wname, stname, wchan, wreg, wshift, winvert, \ wevent, wflags) \ { .id = snd_soc_dapm_aif_out, .name = wname, .sname = stname, \ - SND_SOC_DAPM_INIT_REG_VAL(wreg, wshift, winvert), \ + .channel = wchan, SND_SOC_DAPM_INIT_REG_VAL(wreg, wshift, winvert), \ .event = wevent, .event_flags = wflags } #define SND_SOC_DAPM_DAC(wname, stname, wreg, wshift, winvert) \ { .id = snd_soc_dapm_dac, .name = wname, .sname = stname, \ @@ -407,6 +407,10 @@ int snd_soc_dapm_new_dai_widgets(struct snd_soc_dapm_context *dapm, int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card); void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card); +int snd_soc_dapm_update_dai(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct snd_soc_dai *dai); + /* dapm path setup */ int snd_soc_dapm_new_widgets(struct snd_soc_card *card); void snd_soc_dapm_free(struct snd_soc_dapm_context *dapm); @@ -627,6 +631,8 @@ struct snd_soc_dapm_widget { int endpoints[2]; struct clk *clk; + + int channel; }; struct snd_soc_dapm_update { diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index e71cd5b660ad..36d964a52874 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -2541,6 +2541,78 @@ int snd_soc_dapm_sync(struct snd_soc_dapm_context *dapm) } EXPORT_SYMBOL_GPL(snd_soc_dapm_sync); +static int dapm_update_dai_chan(struct snd_soc_dapm_path *p, + struct snd_soc_dapm_widget *w, + int channels) +{ + switch (w->id) { + case snd_soc_dapm_aif_out: + case snd_soc_dapm_aif_in: + break; + default: + return 0; + } + + dev_dbg(w->dapm->dev, "%s DAI route %s -> %s\n", + w->channel < channels ? "Connecting" : "Disconnecting", + p->source->name, p->sink->name); + + if (w->channel < channels) + soc_dapm_connect_path(p, true, "dai update"); + else + soc_dapm_connect_path(p, false, "dai update"); + + return 0; +} + +static int dapm_update_dai_unlocked(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct snd_soc_dai *dai) +{ + int dir = substream->stream; + int channels = params_channels(params); + struct snd_soc_dapm_path *p; + struct snd_soc_dapm_widget *w; + int ret; + + if (dir == SNDRV_PCM_STREAM_PLAYBACK) + w = dai->playback_widget; + else + w = dai->capture_widget; + + dev_dbg(dai->dev, "Update DAI routes for %s %s\n", dai->name, + dir == SNDRV_PCM_STREAM_PLAYBACK ? "playback" : "capture"); + + snd_soc_dapm_widget_for_each_sink_path(w, p) { + ret = dapm_update_dai_chan(p, p->sink, channels); + if (ret < 0) + return ret; + } + + snd_soc_dapm_widget_for_each_source_path(w, p) { + ret = dapm_update_dai_chan(p, p->source, channels); + if (ret < 0) + return ret; + } + + return 0; +} + +int snd_soc_dapm_update_dai(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct snd_soc_dai *dai) +{ + struct snd_soc_pcm_runtime *rtd = substream->private_data; + int ret; + + mutex_lock_nested(&rtd->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + ret = dapm_update_dai_unlocked(substream, params, dai); + mutex_unlock(&rtd->card->dapm_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(snd_soc_dapm_update_dai); + /* * dapm_update_widget_flags() - Re-compute widget sink and source flags * @w: The widget for which to update the flags @@ -3706,6 +3778,8 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, ret = soc_dai_hw_params(&substream, params, source); if (ret < 0) goto out; + + dapm_update_dai_unlocked(&substream, params, source); } substream.stream = SNDRV_PCM_STREAM_PLAYBACK; @@ -3726,6 +3800,8 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, ret = soc_dai_hw_params(&substream, params, sink); if (ret < 0) goto out; + + dapm_update_dai_unlocked(&substream, params, sink); } break; diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 03f36e534050..a5b40e82dea4 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -969,6 +969,8 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream, codec_dai->channels = params_channels(&codec_params); codec_dai->sample_bits = snd_pcm_format_physical_width( params_format(&codec_params)); + + snd_soc_dapm_update_dai(substream, &codec_params, codec_dai); } ret = soc_dai_hw_params(substream, params, cpu_dai); @@ -998,6 +1000,8 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream, cpu_dai->sample_bits = snd_pcm_format_physical_width(params_format(params)); + snd_soc_dapm_update_dai(substream, params, cpu_dai); + ret = soc_pcm_params_symmetry(substream, params); if (ret) goto component_err; -- cgit v1.2.3 From d5d30d5a5c60628de5e77e3f292a8f9012d51350 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 2 Feb 2019 16:35:26 -0800 Subject: libnvdimm/dimm: Add a no-BLK quirk based on NVDIMM family As Dexuan reports the NVDIMM_FAMILY_HYPERV platform is incompatible with the existing Linux namespace implementation because it uses NSLABEL_FLAG_LOCAL for x1-width PMEM interleave sets. Quirk it as an platform / DIMM that does not provide BLK-aperture access. Allow the libnvdimm core to assume no potential for aliasing. In case other implementations make the same mistake, provide a "noblk" module parameter to force-enable the quirk. Link: https://lkml.kernel.org/r/PU1P153MB0169977604493B82B662A01CBF920@PU1P153MB0169.APCP153.PROD.OUTLOOK.COM Reported-by: Dexuan Cui Tested-by: Dexuan Cui Signed-off-by: Dan Williams --- drivers/acpi/nfit/core.c | 4 ++++ drivers/nvdimm/dimm_devs.c | 7 +++++++ drivers/nvdimm/label.c | 3 +++ drivers/nvdimm/namespace_devs.c | 6 ++++++ drivers/nvdimm/region_devs.c | 7 +++++++ include/linux/libnvdimm.h | 2 ++ 6 files changed, 29 insertions(+) (limited to 'include') diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 4a7e8b1fa43b..811c399a3a76 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2016,6 +2016,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) cmd_mask |= nfit_mem->dsm_mask & NVDIMM_STANDARD_CMDMASK; } + /* Quirk to ignore LOCAL for labels on HYPERV DIMMs */ + if (nfit_mem->family == NVDIMM_FAMILY_HYPERV) + set_bit(NDD_NOBLK, &flags); + if (test_bit(NFIT_MEM_LSR, &nfit_mem->flags)) { set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask); set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask); diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 4890310df874..553aa78abeee 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -11,6 +11,7 @@ * General Public License for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -25,6 +26,10 @@ static DEFINE_IDA(dimm_ida); +static bool noblk; +module_param(noblk, bool, 0444); +MODULE_PARM_DESC(noblk, "force disable BLK / local alias support"); + /* * Retrieve bus and dimm handle and return if this bus supports * get_config_data commands @@ -551,6 +556,8 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus, nvdimm->dimm_id = dimm_id; nvdimm->provider_data = provider_data; + if (noblk) + flags |= 1 << NDD_NOBLK; nvdimm->flags = flags; nvdimm->cmd_mask = cmd_mask; nvdimm->num_flush = num_flush; diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index 6d6e9a12150b..f3d753d3169c 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -392,6 +392,7 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) return 0; /* no label, nothing to reserve */ for_each_clear_bit_le(slot, free, nslot) { + struct nvdimm *nvdimm = to_nvdimm(ndd->dev); struct nd_namespace_label *nd_label; struct nd_region *nd_region = NULL; u8 label_uuid[NSLABEL_UUID_LEN]; @@ -406,6 +407,8 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN); flags = __le32_to_cpu(nd_label->flags); + if (test_bit(NDD_NOBLK, &nvdimm->flags)) + flags &= ~NSLABEL_FLAG_LOCAL; nd_label_gen_id(&label_id, label_uuid, flags); res = nvdimm_allocate_dpa(ndd, &label_id, __le64_to_cpu(nd_label->dpa), diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 4b077555ac70..3677b0c4a33d 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -2492,6 +2492,12 @@ static int init_active_labels(struct nd_region *nd_region) if (!label_ent) break; label = nd_label_active(ndd, j); + if (test_bit(NDD_NOBLK, &nvdimm->flags)) { + u32 flags = __le32_to_cpu(label->flags); + + flags &= ~NSLABEL_FLAG_LOCAL; + label->flags = __cpu_to_le32(flags); + } label_ent->label = label; mutex_lock(&nd_mapping->lock); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index e2818f94f292..3b58baa44b5c 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -1003,6 +1003,13 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, if (test_bit(NDD_UNARMED, &nvdimm->flags)) ro = 1; + + if (test_bit(NDD_NOBLK, &nvdimm->flags) + && dev_type == &nd_blk_device_type) { + dev_err(&nvdimm_bus->dev, "%s: %s mapping%d is not BLK capable\n", + caller, dev_name(&nvdimm->dev), i); + return NULL; + } } if (dev_type == &nd_blk_device_type) { diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 5440f11b0907..7da406ae3a2b 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -42,6 +42,8 @@ enum { NDD_SECURITY_OVERWRITE = 3, /* tracking whether or not there is a pending device reference */ NDD_WORK_PENDING = 4, + /* ignore / filter NSLABEL_FLAG_LOCAL for this DIMM, i.e. no aliasing */ + NDD_NOBLK = 5, /* need to set a limit somewhere, but yes, this is likely overkill */ ND_IOCTL_MAX_BUFLEN = SZ_4M, -- cgit v1.2.3 From 79a4e91d1bb2a411a4ce2baa93680fa707567003 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sat, 2 Feb 2019 19:50:17 -0800 Subject: device.h: Add __cold to dev_ logging functions Add __cold to the dev_ logging functions similar to the use of __cold in the generic printk function. Using __cold moves all the dev_ logging functions out-of-line possibly improving code locality and runtime performance. Signed-off-by: Joe Perches Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 0ab0a3a80ec3..a36830e2d0e5 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1384,28 +1384,28 @@ void device_link_remove(void *consumer, struct device *supplier); #ifdef CONFIG_PRINTK -__printf(3, 0) +__printf(3, 0) __cold int dev_vprintk_emit(int level, const struct device *dev, const char *fmt, va_list args); -__printf(3, 4) +__printf(3, 4) __cold int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...); -__printf(3, 4) +__printf(3, 4) __cold void dev_printk(const char *level, const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_emerg(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_alert(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_crit(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_err(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_warn(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_notice(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_info(const struct device *dev, const char *fmt, ...); #else -- cgit v1.2.3 From dda7a817f2873a0e0b1c7fde1265758f3623daa4 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 22 Jan 2019 08:48:49 +0200 Subject: net/mlx5: Add XRC transport to ODP device capabilities layout The device capabilities for ODP structure was missing the field for XRC transport so add it here. Signed-off-by: Moni Shoua Reviewed-by: Majd Dibbiny Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 35fe5217b244..5407db8ba8e1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -831,7 +831,9 @@ struct mlx5_ifc_odp_cap_bits { struct mlx5_ifc_odp_per_transport_service_cap_bits ud_odp_caps; - u8 reserved_at_e0[0x720]; + struct mlx5_ifc_odp_per_transport_service_cap_bits xrc_odp_caps; + + u8 reserved_at_100[0x700]; }; struct mlx5_ifc_calc_op { -- cgit v1.2.3 From 46861e3e88be18846971792b763eaf520a91a802 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 22 Jan 2019 08:48:51 +0200 Subject: net/mlx5: Set ODP SRQ support in firmware To avoid compatibility issue with older kernels the firmware doesn't allow SRQ to work with ODP unless kernel asks for it. Signed-off-by: Moni Shoua Reviewed-by: Majd Dibbiny Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 53 ++++++++++++++++++++++++++ include/linux/mlx5/device.h | 3 ++ include/linux/mlx5/mlx5_ifc.h | 1 + 3 files changed, 57 insertions(+) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 085e1133b8d5..e38aa206ab6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -459,6 +459,53 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev) return err; } +static int handle_hca_cap_odp(struct mlx5_core_dev *dev) +{ + void *set_ctx; + void *set_hca_cap; + int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + int err; + + if (!MLX5_CAP_GEN(dev, pg)) + return 0; + + err = mlx5_core_get_caps(dev, MLX5_CAP_ODP); + if (err) + return err; + + /** + * If all bits are cleared we shouldn't try to set it + * or we might fail while trying to access a reserved bit. + */ + if (!(MLX5_CAP_ODP_MAX(dev, ud_odp_caps.srq_receive) || + MLX5_CAP_ODP_MAX(dev, rc_odp_caps.srq_receive) || + MLX5_CAP_ODP_MAX(dev, xrc_odp_caps.srq_receive))) + return 0; + + set_ctx = kzalloc(set_sz, GFP_KERNEL); + if (!set_ctx) + return -ENOMEM; + + set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); + memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP], + MLX5_ST_SZ_BYTES(odp_cap)); + + /* set ODP SRQ support for RC/UD and XRC transports */ + MLX5_SET(odp_cap, set_hca_cap, ud_odp_caps.srq_receive, + (MLX5_CAP_ODP_MAX(dev, ud_odp_caps.srq_receive))); + + MLX5_SET(odp_cap, set_hca_cap, rc_odp_caps.srq_receive, + (MLX5_CAP_ODP_MAX(dev, rc_odp_caps.srq_receive))); + + MLX5_SET(odp_cap, set_hca_cap, xrc_odp_caps.srq_receive, + (MLX5_CAP_ODP_MAX(dev, xrc_odp_caps.srq_receive))); + + err = set_caps(dev, set_ctx, set_sz, MLX5_SET_HCA_CAP_OP_MOD_ODP); + + kfree(set_ctx); + return err; +} + static int handle_hca_cap(struct mlx5_core_dev *dev) { void *set_ctx = NULL; @@ -931,6 +978,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto reclaim_boot_pages; } + err = handle_hca_cap_odp(dev); + if (err) { + dev_err(&pdev->dev, "handle_hca_cap_odp failed\n"); + goto reclaim_boot_pages; + } + err = mlx5_satisfy_startup_pages(dev, 0); if (err) { dev_err(&pdev->dev, "failed to allocate init pages\n"); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8c4a820bd4c1..0845a227a7b2 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1201,6 +1201,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca_cur[MLX5_CAP_ODP], cap) +#define MLX5_CAP_ODP_MAX(mdev, cap)\ + MLX5_GET(odp_cap, mdev->caps.hca_max[MLX5_CAP_ODP], cap) + #define MLX5_CAP_VECTOR_CALC(mdev, cap) \ MLX5_GET(vector_calc_cap, \ mdev->caps.hca_cur[MLX5_CAP_VECTOR_CALC], cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5407db8ba8e1..c5c679390fbd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -72,6 +72,7 @@ enum { enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, + MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, }; -- cgit v1.2.3 From 7f1bc6e95d7840d4305595b3e4025cddda88cee5 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 2 Feb 2019 07:34:46 -0800 Subject: sockopt: Rename SO_TIMESTAMP* to SO_TIMESTAMP*_OLD SO_TIMESTAMP, SO_TIMESTAMPNS and SO_TIMESTAMPING options, the way they are currently defined, are not y2038 safe. Subsequent patches in the series add new y2038 safe versions of these options which provide 64 bit timestamps on all architectures uniformly. Hence, rename existing options with OLD tag suffixes. Also note that kernel will not use the untagged SO_TIMESTAMP* and SCM_TIMESTAMP* options internally anymore. Signed-off-by: Deepa Dinamani Acked-by: Willem de Bruijn Cc: deller@gmx.de Cc: dhowells@redhat.com Cc: jejb@parisc-linux.org Cc: ralf@linux-mips.org Cc: rth@twiddle.net Cc: linux-afs@lists.infradead.org Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-parisc@vger.kernel.org Cc: linux-rdma@vger.kernel.org Cc: sparclinux@vger.kernel.org Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 23 ++++++++++++++++------- arch/mips/include/uapi/asm/socket.h | 23 ++++++++++++++++------- arch/parisc/include/uapi/asm/socket.h | 23 ++++++++++++++++------- arch/sparc/include/uapi/asm/socket.h | 24 ++++++++++++++++-------- include/uapi/asm-generic/socket.h | 23 ++++++++++++++++------- net/compat.c | 6 +++--- net/core/sock.c | 16 ++++++++-------- net/ipv4/tcp.c | 6 +++--- net/rds/af_rds.c | 2 +- net/rds/recv.c | 2 +- net/rxrpc/local_object.c | 2 +- net/socket.c | 8 ++++---- 12 files changed, 101 insertions(+), 57 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index b1c9b542c021..992a0a6dcea1 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -51,13 +51,9 @@ #define SO_GET_FILTER SO_ATTACH_FILTER #define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP #define SO_PEERSEC 30 #define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 19 @@ -66,9 +62,6 @@ #define SO_MARK 36 -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_RXQ_OVFL 40 #define SO_WIFI_STATUS 41 @@ -117,4 +110,20 @@ #define SO_BINDTOIFINDEX 62 +#define SO_TIMESTAMP_OLD 29 +#define SO_TIMESTAMPNS_OLD 35 +#define SO_TIMESTAMPING_OLD 37 + +#if !defined(__KERNEL__) + +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 73e25e35d803..0f4516c34df2 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -65,21 +65,14 @@ #define SO_GET_FILTER SO_ATTACH_FILTER #define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP #define SO_PEERSEC 30 #define SO_SNDBUFFORCE 31 #define SO_RCVBUFFORCE 33 #define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SO_MARK 36 -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_RXQ_OVFL 40 #define SO_WIFI_STATUS 41 @@ -128,4 +121,20 @@ #define SO_BINDTOIFINDEX 62 +#define SO_TIMESTAMP_OLD 29 +#define SO_TIMESTAMPNS_OLD 35 +#define SO_TIMESTAMPING_OLD 37 + +#if !defined(__KERNEL__) + +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 52bed5976cbe..7c180321ebd6 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -34,10 +34,6 @@ #define SO_BSDCOMPAT 0x400e #define SO_PASSCRED 0x4010 #define SO_PEERCRED 0x4011 -#define SO_TIMESTAMP 0x4012 -#define SCM_TIMESTAMP SO_TIMESTAMP -#define SO_TIMESTAMPNS 0x4013 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x4016 @@ -58,9 +54,6 @@ #define SO_MARK 0x401f -#define SO_TIMESTAMPING 0x4020 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_RXQ_OVFL 0x4021 #define SO_WIFI_STATUS 0x4022 @@ -109,4 +102,20 @@ #define SO_BINDTOIFINDEX 0x4037 +#define SO_TIMESTAMP_OLD 0x4012 +#define SO_TIMESTAMPNS_OLD 0x4013 +#define SO_TIMESTAMPING_OLD 0x4020 + +#if !defined(__KERNEL__) + +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index bbdb81594dd4..d8a1bbc3e6c4 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -33,7 +33,6 @@ #define SO_PROTOCOL 0x1028 #define SO_DOMAIN 0x1029 - /* Linux specific, keep the same. */ #define SO_NO_CHECK 0x000b #define SO_PRIORITY 0x000c @@ -45,19 +44,12 @@ #define SO_GET_FILTER SO_ATTACH_FILTER #define SO_PEERNAME 0x001c -#define SO_TIMESTAMP 0x001d -#define SCM_TIMESTAMP SO_TIMESTAMP #define SO_PEERSEC 0x001e #define SO_PASSSEC 0x001f -#define SO_TIMESTAMPNS 0x0021 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SO_MARK 0x0022 -#define SO_TIMESTAMPING 0x0023 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_RXQ_OVFL 0x0024 #define SO_WIFI_STATUS 0x0025 @@ -111,4 +103,20 @@ #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 #define SO_SECURITY_ENCRYPTION_NETWORK 0x5004 +#define SO_TIMESTAMP_OLD 0x001d +#define SO_TIMESTAMPNS_OLD 0x0021 +#define SO_TIMESTAMPING_OLD 0x0023 + +#if !defined(__KERNEL__) + +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* _ASM_SOCKET_H */ diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 3066ab3853a8..4ef3aed31fb7 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -46,21 +46,14 @@ #define SO_GET_FILTER SO_ATTACH_FILTER #define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP #define SO_ACCEPTCONN 30 #define SO_PEERSEC 31 #define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SO_MARK 36 -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_PROTOCOL 38 #define SO_DOMAIN 39 @@ -112,4 +105,20 @@ #define SO_BINDTOIFINDEX 62 +#define SO_TIMESTAMP_OLD 29 +#define SO_TIMESTAMPNS_OLD 35 +#define SO_TIMESTAMPING_OLD 37 + +#if !defined(__KERNEL__) + +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/net/compat.c b/net/compat.c index ce8f6e8cdcd2..ccf93cd0e49b 100644 --- a/net/compat.c +++ b/net/compat.c @@ -219,7 +219,7 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat } if (!COMPAT_USE_64BIT_TIME) { - if (level == SOL_SOCKET && type == SCM_TIMESTAMP) { + if (level == SOL_SOCKET && type == SO_TIMESTAMP_OLD) { struct timeval *tv = (struct timeval *)data; ctv.tv_sec = tv->tv_sec; ctv.tv_usec = tv->tv_usec; @@ -227,8 +227,8 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat len = sizeof(ctv); } if (level == SOL_SOCKET && - (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) { - int count = type == SCM_TIMESTAMPNS ? 1 : 3; + (type == SO_TIMESTAMPNS_OLD || type == SO_TIMESTAMPING_OLD)) { + int count = type == SO_TIMESTAMPNS_OLD ? 1 : 3; int i; struct timespec *ts = (struct timespec *)data; for (i = 0; i < count; i++) { diff --git a/net/core/sock.c b/net/core/sock.c index 29c0028df5ae..d5ca8641968f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -867,10 +867,10 @@ set_rcvbuf: clear_bit(SOCK_PASSCRED, &sock->flags); break; - case SO_TIMESTAMP: - case SO_TIMESTAMPNS: + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMPNS_OLD: if (valbool) { - if (optname == SO_TIMESTAMP) + if (optname == SO_TIMESTAMP_OLD) sock_reset_flag(sk, SOCK_RCVTSTAMPNS); else sock_set_flag(sk, SOCK_RCVTSTAMPNS); @@ -882,7 +882,7 @@ set_rcvbuf: } break; - case SO_TIMESTAMPING: + case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; break; @@ -1243,16 +1243,16 @@ int sock_getsockopt(struct socket *sock, int level, int optname, sock_warn_obsolete_bsdism("getsockopt"); break; - case SO_TIMESTAMP: + case SO_TIMESTAMP_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && !sock_flag(sk, SOCK_RCVTSTAMPNS); break; - case SO_TIMESTAMPNS: + case SO_TIMESTAMPNS_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS); break; - case SO_TIMESTAMPING: + case SO_TIMESTAMPING_OLD: v.val = sk->sk_tsflags; break; @@ -2168,7 +2168,7 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, return -EINVAL; sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; - case SO_TIMESTAMPING: + case SO_TIMESTAMPING_OLD: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6f8d292ad501..e29aec59cad1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1867,13 +1867,13 @@ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(tss->ts[0]), &tss->ts[0]); } else { tv.tv_sec = tss->ts[0].tv_sec; tv.tv_usec = tss->ts[0].tv_nsec / 1000; - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } } @@ -1893,7 +1893,7 @@ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, if (has_timestamping) { tss->ts[1] = (struct timespec) {0}; - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING, + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_OLD, sizeof(*tss), tss); } } diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 65387e1e6964..eeb4639adbe5 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -430,7 +430,7 @@ static int rds_setsockopt(struct socket *sock, int level, int optname, ret = rds_set_transport(rs, optval, optlen); release_sock(sock->sk); break; - case SO_TIMESTAMP: + case SO_TIMESTAMP_OLD: lock_sock(sock->sk); ret = rds_enable_recvtstamp(sock->sk, optval, optlen); release_sock(sock->sk); diff --git a/net/rds/recv.c b/net/rds/recv.c index 727639dac8a7..04e30d63a159 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -550,7 +550,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, if ((inc->i_rx_tstamp != 0) && sock_flag(rds_rs_to_sk(rs), SOCK_RCVTSTAMP)) { struct timeval tv = ktime_to_timeval(inc->i_rx_tstamp); - ret = put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, + ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); if (ret) goto out; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 0906e51d3cfb..15cf42d5b53a 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -202,7 +202,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) /* We want receive timestamps. */ opt = 1; - ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS, + ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS_OLD, (char *)&opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); diff --git a/net/socket.c b/net/socket.c index e89884e2197b..5087f9e40f3a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -669,7 +669,7 @@ static bool skb_is_err_queue(const struct sk_buff *skb) * before the software timestamp is received, a hardware TX timestamp may be * returned only if there is no software TX timestamp. Ignore false software * timestamps, which may be made in the __sock_recv_timestamp() call when the - * option SO_TIMESTAMP(NS) is enabled on the socket, even when the skb has a + * option SO_TIMESTAMP_OLD(NS) is enabled on the socket, even when the skb has a * hardware timestamp. */ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) @@ -721,12 +721,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { struct timeval tv; skb_get_timestamp(skb, &tv); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } else { struct timespec ts; skb_get_timestampns(skb, &ts); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts), &ts); } } @@ -746,7 +746,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, } if (!empty) { put_cmsg(msg, SOL_SOCKET, - SCM_TIMESTAMPING, sizeof(tss), &tss); + SO_TIMESTAMPING_OLD, sizeof(tss), &tss); if (skb_is_err_queue(skb) && skb->len && SKB_EXT_ERR(skb)->opt_stats) -- cgit v1.2.3 From bcb3fc3247e5a7ceb467ca0cfdaa4c1b830dd8f9 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 2 Feb 2019 07:34:47 -0800 Subject: arch: sparc: Override struct __kernel_old_timeval struct __kernel_old_timeval is supposed to have the same layout as struct timeval. But, it was inadvarently missed that __kernel_suseconds has a different definition for sparc64. Provide an asm-specific override that fixes it. Reported-by: Arnd Bergmann Suggested-by: Arnd Bergmann Signed-off-by: Deepa Dinamani Acked-by: Willem de Bruijn Cc: sparclinux@vger.kernel.org Signed-off-by: David S. Miller --- arch/sparc/include/uapi/asm/posix_types.h | 10 ++++++++++ include/uapi/linux/time.h | 2 ++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/arch/sparc/include/uapi/asm/posix_types.h b/arch/sparc/include/uapi/asm/posix_types.h index fec499d6efb7..f139e0048628 100644 --- a/arch/sparc/include/uapi/asm/posix_types.h +++ b/arch/sparc/include/uapi/asm/posix_types.h @@ -19,6 +19,16 @@ typedef unsigned short __kernel_old_gid_t; typedef int __kernel_suseconds_t; #define __kernel_suseconds_t __kernel_suseconds_t +typedef long __kernel_long_t; +typedef unsigned long __kernel_ulong_t; +#define __kernel_long_t __kernel_long_t + +struct __kernel_old_timeval { + __kernel_long_t tv_sec; + __kernel_suseconds_t tv_usec; +}; +#define __kernel_old_timeval __kernel_old_timeval + #else /* sparc 32 bit */ diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index 6b56a2208be7..04d5587f30d3 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -63,10 +63,12 @@ struct __kernel_itimerspec { * here, this is probably because it is not y2038 safe and needs to * be changed to use another interface. */ +#ifndef __kernel_old_timeval struct __kernel_old_timeval { __kernel_long_t tv_sec; __kernel_long_t tv_usec; }; +#endif /* * The IDs of the various system clocks (for POSIX.1b interval timers): -- cgit v1.2.3 From 13c6ee2a921683bae4bb4ba57b1f5b82f49e6b8a Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 2 Feb 2019 07:34:48 -0800 Subject: socket: Use old_timeval types for socket timestamps As part of y2038 solution, all internal uses of struct timeval are replaced by struct __kernel_old_timeval and struct compat_timeval by struct old_timeval32. Make socket timestamps use these new types. This is mainly to be able to verify that the kernel build is y2038 safe when such non y2038 safe types are not supported anymore. Signed-off-by: Deepa Dinamani Acked-by: Willem de Bruijn Cc: isdn@linux-pingi.de Signed-off-by: David S. Miller --- drivers/isdn/mISDN/socket.c | 2 +- include/linux/skbuff.h | 6 +++--- net/bluetooth/hci_sock.c | 4 ++-- net/compat.c | 6 +++--- net/ipv4/tcp.c | 2 +- net/rds/recv.c | 2 +- net/socket.c | 2 +- 7 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index 15d3ca37669a..4ab8b1b6608f 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -103,7 +103,7 @@ mISDN_ctrl(struct mISDNchannel *ch, u_int cmd, void *arg) static inline void mISDN_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { - struct timeval tv; + struct __kernel_old_timeval tv; if (_pms(sk)->cmask & MISDN_TIME_STAMP) { skb_get_timestamp(skb, &tv); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c34595374e93..4001611a4c9f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3486,16 +3486,16 @@ static inline ktime_t skb_get_ktime(const struct sk_buff *skb) /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from - * @stamp: pointer to struct timeval to store stamp in + * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, - struct timeval *stamp) + struct __kernel_old_timeval *stamp) { - *stamp = ktime_to_timeval(skb->tstamp); + *stamp = ns_to_kernel_old_timeval(skb->tstamp); } static inline void skb_get_timestampns(const struct sk_buff *skb, diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1506e1632394..65228bfa4487 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1383,9 +1383,9 @@ static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, if (mask & HCI_CMSG_TSTAMP) { #ifdef CONFIG_COMPAT - struct compat_timeval ctv; + struct old_timeval32 ctv; #endif - struct timeval tv; + struct __kernel_old_timeval tv; void *data; int len; diff --git a/net/compat.c b/net/compat.c index ccf93cd0e49b..9629f053d4fa 100644 --- a/net/compat.c +++ b/net/compat.c @@ -209,8 +209,8 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat { struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control; struct compat_cmsghdr cmhdr; - struct compat_timeval ctv; - struct compat_timespec cts[3]; + struct old_timeval32 ctv; + struct old_timespec32 cts[3]; int cmlen; if (cm == NULL || kmsg->msg_controllen < sizeof(*cm)) { @@ -220,7 +220,7 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat if (!COMPAT_USE_64BIT_TIME) { if (level == SOL_SOCKET && type == SO_TIMESTAMP_OLD) { - struct timeval *tv = (struct timeval *)data; + struct __kernel_old_timeval *tv = (struct __kernel_old_timeval *)data; ctv.tv_sec = tv->tv_sec; ctv.tv_usec = tv->tv_usec; data = &ctv; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e29aec59cad1..3ce41b04c0f0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1861,7 +1861,7 @@ static void tcp_update_recv_tstamps(struct sk_buff *skb, static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping *tss) { - struct timeval tv; + struct __kernel_old_timeval tv; bool has_timestamping = false; if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { diff --git a/net/rds/recv.c b/net/rds/recv.c index 04e30d63a159..435bf2320cd3 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -549,7 +549,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, if ((inc->i_rx_tstamp != 0) && sock_flag(rds_rs_to_sk(rs), SOCK_RCVTSTAMP)) { - struct timeval tv = ktime_to_timeval(inc->i_rx_tstamp); + struct __kernel_old_timeval tv = ns_to_kernel_old_timeval(inc->i_rx_tstamp); ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); if (ret) diff --git a/net/socket.c b/net/socket.c index 5087f9e40f3a..9cc281cdb9d9 100644 --- a/net/socket.c +++ b/net/socket.c @@ -719,7 +719,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, if (need_software_tstamp) { if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { - struct timeval tv; + struct __kernel_old_timeval tv; skb_get_timestamp(skb, &tv); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); -- cgit v1.2.3 From 98bb03c865d7ddf7a9a2eb80f9a0dd5f261c56ad Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 2 Feb 2019 07:34:49 -0800 Subject: socket: Add struct __kernel_sock_timeval The new type is meant to be used as a y2038 safe structure to be used as part of cmsg data. Presently the SO_TIMESTAMP socket option uses struct timeval for timestamps. This is not y2038 safe. Subsequent patches in the series add new y2038 safe socket option to be used in the place of SO_TIMESTAMP_OLD. struct __kernel_sock_timeval will be used as the timestamp format at that time. struct __kernel_sock_timeval also maintains the same layout across 32 bit and 64 bit ABIs. Signed-off-by: Deepa Dinamani Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/time.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index 04d5587f30d3..b8ad1b86b942 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -70,6 +70,11 @@ struct __kernel_old_timeval { }; #endif +struct __kernel_sock_timeval { + __s64 tv_sec; + __s64 tv_usec; +}; + /* * The IDs of the various system clocks (for POSIX.1b interval timers): */ -- cgit v1.2.3 From 887feae36aee6c08e0dafcdaa5ba921abbb2c56b Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 2 Feb 2019 07:34:50 -0800 Subject: socket: Add SO_TIMESTAMP[NS]_NEW Add SO_TIMESTAMP_NEW and SO_TIMESTAMPNS_NEW variants of socket timestamp options. These are the y2038 safe versions of the SO_TIMESTAMP_OLD and SO_TIMESTAMPNS_OLD for all architectures. Note that the format of scm_timestamping.ts[0] is not changed in this patch. Signed-off-by: Deepa Dinamani Acked-by: Willem de Bruijn Cc: jejb@parisc-linux.org Cc: ralf@linux-mips.org Cc: rth@twiddle.net Cc: linux-alpha@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-parisc@vger.kernel.org Cc: linux-rdma@vger.kernel.org Cc: netdev@vger.kernel.org Cc: sparclinux@vger.kernel.org Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 14 ++++++++++++-- arch/mips/include/uapi/asm/socket.h | 14 ++++++++++++-- arch/parisc/include/uapi/asm/socket.h | 14 ++++++++++++-- arch/sparc/include/uapi/asm/socket.h | 14 ++++++++++++-- include/linux/skbuff.h | 18 ++++++++++++++++++ include/net/sock.h | 1 + include/uapi/asm-generic/socket.h | 15 +++++++++++++-- net/core/sock.c | 21 +++++++++++++++++++-- net/ipv4/tcp.c | 33 +++++++++++++++++++++++++-------- net/rds/af_rds.c | 8 ++++++-- net/rds/recv.c | 16 ++++++++++++++-- net/socket.c | 35 +++++++++++++++++++++++++++-------- 12 files changed, 171 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 992a0a6dcea1..aab11eec7c22 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -3,6 +3,7 @@ #define _UAPI_ASM_SOCKET_H #include +#include /* For setsockopt(2) */ /* @@ -114,10 +115,19 @@ #define SO_TIMESTAMPNS_OLD 35 #define SO_TIMESTAMPING_OLD 37 +#define SO_TIMESTAMP_NEW 63 +#define SO_TIMESTAMPNS_NEW 64 + #if !defined(__KERNEL__) -#define SO_TIMESTAMP SO_TIMESTAMP_OLD -#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#if __BITS_PER_LONG == 64 +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#endif + #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 0f4516c34df2..11014f684d9f 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -11,6 +11,7 @@ #define _UAPI_ASM_SOCKET_H #include +#include /* * For setsockopt(2) @@ -125,10 +126,19 @@ #define SO_TIMESTAMPNS_OLD 35 #define SO_TIMESTAMPING_OLD 37 +#define SO_TIMESTAMP_NEW 63 +#define SO_TIMESTAMPNS_NEW 64 + #if !defined(__KERNEL__) -#define SO_TIMESTAMP SO_TIMESTAMP_OLD -#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#if __BITS_PER_LONG == 64 +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#endif + #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 7c180321ebd6..cbc4b89c2fe4 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -3,6 +3,7 @@ #define _UAPI_ASM_SOCKET_H #include +#include /* For setsockopt(2) */ #define SOL_SOCKET 0xffff @@ -106,10 +107,19 @@ #define SO_TIMESTAMPNS_OLD 0x4013 #define SO_TIMESTAMPING_OLD 0x4020 +#define SO_TIMESTAMP_NEW 0x4038 +#define SO_TIMESTAMPNS_NEW 0x4039 + #if !defined(__KERNEL__) -#define SO_TIMESTAMP SO_TIMESTAMP_OLD -#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#if __BITS_PER_LONG == 64 +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#endif + #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index d8a1bbc3e6c4..85127425b294 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -3,6 +3,7 @@ #define _ASM_SOCKET_H #include +#include /* For setsockopt(2) */ #define SOL_SOCKET 0xffff @@ -107,10 +108,19 @@ #define SO_TIMESTAMPNS_OLD 0x0021 #define SO_TIMESTAMPING_OLD 0x0023 +#define SO_TIMESTAMP_NEW 0x0041 +#define SO_TIMESTAMPNS_NEW 0x0042 + #if !defined(__KERNEL__) -#define SO_TIMESTAMP SO_TIMESTAMP_OLD -#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#if __BITS_PER_LONG == 64 +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#endif + #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4001611a4c9f..831846617d07 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3498,12 +3498,30 @@ static inline void skb_get_timestamp(const struct sk_buff *skb, *stamp = ns_to_kernel_old_timeval(skb->tstamp); } +static inline void skb_get_new_timestamp(const struct sk_buff *skb, + struct __kernel_sock_timeval *stamp) +{ + struct timespec64 ts = ktime_to_timespec64(skb->tstamp); + + stamp->tv_sec = ts.tv_sec; + stamp->tv_usec = ts.tv_nsec / 1000; +} + static inline void skb_get_timestampns(const struct sk_buff *skb, struct timespec *stamp) { *stamp = ktime_to_timespec(skb->tstamp); } +static inline void skb_get_new_timestampns(const struct sk_buff *skb, + struct __kernel_timespec *stamp) +{ + struct timespec64 ts = ktime_to_timespec64(skb->tstamp); + + stamp->tv_sec = ts.tv_sec; + stamp->tv_nsec = ts.tv_nsec; +} + static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); diff --git a/include/net/sock.h b/include/net/sock.h index 2b229f7be8eb..6679f3c120b0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -805,6 +805,7 @@ enum sock_flags { SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ + SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 4ef3aed31fb7..f22d3f7162f8 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -3,6 +3,7 @@ #define __ASM_GENERIC_SOCKET_H #include +#include /* For setsockopt(2) */ #define SOL_SOCKET 1 @@ -109,10 +110,20 @@ #define SO_TIMESTAMPNS_OLD 35 #define SO_TIMESTAMPING_OLD 37 +#define SO_TIMESTAMP_NEW 63 +#define SO_TIMESTAMPNS_NEW 64 + #if !defined(__KERNEL__) -#define SO_TIMESTAMP SO_TIMESTAMP_OLD -#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) +/* on 64-bit and x32, avoid the ?: operator */ +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#endif + #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/net/core/sock.c b/net/core/sock.c index d5ca8641968f..14b987eab10c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -868,9 +868,16 @@ set_rcvbuf: break; case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: + case SO_TIMESTAMPNS_NEW: if (valbool) { - if (optname == SO_TIMESTAMP_OLD) + if (optname == SO_TIMESTAMP_NEW || optname == SO_TIMESTAMPNS_NEW) + sock_set_flag(sk, SOCK_TSTAMP_NEW); + else + sock_reset_flag(sk, SOCK_TSTAMP_NEW); + + if (optname == SO_TIMESTAMP_OLD || optname == SO_TIMESTAMP_NEW) sock_reset_flag(sk, SOCK_RCVTSTAMPNS); else sock_set_flag(sk, SOCK_RCVTSTAMPNS); @@ -879,6 +886,7 @@ set_rcvbuf: } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); + sock_reset_flag(sk, SOCK_TSTAMP_NEW); } break; @@ -1245,11 +1253,20 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_TIMESTAMP_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && + !sock_flag(sk, SOCK_TSTAMP_NEW) && !sock_flag(sk, SOCK_RCVTSTAMPNS); break; case SO_TIMESTAMPNS_OLD: - v.val = sock_flag(sk, SOCK_RCVTSTAMPNS); + v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW); + break; + + case SO_TIMESTAMP_NEW: + v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW); + break; + + case SO_TIMESTAMPNS_NEW: + v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPING_OLD: diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3ce41b04c0f0..4e9388bf104a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1861,20 +1861,37 @@ static void tcp_update_recv_tstamps(struct sk_buff *skb, static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping *tss) { - struct __kernel_old_timeval tv; + int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); bool has_timestamping = false; if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { - put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, - sizeof(tss->ts[0]), &tss->ts[0]); + if (new_tstamp) { + struct __kernel_timespec kts = {tss->ts[0].tv_sec, tss->ts[0].tv_nsec}; + + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + sizeof(kts), &kts); + } else { + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, + sizeof(tss->ts[0]), &tss->ts[0]); + } } else { - tv.tv_sec = tss->ts[0].tv_sec; - tv.tv_usec = tss->ts[0].tv_nsec / 1000; - - put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, - sizeof(tv), &tv); + if (new_tstamp) { + struct __kernel_sock_timeval stv; + + stv.tv_sec = tss->ts[0].tv_sec; + stv.tv_usec = tss->ts[0].tv_nsec / 1000; + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(stv), &stv); + } else { + struct __kernel_old_timeval tv; + + tv.tv_sec = tss->ts[0].tv_sec; + tv.tv_usec = tss->ts[0].tv_nsec / 1000; + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } } } diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index eeb4639adbe5..65571a6273c3 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -348,7 +348,7 @@ static int rds_set_transport(struct rds_sock *rs, char __user *optval, } static int rds_enable_recvtstamp(struct sock *sk, char __user *optval, - int optlen) + int optlen, int optname) { int val, valbool; @@ -360,6 +360,9 @@ static int rds_enable_recvtstamp(struct sock *sk, char __user *optval, valbool = val ? 1 : 0; + if (optname == SO_TIMESTAMP_NEW) + sock_set_flag(sk, SOCK_TSTAMP_NEW); + if (valbool) sock_set_flag(sk, SOCK_RCVTSTAMP); else @@ -431,8 +434,9 @@ static int rds_setsockopt(struct socket *sock, int level, int optname, release_sock(sock->sk); break; case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: lock_sock(sock->sk); - ret = rds_enable_recvtstamp(sock->sk, optval, optlen); + ret = rds_enable_recvtstamp(sock->sk, optval, optlen, optname); release_sock(sock->sk); break; case SO_RDS_MSG_RXPATH_LATENCY: diff --git a/net/rds/recv.c b/net/rds/recv.c index 435bf2320cd3..6bb6b16ca270 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -550,8 +550,20 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, if ((inc->i_rx_tstamp != 0) && sock_flag(rds_rs_to_sk(rs), SOCK_RCVTSTAMP)) { struct __kernel_old_timeval tv = ns_to_kernel_old_timeval(inc->i_rx_tstamp); - ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, - sizeof(tv), &tv); + + if (!sock_flag(rds_rs_to_sk(rs), SOCK_TSTAMP_NEW)) { + ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } else { + struct __kernel_sock_timeval sk_tv; + + sk_tv.tv_sec = tv.tv_sec; + sk_tv.tv_usec = tv.tv_usec; + + ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(sk_tv), &sk_tv); + } + if (ret) goto out; } diff --git a/net/socket.c b/net/socket.c index 9cc281cdb9d9..1de96abd78d3 100644 --- a/net/socket.c +++ b/net/socket.c @@ -705,6 +705,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); + int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); struct scm_timestamping tss; int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = @@ -719,15 +720,33 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, if (need_software_tstamp) { if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { - struct __kernel_old_timeval tv; - skb_get_timestamp(skb, &tv); - put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, - sizeof(tv), &tv); + if (new_tstamp) { + struct __kernel_sock_timeval tv; + + skb_get_new_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(tv), &tv); + } else { + struct __kernel_old_timeval tv; + + skb_get_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } } else { - struct timespec ts; - skb_get_timestampns(skb, &ts); - put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, - sizeof(ts), &ts); + if (new_tstamp) { + struct __kernel_timespec ts; + + skb_get_new_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + sizeof(ts), &ts); + } else { + struct timespec ts; + + skb_get_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, + sizeof(ts), &ts); + } } } -- cgit v1.2.3 From 9718475e69084de15c3930ce35672a7dc6da866b Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 2 Feb 2019 07:34:51 -0800 Subject: socket: Add SO_TIMESTAMPING_NEW Add SO_TIMESTAMPING_NEW variant of socket timestamp options. This is the y2038 safe versions of the SO_TIMESTAMPING_OLD for all architectures. Signed-off-by: Deepa Dinamani Acked-by: Willem de Bruijn Cc: chris@zankel.net Cc: fenghua.yu@intel.com Cc: rth@twiddle.net Cc: tglx@linutronix.de Cc: ubraun@linux.ibm.com Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-s390@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: sparclinux@vger.kernel.org Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 5 +++-- arch/mips/include/uapi/asm/socket.h | 5 +++-- arch/parisc/include/uapi/asm/socket.h | 5 +++-- arch/sparc/include/uapi/asm/socket.h | 5 +++-- include/linux/socket.h | 8 ++++++++ include/uapi/asm-generic/socket.h | 5 +++-- include/uapi/linux/errqueue.h | 4 ++++ net/core/scm.c | 27 +++++++++++++++++++++++++++ net/core/sock.c | 8 +++++++- net/ipv4/tcp.c | 30 +++++++++++++++++------------- net/smc/af_smc.c | 3 ++- net/socket.c | 13 ++++++++----- 12 files changed, 88 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index aab11eec7c22..934ea6268f1a 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -117,19 +117,20 @@ #define SO_TIMESTAMP_NEW 63 #define SO_TIMESTAMPNS_NEW 64 +#define SO_TIMESTAMPING_NEW 65 #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) #endif -#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD - #define SCM_TIMESTAMP SO_TIMESTAMP #define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SCM_TIMESTAMPING SO_TIMESTAMPING diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 11014f684d9f..110f9506d64f 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -128,19 +128,20 @@ #define SO_TIMESTAMP_NEW 63 #define SO_TIMESTAMPNS_NEW 64 +#define SO_TIMESTAMPING_NEW 65 #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) #endif -#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD - #define SCM_TIMESTAMP SO_TIMESTAMP #define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SCM_TIMESTAMPING SO_TIMESTAMPING diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index cbc4b89c2fe4..bee2a9dde656 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -109,19 +109,20 @@ #define SO_TIMESTAMP_NEW 0x4038 #define SO_TIMESTAMPNS_NEW 0x4039 +#define SO_TIMESTAMPING_NEW 0x403A #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) #endif -#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD - #define SCM_TIMESTAMP SO_TIMESTAMP #define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SCM_TIMESTAMPING SO_TIMESTAMPING diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 85127425b294..2b38dda51426 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -110,19 +110,20 @@ #define SO_TIMESTAMP_NEW 0x0041 #define SO_TIMESTAMPNS_NEW 0x0042 +#define SO_TIMESTAMPING_NEW 0x0043 #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) #endif -#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD - #define SCM_TIMESTAMP SO_TIMESTAMP #define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SCM_TIMESTAMPING SO_TIMESTAMPING diff --git a/include/linux/socket.h b/include/linux/socket.h index ab2041a00e01..6016daeecee4 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -349,9 +349,17 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); +struct timespec64; struct __kernel_timespec; struct old_timespec32; +struct scm_timestamping_internal { + struct timespec64 ts[3]; +}; + +extern void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss); +extern void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss); + /* The __sys_...msg variants allow MSG_CMSG_COMPAT iff * forbid_cmsg_compat==false */ diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index f22d3f7162f8..2713e0fa68ef 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -112,6 +112,7 @@ #define SO_TIMESTAMP_NEW 63 #define SO_TIMESTAMPNS_NEW 64 +#define SO_TIMESTAMPING_NEW 65 #if !defined(__KERNEL__) @@ -119,13 +120,13 @@ /* on 64-bit and x32, avoid the ?: operator */ #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) #endif -#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD - #define SCM_TIMESTAMP SO_TIMESTAMP #define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SCM_TIMESTAMPING SO_TIMESTAMPING diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index c0151200f7d1..d955b9e32288 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -41,6 +41,10 @@ struct scm_timestamping { struct timespec ts[3]; }; +struct scm_timestamping64 { + struct __kernel_timespec ts[3]; +}; + /* The type of scm_timestamping, passed in sock_extended_err ee_info. * This defines the type of ts[0]. For SCM_TSTAMP_SND only, if ts[0] * is zero, then this is a hardware timestamp and recorded in ts[2]. diff --git a/net/core/scm.c b/net/core/scm.c index b1ff8a441748..52ef219cf6df 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -29,6 +29,7 @@ #include #include #include +#include #include @@ -252,6 +253,32 @@ out: } EXPORT_SYMBOL(put_cmsg); +void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) +{ + struct scm_timestamping64 tss; + int i; + + for (i = 0; i < ARRAY_SIZE(tss.ts); i++) { + tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec; + tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec; + } + + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_NEW, sizeof(tss), &tss); +} +EXPORT_SYMBOL(put_cmsg_scm_timestamping64); + +void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) +{ + struct scm_timestamping tss; + int i; + + for (i = 0; i < ARRAY_SIZE(tss.ts); i++) + tss.ts[i] = timespec64_to_timespec(tss_internal->ts[i]); + + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_OLD, sizeof(tss), &tss); +} +EXPORT_SYMBOL(put_cmsg_scm_timestamping); + void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) { struct cmsghdr __user *cm diff --git a/net/core/sock.c b/net/core/sock.c index 14b987eab10c..a9d1ecce96e5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -890,6 +890,8 @@ set_rcvbuf: } break; + case SO_TIMESTAMPING_NEW: + sock_set_flag(sk, SOCK_TSTAMP_NEW); case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; @@ -921,9 +923,13 @@ set_rcvbuf: if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); - else + else { + if (optname == SO_TIMESTAMPING_NEW) + sock_reset_flag(sk, SOCK_TSTAMP_NEW); + sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + } break; case SO_RCVLOWAT: diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4e9388bf104a..cab6b2f2f61d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1844,22 +1844,22 @@ out: #endif static void tcp_update_recv_tstamps(struct sk_buff *skb, - struct scm_timestamping *tss) + struct scm_timestamping_internal *tss) { if (skb->tstamp) - tss->ts[0] = ktime_to_timespec(skb->tstamp); + tss->ts[0] = ktime_to_timespec64(skb->tstamp); else - tss->ts[0] = (struct timespec) {0}; + tss->ts[0] = (struct timespec64) {0}; if (skb_hwtstamps(skb)->hwtstamp) - tss->ts[2] = ktime_to_timespec(skb_hwtstamps(skb)->hwtstamp); + tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); else - tss->ts[2] = (struct timespec) {0}; + tss->ts[2] = (struct timespec64) {0}; } /* Similar to __sock_recv_timestamp, but does not require an skb */ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, - struct scm_timestamping *tss) + struct scm_timestamping_internal *tss) { int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); bool has_timestamping = false; @@ -1873,8 +1873,10 @@ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(kts), &kts); } else { + struct timespec ts_old = timespec64_to_timespec(tss->ts[0]); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, - sizeof(tss->ts[0]), &tss->ts[0]); + sizeof(ts_old), &ts_old); } } else { if (new_tstamp) { @@ -1898,20 +1900,22 @@ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) has_timestamping = true; else - tss->ts[0] = (struct timespec) {0}; + tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) has_timestamping = true; else - tss->ts[2] = (struct timespec) {0}; + tss->ts[2] = (struct timespec64) {0}; } if (has_timestamping) { - tss->ts[1] = (struct timespec) {0}; - put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_OLD, - sizeof(*tss), tss); + tss->ts[1] = (struct timespec64) {0}; + if (sock_flag(sk, SOCK_TSTAMP_NEW)) + put_cmsg_scm_timestamping64(msg, tss); + else + put_cmsg_scm_timestamping(msg, tss); } } @@ -1952,7 +1956,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, long timeo; struct sk_buff *skb, *last; u32 urg_hole = 0; - struct scm_timestamping tss; + struct scm_timestamping_internal tss; bool has_tss = false; bool has_cmsg; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c4e56602e0c6..369870b0ef79 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -291,7 +291,8 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, (1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_WIFI_STATUS) | \ (1UL << SOCK_NOFCS) | \ - (1UL << SOCK_FILTER_LOCKED)) + (1UL << SOCK_FILTER_LOCKED) | \ + (1UL << SOCK_TSTAMP_NEW)) /* copy only relevant settings and flags of SOL_SOCKET level from smc to * clc socket (since smc is not called for these options from net/core) */ diff --git a/net/socket.c b/net/socket.c index 1de96abd78d3..d51930689b98 100644 --- a/net/socket.c +++ b/net/socket.c @@ -706,7 +706,8 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); - struct scm_timestamping tss; + struct scm_timestamping_internal tss; + int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); @@ -752,20 +753,22 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, memset(&tss, 0, sizeof(tss)); if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) && - ktime_to_timespec_cond(skb->tstamp, tss.ts + 0)) + ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && !skb_is_swtx_tstamp(skb, false_tstamp) && - ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { + ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { empty = 0; if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) put_ts_pktinfo(msg, skb); } if (!empty) { - put_cmsg(msg, SOL_SOCKET, - SO_TIMESTAMPING_OLD, sizeof(tss), &tss); + if (sock_flag(sk, SOCK_TSTAMP_NEW)) + put_cmsg_scm_timestamping64(msg, &tss); + else + put_cmsg_scm_timestamping(msg, &tss); if (skb_is_err_queue(skb) && skb->len && SKB_EXT_ERR(skb)->opt_stats) -- cgit v1.2.3 From 45bdc66159d49bfc7f75fe02d25bc74f5d2660cf Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 2 Feb 2019 07:34:53 -0800 Subject: socket: Rename SO_RCVTIMEO/ SO_SNDTIMEO with _OLD suffixes SO_RCVTIMEO and SO_SNDTIMEO socket options use struct timeval as the time format. struct timeval is not y2038 safe. The subsequent patches in the series add support for new socket timeout options with _NEW suffix that will use y2038 safe data structures. Although the existing struct timeval layout is sufficiently wide to represent timeouts, because of the way libc will interpret time_t based on user defined flag, these new flags provide a way of having a structure that is the same for all architectures consistently. Rename the existing options with _OLD suffix forms so that the right option is enabled for userspace applications according to the architecture and time_t definition of libc. Signed-off-by: Deepa Dinamani Acked-by: Willem de Bruijn Cc: ccaulfie@redhat.com Cc: deller@gmx.de Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: rth@twiddle.net Cc: cluster-devel@redhat.com Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: sparclinux@vger.kernel.org Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 7 +++++-- arch/mips/include/uapi/asm/socket.h | 6 ++++-- arch/parisc/include/uapi/asm/socket.h | 6 ++++-- arch/powerpc/include/uapi/asm/socket.h | 4 ++-- arch/sparc/include/uapi/asm/socket.h | 7 +++++-- fs/dlm/lowcomms.c | 4 ++-- include/uapi/asm-generic/socket.h | 6 ++++-- net/core/sock.c | 4 ++-- 8 files changed, 28 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 934ea6268f1a..9826d1db71d0 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -31,8 +31,8 @@ #define SO_RCVBUFFORCE 0x100b #define SO_RCVLOWAT 0x1010 #define SO_SNDLOWAT 0x1011 -#define SO_RCVTIMEO 0x1012 -#define SO_SNDTIMEO 0x1013 +#define SO_RCVTIMEO_OLD 0x1012 +#define SO_SNDTIMEO_OLD 0x1013 #define SO_ACCEPTCONN 0x1014 #define SO_PROTOCOL 0x1028 #define SO_DOMAIN 0x1029 @@ -121,6 +121,9 @@ #if !defined(__KERNEL__) +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD + #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 110f9506d64f..96cc0e907f12 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -39,8 +39,8 @@ #define SO_RCVBUF 0x1002 /* Receive buffer. */ #define SO_SNDLOWAT 0x1003 /* send low-water mark */ #define SO_RCVLOWAT 0x1004 /* receive low-water mark */ -#define SO_SNDTIMEO 0x1005 /* send timeout */ -#define SO_RCVTIMEO 0x1006 /* receive timeout */ +#define SO_SNDTIMEO_OLD 0x1005 /* send timeout */ +#define SO_RCVTIMEO_OLD 0x1006 /* receive timeout */ #define SO_ACCEPTCONN 0x1009 #define SO_PROTOCOL 0x1028 /* protocol type */ #define SO_DOMAIN 0x1029 /* domain/socket family */ @@ -132,6 +132,8 @@ #if !defined(__KERNEL__) +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index bee2a9dde656..046f0cd9cce4 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -22,8 +22,8 @@ #define SO_RCVBUFFORCE 0x100b #define SO_SNDLOWAT 0x1003 #define SO_RCVLOWAT 0x1004 -#define SO_SNDTIMEO 0x1005 -#define SO_RCVTIMEO 0x1006 +#define SO_SNDTIMEO_OLD 0x1005 +#define SO_RCVTIMEO_OLD 0x1006 #define SO_ERROR 0x1007 #define SO_TYPE 0x1008 #define SO_PROTOCOL 0x1028 @@ -113,6 +113,8 @@ #if !defined(__KERNEL__) +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 94de465e0920..12aa0c43e775 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -11,8 +11,8 @@ #define SO_RCVLOWAT 16 #define SO_SNDLOWAT 17 -#define SO_RCVTIMEO 18 -#define SO_SNDTIMEO 19 +#define SO_RCVTIMEO_OLD 18 +#define SO_SNDTIMEO_OLD 19 #define SO_PASSCRED 20 #define SO_PEERCRED 21 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 2b38dda51426..342ffdc3b424 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -21,8 +21,8 @@ #define SO_BSDCOMPAT 0x0400 #define SO_RCVLOWAT 0x0800 #define SO_SNDLOWAT 0x1000 -#define SO_RCVTIMEO 0x2000 -#define SO_SNDTIMEO 0x4000 +#define SO_RCVTIMEO_OLD 0x2000 +#define SO_SNDTIMEO_OLD 0x4000 #define SO_ACCEPTCONN 0x8000 #define SO_SNDBUF 0x1001 @@ -114,6 +114,9 @@ #if !defined(__KERNEL__) +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD + #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 76976d6e50f9..c98ad9777ad9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1089,12 +1089,12 @@ static void sctp_connect_to_sock(struct connection *con) * since O_NONBLOCK argument in connect() function does not work here, * then, we should restore the default value of this attribute. */ - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len, 0); memset(&tv, 0, sizeof(tv)); - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); if (result == -EINPROGRESS) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 2713e0fa68ef..c56b8b487c12 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -30,8 +30,8 @@ #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 #define SO_SNDLOWAT 19 -#define SO_RCVTIMEO 20 -#define SO_SNDTIMEO 21 +#define SO_RCVTIMEO_OLD 20 +#define SO_SNDTIMEO_OLD 21 #endif /* Security levels - as per NRL IPv6 - don't actually do anything */ @@ -116,6 +116,8 @@ #if !defined(__KERNEL__) +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) /* on 64-bit and x32, avoid the ?: operator */ #define SO_TIMESTAMP SO_TIMESTAMP_OLD diff --git a/net/core/sock.c b/net/core/sock.c index a9d1ecce96e5..27b40002b780 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -941,11 +941,11 @@ set_rcvbuf: sk->sk_rcvlowat = val ? : 1; break; - case SO_RCVTIMEO: + case SO_RCVTIMEO_OLD: ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); break; - case SO_SNDTIMEO: + case SO_SNDTIMEO_OLD: ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); break; -- cgit v1.2.3 From a9beb86ae6e55bd92f38453c8623de60b8e5a308 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 2 Feb 2019 07:34:54 -0800 Subject: sock: Add SO_RCVTIMEO_NEW and SO_SNDTIMEO_NEW Add new socket timeout options that are y2038 safe. Signed-off-by: Deepa Dinamani Acked-by: Willem de Bruijn Cc: ccaulfie@redhat.com Cc: davem@davemloft.net Cc: deller@gmx.de Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: rth@twiddle.net Cc: cluster-devel@redhat.com Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: sparclinux@vger.kernel.org Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 12 ++++++-- arch/mips/include/uapi/asm/socket.h | 11 ++++++-- arch/parisc/include/uapi/asm/socket.h | 10 +++++-- arch/sparc/include/uapi/asm/socket.h | 11 ++++++-- include/uapi/asm-generic/socket.h | 11 ++++++-- net/core/sock.c | 53 ++++++++++++++++++++++++++--------- 6 files changed, 83 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 9826d1db71d0..0d0fddb7e738 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -119,19 +119,25 @@ #define SO_TIMESTAMPNS_NEW 64 #define SO_TIMESTAMPING_NEW 65 -#if !defined(__KERNEL__) +#define SO_RCVTIMEO_NEW 66 +#define SO_SNDTIMEO_NEW 67 -#define SO_RCVTIMEO SO_RCVTIMEO_OLD -#define SO_SNDTIMEO SO_SNDTIMEO_OLD +#if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) #define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) #endif #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 96cc0e907f12..eb9f33f8a8b3 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -130,18 +130,25 @@ #define SO_TIMESTAMPNS_NEW 64 #define SO_TIMESTAMPING_NEW 65 +#define SO_RCVTIMEO_NEW 66 +#define SO_SNDTIMEO_NEW 67 + #if !defined(__KERNEL__) -#define SO_RCVTIMEO SO_RCVTIMEO_OLD -#define SO_SNDTIMEO SO_SNDTIMEO_OLD #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) #define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) #endif #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 046f0cd9cce4..16e428f03526 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -111,18 +111,24 @@ #define SO_TIMESTAMPNS_NEW 0x4039 #define SO_TIMESTAMPING_NEW 0x403A +#define SO_RCVTIMEO_NEW 0x4040 +#define SO_SNDTIMEO_NEW 0x4041 + #if !defined(__KERNEL__) -#define SO_RCVTIMEO SO_RCVTIMEO_OLD -#define SO_SNDTIMEO SO_SNDTIMEO_OLD #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) #define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) #endif #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 342ffdc3b424..8c9f74a66b55 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -112,19 +112,26 @@ #define SO_TIMESTAMPNS_NEW 0x0042 #define SO_TIMESTAMPING_NEW 0x0043 +#define SO_RCVTIMEO_NEW 0x0044 +#define SO_SNDTIMEO_NEW 0x0045 + #if !defined(__KERNEL__) -#define SO_RCVTIMEO SO_RCVTIMEO_OLD -#define SO_SNDTIMEO SO_SNDTIMEO_OLD #if __BITS_PER_LONG == 64 #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) #define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) #endif #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index c56b8b487c12..c8b430cb6dc4 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -114,19 +114,26 @@ #define SO_TIMESTAMPNS_NEW 64 #define SO_TIMESTAMPING_NEW 65 +#define SO_RCVTIMEO_NEW 66 +#define SO_SNDTIMEO_NEW 67 + #if !defined(__KERNEL__) -#define SO_RCVTIMEO SO_RCVTIMEO_OLD -#define SO_SNDTIMEO SO_SNDTIMEO_OLD #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) /* on 64-bit and x32, avoid the ?: operator */ #define SO_TIMESTAMP SO_TIMESTAMP_OLD #define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD #define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD #else #define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) #define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) #define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) #endif #define SCM_TIMESTAMP SO_TIMESTAMP diff --git a/net/core/sock.c b/net/core/sock.c index 27b40002b780..a8904ae40713 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -335,9 +335,10 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(__sk_backlog_rcv); -static int sock_get_timeout(long timeo, void *optval) +static int sock_get_timeout(long timeo, void *optval, bool old_timeval) { - struct __kernel_old_timeval tv; + struct __kernel_sock_timeval tv; + int size; if (timeo == MAX_SCHEDULE_TIMEOUT) { tv.tv_sec = 0; @@ -353,13 +354,23 @@ static int sock_get_timeout(long timeo, void *optval) return sizeof(tv32); } - *(struct __kernel_old_timeval *)optval = tv; - return sizeof(tv); + if (old_timeval) { + struct __kernel_old_timeval old_tv; + old_tv.tv_sec = tv.tv_sec; + old_tv.tv_usec = tv.tv_usec; + *(struct __kernel_old_timeval *)optval = old_tv; + size = sizeof(old_tv); + } else { + *(struct __kernel_sock_timeval *)optval = tv; + size = sizeof(tv); + } + + return size; } -static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) +static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval) { - struct __kernel_old_timeval tv; + struct __kernel_sock_timeval tv; if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; @@ -371,6 +382,15 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) return -EFAULT; tv.tv_sec = tv32.tv_sec; tv.tv_usec = tv32.tv_usec; + } else if (old_timeval) { + struct __kernel_old_timeval old_tv; + + if (optlen < sizeof(old_tv)) + return -EINVAL; + if (copy_from_user(&old_tv, optval, sizeof(old_tv))) + return -EFAULT; + tv.tv_sec = old_tv.tv_sec; + tv.tv_usec = old_tv.tv_usec; } else { if (optlen < sizeof(tv)) return -EINVAL; @@ -394,8 +414,8 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) *timeo_p = MAX_SCHEDULE_TIMEOUT; if (tv.tv_sec == 0 && tv.tv_usec == 0) return 0; - if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1)) - *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP(tv.tv_usec, USEC_PER_SEC / HZ); + if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) + *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); return 0; } @@ -942,11 +962,13 @@ set_rcvbuf: break; case SO_RCVTIMEO_OLD: - ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); + case SO_RCVTIMEO_NEW: + ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD); break; case SO_SNDTIMEO_OLD: - ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); + case SO_SNDTIMEO_NEW: + ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD); break; case SO_ATTACH_FILTER: @@ -1171,6 +1193,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct linger ling; struct old_timeval32 tm32; struct __kernel_old_timeval tm; + struct __kernel_sock_timeval stm; struct sock_txtime txtime; } v; @@ -1279,12 +1302,14 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_tsflags; break; - case SO_RCVTIMEO: - lv = sock_get_timeout(sk->sk_rcvtimeo, &v); + case SO_RCVTIMEO_OLD: + case SO_RCVTIMEO_NEW: + lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname); break; - case SO_SNDTIMEO: - lv = sock_get_timeout(sk->sk_sndtimeo, &v); + case SO_SNDTIMEO_OLD: + case SO_SNDTIMEO_NEW: + lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: -- cgit v1.2.3 From bff5731d43efbdf0bbd2d73cab32fe6435ea1046 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 1 Feb 2019 17:56:28 -0800 Subject: net: devlink: report cell size of shared buffers Shared buffer allocation is usually done in cell increments. Drivers will either round up the allocation or refuse the configuration if it's not an exact multiple of cell size. Drivers know exactly the cell size of shared buffer, so help out users by providing this information in dumps. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 1 + drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c | 1 + include/net/devlink.h | 1 + include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 3 +++ 5 files changed, 8 insertions(+) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 12c61e0cc570..80066f437a65 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -713,6 +713,7 @@ int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core, pool_info->pool_type = (enum devlink_sb_pool_type) dir; pool_info->size = mlxsw_sp_cells_bytes(mlxsw_sp, pr->size); pool_info->threshold_type = (enum devlink_sb_threshold_type) pr->mode; + pool_info->cell_size = mlxsw_sp->sb->cell_size; return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c b/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c index 814360ed3a20..ea2e3f829aba 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c @@ -48,6 +48,7 @@ int nfp_shared_buf_pool_get(struct nfp_pf *pf, unsigned int sb, u16 pool_index, pool_info->pool_type = le32_to_cpu(get_data.pool_type); pool_info->threshold_type = le32_to_cpu(get_data.threshold_type); pool_info->size = le32_to_cpu(get_data.size) * unit_size; + pool_info->cell_size = unit_size; return 0; } diff --git a/include/net/devlink.h b/include/net/devlink.h index 1c8523920f66..74d992a68a06 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -62,6 +62,7 @@ struct devlink_sb_pool_info { enum devlink_sb_pool_type pool_type; u32 size; enum devlink_sb_threshold_type threshold_type; + u32 cell_size; }; /** diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 7fffd879c328..054b2d1a4537 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -300,6 +300,8 @@ enum devlink_attr { DEVLINK_ATTR_INFO_VERSION_NAME, /* string */ DEVLINK_ATTR_INFO_VERSION_VALUE, /* string */ + DEVLINK_ATTR_SB_POOL_CELL_SIZE, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index eb839d74bcc0..52bf27491fb8 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -932,6 +932,9 @@ static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, pool_info.threshold_type)) goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE, + pool_info.cell_size)) + goto nla_put_failure; genlmsg_end(msg, hdr); return 0; -- cgit v1.2.3 From 9fb20801dab46238706267896df1b3938d977129 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 1 Feb 2019 20:20:52 -0800 Subject: net: Fix ip_mc_{dec,inc}_group allocation context After 4effd28c1245 ("bridge: join all-snoopers multicast address"), I started seeing the following sleep in atomic warnings: [ 26.763893] BUG: sleeping function called from invalid context at mm/slab.h:421 [ 26.771425] in_atomic(): 1, irqs_disabled(): 0, pid: 1658, name: sh [ 26.777855] INFO: lockdep is turned off. [ 26.781916] CPU: 0 PID: 1658 Comm: sh Not tainted 5.0.0-rc4 #20 [ 26.787943] Hardware name: BCM97278SV (DT) [ 26.792118] Call trace: [ 26.794645] dump_backtrace+0x0/0x170 [ 26.798391] show_stack+0x24/0x30 [ 26.801787] dump_stack+0xa4/0xe4 [ 26.805182] ___might_sleep+0x208/0x218 [ 26.809102] __might_sleep+0x78/0x88 [ 26.812762] kmem_cache_alloc_trace+0x64/0x28c [ 26.817301] igmp_group_dropped+0x150/0x230 [ 26.821573] ip_mc_dec_group+0x1b0/0x1f8 [ 26.825585] br_ip4_multicast_leave_snoopers.isra.11+0x174/0x190 [ 26.831704] br_multicast_toggle+0x78/0xcc [ 26.835887] store_bridge_parm+0xc4/0xfc [ 26.839894] multicast_snooping_store+0x3c/0x4c [ 26.844517] dev_attr_store+0x44/0x5c [ 26.848262] sysfs_kf_write+0x50/0x68 [ 26.852006] kernfs_fop_write+0x14c/0x1b4 [ 26.856102] __vfs_write+0x60/0x190 [ 26.859668] vfs_write+0xc8/0x168 [ 26.863059] ksys_write+0x70/0xc8 [ 26.866449] __arm64_sys_write+0x24/0x30 [ 26.870458] el0_svc_common+0xa0/0x11c [ 26.874291] el0_svc_handler+0x38/0x70 [ 26.878120] el0_svc+0x8/0xc while toggling the bridge's multicast_snooping attribute dynamically. Pass a gfp_t down to igmpv3_add_delrec(), introduce __igmp_group_dropped() and introduce __ip_mc_dec_group() to take a gfp_t argument. Similarly introduce ____ip_mc_inc_group() and __ip_mc_inc_group() to allow caller to specify gfp_t. IPv6 part of the patch appears fine. Fixes: 4effd28c1245 ("bridge: join all-snoopers multicast address") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/igmp.h | 8 +++++++- net/bridge/br_multicast.c | 4 ++-- net/ipv4/igmp.c | 35 ++++++++++++++++++++++++----------- 3 files changed, 33 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 8b4348f69bc5..cc85f4524dbf 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -137,7 +137,13 @@ extern void ip_mc_up(struct in_device *); extern void ip_mc_down(struct in_device *); extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); -extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); +extern void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); +static inline void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) +{ + return __ip_mc_dec_group(in_dev, addr, GFP_KERNEL); +} +extern void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, + gfp_t gfp); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); int ip_mc_check_igmp(struct sk_buff *skb); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 780757b7a82f..1fb885a33c66 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1841,7 +1841,7 @@ static void br_ip4_multicast_join_snoopers(struct net_bridge *br) if (!in_dev) return; - ip_mc_inc_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP)); + __ip_mc_inc_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); in_dev_put(in_dev); } @@ -1872,7 +1872,7 @@ static void br_ip4_multicast_leave_snoopers(struct net_bridge *br) if (WARN_ON(!in_dev)) return; - ip_mc_dec_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP)); + __ip_mc_dec_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); in_dev_put(in_dev); } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a40e48ded10d..b448cf32296c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -159,7 +159,8 @@ static int unsolicited_report_interval(struct in_device *in_dev) return interval_jiffies; } -static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im); +static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, + gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); @@ -1145,7 +1146,8 @@ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) /* * deleted ip_mc_list manipulation */ -static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) +static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, + gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); @@ -1156,7 +1158,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ - pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); + pmc = kzalloc(sizeof(*pmc), gfp); if (!pmc) return; spin_lock_init(&pmc->lock); @@ -1261,7 +1263,7 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) } #endif -static void igmp_group_dropped(struct ip_mc_list *im) +static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST @@ -1292,13 +1294,18 @@ static void igmp_group_dropped(struct ip_mc_list *im) return; } /* IGMPv3 */ - igmpv3_add_delrec(in_dev, im); + igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } +static void igmp_group_dropped(struct ip_mc_list *im) +{ + __igmp_group_dropped(im, GFP_KERNEL); +} + static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; @@ -1400,8 +1407,8 @@ static void ip_mc_hash_remove(struct in_device *in_dev, /* * A socket has joined a multicast group on device dev. */ -static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, - unsigned int mode) +static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, + unsigned int mode, gfp_t gfp) { struct ip_mc_list *im; @@ -1415,7 +1422,7 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, } } - im = kzalloc(sizeof(*im), GFP_KERNEL); + im = kzalloc(sizeof(*im), gfp); if (!im) goto out; @@ -1448,6 +1455,12 @@ out: return; } +void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) +{ + ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); +} +EXPORT_SYMBOL(__ip_mc_inc_group); + void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE); @@ -1634,7 +1647,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) * A socket has left a multicast group on device dev */ -void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) +void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; @@ -1649,7 +1662,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; - igmp_group_dropped(i); + __igmp_group_dropped(i, gfp); ip_mc_clear_src(i); if (!in_dev->dead) @@ -1662,7 +1675,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) } } } -EXPORT_SYMBOL(ip_mc_dec_group); +EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ -- cgit v1.2.3 From 5f3d544f1671d214cd26e45bda326f921455256e Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Fri, 1 Feb 2019 22:45:17 -0500 Subject: audit: remove audit_context when CONFIG_ AUDIT and not AUDITSYSCALL Remove audit_context from struct task_struct and struct audit_buffer when CONFIG_AUDIT is enabled but CONFIG_AUDITSYSCALL is not. Also, audit_log_name() (and supporting inode and fcaps functions) should have been put back in auditsc.c when soft and hard link logging was normalized since it is only used by syscall auditing. See github issue https://github.com/linux-audit/audit-kernel/issues/105 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/sched.h | 4 +- kernel/audit.c | 157 ------------------------------------------------- kernel/audit.h | 9 --- kernel/auditsc.c | 158 ++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 161 insertions(+), 167 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index f9788bb122c5..765119df759a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -885,8 +885,10 @@ struct task_struct { struct callback_head *task_works; - struct audit_context *audit_context; #ifdef CONFIG_AUDIT +#ifdef CONFIG_AUDITSYSCALL + struct audit_context *audit_context; +#endif kuid_t loginuid; unsigned int sessionid; #endif diff --git a/kernel/audit.c b/kernel/audit.c index b7177a8def2e..c89ea48c70a6 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -2067,163 +2067,6 @@ void audit_log_key(struct audit_buffer *ab, char *key) audit_log_format(ab, "(null)"); } -void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) -{ - int i; - - if (cap_isclear(*cap)) { - audit_log_format(ab, " %s=0", prefix); - return; - } - audit_log_format(ab, " %s=", prefix); - CAP_FOR_EACH_U32(i) - audit_log_format(ab, "%08x", cap->cap[CAP_LAST_U32 - i]); -} - -static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) -{ - if (name->fcap_ver == -1) { - audit_log_format(ab, " cap_fe=? cap_fver=? cap_fp=? cap_fi=?"); - return; - } - audit_log_cap(ab, "cap_fp", &name->fcap.permitted); - audit_log_cap(ab, "cap_fi", &name->fcap.inheritable); - audit_log_format(ab, " cap_fe=%d cap_fver=%x cap_frootid=%d", - name->fcap.fE, name->fcap_ver, - from_kuid(&init_user_ns, name->fcap.rootid)); -} - -static inline int audit_copy_fcaps(struct audit_names *name, - const struct dentry *dentry) -{ - struct cpu_vfs_cap_data caps; - int rc; - - if (!dentry) - return 0; - - rc = get_vfs_caps_from_disk(dentry, &caps); - if (rc) - return rc; - - name->fcap.permitted = caps.permitted; - name->fcap.inheritable = caps.inheritable; - name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); - name->fcap.rootid = caps.rootid; - name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >> - VFS_CAP_REVISION_SHIFT; - - return 0; -} - -/* Copy inode data into an audit_names. */ -void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, - struct inode *inode, unsigned int flags) -{ - name->ino = inode->i_ino; - name->dev = inode->i_sb->s_dev; - name->mode = inode->i_mode; - name->uid = inode->i_uid; - name->gid = inode->i_gid; - name->rdev = inode->i_rdev; - security_inode_getsecid(inode, &name->osid); - if (flags & AUDIT_INODE_NOEVAL) { - name->fcap_ver = -1; - return; - } - audit_copy_fcaps(name, dentry); -} - -/** - * audit_log_name - produce AUDIT_PATH record from struct audit_names - * @context: audit_context for the task - * @n: audit_names structure with reportable details - * @path: optional path to report instead of audit_names->name - * @record_num: record number to report when handling a list of names - * @call_panic: optional pointer to int that will be updated if secid fails - */ -void audit_log_name(struct audit_context *context, struct audit_names *n, - const struct path *path, int record_num, int *call_panic) -{ - struct audit_buffer *ab; - ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH); - if (!ab) - return; - - audit_log_format(ab, "item=%d", record_num); - - if (path) - audit_log_d_path(ab, " name=", path); - else if (n->name) { - switch (n->name_len) { - case AUDIT_NAME_FULL: - /* log the full path */ - audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, n->name->name); - break; - case 0: - /* name was specified as a relative path and the - * directory component is the cwd */ - audit_log_d_path(ab, " name=", &context->pwd); - break; - default: - /* log the name's directory component */ - audit_log_format(ab, " name="); - audit_log_n_untrustedstring(ab, n->name->name, - n->name_len); - } - } else - audit_log_format(ab, " name=(null)"); - - if (n->ino != AUDIT_INO_UNSET) - audit_log_format(ab, " inode=%lu" - " dev=%02x:%02x mode=%#ho" - " ouid=%u ogid=%u rdev=%02x:%02x", - n->ino, - MAJOR(n->dev), - MINOR(n->dev), - n->mode, - from_kuid(&init_user_ns, n->uid), - from_kgid(&init_user_ns, n->gid), - MAJOR(n->rdev), - MINOR(n->rdev)); - if (n->osid != 0) { - char *ctx = NULL; - u32 len; - if (security_secid_to_secctx( - n->osid, &ctx, &len)) { - audit_log_format(ab, " osid=%u", n->osid); - if (call_panic) - *call_panic = 2; - } else { - audit_log_format(ab, " obj=%s", ctx); - security_release_secctx(ctx, len); - } - } - - /* log the audit_names record type */ - switch(n->type) { - case AUDIT_TYPE_NORMAL: - audit_log_format(ab, " nametype=NORMAL"); - break; - case AUDIT_TYPE_PARENT: - audit_log_format(ab, " nametype=PARENT"); - break; - case AUDIT_TYPE_CHILD_DELETE: - audit_log_format(ab, " nametype=DELETE"); - break; - case AUDIT_TYPE_CHILD_CREATE: - audit_log_format(ab, " nametype=CREATE"); - break; - default: - audit_log_format(ab, " nametype=UNKNOWN"); - break; - } - - audit_log_fcaps(ab, n); - audit_log_end(ab); -} - int audit_log_task_context(struct audit_buffer *ab) { char *ctx = NULL; diff --git a/kernel/audit.h b/kernel/audit.h index 002f0f7ba732..82734f438ddd 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -213,15 +213,6 @@ extern bool audit_ever_enabled; extern void audit_log_session_info(struct audit_buffer *ab); -extern void audit_copy_inode(struct audit_names *name, - const struct dentry *dentry, - struct inode *inode, unsigned int flags); -extern void audit_log_cap(struct audit_buffer *ab, char *prefix, - kernel_cap_t *cap); -extern void audit_log_name(struct audit_context *context, - struct audit_names *n, const struct path *path, - int record_num, int *call_panic); - extern int auditd_test_task(struct task_struct *task); #define AUDIT_INODE_BUCKETS 32 diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 7d37cb1e4aef..d1eab1d4a930 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1139,6 +1139,32 @@ out: kfree(buf_head); } +void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) +{ + int i; + + if (cap_isclear(*cap)) { + audit_log_format(ab, " %s=0", prefix); + return; + } + audit_log_format(ab, " %s=", prefix); + CAP_FOR_EACH_U32(i) + audit_log_format(ab, "%08x", cap->cap[CAP_LAST_U32 - i]); +} + +static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) +{ + if (name->fcap_ver == -1) { + audit_log_format(ab, " cap_fe=? cap_fver=? cap_fp=? cap_fi=?"); + return; + } + audit_log_cap(ab, "cap_fp", &name->fcap.permitted); + audit_log_cap(ab, "cap_fi", &name->fcap.inheritable); + audit_log_format(ab, " cap_fe=%d cap_fver=%x cap_frootid=%d", + name->fcap.fE, name->fcap_ver, + from_kuid(&init_user_ns, name->fcap.rootid)); +} + static void show_special(struct audit_context *context, int *call_panic) { struct audit_buffer *ab; @@ -1261,6 +1287,97 @@ static inline int audit_proctitle_rtrim(char *proctitle, int len) return len; } +/* + * audit_log_name - produce AUDIT_PATH record from struct audit_names + * @context: audit_context for the task + * @n: audit_names structure with reportable details + * @path: optional path to report instead of audit_names->name + * @record_num: record number to report when handling a list of names + * @call_panic: optional pointer to int that will be updated if secid fails + */ +static void audit_log_name(struct audit_context *context, struct audit_names *n, + const struct path *path, int record_num, int *call_panic) +{ + struct audit_buffer *ab; + + ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH); + if (!ab) + return; + + audit_log_format(ab, "item=%d", record_num); + + if (path) + audit_log_d_path(ab, " name=", path); + else if (n->name) { + switch (n->name_len) { + case AUDIT_NAME_FULL: + /* log the full path */ + audit_log_format(ab, " name="); + audit_log_untrustedstring(ab, n->name->name); + break; + case 0: + /* name was specified as a relative path and the + * directory component is the cwd + */ + audit_log_d_path(ab, " name=", &context->pwd); + break; + default: + /* log the name's directory component */ + audit_log_format(ab, " name="); + audit_log_n_untrustedstring(ab, n->name->name, + n->name_len); + } + } else + audit_log_format(ab, " name=(null)"); + + if (n->ino != AUDIT_INO_UNSET) + audit_log_format(ab, " inode=%lu dev=%02x:%02x mode=%#ho ouid=%u ogid=%u rdev=%02x:%02x", + n->ino, + MAJOR(n->dev), + MINOR(n->dev), + n->mode, + from_kuid(&init_user_ns, n->uid), + from_kgid(&init_user_ns, n->gid), + MAJOR(n->rdev), + MINOR(n->rdev)); + if (n->osid != 0) { + char *ctx = NULL; + u32 len; + + if (security_secid_to_secctx( + n->osid, &ctx, &len)) { + audit_log_format(ab, " osid=%u", n->osid); + if (call_panic) + *call_panic = 2; + } else { + audit_log_format(ab, " obj=%s", ctx); + security_release_secctx(ctx, len); + } + } + + /* log the audit_names record type */ + switch (n->type) { + case AUDIT_TYPE_NORMAL: + audit_log_format(ab, " nametype=NORMAL"); + break; + case AUDIT_TYPE_PARENT: + audit_log_format(ab, " nametype=PARENT"); + break; + case AUDIT_TYPE_CHILD_DELETE: + audit_log_format(ab, " nametype=DELETE"); + break; + case AUDIT_TYPE_CHILD_CREATE: + audit_log_format(ab, " nametype=CREATE"); + break; + default: + audit_log_format(ab, " nametype=UNKNOWN"); + break; + } + + audit_log_fcaps(ab, n); + audit_log_end(ab); +} + static void audit_log_proctitle(void) { int res; @@ -1756,6 +1873,47 @@ void __audit_getname(struct filename *name) get_fs_pwd(current->fs, &context->pwd); } +static inline int audit_copy_fcaps(struct audit_names *name, + const struct dentry *dentry) +{ + struct cpu_vfs_cap_data caps; + int rc; + + if (!dentry) + return 0; + + rc = get_vfs_caps_from_disk(dentry, &caps); + if (rc) + return rc; + + name->fcap.permitted = caps.permitted; + name->fcap.inheritable = caps.inheritable; + name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); + name->fcap.rootid = caps.rootid; + name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >> + VFS_CAP_REVISION_SHIFT; + + return 0; +} + +/* Copy inode data into an audit_names. */ +void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, + struct inode *inode, unsigned int flags) +{ + name->ino = inode->i_ino; + name->dev = inode->i_sb->s_dev; + name->mode = inode->i_mode; + name->uid = inode->i_uid; + name->gid = inode->i_gid; + name->rdev = inode->i_rdev; + security_inode_getsecid(inode, &name->osid); + if (flags & AUDIT_INODE_NOEVAL) { + name->fcap_ver = -1; + return; + } + audit_copy_fcaps(name, dentry); +} + /** * __audit_inode - store the inode and device from a lookup * @name: name being audited -- cgit v1.2.3 From ce3fdb697f684b0c018cda8af91f953b7936a9c2 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sat, 2 Feb 2019 19:47:25 -0800 Subject: netdevice.h: Add __cold to netdev_ logging functions Add __cold to the netdev_ logging functions similar to the use of __cold in the generic printk function. Using __cold moves all the netdev_ logging functions out-of-line possibly improving code locality and runtime performance. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/netdevice.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e675ef97a426..ba57d0ba425e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4663,22 +4663,22 @@ static inline const char *netdev_reg_state(const struct net_device *dev) return " (unknown)"; } -__printf(3, 4) +__printf(3, 4) __cold void netdev_printk(const char *level, const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_emerg(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_alert(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_crit(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_err(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_warn(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_notice(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_info(const struct net_device *dev, const char *format, ...); #define netdev_level_once(level, dev, fmt, ...) \ -- cgit v1.2.3 From 494c704f9af0a0cddf593b381ea44320888733e6 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 2 Feb 2019 10:41:13 +0100 Subject: efi: Use 32-bit alignment for efi_guid_t The UEFI spec and EDK2 reference implementation both define EFI_GUID as struct { u32 a; u16; b; u16 c; u8 d[8]; }; and so the implied alignment is 32 bits not 8 bits like our guid_t. In some cases (i.e., on 32-bit ARM), this means that firmware services invoked by the kernel may assume that efi_guid_t* arguments are 32-bit aligned, and use memory accessors that do not tolerate misalignment. So let's set the minimum alignment to 32 bits. Note that the UEFI spec as well as some comments in the EDK2 code base suggest that EFI_GUID should be 64-bit aligned, but this appears to be a mistake, given that no code seems to exist that actually enforces that or relies on it. Reported-by: Heinrich Schuchardt Signed-off-by: Ard Biesheuvel Reviewed-by: Leif Lindholm Cc: AKASHI Takahiro Cc: Alexander Graf Cc: Bjorn Andersson Cc: Borislav Petkov Cc: Jeffrey Hugo Cc: Lee Jones Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Jones Cc: Peter Zijlstra Cc: Sai Praneeth Prakhya Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20190202094119.13230-5-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 45ff763fba76..be08518c2553 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -48,7 +48,20 @@ typedef u16 efi_char16_t; /* UNICODE character */ typedef u64 efi_physical_addr_t; typedef void *efi_handle_t; -typedef guid_t efi_guid_t; +/* + * The UEFI spec and EDK2 reference implementation both define EFI_GUID as + * struct { u32 a; u16; b; u16 c; u8 d[8]; }; and so the implied alignment + * is 32 bits not 8 bits like our guid_t. In some cases (i.e., on 32-bit ARM), + * this means that firmware services invoked by the kernel may assume that + * efi_guid_t* arguments are 32-bit aligned, and use memory accessors that + * do not tolerate misalignment. So let's set the minimum alignment to 32 bits. + * + * Note that the UEFI spec as well as some comments in the EDK2 code base + * suggest that EFI_GUID should be 64-bit aligned, but this appears to be + * a mistake, given that no code seems to exist that actually enforces that + * or relies on it. + */ +typedef guid_t efi_guid_t __aligned(__alignof__(u32)); #define EFI_GUID(a,b,c,d0,d1,d2,d3,d4,d5,d6,d7) \ GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) -- cgit v1.2.3 From 8c94abbbe1ba24961278055434504b7dc3595415 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Mon, 28 Jan 2019 14:27:26 +0200 Subject: perf: Convert perf_event_context.refcount to refcount_t atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable perf_event_context.refcount is used as pure reference counter. Convert it to refcount_t and fix up the operations. ** Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. Please check Documentation/core-api/refcount-vs-atomic.rst for more information. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the perf_event_context.refcount it might make a difference in following places: - get_ctx(), perf_event_ctx_lock_nested(), perf_lock_task_context() and __perf_event_ctx_lock_double(): increment in refcount_inc_not_zero() only guarantees control dependency on success vs. fully ordered atomic counterpart - put_ctx(): decrement in refcount_dec_and_test() provides RELEASE ordering and ACQUIRE ordering + control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook Signed-off-by: Elena Reshetova Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: David Windsor Reviewed-by: Hans Liljestrand Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@kernel.org Cc: namhyung@kernel.org Link: https://lkml.kernel.org/r/1548678448-24458-2-git-send-email-elena.reshetova@intel.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 3 ++- kernel/events/core.c | 12 ++++++------ 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a79e59fc3b7d..6cb5d483ab34 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -54,6 +54,7 @@ struct perf_guest_info_callbacks { #include #include #include +#include #include struct perf_callchain_entry { @@ -737,7 +738,7 @@ struct perf_event_context { int nr_stat; int nr_freq; int rotate_disable; - atomic_t refcount; + refcount_t refcount; struct task_struct *task; /* diff --git a/kernel/events/core.c b/kernel/events/core.c index 5b89de7918d0..677164d54547 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1172,7 +1172,7 @@ static void perf_event_ctx_deactivate(struct perf_event_context *ctx) static void get_ctx(struct perf_event_context *ctx) { - WARN_ON(!atomic_inc_not_zero(&ctx->refcount)); + refcount_inc(&ctx->refcount); } static void free_ctx(struct rcu_head *head) @@ -1186,7 +1186,7 @@ static void free_ctx(struct rcu_head *head) static void put_ctx(struct perf_event_context *ctx) { - if (atomic_dec_and_test(&ctx->refcount)) { + if (refcount_dec_and_test(&ctx->refcount)) { if (ctx->parent_ctx) put_ctx(ctx->parent_ctx); if (ctx->task && ctx->task != TASK_TOMBSTONE) @@ -1268,7 +1268,7 @@ perf_event_ctx_lock_nested(struct perf_event *event, int nesting) again: rcu_read_lock(); ctx = READ_ONCE(event->ctx); - if (!atomic_inc_not_zero(&ctx->refcount)) { + if (!refcount_inc_not_zero(&ctx->refcount)) { rcu_read_unlock(); goto again; } @@ -1401,7 +1401,7 @@ retry: } if (ctx->task == TASK_TOMBSTONE || - !atomic_inc_not_zero(&ctx->refcount)) { + !refcount_inc_not_zero(&ctx->refcount)) { raw_spin_unlock(&ctx->lock); ctx = NULL; } else { @@ -4057,7 +4057,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx) INIT_LIST_HEAD(&ctx->event_list); INIT_LIST_HEAD(&ctx->pinned_active); INIT_LIST_HEAD(&ctx->flexible_active); - atomic_set(&ctx->refcount, 1); + refcount_set(&ctx->refcount, 1); } static struct perf_event_context * @@ -10613,7 +10613,7 @@ __perf_event_ctx_lock_double(struct perf_event *group_leader, again: rcu_read_lock(); gctx = READ_ONCE(group_leader->ctx); - if (!atomic_inc_not_zero(&gctx->refcount)) { + if (!refcount_inc_not_zero(&gctx->refcount)) { rcu_read_unlock(); goto again; } -- cgit v1.2.3 From d036bda7d0e7269c2982eb979acfef855f5d7977 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Fri, 18 Jan 2019 14:27:26 +0200 Subject: sched/core: Convert sighand_struct.count to refcount_t atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable sighand_struct.count is used as pure reference counter. Convert it to refcount_t and fix up the operations. ** Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. The full comparison can be seen in https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon in state to be merged to the documentation tree. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the sighand_struct.count it might make a difference in following places: - __cleanup_sighand: decrement in refcount_dec_and_test() only provides RELEASE ordering and control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook Signed-off-by: Elena Reshetova Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: David Windsor Reviewed-by: Hans Liljestrand Reviewed-by: Andrea Parri Reviewed-by: Oleg Nesterov Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: viro@zeniv.linux.org.uk Link: https://lkml.kernel.org/r/1547814450-18902-2-git-send-email-elena.reshetova@intel.com Signed-off-by: Ingo Molnar --- fs/exec.c | 4 ++-- fs/proc/task_nommu.c | 2 +- include/linux/sched/signal.h | 3 ++- kernel/fork.c | 8 ++++---- 4 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/fs/exec.c b/fs/exec.c index fb72d36f7823..966cd98a2ce2 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1189,7 +1189,7 @@ no_thread_group: flush_itimer_signals(); #endif - if (atomic_read(&oldsighand->count) != 1) { + if (refcount_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND @@ -1199,7 +1199,7 @@ no_thread_group: if (!newsighand) return -ENOMEM; - atomic_set(&newsighand->count, 1); + refcount_set(&newsighand->count, 1); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 0b63d68dedb2..f912872fbf91 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -64,7 +64,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) else bytes += kobjsize(current->files); - if (current->sighand && atomic_read(¤t->sighand->count) > 1) + if (current->sighand && refcount_read(¤t->sighand->count) > 1) sbytes += kobjsize(current->sighand); else bytes += kobjsize(current->sighand); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 13789d10a50e..37eeb1a28eba 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -8,13 +8,14 @@ #include #include #include +#include /* * Types defining task->signal and task->sighand and APIs using them: */ struct sighand_struct { - atomic_t count; + refcount_t count; struct k_sigaction action[_NSIG]; spinlock_t siglock; wait_queue_head_t signalfd_wqh; diff --git a/kernel/fork.c b/kernel/fork.c index b69248e6f0e0..370856d4c0b3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1463,7 +1463,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { - atomic_inc(¤t->sighand->count); + refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); @@ -1471,7 +1471,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) if (!sig) return -ENOMEM; - atomic_set(&sig->count, 1); + refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); @@ -1480,7 +1480,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_sighand(struct sighand_struct *sighand) { - if (atomic_dec_and_test(&sighand->count)) { + if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it @@ -2439,7 +2439,7 @@ static int check_unshare_flags(unsigned long unshare_flags) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { - if (atomic_read(¤t->sighand->count) > 1) + if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { -- cgit v1.2.3 From 60d4de3ff7f775509deba94b3db3c1abe55bf7a5 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Fri, 18 Jan 2019 14:27:27 +0200 Subject: sched/core: Convert signal_struct.sigcnt to refcount_t atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable signal_struct.sigcnt is used as pure reference counter. Convert it to refcount_t and fix up the operations. ** Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. The full comparison can be seen in https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon in state to be merged to the documentation tree. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the signal_struct.sigcnt it might make a difference in following places: - put_signal_struct(): decrement in refcount_dec_and_test() only provides RELEASE ordering and control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook Signed-off-by: Elena Reshetova Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: David Windsor Reviewed-by: Hans Liljestrand Reviewed-by: Andrea Parri Reviewed-by: Oleg Nesterov Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: viro@zeniv.linux.org.uk Link: https://lkml.kernel.org/r/1547814450-18902-3-git-send-email-elena.reshetova@intel.com Signed-off-by: Ingo Molnar --- include/linux/sched/signal.h | 2 +- init/init_task.c | 2 +- kernel/fork.c | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 37eeb1a28eba..ae5655197698 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -83,7 +83,7 @@ struct multiprocess_signals { * the locking of signal_struct. */ struct signal_struct { - atomic_t sigcnt; + refcount_t sigcnt; atomic_t live; int nr_threads; struct list_head thread_head; diff --git a/init/init_task.c b/init/init_task.c index 5aebe3be4d7c..9aa3ebc74970 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -44,7 +44,7 @@ static struct signal_struct init_signals = { }; static struct sighand_struct init_sighand = { - .count = ATOMIC_INIT(1), + .count = REFCOUNT_INIT(1), .action = { { { .sa_handler = SIG_DFL, } }, }, .siglock = __SPIN_LOCK_UNLOCKED(init_sighand.siglock), .signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh), diff --git a/kernel/fork.c b/kernel/fork.c index 370856d4c0b3..935a42d5f8ff 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -710,7 +710,7 @@ static inline void free_signal_struct(struct signal_struct *sig) static inline void put_signal_struct(struct signal_struct *sig) { - if (atomic_dec_and_test(&sig->sigcnt)) + if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } @@ -1527,7 +1527,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->nr_threads = 1; atomic_set(&sig->live, 1); - atomic_set(&sig->sigcnt, 1); + refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); @@ -2082,7 +2082,7 @@ static __latent_entropy struct task_struct *copy_process( } else { current->signal->nr_threads++; atomic_inc(¤t->signal->live); - atomic_inc(¤t->signal->sigcnt); + refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); -- cgit v1.2.3 From ec1d281923cf81cc660343d0cb8ffc837ffb991d Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Fri, 18 Jan 2019 14:27:29 +0200 Subject: sched/core: Convert task_struct.usage to refcount_t atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable task_struct.usage is used as pure reference counter. Convert it to refcount_t and fix up the operations. ** Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. The full comparison can be seen in https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon in state to be merged to the documentation tree. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the task_struct.usage it might make a difference in following places: - put_task_struct(): decrement in refcount_dec_and_test() only provides RELEASE ordering and control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook Signed-off-by: Elena Reshetova Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: David Windsor Reviewed-by: Hans Liljestrand Reviewed-by: Andrea Parri Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: viro@zeniv.linux.org.uk Link: https://lkml.kernel.org/r/1547814450-18902-5-git-send-email-elena.reshetova@intel.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 ++- include/linux/sched/task.h | 4 ++-- init/init_task.c | 2 +- kernel/fork.c | 4 ++-- 4 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index e2bba022827d..9d14d6864ca6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -607,7 +608,7 @@ struct task_struct { randomized_struct_fields_start void *stack; - atomic_t usage; + refcount_t usage; /* Per task flags (PF_*), defined further below: */ unsigned int flags; unsigned int ptrace; diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 44c6f15800ff..2e97a2227045 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -88,13 +88,13 @@ extern void sched_exec(void); #define sched_exec() {} #endif -#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) +#define get_task_struct(tsk) do { refcount_inc(&(tsk)->usage); } while(0) extern void __put_task_struct(struct task_struct *t); static inline void put_task_struct(struct task_struct *t) { - if (atomic_dec_and_test(&t->usage)) + if (refcount_dec_and_test(&t->usage)) __put_task_struct(t); } diff --git a/init/init_task.c b/init/init_task.c index 9aa3ebc74970..aca34c89529f 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -65,7 +65,7 @@ struct task_struct init_task #endif .state = 0, .stack = init_stack, - .usage = ATOMIC_INIT(2), + .usage = REFCOUNT_INIT(2), .flags = PF_KTHREAD, .prio = MAX_PRIO - 20, .static_prio = MAX_PRIO - 20, diff --git a/kernel/fork.c b/kernel/fork.c index 935a42d5f8ff..3f7e192e29f2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -717,7 +717,7 @@ static inline void put_signal_struct(struct signal_struct *sig) void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); - WARN_ON(atomic_read(&tsk->usage)); + WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); cgroup_free(tsk); @@ -896,7 +896,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) * One for us, one for whoever does the "release_task()" (usually * parent) */ - atomic_set(&tsk->usage, 2); + refcount_set(&tsk->usage, 2); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif -- cgit v1.2.3 From f0b89d3958d73cd0785ec381f0ddf8efb6f183d8 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Fri, 18 Jan 2019 14:27:30 +0200 Subject: sched/core: Convert task_struct.stack_refcount to refcount_t atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable task_struct.stack_refcount is used as pure reference counter. Convert it to refcount_t and fix up the operations. ** Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. The full comparison can be seen in https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon in state to be merged to the documentation tree. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the task_struct.stack_refcount it might make a difference in following places: - try_get_task_stack(): increment in refcount_inc_not_zero() only guarantees control dependency on success vs. fully ordered atomic counterpart - put_task_stack(): decrement in refcount_dec_and_test() only provides RELEASE ordering and control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook Signed-off-by: Elena Reshetova Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: David Windsor Reviewed-by: Hans Liljestrand Reviewed-by: Andrea Parri Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: viro@zeniv.linux.org.uk Link: https://lkml.kernel.org/r/1547814450-18902-6-git-send-email-elena.reshetova@intel.com Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 1 + include/linux/sched.h | 2 +- include/linux/sched/task_stack.h | 2 +- init/init_task.c | 2 +- kernel/fork.c | 6 +++--- 5 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index a7083a45a26c..6049baa5b8bc 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/sched.h b/include/linux/sched.h index 9d14d6864ca6..628bf13cb5a5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1194,7 +1194,7 @@ struct task_struct { #endif #ifdef CONFIG_THREAD_INFO_IN_TASK /* A live task holds one reference: */ - atomic_t stack_refcount; + refcount_t stack_refcount; #endif #ifdef CONFIG_LIVEPATCH int patch_state; diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 6a841929073f..2413427e439c 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -61,7 +61,7 @@ static inline unsigned long *end_of_stack(struct task_struct *p) #ifdef CONFIG_THREAD_INFO_IN_TASK static inline void *try_get_task_stack(struct task_struct *tsk) { - return atomic_inc_not_zero(&tsk->stack_refcount) ? + return refcount_inc_not_zero(&tsk->stack_refcount) ? task_stack_page(tsk) : NULL; } diff --git a/init/init_task.c b/init/init_task.c index aca34c89529f..46dbf546264d 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -61,7 +61,7 @@ struct task_struct init_task = { #ifdef CONFIG_THREAD_INFO_IN_TASK .thread_info = INIT_THREAD_INFO(init_task), - .stack_refcount = ATOMIC_INIT(1), + .stack_refcount = REFCOUNT_INIT(1), #endif .state = 0, .stack = init_stack, diff --git a/kernel/fork.c b/kernel/fork.c index 3f7e192e29f2..77059b211608 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -429,7 +429,7 @@ static void release_task_stack(struct task_struct *tsk) #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { - if (atomic_dec_and_test(&tsk->stack_refcount)) + if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif @@ -447,7 +447,7 @@ void free_task(struct task_struct *tsk) * If the task had a separate stack allocation, it should be gone * by now. */ - WARN_ON_ONCE(atomic_read(&tsk->stack_refcount) != 0); + WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); @@ -867,7 +867,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->stack_vm_area = stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK - atomic_set(&tsk->stack_refcount, 1); + refcount_set(&tsk->stack_refcount, 1); #endif if (err) -- cgit v1.2.3 From 07879c6a3740fbbf3c8891a0ab484c20a12794d8 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 18 Dec 2018 11:53:52 -0800 Subject: sched/wake_q: Reduce reference counting for special users Some users, specifically futexes and rwsems, required fixes that allowed the callers to be safe when wakeups occur before they are expected by wake_up_q(). Such scenarios also play games and rely on reference counting, and until now were pivoting on wake_q doing it. With the wake_q_add() call being moved down, this can no longer be the case. As such we end up with a a double task refcounting overhead; and these callers care enough about this (being rather core-ish). This patch introduces a wake_q_add_safe() call that serves for callers that have already done refcounting and therefore the task is 'safe' from wake_q point of view (int that it requires reference throughout the entire queue/>wakeup cycle). In the one case it has internal reference counting, in the other case it consumes the reference counting. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Cc: Xie Yongji Cc: Yongji Xie Cc: andrea.parri@amarulasolutions.com Cc: lilin24@baidu.com Cc: liuqi16@baidu.com Cc: nixun@baidu.com Cc: yuanlinsi01@baidu.com Cc: zhangyu31@baidu.com Link: https://lkml.kernel.org/r/20181218195352.7orq3upiwfdbrdne@linux-r8p5 Signed-off-by: Ingo Molnar --- include/linux/sched/wake_q.h | 4 +-- kernel/futex.c | 3 +-- kernel/locking/rwsem-xadd.c | 4 +-- kernel/sched/core.c | 60 ++++++++++++++++++++++++++++++++------------ 4 files changed, 48 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 545f37138057..ad826d2a4557 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -51,8 +51,8 @@ static inline void wake_q_init(struct wake_q_head *head) head->lastp = &head->first; } -extern void wake_q_add(struct wake_q_head *head, - struct task_struct *task); +extern void wake_q_add(struct wake_q_head *head, struct task_struct *task); +extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task); extern void wake_up_q(struct wake_q_head *head); #endif /* _LINUX_SCHED_WAKE_Q_H */ diff --git a/kernel/futex.c b/kernel/futex.c index 69e619baf709..2abe1a0b3062 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1463,8 +1463,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) * Queue the task for later wakeup for after we've released * the hb->lock. wake_q_add() grabs reference to p. */ - wake_q_add(wake_q, p); - put_task_struct(p); + wake_q_add_safe(wake_q, p); } /* diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 50d9af615dc4..fbe96341beee 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -211,9 +211,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, * Ensure issuing the wakeup (either by us or someone else) * after setting the reader waiter to nil. */ - wake_q_add(wake_q, tsk); - /* wake_q_add() already take the task ref */ - put_task_struct(tsk); + wake_q_add_safe(wake_q, tsk); } adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3c8b4dba3d2d..64ceaa5158c5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -396,19 +396,7 @@ static bool set_nr_if_polling(struct task_struct *p) #endif #endif -/** - * wake_q_add() - queue a wakeup for 'later' waking. - * @head: the wake_q_head to add @task to - * @task: the task to queue for 'later' wakeup - * - * Queue a task for later wakeup, most likely by the wake_up_q() call in the - * same context, _HOWEVER_ this is not guaranteed, the wakeup can come - * instantly. - * - * This function must be used as-if it were wake_up_process(); IOW the task - * must be ready to be woken at this location. - */ -void wake_q_add(struct wake_q_head *head, struct task_struct *task) +static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task) { struct wake_q_node *node = &task->wake_q; @@ -422,15 +410,55 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) */ smp_mb__before_atomic(); if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))) - return; - - get_task_struct(task); + return false; /* * The head is context local, there can be no concurrency. */ *head->lastp = node; head->lastp = &node->next; + return true; +} + +/** + * wake_q_add() - queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + */ +void wake_q_add(struct wake_q_head *head, struct task_struct *task) +{ + if (__wake_q_add(head, task)) + get_task_struct(task); +} + +/** + * wake_q_add_safe() - safely queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + * + * This function is essentially a task-safe equivalent to wake_q_add(). Callers + * that already hold reference to @task can call the 'safe' version and trust + * wake_q to do the right thing depending whether or not the @task is already + * queued for wakeup. + */ +void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task) +{ + if (!__wake_q_add(head, task)) + put_task_struct(task); } void wake_up_q(struct wake_q_head *head) -- cgit v1.2.3 From 23127296889fe84b0762b191b5d041e8ba6f2599 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 23 Jan 2019 16:26:53 +0100 Subject: sched/fair: Update scale invariance of PELT The current implementation of load tracking invariance scales the contribution with current frequency and uarch performance (only for utilization) of the CPU. One main result of this formula is that the figures are capped by current capacity of CPU. Another one is that the load_avg is not invariant because not scaled with uarch. The util_avg of a periodic task that runs r time slots every p time slots varies in the range : U * (1-y^r)/(1-y^p) * y^i < Utilization < U * (1-y^r)/(1-y^p) with U is the max util_avg value = SCHED_CAPACITY_SCALE At a lower capacity, the range becomes: U * C * (1-y^r')/(1-y^p) * y^i' < Utilization < U * C * (1-y^r')/(1-y^p) with C reflecting the compute capacity ratio between current capacity and max capacity. so C tries to compensate changes in (1-y^r') but it can't be accurate. Instead of scaling the contribution value of PELT algo, we should scale the running time. The PELT signal aims to track the amount of computation of tasks and/or rq so it seems more correct to scale the running time to reflect the effective amount of computation done since the last update. In order to be fully invariant, we need to apply the same amount of running time and idle time whatever the current capacity. Because running at lower capacity implies that the task will run longer, we have to ensure that the same amount of idle time will be applied when system becomes idle and no idle time has been "stolen". But reaching the maximum utilization value (SCHED_CAPACITY_SCALE) means that the task is seen as an always-running task whatever the capacity of the CPU (even at max compute capacity). In this case, we can discard this "stolen" idle times which becomes meaningless. In order to achieve this time scaling, a new clock_pelt is created per rq. The increase of this clock scales with current capacity when something is running on rq and synchronizes with clock_task when rq is idle. With this mechanism, we ensure the same running and idle time whatever the current capacity. This also enables to simplify the pelt algorithm by removing all references of uarch and frequency and applying the same contribution to utilization and loads. Furthermore, the scaling is done only once per update of clock (update_rq_clock_task()) instead of during each update of sched_entities and cfs/rt/dl_rq of the rq like the current implementation. This is interesting when cgroup are involved as shown in the results below: On a hikey (octo Arm64 platform). Performance cpufreq governor and only shallowest c-state to remove variance generated by those power features so we only track the impact of pelt algo. each test runs 16 times: ./perf bench sched pipe (higher is better) kernel tip/sched/core + patch ops/seconds ops/seconds diff cgroup root 59652(+/- 0.18%) 59876(+/- 0.24%) +0.38% level1 55608(+/- 0.27%) 55923(+/- 0.24%) +0.57% level2 52115(+/- 0.29%) 52564(+/- 0.22%) +0.86% hackbench -l 1000 (lower is better) kernel tip/sched/core + patch duration(sec) duration(sec) diff cgroup root 4.453(+/- 2.37%) 4.383(+/- 2.88%) -1.57% level1 4.859(+/- 8.50%) 4.830(+/- 7.07%) -0.60% level2 5.063(+/- 9.83%) 4.928(+/- 9.66%) -2.66% Then, the responsiveness of PELT is improved when CPU is not running at max capacity with this new algorithm. I have put below some examples of duration to reach some typical load values according to the capacity of the CPU with current implementation and with this patch. These values has been computed based on the geometric series and the half period value: Util (%) max capacity half capacity(mainline) half capacity(w/ patch) 972 (95%) 138ms not reachable 276ms 486 (47.5%) 30ms 138ms 60ms 256 (25%) 13ms 32ms 26ms On my hikey (octo Arm64 platform) with schedutil governor, the time to reach max OPP when starting from a null utilization, decreases from 223ms with current scale invariance down to 121ms with the new algorithm. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Morten.Rasmussen@arm.com Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: patrick.bellasi@arm.com Cc: pjt@google.com Cc: pkondeti@codeaurora.org Cc: quentin.perret@arm.com Cc: rjw@rjwysocki.net Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Link: https://lkml.kernel.org/r/1548257214-13745-3-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 23 +++------- kernel/sched/core.c | 1 + kernel/sched/deadline.c | 6 +-- kernel/sched/fair.c | 45 ++++++++++--------- kernel/sched/pelt.c | 45 ++++++++++--------- kernel/sched/pelt.h | 114 ++++++++++++++++++++++++++++++++++++++++++++++-- kernel/sched/rt.c | 6 +-- kernel/sched/sched.h | 5 ++- 8 files changed, 177 insertions(+), 68 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 628bf13cb5a5..351c0fe64c85 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -357,12 +357,6 @@ struct util_est { * For cfs_rq, it is the aggregated load_avg of all runnable and * blocked sched_entities. * - * load_avg may also take frequency scaling into account: - * - * load_avg = runnable% * scale_load_down(load) * freq% - * - * where freq% is the CPU frequency normalized to the highest frequency. - * * [util_avg definition] * * util_avg = running% * SCHED_CAPACITY_SCALE @@ -371,17 +365,14 @@ struct util_est { * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable * and blocked sched_entities. * - * util_avg may also factor frequency scaling and CPU capacity scaling: - * - * util_avg = running% * SCHED_CAPACITY_SCALE * freq% * capacity% - * - * where freq% is the same as above, and capacity% is the CPU capacity - * normalized to the greatest capacity (due to uarch differences, etc). + * load_avg and util_avg don't direcly factor frequency scaling and CPU + * capacity scaling. The scaling is done through the rq_clock_pelt that + * is used for computing those signals (see update_rq_clock_pelt()) * - * N.B., the above ratios (runnable%, running%, freq%, and capacity%) - * themselves are in the range of [0, 1]. To do fixed point arithmetics, - * we therefore scale them to as large a range as necessary. This is for - * example reflected by util_avg's SCHED_CAPACITY_SCALE. + * N.B., the above ratios (runnable% and running%) themselves are in the + * range of [0, 1]. To do fixed point arithmetics, we therefore scale them + * to as large a range as necessary. This is for example reflected by + * util_avg's SCHED_CAPACITY_SCALE. * * [Overflow issue] * diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a674c7db2f29..32e06704565e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -180,6 +180,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) update_irq_load_avg(rq, irq_delta + steal); #endif + update_rq_clock_pelt(rq, delta); } void update_rq_clock(struct rq *rq) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fb8b7b5d745d..6a73e41a2016 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1767,7 +1767,7 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) deadline_queue_push_tasks(rq); if (rq->curr->sched_class != &dl_sched_class) - update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0); return p; } @@ -1776,7 +1776,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -1793,7 +1793,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) { update_curr_dl(rq); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); /* * Even when we have runtime, update_curr_dl() might have resulted in us * not being the leftmost task anymore. In that case NEED_RESCHED will diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index da13e834e990..f41f2eec6186 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -673,9 +673,8 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) return calc_delta_fair(sched_slice(cfs_rq, se), se); } -#ifdef CONFIG_SMP #include "pelt.h" -#include "sched-pelt.h" +#ifdef CONFIG_SMP static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu); static unsigned long task_h_load(struct task_struct *p); @@ -763,7 +762,7 @@ void post_init_entity_util_avg(struct sched_entity *se) * such that the next switched_to_fair() has the * expected state. */ - se->avg.last_update_time = cfs_rq_clock_task(cfs_rq); + se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq); return; } } @@ -3109,7 +3108,7 @@ void set_task_rq_fair(struct sched_entity *se, p_last_update_time = prev->avg.last_update_time; n_last_update_time = next->avg.last_update_time; #endif - __update_load_avg_blocked_se(p_last_update_time, cpu_of(rq_of(prev)), se); + __update_load_avg_blocked_se(p_last_update_time, se); se->avg.last_update_time = n_last_update_time; } @@ -3244,11 +3243,11 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf /* * runnable_sum can't be lower than running_sum - * As running sum is scale with CPU capacity wehreas the runnable sum - * is not we rescale running_sum 1st + * Rescale running sum to be in the same range as runnable sum + * running_sum is in [0 : LOAD_AVG_MAX << SCHED_CAPACITY_SHIFT] + * runnable_sum is in [0 : LOAD_AVG_MAX] */ - running_sum = se->avg.util_sum / - arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); + running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT; runnable_sum = max(runnable_sum, running_sum); load_sum = (s64)se_weight(se) * runnable_sum; @@ -3351,7 +3350,7 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum /** * update_cfs_rq_load_avg - update the cfs_rq's load/util averages - * @now: current time, as per cfs_rq_clock_task() + * @now: current time, as per cfs_rq_clock_pelt() * @cfs_rq: cfs_rq to update * * The cfs_rq avg is the direct sum of all its entities (blocked and runnable) @@ -3396,7 +3395,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) decayed = 1; } - decayed |= __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq); + decayed |= __update_load_avg_cfs_rq(now, cfs_rq); #ifndef CONFIG_64BIT smp_wmb(); @@ -3486,9 +3485,7 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s /* Update task and its cfs_rq load average */ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { - u64 now = cfs_rq_clock_task(cfs_rq); - struct rq *rq = rq_of(cfs_rq); - int cpu = cpu_of(rq); + u64 now = cfs_rq_clock_pelt(cfs_rq); int decayed; /* @@ -3496,7 +3493,7 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s * track group sched_entity load average for task_h_load calc in migration */ if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) - __update_load_avg_se(now, cpu, cfs_rq, se); + __update_load_avg_se(now, cfs_rq, se); decayed = update_cfs_rq_load_avg(now, cfs_rq); decayed |= propagate_entity_load_avg(se); @@ -3548,7 +3545,7 @@ void sync_entity_load_avg(struct sched_entity *se) u64 last_update_time; last_update_time = cfs_rq_last_update_time(cfs_rq); - __update_load_avg_blocked_se(last_update_time, cpu_of(rq_of(cfs_rq)), se); + __update_load_avg_blocked_se(last_update_time, se); } /* @@ -7015,6 +7012,12 @@ idle: if (new_tasks > 0) goto again; + /* + * rq is about to be idle, check if we need to update the + * lost_idle_time of clock_pelt + */ + update_idle_rq_clock_pelt(rq); + return NULL; } @@ -7657,7 +7660,7 @@ static void update_blocked_averages(int cpu) if (throttled_hierarchy(cfs_rq)) continue; - if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq)) + if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) update_tg_load_avg(cfs_rq, 0); /* Propagate pending load changes to the parent, if any: */ @@ -7671,8 +7674,8 @@ static void update_blocked_averages(int cpu) } curr_class = rq->curr->sched_class; - update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); - update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); /* Don't need periodic decay once load/util_avg are null */ if (others_have_blocked(rq)) @@ -7742,11 +7745,11 @@ static inline void update_blocked_averages(int cpu) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); + update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq); curr_class = rq->curr->sched_class; - update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); - update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index 90fb5bc12ad4..befce29bd882 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -26,7 +26,6 @@ #include #include "sched.h" -#include "sched-pelt.h" #include "pelt.h" /* @@ -106,16 +105,12 @@ static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) * n=1 */ static __always_inline u32 -accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, +accumulate_sum(u64 delta, struct sched_avg *sa, unsigned long load, unsigned long runnable, int running) { - unsigned long scale_freq, scale_cpu; u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ u64 periods; - scale_freq = arch_scale_freq_capacity(cpu); - scale_cpu = arch_scale_cpu_capacity(NULL, cpu); - delta += sa->period_contrib; periods = delta / 1024; /* A period is 1024us (~1ms) */ @@ -137,13 +132,12 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, } sa->period_contrib = delta; - contrib = cap_scale(contrib, scale_freq); if (load) sa->load_sum += load * contrib; if (runnable) sa->runnable_load_sum += runnable * contrib; if (running) - sa->util_sum += contrib * scale_cpu; + sa->util_sum += contrib << SCHED_CAPACITY_SHIFT; return periods; } @@ -177,7 +171,7 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] */ static __always_inline int -___update_load_sum(u64 now, int cpu, struct sched_avg *sa, +___update_load_sum(u64 now, struct sched_avg *sa, unsigned long load, unsigned long runnable, int running) { u64 delta; @@ -221,7 +215,7 @@ ___update_load_sum(u64 now, int cpu, struct sched_avg *sa, * Step 1: accumulate *_sum since last_update_time. If we haven't * crossed period boundaries, finish. */ - if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) + if (!accumulate_sum(delta, sa, load, runnable, running)) return 0; return 1; @@ -267,9 +261,9 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna * runnable_load_avg = \Sum se->avg.runable_load_avg */ -int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) +int __update_load_avg_blocked_se(u64 now, struct sched_entity *se) { - if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { + if (___update_load_sum(now, &se->avg, 0, 0, 0)) { ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); return 1; } @@ -277,9 +271,9 @@ int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) return 0; } -int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) +int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se) { - if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, + if (___update_load_sum(now, &se->avg, !!se->on_rq, !!se->on_rq, cfs_rq->curr == se)) { ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); @@ -290,9 +284,9 @@ int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_e return 0; } -int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) +int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq) { - if (___update_load_sum(now, cpu, &cfs_rq->avg, + if (___update_load_sum(now, &cfs_rq->avg, scale_load_down(cfs_rq->load.weight), scale_load_down(cfs_rq->runnable_weight), cfs_rq->curr != NULL)) { @@ -317,7 +311,7 @@ int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) int update_rt_rq_load_avg(u64 now, struct rq *rq, int running) { - if (___update_load_sum(now, rq->cpu, &rq->avg_rt, + if (___update_load_sum(now, &rq->avg_rt, running, running, running)) { @@ -340,7 +334,7 @@ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running) int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) { - if (___update_load_sum(now, rq->cpu, &rq->avg_dl, + if (___update_load_sum(now, &rq->avg_dl, running, running, running)) { @@ -365,22 +359,31 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) int update_irq_load_avg(struct rq *rq, u64 running) { int ret = 0; + + /* + * We can't use clock_pelt because irq time is not accounted in + * clock_task. Instead we directly scale the running time to + * reflect the real amount of computation + */ + running = cap_scale(running, arch_scale_freq_capacity(cpu_of(rq))); + running = cap_scale(running, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + /* * We know the time that has been used by interrupt since last update * but we don't when. Let be pessimistic and assume that interrupt has * happened just before the update. This is not so far from reality * because interrupt will most probably wake up task and trig an update - * of rq clock during which the metric si updated. + * of rq clock during which the metric is updated. * We start to decay with normal context time and then we add the * interrupt context time. * We can safely remove running from rq->clock because * rq->clock += delta with delta >= running */ - ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq, + ret = ___update_load_sum(rq->clock - running, &rq->avg_irq, 0, 0, 0); - ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq, + ret += ___update_load_sum(rq->clock, &rq->avg_irq, 1, 1, 1); diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 7e56b489ff32..7489d5f56960 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -1,8 +1,9 @@ #ifdef CONFIG_SMP +#include "sched-pelt.h" -int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se); -int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se); -int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq); +int __update_load_avg_blocked_se(u64 now, struct sched_entity *se); +int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se); +int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq); int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); @@ -42,6 +43,101 @@ static inline void cfs_se_util_change(struct sched_avg *avg) WRITE_ONCE(avg->util_est.enqueued, enqueued); } +/* + * The clock_pelt scales the time to reflect the effective amount of + * computation done during the running delta time but then sync back to + * clock_task when rq is idle. + * + * + * absolute time | 1| 2| 3| 4| 5| 6| 7| 8| 9|10|11|12|13|14|15|16 + * @ max capacity ------******---------------******--------------- + * @ half capacity ------************---------************--------- + * clock pelt | 1| 2| 3| 4| 7| 8| 9| 10| 11|14|15|16 + * + */ +static inline void update_rq_clock_pelt(struct rq *rq, s64 delta) +{ + if (unlikely(is_idle_task(rq->curr))) { + /* The rq is idle, we can sync to clock_task */ + rq->clock_pelt = rq_clock_task(rq); + return; + } + + /* + * When a rq runs at a lower compute capacity, it will need + * more time to do the same amount of work than at max + * capacity. In order to be invariant, we scale the delta to + * reflect how much work has been really done. + * Running longer results in stealing idle time that will + * disturb the load signal compared to max capacity. This + * stolen idle time will be automatically reflected when the + * rq will be idle and the clock will be synced with + * rq_clock_task. + */ + + /* + * Scale the elapsed time to reflect the real amount of + * computation + */ + delta = cap_scale(delta, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + delta = cap_scale(delta, arch_scale_freq_capacity(cpu_of(rq))); + + rq->clock_pelt += delta; +} + +/* + * When rq becomes idle, we have to check if it has lost idle time + * because it was fully busy. A rq is fully used when the /Sum util_sum + * is greater or equal to: + * (LOAD_AVG_MAX - 1024 + rq->cfs.avg.period_contrib) << SCHED_CAPACITY_SHIFT; + * For optimization and computing rounding purpose, we don't take into account + * the position in the current window (period_contrib) and we use the higher + * bound of util_sum to decide. + */ +static inline void update_idle_rq_clock_pelt(struct rq *rq) +{ + u32 divider = ((LOAD_AVG_MAX - 1024) << SCHED_CAPACITY_SHIFT) - LOAD_AVG_MAX; + u32 util_sum = rq->cfs.avg.util_sum; + util_sum += rq->avg_rt.util_sum; + util_sum += rq->avg_dl.util_sum; + + /* + * Reflecting stolen time makes sense only if the idle + * phase would be present at max capacity. As soon as the + * utilization of a rq has reached the maximum value, it is + * considered as an always runnig rq without idle time to + * steal. This potential idle time is considered as lost in + * this case. We keep track of this lost idle time compare to + * rq's clock_task. + */ + if (util_sum >= divider) + rq->lost_idle_time += rq_clock_task(rq) - rq->clock_pelt; +} + +static inline u64 rq_clock_pelt(struct rq *rq) +{ + lockdep_assert_held(&rq->lock); + assert_clock_updated(rq); + + return rq->clock_pelt - rq->lost_idle_time; +} + +#ifdef CONFIG_CFS_BANDWIDTH +/* rq->task_clock normalized against any time this cfs_rq has spent throttled */ +static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) +{ + if (unlikely(cfs_rq->throttle_count)) + return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time; + + return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time; +} +#else +static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) +{ + return rq_clock_pelt(rq_of(cfs_rq)); +} +#endif + #else static inline int @@ -67,6 +163,18 @@ update_irq_load_avg(struct rq *rq, u64 running) { return 0; } + +static inline u64 rq_clock_pelt(struct rq *rq) +{ + return rq_clock_task(rq); +} + +static inline void +update_rq_clock_pelt(struct rq *rq, s64 delta) { } + +static inline void +update_idle_rq_clock_pelt(struct rq *rq) { } + #endif diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e4f398ad9e73..90fa23d36565 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1587,7 +1587,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * rt task */ if (rq->curr->sched_class != &rt_sched_class) - update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0); return p; } @@ -1596,7 +1596,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); - update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1); /* * The previous task needs to be made eligible for pushing @@ -2325,7 +2325,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); - update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1); watchdog(rq, p); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0ed130fae2a9..fe31bc472f3e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -861,7 +861,10 @@ struct rq { unsigned int clock_update_flags; u64 clock; - u64 clock_task; + /* Ensure that all clocks are in the same cache line */ + u64 clock_task ____cacheline_aligned; + u64 clock_pelt; + unsigned long lost_idle_time; atomic_t nr_iowait; -- cgit v1.2.3 From c546951d9c9300065bad253ecdf1ac59ce9d06c8 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Mon, 21 Jan 2019 16:52:40 +0100 Subject: sched/core: Use READ_ONCE()/WRITE_ONCE() in move_queued_task()/task_rq_lock() move_queued_task() synchronizes with task_rq_lock() as follows: move_queued_task() task_rq_lock() [S] ->on_rq = MIGRATING [L] rq = task_rq() WMB (__set_task_cpu()) ACQUIRE (rq->lock); [S] ->cpu = new_cpu [L] ->on_rq where "[L] rq = task_rq()" is ordered before "ACQUIRE (rq->lock)" by an address dependency and, in turn, "ACQUIRE (rq->lock)" is ordered before "[L] ->on_rq" by the ACQUIRE itself. Use READ_ONCE() to load ->cpu in task_rq() (c.f., task_cpu()) to honor this address dependency. Also, mark the accesses to ->cpu and ->on_rq with READ_ONCE()/WRITE_ONCE() to comply with the LKMM. Signed-off-by: Andrea Parri Signed-off-by: Peter Zijlstra (Intel) Cc: Alan Stern Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: https://lkml.kernel.org/r/20190121155240.27173-1-andrea.parri@amarulasolutions.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- kernel/sched/core.c | 9 +++++---- kernel/sched/sched.h | 6 +++--- 3 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 351c0fe64c85..4112639c2a85 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1745,9 +1745,9 @@ static __always_inline bool need_resched(void) static inline unsigned int task_cpu(const struct task_struct *p) { #ifdef CONFIG_THREAD_INFO_IN_TASK - return p->cpu; + return READ_ONCE(p->cpu); #else - return task_thread_info(p)->cpu; + return READ_ONCE(task_thread_info(p)->cpu); #endif } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 32e06704565e..ec1b67a195cc 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -107,11 +107,12 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) * [L] ->on_rq * RELEASE (rq->lock) * - * If we observe the old CPU in task_rq_lock, the acquire of + * If we observe the old CPU in task_rq_lock(), the acquire of * the old rq->lock will fully serialize against the stores. * - * If we observe the new CPU in task_rq_lock, the acquire will - * pair with the WMB to ensure we must then also see migrating. + * If we observe the new CPU in task_rq_lock(), the address + * dependency headed by '[L] rq = task_rq()' and the acquire + * will pair with the WMB to ensure we then also see migrating. */ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { rq_pin_lock(rq, rf); @@ -916,7 +917,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf, { lockdep_assert_held(&rq->lock); - p->on_rq = TASK_ON_RQ_MIGRATING; + WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING); dequeue_task(rq, p, DEQUEUE_NOCLOCK); set_task_cpu(p, new_cpu); rq_unlock(rq, rf); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 99e2a7772d16..c688ef5012e5 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1479,9 +1479,9 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) */ smp_wmb(); #ifdef CONFIG_THREAD_INFO_IN_TASK - p->cpu = cpu; + WRITE_ONCE(p->cpu, cpu); #else - task_thread_info(p)->cpu = cpu; + WRITE_ONCE(task_thread_info(p)->cpu, cpu); #endif p->wake_cpu = cpu; #endif @@ -1582,7 +1582,7 @@ static inline int task_on_rq_queued(struct task_struct *p) static inline int task_on_rq_migrating(struct task_struct *p) { - return p->on_rq == TASK_ON_RQ_MIGRATING; + return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING; } /* -- cgit v1.2.3 From 25db146aa7262bc95c314b2df35db107f5eadd55 Mon Sep 17 00:00:00 2001 From: Jian Hu Date: Fri, 1 Feb 2019 15:53:43 +0100 Subject: dt-bindings: clk: meson: add g12a periph clock controller bindings Add new clock controller compatible and dt-bindings header for the Everything-Else domain of the g12a SoC Reviewed-by: Rob Herring Signed-off-by: Jian Hu Signed-off-by: Jerome Brunet Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://lkml.kernel.org/r/20190201145345.6795-3-jbrunet@baylibre.com --- .../bindings/clock/amlogic,gxbb-clkc.txt | 1 + include/dt-bindings/clock/g12a-clkc.h | 135 +++++++++++++++++++++ 2 files changed, 136 insertions(+) create mode 100644 include/dt-bindings/clock/g12a-clkc.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt b/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt index a6871953bf04..5c8b105be4d6 100644 --- a/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt +++ b/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt @@ -9,6 +9,7 @@ Required Properties: "amlogic,gxbb-clkc" for GXBB SoC, "amlogic,gxl-clkc" for GXL and GXM SoC, "amlogic,axg-clkc" for AXG SoC. + "amlogic,g12a-clkc" for G12A SoC. - clocks : list of clock phandle, one for each entry clock-names. - clock-names : should contain the following: * "xtal": the platform xtal diff --git a/include/dt-bindings/clock/g12a-clkc.h b/include/dt-bindings/clock/g12a-clkc.h new file mode 100644 index 000000000000..83b657038d1e --- /dev/null +++ b/include/dt-bindings/clock/g12a-clkc.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0+ OR MIT */ +/* + * Meson-G12A clock tree IDs + * + * Copyright (c) 2018 Amlogic, Inc. All rights reserved. + */ + +#ifndef __G12A_CLKC_H +#define __G12A_CLKC_H + +#define CLKID_SYS_PLL 0 +#define CLKID_FIXED_PLL 1 +#define CLKID_FCLK_DIV2 2 +#define CLKID_FCLK_DIV3 3 +#define CLKID_FCLK_DIV4 4 +#define CLKID_FCLK_DIV5 5 +#define CLKID_FCLK_DIV7 6 +#define CLKID_GP0_PLL 7 +#define CLKID_CLK81 10 +#define CLKID_MPLL0 11 +#define CLKID_MPLL1 12 +#define CLKID_MPLL2 13 +#define CLKID_MPLL3 14 +#define CLKID_DDR 15 +#define CLKID_DOS 16 +#define CLKID_AUDIO_LOCKER 17 +#define CLKID_MIPI_DSI_HOST 18 +#define CLKID_ETH_PHY 19 +#define CLKID_ISA 20 +#define CLKID_PL301 21 +#define CLKID_PERIPHS 22 +#define CLKID_SPICC0 23 +#define CLKID_I2C 24 +#define CLKID_SANA 25 +#define CLKID_SD 26 +#define CLKID_RNG0 27 +#define CLKID_UART0 28 +#define CLKID_SPICC1 29 +#define CLKID_HIU_IFACE 30 +#define CLKID_MIPI_DSI_PHY 31 +#define CLKID_ASSIST_MISC 32 +#define CLKID_SD_EMMC_A 33 +#define CLKID_SD_EMMC_B 34 +#define CLKID_SD_EMMC_C 35 +#define CLKID_AUDIO_CODEC 36 +#define CLKID_AUDIO 37 +#define CLKID_ETH 38 +#define CLKID_DEMUX 39 +#define CLKID_AUDIO_IFIFO 40 +#define CLKID_ADC 41 +#define CLKID_UART1 42 +#define CLKID_G2D 43 +#define CLKID_RESET 44 +#define CLKID_PCIE_COMB 45 +#define CLKID_PARSER 46 +#define CLKID_USB 47 +#define CLKID_PCIE_PHY 48 +#define CLKID_AHB_ARB0 49 +#define CLKID_AHB_DATA_BUS 50 +#define CLKID_AHB_CTRL_BUS 51 +#define CLKID_HTX_HDCP22 52 +#define CLKID_HTX_PCLK 53 +#define CLKID_BT656 54 +#define CLKID_USB1_DDR_BRIDGE 55 +#define CLKID_MMC_PCLK 56 +#define CLKID_UART2 57 +#define CLKID_VPU_INTR 58 +#define CLKID_GIC 59 +#define CLKID_SD_EMMC_A_CLK0 60 +#define CLKID_SD_EMMC_B_CLK0 61 +#define CLKID_SD_EMMC_C_CLK0 62 +#define CLKID_HIFI_PLL 74 +#define CLKID_VCLK2_VENCI0 80 +#define CLKID_VCLK2_VENCI1 81 +#define CLKID_VCLK2_VENCP0 82 +#define CLKID_VCLK2_VENCP1 83 +#define CLKID_VCLK2_VENCT0 84 +#define CLKID_VCLK2_VENCT1 85 +#define CLKID_VCLK2_OTHER 86 +#define CLKID_VCLK2_ENCI 87 +#define CLKID_VCLK2_ENCP 88 +#define CLKID_DAC_CLK 89 +#define CLKID_AOCLK 90 +#define CLKID_IEC958 91 +#define CLKID_ENC480P 92 +#define CLKID_RNG1 93 +#define CLKID_VCLK2_ENCT 94 +#define CLKID_VCLK2_ENCL 95 +#define CLKID_VCLK2_VENCLMMC 96 +#define CLKID_VCLK2_VENCL 97 +#define CLKID_VCLK2_OTHER1 98 +#define CLKID_FCLK_DIV2P5 99 +#define CLKID_DMA 105 +#define CLKID_EFUSE 106 +#define CLKID_ROM_BOOT 107 +#define CLKID_RESET_SEC 108 +#define CLKID_SEC_AHB_APB3 109 +#define CLKID_VPU_0_SEL 110 +#define CLKID_VPU_0 112 +#define CLKID_VPU_1_SEL 113 +#define CLKID_VPU_1 115 +#define CLKID_VPU 116 +#define CLKID_VAPB_0_SEL 117 +#define CLKID_VAPB_0 119 +#define CLKID_VAPB_1_SEL 120 +#define CLKID_VAPB_1 122 +#define CLKID_VAPB_SEL 123 +#define CLKID_VAPB 124 +#define CLKID_HDMI_PLL 128 +#define CLKID_VID_PLL 129 +#define CLKID_VCLK 138 +#define CLKID_VCLK2 139 +#define CLKID_VCLK_DIV1 148 +#define CLKID_VCLK_DIV2 149 +#define CLKID_VCLK_DIV4 150 +#define CLKID_VCLK_DIV6 151 +#define CLKID_VCLK_DIV12 152 +#define CLKID_VCLK2_DIV1 153 +#define CLKID_VCLK2_DIV2 154 +#define CLKID_VCLK2_DIV4 155 +#define CLKID_VCLK2_DIV6 156 +#define CLKID_VCLK2_DIV12 157 +#define CLKID_CTS_ENCI 162 +#define CLKID_CTS_ENCP 163 +#define CLKID_CTS_VDAC 164 +#define CLKID_HDMI_TX 165 +#define CLKID_HDMI 168 +#define CLKID_MALI_0_SEL 169 +#define CLKID_MALI_0 171 +#define CLKID_MALI_1_SEL 172 +#define CLKID_MALI_1 174 +#define CLKID_MALI 175 +#define CLKID_MPLL_5OM 177 + +#endif /* __G12A_CLKC_H */ -- cgit v1.2.3 From 74cf15cb69c0beb6cdaae3ff43f5231232a1f1b0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 3 Dec 2018 15:59:40 +0100 Subject: iwlwifi: mvm: add HE TB PPDU SIG-A BW to radiotap Expose the trigger-based PPDU SIG-A bandwidth to radiotap in the newly defined bits thereof. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 21 +++++++++++++++------ include/net/ieee80211_radiotap.h | 6 ++++++ 2 files changed, 21 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index b5ff3325c1d3..d2728fe6a041 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -960,6 +960,7 @@ iwl_mvm_decode_he_phy_ru_alloc(struct iwl_mvm_rx_phy_data *phy_data, * the TSF/timers are not be transmitted in HE-MU. */ u8 ru = le32_get_bits(phy_data->d1, IWL_RX_PHY_DATA1_HE_RU_ALLOC_MASK); + u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK; u8 offs = 0; rx_status->bw = RATE_INFO_BW_HE_RU; @@ -1002,19 +1003,27 @@ iwl_mvm_decode_he_phy_ru_alloc(struct iwl_mvm_rx_phy_data *phy_data, he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC); - if (he_mu) { #define CHECK_BW(bw) \ BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_ ## bw ## MHZ != \ + RATE_MCS_CHAN_WIDTH_##bw >> RATE_MCS_CHAN_WIDTH_POS); \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_ ## bw ## MHZ != \ RATE_MCS_CHAN_WIDTH_##bw >> RATE_MCS_CHAN_WIDTH_POS) - CHECK_BW(20); - CHECK_BW(40); - CHECK_BW(80); - CHECK_BW(160); + CHECK_BW(20); + CHECK_BW(40); + CHECK_BW(80); + CHECK_BW(160); + + if (he_mu) he_mu->flags2 |= le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK, rate_n_flags), IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW); - } + else if (he_type == RATE_MCS_HE_TYPE_TRIG) + he->data6 |= + cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_KNOWN) | + le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK, + rate_n_flags), + IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW); } static void iwl_mvm_decode_he_phy_data(struct iwl_mvm *mvm, diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 8014153bdd49..38c48bb80439 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -291,6 +291,12 @@ enum ieee80211_radiotap_he_bits { IEEE80211_RADIOTAP_HE_DATA6_NSTS = 0x000f, IEEE80211_RADIOTAP_HE_DATA6_DOPPLER = 0x0010, + IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_KNOWN = 0x0020, + IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW = 0x00c0, + IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_20MHZ = 0, + IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_40MHZ = 1, + IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_80MHZ = 2, + IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_160MHZ = 3, IEEE80211_RADIOTAP_HE_DATA6_TXOP = 0x7f00, IEEE80211_RADIOTAP_HE_DATA6_MIDAMBLE_PDCTY = 0x8000, }; -- cgit v1.2.3 From adfebb51e1750c5df9e5d42f505b73c5542a879d Mon Sep 17 00:00:00 2001 From: Bard liao Date: Fri, 1 Feb 2019 11:07:40 -0600 Subject: ASoC: topology: unload physical dai link in remove soc_tplg_link_config() will find the physical dai link and call soc_tplg_dai_link_load() to load the BE dai link. Currently remove_link() is only used to remove the FE dai link which is created by the topology. The BE dai link cannot however be unloaded in snd_soc_tplg_component _remove(), which is problematic if anything needs to be released or reinitialized. This patch aligns the definitions of dynamic types with the existing UAPI and adds a new remove_backend_link() routine to unload the the BE dai link when snd_soc_tplg_component_remove() is invoked. Signed-off-by: Bard liao Signed-off-by: Pierre-Louis Bossart Signed-off-by: Mark Brown --- include/sound/soc-topology.h | 1 + sound/soc/soc-topology.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) (limited to 'include') diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h index 8c43cfc240fa..5223896de26f 100644 --- a/include/sound/soc-topology.h +++ b/include/sound/soc-topology.h @@ -45,6 +45,7 @@ enum snd_soc_dobj_type { SND_SOC_DOBJ_DAI_LINK, SND_SOC_DOBJ_PCM, SND_SOC_DOBJ_CODEC_LINK, + SND_SOC_DOBJ_BACKEND_LINK, }; /* dynamic control object */ diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 23d421370e6c..246d2a2d43c8 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -557,6 +557,25 @@ static void remove_link(struct snd_soc_component *comp, kfree(link); } +/* unload dai link */ +static void remove_backend_link(struct snd_soc_component *comp, + struct snd_soc_dobj *dobj, int pass) +{ + if (pass != SOC_TPLG_PASS_LINK) + return; + + if (dobj->ops && dobj->ops->link_unload) + dobj->ops->link_unload(comp, dobj); + + /* + * We don't free the link here as what remove_link() do since BE + * links are not allocated by topology. + * We however need to reset the dobj type to its initial values + */ + dobj->type = SND_SOC_DOBJ_NONE; + list_del(&dobj->list); +} + /* bind a kcontrol to it's IO handlers */ static int soc_tplg_kcontrol_bind_io(struct snd_soc_tplg_ctl_hdr *hdr, struct snd_kcontrol_new *k, @@ -2163,6 +2182,12 @@ static int soc_tplg_link_config(struct soc_tplg *tplg, return ret; } + /* for unloading it in snd_soc_tplg_component_remove */ + link->dobj.index = tplg->index; + link->dobj.ops = tplg->ops; + link->dobj.type = SND_SOC_DOBJ_BACKEND_LINK; + list_add(&link->dobj.list, &tplg->comp->dobj_list); + return 0; } @@ -2649,6 +2674,13 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index) case SND_SOC_DOBJ_DAI_LINK: remove_link(comp, dobj, pass); break; + case SND_SOC_DOBJ_BACKEND_LINK: + /* + * call link_unload ops if extra + * deinitialization is needed. + */ + remove_backend_link(comp, dobj, pass); + break; default: dev_err(comp->dev, "ASoC: invalid component type %d for removal\n", dobj->type); -- cgit v1.2.3 From a46c52d9f2659498f0c0871f7f2333a692c243fe Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 29 Jan 2019 15:51:17 +0800 Subject: netfilter: nft_tunnel: Add NFTA_TUNNEL_MODE options nft "tunnel" expr match both the tun_info of RX and TX. This patch provide the NFTA_TUNNEL_MODE to individually match the tun_info of RX or TX. Signed-off-by: wenxu Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 9 +++++++++ net/netfilter/nft_tunnel.c | 34 ++++++++++++++++++++++++++++++-- 2 files changed, 41 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 030302893d96..a66c8de006cc 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1727,10 +1727,19 @@ enum nft_tunnel_keys { }; #define NFT_TUNNEL_MAX (__NFT_TUNNEL_MAX - 1) +enum nft_tunnel_mode { + NFT_TUNNEL_MODE_NONE, + NFT_TUNNEL_MODE_RX, + NFT_TUNNEL_MODE_TX, + __NFT_TUNNEL_MODE_MAX +}; +#define NFT_TUNNEL_MODE_MAX (__NFT_TUNNEL_MODE_MAX - 1) + enum nft_tunnel_attributes { NFTA_TUNNEL_UNSPEC, NFTA_TUNNEL_KEY, NFTA_TUNNEL_DREG, + NFTA_TUNNEL_MODE, __NFTA_TUNNEL_MAX }; #define NFTA_TUNNEL_MAX (__NFTA_TUNNEL_MAX - 1) diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 3a15f219e4e7..ea28588c5eed 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -15,6 +15,7 @@ struct nft_tunnel { enum nft_tunnel_keys key:8; enum nft_registers dreg:8; + enum nft_tunnel_mode mode:8; }; static void nft_tunnel_get_eval(const struct nft_expr *expr, @@ -29,14 +30,32 @@ static void nft_tunnel_get_eval(const struct nft_expr *expr, switch (priv->key) { case NFT_TUNNEL_PATH: - nft_reg_store8(dest, !!tun_info); + if (!tun_info) { + nft_reg_store8(dest, false); + return; + } + if (priv->mode == NFT_TUNNEL_MODE_NONE || + (priv->mode == NFT_TUNNEL_MODE_RX && + !(tun_info->mode & IP_TUNNEL_INFO_TX)) || + (priv->mode == NFT_TUNNEL_MODE_TX && + (tun_info->mode & IP_TUNNEL_INFO_TX))) + nft_reg_store8(dest, true); + else + nft_reg_store8(dest, false); break; case NFT_TUNNEL_ID: if (!tun_info) { regs->verdict.code = NFT_BREAK; return; } - *dest = ntohl(tunnel_id_to_key32(tun_info->key.tun_id)); + if (priv->mode == NFT_TUNNEL_MODE_NONE || + (priv->mode == NFT_TUNNEL_MODE_RX && + !(tun_info->mode & IP_TUNNEL_INFO_TX)) || + (priv->mode == NFT_TUNNEL_MODE_TX && + (tun_info->mode & IP_TUNNEL_INFO_TX))) + *dest = ntohl(tunnel_id_to_key32(tun_info->key.tun_id)); + else + regs->verdict.code = NFT_BREAK; break; default: WARN_ON(1); @@ -47,6 +66,7 @@ static void nft_tunnel_get_eval(const struct nft_expr *expr, static const struct nla_policy nft_tunnel_policy[NFTA_TUNNEL_MAX + 1] = { [NFTA_TUNNEL_KEY] = { .type = NLA_U32 }, [NFTA_TUNNEL_DREG] = { .type = NLA_U32 }, + [NFTA_TUNNEL_MODE] = { .type = NLA_U32 }, }; static int nft_tunnel_get_init(const struct nft_ctx *ctx, @@ -74,6 +94,14 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx, priv->dreg = nft_parse_register(tb[NFTA_TUNNEL_DREG]); + if (tb[NFTA_TUNNEL_MODE]) { + priv->mode = ntohl(nla_get_be32(tb[NFTA_TUNNEL_MODE])); + if (priv->mode > NFT_TUNNEL_MODE_MAX) + return -EOPNOTSUPP; + } else { + priv->mode = NFT_TUNNEL_MODE_NONE; + } + return nft_validate_register_store(ctx, priv->dreg, NULL, NFT_DATA_VALUE, len); } @@ -87,6 +115,8 @@ static int nft_tunnel_get_dump(struct sk_buff *skb, goto nla_put_failure; if (nft_dump_register(skb, NFTA_TUNNEL_DREG, priv->dreg)) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_TUNNEL_MODE, htonl(priv->mode))) + goto nla_put_failure; return 0; nla_put_failure: -- cgit v1.2.3 From 77000bc43da17d5d6bc4ebfaf44d52d43bb69492 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 Feb 2019 16:31:04 +0100 Subject: uio: remove the unused iov_for_each macro Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- .clang-format | 1 - include/linux/uio.h | 8 -------- 2 files changed, 9 deletions(-) (limited to 'include') diff --git a/.clang-format b/.clang-format index e6080f5834a3..c144d9c24d5d 100644 --- a/.clang-format +++ b/.clang-format @@ -259,7 +259,6 @@ ForEachMacros: - 'idr_for_each_entry_ul' - 'inet_bind_bucket_for_each' - 'inet_lhash2_for_each_icsk_rcu' - - 'iov_for_each' - 'key_for_each' - 'key_for_each_safe' - 'klp_for_each_func' diff --git a/include/linux/uio.h b/include/linux/uio.h index ecf584f6b82d..87477e1640f9 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -110,14 +110,6 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) }; } -#define iov_for_each(iov, iter, start) \ - if (iov_iter_type(start) == ITER_IOVEC || \ - iov_iter_type(start) == ITER_KVEC) \ - for (iter = (start); \ - (iter).count && \ - ((iov = iov_iter_iovec(&(iter))), 1); \ - iov_iter_advance(&(iter), (iov).iov_len)) - size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); -- cgit v1.2.3 From 960587285a56ec3cafb4d1e6b25c19eced4d0bce Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 2 Feb 2019 10:16:59 +0100 Subject: netfilter: nat: remove module dependency on ipv6 core nf_nat_ipv6 calls two ipv6 core functions, so add those to v6ops to avoid the module dependency. This is a prerequisite for merging ipv4 and ipv6 nat implementations. Add wrappers to avoid the indirection if ipv6 is builtin. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 6 ++++++ net/ipv6/netfilter.c | 4 ++++ net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 17 ++++++++++++++++- net/ipv6/netfilter/nf_nat_masquerade_ipv6.c | 21 +++++++++++++++++++-- 4 files changed, 45 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index c0dc4dd78887..ad4223c10488 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -33,6 +33,12 @@ struct nf_ipv6_ops { int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); +#if IS_MODULE(CONFIG_IPV6) + int (*route_me_harder)(struct net *net, struct sk_buff *skb); + int (*dev_get_saddr)(struct net *net, const struct net_device *dev, + const struct in6_addr *daddr, unsigned int srcprefs, + struct in6_addr *saddr); +#endif }; #ifdef CONFIG_NETFILTER diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 8b075f0bc351..0a5caf263889 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -112,6 +112,10 @@ static const struct nf_ipv6_ops ipv6ops = { .fragment = ip6_fragment, .route = nf_ip6_route, .reroute = nf_ip6_reroute, +#if IS_MODULE(CONFIG_IPV6) + .route_me_harder = ip6_route_me_harder, + .dev_get_saddr = ipv6_dev_get_saddr, +#endif }; int __init ipv6_netfilter_init(void) diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 9c914db44bec..b52026adb3e7 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -317,6 +318,20 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb, return ret; } +static int nat_route_me_harder(struct net *net, struct sk_buff *skb) +{ +#ifdef CONFIG_IPV6_MODULE + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return -EHOSTUNREACH; + + return v6_ops->route_me_harder(net, skb); +#else + return ip6_route_me_harder(net, skb); +#endif +} + static unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -333,7 +348,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { - err = ip6_route_me_harder(state->net, skb); + err = nat_route_me_harder(state->net, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 0ad0da5a2600..fd313b726263 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -24,6 +24,23 @@ static atomic_t v6_worker_count; +static int +nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, + const struct in6_addr *daddr, unsigned int srcprefs, + struct in6_addr *saddr) +{ +#ifdef CONFIG_IPV6_MODULE + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return -EHOSTUNREACH; + + return v6_ops->dev_get_saddr(net, dev, daddr, srcprefs, saddr); +#else + return ipv6_dev_get_saddr(net, dev, daddr, srcprefs, saddr); +#endif +} + unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, const struct net_device *out) @@ -38,8 +55,8 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY))); - if (ipv6_dev_get_saddr(nf_ct_net(ct), out, - &ipv6_hdr(skb)->daddr, 0, &src) < 0) + if (nat_ipv6_dev_get_saddr(nf_ct_net(ct), out, + &ipv6_hdr(skb)->daddr, 0, &src) < 0) return NF_DROP; nat = nf_ct_nat_ext_add(ct); -- cgit v1.2.3 From ac02bcf9cc1e4aefb0a7156a2ae26e8396b15f24 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 2 Feb 2019 10:17:00 +0100 Subject: netfilter: ipv6: avoid indirect calls for IPV6=y case indirect calls are only needed if ipv6 is a module. Add helpers to abstract the v6ops indirections and use them instead. fragment, reroute and route_input are kept as indirect calls. The first two are not not used in hot path and route_input is only used by bridge netfilter. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 64 +++++++++++++++++++++++++++++++-------- net/ipv6/netfilter.c | 15 ++++----- net/ipv6/netfilter/nft_fib_ipv6.c | 9 ++---- net/netfilter/utils.c | 6 ++-- net/netfilter/xt_addrtype.c | 16 +++------- 5 files changed, 68 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index ad4223c10488..471e9467105b 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -25,29 +25,24 @@ struct nf_queue_entry; * if IPv6 is a module. */ struct nf_ipv6_ops { +#if IS_MODULE(CONFIG_IPV6) int (*chk_addr)(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); - void (*route_input)(struct sk_buff *skb); - int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, - int (*output)(struct net *, struct sock *, struct sk_buff *)); - int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl, - bool strict); - int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); -#if IS_MODULE(CONFIG_IPV6) int (*route_me_harder)(struct net *net, struct sk_buff *skb); int (*dev_get_saddr)(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); + int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl, + bool strict); #endif + void (*route_input)(struct sk_buff *skb); + int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); + int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); }; #ifdef CONFIG_NETFILTER -int ip6_route_me_harder(struct net *net, struct sk_buff *skb); -__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol); - -int ipv6_netfilter_init(void); -void ipv6_netfilter_fini(void); +#include extern const struct nf_ipv6_ops __rcu *nf_ipv6_ops; static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) @@ -55,6 +50,49 @@ static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) return rcu_dereference(nf_ipv6_ops); } +static inline int nf_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return 1; + + return v6_ops->chk_addr(net, addr, dev, strict); +#else + return ipv6_chk_addr(net, addr, dev, strict); +#endif +} + +int __nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict); + +static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + + if (v6ops) + return v6ops->route(net, dst, fl, strict); + + return -EHOSTUNREACH; +#endif +#if IS_BUILTIN(CONFIG_IPV6) + return __nf_ip6_route(net, dst, fl, strict); +#else + return -EHOSTUNREACH; +#endif +} + +int ip6_route_me_harder(struct net *net, struct sk_buff *skb); +__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol); + +int ipv6_netfilter_init(void); +void ipv6_netfilter_fini(void); + #else /* CONFIG_NETFILTER */ static inline int ipv6_netfilter_init(void) { return 0; } static inline void ipv6_netfilter_fini(void) { return; } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 0a5caf263889..a8263031f3a6 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -84,8 +84,8 @@ static int nf_ip6_reroute(struct sk_buff *skb, return 0; } -static int nf_ip6_route(struct net *net, struct dst_entry **dst, - struct flowi *fl, bool strict) +int __nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict) { static const struct ipv6_pinfo fake_pinfo; static const struct inet_sock fake_sk = { @@ -105,17 +105,18 @@ static int nf_ip6_route(struct net *net, struct dst_entry **dst, *dst = result; return err; } +EXPORT_SYMBOL_GPL(__nf_ip6_route); static const struct nf_ipv6_ops ipv6ops = { - .chk_addr = ipv6_chk_addr, - .route_input = ip6_route_input, - .fragment = ip6_fragment, - .route = nf_ip6_route, - .reroute = nf_ip6_reroute, #if IS_MODULE(CONFIG_IPV6) + .chk_addr = ipv6_chk_addr, .route_me_harder = ip6_route_me_harder, .dev_get_saddr = ipv6_dev_get_saddr, + .route = __nf_ip6_route, #endif + .route_input = ip6_route_input, + .fragment = ip6_fragment, + .reroute = nf_ip6_reroute, }; int __init ipv6_netfilter_init(void) diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 36be3cf0adef..73cdc0bc63f7 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -59,7 +59,6 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv, struct ipv6hdr *iph) { const struct net_device *dev = NULL; - const struct nf_ipv6_ops *v6ops; int route_err, addrtype; struct rt6_info *rt; struct flowi6 fl6 = { @@ -68,10 +67,6 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv, }; u32 ret = 0; - v6ops = nf_get_ipv6_ops(); - if (!v6ops) - return RTN_UNREACHABLE; - if (priv->flags & NFTA_FIB_F_IIF) dev = nft_in(pkt); else if (priv->flags & NFTA_FIB_F_OIF) @@ -79,10 +74,10 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv, nft_fib6_flowi_init(&fl6, priv, pkt, dev, iph); - if (dev && v6ops->chk_addr(nft_net(pkt), &fl6.daddr, dev, true)) + if (dev && nf_ipv6_chk_addr(nft_net(pkt), &fl6.daddr, dev, true)) ret = RTN_LOCAL; - route_err = v6ops->route(nft_net(pkt), (struct dst_entry **)&rt, + route_err = nf_ip6_route(nft_net(pkt), (struct dst_entry **)&rt, flowi6_to_flowi(&fl6), false); if (route_err) goto err; diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index 55af9f247993..06dc55590441 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -162,7 +162,7 @@ EXPORT_SYMBOL_GPL(nf_checksum_partial); int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict, unsigned short family) { - const struct nf_ipv6_ops *v6ops; + const struct nf_ipv6_ops *v6ops __maybe_unused; int ret = 0; switch (family) { @@ -170,9 +170,7 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, ret = nf_ip_route(net, dst, fl, strict); break; case AF_INET6: - v6ops = rcu_dereference(nf_ipv6_ops); - if (v6ops) - ret = v6ops->route(net, dst, fl, strict); + ret = nf_ip6_route(net, dst, fl, strict); break; } diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 89e281b3bfc2..29987ff03621 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -36,7 +36,6 @@ MODULE_ALIAS("ip6t_addrtype"); static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, const struct in6_addr *addr, u16 mask) { - const struct nf_ipv6_ops *v6ops; struct flowi6 flow; struct rt6_info *rt; u32 ret = 0; @@ -47,18 +46,13 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, if (dev) flow.flowi6_oif = dev->ifindex; - v6ops = nf_get_ipv6_ops(); - if (v6ops) { - if (dev && (mask & XT_ADDRTYPE_LOCAL)) { - if (v6ops->chk_addr(net, addr, dev, true)) - ret = XT_ADDRTYPE_LOCAL; - } - route_err = v6ops->route(net, (struct dst_entry **)&rt, - flowi6_to_flowi(&flow), false); - } else { - route_err = 1; + if (dev && (mask & XT_ADDRTYPE_LOCAL)) { + if (nf_ipv6_chk_addr(net, addr, dev, true)) + ret = XT_ADDRTYPE_LOCAL; } + route_err = nf_ip6_route(net, (struct dst_entry **)&rt, + flowi6_to_flowi(&flow), false); if (route_err) return XT_ADDRTYPE_UNREACHABLE; -- cgit v1.2.3 From da82334219bc386ef7ea5b4b185a339a973dd513 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 22 Jan 2019 08:48:41 +0200 Subject: IB/core: Allocate a bit for SRQ ODP support The ODP support matrix is per operation and per transport. The support for each transport (RC, UD, etc.) is described with a bit field. ODP for SRQ WQEs is considered a different kind of support from ODP for RQ WQs and therefore needs a different capability bit. Signed-off-by: Moni Shoua Reviewed-by: Majd Dibbiny Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 5fc3be884444..5eefdea62831 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -268,6 +268,7 @@ enum ib_odp_transport_cap_bits { IB_ODP_SUPPORT_WRITE = 1 << 2, IB_ODP_SUPPORT_READ = 1 << 3, IB_ODP_SUPPORT_ATOMIC = 1 << 4, + IB_ODP_SUPPORT_SRQ_RECV = 1 << 5, }; struct ib_odp_caps { -- cgit v1.2.3 From 52a72e2a395fa3c5ab5df41058a8511e87215730 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 22 Jan 2019 08:48:42 +0200 Subject: IB/uverbs: Expose XRC ODP device capabilities Expose XRC ODP capabilities as part of the extended device capabilities. Signed-off-by: Moni Shoua Reviewed-by: Majd Dibbiny Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/uverbs_cmd.c | 1 + include/rdma/ib_verbs.h | 1 + include/uapi/rdma/ib_user_verbs.h | 2 ++ 3 files changed, 4 insertions(+) (limited to 'include') diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index d4f1a2ef5015..68c4ea514faf 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -3613,6 +3613,7 @@ static int ib_uverbs_ex_query_device(struct uverbs_attr_bundle *attrs) attr.odp_caps.per_transport_caps.uc_odp_caps; resp.odp_caps.per_transport_caps.ud_odp_caps = attr.odp_caps.per_transport_caps.ud_odp_caps; + resp.xrc_odp_caps = attr.odp_caps.per_transport_caps.xrc_odp_caps; resp.timestamp_mask = attr.timestamp_mask; resp.hca_core_clock = attr.hca_core_clock; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 5eefdea62831..8219c07340a9 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -277,6 +277,7 @@ struct ib_odp_caps { uint32_t rc_odp_caps; uint32_t uc_odp_caps; uint32_t ud_odp_caps; + uint32_t xrc_odp_caps; } per_transport_caps; }; diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 480d9a60b68e..0474c7400268 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -270,6 +270,8 @@ struct ib_uverbs_ex_query_device_resp { struct ib_uverbs_tm_caps tm_caps; struct ib_uverbs_cq_moderation_caps cq_moderation_caps; __aligned_u64 max_dm_size; + __u32 xrc_odp_caps; + __u32 reserved; }; struct ib_uverbs_query_port { -- cgit v1.2.3 From a163afc88556e099271a7b423295bc5176fcecce Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 31 Jan 2019 08:30:34 -0800 Subject: IB/core: Remove ib_sg_dma_address() and ib_sg_dma_len() Keeping single line wrapper functions is not useful. Hence remove the ib_sg_dma_address() and ib_sg_dma_len() functions. This patch does not change any functionality. Signed-off-by: Bart Van Assche Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/rw.c | 12 +++++------- drivers/infiniband/ulp/iser/iser_memory.c | 9 ++++----- drivers/infiniband/ulp/srp/ib_srp.c | 17 +++++++---------- include/rdma/ib_verbs.h | 27 --------------------------- net/rds/ib.h | 12 ++++-------- net/rds/ib_fmr.c | 8 ++++---- net/rds/ib_frmr.c | 4 ++-- net/rds/ib_recv.c | 8 +++----- net/rds/ib_send.c | 15 +++++++-------- 9 files changed, 36 insertions(+), 76 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c index d22c4a2ebac6..89a5be3a2f97 100644 --- a/drivers/infiniband/core/rw.c +++ b/drivers/infiniband/core/rw.c @@ -179,7 +179,6 @@ static int rdma_rw_init_map_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp, struct scatterlist *sg, u32 sg_cnt, u32 offset, u64 remote_addr, u32 rkey, enum dma_data_direction dir) { - struct ib_device *dev = qp->pd->device; u32 max_sge = dir == DMA_TO_DEVICE ? qp->max_write_sge : qp->max_read_sge; struct ib_sge *sge; @@ -209,8 +208,8 @@ static int rdma_rw_init_map_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp, rdma_wr->wr.sg_list = sge; for (j = 0; j < nr_sge; j++, sg = sg_next(sg)) { - sge->addr = ib_sg_dma_address(dev, sg) + offset; - sge->length = ib_sg_dma_len(dev, sg) - offset; + sge->addr = sg_dma_address(sg) + offset; + sge->length = sg_dma_len(sg) - offset; sge->lkey = qp->pd->local_dma_lkey; total_len += sge->length; @@ -236,14 +235,13 @@ static int rdma_rw_init_single_wr(struct rdma_rw_ctx *ctx, struct ib_qp *qp, struct scatterlist *sg, u32 offset, u64 remote_addr, u32 rkey, enum dma_data_direction dir) { - struct ib_device *dev = qp->pd->device; struct ib_rdma_wr *rdma_wr = &ctx->single.wr; ctx->nr_ops = 1; ctx->single.sge.lkey = qp->pd->local_dma_lkey; - ctx->single.sge.addr = ib_sg_dma_address(dev, sg) + offset; - ctx->single.sge.length = ib_sg_dma_len(dev, sg) - offset; + ctx->single.sge.addr = sg_dma_address(sg) + offset; + ctx->single.sge.length = sg_dma_len(sg) - offset; memset(rdma_wr, 0, sizeof(*rdma_wr)); if (dir == DMA_TO_DEVICE) @@ -294,7 +292,7 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num, * Skip to the S/G entry that sg_offset falls into: */ for (;;) { - u32 len = ib_sg_dma_len(dev, sg); + u32 len = sg_dma_len(sg); if (sg_offset < len) break; diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 394d1b9c2ff7..2ba70729d7b0 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -145,9 +145,8 @@ static void iser_data_buf_dump(struct iser_data_buf *data, for_each_sg(data->sg, sg, data->dma_nents, i) iser_dbg("sg[%d] dma_addr:0x%lX page:0x%p " "off:0x%x sz:0x%x dma_len:0x%x\n", - i, (unsigned long)ib_sg_dma_address(ibdev, sg), - sg_page(sg), sg->offset, - sg->length, ib_sg_dma_len(ibdev, sg)); + i, (unsigned long)sg_dma_address(sg), + sg_page(sg), sg->offset, sg->length, sg_dma_len(sg)); } static void iser_dump_page_vec(struct iser_page_vec *page_vec) @@ -204,8 +203,8 @@ iser_reg_dma(struct iser_device *device, struct iser_data_buf *mem, reg->rkey = device->pd->unsafe_global_rkey; else reg->rkey = 0; - reg->sge.addr = ib_sg_dma_address(device->ib_device, &sg[0]); - reg->sge.length = ib_sg_dma_len(device->ib_device, &sg[0]); + reg->sge.addr = sg_dma_address(&sg[0]); + reg->sge.length = sg_dma_len(&sg[0]); iser_dbg("Single DMA entry: lkey=0x%x, rkey=0x%x, addr=0x%llx," " length=0x%x\n", reg->sge.lkey, reg->rkey, diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 29fe46dbdbf1..84184910f038 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1600,9 +1600,8 @@ static int srp_map_sg_entry(struct srp_map_state *state, { struct srp_target_port *target = ch->target; struct srp_device *dev = target->srp_host->srp_dev; - struct ib_device *ibdev = dev->dev; - dma_addr_t dma_addr = ib_sg_dma_address(ibdev, sg); - unsigned int dma_len = ib_sg_dma_len(ibdev, sg); + dma_addr_t dma_addr = sg_dma_address(sg); + unsigned int dma_len = sg_dma_len(sg); unsigned int len = 0; int ret; @@ -1696,13 +1695,11 @@ static int srp_map_sg_dma(struct srp_map_state *state, struct srp_rdma_ch *ch, int count) { struct srp_target_port *target = ch->target; - struct srp_device *dev = target->srp_host->srp_dev; struct scatterlist *sg; int i; for_each_sg(scat, sg, count, i) { - srp_map_desc(state, ib_sg_dma_address(dev->dev, sg), - ib_sg_dma_len(dev->dev, sg), + srp_map_desc(state, sg_dma_address(sg), sg_dma_len(sg), target->global_rkey); } @@ -1852,8 +1849,8 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch, buf->len = cpu_to_be32(data_len); WARN_ON_ONCE((void *)(buf + 1) > (void *)cmd + len); for_each_sg(scat, sg, count, i) { - sge[i].addr = ib_sg_dma_address(ibdev, sg); - sge[i].length = ib_sg_dma_len(ibdev, sg); + sge[i].addr = sg_dma_address(sg); + sge[i].length = sg_dma_len(sg); sge[i].lkey = target->lkey; } req->cmd->num_sge += count; @@ -1874,9 +1871,9 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch, struct srp_direct_buf *buf; buf = (void *)cmd->add_data + cmd->add_cdb_len; - buf->va = cpu_to_be64(ib_sg_dma_address(ibdev, scat)); + buf->va = cpu_to_be64(sg_dma_address(scat)); buf->key = cpu_to_be32(target->global_rkey); - buf->len = cpu_to_be32(ib_sg_dma_len(ibdev, scat)); + buf->len = cpu_to_be32(sg_dma_len(scat)); req->nmdesc = 0; goto map_complete; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 8219c07340a9..f7e8709e48cd 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -3705,33 +3705,6 @@ static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, { dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } -/** - * ib_sg_dma_address - Return the DMA address from a scatter/gather entry - * @dev: The device for which the DMA addresses were created - * @sg: The scatter/gather entry - * - * Note: this function is obsolete. To do: change all occurrences of - * ib_sg_dma_address() into sg_dma_address(). - */ -static inline u64 ib_sg_dma_address(struct ib_device *dev, - struct scatterlist *sg) -{ - return sg_dma_address(sg); -} - -/** - * ib_sg_dma_len - Return the DMA length from a scatter/gather entry - * @dev: The device for which the DMA addresses were created - * @sg: The scatter/gather entry - * - * Note: this function is obsolete. To do: change all occurrences of - * ib_sg_dma_len() into sg_dma_len(). - */ -static inline unsigned int ib_sg_dma_len(struct ib_device *dev, - struct scatterlist *sg) -{ - return sg_dma_len(sg); -} /** * ib_dma_max_seg_size - Return the size limit of a single DMA transfer diff --git a/net/rds/ib.h b/net/rds/ib.h index 71ff356ee702..1fd1cac85da2 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -331,10 +331,8 @@ static inline void rds_ib_dma_sync_sg_for_cpu(struct ib_device *dev, unsigned int i; for_each_sg(sglist, sg, sg_dma_len, i) { - ib_dma_sync_single_for_cpu(dev, - ib_sg_dma_address(dev, sg), - ib_sg_dma_len(dev, sg), - direction); + ib_dma_sync_single_for_cpu(dev, sg_dma_address(sg), + sg_dma_len(sg), direction); } } #define ib_dma_sync_sg_for_cpu rds_ib_dma_sync_sg_for_cpu @@ -348,10 +346,8 @@ static inline void rds_ib_dma_sync_sg_for_device(struct ib_device *dev, unsigned int i; for_each_sg(sglist, sg, sg_dma_len, i) { - ib_dma_sync_single_for_device(dev, - ib_sg_dma_address(dev, sg), - ib_sg_dma_len(dev, sg), - direction); + ib_dma_sync_single_for_device(dev, sg_dma_address(sg), + sg_dma_len(sg), direction); } } #define ib_dma_sync_sg_for_device rds_ib_dma_sync_sg_for_device diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index e0f70c4051b6..31cf37da4510 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -108,8 +108,8 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, page_cnt = 0; for (i = 0; i < sg_dma_len; ++i) { - unsigned int dma_len = ib_sg_dma_len(dev, &scat[i]); - u64 dma_addr = ib_sg_dma_address(dev, &scat[i]); + unsigned int dma_len = sg_dma_len(&scat[i]); + u64 dma_addr = sg_dma_address(&scat[i]); if (dma_addr & ~PAGE_MASK) { if (i > 0) { @@ -148,8 +148,8 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, page_cnt = 0; for (i = 0; i < sg_dma_len; ++i) { - unsigned int dma_len = ib_sg_dma_len(dev, &scat[i]); - u64 dma_addr = ib_sg_dma_address(dev, &scat[i]); + unsigned int dma_len = sg_dma_len(&scat[i]); + u64 dma_addr = sg_dma_address(&scat[i]); for (j = 0; j < dma_len; j += PAGE_SIZE) dma_pages[page_cnt++] = diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 6431a023ac89..688dcd68d4ea 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -181,8 +181,8 @@ static int rds_ib_map_frmr(struct rds_ib_device *rds_ibdev, ret = -EINVAL; for (i = 0; i < ibmr->sg_dma_len; ++i) { - unsigned int dma_len = ib_sg_dma_len(dev, &ibmr->sg[i]); - u64 dma_addr = ib_sg_dma_address(dev, &ibmr->sg[i]); + unsigned int dma_len = sg_dma_len(&ibmr->sg[i]); + u64 dma_addr = sg_dma_address(&ibmr->sg[i]); frmr->sg_byte_len += dma_len; if (dma_addr & ~PAGE_MASK) { diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 2f16146e4ec9..672b91a9e207 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -346,8 +346,8 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn, sge->length = sizeof(struct rds_header); sge = &recv->r_sge[1]; - sge->addr = ib_sg_dma_address(ic->i_cm_id->device, &recv->r_frag->f_sg); - sge->length = ib_sg_dma_len(ic->i_cm_id->device, &recv->r_frag->f_sg); + sge->addr = sg_dma_address(&recv->r_frag->f_sg); + sge->length = sg_dma_len(&recv->r_frag->f_sg); ret = 0; out: @@ -409,9 +409,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) rdsdebug("recv %p ibinc %p page %p addr %lu\n", recv, recv->r_ibinc, sg_page(&recv->r_frag->f_sg), - (long) ib_sg_dma_address( - ic->i_cm_id->device, - &recv->r_frag->f_sg)); + (long)sg_dma_address(&recv->r_frag->f_sg)); /* XXX when can this fail? */ ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, NULL); diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 2dcb555e6350..dc5897a3a958 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -645,16 +645,16 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, if (i < work_alloc && scat != &rm->data.op_sg[rm->data.op_count]) { len = min(RDS_FRAG_SIZE, - ib_sg_dma_len(dev, scat) - rm->data.op_dmaoff); + sg_dma_len(scat) - rm->data.op_dmaoff); send->s_wr.num_sge = 2; - send->s_sge[1].addr = ib_sg_dma_address(dev, scat); + send->s_sge[1].addr = sg_dma_address(scat); send->s_sge[1].addr += rm->data.op_dmaoff; send->s_sge[1].length = len; bytes_sent += len; rm->data.op_dmaoff += len; - if (rm->data.op_dmaoff == ib_sg_dma_len(dev, scat)) { + if (rm->data.op_dmaoff == sg_dma_len(scat)) { scat++; rm->data.op_dmasg++; rm->data.op_dmaoff = 0; @@ -808,8 +808,8 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op) } /* Convert our struct scatterlist to struct ib_sge */ - send->s_sge[0].addr = ib_sg_dma_address(ic->i_cm_id->device, op->op_sg); - send->s_sge[0].length = ib_sg_dma_len(ic->i_cm_id->device, op->op_sg); + send->s_sge[0].addr = sg_dma_address(op->op_sg); + send->s_sge[0].length = sg_dma_len(op->op_sg); send->s_sge[0].lkey = ic->i_pd->local_dma_lkey; rdsdebug("rva %Lx rpa %Lx len %u\n", op->op_remote_addr, @@ -921,9 +921,8 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) for (j = 0; j < send->s_rdma_wr.wr.num_sge && scat != &op->op_sg[op->op_count]; j++) { - len = ib_sg_dma_len(ic->i_cm_id->device, scat); - send->s_sge[j].addr = - ib_sg_dma_address(ic->i_cm_id->device, scat); + len = sg_dma_len(scat); + send->s_sge[j].addr = sg_dma_address(scat); send->s_sge[j].length = len; send->s_sge[j].lkey = ic->i_pd->local_dma_lkey; -- cgit v1.2.3 From 219a3e8676f3132d27b530c7d2d6bcab89536b57 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Mon, 21 Jan 2019 17:59:28 +0800 Subject: integrity, KEYS: add a reference to platform keyring commit 9dc92c45177a ("integrity: Define a trusted platform keyring") introduced a .platform keyring for storing preboot keys, used for verifying kernel image signatures. Currently only IMA-appraisal is able to use the keyring to verify kernel images that have their signature stored in xattr. This patch exposes the .platform keyring, making it accessible for verifying PE signed kernel images as well. Suggested-by: Mimi Zohar Signed-off-by: Kairui Song Cc: David Howells [zohar@linux.ibm.com: fixed checkpatch errors, squashed with patch fix] Signed-off-by: Mimi Zohar --- certs/system_keyring.c | 10 ++++++++++ include/keys/system_keyring.h | 8 ++++++++ security/integrity/digsig.c | 3 +++ 3 files changed, 21 insertions(+) (limited to 'include') diff --git a/certs/system_keyring.c b/certs/system_keyring.c index 81728717523d..da055e901df4 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -24,6 +24,9 @@ static struct key *builtin_trusted_keys; #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING static struct key *secondary_trusted_keys; #endif +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING +static struct key *platform_trusted_keys; +#endif extern __initconst const u8 system_certificate_list[]; extern __initconst const unsigned long system_certificate_list_size; @@ -266,3 +269,10 @@ error: EXPORT_SYMBOL_GPL(verify_pkcs7_signature); #endif /* CONFIG_SYSTEM_DATA_VERIFICATION */ + +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING +void __init set_platform_trusted_keys(struct key *keyring) +{ + platform_trusted_keys = keyring; +} +#endif diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index 359c2f936004..42a93eda331c 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -61,5 +61,13 @@ static inline struct key *get_ima_blacklist_keyring(void) } #endif /* CONFIG_IMA_BLACKLIST_KEYRING */ +#if defined(CONFIG_INTEGRITY_PLATFORM_KEYRING) && \ + defined(CONFIG_SYSTEM_TRUSTED_KEYRING) +extern void __init set_platform_trusted_keys(struct key *keyring); +#else +static inline void set_platform_trusted_keys(struct key *keyring) +{ +} +#endif #endif /* _KEYS_SYSTEM_KEYRING_H */ diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index f45d6edecf99..e19c2eb72c51 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -87,6 +87,9 @@ static int __integrity_init_keyring(const unsigned int id, key_perm_t perm, pr_info("Can't allocate %s keyring (%d)\n", keyring_name[id], err); keyring[id] = NULL; + } else { + if (id == INTEGRITY_KEYRING_PLATFORM) + set_platform_trusted_keys(keyring[id]); } return err; -- cgit v1.2.3 From 278311e417be60f7caef6fcb12bda4da2711ceff Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Mon, 21 Jan 2019 17:59:29 +0800 Subject: kexec, KEYS: Make use of platform keyring for signature verify This patch allows the kexec_file_load syscall to verify the PE signed kernel image signature based on the preboot keys stored in the .platform keyring, as fall back, if the signature verification failed due to not finding the public key in the secondary or builtin keyrings. This commit adds a VERIFY_USE_PLATFORM_KEYRING similar to previous VERIFY_USE_SECONDARY_KEYRING indicating that verify_pkcs7_signature should verify the signature using platform keyring. Also, decrease the error message log level when verification failed with -ENOKEY, so that if called tried multiple time with different keyring it won't generate extra noises. Signed-off-by: Kairui Song Cc: David Howells Acked-by: Dave Young (for kexec_file_load part) [zohar@linux.ibm.com: tweaked the first paragraph of the patch description, and fixed checkpatch warning.] Signed-off-by: Mimi Zohar --- arch/x86/kernel/kexec-bzimage64.c | 14 +++++++++++--- certs/system_keyring.c | 13 ++++++++++++- include/linux/verification.h | 1 + 3 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 278cd07228dd..e1215a600064 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -531,9 +531,17 @@ static int bzImage64_cleanup(void *loader_data) #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) { - return verify_pefile_signature(kernel, kernel_len, - VERIFY_USE_SECONDARY_KEYRING, - VERIFYING_KEXEC_PE_SIGNATURE); + int ret; + + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_SECONDARY_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) { + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_PLATFORM_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + } + return ret; } #endif diff --git a/certs/system_keyring.c b/certs/system_keyring.c index da055e901df4..c05c29ae4d5d 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -240,11 +240,22 @@ int verify_pkcs7_signature(const void *data, size_t len, #else trusted_keys = builtin_trusted_keys; #endif + } else if (trusted_keys == VERIFY_USE_PLATFORM_KEYRING) { +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING + trusted_keys = platform_trusted_keys; +#else + trusted_keys = NULL; +#endif + if (!trusted_keys) { + ret = -ENOKEY; + pr_devel("PKCS#7 platform keyring is not available\n"); + goto error; + } } ret = pkcs7_validate_trust(pkcs7, trusted_keys); if (ret < 0) { if (ret == -ENOKEY) - pr_err("PKCS#7 signature not signed with a trusted key\n"); + pr_devel("PKCS#7 signature not signed with a trusted key\n"); goto error; } diff --git a/include/linux/verification.h b/include/linux/verification.h index cfa4730d607a..018fb5f13d44 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -17,6 +17,7 @@ * should be used. */ #define VERIFY_USE_SECONDARY_KEYRING ((struct key *)1UL) +#define VERIFY_USE_PLATFORM_KEYRING ((struct key *)2UL) /* * The use to which an asymmetric key is being put. -- cgit v1.2.3 From fdb2410f7702f25f82804a261f90ad03422bd2c3 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 22 Jan 2019 14:06:49 -0600 Subject: ima: define ima_post_create_tmpfile() hook and add missing call If tmpfiles can be made persistent, then newly created tmpfiles need to be treated like any other new files in policy. This patch indicates which newly created tmpfiles are in policy, causing the file hash to be calculated on __fput(). Reported-by: Ignaz Forster [rgoldwyn@suse.com: Call ima_post_create_tmpfile() in vfs_tmpfile() as opposed to do_tmpfile(). This will help the case for overlayfs where copy_up is denied while overwriting a file.] Signed-off-by: Goldwyn Rodrigues Signed-off-by: Mimi Zohar --- fs/namei.c | 1 + include/linux/ima.h | 5 +++++ security/integrity/ima/ima_main.c | 35 +++++++++++++++++++++++++++++++++-- 3 files changed, 39 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/namei.c b/fs/namei.c index 914178cdbe94..373a7ec4b09d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3462,6 +3462,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } + ima_post_create_tmpfile(inode); return child; out_err: diff --git a/include/linux/ima.h b/include/linux/ima.h index b5e16b8c50b7..dc12fbcf484c 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -18,6 +18,7 @@ struct linux_binprm; #ifdef CONFIG_IMA extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask); +extern void ima_post_create_tmpfile(struct inode *inode); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern int ima_load_data(enum kernel_load_data_id id); @@ -56,6 +57,10 @@ static inline int ima_file_check(struct file *file, int mask) return 0; } +static inline void ima_post_create_tmpfile(struct inode *inode) +{ +} + static inline void ima_file_free(struct file *file) { return; diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 4ffac4f5c647..357edd140c09 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -396,6 +396,33 @@ int ima_file_check(struct file *file, int mask) } EXPORT_SYMBOL_GPL(ima_file_check); +/** + * ima_post_create_tmpfile - mark newly created tmpfile as new + * @file : newly created tmpfile + * + * No measuring, appraising or auditing of newly created tmpfiles is needed. + * Skip calling process_measurement(), but indicate which newly, created + * tmpfiles are in policy. + */ +void ima_post_create_tmpfile(struct inode *inode) +{ + struct integrity_iint_cache *iint; + int must_appraise; + + must_appraise = ima_must_appraise(inode, MAY_ACCESS, FILE_CHECK); + if (!must_appraise) + return; + + /* Nothing to do if we can't allocate memory */ + iint = integrity_inode_get(inode); + if (!iint) + return; + + /* needed for writing the security xattrs */ + set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); + iint->ima_file_status = INTEGRITY_PASS; +} + /** * ima_post_path_mknod - mark as a new inode * @dentry: newly created dentry @@ -413,9 +440,13 @@ void ima_post_path_mknod(struct dentry *dentry) if (!must_appraise) return; + /* Nothing to do if we can't allocate memory */ iint = integrity_inode_get(inode); - if (iint) - iint->flags |= IMA_NEW_FILE; + if (!iint) + return; + + /* needed for re-opening empty files */ + iint->flags |= IMA_NEW_FILE; } /** -- cgit v1.2.3 From 668aa15b5bf87f156ec805cb7348c785c56b82ab Mon Sep 17 00:00:00 2001 From: Kamal Heib Date: Tue, 29 Jan 2019 12:08:50 +0200 Subject: RDMA/rxe: Improve loopback marking Currently a packet is marked for loopback only if the source and destination addresses equals. This is not enough when multiple gids are present in rxe device's gid table and the traffic is from one gid to another. Fix it by marking the packet for loopback if the destination MAC address is equal to the source MAC address. Signed-off-by: Kamal Heib Reviewed-by: Yuval Shaia Tested-by: Yuval Shaia Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_av.c | 1 + drivers/infiniband/sw/rxe/rxe_net.c | 9 +++------ include/uapi/rdma/rdma_user_rxe.h | 3 +-- 3 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/sw/rxe/rxe_av.c b/drivers/infiniband/sw/rxe/rxe_av.c index 27a7dec18874..81ee756c19b8 100644 --- a/drivers/infiniband/sw/rxe/rxe_av.c +++ b/drivers/infiniband/sw/rxe/rxe_av.c @@ -38,6 +38,7 @@ void rxe_init_av(struct rdma_ah_attr *attr, struct rxe_av *av) { rxe_av_from_attr(rdma_ah_get_port_num(attr), av, attr); rxe_av_fill_ip_info(av, attr); + memcpy(av->dmac, attr->roce.dmac, ETH_ALEN); } int rxe_av_chk_attr(struct rxe_dev *rxe, struct rdma_ah_attr *attr) diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 19f3c69916b1..3b162e92e8e8 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -384,9 +384,6 @@ static int prepare4(struct rxe_pkt_info *pkt, struct sk_buff *skb, return -EHOSTUNREACH; } - if (!memcmp(saddr, daddr, sizeof(*daddr))) - pkt->mask |= RXE_LOOPBACK_MASK; - prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); @@ -411,9 +408,6 @@ static int prepare6(struct rxe_pkt_info *pkt, struct sk_buff *skb, return -EHOSTUNREACH; } - if (!memcmp(saddr, daddr, sizeof(*daddr))) - pkt->mask |= RXE_LOOPBACK_MASK; - prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); @@ -437,6 +431,9 @@ int rxe_prepare(struct rxe_pkt_info *pkt, struct sk_buff *skb, u32 *crc) *crc = rxe_icrc_hdr(pkt, skb); + if (ether_addr_equal(skb->dev->dev_addr, av->dmac)) + pkt->mask |= RXE_LOOPBACK_MASK; + return err; } diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h index 44ef6a3b7afc..aae2e696bb38 100644 --- a/include/uapi/rdma/rdma_user_rxe.h +++ b/include/uapi/rdma/rdma_user_rxe.h @@ -58,8 +58,7 @@ struct rxe_global_route { struct rxe_av { __u8 port_num; __u8 network_type; - __u16 reserved1; - __u32 reserved2; + __u8 dmac[6]; struct rxe_global_route grh; union { struct sockaddr_in _sockaddr_in; -- cgit v1.2.3 From 3eb450367d0823226515ee24712ed08eccb33eb9 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Tue, 23 Oct 2018 23:21:14 -0400 Subject: rds: add type of service(tos) infrastructure RDS Service type (TOS) is user-defined and needs to be configured via RDS IOCTL interface. It must be set before initiating any traffic and once set the TOS can not be changed. All out-going traffic from the socket will be associated with its TOS. Reviewed-by: Sowmini Varadhan Signed-off-by: Santosh Shilimkar [yanjun.zhu@oracle.com: Adapted original patch with ipv6 changes] Signed-off-by: Zhu Yanjun --- include/uapi/linux/rds.h | 11 +++++++++++ net/rds/af_rds.c | 35 ++++++++++++++++++++++++++++++++++- net/rds/connection.c | 20 +++++++++++--------- net/rds/ib.c | 1 + net/rds/ib_cm.c | 2 +- net/rds/rdma_transport.c | 1 + net/rds/rds.h | 9 +++++++-- net/rds/recv.c | 1 + net/rds/send.c | 6 +++--- net/rds/tcp.c | 1 + net/rds/tcp_listen.c | 2 +- 11 files changed, 72 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index 8b73cb603c5f..5d0f76c780e5 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -69,6 +69,12 @@ #define RDS_TRANS_COUNT 3 #define RDS_TRANS_NONE (~0) +/* IOCTLS commands for SOL_RDS */ +#define SIOCRDSSETTOS (SIOCPROTOPRIVATE) +#define SIOCRDSGETTOS (SIOCPROTOPRIVATE + 1) + +typedef __u8 rds_tos_t; + /* * Control message types for SOL_RDS. * @@ -149,6 +155,7 @@ struct rds_info_connection { __be32 faddr; __u8 transport[TRANSNAMSIZ]; /* null term ascii */ __u8 flags; + __u8 tos; } __attribute__((packed)); struct rds6_info_connection { @@ -171,6 +178,7 @@ struct rds_info_message { __be16 lport; __be16 fport; __u8 flags; + __u8 tos; } __attribute__((packed)); struct rds6_info_message { @@ -214,6 +222,7 @@ struct rds_info_tcp_socket { __u32 last_sent_nxt; __u32 last_expected_una; __u32 last_seen_una; + __u8 tos; } __attribute__((packed)); struct rds6_info_tcp_socket { @@ -240,6 +249,7 @@ struct rds_info_rdma_connection { __u32 max_send_sge; __u32 rdma_mr_max; __u32 rdma_mr_size; + __u8 tos; }; struct rds6_info_rdma_connection { @@ -253,6 +263,7 @@ struct rds6_info_rdma_connection { __u32 max_send_sge; __u32 rdma_mr_max; __u32 rdma_mr_size; + __u8 tos; }; /* RDS message Receive Path Latency points */ diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 65571a6273c3..904515858037 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -254,7 +254,38 @@ static __poll_t rds_poll(struct file *file, struct socket *sock, static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { - return -ENOIOCTLCMD; + struct rds_sock *rs = rds_sk_to_rs(sock->sk); + rds_tos_t tos; + + switch (cmd) { + case SIOCRDSSETTOS: + if (get_user(tos, (rds_tos_t __user *)arg)) + return -EFAULT; + + if (rs->rs_transport && + rs->rs_transport->t_type == RDS_TRANS_TCP) + tos = 0; + + spin_lock_bh(&rds_sock_lock); + if (rs->rs_tos || rs->rs_conn) { + spin_unlock_bh(&rds_sock_lock); + return -EINVAL; + } + rs->rs_tos = tos; + spin_unlock_bh(&rds_sock_lock); + break; + case SIOCRDSGETTOS: + spin_lock_bh(&rds_sock_lock); + tos = rs->rs_tos; + spin_unlock_bh(&rds_sock_lock); + if (put_user(tos, (rds_tos_t __user *)arg)) + return -EFAULT; + break; + default: + return -ENOIOCTLCMD; + } + + return 0; } static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval, @@ -650,6 +681,8 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol) spin_lock_init(&rs->rs_rdma_lock); rs->rs_rdma_keys = RB_ROOT; rs->rs_rx_traces = 0; + rs->rs_tos = 0; + rs->rs_conn = NULL; spin_lock_bh(&rds_sock_lock); list_add_tail(&rs->rs_item, &rds_sock_list); diff --git a/net/rds/connection.c b/net/rds/connection.c index 1ab14b68ecc8..7ea134f9a825 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -84,7 +84,7 @@ static struct rds_connection *rds_conn_lookup(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - int dev_if) + u8 tos, int dev_if) { struct rds_connection *conn, *ret = NULL; @@ -92,6 +92,7 @@ static struct rds_connection *rds_conn_lookup(struct net *net, if (ipv6_addr_equal(&conn->c_faddr, faddr) && ipv6_addr_equal(&conn->c_laddr, laddr) && conn->c_trans == trans && + conn->c_tos == tos && net == rds_conn_net(conn) && conn->c_dev_if == dev_if) { ret = conn; @@ -160,7 +161,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - gfp_t gfp, + gfp_t gfp, u8 tos, int is_outgoing, int dev_if) { @@ -172,7 +173,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); rcu_read_lock(); - conn = rds_conn_lookup(net, head, laddr, faddr, trans, dev_if); + conn = rds_conn_lookup(net, head, laddr, faddr, trans, tos, dev_if); if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && @@ -206,6 +207,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, conn->c_isv6 = !ipv6_addr_v4mapped(laddr); conn->c_faddr = *faddr; conn->c_dev_if = dev_if; + conn->c_tos = tos; #if IS_ENABLED(CONFIG_IPV6) /* If the local address is link local, set c_bound_if to be the @@ -298,7 +300,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, struct rds_connection *found; found = rds_conn_lookup(net, head, laddr, faddr, trans, - dev_if); + tos, dev_if); if (found) { struct rds_conn_path *cp; int i; @@ -333,10 +335,10 @@ out: struct rds_connection *rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, - struct rds_transport *trans, gfp_t gfp, - int dev_if) + struct rds_transport *trans, u8 tos, + gfp_t gfp, int dev_if) { - return __rds_conn_create(net, laddr, faddr, trans, gfp, 0, dev_if); + return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 0, dev_if); } EXPORT_SYMBOL_GPL(rds_conn_create); @@ -344,9 +346,9 @@ struct rds_connection *rds_conn_create_outgoing(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - gfp_t gfp, int dev_if) + u8 tos, gfp_t gfp, int dev_if) { - return __rds_conn_create(net, laddr, faddr, trans, gfp, 1, dev_if); + return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 1, dev_if); } EXPORT_SYMBOL_GPL(rds_conn_create_outgoing); diff --git a/net/rds/ib.c b/net/rds/ib.c index 9d7b7586f240..21b6588b71ca 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -301,6 +301,7 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, iinfo->src_addr = conn->c_laddr.s6_addr32[3]; iinfo->dst_addr = conn->c_faddr.s6_addr32[3]; + iinfo->tos = conn->c_tos; memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid)); memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid)); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index a1c3ad380ec8..70518e329a9e 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -786,7 +786,7 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, /* RDS/IB is not currently netns aware, thus init_net */ conn = rds_conn_create(&init_net, daddr6, saddr6, - &rds_ib_transport, GFP_KERNEL, ifindex); + &rds_ib_transport, 0, GFP_KERNEL, ifindex); if (IS_ERR(conn)) { rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn)); conn = NULL; diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index 63cbc6b8560c..e37f91537d29 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -115,6 +115,7 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, pr_warn("RDS/RDMA: conn <%pI6c, %pI6c> rejected, dropping connection\n", &conn->c_laddr, &conn->c_faddr); conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION; + conn->c_tos = 0; rds_conn_drop(conn); } rdsdebug("Connection rejected: %s\n", diff --git a/net/rds/rds.h b/net/rds/rds.h index 660023f08553..7e52b92092d7 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -158,6 +158,9 @@ struct rds_connection { unsigned int c_version; possible_net_t c_net; + /* TOS */ + u8 c_tos; + struct list_head c_map_item; unsigned long c_map_queued; @@ -652,6 +655,7 @@ struct rds_sock { u8 rs_rx_traces; u8 rs_rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX]; struct rds_msg_zcopy_queue rs_zcookie_queue; + u8 rs_tos; }; static inline struct rds_sock *rds_sk_to_rs(const struct sock *sk) @@ -760,13 +764,14 @@ void rds_conn_exit(void); struct rds_connection *rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, - struct rds_transport *trans, gfp_t gfp, + struct rds_transport *trans, + u8 tos, gfp_t gfp, int dev_if); struct rds_connection *rds_conn_create_outgoing(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - gfp_t gfp, int dev_if); + u8 tos, gfp_t gfp, int dev_if); void rds_conn_shutdown(struct rds_conn_path *cpath); void rds_conn_destroy(struct rds_connection *conn); void rds_conn_drop(struct rds_connection *conn); diff --git a/net/rds/recv.c b/net/rds/recv.c index 6bb6b16ca270..853de4876088 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -782,6 +782,7 @@ void rds_inc_info_copy(struct rds_incoming *inc, minfo.seq = be64_to_cpu(inc->i_hdr.h_sequence); minfo.len = be32_to_cpu(inc->i_hdr.h_len); + minfo.tos = inc->i_conn->c_tos; if (flip) { minfo.laddr = daddr; diff --git a/net/rds/send.c b/net/rds/send.c index fd8b687d5c05..c555e121b908 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1277,12 +1277,12 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* rds_conn_create has a spinlock that runs with IRQ off. * Caching the conn in the socket helps a lot. */ - if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr)) + if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr)) { conn = rs->rs_conn; - else { + } else { conn = rds_conn_create_outgoing(sock_net(sock->sk), &rs->rs_bound_addr, &daddr, - rs->rs_transport, + rs->rs_transport, 0, sock->sk->sk_allocation, scope_id); if (IS_ERR(conn)) { diff --git a/net/rds/tcp.c b/net/rds/tcp.c index c16f0a362c32..eb6851952cbf 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -267,6 +267,7 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len, tsinfo.last_sent_nxt = tc->t_last_sent_nxt; tsinfo.last_expected_una = tc->t_last_expected_una; tsinfo.last_seen_una = tc->t_last_seen_una; + tsinfo.tos = tc->t_cpath->cp_conn->c_tos; rds_info_copy(iter, &tsinfo, sizeof(tsinfo)); } diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index c12203f646da..810a3a49e947 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -200,7 +200,7 @@ int rds_tcp_accept_one(struct socket *sock) conn = rds_conn_create(sock_net(sock->sk), my_addr, peer_addr, - &rds_tcp_transport, GFP_KERNEL, dev_if); + &rds_tcp_transport, 0, GFP_KERNEL, dev_if); if (IS_ERR(conn)) { ret = PTR_ERR(conn); -- cgit v1.2.3 From f76903d574b26bc596951a5c5e757eb02c67abbd Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Tue, 29 Jan 2019 13:33:11 -0800 Subject: RDMA/IWPM: refactor the IWPM message attribute names In order to add new IWPM_NL attributes, the enums for the IWPM commands attributes are refactored such that a new attribute can be added without breaking ABI version 3. Instead of sharing nl attribute enums for both request and response messages, we create separate enums for each IWPM message request and reply. This allows us to extend any given IWPM message by adding new attributes for just that message. These new enums are created, though, in a way to avoid breaking ABI version 3. Signed-off-by: Steve Wise Reviewed-by: Tatyana Nikolova Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/iwpm_msg.c | 40 ++++++++++++++++++++++---------------- include/uapi/rdma/rdma_netlink.h | 21 +++++++++++++++++--- 2 files changed, 41 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c index 8861c052155a..3a8753595c8f 100644 --- a/drivers/infiniband/core/iwpm_msg.c +++ b/drivers/infiniband/core/iwpm_msg.c @@ -403,10 +403,12 @@ register_pid_response_exit: /* netlink attribute policy for the received response to add mapping request */ static const struct nla_policy resp_add_policy[IWPM_NLA_RMANAGE_MAPPING_MAX] = { - [IWPM_NLA_MANAGE_MAPPING_SEQ] = { .type = NLA_U32 }, - [IWPM_NLA_MANAGE_ADDR] = { .len = sizeof(struct sockaddr_storage) }, - [IWPM_NLA_MANAGE_MAPPED_LOC_ADDR] = { .len = sizeof(struct sockaddr_storage) }, - [IWPM_NLA_RMANAGE_MAPPING_ERR] = { .type = NLA_U16 } + [IWPM_NLA_RMANAGE_MAPPING_SEQ] = { .type = NLA_U32 }, + [IWPM_NLA_RMANAGE_ADDR] = { + .len = sizeof(struct sockaddr_storage) }, + [IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR] = { + .len = sizeof(struct sockaddr_storage) }, + [IWPM_NLA_RMANAGE_MAPPING_ERR] = { .type = NLA_U16 } }; /* @@ -430,7 +432,7 @@ int iwpm_add_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb) atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); - msg_seq = nla_get_u32(nltb[IWPM_NLA_MANAGE_MAPPING_SEQ]); + msg_seq = nla_get_u32(nltb[IWPM_NLA_RMANAGE_MAPPING_SEQ]); nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { pr_info("%s: Could not find a matching request (seq = %u)\n", @@ -439,9 +441,9 @@ int iwpm_add_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb) } pm_msg = nlmsg_request->req_buffer; local_sockaddr = (struct sockaddr_storage *) - nla_data(nltb[IWPM_NLA_MANAGE_ADDR]); + nla_data(nltb[IWPM_NLA_RMANAGE_ADDR]); mapped_sockaddr = (struct sockaddr_storage *) - nla_data(nltb[IWPM_NLA_MANAGE_MAPPED_LOC_ADDR]); + nla_data(nltb[IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR]); if (iwpm_compare_sockaddr(local_sockaddr, &pm_msg->loc_addr)) { nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; @@ -472,11 +474,15 @@ add_mapping_response_exit: /* netlink attribute policy for the response to add and query mapping request * and response with remote address info */ static const struct nla_policy resp_query_policy[IWPM_NLA_RQUERY_MAPPING_MAX] = { - [IWPM_NLA_QUERY_MAPPING_SEQ] = { .type = NLA_U32 }, - [IWPM_NLA_QUERY_LOCAL_ADDR] = { .len = sizeof(struct sockaddr_storage) }, - [IWPM_NLA_QUERY_REMOTE_ADDR] = { .len = sizeof(struct sockaddr_storage) }, - [IWPM_NLA_RQUERY_MAPPED_LOC_ADDR] = { .len = sizeof(struct sockaddr_storage) }, - [IWPM_NLA_RQUERY_MAPPED_REM_ADDR] = { .len = sizeof(struct sockaddr_storage) }, + [IWPM_NLA_RQUERY_MAPPING_SEQ] = { .type = NLA_U32 }, + [IWPM_NLA_RQUERY_LOCAL_ADDR] = { + .len = sizeof(struct sockaddr_storage) }, + [IWPM_NLA_RQUERY_REMOTE_ADDR] = { + .len = sizeof(struct sockaddr_storage) }, + [IWPM_NLA_RQUERY_MAPPED_LOC_ADDR] = { + .len = sizeof(struct sockaddr_storage) }, + [IWPM_NLA_RQUERY_MAPPED_REM_ADDR] = { + .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RQUERY_MAPPING_ERR] = { .type = NLA_U16 } }; @@ -502,7 +508,7 @@ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb, return -EINVAL; atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); - msg_seq = nla_get_u32(nltb[IWPM_NLA_QUERY_MAPPING_SEQ]); + msg_seq = nla_get_u32(nltb[IWPM_NLA_RQUERY_MAPPING_SEQ]); nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { pr_info("%s: Could not find a matching request (seq = %u)\n", @@ -511,9 +517,9 @@ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb, } pm_msg = nlmsg_request->req_buffer; local_sockaddr = (struct sockaddr_storage *) - nla_data(nltb[IWPM_NLA_QUERY_LOCAL_ADDR]); + nla_data(nltb[IWPM_NLA_RQUERY_LOCAL_ADDR]); remote_sockaddr = (struct sockaddr_storage *) - nla_data(nltb[IWPM_NLA_QUERY_REMOTE_ADDR]); + nla_data(nltb[IWPM_NLA_RQUERY_REMOTE_ADDR]); mapped_loc_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR]); mapped_rem_sockaddr = (struct sockaddr_storage *) @@ -588,9 +594,9 @@ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb) atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); local_sockaddr = (struct sockaddr_storage *) - nla_data(nltb[IWPM_NLA_QUERY_LOCAL_ADDR]); + nla_data(nltb[IWPM_NLA_RQUERY_LOCAL_ADDR]); remote_sockaddr = (struct sockaddr_storage *) - nla_data(nltb[IWPM_NLA_QUERY_REMOTE_ADDR]); + nla_data(nltb[IWPM_NLA_RQUERY_REMOTE_ADDR]); mapped_loc_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR]); mapped_rem_sockaddr = (struct sockaddr_storage *) diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h index 2e18b77a817f..42d53e182d5f 100644 --- a/include/uapi/rdma/rdma_netlink.h +++ b/include/uapi/rdma/rdma_netlink.h @@ -83,13 +83,20 @@ enum { IWPM_NLA_MANAGE_MAPPING_UNSPEC = 0, IWPM_NLA_MANAGE_MAPPING_SEQ, IWPM_NLA_MANAGE_ADDR, - IWPM_NLA_MANAGE_MAPPED_LOC_ADDR, + IWPM_NLA_MANAGE_MAPPING_MAX +}; + +enum { + IWPM_NLA_RMANAGE_MAPPING_UNSPEC = 0, + IWPM_NLA_RMANAGE_MAPPING_SEQ, + IWPM_NLA_RMANAGE_ADDR, + IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR, + /* The following maintains bisectability of rdma-core */ + IWPM_NLA_MANAGE_MAPPED_LOC_ADDR = IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR, IWPM_NLA_RMANAGE_MAPPING_ERR, IWPM_NLA_RMANAGE_MAPPING_MAX }; -#define IWPM_NLA_MANAGE_MAPPING_MAX 3 -#define IWPM_NLA_QUERY_MAPPING_MAX 4 #define IWPM_NLA_MAPINFO_SEND_MAX 3 enum { @@ -97,6 +104,14 @@ enum { IWPM_NLA_QUERY_MAPPING_SEQ, IWPM_NLA_QUERY_LOCAL_ADDR, IWPM_NLA_QUERY_REMOTE_ADDR, + IWPM_NLA_QUERY_MAPPING_MAX, +}; + +enum { + IWPM_NLA_RQUERY_MAPPING_UNSPEC = 0, + IWPM_NLA_RQUERY_MAPPING_SEQ, + IWPM_NLA_RQUERY_LOCAL_ADDR, + IWPM_NLA_RQUERY_REMOTE_ADDR, IWPM_NLA_RQUERY_MAPPED_LOC_ADDR, IWPM_NLA_RQUERY_MAPPED_REM_ADDR, IWPM_NLA_RQUERY_MAPPING_ERR, -- cgit v1.2.3 From b0bad9ad514fc1dd8890f1749f5d2425a73270e3 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Tue, 29 Jan 2019 13:33:16 -0800 Subject: RDMA/IWPM: Support no port mapping requirements A soft iwarp driver that uses the host TCP stack via a kernel mode socket does not need port mapping. In fact, if the port map daemon, iwpmd, is running, then iwpmd must not try and create/bind a socket to the actual port for a soft iwarp connection, since the driver already has that socket bound. Yet if the soft iwarp driver wants to interoperate with hard iwarp devices that -are- using port mapping, then the soft iwarp driver's mappings still need to be maintained and advertised by the iwpm protocol. This patch enhances the rdma driver<->iwcm interface to allow an iwarp driver to specify that it does not want port mapping. The iwpm kernel<->iwpmd interface is also enhanced to pass up this information on map requests. Care is taken to interoperate with the current iwpmd version (ABI version 3) and only use the new NL attributes if iwpmd supports ABI version 4. The ABI version define has also been created in rdma_netlink.h so both kernel and user code can share it. The iwcm and iwpmd negotiate the ABI version to use with a new HELLO netlink message. Signed-off-by: Steve Wise Reviewed-by: Tatyana Nikolova Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/iwcm.c | 7 +++- drivers/infiniband/core/iwpm_msg.c | 80 +++++++++++++++++++++++++++++++++++-- drivers/infiniband/core/iwpm_util.c | 48 +++++++++++++++++++++- drivers/infiniband/core/iwpm_util.h | 12 ++++++ include/rdma/iw_cm.h | 13 ++++++ include/rdma/iw_portmap.h | 15 ++++++- include/uapi/rdma/rdma_netlink.h | 24 +++++++++++ 7 files changed, 192 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 476abc74178e..350ea2bab78a 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -87,7 +87,8 @@ static struct rdma_nl_cbs iwcm_nl_cb_table[RDMA_NL_IWPM_NUM_OPS] = { [RDMA_NL_IWPM_REMOTE_INFO] = {.dump = iwpm_remote_info_cb}, [RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb}, [RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb}, - [RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb} + [RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}, + [RDMA_NL_IWPM_HELLO] = {.dump = iwpm_hello_cb} }; static struct workqueue_struct *iwcm_wq; @@ -525,6 +526,8 @@ static int iw_cm_map(struct iw_cm_id *cm_id, bool active) cm_id->mapped = true; pm_msg.loc_addr = cm_id->local_addr; pm_msg.rem_addr = cm_id->remote_addr; + pm_msg.flags = (cm_id->device->iwcm->driver_flags & IW_F_NO_PORT_MAP) ? + IWPM_FLAGS_NO_PORT_MAP : 0; if (active) status = iwpm_add_and_query_mapping(&pm_msg, RDMA_NL_IWCM); @@ -543,7 +546,7 @@ static int iw_cm_map(struct iw_cm_id *cm_id, bool active) return iwpm_create_mapinfo(&cm_id->local_addr, &cm_id->m_local_addr, - RDMA_NL_IWCM); + RDMA_NL_IWCM, pm_msg.flags); } /* diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c index 3a8753595c8f..2e30e65b0816 100644 --- a/drivers/infiniband/core/iwpm_msg.c +++ b/drivers/infiniband/core/iwpm_msg.c @@ -34,7 +34,7 @@ #include "iwpm_util.h" static const char iwpm_ulib_name[IWPM_ULIBNAME_SIZE] = "iWarpPortMapperUser"; -static int iwpm_ulib_version = 3; +u16 iwpm_ulib_version = IWPM_UABI_VERSION_MIN; static int iwpm_user_pid = IWPM_PID_UNDEFINED; static atomic_t echo_nlmsg_seq; @@ -130,6 +130,7 @@ pid_query_error: * nlmsg attributes: * [IWPM_NLA_MANAGE_MAPPING_SEQ] * [IWPM_NLA_MANAGE_ADDR] + * [IWPM_NLA_MANAGE_FLAGS] */ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) { @@ -173,6 +174,18 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) if (ret) goto add_mapping_error; + /* If flags are required and we're not V4, then return a quiet error */ + if (pm_msg->flags && iwpm_ulib_version == IWPM_UABI_VERSION_MIN) { + ret = -EINVAL; + goto add_mapping_error_nowarn; + } + if (iwpm_ulib_version > IWPM_UABI_VERSION_MIN) { + ret = ibnl_put_attr(skb, nlh, sizeof(u32), &pm_msg->flags, + IWPM_NLA_MANAGE_FLAGS); + if (ret) + goto add_mapping_error; + } + nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; @@ -187,6 +200,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) return ret; add_mapping_error: pr_info("%s: %s (client = %d)\n", __func__, err_str, nl_client); +add_mapping_error_nowarn: if (skb) dev_kfree_skb(skb); if (nlmsg_request) @@ -201,6 +215,7 @@ add_mapping_error: * [IWPM_NLA_QUERY_MAPPING_SEQ] * [IWPM_NLA_QUERY_LOCAL_ADDR] * [IWPM_NLA_QUERY_REMOTE_ADDR] + * [IWPM_NLA_QUERY_FLAGS] */ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) { @@ -251,6 +266,18 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) if (ret) goto query_mapping_error; + /* If flags are required and we're not V4, then return a quite error */ + if (pm_msg->flags && iwpm_ulib_version == IWPM_UABI_VERSION_MIN) { + ret = -EINVAL; + goto query_mapping_error_nowarn; + } + if (iwpm_ulib_version > IWPM_UABI_VERSION_MIN) { + ret = ibnl_put_attr(skb, nlh, sizeof(u32), &pm_msg->flags, + IWPM_NLA_QUERY_FLAGS); + if (ret) + goto query_mapping_error; + } + nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; @@ -264,6 +291,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) return ret; query_mapping_error: pr_info("%s: %s (client = %d)\n", __func__, err_str, nl_client); +query_mapping_error_nowarn: if (skb) dev_kfree_skb(skb); if (nlmsg_request) @@ -379,7 +407,7 @@ int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb) /* check device name, ulib name and version */ if (strcmp(pm_msg->dev_name, dev_name) || strcmp(iwpm_ulib_name, iwpm_name) || - iwpm_version != iwpm_ulib_version) { + iwpm_version < IWPM_UABI_VERSION_MIN) { pr_info("%s: Incorrect info (dev = %s name = %s version = %d)\n", __func__, dev_name, iwpm_name, iwpm_version); @@ -387,6 +415,10 @@ int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb) goto register_pid_response_exit; } iwpm_user_pid = cb->nlh->nlmsg_pid; + iwpm_ulib_version = iwpm_version; + if (iwpm_ulib_version < IWPM_UABI_VERSION) + pr_warn_once("%s: Down level iwpmd/pid %u. Continuing...", + __func__, iwpm_user_pid); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n", __func__, iwpm_user_pid); @@ -661,7 +693,7 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) iwpm_name = (char *)nla_data(nltb[IWPM_NLA_MAPINFO_ULIB_NAME]); iwpm_version = nla_get_u16(nltb[IWPM_NLA_MAPINFO_ULIB_VER]); if (strcmp(iwpm_ulib_name, iwpm_name) || - iwpm_version != iwpm_ulib_version) { + iwpm_version < IWPM_UABI_VERSION_MIN) { pr_info("%s: Invalid port mapper name = %s version = %d\n", __func__, iwpm_name, iwpm_version); return ret; @@ -675,6 +707,11 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) iwpm_set_registration(nl_client, IWPM_REG_INCOMPL); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); iwpm_user_pid = cb->nlh->nlmsg_pid; + + if (iwpm_ulib_version < IWPM_UABI_VERSION) + pr_warn_once("%s: Down level iwpmd/pid %u. Continuing...", + __func__, iwpm_user_pid); + if (!iwpm_mapinfo_available()) return 0; pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n", @@ -754,3 +791,40 @@ int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb) up(&nlmsg_request->sem); return 0; } + +/* netlink attribute policy for the received hello request */ +static const struct nla_policy hello_policy[IWPM_NLA_HELLO_MAX] = { + [IWPM_NLA_HELLO_ABI_VERSION] = { .type = NLA_U16 } +}; + +/* + * iwpm_hello_cb - Process a port mapper hello request + */ +int iwpm_hello_cb(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nlattr *nltb[IWPM_NLA_HELLO_MAX]; + const char *msg_type = "Hello request"; + u8 nl_client; + u16 abi_version; + int ret = -EINVAL; + + if (iwpm_parse_nlmsg(cb, IWPM_NLA_HELLO_MAX, hello_policy, nltb, + msg_type)) { + pr_info("%s: Unable to parse nlmsg\n", __func__); + return ret; + } + abi_version = nla_get_u16(nltb[IWPM_NLA_HELLO_ABI_VERSION]); + nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type); + if (!iwpm_valid_client(nl_client)) { + pr_info("%s: Invalid port mapper client = %d\n", + __func__, nl_client); + return ret; + } + iwpm_set_registration(nl_client, IWPM_REG_INCOMPL); + atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); + iwpm_ulib_version = min_t(u16, IWPM_UABI_VERSION, abi_version); + pr_debug("Using ABI version %u\n", iwpm_ulib_version); + iwpm_user_pid = cb->nlh->nlmsg_pid; + ret = iwpm_send_hello(nl_client, iwpm_user_pid, iwpm_ulib_version); + return ret; +} diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c index cdb63f3f4de7..363938435476 100644 --- a/drivers/infiniband/core/iwpm_util.c +++ b/drivers/infiniband/core/iwpm_util.c @@ -114,7 +114,7 @@ static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage *, int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr, struct sockaddr_storage *mapped_sockaddr, - u8 nl_client) + u8 nl_client, u32 map_flags) { struct hlist_head *hash_bucket_head = NULL; struct iwpm_mapping_info *map_info; @@ -132,6 +132,7 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr, memcpy(&map_info->mapped_sockaddr, mapped_sockaddr, sizeof(struct sockaddr_storage)); map_info->nl_client = nl_client; + map_info->map_flags = map_flags; spin_lock_irqsave(&iwpm_mapinfo_lock, flags); if (iwpm_hash_bucket) { @@ -686,6 +687,14 @@ int iwpm_send_mapinfo(u8 nl_client, int iwpm_pid) if (ret) goto send_mapping_info_unlock; + if (iwpm_ulib_version > IWPM_UABI_VERSION_MIN) { + ret = ibnl_put_attr(skb, nlh, sizeof(u32), + &map_info->map_flags, + IWPM_NLA_MAPINFO_FLAGS); + if (ret) + goto send_mapping_info_unlock; + } + nlmsg_end(skb, nlh); iwpm_print_sockaddr(&map_info->local_sockaddr, @@ -754,3 +763,40 @@ int iwpm_mapinfo_available(void) spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags); return full_bucket; } + +int iwpm_send_hello(u8 nl_client, int iwpm_pid, u16 abi_version) +{ + struct sk_buff *skb = NULL; + struct nlmsghdr *nlh; + u32 msg_seq; + const char *err_str = ""; + int ret = -EINVAL; + + skb = iwpm_create_nlmsg(RDMA_NL_IWPM_HELLO, &nlh, nl_client); + if (!skb) { + err_str = "Unable to create a nlmsg"; + goto hello_num_error; + } + nlh->nlmsg_seq = iwpm_get_nlmsg_seq(); + msg_seq = 0; + err_str = "Unable to put attribute of abi_version into nlmsg"; + ret = ibnl_put_attr(skb, nlh, sizeof(u16), &abi_version, + IWPM_NLA_HELLO_ABI_VERSION); + if (ret) + goto hello_num_error; + nlmsg_end(skb, nlh); + + ret = rdma_nl_unicast(skb, iwpm_pid); + if (ret) { + skb = NULL; + err_str = "Unable to send a nlmsg"; + goto hello_num_error; + } + pr_debug("%s: Sent hello abi_version = %u\n", __func__, abi_version); + return 0; +hello_num_error: + pr_info("%s: %s\n", __func__, err_str); + if (skb) + dev_kfree_skb(skb); + return ret; +} diff --git a/drivers/infiniband/core/iwpm_util.h b/drivers/infiniband/core/iwpm_util.h index af1fc14a0d3d..7e2bcc72f66c 100644 --- a/drivers/infiniband/core/iwpm_util.h +++ b/drivers/infiniband/core/iwpm_util.h @@ -78,6 +78,7 @@ struct iwpm_mapping_info { struct sockaddr_storage local_sockaddr; struct sockaddr_storage mapped_sockaddr; u8 nl_client; + u32 map_flags; }; struct iwpm_remote_info { @@ -266,4 +267,15 @@ int iwpm_parse_nlmsg(struct netlink_callback *cb, int policy_max, * @msg: Message to print */ void iwpm_print_sockaddr(struct sockaddr_storage *sockaddr, char *msg); + +/** + * iwpm_send_hello - Send hello response to iwpmd + * + * @nl_client: The index of the netlink client + * @abi_version: The kernel's abi_version + * + * Returns 0 on success or a negative error code + */ +int iwpm_send_hello(u8 nl_client, int iwpm_pid, u16 abi_version); +extern u16 iwpm_ulib_version; #endif diff --git a/include/rdma/iw_cm.h b/include/rdma/iw_cm.h index 5cd7701db148..48512abd3162 100644 --- a/include/rdma/iw_cm.h +++ b/include/rdma/iw_cm.h @@ -105,6 +105,18 @@ struct iw_cm_conn_param { u32 qpn; }; +enum iw_flags { + + /* + * This flag allows the iwcm and iwpmd to still advertise + * mappings but the real and mapped port numbers are the + * same. Further, iwpmd will not bind any user socket to + * reserve the port. This is required for soft iwarp + * to play in the port mapped iwarp space. + */ + IW_F_NO_PORT_MAP = (1 << 0), +}; + struct iw_cm_verbs { void (*add_ref)(struct ib_qp *qp); @@ -127,6 +139,7 @@ struct iw_cm_verbs { int (*destroy_listen)(struct iw_cm_id *cm_id); char ifname[IFNAMSIZ]; + enum iw_flags driver_flags; }; /** diff --git a/include/rdma/iw_portmap.h b/include/rdma/iw_portmap.h index fda31673a562..84fac196ef80 100644 --- a/include/rdma/iw_portmap.h +++ b/include/rdma/iw_portmap.h @@ -58,6 +58,7 @@ struct iwpm_sa_data { struct sockaddr_storage mapped_loc_addr; struct sockaddr_storage rem_addr; struct sockaddr_storage mapped_rem_addr; + u32 flags; }; /** @@ -205,9 +206,11 @@ int iwpm_get_remote_info(struct sockaddr_storage *mapped_loc_addr, * @local_addr: Local ip/tcp address * @mapped_addr: Mapped local ip/tcp address * @nl_client: The index of the netlink client + * @map_flags: IWPM mapping flags */ int iwpm_create_mapinfo(struct sockaddr_storage *local_addr, - struct sockaddr_storage *mapped_addr, u8 nl_client); + struct sockaddr_storage *mapped_addr, u8 nl_client, + u32 map_flags); /** * iwpm_remove_mapinfo - Remove local and mapped IPv4/IPv6 address @@ -221,4 +224,14 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_addr, int iwpm_remove_mapinfo(struct sockaddr_storage *local_addr, struct sockaddr_storage *mapped_addr); +/** + * iwpm_hello_cb - Process a hello message from iwpmd + * + * @skb: + * @cb: Contains the received message (payload and netlink header) + * + * Using the received port mapper pid, send the kernel's abi_version + * after adjusting it to support the iwpmd version. + */ +int iwpm_hello_cb(struct sk_buff *skb, struct netlink_callback *cb); #endif /* _IW_PORTMAP_H */ diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h index 42d53e182d5f..0f5263767fb4 100644 --- a/include/uapi/rdma/rdma_netlink.h +++ b/include/uapi/rdma/rdma_netlink.h @@ -35,6 +35,19 @@ enum { RDMA_NL_RDMA_CM_NUM_ATTR, }; +/* The minimum version that the iwpm kernel supports */ +#define IWPM_UABI_VERSION_MIN 3 + +/* The latest version that the iwpm kernel supports */ +#define IWPM_UABI_VERSION 4 + +/* iwarp port mapper message flags */ +enum { + + /* Do not map the port for this IWPM request */ + IWPM_FLAGS_NO_PORT_MAP = (1 << 0), +}; + /* iwarp port mapper op-codes */ enum { RDMA_NL_IWPM_REG_PID = 0, @@ -45,6 +58,7 @@ enum { RDMA_NL_IWPM_HANDLE_ERR, RDMA_NL_IWPM_MAPINFO, RDMA_NL_IWPM_MAPINFO_NUM, + RDMA_NL_IWPM_HELLO, RDMA_NL_IWPM_NUM_OPS }; @@ -83,6 +97,7 @@ enum { IWPM_NLA_MANAGE_MAPPING_UNSPEC = 0, IWPM_NLA_MANAGE_MAPPING_SEQ, IWPM_NLA_MANAGE_ADDR, + IWPM_NLA_MANAGE_FLAGS, IWPM_NLA_MANAGE_MAPPING_MAX }; @@ -98,12 +113,14 @@ enum { }; #define IWPM_NLA_MAPINFO_SEND_MAX 3 +#define IWPM_NLA_REMOVE_MAPPING_MAX 3 enum { IWPM_NLA_QUERY_MAPPING_UNSPEC = 0, IWPM_NLA_QUERY_MAPPING_SEQ, IWPM_NLA_QUERY_LOCAL_ADDR, IWPM_NLA_QUERY_REMOTE_ADDR, + IWPM_NLA_QUERY_FLAGS, IWPM_NLA_QUERY_MAPPING_MAX, }; @@ -129,6 +146,7 @@ enum { IWPM_NLA_MAPINFO_UNSPEC = 0, IWPM_NLA_MAPINFO_LOCAL_ADDR, IWPM_NLA_MAPINFO_MAPPED_ADDR, + IWPM_NLA_MAPINFO_FLAGS, IWPM_NLA_MAPINFO_MAX }; @@ -147,6 +165,12 @@ enum { IWPM_NLA_ERR_MAX }; +enum { + IWPM_NLA_HELLO_UNSPEC = 0, + IWPM_NLA_HELLO_ABI_VERSION, + IWPM_NLA_HELLO_MAX +}; + /* * Local service operations: * RESOLVE - The client requests the local service to resolve a path. -- cgit v1.2.3 From f80d2f0846b7b9ceb1f2a5951229ee4391edaebd Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 25 Jan 2019 10:34:43 -0800 Subject: scsi: target/core: Remove the write_pending_status() callback function Due to the patch that makes TMF handling synchronous the write_pending_status() callback function is no longer called. Hence remove it. Acked-by: Felipe Balbi Reviewed-by: Sagi Grimberg Reviewed-by: Andy Grover Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Bryant G. Ly Cc: Nicholas Bellinger Cc: Mike Christie Cc: Himanshu Madhani Cc: Quinn Tran Cc: Saurav Kashyap Cc: Michael S. Tsirkin Cc: Juergen Gross Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- Documentation/target/tcm_mod_builder.py | 8 ------- drivers/infiniband/ulp/srpt/ib_srpt.c | 9 -------- drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 6 ------ drivers/scsi/qla2xxx/tcm_qla2xxx.c | 31 ---------------------------- drivers/target/iscsi/iscsi_target_configfs.c | 13 ------------ drivers/target/loopback/tcm_loop.c | 6 ------ drivers/target/sbp/sbp_target.c | 6 ------ drivers/target/target_core_configfs.c | 4 ---- drivers/target/target_core_xcopy.c | 6 ------ drivers/target/tcm_fc/tcm_fc.h | 1 - drivers/target/tcm_fc/tfc_cmd.c | 7 ------- drivers/target/tcm_fc/tfc_conf.c | 1 - drivers/usb/gadget/function/f_tcm.c | 9 -------- drivers/vhost/scsi.c | 6 ------ drivers/xen/xen-scsiback.c | 6 ------ include/target/target_core_fabric.h | 1 - 16 files changed, 120 deletions(-) (limited to 'include') diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py index 94bf6944bb1e..95d6e31f1e3a 100755 --- a/Documentation/target/tcm_mod_builder.py +++ b/Documentation/target/tcm_mod_builder.py @@ -297,7 +297,6 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name): buf += " .sess_get_index = " + fabric_mod_name + "_sess_get_index,\n" buf += " .sess_get_initiator_sid = NULL,\n" buf += " .write_pending = " + fabric_mod_name + "_write_pending,\n" - buf += " .write_pending_status = " + fabric_mod_name + "_write_pending_status,\n" buf += " .set_default_node_attributes = " + fabric_mod_name + "_set_default_node_attrs,\n" buf += " .get_cmd_state = " + fabric_mod_name + "_get_cmd_state,\n" buf += " .queue_data_in = " + fabric_mod_name + "_queue_data_in,\n" @@ -479,13 +478,6 @@ def tcm_mod_dump_fabric_ops(proto_ident, fabric_mod_dir_var, fabric_mod_name): buf += "}\n\n" bufi += "int " + fabric_mod_name + "_write_pending(struct se_cmd *);\n" - if re.search('write_pending_status\)\(', fo): - buf += "int " + fabric_mod_name + "_write_pending_status(struct se_cmd *se_cmd)\n" - buf += "{\n" - buf += " return 0;\n" - buf += "}\n\n" - bufi += "int " + fabric_mod_name + "_write_pending_status(struct se_cmd *);\n" - if re.search('set_default_node_attributes\)\(', fo): buf += "void " + fabric_mod_name + "_set_default_node_attrs(struct se_node_acl *nacl)\n" buf += "{\n" diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index e9c336cff8f5..8cee8c6c6be9 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -2703,14 +2703,6 @@ static int srpt_rdma_cm_handler(struct rdma_cm_id *cm_id, return ret; } -static int srpt_write_pending_status(struct se_cmd *se_cmd) -{ - struct srpt_send_ioctx *ioctx; - - ioctx = container_of(se_cmd, struct srpt_send_ioctx, cmd); - return ioctx->state == SRPT_STATE_NEED_DATA; -} - /* * srpt_write_pending - Start data transfer from initiator to target (write). */ @@ -3806,7 +3798,6 @@ static const struct target_core_fabric_ops srpt_template = { .sess_get_index = srpt_sess_get_index, .sess_get_initiator_sid = NULL, .write_pending = srpt_write_pending, - .write_pending_status = srpt_write_pending_status, .set_default_node_attributes = srpt_set_default_node_attrs, .get_cmd_state = srpt_get_tcm_cmd_state, .queue_data_in = srpt_queue_data_in, diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index cc9cae469c4b..7ca277e28d63 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -3788,11 +3788,6 @@ static int ibmvscsis_write_pending(struct se_cmd *se_cmd) return 0; } -static int ibmvscsis_write_pending_status(struct se_cmd *se_cmd) -{ - return 0; -} - static void ibmvscsis_set_default_node_attrs(struct se_node_acl *nacl) { } @@ -4053,7 +4048,6 @@ static const struct target_core_fabric_ops ibmvscsis_ops = { .release_cmd = ibmvscsis_release_cmd, .sess_get_index = ibmvscsis_sess_get_index, .write_pending = ibmvscsis_write_pending, - .write_pending_status = ibmvscsis_write_pending_status, .set_default_node_attributes = ibmvscsis_set_default_node_attrs, .get_cmd_state = ibmvscsis_get_cmd_state, .queue_data_in = ibmvscsis_queue_data_in, diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 283e6b80abb5..8a3075d17c63 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -420,26 +420,6 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd) return qlt_rdy_to_xfer(cmd); } -static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd) -{ - unsigned long flags; - /* - * Check for WRITE_PENDING status to determine if we need to wait for - * CTIO aborts to be posted via hardware in tcm_qla2xxx_handle_data(). - */ - spin_lock_irqsave(&se_cmd->t_state_lock, flags); - if (se_cmd->t_state == TRANSPORT_WRITE_PENDING || - se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) { - spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); - wait_for_completion_timeout(&se_cmd->t_transport_stop_comp, - 50); - return 0; - } - spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); - - return 0; -} - static void tcm_qla2xxx_set_default_node_attrs(struct se_node_acl *nacl) { return; @@ -537,15 +517,6 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work) cmd->qpair->tgt_counters.qla_core_ret_ctio++; if (!cmd->write_data_transferred) { - /* - * Check if se_cmd has already been aborted via LUN_RESET, and - * waiting upon completion in tcm_qla2xxx_write_pending_status() - */ - if (cmd->se_cmd.transport_state & CMD_T_ABORTED) { - complete(&cmd->se_cmd.t_transport_stop_comp); - return; - } - switch (cmd->dif_err_code) { case DIF_ERR_GRD: cmd->se_cmd.pi_err = @@ -1902,7 +1873,6 @@ static const struct target_core_fabric_ops tcm_qla2xxx_ops = { .sess_get_index = tcm_qla2xxx_sess_get_index, .sess_get_initiator_sid = NULL, .write_pending = tcm_qla2xxx_write_pending, - .write_pending_status = tcm_qla2xxx_write_pending_status, .set_default_node_attributes = tcm_qla2xxx_set_default_node_attrs, .get_cmd_state = tcm_qla2xxx_get_cmd_state, .queue_data_in = tcm_qla2xxx_queue_data_in, @@ -1943,7 +1913,6 @@ static const struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = { .sess_get_index = tcm_qla2xxx_sess_get_index, .sess_get_initiator_sid = NULL, .write_pending = tcm_qla2xxx_write_pending, - .write_pending_status = tcm_qla2xxx_write_pending_status, .set_default_node_attributes = tcm_qla2xxx_set_default_node_attrs, .get_cmd_state = tcm_qla2xxx_get_cmd_state, .queue_data_in = tcm_qla2xxx_queue_data_in, diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index a5481dfeae8d..cac94c94ef5d 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1389,18 +1389,6 @@ static int lio_write_pending(struct se_cmd *se_cmd) return 0; } -static int lio_write_pending_status(struct se_cmd *se_cmd) -{ - struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd); - int ret; - - spin_lock_bh(&cmd->istate_lock); - ret = !(cmd->cmd_flags & ICF_GOT_LAST_DATAOUT); - spin_unlock_bh(&cmd->istate_lock); - - return ret; -} - static int lio_queue_status(struct se_cmd *se_cmd) { struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd); @@ -1564,7 +1552,6 @@ const struct target_core_fabric_ops iscsi_ops = { .sess_get_index = lio_sess_get_index, .sess_get_initiator_sid = lio_sess_get_initiator_sid, .write_pending = lio_write_pending, - .write_pending_status = lio_write_pending_status, .set_default_node_attributes = lio_set_default_node_attributes, .get_cmd_state = iscsi_get_cmd_state, .queue_data_in = lio_queue_data_in, diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 7bd7c0c0db6f..89c6e3719d2b 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -560,11 +560,6 @@ static int tcm_loop_write_pending(struct se_cmd *se_cmd) return 0; } -static int tcm_loop_write_pending_status(struct se_cmd *se_cmd) -{ - return 0; -} - static int tcm_loop_queue_data_in(struct se_cmd *se_cmd) { struct tcm_loop_cmd *tl_cmd = container_of(se_cmd, @@ -1159,7 +1154,6 @@ static const struct target_core_fabric_ops loop_ops = { .release_cmd = tcm_loop_release_cmd, .sess_get_index = tcm_loop_sess_get_index, .write_pending = tcm_loop_write_pending, - .write_pending_status = tcm_loop_write_pending_status, .set_default_node_attributes = tcm_loop_set_default_node_attributes, .get_cmd_state = tcm_loop_get_cmd_state, .queue_data_in = tcm_loop_queue_data_in, diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index 08cee13dfb9a..b0d3583998f0 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -1749,11 +1749,6 @@ static int sbp_write_pending(struct se_cmd *se_cmd) return 0; } -static int sbp_write_pending_status(struct se_cmd *se_cmd) -{ - return 0; -} - static void sbp_set_default_node_attrs(struct se_node_acl *nacl) { return; @@ -2329,7 +2324,6 @@ static const struct target_core_fabric_ops sbp_ops = { .release_cmd = sbp_release_cmd, .sess_get_index = sbp_sess_get_index, .write_pending = sbp_write_pending, - .write_pending_status = sbp_write_pending_status, .set_default_node_attributes = sbp_set_default_node_attrs, .get_cmd_state = sbp_get_cmd_state, .queue_data_in = sbp_queue_data_in, diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 72016d0dfca5..1124c84a3b7f 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -401,10 +401,6 @@ static int target_fabric_tf_ops_check(const struct target_core_fabric_ops *tfo) pr_err("Missing tfo->write_pending()\n"); return -EINVAL; } - if (!tfo->write_pending_status) { - pr_err("Missing tfo->write_pending_status()\n"); - return -EINVAL; - } if (!tfo->set_default_node_attributes) { pr_err("Missing tfo->set_default_node_attributes()\n"); return -EINVAL; diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index c2e1fc927fdf..9be1418e919f 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -442,11 +442,6 @@ static int xcopy_pt_write_pending(struct se_cmd *se_cmd) return 0; } -static int xcopy_pt_write_pending_status(struct se_cmd *se_cmd) -{ - return 0; -} - static int xcopy_pt_queue_data_in(struct se_cmd *se_cmd) { return 0; @@ -463,7 +458,6 @@ static const struct target_core_fabric_ops xcopy_pt_tfo = { .release_cmd = xcopy_pt_release_cmd, .check_stop_free = xcopy_pt_check_stop_free, .write_pending = xcopy_pt_write_pending, - .write_pending_status = xcopy_pt_write_pending_status, .queue_data_in = xcopy_pt_queue_data_in, .queue_status = xcopy_pt_queue_status, }; diff --git a/drivers/target/tcm_fc/tcm_fc.h b/drivers/target/tcm_fc/tcm_fc.h index 11d27b93b413..b8ced4458118 100644 --- a/drivers/target/tcm_fc/tcm_fc.h +++ b/drivers/target/tcm_fc/tcm_fc.h @@ -158,7 +158,6 @@ void ft_release_cmd(struct se_cmd *); int ft_queue_status(struct se_cmd *); int ft_queue_data_in(struct se_cmd *); int ft_write_pending(struct se_cmd *); -int ft_write_pending_status(struct se_cmd *); int ft_get_cmd_state(struct se_cmd *); void ft_queue_tm_resp(struct se_cmd *); void ft_aborted_task(struct se_cmd *); diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index a183d4da7db2..f0529ba58f4c 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -184,13 +184,6 @@ int ft_queue_status(struct se_cmd *se_cmd) return 0; } -int ft_write_pending_status(struct se_cmd *se_cmd) -{ - struct ft_cmd *cmd = container_of(se_cmd, struct ft_cmd, se_cmd); - - return cmd->write_data_len != se_cmd->data_length; -} - /* * Send TX_RDY (transfer ready). */ diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c index 1ce49518d440..c873a052fcb0 100644 --- a/drivers/target/tcm_fc/tfc_conf.c +++ b/drivers/target/tcm_fc/tfc_conf.c @@ -437,7 +437,6 @@ static const struct target_core_fabric_ops ft_fabric_ops = { .sess_get_index = ft_sess_get_index, .sess_get_initiator_sid = NULL, .write_pending = ft_write_pending, - .write_pending_status = ft_write_pending_status, .set_default_node_attributes = ft_set_default_node_attr, .get_cmd_state = ft_get_cmd_state, .queue_data_in = ft_queue_data_in, diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 34f5982cab78..7f01f78b1d23 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1292,14 +1292,6 @@ static u32 usbg_sess_get_index(struct se_session *se_sess) return 0; } -/* - * XXX Error recovery: return != 0 if we expect writes. Dunno when that could be - */ -static int usbg_write_pending_status(struct se_cmd *se_cmd) -{ - return 0; -} - static void usbg_set_default_node_attrs(struct se_node_acl *nacl) { } @@ -1725,7 +1717,6 @@ static const struct target_core_fabric_ops usbg_ops = { .sess_get_index = usbg_sess_get_index, .sess_get_initiator_sid = NULL, .write_pending = usbg_send_write_request, - .write_pending_status = usbg_write_pending_status, .set_default_node_attributes = usbg_set_default_node_attrs, .get_cmd_state = usbg_get_cmd_state, .queue_data_in = usbg_send_read_response, diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 8e10ab436d1f..ad7899f99b97 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -346,11 +346,6 @@ static int vhost_scsi_write_pending(struct se_cmd *se_cmd) return 0; } -static int vhost_scsi_write_pending_status(struct se_cmd *se_cmd) -{ - return 0; -} - static void vhost_scsi_set_default_node_attrs(struct se_node_acl *nacl) { return; @@ -2298,7 +2293,6 @@ static const struct target_core_fabric_ops vhost_scsi_ops = { .sess_get_index = vhost_scsi_sess_get_index, .sess_get_initiator_sid = NULL, .write_pending = vhost_scsi_write_pending, - .write_pending_status = vhost_scsi_write_pending_status, .set_default_node_attributes = vhost_scsi_set_default_node_attrs, .get_cmd_state = vhost_scsi_get_cmd_state, .queue_data_in = vhost_scsi_queue_data_in, diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index c9e23a126218..e59937293a32 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1404,11 +1404,6 @@ static int scsiback_write_pending(struct se_cmd *se_cmd) return 0; } -static int scsiback_write_pending_status(struct se_cmd *se_cmd) -{ - return 0; -} - static void scsiback_set_default_node_attrs(struct se_node_acl *nacl) { } @@ -1818,7 +1813,6 @@ static const struct target_core_fabric_ops scsiback_ops = { .sess_get_index = scsiback_sess_get_index, .sess_get_initiator_sid = NULL, .write_pending = scsiback_write_pending, - .write_pending_status = scsiback_write_pending_status, .set_default_node_attributes = scsiback_set_default_node_attrs, .get_cmd_state = scsiback_get_cmd_state, .queue_data_in = scsiback_queue_data_in, diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index ee5ddd81cd8d..691c6b5e6520 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -74,7 +74,6 @@ struct target_core_fabric_ops { u32 (*sess_get_initiator_sid)(struct se_session *, unsigned char *, u32); int (*write_pending)(struct se_cmd *); - int (*write_pending_status)(struct se_cmd *); void (*set_default_node_attributes)(struct se_node_acl *); int (*get_cmd_state)(struct se_cmd *); int (*queue_data_in)(struct se_cmd *); -- cgit v1.2.3 From 3f0661a492a199b7de2fb63eceba8c79039bff83 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 25 Jan 2019 10:34:44 -0800 Subject: scsi: target/core: Remove several state tests from the TMF code Whether or not a session is being torn down does not affect whether or not SCSI commands are in the task set. Hence remove the "tearing down" checks from the TMF code. The TRANSPORT_ISTATE_PROCESSING check is left out because it is now safe to wait for a command that is in that state. The CMD_T_PRE_EXECUTE is left out because abort processing is postponed until after commands have left the pre-execute state since the patch that makes TMF processing synchronous. See also commit 1c21a48055a6 ("target: Avoid early CMD_T_PRE_EXECUTE failures during ABORT_TASK"). Cc: Nicholas Bellinger Cc: Mike Christie Cc: Christoph Hellwig Cc: Hannes Reinecke Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/target/target_core_tmr.c | 25 ------------------------- drivers/target/target_core_transport.c | 2 -- include/target/target_core_base.h | 1 - 3 files changed, 28 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index ad0061e09d4c..df1ca827de68 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -114,21 +114,6 @@ static bool __target_check_io_state(struct se_cmd *se_cmd, spin_unlock(&se_cmd->t_state_lock); return false; } - if (se_cmd->transport_state & CMD_T_PRE_EXECUTE) { - if (se_cmd->scsi_status) { - pr_debug("Attempted to abort io tag: %llu early failure" - " status: 0x%02x\n", se_cmd->tag, - se_cmd->scsi_status); - spin_unlock(&se_cmd->t_state_lock); - return false; - } - } - if (sess->sess_tearing_down) { - pr_debug("Attempted to abort io tag: %llu already shutdown," - " skipping\n", se_cmd->tag); - spin_unlock(&se_cmd->t_state_lock); - return false; - } se_cmd->transport_state |= CMD_T_ABORTED; if ((tmr_sess != se_cmd->se_sess) && tas) @@ -239,16 +224,6 @@ static void core_tmr_drain_tmr_list( spin_unlock(&sess->sess_cmd_lock); continue; } - if (cmd->t_state == TRANSPORT_ISTATE_PROCESSING) { - spin_unlock(&cmd->t_state_lock); - spin_unlock(&sess->sess_cmd_lock); - continue; - } - if (sess->sess_tearing_down) { - spin_unlock(&cmd->t_state_lock); - spin_unlock(&sess->sess_cmd_lock); - continue; - } cmd->transport_state |= CMD_T_ABORTED; spin_unlock(&cmd->t_state_lock); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index ef9e75b359d4..b25d27e8ca20 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -2056,7 +2056,6 @@ void target_execute_cmd(struct se_cmd *cmd) spin_lock_irq(&cmd->t_state_lock); cmd->t_state = TRANSPORT_PROCESSING; - cmd->transport_state &= ~CMD_T_PRE_EXECUTE; cmd->transport_state |= CMD_T_ACTIVE | CMD_T_SENT; spin_unlock_irq(&cmd->t_state_lock); @@ -2765,7 +2764,6 @@ int target_get_sess_cmd(struct se_cmd *se_cmd, bool ack_kref) ret = -ESHUTDOWN; goto out; } - se_cmd->transport_state |= CMD_T_PRE_EXECUTE; list_add_tail(&se_cmd->se_cmd_list, &se_sess->sess_cmd_list); percpu_ref_get(&se_sess->cmd_count); out: diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 69b7b955902c..19a5bf4214fc 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -502,7 +502,6 @@ struct se_cmd { #define CMD_T_STOP (1 << 5) #define CMD_T_TAS (1 << 10) #define CMD_T_FABRIC_STOP (1 << 11) -#define CMD_T_PRE_EXECUTE (1 << 12) spinlock_t t_state_lock; struct kref cmd_kref; struct completion t_transport_stop_comp; -- cgit v1.2.3 From 94ebb47160085343ecaaeab90fa7ffbb86030613 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 25 Jan 2019 10:34:47 -0800 Subject: scsi: target/core: Add target_send_busy() Introduce a function that sends the SCSI status "BUSY" back to the initiator. The next patch will add a call to this function in the srpt target driver. Reviewed-by: Hannes Reinecke Cc: Nicholas Bellinger Cc: Mike Christie Cc: Christoph Hellwig Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/target/target_core_transport.c | 16 ++++++++++++++++ include/target/target_core_fabric.h | 1 + 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 6471ede00336..e3f7e21e6614 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -3246,6 +3246,22 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd, } EXPORT_SYMBOL(transport_send_check_condition_and_sense); +/** + * target_send_busy - Send SCSI BUSY status back to the initiator + * @cmd: SCSI command for which to send a BUSY reply. + * + * Note: Only call this function if target_submit_cmd*() failed. + */ +int target_send_busy(struct se_cmd *cmd) +{ + WARN_ON_ONCE(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB); + + cmd->scsi_status = SAM_STAT_BUSY; + trace_target_cmd_complete(cmd); + return cmd->se_tfo->queue_status(cmd); +} +EXPORT_SYMBOL(target_send_busy); + static void target_tmr_work(struct work_struct *work) { struct se_cmd *cmd = container_of(work, struct se_cmd, work); diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 691c6b5e6520..8ed90407f062 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -173,6 +173,7 @@ int transport_generic_free_cmd(struct se_cmd *, int); bool transport_wait_for_tasks(struct se_cmd *); int transport_send_check_condition_and_sense(struct se_cmd *, sense_reason_t, int); +int target_send_busy(struct se_cmd *cmd); int target_get_sess_cmd(struct se_cmd *, bool); int target_put_sess_cmd(struct se_cmd *); void target_sess_cmd_list_set_waiting(struct se_session *); -- cgit v1.2.3 From 5468e82f7034f0ae175a3ce075441356099bdaa3 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 4 Feb 2019 11:26:18 +0100 Subject: net: phy: fixed-phy: Drop GPIO from fixed_phy_add() All users of the fixed_phy_add() pass -1 as GPIO number to the fixed phy driver, and all users of fixed_phy_register() pass -1 as GPIO number as well, except for the device tree MDIO bus. Any new users should create a proper device and pass the GPIO as a descriptor associated with the device so delete the GPIO argument from the calls and drop the code looking requesting a GPIO in fixed_phy_add(). In fixed phy_register(), investigate the "fixed-link" node and pick the GPIO descriptor from "link-gpios" if this property exists. Move the corresponding code out of of_mdio.c as the fixed phy code anyways requires OF to be in use. Tested-by: Andrew Lunn Signed-off-by: Linus Walleij Signed-off-by: David S. Miller --- .../networking/device_drivers/stmicro/stmmac.txt | 2 +- arch/m68k/coldfire/m5272.c | 2 +- arch/mips/ar7/platform.c | 4 +- arch/mips/bcm47xx/setup.c | 2 +- drivers/net/dsa/dsa_loop.c | 2 +- drivers/net/ethernet/broadcom/bgmac.c | 2 +- drivers/net/ethernet/broadcom/genet/bcmmii.c | 2 +- drivers/net/phy/fixed_phy.c | 82 ++++++++++++++++------ drivers/net/usb/lan78xx.c | 3 +- drivers/of/of_mdio.c | 9 +-- include/linux/phy_fixed.h | 8 +-- 11 files changed, 72 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/Documentation/networking/device_drivers/stmicro/stmmac.txt b/Documentation/networking/device_drivers/stmicro/stmmac.txt index 2bb07078f535..1ae979fd90d2 100644 --- a/Documentation/networking/device_drivers/stmicro/stmmac.txt +++ b/Documentation/networking/device_drivers/stmicro/stmmac.txt @@ -267,7 +267,7 @@ static struct fixed_phy_status stmmac0_fixed_phy_status = { During the board's device_init we can configure the first MAC for fixed_link by calling: - fixed_phy_add(PHY_POLL, 1, &stmmac0_fixed_phy_status, -1); + fixed_phy_add(PHY_POLL, 1, &stmmac0_fixed_phy_status); and the second one, with a real PHY device attached to the bus, by using the stmmac_mdio_bus_data structure (to provide the id, the reset procedure etc). diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c index ad1185c68df7..6b3ab583c698 100644 --- a/arch/m68k/coldfire/m5272.c +++ b/arch/m68k/coldfire/m5272.c @@ -127,7 +127,7 @@ static struct fixed_phy_status nettel_fixed_phy_status __initdata = { static int __init init_BSP(void) { m5272_uarts_init(); - fixed_phy_add(PHY_POLL, 0, &nettel_fixed_phy_status, -1); + fixed_phy_add(PHY_POLL, 0, &nettel_fixed_phy_status); return 0; } diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c index f09262e0a72f..10ff07b7721e 100644 --- a/arch/mips/ar7/platform.c +++ b/arch/mips/ar7/platform.c @@ -683,7 +683,7 @@ static int __init ar7_register_devices(void) if (ar7_has_high_cpmac()) { res = fixed_phy_add(PHY_POLL, cpmac_high.id, - &fixed_phy_status, -1); + &fixed_phy_status); if (!res) { cpmac_get_mac(1, cpmac_high_data.dev_addr); @@ -696,7 +696,7 @@ static int __init ar7_register_devices(void) } else cpmac_low_data.phy_mask = 0xffffffff; - res = fixed_phy_add(PHY_POLL, cpmac_low.id, &fixed_phy_status, -1); + res = fixed_phy_add(PHY_POLL, cpmac_low.id, &fixed_phy_status); if (!res) { cpmac_get_mac(0, cpmac_low_data.dev_addr); res = platform_device_register(&cpmac_low); diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index fe3773539eff..82627c264964 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -274,7 +274,7 @@ static int __init bcm47xx_register_bus_complete(void) bcm47xx_leds_register(); bcm47xx_workarounds(); - fixed_phy_add(PHY_POLL, 0, &bcm47xx_fixed_phy_status, -1); + fixed_phy_add(PHY_POLL, 0, &bcm47xx_fixed_phy_status); return 0; } device_initcall(bcm47xx_register_bus_complete); diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index 816f34d64736..17482ae09aa5 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -343,7 +343,7 @@ static int __init dsa_loop_init(void) unsigned int i; for (i = 0; i < NUM_FIXED_PHYS; i++) - phydevs[i] = fixed_phy_register(PHY_POLL, &status, -1, NULL); + phydevs[i] = fixed_phy_register(PHY_POLL, &status, NULL); return mdio_driver_register(&dsa_loop_drv); } diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 2d3a44c40221..4632dd5dbad1 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1446,7 +1446,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac) struct phy_device *phy_dev; int err; - phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, -1, NULL); + phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); if (!phy_dev || IS_ERR(phy_dev)) { dev_err(bgmac->dev, "Failed to register fixed PHY device\n"); return -ENODEV; diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index aceb9b7b55bd..51880d83131a 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -525,7 +525,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) .asym_pause = 0, }; - phydev = fixed_phy_register(PHY_POLL, &fphy_status, -1, NULL); + phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); if (!phydev || IS_ERR(phydev)) { dev_err(kdev, "failed to register fixed PHY device\n"); return -ENODEV; diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 47a8cb574c45..f136a23c1a35 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include #include @@ -38,7 +38,7 @@ struct fixed_phy { bool no_carrier; int (*link_update)(struct net_device *, struct fixed_phy_status *); struct list_head node; - int link_gpio; + struct gpio_desc *link_gpiod; }; static struct platform_device *pdev; @@ -67,8 +67,8 @@ EXPORT_SYMBOL_GPL(fixed_phy_change_carrier); static void fixed_phy_update(struct fixed_phy *fp) { - if (!fp->no_carrier && gpio_is_valid(fp->link_gpio)) - fp->status.link = !!gpio_get_value_cansleep(fp->link_gpio); + if (!fp->no_carrier && fp->link_gpiod) + fp->status.link = !!gpiod_get_value_cansleep(fp->link_gpiod); } static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num) @@ -133,9 +133,9 @@ int fixed_phy_set_link_update(struct phy_device *phydev, } EXPORT_SYMBOL_GPL(fixed_phy_set_link_update); -int fixed_phy_add(unsigned int irq, int phy_addr, - struct fixed_phy_status *status, - int link_gpio) +static int fixed_phy_add_gpiod(unsigned int irq, int phy_addr, + struct fixed_phy_status *status, + struct gpio_desc *gpiod) { int ret; struct fixed_mdio_bus *fmb = &platform_fmb; @@ -156,24 +156,19 @@ int fixed_phy_add(unsigned int irq, int phy_addr, fp->addr = phy_addr; fp->status = *status; - fp->link_gpio = link_gpio; - - if (gpio_is_valid(fp->link_gpio)) { - ret = gpio_request_one(fp->link_gpio, GPIOF_DIR_IN, - "fixed-link-gpio-link"); - if (ret) - goto err_regs; - } + fp->link_gpiod = gpiod; fixed_phy_update(fp); list_add_tail(&fp->node, &fmb->phys); return 0; +} -err_regs: - kfree(fp); - return ret; +int fixed_phy_add(unsigned int irq, int phy_addr, + struct fixed_phy_status *status) { + + return fixed_phy_add_gpiod(irq, phy_addr, status, NULL); } EXPORT_SYMBOL_GPL(fixed_phy_add); @@ -187,8 +182,8 @@ static void fixed_phy_del(int phy_addr) list_for_each_entry_safe(fp, tmp, &fmb->phys, node) { if (fp->addr == phy_addr) { list_del(&fp->node); - if (gpio_is_valid(fp->link_gpio)) - gpio_free(fp->link_gpio); + if (fp->link_gpiod) + gpiod_put(fp->link_gpiod); kfree(fp); ida_simple_remove(&phy_fixed_ida, phy_addr); return; @@ -196,12 +191,50 @@ static void fixed_phy_del(int phy_addr) } } +#ifdef CONFIG_OF_GPIO +static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np) +{ + struct device_node *fixed_link_node; + struct gpio_desc *gpiod; + + if (!np) + return NULL; + + fixed_link_node = of_get_child_by_name(np, "fixed-link"); + if (!fixed_link_node) + return NULL; + + /* + * As the fixed link is just a device tree node without any + * Linux device associated with it, we simply have obtain + * the GPIO descriptor from the device tree like this. + */ + gpiod = gpiod_get_from_of_node(fixed_link_node, "link-gpios", 0, + GPIOD_IN, "mdio"); + of_node_put(fixed_link_node); + if (IS_ERR(gpiod)) { + if (PTR_ERR(gpiod) == -EPROBE_DEFER) + return gpiod; + pr_err("error getting GPIO for fixed link %pOF, proceed without\n", + fixed_link_node); + gpiod = NULL; + } + + return gpiod; +} +#else +static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np) +{ + return NULL; +} +#endif + struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, - int link_gpio, struct device_node *np) { struct fixed_mdio_bus *fmb = &platform_fmb; + struct gpio_desc *gpiod = NULL; struct phy_device *phy; int phy_addr; int ret; @@ -209,12 +242,17 @@ struct phy_device *fixed_phy_register(unsigned int irq, if (!fmb->mii_bus || fmb->mii_bus->state != MDIOBUS_REGISTERED) return ERR_PTR(-EPROBE_DEFER); + /* Check if we have a GPIO associated with this fixed phy */ + gpiod = fixed_phy_get_gpiod(np); + if (IS_ERR(gpiod)) + return ERR_CAST(gpiod); + /* Get the next available PHY address, up to PHY_MAX_ADDR */ phy_addr = ida_simple_get(&phy_fixed_ida, 0, PHY_MAX_ADDR, GFP_KERNEL); if (phy_addr < 0) return ERR_PTR(phy_addr); - ret = fixed_phy_add(irq, phy_addr, status, link_gpio); + ret = fixed_phy_add_gpiod(irq, phy_addr, status, gpiod); if (ret < 0) { ida_simple_remove(&phy_fixed_ida, phy_addr); return ERR_PTR(ret); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index e96bc0c6140f..3d92ea6fcc02 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2051,8 +2051,7 @@ static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev) phydev = phy_find_first(dev->mdiobus); if (!phydev) { netdev_dbg(dev->net, "PHY Not Found!! Registering Fixed PHY\n"); - phydev = fixed_phy_register(PHY_POLL, &fphy_status, -1, - NULL); + phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); if (IS_ERR(phydev)) { netdev_err(dev->net, "No PHY/fixed_PHY found\n"); return NULL; diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 5ad1342f5682..de6157357e26 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -463,7 +462,6 @@ int of_phy_register_fixed_link(struct device_node *np) struct device_node *fixed_link_node; u32 fixed_link_prop[5]; const char *managed; - int link_gpio = -1; if (of_property_read_string(np, "managed", &managed) == 0 && strcmp(managed, "in-band-status") == 0) { @@ -485,11 +483,7 @@ int of_phy_register_fixed_link(struct device_node *np) status.pause = of_property_read_bool(fixed_link_node, "pause"); status.asym_pause = of_property_read_bool(fixed_link_node, "asym-pause"); - link_gpio = of_get_named_gpio_flags(fixed_link_node, - "link-gpios", 0, NULL); of_node_put(fixed_link_node); - if (link_gpio == -EPROBE_DEFER) - return -EPROBE_DEFER; goto register_phy; } @@ -508,8 +502,7 @@ int of_phy_register_fixed_link(struct device_node *np) return -ENODEV; register_phy: - return PTR_ERR_OR_ZERO(fixed_phy_register(PHY_POLL, &status, link_gpio, - np)); + return PTR_ERR_OR_ZERO(fixed_phy_register(PHY_POLL, &status, np)); } EXPORT_SYMBOL(of_phy_register_fixed_link); diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index 9525567b1951..c78fc203db43 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -15,11 +15,9 @@ struct device_node; #if IS_ENABLED(CONFIG_FIXED_PHY) extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier); extern int fixed_phy_add(unsigned int irq, int phy_id, - struct fixed_phy_status *status, - int link_gpio); + struct fixed_phy_status *status); extern struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, - int link_gpio, struct device_node *np); extern void fixed_phy_unregister(struct phy_device *phydev); extern int fixed_phy_set_link_update(struct phy_device *phydev, @@ -27,14 +25,12 @@ extern int fixed_phy_set_link_update(struct phy_device *phydev, struct fixed_phy_status *)); #else static inline int fixed_phy_add(unsigned int irq, int phy_id, - struct fixed_phy_status *status, - int link_gpio) + struct fixed_phy_status *status) { return -ENODEV; } static inline struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, - int gpio_link, struct device_node *np) { return ERR_PTR(-ENODEV); -- cgit v1.2.3 From 0300b1147e528fe6f6b0632b0ef353a87810dabf Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 25 Jan 2019 10:34:54 -0800 Subject: scsi: target/iscsi: Fix spelling of "unsolicited" Change "unsoliticed" into "unsolicited". Cc: Nicholas Bellinger Cc: Mike Christie Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Sagi Grimberg Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/infiniband/ulp/isert/ib_isert.c | 2 +- drivers/target/iscsi/cxgbit/cxgbit_target.c | 2 +- drivers/target/iscsi/iscsi_target.c | 8 ++++---- drivers/target/iscsi/iscsi_target.h | 2 +- drivers/target/iscsi/iscsi_target_erl1.c | 2 +- include/target/iscsi/iscsi_transport.h | 2 +- 6 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index e3dd13798d79..989f1ac4245c 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -1186,7 +1186,7 @@ sequence_cmd: rc = iscsit_sequence_cmd(conn, cmd, buf, hdr->cmdsn); if (!rc && dump_payload == false && unsol_data) - iscsit_set_unsoliticed_dataout(cmd); + iscsit_set_unsolicited_dataout(cmd); else if (dump_payload && imm_data) target_put_sess_cmd(&cmd->se_cmd); diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c index 25eb3891e34b..29b350a0b58f 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_target.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -960,7 +960,7 @@ after_immediate_data: target_put_sess_cmd(&cmd->se_cmd); return 0; } else if (cmd->unsolicited_data) { - iscsit_set_unsoliticed_dataout(cmd); + iscsit_set_unsolicited_dataout(cmd); } } else if (immed_ret == IMMEDIATE_DATA_ERL1_CRC_FAILURE) { diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 98984c3adfba..7059ffdb0c20 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1194,7 +1194,7 @@ attach_cmd: } EXPORT_SYMBOL(iscsit_setup_scsi_cmd); -void iscsit_set_unsoliticed_dataout(struct iscsi_cmd *cmd) +void iscsit_set_unsolicited_dataout(struct iscsi_cmd *cmd) { iscsit_set_dataout_sequence_values(cmd); @@ -1202,7 +1202,7 @@ void iscsit_set_unsoliticed_dataout(struct iscsi_cmd *cmd) iscsit_start_dataout_timer(cmd, cmd->conn); spin_unlock_bh(&cmd->dataout_timeout_lock); } -EXPORT_SYMBOL(iscsit_set_unsoliticed_dataout); +EXPORT_SYMBOL(iscsit_set_unsolicited_dataout); int iscsit_process_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr) @@ -1236,7 +1236,7 @@ int iscsit_process_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, */ if (!cmd->immediate_data) { if (!cmd->sense_reason && cmd->unsolicited_data) - iscsit_set_unsoliticed_dataout(cmd); + iscsit_set_unsolicited_dataout(cmd); if (!cmd->sense_reason) return 0; @@ -1308,7 +1308,7 @@ after_immediate_data: target_put_sess_cmd(&cmd->se_cmd); return rc; } else if (cmd->unsolicited_data) - iscsit_set_unsoliticed_dataout(cmd); + iscsit_set_unsolicited_dataout(cmd); } else if (immed_ret == IMMEDIATE_DATA_ERL1_CRC_FAILURE) { /* diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h index 48bac0acf8c7..c95f56a3ce31 100644 --- a/drivers/target/iscsi/iscsi_target.h +++ b/drivers/target/iscsi/iscsi_target.h @@ -31,7 +31,7 @@ extern int iscsit_reset_np_thread(struct iscsi_np *, struct iscsi_tpg_np *, struct iscsi_portal_group *, bool); extern int iscsit_del_np(struct iscsi_np *); extern int iscsit_reject_cmd(struct iscsi_cmd *cmd, u8, unsigned char *); -extern void iscsit_set_unsoliticed_dataout(struct iscsi_cmd *); +extern void iscsit_set_unsolicited_dataout(struct iscsi_cmd *); extern int iscsit_logout_closesession(struct iscsi_cmd *, struct iscsi_conn *); extern int iscsit_logout_closeconnection(struct iscsi_cmd *, struct iscsi_conn *); extern int iscsit_logout_removeconnforrecovery(struct iscsi_cmd *, struct iscsi_conn *); diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c index 38210ab09887..c27335c29640 100644 --- a/drivers/target/iscsi/iscsi_target_erl1.c +++ b/drivers/target/iscsi/iscsi_target_erl1.c @@ -979,7 +979,7 @@ int iscsit_execute_cmd(struct iscsi_cmd *cmd, int ooo) if (cmd->se_cmd.transport_state & CMD_T_ABORTED) return 0; - iscsit_set_unsoliticed_dataout(cmd); + iscsit_set_unsolicited_dataout(cmd); } return transport_handle_cdb_direct(&cmd->se_cmd); diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 91948bc5b185..8b4b8ce2c1ae 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -53,7 +53,7 @@ extern void iscsit_put_transport(struct iscsit_transport *); */ extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *, unsigned char *); -extern void iscsit_set_unsoliticed_dataout(struct iscsi_cmd *); +extern void iscsit_set_unsolicited_dataout(struct iscsi_cmd *); extern int iscsit_process_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *, struct iscsi_scsi_req *); extern int -- cgit v1.2.3 From 1e65cc1631c187c4607e9a2067769791be529ce6 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 25 Jan 2019 10:34:55 -0800 Subject: scsi: target/iscsi: Rename a function and a function pointer Having both a function and a function pointer member with the same name (iscsit_release_cmd) is confusing. Hence rename the function pointer member. Cc: Nicholas Bellinger Cc: Mike Christie Cc: Christoph Hellwig Cc: Hannes Reinecke Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/target/iscsi/cxgbit/cxgbit.h | 2 +- drivers/target/iscsi/cxgbit/cxgbit_ddp.c | 2 +- drivers/target/iscsi/cxgbit/cxgbit_main.c | 2 +- drivers/target/iscsi/iscsi_target_util.c | 4 ++-- include/target/iscsi/iscsi_transport.h | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/target/iscsi/cxgbit/cxgbit.h b/drivers/target/iscsi/cxgbit/cxgbit.h index 417b9e66b0cd..3cca22e19964 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit.h +++ b/drivers/target/iscsi/cxgbit/cxgbit.h @@ -345,7 +345,7 @@ struct cxgbit_device *cxgbit_find_device(struct net_device *, u8 *); int cxgbit_ddp_init(struct cxgbit_device *); int cxgbit_setup_conn_pgidx(struct cxgbit_sock *, u32); int cxgbit_reserve_ttt(struct cxgbit_sock *, struct iscsi_cmd *); -void cxgbit_release_cmd(struct iscsi_conn *, struct iscsi_cmd *); +void cxgbit_unmap_cmd(struct iscsi_conn *, struct iscsi_cmd *); static inline struct cxgbi_ppm *cdev2ppm(struct cxgbit_device *cdev) diff --git a/drivers/target/iscsi/cxgbit/cxgbit_ddp.c b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c index 76a262674c8d..d57fd3ed3fa5 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_ddp.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c @@ -263,7 +263,7 @@ out: r2t->targ_xfer_tag = ttinfo->tag; } -void cxgbit_release_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd) +void cxgbit_unmap_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd) { struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd); diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c index c011c826fc26..4a7bb0b49d17 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_main.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -678,7 +678,7 @@ static struct iscsit_transport cxgbit_transport = { .iscsit_get_r2t_ttt = cxgbit_get_r2t_ttt, .iscsit_get_rx_pdu = cxgbit_get_rx_pdu, .iscsit_validate_params = cxgbit_validate_params, - .iscsit_release_cmd = cxgbit_release_cmd, + .iscsit_unmap_cmd = cxgbit_unmap_cmd, .iscsit_aborted_task = iscsit_aborted_task, .iscsit_get_sup_prot_ops = cxgbit_get_sup_prot_ops, }; diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 58886d4b33cb..3ac494f63a0b 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -760,8 +760,8 @@ void __iscsit_free_cmd(struct iscsi_cmd *cmd, bool check_queues) iscsit_remove_cmd_from_response_queue(cmd, conn); } - if (conn && conn->conn_transport->iscsit_release_cmd) - conn->conn_transport->iscsit_release_cmd(conn, cmd); + if (conn && conn->conn_transport->iscsit_unmap_cmd) + conn->conn_transport->iscsit_unmap_cmd(conn, cmd); } void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown) diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 8b4b8ce2c1ae..75bee29fd7dd 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -26,7 +26,7 @@ struct iscsit_transport { void (*iscsit_aborted_task)(struct iscsi_conn *, struct iscsi_cmd *); int (*iscsit_xmit_pdu)(struct iscsi_conn *, struct iscsi_cmd *, struct iscsi_datain_req *, const void *, u32); - void (*iscsit_release_cmd)(struct iscsi_conn *, struct iscsi_cmd *); + void (*iscsit_unmap_cmd)(struct iscsi_conn *, struct iscsi_cmd *); void (*iscsit_get_rx_pdu)(struct iscsi_conn *); int (*iscsit_validate_params)(struct iscsi_conn *); void (*iscsit_get_r2t_ttt)(struct iscsi_conn *, struct iscsi_cmd *, -- cgit v1.2.3 From 809ab9371ca0a96b44d9866ad82849410759a45b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 26 Jan 2019 00:52:26 -0500 Subject: XArray: Update xa_erase family descriptions xa_erase does not allocate memory and doesn't have a gfp parameter. Update the descriptions of all four variants to be more useful. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 12 ++++++------ lib/xarray.c | 17 ++++++++--------- 2 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 5d9d318bcf7a..e11841537631 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -526,9 +526,9 @@ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, * @xa: XArray. * @index: Index of entry. * - * This function is the equivalent of calling xa_store() with %NULL as - * the third argument. The XArray does not need to allocate memory, so - * the user does not need to provide GFP flags. + * After this function returns, loading from @index will return %NULL. + * If the index is part of a multi-index entry, all indices will be erased + * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. @@ -550,9 +550,9 @@ static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) * @xa: XArray. * @index: Index of entry. * - * This function is the equivalent of calling xa_store() with %NULL as - * the third argument. The XArray does not need to allocate memory, so - * the user does not need to provide GFP flags. + * After this function returns, loading from @index will return %NULL. + * If the index is part of a multi-index entry, all indices will be erased + * and none of the entries will be part of a multi-index entry. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. diff --git a/lib/xarray.c b/lib/xarray.c index 81c3171ddde9..fb783bf2a441 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1294,13 +1294,12 @@ static void *xas_result(struct xa_state *xas, void *curr) * @xa: XArray. * @index: Index into array. * - * If the entry at this index is a multi-index entry then all indices will - * be erased, and the entry will no longer be a multi-index entry. - * This function expects the xa_lock to be held on entry. + * After this function returns, loading from @index will return %NULL. + * If the index is part of a multi-index entry, all indices will be erased + * and none of the entries will be part of a multi-index entry. * - * Context: Any context. Expects xa_lock to be held on entry. May - * release and reacquire xa_lock if @gfp flags permit. - * Return: The old entry at this index. + * Context: Any context. Expects xa_lock to be held on entry. + * Return: The entry which used to be at this index. */ void *__xa_erase(struct xarray *xa, unsigned long index) { @@ -1314,9 +1313,9 @@ EXPORT_SYMBOL(__xa_erase); * @xa: XArray. * @index: Index of entry. * - * This function is the equivalent of calling xa_store() with %NULL as - * the third argument. The XArray does not need to allocate memory, so - * the user does not need to provide GFP flags. + * After this function returns, loading from @index will return %NULL. + * If the index is part of a multi-index entry, all indices will be erased + * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock. * Return: The entry which used to be at this index. -- cgit v1.2.3 From fe6f42cf6eb3183ebd6ab6b0b7dcbee2600c2baa Mon Sep 17 00:00:00 2001 From: Nava kishore Manne Date: Wed, 6 Feb 2019 16:37:19 +0530 Subject: firmware: xilinx: Add zynqmp_pm_get_chipid() API This patch adds a new API to provide access to the hardware related data like soc revision, IDCODE... etc. Signed-off-by: Nava kishore Manne Signed-off-by: Michal Simek --- drivers/firmware/xilinx/zynqmp.c | 24 ++++++++++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 2 ++ 2 files changed, 26 insertions(+) (limited to 'include') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 70b50377ae5f..16a23bc4c2c3 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -186,6 +186,29 @@ static int zynqmp_pm_get_api_version(u32 *version) return ret; } +/** + * zynqmp_pm_get_chipid - Get silicon ID registers + * @idcode: IDCODE register + * @version: version register + * + * Return: Returns the status of the operation and the idcode and version + * registers in @idcode and @version. + */ +static int zynqmp_pm_get_chipid(u32 *idcode, u32 *version) +{ + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + if (!idcode || !version) + return -EINVAL; + + ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, 0, 0, 0, 0, ret_payload); + *idcode = ret_payload[1]; + *version = ret_payload[2]; + + return ret; +} + /** * zynqmp_pm_get_trustzone_version() - Get secure trustzone firmware version * @version: Returned version value @@ -509,6 +532,7 @@ static int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, static const struct zynqmp_eemi_ops eemi_ops = { .get_api_version = zynqmp_pm_get_api_version, + .get_chipid = zynqmp_pm_get_chipid, .query_data = zynqmp_pm_query_data, .clock_enable = zynqmp_pm_clock_enable, .clock_disable = zynqmp_pm_clock_disable, diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 07c587a0b06e..5a1f19848100 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -36,6 +36,7 @@ enum pm_api_id { PM_GET_API_VERSION = 1, PM_RESET_ASSERT = 17, PM_RESET_GET_STATUS, + PM_GET_CHIPID = 24, PM_IOCTL = 34, PM_QUERY_DATA, PM_CLOCK_ENABLE, @@ -224,6 +225,7 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*get_api_version)(u32 *version); + int (*get_chipid)(u32 *idcode, u32 *version); int (*query_data)(struct zynqmp_pm_query_data qdata, u32 *out); int (*clock_enable)(u32 clock_id); int (*clock_disable)(u32 clock_id); -- cgit v1.2.3 From 2292822e1576c89191a65c3d0da584d75d3c033f Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 19 Jan 2019 13:16:53 +0100 Subject: i2c: algo-bit: include main i2c header We are using symbols from it, so we should include it directly. Found after sorting includes in a driver. Signed-off-by: Wolfram Sang Reviewed-by: Simon Horman Signed-off-by: Wolfram Sang --- include/linux/i2c-algo-bit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/i2c-algo-bit.h b/include/linux/i2c-algo-bit.h index 63904ba6887e..d64cebc6e65a 100644 --- a/include/linux/i2c-algo-bit.h +++ b/include/linux/i2c-algo-bit.h @@ -25,6 +25,8 @@ #ifndef _LINUX_I2C_ALGO_BIT_H #define _LINUX_I2C_ALGO_BIT_H +#include + /* --- Defines for bit-adapters --------------------------------------- */ /* * This struct contains the hw-dependent functions of bit-style adapters to -- cgit v1.2.3 From 738ac0679b969776a638daf2cfb5011049d467da Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 19 Jan 2019 13:16:54 +0100 Subject: i2c: algo-bit: convert to SPDX header And use kernel style for the remaining comments in the header. Signed-off-by: Wolfram Sang Reviewed-by: Simon Horman Signed-off-by: Wolfram Sang --- drivers/i2c/algos/i2c-algo-bit.c | 25 ++++++++----------------- include/linux/i2c-algo-bit.h | 31 ++++++++----------------------- 2 files changed, 16 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c index c33dcfb87993..5e5990a83da5 100644 --- a/drivers/i2c/algos/i2c-algo-bit.c +++ b/drivers/i2c/algos/i2c-algo-bit.c @@ -1,21 +1,12 @@ -/* ------------------------------------------------------------------------- - * i2c-algo-bit.c i2c driver algorithms for bit-shift adapters - * ------------------------------------------------------------------------- +// SPDX-License-Identifier: GPL-2.0+ +/* + * i2c-algo-bit.c: i2c driver algorithms for bit-shift adapters + * * Copyright (C) 1995-2000 Simon G. Vogl - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - * ------------------------------------------------------------------------- */ - -/* With some changes from Frodo Looijaard , Kyösti Mälkki - and Jean Delvare */ + * + * With some changes from Frodo Looijaard , Kyösti Mälkki + * and Jean Delvare + */ #include #include diff --git a/include/linux/i2c-algo-bit.h b/include/linux/i2c-algo-bit.h index d64cebc6e65a..69045df78e2d 100644 --- a/include/linux/i2c-algo-bit.h +++ b/include/linux/i2c-algo-bit.h @@ -1,26 +1,11 @@ -/* ------------------------------------------------------------------------- */ -/* i2c-algo-bit.h i2c driver algorithms for bit-shift adapters */ -/* ------------------------------------------------------------------------- */ -/* Copyright (C) 1995-99 Simon G. Vogl - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - MA 02110-1301 USA. */ -/* ------------------------------------------------------------------------- */ - -/* With some changes from Kyösti Mälkki and even - Frodo Looijaard */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * i2c-algo-bit.h: i2c driver algorithms for bit-shift adapters + * + * Copyright (C) 1995-99 Simon G. Vogl + * With some changes from Kyösti Mälkki and even + * Frodo Looijaard + */ #ifndef _LINUX_I2C_ALGO_BIT_H #define _LINUX_I2C_ALGO_BIT_H -- cgit v1.2.3 From b525903c254dab2491410f0f23707691b7c2c317 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Thu, 31 Jan 2019 14:53:58 +0000 Subject: genirq: Provide basic NMI management for interrupt lines Add functionality to allocate interrupt lines that will deliver IRQs as Non-Maskable Interrupts. These allocations are only successful if the irqchip provides the necessary support and allows NMI delivery for the interrupt line. Interrupt lines allocated for NMI delivery must be enabled/disabled through enable_nmi/disable_nmi_nosync to keep their state consistent. To treat a PERCPU IRQ as NMI, the interrupt must not be shared nor threaded, the irqchip directly managing the IRQ must be the root irqchip and the irqchip cannot be behind a slow bus. Signed-off-by: Julien Thierry Reviewed-by: Marc Zyngier Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Marc Zyngier Signed-off-by: Marc Zyngier --- include/linux/interrupt.h | 9 ++ include/linux/irq.h | 7 ++ kernel/irq/debugfs.c | 6 +- kernel/irq/internals.h | 2 + kernel/irq/manage.c | 228 +++++++++++++++++++++++++++++++++++++++++++++- 5 files changed, 249 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index c672f34235e7..9941d1a8d83c 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -156,6 +156,10 @@ __request_percpu_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *devname, void __percpu *percpu_dev_id); +extern int __must_check +request_nmi(unsigned int irq, irq_handler_t handler, unsigned long flags, + const char *name, void *dev); + static inline int __must_check request_percpu_irq(unsigned int irq, irq_handler_t handler, const char *devname, void __percpu *percpu_dev_id) @@ -167,6 +171,8 @@ request_percpu_irq(unsigned int irq, irq_handler_t handler, extern const void *free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); +extern const void *free_nmi(unsigned int irq, void *dev_id); + struct device; extern int __must_check @@ -217,6 +223,9 @@ extern void enable_percpu_irq(unsigned int irq, unsigned int type); extern bool irq_percpu_is_enabled(unsigned int irq); extern void irq_wake_thread(unsigned int irq, void *dev_id); +extern void disable_nmi_nosync(unsigned int irq); +extern void enable_nmi(unsigned int irq); + /* The following three functions are for the core kernel use only. */ extern void suspend_device_irqs(void); extern void resume_device_irqs(void); diff --git a/include/linux/irq.h b/include/linux/irq.h index def2b2aac8b1..a7298e4998c8 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -442,6 +442,8 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @irq_set_vcpu_affinity: optional to target a vCPU in a virtual machine * @ipi_send_single: send a single IPI to destination cpus * @ipi_send_mask: send an IPI to destination cpus in cpumask + * @irq_nmi_setup: function called from core code before enabling an NMI + * @irq_nmi_teardown: function called from core code after disabling an NMI * @flags: chip specific flags */ struct irq_chip { @@ -490,6 +492,9 @@ struct irq_chip { void (*ipi_send_single)(struct irq_data *data, unsigned int cpu); void (*ipi_send_mask)(struct irq_data *data, const struct cpumask *dest); + int (*irq_nmi_setup)(struct irq_data *data); + void (*irq_nmi_teardown)(struct irq_data *data); + unsigned long flags; }; @@ -505,6 +510,7 @@ struct irq_chip { * IRQCHIP_ONESHOT_SAFE: One shot does not require mask/unmask * IRQCHIP_EOI_THREADED: Chip requires eoi() on unmask in threaded mode * IRQCHIP_SUPPORTS_LEVEL_MSI Chip can provide two doorbells for Level MSIs + * IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -515,6 +521,7 @@ enum { IRQCHIP_ONESHOT_SAFE = (1 << 5), IRQCHIP_EOI_THREADED = (1 << 6), IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), + IRQCHIP_SUPPORTS_NMI = (1 << 8), }; #include diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 6f636136cccc..59a04d2a66df 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -56,6 +56,7 @@ static const struct irq_bit_descr irqchip_flags[] = { BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE), BIT_MASK_DESCR(IRQCHIP_EOI_THREADED), BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI), + BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI), }; static void @@ -140,6 +141,7 @@ static const struct irq_bit_descr irqdesc_istates[] = { BIT_MASK_DESCR(IRQS_WAITING), BIT_MASK_DESCR(IRQS_PENDING), BIT_MASK_DESCR(IRQS_SUSPENDED), + BIT_MASK_DESCR(IRQS_NMI), }; @@ -203,8 +205,8 @@ static ssize_t irq_debug_write(struct file *file, const char __user *user_buf, chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); - if (irq_settings_is_level(desc)) { - /* Can't do level, sorry */ + if (irq_settings_is_level(desc) || desc->istate & IRQS_NMI) { + /* Can't do level nor NMIs, sorry */ err = -EINVAL; } else { desc->istate |= IRQS_PENDING; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index ca6afa267070..2a77cdd27ca9 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -49,6 +49,7 @@ enum { * IRQS_WAITING - irq is waiting * IRQS_PENDING - irq is pending and replayed later * IRQS_SUSPENDED - irq is suspended + * IRQS_NMI - irq line is used to deliver NMIs */ enum { IRQS_AUTODETECT = 0x00000001, @@ -60,6 +61,7 @@ enum { IRQS_PENDING = 0x00000200, IRQS_SUSPENDED = 0x00000800, IRQS_TIMINGS = 0x00001000, + IRQS_NMI = 0x00002000, }; #include "debug.h" diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index a4888ce4667a..9472ae987946 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -341,7 +341,7 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) /* The release function is promised process context */ might_sleep(); - if (!desc) + if (!desc || desc->istate & IRQS_NMI) return -EINVAL; /* Complete initialisation of *notify */ @@ -550,6 +550,21 @@ bool disable_hardirq(unsigned int irq) } EXPORT_SYMBOL_GPL(disable_hardirq); +/** + * disable_nmi_nosync - disable an nmi without waiting + * @irq: Interrupt to disable + * + * Disable the selected interrupt line. Disables and enables are + * nested. + * The interrupt to disable must have been requested through request_nmi. + * Unlike disable_nmi(), this function does not ensure existing + * instances of the IRQ handler have completed before returning. + */ +void disable_nmi_nosync(unsigned int irq) +{ + disable_irq_nosync(irq); +} + void __enable_irq(struct irq_desc *desc) { switch (desc->depth) { @@ -606,6 +621,20 @@ out: } EXPORT_SYMBOL(enable_irq); +/** + * enable_nmi - enable handling of an nmi + * @irq: Interrupt to enable + * + * The interrupt to enable must have been requested through request_nmi. + * Undoes the effect of one call to disable_nmi(). If this + * matches the last disable, processing of interrupts on this + * IRQ line is re-enabled. + */ +void enable_nmi(unsigned int irq) +{ + enable_irq(irq); +} + static int set_irq_wake_real(unsigned int irq, unsigned int on) { struct irq_desc *desc = irq_to_desc(irq); @@ -641,6 +670,12 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on) if (!desc) return -EINVAL; + /* Don't use NMIs as wake up interrupts please */ + if (desc->istate & IRQS_NMI) { + ret = -EINVAL; + goto out_unlock; + } + /* wakeup-capable irqs can be shared between drivers that * don't need to have the same sleep mode behaviors. */ @@ -663,6 +698,8 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on) irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE); } } + +out_unlock: irq_put_desc_busunlock(desc, flags); return ret; } @@ -1125,6 +1162,39 @@ static void irq_release_resources(struct irq_desc *desc) c->irq_release_resources(d); } +static bool irq_supports_nmi(struct irq_desc *desc) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + /* Only IRQs directly managed by the root irqchip can be set as NMI */ + if (d->parent_data) + return false; +#endif + /* Don't support NMIs for chips behind a slow bus */ + if (d->chip->irq_bus_lock || d->chip->irq_bus_sync_unlock) + return false; + + return d->chip->flags & IRQCHIP_SUPPORTS_NMI; +} + +static int irq_nmi_setup(struct irq_desc *desc) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + struct irq_chip *c = d->chip; + + return c->irq_nmi_setup ? c->irq_nmi_setup(d) : -EINVAL; +} + +static void irq_nmi_teardown(struct irq_desc *desc) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + struct irq_chip *c = d->chip; + + if (c->irq_nmi_teardown) + c->irq_nmi_teardown(d); +} + static int setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) { @@ -1299,9 +1369,17 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * fields must have IRQF_SHARED set and the bits which * set the trigger type must match. Also all must * agree on ONESHOT. + * Interrupt lines used for NMIs cannot be shared. */ unsigned int oldtype; + if (desc->istate & IRQS_NMI) { + pr_err("Invalid attempt to share NMI for %s (irq %d) on irqchip %s.\n", + new->name, irq, desc->irq_data.chip->name); + ret = -EINVAL; + goto out_unlock; + } + /* * If nobody did set the configuration before, inherit * the one provided by the requester. @@ -1753,6 +1831,59 @@ const void *free_irq(unsigned int irq, void *dev_id) } EXPORT_SYMBOL(free_irq); +/* This function must be called with desc->lock held */ +static const void *__cleanup_nmi(unsigned int irq, struct irq_desc *desc) +{ + const char *devname = NULL; + + desc->istate &= ~IRQS_NMI; + + if (!WARN_ON(desc->action == NULL)) { + irq_pm_remove_action(desc, desc->action); + devname = desc->action->name; + unregister_handler_proc(irq, desc->action); + + kfree(desc->action); + desc->action = NULL; + } + + irq_settings_clr_disable_unlazy(desc); + irq_shutdown(desc); + + irq_release_resources(desc); + + irq_chip_pm_put(&desc->irq_data); + module_put(desc->owner); + + return devname; +} + +const void *free_nmi(unsigned int irq, void *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; + const void *devname; + + if (!desc || WARN_ON(!(desc->istate & IRQS_NMI))) + return NULL; + + if (WARN_ON(irq_settings_is_per_cpu_devid(desc))) + return NULL; + + /* NMI still enabled */ + if (WARN_ON(desc->depth == 0)) + disable_nmi_nosync(irq); + + raw_spin_lock_irqsave(&desc->lock, flags); + + irq_nmi_teardown(desc); + devname = __cleanup_nmi(irq, desc); + + raw_spin_unlock_irqrestore(&desc->lock, flags); + + return devname; +} + /** * request_threaded_irq - allocate an interrupt line * @irq: Interrupt line to allocate @@ -1922,6 +2053,101 @@ int request_any_context_irq(unsigned int irq, irq_handler_t handler, } EXPORT_SYMBOL_GPL(request_any_context_irq); +/** + * request_nmi - allocate an interrupt line for NMI delivery + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs. + * Threaded handler for threaded interrupts. + * @irqflags: Interrupt type flags + * @name: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * This call allocates interrupt resources and enables the + * interrupt line and IRQ handling. It sets up the IRQ line + * to be handled as an NMI. + * + * An interrupt line delivering NMIs cannot be shared and IRQ handling + * cannot be threaded. + * + * Interrupt lines requested for NMI delivering must produce per cpu + * interrupts and have auto enabling setting disabled. + * + * Dev_id must be globally unique. Normally the address of the + * device data structure is used as the cookie. Since the handler + * receives this value it makes sense to use it. + * + * If the interrupt line cannot be used to deliver NMIs, function + * will fail and return a negative value. + */ +int request_nmi(unsigned int irq, irq_handler_t handler, + unsigned long irqflags, const char *name, void *dev_id) +{ + struct irqaction *action; + struct irq_desc *desc; + unsigned long flags; + int retval; + + if (irq == IRQ_NOTCONNECTED) + return -ENOTCONN; + + /* NMI cannot be shared, used for Polling */ + if (irqflags & (IRQF_SHARED | IRQF_COND_SUSPEND | IRQF_IRQPOLL)) + return -EINVAL; + + if (!(irqflags & IRQF_PERCPU)) + return -EINVAL; + + if (!handler) + return -EINVAL; + + desc = irq_to_desc(irq); + + if (!desc || irq_settings_can_autoenable(desc) || + !irq_settings_can_request(desc) || + WARN_ON(irq_settings_is_per_cpu_devid(desc)) || + !irq_supports_nmi(desc)) + return -EINVAL; + + action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); + if (!action) + return -ENOMEM; + + action->handler = handler; + action->flags = irqflags | IRQF_NO_THREAD | IRQF_NOBALANCING; + action->name = name; + action->dev_id = dev_id; + + retval = irq_chip_pm_get(&desc->irq_data); + if (retval < 0) + goto err_out; + + retval = __setup_irq(irq, desc, action); + if (retval) + goto err_irq_setup; + + raw_spin_lock_irqsave(&desc->lock, flags); + + /* Setup NMI state */ + desc->istate |= IRQS_NMI; + retval = irq_nmi_setup(desc); + if (retval) { + __cleanup_nmi(irq, desc); + raw_spin_unlock_irqrestore(&desc->lock, flags); + return -EINVAL; + } + + raw_spin_unlock_irqrestore(&desc->lock, flags); + + return 0; + +err_irq_setup: + irq_chip_pm_put(&desc->irq_data); +err_out: + kfree(action); + + return retval; +} + void enable_percpu_irq(unsigned int irq, unsigned int type) { unsigned int cpu = smp_processor_id(); -- cgit v1.2.3 From 4b078c3f1a26487c39363089ba0d5c6b09f2a89f Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Thu, 31 Jan 2019 14:53:59 +0000 Subject: genirq: Provide NMI management for percpu_devid interrupts Add support for percpu_devid interrupts treated as NMIs. Percpu_devid NMIs need to be setup/torn down on each CPU they target. The same restrictions as for global NMIs still apply for percpu_devid NMIs. Signed-off-by: Julien Thierry Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Marc Zyngier Signed-off-by: Marc Zyngier --- include/linux/interrupt.h | 9 +++ kernel/irq/manage.c | 177 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 186 insertions(+) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9941d1a8d83c..831ddcdc5597 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -168,10 +168,15 @@ request_percpu_irq(unsigned int irq, irq_handler_t handler, devname, percpu_dev_id); } +extern int __must_check +request_percpu_nmi(unsigned int irq, irq_handler_t handler, + const char *devname, void __percpu *dev); + extern const void *free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); extern const void *free_nmi(unsigned int irq, void *dev_id); +extern void free_percpu_nmi(unsigned int irq, void __percpu *percpu_dev_id); struct device; @@ -224,7 +229,11 @@ extern bool irq_percpu_is_enabled(unsigned int irq); extern void irq_wake_thread(unsigned int irq, void *dev_id); extern void disable_nmi_nosync(unsigned int irq); +extern void disable_percpu_nmi(unsigned int irq); extern void enable_nmi(unsigned int irq); +extern void enable_percpu_nmi(unsigned int irq, unsigned int type); +extern int prepare_percpu_nmi(unsigned int irq); +extern void teardown_percpu_nmi(unsigned int irq); /* The following three functions are for the core kernel use only. */ extern void suspend_device_irqs(void); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 9472ae987946..0a1ebc004a59 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -2182,6 +2182,11 @@ out: } EXPORT_SYMBOL_GPL(enable_percpu_irq); +void enable_percpu_nmi(unsigned int irq, unsigned int type) +{ + enable_percpu_irq(irq, type); +} + /** * irq_percpu_is_enabled - Check whether the per cpu irq is enabled * @irq: Linux irq number to check for @@ -2221,6 +2226,11 @@ void disable_percpu_irq(unsigned int irq) } EXPORT_SYMBOL_GPL(disable_percpu_irq); +void disable_percpu_nmi(unsigned int irq) +{ + disable_percpu_irq(irq); +} + /* * Internal function to unregister a percpu irqaction. */ @@ -2252,6 +2262,8 @@ static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_ /* Found it - now remove it from the list of entries: */ desc->action = NULL; + desc->istate &= ~IRQS_NMI; + raw_spin_unlock_irqrestore(&desc->lock, flags); unregister_handler_proc(irq, action); @@ -2305,6 +2317,19 @@ void free_percpu_irq(unsigned int irq, void __percpu *dev_id) } EXPORT_SYMBOL_GPL(free_percpu_irq); +void free_percpu_nmi(unsigned int irq, void __percpu *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc || !irq_settings_is_per_cpu_devid(desc)) + return; + + if (WARN_ON(!(desc->istate & IRQS_NMI))) + return; + + kfree(__free_percpu_irq(irq, dev_id)); +} + /** * setup_percpu_irq - setup a per-cpu interrupt * @irq: Interrupt line to setup @@ -2394,6 +2419,158 @@ int __request_percpu_irq(unsigned int irq, irq_handler_t handler, } EXPORT_SYMBOL_GPL(__request_percpu_irq); +/** + * request_percpu_nmi - allocate a percpu interrupt line for NMI delivery + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs. + * @name: An ascii name for the claiming device + * @dev_id: A percpu cookie passed back to the handler function + * + * This call allocates interrupt resources for a per CPU NMI. Per CPU NMIs + * have to be setup on each CPU by calling ready_percpu_nmi() before being + * enabled on the same CPU by using enable_percpu_nmi(). + * + * Dev_id must be globally unique. It is a per-cpu variable, and + * the handler gets called with the interrupted CPU's instance of + * that variable. + * + * Interrupt lines requested for NMI delivering should have auto enabling + * setting disabled. + * + * If the interrupt line cannot be used to deliver NMIs, function + * will fail returning a negative value. + */ +int request_percpu_nmi(unsigned int irq, irq_handler_t handler, + const char *name, void __percpu *dev_id) +{ + struct irqaction *action; + struct irq_desc *desc; + unsigned long flags; + int retval; + + if (!handler) + return -EINVAL; + + desc = irq_to_desc(irq); + + if (!desc || !irq_settings_can_request(desc) || + !irq_settings_is_per_cpu_devid(desc) || + irq_settings_can_autoenable(desc) || + !irq_supports_nmi(desc)) + return -EINVAL; + + /* The line cannot already be NMI */ + if (desc->istate & IRQS_NMI) + return -EINVAL; + + action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); + if (!action) + return -ENOMEM; + + action->handler = handler; + action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND | IRQF_NO_THREAD + | IRQF_NOBALANCING; + action->name = name; + action->percpu_dev_id = dev_id; + + retval = irq_chip_pm_get(&desc->irq_data); + if (retval < 0) + goto err_out; + + retval = __setup_irq(irq, desc, action); + if (retval) + goto err_irq_setup; + + raw_spin_lock_irqsave(&desc->lock, flags); + desc->istate |= IRQS_NMI; + raw_spin_unlock_irqrestore(&desc->lock, flags); + + return 0; + +err_irq_setup: + irq_chip_pm_put(&desc->irq_data); +err_out: + kfree(action); + + return retval; +} + +/** + * prepare_percpu_nmi - performs CPU local setup for NMI delivery + * @irq: Interrupt line to prepare for NMI delivery + * + * This call prepares an interrupt line to deliver NMI on the current CPU, + * before that interrupt line gets enabled with enable_percpu_nmi(). + * + * As a CPU local operation, this should be called from non-preemptible + * context. + * + * If the interrupt line cannot be used to deliver NMIs, function + * will fail returning a negative value. + */ +int prepare_percpu_nmi(unsigned int irq) +{ + unsigned long flags; + struct irq_desc *desc; + int ret = 0; + + WARN_ON(preemptible()); + + desc = irq_get_desc_lock(irq, &flags, + IRQ_GET_DESC_CHECK_PERCPU); + if (!desc) + return -EINVAL; + + if (WARN(!(desc->istate & IRQS_NMI), + KERN_ERR "prepare_percpu_nmi called for a non-NMI interrupt: irq %u\n", + irq)) { + ret = -EINVAL; + goto out; + } + + ret = irq_nmi_setup(desc); + if (ret) { + pr_err("Failed to setup NMI delivery: irq %u\n", irq); + goto out; + } + +out: + irq_put_desc_unlock(desc, flags); + return ret; +} + +/** + * teardown_percpu_nmi - undoes NMI setup of IRQ line + * @irq: Interrupt line from which CPU local NMI configuration should be + * removed + * + * This call undoes the setup done by prepare_percpu_nmi(). + * + * IRQ line should not be enabled for the current CPU. + * + * As a CPU local operation, this should be called from non-preemptible + * context. + */ +void teardown_percpu_nmi(unsigned int irq) +{ + unsigned long flags; + struct irq_desc *desc; + + WARN_ON(preemptible()); + + desc = irq_get_desc_lock(irq, &flags, + IRQ_GET_DESC_CHECK_PERCPU); + if (!desc) + return; + + if (WARN_ON(!(desc->istate & IRQS_NMI))) + goto out; + + irq_nmi_teardown(desc); +out: + irq_put_desc_unlock(desc, flags); +} + /** * irq_get_irqchip_state - returns the irqchip state of a interrupt. * @irq: Interrupt line that is forwarded to a VM -- cgit v1.2.3 From 2dcf1fbcad352baaa5f47b17e57c5743c8eedbad Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Thu, 31 Jan 2019 14:54:00 +0000 Subject: genirq: Provide NMI handlers Provide flow handlers that are NMI safe for interrupts and percpu_devid interrupts. Signed-off-by: Julien Thierry Acked-by: Marc Zyngier Cc: Thomas Gleixner Cc: Marc Zyngier Cc: Peter Zijlstra Signed-off-by: Marc Zyngier --- include/linux/irq.h | 3 +++ kernel/irq/chip.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index a7298e4998c8..5e91f6bcaacd 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -601,6 +601,9 @@ extern void handle_percpu_devid_irq(struct irq_desc *desc); extern void handle_bad_irq(struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); +extern void handle_fasteoi_nmi(struct irq_desc *desc); +extern void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc); + extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); extern int irq_chip_pm_get(struct irq_data *data); extern int irq_chip_pm_put(struct irq_data *data); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 34e969069488..c32d5f386f68 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -729,6 +729,37 @@ out: } EXPORT_SYMBOL_GPL(handle_fasteoi_irq); +/** + * handle_fasteoi_nmi - irq handler for NMI interrupt lines + * @desc: the interrupt description structure for this irq + * + * A simple NMI-safe handler, considering the restrictions + * from request_nmi. + * + * Only a single callback will be issued to the chip: an ->eoi() + * call when the interrupt has been serviced. This enables support + * for modern forms of interrupt handlers, which handle the flow + * details in hardware, transparently. + */ +void handle_fasteoi_nmi(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct irqaction *action = desc->action; + unsigned int irq = irq_desc_get_irq(desc); + irqreturn_t res; + + trace_irq_handler_entry(irq, action); + /* + * NMIs cannot be shared, there is only one action. + */ + res = action->handler(irq, action->dev_id); + trace_irq_handler_exit(irq, action, res); + + if (chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); +} +EXPORT_SYMBOL_GPL(handle_fasteoi_nmi); + /** * handle_edge_irq - edge type IRQ handler * @desc: the interrupt description structure for this irq @@ -908,6 +939,29 @@ void handle_percpu_devid_irq(struct irq_desc *desc) chip->irq_eoi(&desc->irq_data); } +/** + * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu + * dev ids + * @desc: the interrupt description structure for this irq + * + * Similar to handle_fasteoi_nmi, but handling the dev_id cookie + * as a percpu pointer. + */ +void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct irqaction *action = desc->action; + unsigned int irq = irq_desc_get_irq(desc); + irqreturn_t res; + + trace_irq_handler_entry(irq, action); + res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id)); + trace_irq_handler_exit(irq, action, res); + + if (chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); +} + static void __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, int is_chained, const char *name) -- cgit v1.2.3 From 6e4933a006616343f66c4702dc4fc56bb25e7b02 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Thu, 31 Jan 2019 14:54:01 +0000 Subject: irqdesc: Add domain handler for NMIs NMI handling code should be executed between calls to nmi_enter and nmi_exit. Add a separate domain handler to properly setup NMI context when handling an interrupt requested as NMI. Signed-off-by: Julien Thierry Acked-by: Marc Zyngier Cc: Thomas Gleixner Cc: Marc Zyngier Cc: Will Deacon Cc: Peter Zijlstra Signed-off-by: Marc Zyngier --- include/linux/irqdesc.h | 5 +++++ kernel/irq/irqdesc.c | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index dd1e40ddac7d..ba05b0d6401a 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -171,6 +171,11 @@ static inline int handle_domain_irq(struct irq_domain *domain, { return __handle_domain_irq(domain, hwirq, true, regs); } + +#ifdef CONFIG_IRQ_DOMAIN +int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq, + struct pt_regs *regs); +#endif #endif /* Test to see if a driver has successfully requested an irq */ diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index ee062b7939d3..a1d7a7d484e0 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -669,6 +669,41 @@ int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, set_irq_regs(old_regs); return ret; } + +#ifdef CONFIG_IRQ_DOMAIN +/** + * handle_domain_nmi - Invoke the handler for a HW irq belonging to a domain + * @domain: The domain where to perform the lookup + * @hwirq: The HW irq number to convert to a logical one + * @regs: Register file coming from the low-level handling code + * + * Returns: 0 on success, or -EINVAL if conversion has failed + */ +int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq, + struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + unsigned int irq; + int ret = 0; + + nmi_enter(); + + irq = irq_find_mapping(domain, hwirq); + + /* + * ack_bad_irq is not NMI-safe, just report + * an invalid interrupt. + */ + if (likely(irq)) + generic_handle_irq(irq); + else + ret = -EINVAL; + + nmi_exit(); + set_irq_regs(old_regs); + return ret; +} +#endif #endif /* Dynamic interrupt handling */ -- cgit v1.2.3 From 013e6292aaf5e4b083a50a0f9e17e93628616860 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 11:57:20 +0100 Subject: mtd: rawnand: Simplify the locking nand_get_device() was complex for apparently no good reason. Let's replace this locking scheme with 2 mutexes: one attached to the controller and another one attached to the chip. Every time the core calls nand_get_device(), it will first lock the chip and if the chip is not suspended, will then lock the controller. nand_release_device() will release both lock in the reverse order. nand_get_device() can sleep, just like the previous implementation, which means you should never call that from an atomic context. We also get rid of - the chip->state field, since all it was used for was flagging the chip as suspended. We replace it by a field called chip->suspended and directly set it from nand_suspend/resume() - the controller->wq and controller->active fields which are no longer needed since the new controller->lock (now a mutex) guarantees that all operations are serialized at the controller level - panic_nand_get_device() which would anyway be a no-op. Talking about panic write, I keep thinking the rawnand implementation is unsafe because there's not negotiation with the controller to know when it's actually done with it's previous operation. I don't intend to fix that here, but that's probably something we should look at, or maybe we should consider dropping the ->_panic_write() implementation Last important change to mention: we now return -EBUSY when someone tries to access a device that as been suspended, and propagate this error to the upper layer. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 111 ++++++++++++++++----------------------- include/linux/mtd/rawnand.h | 24 ++++----- 2 files changed, 54 insertions(+), 81 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index cca4b24d2ffa..96cadead262e 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -278,11 +278,8 @@ EXPORT_SYMBOL_GPL(nand_deselect_target); static void nand_release_device(struct nand_chip *chip) { /* Release the controller and the chip */ - spin_lock(&chip->controller->lock); - chip->controller->active = NULL; - chip->state = FL_READY; - wake_up(&chip->controller->wq); - spin_unlock(&chip->controller->lock); + mutex_unlock(&chip->controller->lock); + mutex_unlock(&chip->lock); } /** @@ -330,58 +327,24 @@ static int nand_isbad_bbm(struct nand_chip *chip, loff_t ofs) return nand_block_bad(chip, ofs); } -/** - * panic_nand_get_device - [GENERIC] Get chip for selected access - * @chip: the nand chip descriptor - * @new_state: the state which is requested - * - * Used when in panic, no locks are taken. - */ -static void panic_nand_get_device(struct nand_chip *chip, int new_state) -{ - /* Hardware controller shared among independent devices */ - chip->controller->active = chip; - chip->state = new_state; -} - /** * nand_get_device - [GENERIC] Get chip for selected access * @chip: NAND chip structure - * @new_state: the state which is requested * - * Get the device and lock it for exclusive access + * Lock the device and its controller for exclusive access + * + * Return: -EBUSY if the chip has been suspended, 0 otherwise */ -static int -nand_get_device(struct nand_chip *chip, int new_state) +static int nand_get_device(struct nand_chip *chip) { - spinlock_t *lock = &chip->controller->lock; - wait_queue_head_t *wq = &chip->controller->wq; - DECLARE_WAITQUEUE(wait, current); -retry: - spin_lock(lock); - - /* Hardware controller shared among independent devices */ - if (!chip->controller->active) - chip->controller->active = chip; - - if (chip->controller->active == chip && chip->state == FL_READY) { - chip->state = new_state; - spin_unlock(lock); - return 0; - } - if (new_state == FL_PM_SUSPENDED) { - if (chip->controller->active->state == FL_PM_SUSPENDED) { - chip->state = FL_PM_SUSPENDED; - spin_unlock(lock); - return 0; - } + mutex_lock(&chip->lock); + if (chip->suspended) { + mutex_unlock(&chip->lock); + return -EBUSY; } - set_current_state(TASK_UNINTERRUPTIBLE); - add_wait_queue(wq, &wait); - spin_unlock(lock); - schedule(); - remove_wait_queue(wq, &wait); - goto retry; + mutex_lock(&chip->controller->lock); + + return 0; } /** @@ -602,7 +565,10 @@ static int nand_block_markbad_lowlevel(struct nand_chip *chip, loff_t ofs) nand_erase_nand(chip, &einfo, 0); /* Write bad block marker to OOB */ - nand_get_device(chip, FL_WRITING); + ret = nand_get_device(chip); + if (ret) + return ret; + ret = nand_markbad_bbm(chip, ofs); nand_release_device(chip); } @@ -3580,7 +3546,9 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from, ops->mode != MTD_OPS_RAW) return -ENOTSUPP; - nand_get_device(chip, FL_READING); + ret = nand_get_device(chip); + if (ret) + return ret; if (!ops->datbuf) ret = nand_do_read_oob(chip, from, ops); @@ -4099,9 +4067,6 @@ static int panic_nand_write(struct mtd_info *mtd, loff_t to, size_t len, struct mtd_oob_ops ops; int ret; - /* Grab the device */ - panic_nand_get_device(chip, FL_WRITING); - nand_select_target(chip, chipnr); /* Wait for the device to get ready */ @@ -4132,7 +4097,9 @@ static int nand_write_oob(struct mtd_info *mtd, loff_t to, ops->retlen = 0; - nand_get_device(chip, FL_WRITING); + ret = nand_get_device(chip); + if (ret) + return ret; switch (ops->mode) { case MTD_OPS_PLACE_OOB: @@ -4205,7 +4172,9 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, return -EINVAL; /* Grab the lock and see if the device is available */ - nand_get_device(chip, FL_ERASING); + ret = nand_get_device(chip); + if (ret) + return ret; /* Shift to get first page */ page = (int)(instr->addr >> chip->page_shift); @@ -4298,7 +4267,7 @@ static void nand_sync(struct mtd_info *mtd) pr_debug("%s: called\n", __func__); /* Grab the lock and see if the device is available */ - nand_get_device(chip, FL_SYNCING); + WARN_ON(nand_get_device(chip)); /* Release it and go back */ nand_release_device(chip); } @@ -4315,7 +4284,10 @@ static int nand_block_isbad(struct mtd_info *mtd, loff_t offs) int ret; /* Select the NAND device */ - nand_get_device(chip, FL_READING); + ret = nand_get_device(chip); + if (ret) + return ret; + nand_select_target(chip, chipnr); ret = nand_block_checkbad(chip, offs, 0); @@ -4388,7 +4360,13 @@ static int nand_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len) */ static int nand_suspend(struct mtd_info *mtd) { - return nand_get_device(mtd_to_nand(mtd), FL_PM_SUSPENDED); + struct nand_chip *chip = mtd_to_nand(mtd); + + mutex_lock(&chip->lock); + chip->suspended = 1; + mutex_unlock(&chip->lock); + + return 0; } /** @@ -4399,11 +4377,13 @@ static void nand_resume(struct mtd_info *mtd) { struct nand_chip *chip = mtd_to_nand(mtd); - if (chip->state == FL_PM_SUSPENDED) - nand_release_device(chip); + mutex_lock(&chip->lock); + if (chip->suspended) + chip->suspended = 0; else pr_err("%s called for a chip which is not in suspended state\n", __func__); + mutex_unlock(&chip->lock); } /** @@ -4413,7 +4393,7 @@ static void nand_resume(struct mtd_info *mtd) */ static void nand_shutdown(struct mtd_info *mtd) { - nand_get_device(mtd_to_nand(mtd), FL_PM_SUSPENDED); + nand_suspend(mtd); } /* Set default functions */ @@ -5018,6 +4998,8 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips, /* Assume all dies are deselected when we enter nand_scan_ident(). */ chip->cur_cs = -1; + mutex_init(&chip->lock); + /* Enforce the right timings for reset/detection */ onfi_fill_data_interface(chip, NAND_SDR_IFACE, 0); @@ -5717,9 +5699,6 @@ static int nand_scan_tail(struct nand_chip *chip) } chip->subpagesize = mtd->writesize >> mtd->subpage_sft; - /* Initialize state */ - chip->state = FL_READY; - /* Invalidate the pagebuffer reference */ chip->pagebuf = -1; diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 33e240acdc6d..17d2d9ae33bf 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -16,13 +16,12 @@ #ifndef __LINUX_MTD_RAWNAND_H #define __LINUX_MTD_RAWNAND_H -#include -#include #include #include #include #include #include +#include #include #include @@ -897,25 +896,17 @@ struct nand_controller_ops { /** * struct nand_controller - Structure used to describe a NAND controller * - * @lock: protection lock - * @active: the mtd device which holds the controller currently - * @wq: wait queue to sleep on if a NAND operation is in - * progress used instead of the per chip wait queue - * when a hw controller is available. + * @lock: lock used to serialize accesses to the NAND controller * @ops: NAND controller operations. */ struct nand_controller { - spinlock_t lock; - struct nand_chip *active; - wait_queue_head_t wq; + struct mutex lock; const struct nand_controller_ops *ops; }; static inline void nand_controller_init(struct nand_controller *nfc) { - nfc->active = NULL; - spin_lock_init(&nfc->lock); - init_waitqueue_head(&nfc->wq); + mutex_init(&nfc->lock); } /** @@ -983,7 +974,6 @@ struct nand_legacy { * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure * @buf_align: minimum buffer alignment required by a platform - * @state: [INTERN] the current state of the NAND device * @oob_poi: "poison value buffer," used for laying out OOB data * before writing * @page_shift: [INTERN] number of address bits in a page (column @@ -1034,6 +1024,9 @@ struct nand_legacy { * cur_cs < numchips. NAND Controller drivers should not * modify this value, but they're allowed to read it. * @read_retries: [INTERN] the number of read retry modes supported + * @lock: lock protecting the suspended field. Also used to + * serialize accesses to the NAND device. + * @suspended: set to 1 when the device is suspended, 0 when it's not. * @bbt: [INTERN] bad block table pointer * @bbt_td: [REPLACEABLE] bad block table descriptor for flash * lookup. @@ -1088,7 +1081,8 @@ struct nand_chip { int read_retries; - flstate_t state; + struct mutex lock; + unsigned int suspended : 1; uint8_t *oob_poi; struct nand_controller *controller; -- cgit v1.2.3 From 2d73f3d66b7052c0175f9f33d271ae50826c222e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 21 Jan 2019 15:32:07 +0900 Subject: mtd: rawnand: remove ->legacy.erase and single_erase() Now that the last user of this hook, denali.c, stopped using it, we can remove the erase hook from nand_legacy. I squashed single_erase() because only the difference between single_erase() and nand_erase_op() is the number of bit shifts. The status/ret conversion in nand_erase_nand() is unneeded since commit eb94555e9e97 ("mtd: nand: use usual return values for the ->erase() hook"). Cleaned it up now. Signed-off-by: Masahiro Yamada Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 31 ++++--------------------------- include/linux/mtd/rawnand.h | 2 -- 2 files changed, 4 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index e05ecf2e4269..cf207d6e7a81 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -4121,23 +4121,6 @@ out: return ret; } -/** - * single_erase - [GENERIC] NAND standard block erase command function - * @chip: NAND chip object - * @page: the page address of the block which will be erased - * - * Standard erase command for NAND chips. Returns NAND status. - */ -static int single_erase(struct nand_chip *chip, int page) -{ - unsigned int eraseblock; - - /* Send commands to erase a block */ - eraseblock = page >> (chip->phys_erase_shift - chip->page_shift); - - return nand_erase_op(chip, eraseblock); -} - /** * nand_erase - [MTD Interface] erase block(s) * @mtd: MTD device structure @@ -4161,7 +4144,7 @@ static int nand_erase(struct mtd_info *mtd, struct erase_info *instr) int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, int allowbbt) { - int page, status, pages_per_block, ret, chipnr; + int page, pages_per_block, ret, chipnr; loff_t len; pr_debug("%s: start = 0x%012llx, len = %llu\n", @@ -4215,17 +4198,11 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, (page + pages_per_block)) chip->pagebuf = -1; - if (chip->legacy.erase) - status = chip->legacy.erase(chip, - page & chip->pagemask); - else - status = single_erase(chip, page & chip->pagemask); - - /* See if block erase succeeded */ - if (status) { + ret = nand_erase_op(chip, (page & chip->pagemask) >> + (chip->phys_erase_shift - chip->page_shift)); + if (ret) { pr_debug("%s: failed erase, page 0x%08x\n", __func__, page); - ret = -EIO; instr->fail_addr = ((loff_t)page << chip->page_shift); goto erase_exit; diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 17d2d9ae33bf..b7445a44a814 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -927,7 +927,6 @@ static inline void nand_controller_init(struct nand_controller *nfc) * @waitfunc: hardware specific function for wait on ready. * @block_bad: check if a block is bad, using OOB markers * @block_markbad: mark a block bad - * @erase: erase function * @set_features: set the NAND chip features * @get_features: get the NAND chip features * @chip_delay: chip dependent delay for transferring data from array to read @@ -953,7 +952,6 @@ struct nand_legacy { int (*waitfunc)(struct nand_chip *chip); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); - int (*erase)(struct nand_chip *chip, int page); int (*set_features)(struct nand_chip *chip, int feature_addr, u8 *subfeature_para); int (*get_features)(struct nand_chip *chip, int feature_addr, -- cgit v1.2.3 From 278bca7f318e6a29f482eabbca52db538dc5d4e6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 10 Jan 2019 21:00:27 +0200 Subject: vfio-mdev: Switch to use new generic UUID API There are new types and helpers that are supposed to be used in new code. As a preparation to get rid of legacy types and API functions do the conversion here. Cc: Kirti Wankhede Cc: Alex Williamson Signed-off-by: Andy Shevchenko Reviewed-by: Christoph Hellwig Signed-off-by: Alex Williamson --- drivers/vfio/mdev/mdev_core.c | 16 ++++++++-------- drivers/vfio/mdev/mdev_private.h | 5 +++-- drivers/vfio/mdev/mdev_sysfs.c | 6 +++--- include/linux/mdev.h | 2 +- samples/vfio-mdev/mtty.c | 8 ++++---- 5 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c index 0212f0ee8aea..b96fedc77ee5 100644 --- a/drivers/vfio/mdev/mdev_core.c +++ b/drivers/vfio/mdev/mdev_core.c @@ -60,9 +60,9 @@ struct mdev_device *mdev_from_dev(struct device *dev) } EXPORT_SYMBOL(mdev_from_dev); -uuid_le mdev_uuid(struct mdev_device *mdev) +const guid_t *mdev_uuid(struct mdev_device *mdev) { - return mdev->uuid; + return &mdev->uuid; } EXPORT_SYMBOL(mdev_uuid); @@ -88,8 +88,7 @@ static void mdev_release_parent(struct kref *kref) put_device(dev); } -static -inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent) +static inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent) { if (parent) kref_get(&parent->ref); @@ -276,7 +275,8 @@ static void mdev_device_release(struct device *dev) kfree(mdev); } -int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid) +int mdev_device_create(struct kobject *kobj, + struct device *dev, const guid_t *uuid) { int ret; struct mdev_device *mdev, *tmp; @@ -291,7 +291,7 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid) /* Check for duplicate */ list_for_each_entry(tmp, &mdev_list, next) { - if (!uuid_le_cmp(tmp->uuid, uuid)) { + if (guid_equal(&tmp->uuid, uuid)) { mutex_unlock(&mdev_list_lock); ret = -EEXIST; goto mdev_fail; @@ -305,7 +305,7 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid) goto mdev_fail; } - memcpy(&mdev->uuid, &uuid, sizeof(uuid_le)); + guid_copy(&mdev->uuid, uuid); list_add(&mdev->next, &mdev_list); mutex_unlock(&mdev_list_lock); @@ -315,7 +315,7 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid) mdev->dev.parent = dev; mdev->dev.bus = &mdev_bus_type; mdev->dev.release = mdev_device_release; - dev_set_name(&mdev->dev, "%pUl", uuid.b); + dev_set_name(&mdev->dev, "%pUl", uuid); ret = device_register(&mdev->dev); if (ret) { diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h index b5819b7d7ef7..379758c52b1b 100644 --- a/drivers/vfio/mdev/mdev_private.h +++ b/drivers/vfio/mdev/mdev_private.h @@ -28,7 +28,7 @@ struct mdev_parent { struct mdev_device { struct device dev; struct mdev_parent *parent; - uuid_le uuid; + guid_t uuid; void *driver_data; struct kref ref; struct list_head next; @@ -58,7 +58,8 @@ void parent_remove_sysfs_files(struct mdev_parent *parent); int mdev_create_sysfs_files(struct device *dev, struct mdev_type *type); void mdev_remove_sysfs_files(struct device *dev, struct mdev_type *type); -int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid); +int mdev_device_create(struct kobject *kobj, + struct device *dev, const guid_t *uuid); int mdev_device_remove(struct device *dev, bool force_remove); #endif /* MDEV_PRIVATE_H */ diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c index ce5dd219f2c8..5193a0e0ce5a 100644 --- a/drivers/vfio/mdev/mdev_sysfs.c +++ b/drivers/vfio/mdev/mdev_sysfs.c @@ -55,7 +55,7 @@ static ssize_t create_store(struct kobject *kobj, struct device *dev, const char *buf, size_t count) { char *str; - uuid_le uuid; + guid_t uuid; int ret; if ((count < UUID_STRING_LEN) || (count > UUID_STRING_LEN + 1)) @@ -65,12 +65,12 @@ static ssize_t create_store(struct kobject *kobj, struct device *dev, if (!str) return -ENOMEM; - ret = uuid_le_to_bin(str, &uuid); + ret = guid_parse(str, &uuid); kfree(str); if (ret) return ret; - ret = mdev_device_create(kobj, dev, uuid); + ret = mdev_device_create(kobj, dev, &uuid); if (ret) return ret; diff --git a/include/linux/mdev.h b/include/linux/mdev.h index b6e048e1045f..d7aee90e5da5 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -120,7 +120,7 @@ struct mdev_driver { extern void *mdev_get_drvdata(struct mdev_device *mdev); extern void mdev_set_drvdata(struct mdev_device *mdev, void *data); -extern uuid_le mdev_uuid(struct mdev_device *mdev); +extern const guid_t *mdev_uuid(struct mdev_device *mdev); extern struct bus_type mdev_bus_type; diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index f6732aa16bb1..19cd29071ab0 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -156,15 +156,15 @@ static const struct file_operations vd_fops = { /* function prototypes */ -static int mtty_trigger_interrupt(uuid_le uuid); +static int mtty_trigger_interrupt(const guid_t *uuid); /* Helper functions */ -static struct mdev_state *find_mdev_state_by_uuid(uuid_le uuid) +static struct mdev_state *find_mdev_state_by_uuid(const guid_t *uuid) { struct mdev_state *mds; list_for_each_entry(mds, &mdev_devices_list, next) { - if (uuid_le_cmp(mdev_uuid(mds->mdev), uuid) == 0) + if (guid_equal(mdev_uuid(mds->mdev), uuid)) return mds; } @@ -1032,7 +1032,7 @@ static int mtty_set_irqs(struct mdev_device *mdev, uint32_t flags, return ret; } -static int mtty_trigger_interrupt(uuid_le uuid) +static int mtty_trigger_interrupt(const guid_t *uuid) { int ret = -1; struct mdev_state *mdev_state; -- cgit v1.2.3 From c3424f59a0cb994a098c3701bf14617580a18290 Mon Sep 17 00:00:00 2001 From: Weiyi Lu Date: Fri, 14 Dec 2018 10:04:16 +0800 Subject: dt-bindings: clock: add clock for MT2712 Add new clock according to 3rd ECO design change. It's the parent clock of audio clock mux. Signed-off-by: Weiyi Lu Reviewed-by: Rob Herring Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/mt2712-clk.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/mt2712-clk.h b/include/dt-bindings/clock/mt2712-clk.h index 76265836a1e1..c3b29dff9c0e 100644 --- a/include/dt-bindings/clock/mt2712-clk.h +++ b/include/dt-bindings/clock/mt2712-clk.h @@ -228,7 +228,8 @@ #define CLK_TOP_NFI2X_EN 189 #define CLK_TOP_NFIECC_EN 190 #define CLK_TOP_NFI1X_CK_EN 191 -#define CLK_TOP_NR_CLK 192 +#define CLK_TOP_APLL2_D3 192 +#define CLK_TOP_NR_CLK 193 /* INFRACFG */ -- cgit v1.2.3 From a78e8723a50530d15faa25cc0b6f009bcd251c20 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 16 Jan 2019 09:55:41 +0200 Subject: RDMA/cma: Remove CM_ID statistics provided by rdma-cm module Netlink statistics exported by rdma-cm never had any working user space component published to the mailing list or to any open source project. Canvassing various proprietary users, and the original requester, we find that there are no real users of this interface. This patch simply removes all occurrences of RDMA CM netlink in favour of modern nldev implementation, which provides the same information and accompanied by widely used user space component. Signed-off-by: Leon Romanovsky Reviewed-by: Steve Wise Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cma.c | 83 --------------------------------------- drivers/infiniband/core/netlink.c | 4 +- include/uapi/rdma/rdma_netlink.h | 17 +------- 3 files changed, 3 insertions(+), 101 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 81bded0d37d1..e15546ae4d0f 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -4616,85 +4616,6 @@ static void cma_remove_one(struct ib_device *device, void *client_data) kfree(cma_dev); } -static int cma_get_id_stats(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct nlmsghdr *nlh; - struct rdma_cm_id_stats *id_stats; - struct rdma_id_private *id_priv; - struct rdma_cm_id *id = NULL; - struct cma_device *cma_dev; - int i_dev = 0, i_id = 0; - - /* - * We export all of the IDs as a sequence of messages. Each - * ID gets its own netlink message. - */ - mutex_lock(&lock); - - list_for_each_entry(cma_dev, &dev_list, list) { - if (i_dev < cb->args[0]) { - i_dev++; - continue; - } - - i_id = 0; - list_for_each_entry(id_priv, &cma_dev->id_list, list) { - if (i_id < cb->args[1]) { - i_id++; - continue; - } - - id_stats = ibnl_put_msg(skb, &nlh, cb->nlh->nlmsg_seq, - sizeof *id_stats, RDMA_NL_RDMA_CM, - RDMA_NL_RDMA_CM_ID_STATS, - NLM_F_MULTI); - if (!id_stats) - goto out; - - memset(id_stats, 0, sizeof *id_stats); - id = &id_priv->id; - id_stats->node_type = id->route.addr.dev_addr.dev_type; - id_stats->port_num = id->port_num; - id_stats->bound_dev_if = - id->route.addr.dev_addr.bound_dev_if; - - if (ibnl_put_attr(skb, nlh, - rdma_addr_size(cma_src_addr(id_priv)), - cma_src_addr(id_priv), - RDMA_NL_RDMA_CM_ATTR_SRC_ADDR)) - goto out; - if (ibnl_put_attr(skb, nlh, - rdma_addr_size(cma_dst_addr(id_priv)), - cma_dst_addr(id_priv), - RDMA_NL_RDMA_CM_ATTR_DST_ADDR)) - goto out; - - id_stats->pid = task_pid_vnr(id_priv->res.task); - id_stats->port_space = id->ps; - id_stats->cm_state = id_priv->state; - id_stats->qp_num = id_priv->qp_num; - id_stats->qp_type = id->qp_type; - - i_id++; - nlmsg_end(skb, nlh); - } - - cb->args[1] = 0; - i_dev++; - } - -out: - mutex_unlock(&lock); - cb->args[0] = i_dev; - cb->args[1] = i_id; - - return skb->len; -} - -static const struct rdma_nl_cbs cma_cb_table[RDMA_NL_RDMA_CM_NUM_OPS] = { - [RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats}, -}; - static int cma_init_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); @@ -4743,7 +4664,6 @@ static int __init cma_init(void) if (ret) goto err; - rdma_nl_register(RDMA_NL_RDMA_CM, cma_cb_table); cma_configfs_init(); return 0; @@ -4759,7 +4679,6 @@ err_wq: static void __exit cma_cleanup(void) { cma_configfs_exit(); - rdma_nl_unregister(RDMA_NL_RDMA_CM); ib_unregister_client(&cma_client); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); @@ -4767,7 +4686,5 @@ static void __exit cma_cleanup(void) destroy_workqueue(cma_wq); } -MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_RDMA_CM, 1); - module_init(cma_init); module_exit(cma_cleanup); diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index 724f5a62e82f..eecfc0b377c9 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -56,7 +56,6 @@ EXPORT_SYMBOL(rdma_nl_chk_listeners); static bool is_nl_msg_valid(unsigned int type, unsigned int op) { static const unsigned int max_num_ops[RDMA_NL_NUM_CLIENTS] = { - [RDMA_NL_RDMA_CM] = RDMA_NL_RDMA_CM_NUM_OPS, [RDMA_NL_IWCM] = RDMA_NL_IWPM_NUM_OPS, [RDMA_NL_LS] = RDMA_NL_LS_NUM_OPS, [RDMA_NL_NLDEV] = RDMA_NLDEV_NUM_OPS, @@ -181,8 +180,7 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, return -EINVAL; } /* FIXME: Convert IWCM to properly handle doit callbacks */ - if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_RDMA_CM || - index == RDMA_NL_IWCM) { + if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_IWCM) { struct netlink_dump_control c = { .dump = cb_table[op].dump, }; diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h index 0f5263767fb4..3a9e681e4257 100644 --- a/include/uapi/rdma/rdma_netlink.h +++ b/include/uapi/rdma/rdma_netlink.h @@ -5,8 +5,7 @@ #include enum { - RDMA_NL_RDMA_CM = 1, - RDMA_NL_IWCM, + RDMA_NL_IWCM = 2, RDMA_NL_RSVD, RDMA_NL_LS, /* RDMA Local Services */ RDMA_NL_NLDEV, /* RDMA device interface */ @@ -14,8 +13,7 @@ enum { }; enum { - RDMA_NL_GROUP_CM = 1, - RDMA_NL_GROUP_IWPM, + RDMA_NL_GROUP_IWPM = 2, RDMA_NL_GROUP_LS, RDMA_NL_NUM_GROUPS }; @@ -24,17 +22,6 @@ enum { #define RDMA_NL_GET_OP(type) (type & ((1 << 10) - 1)) #define RDMA_NL_GET_TYPE(client, op) ((client << 10) + op) -enum { - RDMA_NL_RDMA_CM_ID_STATS = 0, - RDMA_NL_RDMA_CM_NUM_OPS -}; - -enum { - RDMA_NL_RDMA_CM_ATTR_SRC_ADDR = 1, - RDMA_NL_RDMA_CM_ATTR_DST_ADDR, - RDMA_NL_RDMA_CM_NUM_ATTR, -}; - /* The minimum version that the iwpm kernel supports */ #define IWPM_UABI_VERSION_MIN 3 -- cgit v1.2.3 From a2bfd708b17adb6e597e70d4eca824667f2d4e3c Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Tue, 5 Feb 2019 11:33:22 -0800 Subject: RDMA/iwpm: move kdoc comments to functions Move the iwpm kdoc comments from the prototype declarations to above the function bodies. There are no functional changes in this patch. Signed-off-by: Steve Wise Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/iwpm_msg.c | 116 ++++++++++++++++++++-------- drivers/infiniband/core/iwpm_util.c | 40 ++++++++++ include/rdma/iw_portmap.h | 149 ------------------------------------ 3 files changed, 123 insertions(+), 182 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c index 2e30e65b0816..2452b0ddcf0d 100644 --- a/drivers/infiniband/core/iwpm_msg.c +++ b/drivers/infiniband/core/iwpm_msg.c @@ -38,14 +38,21 @@ u16 iwpm_ulib_version = IWPM_UABI_VERSION_MIN; static int iwpm_user_pid = IWPM_PID_UNDEFINED; static atomic_t echo_nlmsg_seq; +/** + * iwpm_valid_pid - Check if the userspace iwarp port mapper pid is valid + * + * Returns true if the pid is greater than zero, otherwise returns false + */ int iwpm_valid_pid(void) { return iwpm_user_pid > 0; } -/* - * iwpm_register_pid - Send a netlink query to user space - * for the iwarp port mapper pid +/** + * iwpm_register_pid - Send a netlink query to userspace + * to get the iwarp port mapper pid + * @pm_msg: Contains driver info to send to the userspace port mapper + * @nl_client: The index of the netlink client * * nlmsg attributes: * [IWPM_NLA_REG_PID_SEQ] @@ -124,13 +131,19 @@ pid_query_error: return ret; } -/* - * iwpm_add_mapping - Send a netlink add mapping message - * to the port mapper +/** + * iwpm_add_mapping - Send a netlink add mapping request to + * the userspace port mapper + * @pm_msg: Contains the local ip/tcp address info to send + * @nl_client: The index of the netlink client + * * nlmsg attributes: * [IWPM_NLA_MANAGE_MAPPING_SEQ] * [IWPM_NLA_MANAGE_ADDR] * [IWPM_NLA_MANAGE_FLAGS] + * + * If the request is successful, the pm_msg stores + * the port mapper response (mapped address info) */ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) { @@ -208,9 +221,12 @@ add_mapping_error_nowarn: return ret; } -/* - * iwpm_add_and_query_mapping - Send a netlink add and query - * mapping message to the port mapper +/** + * iwpm_add_and_query_mapping - Process the port mapper response to + * iwpm_add_and_query_mapping request + * @pm_msg: Contains the local ip/tcp address info to send + * @nl_client: The index of the netlink client + * * nlmsg attributes: * [IWPM_NLA_QUERY_MAPPING_SEQ] * [IWPM_NLA_QUERY_LOCAL_ADDR] @@ -299,9 +315,13 @@ query_mapping_error_nowarn: return ret; } -/* - * iwpm_remove_mapping - Send a netlink remove mapping message - * to the port mapper +/** + * iwpm_remove_mapping - Send a netlink remove mapping request + * to the userspace port mapper + * + * @local_addr: Local ip/tcp address to remove + * @nl_client: The index of the netlink client + * * nlmsg attributes: * [IWPM_NLA_MANAGE_MAPPING_SEQ] * [IWPM_NLA_MANAGE_ADDR] @@ -372,9 +392,14 @@ static const struct nla_policy resp_reg_policy[IWPM_NLA_RREG_PID_MAX] = { [IWPM_NLA_RREG_PID_ERR] = { .type = NLA_U16 } }; -/* - * iwpm_register_pid_cb - Process a port mapper response to - * iwpm_register_pid() +/** + * iwpm_register_pid_cb - Process the port mapper response to + * iwpm_register_pid query + * @skb: + * @cb: Contains the received message (payload and netlink header) + * + * If successful, the function receives the userspace port mapper pid + * which is used in future communication with the port mapper */ int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb) { @@ -443,9 +468,11 @@ static const struct nla_policy resp_add_policy[IWPM_NLA_RMANAGE_MAPPING_MAX] = { [IWPM_NLA_RMANAGE_MAPPING_ERR] = { .type = NLA_U16 } }; -/* - * iwpm_add_mapping_cb - Process a port mapper response to - * iwpm_add_mapping() +/** + * iwpm_add_mapping_cb - Process the port mapper response to + * iwpm_add_mapping request + * @skb: + * @cb: Contains the received message (payload and netlink header) */ int iwpm_add_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb) { @@ -518,9 +545,11 @@ static const struct nla_policy resp_query_policy[IWPM_NLA_RQUERY_MAPPING_MAX] = [IWPM_NLA_RQUERY_MAPPING_ERR] = { .type = NLA_U16 } }; -/* - * iwpm_add_and_query_mapping_cb - Process a port mapper response to - * iwpm_add_and_query_mapping() +/** + * iwpm_add_and_query_mapping_cb - Process the port mapper response to + * iwpm_add_and_query_mapping request + * @skb: + * @cb: Contains the received message (payload and netlink header) */ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb) @@ -598,9 +627,13 @@ query_mapping_response_exit: return 0; } -/* - * iwpm_remote_info_cb - Process a port mapper message, containing - * the remote connecting peer address info +/** + * iwpm_remote_info_cb - Process remote connecting peer address info, which + * the port mapper has received from the connecting peer + * @skb: + * @cb: Contains the received message (payload and netlink header) + * + * Stores the IPv4/IPv6 address info in a hash table */ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { @@ -673,8 +706,14 @@ static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = { [IWPM_NLA_MAPINFO_ULIB_VER] = { .type = NLA_U16 } }; -/* - * iwpm_mapping_info_cb - Process a port mapper request for mapping info +/** + * iwpm_mapping_info_cb - Process a notification that the userspace + * port mapper daemon is started + * @skb: + * @cb: Contains the received message (payload and netlink header) + * + * Using the received port mapper pid, send all the local mapping + * info records to the userspace port mapper */ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { @@ -727,9 +766,11 @@ static const struct nla_policy ack_mapinfo_policy[IWPM_NLA_MAPINFO_NUM_MAX] = { [IWPM_NLA_MAPINFO_ACK_NUM] = { .type = NLA_U32 } }; -/* - * iwpm_ack_mapping_info_cb - Process a port mapper ack for - * the provided mapping info records +/** + * iwpm_ack_mapping_info_cb - Process the port mapper ack for + * the provided local mapping info records + * @skb: + * @cb: Contains the received message (payload and netlink header) */ int iwpm_ack_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { @@ -755,8 +796,11 @@ static const struct nla_policy map_error_policy[IWPM_NLA_ERR_MAX] = { [IWPM_NLA_ERR_CODE] = { .type = NLA_U16 }, }; -/* - * iwpm_mapping_error_cb - Process a port mapper error message +/** + * iwpm_mapping_error_cb - Process port mapper notification for error + * + * @skb: + * @cb: Contains the received message (payload and netlink header) */ int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb) { @@ -797,8 +841,14 @@ static const struct nla_policy hello_policy[IWPM_NLA_HELLO_MAX] = { [IWPM_NLA_HELLO_ABI_VERSION] = { .type = NLA_U16 } }; -/* - * iwpm_hello_cb - Process a port mapper hello request +/** + * iwpm_hello_cb - Process a hello message from iwpmd + * + * @skb: + * @cb: Contains the received message (payload and netlink header) + * + * Using the received port mapper pid, send the kernel's abi_version + * after adjusting it to support the iwpmd version. */ int iwpm_hello_cb(struct sk_buff *skb, struct netlink_callback *cb) { diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c index 363938435476..7b97f6e2075f 100644 --- a/drivers/infiniband/core/iwpm_util.c +++ b/drivers/infiniband/core/iwpm_util.c @@ -51,6 +51,12 @@ static DEFINE_SPINLOCK(iwpm_reminfo_lock); static DEFINE_MUTEX(iwpm_admin_lock); static struct iwpm_admin_data iwpm_admin; +/** + * iwpm_init - Allocate resources for the iwarp port mapper + * @nl_client: The index of the netlink client + * + * Should be called when network interface goes up. + */ int iwpm_init(u8 nl_client) { int ret = 0; @@ -87,6 +93,12 @@ init_exit: static void free_hash_bucket(void); static void free_reminfo_bucket(void); +/** + * iwpm_exit - Deallocate resources for the iwarp port mapper + * @nl_client: The index of the netlink client + * + * Should be called when network interface goes down. + */ int iwpm_exit(u8 nl_client) { @@ -112,6 +124,14 @@ int iwpm_exit(u8 nl_client) static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage *, struct sockaddr_storage *); +/** + * iwpm_create_mapinfo - Store local and mapped IPv4/IPv6 address + * info in a hash table + * @local_addr: Local ip/tcp address + * @mapped_addr: Mapped local ip/tcp address + * @nl_client: The index of the netlink client + * @map_flags: IWPM mapping flags + */ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr, struct sockaddr_storage *mapped_sockaddr, u8 nl_client, u32 map_flags) @@ -151,6 +171,15 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr, return ret; } +/** + * iwpm_remove_mapinfo - Remove local and mapped IPv4/IPv6 address + * info from the hash table + * @local_addr: Local ip/tcp address + * @mapped_local_addr: Mapped local ip/tcp address + * + * Returns err code if mapping info is not found in the hash table, + * otherwise returns 0 + */ int iwpm_remove_mapinfo(struct sockaddr_storage *local_sockaddr, struct sockaddr_storage *mapped_local_addr) { @@ -251,6 +280,17 @@ void iwpm_add_remote_info(struct iwpm_remote_info *rem_info) spin_unlock_irqrestore(&iwpm_reminfo_lock, flags); } +/** + * iwpm_get_remote_info - Get the remote connecting peer address info + * + * @mapped_loc_addr: Mapped local address of the listening peer + * @mapped_rem_addr: Mapped remote address of the connecting peer + * @remote_addr: To store the remote address of the connecting peer + * @nl_client: The index of the netlink client + * + * The remote address info is retrieved and provided to the client in + * the remote_addr. After that it is removed from the hash table + */ int iwpm_get_remote_info(struct sockaddr_storage *mapped_loc_addr, struct sockaddr_storage *mapped_rem_addr, struct sockaddr_storage *remote_addr, diff --git a/include/rdma/iw_portmap.h b/include/rdma/iw_portmap.h index 84fac196ef80..b9fee7feeeb5 100644 --- a/include/rdma/iw_portmap.h +++ b/include/rdma/iw_portmap.h @@ -61,177 +61,28 @@ struct iwpm_sa_data { u32 flags; }; -/** - * iwpm_init - Allocate resources for the iwarp port mapper - * - * Should be called when network interface goes up. - */ int iwpm_init(u8); - -/** - * iwpm_exit - Deallocate resources for the iwarp port mapper - * - * Should be called when network interface goes down. - */ int iwpm_exit(u8); - -/** - * iwpm_valid_pid - Check if the userspace iwarp port mapper pid is valid - * - * Returns true if the pid is greater than zero, otherwise returns false - */ int iwpm_valid_pid(void); - -/** - * iwpm_register_pid - Send a netlink query to userspace - * to get the iwarp port mapper pid - * @pm_msg: Contains driver info to send to the userspace port mapper - * @nl_client: The index of the netlink client - */ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client); - -/** - * iwpm_add_mapping - Send a netlink add mapping request to - * the userspace port mapper - * @pm_msg: Contains the local ip/tcp address info to send - * @nl_client: The index of the netlink client - * - * If the request is successful, the pm_msg stores - * the port mapper response (mapped address info) - */ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client); - -/** - * iwpm_add_and_query_mapping - Send a netlink add and query mapping request - * to the userspace port mapper - * @pm_msg: Contains the local and remote ip/tcp address info to send - * @nl_client: The index of the netlink client - * - * If the request is successful, the pm_msg stores the - * port mapper response (mapped local and remote address info) - */ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client); - -/** - * iwpm_remove_mapping - Send a netlink remove mapping request - * to the userspace port mapper - * - * @local_addr: Local ip/tcp address to remove - * @nl_client: The index of the netlink client - */ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client); - -/** - * iwpm_register_pid_cb - Process the port mapper response to - * iwpm_register_pid query - * @skb: - * @cb: Contains the received message (payload and netlink header) - * - * If successful, the function receives the userspace port mapper pid - * which is used in future communication with the port mapper - */ int iwpm_register_pid_cb(struct sk_buff *, struct netlink_callback *); - -/** - * iwpm_add_mapping_cb - Process the port mapper response to - * iwpm_add_mapping request - * @skb: - * @cb: Contains the received message (payload and netlink header) - */ int iwpm_add_mapping_cb(struct sk_buff *, struct netlink_callback *); - -/** - * iwpm_add_and_query_mapping_cb - Process the port mapper response to - * iwpm_add_and_query_mapping request - * @skb: - * @cb: Contains the received message (payload and netlink header) - */ int iwpm_add_and_query_mapping_cb(struct sk_buff *, struct netlink_callback *); - -/** - * iwpm_remote_info_cb - Process remote connecting peer address info, which - * the port mapper has received from the connecting peer - * - * @cb: Contains the received message (payload and netlink header) - * - * Stores the IPv4/IPv6 address info in a hash table - */ int iwpm_remote_info_cb(struct sk_buff *, struct netlink_callback *); - -/** - * iwpm_mapping_error_cb - Process port mapper notification for error - * - * @skb: - * @cb: Contains the received message (payload and netlink header) - */ int iwpm_mapping_error_cb(struct sk_buff *, struct netlink_callback *); - -/** - * iwpm_mapping_info_cb - Process a notification that the userspace - * port mapper daemon is started - * @skb: - * @cb: Contains the received message (payload and netlink header) - * - * Using the received port mapper pid, send all the local mapping - * info records to the userspace port mapper - */ int iwpm_mapping_info_cb(struct sk_buff *, struct netlink_callback *); - -/** - * iwpm_ack_mapping_info_cb - Process the port mapper ack for - * the provided local mapping info records - * @skb: - * @cb: Contains the received message (payload and netlink header) - */ int iwpm_ack_mapping_info_cb(struct sk_buff *, struct netlink_callback *); - -/** - * iwpm_get_remote_info - Get the remote connecting peer address info - * - * @mapped_loc_addr: Mapped local address of the listening peer - * @mapped_rem_addr: Mapped remote address of the connecting peer - * @remote_addr: To store the remote address of the connecting peer - * @nl_client: The index of the netlink client - * - * The remote address info is retrieved and provided to the client in - * the remote_addr. After that it is removed from the hash table - */ int iwpm_get_remote_info(struct sockaddr_storage *mapped_loc_addr, struct sockaddr_storage *mapped_rem_addr, struct sockaddr_storage *remote_addr, u8 nl_client); - -/** - * iwpm_create_mapinfo - Store local and mapped IPv4/IPv6 address - * info in a hash table - * @local_addr: Local ip/tcp address - * @mapped_addr: Mapped local ip/tcp address - * @nl_client: The index of the netlink client - * @map_flags: IWPM mapping flags - */ int iwpm_create_mapinfo(struct sockaddr_storage *local_addr, struct sockaddr_storage *mapped_addr, u8 nl_client, u32 map_flags); - -/** - * iwpm_remove_mapinfo - Remove local and mapped IPv4/IPv6 address - * info from the hash table - * @local_addr: Local ip/tcp address - * @mapped_addr: Mapped local ip/tcp address - * - * Returns err code if mapping info is not found in the hash table, - * otherwise returns 0 - */ int iwpm_remove_mapinfo(struct sockaddr_storage *local_addr, struct sockaddr_storage *mapped_addr); -/** - * iwpm_hello_cb - Process a hello message from iwpmd - * - * @skb: - * @cb: Contains the received message (payload and netlink header) - * - * Using the received port mapper pid, send the kernel's abi_version - * after adjusting it to support the iwpmd version. - */ int iwpm_hello_cb(struct sk_buff *skb, struct netlink_callback *cb); #endif /* _IW_PORTMAP_H */ -- cgit v1.2.3 From 385156c5f2a61834666f079ee66338f177c65c28 Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Wed, 23 Jan 2019 19:29:44 -0800 Subject: IB/hfi: Move RC functions into a header file This patch moves some RC helper functions into a header file so that they can be called from both RC and TID RDMA functions. In addition, a common function for rewinding a request is created in rdmavt so that it can be shared between qib and hfi1 driver. Reviewed-by: Mike Marciniszyn Signed-off-by: Mitko Haralanov Signed-off-by: Kaike Wan Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/rc.c | 119 +++++++++++++++---------------------- drivers/infiniband/hw/hfi1/rc.h | 50 ++++++++++++++++ drivers/infiniband/hw/qib/qib_rc.c | 7 +-- drivers/infiniband/sw/rdmavt/rc.c | 13 ++++ include/rdma/rdmavt_qp.h | 10 ++++ 5 files changed, 123 insertions(+), 76 deletions(-) create mode 100644 drivers/infiniband/hw/hfi1/rc.h (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 092d5eba980f..6e74cd3814b8 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -51,28 +51,48 @@ #include "hfi.h" #include "qp.h" +#include "rc.h" #include "verbs_txreq.h" #include "trace.h" -/* cut down ridiculously long IB macro names */ -#define OP(x) RC_OP(x) - -static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, - struct rvt_swqe *wqe, - struct hfi1_ibport *ibp); - -static u32 restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe, - u32 psn, u32 pmtu) +struct rvt_ack_entry *find_prev_entry(struct rvt_qp *qp, u32 psn, u8 *prev, + u8 *prev_ack, bool *scheduled) + __must_hold(&qp->s_lock) { - u32 len; + struct rvt_ack_entry *e = NULL; + u8 i, p; + bool s = true; - len = delta_psn(psn, wqe->psn) * pmtu; - ss->sge = wqe->sg_list[0]; - ss->sg_list = wqe->sg_list + 1; - ss->num_sge = wqe->wr.num_sge; - ss->total_len = wqe->length; - rvt_skip_sge(ss, len, false); - return wqe->length - len; + for (i = qp->r_head_ack_queue; ; i = p) { + if (i == qp->s_tail_ack_queue) + s = false; + if (i) + p = i - 1; + else + p = rvt_size_atomic(ib_to_rvt(qp->ibqp.device)); + if (p == qp->r_head_ack_queue) { + e = NULL; + break; + } + e = &qp->s_ack_queue[p]; + if (!e->opcode) { + e = NULL; + break; + } + if (cmp_psn(psn, e->psn) >= 0) { + if (p == qp->s_tail_ack_queue && + cmp_psn(psn, e->lpsn) <= 0) + s = false; + break; + } + } + if (prev) + *prev = p; + if (prev_ack) + *prev_ack = i; + if (scheduled) + *scheduled = s; + return e; } /** @@ -1229,9 +1249,9 @@ static inline void update_last_psn(struct rvt_qp *qp, u32 psn) * This is similar to hfi1_send_complete but has to check to be sure * that the SGEs are not being referenced if the SWQE is being resent. */ -static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, - struct rvt_swqe *wqe, - struct hfi1_ibport *ibp) +struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, + struct rvt_swqe *wqe, + struct hfi1_ibport *ibp) { lockdep_assert_held(&qp->s_lock); /* @@ -1314,8 +1334,8 @@ static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, * May be called at interrupt level, with the QP s_lock held. * Returns 1 if OK, 0 if current operation should be aborted (NAK). */ -static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, - u64 val, struct hfi1_ctxtdata *rcd) +int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, + u64 val, struct hfi1_ctxtdata *rcd) { struct hfi1_ibport *ibp; enum ib_wc_status status; @@ -1754,16 +1774,6 @@ bail: return; } -static inline void rc_defered_ack(struct hfi1_ctxtdata *rcd, - struct rvt_qp *qp) -{ - if (list_empty(&qp->rspwait)) { - qp->r_flags |= RVT_R_RSP_NAK; - rvt_get_qp(qp); - list_add_tail(&qp->rspwait, &rcd->qp_wait_list); - } -} - static inline void rc_cancel_ack(struct rvt_qp *qp) { qp->r_adefered = 0; @@ -1796,8 +1806,9 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data, struct hfi1_ibport *ibp = rcd_to_iport(rcd); struct rvt_ack_entry *e; unsigned long flags; - u8 i, prev; - int old_req; + u8 prev; + u8 mra; /* most recent ACK */ + bool old_req; trace_hfi1_rcv_error(qp, psn); if (diff > 0) { @@ -1843,29 +1854,8 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data, spin_lock_irqsave(&qp->s_lock, flags); - for (i = qp->r_head_ack_queue; ; i = prev) { - if (i == qp->s_tail_ack_queue) - old_req = 0; - if (i) - prev = i - 1; - else - prev = rvt_size_atomic(ib_to_rvt(qp->ibqp.device)); - if (prev == qp->r_head_ack_queue) { - e = NULL; - break; - } - e = &qp->s_ack_queue[prev]; - if (!e->opcode) { - e = NULL; - break; - } - if (cmp_psn(psn, e->psn) >= 0) { - if (prev == qp->s_tail_ack_queue && - cmp_psn(psn, e->lpsn) <= 0) - old_req = 0; - break; - } - } + e = find_prev_entry(qp, psn, &prev, &mra, &old_req); + switch (opcode) { case OP(RDMA_READ_REQUEST): { struct ib_reth *reth; @@ -1940,7 +1930,7 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data, * Resend the most recent ACK if this request is * after all the previous RDMA reads and atomics. */ - if (i == qp->r_head_ack_queue) { + if (mra == qp->r_head_ack_queue) { spin_unlock_irqrestore(&qp->s_lock, flags); qp->r_nak_state = 0; qp->r_ack_psn = qp->r_psn - 1; @@ -1951,7 +1941,7 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data, * Resend the RDMA read or atomic op which * ACKs this duplicate request. */ - qp->s_tail_ack_queue = i; + qp->s_tail_ack_queue = mra; break; } qp->s_ack_state = OP(ACKNOWLEDGE); @@ -1968,17 +1958,6 @@ send_ack: return 0; } -static inline void update_ack_queue(struct rvt_qp *qp, unsigned n) -{ - unsigned next; - - next = n + 1; - if (next > rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) - next = 0; - qp->s_tail_ack_queue = next; - qp->s_ack_state = OP(ACKNOWLEDGE); -} - static void log_cca_event(struct hfi1_pportdata *ppd, u8 sl, u32 rlid, u32 lqpn, u32 rqpn, u8 svc_type) { diff --git a/drivers/infiniband/hw/hfi1/rc.h b/drivers/infiniband/hw/hfi1/rc.h new file mode 100644 index 000000000000..4329eadcb3df --- /dev/null +++ b/drivers/infiniband/hw/hfi1/rc.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* + * Copyright(c) 2018 Intel Corporation. + * + */ + +#ifndef HFI1_RC_H +#define HFI1_RC_H + +/* cut down ridiculously long IB macro names */ +#define OP(x) IB_OPCODE_RC_##x + +static inline void update_ack_queue(struct rvt_qp *qp, unsigned int n) +{ + unsigned int next; + + next = n + 1; + if (next > rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) + next = 0; + qp->s_tail_ack_queue = next; + qp->s_ack_state = OP(ACKNOWLEDGE); +} + +static inline void rc_defered_ack(struct hfi1_ctxtdata *rcd, + struct rvt_qp *qp) +{ + if (list_empty(&qp->rspwait)) { + qp->r_flags |= RVT_R_RSP_NAK; + rvt_get_qp(qp); + list_add_tail(&qp->rspwait, &rcd->qp_wait_list); + } +} + +static inline u32 restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe, + u32 psn, u32 pmtu) +{ + u32 len; + + len = delta_psn(psn, wqe->psn) * pmtu; + return rvt_restart_sge(ss, wqe, len); +} + +struct rvt_ack_entry *find_prev_entry(struct rvt_qp *qp, u32 psn, u8 *prev, + u8 *prev_ack, bool *scheduled); +int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, u64 val, + struct hfi1_ctxtdata *rcd); +struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, struct rvt_swqe *wqe, + struct hfi1_ibport *ibp); + +#endif /* HFI1_RC_H */ diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c index 6fa002940451..50dd9811b088 100644 --- a/drivers/infiniband/hw/qib/qib_rc.c +++ b/drivers/infiniband/hw/qib/qib_rc.c @@ -45,12 +45,7 @@ static u32 restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe, u32 len; len = ((psn - wqe->psn) & QIB_PSN_MASK) * pmtu; - ss->sge = wqe->sg_list[0]; - ss->sg_list = wqe->sg_list + 1; - ss->num_sge = wqe->wr.num_sge; - ss->total_len = wqe->length; - rvt_skip_sge(ss, len, false); - return wqe->length - len; + return rvt_restart_sge(ss, wqe, len); } /** diff --git a/drivers/infiniband/sw/rdmavt/rc.c b/drivers/infiniband/sw/rdmavt/rc.c index 6131cc558bdb..8d71647820a8 100644 --- a/drivers/infiniband/sw/rdmavt/rc.c +++ b/drivers/infiniband/sw/rdmavt/rc.c @@ -187,3 +187,16 @@ void rvt_get_credit(struct rvt_qp *qp, u32 aeth) } } EXPORT_SYMBOL(rvt_get_credit); + +/* rvt_restart_sge - rewind the sge state for a wqe */ +u32 rvt_restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe, u32 len) +{ + ss->sge = wqe->sg_list[0]; + ss->sg_list = wqe->sg_list + 1; + ss->num_sge = wqe->wr.num_sge; + ss->total_len = wqe->length; + rvt_skip_sge(ss, len, false); + return wqe->length - len; +} +EXPORT_SYMBOL(rvt_restart_sge); + diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index cbafb1878669..56a9221378d9 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -628,6 +628,16 @@ __be32 rvt_compute_aeth(struct rvt_qp *qp); */ void rvt_get_credit(struct rvt_qp *qp, u32 aeth); +/** + * rvt_restart_sge - rewind the sge state for a wqe + * @ss: the sge state pointer + * @wqe: the wqe to rewind + * @len: the data length from the start of the wqe in bytes + * + * Returns the remaining data length. + */ +u32 rvt_restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe, u32 len); + /** * @qp - the qp pair * @len - the length -- cgit v1.2.3 From 838b6fd2d9ca29998869e4d1ecf4566efe807666 Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Wed, 23 Jan 2019 19:30:07 -0800 Subject: IB/hfi1: TID RDMA RcvArray programming and TID allocation TID entries are used by hfi1 hardware to receive data payload from incoming packets directly into a user buffer and thus avoid data copying by software. This patch implements the functions for TID allocation, freeing, and programming TID RcvArray entries in hardware for kernel clients. TID entries are managed via lists of TID groups similar to PSM. Furthermore, to track TID resource allocation for each request, software flows are also allocated and freed as needed. Since software flows consume large amount of memory for tracking TID allocation and freeing, it is generally desirable to allocate them dynamically in the send queue and only for TID RDMA requests, but pre-allocate them for receive queue because the send queue could have thousands of entries while the receive queue has only a limited number of entries. Signed-off-by: Mitko Haralanov Signed-off-by: Ashutosh Dixit Signed-off-by: Mike Marciniszyn Signed-off-by: Kaike Wan Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/hfi.h | 2 + drivers/infiniband/hw/hfi1/init.c | 3 +- drivers/infiniband/hw/hfi1/tid_rdma.c | 877 +++++++++++++++++++++++++++++- drivers/infiniband/hw/hfi1/tid_rdma.h | 101 ++++ drivers/infiniband/hw/hfi1/user_exp_rcv.h | 1 - drivers/infiniband/hw/hfi1/verbs.c | 29 +- drivers/infiniband/hw/hfi1/verbs.h | 34 ++ drivers/infiniband/sw/rdmavt/qp.c | 2 +- include/rdma/rdmavt_qp.h | 2 + 9 files changed, 1033 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 78aa344c7403..1412ed157c98 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -303,6 +303,8 @@ struct hfi1_ctxtdata { spinlock_t exp_lock; /* Queue for QP's waiting for HW TID flows */ struct tid_queue flow_queue; + /* Queue for QP's waiting for HW receive array entries */ + struct tid_queue rarr_queue; /* when waiting for rcv or pioavail */ wait_queue_head_t wait; /* uuid from PSM */ diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 56830a514b92..d13304f7340d 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -372,6 +372,7 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa, mutex_init(&rcd->exp_mutex); spin_lock_init(&rcd->exp_lock); INIT_LIST_HEAD(&rcd->flow_queue.queue_head); + INIT_LIST_HEAD(&rcd->rarr_queue.queue_head); hfi1_cdbg(PROC, "setting up context %u\n", rcd->ctxt); @@ -1596,7 +1597,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd) struct hfi1_ctxtdata *rcd = dd->rcd[ctxt]; if (rcd) { - hfi1_clear_tids(rcd); + hfi1_free_ctxt_rcv_groups(rcd); hfi1_free_ctxt(rcd); } } diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 70671212808f..1d02b12590f6 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -8,6 +8,7 @@ #include "qp.h" #include "verbs.h" #include "tid_rdma.h" +#include "exp_rcv.h" #include "trace.h" #define RCV_TID_FLOW_TABLE_CTRL_FLOW_VALID_SMASK BIT_ULL(32) @@ -35,8 +36,14 @@ static u32 mask_generation(u32 a) #define HFI1_KERNEL_MIN_JKEY HFI1_ADMIN_JKEY_RANGE #define HFI1_KERNEL_MAX_JKEY (2 * HFI1_ADMIN_JKEY_RANGE - 1) +/* Maximum number of segments in flight per QP request. */ #define TID_RDMA_MAX_READ_SEGS_PER_REQ 6 #define TID_RDMA_MAX_WRITE_SEGS_PER_REQ 4 +#define MAX_REQ max_t(u16, TID_RDMA_MAX_READ_SEGS_PER_REQ, \ + TID_RDMA_MAX_WRITE_SEGS_PER_REQ) +#define MAX_FLOWS roundup_pow_of_two(MAX_REQ + 1) + +#define MAX_EXPECTED_PAGES (MAX_EXPECTED_BUFFER / PAGE_SIZE) #define TID_OPFN_QP_CTXT_MASK 0xff #define TID_OPFN_QP_CTXT_SHIFT 56 @@ -79,6 +86,11 @@ static u32 mask_generation(u32 a) */ static void tid_rdma_trigger_resume(struct work_struct *work); +static void hfi1_kern_exp_rcv_free_flows(struct tid_rdma_request *req); +static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req, + gfp_t gfp); +static void hfi1_init_trdma_req(struct rvt_qp *qp, + struct tid_rdma_request *req); static u64 tid_rdma_opfn_encode(struct tid_rdma_params *p) { @@ -230,7 +242,7 @@ int hfi1_kern_exp_rcv_init(struct hfi1_ctxtdata *rcd, int reinit) BUILD_BUG_ON(TID_RDMA_JKEY > HFI1_KERNEL_MAX_JKEY); rcd->jkey = TID_RDMA_JKEY; hfi1_set_ctxt_jkey(rcd->dd, rcd, rcd->jkey); - return 0; + return hfi1_alloc_ctxt_rcv_groups(rcd); } /** @@ -266,6 +278,7 @@ int hfi1_qp_priv_init(struct rvt_dev_info *rdi, struct rvt_qp *qp, struct ib_qp_init_attr *init_attr) { struct hfi1_qp_priv *qpriv = qp->priv; + int i, ret; qpriv->rcd = qp_to_rcd(rdi, qp); @@ -278,15 +291,75 @@ int hfi1_qp_priv_init(struct rvt_dev_info *rdi, struct rvt_qp *qp, qpriv->flow_state.generation = KERN_GENERATION_RESERVED; INIT_LIST_HEAD(&qpriv->tid_wait); + if (init_attr->qp_type == IB_QPT_RC && HFI1_CAP_IS_KSET(TID_RDMA)) { + struct hfi1_devdata *dd = qpriv->rcd->dd; + + qpriv->pages = kzalloc_node(TID_RDMA_MAX_PAGES * + sizeof(*qpriv->pages), + GFP_KERNEL, dd->node); + if (!qpriv->pages) + return -ENOMEM; + for (i = 0; i < qp->s_size; i++) { + struct hfi1_swqe_priv *priv; + struct rvt_swqe *wqe = rvt_get_swqe_ptr(qp, i); + + priv = kzalloc_node(sizeof(*priv), GFP_KERNEL, + dd->node); + if (!priv) + return -ENOMEM; + + hfi1_init_trdma_req(qp, &priv->tid_req); + priv->tid_req.e.swqe = wqe; + wqe->priv = priv; + } + for (i = 0; i < rvt_max_atomic(rdi); i++) { + struct hfi1_ack_priv *priv; + + priv = kzalloc_node(sizeof(*priv), GFP_KERNEL, + dd->node); + if (!priv) + return -ENOMEM; + + hfi1_init_trdma_req(qp, &priv->tid_req); + priv->tid_req.e.ack = &qp->s_ack_queue[i]; + + ret = hfi1_kern_exp_rcv_alloc_flows(&priv->tid_req, + GFP_KERNEL); + if (ret) { + kfree(priv); + return ret; + } + qp->s_ack_queue[i].priv = priv; + } + } + return 0; } void hfi1_qp_priv_tid_free(struct rvt_dev_info *rdi, struct rvt_qp *qp) { - struct hfi1_qp_priv *priv = qp->priv; - - if (qp->ibqp.qp_type == IB_QPT_RC && HFI1_CAP_IS_KSET(TID_RDMA)) - cancel_work_sync(&priv->opfn.opfn_work); + struct hfi1_qp_priv *qpriv = qp->priv; + struct rvt_swqe *wqe; + u32 i; + + if (qp->ibqp.qp_type == IB_QPT_RC && HFI1_CAP_IS_KSET(TID_RDMA)) { + for (i = 0; i < qp->s_size; i++) { + wqe = rvt_get_swqe_ptr(qp, i); + kfree(wqe->priv); + wqe->priv = NULL; + } + for (i = 0; i < rvt_max_atomic(rdi); i++) { + struct hfi1_ack_priv *priv = qp->s_ack_queue[i].priv; + + if (priv) + hfi1_kern_exp_rcv_free_flows(&priv->tid_req); + kfree(priv); + qp->s_ack_queue[i].priv = NULL; + } + cancel_work_sync(&qpriv->opfn.opfn_work); + kfree(qpriv->pages); + qpriv->pages = NULL; + } } /* Flow and tid waiter functions */ @@ -540,6 +613,7 @@ void hfi1_tid_rdma_flush_wait(struct rvt_qp *qp) struct hfi1_qp_priv *priv = qp->priv; _tid_rdma_flush_wait(qp, &priv->rcd->flow_queue); + _tid_rdma_flush_wait(qp, &priv->rcd->rarr_queue); } /* Flow functions */ @@ -702,3 +776,796 @@ void hfi1_kern_init_ctxt_generations(struct hfi1_ctxtdata *rcd) kern_set_hw_flow(rcd, KERN_GENERATION_RESERVED, i); } } + +/* TID allocation functions */ +static u8 trdma_pset_order(struct tid_rdma_pageset *s) +{ + u8 count = s->count; + + return ilog2(count) + 1; +} + +/** + * tid_rdma_find_phys_blocks_4k - get groups base on mr info + * @npages - number of pages + * @pages - pointer to an array of page structs + * @list - page set array to return + * + * This routine returns the number of groups associated with + * the current sge information. This implementation is based + * on the expected receive find_phys_blocks() adjusted to + * use the MR information vs. the pfn. + * + * Return: + * the number of RcvArray entries + */ +static u32 tid_rdma_find_phys_blocks_4k(struct tid_rdma_flow *flow, + struct page **pages, + u32 npages, + struct tid_rdma_pageset *list) +{ + u32 pagecount, pageidx, setcount = 0, i; + void *vaddr, *this_vaddr; + + if (!npages) + return 0; + + /* + * Look for sets of physically contiguous pages in the user buffer. + * This will allow us to optimize Expected RcvArray entry usage by + * using the bigger supported sizes. + */ + vaddr = page_address(pages[0]); + for (pageidx = 0, pagecount = 1, i = 1; i <= npages; i++) { + this_vaddr = i < npages ? page_address(pages[i]) : NULL; + /* + * If the vaddr's are not sequential, pages are not physically + * contiguous. + */ + if (this_vaddr != (vaddr + PAGE_SIZE)) { + /* + * At this point we have to loop over the set of + * physically contiguous pages and break them down it + * sizes supported by the HW. + * There are two main constraints: + * 1. The max buffer size is MAX_EXPECTED_BUFFER. + * If the total set size is bigger than that + * program only a MAX_EXPECTED_BUFFER chunk. + * 2. The buffer size has to be a power of two. If + * it is not, round down to the closes power of + * 2 and program that size. + */ + while (pagecount) { + int maxpages = pagecount; + u32 bufsize = pagecount * PAGE_SIZE; + + if (bufsize > MAX_EXPECTED_BUFFER) + maxpages = + MAX_EXPECTED_BUFFER >> + PAGE_SHIFT; + else if (!is_power_of_2(bufsize)) + maxpages = + rounddown_pow_of_two(bufsize) >> + PAGE_SHIFT; + + list[setcount].idx = pageidx; + list[setcount].count = maxpages; + pagecount -= maxpages; + pageidx += maxpages; + setcount++; + } + pageidx = i; + pagecount = 1; + vaddr = this_vaddr; + } else { + vaddr += PAGE_SIZE; + pagecount++; + } + } + /* insure we always return an even number of sets */ + if (setcount & 1) + list[setcount++].count = 0; + return setcount; +} + +/** + * tid_flush_pages - dump out pages into pagesets + * @list - list of pagesets + * @idx - pointer to current page index + * @pages - number of pages to dump + * @sets - current number of pagesset + * + * This routine flushes out accumuated pages. + * + * To insure an even number of sets the + * code may add a filler. + * + * This can happen with when pages is not + * a power of 2 or pages is a power of 2 + * less than the maximum pages. + * + * Return: + * The new number of sets + */ + +static u32 tid_flush_pages(struct tid_rdma_pageset *list, + u32 *idx, u32 pages, u32 sets) +{ + while (pages) { + u32 maxpages = pages; + + if (maxpages > MAX_EXPECTED_PAGES) + maxpages = MAX_EXPECTED_PAGES; + else if (!is_power_of_2(maxpages)) + maxpages = rounddown_pow_of_two(maxpages); + list[sets].idx = *idx; + list[sets++].count = maxpages; + *idx += maxpages; + pages -= maxpages; + } + /* might need a filler */ + if (sets & 1) + list[sets++].count = 0; + return sets; +} + +/** + * tid_rdma_find_phys_blocks_8k - get groups base on mr info + * @pages - pointer to an array of page structs + * @npages - number of pages + * @list - page set array to return + * + * This routine parses an array of pages to compute pagesets + * in an 8k compatible way. + * + * pages are tested two at a time, i, i + 1 for contiguous + * pages and i - 1 and i contiguous pages. + * + * If any condition is false, any accumlated pages are flushed and + * v0,v1 are emitted as separate PAGE_SIZE pagesets + * + * Otherwise, the current 8k is totaled for a future flush. + * + * Return: + * The number of pagesets + * list set with the returned number of pagesets + * + */ +static u32 tid_rdma_find_phys_blocks_8k(struct tid_rdma_flow *flow, + struct page **pages, + u32 npages, + struct tid_rdma_pageset *list) +{ + u32 idx, sets = 0, i; + u32 pagecnt = 0; + void *v0, *v1, *vm1; + + if (!npages) + return 0; + for (idx = 0, i = 0, vm1 = NULL; i < npages; i += 2) { + /* get a new v0 */ + v0 = page_address(pages[i]); + v1 = i + 1 < npages ? + page_address(pages[i + 1]) : NULL; + /* compare i, i + 1 vaddr */ + if (v1 != (v0 + PAGE_SIZE)) { + /* flush out pages */ + sets = tid_flush_pages(list, &idx, pagecnt, sets); + /* output v0,v1 as two pagesets */ + list[sets].idx = idx++; + list[sets++].count = 1; + if (v1) { + list[sets].count = 1; + list[sets++].idx = idx++; + } else { + list[sets++].count = 0; + } + vm1 = NULL; + pagecnt = 0; + continue; + } + /* i,i+1 consecutive, look at i-1,i */ + if (vm1 && v0 != (vm1 + PAGE_SIZE)) { + /* flush out pages */ + sets = tid_flush_pages(list, &idx, pagecnt, sets); + pagecnt = 0; + } + /* pages will always be a multiple of 8k */ + pagecnt += 2; + /* save i-1 */ + vm1 = v1; + /* move to next pair */ + } + /* dump residual pages at end */ + sets = tid_flush_pages(list, &idx, npages - idx, sets); + /* by design cannot be odd sets */ + WARN_ON(sets & 1); + return sets; +} + +/** + * Find pages for one segment of a sge array represented by @ss. The function + * does not check the sge, the sge must have been checked for alignment with a + * prior call to hfi1_kern_trdma_ok. Other sge checking is done as part of + * rvt_lkey_ok and rvt_rkey_ok. Also, the function only modifies the local sge + * copy maintained in @ss->sge, the original sge is not modified. + * + * Unlike IB RDMA WRITE, we can't decrement ss->num_sge here because we are not + * releasing the MR reference count at the same time. Otherwise, we'll "leak" + * references to the MR. This difference requires that we keep track of progress + * into the sg_list. This is done by the cur_seg cursor in the tid_rdma_request + * structure. + */ +static u32 kern_find_pages(struct tid_rdma_flow *flow, + struct page **pages, + struct rvt_sge_state *ss, bool *last) +{ + struct tid_rdma_request *req = flow->req; + struct rvt_sge *sge = &ss->sge; + u32 length = flow->req->seg_len; + u32 len = PAGE_SIZE; + u32 i = 0; + + while (length && req->isge < ss->num_sge) { + pages[i++] = virt_to_page(sge->vaddr); + + sge->vaddr += len; + sge->length -= len; + sge->sge_length -= len; + if (!sge->sge_length) { + if (++req->isge < ss->num_sge) + *sge = ss->sg_list[req->isge - 1]; + } else if (sge->length == 0 && sge->mr->lkey) { + if (++sge->n >= RVT_SEGSZ) { + ++sge->m; + sge->n = 0; + } + sge->vaddr = sge->mr->map[sge->m]->segs[sge->n].vaddr; + sge->length = sge->mr->map[sge->m]->segs[sge->n].length; + } + length -= len; + } + + flow->length = flow->req->seg_len - length; + *last = req->isge == ss->num_sge ? false : true; + return i; +} + +static void dma_unmap_flow(struct tid_rdma_flow *flow) +{ + struct hfi1_devdata *dd; + int i; + struct tid_rdma_pageset *pset; + + dd = flow->req->rcd->dd; + for (i = 0, pset = &flow->pagesets[0]; i < flow->npagesets; + i++, pset++) { + if (pset->count && pset->addr) { + dma_unmap_page(&dd->pcidev->dev, + pset->addr, + PAGE_SIZE * pset->count, + DMA_FROM_DEVICE); + pset->mapped = 0; + } + } +} + +static int dma_map_flow(struct tid_rdma_flow *flow, struct page **pages) +{ + int i; + struct hfi1_devdata *dd = flow->req->rcd->dd; + struct tid_rdma_pageset *pset; + + for (i = 0, pset = &flow->pagesets[0]; i < flow->npagesets; + i++, pset++) { + if (pset->count) { + pset->addr = dma_map_page(&dd->pcidev->dev, + pages[pset->idx], + 0, + PAGE_SIZE * pset->count, + DMA_FROM_DEVICE); + + if (dma_mapping_error(&dd->pcidev->dev, pset->addr)) { + dma_unmap_flow(flow); + return -ENOMEM; + } + pset->mapped = 1; + } + } + return 0; +} + +static inline bool dma_mapped(struct tid_rdma_flow *flow) +{ + return !!flow->pagesets[0].mapped; +} + +/* + * Get pages pointers and identify contiguous physical memory chunks for a + * segment. All segments are of length flow->req->seg_len. + */ +static int kern_get_phys_blocks(struct tid_rdma_flow *flow, + struct page **pages, + struct rvt_sge_state *ss, bool *last) +{ + u8 npages; + + /* Reuse previously computed pagesets, if any */ + if (flow->npagesets) { + if (!dma_mapped(flow)) + return dma_map_flow(flow, pages); + return 0; + } + + npages = kern_find_pages(flow, pages, ss, last); + + if (flow->req->qp->pmtu == enum_to_mtu(OPA_MTU_4096)) + flow->npagesets = + tid_rdma_find_phys_blocks_4k(flow, pages, npages, + flow->pagesets); + else + flow->npagesets = + tid_rdma_find_phys_blocks_8k(flow, pages, npages, + flow->pagesets); + + return dma_map_flow(flow, pages); +} + +static inline void kern_add_tid_node(struct tid_rdma_flow *flow, + struct hfi1_ctxtdata *rcd, char *s, + struct tid_group *grp, u8 cnt) +{ + struct kern_tid_node *node = &flow->tnode[flow->tnode_cnt++]; + + WARN_ON_ONCE(flow->tnode_cnt >= + (TID_RDMA_MAX_SEGMENT_SIZE >> PAGE_SHIFT)); + if (WARN_ON_ONCE(cnt & 1)) + dd_dev_err(rcd->dd, + "unexpected odd allocation cnt %u map 0x%x used %u", + cnt, grp->map, grp->used); + + node->grp = grp; + node->map = grp->map; + node->cnt = cnt; +} + +/* + * Try to allocate pageset_count TID's from TID groups for a context + * + * This function allocates TID's without moving groups between lists or + * modifying grp->map. This is done as follows, being cogizant of the lists + * between which the TID groups will move: + * 1. First allocate complete groups of 8 TID's since this is more efficient, + * these groups will move from group->full without affecting used + * 2. If more TID's are needed allocate from used (will move from used->full or + * stay in used) + * 3. If we still don't have the required number of TID's go back and look again + * at a complete group (will move from group->used) + */ +static int kern_alloc_tids(struct tid_rdma_flow *flow) +{ + struct hfi1_ctxtdata *rcd = flow->req->rcd; + struct hfi1_devdata *dd = rcd->dd; + u32 ngroups, pageidx = 0; + struct tid_group *group = NULL, *used; + u8 use; + + flow->tnode_cnt = 0; + ngroups = flow->npagesets / dd->rcv_entries.group_size; + if (!ngroups) + goto used_list; + + /* First look at complete groups */ + list_for_each_entry(group, &rcd->tid_group_list.list, list) { + kern_add_tid_node(flow, rcd, "complete groups", group, + group->size); + + pageidx += group->size; + if (!--ngroups) + break; + } + + if (pageidx >= flow->npagesets) + goto ok; + +used_list: + /* Now look at partially used groups */ + list_for_each_entry(used, &rcd->tid_used_list.list, list) { + use = min_t(u32, flow->npagesets - pageidx, + used->size - used->used); + kern_add_tid_node(flow, rcd, "used groups", used, use); + + pageidx += use; + if (pageidx >= flow->npagesets) + goto ok; + } + + /* + * Look again at a complete group, continuing from where we left. + * However, if we are at the head, we have reached the end of the + * complete groups list from the first loop above + */ + if (group && &group->list == &rcd->tid_group_list.list) + goto bail_eagain; + group = list_prepare_entry(group, &rcd->tid_group_list.list, + list); + if (list_is_last(&group->list, &rcd->tid_group_list.list)) + goto bail_eagain; + group = list_next_entry(group, list); + use = min_t(u32, flow->npagesets - pageidx, group->size); + kern_add_tid_node(flow, rcd, "complete continue", group, use); + pageidx += use; + if (pageidx >= flow->npagesets) + goto ok; +bail_eagain: + return -EAGAIN; +ok: + return 0; +} + +static void kern_program_rcv_group(struct tid_rdma_flow *flow, int grp_num, + u32 *pset_idx) +{ + struct hfi1_ctxtdata *rcd = flow->req->rcd; + struct hfi1_devdata *dd = rcd->dd; + struct kern_tid_node *node = &flow->tnode[grp_num]; + struct tid_group *grp = node->grp; + struct tid_rdma_pageset *pset; + u32 pmtu_pg = flow->req->qp->pmtu >> PAGE_SHIFT; + u32 rcventry, npages = 0, pair = 0, tidctrl; + u8 i, cnt = 0; + + for (i = 0; i < grp->size; i++) { + rcventry = grp->base + i; + + if (node->map & BIT(i) || cnt >= node->cnt) { + rcv_array_wc_fill(dd, rcventry); + continue; + } + pset = &flow->pagesets[(*pset_idx)++]; + if (pset->count) { + hfi1_put_tid(dd, rcventry, PT_EXPECTED, + pset->addr, trdma_pset_order(pset)); + } else { + hfi1_put_tid(dd, rcventry, PT_INVALID, 0, 0); + } + npages += pset->count; + + rcventry -= rcd->expected_base; + tidctrl = pair ? 0x3 : rcventry & 0x1 ? 0x2 : 0x1; + /* + * A single TID entry will be used to use a rcvarr pair (with + * tidctrl 0x3), if ALL these are true (a) the bit pos is even + * (b) the group map shows current and the next bits as free + * indicating two consecutive rcvarry entries are available (c) + * we actually need 2 more entries + */ + pair = !(i & 0x1) && !((node->map >> i) & 0x3) && + node->cnt >= cnt + 2; + if (!pair) { + if (!pset->count) + tidctrl = 0x1; + flow->tid_entry[flow->tidcnt++] = + EXP_TID_SET(IDX, rcventry >> 1) | + EXP_TID_SET(CTRL, tidctrl) | + EXP_TID_SET(LEN, npages); + /* Efficient DIV_ROUND_UP(npages, pmtu_pg) */ + flow->npkts += (npages + pmtu_pg - 1) >> ilog2(pmtu_pg); + npages = 0; + } + + if (grp->used == grp->size - 1) + tid_group_move(grp, &rcd->tid_used_list, + &rcd->tid_full_list); + else if (!grp->used) + tid_group_move(grp, &rcd->tid_group_list, + &rcd->tid_used_list); + + grp->used++; + grp->map |= BIT(i); + cnt++; + } +} + +static void kern_unprogram_rcv_group(struct tid_rdma_flow *flow, int grp_num) +{ + struct hfi1_ctxtdata *rcd = flow->req->rcd; + struct hfi1_devdata *dd = rcd->dd; + struct kern_tid_node *node = &flow->tnode[grp_num]; + struct tid_group *grp = node->grp; + u32 rcventry; + u8 i, cnt = 0; + + for (i = 0; i < grp->size; i++) { + rcventry = grp->base + i; + + if (node->map & BIT(i) || cnt >= node->cnt) { + rcv_array_wc_fill(dd, rcventry); + continue; + } + + hfi1_put_tid(dd, rcventry, PT_INVALID, 0, 0); + + grp->used--; + grp->map &= ~BIT(i); + cnt++; + + if (grp->used == grp->size - 1) + tid_group_move(grp, &rcd->tid_full_list, + &rcd->tid_used_list); + else if (!grp->used) + tid_group_move(grp, &rcd->tid_used_list, + &rcd->tid_group_list); + } + if (WARN_ON_ONCE(cnt & 1)) { + struct hfi1_ctxtdata *rcd = flow->req->rcd; + struct hfi1_devdata *dd = rcd->dd; + + dd_dev_err(dd, "unexpected odd free cnt %u map 0x%x used %u", + cnt, grp->map, grp->used); + } +} + +static void kern_program_rcvarray(struct tid_rdma_flow *flow) +{ + u32 pset_idx = 0; + int i; + + flow->npkts = 0; + flow->tidcnt = 0; + for (i = 0; i < flow->tnode_cnt; i++) + kern_program_rcv_group(flow, i, &pset_idx); +} + +/** + * hfi1_kern_exp_rcv_setup() - setup TID's and flow for one segment of a + * TID RDMA request + * + * @req: TID RDMA request for which the segment/flow is being set up + * @ss: sge state, maintains state across successive segments of a sge + * @last: set to true after the last sge segment has been processed + * + * This function + * (1) finds a free flow entry in the flow circular buffer + * (2) finds pages and continuous physical chunks constituing one segment + * of an sge + * (3) allocates TID group entries for those chunks + * (4) programs rcvarray entries in the hardware corresponding to those + * TID's + * (5) computes a tidarray with formatted TID entries which can be sent + * to the sender + * (6) Reserves and programs HW flows. + * (7) It also manages queing the QP when TID/flow resources are not + * available. + * + * @req points to struct tid_rdma_request of which the segments are a part. The + * function uses qp, rcd and seg_len members of @req. In the absence of errors, + * req->flow_idx is the index of the flow which has been prepared in this + * invocation of function call. With flow = &req->flows[req->flow_idx], + * flow->tid_entry contains the TID array which the sender can use for TID RDMA + * sends and flow->npkts contains number of packets required to send the + * segment. + * + * hfi1_check_sge_align should be called prior to calling this function and if + * it signals error TID RDMA cannot be used for this sge and this function + * should not be called. + * + * For the queuing, caller must hold the flow->req->qp s_lock from the send + * engine and the function will procure the exp_lock. + * + * Return: + * The function returns -EAGAIN if sufficient number of TID/flow resources to + * map the segment could not be allocated. In this case the function should be + * called again with previous arguments to retry the TID allocation. There are + * no other error returns. The function returns 0 on success. + */ +int hfi1_kern_exp_rcv_setup(struct tid_rdma_request *req, + struct rvt_sge_state *ss, bool *last) + __must_hold(&req->qp->s_lock) +{ + struct tid_rdma_flow *flow = &req->flows[req->setup_head]; + struct hfi1_ctxtdata *rcd = req->rcd; + struct hfi1_qp_priv *qpriv = req->qp->priv; + unsigned long flags; + struct rvt_qp *fqp; + u16 clear_tail = req->clear_tail; + + lockdep_assert_held(&req->qp->s_lock); + /* + * We return error if either (a) we don't have space in the flow + * circular buffer, or (b) we already have max entries in the buffer. + * Max entries depend on the type of request we are processing and the + * negotiated TID RDMA parameters. + */ + if (!CIRC_SPACE(req->setup_head, clear_tail, MAX_FLOWS) || + CIRC_CNT(req->setup_head, clear_tail, MAX_FLOWS) >= + req->n_flows) + return -EINVAL; + + /* + * Get pages, identify contiguous physical memory chunks for the segment + * If we can not determine a DMA address mapping we will treat it just + * like if we ran out of space above. + */ + if (kern_get_phys_blocks(flow, qpriv->pages, ss, last)) { + hfi1_wait_kmem(flow->req->qp); + return -ENOMEM; + } + + spin_lock_irqsave(&rcd->exp_lock, flags); + if (kernel_tid_waiters(rcd, &rcd->rarr_queue, flow->req->qp)) + goto queue; + + /* + * At this point we know the number of pagesets and hence the number of + * TID's to map the segment. Allocate the TID's from the TID groups. If + * we cannot allocate the required number we exit and try again later + */ + if (kern_alloc_tids(flow)) + goto queue; + /* + * Finally program the TID entries with the pagesets, compute the + * tidarray and enable the HW flow + */ + kern_program_rcvarray(flow); + + /* + * Setup the flow state with relevant information. + * This information is used for tracking the sequence of data packets + * for the segment. + * The flow is setup here as this is the most accurate time and place + * to do so. Doing at a later time runs the risk of the flow data in + * qpriv getting out of sync. + */ + memset(&flow->flow_state, 0x0, sizeof(flow->flow_state)); + flow->idx = qpriv->flow_state.index; + flow->flow_state.generation = qpriv->flow_state.generation; + flow->flow_state.spsn = qpriv->flow_state.psn; + flow->flow_state.lpsn = flow->flow_state.spsn + flow->npkts - 1; + flow->flow_state.r_next_psn = + full_flow_psn(flow, flow->flow_state.spsn); + qpriv->flow_state.psn += flow->npkts; + + dequeue_tid_waiter(rcd, &rcd->rarr_queue, flow->req->qp); + /* get head before dropping lock */ + fqp = first_qp(rcd, &rcd->rarr_queue); + spin_unlock_irqrestore(&rcd->exp_lock, flags); + tid_rdma_schedule_tid_wakeup(fqp); + + req->setup_head = (req->setup_head + 1) & (MAX_FLOWS - 1); + return 0; +queue: + queue_qp_for_tid_wait(rcd, &rcd->rarr_queue, flow->req->qp); + spin_unlock_irqrestore(&rcd->exp_lock, flags); + return -EAGAIN; +} + +static void hfi1_tid_rdma_reset_flow(struct tid_rdma_flow *flow) +{ + flow->npagesets = 0; +} + +/* + * This function is called after one segment has been successfully sent to + * release the flow and TID HW/SW resources for that segment. The segments for a + * TID RDMA request are setup and cleared in FIFO order which is managed using a + * circular buffer. + */ +int hfi1_kern_exp_rcv_clear(struct tid_rdma_request *req) + __must_hold(&req->qp->s_lock) +{ + struct tid_rdma_flow *flow = &req->flows[req->clear_tail]; + struct hfi1_ctxtdata *rcd = req->rcd; + unsigned long flags; + int i; + struct rvt_qp *fqp; + + lockdep_assert_held(&req->qp->s_lock); + /* Exit if we have nothing in the flow circular buffer */ + if (!CIRC_CNT(req->setup_head, req->clear_tail, MAX_FLOWS)) + return -EINVAL; + + spin_lock_irqsave(&rcd->exp_lock, flags); + + for (i = 0; i < flow->tnode_cnt; i++) + kern_unprogram_rcv_group(flow, i); + /* To prevent double unprogramming */ + flow->tnode_cnt = 0; + /* get head before dropping lock */ + fqp = first_qp(rcd, &rcd->rarr_queue); + spin_unlock_irqrestore(&rcd->exp_lock, flags); + + dma_unmap_flow(flow); + + hfi1_tid_rdma_reset_flow(flow); + req->clear_tail = (req->clear_tail + 1) & (MAX_FLOWS - 1); + + if (fqp == req->qp) { + __trigger_tid_waiter(fqp); + rvt_put_qp(fqp); + } else { + tid_rdma_schedule_tid_wakeup(fqp); + } + + return 0; +} + +/* + * This function is called to release all the tid entries for + * a request. + */ +void hfi1_kern_exp_rcv_clear_all(struct tid_rdma_request *req) + __must_hold(&req->qp->s_lock) +{ + /* Use memory barrier for proper ordering */ + while (CIRC_CNT(req->setup_head, req->clear_tail, MAX_FLOWS)) { + if (hfi1_kern_exp_rcv_clear(req)) + break; + } +} + +/** + * hfi1_kern_exp_rcv_free_flows - free priviously allocated flow information + * @req - the tid rdma request to be cleaned + */ +static void hfi1_kern_exp_rcv_free_flows(struct tid_rdma_request *req) +{ + kfree(req->flows); + req->flows = NULL; +} + +/** + * __trdma_clean_swqe - clean up for large sized QPs + * @qp: the queue patch + * @wqe: the send wqe + */ +void __trdma_clean_swqe(struct rvt_qp *qp, struct rvt_swqe *wqe) +{ + struct hfi1_swqe_priv *p = wqe->priv; + + hfi1_kern_exp_rcv_free_flows(&p->tid_req); +} + +/* + * This can be called at QP create time or in the data path. + */ +static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req, + gfp_t gfp) +{ + struct tid_rdma_flow *flows; + int i; + + if (likely(req->flows)) + return 0; + flows = kmalloc_node(MAX_FLOWS * sizeof(*flows), gfp, + req->rcd->numa_id); + if (!flows) + return -ENOMEM; + /* mini init */ + for (i = 0; i < MAX_FLOWS; i++) { + flows[i].req = req; + flows[i].npagesets = 0; + flows[i].pagesets[0].mapped = 0; + } + req->flows = flows; + return 0; +} + +static void hfi1_init_trdma_req(struct rvt_qp *qp, + struct tid_rdma_request *req) +{ + struct hfi1_qp_priv *qpriv = qp->priv; + + /* + * Initialize various TID RDMA request variables. + * These variables are "static", which is why they + * can be pre-initialized here before the WRs has + * even been submitted. + * However, non-NULL values for these variables do not + * imply that this WQE has been enabled for TID RDMA. + * Drivers should check the WQE's opcode to determine + * if a request is a TID RDMA one or not. + */ + req->qp = qp; + req->rcd = qpriv->rcd; +} diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.h b/drivers/infiniband/hw/hfi1/tid_rdma.h index 3bc0aaf9568f..524baf8c8fac 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.h +++ b/drivers/infiniband/hw/hfi1/tid_rdma.h @@ -6,7 +6,16 @@ #ifndef HFI1_TID_RDMA_H #define HFI1_TID_RDMA_H +#include +#include "common.h" + +/* Add a convenience helper */ +#define CIRC_ADD(val, add, size) (((val) + (add)) & ((size) - 1)) +#define CIRC_NEXT(val, size) CIRC_ADD(val, 1, size) +#define CIRC_PREV(val, size) CIRC_ADD(val, -1, size) + #define TID_RDMA_MAX_SEGMENT_SIZE BIT(18) /* 256 KiB (for now) */ +#define TID_RDMA_MAX_PAGES (BIT(18) >> PAGE_SHIFT) struct tid_rdma_params { struct rcu_head rcu_head; @@ -36,6 +45,81 @@ struct tid_flow_state { u8 flags; }; +struct tid_rdma_request { + struct rvt_qp *qp; + struct hfi1_ctxtdata *rcd; + union { + struct rvt_swqe *swqe; + struct rvt_ack_entry *ack; + } e; + + struct tid_rdma_flow *flows; /* array of tid flows */ + u16 n_flows; /* size of the flow buffer window */ + u16 setup_head; /* flow index we are setting up */ + u16 clear_tail; /* flow index we are clearing */ + u16 flow_idx; /* flow index most recently set up */ + + u32 seg_len; + + u32 isge; /* index of "current" sge */ +}; + +/* + * When header suppression is used, PSNs associated with a "flow" are + * relevant (and not the PSNs maintained by verbs). Track per-flow + * PSNs here for a TID RDMA segment. + * + */ +struct flow_state { + u32 flags; + u32 resp_ib_psn; /* The IB PSN of the response for this flow */ + u32 generation; /* generation of flow */ + u32 spsn; /* starting PSN in TID space */ + u32 lpsn; /* last PSN in TID space */ + u32 r_next_psn; /* next PSN to be received (in TID space) */ +}; + +struct tid_rdma_pageset { + dma_addr_t addr : 48; /* Only needed for the first page */ + u8 idx: 8; + u8 count : 7; + u8 mapped: 1; +}; + +/** + * kern_tid_node - used for managing TID's in TID groups + * + * @grp_idx: rcd relative index to tid_group + * @map: grp->map captured prior to programming this TID group in HW + * @cnt: Only @cnt of available group entries are actually programmed + */ +struct kern_tid_node { + struct tid_group *grp; + u8 map; + u8 cnt; +}; + +/* Overall info for a TID RDMA segment */ +struct tid_rdma_flow { + /* + * While a TID RDMA segment is being transferred, it uses a QP number + * from the "KDETH section of QP numbers" (which is different from the + * QP number that originated the request). Bits 11-15 of these QP + * numbers identify the "TID flow" for the segment. + */ + struct flow_state flow_state; + struct tid_rdma_request *req; + u32 length; + u8 tnode_cnt; + u8 tidcnt; + u8 idx; + u8 npagesets; + u8 npkts; + struct kern_tid_node tnode[TID_RDMA_MAX_PAGES]; + struct tid_rdma_pageset pagesets[TID_RDMA_MAX_PAGES]; + u32 tid_entry[TID_RDMA_MAX_PAGES]; +}; + bool tid_rdma_conn_req(struct rvt_qp *qp, u64 *data); bool tid_rdma_conn_reply(struct rvt_qp *qp, u64 data); bool tid_rdma_conn_resp(struct rvt_qp *qp, u64 *data); @@ -43,6 +127,23 @@ void tid_rdma_conn_error(struct rvt_qp *qp); void tid_rdma_opfn_init(struct rvt_qp *qp, struct tid_rdma_params *p); int hfi1_kern_exp_rcv_init(struct hfi1_ctxtdata *rcd, int reinit); +int hfi1_kern_exp_rcv_setup(struct tid_rdma_request *req, + struct rvt_sge_state *ss, bool *last); +int hfi1_kern_exp_rcv_clear(struct tid_rdma_request *req); +void hfi1_kern_exp_rcv_clear_all(struct tid_rdma_request *req); +void __trdma_clean_swqe(struct rvt_qp *qp, struct rvt_swqe *wqe); + +/** + * trdma_clean_swqe - clean flows for swqe if large send queue + * @qp: the qp + * @wqe: the send wqe + */ +static inline void trdma_clean_swqe(struct rvt_qp *qp, struct rvt_swqe *wqe) +{ + if (!wqe->priv) + return; + __trdma_clean_swqe(qp, wqe); +} int hfi1_qp_priv_init(struct rvt_dev_info *rdi, struct rvt_qp *qp, struct ib_qp_init_attr *init_attr); diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h index e383cc01a2bf..43b105de1d54 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h @@ -48,7 +48,6 @@ */ #include "hfi.h" - #include "exp_rcv.h" struct tid_pageset { diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 571bfd549c2a..02c1873a976c 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -504,11 +504,28 @@ static void verbs_sdma_complete( hfi1_put_txreq(tx); } +void hfi1_wait_kmem(struct rvt_qp *qp) +{ + struct hfi1_qp_priv *priv = qp->priv; + struct ib_qp *ibqp = &qp->ibqp; + struct ib_device *ibdev = ibqp->device; + struct hfi1_ibdev *dev = to_idev(ibdev); + + if (list_empty(&priv->s_iowait.list)) { + if (list_empty(&dev->memwait)) + mod_timer(&dev->mem_timer, jiffies + 1); + qp->s_flags |= RVT_S_WAIT_KMEM; + list_add_tail(&priv->s_iowait.list, &dev->memwait); + priv->s_iowait.lock = &dev->iowait_lock; + trace_hfi1_qpsleep(qp, RVT_S_WAIT_KMEM); + rvt_get_qp(qp); + } +} + static int wait_kmem(struct hfi1_ibdev *dev, struct rvt_qp *qp, struct hfi1_pkt_state *ps) { - struct hfi1_qp_priv *priv = qp->priv; unsigned long flags; int ret = 0; @@ -517,15 +534,7 @@ static int wait_kmem(struct hfi1_ibdev *dev, write_seqlock(&dev->iowait_lock); list_add_tail(&ps->s_txreq->txreq.list, &ps->wait->tx_head); - if (list_empty(&priv->s_iowait.list)) { - if (list_empty(&dev->memwait)) - mod_timer(&dev->mem_timer, jiffies + 1); - qp->s_flags |= RVT_S_WAIT_KMEM; - list_add_tail(&priv->s_iowait.list, &dev->memwait); - priv->s_iowait.lock = &dev->iowait_lock; - trace_hfi1_qpsleep(qp, RVT_S_WAIT_KMEM); - rvt_get_qp(qp); - } + hfi1_wait_kmem(qp); write_sequnlock(&dev->iowait_lock); hfi1_qp_unbusy(qp, ps->wait); ret = -EBUSY; diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h index 9065e470bebb..94f198b47239 100644 --- a/drivers/infiniband/hw/hfi1/verbs.h +++ b/drivers/infiniband/hw/hfi1/verbs.h @@ -159,6 +159,7 @@ struct hfi1_qp_priv { struct sdma_engine *s_sde; /* current sde */ struct send_context *s_sendcontext; /* current sendcontext */ struct hfi1_ctxtdata *rcd; /* QP's receive context */ + struct page **pages; /* for TID page scan */ u32 tid_enqueue; /* saved when tid waited */ u8 s_sc; /* SC[0..4] for next packet */ struct iowait s_iowait; @@ -173,6 +174,14 @@ struct hfi1_qp_priv { u8 timeout_shift; /* account for number of packets per segment */ }; +struct hfi1_swqe_priv { + struct tid_rdma_request tid_req; +}; + +struct hfi1_ack_priv { + struct tid_rdma_request tid_req; +}; + /* * This structure is used to hold commonly lookedup and computed values during * the send engine progress. @@ -321,6 +330,21 @@ static inline u32 delta_psn(u32 a, u32 b) return (((int)a - (int)b) << PSN_SHIFT) >> PSN_SHIFT; } +/* + * Look through all the active flows for a TID RDMA request and find + * the one (if it exists) that contains the specified PSN. + */ +static inline u32 __full_flow_psn(struct flow_state *state, u32 psn) +{ + return mask_psn((state->generation << HFI1_KDETH_BTH_SEQ_SHIFT) | + (psn & HFI1_KDETH_BTH_SEQ_MASK)); +} + +static inline u32 full_flow_psn(struct tid_rdma_flow *flow, u32 psn) +{ + return __full_flow_psn(&flow->flow_state, psn); +} + struct verbs_txreq; void hfi1_put_txreq(struct verbs_txreq *tx); @@ -403,6 +427,16 @@ static inline bool opa_bth_is_migration(struct ib_other_headers *ohdr) return ohdr->bth[1] & cpu_to_be32(OPA_BTH_MIG_REQ); } +void hfi1_wait_kmem(struct rvt_qp *qp); + +static inline void hfi1_trdma_send_complete(struct rvt_qp *qp, + struct rvt_swqe *wqe, + enum ib_wc_status status) +{ + trdma_clean_swqe(qp, wqe); + rvt_send_complete(qp, wqe, status); +} + extern const enum ib_wc_opcode ib_hfi1_wc_opcode[]; extern const u8 hdr_len_by_opcode[]; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 16247d2a671d..c8e70cf69a8a 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1642,11 +1642,11 @@ int rvt_destroy_qp(struct ib_qp *ibqp) kref_put(&qp->ip->ref, rvt_release_mmap_info); else vfree(qp->r_rq.wq); - vfree(qp->s_wq); rdi->driver_f.qp_priv_free(rdi, qp); kfree(qp->s_ack_queue); rdma_destroy_ah_attr(&qp->remote_ah_attr); rdma_destroy_ah_attr(&qp->alt_ah_attr); + vfree(qp->s_wq); kfree(qp); return 0; } diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 56a9221378d9..9095a0b71250 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -174,6 +174,7 @@ struct rvt_swqe { u32 lpsn; /* last packet sequence number */ u32 ssn; /* send sequence number */ u32 length; /* total length of data in sg_list */ + void *priv; /* driver dependent field */ struct rvt_sge sg_list[0]; }; @@ -235,6 +236,7 @@ struct rvt_ack_entry { u32 lpsn; u8 opcode; u8 sent; + void *priv; }; #define RC_QP_SCALING_INTERVAL 5 -- cgit v1.2.3 From 742a3826cf82395e304df99f6494d04b0dd03a84 Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Wed, 23 Jan 2019 19:30:40 -0800 Subject: IB/hfi1: Add functions to build TID RDMA READ request This patch adds the helper functions to build the TID RDMA READ request on the requester side. The key is to allocate TID resources (TID flow and TID entries) and send the resource information to the responder side along with the read request. Since the TID resources are limited, each TID RDMA READ request has to be split into segments with a default segment size of 256K. A software flow is allocated to track the data transaction for each segment. The work request opcode, packet opcode, and packet formats for TID RDMA READ protocol are also defined in this patch. Reviewed-by: Mike Marciniszyn Signed-off-by: Kaike Wan Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/tid_rdma.c | 200 ++++++++++++++++++++++++++++++++++ drivers/infiniband/hw/hfi1/tid_rdma.h | 32 ++++++ drivers/infiniband/hw/hfi1/verbs.h | 9 ++ include/rdma/ib_hdrs.h | 9 +- include/rdma/tid_rdma_defs.h | 52 +++++++++ 5 files changed, 301 insertions(+), 1 deletion(-) create mode 100644 include/rdma/tid_rdma_defs.h (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 506b5a59ded5..56c8c10b5a85 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -6,11 +6,27 @@ #include "hfi.h" #include "qp.h" +#include "rc.h" #include "verbs.h" #include "tid_rdma.h" #include "exp_rcv.h" #include "trace.h" +/** + * DOC: TID RDMA READ protocol + * + * This is an end-to-end protocol at the hfi1 level between two nodes that + * improves performance by avoiding data copy on the requester side. It + * converts a qualified RDMA READ request into a TID RDMA READ request on + * the requester side and thereafter handles the request and response + * differently. To be qualified, the RDMA READ request should meet the + * following: + * -- The total data length should be greater than 256K; + * -- The total data length should be a multiple of 4K page size; + * -- Each local scatter-gather entry should be 4K page aligned; + * -- Each local scatter-gather entry should be a multiple of 4K page size; + */ + #define RCV_TID_FLOW_TABLE_CTRL_FLOW_VALID_SMASK BIT_ULL(32) #define RCV_TID_FLOW_TABLE_CTRL_HDR_SUPP_EN_SMASK BIT_ULL(33) #define RCV_TID_FLOW_TABLE_CTRL_KEEP_AFTER_SEQ_ERR_SMASK BIT_ULL(34) @@ -18,6 +34,9 @@ #define RCV_TID_FLOW_TABLE_STATUS_SEQ_MISMATCH_SMASK BIT_ULL(37) #define RCV_TID_FLOW_TABLE_STATUS_GEN_MISMATCH_SMASK BIT_ULL(38) +/* Maximum number of packets within a flow generation. */ +#define MAX_TID_FLOW_PSN BIT(HFI1_KDETH_BTH_SEQ_SHIFT) + #define GENERATION_MASK 0xFFFFF static u32 mask_generation(u32 a) @@ -45,6 +64,9 @@ static u32 mask_generation(u32 a) #define MAX_EXPECTED_PAGES (MAX_EXPECTED_BUFFER / PAGE_SIZE) +#define TID_RDMA_DESTQP_FLOW_SHIFT 11 +#define TID_RDMA_DESTQP_FLOW_MASK 0x1f + #define TID_OPFN_QP_CTXT_MASK 0xff #define TID_OPFN_QP_CTXT_SHIFT 56 #define TID_OPFN_QP_KDETH_MASK 0xff @@ -1597,3 +1619,181 @@ u64 hfi1_access_sw_tid_wait(const struct cntr_entry *entry, return dd->verbs_dev.n_tidwait; } + +/* TID RDMA READ functions */ +u32 hfi1_build_tid_rdma_read_packet(struct rvt_swqe *wqe, + struct ib_other_headers *ohdr, u32 *bth1, + u32 *bth2, u32 *len) +{ + struct tid_rdma_request *req = wqe_to_tid_req(wqe); + struct tid_rdma_flow *flow = &req->flows[req->flow_idx]; + struct rvt_qp *qp = req->qp; + struct hfi1_qp_priv *qpriv = qp->priv; + struct hfi1_swqe_priv *wpriv = wqe->priv; + struct tid_rdma_read_req *rreq = &ohdr->u.tid_rdma.r_req; + struct tid_rdma_params *remote; + u32 req_len = 0; + void *req_addr = NULL; + + /* This is the IB psn used to send the request */ + *bth2 = mask_psn(flow->flow_state.ib_spsn + flow->pkt); + + /* TID Entries for TID RDMA READ payload */ + req_addr = &flow->tid_entry[flow->tid_idx]; + req_len = sizeof(*flow->tid_entry) * + (flow->tidcnt - flow->tid_idx); + + memset(&ohdr->u.tid_rdma.r_req, 0, sizeof(ohdr->u.tid_rdma.r_req)); + wpriv->ss.sge.vaddr = req_addr; + wpriv->ss.sge.sge_length = req_len; + wpriv->ss.sge.length = wpriv->ss.sge.sge_length; + /* + * We can safely zero these out. Since the first SGE covers the + * entire packet, nothing else should even look at the MR. + */ + wpriv->ss.sge.mr = NULL; + wpriv->ss.sge.m = 0; + wpriv->ss.sge.n = 0; + + wpriv->ss.sg_list = NULL; + wpriv->ss.total_len = wpriv->ss.sge.sge_length; + wpriv->ss.num_sge = 1; + + /* Construct the TID RDMA READ REQ packet header */ + rcu_read_lock(); + remote = rcu_dereference(qpriv->tid_rdma.remote); + + KDETH_RESET(rreq->kdeth0, KVER, 0x1); + KDETH_RESET(rreq->kdeth1, JKEY, remote->jkey); + rreq->reth.vaddr = cpu_to_be64(wqe->rdma_wr.remote_addr + + req->cur_seg * req->seg_len + flow->sent); + rreq->reth.rkey = cpu_to_be32(wqe->rdma_wr.rkey); + rreq->reth.length = cpu_to_be32(*len); + rreq->tid_flow_psn = + cpu_to_be32((flow->flow_state.generation << + HFI1_KDETH_BTH_SEQ_SHIFT) | + ((flow->flow_state.spsn + flow->pkt) & + HFI1_KDETH_BTH_SEQ_MASK)); + rreq->tid_flow_qp = + cpu_to_be32(qpriv->tid_rdma.local.qp | + ((flow->idx & TID_RDMA_DESTQP_FLOW_MASK) << + TID_RDMA_DESTQP_FLOW_SHIFT) | + qpriv->rcd->ctxt); + rreq->verbs_qp = cpu_to_be32(qp->remote_qpn); + *bth1 &= ~RVT_QPN_MASK; + *bth1 |= remote->qp; + *bth2 |= IB_BTH_REQ_ACK; + rcu_read_unlock(); + + /* We are done with this segment */ + flow->sent += *len; + req->cur_seg++; + qp->s_state = TID_OP(READ_REQ); + req->ack_pending++; + req->flow_idx = (req->flow_idx + 1) & (MAX_FLOWS - 1); + qpriv->pending_tid_r_segs++; + qp->s_num_rd_atomic++; + + /* Set the TID RDMA READ request payload size */ + *len = req_len; + + return sizeof(ohdr->u.tid_rdma.r_req) / sizeof(u32); +} + +/* + * @len: contains the data length to read upon entry and the read request + * payload length upon exit. + */ +u32 hfi1_build_tid_rdma_read_req(struct rvt_qp *qp, struct rvt_swqe *wqe, + struct ib_other_headers *ohdr, u32 *bth1, + u32 *bth2, u32 *len) + __must_hold(&qp->s_lock) +{ + struct hfi1_qp_priv *qpriv = qp->priv; + struct tid_rdma_request *req = wqe_to_tid_req(wqe); + struct tid_rdma_flow *flow = NULL; + u32 hdwords = 0; + bool last; + bool retry = true; + u32 npkts = rvt_div_round_up_mtu(qp, *len); + + /* + * Check sync conditions. Make sure that there are no pending + * segments before freeing the flow. + */ +sync_check: + if (req->state == TID_REQUEST_SYNC) { + if (qpriv->pending_tid_r_segs) + goto done; + + hfi1_kern_clear_hw_flow(req->rcd, qp); + req->state = TID_REQUEST_ACTIVE; + } + + /* + * If the request for this segment is resent, the tid resources should + * have been allocated before. In this case, req->flow_idx should + * fall behind req->setup_head. + */ + if (req->flow_idx == req->setup_head) { + retry = false; + if (req->state == TID_REQUEST_RESEND) { + /* + * This is the first new segment for a request whose + * earlier segments have been re-sent. We need to + * set up the sge pointer correctly. + */ + restart_sge(&qp->s_sge, wqe, req->s_next_psn, + qp->pmtu); + req->isge = 0; + req->state = TID_REQUEST_ACTIVE; + } + + /* + * Check sync. The last PSN of each generation is reserved for + * RESYNC. + */ + if ((qpriv->flow_state.psn + npkts) > MAX_TID_FLOW_PSN - 1) { + req->state = TID_REQUEST_SYNC; + goto sync_check; + } + + /* Allocate the flow if not yet */ + if (hfi1_kern_setup_hw_flow(qpriv->rcd, qp)) + goto done; + + /* + * The following call will advance req->setup_head after + * allocating the tid entries. + */ + if (hfi1_kern_exp_rcv_setup(req, &qp->s_sge, &last)) { + req->state = TID_REQUEST_QUEUED; + + /* + * We don't have resources for this segment. The QP has + * already been queued. + */ + goto done; + } + } + + /* req->flow_idx should only be one slot behind req->setup_head */ + flow = &req->flows[req->flow_idx]; + flow->pkt = 0; + flow->tid_idx = 0; + flow->sent = 0; + if (!retry) { + /* Set the first and last IB PSN for the flow in use.*/ + flow->flow_state.ib_spsn = req->s_next_psn; + flow->flow_state.ib_lpsn = + flow->flow_state.ib_spsn + flow->npkts - 1; + } + + /* Calculate the next segment start psn.*/ + req->s_next_psn += flow->npkts; + + /* Build the packet header */ + hdwords = hfi1_build_tid_rdma_read_packet(wqe, ohdr, bth1, bth2, len); +done: + return hdwords; +} diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.h b/drivers/infiniband/hw/hfi1/tid_rdma.h index 3dbeaa8cb5b3..f692f3ff9419 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.h +++ b/drivers/infiniband/hw/hfi1/tid_rdma.h @@ -45,6 +45,19 @@ struct tid_flow_state { u8 flags; }; +enum tid_rdma_req_state { + TID_REQUEST_INACTIVE = 0, + TID_REQUEST_INIT, + TID_REQUEST_INIT_RESEND, + TID_REQUEST_ACTIVE, + TID_REQUEST_RESEND, + TID_REQUEST_RESEND_ACTIVE, + TID_REQUEST_QUEUED, + TID_REQUEST_SYNC, + TID_REQUEST_RNR_NAK, + TID_REQUEST_COMPLETE, +}; + struct tid_rdma_request { struct rvt_qp *qp; struct hfi1_ctxtdata *rcd; @@ -60,8 +73,13 @@ struct tid_rdma_request { u16 flow_idx; /* flow index most recently set up */ u32 seg_len; + u32 s_next_psn; /* IB PSN of next segment start for read */ + u32 cur_seg; /* index of current segment */ u32 isge; /* index of "current" sge */ + u32 ack_pending; /* num acks pending for this request */ + + enum tid_rdma_req_state state; }; /* @@ -77,6 +95,10 @@ struct flow_state { u32 spsn; /* starting PSN in TID space */ u32 lpsn; /* last PSN in TID space */ u32 r_next_psn; /* next PSN to be received (in TID space) */ + + /* For tid rdma read */ + u32 ib_spsn; /* starting PSN in Verbs space */ + u32 ib_lpsn; /* last PSn in Verbs space */ }; struct tid_rdma_pageset { @@ -110,11 +132,14 @@ struct tid_rdma_flow { struct flow_state flow_state; struct tid_rdma_request *req; u32 length; + u32 sent; u8 tnode_cnt; u8 tidcnt; + u8 tid_idx; u8 idx; u8 npagesets; u8 npkts; + u8 pkt; struct kern_tid_node tnode[TID_RDMA_MAX_PAGES]; struct tid_rdma_pageset pagesets[TID_RDMA_MAX_PAGES]; u32 tid_entry[TID_RDMA_MAX_PAGES]; @@ -159,4 +184,11 @@ struct cntr_entry; u64 hfi1_access_sw_tid_wait(const struct cntr_entry *entry, void *context, int vl, int mode, u64 data); +u32 hfi1_build_tid_rdma_read_packet(struct rvt_swqe *wqe, + struct ib_other_headers *ohdr, + u32 *bth1, u32 *bth2, u32 *len); +u32 hfi1_build_tid_rdma_read_req(struct rvt_qp *qp, struct rvt_swqe *wqe, + struct ib_other_headers *ohdr, u32 *bth1, + u32 *bth2, u32 *len); + #endif /* HFI1_TID_RDMA_H */ diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h index 20729454f181..2965b0957855 100644 --- a/drivers/infiniband/hw/hfi1/verbs.h +++ b/drivers/infiniband/hw/hfi1/verbs.h @@ -170,12 +170,16 @@ struct hfi1_qp_priv { struct rvt_qp *owner; u8 hdr_type; /* 9B or 16B */ unsigned long tid_timer_timeout_jiffies; + + /* For TID RDMA READ */ + u32 pending_tid_r_segs; /* Num of pending tid read segments */ u16 pkts_ps; /* packets per segment */ u8 timeout_shift; /* account for number of packets per segment */ }; struct hfi1_swqe_priv { struct tid_rdma_request tid_req; + struct rvt_sge_state ss; /* Used for TID RDMA READ Request */ }; struct hfi1_ack_priv { @@ -331,6 +335,11 @@ static inline u32 delta_psn(u32 a, u32 b) return (((int)a - (int)b) << PSN_SHIFT) >> PSN_SHIFT; } +static inline struct tid_rdma_request *wqe_to_tid_req(struct rvt_swqe *wqe) +{ + return &((struct hfi1_swqe_priv *)wqe->priv)->tid_req; +} + /* * Look through all the active flows for a TID RDMA request and find * the one (if it exists) that contains the specified PSN. diff --git a/include/rdma/ib_hdrs.h b/include/rdma/ib_hdrs.h index 6e35416170a3..58a0a0f99e7f 100644 --- a/include/rdma/ib_hdrs.h +++ b/include/rdma/ib_hdrs.h @@ -1,5 +1,5 @@ /* - * Copyright(c) 2016 Intel Corporation. + * Copyright(c) 2016 - 2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -100,6 +100,8 @@ struct ib_atomic_eth { __be64 compare_data; /* potentially unaligned */ } __packed; +#include + union ib_ehdrs { struct { __be32 deth[2]; @@ -117,6 +119,11 @@ union ib_ehdrs { __be32 aeth; __be32 ieth; struct ib_atomic_eth atomic_eth; + /* TID RDMA headers */ + union { + struct tid_rdma_read_req r_req; + struct tid_rdma_read_resp r_rsp; + } tid_rdma; } __packed; struct ib_other_headers { diff --git a/include/rdma/tid_rdma_defs.h b/include/rdma/tid_rdma_defs.h new file mode 100644 index 000000000000..1c431ea32b52 --- /dev/null +++ b/include/rdma/tid_rdma_defs.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* + * Copyright(c) 2018 Intel Corporation. + * + */ + +#ifndef TID_RDMA_DEFS_H +#define TID_RDMA_DEFS_H + +#include + +struct tid_rdma_read_req { + __le32 kdeth0; + __le32 kdeth1; + struct ib_reth reth; + __be32 tid_flow_psn; + __be32 tid_flow_qp; + __be32 verbs_qp; +}; + +struct tid_rdma_read_resp { + __le32 kdeth0; + __le32 kdeth1; + __be32 aeth; + __be32 reserved[4]; + __be32 verbs_psn; + __be32 verbs_qp; +}; + +/* + * TID RDMA Opcodes + */ +#define IB_OPCODE_TID_RDMA 0xe0 +enum { + IB_OPCODE_READ_REQ = 0x4, + IB_OPCODE_READ_RESP = 0x5, + + IB_OPCODE(TID_RDMA, READ_REQ), + IB_OPCODE(TID_RDMA, READ_RESP), +}; + +#define TID_OP(x) IB_OPCODE_TID_RDMA_##x + +/* + * Define TID RDMA specific WR opcodes. The ib_wr_opcode + * enum already provides some reserved values for use by + * low level drivers. Two of those are used but renamed + * to be more descriptive. + */ +#define IB_WR_TID_RDMA_READ IB_WR_RESERVED2 + +#endif /* TID_RDMA_DEFS_H */ -- cgit v1.2.3 From 039cd3daf19b9acbf080054d765cbceac842b6a0 Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Wed, 23 Jan 2019 19:31:57 -0800 Subject: IB/hfi1: Increment the retry timeout value for TID RDMA READ request The RC retry timeout value is based on the estimated time for the response packet to come back. However, for TID RDMA READ request, due to the use of header suppression, the driver is normally not notified for each incoming response packet until the last TID RDMA READ response packet. Consequently, the retry timeout value should be extended to cover the transaction time for the entire length of a segment (default 256K) instead of that for a single packet. This patch addresses the issue by introducing new retry timer functions to account for multiple packets and wrapper functions for backward compatibility. Reviewed-by: Mike Marciniszyn Signed-off-by: Kaike Wan Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/sw/rdmavt/qp.c | 11 ++++++----- include/rdma/rdma_vt.h | 12 +++++++++--- include/rdma/rdmavt_qp.h | 6 +++++- 3 files changed, 20 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index c8e70cf69a8a..2769ebdf89fb 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -2393,11 +2393,12 @@ static inline unsigned long rvt_aeth_to_usec(u32 aeth) } /* - * rvt_add_retry_timer - add/start a retry timer + * rvt_add_retry_timer_ext - add/start a retry timer * @qp - the QP + * @shift - timeout shift to wait for multiple packets * add a retry timer on the QP */ -void rvt_add_retry_timer(struct rvt_qp *qp) +void rvt_add_retry_timer_ext(struct rvt_qp *qp, u8 shift) { struct ib_qp *ibqp = &qp->ibqp; struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device); @@ -2405,11 +2406,11 @@ void rvt_add_retry_timer(struct rvt_qp *qp) lockdep_assert_held(&qp->s_lock); qp->s_flags |= RVT_S_TIMER; /* 4.096 usec. * (1 << qp->timeout) */ - qp->s_timer.expires = jiffies + qp->timeout_jiffies + - rdi->busy_jiffies; + qp->s_timer.expires = jiffies + rdi->busy_jiffies + + (qp->timeout_jiffies << shift); add_timer(&qp->s_timer); } -EXPORT_SYMBOL(rvt_add_retry_timer); +EXPORT_SYMBOL(rvt_add_retry_timer_ext); /** * rvt_add_rnr_timer - add/start an rnr timer diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h index 168e40be183c..87d66c9630d7 100644 --- a/include/rdma/rdma_vt.h +++ b/include/rdma/rdma_vt.h @@ -574,9 +574,10 @@ static inline struct rvt_qp *rvt_lookup_qpn(struct rvt_dev_info *rdi, /** * rvt_mod_retry_timer - mod a retry timer * @qp - the QP + * @shift - timeout shift to wait for multiple packets * Modify a potentially already running retry timer */ -static inline void rvt_mod_retry_timer(struct rvt_qp *qp) +static inline void rvt_mod_retry_timer_ext(struct rvt_qp *qp, u8 shift) { struct ib_qp *ibqp = &qp->ibqp; struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device); @@ -584,8 +585,13 @@ static inline void rvt_mod_retry_timer(struct rvt_qp *qp) lockdep_assert_held(&qp->s_lock); qp->s_flags |= RVT_S_TIMER; /* 4.096 usec. * (1 << qp->timeout) */ - mod_timer(&qp->s_timer, jiffies + qp->timeout_jiffies + - rdi->busy_jiffies); + mod_timer(&qp->s_timer, jiffies + rdi->busy_jiffies + + (qp->timeout_jiffies << shift)); +} + +static inline void rvt_mod_retry_timer(struct rvt_qp *qp) +{ + return rvt_mod_retry_timer_ext(qp, 0); } struct rvt_dev_info *rvt_alloc_device(size_t size, int nports); diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 9095a0b71250..d8d88d023092 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -688,7 +688,11 @@ enum hrtimer_restart rvt_rc_rnr_retry(struct hrtimer *t); void rvt_add_rnr_timer(struct rvt_qp *qp, u32 aeth); void rvt_del_timers_sync(struct rvt_qp *qp); void rvt_stop_rc_timers(struct rvt_qp *qp); -void rvt_add_retry_timer(struct rvt_qp *qp); +void rvt_add_retry_timer_ext(struct rvt_qp *qp, u8 shift); +static inline void rvt_add_retry_timer(struct rvt_qp *qp) +{ + rvt_add_retry_timer_ext(qp, 0); +} void rvt_copy_sge(struct rvt_qp *qp, struct rvt_sge_state *ss, void *data, u32 length, -- cgit v1.2.3 From c098bbb00cd1986cbb58ed1712643f80ed00fcc3 Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Wed, 23 Jan 2019 21:48:28 -0800 Subject: IB/hfi1: Build TID RDMA WRITE request This patch adds the functions to build TID RDMA WRITE request. The work request opcode, packet opcode, and packet formats for TID RDMA WRITE protocol are also defined in this patch. Signed-off-by: Mitko Haralanov Signed-off-by: Mike Marciniszyn Signed-off-by: Ashutosh Dixit Signed-off-by: Kaike Wan Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/qp.h | 2 ++ drivers/infiniband/hw/hfi1/tid_rdma.c | 38 ++++++++++++++++++++++++ drivers/infiniband/hw/hfi1/tid_rdma.h | 3 ++ include/rdma/ib_hdrs.h | 5 ++++ include/rdma/tid_rdma_defs.h | 56 +++++++++++++++++++++++++++++++++++ 5 files changed, 104 insertions(+) (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/qp.h b/drivers/infiniband/hw/hfi1/qp.h index ce25a27aa4a1..f74e2509e8b9 100644 --- a/drivers/infiniband/hw/hfi1/qp.h +++ b/drivers/infiniband/hw/hfi1/qp.h @@ -64,12 +64,14 @@ extern const struct rvt_operation_params hfi1_post_parms[]; * HFI1_S_AHG_CLEAR - have send engine clear ahg state * HFI1_S_WAIT_PIO_DRAIN - qp waiting for PIOs to drain * HFI1_S_WAIT_TID_SPACE - a QP is waiting for TID resource + * HFI1_S_WAIT_TID_RESP - waiting for a TID RDMA WRITE response * HFI1_S_MIN_BIT_MASK - the lowest bit that can be used by hfi1 */ #define HFI1_S_AHG_VALID 0x80000000 #define HFI1_S_AHG_CLEAR 0x40000000 #define HFI1_S_WAIT_PIO_DRAIN 0x20000000 #define HFI1_S_WAIT_TID_SPACE 0x10000000 +#define HFI1_S_WAIT_TID_RESP 0x08000000 #define HFI1_S_MIN_BIT_MASK 0x01000000 /* diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 0ee79403acaf..089e301d9bcd 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -2975,3 +2975,41 @@ void setup_tid_rdma_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe) exit: rcu_read_unlock(); } + +/* TID RDMA WRITE functions */ + +u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe, + struct ib_other_headers *ohdr, + u32 *bth1, u32 *bth2, u32 *len) +{ + struct hfi1_qp_priv *qpriv = qp->priv; + struct tid_rdma_request *req = wqe_to_tid_req(wqe); + struct tid_rdma_params *remote; + + rcu_read_lock(); + remote = rcu_dereference(qpriv->tid_rdma.remote); + /* + * Set the number of flow to be used based on negotiated + * parameters. + */ + req->n_flows = remote->max_write; + req->state = TID_REQUEST_ACTIVE; + + KDETH_RESET(ohdr->u.tid_rdma.w_req.kdeth0, KVER, 0x1); + KDETH_RESET(ohdr->u.tid_rdma.w_req.kdeth1, JKEY, remote->jkey); + ohdr->u.tid_rdma.w_req.reth.vaddr = + cpu_to_be64(wqe->rdma_wr.remote_addr + (wqe->length - *len)); + ohdr->u.tid_rdma.w_req.reth.rkey = + cpu_to_be32(wqe->rdma_wr.rkey); + ohdr->u.tid_rdma.w_req.reth.length = cpu_to_be32(*len); + ohdr->u.tid_rdma.w_req.verbs_qp = cpu_to_be32(qp->remote_qpn); + *bth1 &= ~RVT_QPN_MASK; + *bth1 |= remote->qp; + qp->s_state = TID_OP(WRITE_REQ); + qp->s_flags |= HFI1_S_WAIT_TID_RESP; + *bth2 |= IB_BTH_REQ_ACK; + *len = 0; + + rcu_read_unlock(); + return sizeof(ohdr->u.tid_rdma.w_req) / sizeof(u32); +} diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.h b/drivers/infiniband/hw/hfi1/tid_rdma.h index a53598ce45b2..baba539b2b80 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.h +++ b/drivers/infiniband/hw/hfi1/tid_rdma.h @@ -233,4 +233,7 @@ static inline void hfi1_setup_tid_rdma_wqe(struct rvt_qp *qp, setup_tid_rdma_wqe(qp, wqe); } +u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe, + struct ib_other_headers *ohdr, + u32 *bth1, u32 *bth2, u32 *len); #endif /* HFI1_TID_RDMA_H */ diff --git a/include/rdma/ib_hdrs.h b/include/rdma/ib_hdrs.h index 58a0a0f99e7f..9a90bd031e8c 100644 --- a/include/rdma/ib_hdrs.h +++ b/include/rdma/ib_hdrs.h @@ -123,6 +123,11 @@ union ib_ehdrs { union { struct tid_rdma_read_req r_req; struct tid_rdma_read_resp r_rsp; + struct tid_rdma_write_req w_req; + struct tid_rdma_write_resp w_rsp; + struct tid_rdma_write_data w_data; + struct tid_rdma_resync resync; + struct tid_rdma_ack ack; } tid_rdma; } __packed; diff --git a/include/rdma/tid_rdma_defs.h b/include/rdma/tid_rdma_defs.h index 1c431ea32b52..08fe47c7ad2c 100644 --- a/include/rdma/tid_rdma_defs.h +++ b/include/rdma/tid_rdma_defs.h @@ -27,16 +27,71 @@ struct tid_rdma_read_resp { __be32 verbs_qp; }; +struct tid_rdma_write_req { + __le32 kdeth0; + __le32 kdeth1; + struct ib_reth reth; + __be32 reserved[2]; + __be32 verbs_qp; +}; + +struct tid_rdma_write_resp { + __le32 kdeth0; + __le32 kdeth1; + __be32 aeth; + __be32 reserved[3]; + __be32 tid_flow_psn; + __be32 tid_flow_qp; + __be32 verbs_qp; +}; + +struct tid_rdma_write_data { + __le32 kdeth0; + __le32 kdeth1; + __be32 reserved[6]; + __be32 verbs_qp; +}; + +struct tid_rdma_resync { + __le32 kdeth0; + __le32 kdeth1; + __be32 reserved[6]; + __be32 verbs_qp; +}; + +struct tid_rdma_ack { + __le32 kdeth0; + __le32 kdeth1; + __be32 aeth; + __be32 reserved[2]; + __be32 tid_flow_psn; + __be32 verbs_psn; + __be32 tid_flow_qp; + __be32 verbs_qp; +}; + /* * TID RDMA Opcodes */ #define IB_OPCODE_TID_RDMA 0xe0 enum { + IB_OPCODE_WRITE_REQ = 0x0, + IB_OPCODE_WRITE_RESP = 0x1, + IB_OPCODE_WRITE_DATA = 0x2, + IB_OPCODE_WRITE_DATA_LAST = 0x3, IB_OPCODE_READ_REQ = 0x4, IB_OPCODE_READ_RESP = 0x5, + IB_OPCODE_RESYNC = 0x6, + IB_OPCODE_ACK = 0x7, + IB_OPCODE(TID_RDMA, WRITE_REQ), + IB_OPCODE(TID_RDMA, WRITE_RESP), + IB_OPCODE(TID_RDMA, WRITE_DATA), + IB_OPCODE(TID_RDMA, WRITE_DATA_LAST), IB_OPCODE(TID_RDMA, READ_REQ), IB_OPCODE(TID_RDMA, READ_RESP), + IB_OPCODE(TID_RDMA, RESYNC), + IB_OPCODE(TID_RDMA, ACK), }; #define TID_OP(x) IB_OPCODE_TID_RDMA_##x @@ -47,6 +102,7 @@ enum { * low level drivers. Two of those are used but renamed * to be more descriptive. */ +#define IB_WR_TID_RDMA_WRITE IB_WR_RESERVED1 #define IB_WR_TID_RDMA_READ IB_WR_RESERVED2 #endif /* TID_RDMA_DEFS_H */ -- cgit v1.2.3 From 4f9264d156dc6c154a8a6cfae780730bad45c6f8 Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Wed, 23 Jan 2019 21:48:48 -0800 Subject: IB/hfi1: Add an s_acked_ack_queue pointer The s_ack_queue is managed by two pointers into the ring: r_head_ack_queue and s_tail_ack_queue. r_head_ack_queue is the index of where the next received request is going to be placed and s_tail_ack_queue is the entry of the request currently being processed. This works perfectly fine for normal Verbs as the requests are processed one at a time and the s_tail_ack_queue is not moved until the request that it points to is fully completed. In this fashion, s_tail_ack_queue constantly chases r_head_ack_queue and the two pointers can easily be used to determine "queue full" and "queue empty" conditions. The detection of these two conditions are imported in determining when an old entry can safely be overwritten with a new received request and the resources associated with the old request be safely released. When pipelined TID RDMA WRITE is introduced into this mix, things look very different. r_head_ack_queue is still the point at which a newly received request will be inserted, s_tail_ack_queue is still the currently processed request. However, with pipelined TID RDMA WRITE requests, s_tail_ack_queue moves to the next request once all TID RDMA WRITE responses for that request have been sent. The rest of the protocol for a particular request is managed by other pointers specific to TID RDMA - r_tid_tail and r_tid_ack - which point to the entries for which the next TID RDMA DATA packets are going to arrive and the request for which the next TID RDMA ACK packets are to be generated, respectively. What this means is that entries in the ring, which are "behind" s_tail_ack_queue (entries which s_tail_ack_queue has gone past) are no longer considered complete. This is where the problem is - a newly received request could potentially overwrite a still active TID RDMA WRITE request. The reason why the TID RDMA pointers trail s_tail_ack_queue is that the normal Verbs send engine uses s_tail_ack_queue as the pointer for the next response. Since TID RDMA WRITE responses are processed by the normal Verbs send engine, s_tail_ack_queue had to be moved to the next entry once all TID RDMA WRITE response packets were sent to get the desired pipelining between requests. Doing otherwise would mean that the normal Verbs send engine would not be able to send the TID RDMA WRITE responses for the next TID RDMA request until the current one is fully completed. This patch introduces the s_acked_ack_queue index to point to the next request to complete on the responder side. For requests other than TID RDMA WRITE, s_acked_ack_queue should always be kept in sync with s_tail_ack_queue. For TID RDMA WRITE request, it may fall behind s_tail_ack_queue. Reviewed-by: Mike Marciniszyn Signed-off-by: Mitko Haralanov Signed-off-by: Kaike Wan Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/rc.c | 33 ++++++++++++++++++++++++++++----- drivers/infiniband/hw/hfi1/rc.h | 1 + drivers/infiniband/hw/hfi1/tid_rdma.c | 2 ++ drivers/infiniband/hw/hfi1/trace_tid.h | 10 ++++++++-- drivers/infiniband/sw/rdmavt/qp.c | 1 + include/rdma/rdmavt_qp.h | 1 + 6 files changed, 41 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 6c9ef572fc69..9dc8e524510e 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -120,6 +120,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, struct hfi1_qp_priv *priv = qp->priv; bool last_pkt; u32 delta; + u8 next = qp->s_tail_ack_queue; trace_hfi1_rsp_make_rc_ack(qp, 0); lockdep_assert_held(&qp->s_lock); @@ -149,9 +150,17 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, * response has been sent instead of only being * constructed. */ - if (++qp->s_tail_ack_queue > - rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) - qp->s_tail_ack_queue = 0; + if (++next > rvt_size_atomic(&dev->rdi)) + next = 0; + /* + * Only advance the s_acked_ack_queue pointer if there + * have been no TID RDMA requests. + */ + e = &qp->s_ack_queue[qp->s_tail_ack_queue]; + if (e->opcode != TID_OP(WRITE_REQ) && + qp->s_acked_ack_queue == qp->s_tail_ack_queue) + qp->s_acked_ack_queue = next; + qp->s_tail_ack_queue = next; /* FALLTHROUGH */ case OP(SEND_ONLY): case OP(ACKNOWLEDGE): @@ -172,6 +181,10 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, */ len = e->rdma_sge.sge_length; if (len && !e->rdma_sge.mr) { + if (qp->s_acked_ack_queue == + qp->s_tail_ack_queue) + qp->s_acked_ack_queue = + qp->r_head_ack_queue; qp->s_tail_ack_queue = qp->r_head_ack_queue; goto bail; } @@ -202,6 +215,10 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, */ len = e->rdma_sge.sge_length; if (len && !e->rdma_sge.mr) { + if (qp->s_acked_ack_queue == + qp->s_tail_ack_queue) + qp->s_acked_ack_queue = + qp->r_head_ack_queue; qp->s_tail_ack_queue = qp->r_head_ack_queue; goto bail; } @@ -2235,6 +2252,8 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data, e->psn = psn; if (old_req) goto unlock_done; + if (qp->s_acked_ack_queue == qp->s_tail_ack_queue) + qp->s_acked_ack_queue = prev; qp->s_tail_ack_queue = prev; break; } @@ -2248,6 +2267,8 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data, */ if (!e || e->opcode != (u8)opcode || old_req) goto unlock_done; + if (qp->s_tail_ack_queue == qp->s_acked_ack_queue) + qp->s_acked_ack_queue = prev; qp->s_tail_ack_queue = prev; break; } @@ -2274,6 +2295,8 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data, * Resend the RDMA read or atomic op which * ACKs this duplicate request. */ + if (qp->s_tail_ack_queue == qp->s_acked_ack_queue) + qp->s_acked_ack_queue = mra; qp->s_tail_ack_queue = mra; break; } @@ -2646,7 +2669,7 @@ send_last: if (next > rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) next = 0; spin_lock_irqsave(&qp->s_lock, flags); - if (unlikely(next == qp->s_tail_ack_queue)) { + if (unlikely(next == qp->s_acked_ack_queue)) { if (!qp->s_ack_queue[next].sent) goto nack_inv_unlck; update_ack_queue(qp, next); @@ -2723,7 +2746,7 @@ send_last: if (next > rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) next = 0; spin_lock_irqsave(&qp->s_lock, flags); - if (unlikely(next == qp->s_tail_ack_queue)) { + if (unlikely(next == qp->s_acked_ack_queue)) { if (!qp->s_ack_queue[next].sent) goto nack_inv_unlck; update_ack_queue(qp, next); diff --git a/drivers/infiniband/hw/hfi1/rc.h b/drivers/infiniband/hw/hfi1/rc.h index 4329eadcb3df..8e0935b9bf2a 100644 --- a/drivers/infiniband/hw/hfi1/rc.h +++ b/drivers/infiniband/hw/hfi1/rc.h @@ -18,6 +18,7 @@ static inline void update_ack_queue(struct rvt_qp *qp, unsigned int n) if (next > rvt_size_atomic(ib_to_rvt(qp->ibqp.device))) next = 0; qp->s_tail_ack_queue = next; + qp->s_acked_ack_queue = next; qp->s_ack_state = OP(ACKNOWLEDGE); } diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 089e301d9bcd..c320a99afb35 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -2044,6 +2044,8 @@ static int tid_rdma_rcv_error(struct hfi1_packet *packet, goto unlock; } /* Re-process old requests.*/ + if (qp->s_acked_ack_queue == qp->s_tail_ack_queue) + qp->s_acked_ack_queue = prev; qp->s_tail_ack_queue = prev; /* * Since the qp->s_tail_ack_queue is modified, the diff --git a/drivers/infiniband/hw/hfi1/trace_tid.h b/drivers/infiniband/hw/hfi1/trace_tid.h index b71638c22d4b..51f5b0e8da71 100644 --- a/drivers/infiniband/hw/hfi1/trace_tid.h +++ b/drivers/infiniband/hw/hfi1/trace_tid.h @@ -40,7 +40,7 @@ u16 hfi1_trace_get_tid_idx(u32 ent); #define RSP_INFO_PRN "[%s] qpn 0x%x state 0x%x s_state 0x%x psn 0x%x " \ "r_psn 0x%x r_state 0x%x r_flags 0x%x " \ "r_head_ack_queue %u s_tail_ack_queue %u " \ - "s_ack_state 0x%x " \ + "s_acked_ack_queue %u s_ack_state 0x%x " \ "s_nak_state 0x%x s_flags 0x%x ps_flags 0x%x " \ "iow_flags 0x%lx" @@ -62,7 +62,7 @@ u16 hfi1_trace_get_tid_idx(u32 ent); "s_next_psn 0x%x" #define RCV_ERR_PRN "[%s] qpn 0x%x s_flags 0x%x state 0x%x " \ - "s_tail_ack_queue %u " \ + "s_acked_ack_queue %u s_tail_ack_queue %u " \ "r_head_ack_queue %u opcode 0x%x psn 0x%x r_psn 0x%x " \ " diff %d" @@ -671,6 +671,7 @@ DECLARE_EVENT_CLASS(/* rsp_info */ __field(u8, r_flags) __field(u8, r_head_ack_queue) __field(u8, s_tail_ack_queue) + __field(u8, s_acked_ack_queue) __field(u8, s_ack_state) __field(u8, s_nak_state) __field(u8, r_nak_state) @@ -691,6 +692,7 @@ DECLARE_EVENT_CLASS(/* rsp_info */ __entry->r_flags = qp->r_flags; __entry->r_head_ack_queue = qp->r_head_ack_queue; __entry->s_tail_ack_queue = qp->s_tail_ack_queue; + __entry->s_acked_ack_queue = qp->s_acked_ack_queue; __entry->s_ack_state = qp->s_ack_state; __entry->s_nak_state = qp->s_nak_state; __entry->s_flags = qp->s_flags; @@ -709,6 +711,7 @@ DECLARE_EVENT_CLASS(/* rsp_info */ __entry->r_flags, __entry->r_head_ack_queue, __entry->s_tail_ack_queue, + __entry->s_acked_ack_queue, __entry->s_ack_state, __entry->s_nak_state, __entry->s_flags, @@ -1007,6 +1010,7 @@ DECLARE_EVENT_CLASS(/* rc_rcv_err */ __field(u32, qpn) __field(u32, s_flags) __field(u8, state) + __field(u8, s_acked_ack_queue) __field(u8, s_tail_ack_queue) __field(u8, r_head_ack_queue) __field(u32, opcode) @@ -1019,6 +1023,7 @@ DECLARE_EVENT_CLASS(/* rc_rcv_err */ __entry->qpn = qp->ibqp.qp_num; __entry->s_flags = qp->s_flags; __entry->state = qp->state; + __entry->s_acked_ack_queue = qp->s_acked_ack_queue; __entry->s_tail_ack_queue = qp->s_tail_ack_queue; __entry->r_head_ack_queue = qp->r_head_ack_queue; __entry->opcode = opcode; @@ -1032,6 +1037,7 @@ DECLARE_EVENT_CLASS(/* rc_rcv_err */ __entry->qpn, __entry->s_flags, __entry->state, + __entry->s_acked_ack_queue, __entry->s_tail_ack_queue, __entry->r_head_ack_queue, __entry->opcode, diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 2769ebdf89fb..14ec2577bcaa 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -854,6 +854,7 @@ static void rvt_init_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, qp->s_mig_state = IB_MIG_MIGRATED; qp->r_head_ack_queue = 0; qp->s_tail_ack_queue = 0; + qp->s_acked_ack_queue = 0; qp->s_num_rd_atomic = 0; if (qp->r_rq.wq) { qp->r_rq.wq->head = 0; diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index d8d88d023092..4ee612ab6cb4 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -375,6 +375,7 @@ struct rvt_qp { u8 s_rnr_retry; /* requester RNR retry counter */ u8 s_num_rd_atomic; /* number of RDMA read/atomic pending */ u8 s_tail_ack_queue; /* index into s_ack_queue[] */ + u8 s_acked_ack_queue; /* index into s_ack_queue[] */ struct rvt_sge_state s_ack_rdma_sge; struct timer_list s_timer; -- cgit v1.2.3 From 3c6cb20a0d17d7a75778fb0935d6fa427c8177af Mon Sep 17 00:00:00 2001 From: Kaike Wan Date: Wed, 23 Jan 2019 21:51:39 -0800 Subject: IB/hfi1: Add TID RDMA WRITE functionality into RDMA verbs This patch integrates TID RDMA WRITE protocol into normal RDMA verbs framework. The TID RDMA WRITE protocol is an end-to-end protocol between the hfi1 drivers on two OPA nodes that converts a qualified RDMA WRITE request into a TID RDMA WRITE request to avoid data copying on the responder side. Reviewed-by: Mike Marciniszyn Signed-off-by: Mitko Haralanov Signed-off-by: Kaike Wan Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/qp.c | 7 + drivers/infiniband/hw/hfi1/rc.c | 487 +++++++++++++++++++++++++++++---- drivers/infiniband/hw/hfi1/tid_rdma.c | 14 + drivers/infiniband/hw/hfi1/user_sdma.c | 3 +- drivers/infiniband/hw/hfi1/verbs.c | 17 +- drivers/infiniband/hw/hfi1/verbs.h | 1 + include/rdma/rdmavt_qp.h | 1 + 7 files changed, 481 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index 96632c77f36f..cfd598e4b303 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -138,6 +138,12 @@ const struct rvt_operation_params hfi1_post_parms[RVT_OPERATION_MAX] = { .flags = RVT_OPERATION_USE_RESERVE, }, +[IB_WR_TID_RDMA_WRITE] = { + .length = sizeof(struct ib_rdma_wr), + .qpt_support = BIT(IB_QPT_RC), + .flags = RVT_OPERATION_IGN_RNR_CNT, +}, + }; static void flush_list_head(struct list_head *l) @@ -780,6 +786,7 @@ void quiesce_qp(struct rvt_qp *qp) struct hfi1_qp_priv *priv = qp->priv; hfi1_del_tid_reap_timer(qp); + hfi1_del_tid_retry_timer(qp); iowait_sdma_drain(&priv->s_iowait); qp_pio_drain(qp); flush_tx_list(qp); diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index fcb733ea8dfb..6d2abea896e5 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -111,16 +111,17 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, struct hfi1_pkt_state *ps) { struct rvt_ack_entry *e; - u32 hwords; + u32 hwords, hdrlen; u32 len = 0; u32 bth0 = 0, bth2 = 0; u32 bth1 = qp->remote_qpn | (HFI1_CAP_IS_KSET(OPFN) << IB_BTHE_E_SHIFT); int middle = 0; u32 pmtu = qp->pmtu; - struct hfi1_qp_priv *priv = qp->priv; + struct hfi1_qp_priv *qpriv = qp->priv; bool last_pkt; u32 delta; u8 next = qp->s_tail_ack_queue; + struct tid_rdma_request *req; trace_hfi1_rsp_make_rc_ack(qp, 0); lockdep_assert_held(&qp->s_lock); @@ -128,7 +129,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK)) goto bail; - if (priv->hdr_type == HFI1_PKT_TYPE_9B) + if (qpriv->hdr_type == HFI1_PKT_TYPE_9B) /* header size in 32-bit words LRH+BTH = (8+12)/4. */ hwords = 5; else @@ -206,6 +207,21 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, hwords++; qp->s_ack_rdma_psn = e->psn; bth2 = mask_psn(qp->s_ack_rdma_psn++); + } else if (e->opcode == TID_OP(WRITE_REQ)) { + /* + * If a TID RDMA WRITE RESP is being resent, we have to + * wait for the actual request. All requests that are to + * be resent will have their state set to + * TID_REQUEST_RESEND. When the new request arrives, the + * state will be changed to TID_REQUEST_RESEND_ACTIVE. + */ + req = ack_to_tid_req(e); + if (req->state == TID_REQUEST_RESEND || + req->state == TID_REQUEST_INIT_RESEND) + goto bail; + qp->s_ack_state = TID_OP(WRITE_RESP); + qp->s_ack_rdma_psn = mask_psn(e->psn + req->cur_seg); + goto write_resp; } else if (e->opcode == TID_OP(READ_REQ)) { /* * If a TID RDMA read response is being resent and @@ -267,6 +283,59 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, bth2 = mask_psn(qp->s_ack_rdma_psn++); break; + case TID_OP(WRITE_RESP): +write_resp: + /* + * 1. Check if RVT_S_ACK_PENDING is set. If yes, + * goto normal. + * 2. Attempt to allocate TID resources. + * 3. Remove RVT_S_RESP_PENDING flags from s_flags + * 4. If resources not available: + * 4.1 Set RVT_S_WAIT_TID_SPACE + * 4.2 Queue QP on RCD TID queue + * 4.3 Put QP on iowait list. + * 4.4 Build IB RNR NAK with appropriate timeout value + * 4.5 Return indication progress made. + * 5. If resources are available: + * 5.1 Program HW flow CSRs + * 5.2 Build TID RDMA WRITE RESP packet + * 5.3 If more resources needed, do 2.1 - 2.3. + * 5.4 Wake up next QP on RCD TID queue. + * 5.5 Return indication progress made. + */ + + e = &qp->s_ack_queue[qp->s_tail_ack_queue]; + req = ack_to_tid_req(e); + + /* + * Send scheduled RNR NAK's. RNR NAK's need to be sent at + * segment boundaries, not at request boundaries. Don't change + * s_ack_state because we are still in the middle of a request + */ + if (qpriv->rnr_nak_state == TID_RNR_NAK_SEND && + qp->s_tail_ack_queue == qpriv->r_tid_alloc && + req->cur_seg == req->alloc_seg) { + qpriv->rnr_nak_state = TID_RNR_NAK_SENT; + goto normal_no_state; + } + + bth2 = mask_psn(qp->s_ack_rdma_psn); + hdrlen = hfi1_build_tid_rdma_write_resp(qp, e, ohdr, &bth1, + bth2, &len, + &ps->s_txreq->ss); + if (!hdrlen) + return 0; + + hwords += hdrlen; + bth0 = qp->s_ack_state << 24; + qp->s_ack_rdma_psn++; + if (req->cur_seg != req->total_segs) + break; + + e->sent = 1; + qp->s_ack_state = OP(RDMA_READ_RESPONSE_LAST); + break; + case TID_OP(READ_RESP): read_resp: e = &qp->s_ack_queue[qp->s_tail_ack_queue]; @@ -298,8 +367,7 @@ normal: * (see above). */ qp->s_ack_state = OP(SEND_ONLY); - qp->s_flags &= ~RVT_S_ACK_PENDING; - ps->s_txreq->ss = NULL; +normal_no_state: if (qp->s_nak_state) ohdr->u.aeth = cpu_to_be32((qp->r_msn & IB_MSN_MASK) | @@ -311,9 +379,11 @@ normal: len = 0; bth0 = OP(ACKNOWLEDGE) << 24; bth2 = mask_psn(qp->s_ack_psn); + qp->s_flags &= ~RVT_S_ACK_PENDING; + ps->s_txreq->ss = NULL; } qp->s_rdma_ack_cnt++; - ps->s_txreq->sde = priv->s_sde; + ps->s_txreq->sde = qpriv->s_sde; ps->s_txreq->s_cur_size = len; ps->s_txreq->hdr_dwords = hwords; hfi1_make_ruc_header(qp, ohdr, bth0, bth1, bth2, middle, ps); @@ -366,6 +436,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) int middle = 0; int delta; struct tid_rdma_flow *flow = NULL; + struct tid_rdma_params *remote; trace_hfi1_sender_make_rc_req(qp); lockdep_assert_held(&qp->s_lock); @@ -414,7 +485,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) goto done_free_tx; } - if (qp->s_flags & (RVT_S_WAIT_RNR | RVT_S_WAIT_ACK)) + if (qp->s_flags & (RVT_S_WAIT_RNR | RVT_S_WAIT_ACK | HFI1_S_WAIT_HALT)) goto bail; if (cmp_psn(qp->s_psn, qp->s_sending_hpsn) <= 0) { @@ -586,6 +657,108 @@ no_flow_control: qp->s_cur = 0; break; + case IB_WR_TID_RDMA_WRITE: + if (newreq) { + /* + * Limit the number of TID RDMA WRITE requests. + */ + if (atomic_read(&priv->n_tid_requests) >= + HFI1_TID_RDMA_WRITE_CNT) + goto bail; + + if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT)) + qp->s_lsn++; + } + + hwords += hfi1_build_tid_rdma_write_req(qp, wqe, ohdr, + &bth1, &bth2, + &len); + ss = NULL; + if (priv->s_tid_cur == HFI1_QP_WQE_INVALID) { + priv->s_tid_cur = qp->s_cur; + if (priv->s_tid_tail == HFI1_QP_WQE_INVALID) { + priv->s_tid_tail = qp->s_cur; + priv->s_state = TID_OP(WRITE_RESP); + } + } else if (priv->s_tid_cur == priv->s_tid_head) { + struct rvt_swqe *__w; + struct tid_rdma_request *__r; + + __w = rvt_get_swqe_ptr(qp, priv->s_tid_cur); + __r = wqe_to_tid_req(__w); + + /* + * The s_tid_cur pointer is advanced to s_cur if + * any of the following conditions about the WQE + * to which s_ti_cur currently points to are + * satisfied: + * 1. The request is not a TID RDMA WRITE + * request, + * 2. The request is in the INACTIVE or + * COMPLETE states (TID RDMA READ requests + * stay at INACTIVE and TID RDMA WRITE + * transition to COMPLETE when done), + * 3. The request is in the ACTIVE or SYNC + * state and the number of completed + * segments is equal to the total segment + * count. + * (If ACTIVE, the request is waiting for + * ACKs. If SYNC, the request has not + * received any responses because it's + * waiting on a sync point.) + */ + if (__w->wr.opcode != IB_WR_TID_RDMA_WRITE || + __r->state == TID_REQUEST_INACTIVE || + __r->state == TID_REQUEST_COMPLETE || + ((__r->state == TID_REQUEST_ACTIVE || + __r->state == TID_REQUEST_SYNC) && + __r->comp_seg == __r->total_segs)) { + if (priv->s_tid_tail == + priv->s_tid_cur && + priv->s_state == + TID_OP(WRITE_DATA_LAST)) { + priv->s_tid_tail = qp->s_cur; + priv->s_state = + TID_OP(WRITE_RESP); + } + priv->s_tid_cur = qp->s_cur; + } + /* + * A corner case: when the last TID RDMA WRITE + * request was completed, s_tid_head, + * s_tid_cur, and s_tid_tail all point to the + * same location. Other requests are posted and + * s_cur wraps around to the same location, + * where a new TID RDMA WRITE is posted. In + * this case, none of the indices need to be + * updated. However, the priv->s_state should. + */ + if (priv->s_tid_tail == qp->s_cur && + priv->s_state == TID_OP(WRITE_DATA_LAST)) + priv->s_state = TID_OP(WRITE_RESP); + } + req = wqe_to_tid_req(wqe); + if (newreq) { + priv->s_tid_head = qp->s_cur; + priv->pending_tid_w_resp += req->total_segs; + atomic_inc(&priv->n_tid_requests); + atomic_dec(&priv->n_requests); + } else { + req->state = TID_REQUEST_RESEND; + req->comp_seg = delta_psn(bth2, wqe->psn); + /* + * Pull back any segments since we are going + * to re-receive them. + */ + req->setup_head = req->clear_tail; + priv->pending_tid_w_resp += + delta_psn(wqe->lpsn, bth2) + 1; + } + + if (++qp->s_cur == qp->s_size) + qp->s_cur = 0; + break; + case IB_WR_RDMA_READ: /* * Don't allow more operations to be started @@ -745,7 +918,8 @@ no_flow_control: if (qp->s_tail >= qp->s_size) qp->s_tail = 0; } - if (wqe->wr.opcode == IB_WR_RDMA_READ) + if (wqe->wr.opcode == IB_WR_RDMA_READ || + wqe->wr.opcode == IB_WR_TID_RDMA_WRITE) qp->s_psn = wqe->lpsn + 1; else if (wqe->wr.opcode == IB_WR_TID_RDMA_READ) qp->s_psn = req->s_next_psn; @@ -865,6 +1039,33 @@ no_flow_control: if (qp->s_cur == qp->s_size) qp->s_cur = 0; break; + + case TID_OP(WRITE_RESP): + /* + * This value for s_state is used for restarting a TID RDMA + * WRITE request. See comment in OP(RDMA_READ_RESPONSE_MIDDLE + * for more). + */ + req = wqe_to_tid_req(wqe); + req->state = TID_REQUEST_RESEND; + rcu_read_lock(); + remote = rcu_dereference(priv->tid_rdma.remote); + req->comp_seg = delta_psn(qp->s_psn, wqe->psn); + len = wqe->length - (req->comp_seg * remote->max_len); + rcu_read_unlock(); + + bth2 = mask_psn(qp->s_psn); + hwords += hfi1_build_tid_rdma_write_req(qp, wqe, ohdr, &bth1, + &bth2, &len); + qp->s_psn = wqe->lpsn + 1; + ss = NULL; + qp->s_state = TID_OP(WRITE_REQ); + priv->pending_tid_w_resp += delta_psn(wqe->lpsn, bth2) + 1; + priv->s_tid_cur = qp->s_cur; + if (++qp->s_cur == qp->s_size) + qp->s_cur = 0; + break; + case TID_OP(READ_RESP): if (wqe->wr.opcode != IB_WR_TID_RDMA_READ) goto bail; @@ -965,7 +1166,8 @@ no_flow_control: } qp->s_sending_hpsn = bth2; delta = delta_psn(bth2, wqe->psn); - if (delta && delta % HFI1_PSN_CREDIT == 0) + if (delta && delta % HFI1_PSN_CREDIT == 0 && + wqe->wr.opcode != IB_WR_TID_RDMA_WRITE) bth2 |= IB_BTH_REQ_ACK; if (qp->s_flags & RVT_S_SEND_ONE) { qp->s_flags &= ~RVT_S_SEND_ONE; @@ -998,6 +1200,12 @@ bail: bail_no_tx: ps->s_txreq = NULL; qp->s_flags &= ~RVT_S_BUSY; + /* + * If we didn't get a txreq, the QP will be woken up later to try + * again. Set the flags to indicate which work item to wake + * up. + */ + iowait_set_flag(&priv->s_iowait, IOWAIT_PENDING_IB); return 0; } @@ -1285,6 +1493,7 @@ static void reset_psn(struct rvt_qp *qp, u32 psn) lockdep_assert_held(&qp->s_lock); qp->s_cur = n; priv->pending_tid_r_segs = 0; + priv->pending_tid_w_resp = 0; qp->s_num_rd_atomic = 0; /* @@ -1342,6 +1551,10 @@ static void reset_psn(struct rvt_qp *qp, u32 psn) qp->s_state = OP(RDMA_READ_RESPONSE_LAST); break; + case IB_WR_TID_RDMA_WRITE: + qp->s_state = TID_OP(WRITE_RESP); + break; + case IB_WR_RDMA_READ: qp->s_state = OP(RDMA_READ_RESPONSE_MIDDLE); break; @@ -1435,7 +1648,7 @@ void hfi1_restart_rc(struct rvt_qp *qp, u32 psn, int wait) qp->s_flags &= ~(RVT_S_WAIT_FENCE | RVT_S_WAIT_RDMAR | RVT_S_WAIT_SSN_CREDIT | RVT_S_WAIT_PSN | - RVT_S_WAIT_ACK); + RVT_S_WAIT_ACK | HFI1_S_WAIT_TID_RESP); if (wait) qp->s_flags |= RVT_S_SEND_ONE; reset_psn(qp, psn); @@ -1443,7 +1656,8 @@ void hfi1_restart_rc(struct rvt_qp *qp, u32 psn, int wait) /* * Set qp->s_sending_psn to the next PSN after the given one. - * This would be psn+1 except when RDMA reads are present. + * This would be psn+1 except when RDMA reads or TID RDMA ops + * are present. */ static void reset_sending_psn(struct rvt_qp *qp, u32 psn) { @@ -1456,7 +1670,8 @@ static void reset_sending_psn(struct rvt_qp *qp, u32 psn) wqe = rvt_get_swqe_ptr(qp, n); if (cmp_psn(psn, wqe->lpsn) <= 0) { if (wqe->wr.opcode == IB_WR_RDMA_READ || - wqe->wr.opcode == IB_WR_TID_RDMA_READ) + wqe->wr.opcode == IB_WR_TID_RDMA_READ || + wqe->wr.opcode == IB_WR_TID_RDMA_WRITE) qp->s_sending_psn = wqe->lpsn + 1; else qp->s_sending_psn = psn + 1; @@ -1479,8 +1694,9 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah) struct rvt_swqe *wqe; struct ib_header *hdr = NULL; struct hfi1_16b_header *hdr_16b = NULL; - u32 opcode; + u32 opcode, head, tail; u32 psn; + struct tid_rdma_request *req; lockdep_assert_held(&qp->s_lock); if (!(ib_rvt_state_ops[qp->state] & RVT_SEND_OR_FLUSH_OR_RECV_OK)) @@ -1507,29 +1723,84 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah) opcode = ib_bth_get_opcode(ohdr); if ((opcode >= OP(RDMA_READ_RESPONSE_FIRST) && opcode <= OP(ATOMIC_ACKNOWLEDGE)) || - opcode == TID_OP(READ_RESP)) { + opcode == TID_OP(READ_RESP) || + opcode == TID_OP(WRITE_RESP)) { WARN_ON(!qp->s_rdma_ack_cnt); qp->s_rdma_ack_cnt--; return; } psn = ib_bth_get_psn(ohdr); - reset_sending_psn(qp, psn); + /* + * Don't attempt to reset the sending PSN for packets in the + * KDETH PSN space since the PSN does not match anything. + */ + if (opcode != TID_OP(WRITE_DATA) && + opcode != TID_OP(WRITE_DATA_LAST) && + opcode != TID_OP(ACK) && opcode != TID_OP(RESYNC)) + reset_sending_psn(qp, psn); + + /* Handle TID RDMA WRITE packets differently */ + if (opcode >= TID_OP(WRITE_REQ) && + opcode <= TID_OP(WRITE_DATA_LAST)) { + head = priv->s_tid_head; + tail = priv->s_tid_cur; + /* + * s_tid_cur is set to s_tid_head in the case, where + * a new TID RDMA request is being started and all + * previous ones have been completed. + * Therefore, we need to do a secondary check in order + * to properly determine whether we should start the + * RC timer. + */ + wqe = rvt_get_swqe_ptr(qp, tail); + req = wqe_to_tid_req(wqe); + if (head == tail && req->comp_seg < req->total_segs) { + if (tail == 0) + tail = qp->s_size - 1; + else + tail -= 1; + } + } else { + head = qp->s_tail; + tail = qp->s_acked; + } /* * Start timer after a packet requesting an ACK has been sent and * there are still requests that haven't been acked. */ - if ((psn & IB_BTH_REQ_ACK) && qp->s_acked != qp->s_tail && + if ((psn & IB_BTH_REQ_ACK) && tail != head && + opcode != TID_OP(WRITE_DATA) && opcode != TID_OP(WRITE_DATA_LAST) && + opcode != TID_OP(RESYNC) && !(qp->s_flags & - (RVT_S_TIMER | RVT_S_WAIT_RNR | RVT_S_WAIT_PSN)) && - (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK)) { + (RVT_S_TIMER | RVT_S_WAIT_RNR | RVT_S_WAIT_PSN)) && + (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK)) { if (opcode == TID_OP(READ_REQ)) rvt_add_retry_timer_ext(qp, priv->timeout_shift); else rvt_add_retry_timer(qp); } + /* Start TID RDMA ACK timer */ + if ((opcode == TID_OP(WRITE_DATA) || + opcode == TID_OP(WRITE_DATA_LAST) || + opcode == TID_OP(RESYNC)) && + (psn & IB_BTH_REQ_ACK) && + !(priv->s_flags & HFI1_S_TID_RETRY_TIMER) && + (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK)) { + /* + * The TID RDMA ACK packet could be received before this + * function is called. Therefore, add the timer only if TID + * RDMA ACK packets are actually pending. + */ + wqe = rvt_get_swqe_ptr(qp, qp->s_acked); + req = wqe_to_tid_req(wqe); + if (wqe->wr.opcode == IB_WR_TID_RDMA_WRITE && + req->ack_seg < req->cur_seg) + hfi1_add_tid_retry_timer(qp); + } + while (qp->s_last != qp->s_acked) { u32 s_last; @@ -1628,7 +1899,16 @@ struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, } qp->s_retry = qp->s_retry_cnt; - update_last_psn(qp, wqe->lpsn); + /* + * Don't update the last PSN if the request being completed is + * a TID RDMA WRITE request. + * Completion of the TID RDMA WRITE requests are done by the + * TID RDMA ACKs and as such could be for a request that has + * already been ACKed as far as the IB state machine is + * concerned. + */ + if (wqe->wr.opcode != IB_WR_TID_RDMA_WRITE) + update_last_psn(qp, wqe->lpsn); /* * If we are completing a request which is in the process of @@ -1658,6 +1938,54 @@ struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, return wqe; } +static void set_restart_qp(struct rvt_qp *qp, struct hfi1_ctxtdata *rcd) +{ + /* Retry this request. */ + if (!(qp->r_flags & RVT_R_RDMAR_SEQ)) { + qp->r_flags |= RVT_R_RDMAR_SEQ; + hfi1_restart_rc(qp, qp->s_last_psn + 1, 0); + if (list_empty(&qp->rspwait)) { + qp->r_flags |= RVT_R_RSP_SEND; + rvt_get_qp(qp); + list_add_tail(&qp->rspwait, &rcd->qp_wait_list); + } + } +} + +/** + * update_qp_retry_state - Update qp retry state. + * @qp: the QP + * @psn: the packet sequence number of the TID RDMA WRITE RESP. + * @spsn: The start psn for the given TID RDMA WRITE swqe. + * @lpsn: The last psn for the given TID RDMA WRITE swqe. + * + * This function is called to update the qp retry state upon + * receiving a TID WRITE RESP after the qp is scheduled to retry + * a request. + */ +static void update_qp_retry_state(struct rvt_qp *qp, u32 psn, u32 spsn, + u32 lpsn) +{ + struct hfi1_qp_priv *qpriv = qp->priv; + + qp->s_psn = psn + 1; + /* + * If this is the first TID RDMA WRITE RESP packet for the current + * request, change the s_state so that the retry will be processed + * correctly. Similarly, if this is the last TID RDMA WRITE RESP + * packet, change the s_state and advance the s_cur. + */ + if (cmp_psn(psn, lpsn) >= 0) { + qp->s_cur = qpriv->s_tid_cur + 1; + if (qp->s_cur >= qp->s_size) + qp->s_cur = 0; + qp->s_state = TID_OP(WRITE_REQ); + } else if (!cmp_psn(psn, spsn)) { + qp->s_cur = qpriv->s_tid_cur; + qp->s_state = TID_OP(WRITE_RESP); + } +} + /** * do_rc_ack - process an incoming RC ACK * @qp: the QP the ACK came in on @@ -1679,6 +2007,7 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, int ret = 0; u32 ack_psn; int diff; + struct rvt_dev_info *rdi; lockdep_assert_held(&qp->s_lock); /* @@ -1725,18 +2054,10 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, (opcode != TID_OP(READ_RESP) || diff != 0)) || ((wqe->wr.opcode == IB_WR_ATOMIC_CMP_AND_SWP || wqe->wr.opcode == IB_WR_ATOMIC_FETCH_AND_ADD) && - (opcode != OP(ATOMIC_ACKNOWLEDGE) || diff != 0))) { - /* Retry this request. */ - if (!(qp->r_flags & RVT_R_RDMAR_SEQ)) { - qp->r_flags |= RVT_R_RDMAR_SEQ; - hfi1_restart_rc(qp, qp->s_last_psn + 1, 0); - if (list_empty(&qp->rspwait)) { - qp->r_flags |= RVT_R_RSP_SEND; - rvt_get_qp(qp); - list_add_tail(&qp->rspwait, - &rcd->qp_wait_list); - } - } + (opcode != OP(ATOMIC_ACKNOWLEDGE) || diff != 0)) || + (wqe->wr.opcode == IB_WR_TID_RDMA_WRITE && + (delta_psn(psn, qp->s_last_psn) != 1))) { + set_restart_qp(qp, rcd); /* * No need to process the ACK/NAK since we are * restarting an earlier request. @@ -1768,6 +2089,14 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, hfi1_schedule_send(qp); } } + + /* + * TID RDMA WRITE requests will be completed by the TID RDMA + * ACK packet handler (see tid_rdma.c). + */ + if (wqe->wr.opcode == IB_WR_TID_RDMA_WRITE) + break; + wqe = do_rc_completion(qp, wqe, ibp); if (qp->s_acked == qp->s_tail) break; @@ -1785,17 +2114,60 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, else rvt_stop_rc_timers(qp); } else if (qp->s_acked != qp->s_tail) { + struct rvt_swqe *__w = NULL; + + if (qpriv->s_tid_cur != HFI1_QP_WQE_INVALID) + __w = rvt_get_swqe_ptr(qp, qpriv->s_tid_cur); + /* - * We are expecting more ACKs so - * mod the retry timer. - */ - rvt_mod_retry_timer(qp); - /* - * We can stop re-sending the earlier packets and - * continue with the next packet the receiver wants. + * Stop timers if we've received all of the TID RDMA + * WRITE * responses. */ - if (cmp_psn(qp->s_psn, psn) <= 0) - reset_psn(qp, psn + 1); + if (__w && __w->wr.opcode == IB_WR_TID_RDMA_WRITE && + opcode == TID_OP(WRITE_RESP)) { + /* + * Normally, the loop above would correctly + * process all WQEs from s_acked onward and + * either complete them or check for correct + * PSN sequencing. + * However, for TID RDMA, due to pipelining, + * the response may not be for the request at + * s_acked so the above look would just be + * skipped. This does not allow for checking + * the PSN sequencing. It has to be done + * separately. + */ + if (cmp_psn(psn, qp->s_last_psn + 1)) { + set_restart_qp(qp, rcd); + goto bail_stop; + } + /* + * If the psn is being resent, stop the + * resending. + */ + if (qp->s_cur != qp->s_tail && + cmp_psn(qp->s_psn, psn) <= 0) + update_qp_retry_state(qp, psn, + __w->psn, + __w->lpsn); + else if (--qpriv->pending_tid_w_resp) + rvt_mod_retry_timer(qp); + else + rvt_stop_rc_timers(qp); + } else { + /* + * We are expecting more ACKs so + * mod the retry timer. + */ + rvt_mod_retry_timer(qp); + /* + * We can stop re-sending the earlier packets + * and continue with the next packet the + * receiver wants. + */ + if (cmp_psn(qp->s_psn, psn) <= 0) + reset_psn(qp, psn + 1); + } } else { /* No more acks - kill all timers */ rvt_stop_rc_timers(qp); @@ -1811,6 +2183,15 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, rvt_get_credit(qp, aeth); qp->s_rnr_retry = qp->s_rnr_retry_cnt; qp->s_retry = qp->s_retry_cnt; + /* + * If the current request is a TID RDMA WRITE request and the + * response is not a TID RDMA WRITE RESP packet, s_last_psn + * can't be advanced. + */ + if (wqe->wr.opcode == IB_WR_TID_RDMA_WRITE && + opcode != TID_OP(WRITE_RESP) && + cmp_psn(psn, wqe->psn) >= 0) + return 1; update_last_psn(qp, psn); return 1; @@ -1820,20 +2201,31 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, goto bail_stop; if (qp->s_flags & RVT_S_WAIT_RNR) goto bail_stop; - if (qp->s_rnr_retry == 0) { + rdi = ib_to_rvt(qp->ibqp.device); + if (qp->s_rnr_retry == 0 && + !((rdi->post_parms[wqe->wr.opcode].flags & + RVT_OPERATION_IGN_RNR_CNT) && + qp->s_rnr_retry_cnt == 0)) { status = IB_WC_RNR_RETRY_EXC_ERR; goto class_b; } - if (qp->s_rnr_retry_cnt < 7) + if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0) qp->s_rnr_retry--; - /* The last valid PSN is the previous PSN. */ - update_last_psn(qp, psn - 1); + /* + * The last valid PSN is the previous PSN. For TID RDMA WRITE + * request, s_last_psn should be incremented only when a TID + * RDMA WRITE RESP is received to avoid skipping lost TID RDMA + * WRITE RESP packets. + */ + if (wqe->wr.opcode == IB_WR_TID_RDMA_WRITE) { + reset_psn(qp, qp->s_last_psn + 1); + } else { + update_last_psn(qp, psn - 1); + reset_psn(qp, psn); + } ibp->rvp.n_rc_resends += delta_psn(qp->s_psn, psn); - - reset_psn(qp, psn); - qp->s_flags &= ~(RVT_S_WAIT_SSN_CREDIT | RVT_S_WAIT_ACK); rvt_stop_rc_timers(qp); rvt_add_rnr_timer(qp, aeth); @@ -1918,6 +2310,7 @@ static void rdma_seq_err(struct rvt_qp *qp, struct hfi1_ibport *ibp, u32 psn, while (cmp_psn(psn, wqe->lpsn) > 0) { if (wqe->wr.opcode == IB_WR_RDMA_READ || wqe->wr.opcode == IB_WR_TID_RDMA_READ || + wqe->wr.opcode == IB_WR_TID_RDMA_WRITE || wqe->wr.opcode == IB_WR_ATOMIC_CMP_AND_SWP || wqe->wr.opcode == IB_WR_ATOMIC_FETCH_AND_ADD) break; diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 80111dd1d876..490e47a0f68b 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -3205,6 +3205,20 @@ void hfi1_qp_kern_exp_rcv_clear_all(struct rvt_qp *qp) do { struct hfi1_swqe_priv *priv = wqe->priv; + ret = hfi1_kern_exp_rcv_clear(&priv->tid_req); + } while (!ret); + } + for (i = qp->s_acked_ack_queue; i != qp->r_head_ack_queue;) { + struct rvt_ack_entry *e = &qp->s_ack_queue[i]; + + if (++i == rvt_max_atomic(ib_to_rvt(qp->ibqp.device))) + i = 0; + /* Free only locally allocated TID entries */ + if (e->opcode != TID_OP(WRITE_REQ)) + continue; + do { + struct hfi1_ack_priv *priv = e->priv; + ret = hfi1_kern_exp_rcv_clear(&priv->tid_req); } while (!ret); } diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index e5e7fad09f32..6764114b886c 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -1126,7 +1126,8 @@ static inline u32 set_pkt_bth_psn(__be32 bthpsn, u8 expct, u32 frags) 0xffffffull), psn = val & mask; if (expct) - psn = (psn & ~BTH_SEQ_MASK) | ((psn + frags) & BTH_SEQ_MASK); + psn = (psn & ~HFI1_KDETH_BTH_SEQ_MASK) | + ((psn + frags) & HFI1_KDETH_BTH_SEQ_MASK); else psn = psn + frags; return psn & mask; diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 7b87b77582bd..ab97d71cdd92 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -161,6 +161,7 @@ MODULE_PARM_DESC(wss_clean_period, "Count of verbs copies before an entry in the */ const enum ib_wc_opcode ib_hfi1_wc_opcode[] = { [IB_WR_RDMA_WRITE] = IB_WC_RDMA_WRITE, + [IB_WR_TID_RDMA_WRITE] = IB_WC_RDMA_WRITE, [IB_WR_RDMA_WRITE_WITH_IMM] = IB_WC_RDMA_WRITE, [IB_WR_SEND] = IB_WC_SEND, [IB_WR_SEND_WITH_IMM] = IB_WC_SEND, @@ -203,6 +204,12 @@ const u8 hdr_len_by_opcode[256] = { [IB_OPCODE_RC_SEND_ONLY_WITH_INVALIDATE] = 12 + 8 + 4, [IB_OPCODE_TID_RDMA_READ_REQ] = 12 + 8 + 36, [IB_OPCODE_TID_RDMA_READ_RESP] = 12 + 8 + 36, + [IB_OPCODE_TID_RDMA_WRITE_REQ] = 12 + 8 + 36, + [IB_OPCODE_TID_RDMA_WRITE_RESP] = 12 + 8 + 36, + [IB_OPCODE_TID_RDMA_WRITE_DATA] = 12 + 8 + 36, + [IB_OPCODE_TID_RDMA_WRITE_DATA_LAST] = 12 + 8 + 36, + [IB_OPCODE_TID_RDMA_ACK] = 12 + 8 + 36, + [IB_OPCODE_TID_RDMA_RESYNC] = 12 + 8 + 36, /* UC */ [IB_OPCODE_UC_SEND_FIRST] = 12 + 8, [IB_OPCODE_UC_SEND_MIDDLE] = 12 + 8, @@ -248,8 +255,14 @@ static const opcode_handler opcode_handler_tbl[256] = { [IB_OPCODE_RC_SEND_ONLY_WITH_INVALIDATE] = &hfi1_rc_rcv, /* TID RDMA has separate handlers for different opcodes.*/ + [IB_OPCODE_TID_RDMA_WRITE_REQ] = &hfi1_rc_rcv_tid_rdma_write_req, + [IB_OPCODE_TID_RDMA_WRITE_RESP] = &hfi1_rc_rcv_tid_rdma_write_resp, + [IB_OPCODE_TID_RDMA_WRITE_DATA] = &hfi1_rc_rcv_tid_rdma_write_data, + [IB_OPCODE_TID_RDMA_WRITE_DATA_LAST] = &hfi1_rc_rcv_tid_rdma_write_data, [IB_OPCODE_TID_RDMA_READ_REQ] = &hfi1_rc_rcv_tid_rdma_read_req, [IB_OPCODE_TID_RDMA_READ_RESP] = &hfi1_rc_rcv_tid_rdma_read_resp, + [IB_OPCODE_TID_RDMA_RESYNC] = &hfi1_rc_rcv_tid_rdma_resync, + [IB_OPCODE_TID_RDMA_ACK] = &hfi1_rc_rcv_tid_rdma_ack, /* UC */ [IB_OPCODE_UC_SEND_FIRST] = &hfi1_uc_rcv, @@ -1332,7 +1345,9 @@ static void hfi1_fill_device_attr(struct hfi1_devdata *dd) rdi->dparms.props.max_mr_size = U64_MAX; rdi->dparms.props.max_fast_reg_page_list_len = UINT_MAX; rdi->dparms.props.max_qp = hfi1_max_qps; - rdi->dparms.props.max_qp_wr = hfi1_max_qp_wrs; + rdi->dparms.props.max_qp_wr = + (hfi1_max_qp_wrs >= HFI1_QP_WQE_INVALID ? + HFI1_QP_WQE_INVALID - 1 : hfi1_max_qp_wrs); rdi->dparms.props.max_send_sge = hfi1_max_sges; rdi->dparms.props.max_recv_sge = hfi1_max_sges; rdi->dparms.props.max_sge_rd = hfi1_max_sges; diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h index bee3d21a548e..62ace0b2d17a 100644 --- a/drivers/infiniband/hw/hfi1/verbs.h +++ b/drivers/infiniband/hw/hfi1/verbs.h @@ -193,6 +193,7 @@ struct hfi1_qp_priv { u32 r_tid_ack; /* the TID RDMA request to be ACK'ed */ u32 r_tid_alloc; /* Request for which we are allocating resources */ u32 pending_tid_w_segs; /* Num of pending tid write segments */ + u32 pending_tid_w_resp; /* Num of pending tid write responses */ u32 alloc_w_segs; /* Number of segments for which write */ /* resources have been allocated for this QP */ diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 4ee612ab6cb4..f0fbd4063fef 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -246,6 +246,7 @@ struct rvt_ack_entry { #define RVT_OPERATION_ATOMIC_SGE 0x00000004 #define RVT_OPERATION_LOCAL 0x00000008 #define RVT_OPERATION_USE_RESERVE 0x00000010 +#define RVT_OPERATION_IGN_RNR_CNT 0x00000020 #define RVT_OPERATION_MAX (IB_WR_RESERVED10 + 1) -- cgit v1.2.3 From 972248e9111ee6fe9fb56c24ecfd7434f3d713ac Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Jan 2019 09:32:03 +0100 Subject: scsi: bsg-lib: handle bidi requests without block layer help We can just stash away the second request in struct bsg_job instead of using the block layer req->next_rq field, allowing for the eventual removal of the latter. Signed-off-by: Christoph Hellwig Acked-by: Jens Axboe Signed-off-by: Martin K. Petersen --- block/bsg-lib.c | 44 +++++++++++++++++++++---- block/bsg.c | 68 ++++++++------------------------------- drivers/scsi/scsi_transport_sas.c | 1 - include/linux/bsg-lib.h | 4 +++ 4 files changed, 56 insertions(+), 61 deletions(-) (limited to 'include') diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 192129856342..005e2b75d775 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -51,11 +51,40 @@ static int bsg_transport_fill_hdr(struct request *rq, struct sg_io_v4 *hdr, fmode_t mode) { struct bsg_job *job = blk_mq_rq_to_pdu(rq); + int ret; job->request_len = hdr->request_len; job->request = memdup_user(uptr64(hdr->request), hdr->request_len); + if (IS_ERR(job->request)) + return PTR_ERR(job->request); + + if (hdr->dout_xfer_len && hdr->din_xfer_len) { + job->bidi_rq = blk_get_request(rq->q, REQ_OP_SCSI_IN, 0); + if (IS_ERR(job->bidi_rq)) { + ret = PTR_ERR(job->bidi_rq); + goto out; + } + + ret = blk_rq_map_user(rq->q, job->bidi_rq, NULL, + uptr64(hdr->din_xferp), hdr->din_xfer_len, + GFP_KERNEL); + if (ret) + goto out_free_bidi_rq; + + job->bidi_bio = job->bidi_rq->bio; + } else { + job->bidi_rq = NULL; + job->bidi_bio = NULL; + } - return PTR_ERR_OR_ZERO(job->request); + return 0; + +out_free_bidi_rq: + if (job->bidi_rq) + blk_put_request(job->bidi_rq); +out: + kfree(job->request); + return ret; } static int bsg_transport_complete_rq(struct request *rq, struct sg_io_v4 *hdr) @@ -93,7 +122,7 @@ static int bsg_transport_complete_rq(struct request *rq, struct sg_io_v4 *hdr) /* we assume all request payload was transferred, residual == 0 */ hdr->dout_resid = 0; - if (rq->next_rq) { + if (job->bidi_rq) { unsigned int rsp_len = job->reply_payload.payload_len; if (WARN_ON(job->reply_payload_rcv_len > rsp_len)) @@ -111,6 +140,11 @@ static void bsg_transport_free_rq(struct request *rq) { struct bsg_job *job = blk_mq_rq_to_pdu(rq); + if (job->bidi_rq) { + blk_rq_unmap_user(job->bidi_bio); + blk_put_request(job->bidi_rq); + } + kfree(job->request); } @@ -200,7 +234,6 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req) */ static bool bsg_prepare_job(struct device *dev, struct request *req) { - struct request *rsp = req->next_rq; struct bsg_job *job = blk_mq_rq_to_pdu(req); int ret; @@ -211,8 +244,8 @@ static bool bsg_prepare_job(struct device *dev, struct request *req) if (ret) goto failjob_rls_job; } - if (rsp && rsp->bio) { - ret = bsg_map_buffer(&job->reply_payload, rsp); + if (job->bidi_rq) { + ret = bsg_map_buffer(&job->reply_payload, job->bidi_rq); if (ret) goto failjob_rls_rqst_payload; } @@ -369,7 +402,6 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, } q->queuedata = dev; - blk_queue_flag_set(QUEUE_FLAG_BIDI, q); blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); ret = bsg_register_queue(q, dev, name, &bsg_transport_ops); diff --git a/block/bsg.c b/block/bsg.c index a799b0ace55c..f306853c6b08 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -74,6 +74,11 @@ static int bsg_scsi_fill_hdr(struct request *rq, struct sg_io_v4 *hdr, { struct scsi_request *sreq = scsi_req(rq); + if (hdr->dout_xfer_len && hdr->din_xfer_len) { + pr_warn_once("BIDI support in bsg has been removed.\n"); + return -EOPNOTSUPP; + } + sreq->cmd_len = hdr->request_len; if (sreq->cmd_len > BLK_MAX_CDB) { sreq->cmd = kzalloc(sreq->cmd_len, GFP_KERNEL); @@ -114,14 +119,10 @@ static int bsg_scsi_complete_rq(struct request *rq, struct sg_io_v4 *hdr) hdr->response_len = len; } - if (rq->next_rq) { - hdr->dout_resid = sreq->resid_len; - hdr->din_resid = scsi_req(rq->next_rq)->resid_len; - } else if (rq_data_dir(rq) == READ) { + if (rq_data_dir(rq) == READ) hdr->din_resid = sreq->resid_len; - } else { + else hdr->dout_resid = sreq->resid_len; - } return ret; } @@ -140,8 +141,8 @@ static const struct bsg_ops bsg_scsi_ops = { static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg) { - struct request *rq, *next_rq = NULL; - struct bio *bio, *bidi_bio = NULL; + struct request *rq; + struct bio *bio; struct sg_io_v4 hdr; int ret; @@ -164,7 +165,7 @@ static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg) ret = q->bsg_dev.ops->fill_hdr(rq, &hdr, mode); if (ret) - goto out; + return ret; rq->timeout = msecs_to_jiffies(hdr.timeout); if (!rq->timeout) @@ -174,29 +175,6 @@ static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg) if (rq->timeout < BLK_MIN_SG_TIMEOUT) rq->timeout = BLK_MIN_SG_TIMEOUT; - if (hdr.dout_xfer_len && hdr.din_xfer_len) { - if (!test_bit(QUEUE_FLAG_BIDI, &q->queue_flags)) { - ret = -EOPNOTSUPP; - goto out; - } - - pr_warn_once( - "BIDI support in bsg has been deprecated and might be removed. " - "Please report your use case to linux-scsi@vger.kernel.org\n"); - - next_rq = blk_get_request(q, REQ_OP_SCSI_IN, 0); - if (IS_ERR(next_rq)) { - ret = PTR_ERR(next_rq); - goto out; - } - - rq->next_rq = next_rq; - ret = blk_rq_map_user(q, next_rq, NULL, uptr64(hdr.din_xferp), - hdr.din_xfer_len, GFP_KERNEL); - if (ret) - goto out_free_nextrq; - } - if (hdr.dout_xfer_len) { ret = blk_rq_map_user(q, rq, NULL, uptr64(hdr.dout_xferp), hdr.dout_xfer_len, GFP_KERNEL); @@ -206,38 +184,20 @@ static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg) } if (ret) - goto out_unmap_nextrq; + goto out_free_rq; bio = rq->bio; - if (rq->next_rq) - bidi_bio = rq->next_rq->bio; blk_execute_rq(q, NULL, rq, !(hdr.flags & BSG_FLAG_Q_AT_TAIL)); ret = rq->q->bsg_dev.ops->complete_rq(rq, &hdr); - - if (rq->next_rq) { - blk_rq_unmap_user(bidi_bio); - blk_put_request(rq->next_rq); - } - blk_rq_unmap_user(bio); + +out_free_rq: rq->q->bsg_dev.ops->free_rq(rq); blk_put_request(rq); - - if (copy_to_user(uarg, &hdr, sizeof(hdr))) + if (!ret && copy_to_user(uarg, &hdr, sizeof(hdr))) return -EFAULT; return ret; - -out_unmap_nextrq: - if (rq->next_rq) - blk_rq_unmap_user(rq->next_rq->bio); -out_free_nextrq: - if (rq->next_rq) - blk_put_request(rq->next_rq); -out: - q->bsg_dev.ops->free_rq(rq); - blk_put_request(rq); - return ret; } static struct bsg_device *bsg_alloc_device(void) diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 692b46937e52..60f1a81d2034 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -213,7 +213,6 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy) to_sas_host_attrs(shost)->q = q; } - blk_queue_flag_set(QUEUE_FLAG_BIDI, q); return 0; } diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index b356e0006731..7f14517a559b 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -69,6 +69,10 @@ struct bsg_job { int result; unsigned int reply_payload_rcv_len; + /* BIDI support */ + struct request *bidi_rq; + struct bio *bidi_bio; + void *dd_data; /* Used for driver-specific storage */ }; -- cgit v1.2.3 From 19fcae3d4f2dd513d472055fb694d802e9a21b91 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 8 Nov 2018 09:28:20 +0100 Subject: scsi: remove the SCSI OSD library Now that all the users are gone the SCSI OSD library can be removed as well. Signed-off-by: Christoph Hellwig Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- Documentation/scsi/osd.txt | 192 ---- MAINTAINERS | 6 - drivers/scsi/Kconfig | 2 - drivers/scsi/Makefile | 1 - drivers/scsi/osd/Kbuild | 20 - drivers/scsi/osd/Kconfig | 49 - drivers/scsi/osd/osd_debug.h | 30 - drivers/scsi/osd/osd_initiator.c | 2076 -------------------------------------- drivers/scsi/osd/osd_uld.c | 571 ----------- include/scsi/osd_initiator.h | 511 ---------- include/scsi/osd_ore.h | 201 ---- 11 files changed, 3659 deletions(-) delete mode 100644 Documentation/scsi/osd.txt delete mode 100644 drivers/scsi/osd/Kbuild delete mode 100644 drivers/scsi/osd/Kconfig delete mode 100644 drivers/scsi/osd/osd_debug.h delete mode 100644 drivers/scsi/osd/osd_initiator.c delete mode 100644 drivers/scsi/osd/osd_uld.c delete mode 100644 include/scsi/osd_initiator.h delete mode 100644 include/scsi/osd_ore.h (limited to 'include') diff --git a/Documentation/scsi/osd.txt b/Documentation/scsi/osd.txt deleted file mode 100644 index 2bc2ab06b0c0..000000000000 --- a/Documentation/scsi/osd.txt +++ /dev/null @@ -1,192 +0,0 @@ -The OSD Standard -================ -OSD (Object-Based Storage Device) is a T10 SCSI command set that is designed -to provide efficient operation of input/output logical units that manage the -allocation, placement, and accessing of variable-size data-storage containers, -called objects. Objects are intended to contain operating system and application -constructs. Each object has associated attributes attached to it, which are -integral part of the object and provide metadata about the object. The standard -defines some common obligatory attributes, but user attributes can be added as -needed. - -See: http://www.t10.org/ftp/t10/drafts/osd2/ for the latest draft for OSD 2 -or search the web for "OSD SCSI" - -OSD in the Linux Kernel -======================= -osd-initiator: - The main component of OSD in Kernel is the osd-initiator library. Its main -user is intended to be the pNFS-over-objects layout driver, which uses objects -as its back-end data storage. Other clients are the other osd parts listed below. - -osd-uld: - This is a SCSI ULD that registers for OSD type devices and provides a testing -platform, both for the in-kernel initiator as well as connected targets. It -currently has no useful user-mode API, though it could have if need be. - -osd target: - There are no current plans for an OSD target implementation in kernel. For all -needs, a user-mode target that is based on the scsi tgt target framework is -available from Ohio Supercomputer Center (OSC) at: -http://www.open-osd.org/bin/view/Main/OscOsdProject -There are several other target implementations. See http://open-osd.org for more -links. - -Files and Folders -================= -This is the complete list of files included in this work: -include/scsi/ - osd_initiator.h Main API for the initiator library - osd_types.h Common OSD types - osd_sec.h Security Manager API - osd_protocol.h Wire definitions of the OSD standard protocol - osd_attributes.h Wire definitions of OSD attributes - -drivers/scsi/osd/ - osd_initiator.c OSD-Initiator library implementation - osd_uld.c The OSD scsi ULD - osd_ktest.{h,c} In-kernel test suite (called by osd_uld) - osd_debug.h Some printk macros - Makefile For both in-tree and out-of-tree compilation - Kconfig Enables inclusion of the different pieces - osd_test.c User-mode application to call the kernel tests - -The OSD-Initiator Library -========================= -osd_initiator is a low level implementation of an osd initiator encoder. -But even though, it should be intuitive and easy to use. Perhaps over time an -higher lever will form that automates some of the more common recipes. - -init/fini: -- osd_dev_init() associates a scsi_device with an osd_dev structure - and initializes some global pools. This should be done once per scsi_device - (OSD LUN). The osd_dev structure is needed for calling osd_start_request(). - -- osd_dev_fini() cleans up before a osd_dev/scsi_device destruction. - -OSD commands encoding, execution, and decoding of results: - -struct osd_request's is used to iteratively encode an OSD command and carry -its state throughout execution. Each request goes through these stages: - -a. osd_start_request() allocates the request. - -b. Any of the osd_req_* methods is used to encode a request of the specified - type. - -c. osd_req_add_{get,set}_attr_* may be called to add get/set attributes to the - CDB. "List" or "Page" mode can be used exclusively. The attribute-list API - can be called multiple times on the same request. However, only one - attribute-page can be read, as mandated by the OSD standard. - -d. osd_finalize_request() computes offsets into the data-in and data-out buffers - and signs the request using the provided capability key and integrity- - check parameters. - -e. osd_execute_request() may be called to execute the request via the block - layer and wait for its completion. The request can be executed - asynchronously by calling the block layer API directly. - -f. After execution, osd_req_decode_sense() can be called to decode the request's - sense information. - -g. osd_req_decode_get_attr() may be called to retrieve osd_add_get_attr_list() - values. - -h. osd_end_request() must be called to deallocate the request and any resource - associated with it. Note that osd_end_request cleans up the request at any - stage and it must always be called after a successful osd_start_request(). - -osd_request's structure: - -The OSD standard defines a complex structure of IO segments pointed to by -members in the CDB. Up to 3 segments can be deployed in the IN-Buffer and up to -4 in the OUT-Buffer. The ASCII illustration below depicts a secure-read with -associated get+set of attributes-lists. Other combinations very on the same -basic theme. From no-segments-used up to all-segments-used. - -|________OSD-CDB__________| -| | -|read_len (offset=0) -|---------\ -| | | -|get_attrs_list_length | | -|get_attrs_list_offset -|----\ | -| | | | -|retrieved_attrs_alloc_len| | | -|retrieved_attrs_offset -|----|----|-\ -| | | | | -|set_attrs_list_length | | | | -|set_attrs_list_offset -|-\ | | | -| | | | | | -|in_data_integ_offset -|-|--|----|-|-\ -|out_data_integ_offset -|-|--|--\ | | | -\_________________________/ | | | | | | - | | | | | | -|_______OUT-BUFFER________| | | | | | | -| Set attr list | - -More up-to-date information can be found on: -http://open-osd.org - -Boaz Harrosh - -References -========== -Weber, R., "SCSI Object-Based Storage Device Commands", -T10/1355-D ANSI/INCITS 400-2004, -http://www.t10.org/ftp/t10/drafts/osd/osd-r10.pdf - -Weber, R., "SCSI Object-Based Storage Device Commands -2 (OSD-2)" -T10/1729-D, Working Draft, rev. 3 -http://www.t10.org/ftp/t10/drafts/osd2/osd2r03.pdf diff --git a/MAINTAINERS b/MAINTAINERS index 108b340ab625..0cd037950bc3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11385,12 +11385,6 @@ W: http://www.nongnu.org/orinoco/ S: Orphan F: drivers/net/wireless/intersil/orinoco/ -OSD LIBRARY and FILESYSTEM -M: Boaz Harrosh -S: Maintained -F: drivers/scsi/osd/ -F: include/scsi/osd_* - OV2659 OMNIVISION SENSOR DRIVER M: "Lad, Prabhakar" L: linux-media@vger.kernel.org diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 85c5c89f2fa5..237c6294738d 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1515,6 +1515,4 @@ source "drivers/scsi/pcmcia/Kconfig" source "drivers/scsi/device_handler/Kconfig" -source "drivers/scsi/osd/Kconfig" - endmenu diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index fcb41ae329c4..8826111fdf4a 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -150,7 +150,6 @@ obj-$(CONFIG_CHR_DEV_SG) += sg.o obj-$(CONFIG_CHR_DEV_SCH) += ch.o obj-$(CONFIG_SCSI_ENCLOSURE) += ses.o -obj-$(CONFIG_SCSI_OSD_INITIATOR) += osd/ obj-$(CONFIG_SCSI_HISI_SAS) += hisi_sas/ # This goes last, so that "real" scsi devices probe earlier diff --git a/drivers/scsi/osd/Kbuild b/drivers/scsi/osd/Kbuild deleted file mode 100644 index 58cecd45b0f5..000000000000 --- a/drivers/scsi/osd/Kbuild +++ /dev/null @@ -1,20 +0,0 @@ -# -# Kbuild for the OSD modules -# -# Copyright (C) 2008 Panasas Inc. All rights reserved. -# -# Authors: -# Boaz Harrosh -# Benny Halevy -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License version 2 -# - -# libosd.ko - osd-initiator library -libosd-y := osd_initiator.o -obj-$(CONFIG_SCSI_OSD_INITIATOR) += libosd.o - -# osd.ko - SCSI ULD and char-device -osd-y := osd_uld.o -obj-$(CONFIG_SCSI_OSD_ULD) += osd.o diff --git a/drivers/scsi/osd/Kconfig b/drivers/scsi/osd/Kconfig deleted file mode 100644 index 347cc5e33749..000000000000 --- a/drivers/scsi/osd/Kconfig +++ /dev/null @@ -1,49 +0,0 @@ -# -# Kernel configuration file for the OSD scsi protocol -# -# Copyright (C) 2008 Panasas Inc. All rights reserved. -# -# Authors: -# Boaz Harrosh -# Benny Halevy -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public version 2 License as -# published by the Free Software Foundation -# -config SCSI_OSD_INITIATOR - tristate "OSD-Initiator library" - depends on SCSI - help - Enable the OSD-Initiator library (libosd.ko). - NOTE: You must also select CRYPTO_SHA1 + CRYPTO_HMAC and their - dependencies - -config SCSI_OSD_ULD - tristate "OSD Upper Level driver" - depends on SCSI_OSD_INITIATOR - help - Build a SCSI upper layer driver that exports /dev/osdX devices - to user-mode for testing and controlling OSD devices. It is also - needed by exofs, for mounting an OSD based file system. - -config SCSI_OSD_DPRINT_SENSE - int "(0-2) When sense is returned, DEBUG print all sense descriptors" - default 1 - depends on SCSI_OSD_INITIATOR - help - When a CHECK_CONDITION status is returned from a target, and a - sense-buffer is retrieved, turning this on will dump a full - sense-decoding message. Setting to 2 will also print recoverable - errors that might be regularly returned for some filesystem - operations. - -config SCSI_OSD_DEBUG - bool "Compile All OSD modules with lots of DEBUG prints" - default n - depends on SCSI_OSD_INITIATOR - help - OSD Code is populated with lots of OSD_DEBUG(..) printouts to - dmesg. Enable this if you found a bug and you want to help us - track the problem (see also MAINTAINERS). Setting this will also - force SCSI_OSD_DPRINT_SENSE=2. diff --git a/drivers/scsi/osd/osd_debug.h b/drivers/scsi/osd/osd_debug.h deleted file mode 100644 index 26341261bb5c..000000000000 --- a/drivers/scsi/osd/osd_debug.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * osd_debug.h - Some kprintf macros - * - * Copyright (C) 2008 Panasas Inc. All rights reserved. - * - * Authors: - * Boaz Harrosh - * Benny Halevy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * - */ -#ifndef __OSD_DEBUG_H__ -#define __OSD_DEBUG_H__ - -#define OSD_ERR(fmt, a...) printk(KERN_ERR "osd: " fmt, ##a) -#define OSD_INFO(fmt, a...) printk(KERN_NOTICE "osd: " fmt, ##a) - -#ifdef CONFIG_SCSI_OSD_DEBUG -#define OSD_DEBUG(fmt, a...) \ - printk(KERN_NOTICE "osd @%s:%d: " fmt, __func__, __LINE__, ##a) -#else -#define OSD_DEBUG(fmt, a...) do {} while (0) -#endif - -/* u64 has problems with printk this will cast it to unsigned long long */ -#define _LLU(x) (unsigned long long)(x) - -#endif /* ndef __OSD_DEBUG_H__ */ diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c deleted file mode 100644 index 60cf7c5eb880..000000000000 --- a/drivers/scsi/osd/osd_initiator.c +++ /dev/null @@ -1,2076 +0,0 @@ -/* - * osd_initiator - Main body of the osd initiator library. - * - * Note: The file does not contain the advanced security functionality which - * is only needed by the security_manager's initiators. - * - * Copyright (C) 2008 Panasas Inc. All rights reserved. - * - * Authors: - * Boaz Harrosh - * Benny Halevy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the Panasas company nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#include -#include - -#include -#include -#include -#include - -#include -#include - -#include "osd_debug.h" - -#ifndef __unused -# define __unused __attribute__((unused)) -#endif - -enum { OSD_REQ_RETRIES = 1 }; - -MODULE_AUTHOR("Boaz Harrosh "); -MODULE_DESCRIPTION("open-osd initiator library libosd.ko"); -MODULE_LICENSE("GPL"); - -static inline void build_test(void) -{ - /* structures were not packed */ - BUILD_BUG_ON(sizeof(struct osd_capability) != OSD_CAP_LEN); - BUILD_BUG_ON(sizeof(struct osdv2_cdb) != OSD_TOTAL_CDB_LEN); - BUILD_BUG_ON(sizeof(struct osdv1_cdb) != OSDv1_TOTAL_CDB_LEN); -} - -static const char *_osd_ver_desc(struct osd_request *or) -{ - return osd_req_is_ver1(or) ? "OSD1" : "OSD2"; -} - -#define ATTR_DEF_RI(id, len) ATTR_DEF(OSD_APAGE_ROOT_INFORMATION, id, len) - -static int _osd_get_print_system_info(struct osd_dev *od, - void *caps, struct osd_dev_info *odi) -{ - struct osd_request *or; - struct osd_attr get_attrs[] = { - ATTR_DEF_RI(OSD_ATTR_RI_VENDOR_IDENTIFICATION, 8), - ATTR_DEF_RI(OSD_ATTR_RI_PRODUCT_IDENTIFICATION, 16), - ATTR_DEF_RI(OSD_ATTR_RI_PRODUCT_MODEL, 32), - ATTR_DEF_RI(OSD_ATTR_RI_PRODUCT_REVISION_LEVEL, 4), - ATTR_DEF_RI(OSD_ATTR_RI_PRODUCT_SERIAL_NUMBER, 64 /*variable*/), - ATTR_DEF_RI(OSD_ATTR_RI_OSD_NAME, 64 /*variable*/), - ATTR_DEF_RI(OSD_ATTR_RI_TOTAL_CAPACITY, 8), - ATTR_DEF_RI(OSD_ATTR_RI_USED_CAPACITY, 8), - ATTR_DEF_RI(OSD_ATTR_RI_NUMBER_OF_PARTITIONS, 8), - ATTR_DEF_RI(OSD_ATTR_RI_CLOCK, 6), - /* IBM-OSD-SIM Has a bug with this one put it last */ - ATTR_DEF_RI(OSD_ATTR_RI_OSD_SYSTEM_ID, 20), - }; - void *iter = NULL, *pFirst; - int nelem = ARRAY_SIZE(get_attrs), a = 0; - int ret; - - or = osd_start_request(od); - if (!or) - return -ENOMEM; - - /* get attrs */ - osd_req_get_attributes(or, &osd_root_object); - osd_req_add_get_attr_list(or, get_attrs, ARRAY_SIZE(get_attrs)); - - ret = osd_finalize_request(or, 0, caps, NULL); - if (ret) - goto out; - - ret = osd_execute_request(or); - if (ret) { - OSD_ERR("Failed to detect %s => %d\n", _osd_ver_desc(or), ret); - goto out; - } - - osd_req_decode_get_attr_list(or, get_attrs, &nelem, &iter); - - OSD_INFO("Detected %s device\n", - _osd_ver_desc(or)); - - pFirst = get_attrs[a++].val_ptr; - OSD_INFO("VENDOR_IDENTIFICATION [%s]\n", - (char *)pFirst); - - pFirst = get_attrs[a++].val_ptr; - OSD_INFO("PRODUCT_IDENTIFICATION [%s]\n", - (char *)pFirst); - - pFirst = get_attrs[a++].val_ptr; - OSD_INFO("PRODUCT_MODEL [%s]\n", - (char *)pFirst); - - pFirst = get_attrs[a++].val_ptr; - OSD_INFO("PRODUCT_REVISION_LEVEL [%u]\n", - pFirst ? get_unaligned_be32(pFirst) : ~0U); - - pFirst = get_attrs[a++].val_ptr; - OSD_INFO("PRODUCT_SERIAL_NUMBER [%s]\n", - (char *)pFirst); - - odi->osdname_len = get_attrs[a].len; - /* Avoid NULL for memcmp optimization 0-length is good enough */ - odi->osdname = kzalloc(odi->osdname_len + 1, GFP_KERNEL); - if (!odi->osdname) { - ret = -ENOMEM; - goto out; - } - if (odi->osdname_len) - memcpy(odi->osdname, get_attrs[a].val_ptr, odi->osdname_len); - OSD_INFO("OSD_NAME [%s]\n", odi->osdname); - a++; - - pFirst = get_attrs[a++].val_ptr; - OSD_INFO("TOTAL_CAPACITY [0x%llx]\n", - pFirst ? _LLU(get_unaligned_be64(pFirst)) : ~0ULL); - - pFirst = get_attrs[a++].val_ptr; - OSD_INFO("USED_CAPACITY [0x%llx]\n", - pFirst ? _LLU(get_unaligned_be64(pFirst)) : ~0ULL); - - pFirst = get_attrs[a++].val_ptr; - OSD_INFO("NUMBER_OF_PARTITIONS [%llu]\n", - pFirst ? _LLU(get_unaligned_be64(pFirst)) : ~0ULL); - - if (a >= nelem) - goto out; - - /* FIXME: Where are the time utilities */ - pFirst = get_attrs[a++].val_ptr; - OSD_INFO("CLOCK [0x%6phN]\n", pFirst); - - if (a < nelem) { /* IBM-OSD-SIM bug, Might not have it */ - unsigned len = get_attrs[a].len; - char sid_dump[32*4 + 2]; /* 2nibbles+space+ASCII */ - - hex_dump_to_buffer(get_attrs[a].val_ptr, len, 32, 1, - sid_dump, sizeof(sid_dump), true); - OSD_INFO("OSD_SYSTEM_ID(%d)\n" - " [%s]\n", len, sid_dump); - - if (unlikely(len > sizeof(odi->systemid))) { - OSD_ERR("OSD Target error: OSD_SYSTEM_ID too long(%d). " - "device identification might not work\n", len); - len = sizeof(odi->systemid); - } - odi->systemid_len = len; - memcpy(odi->systemid, get_attrs[a].val_ptr, len); - a++; - } -out: - osd_end_request(or); - return ret; -} - -int osd_auto_detect_ver(struct osd_dev *od, - void *caps, struct osd_dev_info *odi) -{ - int ret; - - /* Auto-detect the osd version */ - ret = _osd_get_print_system_info(od, caps, odi); - if (ret) { - osd_dev_set_ver(od, OSD_VER1); - OSD_DEBUG("converting to OSD1\n"); - ret = _osd_get_print_system_info(od, caps, odi); - } - - return ret; -} -EXPORT_SYMBOL(osd_auto_detect_ver); - -static unsigned _osd_req_cdb_len(struct osd_request *or) -{ - return osd_req_is_ver1(or) ? OSDv1_TOTAL_CDB_LEN : OSD_TOTAL_CDB_LEN; -} - -static unsigned _osd_req_alist_elem_size(struct osd_request *or, unsigned len) -{ - return osd_req_is_ver1(or) ? - osdv1_attr_list_elem_size(len) : - osdv2_attr_list_elem_size(len); -} - -static void _osd_req_alist_elem_encode(struct osd_request *or, - void *attr_last, const struct osd_attr *oa) -{ - if (osd_req_is_ver1(or)) { - struct osdv1_attributes_list_element *attr = attr_last; - - attr->attr_page = cpu_to_be32(oa->attr_page); - attr->attr_id = cpu_to_be32(oa->attr_id); - attr->attr_bytes = cpu_to_be16(oa->len); - memcpy(attr->attr_val, oa->val_ptr, oa->len); - } else { - struct osdv2_attributes_list_element *attr = attr_last; - - attr->attr_page = cpu_to_be32(oa->attr_page); - attr->attr_id = cpu_to_be32(oa->attr_id); - attr->attr_bytes = cpu_to_be16(oa->len); - memcpy(attr->attr_val, oa->val_ptr, oa->len); - } -} - -static int _osd_req_alist_elem_decode(struct osd_request *or, - void *cur_p, struct osd_attr *oa, unsigned max_bytes) -{ - unsigned inc; - if (osd_req_is_ver1(or)) { - struct osdv1_attributes_list_element *attr = cur_p; - - if (max_bytes < sizeof(*attr)) - return -1; - - oa->len = be16_to_cpu(attr->attr_bytes); - inc = _osd_req_alist_elem_size(or, oa->len); - if (inc > max_bytes) - return -1; - - oa->attr_page = be32_to_cpu(attr->attr_page); - oa->attr_id = be32_to_cpu(attr->attr_id); - - /* OSD1: On empty attributes we return a pointer to 2 bytes - * of zeros. This keeps similar behaviour with OSD2. - * (See below) - */ - oa->val_ptr = likely(oa->len) ? attr->attr_val : - (u8 *)&attr->attr_bytes; - } else { - struct osdv2_attributes_list_element *attr = cur_p; - - if (max_bytes < sizeof(*attr)) - return -1; - - oa->len = be16_to_cpu(attr->attr_bytes); - inc = _osd_req_alist_elem_size(or, oa->len); - if (inc > max_bytes) - return -1; - - oa->attr_page = be32_to_cpu(attr->attr_page); - oa->attr_id = be32_to_cpu(attr->attr_id); - - /* OSD2: For convenience, on empty attributes, we return 8 bytes - * of zeros here. This keeps the same behaviour with OSD2r04, - * and is nice with null terminating ASCII fields. - * oa->val_ptr == NULL marks the end-of-list, or error. - */ - oa->val_ptr = likely(oa->len) ? attr->attr_val : attr->reserved; - } - return inc; -} - -static unsigned _osd_req_alist_size(struct osd_request *or, void *list_head) -{ - return osd_req_is_ver1(or) ? - osdv1_list_size(list_head) : - osdv2_list_size(list_head); -} - -static unsigned _osd_req_sizeof_alist_header(struct osd_request *or) -{ - return osd_req_is_ver1(or) ? - sizeof(struct osdv1_attributes_list_header) : - sizeof(struct osdv2_attributes_list_header); -} - -static void _osd_req_set_alist_type(struct osd_request *or, - void *list, int list_type) -{ - if (osd_req_is_ver1(or)) { - struct osdv1_attributes_list_header *attr_list = list; - - memset(attr_list, 0, sizeof(*attr_list)); - attr_list->type = list_type; - } else { - struct osdv2_attributes_list_header *attr_list = list; - - memset(attr_list, 0, sizeof(*attr_list)); - attr_list->type = list_type; - } -} - -static bool _osd_req_is_alist_type(struct osd_request *or, - void *list, int list_type) -{ - if (!list) - return false; - - if (osd_req_is_ver1(or)) { - struct osdv1_attributes_list_header *attr_list = list; - - return attr_list->type == list_type; - } else { - struct osdv2_attributes_list_header *attr_list = list; - - return attr_list->type == list_type; - } -} - -/* This is for List-objects not Attributes-Lists */ -static void _osd_req_encode_olist(struct osd_request *or, - struct osd_obj_id_list *list) -{ - struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb); - - if (osd_req_is_ver1(or)) { - cdbh->v1.list_identifier = list->list_identifier; - cdbh->v1.start_address = list->continuation_id; - } else { - cdbh->v2.list_identifier = list->list_identifier; - cdbh->v2.start_address = list->continuation_id; - } -} - -static osd_cdb_offset osd_req_encode_offset(struct osd_request *or, - u64 offset, unsigned *padding) -{ - return __osd_encode_offset(offset, padding, - osd_req_is_ver1(or) ? - OSDv1_OFFSET_MIN_SHIFT : OSD_OFFSET_MIN_SHIFT, - OSD_OFFSET_MAX_SHIFT); -} - -static struct osd_security_parameters * -_osd_req_sec_params(struct osd_request *or) -{ - struct osd_cdb *ocdb = &or->cdb; - - if (osd_req_is_ver1(or)) - return (struct osd_security_parameters *)&ocdb->v1.sec_params; - else - return (struct osd_security_parameters *)&ocdb->v2.sec_params; -} - -void osd_dev_init(struct osd_dev *osdd, struct scsi_device *scsi_device) -{ - memset(osdd, 0, sizeof(*osdd)); - osdd->scsi_device = scsi_device; - osdd->def_timeout = BLK_DEFAULT_SG_TIMEOUT; -#ifdef OSD_VER1_SUPPORT - osdd->version = OSD_VER2; -#endif - /* TODO: Allocate pools for osd_request attributes ... */ -} -EXPORT_SYMBOL(osd_dev_init); - -void osd_dev_fini(struct osd_dev *osdd) -{ - /* TODO: De-allocate pools */ - - osdd->scsi_device = NULL; -} -EXPORT_SYMBOL(osd_dev_fini); - -static struct osd_request *_osd_request_alloc(gfp_t gfp) -{ - struct osd_request *or; - - /* TODO: Use mempool with one saved request */ - or = kzalloc(sizeof(*or), gfp); - return or; -} - -static void _osd_request_free(struct osd_request *or) -{ - kfree(or); -} - -struct osd_request *osd_start_request(struct osd_dev *dev) -{ - struct osd_request *or; - - or = _osd_request_alloc(GFP_KERNEL); - if (!or) - return NULL; - - or->osd_dev = dev; - or->timeout = dev->def_timeout; - or->retries = OSD_REQ_RETRIES; - - return or; -} -EXPORT_SYMBOL(osd_start_request); - -static void _osd_free_seg(struct osd_request *or __unused, - struct _osd_req_data_segment *seg) -{ - if (!seg->buff || !seg->alloc_size) - return; - - kfree(seg->buff); - seg->buff = NULL; - seg->alloc_size = 0; -} - -static void _put_request(struct request *rq) -{ - /* - * If osd_finalize_request() was called but the request was not - * executed through the block layer, then we must release BIOs. - * TODO: Keep error code in or->async_error. Need to audit all - * code paths. - */ - if (unlikely(rq->bio)) - blk_mq_end_request(rq, BLK_STS_IOERR); - else - blk_put_request(rq); -} - -void osd_end_request(struct osd_request *or) -{ - struct request *rq = or->request; - - if (rq) { - if (rq->next_rq) { - _put_request(rq->next_rq); - rq->next_rq = NULL; - } - - _put_request(rq); - } - - _osd_free_seg(or, &or->get_attr); - _osd_free_seg(or, &or->enc_get_attr); - _osd_free_seg(or, &or->set_attr); - _osd_free_seg(or, &or->cdb_cont); - - _osd_request_free(or); -} -EXPORT_SYMBOL(osd_end_request); - -static void _set_error_resid(struct osd_request *or, struct request *req, - blk_status_t error) -{ - or->async_error = error; - or->req_errors = scsi_req(req)->result; - or->sense_len = scsi_req(req)->sense_len; - if (or->sense_len) - memcpy(or->sense, scsi_req(req)->sense, or->sense_len); - if (or->out.req) - or->out.residual = scsi_req(or->out.req)->resid_len; - if (or->in.req) - or->in.residual = scsi_req(or->in.req)->resid_len; -} - -int osd_execute_request(struct osd_request *or) -{ - blk_execute_rq(or->request->q, NULL, or->request, 0); - - if (scsi_req(or->request)->result) { - _set_error_resid(or, or->request, BLK_STS_IOERR); - return -EIO; - } - - _set_error_resid(or, or->request, BLK_STS_OK); - return 0; -} -EXPORT_SYMBOL(osd_execute_request); - -static void osd_request_async_done(struct request *req, blk_status_t error) -{ - struct osd_request *or = req->end_io_data; - - _set_error_resid(or, req, error); - if (req->next_rq) { - blk_put_request(req->next_rq); - req->next_rq = NULL; - } - - blk_put_request(req); - or->request = NULL; - or->in.req = NULL; - or->out.req = NULL; - - if (or->async_done) - or->async_done(or, or->async_private); - else - osd_end_request(or); -} - -int osd_execute_request_async(struct osd_request *or, - osd_req_done_fn *done, void *private) -{ - or->request->end_io_data = or; - or->async_private = private; - or->async_done = done; - - blk_execute_rq_nowait(or->request->q, NULL, or->request, 0, - osd_request_async_done); - return 0; -} -EXPORT_SYMBOL(osd_execute_request_async); - -u8 sg_out_pad_buffer[1 << OSDv1_OFFSET_MIN_SHIFT]; -u8 sg_in_pad_buffer[1 << OSDv1_OFFSET_MIN_SHIFT]; - -static int _osd_realloc_seg(struct osd_request *or, - struct _osd_req_data_segment *seg, unsigned max_bytes) -{ - void *buff; - - if (seg->alloc_size >= max_bytes) - return 0; - - buff = krealloc(seg->buff, max_bytes, GFP_KERNEL); - if (!buff) { - OSD_ERR("Failed to Realloc %d-bytes was-%d\n", max_bytes, - seg->alloc_size); - return -ENOMEM; - } - - memset(buff + seg->alloc_size, 0, max_bytes - seg->alloc_size); - seg->buff = buff; - seg->alloc_size = max_bytes; - return 0; -} - -static int _alloc_cdb_cont(struct osd_request *or, unsigned total_bytes) -{ - OSD_DEBUG("total_bytes=%d\n", total_bytes); - return _osd_realloc_seg(or, &or->cdb_cont, total_bytes); -} - -static int _alloc_set_attr_list(struct osd_request *or, - const struct osd_attr *oa, unsigned nelem, unsigned add_bytes) -{ - unsigned total_bytes = add_bytes; - - for (; nelem; --nelem, ++oa) - total_bytes += _osd_req_alist_elem_size(or, oa->len); - - OSD_DEBUG("total_bytes=%d\n", total_bytes); - return _osd_realloc_seg(or, &or->set_attr, total_bytes); -} - -static int _alloc_get_attr_desc(struct osd_request *or, unsigned max_bytes) -{ - OSD_DEBUG("total_bytes=%d\n", max_bytes); - return _osd_realloc_seg(or, &or->enc_get_attr, max_bytes); -} - -static int _alloc_get_attr_list(struct osd_request *or) -{ - OSD_DEBUG("total_bytes=%d\n", or->get_attr.total_bytes); - return _osd_realloc_seg(or, &or->get_attr, or->get_attr.total_bytes); -} - -/* - * Common to all OSD commands - */ - -static void _osdv1_req_encode_common(struct osd_request *or, - __be16 act, const struct osd_obj_id *obj, u64 offset, u64 len) -{ - struct osdv1_cdb *ocdb = &or->cdb.v1; - - /* - * For speed, the commands - * OSD_ACT_PERFORM_SCSI_COMMAND , V1 0x8F7E, V2 0x8F7C - * OSD_ACT_SCSI_TASK_MANAGEMENT , V1 0x8F7F, V2 0x8F7D - * are not supported here. Should pass zero and set after the call - */ - act &= cpu_to_be16(~0x0080); /* V1 action code */ - - OSD_DEBUG("OSDv1 execute opcode 0x%x\n", be16_to_cpu(act)); - - ocdb->h.varlen_cdb.opcode = VARIABLE_LENGTH_CMD; - ocdb->h.varlen_cdb.additional_cdb_length = OSD_ADDITIONAL_CDB_LENGTH; - ocdb->h.varlen_cdb.service_action = act; - - ocdb->h.partition = cpu_to_be64(obj->partition); - ocdb->h.object = cpu_to_be64(obj->id); - ocdb->h.v1.length = cpu_to_be64(len); - ocdb->h.v1.start_address = cpu_to_be64(offset); -} - -static void _osdv2_req_encode_common(struct osd_request *or, - __be16 act, const struct osd_obj_id *obj, u64 offset, u64 len) -{ - struct osdv2_cdb *ocdb = &or->cdb.v2; - - OSD_DEBUG("OSDv2 execute opcode 0x%x\n", be16_to_cpu(act)); - - ocdb->h.varlen_cdb.opcode = VARIABLE_LENGTH_CMD; - ocdb->h.varlen_cdb.additional_cdb_length = OSD_ADDITIONAL_CDB_LENGTH; - ocdb->h.varlen_cdb.service_action = act; - - ocdb->h.partition = cpu_to_be64(obj->partition); - ocdb->h.object = cpu_to_be64(obj->id); - ocdb->h.v2.length = cpu_to_be64(len); - ocdb->h.v2.start_address = cpu_to_be64(offset); -} - -static void _osd_req_encode_common(struct osd_request *or, - __be16 act, const struct osd_obj_id *obj, u64 offset, u64 len) -{ - if (osd_req_is_ver1(or)) - _osdv1_req_encode_common(or, act, obj, offset, len); - else - _osdv2_req_encode_common(or, act, obj, offset, len); -} - -/* - * Device commands - */ -/*TODO: void osd_req_set_master_seed_xchg(struct osd_request *, ...); */ -/*TODO: void osd_req_set_master_key(struct osd_request *, ...); */ - -void osd_req_format(struct osd_request *or, u64 tot_capacity) -{ - _osd_req_encode_common(or, OSD_ACT_FORMAT_OSD, &osd_root_object, 0, - tot_capacity); -} -EXPORT_SYMBOL(osd_req_format); - -int osd_req_list_dev_partitions(struct osd_request *or, - osd_id initial_id, struct osd_obj_id_list *list, unsigned nelem) -{ - return osd_req_list_partition_objects(or, 0, initial_id, list, nelem); -} -EXPORT_SYMBOL(osd_req_list_dev_partitions); - -static void _osd_req_encode_flush(struct osd_request *or, - enum osd_options_flush_scope_values op) -{ - struct osd_cdb_head *ocdb = osd_cdb_head(&or->cdb); - - ocdb->command_specific_options = op; -} - -void osd_req_flush_obsd(struct osd_request *or, - enum osd_options_flush_scope_values op) -{ - _osd_req_encode_common(or, OSD_ACT_FLUSH_OSD, &osd_root_object, 0, 0); - _osd_req_encode_flush(or, op); -} -EXPORT_SYMBOL(osd_req_flush_obsd); - -/*TODO: void osd_req_perform_scsi_command(struct osd_request *, - const u8 *cdb, ...); */ -/*TODO: void osd_req_task_management(struct osd_request *, ...); */ - -/* - * Partition commands - */ -static void _osd_req_encode_partition(struct osd_request *or, - __be16 act, osd_id partition) -{ - struct osd_obj_id par = { - .partition = partition, - .id = 0, - }; - - _osd_req_encode_common(or, act, &par, 0, 0); -} - -void osd_req_create_partition(struct osd_request *or, osd_id partition) -{ - _osd_req_encode_partition(or, OSD_ACT_CREATE_PARTITION, partition); -} -EXPORT_SYMBOL(osd_req_create_partition); - -void osd_req_remove_partition(struct osd_request *or, osd_id partition) -{ - _osd_req_encode_partition(or, OSD_ACT_REMOVE_PARTITION, partition); -} -EXPORT_SYMBOL(osd_req_remove_partition); - -/*TODO: void osd_req_set_partition_key(struct osd_request *, - osd_id partition, u8 new_key_id[OSD_CRYPTO_KEYID_SIZE], - u8 seed[OSD_CRYPTO_SEED_SIZE]); */ - -static int _osd_req_list_objects(struct osd_request *or, - __be16 action, const struct osd_obj_id *obj, osd_id initial_id, - struct osd_obj_id_list *list, unsigned nelem) -{ - struct request_queue *q = osd_request_queue(or->osd_dev); - u64 len = nelem * sizeof(osd_id) + sizeof(*list); - struct bio *bio; - - _osd_req_encode_common(or, action, obj, (u64)initial_id, len); - - if (list->list_identifier) - _osd_req_encode_olist(or, list); - - WARN_ON(or->in.bio); - bio = bio_map_kern(q, list, len, GFP_KERNEL); - if (IS_ERR(bio)) { - OSD_ERR("!!! Failed to allocate list_objects BIO\n"); - return PTR_ERR(bio); - } - - bio_set_op_attrs(bio, REQ_OP_READ, 0); - or->in.bio = bio; - or->in.total_bytes = bio->bi_iter.bi_size; - return 0; -} - -int osd_req_list_partition_collections(struct osd_request *or, - osd_id partition, osd_id initial_id, struct osd_obj_id_list *list, - unsigned nelem) -{ - struct osd_obj_id par = { - .partition = partition, - .id = 0, - }; - - return osd_req_list_collection_objects(or, &par, initial_id, list, - nelem); -} -EXPORT_SYMBOL(osd_req_list_partition_collections); - -int osd_req_list_partition_objects(struct osd_request *or, - osd_id partition, osd_id initial_id, struct osd_obj_id_list *list, - unsigned nelem) -{ - struct osd_obj_id par = { - .partition = partition, - .id = 0, - }; - - return _osd_req_list_objects(or, OSD_ACT_LIST, &par, initial_id, list, - nelem); -} -EXPORT_SYMBOL(osd_req_list_partition_objects); - -void osd_req_flush_partition(struct osd_request *or, - osd_id partition, enum osd_options_flush_scope_values op) -{ - _osd_req_encode_partition(or, OSD_ACT_FLUSH_PARTITION, partition); - _osd_req_encode_flush(or, op); -} -EXPORT_SYMBOL(osd_req_flush_partition); - -/* - * Collection commands - */ -/*TODO: void osd_req_create_collection(struct osd_request *, - const struct osd_obj_id *); */ -/*TODO: void osd_req_remove_collection(struct osd_request *, - const struct osd_obj_id *); */ - -int osd_req_list_collection_objects(struct osd_request *or, - const struct osd_obj_id *obj, osd_id initial_id, - struct osd_obj_id_list *list, unsigned nelem) -{ - return _osd_req_list_objects(or, OSD_ACT_LIST_COLLECTION, obj, - initial_id, list, nelem); -} -EXPORT_SYMBOL(osd_req_list_collection_objects); - -/*TODO: void query(struct osd_request *, ...); V2 */ - -void osd_req_flush_collection(struct osd_request *or, - const struct osd_obj_id *obj, enum osd_options_flush_scope_values op) -{ - _osd_req_encode_common(or, OSD_ACT_FLUSH_PARTITION, obj, 0, 0); - _osd_req_encode_flush(or, op); -} -EXPORT_SYMBOL(osd_req_flush_collection); - -/*TODO: void get_member_attrs(struct osd_request *, ...); V2 */ -/*TODO: void set_member_attrs(struct osd_request *, ...); V2 */ - -/* - * Object commands - */ -void osd_req_create_object(struct osd_request *or, struct osd_obj_id *obj) -{ - _osd_req_encode_common(or, OSD_ACT_CREATE, obj, 0, 0); -} -EXPORT_SYMBOL(osd_req_create_object); - -void osd_req_remove_object(struct osd_request *or, struct osd_obj_id *obj) -{ - _osd_req_encode_common(or, OSD_ACT_REMOVE, obj, 0, 0); -} -EXPORT_SYMBOL(osd_req_remove_object); - - -/*TODO: void osd_req_create_multi(struct osd_request *or, - struct osd_obj_id *first, struct osd_obj_id_list *list, unsigned nelem); -*/ - -void osd_req_write(struct osd_request *or, - const struct osd_obj_id *obj, u64 offset, - struct bio *bio, u64 len) -{ - _osd_req_encode_common(or, OSD_ACT_WRITE, obj, offset, len); - WARN_ON(or->out.bio || or->out.total_bytes); - WARN_ON(!op_is_write(bio_op(bio))); - or->out.bio = bio; - or->out.total_bytes = len; -} -EXPORT_SYMBOL(osd_req_write); - -int osd_req_write_kern(struct osd_request *or, - const struct osd_obj_id *obj, u64 offset, void* buff, u64 len) -{ - struct request_queue *req_q = osd_request_queue(or->osd_dev); - struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL); - - if (IS_ERR(bio)) - return PTR_ERR(bio); - - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - osd_req_write(or, obj, offset, bio, len); - return 0; -} -EXPORT_SYMBOL(osd_req_write_kern); - -/*TODO: void osd_req_append(struct osd_request *, - const struct osd_obj_id *, struct bio *data_out); */ -/*TODO: void osd_req_create_write(struct osd_request *, - const struct osd_obj_id *, struct bio *data_out, u64 offset); */ -/*TODO: void osd_req_clear(struct osd_request *, - const struct osd_obj_id *, u64 offset, u64 len); */ -/*TODO: void osd_req_punch(struct osd_request *, - const struct osd_obj_id *, u64 offset, u64 len); V2 */ - -void osd_req_flush_object(struct osd_request *or, - const struct osd_obj_id *obj, enum osd_options_flush_scope_values op, - /*V2*/ u64 offset, /*V2*/ u64 len) -{ - if (unlikely(osd_req_is_ver1(or) && (offset || len))) { - OSD_DEBUG("OSD Ver1 flush on specific range ignored\n"); - offset = 0; - len = 0; - } - - _osd_req_encode_common(or, OSD_ACT_FLUSH, obj, offset, len); - _osd_req_encode_flush(or, op); -} -EXPORT_SYMBOL(osd_req_flush_object); - -void osd_req_read(struct osd_request *or, - const struct osd_obj_id *obj, u64 offset, - struct bio *bio, u64 len) -{ - _osd_req_encode_common(or, OSD_ACT_READ, obj, offset, len); - WARN_ON(or->in.bio || or->in.total_bytes); - WARN_ON(op_is_write(bio_op(bio))); - or->in.bio = bio; - or->in.total_bytes = len; -} -EXPORT_SYMBOL(osd_req_read); - -int osd_req_read_kern(struct osd_request *or, - const struct osd_obj_id *obj, u64 offset, void* buff, u64 len) -{ - struct request_queue *req_q = osd_request_queue(or->osd_dev); - struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL); - - if (IS_ERR(bio)) - return PTR_ERR(bio); - - osd_req_read(or, obj, offset, bio, len); - return 0; -} -EXPORT_SYMBOL(osd_req_read_kern); - -static int _add_sg_continuation_descriptor(struct osd_request *or, - const struct osd_sg_entry *sglist, unsigned numentries, u64 *len) -{ - struct osd_sg_continuation_descriptor *oscd; - u32 oscd_size; - unsigned i; - int ret; - - oscd_size = sizeof(*oscd) + numentries * sizeof(oscd->entries[0]); - - if (!or->cdb_cont.total_bytes) { - /* First time, jump over the header, we will write to: - * cdb_cont.buff + cdb_cont.total_bytes - */ - or->cdb_cont.total_bytes = - sizeof(struct osd_continuation_segment_header); - } - - ret = _alloc_cdb_cont(or, or->cdb_cont.total_bytes + oscd_size); - if (unlikely(ret)) - return ret; - - oscd = or->cdb_cont.buff + or->cdb_cont.total_bytes; - oscd->hdr.type = cpu_to_be16(SCATTER_GATHER_LIST); - oscd->hdr.pad_length = 0; - oscd->hdr.length = cpu_to_be32(oscd_size - sizeof(*oscd)); - - *len = 0; - /* copy the sg entries and convert to network byte order */ - for (i = 0; i < numentries; i++) { - oscd->entries[i].offset = cpu_to_be64(sglist[i].offset); - oscd->entries[i].len = cpu_to_be64(sglist[i].len); - *len += sglist[i].len; - } - - or->cdb_cont.total_bytes += oscd_size; - OSD_DEBUG("total_bytes=%d oscd_size=%d numentries=%d\n", - or->cdb_cont.total_bytes, oscd_size, numentries); - return 0; -} - -static int _osd_req_finalize_cdb_cont(struct osd_request *or, const u8 *cap_key) -{ - struct request_queue *req_q = osd_request_queue(or->osd_dev); - struct bio *bio; - struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb); - struct osd_continuation_segment_header *cont_seg_hdr; - - if (!or->cdb_cont.total_bytes) - return 0; - - cont_seg_hdr = or->cdb_cont.buff; - cont_seg_hdr->format = CDB_CONTINUATION_FORMAT_V2; - cont_seg_hdr->service_action = cdbh->varlen_cdb.service_action; - - /* create a bio for continuation segment */ - bio = bio_map_kern(req_q, or->cdb_cont.buff, or->cdb_cont.total_bytes, - GFP_KERNEL); - if (IS_ERR(bio)) - return PTR_ERR(bio); - - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - - /* integrity check the continuation before the bio is linked - * with the other data segments since the continuation - * integrity is separate from the other data segments. - */ - osd_sec_sign_data(cont_seg_hdr->integrity_check, bio, cap_key); - - cdbh->v2.cdb_continuation_length = cpu_to_be32(or->cdb_cont.total_bytes); - - /* we can't use _req_append_segment, because we need to link in the - * continuation bio to the head of the bio list - the - * continuation segment (if it exists) is always the first segment in - * the out data buffer. - */ - bio->bi_next = or->out.bio; - or->out.bio = bio; - or->out.total_bytes += or->cdb_cont.total_bytes; - - return 0; -} - -/* osd_req_write_sg: Takes a @bio that points to the data out buffer and an - * @sglist that has the scatter gather entries. Scatter-gather enables a write - * of multiple none-contiguous areas of an object, in a single call. The extents - * may overlap and/or be in any order. The only constrain is that: - * total_bytes(sglist) >= total_bytes(bio) - */ -int osd_req_write_sg(struct osd_request *or, - const struct osd_obj_id *obj, struct bio *bio, - const struct osd_sg_entry *sglist, unsigned numentries) -{ - u64 len; - int ret = _add_sg_continuation_descriptor(or, sglist, numentries, &len); - - if (ret) - return ret; - osd_req_write(or, obj, 0, bio, len); - - return 0; -} -EXPORT_SYMBOL(osd_req_write_sg); - -/* osd_req_read_sg: Read multiple extents of an object into @bio - * See osd_req_write_sg - */ -int osd_req_read_sg(struct osd_request *or, - const struct osd_obj_id *obj, struct bio *bio, - const struct osd_sg_entry *sglist, unsigned numentries) -{ - u64 len; - u64 off; - int ret; - - if (numentries > 1) { - off = 0; - ret = _add_sg_continuation_descriptor(or, sglist, numentries, - &len); - if (ret) - return ret; - } else { - /* Optimize the case of single segment, read_sg is a - * bidi operation. - */ - len = sglist->len; - off = sglist->offset; - } - osd_req_read(or, obj, off, bio, len); - - return 0; -} -EXPORT_SYMBOL(osd_req_read_sg); - -/* SG-list write/read Kern API - * - * osd_req_{write,read}_sg_kern takes an array of @buff pointers and an array - * of sg_entries. @numentries indicates how many pointers and sg_entries there - * are. By requiring an array of buff pointers. This allows a caller to do a - * single write/read and scatter into multiple buffers. - * NOTE: Each buffer + len should not cross a page boundary. - */ -static struct bio *_create_sg_bios(struct osd_request *or, - void **buff, const struct osd_sg_entry *sglist, unsigned numentries) -{ - struct request_queue *q = osd_request_queue(or->osd_dev); - struct bio *bio; - unsigned i; - - bio = bio_kmalloc(GFP_KERNEL, numentries); - if (unlikely(!bio)) { - OSD_DEBUG("Failed to allocate BIO size=%u\n", numentries); - return ERR_PTR(-ENOMEM); - } - - for (i = 0; i < numentries; i++) { - unsigned offset = offset_in_page(buff[i]); - struct page *page = virt_to_page(buff[i]); - unsigned len = sglist[i].len; - unsigned added_len; - - BUG_ON(offset + len > PAGE_SIZE); - added_len = bio_add_pc_page(q, bio, page, len, offset); - if (unlikely(len != added_len)) { - OSD_DEBUG("bio_add_pc_page len(%d) != added_len(%d)\n", - len, added_len); - bio_put(bio); - return ERR_PTR(-ENOMEM); - } - } - - return bio; -} - -int osd_req_write_sg_kern(struct osd_request *or, - const struct osd_obj_id *obj, void **buff, - const struct osd_sg_entry *sglist, unsigned numentries) -{ - struct bio *bio = _create_sg_bios(or, buff, sglist, numentries); - if (IS_ERR(bio)) - return PTR_ERR(bio); - - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - osd_req_write_sg(or, obj, bio, sglist, numentries); - - return 0; -} -EXPORT_SYMBOL(osd_req_write_sg_kern); - -int osd_req_read_sg_kern(struct osd_request *or, - const struct osd_obj_id *obj, void **buff, - const struct osd_sg_entry *sglist, unsigned numentries) -{ - struct bio *bio = _create_sg_bios(or, buff, sglist, numentries); - if (IS_ERR(bio)) - return PTR_ERR(bio); - - osd_req_read_sg(or, obj, bio, sglist, numentries); - - return 0; -} -EXPORT_SYMBOL(osd_req_read_sg_kern); - - - -void osd_req_get_attributes(struct osd_request *or, - const struct osd_obj_id *obj) -{ - _osd_req_encode_common(or, OSD_ACT_GET_ATTRIBUTES, obj, 0, 0); -} -EXPORT_SYMBOL(osd_req_get_attributes); - -void osd_req_set_attributes(struct osd_request *or, - const struct osd_obj_id *obj) -{ - _osd_req_encode_common(or, OSD_ACT_SET_ATTRIBUTES, obj, 0, 0); -} -EXPORT_SYMBOL(osd_req_set_attributes); - -/* - * Attributes List-mode - */ - -int osd_req_add_set_attr_list(struct osd_request *or, - const struct osd_attr *oa, unsigned nelem) -{ - unsigned total_bytes = or->set_attr.total_bytes; - void *attr_last; - int ret; - - if (or->attributes_mode && - or->attributes_mode != OSD_CDB_GET_SET_ATTR_LISTS) { - WARN_ON(1); - return -EINVAL; - } - or->attributes_mode = OSD_CDB_GET_SET_ATTR_LISTS; - - if (!total_bytes) { /* first-time: allocate and put list header */ - total_bytes = _osd_req_sizeof_alist_header(or); - ret = _alloc_set_attr_list(or, oa, nelem, total_bytes); - if (ret) - return ret; - _osd_req_set_alist_type(or, or->set_attr.buff, - OSD_ATTR_LIST_SET_RETRIEVE); - } - attr_last = or->set_attr.buff + total_bytes; - - for (; nelem; --nelem) { - unsigned elem_size = _osd_req_alist_elem_size(or, oa->len); - - total_bytes += elem_size; - if (unlikely(or->set_attr.alloc_size < total_bytes)) { - or->set_attr.total_bytes = total_bytes - elem_size; - ret = _alloc_set_attr_list(or, oa, nelem, total_bytes); - if (ret) - return ret; - attr_last = - or->set_attr.buff + or->set_attr.total_bytes; - } - - _osd_req_alist_elem_encode(or, attr_last, oa); - - attr_last += elem_size; - ++oa; - } - - or->set_attr.total_bytes = total_bytes; - return 0; -} -EXPORT_SYMBOL(osd_req_add_set_attr_list); - -static int _req_append_segment(struct osd_request *or, - unsigned padding, struct _osd_req_data_segment *seg, - struct _osd_req_data_segment *last_seg, struct _osd_io_info *io) -{ - void *pad_buff; - int ret; - - if (padding) { - /* check if we can just add it to last buffer */ - if (last_seg && - (padding <= last_seg->alloc_size - last_seg->total_bytes)) - pad_buff = last_seg->buff + last_seg->total_bytes; - else - pad_buff = io->pad_buff; - - ret = blk_rq_map_kern(io->req->q, io->req, pad_buff, padding, - GFP_KERNEL); - if (ret) - return ret; - io->total_bytes += padding; - } - - ret = blk_rq_map_kern(io->req->q, io->req, seg->buff, seg->total_bytes, - GFP_KERNEL); - if (ret) - return ret; - - io->total_bytes += seg->total_bytes; - OSD_DEBUG("padding=%d buff=%p total_bytes=%d\n", padding, seg->buff, - seg->total_bytes); - return 0; -} - -static int _osd_req_finalize_set_attr_list(struct osd_request *or) -{ - struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb); - unsigned padding; - int ret; - - if (!or->set_attr.total_bytes) { - cdbh->attrs_list.set_attr_offset = OSD_OFFSET_UNUSED; - return 0; - } - - cdbh->attrs_list.set_attr_bytes = cpu_to_be32(or->set_attr.total_bytes); - cdbh->attrs_list.set_attr_offset = - osd_req_encode_offset(or, or->out.total_bytes, &padding); - - ret = _req_append_segment(or, padding, &or->set_attr, - or->out.last_seg, &or->out); - if (ret) - return ret; - - or->out.last_seg = &or->set_attr; - return 0; -} - -int osd_req_add_get_attr_list(struct osd_request *or, - const struct osd_attr *oa, unsigned nelem) -{ - unsigned total_bytes = or->enc_get_attr.total_bytes; - void *attr_last; - int ret; - - if (or->attributes_mode && - or->attributes_mode != OSD_CDB_GET_SET_ATTR_LISTS) { - WARN_ON(1); - return -EINVAL; - } - or->attributes_mode = OSD_CDB_GET_SET_ATTR_LISTS; - - /* first time calc data-in list header size */ - if (!or->get_attr.total_bytes) - or->get_attr.total_bytes = _osd_req_sizeof_alist_header(or); - - /* calc data-out info */ - if (!total_bytes) { /* first-time: allocate and put list header */ - unsigned max_bytes; - - total_bytes = _osd_req_sizeof_alist_header(or); - max_bytes = total_bytes + - nelem * sizeof(struct osd_attributes_list_attrid); - ret = _alloc_get_attr_desc(or, max_bytes); - if (ret) - return ret; - - _osd_req_set_alist_type(or, or->enc_get_attr.buff, - OSD_ATTR_LIST_GET); - } - attr_last = or->enc_get_attr.buff + total_bytes; - - for (; nelem; --nelem) { - struct osd_attributes_list_attrid *attrid; - const unsigned cur_size = sizeof(*attrid); - - total_bytes += cur_size; - if (unlikely(or->enc_get_attr.alloc_size < total_bytes)) { - or->enc_get_attr.total_bytes = total_bytes - cur_size; - ret = _alloc_get_attr_desc(or, - total_bytes + nelem * sizeof(*attrid)); - if (ret) - return ret; - attr_last = or->enc_get_attr.buff + - or->enc_get_attr.total_bytes; - } - - attrid = attr_last; - attrid->attr_page = cpu_to_be32(oa->attr_page); - attrid->attr_id = cpu_to_be32(oa->attr_id); - - attr_last += cur_size; - - /* calc data-in size */ - or->get_attr.total_bytes += - _osd_req_alist_elem_size(or, oa->len); - ++oa; - } - - or->enc_get_attr.total_bytes = total_bytes; - - OSD_DEBUG( - "get_attr.total_bytes=%u(%u) enc_get_attr.total_bytes=%u(%zu)\n", - or->get_attr.total_bytes, - or->get_attr.total_bytes - _osd_req_sizeof_alist_header(or), - or->enc_get_attr.total_bytes, - (or->enc_get_attr.total_bytes - _osd_req_sizeof_alist_header(or)) - / sizeof(struct osd_attributes_list_attrid)); - - return 0; -} -EXPORT_SYMBOL(osd_req_add_get_attr_list); - -static int _osd_req_finalize_get_attr_list(struct osd_request *or) -{ - struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb); - unsigned out_padding; - unsigned in_padding; - int ret; - - if (!or->enc_get_attr.total_bytes) { - cdbh->attrs_list.get_attr_desc_offset = OSD_OFFSET_UNUSED; - cdbh->attrs_list.get_attr_offset = OSD_OFFSET_UNUSED; - return 0; - } - - ret = _alloc_get_attr_list(or); - if (ret) - return ret; - - /* The out-going buffer info update */ - OSD_DEBUG("out-going\n"); - cdbh->attrs_list.get_attr_desc_bytes = - cpu_to_be32(or->enc_get_attr.total_bytes); - - cdbh->attrs_list.get_attr_desc_offset = - osd_req_encode_offset(or, or->out.total_bytes, &out_padding); - - ret = _req_append_segment(or, out_padding, &or->enc_get_attr, - or->out.last_seg, &or->out); - if (ret) - return ret; - or->out.last_seg = &or->enc_get_attr; - - /* The incoming buffer info update */ - OSD_DEBUG("in-coming\n"); - cdbh->attrs_list.get_attr_alloc_length = - cpu_to_be32(or->get_attr.total_bytes); - - cdbh->attrs_list.get_attr_offset = - osd_req_encode_offset(or, or->in.total_bytes, &in_padding); - - ret = _req_append_segment(or, in_padding, &or->get_attr, NULL, - &or->in); - if (ret) - return ret; - or->in.last_seg = &or->get_attr; - - return 0; -} - -int osd_req_decode_get_attr_list(struct osd_request *or, - struct osd_attr *oa, int *nelem, void **iterator) -{ - unsigned cur_bytes, returned_bytes; - int n; - const unsigned sizeof_attr_list = _osd_req_sizeof_alist_header(or); - void *cur_p; - - if (!_osd_req_is_alist_type(or, or->get_attr.buff, - OSD_ATTR_LIST_SET_RETRIEVE)) { - oa->attr_page = 0; - oa->attr_id = 0; - oa->val_ptr = NULL; - oa->len = 0; - *iterator = NULL; - return 0; - } - - if (*iterator) { - BUG_ON((*iterator < or->get_attr.buff) || - (or->get_attr.buff + or->get_attr.alloc_size < *iterator)); - cur_p = *iterator; - cur_bytes = (*iterator - or->get_attr.buff) - sizeof_attr_list; - returned_bytes = or->get_attr.total_bytes; - } else { /* first time decode the list header */ - cur_bytes = sizeof_attr_list; - returned_bytes = _osd_req_alist_size(or, or->get_attr.buff) + - sizeof_attr_list; - - cur_p = or->get_attr.buff + sizeof_attr_list; - - if (returned_bytes > or->get_attr.alloc_size) { - OSD_DEBUG("target report: space was not big enough! " - "Allocate=%u Needed=%u\n", - or->get_attr.alloc_size, - returned_bytes + sizeof_attr_list); - - returned_bytes = - or->get_attr.alloc_size - sizeof_attr_list; - } - or->get_attr.total_bytes = returned_bytes; - } - - for (n = 0; (n < *nelem) && (cur_bytes < returned_bytes); ++n) { - int inc = _osd_req_alist_elem_decode(or, cur_p, oa, - returned_bytes - cur_bytes); - - if (inc < 0) { - OSD_ERR("BAD FOOD from target. list not valid!" - "c=%d r=%d n=%d\n", - cur_bytes, returned_bytes, n); - oa->val_ptr = NULL; - cur_bytes = returned_bytes; /* break the caller loop */ - break; - } - - cur_bytes += inc; - cur_p += inc; - ++oa; - } - - *iterator = (returned_bytes - cur_bytes) ? cur_p : NULL; - *nelem = n; - return returned_bytes - cur_bytes; -} -EXPORT_SYMBOL(osd_req_decode_get_attr_list); - -/* - * Attributes Page-mode - */ - -int osd_req_add_get_attr_page(struct osd_request *or, - u32 page_id, void *attar_page, unsigned max_page_len, - const struct osd_attr *set_one_attr) -{ - struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb); - - if (or->attributes_mode && - or->attributes_mode != OSD_CDB_GET_ATTR_PAGE_SET_ONE) { - WARN_ON(1); - return -EINVAL; - } - or->attributes_mode = OSD_CDB_GET_ATTR_PAGE_SET_ONE; - - or->get_attr.buff = attar_page; - or->get_attr.total_bytes = max_page_len; - - cdbh->attrs_page.get_attr_page = cpu_to_be32(page_id); - cdbh->attrs_page.get_attr_alloc_length = cpu_to_be32(max_page_len); - - if (!set_one_attr || !set_one_attr->attr_page) - return 0; /* The set is optional */ - - or->set_attr.buff = set_one_attr->val_ptr; - or->set_attr.total_bytes = set_one_attr->len; - - cdbh->attrs_page.set_attr_page = cpu_to_be32(set_one_attr->attr_page); - cdbh->attrs_page.set_attr_id = cpu_to_be32(set_one_attr->attr_id); - cdbh->attrs_page.set_attr_length = cpu_to_be32(set_one_attr->len); - return 0; -} -EXPORT_SYMBOL(osd_req_add_get_attr_page); - -static int _osd_req_finalize_attr_page(struct osd_request *or) -{ - struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb); - unsigned in_padding, out_padding; - int ret; - - /* returned page */ - cdbh->attrs_page.get_attr_offset = - osd_req_encode_offset(or, or->in.total_bytes, &in_padding); - - ret = _req_append_segment(or, in_padding, &or->get_attr, NULL, - &or->in); - if (ret) - return ret; - - if (or->set_attr.total_bytes == 0) - return 0; - - /* set one value */ - cdbh->attrs_page.set_attr_offset = - osd_req_encode_offset(or, or->out.total_bytes, &out_padding); - - ret = _req_append_segment(or, out_padding, &or->set_attr, NULL, - &or->out); - return ret; -} - -static inline void osd_sec_parms_set_out_offset(bool is_v1, - struct osd_security_parameters *sec_parms, osd_cdb_offset offset) -{ - if (is_v1) - sec_parms->v1.data_out_integrity_check_offset = offset; - else - sec_parms->v2.data_out_integrity_check_offset = offset; -} - -static inline void osd_sec_parms_set_in_offset(bool is_v1, - struct osd_security_parameters *sec_parms, osd_cdb_offset offset) -{ - if (is_v1) - sec_parms->v1.data_in_integrity_check_offset = offset; - else - sec_parms->v2.data_in_integrity_check_offset = offset; -} - -static int _osd_req_finalize_data_integrity(struct osd_request *or, - bool has_in, bool has_out, struct bio *out_data_bio, u64 out_data_bytes, - const u8 *cap_key) -{ - struct osd_security_parameters *sec_parms = _osd_req_sec_params(or); - int ret; - - if (!osd_is_sec_alldata(sec_parms)) - return 0; - - if (has_out) { - struct _osd_req_data_segment seg = { - .buff = &or->out_data_integ, - .total_bytes = sizeof(or->out_data_integ), - }; - unsigned pad; - - or->out_data_integ.data_bytes = cpu_to_be64(out_data_bytes); - or->out_data_integ.set_attributes_bytes = cpu_to_be64( - or->set_attr.total_bytes); - or->out_data_integ.get_attributes_bytes = cpu_to_be64( - or->enc_get_attr.total_bytes); - - osd_sec_parms_set_out_offset(osd_req_is_ver1(or), sec_parms, - osd_req_encode_offset(or, or->out.total_bytes, &pad)); - - ret = _req_append_segment(or, pad, &seg, or->out.last_seg, - &or->out); - if (ret) - return ret; - or->out.last_seg = NULL; - - /* they are now all chained to request sign them all together */ - osd_sec_sign_data(&or->out_data_integ, out_data_bio, - cap_key); - } - - if (has_in) { - struct _osd_req_data_segment seg = { - .buff = &or->in_data_integ, - .total_bytes = sizeof(or->in_data_integ), - }; - unsigned pad; - - osd_sec_parms_set_in_offset(osd_req_is_ver1(or), sec_parms, - osd_req_encode_offset(or, or->in.total_bytes, &pad)); - - ret = _req_append_segment(or, pad, &seg, or->in.last_seg, - &or->in); - if (ret) - return ret; - - or->in.last_seg = NULL; - } - - return 0; -} - -/* - * osd_finalize_request and helpers - */ -static struct request *_make_request(struct request_queue *q, bool has_write, - struct _osd_io_info *oii) -{ - struct request *req; - struct bio *bio = oii->bio; - int ret; - - req = blk_get_request(q, has_write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, - 0); - if (IS_ERR(req)) - return req; - - for_each_bio(bio) { - struct bio *bounce_bio = bio; - - ret = blk_rq_append_bio(req, &bounce_bio); - if (ret) - return ERR_PTR(ret); - } - - return req; -} - -static int _init_blk_request(struct osd_request *or, - bool has_in, bool has_out) -{ - struct scsi_device *scsi_device = or->osd_dev->scsi_device; - struct request_queue *q = scsi_device->request_queue; - struct request *req; - int ret; - - req = _make_request(q, has_out, has_out ? &or->out : &or->in); - if (IS_ERR(req)) { - ret = PTR_ERR(req); - goto out; - } - - or->request = req; - req->rq_flags |= RQF_QUIET; - - req->timeout = or->timeout; - scsi_req(req)->retries = or->retries; - - if (has_out) { - or->out.req = req; - if (has_in) { - /* allocate bidi request */ - req = _make_request(q, false, &or->in); - if (IS_ERR(req)) { - OSD_DEBUG("blk_get_request for bidi failed\n"); - ret = PTR_ERR(req); - goto out; - } - or->in.req = or->request->next_rq = req; - } - } else if (has_in) - or->in.req = req; - - ret = 0; -out: - OSD_DEBUG("or=%p has_in=%d has_out=%d => %d, %p\n", - or, has_in, has_out, ret, or->request); - return ret; -} - -int osd_finalize_request(struct osd_request *or, - u8 options, const void *cap, const u8 *cap_key) -{ - struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb); - bool has_in, has_out; - /* Save for data_integrity without the cdb_continuation */ - struct bio *out_data_bio = or->out.bio; - u64 out_data_bytes = or->out.total_bytes; - int ret; - - if (options & OSD_REQ_FUA) - cdbh->options |= OSD_CDB_FUA; - - if (options & OSD_REQ_DPO) - cdbh->options |= OSD_CDB_DPO; - - if (options & OSD_REQ_BYPASS_TIMESTAMPS) - cdbh->timestamp_control = OSD_CDB_BYPASS_TIMESTAMPS; - - osd_set_caps(&or->cdb, cap); - - has_in = or->in.bio || or->get_attr.total_bytes; - has_out = or->out.bio || or->cdb_cont.total_bytes || - or->set_attr.total_bytes || or->enc_get_attr.total_bytes; - - ret = _osd_req_finalize_cdb_cont(or, cap_key); - if (ret) { - OSD_DEBUG("_osd_req_finalize_cdb_cont failed\n"); - return ret; - } - ret = _init_blk_request(or, has_in, has_out); - if (ret) { - OSD_DEBUG("_init_blk_request failed\n"); - return ret; - } - - or->out.pad_buff = sg_out_pad_buffer; - or->in.pad_buff = sg_in_pad_buffer; - - if (!or->attributes_mode) - or->attributes_mode = OSD_CDB_GET_SET_ATTR_LISTS; - cdbh->command_specific_options |= or->attributes_mode; - if (or->attributes_mode == OSD_CDB_GET_ATTR_PAGE_SET_ONE) { - ret = _osd_req_finalize_attr_page(or); - if (ret) { - OSD_DEBUG("_osd_req_finalize_attr_page failed\n"); - return ret; - } - } else { - /* TODO: I think that for the GET_ATTR command these 2 should - * be reversed to keep them in execution order (for embedded - * targets with low memory footprint) - */ - ret = _osd_req_finalize_set_attr_list(or); - if (ret) { - OSD_DEBUG("_osd_req_finalize_set_attr_list failed\n"); - return ret; - } - - ret = _osd_req_finalize_get_attr_list(or); - if (ret) { - OSD_DEBUG("_osd_req_finalize_get_attr_list failed\n"); - return ret; - } - } - - ret = _osd_req_finalize_data_integrity(or, has_in, has_out, - out_data_bio, out_data_bytes, - cap_key); - if (ret) - return ret; - - osd_sec_sign_cdb(&or->cdb, cap_key); - - scsi_req(or->request)->cmd = or->cdb.buff; - scsi_req(or->request)->cmd_len = _osd_req_cdb_len(or); - - return 0; -} -EXPORT_SYMBOL(osd_finalize_request); - -static bool _is_osd_security_code(int code) -{ - return (code == osd_security_audit_value_frozen) || - (code == osd_security_working_key_frozen) || - (code == osd_nonce_not_unique) || - (code == osd_nonce_timestamp_out_of_range) || - (code == osd_invalid_dataout_buffer_integrity_check_value); -} - -#define OSD_SENSE_PRINT1(fmt, a...) \ - do { \ - if (__cur_sense_need_output) \ - OSD_ERR(fmt, ##a); \ - } while (0) - -#define OSD_SENSE_PRINT2(fmt, a...) OSD_SENSE_PRINT1(" " fmt, ##a) - -int osd_req_decode_sense_full(struct osd_request *or, - struct osd_sense_info *osi, bool silent, - struct osd_obj_id *bad_obj_list __unused, int max_obj __unused, - struct osd_attr *bad_attr_list, int max_attr) -{ - int sense_len, original_sense_len; - struct osd_sense_info local_osi; - struct scsi_sense_descriptor_based *ssdb; - void *cur_descriptor; -#if (CONFIG_SCSI_OSD_DPRINT_SENSE == 0) - const bool __cur_sense_need_output = false; -#else - bool __cur_sense_need_output = !silent; -#endif - int ret; - - if (likely(!or->req_errors)) - return 0; - - osi = osi ? : &local_osi; - memset(osi, 0, sizeof(*osi)); - - ssdb = (typeof(ssdb))or->sense; - sense_len = or->sense_len; - if ((sense_len < (int)sizeof(*ssdb) || !ssdb->sense_key)) { - OSD_ERR("Block-layer returned error(0x%x) but " - "sense_len(%u) || key(%d) is empty\n", - or->req_errors, sense_len, ssdb->sense_key); - goto analyze; - } - - if ((ssdb->response_code != 0x72) && (ssdb->response_code != 0x73)) { - OSD_ERR("Unrecognized scsi sense: rcode=%x length=%d\n", - ssdb->response_code, sense_len); - goto analyze; - } - - osi->key = ssdb->sense_key; - osi->additional_code = be16_to_cpu(ssdb->additional_sense_code); - original_sense_len = ssdb->additional_sense_length + 8; - -#if (CONFIG_SCSI_OSD_DPRINT_SENSE == 1) - if (__cur_sense_need_output) - __cur_sense_need_output = (osi->key > scsi_sk_recovered_error); -#endif - OSD_SENSE_PRINT1("Main Sense information key=0x%x length(%d, %d) " - "additional_code=0x%x async_error=%d errors=0x%x\n", - osi->key, original_sense_len, sense_len, - osi->additional_code, or->async_error, - or->req_errors); - - if (original_sense_len < sense_len) - sense_len = original_sense_len; - - cur_descriptor = ssdb->ssd; - sense_len -= sizeof(*ssdb); - while (sense_len > 0) { - struct scsi_sense_descriptor *ssd = cur_descriptor; - int cur_len = ssd->additional_length + 2; - - sense_len -= cur_len; - - if (sense_len < 0) - break; /* sense was truncated */ - - switch (ssd->descriptor_type) { - case scsi_sense_information: - case scsi_sense_command_specific_information: - { - struct scsi_sense_command_specific_data_descriptor - *sscd = cur_descriptor; - - osi->command_info = - get_unaligned_be64(&sscd->information) ; - OSD_SENSE_PRINT2( - "command_specific_information 0x%llx \n", - _LLU(osi->command_info)); - break; - } - case scsi_sense_key_specific: - { - struct scsi_sense_key_specific_data_descriptor - *ssks = cur_descriptor; - - osi->sense_info = get_unaligned_be16(&ssks->value); - OSD_SENSE_PRINT2( - "sense_key_specific_information %u" - "sksv_cd_bpv_bp (0x%x)\n", - osi->sense_info, ssks->sksv_cd_bpv_bp); - break; - } - case osd_sense_object_identification: - { /*FIXME: Keep first not last, Store in array*/ - struct osd_sense_identification_data_descriptor - *osidd = cur_descriptor; - - osi->not_initiated_command_functions = - le32_to_cpu(osidd->not_initiated_functions); - osi->completed_command_functions = - le32_to_cpu(osidd->completed_functions); - osi->obj.partition = be64_to_cpu(osidd->partition_id); - osi->obj.id = be64_to_cpu(osidd->object_id); - OSD_SENSE_PRINT2( - "object_identification pid=0x%llx oid=0x%llx\n", - _LLU(osi->obj.partition), _LLU(osi->obj.id)); - OSD_SENSE_PRINT2( - "not_initiated_bits(%x) " - "completed_command_bits(%x)\n", - osi->not_initiated_command_functions, - osi->completed_command_functions); - break; - } - case osd_sense_response_integrity_check: - { - struct osd_sense_response_integrity_check_descriptor - *d = cur_descriptor; - /* 2nibbles+space+ASCII */ - char dump[sizeof(d->integrity_check_value) * 4 + 2]; - - hex_dump_to_buffer(d->integrity_check_value, - sizeof(d->integrity_check_value), - 32, 1, dump, sizeof(dump), true); - OSD_SENSE_PRINT2("response_integrity [%s]\n", dump); - } - case osd_sense_attribute_identification: - { - struct osd_sense_attributes_data_descriptor - *osadd = cur_descriptor; - unsigned len = min(cur_len, sense_len); - struct osd_sense_attr *pattr = osadd->sense_attrs; - - while (len >= sizeof(*pattr)) { - u32 attr_page = be32_to_cpu(pattr->attr_page); - u32 attr_id = be32_to_cpu(pattr->attr_id); - - if (!osi->attr.attr_page) { - osi->attr.attr_page = attr_page; - osi->attr.attr_id = attr_id; - } - - if (bad_attr_list && max_attr) { - bad_attr_list->attr_page = attr_page; - bad_attr_list->attr_id = attr_id; - bad_attr_list++; - max_attr--; - } - - len -= sizeof(*pattr); - OSD_SENSE_PRINT2( - "osd_sense_attribute_identification" - "attr_page=0x%x attr_id=0x%x\n", - attr_page, attr_id); - } - } - /*These are not legal for OSD*/ - case scsi_sense_field_replaceable_unit: - OSD_SENSE_PRINT2("scsi_sense_field_replaceable_unit\n"); - break; - case scsi_sense_stream_commands: - OSD_SENSE_PRINT2("scsi_sense_stream_commands\n"); - break; - case scsi_sense_block_commands: - OSD_SENSE_PRINT2("scsi_sense_block_commands\n"); - break; - case scsi_sense_ata_return: - OSD_SENSE_PRINT2("scsi_sense_ata_return\n"); - break; - default: - if (ssd->descriptor_type <= scsi_sense_Reserved_last) - OSD_SENSE_PRINT2( - "scsi_sense Reserved descriptor (0x%x)", - ssd->descriptor_type); - else - OSD_SENSE_PRINT2( - "scsi_sense Vendor descriptor (0x%x)", - ssd->descriptor_type); - } - - cur_descriptor += cur_len; - } - -analyze: - if (!osi->key) { - /* scsi sense is Empty, the request was never issued to target - * linux return code might tell us what happened. - */ - if (or->async_error == BLK_STS_RESOURCE) - osi->osd_err_pri = OSD_ERR_PRI_RESOURCE; - else - osi->osd_err_pri = OSD_ERR_PRI_UNREACHABLE; - ret = or->async_error; - } else if (osi->key <= scsi_sk_recovered_error) { - osi->osd_err_pri = 0; - ret = 0; - } else if (osi->additional_code == scsi_invalid_field_in_cdb) { - if (osi->cdb_field_offset == OSD_CFO_STARTING_BYTE) { - osi->osd_err_pri = OSD_ERR_PRI_CLEAR_PAGES; - ret = -EFAULT; /* caller should recover from this */ - } else if (osi->cdb_field_offset == OSD_CFO_OBJECT_ID) { - osi->osd_err_pri = OSD_ERR_PRI_NOT_FOUND; - ret = -ENOENT; - } else if (osi->cdb_field_offset == OSD_CFO_PERMISSIONS) { - osi->osd_err_pri = OSD_ERR_PRI_NO_ACCESS; - ret = -EACCES; - } else { - osi->osd_err_pri = OSD_ERR_PRI_BAD_CRED; - ret = -EINVAL; - } - } else if (osi->additional_code == osd_quota_error) { - osi->osd_err_pri = OSD_ERR_PRI_NO_SPACE; - ret = -ENOSPC; - } else if (_is_osd_security_code(osi->additional_code)) { - osi->osd_err_pri = OSD_ERR_PRI_BAD_CRED; - ret = -EINVAL; - } else { - osi->osd_err_pri = OSD_ERR_PRI_EIO; - ret = -EIO; - } - - if (!or->out.residual) - or->out.residual = or->out.total_bytes; - if (!or->in.residual) - or->in.residual = or->in.total_bytes; - - return ret; -} -EXPORT_SYMBOL(osd_req_decode_sense_full); - -/* - * Implementation of osd_sec.h API - * TODO: Move to a separate osd_sec.c file at a later stage. - */ - -enum { OSD_SEC_CAP_V1_ALL_CAPS = - OSD_SEC_CAP_APPEND | OSD_SEC_CAP_OBJ_MGMT | OSD_SEC_CAP_REMOVE | - OSD_SEC_CAP_CREATE | OSD_SEC_CAP_SET_ATTR | OSD_SEC_CAP_GET_ATTR | - OSD_SEC_CAP_WRITE | OSD_SEC_CAP_READ | OSD_SEC_CAP_POL_SEC | - OSD_SEC_CAP_GLOBAL | OSD_SEC_CAP_DEV_MGMT -}; - -enum { OSD_SEC_CAP_V2_ALL_CAPS = - OSD_SEC_CAP_V1_ALL_CAPS | OSD_SEC_CAP_QUERY | OSD_SEC_CAP_M_OBJECT -}; - -void osd_sec_init_nosec_doall_caps(void *caps, - const struct osd_obj_id *obj, bool is_collection, const bool is_v1) -{ - struct osd_capability *cap = caps; - u8 type; - u8 descriptor_type; - - if (likely(obj->id)) { - if (unlikely(is_collection)) { - type = OSD_SEC_OBJ_COLLECTION; - descriptor_type = is_v1 ? OSD_SEC_OBJ_DESC_OBJ : - OSD_SEC_OBJ_DESC_COL; - } else { - type = OSD_SEC_OBJ_USER; - descriptor_type = OSD_SEC_OBJ_DESC_OBJ; - } - WARN_ON(!obj->partition); - } else { - type = obj->partition ? OSD_SEC_OBJ_PARTITION : - OSD_SEC_OBJ_ROOT; - descriptor_type = OSD_SEC_OBJ_DESC_PAR; - } - - memset(cap, 0, sizeof(*cap)); - - cap->h.format = OSD_SEC_CAP_FORMAT_VER1; - cap->h.integrity_algorithm__key_version = 0; /* MAKE_BYTE(0, 0); */ - cap->h.security_method = OSD_SEC_NOSEC; -/* cap->expiration_time; - cap->AUDIT[30-10]; - cap->discriminator[42-30]; - cap->object_created_time; */ - cap->h.object_type = type; - osd_sec_set_caps(&cap->h, OSD_SEC_CAP_V1_ALL_CAPS); - cap->h.object_descriptor_type = descriptor_type; - cap->od.obj_desc.policy_access_tag = 0; - cap->od.obj_desc.allowed_partition_id = cpu_to_be64(obj->partition); - cap->od.obj_desc.allowed_object_id = cpu_to_be64(obj->id); -} -EXPORT_SYMBOL(osd_sec_init_nosec_doall_caps); - -/* FIXME: Extract version from caps pointer. - * Also Pete's target only supports caps from OSDv1 for now - */ -void osd_set_caps(struct osd_cdb *cdb, const void *caps) -{ - /* NOTE: They start at same address */ - memcpy(&cdb->v1.caps, caps, OSDv1_CAP_LEN); -} - -bool osd_is_sec_alldata(struct osd_security_parameters *sec_parms __unused) -{ - return false; -} - -void osd_sec_sign_cdb(struct osd_cdb *ocdb __unused, const u8 *cap_key __unused) -{ -} - -void osd_sec_sign_data(void *data_integ __unused, - struct bio *bio __unused, const u8 *cap_key __unused) -{ -} - -/* - * Declared in osd_protocol.h - * 4.12.5 Data-In and Data-Out buffer offsets - * byte offset = mantissa * (2^(exponent+8)) - * Returns the smallest allowed encoded offset that contains given @offset - * The actual encoded offset returned is @offset + *@padding. - */ -osd_cdb_offset __osd_encode_offset( - u64 offset, unsigned *padding, int min_shift, int max_shift) -{ - u64 try_offset = -1, mod, align; - osd_cdb_offset be32_offset; - int shift; - - *padding = 0; - if (!offset) - return 0; - - for (shift = min_shift; shift < max_shift; ++shift) { - try_offset = offset >> shift; - if (try_offset < (1 << OSD_OFFSET_MAX_BITS)) - break; - } - - BUG_ON(shift == max_shift); - - align = 1 << shift; - mod = offset & (align - 1); - if (mod) { - *padding = align - mod; - try_offset += 1; - } - - try_offset |= ((shift - 8) & 0xf) << 28; - be32_offset = cpu_to_be32((u32)try_offset); - - OSD_DEBUG("offset=%llu mantissa=%llu exp=%d encoded=%x pad=%d\n", - _LLU(offset), _LLU(try_offset & 0x0FFFFFFF), shift, - be32_offset, *padding); - return be32_offset; -} diff --git a/drivers/scsi/osd/osd_uld.c b/drivers/scsi/osd/osd_uld.c deleted file mode 100644 index eaf36ccf58db..000000000000 --- a/drivers/scsi/osd/osd_uld.c +++ /dev/null @@ -1,571 +0,0 @@ -/* - * osd_uld.c - OSD Upper Layer Driver - * - * A Linux driver module that registers as a SCSI ULD and probes - * for OSD type SCSI devices. - * It's main function is to export osd devices to in-kernel users like - * osdfs and pNFS-objects-LD. It also provides one ioctl for running - * in Kernel tests. - * - * Copyright (C) 2008 Panasas Inc. All rights reserved. - * - * Authors: - * Boaz Harrosh - * Benny Halevy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the Panasas company nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include -#include - -#include "osd_debug.h" - -#ifndef TYPE_OSD -# define TYPE_OSD 0x11 -#endif - -#ifndef SCSI_OSD_MAJOR -# define SCSI_OSD_MAJOR 260 -#endif -#define SCSI_OSD_MAX_MINOR MINORMASK - -static const char osd_name[] = "osd"; -static const char *osd_version_string = "open-osd 0.2.1"; - -MODULE_AUTHOR("Boaz Harrosh "); -MODULE_DESCRIPTION("open-osd Upper-Layer-Driver osd.ko"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_CHARDEV_MAJOR(SCSI_OSD_MAJOR); -MODULE_ALIAS_SCSI_DEVICE(TYPE_OSD); - -struct osd_uld_device { - int minor; - struct device class_dev; - struct cdev cdev; - struct osd_dev od; - struct osd_dev_info odi; - struct gendisk *disk; -}; - -struct osd_dev_handle { - struct osd_dev od; - struct file *file; - struct osd_uld_device *oud; -} ; - -static DEFINE_IDA(osd_minor_ida); - -/* - * scsi sysfs attribute operations - */ -static ssize_t osdname_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct osd_uld_device *ould = container_of(dev, struct osd_uld_device, - class_dev); - return sprintf(buf, "%s\n", ould->odi.osdname); -} -static DEVICE_ATTR_RO(osdname); - -static ssize_t systemid_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct osd_uld_device *ould = container_of(dev, struct osd_uld_device, - class_dev); - - memcpy(buf, ould->odi.systemid, ould->odi.systemid_len); - return ould->odi.systemid_len; -} -static DEVICE_ATTR_RO(systemid); - -static struct attribute *osd_uld_attrs[] = { - &dev_attr_osdname.attr, - &dev_attr_systemid.attr, - NULL, -}; -ATTRIBUTE_GROUPS(osd_uld); - -static struct class osd_uld_class = { - .owner = THIS_MODULE, - .name = "scsi_osd", - .dev_groups = osd_uld_groups, -}; - -/* - * Char Device operations - */ - -static int osd_uld_open(struct inode *inode, struct file *file) -{ - struct osd_uld_device *oud = container_of(inode->i_cdev, - struct osd_uld_device, cdev); - - get_device(&oud->class_dev); - /* cache osd_uld_device on file handle */ - file->private_data = oud; - OSD_DEBUG("osd_uld_open %p\n", oud); - return 0; -} - -static int osd_uld_release(struct inode *inode, struct file *file) -{ - struct osd_uld_device *oud = file->private_data; - - OSD_DEBUG("osd_uld_release %p\n", file->private_data); - file->private_data = NULL; - put_device(&oud->class_dev); - return 0; -} - -/* FIXME: Only one vector for now */ -unsigned g_test_ioctl; -do_test_fn *g_do_test; - -int osduld_register_test(unsigned ioctl, do_test_fn *do_test) -{ - if (g_test_ioctl) - return -EINVAL; - - g_test_ioctl = ioctl; - g_do_test = do_test; - return 0; -} -EXPORT_SYMBOL(osduld_register_test); - -void osduld_unregister_test(unsigned ioctl) -{ - if (ioctl == g_test_ioctl) { - g_test_ioctl = 0; - g_do_test = NULL; - } -} -EXPORT_SYMBOL(osduld_unregister_test); - -static do_test_fn *_find_ioctl(unsigned cmd) -{ - if (g_test_ioctl == cmd) - return g_do_test; - else - return NULL; -} - -static long osd_uld_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - struct osd_uld_device *oud = file->private_data; - int ret; - do_test_fn *do_test; - - do_test = _find_ioctl(cmd); - if (do_test) - ret = do_test(&oud->od, cmd, arg); - else { - OSD_ERR("Unknown ioctl %d: osd_uld_device=%p\n", cmd, oud); - ret = -ENOIOCTLCMD; - } - return ret; -} - -static const struct file_operations osd_fops = { - .owner = THIS_MODULE, - .open = osd_uld_open, - .release = osd_uld_release, - .unlocked_ioctl = osd_uld_ioctl, - .llseek = noop_llseek, -}; - -struct osd_dev *osduld_path_lookup(const char *name) -{ - struct osd_uld_device *oud; - struct osd_dev_handle *odh; - struct file *file; - int error; - - if (!name || !*name) { - OSD_ERR("Mount with !path || !*path\n"); - return ERR_PTR(-EINVAL); - } - - odh = kzalloc(sizeof(*odh), GFP_KERNEL); - if (unlikely(!odh)) - return ERR_PTR(-ENOMEM); - - file = filp_open(name, O_RDWR, 0); - if (IS_ERR(file)) { - error = PTR_ERR(file); - goto free_od; - } - - if (file->f_op != &osd_fops){ - error = -EINVAL; - goto close_file; - } - - oud = file->private_data; - - odh->od = oud->od; - odh->file = file; - odh->oud = oud; - - return &odh->od; - -close_file: - fput(file); -free_od: - kfree(odh); - return ERR_PTR(error); -} -EXPORT_SYMBOL(osduld_path_lookup); - -static inline bool _the_same_or_null(const u8 *a1, unsigned a1_len, - const u8 *a2, unsigned a2_len) -{ - if (!a2_len) /* User string is Empty means don't care */ - return true; - - if (a1_len != a2_len) - return false; - - return 0 == memcmp(a1, a2, a1_len); -} - -static int _match_odi(struct device *dev, const void *find_data) -{ - struct osd_uld_device *oud = container_of(dev, struct osd_uld_device, - class_dev); - const struct osd_dev_info *odi = find_data; - - if (_the_same_or_null(oud->odi.systemid, oud->odi.systemid_len, - odi->systemid, odi->systemid_len) && - _the_same_or_null(oud->odi.osdname, oud->odi.osdname_len, - odi->osdname, odi->osdname_len)) { - OSD_DEBUG("found device sysid_len=%d osdname=%d\n", - odi->systemid_len, odi->osdname_len); - return 1; - } else { - return 0; - } -} - -/* osduld_info_lookup - Loop through all devices, return the requested osd_dev. - * - * if @odi->systemid_len and/or @odi->osdname_len are zero, they act as a don't - * care. .e.g if they're both zero /dev/osd0 is returned. - */ -struct osd_dev *osduld_info_lookup(const struct osd_dev_info *odi) -{ - struct device *dev = class_find_device(&osd_uld_class, NULL, odi, _match_odi); - if (likely(dev)) { - struct osd_dev_handle *odh = kzalloc(sizeof(*odh), GFP_KERNEL); - struct osd_uld_device *oud = container_of(dev, - struct osd_uld_device, class_dev); - - if (unlikely(!odh)) { - put_device(dev); - return ERR_PTR(-ENOMEM); - } - - odh->od = oud->od; - odh->oud = oud; - - return &odh->od; - } - - return ERR_PTR(-ENODEV); -} -EXPORT_SYMBOL(osduld_info_lookup); - -void osduld_put_device(struct osd_dev *od) -{ - if (od && !IS_ERR(od)) { - struct osd_dev_handle *odh = - container_of(od, struct osd_dev_handle, od); - struct osd_uld_device *oud = odh->oud; - - BUG_ON(od->scsi_device != oud->od.scsi_device); - - /* If scsi has released the device (logout), and exofs has last - * reference on oud it will be freed by above osd_uld_release - * within fput below. But this will oops in cdev_release which - * is called after the fops->release. A get_/put_ pair makes - * sure we have a cdev for the duration of fput - */ - if (odh->file) { - get_device(&oud->class_dev); - fput(odh->file); - } - put_device(&oud->class_dev); - kfree(odh); - } -} -EXPORT_SYMBOL(osduld_put_device); - -const struct osd_dev_info *osduld_device_info(struct osd_dev *od) -{ - struct osd_dev_handle *odh = - container_of(od, struct osd_dev_handle, od); - return &odh->oud->odi; -} -EXPORT_SYMBOL(osduld_device_info); - -bool osduld_device_same(struct osd_dev *od, const struct osd_dev_info *odi) -{ - struct osd_dev_handle *odh = - container_of(od, struct osd_dev_handle, od); - struct osd_uld_device *oud = odh->oud; - - return (oud->odi.systemid_len == odi->systemid_len) && - _the_same_or_null(oud->odi.systemid, oud->odi.systemid_len, - odi->systemid, odi->systemid_len) && - (oud->odi.osdname_len == odi->osdname_len) && - _the_same_or_null(oud->odi.osdname, oud->odi.osdname_len, - odi->osdname, odi->osdname_len); -} -EXPORT_SYMBOL(osduld_device_same); - -/* - * Scsi Device operations - */ - -static int __detect_osd(struct osd_uld_device *oud) -{ - struct scsi_device *scsi_device = oud->od.scsi_device; - struct scsi_sense_hdr sense_hdr; - char caps[OSD_CAP_LEN]; - int error; - - /* sending a test_unit_ready as first command seems to be needed - * by some targets - */ - OSD_DEBUG("start scsi_test_unit_ready %p %p %p\n", - oud, scsi_device, scsi_device->request_queue); - error = scsi_test_unit_ready(scsi_device, 10*HZ, 5, &sense_hdr); - if (error) - OSD_ERR("warning: scsi_test_unit_ready failed\n"); - - osd_sec_init_nosec_doall_caps(caps, &osd_root_object, false, true); - if (osd_auto_detect_ver(&oud->od, caps, &oud->odi)) - return -ENODEV; - - return 0; -} - -static void __remove(struct device *dev) -{ - struct osd_uld_device *oud = container_of(dev, struct osd_uld_device, - class_dev); - struct scsi_device *scsi_device = oud->od.scsi_device; - - kfree(oud->odi.osdname); - - osd_dev_fini(&oud->od); - scsi_device_put(scsi_device); - - OSD_INFO("osd_remove %s\n", - oud->disk ? oud->disk->disk_name : NULL); - - if (oud->disk) - put_disk(oud->disk); - - kfree(oud); -} - -static int osd_probe(struct device *dev) -{ - struct scsi_device *scsi_device = to_scsi_device(dev); - struct gendisk *disk; - struct osd_uld_device *oud; - int minor; - int error; - - if (scsi_device->type != TYPE_OSD) - return -ENODEV; - - minor = ida_alloc_max(&osd_minor_ida, SCSI_OSD_MAX_MINOR, GFP_KERNEL); - if (minor == -ENOSPC) - return -EBUSY; - if (minor < 0) - return -ENODEV; - - error = -ENOMEM; - oud = kzalloc(sizeof(*oud), GFP_KERNEL); - if (NULL == oud) - goto err_retract_minor; - - /* class device member */ - device_initialize(&oud->class_dev); - dev_set_drvdata(dev, oud); - oud->minor = minor; - oud->class_dev.devt = MKDEV(SCSI_OSD_MAJOR, oud->minor); - oud->class_dev.class = &osd_uld_class; - oud->class_dev.parent = dev; - oud->class_dev.release = __remove; - - /* hold one more reference to the scsi_device that will get released - * in __release, in case a logout is happening while fs is mounted - */ - if (scsi_device_get(scsi_device)) - goto err_retract_minor; - osd_dev_init(&oud->od, scsi_device); - - /* allocate a disk and set it up */ - /* FIXME: do we need this since sg has already done that */ - disk = alloc_disk(1); - if (!disk) { - OSD_ERR("alloc_disk failed\n"); - goto err_free_osd; - } - disk->major = SCSI_OSD_MAJOR; - disk->first_minor = oud->minor; - sprintf(disk->disk_name, "osd%d", oud->minor); - oud->disk = disk; - - /* Detect the OSD Version */ - error = __detect_osd(oud); - if (error) { - OSD_ERR("osd detection failed, non-compatible OSD device\n"); - goto err_free_osd; - } - - /* init the char-device for communication with user-mode */ - cdev_init(&oud->cdev, &osd_fops); - oud->cdev.owner = THIS_MODULE; - - error = dev_set_name(&oud->class_dev, "%s", disk->disk_name); - if (error) { - OSD_ERR("dev_set_name failed => %d\n", error); - goto err_free_osd; - } - - error = cdev_device_add(&oud->cdev, &oud->class_dev); - if (error) { - OSD_ERR("device_register failed => %d\n", error); - goto err_free_osd; - } - - OSD_INFO("osd_probe %s\n", disk->disk_name); - return 0; - -err_free_osd: - put_device(&oud->class_dev); -err_retract_minor: - ida_free(&osd_minor_ida, minor); - return error; -} - -static int osd_remove(struct device *dev) -{ - struct scsi_device *scsi_device = to_scsi_device(dev); - struct osd_uld_device *oud = dev_get_drvdata(dev); - - if (oud->od.scsi_device != scsi_device) { - OSD_ERR("Half cooked osd-device %p, || %p!=%p", - dev, oud->od.scsi_device, scsi_device); - } - - cdev_device_del(&oud->cdev, &oud->class_dev); - ida_free(&osd_minor_ida, oud->minor); - put_device(&oud->class_dev); - - return 0; -} - -/* - * Global driver and scsi registration - */ - -static struct scsi_driver osd_driver = { - .gendrv = { - .name = osd_name, - .owner = THIS_MODULE, - .probe = osd_probe, - .remove = osd_remove, - } -}; - -static int __init osd_uld_init(void) -{ - int err; - - err = class_register(&osd_uld_class); - if (err) { - OSD_ERR("Unable to register sysfs class => %d\n", err); - return err; - } - - err = register_chrdev_region(MKDEV(SCSI_OSD_MAJOR, 0), - SCSI_OSD_MAX_MINOR, osd_name); - if (err) { - OSD_ERR("Unable to register major %d for osd ULD => %d\n", - SCSI_OSD_MAJOR, err); - goto err_out; - } - - err = scsi_register_driver(&osd_driver.gendrv); - if (err) { - OSD_ERR("scsi_register_driver failed => %d\n", err); - goto err_out_chrdev; - } - - OSD_INFO("LOADED %s\n", osd_version_string); - return 0; - -err_out_chrdev: - unregister_chrdev_region(MKDEV(SCSI_OSD_MAJOR, 0), SCSI_OSD_MAX_MINOR); -err_out: - class_unregister(&osd_uld_class); - return err; -} - -static void __exit osd_uld_exit(void) -{ - scsi_unregister_driver(&osd_driver.gendrv); - unregister_chrdev_region(MKDEV(SCSI_OSD_MAJOR, 0), SCSI_OSD_MAX_MINOR); - class_unregister(&osd_uld_class); - OSD_INFO("UNLOADED %s\n", osd_version_string); -} - -module_init(osd_uld_init); -module_exit(osd_uld_exit); diff --git a/include/scsi/osd_initiator.h b/include/scsi/osd_initiator.h deleted file mode 100644 index 86a569d008b2..000000000000 --- a/include/scsi/osd_initiator.h +++ /dev/null @@ -1,511 +0,0 @@ -/* - * osd_initiator.h - OSD initiator API definition - * - * Copyright (C) 2008 Panasas Inc. All rights reserved. - * - * Authors: - * Boaz Harrosh - * Benny Halevy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * - */ -#ifndef __OSD_INITIATOR_H__ -#define __OSD_INITIATOR_H__ - -#include -#include - -#include -#include - -/* Note: "NI" in comments below means "Not Implemented yet" */ - -/* Configure of code: - * #undef if you *don't* want OSD v1 support in runtime. - * If #defined the initiator will dynamically configure to encode OSD v1 - * CDB's if the target is detected to be OSD v1 only. - * OSD v2 only commands, options, and attributes will be ignored if target - * is v1 only. - * If #defined will result in bigger/slower code (OK Slower maybe not) - * Q: Should this be CONFIG_SCSI_OSD_VER1_SUPPORT and set from Kconfig? - */ -#define OSD_VER1_SUPPORT y - -enum osd_std_version { - OSD_VER_NONE = 0, - OSD_VER1 = 1, - OSD_VER2 = 2, -}; - -/* - * Object-based Storage Device. - * This object represents an OSD device. - * It is not a full linux device in any way. It is only - * a place to hang resources associated with a Linux - * request Q and some default properties. - */ -struct osd_dev { - struct scsi_device *scsi_device; - unsigned def_timeout; - -#ifdef OSD_VER1_SUPPORT - enum osd_std_version version; -#endif -}; - -/* Unique Identification of an OSD device */ -struct osd_dev_info { - unsigned systemid_len; - u8 systemid[OSD_SYSTEMID_LEN]; - unsigned osdname_len; - u8 *osdname; -}; - -/* Retrieve/return osd_dev(s) for use by Kernel clients - * Use IS_ERR/ERR_PTR on returned "osd_dev *". - */ -struct osd_dev *osduld_path_lookup(const char *dev_name); -struct osd_dev *osduld_info_lookup(const struct osd_dev_info *odi); -void osduld_put_device(struct osd_dev *od); - -const struct osd_dev_info *osduld_device_info(struct osd_dev *od); -bool osduld_device_same(struct osd_dev *od, const struct osd_dev_info *odi); - -/* Add/remove test ioctls from external modules */ -typedef int (do_test_fn)(struct osd_dev *od, unsigned cmd, unsigned long arg); -int osduld_register_test(unsigned ioctl, do_test_fn *do_test); -void osduld_unregister_test(unsigned ioctl); - -/* These are called by uld at probe time */ -void osd_dev_init(struct osd_dev *od, struct scsi_device *scsi_device); -void osd_dev_fini(struct osd_dev *od); - -/** - * osd_auto_detect_ver - Detect the OSD version, return Unique Identification - * - * @od: OSD target lun handle - * @caps: Capabilities authorizing OSD root read attributes access - * @odi: Retrieved information uniquely identifying the osd target lun - * Note: odi->osdname must be kfreed by caller. - * - * Auto detects the OSD version of the OSD target and sets the @od - * accordingly. Meanwhile also returns the "system id" and "osd name" root - * attributes which uniquely identify the OSD target. This member is usually - * called by the ULD. ULD users should call osduld_device_info(). - * This rutine allocates osd requests and memory at GFP_KERNEL level and might - * sleep. - */ -int osd_auto_detect_ver(struct osd_dev *od, - void *caps, struct osd_dev_info *odi); - -static inline struct request_queue *osd_request_queue(struct osd_dev *od) -{ - return od->scsi_device->request_queue; -} - -/* we might want to use function vector in the future */ -static inline void osd_dev_set_ver(struct osd_dev *od, enum osd_std_version v) -{ -#ifdef OSD_VER1_SUPPORT - od->version = v; -#endif -} - -static inline bool osd_dev_is_ver1(struct osd_dev *od) -{ -#ifdef OSD_VER1_SUPPORT - return od->version == OSD_VER1; -#else - return false; -#endif -} - -struct osd_request; -typedef void (osd_req_done_fn)(struct osd_request *or, void *private); - -struct osd_request { - struct osd_cdb cdb; - struct osd_data_out_integrity_info out_data_integ; - struct osd_data_in_integrity_info in_data_integ; - - struct osd_dev *osd_dev; - struct request *request; - - struct _osd_req_data_segment { - void *buff; - unsigned alloc_size; /* 0 here means: don't call kfree */ - unsigned total_bytes; - } cdb_cont, set_attr, enc_get_attr, get_attr; - - struct _osd_io_info { - struct bio *bio; - u64 total_bytes; - u64 residual; - struct request *req; - struct _osd_req_data_segment *last_seg; - u8 *pad_buff; - } out, in; - - unsigned timeout; - unsigned retries; - unsigned sense_len; - u8 sense[OSD_MAX_SENSE_LEN]; - enum osd_attributes_mode attributes_mode; - - osd_req_done_fn *async_done; - void *async_private; - blk_status_t async_error; - int req_errors; -}; - -static inline bool osd_req_is_ver1(struct osd_request *or) -{ - return osd_dev_is_ver1(or->osd_dev); -} - -/* - * How to use the osd library: - * - * osd_start_request - * Allocates a request. - * - * osd_req_* - * Call one of, to encode the desired operation. - * - * osd_add_{get,set}_attr - * Optionally add attributes to the CDB, list or page mode. - * - * osd_finalize_request - * Computes final data out/in offsets and signs the request, - * making it ready for execution. - * - * osd_execute_request - * May be called to execute it through the block layer. Other wise submit - * the associated block request in some other way. - * - * After execution: - * osd_req_decode_sense - * Decodes sense information to verify execution results. - * - * osd_req_decode_get_attr - * Retrieve osd_add_get_attr_list() values if used. - * - * osd_end_request - * Must be called to deallocate the request. - */ - -/** - * osd_start_request - Allocate and initialize an osd_request - * - * @osd_dev: OSD device that holds the scsi-device and default values - * that the request is associated with. - * - * Allocate osd_request and initialize all members to the - * default/initial state. - */ -struct osd_request *osd_start_request(struct osd_dev *od); - -enum osd_req_options { - OSD_REQ_FUA = 0x08, /* Force Unit Access */ - OSD_REQ_DPO = 0x10, /* Disable Page Out */ - - OSD_REQ_BYPASS_TIMESTAMPS = 0x80, -}; - -/** - * osd_finalize_request - Sign request and prepare request for execution - * - * @or: osd_request to prepare - * @options: combination of osd_req_options bit flags or 0. - * @cap: A Pointer to an OSD_CAP_LEN bytes buffer that is received from - * The security manager as capabilities for this cdb. - * @cap_key: The cryptographic key used to sign the cdb/data. Can be null - * if NOSEC is used. - * - * The actual request and bios are only allocated here, so are the get_attr - * buffers that will receive the returned attributes. Copy's @cap to cdb. - * Sign the cdb/data with @cap_key. - */ -int osd_finalize_request(struct osd_request *or, - u8 options, const void *cap, const u8 *cap_key); - -/** - * osd_execute_request - Execute the request synchronously through block-layer - * - * @or: osd_request to Executed - * - * Calls blk_execute_rq to q the command and waits for completion. - */ -int osd_execute_request(struct osd_request *or); - -/** - * osd_execute_request_async - Execute the request without waitting. - * - * @or: - osd_request to Executed - * @done: (Optional) - Called at end of execution - * @private: - Will be passed to @done function - * - * Calls blk_execute_rq_nowait to queue the command. When execution is done - * optionally calls @done with @private as parameter. @or->async_error will - * have the return code - */ -int osd_execute_request_async(struct osd_request *or, - osd_req_done_fn *done, void *private); - -/** - * osd_req_decode_sense_full - Decode sense information after execution. - * - * @or: - osd_request to examine - * @osi - Receives a more detailed error report information (optional). - * @silent - Do not print to dmsg (Even if enabled) - * @bad_obj_list - Some commands act on multiple objects. Failed objects will - * be received here (optional) - * @max_obj - Size of @bad_obj_list. - * @bad_attr_list - List of failing attributes (optional) - * @max_attr - Size of @bad_attr_list. - * - * After execution, osd_request results are analyzed using this function. The - * return code is the final disposition on the error. So it is possible that a - * CHECK_CONDITION was returned from target but this will return NO_ERROR, for - * example on recovered errors. All parameters are optional if caller does - * not need any returned information. - * Note: This function will also dump the error to dmsg according to settings - * of the SCSI_OSD_DPRINT_SENSE Kconfig value. Set @silent if you know the - * command would routinely fail, to not spam the dmsg file. - */ - -/** - * osd_err_priority - osd categorized return codes in ascending severity. - * - * The categories are borrowed from the pnfs_osd_errno enum. - * See comments for translated Linux codes returned by osd_req_decode_sense. - */ -enum osd_err_priority { - OSD_ERR_PRI_NO_ERROR = 0, - /* Recoverable, caller should clear_highpage() all pages */ - OSD_ERR_PRI_CLEAR_PAGES = 1, /* -EFAULT */ - OSD_ERR_PRI_RESOURCE = 2, /* -ENOMEM */ - OSD_ERR_PRI_BAD_CRED = 3, /* -EINVAL */ - OSD_ERR_PRI_NO_ACCESS = 4, /* -EACCES */ - OSD_ERR_PRI_UNREACHABLE = 5, /* any other */ - OSD_ERR_PRI_NOT_FOUND = 6, /* -ENOENT */ - OSD_ERR_PRI_NO_SPACE = 7, /* -ENOSPC */ - OSD_ERR_PRI_EIO = 8, /* -EIO */ -}; - -struct osd_sense_info { - enum osd_err_priority osd_err_pri; - - int key; /* one of enum scsi_sense_keys */ - int additional_code ; /* enum osd_additional_sense_codes */ - union { /* Sense specific information */ - u16 sense_info; - u16 cdb_field_offset; /* scsi_invalid_field_in_cdb */ - }; - union { /* Command specific information */ - u64 command_info; - }; - - u32 not_initiated_command_functions; /* osd_command_functions_bits */ - u32 completed_command_functions; /* osd_command_functions_bits */ - struct osd_obj_id obj; - struct osd_attr attr; -}; - -int osd_req_decode_sense_full(struct osd_request *or, - struct osd_sense_info *osi, bool silent, - struct osd_obj_id *bad_obj_list, int max_obj, - struct osd_attr *bad_attr_list, int max_attr); - -static inline int osd_req_decode_sense(struct osd_request *or, - struct osd_sense_info *osi) -{ - return osd_req_decode_sense_full(or, osi, false, NULL, 0, NULL, 0); -} - -/** - * osd_end_request - return osd_request to free store - * - * @or: osd_request to free - * - * Deallocate all osd_request resources (struct req's, BIOs, buffers, etc.) - */ -void osd_end_request(struct osd_request *or); - -/* - * CDB Encoding - * - * Note: call only one of the following methods. - */ - -/* - * Device commands - */ -void osd_req_set_master_seed_xchg(struct osd_request *or, ...);/* NI */ -void osd_req_set_master_key(struct osd_request *or, ...);/* NI */ - -void osd_req_format(struct osd_request *or, u64 tot_capacity); - -/* list all partitions - * @list header must be initialized to zero on first run. - * - * Call osd_is_obj_list_done() to find if we got the complete list. - */ -int osd_req_list_dev_partitions(struct osd_request *or, - osd_id initial_id, struct osd_obj_id_list *list, unsigned nelem); - -void osd_req_flush_obsd(struct osd_request *or, - enum osd_options_flush_scope_values); - -void osd_req_perform_scsi_command(struct osd_request *or, - const u8 *cdb, ...);/* NI */ -void osd_req_task_management(struct osd_request *or, ...);/* NI */ - -/* - * Partition commands - */ -void osd_req_create_partition(struct osd_request *or, osd_id partition); -void osd_req_remove_partition(struct osd_request *or, osd_id partition); - -void osd_req_set_partition_key(struct osd_request *or, - osd_id partition, u8 new_key_id[OSD_CRYPTO_KEYID_SIZE], - u8 seed[OSD_CRYPTO_SEED_SIZE]);/* NI */ - -/* list all collections in the partition - * @list header must be init to zero on first run. - * - * Call osd_is_obj_list_done() to find if we got the complete list. - */ -int osd_req_list_partition_collections(struct osd_request *or, - osd_id partition, osd_id initial_id, struct osd_obj_id_list *list, - unsigned nelem); - -/* list all objects in the partition - * @list header must be init to zero on first run. - * - * Call osd_is_obj_list_done() to find if we got the complete list. - */ -int osd_req_list_partition_objects(struct osd_request *or, - osd_id partition, osd_id initial_id, struct osd_obj_id_list *list, - unsigned nelem); - -void osd_req_flush_partition(struct osd_request *or, - osd_id partition, enum osd_options_flush_scope_values); - -/* - * Collection commands - */ -void osd_req_create_collection(struct osd_request *or, - const struct osd_obj_id *);/* NI */ -void osd_req_remove_collection(struct osd_request *or, - const struct osd_obj_id *);/* NI */ - -/* list all objects in the collection */ -int osd_req_list_collection_objects(struct osd_request *or, - const struct osd_obj_id *, osd_id initial_id, - struct osd_obj_id_list *list, unsigned nelem); - -/* V2 only filtered list of objects in the collection */ -void osd_req_query(struct osd_request *or, ...);/* NI */ - -void osd_req_flush_collection(struct osd_request *or, - const struct osd_obj_id *, enum osd_options_flush_scope_values); - -void osd_req_get_member_attrs(struct osd_request *or, ...);/* V2-only NI */ -void osd_req_set_member_attrs(struct osd_request *or, ...);/* V2-only NI */ - -/* - * Object commands - */ -void osd_req_create_object(struct osd_request *or, struct osd_obj_id *); -void osd_req_remove_object(struct osd_request *or, struct osd_obj_id *); - -void osd_req_write(struct osd_request *or, - const struct osd_obj_id *obj, u64 offset, struct bio *bio, u64 len); -int osd_req_write_kern(struct osd_request *or, - const struct osd_obj_id *obj, u64 offset, void *buff, u64 len); -void osd_req_append(struct osd_request *or, - const struct osd_obj_id *, struct bio *data_out);/* NI */ -void osd_req_create_write(struct osd_request *or, - const struct osd_obj_id *, struct bio *data_out, u64 offset);/* NI */ -void osd_req_clear(struct osd_request *or, - const struct osd_obj_id *, u64 offset, u64 len);/* NI */ -void osd_req_punch(struct osd_request *or, - const struct osd_obj_id *, u64 offset, u64 len);/* V2-only NI */ - -void osd_req_flush_object(struct osd_request *or, - const struct osd_obj_id *, enum osd_options_flush_scope_values, - /*V2*/ u64 offset, /*V2*/ u64 len); - -void osd_req_read(struct osd_request *or, - const struct osd_obj_id *obj, u64 offset, struct bio *bio, u64 len); -int osd_req_read_kern(struct osd_request *or, - const struct osd_obj_id *obj, u64 offset, void *buff, u64 len); - -/* Scatter/Gather write/read commands */ -int osd_req_write_sg(struct osd_request *or, - const struct osd_obj_id *obj, struct bio *bio, - const struct osd_sg_entry *sglist, unsigned numentries); -int osd_req_read_sg(struct osd_request *or, - const struct osd_obj_id *obj, struct bio *bio, - const struct osd_sg_entry *sglist, unsigned numentries); -int osd_req_write_sg_kern(struct osd_request *or, - const struct osd_obj_id *obj, void **buff, - const struct osd_sg_entry *sglist, unsigned numentries); -int osd_req_read_sg_kern(struct osd_request *or, - const struct osd_obj_id *obj, void **buff, - const struct osd_sg_entry *sglist, unsigned numentries); - -/* - * Root/Partition/Collection/Object Attributes commands - */ - -/* get before set */ -void osd_req_get_attributes(struct osd_request *or, const struct osd_obj_id *); - -/* set before get */ -void osd_req_set_attributes(struct osd_request *or, const struct osd_obj_id *); - -/* - * Attributes appended to most commands - */ - -/* Attributes List mode (or V2 CDB) */ - /* - * TODO: In ver2 if at finalize time only one attr was set and no gets, - * then the Attributes CDB mode is used automatically to save IO. - */ - -/* set a list of attributes. */ -int osd_req_add_set_attr_list(struct osd_request *or, - const struct osd_attr *, unsigned nelem); - -/* get a list of attributes */ -int osd_req_add_get_attr_list(struct osd_request *or, - const struct osd_attr *, unsigned nelem); - -/* - * Attributes list decoding - * Must be called after osd_request.request was executed - * It is called in a loop to decode the returned get_attr - * (see osd_add_get_attr) - */ -int osd_req_decode_get_attr_list(struct osd_request *or, - struct osd_attr *, int *nelem, void **iterator); - -/* Attributes Page mode */ - -/* - * Read an attribute page and optionally set one attribute - * - * Retrieves the attribute page directly to a user buffer. - * @attr_page_data shall stay valid until end of execution. - * See osd_attributes.h for common page structures - */ -int osd_req_add_get_attr_page(struct osd_request *or, - u32 page_id, void *attr_page_data, unsigned max_page_len, - const struct osd_attr *set_one); - -#endif /* __OSD_LIB_H__ */ diff --git a/include/scsi/osd_ore.h b/include/scsi/osd_ore.h deleted file mode 100644 index 7a8d2cd30328..000000000000 --- a/include/scsi/osd_ore.h +++ /dev/null @@ -1,201 +0,0 @@ -/* - * Copyright (C) 2011 - * Boaz Harrosh - * - * Public Declarations of the ORE API - * - * This file is part of the ORE (Object Raid Engine) library. - * - * ORE is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. (GPL v2) - * - * ORE is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with the ORE; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __ORE_H__ -#define __ORE_H__ - -#include -#include -#include -#include -#include - -struct ore_comp { - struct osd_obj_id obj; - u8 cred[OSD_CAP_LEN]; -}; - -struct ore_layout { - /* Our way of looking at the data_map */ - enum pnfs_osd_raid_algorithm4 - raid_algorithm; - unsigned stripe_unit; - unsigned mirrors_p1; - - unsigned group_width; - unsigned parity; - u64 group_depth; - unsigned group_count; - - /* Cached often needed calculations filled in by - * ore_verify_layout - */ - unsigned long max_io_length; /* Max length that should be passed to - * ore_get_rw_state - */ -}; - -struct ore_dev { - struct osd_dev *od; -}; - -struct ore_components { - unsigned first_dev; /* First logical device no */ - unsigned numdevs; /* Num of devices in array */ - /* If @single_comp == EC_SINGLE_COMP, @comps points to a single - * component. else there are @numdevs components - */ - enum EC_COMP_USAGE { - EC_SINGLE_COMP = 0, EC_MULTPLE_COMPS = 0xffffffff - } single_comp; - struct ore_comp *comps; - - /* Array of pointers to ore_dev-* . User will usually have these pointed - * too a bigger struct which contain an "ore_dev ored" member and use - * container_of(oc->ods[i], struct foo_dev, ored) to access the bigger - * structure. - */ - struct ore_dev **ods; -}; - -/* ore_comp_dev Recievies a logical device index */ -static inline struct osd_dev *ore_comp_dev( - const struct ore_components *oc, unsigned i) -{ - BUG_ON((i < oc->first_dev) || (oc->first_dev + oc->numdevs <= i)); - return oc->ods[i - oc->first_dev]->od; -} - -static inline void ore_comp_set_dev( - struct ore_components *oc, unsigned i, struct osd_dev *od) -{ - oc->ods[i - oc->first_dev]->od = od; -} - -struct ore_striping_info { - u64 offset; - u64 obj_offset; - u64 length; - u64 first_stripe_start; /* only used in raid writes */ - u64 M; /* for truncate */ - unsigned bytes_in_stripe; - unsigned dev; - unsigned par_dev; - unsigned unit_off; - unsigned cur_pg; - unsigned cur_comp; - unsigned maxdevUnits; -}; - -struct ore_io_state; -typedef void (*ore_io_done_fn)(struct ore_io_state *ios, void *private); -struct _ore_r4w_op { - /* @Priv given here is passed ios->private */ - struct page * (*get_page)(void *priv, u64 page_index, bool *uptodate); - void (*put_page)(void *priv, struct page *page); -}; - -struct ore_io_state { - struct kref kref; - struct ore_striping_info si; - - void *private; - ore_io_done_fn done; - - struct ore_layout *layout; - struct ore_components *oc; - - /* Global read/write IO*/ - loff_t offset; - unsigned long length; - void *kern_buff; - - struct page **pages; - unsigned nr_pages; - unsigned pgbase; - unsigned pages_consumed; - - /* Attributes */ - unsigned in_attr_len; - struct osd_attr *in_attr; - unsigned out_attr_len; - struct osd_attr *out_attr; - - bool reading; - - /* House keeping of Parity pages */ - bool extra_part_alloc; - struct page **parity_pages; - unsigned max_par_pages; - unsigned cur_par_page; - unsigned sgs_per_dev; - struct __stripe_pages_2d *sp2d; - struct ore_io_state *ios_read_4_write; - const struct _ore_r4w_op *r4w; - - /* Variable array of size numdevs */ - unsigned numdevs; - struct ore_per_dev_state { - struct osd_request *or; - struct bio *bio; - loff_t offset; - unsigned length; - unsigned last_sgs_total; - unsigned dev; - struct osd_sg_entry *sglist; - unsigned cur_sg; - } per_dev[]; -}; - -static inline unsigned ore_io_state_size(unsigned numdevs) -{ - return sizeof(struct ore_io_state) + - sizeof(struct ore_per_dev_state) * numdevs; -} - -/* ore.c */ -int ore_verify_layout(unsigned total_comps, struct ore_layout *layout); -void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset, - u64 length, struct ore_striping_info *si); -int ore_get_rw_state(struct ore_layout *layout, struct ore_components *comps, - bool is_reading, u64 offset, u64 length, - struct ore_io_state **ios); -int ore_get_io_state(struct ore_layout *layout, struct ore_components *comps, - struct ore_io_state **ios); -void ore_put_io_state(struct ore_io_state *ios); - -typedef void (*ore_on_dev_error)(struct ore_io_state *ios, struct ore_dev *od, - unsigned dev_index, enum osd_err_priority oep, - u64 dev_offset, u64 dev_len); -int ore_check_io(struct ore_io_state *ios, ore_on_dev_error rep); - -int ore_create(struct ore_io_state *ios); -int ore_remove(struct ore_io_state *ios); -int ore_write(struct ore_io_state *ios); -int ore_read(struct ore_io_state *ios); -int ore_truncate(struct ore_layout *layout, struct ore_components *comps, - u64 size); - -int extract_attr_from_ios(struct ore_io_state *ios, struct osd_attr *attr); - -extern const struct osd_attr g_attr_logical_length; - -#endif -- cgit v1.2.3 From ae3d56d81507c33024ba7c1eae2ef433aa9bc0d5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Jan 2019 09:33:07 +0100 Subject: scsi: remove bidirectional command support No real need for bidi support once the OSD code is gone. Signed-off-by: Christoph Hellwig Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- drivers/scsi/cxgbi/libcxgbi.c | 13 +++--- drivers/scsi/iscsi_tcp.c | 9 +--- drivers/scsi/libiscsi.c | 64 +++------------------------- drivers/scsi/libiscsi_tcp.c | 8 ++-- drivers/scsi/scsi_debug.c | 85 ++++---------------------------------- drivers/scsi/scsi_error.c | 3 -- drivers/scsi/scsi_lib.c | 60 ++------------------------- drivers/scsi/virtio_scsi.c | 14 ++----- drivers/target/loopback/tcm_loop.c | 15 ------- drivers/usb/storage/uas.c | 11 +---- include/scsi/scsi_cmnd.h | 19 +-------- include/scsi/scsi_eh.h | 1 - 12 files changed, 34 insertions(+), 268 deletions(-) (limited to 'include') diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 75f876409fb9..4466ae5c9a74 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -1211,7 +1211,7 @@ scmd_get_params(struct scsi_cmnd *sc, struct scatterlist **sgl, unsigned int *sgcnt, unsigned int *dlen, unsigned int prot) { - struct scsi_data_buffer *sdb = prot ? scsi_prot(sc) : scsi_out(sc); + struct scsi_data_buffer *sdb = prot ? scsi_prot(sc) : &sc->sdb; *sgl = sdb->table.sgl; *sgcnt = sdb->table.nents; @@ -1427,8 +1427,7 @@ static void task_release_itt(struct iscsi_task *task, itt_t hdr_itt) log_debug(1 << CXGBI_DBG_DDP, "cdev 0x%p, task 0x%p, release tag 0x%x.\n", cdev, task, tag); - if (sc && - (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE) && + if (sc && sc->sc_data_direction == DMA_FROM_DEVICE && cxgbi_ppm_is_ddp_tag(ppm, tag)) { struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); struct cxgbi_task_tag_info *ttinfo = &tdata->ttinfo; @@ -1460,9 +1459,7 @@ static int task_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt) u32 tag = 0; int err = -EINVAL; - if (sc && - (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE) - ) { + if (sc && sc->sc_data_direction == DMA_FROM_DEVICE) { struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); struct cxgbi_task_tag_info *ttinfo = &tdata->ttinfo; @@ -1896,7 +1893,7 @@ int cxgbi_conn_alloc_pdu(struct iscsi_task *task, u8 opcode) if (SKB_MAX_HEAD(cdev->skb_tx_rsvd) > (512 * MAX_SKB_FRAGS) && (opcode == ISCSI_OP_SCSI_DATA_OUT || (opcode == ISCSI_OP_SCSI_CMD && - (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_TO_DEVICE)))) + sc->sc_data_direction == DMA_TO_DEVICE))) /* data could goes into skb head */ headroom += min_t(unsigned int, SKB_MAX_HEAD(cdev->skb_tx_rsvd), @@ -1971,7 +1968,7 @@ int cxgbi_conn_init_pdu(struct iscsi_task *task, unsigned int offset, return 0; if (task->sc) { - struct scsi_data_buffer *sdb = scsi_out(task->sc); + struct scsi_data_buffer *sdb = &task->sc->sdb; struct scatterlist *sg = NULL; int err; diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index cae6368ebb98..ed3debce2819 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -518,7 +518,7 @@ static int iscsi_sw_tcp_pdu_init(struct iscsi_task *task, if (!task->sc) iscsi_sw_tcp_send_linear_data_prep(conn, task->data, count); else { - struct scsi_data_buffer *sdb = scsi_out(task->sc); + struct scsi_data_buffer *sdb = &task->sc->sdb; err = iscsi_sw_tcp_send_data_prep(conn, sdb->table.sgl, sdb->table.nents, offset, @@ -952,12 +952,6 @@ static umode_t iscsi_sw_tcp_attr_is_visible(int param_type, int param) return 0; } -static int iscsi_sw_tcp_slave_alloc(struct scsi_device *sdev) -{ - blk_queue_flag_set(QUEUE_FLAG_BIDI, sdev->request_queue); - return 0; -} - static int iscsi_sw_tcp_slave_configure(struct scsi_device *sdev) { struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(sdev->host); @@ -985,7 +979,6 @@ static struct scsi_host_template iscsi_sw_tcp_sht = { .eh_device_reset_handler= iscsi_eh_device_reset, .eh_target_reset_handler = iscsi_eh_recover_target, .dma_boundary = PAGE_SIZE - 1, - .slave_alloc = iscsi_sw_tcp_slave_alloc, .slave_configure = iscsi_sw_tcp_slave_configure, .target_alloc = iscsi_target_alloc, .proc_name = "iscsi_tcp", diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index b8d325ce8754..bca3a8636c27 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -228,32 +228,6 @@ static int iscsi_prep_ecdb_ahs(struct iscsi_task *task) return 0; } -static int iscsi_prep_bidi_ahs(struct iscsi_task *task) -{ - struct scsi_cmnd *sc = task->sc; - struct iscsi_rlength_ahdr *rlen_ahdr; - int rc; - - rlen_ahdr = iscsi_next_hdr(task); - rc = iscsi_add_hdr(task, sizeof(*rlen_ahdr)); - if (rc) - return rc; - - rlen_ahdr->ahslength = - cpu_to_be16(sizeof(rlen_ahdr->read_length) + - sizeof(rlen_ahdr->reserved)); - rlen_ahdr->ahstype = ISCSI_AHSTYPE_RLENGTH; - rlen_ahdr->reserved = 0; - rlen_ahdr->read_length = cpu_to_be32(scsi_in(sc)->length); - - ISCSI_DBG_SESSION(task->conn->session, - "bidi-in rlen_ahdr->read_length(%d) " - "rlen_ahdr->ahslength(%d)\n", - be32_to_cpu(rlen_ahdr->read_length), - be16_to_cpu(rlen_ahdr->ahslength)); - return 0; -} - /** * iscsi_check_tmf_restrictions - check if a task is affected by TMF * @task: iscsi task @@ -392,13 +366,6 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task) memcpy(hdr->cdb, sc->cmnd, cmd_len); task->imm_count = 0; - if (scsi_bidi_cmnd(sc)) { - hdr->flags |= ISCSI_FLAG_CMD_READ; - rc = iscsi_prep_bidi_ahs(task); - if (rc) - return rc; - } - if (scsi_get_prot_op(sc) != SCSI_PROT_NORMAL) task->protected = true; @@ -473,12 +440,10 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task) conn->scsicmd_pdus_cnt++; ISCSI_DBG_SESSION(session, "iscsi prep [%s cid %d sc %p cdb 0x%x " - "itt 0x%x len %d bidi_len %d cmdsn %d win %d]\n", - scsi_bidi_cmnd(sc) ? "bidirectional" : + "itt 0x%x len %d cmdsn %d win %d]\n", sc->sc_data_direction == DMA_TO_DEVICE ? "write" : "read", conn->id, sc, sc->cmnd[0], task->itt, transfer_length, - scsi_bidi_cmnd(sc) ? scsi_in(sc)->length : 0, session->cmdsn, session->max_cmdsn - session->exp_cmdsn + 1); return 0; @@ -647,12 +612,7 @@ static void fail_scsi_task(struct iscsi_task *task, int err) state = ISCSI_TASK_ABRT_TMF; sc->result = err << 16; - if (!scsi_bidi_cmnd(sc)) - scsi_set_resid(sc, scsi_bufflen(sc)); - else { - scsi_out(sc)->resid = scsi_out(sc)->length; - scsi_in(sc)->resid = scsi_in(sc)->length; - } + scsi_set_resid(sc, scsi_bufflen(sc)); /* regular RX path uses back_lock */ spin_lock_bh(&conn->session->back_lock); @@ -907,14 +867,7 @@ invalid_datalen: if (rhdr->flags & (ISCSI_FLAG_CMD_BIDI_UNDERFLOW | ISCSI_FLAG_CMD_BIDI_OVERFLOW)) { - int res_count = be32_to_cpu(rhdr->bi_residual_count); - - if (scsi_bidi_cmnd(sc) && res_count > 0 && - (rhdr->flags & ISCSI_FLAG_CMD_BIDI_OVERFLOW || - res_count <= scsi_in(sc)->length)) - scsi_in(sc)->resid = res_count; - else - sc->result = (DID_BAD_TARGET << 16) | rhdr->cmd_status; + sc->result = (DID_BAD_TARGET << 16) | rhdr->cmd_status; } if (rhdr->flags & (ISCSI_FLAG_CMD_UNDERFLOW | @@ -961,8 +914,8 @@ iscsi_data_in_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr, if (res_count > 0 && (rhdr->flags & ISCSI_FLAG_CMD_OVERFLOW || - res_count <= scsi_in(sc)->length)) - scsi_in(sc)->resid = res_count; + res_count <= sc->sdb.length)) + sc->sdb.resid = res_count; else sc->result = (DID_BAD_TARGET << 16) | rhdr->cmd_status; } @@ -1804,12 +1757,7 @@ fault: spin_unlock_bh(&session->frwd_lock); ISCSI_DBG_SESSION(session, "iscsi: cmd 0x%x is not queued (%d)\n", sc->cmnd[0], reason); - if (!scsi_bidi_cmnd(sc)) - scsi_set_resid(sc, scsi_bufflen(sc)); - else { - scsi_out(sc)->resid = scsi_out(sc)->length; - scsi_in(sc)->resid = scsi_in(sc)->length; - } + scsi_set_resid(sc, scsi_bufflen(sc)); sc->scsi_done(sc); return 0; } diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 8a6b1b3f8277..9923e9e3b884 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -495,7 +495,7 @@ static int iscsi_tcp_data_in(struct iscsi_conn *conn, struct iscsi_task *task) struct iscsi_tcp_task *tcp_task = task->dd_data; struct iscsi_data_rsp *rhdr = (struct iscsi_data_rsp *)tcp_conn->in.hdr; int datasn = be32_to_cpu(rhdr->datasn); - unsigned total_in_length = scsi_in(task->sc)->length; + unsigned total_in_length = task->sc->sdb.length; /* * lib iscsi will update this in the completion handling if there @@ -580,11 +580,11 @@ static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) data_length, session->max_burst); data_offset = be32_to_cpu(rhdr->data_offset); - if (data_offset + data_length > scsi_out(task->sc)->length) { + if (data_offset + data_length > task->sc->sdb.length) { iscsi_conn_printk(KERN_ERR, conn, "invalid R2T with data len %u at offset %u " "and total length %d\n", data_length, - data_offset, scsi_out(task->sc)->length); + data_offset, task->sc->sdb.length); return ISCSI_ERR_DATALEN; } @@ -696,7 +696,7 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr) if (tcp_conn->in.datalen) { struct iscsi_tcp_task *tcp_task = task->dd_data; struct ahash_request *rx_hash = NULL; - struct scsi_data_buffer *sdb = scsi_in(task->sc); + struct scsi_data_buffer *sdb = &task->sc->sdb; /* * Setup copy of Data-In into the struct scsi_cmnd diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 661512bec3ac..8044bb08455d 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -430,7 +430,6 @@ static int resp_rsup_opcodes(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_rsup_tmfs(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_write_same_10(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_write_same_16(struct scsi_cmnd *, struct sdebug_dev_info *); -static int resp_xdwriteread_10(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_comp_write(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_write_buffer(struct scsi_cmnd *, struct sdebug_dev_info *); static int resp_sync_cache(struct scsi_cmnd *, struct sdebug_dev_info *); @@ -600,9 +599,6 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = { {0, 0x42, 0, F_D_OUT | FF_MEDIA_IO, resp_unmap, NULL, /* UNMAP */ {10, 0x1, 0, 0, 0, 0, 0x3f, 0xff, 0xff, 0xc7, 0, 0, 0, 0, 0, 0} }, /* 25 */ - {0, 0x53, 0, F_D_IN | F_D_OUT | FF_MEDIA_IO, resp_xdwriteread_10, - NULL, {10, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, 0xc7, - 0, 0, 0, 0, 0, 0} }, /* XDWRITEREAD(10) */ {0, 0x3b, 0, F_D_OUT_MAYBE, resp_write_buffer, NULL, {10, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc7, 0, 0, 0, 0, 0, 0} }, /* WRITE_BUFFER */ @@ -1010,11 +1006,11 @@ static int fill_from_dev_buffer(struct scsi_cmnd *scp, unsigned char *arr, int arr_len) { int act_len; - struct scsi_data_buffer *sdb = scsi_in(scp); + struct scsi_data_buffer *sdb = &scp->sdb; if (!sdb->length) return 0; - if (!(scsi_bidi_cmnd(scp) || scp->sc_data_direction == DMA_FROM_DEVICE)) + if (scp->sc_data_direction != DMA_FROM_DEVICE) return DID_ERROR << 16; act_len = sg_copy_from_buffer(sdb->table.sgl, sdb->table.nents, @@ -1033,12 +1029,12 @@ static int p_fill_from_dev_buffer(struct scsi_cmnd *scp, const void *arr, int arr_len, unsigned int off_dst) { int act_len, n; - struct scsi_data_buffer *sdb = scsi_in(scp); + struct scsi_data_buffer *sdb = &scp->sdb; off_t skip = off_dst; if (sdb->length <= off_dst) return 0; - if (!(scsi_bidi_cmnd(scp) || scp->sc_data_direction == DMA_FROM_DEVICE)) + if (scp->sc_data_direction != DMA_FROM_DEVICE) return DID_ERROR << 16; act_len = sg_pcopy_from_buffer(sdb->table.sgl, sdb->table.nents, @@ -1058,7 +1054,7 @@ static int fetch_to_dev_buffer(struct scsi_cmnd *scp, unsigned char *arr, { if (!scsi_bufflen(scp)) return 0; - if (!(scsi_bidi_cmnd(scp) || scp->sc_data_direction == DMA_TO_DEVICE)) + if (scp->sc_data_direction != DMA_TO_DEVICE) return -1; return scsi_sg_copy_to_buffer(scp, arr, arr_len); @@ -2477,21 +2473,19 @@ static int do_device_access(struct scsi_cmnd *scmd, u32 sg_skip, u64 lba, { int ret; u64 block, rest = 0; - struct scsi_data_buffer *sdb; + struct scsi_data_buffer *sdb = &scmd->sdb; enum dma_data_direction dir; if (do_write) { - sdb = scsi_out(scmd); dir = DMA_TO_DEVICE; write_since_sync = true; } else { - sdb = scsi_in(scmd); dir = DMA_FROM_DEVICE; } if (!sdb->length) return 0; - if (!(scsi_bidi_cmnd(scmd) || scmd->sc_data_direction == dir)) + if (scmd->sc_data_direction != dir) return -1; block = do_div(lba, sdebug_store_sectors); @@ -2774,7 +2768,7 @@ static int resp_read_dt0(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) if (unlikely(ret == -1)) return DID_ERROR << 16; - scsi_in(scp)->resid = scsi_bufflen(scp) - ret; + scp->sdb.resid = scsi_bufflen(scp) - ret; if (unlikely(sqcp)) { if (sqcp->inj_recovered) { @@ -3718,68 +3712,6 @@ static int resp_report_luns(struct scsi_cmnd *scp, return res; } -static int resp_xdwriteread(struct scsi_cmnd *scp, unsigned long long lba, - unsigned int num, struct sdebug_dev_info *devip) -{ - int j; - unsigned char *kaddr, *buf; - unsigned int offset; - struct scsi_data_buffer *sdb = scsi_in(scp); - struct sg_mapping_iter miter; - - /* better not to use temporary buffer. */ - buf = kzalloc(scsi_bufflen(scp), GFP_ATOMIC); - if (!buf) { - mk_sense_buffer(scp, ILLEGAL_REQUEST, INSUFF_RES_ASC, - INSUFF_RES_ASCQ); - return check_condition_result; - } - - scsi_sg_copy_to_buffer(scp, buf, scsi_bufflen(scp)); - - offset = 0; - sg_miter_start(&miter, sdb->table.sgl, sdb->table.nents, - SG_MITER_ATOMIC | SG_MITER_TO_SG); - - while (sg_miter_next(&miter)) { - kaddr = miter.addr; - for (j = 0; j < miter.length; j++) - *(kaddr + j) ^= *(buf + offset + j); - - offset += miter.length; - } - sg_miter_stop(&miter); - kfree(buf); - - return 0; -} - -static int resp_xdwriteread_10(struct scsi_cmnd *scp, - struct sdebug_dev_info *devip) -{ - u8 *cmd = scp->cmnd; - u64 lba; - u32 num; - int errsts; - - if (!scsi_bidi_cmnd(scp)) { - mk_sense_buffer(scp, ILLEGAL_REQUEST, INSUFF_RES_ASC, - INSUFF_RES_ASCQ); - return check_condition_result; - } - errsts = resp_read_dt0(scp, devip); - if (errsts) - return errsts; - if (!(cmd[1] & 0x4)) { /* DISABLE_WRITE is not set */ - errsts = resp_write_dt0(scp, devip); - if (errsts) - return errsts; - } - lba = get_unaligned_be32(cmd + 2); - num = get_unaligned_be16(cmd + 7); - return resp_xdwriteread(scp, lba, num, devip); -} - static struct sdebug_queue *get_queue(struct scsi_cmnd *cmnd) { u32 tag = blk_mq_unique_tag(cmnd->request); @@ -3953,7 +3885,6 @@ static int scsi_debug_slave_alloc(struct scsi_device *sdp) if (sdebug_verbose) pr_info("slave_alloc <%u %u %u %llu>\n", sdp->host->host_no, sdp->channel, sdp->id, sdp->lun); - blk_queue_flag_set(QUEUE_FLAG_BIDI, sdp->request_queue); return 0; } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 16eef068e9e9..1b8378f36139 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -965,7 +965,6 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, ses->cmnd = scmd->cmnd; ses->data_direction = scmd->sc_data_direction; ses->sdb = scmd->sdb; - ses->next_rq = scmd->request->next_rq; ses->result = scmd->result; ses->underflow = scmd->underflow; ses->prot_op = scmd->prot_op; @@ -976,7 +975,6 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, scmd->cmnd = ses->eh_cmnd; memset(scmd->cmnd, 0, BLK_MAX_CDB); memset(&scmd->sdb, 0, sizeof(scmd->sdb)); - scmd->request->next_rq = NULL; scmd->result = 0; if (sense_bytes) { @@ -1029,7 +1027,6 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) scmd->cmnd = ses->cmnd; scmd->sc_data_direction = ses->data_direction; scmd->sdb = ses->sdb; - scmd->request->next_rq = ses->next_rq; scmd->result = ses->result; scmd->underflow = ses->underflow; scmd->prot_op = ses->prot_op; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 00cd365fb7d2..2667bb95a441 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -556,15 +556,8 @@ static void scsi_uninit_cmd(struct scsi_cmnd *cmd) static void scsi_mq_free_sgtables(struct scsi_cmnd *cmd) { - struct scsi_data_buffer *sdb; - if (cmd->sdb.table.nents) sg_free_table_chained(&cmd->sdb.table, true); - if (cmd->request->next_rq) { - sdb = cmd->request->next_rq->special; - if (sdb) - sg_free_table_chained(&sdb->table, true); - } if (scsi_prot_sg_count(cmd)) sg_free_table_chained(&cmd->prot_sdb->table, true); } @@ -578,7 +571,7 @@ static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd) /* Returns false when no more bytes to process, true if there are more */ static bool scsi_end_request(struct request *req, blk_status_t error, - unsigned int bytes, unsigned int bidi_bytes) + unsigned int bytes) { struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req); struct scsi_device *sdev = cmd->device; @@ -587,11 +580,6 @@ static bool scsi_end_request(struct request *req, blk_status_t error, if (blk_update_request(req, error, bytes)) return true; - /* Bidi request must be completed as a whole */ - if (unlikely(bidi_bytes) && - blk_update_request(req->next_rq, error, bidi_bytes)) - return true; - if (blk_queue_add_random(q)) add_disk_randomness(req->rq_disk); @@ -816,7 +804,7 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) scsi_print_command(cmd); } } - if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req), 0)) + if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req))) return; /*FALLTHRU*/ case ACTION_REPREP: @@ -951,29 +939,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) */ scsi_req(req)->result = cmd->result; scsi_req(req)->resid_len = scsi_get_resid(cmd); - - if (unlikely(scsi_bidi_cmnd(cmd))) { - /* - * Bidi commands Must be complete as a whole, - * both sides at once. - */ - scsi_req(req->next_rq)->resid_len = scsi_in(cmd)->resid; - if (scsi_end_request(req, BLK_STS_OK, blk_rq_bytes(req), - blk_rq_bytes(req->next_rq))) - WARN_ONCE(true, - "Bidi command with remaining bytes"); - return; - } - } - - /* no bidi support yet, other than in pass-through */ - if (unlikely(blk_bidi_rq(req))) { - WARN_ONCE(true, "Only support bidi command in passthrough"); - scmd_printk(KERN_ERR, cmd, "Killing bidi command\n"); - if (scsi_end_request(req, BLK_STS_IOERR, blk_rq_bytes(req), - blk_rq_bytes(req->next_rq))) - WARN_ONCE(true, "Bidi command with remaining bytes"); - return; } /* @@ -990,13 +955,13 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) * to retry code. Fast path should return in this block. */ if (likely(blk_rq_bytes(req) > 0 || blk_stat == BLK_STS_OK)) { - if (likely(!scsi_end_request(req, blk_stat, good_bytes, 0))) + if (likely(!scsi_end_request(req, blk_stat, good_bytes))) return; /* no bytes remaining */ } /* Kill remainder if no retries. */ if (unlikely(blk_stat && scsi_noretry_cmd(cmd))) { - if (scsi_end_request(req, blk_stat, blk_rq_bytes(req), 0)) + if (scsi_end_request(req, blk_stat, blk_rq_bytes(req))) WARN_ONCE(true, "Bytes remaining after failed, no-retry command"); return; @@ -1058,12 +1023,6 @@ blk_status_t scsi_init_io(struct scsi_cmnd *cmd) if (ret) return ret; - if (blk_bidi_rq(rq)) { - ret = scsi_init_sgtable(rq->next_rq, rq->next_rq->special); - if (ret) - goto out_free_sgtables; - } - if (blk_integrity_rq(rq)) { struct scsi_data_buffer *prot_sdb = cmd->prot_sdb; int ivecs, count; @@ -1624,17 +1583,6 @@ static blk_status_t scsi_mq_prep_fn(struct request *req) (struct scatterlist *)(cmd->prot_sdb + 1); } - if (blk_bidi_rq(req)) { - struct request *next_rq = req->next_rq; - struct scsi_data_buffer *bidi_sdb = blk_mq_rq_to_pdu(next_rq); - - memset(bidi_sdb, 0, sizeof(struct scsi_data_buffer)); - bidi_sdb->table.sgl = - (struct scatterlist *)(bidi_sdb + 1); - - next_rq->special = bidi_sdb; - } - blk_mq_start_request(req); return scsi_setup_cmnd(sdev, req); diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 772b976e4ee4..1a6f150cd2d8 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -100,16 +100,8 @@ static inline struct Scsi_Host *virtio_scsi_host(struct virtio_device *vdev) static void virtscsi_compute_resid(struct scsi_cmnd *sc, u32 resid) { - if (!resid) - return; - - if (!scsi_bidi_cmnd(sc)) { + if (resid) scsi_set_resid(sc, resid); - return; - } - - scsi_in(sc)->resid = min(resid, scsi_in(sc)->length); - scsi_out(sc)->resid = resid - scsi_in(sc)->resid; } /** @@ -403,9 +395,9 @@ static int virtscsi_add_cmd(struct virtqueue *vq, if (sc && sc->sc_data_direction != DMA_NONE) { if (sc->sc_data_direction != DMA_FROM_DEVICE) - out = &scsi_out(sc)->table; + out = &sc->sdb.table; if (sc->sc_data_direction != DMA_TO_DEVICE) - in = &scsi_in(sc)->table; + in = &sc->sdb.table; } /* Request header. */ diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 89c6e3719d2b..3305b47fdf53 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -128,14 +128,6 @@ static void tcm_loop_submission_work(struct work_struct *work) set_host_byte(sc, DID_ERROR); goto out_done; } - if (scsi_bidi_cmnd(sc)) { - struct scsi_data_buffer *sdb = scsi_in(sc); - - sgl_bidi = sdb->table.sgl; - sgl_bidi_count = sdb->table.nents; - se_cmd->se_cmd_flags |= SCF_BIDI; - - } transfer_length = scsi_transfer_length(sc); if (!scsi_prot_sg_count(sc) && @@ -304,12 +296,6 @@ static int tcm_loop_target_reset(struct scsi_cmnd *sc) return FAILED; } -static int tcm_loop_slave_alloc(struct scsi_device *sd) -{ - blk_queue_flag_set(QUEUE_FLAG_BIDI, sd->request_queue); - return 0; -} - static struct scsi_host_template tcm_loop_driver_template = { .show_info = tcm_loop_show_info, .proc_name = "tcm_loopback", @@ -325,7 +311,6 @@ static struct scsi_host_template tcm_loop_driver_template = { .cmd_per_lun = 1024, .max_sectors = 0xFFFF, .dma_boundary = PAGE_SIZE - 1, - .slave_alloc = tcm_loop_slave_alloc, .module = THIS_MODULE, .track_queue_depth = 1, }; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 36742e8e7edc..95f2142093d5 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -368,25 +368,19 @@ static void uas_data_cmplt(struct urb *urb) struct scsi_cmnd *cmnd = urb->context; struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata; - struct scsi_data_buffer *sdb = NULL; + struct scsi_data_buffer *sdb = &cmnd->sdb; unsigned long flags; int status = urb->status; spin_lock_irqsave(&devinfo->lock, flags); if (cmdinfo->data_in_urb == urb) { - sdb = scsi_in(cmnd); cmdinfo->state &= ~DATA_IN_URB_INFLIGHT; cmdinfo->data_in_urb = NULL; } else if (cmdinfo->data_out_urb == urb) { - sdb = scsi_out(cmnd); cmdinfo->state &= ~DATA_OUT_URB_INFLIGHT; cmdinfo->data_out_urb = NULL; } - if (sdb == NULL) { - WARN_ON_ONCE(1); - goto out; - } if (devinfo->resetting) goto out; @@ -426,8 +420,7 @@ static struct urb *uas_alloc_data_urb(struct uas_dev_info *devinfo, gfp_t gfp, struct usb_device *udev = devinfo->udev; struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; struct urb *urb = usb_alloc_urb(0, gfp); - struct scsi_data_buffer *sdb = (dir == DMA_FROM_DEVICE) - ? scsi_in(cmnd) : scsi_out(cmnd); + struct scsi_data_buffer *sdb = &cmnd->sdb; unsigned int pipe = (dir == DMA_FROM_DEVICE) ? devinfo->data_in_pipe : devinfo->data_out_pipe; diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index d85e6befa26b..af6ae3e1eba6 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -213,23 +213,6 @@ static inline int scsi_get_resid(struct scsi_cmnd *cmd) #define scsi_for_each_sg(cmd, sg, nseg, __i) \ for_each_sg(scsi_sglist(cmd), sg, nseg, __i) -static inline int scsi_bidi_cmnd(struct scsi_cmnd *cmd) -{ - return blk_bidi_rq(cmd->request) && - (cmd->request->next_rq->special != NULL); -} - -static inline struct scsi_data_buffer *scsi_in(struct scsi_cmnd *cmd) -{ - return scsi_bidi_cmnd(cmd) ? - cmd->request->next_rq->special : &cmd->sdb; -} - -static inline struct scsi_data_buffer *scsi_out(struct scsi_cmnd *cmd) -{ - return &cmd->sdb; -} - static inline int scsi_sg_copy_from_buffer(struct scsi_cmnd *cmd, void *buf, int buflen) { @@ -351,7 +334,7 @@ static inline void set_driver_byte(struct scsi_cmnd *cmd, char status) static inline unsigned scsi_transfer_length(struct scsi_cmnd *scmd) { - unsigned int xfer_len = scsi_out(scmd)->length; + unsigned int xfer_len = scmd->sdb.length; unsigned int prot_interval = scsi_prot_interval(scmd); if (scmd->prot_flags & SCSI_PROT_TRANSFER_PI) diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 2b7e227960e1..3810b340551c 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -39,7 +39,6 @@ struct scsi_eh_save { unsigned char prot_op; unsigned char *cmnd; struct scsi_data_buffer sdb; - struct request *next_rq; /* new command support */ unsigned char eh_cmnd[BLK_MAX_CDB]; struct scatterlist sense_sgl; -- cgit v1.2.3 From 69ed175c195595c73901e18366cb0ebeaeb68b8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 19:35:11 +0100 Subject: scsi: block: remove req->special No users left. Signed-off-by: Christoph Hellwig Acked-by: Jens Axboe Signed-off-by: Martin K. Petersen --- block/blk-mq.c | 1 - drivers/scsi/sd.c | 2 -- include/linux/blkdev.h | 2 -- 3 files changed, 5 deletions(-) (limited to 'include') diff --git a/block/blk-mq.c b/block/blk-mq.c index 3ba37b9e15e9..502cbf964a3b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -331,7 +331,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, #if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; #endif - rq->special = NULL; /* tag was already set */ rq->extra_len = 0; WRITE_ONCE(rq->deadline, 0); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 3db9b1fe7516..c124459041dc 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1171,8 +1171,6 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) if (ret != BLK_STS_OK) return ret; - WARN_ON_ONCE(cmd != rq->special); - if (!scsi_device_online(sdp) || sdp->changed) { scmd_printk(KERN_ERR, cmd, "device offline or changed\n"); return BLK_STS_IOERR; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 338604dff7d0..fd1450d53f1c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -216,8 +216,6 @@ struct request { unsigned short write_hint; unsigned short ioprio; - void *special; /* opaque pointer available for LLD use */ - unsigned int extra_len; /* length of alignment and padding */ enum mq_rq_state state; -- cgit v1.2.3 From 8b3238cabd50e2715b6544e724e74685209b190a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 08:01:10 -0800 Subject: scsi: block: remove bidi support Unused now, and another field in struct request bites the dust. Signed-off-by: Christoph Hellwig Acked-by: Jens Axboe Signed-off-by: Martin K. Petersen --- block/blk-mq-debugfs.c | 1 - block/blk-mq.c | 3 --- include/linux/blkdev.h | 6 ------ 3 files changed, 10 deletions(-) (limited to 'include') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 90d68760af08..ac832547160a 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -115,7 +115,6 @@ static int queue_pm_only_show(void *data, struct seq_file *m) static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(STOPPED), QUEUE_FLAG_NAME(DYING), - QUEUE_FLAG_NAME(BIDI), QUEUE_FLAG_NAME(NOMERGES), QUEUE_FLAG_NAME(SAME_COMP), QUEUE_FLAG_NAME(FAIL_IO), diff --git a/block/blk-mq.c b/block/blk-mq.c index 502cbf964a3b..820d131a6893 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -339,7 +339,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->end_io = NULL; rq->end_io_data = NULL; - rq->next_rq = NULL; data->ctx->rq_dispatched[op_is_sync(op)]++; refcount_set(&rq->ref, 1); @@ -549,8 +548,6 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error) rq_qos_done(rq->q, rq); rq->end_io(rq, error); } else { - if (unlikely(blk_bidi_rq(rq))) - blk_mq_free_request(rq->next_rq); blk_mq_free_request(rq); } } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index fd1450d53f1c..21beb456b97a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -234,9 +234,6 @@ struct request { */ rq_end_io_fn *end_io; void *end_io_data; - - /* for bidi */ - struct request *next_rq; }; static inline bool blk_op_is_scsi(unsigned int op) @@ -572,7 +569,6 @@ struct request_queue { #define QUEUE_FLAG_STOPPED 1 /* queue is stopped */ #define QUEUE_FLAG_DYING 2 /* queue being torn down */ -#define QUEUE_FLAG_BIDI 4 /* queue supports bidi requests */ #define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ @@ -644,8 +640,6 @@ static inline bool blk_account_rq(struct request *rq) return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); } -#define blk_bidi_rq(rq) ((rq)->next_rq != NULL) - #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) -- cgit v1.2.3 From 5870970b9a828d8693aa6d15742573289d7dbcd0 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Thu, 31 Jan 2019 14:58:39 +0000 Subject: arm64: Fix HCR.TGE status for NMI contexts When using VHE, the host needs to clear HCR_EL2.TGE bit in order to interact with guest TLBs, switching from EL2&0 translation regime to EL1&0. However, some non-maskable asynchronous event could happen while TGE is cleared like SDEI. Because of this address translation operations relying on EL2&0 translation regime could fail (tlb invalidation, userspace access, ...). Fix this by properly setting HCR_EL2.TGE when entering NMI context and clear it if necessary when returning to the interrupted context. Signed-off-by: Julien Thierry Suggested-by: Marc Zyngier Reviewed-by: Marc Zyngier Reviewed-by: James Morse Cc: Arnd Bergmann Cc: Will Deacon Cc: Marc Zyngier Cc: James Morse Cc: linux-arch@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/hardirq.h | 31 +++++++++++++++++++++++++++++++ arch/arm64/kernel/irq.c | 3 +++ include/linux/hardirq.h | 7 +++++++ 3 files changed, 41 insertions(+) (limited to 'include') diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index 1473fc2f7ab7..89691c86640a 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -17,8 +17,12 @@ #define __ASM_HARDIRQ_H #include +#include #include +#include #include +#include +#include #define NR_IPI 7 @@ -37,6 +41,33 @@ u64 smp_irq_stat_cpu(unsigned int cpu); #define __ARCH_IRQ_EXIT_IRQS_DISABLED 1 +struct nmi_ctx { + u64 hcr; +}; + +DECLARE_PER_CPU(struct nmi_ctx, nmi_contexts); + +#define arch_nmi_enter() \ + do { \ + if (is_kernel_in_hyp_mode()) { \ + struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts); \ + nmi_ctx->hcr = read_sysreg(hcr_el2); \ + if (!(nmi_ctx->hcr & HCR_TGE)) { \ + write_sysreg(nmi_ctx->hcr | HCR_TGE, hcr_el2); \ + isb(); \ + } \ + } \ + } while (0) + +#define arch_nmi_exit() \ + do { \ + if (is_kernel_in_hyp_mode()) { \ + struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts); \ + if (!(nmi_ctx->hcr & HCR_TGE)) \ + write_sysreg(nmi_ctx->hcr, hcr_el2); \ + } \ + } while (0) + static inline void ack_bad_irq(unsigned int irq) { extern unsigned long irq_err_count; diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 780a12f59a8f..92fa81798fb9 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -33,6 +33,9 @@ unsigned long irq_err_count; +/* Only access this in an NMI enter/exit */ +DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts); + DEFINE_PER_CPU(unsigned long *, irq_stack_ptr); int arch_show_interrupts(struct seq_file *p, int prec) diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 0fbbcdf0c178..da0af631ded5 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -60,8 +60,14 @@ extern void irq_enter(void); */ extern void irq_exit(void); +#ifndef arch_nmi_enter +#define arch_nmi_enter() do { } while (0) +#define arch_nmi_exit() do { } while (0) +#endif + #define nmi_enter() \ do { \ + arch_nmi_enter(); \ printk_nmi_enter(); \ lockdep_off(); \ ftrace_nmi_enter(); \ @@ -80,6 +86,7 @@ extern void irq_exit(void); ftrace_nmi_exit(); \ lockdep_on(); \ printk_nmi_exit(); \ + arch_nmi_exit(); \ } while (0) #endif /* LINUX_HARDIRQ_H */ -- cgit v1.2.3 From 13b210ddf474d9f3368766008a89fe82a6f90b48 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Thu, 31 Jan 2019 14:58:49 +0000 Subject: efi: Let architectures decide the flags that should be saved/restored Currently, irqflags are saved before calling runtime services and checked for mismatch on return. Provide a pair of overridable macros to save and restore (if needed) the state that need to be preserved on return from a runtime service. This allows to check for flags that are not necesarly related to irqflags. Signed-off-by: Julien Thierry Acked-by: Catalin Marinas Acked-by: Ard Biesheuvel Acked-by: Marc Zyngier Cc: Ard Biesheuvel Cc: linux-efi@vger.kernel.org Signed-off-by: Catalin Marinas --- drivers/firmware/efi/runtime-wrappers.c | 17 +++++++++++++++-- include/linux/efi.h | 5 +++-- 2 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index 8903b9ccfc2b..c70df5ae7c4a 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -89,11 +89,24 @@ exit: \ efi_rts_work.status; \ }) +#ifndef arch_efi_save_flags +#define arch_efi_save_flags(state_flags) local_save_flags(state_flags) +#define arch_efi_restore_flags(state_flags) local_irq_restore(state_flags) +#endif + +unsigned long efi_call_virt_save_flags(void) +{ + unsigned long flags; + + arch_efi_save_flags(flags); + return flags; +} + void efi_call_virt_check_flags(unsigned long flags, const char *call) { unsigned long cur_flags, mismatch; - local_save_flags(cur_flags); + cur_flags = efi_call_virt_save_flags(); mismatch = flags ^ cur_flags; if (!WARN_ON_ONCE(mismatch & ARCH_EFI_IRQ_FLAGS_MASK)) @@ -102,7 +115,7 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call) add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_NOW_UNRELIABLE); pr_err_ratelimited(FW_BUG "IRQ flags corrupted (0x%08lx=>0x%08lx) by EFI %s\n", flags, cur_flags, call); - local_irq_restore(flags); + arch_efi_restore_flags(flags); } /* diff --git a/include/linux/efi.h b/include/linux/efi.h index 45ff763fba76..bd80b7ec35db 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1607,6 +1607,7 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, bool efi_runtime_disabled(void); extern void efi_call_virt_check_flags(unsigned long flags, const char *call); +extern unsigned long efi_call_virt_save_flags(void); enum efi_secureboot_mode { efi_secureboot_mode_unset, @@ -1652,7 +1653,7 @@ void efi_retrieve_tpm2_eventlog(efi_system_table_t *sys_table); \ arch_efi_call_virt_setup(); \ \ - local_save_flags(__flags); \ + __flags = efi_call_virt_save_flags(); \ __s = arch_efi_call_virt(p, f, args); \ efi_call_virt_check_flags(__flags, __stringify(f)); \ \ @@ -1667,7 +1668,7 @@ void efi_retrieve_tpm2_eventlog(efi_system_table_t *sys_table); \ arch_efi_call_virt_setup(); \ \ - local_save_flags(__flags); \ + __flags = efi_call_virt_save_flags(); \ arch_efi_call_virt(p, f, args); \ efi_call_virt_check_flags(__flags, __stringify(f)); \ \ -- cgit v1.2.3 From 840018668ce2d96783356204ff282d6c9b0e5f66 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 31 Jan 2019 11:47:08 -0700 Subject: perf/aux: Make perf_event accessible to setup_aux() When pmu::setup_aux() is called the coresight PMU needs to know which sink to use for the session by looking up the information in the event's attr::config2 field. As such simply replace the cpu information by the complete perf_event structure and change all affected customers. Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki Poulouse Acked-by: Peter Zijlstra Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Greg Kroah-Hartman Cc: H. Peter Anvin Cc: Heiko Carstens Cc: Jiri Olsa Cc: Mark Rutland Cc: Martin Schwidefsky Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Link: http://lkml.kernel.org/r/20190131184714.20388-2-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- arch/s390/kernel/perf_cpum_sf.c | 6 +++--- arch/x86/events/intel/bts.c | 4 +++- arch/x86/events/intel/pt.c | 5 +++-- drivers/hwtracing/coresight/coresight-etm-perf.c | 6 +++--- drivers/perf/arm_spe_pmu.c | 6 +++--- include/linux/perf_event.h | 2 +- kernel/events/ring_buffer.c | 2 +- 7 files changed, 17 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index bfabeb1889cc..1266194afb02 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1600,7 +1600,7 @@ static void aux_sdb_init(unsigned long sdb) /* * aux_buffer_setup() - Setup AUX buffer for diagnostic mode sampling - * @cpu: On which to allocate, -1 means current + * @event: Event the buffer is setup for, event->cpu == -1 means current * @pages: Array of pointers to buffer pages passed from perf core * @nr_pages: Total pages * @snapshot: Flag for snapshot mode @@ -1612,8 +1612,8 @@ static void aux_sdb_init(unsigned long sdb) * * Return the private AUX buffer structure if success or NULL if fails. */ -static void *aux_buffer_setup(int cpu, void **pages, int nr_pages, - bool snapshot) +static void *aux_buffer_setup(struct perf_event *event, void **pages, + int nr_pages, bool snapshot) { struct sf_buffer *sfb; struct aux_buffer *aux; diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index a01ef1b0f883..7cdd7b13bbda 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -77,10 +77,12 @@ static size_t buf_size(struct page *page) } static void * -bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite) +bts_buffer_setup_aux(struct perf_event *event, void **pages, + int nr_pages, bool overwrite) { struct bts_buffer *buf; struct page *page; + int cpu = event->cpu; int node = (cpu == -1) ? cpu : cpu_to_node(cpu); unsigned long offset; size_t size = nr_pages << PAGE_SHIFT; diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 9494ca68fd9d..c0e86ff21f81 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -1114,10 +1114,11 @@ static int pt_buffer_init_topa(struct pt_buffer *buf, unsigned long nr_pages, * Return: Our private PT buffer structure. */ static void * -pt_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool snapshot) +pt_buffer_setup_aux(struct perf_event *event, void **pages, + int nr_pages, bool snapshot) { struct pt_buffer *buf; - int node, ret; + int node, ret, cpu = event->cpu; if (!nr_pages) return NULL; diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index abe8249b893b..f21eb28b6782 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -177,15 +177,15 @@ static void etm_free_aux(void *data) schedule_work(&event_data->work); } -static void *etm_setup_aux(int event_cpu, void **pages, +static void *etm_setup_aux(struct perf_event *event, void **pages, int nr_pages, bool overwrite) { - int cpu; + int cpu = event->cpu; cpumask_t *mask; struct coresight_device *sink; struct etm_event_data *event_data = NULL; - event_data = alloc_event_data(event_cpu); + event_data = alloc_event_data(cpu); if (!event_data) return NULL; INIT_WORK(&event_data->work, free_event_data); diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index 8e46a9dad2fa..7cb766dafe85 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -824,10 +824,10 @@ static void arm_spe_pmu_read(struct perf_event *event) { } -static void *arm_spe_pmu_setup_aux(int cpu, void **pages, int nr_pages, - bool snapshot) +static void *arm_spe_pmu_setup_aux(struct perf_event *event, void **pages, + int nr_pages, bool snapshot) { - int i; + int i, cpu = event->cpu; struct page **pglist; struct arm_spe_pmu_buf *buf; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6cb5d483ab34..d9c3610e0e25 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -410,7 +410,7 @@ struct pmu { /* * Set up pmu-private data structures for an AUX area */ - void *(*setup_aux) (int cpu, void **pages, + void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 805f0423ee0b..70ae2422cbaf 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -657,7 +657,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, goto out; } - rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages, + rb->aux_priv = event->pmu->setup_aux(event, rb->aux_pages, nr_pages, overwrite); if (!rb->aux_priv) goto out; -- cgit v1.2.3 From bb8e370bdc141ddff526e5e5ee74210c91fee0b8 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 31 Jan 2019 11:47:09 -0700 Subject: coresight: perf: Add "sinks" group to PMU directory Add a "sinks" directory entry so that users can see all the sinks available in the system in a single place. Individual sink are added as they are registered with the coresight bus. Committer tests: Test built on a ubuntu 18.04 container with a cross build environment to arm64, the new field is there, need to find a machine with this feature to do further testing in the future. root@d15263e5734a:/git/perf# grep CORESIGHT /tmp/build/v5.0-rc2+/.config CONFIG_CORESIGHT=y CONFIG_CORESIGHT_LINKS_AND_SINKS=y CONFIG_CORESIGHT_LINK_AND_SINK_TMC=y CONFIG_CORESIGHT_CATU=y CONFIG_CORESIGHT_SINK_TPIU=y CONFIG_CORESIGHT_SINK_ETBV10=y CONFIG_CORESIGHT_SOURCE_ETM4X=y CONFIG_CORESIGHT_DYNAMIC_REPLICATOR=y CONFIG_CORESIGHT_STM=y CONFIG_CORESIGHT_CPU_DEBUG=m root@d15263e5734a:/git/perf# root@d15263e5734a:/git/perf# file /tmp/build/v5.0-rc2+/drivers/hwtracing/coresight/*.o .../coresight/coresight-catu.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-cpu-debug.mod.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-cpu-debug.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-dynamic-replicator.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-etb10.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-etm-perf.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-etm4x-sysfs.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-etm4x.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-funnel.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-replicator.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-stm.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-tmc-etf.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-tmc-etr.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-tmc.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight-tpiu.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/coresight.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped .../coresight/of_coresight.o: ELF 64-bit MSB relocatable, ARM aarch64, version 1 (SYSV), not stripped root@d15263e5734a:/git/perf# root@d15263e5734a:/git/perf# pahole -C coresight_device /tmp/build/v5.0-rc2+/drivers/hwtracing/coresight/coresight.o struct coresight_device { struct coresight_connection * conns; /* 0 8 */ int nr_inport; /* 8 4 */ int nr_outport; /* 12 4 */ enum coresight_dev_type type; /* 16 4 */ union coresight_dev_subtype subtype; /* 20 8 */ /* XXX 4 bytes hole, try to pack */ const struct coresight_ops * ops; /* 32 8 */ struct device dev; /* 40 1408 */ /* XXX last struct has 7 bytes of padding */ /* --- cacheline 22 boundary (1408 bytes) was 40 bytes ago --- */ atomic_t * refcnt; /* 1448 8 */ bool orphan; /* 1456 1 */ bool enable; /* 1457 1 */ bool activated; /* 1458 1 */ /* XXX 5 bytes hole, try to pack */ struct dev_ext_attribute * ea; /* 1464 8 */ /* size: 1472, cachelines: 23, members: 12 */ /* sum members: 1463, holes: 2, sum holes: 9 */ /* paddings: 1, sum paddings: 7 */ }; root@d15263e5734a:/git/perf# Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki K Poulose Acked-by: Peter Zijlstra Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Greg Kroah-Hartman Cc: H. Peter Anvin Cc: Heiko Carstens Cc: Jiri Olsa Cc: Mark Rutland Cc: Martin Schwidefsky Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Link: http://lkml.kernel.org/r/20190131184714.20388-3-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- drivers/hwtracing/coresight/coresight-etm-perf.c | 82 ++++++++++++++++++++++++ drivers/hwtracing/coresight/coresight-etm-perf.h | 6 +- drivers/hwtracing/coresight/coresight.c | 18 ++++++ include/linux/coresight.h | 7 +- 4 files changed, 110 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index f21eb28b6782..cdbdb28dc175 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -43,8 +44,18 @@ static const struct attribute_group etm_pmu_format_group = { .attrs = etm_config_formats_attr, }; +static struct attribute *etm_config_sinks_attr[] = { + NULL, +}; + +static const struct attribute_group etm_pmu_sinks_group = { + .name = "sinks", + .attrs = etm_config_sinks_attr, +}; + static const struct attribute_group *etm_pmu_attr_groups[] = { &etm_pmu_format_group, + &etm_pmu_sinks_group, NULL, }; @@ -479,6 +490,77 @@ int etm_perf_symlink(struct coresight_device *csdev, bool link) return 0; } +static ssize_t etm_perf_sink_name_show(struct device *dev, + struct device_attribute *dattr, + char *buf) +{ + struct dev_ext_attribute *ea; + + ea = container_of(dattr, struct dev_ext_attribute, attr); + return scnprintf(buf, PAGE_SIZE, "0x%lx\n", (unsigned long)(ea->var)); +} + +int etm_perf_add_symlink_sink(struct coresight_device *csdev) +{ + int ret; + unsigned long hash; + const char *name; + struct device *pmu_dev = etm_pmu.dev; + struct device *pdev = csdev->dev.parent; + struct dev_ext_attribute *ea; + + if (csdev->type != CORESIGHT_DEV_TYPE_SINK && + csdev->type != CORESIGHT_DEV_TYPE_LINKSINK) + return -EINVAL; + + if (csdev->ea != NULL) + return -EINVAL; + + if (!etm_perf_up) + return -EPROBE_DEFER; + + ea = devm_kzalloc(pdev, sizeof(*ea), GFP_KERNEL); + if (!ea) + return -ENOMEM; + + name = dev_name(pdev); + /* See function coresight_get_sink_by_id() to know where this is used */ + hash = hashlen_hash(hashlen_string(NULL, name)); + + ea->attr.attr.name = devm_kstrdup(pdev, name, GFP_KERNEL); + if (!ea->attr.attr.name) + return -ENOMEM; + + ea->attr.attr.mode = 0444; + ea->attr.show = etm_perf_sink_name_show; + ea->var = (unsigned long *)hash; + + ret = sysfs_add_file_to_group(&pmu_dev->kobj, + &ea->attr.attr, "sinks"); + + if (!ret) + csdev->ea = ea; + + return ret; +} + +void etm_perf_del_symlink_sink(struct coresight_device *csdev) +{ + struct device *pmu_dev = etm_pmu.dev; + struct dev_ext_attribute *ea = csdev->ea; + + if (csdev->type != CORESIGHT_DEV_TYPE_SINK && + csdev->type != CORESIGHT_DEV_TYPE_LINKSINK) + return; + + if (!ea) + return; + + sysfs_remove_file_from_group(&pmu_dev->kobj, + &ea->attr.attr, "sinks"); + csdev->ea = NULL; +} + static int __init etm_perf_init(void) { int ret; diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h index da7d9336a15c..015213abe00a 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.h +++ b/drivers/hwtracing/coresight/coresight-etm-perf.h @@ -59,6 +59,8 @@ struct etm_event_data { #ifdef CONFIG_CORESIGHT int etm_perf_symlink(struct coresight_device *csdev, bool link); +int etm_perf_add_symlink_sink(struct coresight_device *csdev); +void etm_perf_del_symlink_sink(struct coresight_device *csdev); static inline void *etm_perf_sink_config(struct perf_output_handle *handle) { struct etm_event_data *data = perf_get_aux(handle); @@ -70,7 +72,9 @@ static inline void *etm_perf_sink_config(struct perf_output_handle *handle) #else static inline int etm_perf_symlink(struct coresight_device *csdev, bool link) { return -EINVAL; } - +int etm_perf_add_symlink_sink(struct coresight_device *csdev) +{ return -EINVAL; } +void etm_perf_del_symlink_sink(struct coresight_device *csdev) {} static inline void *etm_perf_sink_config(struct perf_output_handle *handle) { return NULL; diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 2b0df1a0a8df..d7fa90be6f42 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -18,6 +18,7 @@ #include #include +#include "coresight-etm-perf.h" #include "coresight-priv.h" static DEFINE_MUTEX(coresight_mutex); @@ -1167,6 +1168,22 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) goto err_out; } + if (csdev->type == CORESIGHT_DEV_TYPE_SINK || + csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + ret = etm_perf_add_symlink_sink(csdev); + + if (ret) { + device_unregister(&csdev->dev); + /* + * As with the above, all resources are free'd + * explicitly via coresight_device_release() triggered + * from put_device(), which is in turn called from + * function device_unregister(). + */ + goto err_out; + } + } + mutex_lock(&coresight_mutex); coresight_fixup_device_conns(csdev); @@ -1185,6 +1202,7 @@ EXPORT_SYMBOL_GPL(coresight_register); void coresight_unregister(struct coresight_device *csdev) { + etm_perf_del_symlink_sink(csdev); /* Remove references of that device in the topology */ coresight_remove_conns(csdev); device_unregister(&csdev->dev); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 46c67a764877..7b87965f7a65 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -154,8 +154,9 @@ struct coresight_connection { * @orphan: true if the component has connections that haven't been linked. * @enable: 'true' if component is currently part of an active path. * @activated: 'true' only if a _sink_ has been activated. A sink can be - activated but not yet enabled. Enabling for a _sink_ - happens when a source has been selected for that it. + * activated but not yet enabled. Enabling for a _sink_ + * appens when a source has been selected for that it. + * @ea: Device attribute for sink representation under PMU directory. */ struct coresight_device { struct coresight_connection *conns; @@ -168,7 +169,9 @@ struct coresight_device { atomic_t *refcnt; bool orphan; bool enable; /* true only if configured as part of a path */ + /* sink specific fields */ bool activated; /* true only if a sink is part of a path */ + struct dev_ext_attribute *ea; }; #define to_coresight_device(d) container_of(d, struct coresight_device, dev) -- cgit v1.2.3 From 5f02a877638472e83cb5e335f9eec27052b1c7c2 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 10 Jan 2019 19:04:28 +0200 Subject: fsnotify: annotate directory entry modification events "dirent" events are referring to events that modify directory entries, such as create,delete,rename. Those events should always be reported on a watched directory, regardless if FS_EVENT_ON_CHILD is set on the watch mask. fsnotify_nameremove() and fsnotify_move() were modified to no longer set the FS_EVENT_ON_CHILD event bit. This is a semantic change to align with the "dirent" event definition. It has no effect on any existing backend, because dnotify, inotify and audit always requets the child events and fanotify does not get the delete,rename events. The fsnotify_dirent() helper is used instead of fsnotify_parent() to report a dirent event to dentry->d_parent without FS_EVENT_ON_CHILD and regardless if parent has the FS_EVENT_ON_CHILD bit set. Unlike fsnotify_parent(), fsnotify_dirent() assumes that dentry->d_name and dentry->d_parent are stable. For fsnotify_create()/fsnotify_mkdir(), this assumption is abviously correct. For fsnotify_nameremove(), it is less trivial, so we use dget_parent() and take_dentry_name_snapshot() to grab stable references. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 49 +++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 40 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 2ccb08cb5d6a..39b22e88423d 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -17,8 +17,22 @@ #include #include +/* + * Notify this @dir inode about a change in the directory entry @dentry. + * + * Unlike fsnotify_parent(), the event will be reported regardless of the + * FS_EVENT_ON_CHILD mask on the parent inode. + */ +static inline int fsnotify_dirent(struct inode *dir, struct dentry *dentry, + __u32 mask) +{ + return fsnotify(dir, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, + dentry->d_name.name, 0); +} + /* Notify this dentry's parent about a child's events. */ -static inline int fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask) +static inline int fsnotify_parent(const struct path *path, + struct dentry *dentry, __u32 mask) { if (!dentry) dentry = path->dentry; @@ -85,8 +99,8 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); - __u32 old_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_FROM); - __u32 new_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_TO); + __u32 old_dir_mask = FS_MOVED_FROM; + __u32 new_dir_mask = FS_MOVED_TO; const unsigned char *new_name = moved->d_name.name; if (old_dir == new_dir) @@ -128,15 +142,35 @@ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) /* * fsnotify_nameremove - a filename was removed from a directory + * + * This is mostly called under parent vfs inode lock so name and + * dentry->d_parent should be stable. However there are some corner cases where + * inode lock is not held. So to be on the safe side and be reselient to future + * callers and out of tree users of d_delete(), we do not assume that d_parent + * and d_name are stable and we use dget_parent() and + * take_dentry_name_snapshot() to grab stable references. */ static inline void fsnotify_nameremove(struct dentry *dentry, int isdir) { + struct dentry *parent; + struct name_snapshot name; __u32 mask = FS_DELETE; + /* d_delete() of pseudo inode? (e.g. __ns_get_path() playing tricks) */ + if (IS_ROOT(dentry)) + return; + if (isdir) mask |= FS_ISDIR; - fsnotify_parent(NULL, dentry, mask); + parent = dget_parent(dentry); + take_dentry_name_snapshot(&name, dentry); + + fsnotify(d_inode(parent), mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, + name.name, 0); + + release_dentry_name_snapshot(&name); + dput(parent); } /* @@ -155,7 +189,7 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) { audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify(inode, FS_CREATE, dentry->d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0); + fsnotify_dirent(inode, dentry, FS_CREATE); } /* @@ -176,12 +210,9 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct */ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) { - __u32 mask = (FS_CREATE | FS_ISDIR); - struct inode *d_inode = dentry->d_inode; - audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify(inode, mask, d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0); + fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR); } /* -- cgit v1.2.3 From e220140ff6241e180d0c2fc294e61ee6bbc6a18e Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 10 Jan 2019 19:04:29 +0200 Subject: fsnotify: remove dirent events from FS_EVENTS_POSS_ON_CHILD mask "dirent" events are referring to events that modify directory entries, such as create,delete,rename. Those events are always be reported on a watched directory, regardless if FS_EVENT_ON_CHILD is set on the watch mask. ALL_FSNOTIFY_DIRENT_EVENTS defines all the dirent event types and those event types are removed from FS_EVENTS_POSS_ON_CHILD. That means for a directory with an inotify watch and only dirent events in the mask (i.e. create,delete,move), all children dentries will no longer have the DCACHE_FSNOTIFY_PARENT_WATCHED flag set. This will allow all events that happen on children to be optimized away in __fsnotify_parent() without the need to dereference child->d_parent->d_inode->i_fsnotify_mask. Since the dirent events are never repoted via __fsnotify_parent(), this results in no change of logic, but only an optimization. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7639774e7475..7f195d43efaf 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -59,27 +59,33 @@ * dnotify and inotify. */ #define FS_EVENT_ON_CHILD 0x08000000 -/* This is a list of all events that may get sent to a parernt based on fs event - * happening to inodes inside that directory */ -#define FS_EVENTS_POSS_ON_CHILD (FS_ACCESS | FS_MODIFY | FS_ATTRIB |\ - FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN |\ - FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE |\ - FS_DELETE | FS_OPEN_PERM | FS_ACCESS_PERM | \ - FS_OPEN_EXEC | FS_OPEN_EXEC_PERM) - #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) +/* + * Directory entry modification events - reported only to directory + * where entry is modified and not to a watching parent. + * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event + * when a directory entry inside a child subdir changes. + */ +#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE) + #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) +/* + * This is a list of all events that may get sent to a parent based on fs event + * happening to inodes inside that directory. + */ +#define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ + FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ + FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ + FS_OPEN | FS_OPEN_EXEC) + /* Events that can be reported to backends */ -#define ALL_FSNOTIFY_EVENTS (FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ - FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN | \ - FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE | \ - FS_DELETE | FS_DELETE_SELF | FS_MOVE_SELF | \ - FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ - FS_OPEN_PERM | FS_ACCESS_PERM | FS_DN_RENAME | \ - FS_OPEN_EXEC | FS_OPEN_EXEC_PERM) +#define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ + FS_EVENTS_POSS_ON_CHILD | \ + FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ + FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ -- cgit v1.2.3 From a0a92d261f2922f4b5d2c0a98d6c41a89c7f5edd Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 10 Jan 2019 19:04:31 +0200 Subject: fsnotify: move mask out of struct fsnotify_event Common fsnotify_event helpers have no need for the mask field. It is only used by backend code, so move the field out of the abstract fsnotify_event struct and into the concrete backend event structs. This change packs struct inotify_event_info better on 64bit machine and will allow us to cram some more fields into struct fanotify_event_info. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 11 +++++++---- fs/notify/fanotify/fanotify.h | 1 + fs/notify/fanotify/fanotify_user.c | 10 +++++----- fs/notify/inotify/inotify.h | 1 + fs/notify/inotify/inotify_fsnotify.c | 9 +++++---- fs/notify/inotify/inotify_user.c | 5 +++-- fs/notify/notification.c | 22 +--------------------- include/linux/fsnotify_backend.h | 10 ++++++---- 8 files changed, 29 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 3723f3d18d20..98197802bbfb 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -36,20 +36,22 @@ static bool should_merge(struct fsnotify_event *old_fsn, static int fanotify_merge(struct list_head *list, struct fsnotify_event *event) { struct fsnotify_event *test_event; + struct fanotify_event_info *new; pr_debug("%s: list=%p event=%p\n", __func__, list, event); + new = FANOTIFY_E(event); /* * Don't merge a permission event with any other event so that we know * the event structure we have created in fanotify_handle_event() is the * one we should check for permission response. */ - if (fanotify_is_perm_event(event->mask)) + if (fanotify_is_perm_event(new->mask)) return 0; list_for_each_entry_reverse(test_event, list, list) { if (should_merge(test_event, event)) { - test_event->mask |= event->mask; + FANOTIFY_E(test_event)->mask |= new->mask; return 1; } } @@ -173,7 +175,8 @@ struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group, if (!event) goto out; init: __maybe_unused - fsnotify_init_event(&event->fse, inode, mask); + fsnotify_init_event(&event->fse, inode); + event->mask = mask; if (FAN_GROUP_FLAG(group, FAN_REPORT_TID)) event->pid = get_pid(task_pid(current)); else @@ -280,7 +283,7 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event) event = FANOTIFY_E(fsn_event); path_put(&event->path); put_pid(event->pid); - if (fanotify_is_perm_event(fsn_event->mask)) { + if (fanotify_is_perm_event(event->mask)) { kmem_cache_free(fanotify_perm_event_cachep, FANOTIFY_PE(fsn_event)); return; diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index ea05b8a401e7..e630d787d4c3 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -14,6 +14,7 @@ extern struct kmem_cache *fanotify_perm_event_cachep; */ struct fanotify_event_info { struct fsnotify_event fse; + u32 mask; /* * We hold ref to this path so it may be dereferenced at any point * during this object's lifetime diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 9c870b0d2b56..dea47d07cc29 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -131,9 +131,9 @@ static int fill_event_metadata(struct fsnotify_group *group, metadata->metadata_len = FAN_EVENT_METADATA_LEN; metadata->vers = FANOTIFY_METADATA_VERSION; metadata->reserved = 0; - metadata->mask = fsn_event->mask & FANOTIFY_OUTGOING_EVENTS; + metadata->mask = event->mask & FANOTIFY_OUTGOING_EVENTS; metadata->pid = pid_vnr(event->pid); - if (unlikely(fsn_event->mask & FAN_Q_OVERFLOW)) + if (unlikely(event->mask & FAN_Q_OVERFLOW)) metadata->fd = FAN_NOFD; else { metadata->fd = create_fd(group, event, file); @@ -230,7 +230,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, fanotify_event_metadata.event_len)) goto out_close_fd; - if (fanotify_is_perm_event(event->mask)) + if (fanotify_is_perm_event(FANOTIFY_E(event)->mask)) FANOTIFY_PE(event)->fd = fd; if (fd != FAN_NOFD) @@ -316,7 +316,7 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, * Permission events get queued to wait for response. Other * events can be destroyed now. */ - if (!fanotify_is_perm_event(kevent->mask)) { + if (!fanotify_is_perm_event(FANOTIFY_E(kevent)->mask)) { fsnotify_destroy_event(group, kevent); } else { if (ret <= 0) { @@ -401,7 +401,7 @@ static int fanotify_release(struct inode *ignored, struct file *file) */ while (!fsnotify_notify_queue_is_empty(group)) { fsn_event = fsnotify_remove_first_event(group); - if (!(fsn_event->mask & FANOTIFY_PERM_EVENTS)) { + if (!(FANOTIFY_E(fsn_event)->mask & FANOTIFY_PERM_EVENTS)) { spin_unlock(&group->notification_lock); fsnotify_destroy_event(group, fsn_event); spin_lock(&group->notification_lock); diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index 7e4578d35b61..74ae60305189 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -5,6 +5,7 @@ struct inotify_event_info { struct fsnotify_event fse; + u32 mask; int wd; u32 sync_cookie; int name_len; diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index f4184b4f3815..fe97299975f2 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -43,11 +43,11 @@ static bool event_compare(struct fsnotify_event *old_fsn, { struct inotify_event_info *old, *new; - if (old_fsn->mask & FS_IN_IGNORED) - return false; old = INOTIFY_E(old_fsn); new = INOTIFY_E(new_fsn); - if ((old_fsn->mask == new_fsn->mask) && + if (old->mask & FS_IN_IGNORED) + return false; + if ((old->mask == new->mask) && (old_fsn->inode == new_fsn->inode) && (old->name_len == new->name_len) && (!old->name_len || !strcmp(old->name, new->name))) @@ -114,7 +114,8 @@ int inotify_handle_event(struct fsnotify_group *group, } fsn_event = &event->fse; - fsnotify_init_event(fsn_event, inode, mask); + fsnotify_init_event(fsn_event, inode); + event->mask = mask; event->wd = i_mark->wd; event->sync_cookie = cookie; event->name_len = len; diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 798f1253141a..e2901fbb9f76 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -189,7 +189,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, */ pad_name_len = round_event_name_len(fsn_event); inotify_event.len = pad_name_len; - inotify_event.mask = inotify_mask_to_arg(fsn_event->mask); + inotify_event.mask = inotify_mask_to_arg(event->mask); inotify_event.wd = event->wd; inotify_event.cookie = event->sync_cookie; @@ -634,7 +634,8 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) return ERR_PTR(-ENOMEM); } group->overflow_event = &oevent->fse; - fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); + fsnotify_init_event(group->overflow_event, NULL); + oevent->mask = FS_Q_OVERFLOW; oevent->wd = -1; oevent->sync_cookie = 0; oevent->name_len = 0; diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 3c3e36745f59..027d5d5bb90e 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -71,7 +71,7 @@ void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event) { /* Overflow events are per-group and we don't want to free them */ - if (!event || event->mask == FS_Q_OVERFLOW) + if (!event || event == group->overflow_event) return; /* * If the event is still queued, we have a problem... Do an unreliable @@ -194,23 +194,3 @@ void fsnotify_flush_notify(struct fsnotify_group *group) } spin_unlock(&group->notification_lock); } - -/* - * fsnotify_create_event - Allocate a new event which will be sent to each - * group's handle_event function if the group was interested in this - * particular event. - * - * @inode the inode which is supposed to receive the event (sometimes a - * parent of the inode to which the event happened. - * @mask what actually happened. - * @data pointer to the object which was actually affected - * @data_type flag indication if the data is a file, path, inode, nothing... - * @name the filename, if available - */ -void fsnotify_init_event(struct fsnotify_event *event, struct inode *inode, - u32 mask) -{ - INIT_LIST_HEAD(&event->list); - event->inode = inode; - event->mask = mask; -} diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7f195d43efaf..1e4b88bd1443 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -135,7 +135,6 @@ struct fsnotify_event { struct list_head list; /* inode may ONLY be dereferenced during handle_event(). */ struct inode *inode; /* either the inode the event happened to or its parent */ - u32 mask; /* the type of access, bitwise OR for FS_* event types */ }; /* @@ -485,9 +484,12 @@ extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); -/* put here because inotify does some weird stuff when destroying watches */ -extern void fsnotify_init_event(struct fsnotify_event *event, - struct inode *to_tell, u32 mask); +static inline void fsnotify_init_event(struct fsnotify_event *event, + struct inode *inode) +{ + INIT_LIST_HEAD(&event->list); + event->inode = inode; +} #else -- cgit v1.2.3 From d6cd33ad71029a3f77ba1686caf55d4dea58d916 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 29 Jan 2019 11:31:52 +0100 Subject: regulator: gpio: Convert to use descriptors This converts the GPIO regulator driver to use decriptors only. We have to let go of the array gpio handling: the fetched descriptors are handled individually anyway, and the array retrieveal function does not make it possible to retrieve each GPIO descriptor with unique flags. Instead get them one by one. We request the "enable" GPIO separately as before, and make sure that this line is requested as nonexclusive since enable lines can be shared and the regulator core expects this. Most users of the GPIO regulator are using device tree. There are two boards in the kernel using the gpio regulator from a non-devicetree path: PXA hx4700 and magician. Make sure to switch these over to use descriptors as well. Cc: Philipp Zabel # Magician Cc: Petr Cvek # Magician Cc: Robert Jarzmik # PXA Cc: Paul Parsons # hx4700 Cc: Kevin Hilman # Meson Cc: Neil Armstrong # Meson Tested-by: Marek Szyprowski Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- arch/arm/mach-pxa/hx4700.c | 23 +++-- arch/arm/mach-pxa/magician.c | 23 +++-- drivers/regulator/gpio-regulator.c | 150 ++++++++++++------------------- include/linux/regulator/gpio-regulator.h | 12 +-- 4 files changed, 95 insertions(+), 113 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c index b79b757fdd41..51d38d5e776a 100644 --- a/arch/arm/mach-pxa/hx4700.c +++ b/arch/arm/mach-pxa/hx4700.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -702,9 +703,7 @@ static struct regulator_init_data bq24022_init_data = { .consumer_supplies = bq24022_consumers, }; -static struct gpio bq24022_gpios[] = { - { GPIO96_HX4700_BQ24022_ISET2, GPIOF_OUT_INIT_LOW, "bq24022_iset2" }, -}; +static enum gpiod_flags bq24022_gpiod_gflags[] = { GPIOD_OUT_LOW }; static struct gpio_regulator_state bq24022_states[] = { { .value = 100000, .gpios = (0 << 0) }, @@ -714,12 +713,10 @@ static struct gpio_regulator_state bq24022_states[] = { static struct gpio_regulator_config bq24022_info = { .supply_name = "bq24022", - .enable_gpio = GPIO72_HX4700_BQ24022_nCHARGE_EN, - .enable_high = 0, .enabled_at_boot = 0, - .gpios = bq24022_gpios, - .nr_gpios = ARRAY_SIZE(bq24022_gpios), + .gflags = bq24022_gpiod_gflags, + .ngpios = ARRAY_SIZE(bq24022_gpiod_gflags), .states = bq24022_states, .nr_states = ARRAY_SIZE(bq24022_states), @@ -736,6 +733,17 @@ static struct platform_device bq24022 = { }, }; +static struct gpiod_lookup_table bq24022_gpiod_table = { + .dev_id = "gpio-regulator", + .table = { + GPIO_LOOKUP("gpio-pxa", GPIO96_HX4700_BQ24022_ISET2, + NULL, GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-pxa", GPIO72_HX4700_BQ24022_nCHARGE_EN, + "enable", GPIO_ACTIVE_LOW), + { }, + }, +}; + /* * StrataFlash */ @@ -878,6 +886,7 @@ static void __init hx4700_init(void) pxa_set_btuart_info(NULL); pxa_set_stuart_info(NULL); + gpiod_add_lookup_table(&bq24022_gpiod_table); platform_add_devices(devices, ARRAY_SIZE(devices)); pwm_add_table(hx4700_pwm_lookup, ARRAY_SIZE(hx4700_pwm_lookup)); diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c index 08b079653c3f..6538a7c0e504 100644 --- a/arch/arm/mach-pxa/magician.c +++ b/arch/arm/mach-pxa/magician.c @@ -645,9 +645,8 @@ static struct regulator_init_data bq24022_init_data = { .consumer_supplies = bq24022_consumers, }; -static struct gpio bq24022_gpios[] = { - { EGPIO_MAGICIAN_BQ24022_ISET2, GPIOF_OUT_INIT_LOW, "bq24022_iset2" }, -}; + +static enum gpiod_flags bq24022_gpiod_gflags[] = { GPIOD_OUT_LOW }; static struct gpio_regulator_state bq24022_states[] = { { .value = 100000, .gpios = (0 << 0) }, @@ -657,12 +656,10 @@ static struct gpio_regulator_state bq24022_states[] = { static struct gpio_regulator_config bq24022_info = { .supply_name = "bq24022", - .enable_gpio = GPIO30_MAGICIAN_BQ24022_nCHARGE_EN, - .enable_high = 0, .enabled_at_boot = 1, - .gpios = bq24022_gpios, - .nr_gpios = ARRAY_SIZE(bq24022_gpios), + .gflags = bq24022_gpiod_gflags, + .ngpios = ARRAY_SIZE(bq24022_gpiod_gflags), .states = bq24022_states, .nr_states = ARRAY_SIZE(bq24022_states), @@ -679,6 +676,17 @@ static struct platform_device bq24022 = { }, }; +static struct gpiod_lookup_table bq24022_gpiod_table = { + .dev_id = "gpio-regulator", + .table = { + GPIO_LOOKUP("gpio-pxa", EGPIO_MAGICIAN_BQ24022_ISET2, + NULL, GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-pxa", GPIO30_MAGICIAN_BQ24022_nCHARGE_EN, + "enable", GPIO_ACTIVE_LOW), + { }, + }, +}; + /* * fixed regulator for ads7846 */ @@ -1027,6 +1035,7 @@ static void __init magician_init(void) regulator_register_always_on(0, "power", pwm_backlight_supply, ARRAY_SIZE(pwm_backlight_supply), 5000000); + gpiod_add_lookup_table(&bq24022_gpiod_table); platform_add_devices(ARRAY_AND_SIZE(devices)); } diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c index b2f5ec4f658a..07fb41abd4e8 100644 --- a/drivers/regulator/gpio-regulator.c +++ b/drivers/regulator/gpio-regulator.c @@ -30,16 +30,15 @@ #include #include #include -#include +#include #include #include -#include struct gpio_regulator_data { struct regulator_desc desc; struct regulator_dev *dev; - struct gpio *gpios; + struct gpio_desc **gpiods; int nr_gpios; struct gpio_regulator_state *states; @@ -82,7 +81,7 @@ static int gpio_regulator_set_voltage(struct regulator_dev *dev, for (ptr = 0; ptr < data->nr_gpios; ptr++) { state = (target & (1 << ptr)) >> ptr; - gpio_set_value_cansleep(data->gpios[ptr].gpio, state); + gpiod_set_value_cansleep(data->gpiods[ptr], state); } data->state = target; @@ -119,7 +118,7 @@ static int gpio_regulator_set_current_limit(struct regulator_dev *dev, for (ptr = 0; ptr < data->nr_gpios; ptr++) { state = (target & (1 << ptr)) >> ptr; - gpio_set_value_cansleep(data->gpios[ptr].gpio, state); + gpiod_set_value_cansleep(data->gpiods[ptr], state); } data->state = target; @@ -138,7 +137,8 @@ of_get_gpio_regulator_config(struct device *dev, struct device_node *np, { struct gpio_regulator_config *config; const char *regtype; - int proplen, gpio, i; + int proplen, i; + int ngpios; int ret; config = devm_kzalloc(dev, @@ -153,59 +153,36 @@ of_get_gpio_regulator_config(struct device *dev, struct device_node *np, config->supply_name = config->init_data->constraints.name; - if (of_property_read_bool(np, "enable-active-high")) - config->enable_high = true; - if (of_property_read_bool(np, "enable-at-boot")) config->enabled_at_boot = true; of_property_read_u32(np, "startup-delay-us", &config->startup_delay); - config->enable_gpio = of_get_named_gpio(np, "enable-gpio", 0); - if (config->enable_gpio < 0 && config->enable_gpio != -ENOENT) - return ERR_PTR(config->enable_gpio); - - /* Fetch GPIOs. - optional property*/ - ret = of_gpio_count(np); - if ((ret < 0) && (ret != -ENOENT)) - return ERR_PTR(ret); - - if (ret > 0) { - config->nr_gpios = ret; - config->gpios = devm_kcalloc(dev, - config->nr_gpios, sizeof(struct gpio), - GFP_KERNEL); - if (!config->gpios) + /* Fetch GPIO init levels */ + ngpios = gpiod_count(dev, NULL); + if (ngpios > 0) { + config->gflags = devm_kzalloc(dev, + sizeof(enum gpiod_flags) + * ngpios, + GFP_KERNEL); + if (!config->gflags) return ERR_PTR(-ENOMEM); - proplen = of_property_count_u32_elems(np, "gpios-states"); - /* optional property */ - if (proplen < 0) - proplen = 0; + for (i = 0; i < ngpios; i++) { + u32 val; - if (proplen > 0 && proplen != config->nr_gpios) { - dev_warn(dev, "gpios <-> gpios-states mismatch\n"); - proplen = 0; - } + ret = of_property_read_u32_index(np, "gpios-states", i, + &val); - for (i = 0; i < config->nr_gpios; i++) { - gpio = of_get_named_gpio(np, "gpios", i); - if (gpio < 0) { - if (gpio != -ENOENT) - return ERR_PTR(gpio); - break; - } - config->gpios[i].gpio = gpio; - config->gpios[i].label = config->supply_name; - if (proplen > 0) { - of_property_read_u32_index(np, "gpios-states", - i, &ret); - if (ret) - config->gpios[i].flags = - GPIOF_OUT_INIT_HIGH; - } + /* Default to high per specification */ + if (ret) + config->gflags[i] = GPIOD_OUT_HIGH; + else + config->gflags[i] = + val ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW; } } + config->ngpios = ngpios; /* Fetch states. */ proplen = of_property_count_u32_elems(np, "states"); @@ -255,7 +232,8 @@ static int gpio_regulator_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct gpio_regulator_data *drvdata; struct regulator_config cfg = { }; - int ptr, ret, state; + enum gpiod_flags gflags; + int ptr, ret, state, i; drvdata = devm_kzalloc(&pdev->dev, sizeof(struct gpio_regulator_data), GFP_KERNEL); @@ -275,26 +253,21 @@ static int gpio_regulator_probe(struct platform_device *pdev) return -ENOMEM; } - if (config->nr_gpios != 0) { - drvdata->gpios = kmemdup(config->gpios, - config->nr_gpios * sizeof(struct gpio), - GFP_KERNEL); - if (drvdata->gpios == NULL) { - dev_err(&pdev->dev, "Failed to allocate gpio data\n"); - ret = -ENOMEM; - goto err_name; - } - - drvdata->nr_gpios = config->nr_gpios; - ret = gpio_request_array(drvdata->gpios, drvdata->nr_gpios); - if (ret) { - if (ret != -EPROBE_DEFER) - dev_err(&pdev->dev, - "Could not obtain regulator setting GPIOs: %d\n", - ret); - goto err_memgpio; - } + drvdata->gpiods = devm_kzalloc(&pdev->dev, sizeof(struct gpio_desc *), + GFP_KERNEL); + if (!drvdata->gpiods) + return -ENOMEM; + for (i = 0; i < config->ngpios; i++) { + drvdata->gpiods[i] = devm_gpiod_get_index(&pdev->dev, + NULL, + i, + config->gflags[i]); + if (IS_ERR(drvdata->gpiods[i])) + return PTR_ERR(drvdata->gpiods[i]); + /* This is good to know */ + gpiod_set_consumer_name(drvdata->gpiods[i], drvdata->desc.name); } + drvdata->nr_gpios = config->ngpios; drvdata->states = kmemdup(config->states, config->nr_states * @@ -303,7 +276,7 @@ static int gpio_regulator_probe(struct platform_device *pdev) if (drvdata->states == NULL) { dev_err(&pdev->dev, "Failed to allocate state data\n"); ret = -ENOMEM; - goto err_stategpio; + goto err_name; } drvdata->nr_states = config->nr_states; @@ -330,7 +303,7 @@ static int gpio_regulator_probe(struct platform_device *pdev) /* build initial state from gpio init data. */ state = 0; for (ptr = 0; ptr < drvdata->nr_gpios; ptr++) { - if (config->gpios[ptr].flags & GPIOF_OUT_INIT_HIGH) + if (config->gflags[ptr] == GPIOD_OUT_HIGH) state |= (1 << ptr); } drvdata->state = state; @@ -340,21 +313,19 @@ static int gpio_regulator_probe(struct platform_device *pdev) cfg.driver_data = drvdata; cfg.of_node = np; - if (gpio_is_valid(config->enable_gpio)) { - cfg.ena_gpio = config->enable_gpio; - cfg.ena_gpio_initialized = true; - } - cfg.ena_gpio_invert = !config->enable_high; - if (config->enabled_at_boot) { - if (config->enable_high) - cfg.ena_gpio_flags |= GPIOF_OUT_INIT_HIGH; - else - cfg.ena_gpio_flags |= GPIOF_OUT_INIT_LOW; - } else { - if (config->enable_high) - cfg.ena_gpio_flags |= GPIOF_OUT_INIT_LOW; - else - cfg.ena_gpio_flags |= GPIOF_OUT_INIT_HIGH; + /* + * The signal will be inverted by the GPIO core if flagged so in the + * decriptor. + */ + if (config->enabled_at_boot) + gflags = GPIOD_OUT_HIGH | GPIOD_FLAGS_BIT_NONEXCLUSIVE; + else + gflags = GPIOD_OUT_LOW | GPIOD_FLAGS_BIT_NONEXCLUSIVE; + + cfg.ena_gpiod = gpiod_get_optional(&pdev->dev, "enable", gflags); + if (IS_ERR(cfg.ena_gpiod)) { + ret = PTR_ERR(cfg.ena_gpiod); + goto err_memstate; } drvdata->dev = regulator_register(&drvdata->desc, &cfg); @@ -370,10 +341,6 @@ static int gpio_regulator_probe(struct platform_device *pdev) err_memstate: kfree(drvdata->states); -err_stategpio: - gpio_free_array(drvdata->gpios, drvdata->nr_gpios); -err_memgpio: - kfree(drvdata->gpios); err_name: kfree(drvdata->desc.name); return ret; @@ -384,12 +351,7 @@ static int gpio_regulator_remove(struct platform_device *pdev) struct gpio_regulator_data *drvdata = platform_get_drvdata(pdev); regulator_unregister(drvdata->dev); - - gpio_free_array(drvdata->gpios, drvdata->nr_gpios); - kfree(drvdata->states); - kfree(drvdata->gpios); - kfree(drvdata->desc.name); return 0; diff --git a/include/linux/regulator/gpio-regulator.h b/include/linux/regulator/gpio-regulator.h index 19fbd267406d..49c407afb944 100644 --- a/include/linux/regulator/gpio-regulator.h +++ b/include/linux/regulator/gpio-regulator.h @@ -21,6 +21,8 @@ #ifndef __REGULATOR_GPIO_H #define __REGULATOR_GPIO_H +#include + struct regulator_init_data; enum regulator_type; @@ -53,9 +55,9 @@ struct gpio_regulator_state { * This is used to keep the regulator at * the default state * @startup_delay: Start-up time in microseconds - * @gpios: Array containing the gpios needed to control - * the setting of the regulator - * @nr_gpios: Number of gpios + * @gflags: Array of GPIO configuration flags for initial + * states + * @ngpios: Number of GPIOs and configurations available * @states: Array of gpio_regulator_state entries describing * the gpio state for specific voltages * @nr_states: Number of states available @@ -74,8 +76,8 @@ struct gpio_regulator_config { unsigned enabled_at_boot:1; unsigned startup_delay; - struct gpio *gpios; - int nr_gpios; + enum gpiod_flags *gflags; + int ngpios; struct gpio_regulator_state *states; int nr_states; -- cgit v1.2.3 From 01dc79cd6fe7d25b0eba84009634f5435cbdb4e6 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 29 Jan 2019 11:31:53 +0100 Subject: regulator: fixed/gpio: Pull inversion/OD into gpiolib This pushes the handling of inversion semantics and open drain settings to the GPIO descriptor and gpiolib. All affected board files are also augmented. This is especially nice since we don't have to have any confusing flags passed around to the left and right littering the fixed and GPIO regulator drivers and the regulator core. It is all just very straight-forward: the core asks the GPIO line to be asserted or deasserted and gpiolib deals with the rest depending on how the platform is configured: if the line is active low, it deals with that, if the line is open drain, it deals with that too. Cc: Alexander Shiyan # i.MX boards user Cc: Haojian Zhuang # MMP2 maintainer Cc: Aaro Koskinen # OMAP1 maintainer Cc: Tony Lindgren # OMAP1,2,3 maintainer Cc: Mike Rapoport # EM-X270 maintainer Cc: Robert Jarzmik # EZX maintainer Cc: Philipp Zabel # Magician maintainer Cc: Petr Cvek # Magician Cc: Robert Jarzmik # PXA Cc: Paul Parsons # hx4700 Cc: Daniel Mack # Raumfeld maintainer Cc: Marc Zyngier # Zeus maintainer Cc: Geert Uytterhoeven # SuperH pinctrl/GPIO maintainer Cc: Russell King # SA1100 Tested-by: Marek Szyprowski Tested-by: Janusz Krzysztofik #OMAP1 Amstrad Delta Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- arch/arm/mach-imx/mach-mx21ads.c | 1 - arch/arm/mach-imx/mach-mx27ads.c | 2 +- arch/arm/mach-mmp/brownstone.c | 1 - arch/arm/mach-omap1/board-ams-delta.c | 2 -- arch/arm/mach-omap2/pdata-quirks.c | 1 - arch/arm/mach-pxa/em-x270.c | 1 - arch/arm/mach-pxa/ezx.c | 3 +- arch/arm/mach-pxa/raumfeld.c | 1 - arch/arm/mach-pxa/zeus.c | 3 +- arch/arm/mach-sa1100/assabet.c | 1 - arch/sh/boards/mach-ecovec24/setup.c | 2 -- .../intel-mid/device_libs/platform_bcm43xx.c | 1 - drivers/regulator/core.c | 8 ++--- drivers/regulator/da9055-regulator.c | 1 - drivers/regulator/fixed.c | 35 +++++----------------- include/linux/regulator/fixed.h | 10 ------- include/linux/regulator/gpio-regulator.h | 6 ---- 17 files changed, 13 insertions(+), 66 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-imx/mach-mx21ads.c b/arch/arm/mach-imx/mach-mx21ads.c index 2e1e540f2e5a..d278fb672d40 100644 --- a/arch/arm/mach-imx/mach-mx21ads.c +++ b/arch/arm/mach-imx/mach-mx21ads.c @@ -205,7 +205,6 @@ static struct regulator_init_data mx21ads_lcd_regulator_init_data = { static struct fixed_voltage_config mx21ads_lcd_regulator_pdata = { .supply_name = "LCD", .microvolts = 3300000, - .enable_high = 1, .init_data = &mx21ads_lcd_regulator_init_data, }; diff --git a/arch/arm/mach-imx/mach-mx27ads.c b/arch/arm/mach-imx/mach-mx27ads.c index f5e04047ed13..6dd7f57c332f 100644 --- a/arch/arm/mach-imx/mach-mx27ads.c +++ b/arch/arm/mach-imx/mach-mx27ads.c @@ -237,7 +237,7 @@ static struct fixed_voltage_config mx27ads_lcd_regulator_pdata = { static struct gpiod_lookup_table mx27ads_lcd_regulator_gpiod_table = { .dev_id = "reg-fixed-voltage.0", /* Let's hope ID 0 is what we get */ .table = { - GPIO_LOOKUP("LCD", 0, NULL, GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("LCD", 0, NULL, GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mach-mmp/brownstone.c b/arch/arm/mach-mmp/brownstone.c index a04e249c654b..d2560fb1e835 100644 --- a/arch/arm/mach-mmp/brownstone.c +++ b/arch/arm/mach-mmp/brownstone.c @@ -149,7 +149,6 @@ static struct regulator_init_data brownstone_v_5vp_data = { static struct fixed_voltage_config brownstone_v_5vp = { .supply_name = "v_5vp", .microvolts = 5000000, - .enable_high = 1, .enabled_at_boot = 1, .init_data = &brownstone_v_5vp_data, }; diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index c4c0a8ea11e4..be30c3c061b4 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -267,7 +267,6 @@ static struct fixed_voltage_config modem_nreset_config = { .supply_name = "modem_nreset", .microvolts = 3300000, .startup_delay = 25000, - .enable_high = 1, .enabled_at_boot = 1, .init_data = &modem_nreset_data, }; @@ -533,7 +532,6 @@ static struct regulator_init_data keybrd_pwr_initdata = { static struct fixed_voltage_config keybrd_pwr_config = { .supply_name = "keybrd_pwr", .microvolts = 5000000, - .enable_high = 1, .init_data = &keybrd_pwr_initdata, }; diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index 8a5b6ed4ec36..a2ecc5e69abb 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -330,7 +330,6 @@ static struct fixed_voltage_config pandora_vwlan = { .supply_name = "vwlan", .microvolts = 1800000, /* 1.8V */ .startup_delay = 50000, /* 50ms */ - .enable_high = 1, .init_data = &pandora_vmmc3, }; diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c index 32c1edeb3f14..5ba7bb7f7d51 100644 --- a/arch/arm/mach-pxa/em-x270.c +++ b/arch/arm/mach-pxa/em-x270.c @@ -976,7 +976,6 @@ static struct fixed_voltage_config camera_dummy_config = { .supply_name = "camera_vdd", .input_supply = "vcc cam", .microvolts = 2800000, - .enable_high = 0, .init_data = &camera_dummy_initdata, }; diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c index 565965e9acc7..5e110e70ce5a 100644 --- a/arch/arm/mach-pxa/ezx.c +++ b/arch/arm/mach-pxa/ezx.c @@ -714,7 +714,6 @@ static struct regulator_init_data camera_regulator_initdata = { static struct fixed_voltage_config camera_regulator_config = { .supply_name = "camera_vdd", .microvolts = 2800000, - .enable_high = 0, .init_data = &camera_regulator_initdata, }; @@ -730,7 +729,7 @@ static struct gpiod_lookup_table camera_supply_gpiod_table = { .dev_id = "reg-fixed-voltage.1", .table = { GPIO_LOOKUP("gpio-pxa", GPIO50_nCAM_EN, - NULL, GPIO_ACTIVE_HIGH), + NULL, GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c index e1db072756f2..e13bfc9b01d2 100644 --- a/arch/arm/mach-pxa/raumfeld.c +++ b/arch/arm/mach-pxa/raumfeld.c @@ -883,7 +883,6 @@ static struct regulator_init_data audio_va_initdata = { static struct fixed_voltage_config audio_va_config = { .supply_name = "audio_va", .microvolts = 5000000, - .enable_high = 1, .enabled_at_boot = 0, .init_data = &audio_va_initdata, }; diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c index c411f79d4cb5..ebd654302387 100644 --- a/arch/arm/mach-pxa/zeus.c +++ b/arch/arm/mach-pxa/zeus.c @@ -426,7 +426,7 @@ static struct gpiod_lookup_table can_regulator_gpiod_table = { .dev_id = "reg-fixed-voltage.0", .table = { GPIO_LOOKUP("gpio-pxa", ZEUS_CAN_SHDN_GPIO, - NULL, GPIO_ACTIVE_HIGH), + NULL, GPIO_ACTIVE_LOW), { }, }, }; @@ -547,7 +547,6 @@ static struct regulator_init_data zeus_ohci_regulator_data = { static struct fixed_voltage_config zeus_ohci_regulator_config = { .supply_name = "vbus2", .microvolts = 5000000, /* 5.0V */ - .enable_high = 1, .startup_delay = 0, .init_data = &zeus_ohci_regulator_data, }; diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c index dfa42496ec27..d09c3f236186 100644 --- a/arch/arm/mach-sa1100/assabet.c +++ b/arch/arm/mach-sa1100/assabet.c @@ -469,7 +469,6 @@ static struct regulator_consumer_supply assabet_cf_vcc_consumers[] = { static struct fixed_voltage_config assabet_cf_vcc_pdata __initdata = { .supply_name = "cf-power", .microvolts = 3300000, - .enable_high = 1, }; static struct gpiod_lookup_table assabet_cf_vcc_gpio_table = { diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 22b4106b8084..5495efa07335 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -630,7 +630,6 @@ static struct regulator_init_data cn12_power_init_data = { static struct fixed_voltage_config cn12_power_info = { .supply_name = "CN12 SD/MMC Vdd", .microvolts = 3300000, - .enable_high = 1, .init_data = &cn12_power_init_data, }; @@ -671,7 +670,6 @@ static struct regulator_init_data sdhi0_power_init_data = { static struct fixed_voltage_config sdhi0_power_info = { .supply_name = "CN11 SD/MMC Vdd", .microvolts = 3300000, - .enable_high = 1, .init_data = &sdhi0_power_init_data, }; diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c index 96f438d4b026..1421d5330b2c 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c @@ -44,7 +44,6 @@ static struct fixed_voltage_config bcm43xx_vmmc = { */ .microvolts = 2000000, /* 1.8V */ .startup_delay = 250 * 1000, /* 250ms */ - .enable_high = 1, /* active high */ .enabled_at_boot = 0, /* disabled at boot */ .init_data = &bcm43xx_vmmc_data, }; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 430a73dea487..1778c5d1b2d0 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -82,7 +82,6 @@ struct regulator_enable_gpio { struct gpio_desc *gpiod; u32 enable_count; /* a number of enabled shared GPIO */ u32 request_count; /* a number of requested shared GPIO */ - unsigned int ena_gpio_invert:1; }; /* @@ -2268,7 +2267,6 @@ static int regulator_ena_gpio_request(struct regulator_dev *rdev, } pin->gpiod = gpiod; - pin->ena_gpio_invert = config->ena_gpio_invert; list_add(&pin->list, ®ulator_ena_gpio_list); update_ena_gpio_to_rdev: @@ -2319,8 +2317,7 @@ static int regulator_ena_gpio_ctrl(struct regulator_dev *rdev, bool enable) if (enable) { /* Enable GPIO at initial use */ if (pin->enable_count == 0) - gpiod_set_value_cansleep(pin->gpiod, - !pin->ena_gpio_invert); + gpiod_set_value_cansleep(pin->gpiod, 1); pin->enable_count++; } else { @@ -2331,8 +2328,7 @@ static int regulator_ena_gpio_ctrl(struct regulator_dev *rdev, bool enable) /* Disable GPIO if not used */ if (pin->enable_count <= 1) { - gpiod_set_value_cansleep(pin->gpiod, - pin->ena_gpio_invert); + gpiod_set_value_cansleep(pin->gpiod, 0); pin->enable_count = 0; } } diff --git a/drivers/regulator/da9055-regulator.c b/drivers/regulator/da9055-regulator.c index 588c3d2445cf..417cafe2aba0 100644 --- a/drivers/regulator/da9055-regulator.c +++ b/drivers/regulator/da9055-regulator.c @@ -457,7 +457,6 @@ static int da9055_gpio_init(struct da9055_regulator *regulator, int gpio_mux = pdata->gpio_ren[id]; config->ena_gpiod = pdata->ena_gpiods[id]; - config->ena_gpio_invert = 1; /* * GPI pin is muxed with regulator to control the diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index 9abdb9130766..b5afc9db2c61 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -79,15 +79,6 @@ of_get_fixed_voltage_config(struct device *dev, of_property_read_u32(np, "startup-delay-us", &config->startup_delay); - /* - * FIXME: we pulled active low/high and open drain handling into - * gpiolib so it will be handled there. Delete this in the second - * step when we also remove the custom inversion handling for all - * legacy boardfiles. - */ - config->enable_high = 1; - config->gpio_is_open_drain = 0; - if (of_find_property(np, "vin-supply", NULL)) config->input_supply = "vin"; @@ -151,24 +142,14 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev) drvdata->desc.fixed_uV = config->microvolts; - cfg.ena_gpio_invert = !config->enable_high; - if (config->enabled_at_boot) { - if (config->enable_high) - gflags = GPIOD_OUT_HIGH; - else - gflags = GPIOD_OUT_LOW; - } else { - if (config->enable_high) - gflags = GPIOD_OUT_LOW; - else - gflags = GPIOD_OUT_HIGH; - } - if (config->gpio_is_open_drain) { - if (gflags == GPIOD_OUT_HIGH) - gflags = GPIOD_OUT_HIGH_OPEN_DRAIN; - else - gflags = GPIOD_OUT_LOW_OPEN_DRAIN; - } + /* + * The signal will be inverted by the GPIO core if flagged so in the + * decriptor. + */ + if (config->enabled_at_boot) + gflags = GPIOD_OUT_HIGH; + else + gflags = GPIOD_OUT_LOW; /* * Some fixed regulators share the enable line between two diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h index 1a4340ed8e2b..f10140da7145 100644 --- a/include/linux/regulator/fixed.h +++ b/include/linux/regulator/fixed.h @@ -25,14 +25,6 @@ struct regulator_init_data; * @input_supply: Name of the input regulator supply * @microvolts: Output voltage of regulator * @startup_delay: Start-up time in microseconds - * @gpio_is_open_drain: Gpio pin is open drain or normal type. - * If it is open drain type then HIGH will be set - * through PULL-UP with setting gpio as input - * and low will be set as gpio-output with driven - * to low. For non-open-drain case, the gpio will - * will be in output and drive to low/high accordingly. - * @enable_high: Polarity of enable GPIO - * 1 = Active high, 0 = Active low * @enabled_at_boot: Whether regulator has been enabled at * boot or not. 1 = Yes, 0 = No * This is used to keep the regulator at @@ -48,8 +40,6 @@ struct fixed_voltage_config { const char *input_supply; int microvolts; unsigned startup_delay; - unsigned gpio_is_open_drain:1; - unsigned enable_high:1; unsigned enabled_at_boot:1; struct regulator_init_data *init_data; }; diff --git a/include/linux/regulator/gpio-regulator.h b/include/linux/regulator/gpio-regulator.h index 49c407afb944..11cd6375215d 100644 --- a/include/linux/regulator/gpio-regulator.h +++ b/include/linux/regulator/gpio-regulator.h @@ -46,10 +46,6 @@ struct gpio_regulator_state { /** * struct gpio_regulator_config - config structure * @supply_name: Name of the regulator supply - * @enable_gpio: GPIO to use for enable control - * set to -EINVAL if not used - * @enable_high: Polarity of enable GPIO - * 1 = Active high, 0 = Active low * @enabled_at_boot: Whether regulator has been enabled at * boot or not. 1 = Yes, 0 = No * This is used to keep the regulator at @@ -71,8 +67,6 @@ struct gpio_regulator_state { struct gpio_regulator_config { const char *supply_name; - int enable_gpio; - unsigned enable_high:1; unsigned enabled_at_boot:1; unsigned startup_delay; -- cgit v1.2.3 From 541d052d721506549774ab780a2709e4ff8ca79b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 29 Jan 2019 11:31:56 +0100 Subject: regulator: core: Only support passing enable GPIO descriptors Now that we changed all providers to pass descriptors into the core for enable GPIOs instead of a global GPIO number, delete the support for passing GPIO numbers in, and we get a cleanup and size reduction in the core, and from a GPIO point of view we use the modern, cleaner interface. Tested-by: Marek Szyprowski Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- drivers/regulator/core.c | 32 ++++++-------------------------- include/linux/regulator/driver.h | 12 +----------- 2 files changed, 7 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 1778c5d1b2d0..4fb475a2e4f2 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include @@ -2236,35 +2235,19 @@ static int regulator_ena_gpio_request(struct regulator_dev *rdev, { struct regulator_enable_gpio *pin; struct gpio_desc *gpiod; - int ret; - if (config->ena_gpiod) - gpiod = config->ena_gpiod; - else - gpiod = gpio_to_desc(config->ena_gpio); + gpiod = config->ena_gpiod; list_for_each_entry(pin, ®ulator_ena_gpio_list, list) { if (pin->gpiod == gpiod) { - rdev_dbg(rdev, "GPIO %d is already used\n", - config->ena_gpio); + rdev_dbg(rdev, "GPIO is already used\n"); goto update_ena_gpio_to_rdev; } } - if (!config->ena_gpiod) { - ret = gpio_request_one(config->ena_gpio, - GPIOF_DIR_OUT | config->ena_gpio_flags, - rdev_get_name(rdev)); - if (ret) - return ret; - } - pin = kzalloc(sizeof(struct regulator_enable_gpio), GFP_KERNEL); - if (pin == NULL) { - if (!config->ena_gpiod) - gpio_free(config->ena_gpio); + if (pin == NULL) return -ENOMEM; - } pin->gpiod = gpiod; list_add(&pin->list, ®ulator_ena_gpio_list); @@ -2287,7 +2270,6 @@ static void regulator_ena_gpio_free(struct regulator_dev *rdev) if (pin->gpiod == rdev->ena_pin->gpiod) { if (pin->request_count <= 1) { pin->request_count = 0; - gpiod_put(pin->gpiod); list_del(&pin->list); kfree(pin); rdev->ena_pin = NULL; @@ -4971,15 +4953,13 @@ regulator_register(const struct regulator_desc *regulator_desc, goto clean; } - if (config->ena_gpiod || - ((config->ena_gpio || config->ena_gpio_initialized) && - gpio_is_valid(config->ena_gpio))) { + if (config->ena_gpiod) { mutex_lock(®ulator_list_mutex); ret = regulator_ena_gpio_request(rdev, config); mutex_unlock(®ulator_list_mutex); if (ret != 0) { - rdev_err(rdev, "Failed to request enable GPIO%d: %d\n", - config->ena_gpio, ret); + rdev_err(rdev, "Failed to request enable GPIO: %d\n", + ret); goto clean; } /* The regulator core took over the GPIO descriptor */ diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 795b38a06b6c..7f8345bff4e1 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -401,13 +401,7 @@ struct regulator_desc { * NULL). * @regmap: regmap to use for core regmap helpers if dev_get_regmap() is * insufficient. - * @ena_gpio_initialized: GPIO controlling regulator enable was properly - * initialized, meaning that >= 0 is a valid gpio - * identifier and < 0 is a non existent gpio. - * @ena_gpio: GPIO controlling regulator enable. - * @ena_gpiod: GPIO descriptor controlling regulator enable. - * @ena_gpio_invert: Sense for GPIO enable control. - * @ena_gpio_flags: Flags to use when calling gpio_request_one() + * @ena_gpiod: GPIO controlling regulator enable. */ struct regulator_config { struct device *dev; @@ -416,11 +410,7 @@ struct regulator_config { struct device_node *of_node; struct regmap *regmap; - bool ena_gpio_initialized; - int ena_gpio; struct gpio_desc *ena_gpiod; - unsigned int ena_gpio_invert:1; - unsigned int ena_gpio_flags; }; /* -- cgit v1.2.3 From d325c402964e7c63db94e9138c530832269a1297 Mon Sep 17 00:00:00 2001 From: Miroslav Benes Date: Fri, 28 Dec 2018 14:38:47 +0100 Subject: ring-buffer: Remove unused function ring_buffer_page_len() Commit 6b7e633fe9c2 ("tracing: Remove extra zeroing out of the ring buffer page") removed the only caller of ring_buffer_page_len(). The function is now unused and may be removed. Link: http://lkml.kernel.org/r/20181228133847.106177-1-mbenes@suse.cz Signed-off-by: Miroslav Benes Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 2 -- kernel/trace/ring_buffer.c | 14 -------------- 2 files changed, 16 deletions(-) (limited to 'include') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 5b9ae62272bb..f1429675f252 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -187,8 +187,6 @@ void ring_buffer_set_clock(struct ring_buffer *buffer, void ring_buffer_set_time_stamp_abs(struct ring_buffer *buffer, bool abs); bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer); -size_t ring_buffer_page_len(void *page); - size_t ring_buffer_nr_pages(struct ring_buffer *buffer, int cpu); size_t ring_buffer_nr_dirty_pages(struct ring_buffer *buffer, int cpu); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 06e864a334bb..9a91479bbbfe 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -353,20 +353,6 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } -/** - * ring_buffer_page_len - the size of data on the page. - * @page: The page to read - * - * Returns the amount of data on the page, including buffer page header. - */ -size_t ring_buffer_page_len(void *page) -{ - struct buffer_data_page *bpage = page; - - return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS) - + BUF_PAGE_HDR_SIZE; -} - /* * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing * this issue out. -- cgit v1.2.3 From 7453e1dafdec076f87384c8647d2960affd57ecc Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 4 Feb 2019 14:53:04 +0100 Subject: ALSA: info: Add standard helpers for card proc file entries Two new helper functions are added here for cleaning up the existing lengthy calls. Reviewed-by: Jaroslav Kysela Signed-off-by: Takashi Iwai --- include/sound/info.h | 35 +++++++++++++++++++++++++++++++++++ sound/core/info.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) (limited to 'include') diff --git a/include/sound/info.h b/include/sound/info.h index becdf66d2825..96530f7599e1 100644 --- a/include/sound/info.h +++ b/include/sound/info.h @@ -160,6 +160,13 @@ static inline void snd_info_set_text_ops(struct snd_info_entry *entry, entry->c.text.read = read; } +int snd_card_rw_proc_new(struct snd_card *card, const char *name, + void *private_data, + void (*read)(struct snd_info_entry *, + struct snd_info_buffer *), + void (*write)(struct snd_info_entry *entry, + struct snd_info_buffer *buffer)); + int snd_info_check_reserved_words(const char *str); #else @@ -189,10 +196,38 @@ static inline int snd_card_proc_new(struct snd_card *card, const char *name, static inline void snd_info_set_text_ops(struct snd_info_entry *entry __attribute__((unused)), void *private_data, void (*read)(struct snd_info_entry *, struct snd_info_buffer *)) {} +static inline int snd_card_rw_proc_new(struct snd_card *card, const char *name, + void *private_data, + void (*read)(struct snd_info_entry *, + struct snd_info_buffer *), + void (*write)(struct snd_info_entry *entry, + struct snd_info_buffer *buffer)) +{ + return 0; +} static inline int snd_info_check_reserved_words(const char *str) { return 1; } #endif +/** + * snd_card_ro_proc_new - Create a read-only text proc file entry for the card + * @card: the card instance + * @name: the file name + * @private_data: the arbitrary private data + * @read: the read callback + * + * This proc file entry will be registered via snd_card_register() call, and + * it will be removed automatically at the card removal, too. + */ +static inline int +snd_card_ro_proc_new(struct snd_card *card, const char *name, + void *private_data, + void (*read)(struct snd_info_entry *, + struct snd_info_buffer *)) +{ + return snd_card_rw_proc_new(card, name, private_data, read, NULL); +} + /* * OSS info part */ diff --git a/sound/core/info.c b/sound/core/info.c index 5cd00629c0f5..6c149fa54d2d 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -866,6 +866,38 @@ int snd_info_register(struct snd_info_entry *entry) } EXPORT_SYMBOL(snd_info_register); +/** + * snd_card_rw_proc_new - Create a read/write text proc file entry for the card + * @card: the card instance + * @name: the file name + * @private_data: the arbitrary private data + * @read: the read callback + * @write: the write callback, NULL for read-only + * + * This proc file entry will be registered via snd_card_register() call, and + * it will be removed automatically at the card removal, too. + */ +int snd_card_rw_proc_new(struct snd_card *card, const char *name, + void *private_data, + void (*read)(struct snd_info_entry *, + struct snd_info_buffer *), + void (*write)(struct snd_info_entry *entry, + struct snd_info_buffer *buffer)) +{ + struct snd_info_entry *entry; + + entry = snd_info_create_card_entry(card, name, card->proc_root); + if (!entry) + return -ENOMEM; + snd_info_set_text_ops(entry, private_data, read); + if (write) { + entry->mode |= 0200; + entry->c.text.write = write; + } + return 0; +} +EXPORT_SYMBOL_GPL(snd_card_rw_proc_new); + /* */ -- cgit v1.2.3 From 9725752867cb158e076bcb6bc4bdb35d9710b1bd Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 5 Feb 2019 16:10:00 +0100 Subject: ALSA: info: Drop unused snd_info_entry.card field It's referred only in snd_card_id_read() which can receive the card object via private_data. Reviewed-by: Jaroslav Kysela Signed-off-by: Takashi Iwai --- include/sound/info.h | 1 - sound/core/info.c | 4 +--- sound/core/init.c | 6 ++++-- 3 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/sound/info.h b/include/sound/info.h index 96530f7599e1..97fdda41e076 100644 --- a/include/sound/info.h +++ b/include/sound/info.h @@ -82,7 +82,6 @@ struct snd_info_entry { struct snd_info_entry_ops *ops; } c; struct snd_info_entry *parent; - struct snd_card *card; struct module *module; void *private_data; void (*private_free)(struct snd_info_entry *entry); diff --git a/sound/core/info.c b/sound/core/info.c index 6c149fa54d2d..4d23069e7928 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -750,10 +750,8 @@ struct snd_info_entry *snd_info_create_card_entry(struct snd_card *card, if (!parent) parent = card->proc_root; entry = snd_info_create_entry(name, parent); - if (entry) { + if (entry) entry->module = card->module; - entry->card = card; - } return entry; } EXPORT_SYMBOL(snd_info_create_card_entry); diff --git a/sound/core/init.c b/sound/core/init.c index 4849c611c0fe..5252a9ce13dc 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -104,7 +104,9 @@ EXPORT_SYMBOL(snd_mixer_oss_notify_callback); static void snd_card_id_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { - snd_iprintf(buffer, "%s\n", entry->card->id); + struct snd_card *card = entry->private_data; + + snd_iprintf(buffer, "%s\n", card->id); } static int init_info_for_card(struct snd_card *card) @@ -116,7 +118,7 @@ static int init_info_for_card(struct snd_card *card) dev_dbg(card->dev, "unable to create card entry\n"); return -ENOMEM; } - entry->c.text.read = snd_card_id_read; + snd_info_set_text_ops(entry, card, snd_card_id_read); card->proc_id = entry; return snd_info_card_register(card); -- cgit v1.2.3 From 29b2625ff605394ecd0b078e0cb67a151bb4d80c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 5 Feb 2019 16:26:06 +0100 Subject: ALSA: info: Move card id proc creation into info.c The creation of card's id proc file can be moved gracefully into info.c. Also, the assignment of card->proc_id is superfluous and can be dropped. So let's do it. Basically this is no functional change but code refactoring, but one potential behavior change is that now it returns properly the error code from snd_info_card_register(), which is a good thing (tm). Reviewed-by: Jaroslav Kysela Signed-off-by: Takashi Iwai --- include/sound/core.h | 1 - sound/core/info.c | 11 ++++++++++- sound/core/init.c | 33 ++++----------------------------- 3 files changed, 14 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/sound/core.h b/include/sound/core.h index 36a5934cf4b1..e923c23e05dd 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -120,7 +120,6 @@ struct snd_card { struct list_head ctl_files; /* active control files */ struct snd_info_entry *proc_root; /* root for soundcard specific files */ - struct snd_info_entry *proc_id; /* the card id */ struct proc_dir_entry *proc_root_link; /* number link to real id */ struct list_head files_list; /* all files associated to this card */ diff --git a/sound/core/info.c b/sound/core/info.c index 7a4e733172ee..96a074019c33 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -504,6 +504,14 @@ int __exit snd_info_done(void) return 0; } +static void snd_card_id_read(struct snd_info_entry *entry, + struct snd_info_buffer *buffer) +{ + struct snd_card *card = entry->private_data; + + snd_iprintf(buffer, "%s\n", card->id); +} + /* * create a card proc file * called from init.c @@ -521,7 +529,8 @@ int snd_info_card_create(struct snd_card *card) if (!entry) return -ENOMEM; card->proc_root = entry; - return 0; + + return snd_card_ro_proc_new(card, "id", card, snd_card_id_read); } /* diff --git a/sound/core/init.c b/sound/core/init.c index 5252a9ce13dc..0c4dc40376a7 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -100,33 +100,6 @@ int (*snd_mixer_oss_notify_callback)(struct snd_card *card, int free_flag); EXPORT_SYMBOL(snd_mixer_oss_notify_callback); #endif -#ifdef CONFIG_SND_PROC_FS -static void snd_card_id_read(struct snd_info_entry *entry, - struct snd_info_buffer *buffer) -{ - struct snd_card *card = entry->private_data; - - snd_iprintf(buffer, "%s\n", card->id); -} - -static int init_info_for_card(struct snd_card *card) -{ - struct snd_info_entry *entry; - - entry = snd_info_create_card_entry(card, "id", card->proc_root); - if (!entry) { - dev_dbg(card->dev, "unable to create card entry\n"); - return -ENOMEM; - } - snd_info_set_text_ops(entry, card, snd_card_id_read); - card->proc_id = entry; - - return snd_info_card_register(card); -} -#else /* !CONFIG_SND_PROC_FS */ -#define init_info_for_card(card) -#endif - static int check_empty_slot(struct module *module, int slot) { return !slots[slot] || !*slots[slot]; @@ -493,7 +466,6 @@ static int snd_card_do_free(struct snd_card *card) snd_device_free_all(card); if (card->private_free) card->private_free(card); - snd_info_free_entry(card->proc_id); if (snd_info_card_free(card) < 0) { dev_warn(card->dev, "unable to free card info\n"); /* Not fatal error */ @@ -797,7 +769,10 @@ int snd_card_register(struct snd_card *card) } snd_cards[card->number] = card; mutex_unlock(&snd_card_mutex); - init_info_for_card(card); + err = snd_info_card_register(card); + if (err < 0) + return err; + #if IS_ENABLED(CONFIG_SND_MIXER_OSS) if (snd_mixer_oss_notify_callback) snd_mixer_oss_notify_callback(card, SND_MIXER_OSS_NOTIFY_REGISTER); -- cgit v1.2.3 From f13d4b5f85e1c436c9bf21205509266b5a81a320 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 5 Feb 2019 10:22:28 -0600 Subject: ASoC: dapm: harden use of lookup tables To detect potential errors, let's add: a) build-time warnings when the table size isn't aligned with the enum list b) run-time warnings when the values are not initialized. This requires an increase by one of all values to avoid the default 0. Suggested-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Mark Brown --- include/sound/soc-dapm.h | 3 + sound/soc/soc-dapm.c | 158 ++++++++++++++++++++++++----------------------- 2 files changed, 85 insertions(+), 76 deletions(-) (limited to 'include') diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 79b4ddfb8e9e..c00a0b8ade08 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -523,6 +523,9 @@ enum snd_soc_dapm_type { snd_soc_dapm_asrc, /* DSP/CODEC ASRC component */ snd_soc_dapm_encoder, /* FW/SW audio encoder component */ snd_soc_dapm_decoder, /* FW/SW audio decoder component */ + + /* Don't edit below this line */ + SND_SOC_DAPM_TYPE_COUNT }; enum snd_soc_dapm_subclass { diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 40e7190f533a..d31d295b540f 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -64,85 +64,85 @@ snd_soc_dapm_new_control_unlocked(struct snd_soc_dapm_context *dapm, /* dapm power sequences - make this per codec in the future */ static int dapm_up_seq[] = { - [snd_soc_dapm_pre] = 0, - [snd_soc_dapm_regulator_supply] = 1, - [snd_soc_dapm_pinctrl] = 1, - [snd_soc_dapm_clock_supply] = 1, - [snd_soc_dapm_supply] = 2, - [snd_soc_dapm_micbias] = 3, - [snd_soc_dapm_vmid] = 3, - [snd_soc_dapm_dai_link] = 2, - [snd_soc_dapm_dai_in] = 4, - [snd_soc_dapm_dai_out] = 4, - [snd_soc_dapm_aif_in] = 4, - [snd_soc_dapm_aif_out] = 4, - [snd_soc_dapm_mic] = 5, - [snd_soc_dapm_siggen] = 5, - [snd_soc_dapm_input] = 5, - [snd_soc_dapm_output] = 5, - [snd_soc_dapm_mux] = 6, - [snd_soc_dapm_demux] = 6, - [snd_soc_dapm_dac] = 7, - [snd_soc_dapm_switch] = 8, - [snd_soc_dapm_mixer] = 8, - [snd_soc_dapm_mixer_named_ctl] = 8, - [snd_soc_dapm_pga] = 9, - [snd_soc_dapm_buffer] = 9, - [snd_soc_dapm_scheduler] = 9, - [snd_soc_dapm_effect] = 9, - [snd_soc_dapm_src] = 9, - [snd_soc_dapm_asrc] = 9, - [snd_soc_dapm_encoder] = 9, - [snd_soc_dapm_decoder] = 9, - [snd_soc_dapm_adc] = 10, - [snd_soc_dapm_out_drv] = 11, - [snd_soc_dapm_hp] = 11, - [snd_soc_dapm_spk] = 11, - [snd_soc_dapm_line] = 11, - [snd_soc_dapm_sink] = 11, - [snd_soc_dapm_kcontrol] = 12, - [snd_soc_dapm_post] = 13, + [snd_soc_dapm_pre] = 1, + [snd_soc_dapm_regulator_supply] = 2, + [snd_soc_dapm_pinctrl] = 2, + [snd_soc_dapm_clock_supply] = 2, + [snd_soc_dapm_supply] = 3, + [snd_soc_dapm_micbias] = 4, + [snd_soc_dapm_vmid] = 4, + [snd_soc_dapm_dai_link] = 3, + [snd_soc_dapm_dai_in] = 5, + [snd_soc_dapm_dai_out] = 5, + [snd_soc_dapm_aif_in] = 5, + [snd_soc_dapm_aif_out] = 5, + [snd_soc_dapm_mic] = 6, + [snd_soc_dapm_siggen] = 6, + [snd_soc_dapm_input] = 6, + [snd_soc_dapm_output] = 6, + [snd_soc_dapm_mux] = 7, + [snd_soc_dapm_demux] = 7, + [snd_soc_dapm_dac] = 8, + [snd_soc_dapm_switch] = 9, + [snd_soc_dapm_mixer] = 9, + [snd_soc_dapm_mixer_named_ctl] = 9, + [snd_soc_dapm_pga] = 10, + [snd_soc_dapm_buffer] = 10, + [snd_soc_dapm_scheduler] = 10, + [snd_soc_dapm_effect] = 10, + [snd_soc_dapm_src] = 10, + [snd_soc_dapm_asrc] = 10, + [snd_soc_dapm_encoder] = 10, + [snd_soc_dapm_decoder] = 10, + [snd_soc_dapm_adc] = 11, + [snd_soc_dapm_out_drv] = 12, + [snd_soc_dapm_hp] = 12, + [snd_soc_dapm_spk] = 12, + [snd_soc_dapm_line] = 12, + [snd_soc_dapm_sink] = 12, + [snd_soc_dapm_kcontrol] = 13, + [snd_soc_dapm_post] = 14, }; static int dapm_down_seq[] = { - [snd_soc_dapm_pre] = 0, - [snd_soc_dapm_kcontrol] = 1, - [snd_soc_dapm_adc] = 2, - [snd_soc_dapm_hp] = 3, - [snd_soc_dapm_spk] = 3, - [snd_soc_dapm_line] = 3, - [snd_soc_dapm_out_drv] = 3, - [snd_soc_dapm_sink] = 3, - [snd_soc_dapm_pga] = 4, - [snd_soc_dapm_buffer] = 4, - [snd_soc_dapm_scheduler] = 4, - [snd_soc_dapm_effect] = 4, - [snd_soc_dapm_src] = 4, - [snd_soc_dapm_asrc] = 4, - [snd_soc_dapm_encoder] = 4, - [snd_soc_dapm_decoder] = 4, - [snd_soc_dapm_switch] = 5, - [snd_soc_dapm_mixer_named_ctl] = 5, - [snd_soc_dapm_mixer] = 5, - [snd_soc_dapm_dac] = 6, - [snd_soc_dapm_mic] = 7, - [snd_soc_dapm_siggen] = 7, - [snd_soc_dapm_input] = 7, - [snd_soc_dapm_output] = 7, - [snd_soc_dapm_micbias] = 8, - [snd_soc_dapm_vmid] = 8, - [snd_soc_dapm_mux] = 9, - [snd_soc_dapm_demux] = 9, - [snd_soc_dapm_aif_in] = 10, - [snd_soc_dapm_aif_out] = 10, - [snd_soc_dapm_dai_in] = 10, - [snd_soc_dapm_dai_out] = 10, - [snd_soc_dapm_dai_link] = 11, - [snd_soc_dapm_supply] = 12, - [snd_soc_dapm_clock_supply] = 13, - [snd_soc_dapm_pinctrl] = 13, - [snd_soc_dapm_regulator_supply] = 13, - [snd_soc_dapm_post] = 14, + [snd_soc_dapm_pre] = 1, + [snd_soc_dapm_kcontrol] = 2, + [snd_soc_dapm_adc] = 3, + [snd_soc_dapm_hp] = 4, + [snd_soc_dapm_spk] = 4, + [snd_soc_dapm_line] = 4, + [snd_soc_dapm_out_drv] = 4, + [snd_soc_dapm_sink] = 4, + [snd_soc_dapm_pga] = 5, + [snd_soc_dapm_buffer] = 5, + [snd_soc_dapm_scheduler] = 5, + [snd_soc_dapm_effect] = 5, + [snd_soc_dapm_src] = 5, + [snd_soc_dapm_asrc] = 5, + [snd_soc_dapm_encoder] = 5, + [snd_soc_dapm_decoder] = 5, + [snd_soc_dapm_switch] = 6, + [snd_soc_dapm_mixer_named_ctl] = 6, + [snd_soc_dapm_mixer] = 6, + [snd_soc_dapm_dac] = 7, + [snd_soc_dapm_mic] = 8, + [snd_soc_dapm_siggen] = 8, + [snd_soc_dapm_input] = 8, + [snd_soc_dapm_output] = 8, + [snd_soc_dapm_micbias] = 9, + [snd_soc_dapm_vmid] = 9, + [snd_soc_dapm_mux] = 10, + [snd_soc_dapm_demux] = 10, + [snd_soc_dapm_aif_in] = 11, + [snd_soc_dapm_aif_out] = 11, + [snd_soc_dapm_dai_in] = 11, + [snd_soc_dapm_dai_out] = 11, + [snd_soc_dapm_dai_link] = 12, + [snd_soc_dapm_supply] = 13, + [snd_soc_dapm_clock_supply] = 14, + [snd_soc_dapm_pinctrl] = 14, + [snd_soc_dapm_regulator_supply] = 14, + [snd_soc_dapm_post] = 15, }; static void dapm_assert_locked(struct snd_soc_dapm_context *dapm) @@ -1425,11 +1425,17 @@ static int dapm_seq_compare(struct snd_soc_dapm_widget *a, { int *sort; + BUILD_BUG_ON(ARRAY_SIZE(dapm_up_seq) != SND_SOC_DAPM_TYPE_COUNT); + BUILD_BUG_ON(ARRAY_SIZE(dapm_down_seq) != SND_SOC_DAPM_TYPE_COUNT); + if (power_up) sort = dapm_up_seq; else sort = dapm_down_seq; + WARN_ONCE(sort[a->id] == 0, "offset a->id %d not initialized\n", a->id); + WARN_ONCE(sort[b->id] == 0, "offset b->id %d not initialized\n", b->id); + if (sort[a->id] != sort[b->id]) return sort[a->id] - sort[b->id]; if (a->subseq != b->subseq) { -- cgit v1.2.3 From 1878f0dcbff0cd07f62602deb160a44d69a8f146 Mon Sep 17 00:00:00 2001 From: Nikita Yushchenko Date: Wed, 6 Feb 2019 07:36:40 +0100 Subject: net: phy: provide full set of accessor functions to MMD registers This adds full set of locked and unlocked accessor functions to read and write PHY MMD registers and/or bitfields. Set of functions exactly matches what is already available for PHY legacy registers. Signed-off-by: Nikita Yushchenko Signed-off-by: Andrew Lunn Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy-core.c | 116 ++++++++++++++++++++++++++++++++++----- include/linux/phy.h | 134 +++++++++++++++++++++++++++++++++++++-------- 2 files changed, 214 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 909b3344babf..7d6aad287f84 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -414,15 +414,15 @@ static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad, } /** - * phy_read_mmd - Convenience function for reading a register + * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. * @phydev: The phy_device struct * @devad: The MMD to read from (0..31) * @regnum: The register on the MMD to read (0..65535) * - * Same rules as for phy_read(); + * Same rules as for __phy_read(); */ -int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) +int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) { int val; @@ -434,33 +434,52 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) } else if (phydev->is_c45) { u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff); - val = mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, addr); + val = __mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, addr); } else { struct mii_bus *bus = phydev->mdio.bus; int phy_addr = phydev->mdio.addr; - mutex_lock(&bus->mdio_lock); mmd_phy_indirect(bus, phy_addr, devad, regnum); /* Read the content of the MMD's selected register */ val = __mdiobus_read(bus, phy_addr, MII_MMD_DATA); - mutex_unlock(&bus->mdio_lock); } return val; } +EXPORT_SYMBOL(__phy_read_mmd); + +/** + * phy_read_mmd - Convenience function for reading a register + * from an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * + * Same rules as for phy_read(); + */ +int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_read_mmd(phydev, devad, regnum); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} EXPORT_SYMBOL(phy_read_mmd); /** - * phy_write_mmd - Convenience function for writing a register + * __phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. * @phydev: The phy_device struct * @devad: The MMD to read from * @regnum: The register on the MMD to read * @val: value to write to @regnum * - * Same rules as for phy_write(); + * Same rules as for __phy_write(); */ -int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) +int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { int ret; @@ -472,23 +491,43 @@ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) } else if (phydev->is_c45) { u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff); - ret = mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, - addr, val); + ret = __mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, + addr, val); } else { struct mii_bus *bus = phydev->mdio.bus; int phy_addr = phydev->mdio.addr; - mutex_lock(&bus->mdio_lock); mmd_phy_indirect(bus, phy_addr, devad, regnum); /* Write the data into MMD's selected register */ __mdiobus_write(bus, phy_addr, MII_MMD_DATA, val); - mutex_unlock(&bus->mdio_lock); ret = 0; } return ret; } +EXPORT_SYMBOL(__phy_write_mmd); + +/** + * phy_write_mmd - Convenience function for writing a register + * on an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * @val: value to write to @regnum + * + * Same rules as for phy_write(); + */ +int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_write_mmd(phydev, devad, regnum, val); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} EXPORT_SYMBOL(phy_write_mmd); /** @@ -538,6 +577,57 @@ int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) } EXPORT_SYMBOL_GPL(phy_modify); +/** + * __phy_modify_mmd - Convenience function for modifying a register on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * Unlocked helper function which allows a MMD register to be modified as + * new register value = (old register value & ~mask) | set + */ +int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set) +{ + int ret; + + ret = __phy_read_mmd(phydev, devad, regnum); + if (ret < 0) + return ret; + + ret = __phy_write_mmd(phydev, devad, regnum, (ret & ~mask) | set); + + return ret < 0 ? ret : 0; +} +EXPORT_SYMBOL_GPL(__phy_modify_mmd); + +/** + * phy_modify_mmd - Convenience function for modifying a register on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_modify_mmd(phydev, devad, regnum, mask, set); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(phy_modify_mmd); + static int __phy_read_page(struct phy_device *phydev) { return phydev->drv->read_page(phydev); diff --git a/include/linux/phy.h b/include/linux/phy.h index 70f83d0d7469..237dd035858a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -692,17 +692,6 @@ static inline bool phy_is_started(struct phy_device *phydev) void phy_resolve_aneg_linkmode(struct phy_device *phydev); -/** - * phy_read_mmd - Convenience function for reading a register - * from an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to read from - * @regnum: The register on the MMD to read - * - * Same rules as for phy_read(); - */ -int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); - /** * phy_read - Convenience function for reading a given PHY register * @phydev: the phy_device struct @@ -758,9 +747,60 @@ static inline int __phy_write(struct phy_device *phydev, u32 regnum, u16 val) val); } +/** + * phy_read_mmd - Convenience function for reading a register + * from an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * + * Same rules as for phy_read(); + */ +int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); + +/** + * __phy_read_mmd - Convenience function for reading a register + * from an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * + * Same rules as for __phy_read(); + */ +int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); + +/** + * phy_write_mmd - Convenience function for writing a register + * on an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to write to + * @regnum: The register on the MMD to read + * @val: value to write to @regnum + * + * Same rules as for phy_write(); + */ +int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); + +/** + * __phy_write_mmd - Convenience function for writing a register + * on an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to write to + * @regnum: The register on the MMD to read + * @val: value to write to @regnum + * + * Same rules as for __phy_write(); + */ +int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); + int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); +int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set); +int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set); + /** * __phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct @@ -810,6 +850,66 @@ static inline int phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) return phy_modify(phydev, regnum, val, 0); } +/** + * __phy_set_bits_mmd - Convenience function for setting bits in a register + * on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @val: bits to set + * + * The caller must have taken the MDIO bus lock. + */ +static inline int __phy_set_bits_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + return __phy_modify_mmd(phydev, devad, regnum, 0, val); +} + +/** + * __phy_clear_bits_mmd - Convenience function for clearing bits in a register + * on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @val: bits to clear + * + * The caller must have taken the MDIO bus lock. + */ +static inline int __phy_clear_bits_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + return __phy_modify_mmd(phydev, devad, regnum, val, 0); +} + +/** + * phy_set_bits_mmd - Convenience function for setting bits in a register + * on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @val: bits to set + */ +static inline int phy_set_bits_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + return phy_modify_mmd(phydev, devad, regnum, 0, val); +} + +/** + * phy_clear_bits_mmd - Convenience function for clearing bits in a register + * on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @val: bits to clear + */ +static inline int phy_clear_bits_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + return phy_modify_mmd(phydev, devad, regnum, val, 0); +} + /** * phy_interrupt_is_valid - Convenience function for testing a given PHY irq * @phydev: the phy_device struct @@ -886,18 +986,6 @@ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) return phydev->is_pseudo_fixed_link; } -/** - * phy_write_mmd - Convenience function for writing a register - * on an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to read from - * @regnum: The register on the MMD to read - * @val: value to write to @regnum - * - * Same rules as for phy_write(); - */ -int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); - int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); -- cgit v1.2.3 From fd9dc93e36231fb6d520e0edd467058fad4fd12d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 6 Feb 2019 13:07:11 -0500 Subject: XArray: Change xa_insert to return -EBUSY Userspace translates EEXIST to "File exists" which isn't a very good error message for the problem. "Device or resource busy" is a better indication of what went wrong. Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 2 +- fs/nilfs2/btnode.c | 2 +- include/linux/xarray.h | 6 +++--- lib/test_xarray.c | 4 ++-- lib/xarray.c | 4 ++-- 5 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index 5d54b27c6eba..42bb1a62650f 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -85,7 +85,7 @@ which was at that index; if it returns the same entry which was passed as If you want to only store a new entry to an index if the current entry at that index is ``NULL``, you can use :c:func:`xa_insert` which -returns ``-EEXIST`` if the entry is not empty. +returns ``-EBUSY`` if the entry is not empty. You can enquire whether a mark is set on an entry by using :c:func:`xa_get_mark`. If the entry is not ``NULL``, you can set a mark diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index f2129a5d9f23..4391fd3abd8f 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -189,7 +189,7 @@ retry: */ if (!err) return 0; - else if (err != -EEXIST) + else if (err != -EBUSY) goto failed_unlock; err = invalidate_inode_pages2_range(btnc, newkey, newkey); diff --git a/include/linux/xarray.h b/include/linux/xarray.h index e11841537631..57cf35c4d094 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -664,7 +664,7 @@ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. - * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int xa_insert(struct xarray *xa, unsigned long index, @@ -693,7 +693,7 @@ static inline int xa_insert(struct xarray *xa, unsigned long index, * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. - * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int xa_insert_bh(struct xarray *xa, unsigned long index, @@ -722,7 +722,7 @@ static inline int xa_insert_bh(struct xarray *xa, unsigned long index, * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. - * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int xa_insert_irq(struct xarray *xa, unsigned long index, diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 671a93ee09e6..9d894e93456c 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -346,7 +346,7 @@ static noinline void check_cmpxchg(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); XA_BUG_ON(xa, xa_store_index(xa, 12345678, GFP_KERNEL) != NULL); - XA_BUG_ON(xa, xa_insert(xa, 12345678, xa, GFP_KERNEL) != -EEXIST); + XA_BUG_ON(xa, xa_insert(xa, 12345678, xa, GFP_KERNEL) != -EBUSY); XA_BUG_ON(xa, xa_cmpxchg(xa, 12345678, SIX, FIVE, GFP_KERNEL) != LOTS); XA_BUG_ON(xa, xa_cmpxchg(xa, 12345678, LOTS, FIVE, GFP_KERNEL) != LOTS); XA_BUG_ON(xa, xa_cmpxchg(xa, 12345678, FIVE, LOTS, GFP_KERNEL) != FIVE); @@ -388,7 +388,7 @@ static noinline void check_reserve(struct xarray *xa) /* But xa_insert does not */ xa_reserve(xa, 12345678, GFP_KERNEL); XA_BUG_ON(xa, xa_insert(xa, 12345678, xa_mk_value(12345678), 0) != - -EEXIST); + -EBUSY); XA_BUG_ON(xa, xa_empty(xa)); XA_BUG_ON(xa, xa_erase(xa, 12345678) != NULL); XA_BUG_ON(xa, !xa_empty(xa)); diff --git a/lib/xarray.c b/lib/xarray.c index fb783bf2a441..1b97ca58bd15 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1451,7 +1451,7 @@ EXPORT_SYMBOL(__xa_cmpxchg); * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. - * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) @@ -1471,7 +1471,7 @@ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } else { - xas_set_err(&xas, -EEXIST); + xas_set_err(&xas, -EBUSY); } } while (__xas_nomem(&xas, gfp)); -- cgit v1.2.3 From 3ccaf57a6a63ad171a951dcaddffc453b2414c7b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 14:43:22 -0400 Subject: XArray: Add support for 1s-based allocation A lot of places want to allocate IDs starting at 1 instead of 0. While the xa_alloc() API supports this, it's not very efficient if lots of IDs are allocated, due to having to walk down to the bottom of the tree to see if ID 1 is available, then all the way over to the next non-allocated ID. This method marks ID 0 as being occupied which wastes one slot in the XArray, but preserves xa_empty() as working. Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 10 +++-- include/linux/xarray.h | 14 ++++++- lib/test_xarray.c | 88 ++++++++++++++++++++++++--------------- lib/xarray.c | 11 +++++ 4 files changed, 86 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index 42bb1a62650f..e90c4925cd37 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -131,17 +131,21 @@ If you use :c:func:`DEFINE_XARRAY_ALLOC` to define the XArray, or initialise it by passing ``XA_FLAGS_ALLOC`` to :c:func:`xa_init_flags`, the XArray changes to track whether entries are in use or not. -You can call :c:func:`xa_alloc` to store the entry at any unused index +You can call :c:func:`xa_alloc` to store the entry at an unused index in the XArray. If you need to modify the array from interrupt context, you can use :c:func:`xa_alloc_bh` or :c:func:`xa_alloc_irq` to disable interrupts while allocating the ID. -Using :c:func:`xa_store`, :c:func:`xa_cmpxchg` or :c:func:`xa_insert` -will mark the entry as being allocated. Unlike a normal XArray, storing +Using :c:func:`xa_store`, :c:func:`xa_cmpxchg` or :c:func:`xa_insert` will +also mark the entry as being allocated. Unlike a normal XArray, storing ``NULL`` will mark the entry as being in use, like :c:func:`xa_reserve`. To free an entry, use :c:func:`xa_erase` (or :c:func:`xa_release` if you only want to free the entry if it's ``NULL``). +By default, the lowest free entry is allocated starting from 0. If you +want to allocate entries starting at 1, it is more efficient to use +:c:func:`DEFINE_XARRAY_ALLOC1` or ``XA_FLAGS_ALLOC1``. + You cannot use ``XA_MARK_0`` with an allocating XArray as this mark is used to track whether an entry is free or not. The other marks are available for your use. diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 57cf35c4d094..99dd0838b4ba 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -220,10 +220,13 @@ enum xa_lock_type { #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) +#define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) +/* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */ #define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) +#define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY) /** * struct xarray - The anchor of the XArray. @@ -279,7 +282,7 @@ struct xarray { #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) /** - * DEFINE_XARRAY_ALLOC() - Define an XArray which can allocate IDs. + * DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. @@ -287,6 +290,15 @@ struct xarray { */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) +/** + * DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1. + * @name: A string that names your XArray. + * + * This is intended for file scope definitions of allocating XArrays. + * See also DEFINE_XARRAY(). + */ +#define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1) + void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 9d894e93456c..cd74f8f32abe 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -589,64 +589,86 @@ static noinline void check_multi_store(struct xarray *xa) #endif } -static DEFINE_XARRAY_ALLOC(xa0); - -static noinline void check_xa_alloc(void) +static noinline void check_xa_alloc_1(struct xarray *xa, unsigned int base) { int i; u32 id; - /* An empty array should assign 0 to the first alloc */ - xa_alloc_index(&xa0, 0, GFP_KERNEL); + XA_BUG_ON(xa, !xa_empty(xa)); + /* An empty array should assign %base to the first alloc */ + xa_alloc_index(xa, base, GFP_KERNEL); /* Erasing it should make the array empty again */ - xa_erase_index(&xa0, 0); - XA_BUG_ON(&xa0, !xa_empty(&xa0)); + xa_erase_index(xa, base); + XA_BUG_ON(xa, !xa_empty(xa)); + + /* And it should assign %base again */ + xa_alloc_index(xa, base, GFP_KERNEL); + + /* Allocating and then erasing a lot should not lose base */ + for (i = base + 1; i < 2 * XA_CHUNK_SIZE; i++) + xa_alloc_index(xa, i, GFP_KERNEL); + for (i = base; i < 2 * XA_CHUNK_SIZE; i++) + xa_erase_index(xa, i); + xa_alloc_index(xa, base, GFP_KERNEL); + + /* Destroying the array should do the same as erasing */ + xa_destroy(xa); - /* And it should assign 0 again */ - xa_alloc_index(&xa0, 0, GFP_KERNEL); + /* And it should assign %base again */ + xa_alloc_index(xa, base, GFP_KERNEL); - /* The next assigned ID should be 1 */ - xa_alloc_index(&xa0, 1, GFP_KERNEL); - xa_erase_index(&xa0, 1); + /* The next assigned ID should be base+1 */ + xa_alloc_index(xa, base + 1, GFP_KERNEL); + xa_erase_index(xa, base + 1); /* Storing a value should mark it used */ - xa_store_index(&xa0, 1, GFP_KERNEL); - xa_alloc_index(&xa0, 2, GFP_KERNEL); + xa_store_index(xa, base + 1, GFP_KERNEL); + xa_alloc_index(xa, base + 2, GFP_KERNEL); - /* If we then erase 0, it should be free */ - xa_erase_index(&xa0, 0); - xa_alloc_index(&xa0, 0, GFP_KERNEL); + /* If we then erase base, it should be free */ + xa_erase_index(xa, base); + xa_alloc_index(xa, base, GFP_KERNEL); - xa_erase_index(&xa0, 1); - xa_erase_index(&xa0, 2); + xa_erase_index(xa, base + 1); + xa_erase_index(xa, base + 2); for (i = 1; i < 5000; i++) { - xa_alloc_index(&xa0, i, GFP_KERNEL); + xa_alloc_index(xa, base + i, GFP_KERNEL); } - xa_destroy(&xa0); + xa_destroy(xa); + /* Check that we fail properly at the limit of allocation */ id = 0xfffffffeU; - XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_index(id), + XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_index(id), GFP_KERNEL) != 0); - XA_BUG_ON(&xa0, id != 0xfffffffeU); - XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_index(id), + XA_BUG_ON(xa, id != 0xfffffffeU); + XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_index(id), GFP_KERNEL) != 0); - XA_BUG_ON(&xa0, id != 0xffffffffU); - XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_index(id), + XA_BUG_ON(xa, id != 0xffffffffU); + XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_index(id), GFP_KERNEL) != -ENOSPC); - XA_BUG_ON(&xa0, id != 0xffffffffU); - xa_destroy(&xa0); + XA_BUG_ON(xa, id != 0xffffffffU); + xa_destroy(xa); id = 10; - XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, 5, xa_mk_index(id), + XA_BUG_ON(xa, xa_alloc(xa, &id, 5, xa_mk_index(id), GFP_KERNEL) != -ENOSPC); - XA_BUG_ON(&xa0, xa_store_index(&xa0, 3, GFP_KERNEL) != 0); - XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, 5, xa_mk_index(id), + XA_BUG_ON(xa, xa_store_index(xa, 3, GFP_KERNEL) != 0); + XA_BUG_ON(xa, xa_alloc(xa, &id, 5, xa_mk_index(id), GFP_KERNEL) != -ENOSPC); - xa_erase_index(&xa0, 3); - XA_BUG_ON(&xa0, !xa_empty(&xa0)); + xa_erase_index(xa, 3); + XA_BUG_ON(xa, !xa_empty(xa)); +} + +static DEFINE_XARRAY_ALLOC(xa0); +static DEFINE_XARRAY_ALLOC1(xa1); + +static noinline void check_xa_alloc(void) +{ + check_xa_alloc_1(&xa0, 0); + check_xa_alloc_1(&xa1, 1); } static noinline void __check_store_iter(struct xarray *xa, unsigned long start, diff --git a/lib/xarray.c b/lib/xarray.c index 1b97ca58bd15..468fb7b7963f 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -57,6 +57,11 @@ static inline bool xa_track_free(const struct xarray *xa) return xa->xa_flags & XA_FLAGS_TRACK_FREE; } +static inline bool xa_zero_busy(const struct xarray *xa) +{ + return xa->xa_flags & XA_FLAGS_ZERO_BUSY; +} + static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) @@ -432,6 +437,8 @@ static void xas_shrink(struct xa_state *xas) break; if (!xa_is_node(entry) && node->shift) break; + if (xa_is_zero(entry) && xa_zero_busy(xa)) + entry = NULL; xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); @@ -628,6 +635,8 @@ static void *xas_create(struct xa_state *xas, bool allow_root) if (xas_top(node)) { entry = xa_head_locked(xa); xas->xa_node = NULL; + if (!entry && xa_zero_busy(xa)) + entry = XA_ZERO_ENTRY; shift = xas_expand(xas, entry); if (shift < 0) return NULL; @@ -1942,6 +1951,8 @@ void xa_destroy(struct xarray *xa) entry = xa_head_locked(xa); RCU_INIT_POINTER(xa->xa_head, NULL); xas_init_marks(&xas); + if (xa_zero_busy(xa)) + xa_mark_clear(xa, XA_FREE_MARK); /* lockdep checks we're still holding the lock in xas_free_nodes() */ if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry)); -- cgit v1.2.3 From a3e4d3f97ec844de005a679585c04c5c03dfbdb6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 31 Dec 2018 10:41:01 -0500 Subject: XArray: Redesign xa_alloc API It was too easy to forget to initialise the start index. Add an xa_limit data structure which can be used to pass min & max, and define a couple of special values for common cases. Also add some more tests cribbed from the IDR test suite. Change the return value from -ENOSPC to -EBUSY to match xa_insert(). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 80 +++++++++++++++++++++++++++++----------------- lib/test_xarray.c | 86 ++++++++++++++++++++++++++++++++++++++++---------- lib/xarray.c | 29 ++++++++--------- 3 files changed, 135 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 99dd0838b4ba..883bb958e462 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -200,6 +200,27 @@ static inline int xa_err(void *entry) return 0; } +/** + * struct xa_limit - Represents a range of IDs. + * @min: The lowest ID to allocate (inclusive). + * @max: The maximum ID to allocate (inclusive). + * + * This structure is used either directly or via the XA_LIMIT() macro + * to communicate the range of IDs that are valid for allocation. + * Two common ranges are predefined for you: + * * xa_limit_32b - [0 - UINT_MAX] + * * xa_limit_31b - [0 - INT_MAX] + */ +struct xa_limit { + u32 max; + u32 min; +}; + +#define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max } + +#define xa_limit_32b XA_LIMIT(0, UINT_MAX) +#define xa_limit_31b XA_LIMIT(0, INT_MAX) + typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) #define XA_MARK_1 ((__force xa_mark_t)1U) @@ -476,7 +497,8 @@ void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); -int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t); +int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, + struct xa_limit, gfp_t); int __xa_reserve(struct xarray *, unsigned long index, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -753,26 +775,26 @@ static inline int xa_insert_irq(struct xarray *xa, unsigned long index, * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. - * @max: Maximum ID to allocate (inclusive). * @entry: New entry. + * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * - * Allocates an unused ID in the range specified by @id and @max. - * Updates the @id pointer with the index, then stores the entry at that - * index. A concurrent lookup will not see an uninitialised @id. + * Finds an empty entry in @xa between @limit.min and @limit.max, + * stores the index into the @id pointer, then stores the entry at + * that index. A concurrent lookup will not see an uninitialised @id. * - * Context: Process context. Takes and releases the xa_lock. May sleep if + * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. - * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if - * there is no more space in the XArray. + * Return: 0 on success, -ENOMEM if memory could not be allocated or + * -EBUSY if there are no free entries in @limit. */ -static inline int xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, - gfp_t gfp) +static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, + void *entry, struct xa_limit limit, gfp_t gfp) { int err; xa_lock(xa); - err = __xa_alloc(xa, id, max, entry, gfp); + err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); return err; @@ -782,26 +804,26 @@ static inline int xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, * xa_alloc_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. - * @max: Maximum ID to allocate (inclusive). * @entry: New entry. + * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * - * Allocates an unused ID in the range specified by @id and @max. - * Updates the @id pointer with the index, then stores the entry at that - * index. A concurrent lookup will not see an uninitialised @id. + * Finds an empty entry in @xa between @limit.min and @limit.max, + * stores the index into the @id pointer, then stores the entry at + * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. - * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if - * there is no more space in the XArray. + * Return: 0 on success, -ENOMEM if memory could not be allocated or + * -EBUSY if there are no free entries in @limit. */ -static inline int xa_alloc_bh(struct xarray *xa, u32 *id, u32 max, void *entry, - gfp_t gfp) +static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, + void *entry, struct xa_limit limit, gfp_t gfp) { int err; xa_lock_bh(xa); - err = __xa_alloc(xa, id, max, entry, gfp); + err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); return err; @@ -811,26 +833,26 @@ static inline int xa_alloc_bh(struct xarray *xa, u32 *id, u32 max, void *entry, * xa_alloc_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. - * @max: Maximum ID to allocate (inclusive). * @entry: New entry. + * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * - * Allocates an unused ID in the range specified by @id and @max. - * Updates the @id pointer with the index, then stores the entry at that - * index. A concurrent lookup will not see an uninitialised @id. + * Finds an empty entry in @xa between @limit.min and @limit.max, + * stores the index into the @id pointer, then stores the entry at + * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. - * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if - * there is no more space in the XArray. + * Return: 0 on success, -ENOMEM if memory could not be allocated or + * -EBUSY if there are no free entries in @limit. */ -static inline int xa_alloc_irq(struct xarray *xa, u32 *id, u32 max, void *entry, - gfp_t gfp) +static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, + void *entry, struct xa_limit limit, gfp_t gfp) { int err; xa_lock_irq(xa); - err = __xa_alloc(xa, id, max, entry, gfp); + err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); return err; diff --git a/lib/test_xarray.c b/lib/test_xarray.c index cd74f8f32abe..b5a6b981454d 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -40,9 +40,9 @@ static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp) static void xa_alloc_index(struct xarray *xa, unsigned long index, gfp_t gfp) { - u32 id = 0; + u32 id; - XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_index(index), + XA_BUG_ON(xa, xa_alloc(xa, &id, xa_mk_index(index), xa_limit_32b, gfp) != 0); XA_BUG_ON(xa, id != index); } @@ -640,28 +640,81 @@ static noinline void check_xa_alloc_1(struct xarray *xa, unsigned int base) xa_destroy(xa); /* Check that we fail properly at the limit of allocation */ - id = 0xfffffffeU; - XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_index(id), + XA_BUG_ON(xa, xa_alloc(xa, &id, xa_mk_index(UINT_MAX - 1), + XA_LIMIT(UINT_MAX - 1, UINT_MAX), GFP_KERNEL) != 0); XA_BUG_ON(xa, id != 0xfffffffeU); - XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_index(id), + XA_BUG_ON(xa, xa_alloc(xa, &id, xa_mk_index(UINT_MAX), + XA_LIMIT(UINT_MAX - 1, UINT_MAX), GFP_KERNEL) != 0); XA_BUG_ON(xa, id != 0xffffffffU); - XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_index(id), - GFP_KERNEL) != -ENOSPC); - XA_BUG_ON(xa, id != 0xffffffffU); + id = 3; + XA_BUG_ON(xa, xa_alloc(xa, &id, xa_mk_index(0), + XA_LIMIT(UINT_MAX - 1, UINT_MAX), + GFP_KERNEL) != -EBUSY); + XA_BUG_ON(xa, id != 3); xa_destroy(xa); - id = 10; - XA_BUG_ON(xa, xa_alloc(xa, &id, 5, xa_mk_index(id), - GFP_KERNEL) != -ENOSPC); + XA_BUG_ON(xa, xa_alloc(xa, &id, xa_mk_index(10), XA_LIMIT(10, 5), + GFP_KERNEL) != -EBUSY); XA_BUG_ON(xa, xa_store_index(xa, 3, GFP_KERNEL) != 0); - XA_BUG_ON(xa, xa_alloc(xa, &id, 5, xa_mk_index(id), - GFP_KERNEL) != -ENOSPC); + XA_BUG_ON(xa, xa_alloc(xa, &id, xa_mk_index(10), XA_LIMIT(10, 5), + GFP_KERNEL) != -EBUSY); xa_erase_index(xa, 3); XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_xa_alloc_2(struct xarray *xa, unsigned int base) +{ + unsigned int i, id; + unsigned long index; + void *entry; + + /* Allocate and free a NULL and check xa_empty() behaves */ + XA_BUG_ON(xa, !xa_empty(xa)); + XA_BUG_ON(xa, xa_alloc(xa, &id, NULL, xa_limit_32b, GFP_KERNEL) != 0); + XA_BUG_ON(xa, id != base); + XA_BUG_ON(xa, xa_empty(xa)); + XA_BUG_ON(xa, xa_erase(xa, id) != NULL); + XA_BUG_ON(xa, !xa_empty(xa)); + + /* Ditto, but check destroy instead of erase */ + XA_BUG_ON(xa, !xa_empty(xa)); + XA_BUG_ON(xa, xa_alloc(xa, &id, NULL, xa_limit_32b, GFP_KERNEL) != 0); + XA_BUG_ON(xa, id != base); + XA_BUG_ON(xa, xa_empty(xa)); + xa_destroy(xa); + XA_BUG_ON(xa, !xa_empty(xa)); + + for (i = base; i < base + 10; i++) { + XA_BUG_ON(xa, xa_alloc(xa, &id, NULL, xa_limit_32b, + GFP_KERNEL) != 0); + XA_BUG_ON(xa, id != i); + } + + XA_BUG_ON(xa, xa_store(xa, 3, xa_mk_index(3), GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_store(xa, 4, xa_mk_index(4), GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_store(xa, 4, NULL, GFP_KERNEL) != xa_mk_index(4)); + XA_BUG_ON(xa, xa_erase(xa, 5) != NULL); + XA_BUG_ON(xa, xa_alloc(xa, &id, NULL, xa_limit_32b, GFP_KERNEL) != 0); + XA_BUG_ON(xa, id != 5); + + xa_for_each(xa, index, entry) { + xa_erase_index(xa, index); + } + + for (i = base; i < base + 9; i++) { + XA_BUG_ON(xa, xa_erase(xa, i) != NULL); + XA_BUG_ON(xa, xa_empty(xa)); + } + XA_BUG_ON(xa, xa_erase(xa, 8) != NULL); + XA_BUG_ON(xa, xa_empty(xa)); + XA_BUG_ON(xa, xa_erase(xa, base + 9) != NULL); + XA_BUG_ON(xa, !xa_empty(xa)); + + xa_destroy(xa); +} + static DEFINE_XARRAY_ALLOC(xa0); static DEFINE_XARRAY_ALLOC1(xa1); @@ -669,6 +722,8 @@ static noinline void check_xa_alloc(void) { check_xa_alloc_1(&xa0, 0); check_xa_alloc_1(&xa1, 1); + check_xa_alloc_2(&xa0, 0); + check_xa_alloc_2(&xa1, 1); } static noinline void __check_store_iter(struct xarray *xa, unsigned long start, @@ -1219,9 +1274,8 @@ static void check_align_1(struct xarray *xa, char *name) void *entry; for (i = 0; i < 8; i++) { - id = 0; - XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, name + i, GFP_KERNEL) - != 0); + XA_BUG_ON(xa, xa_alloc(xa, &id, name + i, xa_limit_32b, + GFP_KERNEL) != 0); XA_BUG_ON(xa, id != i); } xa_for_each(xa, index, entry) diff --git a/lib/xarray.c b/lib/xarray.c index 468fb7b7963f..c707388fb05e 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1615,23 +1615,23 @@ EXPORT_SYMBOL(xa_store_range); * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. - * @max: Maximum ID to allocate (inclusive). + * @limit: Range for allocated ID. * @entry: New entry. * @gfp: Memory allocation flags. * - * Allocates an unused ID in the range specified by @id and @max. - * Updates the @id pointer with the index, then stores the entry at that - * index. A concurrent lookup will not see an uninitialised @id. + * Finds an empty entry in @xa between @limit.min and @limit.max, + * stores the index into the @id pointer, then stores the entry at + * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. - * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if - * there is no more space in the XArray. + * Return: 0 on success, -ENOMEM if memory could not be allocated or + * -EBUSY if there are no free entries in @limit. */ -int __xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, gfp_t gfp) +int __xa_alloc(struct xarray *xa, u32 *id, void *entry, + struct xa_limit limit, gfp_t gfp) { XA_STATE(xas, xa, 0); - int err; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; @@ -1642,18 +1642,17 @@ int __xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, gfp_t gfp) entry = XA_ZERO_ENTRY; do { - xas.xa_index = *id; - xas_find_marked(&xas, max, XA_FREE_MARK); + xas.xa_index = limit.min; + xas_find_marked(&xas, limit.max, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) - xas_set_err(&xas, -ENOSPC); + xas_set_err(&xas, -EBUSY); + else + *id = xas.xa_index; xas_store(&xas, entry); xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); - err = xas_error(&xas); - if (!err) - *id = xas.xa_index; - return err; + return xas_error(&xas); } EXPORT_SYMBOL(__xa_alloc); -- cgit v1.2.3 From 2fa044e51a1f35d7b04cbde07ec513b0ba195e38 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 6 Nov 2018 14:13:35 -0500 Subject: XArray: Add cyclic allocation This differs slightly from the IDR equivalent in five ways. 1. It can allocate up to UINT_MAX instead of being limited to INT_MAX, like xa_alloc(). Also like xa_alloc(), it will write to the 'id' pointer before placing the entry in the XArray. 2. The 'next' cursor is allocated separately from the XArray instead of being part of the IDR. This saves memory for all the users which do not use the cyclic allocation API and suits some users better. 3. It returns -EBUSY instead of -ENOSPC. 4. It will attempt to wrap back to the minimum value on memory allocation failure as well as on an -EBUSY error, assuming that a user would rather allocate a small ID than suffer an ID allocation failure. 5. It reports whether it has wrapped, which is important to some users. Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 4 +- include/linux/xarray.h | 102 ++++++++++++++++++++++++++++++++++++++ lib/test_xarray.c | 53 ++++++++++++++++++++ lib/xarray.c | 50 +++++++++++++++++++ 4 files changed, 208 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index e90c4925cd37..c7436da5c4ad 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -144,7 +144,9 @@ you only want to free the entry if it's ``NULL``). By default, the lowest free entry is allocated starting from 0. If you want to allocate entries starting at 1, it is more efficient to use -:c:func:`DEFINE_XARRAY_ALLOC1` or ``XA_FLAGS_ALLOC1``. +:c:func:`DEFINE_XARRAY_ALLOC1` or ``XA_FLAGS_ALLOC1``. If you want to +allocate IDs up to a maximum, then wrap back around to the lowest free +ID, you can use :c:func:`xa_alloc_cyclic`. You cannot use ``XA_MARK_0`` with an allocating XArray as this mark is used to track whether an entry is free or not. The other marks are diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 883bb958e462..5ed6b462e754 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -242,6 +242,7 @@ enum xa_lock_type { #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) +#define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) @@ -499,6 +500,8 @@ void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, int __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, struct xa_limit, gfp_t); +int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry, + struct xa_limit, u32 *next, gfp_t); int __xa_reserve(struct xarray *, unsigned long index, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -858,6 +861,105 @@ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, return err; } +/** + * xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @entry: New entry. + * @limit: Range of allocated ID. + * @next: Pointer to next ID to allocate. + * @gfp: Memory allocation flags. + * + * Finds an empty entry in @xa between @limit.min and @limit.max, + * stores the index into the @id pointer, then stores the entry at + * that index. A concurrent lookup will not see an uninitialised @id. + * The search for an empty entry will start at @next and will wrap + * around if necessary. + * + * Context: Any context. Takes and releases the xa_lock. May sleep if + * the @gfp flags permit. + * Return: 0 if the allocation succeeded without wrapping. 1 if the + * allocation succeeded after wrapping, -ENOMEM if memory could not be + * allocated or -EBUSY if there are no free entries in @limit. + */ +static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, + struct xa_limit limit, u32 *next, gfp_t gfp) +{ + int err; + + xa_lock(xa); + err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); + xa_unlock(xa); + + return err; +} + +/** + * xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @entry: New entry. + * @limit: Range of allocated ID. + * @next: Pointer to next ID to allocate. + * @gfp: Memory allocation flags. + * + * Finds an empty entry in @xa between @limit.min and @limit.max, + * stores the index into the @id pointer, then stores the entry at + * that index. A concurrent lookup will not see an uninitialised @id. + * The search for an empty entry will start at @next and will wrap + * around if necessary. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: 0 if the allocation succeeded without wrapping. 1 if the + * allocation succeeded after wrapping, -ENOMEM if memory could not be + * allocated or -EBUSY if there are no free entries in @limit. + */ +static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, + struct xa_limit limit, u32 *next, gfp_t gfp) +{ + int err; + + xa_lock_bh(xa); + err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); + xa_unlock_bh(xa); + + return err; +} + +/** + * xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @entry: New entry. + * @limit: Range of allocated ID. + * @next: Pointer to next ID to allocate. + * @gfp: Memory allocation flags. + * + * Finds an empty entry in @xa between @limit.min and @limit.max, + * stores the index into the @id pointer, then stores the entry at + * that index. A concurrent lookup will not see an uninitialised @id. + * The search for an empty entry will start at @next and will wrap + * around if necessary. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: 0 if the allocation succeeded without wrapping. 1 if the + * allocation succeeded after wrapping, -ENOMEM if memory could not be + * allocated or -EBUSY if there are no free entries in @limit. + */ +static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, + struct xa_limit limit, u32 *next, gfp_t gfp) +{ + int err; + + xa_lock_irq(xa); + err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); + xa_unlock_irq(xa); + + return err; +} + /** * xa_reserve() - Reserve this index in the XArray. * @xa: XArray. diff --git a/lib/test_xarray.c b/lib/test_xarray.c index b5a6b981454d..eaf53f742c72 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -715,6 +715,57 @@ static noinline void check_xa_alloc_2(struct xarray *xa, unsigned int base) xa_destroy(xa); } +static noinline void check_xa_alloc_3(struct xarray *xa, unsigned int base) +{ + struct xa_limit limit = XA_LIMIT(1, 0x3fff); + u32 next = 0; + unsigned int i, id; + unsigned long index; + void *entry; + + XA_BUG_ON(xa, xa_alloc_cyclic(xa, &id, xa_mk_index(1), limit, + &next, GFP_KERNEL) != 0); + XA_BUG_ON(xa, id != 1); + + next = 0x3ffd; + XA_BUG_ON(xa, xa_alloc_cyclic(xa, &id, xa_mk_index(0x3ffd), limit, + &next, GFP_KERNEL) != 0); + XA_BUG_ON(xa, id != 0x3ffd); + xa_erase_index(xa, 0x3ffd); + xa_erase_index(xa, 1); + XA_BUG_ON(xa, !xa_empty(xa)); + + for (i = 0x3ffe; i < 0x4003; i++) { + if (i < 0x4000) + entry = xa_mk_index(i); + else + entry = xa_mk_index(i - 0x3fff); + XA_BUG_ON(xa, xa_alloc_cyclic(xa, &id, entry, limit, + &next, GFP_KERNEL) != (id == 1)); + XA_BUG_ON(xa, xa_mk_index(id) != entry); + } + + /* Check wrap-around is handled correctly */ + if (base != 0) + xa_erase_index(xa, base); + xa_erase_index(xa, base + 1); + next = UINT_MAX; + XA_BUG_ON(xa, xa_alloc_cyclic(xa, &id, xa_mk_index(UINT_MAX), + xa_limit_32b, &next, GFP_KERNEL) != 0); + XA_BUG_ON(xa, id != UINT_MAX); + XA_BUG_ON(xa, xa_alloc_cyclic(xa, &id, xa_mk_index(base), + xa_limit_32b, &next, GFP_KERNEL) != 1); + XA_BUG_ON(xa, id != base); + XA_BUG_ON(xa, xa_alloc_cyclic(xa, &id, xa_mk_index(base + 1), + xa_limit_32b, &next, GFP_KERNEL) != 0); + XA_BUG_ON(xa, id != base + 1); + + xa_for_each(xa, index, entry) + xa_erase_index(xa, index); + + XA_BUG_ON(xa, !xa_empty(xa)); +} + static DEFINE_XARRAY_ALLOC(xa0); static DEFINE_XARRAY_ALLOC1(xa1); @@ -724,6 +775,8 @@ static noinline void check_xa_alloc(void) check_xa_alloc_1(&xa1, 1); check_xa_alloc_2(&xa0, 0); check_xa_alloc_2(&xa1, 1); + check_xa_alloc_3(&xa0, 0); + check_xa_alloc_3(&xa1, 1); } static noinline void __check_store_iter(struct xarray *xa, unsigned long start, diff --git a/lib/xarray.c b/lib/xarray.c index c707388fb05e..89e37ac50850 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1656,6 +1656,56 @@ int __xa_alloc(struct xarray *xa, u32 *id, void *entry, } EXPORT_SYMBOL(__xa_alloc); +/** + * __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @entry: New entry. + * @limit: Range of allocated ID. + * @next: Pointer to next ID to allocate. + * @gfp: Memory allocation flags. + * + * Finds an empty entry in @xa between @limit.min and @limit.max, + * stores the index into the @id pointer, then stores the entry at + * that index. A concurrent lookup will not see an uninitialised @id. + * The search for an empty entry will start at @next and will wrap + * around if necessary. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if @gfp flags permit. + * Return: 0 if the allocation succeeded without wrapping. 1 if the + * allocation succeeded after wrapping, -ENOMEM if memory could not be + * allocated or -EBUSY if there are no free entries in @limit. + */ +int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, + struct xa_limit limit, u32 *next, gfp_t gfp) +{ + u32 min = limit.min; + int ret; + + limit.min = max(min, *next); + ret = __xa_alloc(xa, id, entry, limit, gfp); + if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) { + xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED; + ret = 1; + } + + if (ret < 0 && limit.min > min) { + limit.min = min; + ret = __xa_alloc(xa, id, entry, limit, gfp); + if (ret == 0) + ret = 1; + } + + if (ret >= 0) { + *next = *id + 1; + if (*next == 0) + xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED; + } + return ret; +} +EXPORT_SYMBOL(__xa_alloc_cyclic); + /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. -- cgit v1.2.3 From 60b8f0ddf1a927ef02141a6610fd52575134f821 Mon Sep 17 00:00:00 2001 From: Phil Edworthy Date: Mon, 3 Dec 2018 11:13:09 +0000 Subject: clk: Add (devm_)clk_get_optional() functions This adds clk_get_optional() and devm_clk_get_optional() functions to get optional clocks. They behave the same as (devm_)clk_get() except where there is no clock producer. In this case, instead of returning -ENOENT, the function returns NULL. This makes error checking simpler and allows clk_prepare_enable, etc to be called on the returned reference without additional checks. Signed-off-by: Phil Edworthy Reviewed-by: Andy Shevchenko Cc: Russell King [sboyd@kernel.org: Document in devres.txt] Signed-off-by: Stephen Boyd --- Documentation/driver-model/devres.txt | 1 + drivers/clk/clk-devres.c | 11 +++++++++++ include/linux/clk.h | 36 +++++++++++++++++++++++++++++++++++ 3 files changed, 48 insertions(+) (limited to 'include') diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt index b277cafce71e..83f38c0439cd 100644 --- a/Documentation/driver-model/devres.txt +++ b/Documentation/driver-model/devres.txt @@ -242,6 +242,7 @@ certainly invest a bit more effort into libata core layer). CLOCK devm_clk_get() + devm_clk_get_optional() devm_clk_put() devm_clk_hw_register() devm_of_clk_add_hw_provider() diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index c9a86156ced8..daa1fc8fba53 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -29,6 +29,17 @@ struct clk *devm_clk_get(struct device *dev, const char *id) } EXPORT_SYMBOL(devm_clk_get); +struct clk *devm_clk_get_optional(struct device *dev, const char *id) +{ + struct clk *clk = devm_clk_get(dev, id); + + if (clk == ERR_PTR(-ENOENT)) + return NULL; + + return clk; +} +EXPORT_SYMBOL(devm_clk_get_optional); + struct clk_bulk_devres { struct clk_bulk_data *clks; int num_clks; diff --git a/include/linux/clk.h b/include/linux/clk.h index a7773b5c0b9f..d8bc1a856b39 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -383,6 +383,17 @@ int __must_check devm_clk_bulk_get_all(struct device *dev, */ struct clk *devm_clk_get(struct device *dev, const char *id); +/** + * devm_clk_get_optional - lookup and obtain a managed reference to an optional + * clock producer. + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Behaves the same as devm_clk_get() except where there is no clock producer. + * In this case, instead of returning -ENOENT, the function returns NULL. + */ +struct clk *devm_clk_get_optional(struct device *dev, const char *id); + /** * devm_get_clk_from_child - lookup and obtain a managed reference to a * clock producer from child node. @@ -718,6 +729,12 @@ static inline struct clk *devm_clk_get(struct device *dev, const char *id) return NULL; } +static inline struct clk *devm_clk_get_optional(struct device *dev, + const char *id) +{ + return NULL; +} + static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks) { @@ -862,6 +879,25 @@ static inline void clk_bulk_disable_unprepare(int num_clks, clk_bulk_unprepare(num_clks, clks); } +/** + * clk_get_optional - lookup and obtain a reference to an optional clock + * producer. + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Behaves the same as clk_get() except where there is no clock producer. In + * this case, instead of returning -ENOENT, the function returns NULL. + */ +static inline struct clk *clk_get_optional(struct device *dev, const char *id) +{ + struct clk *clk = clk_get(dev, id); + + if (clk == ERR_PTR(-ENOENT)) + return NULL; + + return clk; +} + #if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK) struct clk *of_clk_get(struct device_node *np, int index); struct clk *of_clk_get_by_name(struct device_node *np, const char *name); -- cgit v1.2.3 From 3eee6c7d119cd8563ad25898f94d6c1b514da548 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 7 Dec 2018 13:09:39 +0200 Subject: clkdev: add managed clkdev lookup registration Clkdev registration lacks of managed registration functions and it seems few drivers do not drop clkdev lookups at exit. Add devm_clk_hw_register_clkdev and devm_clk_release_clkdev to ease lookup releasing at exit. Signed-off-by: Matti Vaittinen Signed-off-by: Stephen Boyd --- Documentation/driver-model/devres.txt | 1 + drivers/clk/clkdev.c | 111 +++++++++++++++++++++++++++------- include/linux/clkdev.h | 4 ++ 3 files changed, 93 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt index b277cafce71e..805b7bf5d98f 100644 --- a/Documentation/driver-model/devres.txt +++ b/Documentation/driver-model/devres.txt @@ -245,6 +245,7 @@ CLOCK devm_clk_put() devm_clk_hw_register() devm_of_clk_add_hw_provider() + devm_clk_hw_register_clkdev() DMA dmaenginem_async_device_register() diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c index 9ab3db8b3988..4621f8a91fc0 100644 --- a/drivers/clk/clkdev.c +++ b/drivers/clk/clkdev.c @@ -401,6 +401,23 @@ static struct clk_lookup *__clk_register_clkdev(struct clk_hw *hw, return cl; } +static int do_clk_register_clkdev(struct clk_hw *hw, + struct clk_lookup **cl, const char *con_id, const char *dev_id) +{ + if (IS_ERR(hw)) + return PTR_ERR(hw); + /* + * Since dev_id can be NULL, and NULL is handled specially, we must + * pass it as either a NULL format string, or with "%s". + */ + if (dev_id) + *cl = __clk_register_clkdev(hw, con_id, "%s", dev_id); + else + *cl = __clk_register_clkdev(hw, con_id, NULL); + + return *cl ? 0 : -ENOMEM; +} + /** * clk_register_clkdev - register one clock lookup for a struct clk * @clk: struct clk to associate with all clk_lookups @@ -423,17 +440,8 @@ int clk_register_clkdev(struct clk *clk, const char *con_id, if (IS_ERR(clk)) return PTR_ERR(clk); - /* - * Since dev_id can be NULL, and NULL is handled specially, we must - * pass it as either a NULL format string, or with "%s". - */ - if (dev_id) - cl = __clk_register_clkdev(__clk_get_hw(clk), con_id, "%s", - dev_id); - else - cl = __clk_register_clkdev(__clk_get_hw(clk), con_id, NULL); - - return cl ? 0 : -ENOMEM; + return do_clk_register_clkdev(__clk_get_hw(clk), &cl, con_id, + dev_id); } EXPORT_SYMBOL(clk_register_clkdev); @@ -456,18 +464,75 @@ int clk_hw_register_clkdev(struct clk_hw *hw, const char *con_id, { struct clk_lookup *cl; - if (IS_ERR(hw)) - return PTR_ERR(hw); + return do_clk_register_clkdev(hw, &cl, con_id, dev_id); +} +EXPORT_SYMBOL(clk_hw_register_clkdev); - /* - * Since dev_id can be NULL, and NULL is handled specially, we must - * pass it as either a NULL format string, or with "%s". - */ - if (dev_id) - cl = __clk_register_clkdev(hw, con_id, "%s", dev_id); - else - cl = __clk_register_clkdev(hw, con_id, NULL); +static void devm_clkdev_release(struct device *dev, void *res) +{ + clkdev_drop(*(struct clk_lookup **)res); +} - return cl ? 0 : -ENOMEM; +static int devm_clk_match_clkdev(struct device *dev, void *res, void *data) +{ + struct clk_lookup **l = res; + + return *l == data; } -EXPORT_SYMBOL(clk_hw_register_clkdev); + +/** + * devm_clk_release_clkdev - Resource managed clkdev lookup release + * @dev: device this lookup is bound + * @con_id: connection ID string on device + * @dev_id: format string describing device name + * + * Drop the clkdev lookup created with devm_clk_hw_register_clkdev. + * Normally this function will not need to be called and the resource + * management code will ensure that the resource is freed. + */ +void devm_clk_release_clkdev(struct device *dev, const char *con_id, + const char *dev_id) +{ + struct clk_lookup *cl; + int rval; + + cl = clk_find(dev_id, con_id); + WARN_ON(!cl); + rval = devres_release(dev, devm_clkdev_release, + devm_clk_match_clkdev, cl); + WARN_ON(rval); +} +EXPORT_SYMBOL(devm_clk_release_clkdev); + +/** + * devm_clk_hw_register_clkdev - managed clk lookup registration for clk_hw + * @dev: device this lookup is bound + * @hw: struct clk_hw to associate with all clk_lookups + * @con_id: connection ID string on device + * @dev_id: format string describing device name + * + * con_id or dev_id may be NULL as a wildcard, just as in the rest of + * clkdev. + * + * To make things easier for mass registration, we detect error clk_hws + * from a previous clk_hw_register_*() call, and return the error code for + * those. This is to permit this function to be called immediately + * after clk_hw_register_*(). + */ +int devm_clk_hw_register_clkdev(struct device *dev, struct clk_hw *hw, + const char *con_id, const char *dev_id) +{ + int rval = -ENOMEM; + struct clk_lookup **cl; + + cl = devres_alloc(devm_clkdev_release, sizeof(*cl), GFP_KERNEL); + if (cl) { + rval = do_clk_register_clkdev(hw, cl, con_id, dev_id); + if (!rval) + devres_add(dev, cl); + else + devres_free(cl); + } + return rval; +} +EXPORT_SYMBOL(devm_clk_hw_register_clkdev); diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h index 4890ff033220..ccb32af5848b 100644 --- a/include/linux/clkdev.h +++ b/include/linux/clkdev.h @@ -52,4 +52,8 @@ int clk_add_alias(const char *, const char *, const char *, struct device *); int clk_register_clkdev(struct clk *, const char *, const char *); int clk_hw_register_clkdev(struct clk_hw *, const char *, const char *); +int devm_clk_hw_register_clkdev(struct device *dev, struct clk_hw *hw, + const char *con_id, const char *dev_id); +void devm_clk_release_clkdev(struct device *dev, const char *con_id, + const char *dev_id); #endif -- cgit v1.2.3 From 8f2566225ae2d62d532bb1810ed74fa4bbc5bbdb Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 2 Feb 2019 12:50:43 +0100 Subject: flow_offload: add flow_rule and flow_match structures and use them This patch wraps the dissector key and mask - that flower uses to represent the matching side - around the flow_match structure. To avoid a follow up patch that would edit the same LoCs in the drivers, this patch also wraps this new flow match structure around the flow rule object. This new structure will also contain the flow actions in follow up patches. This introduces two new interfaces: bool flow_rule_match_key(rule, dissector_id) that returns true if a given matching key is set on, and: flow_rule_match_XYZ(rule, &match); To fetch the matching side XYZ into the match container structure, to retrieve the key and the mask with one single call. Signed-off-by: Pablo Neira Ayuso Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 174 ++++----- .../net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 194 ++++------ drivers/net/ethernet/intel/i40e/i40e_main.c | 178 ++++----- drivers/net/ethernet/intel/iavf/iavf_main.c | 195 ++++------ drivers/net/ethernet/intel/igb/igb_main.c | 64 ++-- .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 68 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 376 ++++++++----------- .../net/ethernet/mellanox/mlxsw/spectrum_flower.c | 202 +++++----- drivers/net/ethernet/netronome/nfp/flower/action.c | 11 +- drivers/net/ethernet/netronome/nfp/flower/match.c | 417 +++++++++++---------- .../net/ethernet/netronome/nfp/flower/offload.c | 149 +++----- drivers/net/ethernet/qlogic/qede/qede_filter.c | 85 ++--- include/net/flow_offload.h | 115 ++++++ include/net/pkt_cls.h | 11 +- net/core/Makefile | 2 +- net/core/flow_offload.c | 143 +++++++ net/sched/cls_flower.c | 47 ++- 17 files changed, 1209 insertions(+), 1222 deletions(-) create mode 100644 include/net/flow_offload.h create mode 100644 net/core/flow_offload.c (limited to 'include') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index c683b5e96b1d..90a2170c5138 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -177,18 +177,12 @@ static int bnxt_tc_parse_actions(struct bnxt *bp, return 0; } -#define GET_KEY(flow_cmd, key_type) \ - skb_flow_dissector_target((flow_cmd)->dissector, key_type,\ - (flow_cmd)->key) -#define GET_MASK(flow_cmd, key_type) \ - skb_flow_dissector_target((flow_cmd)->dissector, key_type,\ - (flow_cmd)->mask) - static int bnxt_tc_parse_flow(struct bnxt *bp, struct tc_cls_flower_offload *tc_flow_cmd, struct bnxt_tc_flow *flow) { - struct flow_dissector *dissector = tc_flow_cmd->dissector; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(tc_flow_cmd); + struct flow_dissector *dissector = rule->match.dissector; /* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */ if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || @@ -198,140 +192,120 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, return -EOPNOTSUPP; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC); - struct flow_dissector_key_basic *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - flow->l2_key.ether_type = key->n_proto; - flow->l2_mask.ether_type = mask->n_proto; + flow_rule_match_basic(rule, &match); + flow->l2_key.ether_type = match.key->n_proto; + flow->l2_mask.ether_type = match.mask->n_proto; - if (key->n_proto == htons(ETH_P_IP) || - key->n_proto == htons(ETH_P_IPV6)) { - flow->l4_key.ip_proto = key->ip_proto; - flow->l4_mask.ip_proto = mask->ip_proto; + if (match.key->n_proto == htons(ETH_P_IP) || + match.key->n_proto == htons(ETH_P_IPV6)) { + flow->l4_key.ip_proto = match.key->ip_proto; + flow->l4_mask.ip_proto = match.mask->ip_proto; } } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS); - struct flow_dissector_key_eth_addrs *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + flow_rule_match_eth_addrs(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_ETH_ADDRS; - ether_addr_copy(flow->l2_key.dmac, key->dst); - ether_addr_copy(flow->l2_mask.dmac, mask->dst); - ether_addr_copy(flow->l2_key.smac, key->src); - ether_addr_copy(flow->l2_mask.smac, mask->src); + ether_addr_copy(flow->l2_key.dmac, match.key->dst); + ether_addr_copy(flow->l2_mask.dmac, match.mask->dst); + ether_addr_copy(flow->l2_key.smac, match.key->src); + ether_addr_copy(flow->l2_mask.smac, match.mask->src); } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN); - struct flow_dissector_key_vlan *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + flow_rule_match_vlan(rule, &match); flow->l2_key.inner_vlan_tci = - cpu_to_be16(VLAN_TCI(key->vlan_id, key->vlan_priority)); + cpu_to_be16(VLAN_TCI(match.key->vlan_id, + match.key->vlan_priority)); flow->l2_mask.inner_vlan_tci = - cpu_to_be16((VLAN_TCI(mask->vlan_id, mask->vlan_priority))); + cpu_to_be16((VLAN_TCI(match.mask->vlan_id, + match.mask->vlan_priority))); flow->l2_key.inner_vlan_tpid = htons(ETH_P_8021Q); flow->l2_mask.inner_vlan_tpid = htons(0xffff); flow->l2_key.num_vlans = 1; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { - struct flow_dissector_key_ipv4_addrs *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS); - struct flow_dissector_key_ipv4_addrs *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match; + flow_rule_match_ipv4_addrs(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_IPV4_ADDRS; - flow->l3_key.ipv4.daddr.s_addr = key->dst; - flow->l3_mask.ipv4.daddr.s_addr = mask->dst; - flow->l3_key.ipv4.saddr.s_addr = key->src; - flow->l3_mask.ipv4.saddr.s_addr = mask->src; - } else if (dissector_uses_key(dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { - struct flow_dissector_key_ipv6_addrs *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS); - struct flow_dissector_key_ipv6_addrs *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS); - + flow->l3_key.ipv4.daddr.s_addr = match.key->dst; + flow->l3_mask.ipv4.daddr.s_addr = match.mask->dst; + flow->l3_key.ipv4.saddr.s_addr = match.key->src; + flow->l3_mask.ipv4.saddr.s_addr = match.mask->src; + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_IPV6_ADDRS; - flow->l3_key.ipv6.daddr = key->dst; - flow->l3_mask.ipv6.daddr = mask->dst; - flow->l3_key.ipv6.saddr = key->src; - flow->l3_mask.ipv6.saddr = mask->src; + flow->l3_key.ipv6.daddr = match.key->dst; + flow->l3_mask.ipv6.daddr = match.mask->dst; + flow->l3_key.ipv6.saddr = match.key->src; + flow->l3_mask.ipv6.saddr = match.mask->src; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS); - struct flow_dissector_key_ports *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + flow_rule_match_ports(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_PORTS; - flow->l4_key.ports.dport = key->dst; - flow->l4_mask.ports.dport = mask->dst; - flow->l4_key.ports.sport = key->src; - flow->l4_mask.ports.sport = mask->src; + flow->l4_key.ports.dport = match.key->dst; + flow->l4_mask.ports.dport = match.mask->dst; + flow->l4_key.ports.sport = match.key->src; + flow->l4_mask.ports.sport = match.mask->src; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ICMP)) { - struct flow_dissector_key_icmp *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP); - struct flow_dissector_key_icmp *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP)) { + struct flow_match_icmp match; + flow_rule_match_icmp(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_ICMP; - flow->l4_key.icmp.type = key->type; - flow->l4_key.icmp.code = key->code; - flow->l4_mask.icmp.type = mask->type; - flow->l4_mask.icmp.code = mask->code; + flow->l4_key.icmp.type = match.key->type; + flow->l4_key.icmp.code = match.key->code; + flow->l4_mask.icmp.type = match.mask->type; + flow->l4_mask.icmp.code = match.mask->code; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { - struct flow_dissector_key_ipv4_addrs *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS); - struct flow_dissector_key_ipv4_addrs *mask = - GET_MASK(tc_flow_cmd, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match; + flow_rule_match_enc_ipv4_addrs(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS; - flow->tun_key.u.ipv4.dst = key->dst; - flow->tun_mask.u.ipv4.dst = mask->dst; - flow->tun_key.u.ipv4.src = key->src; - flow->tun_mask.u.ipv4.src = mask->src; - } else if (dissector_uses_key(dissector, + flow->tun_key.u.ipv4.dst = match.key->dst; + flow->tun_mask.u.ipv4.dst = match.mask->dst; + flow->tun_key.u.ipv4.src = match.key->src; + flow->tun_mask.u.ipv4.src = match.mask->src; + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { return -EOPNOTSUPP; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID); - struct flow_dissector_key_keyid *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; + flow_rule_match_enc_keyid(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_ID; - flow->tun_key.tun_id = key32_to_tunnel_id(key->keyid); - flow->tun_mask.tun_id = key32_to_tunnel_id(mask->keyid); + flow->tun_key.tun_id = key32_to_tunnel_id(match.key->keyid); + flow->tun_mask.tun_id = key32_to_tunnel_id(match.mask->keyid); } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { - struct flow_dissector_key_ports *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS); - struct flow_dissector_key_ports *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) { + struct flow_match_ports match; + flow_rule_match_enc_ports(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_PORTS; - flow->tun_key.tp_dst = key->dst; - flow->tun_mask.tp_dst = mask->dst; - flow->tun_key.tp_src = key->src; - flow->tun_mask.tp_src = mask->src; + flow->tun_key.tp_dst = match.key->dst; + flow->tun_mask.tp_dst = match.mask->dst; + flow->tun_key.tp_src = match.key->src; + flow->tun_mask.tp_src = match.mask->src; } return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index c116f96956fe..39c5af5dad3d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -83,28 +83,23 @@ static void cxgb4_process_flow_match(struct net_device *dev, struct tc_cls_flower_offload *cls, struct ch_filter_specification *fs) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls); u16 addr_type = 0; - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - cls->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; - addr_type = key->addr_type; + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_BASIC, - cls->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_BASIC, - cls->mask); - u16 ethtype_key = ntohs(key->n_proto); - u16 ethtype_mask = ntohs(mask->n_proto); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + u16 ethtype_key, ethtype_mask; + + flow_rule_match_basic(rule, &match); + ethtype_key = ntohs(match.key->n_proto); + ethtype_mask = ntohs(match.mask->n_proto); if (ethtype_key == ETH_P_ALL) { ethtype_key = 0; @@ -116,115 +111,89 @@ static void cxgb4_process_flow_match(struct net_device *dev, fs->val.ethtype = ethtype_key; fs->mask.ethtype = ethtype_mask; - fs->val.proto = key->ip_proto; - fs->mask.proto = mask->ip_proto; + fs->val.proto = match.key->ip_proto; + fs->mask.proto = match.mask->ip_proto; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - cls->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - cls->mask); + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); fs->type = 0; - memcpy(&fs->val.lip[0], &key->dst, sizeof(key->dst)); - memcpy(&fs->val.fip[0], &key->src, sizeof(key->src)); - memcpy(&fs->mask.lip[0], &mask->dst, sizeof(mask->dst)); - memcpy(&fs->mask.fip[0], &mask->src, sizeof(mask->src)); + memcpy(&fs->val.lip[0], &match.key->dst, sizeof(match.key->dst)); + memcpy(&fs->val.fip[0], &match.key->src, sizeof(match.key->src)); + memcpy(&fs->mask.lip[0], &match.mask->dst, sizeof(match.mask->dst)); + memcpy(&fs->mask.fip[0], &match.mask->src, sizeof(match.mask->src)); /* also initialize nat_lip/fip to same values */ - memcpy(&fs->nat_lip[0], &key->dst, sizeof(key->dst)); - memcpy(&fs->nat_fip[0], &key->src, sizeof(key->src)); - + memcpy(&fs->nat_lip[0], &match.key->dst, sizeof(match.key->dst)); + memcpy(&fs->nat_fip[0], &match.key->src, sizeof(match.key->src)); } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - cls->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - cls->mask); + struct flow_match_ipv6_addrs match; + flow_rule_match_ipv6_addrs(rule, &match); fs->type = 1; - memcpy(&fs->val.lip[0], key->dst.s6_addr, sizeof(key->dst)); - memcpy(&fs->val.fip[0], key->src.s6_addr, sizeof(key->src)); - memcpy(&fs->mask.lip[0], mask->dst.s6_addr, sizeof(mask->dst)); - memcpy(&fs->mask.fip[0], mask->src.s6_addr, sizeof(mask->src)); + memcpy(&fs->val.lip[0], match.key->dst.s6_addr, + sizeof(match.key->dst)); + memcpy(&fs->val.fip[0], match.key->src.s6_addr, + sizeof(match.key->src)); + memcpy(&fs->mask.lip[0], match.mask->dst.s6_addr, + sizeof(match.mask->dst)); + memcpy(&fs->mask.fip[0], match.mask->src.s6_addr, + sizeof(match.mask->src)); /* also initialize nat_lip/fip to same values */ - memcpy(&fs->nat_lip[0], key->dst.s6_addr, sizeof(key->dst)); - memcpy(&fs->nat_fip[0], key->src.s6_addr, sizeof(key->src)); + memcpy(&fs->nat_lip[0], match.key->dst.s6_addr, + sizeof(match.key->dst)); + memcpy(&fs->nat_fip[0], match.key->src.s6_addr, + sizeof(match.key->src)); } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key, *mask; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; - key = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_PORTS, - cls->key); - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_PORTS, - cls->mask); - fs->val.lport = cpu_to_be16(key->dst); - fs->mask.lport = cpu_to_be16(mask->dst); - fs->val.fport = cpu_to_be16(key->src); - fs->mask.fport = cpu_to_be16(mask->src); + flow_rule_match_ports(rule, &match); + fs->val.lport = cpu_to_be16(match.key->dst); + fs->mask.lport = cpu_to_be16(match.mask->dst); + fs->val.fport = cpu_to_be16(match.key->src); + fs->mask.fport = cpu_to_be16(match.mask->src); /* also initialize nat_lport/fport to same values */ - fs->nat_lport = cpu_to_be16(key->dst); - fs->nat_fport = cpu_to_be16(key->src); + fs->nat_lport = cpu_to_be16(match.key->dst); + fs->nat_fport = cpu_to_be16(match.key->src); } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) { - struct flow_dissector_key_ip *key, *mask; - - key = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IP, - cls->key); - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IP, - cls->mask); - fs->val.tos = key->tos; - fs->mask.tos = mask->tos; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match; + + flow_rule_match_ip(rule, &match); + fs->val.tos = match.key->tos; + fs->mask.tos = match.mask->tos; } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *key, *mask; - - key = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - cls->key); - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - cls->mask); - fs->val.vni = be32_to_cpu(key->keyid); - fs->mask.vni = be32_to_cpu(mask->keyid); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; + + flow_rule_match_enc_keyid(rule, &match); + fs->val.vni = be32_to_cpu(match.key->keyid); + fs->mask.vni = be32_to_cpu(match.mask->keyid); if (fs->mask.vni) { fs->val.encap_vld = 1; fs->mask.encap_vld = 1; } } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key, *mask; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; u16 vlan_tci, vlan_tci_mask; - key = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_VLAN, - cls->key); - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_VLAN, - cls->mask); - vlan_tci = key->vlan_id | (key->vlan_priority << - VLAN_PRIO_SHIFT); - vlan_tci_mask = mask->vlan_id | (mask->vlan_priority << - VLAN_PRIO_SHIFT); + flow_rule_match_vlan(rule, &match); + vlan_tci = match.key->vlan_id | (match.key->vlan_priority << + VLAN_PRIO_SHIFT); + vlan_tci_mask = match.mask->vlan_id | (match.mask->vlan_priority << + VLAN_PRIO_SHIFT); fs->val.ivlan = vlan_tci; fs->mask.ivlan = vlan_tci_mask; @@ -255,10 +224,12 @@ static void cxgb4_process_flow_match(struct net_device *dev, static int cxgb4_validate_flow_match(struct net_device *dev, struct tc_cls_flower_offload *cls) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls); + struct flow_dissector *dissector = rule->match.dissector; u16 ethtype_mask = 0; u16 ethtype_key = 0; - if (cls->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | @@ -268,36 +239,29 @@ static int cxgb4_validate_flow_match(struct net_device *dev, BIT(FLOW_DISSECTOR_KEY_VLAN) | BIT(FLOW_DISSECTOR_KEY_IP))) { netdev_warn(dev, "Unsupported key used: 0x%x\n", - cls->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_BASIC, - cls->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_BASIC, - cls->mask); - ethtype_key = ntohs(key->n_proto); - ethtype_mask = ntohs(mask->n_proto); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + ethtype_key = ntohs(match.key->n_proto); + ethtype_mask = ntohs(match.mask->n_proto); } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { u16 eth_ip_type = ethtype_key & ethtype_mask; - struct flow_dissector_key_ip *mask; + struct flow_match_ip match; if (eth_ip_type != ETH_P_IP && eth_ip_type != ETH_P_IPV6) { netdev_err(dev, "IP Key supported only with IPv4/v6"); return -EINVAL; } - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IP, - cls->mask); - if (mask->ttl) { + flow_rule_match_ip(rule, &match); + if (match.mask->ttl) { netdev_warn(dev, "ttl match unsupported for offload"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 5c6731b97059..44856a84738d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7169,11 +7169,13 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, struct tc_cls_flower_offload *f, struct i40e_cloud_filter *filter) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0; struct i40e_pf *pf = vsi->back; u8 field_flags = 0; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -7183,143 +7185,109 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, BIT(FLOW_DISSECTOR_KEY_PORTS) | BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n", - f->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; - struct flow_dissector_key_keyid *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); - - if (mask->keyid != 0) + flow_rule_match_enc_keyid(rule, &match); + if (match.mask->keyid != 0) field_flags |= I40E_CLOUD_FIELD_TEN_ID; - filter->tenant_id = be32_to_cpu(key->keyid); + filter->tenant_id = be32_to_cpu(match.key->keyid); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - n_proto_key = ntohs(key->n_proto); - n_proto_mask = ntohs(mask->n_proto); + flow_rule_match_basic(rule, &match); + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); if (n_proto_key == ETH_P_ALL) { n_proto_key = 0; n_proto_mask = 0; } filter->n_proto = n_proto_key & n_proto_mask; - filter->ip_proto = key->ip_proto; + filter->ip_proto = match.key->ip_proto; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; - struct flow_dissector_key_eth_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); + flow_rule_match_eth_addrs(rule, &match); /* use is_broadcast and is_zero to check for all 0xf or 0 */ - if (!is_zero_ether_addr(mask->dst)) { - if (is_broadcast_ether_addr(mask->dst)) { + if (!is_zero_ether_addr(match.mask->dst)) { + if (is_broadcast_ether_addr(match.mask->dst)) { field_flags |= I40E_CLOUD_FIELD_OMAC; } else { dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n", - mask->dst); + match.mask->dst); return I40E_ERR_CONFIG; } } - if (!is_zero_ether_addr(mask->src)) { - if (is_broadcast_ether_addr(mask->src)) { + if (!is_zero_ether_addr(match.mask->src)) { + if (is_broadcast_ether_addr(match.mask->src)) { field_flags |= I40E_CLOUD_FIELD_IMAC; } else { dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n", - mask->src); + match.mask->src); return I40E_ERR_CONFIG; } } - ether_addr_copy(filter->dst_mac, key->dst); - ether_addr_copy(filter->src_mac, key->src); + ether_addr_copy(filter->dst_mac, match.key->dst); + ether_addr_copy(filter->src_mac, match.key->src); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; - if (mask->vlan_id) { - if (mask->vlan_id == VLAN_VID_MASK) { + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_id) { + if (match.mask->vlan_id == VLAN_VID_MASK) { field_flags |= I40E_CLOUD_FIELD_IVLAN; } else { dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n", - mask->vlan_id); + match.mask->vlan_id); return I40E_ERR_CONFIG; } } - filter->vlan_id = cpu_to_be16(key->vlan_id); + filter->vlan_id = cpu_to_be16(match.key->vlan_id); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; - addr_type = key->addr_type; + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); - - if (mask->dst) { - if (mask->dst == cpu_to_be32(0xffffffff)) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be32(0xffffffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n", - &mask->dst); + &match.mask->dst); return I40E_ERR_CONFIG; } } - if (mask->src) { - if (mask->src == cpu_to_be32(0xffffffff)) { + if (match.mask->src) { + if (match.mask->src == cpu_to_be32(0xffffffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n", - &mask->src); + &match.mask->src); return I40E_ERR_CONFIG; } } @@ -7328,70 +7296,60 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n"); return I40E_ERR_CONFIG; } - filter->dst_ipv4 = key->dst; - filter->src_ipv4 = key->src; + filter->dst_ipv4 = match.key->dst; + filter->src_ipv4 = match.key->src; } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); /* src and dest IPV6 address should not be LOOPBACK * (0:0:0:0:0:0:0:1), which can be represented as ::1 */ - if (ipv6_addr_loopback(&key->dst) || - ipv6_addr_loopback(&key->src)) { + if (ipv6_addr_loopback(&match.key->dst) || + ipv6_addr_loopback(&match.key->src)) { dev_err(&pf->pdev->dev, "Bad ipv6, addr is LOOPBACK\n"); return I40E_ERR_CONFIG; } - if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + if (!ipv6_addr_any(&match.mask->dst) || + !ipv6_addr_any(&match.mask->src)) field_flags |= I40E_CLOUD_FIELD_IIP; - memcpy(&filter->src_ipv6, &key->src.s6_addr32, + memcpy(&filter->src_ipv6, &match.key->src.s6_addr32, sizeof(filter->src_ipv6)); - memcpy(&filter->dst_ipv6, &key->dst.s6_addr32, + memcpy(&filter->dst_ipv6, &match.key->dst.s6_addr32, sizeof(filter->dst_ipv6)); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; - if (mask->src) { - if (mask->src == cpu_to_be16(0xffff)) { + flow_rule_match_ports(rule, &match); + if (match.mask->src) { + if (match.mask->src == cpu_to_be16(0xffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n", - be16_to_cpu(mask->src)); + be16_to_cpu(match.mask->src)); return I40E_ERR_CONFIG; } } - if (mask->dst) { - if (mask->dst == cpu_to_be16(0xffff)) { + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be16(0xffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n", - be16_to_cpu(mask->dst)); + be16_to_cpu(match.mask->dst)); return I40E_ERR_CONFIG; } } - filter->dst_port = key->dst; - filter->src_port = key->src; + filter->dst_port = match.key->dst; + filter->src_port = match.key->src; switch (filter->ip_proto) { case IPPROTO_TCP: diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 9f2b7b7adf6b..4569d69a2b55 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2439,6 +2439,8 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, struct tc_cls_flower_offload *f, struct iavf_cloud_filter *filter) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; u16 n_proto_mask = 0; u16 n_proto_key = 0; u8 field_flags = 0; @@ -2447,7 +2449,7 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, int i = 0; struct virtchnl_filter *vf = &filter->f; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -2457,32 +2459,24 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, BIT(FLOW_DISSECTOR_KEY_PORTS) | BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n", - f->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; - if (mask->keyid != 0) + flow_rule_match_enc_keyid(rule, &match); + if (match.mask->keyid != 0) field_flags |= IAVF_CLOUD_FIELD_TEN_ID; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); - n_proto_key = ntohs(key->n_proto); - n_proto_mask = ntohs(mask->n_proto); + flow_rule_match_basic(rule, &match); + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); if (n_proto_key == ETH_P_ALL) { n_proto_key = 0; @@ -2496,122 +2490,103 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, vf->flow_type = VIRTCHNL_TCP_V6_FLOW; } - if (key->ip_proto != IPPROTO_TCP) { + if (match.key->ip_proto != IPPROTO_TCP) { dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n"); return -EINVAL; } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + + flow_rule_match_eth_addrs(rule, &match); - struct flow_dissector_key_eth_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); /* use is_broadcast and is_zero to check for all 0xf or 0 */ - if (!is_zero_ether_addr(mask->dst)) { - if (is_broadcast_ether_addr(mask->dst)) { + if (!is_zero_ether_addr(match.mask->dst)) { + if (is_broadcast_ether_addr(match.mask->dst)) { field_flags |= IAVF_CLOUD_FIELD_OMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n", - mask->dst); + match.mask->dst); return I40E_ERR_CONFIG; } } - if (!is_zero_ether_addr(mask->src)) { - if (is_broadcast_ether_addr(mask->src)) { + if (!is_zero_ether_addr(match.mask->src)) { + if (is_broadcast_ether_addr(match.mask->src)) { field_flags |= IAVF_CLOUD_FIELD_IMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n", - mask->src); + match.mask->src); return I40E_ERR_CONFIG; } } - if (!is_zero_ether_addr(key->dst)) - if (is_valid_ether_addr(key->dst) || - is_multicast_ether_addr(key->dst)) { + if (!is_zero_ether_addr(match.key->dst)) + if (is_valid_ether_addr(match.key->dst) || + is_multicast_ether_addr(match.key->dst)) { /* set the mask if a valid dst_mac address */ for (i = 0; i < ETH_ALEN; i++) vf->mask.tcp_spec.dst_mac[i] |= 0xff; ether_addr_copy(vf->data.tcp_spec.dst_mac, - key->dst); + match.key->dst); } - if (!is_zero_ether_addr(key->src)) - if (is_valid_ether_addr(key->src) || - is_multicast_ether_addr(key->src)) { + if (!is_zero_ether_addr(match.key->src)) + if (is_valid_ether_addr(match.key->src) || + is_multicast_ether_addr(match.key->src)) { /* set the mask if a valid dst_mac address */ for (i = 0; i < ETH_ALEN; i++) vf->mask.tcp_spec.src_mac[i] |= 0xff; ether_addr_copy(vf->data.tcp_spec.src_mac, - key->src); + match.key->src); } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; - if (mask->vlan_id) { - if (mask->vlan_id == VLAN_VID_MASK) { + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_id) { + if (match.mask->vlan_id == VLAN_VID_MASK) { field_flags |= IAVF_CLOUD_FIELD_IVLAN; } else { dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n", - mask->vlan_id); + match.mask->vlan_id); return I40E_ERR_CONFIG; } } vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff); - vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id); + vf->data.tcp_spec.vlan_id = cpu_to_be16(match.key->vlan_id); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; - addr_type = key->addr_type; + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); - - if (mask->dst) { - if (mask->dst == cpu_to_be32(0xffffffff)) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be32(0xffffffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n", - be32_to_cpu(mask->dst)); + be32_to_cpu(match.mask->dst)); return I40E_ERR_CONFIG; } } - if (mask->src) { - if (mask->src == cpu_to_be32(0xffffffff)) { + if (match.mask->src) { + if (match.mask->src == cpu_to_be32(0xffffffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", - be32_to_cpu(mask->dst)); + be32_to_cpu(match.mask->dst)); return I40E_ERR_CONFIG; } } @@ -2620,28 +2595,23 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n"); return I40E_ERR_CONFIG; } - if (key->dst) { + if (match.key->dst) { vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff); - vf->data.tcp_spec.dst_ip[0] = key->dst; + vf->data.tcp_spec.dst_ip[0] = match.key->dst; } - if (key->src) { + if (match.key->src) { vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff); - vf->data.tcp_spec.src_ip[0] = key->src; + vf->data.tcp_spec.src_ip[0] = match.key->src; } } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); /* validate mask, make sure it is not IPV6_ADDR_ANY */ - if (ipv6_addr_any(&mask->dst)) { + if (ipv6_addr_any(&match.mask->dst)) { dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n", IPV6_ADDR_ANY); return I40E_ERR_CONFIG; @@ -2650,61 +2620,56 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, /* src and dest IPv6 address should not be LOOPBACK * (0:0:0:0:0:0:0:1) which can be represented as ::1 */ - if (ipv6_addr_loopback(&key->dst) || - ipv6_addr_loopback(&key->src)) { + if (ipv6_addr_loopback(&match.key->dst) || + ipv6_addr_loopback(&match.key->src)) { dev_err(&adapter->pdev->dev, "ipv6 addr should not be loopback\n"); return I40E_ERR_CONFIG; } - if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + if (!ipv6_addr_any(&match.mask->dst) || + !ipv6_addr_any(&match.mask->src)) field_flags |= IAVF_CLOUD_FIELD_IIP; for (i = 0; i < 4; i++) vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff); - memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32, + memcpy(&vf->data.tcp_spec.dst_ip, &match.key->dst.s6_addr32, sizeof(vf->data.tcp_spec.dst_ip)); for (i = 0; i < 4; i++) vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff); - memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32, + memcpy(&vf->data.tcp_spec.src_ip, &match.key->src.s6_addr32, sizeof(vf->data.tcp_spec.src_ip)); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); - - if (mask->src) { - if (mask->src == cpu_to_be16(0xffff)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); + if (match.mask->src) { + if (match.mask->src == cpu_to_be16(0xffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad src port mask %u\n", - be16_to_cpu(mask->src)); + be16_to_cpu(match.mask->src)); return I40E_ERR_CONFIG; } } - if (mask->dst) { - if (mask->dst == cpu_to_be16(0xffff)) { + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be16(0xffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n", - be16_to_cpu(mask->dst)); + be16_to_cpu(match.mask->dst)); return I40E_ERR_CONFIG; } } - if (key->dst) { + if (match.key->dst) { vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff); - vf->data.tcp_spec.dst_port = key->dst; + vf->data.tcp_spec.dst_port = match.key->dst; } - if (key->src) { + if (match.key->src) { vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff); - vf->data.tcp_spec.src_port = key->src; + vf->data.tcp_spec.src_port = match.key->src; } } vf->field_flags = field_flags; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index d35cc9697e2d..6d812e96572d 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2581,9 +2581,11 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, int traffic_class, struct igb_nfc_filter *input) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; struct netlink_ext_ack *extack = f->common.extack; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -2593,78 +2595,60 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, return -EOPNOTSUPP; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key, *mask; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); - - if (!is_zero_ether_addr(mask->dst)) { - if (!is_broadcast_ether_addr(mask->dst)) { + flow_rule_match_eth_addrs(rule, &match); + if (!is_zero_ether_addr(match.mask->dst)) { + if (!is_broadcast_ether_addr(match.mask->dst)) { NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for destination MAC address"); return -EINVAL; } input->filter.match_flags |= IGB_FILTER_FLAG_DST_MAC_ADDR; - ether_addr_copy(input->filter.dst_addr, key->dst); + ether_addr_copy(input->filter.dst_addr, match.key->dst); } - if (!is_zero_ether_addr(mask->src)) { - if (!is_broadcast_ether_addr(mask->src)) { + if (!is_zero_ether_addr(match.mask->src)) { + if (!is_broadcast_ether_addr(match.mask->src)) { NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for source MAC address"); return -EINVAL; } input->filter.match_flags |= IGB_FILTER_FLAG_SRC_MAC_ADDR; - ether_addr_copy(input->filter.src_addr, key->src); + ether_addr_copy(input->filter.src_addr, match.key->src); } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key, *mask; - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - if (mask->n_proto) { - if (mask->n_proto != ETHER_TYPE_FULL_MASK) { + flow_rule_match_basic(rule, &match); + if (match.mask->n_proto) { + if (match.mask->n_proto != ETHER_TYPE_FULL_MASK) { NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for EtherType filter"); return -EINVAL; } input->filter.match_flags |= IGB_FILTER_FLAG_ETHER_TYPE; - input->filter.etype = key->n_proto; + input->filter.etype = match.key->n_proto; } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key, *mask; - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; - if (mask->vlan_priority) { - if (mask->vlan_priority != VLAN_PRIO_FULL_MASK) { + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_priority) { + if (match.mask->vlan_priority != VLAN_PRIO_FULL_MASK) { NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN priority"); return -EINVAL; } input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI; - input->filter.vlan_tci = key->vlan_priority; + input->filter.vlan_tci = match.key->vlan_priority; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 046948ead152..47bb4eb894c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -496,25 +496,21 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, void *headers_c, void *headers_v) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); struct netlink_ext_ack *extack = f->common.extack; - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - f->mask); void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + struct flow_match_ports enc_ports; + + flow_rule_match_enc_ports(rule, &enc_ports); /* Full udp dst port must be given */ - if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) || - memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) { + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) || + memchr_inv(&enc_ports.mask->dst, 0xff, sizeof(enc_ports.mask->dst))) { NL_SET_ERR_MSG_MOD(extack, "VXLAN decap filter must include enc_dst_port condition"); netdev_warn(priv->netdev, @@ -523,12 +519,12 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, } /* udp dst port must be knonwn as a VXLAN port */ - if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst))) { + if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(enc_ports.key->dst))) { NL_SET_ERR_MSG_MOD(extack, "Matched UDP port is not registered as a VXLAN port"); netdev_warn(priv->netdev, "UDP port %d is not registered as a VXLAN port\n", - be16_to_cpu(key->dst)); + be16_to_cpu(enc_ports.key->dst)); return -EOPNOTSUPP; } @@ -536,26 +532,26 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst)); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, + ntohs(enc_ports.mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, + ntohs(enc_ports.key->dst)); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, ntohs(mask->src)); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, ntohs(key->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, + ntohs(enc_ports.mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, + ntohs(enc_ports.key->src)); /* match on VNI */ - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->key); - struct flow_dissector_key_keyid *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid enc_keyid; + + flow_rule_match_enc_keyid(rule, &enc_keyid); + MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni, - be32_to_cpu(mask->keyid)); + be32_to_cpu(enc_keyid.mask->keyid)); MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni, - be32_to_cpu(key->keyid)); + be32_to_cpu(enc_keyid.key->keyid)); } return 0; } @@ -570,6 +566,7 @@ static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv, misc_parameters); void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); if (!MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap)) { NL_SET_ERR_MSG_MOD(f->common.extack, @@ -587,21 +584,14 @@ static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_misc, misc_v, gre_protocol, ETH_P_TEB); /* gre key */ - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *mask = NULL; - struct flow_dissector_key_keyid *key = NULL; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid enc_keyid; - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); + flow_rule_match_enc_keyid(rule, &enc_keyid); MLX5_SET(fte_match_set_misc, misc_c, - gre_key.key, be32_to_cpu(mask->keyid)); - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->key); + gre_key.key, be32_to_cpu(enc_keyid.mask->keyid)); MLX5_SET(fte_match_set_misc, misc_v, - gre_key.key, be32_to_cpu(key->keyid)); + gre_key.key, be32_to_cpu(enc_keyid.key->keyid)); } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 74159d39dd66..cd289ce0582d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1309,12 +1309,9 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, outer_headers); void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); - - struct flow_dissector_key_control *enc_control = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL, - f->key); - int err = 0; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_match_control enc_control; + int err; err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f, headers_c, headers_v); @@ -1324,79 +1321,70 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, return err; } - if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, - f->mask); + flow_rule_match_enc_control(rule, &enc_control); + + if (enc_control.key->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_enc_ipv4_addrs(rule, &match); MLX5_SET(fte_match_set_lyr_2_4, headers_c, src_ipv4_src_ipv6.ipv4_layout.ipv4, - ntohl(mask->src)); + ntohl(match.mask->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, src_ipv4_src_ipv6.ipv4_layout.ipv4, - ntohl(key->src)); + ntohl(match.key->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_c, dst_ipv4_dst_ipv6.ipv4_layout.ipv4, - ntohl(mask->dst)); + ntohl(match.mask->dst)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4, - ntohl(key->dst)); + ntohl(match.key->dst)); MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP); - } else if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, - f->mask); + } else if (enc_control.key->addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_match_ipv6_addrs match; + flow_rule_match_enc_ipv6_addrs(rule, &match); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, src_ipv4_src_ipv6.ipv6_layout.ipv6), - &mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + &match.mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, src_ipv4_src_ipv6.ipv6_layout.ipv6), - &key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + &match.key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + &match.mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + &match.key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { - struct flow_dissector_key_ip *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IP, - f->key); - struct flow_dissector_key_ip *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IP, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) { + struct flow_match_ip match; - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3); + flow_rule_match_enc_ip(rule, &match); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, + match.mask->tos & 0x3); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, + match.key->tos & 0x3); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos >> 2); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, + match.mask->tos >> 2); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, + match.key->tos >> 2); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, + match.mask->ttl); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, + match.key->ttl); - if (mask->ttl && + if (match.mask->ttl && !MLX5_CAP_ESW_FLOWTABLE_FDB (priv->mdev, ft_field_support.outer_ipv4_ttl)) { @@ -1437,12 +1425,14 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, misc_parameters); void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; u16 addr_type = 0; u8 ip_proto = 0; *match_level = MLX5_MATCH_NONE; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -1461,20 +1451,18 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, BIT(FLOW_DISSECTOR_KEY_ENC_IP))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported key"); netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", - f->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } - if ((dissector_uses_key(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) || - dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) || - dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) && - dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL, - f->key); - switch (key->addr_type) { + if ((flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) && + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_enc_control(rule, &match); + switch (match.key->addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: case FLOW_DISSECTOR_KEY_IPV6_ADDRS: if (parse_tunnel_attr(priv, spec, f, filter_dev)) @@ -1493,35 +1481,27 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, inner_headers); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype, - ntohs(mask->n_proto)); + ntohs(match.mask->n_proto)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, - ntohs(key->n_proto)); + ntohs(match.key->n_proto)); - if (mask->n_proto) + if (match.mask->n_proto) *match_level = MLX5_MATCH_L2; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); - if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) { - if (key->vlan_tpid == htons(ETH_P_8021AD)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_id || + match.mask->vlan_priority || + match.mask->vlan_tpid) { + if (match.key->vlan_tpid == htons(ETH_P_8021AD)) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, @@ -1533,11 +1513,15 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, cvlan_tag, 1); } - MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, + match.mask->vlan_id); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, + match.key->vlan_id); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, + match.mask->vlan_priority); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, + match.key->vlan_priority); *match_level = MLX5_MATCH_L2; } @@ -1547,17 +1531,14 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, *match_level = MLX5_MATCH_L2; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CVLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CVLAN, - f->mask); - if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) { - if (key->vlan_tpid == htons(ETH_P_8021AD)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_id || + match.mask->vlan_priority || + match.mask->vlan_tpid) { + if (match.key->vlan_tpid == htons(ETH_P_8021AD)) { MLX5_SET(fte_match_set_misc, misc_c, outer_second_svlan_tag, 1); MLX5_SET(fte_match_set_misc, misc_v, @@ -1570,69 +1551,58 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, } MLX5_SET(fte_match_set_misc, misc_c, outer_second_vid, - mask->vlan_id); + match.mask->vlan_id); MLX5_SET(fte_match_set_misc, misc_v, outer_second_vid, - key->vlan_id); + match.key->vlan_id); MLX5_SET(fte_match_set_misc, misc_c, outer_second_prio, - mask->vlan_priority); + match.mask->vlan_priority); MLX5_SET(fte_match_set_misc, misc_v, outer_second_prio, - key->vlan_priority); + match.key->vlan_priority); *match_level = MLX5_MATCH_L2; } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); - struct flow_dissector_key_eth_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + flow_rule_match_eth_addrs(rule, &match); ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, dmac_47_16), - mask->dst); + match.mask->dst); ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dmac_47_16), - key->dst); + match.key->dst); ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, smac_47_16), - mask->src); + match.mask->src); ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, smac_47_16), - key->src); + match.key->src); - if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst)) + if (!is_zero_ether_addr(match.mask->src) || + !is_zero_ether_addr(match.mask->dst)) *match_level = MLX5_MATCH_L2; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; - struct flow_dissector_key_control *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->mask); - addr_type = key->addr_type; + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; /* the HW doesn't support frag first/later */ - if (mask->flags & FLOW_DIS_FIRST_FRAG) + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) return -EOPNOTSUPP; - if (mask->flags & FLOW_DIS_IS_FRAGMENT) { + if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, - key->flags & FLOW_DIS_IS_FRAGMENT); + match.key->flags & FLOW_DIS_IS_FRAGMENT); /* the HW doesn't need L3 inline to match on frag=no */ - if (!(key->flags & FLOW_DIS_IS_FRAGMENT)) + if (!(match.key->flags & FLOW_DIS_IS_FRAGMENT)) *match_level = MLX5_MATCH_L2; /* *** L2 attributes parsing up to here *** */ else @@ -1640,102 +1610,85 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); - ip_proto = key->ip_proto; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + ip_proto = match.key->ip_proto; MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol, - mask->ip_proto); + match.mask->ip_proto); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, - key->ip_proto); + match.key->ip_proto); - if (mask->ip_proto) + if (match.mask->ip_proto) *match_level = MLX5_MATCH_L3; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); + struct flow_match_ipv4_addrs match; + flow_rule_match_ipv4_addrs(rule, &match); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, src_ipv4_src_ipv6.ipv4_layout.ipv4), - &mask->src, sizeof(mask->src)); + &match.mask->src, sizeof(match.mask->src)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, src_ipv4_src_ipv6.ipv4_layout.ipv4), - &key->src, sizeof(key->src)); + &match.key->src, sizeof(match.key->src)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), - &mask->dst, sizeof(mask->dst)); + &match.mask->dst, sizeof(match.mask->dst)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), - &key->dst, sizeof(key->dst)); + &match.key->dst, sizeof(match.key->dst)); - if (mask->src || mask->dst) + if (match.mask->src || match.mask->dst) *match_level = MLX5_MATCH_L3; } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + struct flow_match_ipv6_addrs match; + flow_rule_match_ipv6_addrs(rule, &match); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, src_ipv4_src_ipv6.ipv6_layout.ipv6), - &mask->src, sizeof(mask->src)); + &match.mask->src, sizeof(match.mask->src)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, src_ipv4_src_ipv6.ipv6_layout.ipv6), - &key->src, sizeof(key->src)); + &match.key->src, sizeof(match.key->src)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &mask->dst, sizeof(mask->dst)); + &match.mask->dst, sizeof(match.mask->dst)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &key->dst, sizeof(key->dst)); + &match.key->dst, sizeof(match.key->dst)); - if (ipv6_addr_type(&mask->src) != IPV6_ADDR_ANY || - ipv6_addr_type(&mask->dst) != IPV6_ADDR_ANY) + if (ipv6_addr_type(&match.mask->src) != IPV6_ADDR_ANY || + ipv6_addr_type(&match.mask->dst) != IPV6_ADDR_ANY) *match_level = MLX5_MATCH_L3; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) { - struct flow_dissector_key_ip *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IP, - f->key); - struct flow_dissector_key_ip *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IP, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match; - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3); + flow_rule_match_ip(rule, &match); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, + match.mask->tos & 0x3); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, + match.key->tos & 0x3); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos >> 2); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, + match.mask->tos >> 2); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, + match.key->tos >> 2); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, + match.mask->ttl); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, + match.key->ttl); - if (mask->ttl && + if (match.mask->ttl && !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, ft_field_support.outer_ipv4_ttl)) { NL_SET_ERR_MSG_MOD(extack, @@ -1743,44 +1696,39 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (mask->tos || mask->ttl) + if (match.mask->tos || match.mask->ttl) *match_level = MLX5_MATCH_L3; } /* *** L3 attributes parsing up to here *** */ - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); switch (ip_proto) { case IPPROTO_TCP: MLX5_SET(fte_match_set_lyr_2_4, headers_c, - tcp_sport, ntohs(mask->src)); + tcp_sport, ntohs(match.mask->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - tcp_sport, ntohs(key->src)); + tcp_sport, ntohs(match.key->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_c, - tcp_dport, ntohs(mask->dst)); + tcp_dport, ntohs(match.mask->dst)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - tcp_dport, ntohs(key->dst)); + tcp_dport, ntohs(match.key->dst)); break; case IPPROTO_UDP: MLX5_SET(fte_match_set_lyr_2_4, headers_c, - udp_sport, ntohs(mask->src)); + udp_sport, ntohs(match.mask->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - udp_sport, ntohs(key->src)); + udp_sport, ntohs(match.key->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_c, - udp_dport, ntohs(mask->dst)); + udp_dport, ntohs(match.mask->dst)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - udp_dport, ntohs(key->dst)); + udp_dport, ntohs(match.key->dst)); break; default: NL_SET_ERR_MSG_MOD(extack, @@ -1790,26 +1738,20 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, return -EINVAL; } - if (mask->src || mask->dst) + if (match.mask->src || match.mask->dst) *match_level = MLX5_MATCH_L4; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP)) { - struct flow_dissector_key_tcp *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_TCP, - f->key); - struct flow_dissector_key_tcp *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_TCP, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_match_tcp match; + flow_rule_match_tcp(rule, &match); MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_flags, - ntohs(mask->flags)); + ntohs(match.mask->flags)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, tcp_flags, - ntohs(key->flags)); + ntohs(match.key->flags)); - if (mask->flags) + if (match.mask->flags) *match_level = MLX5_MATCH_L4; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index ff072358d950..a20379e29e02 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -113,59 +113,49 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei, struct tc_cls_flower_offload *f) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(f->rule, &match); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31, - (char *) &key->src, - (char *) &mask->src, 4); + (char *) &match.key->src, + (char *) &match.mask->src, 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31, - (char *) &key->dst, - (char *) &mask->dst, 4); + (char *) &match.key->dst, + (char *) &match.mask->dst, 4); } static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei, struct tc_cls_flower_offload *f) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(f->rule, &match); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_96_127, - &key->src.s6_addr[0x0], - &mask->src.s6_addr[0x0], 4); + &match.key->src.s6_addr[0x0], + &match.mask->src.s6_addr[0x0], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_64_95, - &key->src.s6_addr[0x4], - &mask->src.s6_addr[0x4], 4); + &match.key->src.s6_addr[0x4], + &match.mask->src.s6_addr[0x4], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_32_63, - &key->src.s6_addr[0x8], - &mask->src.s6_addr[0x8], 4); + &match.key->src.s6_addr[0x8], + &match.mask->src.s6_addr[0x8], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31, - &key->src.s6_addr[0xC], - &mask->src.s6_addr[0xC], 4); + &match.key->src.s6_addr[0xC], + &match.mask->src.s6_addr[0xC], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_96_127, - &key->dst.s6_addr[0x0], - &mask->dst.s6_addr[0x0], 4); + &match.key->dst.s6_addr[0x0], + &match.mask->dst.s6_addr[0x0], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_64_95, - &key->dst.s6_addr[0x4], - &mask->dst.s6_addr[0x4], 4); + &match.key->dst.s6_addr[0x4], + &match.mask->dst.s6_addr[0x4], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_32_63, - &key->dst.s6_addr[0x8], - &mask->dst.s6_addr[0x8], 4); + &match.key->dst.s6_addr[0x8], + &match.mask->dst.s6_addr[0x8], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31, - &key->dst.s6_addr[0xC], - &mask->dst.s6_addr[0xC], 4); + &match.key->dst.s6_addr[0xC], + &match.mask->dst.s6_addr[0xC], 4); } static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp, @@ -173,9 +163,10 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp, struct tc_cls_flower_offload *f, u8 ip_proto) { - struct flow_dissector_key_ports *key, *mask; + const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_match_ports match; - if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) return 0; if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) { @@ -184,16 +175,13 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp, return -EINVAL; } - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); + flow_rule_match_ports(rule, &match); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_DST_L4_PORT, - ntohs(key->dst), ntohs(mask->dst)); + ntohs(match.key->dst), + ntohs(match.mask->dst)); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_SRC_L4_PORT, - ntohs(key->src), ntohs(mask->src)); + ntohs(match.key->src), + ntohs(match.mask->src)); return 0; } @@ -202,9 +190,10 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp, struct tc_cls_flower_offload *f, u8 ip_proto) { - struct flow_dissector_key_tcp *key, *mask; + const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_match_tcp match; - if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP)) + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) return 0; if (ip_proto != IPPROTO_TCP) { @@ -213,14 +202,11 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp, return -EINVAL; } - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_TCP, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_TCP, - f->mask); + flow_rule_match_tcp(rule, &match); + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_TCP_FLAGS, - ntohs(key->flags), ntohs(mask->flags)); + ntohs(match.key->flags), + ntohs(match.mask->flags)); return 0; } @@ -229,9 +215,10 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp, struct tc_cls_flower_offload *f, u16 n_proto) { - struct flow_dissector_key_ip *key, *mask; + const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_match_ip match; - if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) return 0; if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) { @@ -240,20 +227,18 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp, return -EINVAL; } - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IP, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IP, - f->mask); + flow_rule_match_ip(rule, &match); + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_TTL_, - key->ttl, mask->ttl); + match.key->ttl, match.mask->ttl); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_ECN, - key->tos & 0x3, mask->tos & 0x3); + match.key->tos & 0x3, + match.mask->tos & 0x3); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_DSCP, - key->tos >> 6, mask->tos >> 6); + match.key->tos >> 6, + match.mask->tos >> 6); return 0; } @@ -263,13 +248,15 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, struct tc_cls_flower_offload *f) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; u16 n_proto_mask = 0; u16 n_proto_key = 0; u16 addr_type = 0; u8 ip_proto = 0; int err; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -286,25 +273,19 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_rulei_priority(rulei, f->common.prio); - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); - addr_type = key->addr_type; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); - n_proto_key = ntohs(key->n_proto); - n_proto_mask = ntohs(mask->n_proto); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); if (n_proto_key == ETH_P_ALL) { n_proto_key = 0; @@ -314,60 +295,53 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, MLXSW_AFK_ELEMENT_ETHERTYPE, n_proto_key, n_proto_mask); - ip_proto = key->ip_proto; + ip_proto = match.key->ip_proto; mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_PROTO, - key->ip_proto, mask->ip_proto); + match.key->ip_proto, + match.mask->ip_proto); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); - struct flow_dissector_key_eth_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + flow_rule_match_eth_addrs(rule, &match); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DMAC_32_47, - key->dst, mask->dst, 2); + match.key->dst, + match.mask->dst, 2); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DMAC_0_31, - key->dst + 2, mask->dst + 2, 4); + match.key->dst + 2, + match.mask->dst + 2, 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SMAC_32_47, - key->src, mask->src, 2); + match.key->src, + match.mask->src, 2); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SMAC_0_31, - key->src + 2, mask->src + 2, 4); + match.key->src + 2, + match.mask->src + 2, 4); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + flow_rule_match_vlan(rule, &match); if (mlxsw_sp_acl_block_is_egress_bound(block)) { NL_SET_ERR_MSG_MOD(f->common.extack, "vlan_id key is not supported on egress"); return -EOPNOTSUPP; } - if (mask->vlan_id != 0) + if (match.mask->vlan_id != 0) mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VID, - key->vlan_id, - mask->vlan_id); - if (mask->vlan_priority != 0) + match.key->vlan_id, + match.mask->vlan_id); + if (match.mask->vlan_priority != 0) mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_PCP, - key->vlan_priority, - mask->vlan_priority); + match.key->vlan_priority, + match.mask->vlan_priority); } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 8d54b36afee8..43192640bdd1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -587,6 +587,7 @@ static int nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow, char *nfp_action, int *a_len, u32 *csum_updated) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src; struct nfp_fl_set_ipv6_tc_hl_fl set_ip6_tc_hl_fl; struct nfp_fl_set_ip4_ttl_tos set_ip_ttl_tos; @@ -643,13 +644,11 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow, return err; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *basic; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->key); - ip_proto = basic->ip_proto; + flow_rule_match_basic(rule, &match); + ip_proto = match.key->ip_proto; } if (set_eth.head.len_lw) { diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index c04a0d6b0184..1279fa5da9e1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -8,31 +8,41 @@ #include "main.h" static void -nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *frame, - struct tc_cls_flower_offload *flow, u8 key_type, - bool mask_version) +nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext, + struct nfp_flower_meta_tci *msk, + struct tc_cls_flower_offload *flow, u8 key_type) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_vlan *flow_vlan; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); u16 tmp_tci; - memset(frame, 0, sizeof(struct nfp_flower_meta_tci)); + memset(ext, 0, sizeof(struct nfp_flower_meta_tci)); + memset(msk, 0, sizeof(struct nfp_flower_meta_tci)); + /* Populate the metadata frame. */ - frame->nfp_flow_key_layer = key_type; - frame->mask_id = ~0; + ext->nfp_flow_key_layer = key_type; + ext->mask_id = ~0; + + msk->nfp_flow_key_layer = key_type; + msk->mask_id = ~0; - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - flow_vlan = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_VLAN, - target); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); /* Populate the tci field. */ - if (flow_vlan->vlan_id || flow_vlan->vlan_priority) { + if (match.key->vlan_id || match.key->vlan_priority) { + tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, + match.key->vlan_priority) | + FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, + match.key->vlan_id) | + NFP_FLOWER_MASK_VLAN_CFI; + ext->tci = cpu_to_be16(tmp_tci); tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, - flow_vlan->vlan_priority) | + match.mask->vlan_priority) | FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, - flow_vlan->vlan_id) | + match.mask->vlan_id) | NFP_FLOWER_MASK_VLAN_CFI; - frame->tci = cpu_to_be16(tmp_tci); + msk->tci = cpu_to_be16(tmp_tci); } } } @@ -64,231 +74,244 @@ nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port, } static void -nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext, + struct nfp_flower_mac_mpls *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_eth_addrs *addr; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); - memset(frame, 0, sizeof(struct nfp_flower_mac_mpls)); + memset(ext, 0, sizeof(struct nfp_flower_mac_mpls)); + memset(msk, 0, sizeof(struct nfp_flower_mac_mpls)); - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - addr = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - target); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + + flow_rule_match_eth_addrs(rule, &match); /* Populate mac frame. */ - ether_addr_copy(frame->mac_dst, &addr->dst[0]); - ether_addr_copy(frame->mac_src, &addr->src[0]); + ether_addr_copy(ext->mac_dst, &match.key->dst[0]); + ether_addr_copy(ext->mac_src, &match.key->src[0]); + ether_addr_copy(msk->mac_dst, &match.mask->dst[0]); + ether_addr_copy(msk->mac_src, &match.mask->src[0]); } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) { - struct flow_dissector_key_mpls *mpls; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) { + struct flow_match_mpls match; u32 t_mpls; - mpls = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_MPLS, - target); - - t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, mpls->mpls_label) | - FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, mpls->mpls_tc) | - FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, mpls->mpls_bos) | + flow_rule_match_mpls(rule, &match); + t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.key->mpls_label) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.key->mpls_tc) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.key->mpls_bos) | NFP_FLOWER_MASK_MPLS_Q; - - frame->mpls_lse = cpu_to_be32(t_mpls); - } else if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC)) { + ext->mpls_lse = cpu_to_be32(t_mpls); + t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.mask->mpls_label) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.mask->mpls_tc) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.mask->mpls_bos) | + NFP_FLOWER_MASK_MPLS_Q; + msk->mpls_lse = cpu_to_be32(t_mpls); + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { /* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q * bit, which indicates an mpls ether type but without any * mpls fields. */ - struct flow_dissector_key_basic *key_basic; - - key_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->key); - if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) || - key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) - frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q); + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + if (match.key->n_proto == cpu_to_be16(ETH_P_MPLS_UC) || + match.key->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) { + ext->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q); + msk->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q); + } } } static void -nfp_flower_compile_tport(struct nfp_flower_tp_ports *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_tport(struct nfp_flower_tp_ports *ext, + struct nfp_flower_tp_ports *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ports *tp; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); - memset(frame, 0, sizeof(struct nfp_flower_tp_ports)); + memset(ext, 0, sizeof(struct nfp_flower_tp_ports)); + memset(msk, 0, sizeof(struct nfp_flower_tp_ports)); - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - tp = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_PORTS, - target); - frame->port_src = tp->src; - frame->port_dst = tp->dst; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); + ext->port_src = match.key->src; + ext->port_dst = match.key->dst; + msk->port_src = match.mask->src; + msk->port_dst = match.mask->dst; } } static void -nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext, + struct nfp_flower_ip_ext *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *basic; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - target); - frame->proto = basic->ip_proto; + flow_rule_match_basic(rule, &match); + ext->proto = match.key->ip_proto; + msk->proto = match.mask->ip_proto; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) { - struct flow_dissector_key_ip *flow_ip; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match; - flow_ip = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_IP, - target); - frame->tos = flow_ip->tos; - frame->ttl = flow_ip->ttl; + flow_rule_match_ip(rule, &match); + ext->tos = match.key->tos; + ext->ttl = match.key->ttl; + msk->tos = match.mask->tos; + msk->ttl = match.mask->ttl; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) { - struct flow_dissector_key_tcp *tcp; - u32 tcp_flags; - - tcp = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_TCP, target); - tcp_flags = be16_to_cpu(tcp->flags); - - if (tcp_flags & TCPHDR_FIN) - frame->flags |= NFP_FL_TCP_FLAG_FIN; - if (tcp_flags & TCPHDR_SYN) - frame->flags |= NFP_FL_TCP_FLAG_SYN; - if (tcp_flags & TCPHDR_RST) - frame->flags |= NFP_FL_TCP_FLAG_RST; - if (tcp_flags & TCPHDR_PSH) - frame->flags |= NFP_FL_TCP_FLAG_PSH; - if (tcp_flags & TCPHDR_URG) - frame->flags |= NFP_FL_TCP_FLAG_URG; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_match_tcp match; + u16 tcp_flags; + + flow_rule_match_tcp(rule, &match); + tcp_flags = be16_to_cpu(match.key->flags); + + if (tcp_flags & TCPHDR_FIN) { + ext->flags |= NFP_FL_TCP_FLAG_FIN; + msk->flags |= NFP_FL_TCP_FLAG_FIN; + } + if (tcp_flags & TCPHDR_SYN) { + ext->flags |= NFP_FL_TCP_FLAG_SYN; + msk->flags |= NFP_FL_TCP_FLAG_SYN; + } + if (tcp_flags & TCPHDR_RST) { + ext->flags |= NFP_FL_TCP_FLAG_RST; + msk->flags |= NFP_FL_TCP_FLAG_RST; + } + if (tcp_flags & TCPHDR_PSH) { + ext->flags |= NFP_FL_TCP_FLAG_PSH; + msk->flags |= NFP_FL_TCP_FLAG_PSH; + } + if (tcp_flags & TCPHDR_URG) { + ext->flags |= NFP_FL_TCP_FLAG_URG; + msk->flags |= NFP_FL_TCP_FLAG_URG; + } } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; - key = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - target); - if (key->flags & FLOW_DIS_IS_FRAGMENT) - frame->flags |= NFP_FL_IP_FRAGMENTED; - if (key->flags & FLOW_DIS_FIRST_FRAG) - frame->flags |= NFP_FL_IP_FRAG_FIRST; + flow_rule_match_control(rule, &match); + if (match.key->flags & FLOW_DIS_IS_FRAGMENT) { + ext->flags |= NFP_FL_IP_FRAGMENTED; + msk->flags |= NFP_FL_IP_FRAGMENTED; + } + if (match.key->flags & FLOW_DIS_FIRST_FRAG) { + ext->flags |= NFP_FL_IP_FRAG_FIRST; + msk->flags |= NFP_FL_IP_FRAG_FIRST; + } } } static void -nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext, + struct nfp_flower_ipv4 *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ipv4_addrs *addr; - - memset(frame, 0, sizeof(struct nfp_flower_ipv4)); - - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { - addr = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - target); - frame->ipv4_src = addr->src; - frame->ipv4_dst = addr->dst; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); + struct flow_match_ipv4_addrs match; + + memset(ext, 0, sizeof(struct nfp_flower_ipv4)); + memset(msk, 0, sizeof(struct nfp_flower_ipv4)); + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + flow_rule_match_ipv4_addrs(rule, &match); + ext->ipv4_src = match.key->src; + ext->ipv4_dst = match.key->dst; + msk->ipv4_src = match.mask->src; + msk->ipv4_dst = match.mask->dst; } - nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version); + nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, flow); } static void -nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *ext, + struct nfp_flower_ipv6 *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ipv6_addrs *addr; - - memset(frame, 0, sizeof(struct nfp_flower_ipv6)); - - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { - addr = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - target); - frame->ipv6_src = addr->src; - frame->ipv6_dst = addr->dst; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); + + memset(ext, 0, sizeof(struct nfp_flower_ipv6)); + memset(msk, 0, sizeof(struct nfp_flower_ipv6)); + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); + ext->ipv6_src = match.key->src; + ext->ipv6_dst = match.key->dst; + msk->ipv6_src = match.mask->src; + msk->ipv6_dst = match.mask->dst; } - nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version); + nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, flow); } static int -nfp_flower_compile_geneve_opt(void *key_buf, struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_geneve_opt(void *ext, void *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_enc_opts *opts; + struct flow_match_enc_opts match; - opts = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_OPTS, - target); - memcpy(key_buf, opts->data, opts->len); + flow_rule_match_enc_opts(flow->rule, &match); + memcpy(ext, match.key->data, match.key->len); + memcpy(msk, match.mask->data, match.mask->len); return 0; } static void -nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *ext, + struct nfp_flower_ipv4_udp_tun *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ipv4_addrs *tun_ips; - struct flow_dissector_key_keyid *vni; - struct flow_dissector_key_ip *ip; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); - memset(frame, 0, sizeof(struct nfp_flower_ipv4_udp_tun)); + memset(ext, 0, sizeof(struct nfp_flower_ipv4_udp_tun)); + memset(msk, 0, sizeof(struct nfp_flower_ipv4_udp_tun)); - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; u32 temp_vni; - vni = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - target); - temp_vni = be32_to_cpu(vni->keyid) << NFP_FL_TUN_VNI_OFFSET; - frame->tun_id = cpu_to_be32(temp_vni); + flow_rule_match_enc_keyid(rule, &match); + temp_vni = be32_to_cpu(match.key->keyid) << NFP_FL_TUN_VNI_OFFSET; + ext->tun_id = cpu_to_be32(temp_vni); + temp_vni = be32_to_cpu(match.mask->keyid) << NFP_FL_TUN_VNI_OFFSET; + msk->tun_id = cpu_to_be32(temp_vni); } - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { - tun_ips = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, - target); - frame->ip_src = tun_ips->src; - frame->ip_dst = tun_ips->dst; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_enc_ipv4_addrs(rule, &match); + ext->ip_src = match.key->src; + ext->ip_dst = match.key->dst; + msk->ip_src = match.mask->src; + msk->ip_dst = match.mask->dst; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { - ip = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_IP, - target); - frame->tos = ip->tos; - frame->ttl = ip->ttl; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) { + struct flow_match_ip match; + + flow_rule_match_enc_ip(rule, &match); + ext->tos = match.key->tos; + ext->ttl = match.key->ttl; + msk->tos = match.mask->tos; + msk->ttl = match.mask->ttl; } } @@ -313,12 +336,9 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, ext = nfp_flow->unmasked_data; msk = nfp_flow->mask_data; - /* Populate Exact Metadata. */ nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)ext, - flow, key_ls->key_layer, false); - /* Populate Mask Metadata. */ - nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)msk, - flow, key_ls->key_layer, true); + (struct nfp_flower_meta_tci *)msk, + flow, key_ls->key_layer); ext += sizeof(struct nfp_flower_meta_tci); msk += sizeof(struct nfp_flower_meta_tci); @@ -348,45 +368,33 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, msk += sizeof(struct nfp_flower_in_port); if (NFP_FLOWER_LAYER_MAC & key_ls->key_layer) { - /* Populate Exact MAC Data. */ nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)ext, - flow, false); - /* Populate Mask MAC Data. */ - nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)msk, - flow, true); + (struct nfp_flower_mac_mpls *)msk, + flow); ext += sizeof(struct nfp_flower_mac_mpls); msk += sizeof(struct nfp_flower_mac_mpls); } if (NFP_FLOWER_LAYER_TP & key_ls->key_layer) { - /* Populate Exact TP Data. */ nfp_flower_compile_tport((struct nfp_flower_tp_ports *)ext, - flow, false); - /* Populate Mask TP Data. */ - nfp_flower_compile_tport((struct nfp_flower_tp_ports *)msk, - flow, true); + (struct nfp_flower_tp_ports *)msk, + flow); ext += sizeof(struct nfp_flower_tp_ports); msk += sizeof(struct nfp_flower_tp_ports); } if (NFP_FLOWER_LAYER_IPV4 & key_ls->key_layer) { - /* Populate Exact IPv4 Data. */ nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)ext, - flow, false); - /* Populate Mask IPv4 Data. */ - nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)msk, - flow, true); + (struct nfp_flower_ipv4 *)msk, + flow); ext += sizeof(struct nfp_flower_ipv4); msk += sizeof(struct nfp_flower_ipv4); } if (NFP_FLOWER_LAYER_IPV6 & key_ls->key_layer) { - /* Populate Exact IPv4 Data. */ nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)ext, - flow, false); - /* Populate Mask IPv4 Data. */ - nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)msk, - flow, true); + (struct nfp_flower_ipv6 *)msk, + flow); ext += sizeof(struct nfp_flower_ipv6); msk += sizeof(struct nfp_flower_ipv6); } @@ -395,10 +403,7 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE) { __be32 tun_dst; - /* Populate Exact VXLAN Data. */ - nfp_flower_compile_ipv4_udp_tun((void *)ext, flow, false); - /* Populate Mask VXLAN Data. */ - nfp_flower_compile_ipv4_udp_tun((void *)msk, flow, true); + nfp_flower_compile_ipv4_udp_tun((void *)ext, (void *)msk, flow); tun_dst = ((struct nfp_flower_ipv4_udp_tun *)ext)->ip_dst; ext += sizeof(struct nfp_flower_ipv4_udp_tun); msk += sizeof(struct nfp_flower_ipv4_udp_tun); @@ -410,11 +415,7 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, nfp_tunnel_add_ipv4_off(app, tun_dst); if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) { - err = nfp_flower_compile_geneve_opt(ext, flow, false); - if (err) - return err; - - err = nfp_flower_compile_geneve_opt(msk, flow, true); + err = nfp_flower_compile_geneve_opt(ext, msk, flow); if (err) return err; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 2cdbf29ecbe7..74f7ff292052 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -102,23 +102,22 @@ nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow, static bool nfp_flower_check_higher_than_mac(struct tc_cls_flower_offload *f) { - return dissector_uses_key(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS) || - dissector_uses_key(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS) || - dissector_uses_key(f->dissector, - FLOW_DISSECTOR_KEY_PORTS) || - dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ICMP); + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + + return flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP); } static int -nfp_flower_calc_opt_layer(struct flow_dissector_key_enc_opts *enc_opts, +nfp_flower_calc_opt_layer(struct flow_match_enc_opts *enc_opts, u32 *key_layer_two, int *key_size) { - if (enc_opts->len > NFP_FL_MAX_GENEVE_OPT_KEY) + if (enc_opts->key->len > NFP_FL_MAX_GENEVE_OPT_KEY) return -EOPNOTSUPP; - if (enc_opts->len > 0) { + if (enc_opts->key->len > 0) { *key_layer_two |= NFP_FLOWER_LAYER2_GENEVE_OP; *key_size += sizeof(struct nfp_flower_geneve_options); } @@ -133,20 +132,21 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, struct tc_cls_flower_offload *flow, enum nfp_flower_tun_type *tun_type) { - struct flow_dissector_key_basic *mask_basic = NULL; - struct flow_dissector_key_basic *key_basic = NULL; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); + struct flow_dissector *dissector = rule->match.dissector; + struct flow_match_basic basic = { NULL, NULL}; struct nfp_flower_priv *priv = app->priv; u32 key_layer_two; u8 key_layer; int key_size; int err; - if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR) + if (dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR) return -EOPNOTSUPP; /* If any tun dissector is used then the required set must be used. */ - if (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR && - (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R) + if (dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR && + (dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R) != NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R) return -EOPNOTSUPP; @@ -155,76 +155,53 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, key_size = sizeof(struct nfp_flower_meta_tci) + sizeof(struct nfp_flower_in_port); - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS) || - dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) { key_layer |= NFP_FLOWER_LAYER_MAC; key_size += sizeof(struct nfp_flower_mac_mpls); } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *flow_vlan; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan vlan; - flow_vlan = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_VLAN, - flow->mask); + flow_rule_match_vlan(rule, &vlan); if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_PCP) && - flow_vlan->vlan_priority) + vlan.key->vlan_priority) return -EOPNOTSUPP; } - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL)) { - struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL; - struct flow_dissector_key_ports *mask_enc_ports = NULL; - struct flow_dissector_key_enc_opts *enc_op = NULL; - struct flow_dissector_key_ports *enc_ports = NULL; - struct flow_dissector_key_control *mask_enc_ctl = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL, - flow->mask); - struct flow_dissector_key_control *enc_ctl = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL, - flow->key); - - if (mask_enc_ctl->addr_type != 0xffff || - enc_ctl->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS) + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + struct flow_match_enc_opts enc_op = { NULL, NULL }; + struct flow_match_ipv4_addrs ipv4_addrs; + struct flow_match_control enc_ctl; + struct flow_match_ports enc_ports; + + flow_rule_match_enc_control(rule, &enc_ctl); + + if (enc_ctl.mask->addr_type != 0xffff || + enc_ctl.key->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS) return -EOPNOTSUPP; /* These fields are already verified as used. */ - mask_ipv4 = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, - flow->mask); - if (mask_ipv4->dst != cpu_to_be32(~0)) + flow_rule_match_enc_ipv4_addrs(rule, &ipv4_addrs); + if (ipv4_addrs.mask->dst != cpu_to_be32(~0)) return -EOPNOTSUPP; - mask_enc_ports = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - flow->mask); - enc_ports = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - flow->key); - if (mask_enc_ports->dst != cpu_to_be16(~0)) + flow_rule_match_enc_ports(rule, &enc_ports); + if (enc_ports.mask->dst != cpu_to_be16(~0)) return -EOPNOTSUPP; - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_OPTS)) { - enc_op = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_OPTS, - flow->key); - } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) + flow_rule_match_enc_opts(rule, &enc_op); - switch (enc_ports->dst) { + switch (enc_ports.key->dst) { case htons(NFP_FL_VXLAN_PORT): *tun_type = NFP_FL_TUNNEL_VXLAN; key_layer |= NFP_FLOWER_LAYER_VXLAN; key_size += sizeof(struct nfp_flower_ipv4_udp_tun); - if (enc_op) + if (enc_op.key) return -EOPNOTSUPP; break; case htons(NFP_FL_GENEVE_PORT): @@ -236,11 +213,11 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, key_layer_two |= NFP_FLOWER_LAYER2_GENEVE; key_size += sizeof(struct nfp_flower_ipv4_udp_tun); - if (!enc_op) + if (!enc_op.key) break; if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT)) return -EOPNOTSUPP; - err = nfp_flower_calc_opt_layer(enc_op, &key_layer_two, + err = nfp_flower_calc_opt_layer(&enc_op, &key_layer_two, &key_size); if (err) return err; @@ -254,19 +231,12 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, return -EOPNOTSUPP; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - mask_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) + flow_rule_match_basic(rule, &basic); - key_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->key); - } - - if (mask_basic && mask_basic->n_proto) { + if (basic.mask && basic.mask->n_proto) { /* Ethernet type is present in the key. */ - switch (key_basic->n_proto) { + switch (basic.key->n_proto) { case cpu_to_be16(ETH_P_IP): key_layer |= NFP_FLOWER_LAYER_IPV4; key_size += sizeof(struct nfp_flower_ipv4); @@ -305,9 +275,9 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } } - if (mask_basic && mask_basic->ip_proto) { + if (basic.mask && basic.mask->ip_proto) { /* Ethernet type is present in the key. */ - switch (key_basic->ip_proto) { + switch (basic.key->ip_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_SCTP: @@ -324,14 +294,12 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) { - struct flow_dissector_key_tcp *tcp; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_match_tcp tcp; u32 tcp_flags; - tcp = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_TCP, - flow->key); - tcp_flags = be16_to_cpu(tcp->flags); + flow_rule_match_tcp(rule, &tcp); + tcp_flags = be16_to_cpu(tcp.key->flags); if (tcp_flags & ~NFP_FLOWER_SUPPORTED_TCPFLAGS) return -EOPNOTSUPP; @@ -347,12 +315,12 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, * space, thus we need to ensure we include a IPv4/IPv6 key * layer if we have not done so already. */ - if (!key_basic) + if (!basic.key) return -EOPNOTSUPP; if (!(key_layer & NFP_FLOWER_LAYER_IPV4) && !(key_layer & NFP_FLOWER_LAYER_IPV6)) { - switch (key_basic->n_proto) { + switch (basic.key->n_proto) { case cpu_to_be16(ETH_P_IP): key_layer |= NFP_FLOWER_LAYER_IPV4; key_size += sizeof(struct nfp_flower_ipv4); @@ -369,14 +337,11 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key_ctl; - - key_ctl = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - flow->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control ctl; - if (key_ctl->flags & ~NFP_FLOWER_SUPPORTED_CTLFLAGS) + flow_rule_match_control(rule, &ctl); + if (ctl.key->flags & ~NFP_FLOWER_SUPPORTED_CTLFLAGS) return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index b16ce7d93caf..81d5b9304229 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -2033,24 +2033,20 @@ qede_tc_parse_ports(struct qede_dev *edev, struct tc_cls_flower_offload *f, struct qede_arfs_tuple *t) { - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key, *mask; - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); - - if ((key->src && mask->src != U16_MAX) || - (key->dst && mask->dst != U16_MAX)) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); + if ((match.key->src && match.mask->src != U16_MAX) || + (match.key->dst && match.mask->dst != U16_MAX)) { DP_NOTICE(edev, "Do not support ports masks\n"); return -EINVAL; } - t->src_port = key->src; - t->dst_port = key->dst; + t->src_port = match.key->src; + t->dst_port = match.key->dst; } return 0; @@ -2061,32 +2057,27 @@ qede_tc_parse_v6_common(struct qede_dev *edev, struct tc_cls_flower_offload *f, struct qede_arfs_tuple *t) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); struct in6_addr zero_addr, addr; memset(&zero_addr, 0, sizeof(addr)); memset(&addr, 0xff, sizeof(addr)); - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { - struct flow_dissector_key_ipv6_addrs *key, *mask; - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_match_ipv6_addrs match; - if ((memcmp(&key->src, &zero_addr, sizeof(addr)) && - memcmp(&mask->src, &addr, sizeof(addr))) || - (memcmp(&key->dst, &zero_addr, sizeof(addr)) && - memcmp(&mask->dst, &addr, sizeof(addr)))) { + flow_rule_match_ipv6_addrs(rule, &match); + if ((memcmp(&match.key->src, &zero_addr, sizeof(addr)) && + memcmp(&match.mask->src, &addr, sizeof(addr))) || + (memcmp(&match.key->dst, &zero_addr, sizeof(addr)) && + memcmp(&match.mask->dst, &addr, sizeof(addr)))) { DP_NOTICE(edev, "Do not support IPv6 address prefix/mask\n"); return -EINVAL; } - memcpy(&t->src_ipv6, &key->src, sizeof(addr)); - memcpy(&t->dst_ipv6, &key->dst, sizeof(addr)); + memcpy(&t->src_ipv6, &match.key->src, sizeof(addr)); + memcpy(&t->dst_ipv6, &match.key->dst, sizeof(addr)); } if (qede_tc_parse_ports(edev, f, t)) @@ -2100,24 +2091,20 @@ qede_tc_parse_v4_common(struct qede_dev *edev, struct tc_cls_flower_offload *f, struct qede_arfs_tuple *t) { - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { - struct flow_dissector_key_ipv4_addrs *key, *mask; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match; - if ((key->src && mask->src != U32_MAX) || - (key->dst && mask->dst != U32_MAX)) { + flow_rule_match_ipv4_addrs(rule, &match); + if ((match.key->src && match.mask->src != U32_MAX) || + (match.key->dst && match.mask->dst != U32_MAX)) { DP_NOTICE(edev, "Do not support ipv4 prefix/masks\n"); return -EINVAL; } - t->src_ipv4 = key->src; - t->dst_ipv4 = key->dst; + t->src_ipv4 = match.key->src; + t->dst_ipv4 = match.key->dst; } if (qede_tc_parse_ports(edev, f, t)) @@ -2175,19 +2162,21 @@ qede_parse_flower_attr(struct qede_dev *edev, __be16 proto, struct tc_cls_flower_offload *f, struct qede_arfs_tuple *tuple) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; int rc = -EINVAL; u8 ip_proto = 0; memset(tuple, 0, sizeof(*tuple)); - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | BIT(FLOW_DISSECTOR_KEY_PORTS))) { DP_NOTICE(edev, "Unsupported key set:0x%x\n", - f->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } @@ -2197,13 +2186,11 @@ qede_parse_flower_attr(struct qede_dev *edev, __be16 proto, return -EPROTONOSUPPORT; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - ip_proto = key->ip_proto; + flow_rule_match_basic(rule, &match); + ip_proto = match.key->ip_proto; } if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IP)) diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h new file mode 100644 index 000000000000..461c66595763 --- /dev/null +++ b/include/net/flow_offload.h @@ -0,0 +1,115 @@ +#ifndef _NET_FLOW_OFFLOAD_H +#define _NET_FLOW_OFFLOAD_H + +#include + +struct flow_match { + struct flow_dissector *dissector; + void *mask; + void *key; +}; + +struct flow_match_basic { + struct flow_dissector_key_basic *key, *mask; +}; + +struct flow_match_control { + struct flow_dissector_key_control *key, *mask; +}; + +struct flow_match_eth_addrs { + struct flow_dissector_key_eth_addrs *key, *mask; +}; + +struct flow_match_vlan { + struct flow_dissector_key_vlan *key, *mask; +}; + +struct flow_match_ipv4_addrs { + struct flow_dissector_key_ipv4_addrs *key, *mask; +}; + +struct flow_match_ipv6_addrs { + struct flow_dissector_key_ipv6_addrs *key, *mask; +}; + +struct flow_match_ip { + struct flow_dissector_key_ip *key, *mask; +}; + +struct flow_match_ports { + struct flow_dissector_key_ports *key, *mask; +}; + +struct flow_match_icmp { + struct flow_dissector_key_icmp *key, *mask; +}; + +struct flow_match_tcp { + struct flow_dissector_key_tcp *key, *mask; +}; + +struct flow_match_mpls { + struct flow_dissector_key_mpls *key, *mask; +}; + +struct flow_match_enc_keyid { + struct flow_dissector_key_keyid *key, *mask; +}; + +struct flow_match_enc_opts { + struct flow_dissector_key_enc_opts *key, *mask; +}; + +struct flow_rule; + +void flow_rule_match_basic(const struct flow_rule *rule, + struct flow_match_basic *out); +void flow_rule_match_control(const struct flow_rule *rule, + struct flow_match_control *out); +void flow_rule_match_eth_addrs(const struct flow_rule *rule, + struct flow_match_eth_addrs *out); +void flow_rule_match_vlan(const struct flow_rule *rule, + struct flow_match_vlan *out); +void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out); +void flow_rule_match_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out); +void flow_rule_match_ip(const struct flow_rule *rule, + struct flow_match_ip *out); +void flow_rule_match_ports(const struct flow_rule *rule, + struct flow_match_ports *out); +void flow_rule_match_tcp(const struct flow_rule *rule, + struct flow_match_tcp *out); +void flow_rule_match_icmp(const struct flow_rule *rule, + struct flow_match_icmp *out); +void flow_rule_match_mpls(const struct flow_rule *rule, + struct flow_match_mpls *out); +void flow_rule_match_enc_control(const struct flow_rule *rule, + struct flow_match_control *out); +void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out); +void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out); +void flow_rule_match_enc_ip(const struct flow_rule *rule, + struct flow_match_ip *out); +void flow_rule_match_enc_ports(const struct flow_rule *rule, + struct flow_match_ports *out); +void flow_rule_match_enc_keyid(const struct flow_rule *rule, + struct flow_match_enc_keyid *out); +void flow_rule_match_enc_opts(const struct flow_rule *rule, + struct flow_match_enc_opts *out); + +struct flow_rule { + struct flow_match match; +}; + +struct flow_rule *flow_rule_alloc(void); + +static inline bool flow_rule_match_key(const struct flow_rule *rule, + enum flow_dissector_key_id key) +{ + return dissector_uses_key(rule->match.dissector, key); +} + +#endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 40965fbbcd31..04b64523cc32 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -6,6 +6,7 @@ #include #include #include +#include /* TC action not accessible from user space */ #define TC_ACT_REINSERT (TC_ACT_VALUE_MAX + 1) @@ -760,13 +761,17 @@ struct tc_cls_flower_offload { struct tc_cls_common_offload common; enum tc_fl_command command; unsigned long cookie; - struct flow_dissector *dissector; - struct fl_flow_key *mask; - struct fl_flow_key *key; + struct flow_rule *rule; struct tcf_exts *exts; u32 classid; }; +static inline struct flow_rule * +tc_cls_flower_offload_flow_rule(struct tc_cls_flower_offload *tc_flow_cmd) +{ + return tc_flow_cmd->rule; +} + enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, diff --git a/net/core/Makefile b/net/core/Makefile index fccd31e0e7f7..f97d6254e564 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ - fib_notifier.o xdp.o + fib_notifier.o xdp.o flow_offload.o obj-y += net-sysfs.o obj-$(CONFIG_PAGE_POOL) += page_pool.o diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c new file mode 100644 index 000000000000..2fbf6903d2f6 --- /dev/null +++ b/net/core/flow_offload.c @@ -0,0 +1,143 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include +#include +#include + +struct flow_rule *flow_rule_alloc(void) +{ + return kzalloc(sizeof(struct flow_rule), GFP_KERNEL); +} +EXPORT_SYMBOL(flow_rule_alloc); + +#define FLOW_DISSECTOR_MATCH(__rule, __type, __out) \ + const struct flow_match *__m = &(__rule)->match; \ + struct flow_dissector *__d = (__m)->dissector; \ + \ + (__out)->key = skb_flow_dissector_target(__d, __type, (__m)->key); \ + (__out)->mask = skb_flow_dissector_target(__d, __type, (__m)->mask); \ + +void flow_rule_match_basic(const struct flow_rule *rule, + struct flow_match_basic *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_BASIC, out); +} +EXPORT_SYMBOL(flow_rule_match_basic); + +void flow_rule_match_control(const struct flow_rule *rule, + struct flow_match_control *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CONTROL, out); +} +EXPORT_SYMBOL(flow_rule_match_control); + +void flow_rule_match_eth_addrs(const struct flow_rule *rule, + struct flow_match_eth_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_eth_addrs); + +void flow_rule_match_vlan(const struct flow_rule *rule, + struct flow_match_vlan *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_VLAN, out); +} +EXPORT_SYMBOL(flow_rule_match_vlan); + +void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_ipv4_addrs); + +void flow_rule_match_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_ipv6_addrs); + +void flow_rule_match_ip(const struct flow_rule *rule, + struct flow_match_ip *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IP, out); +} +EXPORT_SYMBOL(flow_rule_match_ip); + +void flow_rule_match_ports(const struct flow_rule *rule, + struct flow_match_ports *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_PORTS, out); +} +EXPORT_SYMBOL(flow_rule_match_ports); + +void flow_rule_match_tcp(const struct flow_rule *rule, + struct flow_match_tcp *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_TCP, out); +} +EXPORT_SYMBOL(flow_rule_match_tcp); + +void flow_rule_match_icmp(const struct flow_rule *rule, + struct flow_match_icmp *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ICMP, out); +} +EXPORT_SYMBOL(flow_rule_match_icmp); + +void flow_rule_match_mpls(const struct flow_rule *rule, + struct flow_match_mpls *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_MPLS, out); +} +EXPORT_SYMBOL(flow_rule_match_mpls); + +void flow_rule_match_enc_control(const struct flow_rule *rule, + struct flow_match_control *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_control); + +void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ipv4_addrs); + +void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ipv6_addrs); + +void flow_rule_match_enc_ip(const struct flow_rule *rule, + struct flow_match_ip *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IP, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ip); + +void flow_rule_match_enc_ports(const struct flow_rule *rule, + struct flow_match_ports *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_PORTS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ports); + +void flow_rule_match_enc_keyid(const struct flow_rule *rule, + struct flow_match_enc_keyid *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_KEYID, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_keyid); + +void flow_rule_match_enc_opts(const struct flow_rule *rule, + struct flow_match_enc_opts *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_OPTS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_opts); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f6aa57fbbbaf..aaffea0b66e9 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -381,16 +381,22 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, bool skip_sw = tc_skip_sw(f->flags); int err; + cls_flower.rule = flow_rule_alloc(); + if (!cls_flower.rule) + return -ENOMEM; + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; - cls_flower.dissector = &f->mask->dissector; - cls_flower.mask = &f->mask->key; - cls_flower.key = &f->mkey; + cls_flower.rule->match.dissector = &f->mask->dissector; + cls_flower.rule->match.mask = &f->mask->key; + cls_flower.rule->match.key = &f->mkey; cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; err = tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw); + kfree(cls_flower.rule); + if (err < 0) { fl_hw_destroy_filter(tp, f, NULL); return err; @@ -1463,18 +1469,24 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, if (tc_skip_hw(f->flags)) continue; + cls_flower.rule = flow_rule_alloc(); + if (!cls_flower.rule) + return -ENOMEM; + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = add ? TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long)f; - cls_flower.dissector = &mask->dissector; - cls_flower.mask = &mask->key; - cls_flower.key = &f->mkey; + cls_flower.rule->match.dissector = &mask->dissector; + cls_flower.rule->match.mask = &mask->key; + cls_flower.rule->match.key = &f->mkey; cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + kfree(cls_flower.rule); + if (err) { if (add && tc_skip_sw(f->flags)) return err; @@ -1489,25 +1501,32 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, return 0; } -static void fl_hw_create_tmplt(struct tcf_chain *chain, - struct fl_flow_tmplt *tmplt) +static int fl_hw_create_tmplt(struct tcf_chain *chain, + struct fl_flow_tmplt *tmplt) { struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = chain->block; struct tcf_exts dummy_exts = { 0, }; + cls_flower.rule = flow_rule_alloc(); + if (!cls_flower.rule) + return -ENOMEM; + cls_flower.common.chain_index = chain->index; cls_flower.command = TC_CLSFLOWER_TMPLT_CREATE; cls_flower.cookie = (unsigned long) tmplt; - cls_flower.dissector = &tmplt->dissector; - cls_flower.mask = &tmplt->mask; - cls_flower.key = &tmplt->dummy_key; + cls_flower.rule->match.dissector = &tmplt->dissector; + cls_flower.rule->match.mask = &tmplt->mask; + cls_flower.rule->match.key = &tmplt->dummy_key; cls_flower.exts = &dummy_exts; /* We don't care if driver (any of them) fails to handle this * call. It serves just as a hint for it. */ tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + kfree(cls_flower.rule); + + return 0; } static void fl_hw_destroy_tmplt(struct tcf_chain *chain, @@ -1551,12 +1570,14 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack); if (err) goto errout_tmplt; - kfree(tb); fl_init_dissector(&tmplt->dissector, &tmplt->mask); - fl_hw_create_tmplt(chain, tmplt); + err = fl_hw_create_tmplt(chain, tmplt); + if (err) + goto errout_tmplt; + kfree(tb); return tmplt; errout_tmplt: -- cgit v1.2.3 From e3ab786b42535da00c731c3585165e88bf35ab09 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 2 Feb 2019 12:50:45 +0100 Subject: flow_offload: add flow action infrastructure This new infrastructure defines the nic actions that you can perform from existing network drivers. This infrastructure allows us to avoid a direct dependency with the native software TC action representation. Signed-off-by: Pablo Neira Ayuso Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/flow_offload.h | 69 +++++++++++++++++++++++++++++++++++++++++++++- include/net/pkt_cls.h | 1 + net/core/flow_offload.c | 14 ++++++++-- net/sched/cls_api.c | 17 ++++++++++++ net/sched/cls_flower.c | 7 +++-- 5 files changed, 102 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 461c66595763..dabc819b6cc9 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -100,11 +100,78 @@ void flow_rule_match_enc_keyid(const struct flow_rule *rule, void flow_rule_match_enc_opts(const struct flow_rule *rule, struct flow_match_enc_opts *out); +enum flow_action_id { + FLOW_ACTION_ACCEPT = 0, + FLOW_ACTION_DROP, + FLOW_ACTION_TRAP, + FLOW_ACTION_GOTO, + FLOW_ACTION_REDIRECT, + FLOW_ACTION_MIRRED, + FLOW_ACTION_VLAN_PUSH, + FLOW_ACTION_VLAN_POP, + FLOW_ACTION_VLAN_MANGLE, + FLOW_ACTION_TUNNEL_ENCAP, + FLOW_ACTION_TUNNEL_DECAP, + FLOW_ACTION_MANGLE, + FLOW_ACTION_ADD, + FLOW_ACTION_CSUM, + FLOW_ACTION_MARK, +}; + +/* This is mirroring enum pedit_header_type definition for easy mapping between + * tc pedit action. Legacy TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK is mapped to + * FLOW_ACT_MANGLE_UNSPEC, which is supported by no driver. + */ +enum flow_action_mangle_base { + FLOW_ACT_MANGLE_UNSPEC = 0, + FLOW_ACT_MANGLE_HDR_TYPE_ETH, + FLOW_ACT_MANGLE_HDR_TYPE_IP4, + FLOW_ACT_MANGLE_HDR_TYPE_IP6, + FLOW_ACT_MANGLE_HDR_TYPE_TCP, + FLOW_ACT_MANGLE_HDR_TYPE_UDP, +}; + +struct flow_action_entry { + enum flow_action_id id; + union { + u32 chain_index; /* FLOW_ACTION_GOTO */ + struct net_device *dev; /* FLOW_ACTION_REDIRECT */ + struct { /* FLOW_ACTION_VLAN */ + u16 vid; + __be16 proto; + u8 prio; + } vlan; + struct { /* FLOW_ACTION_PACKET_EDIT */ + enum flow_action_mangle_base htype; + u32 offset; + u32 mask; + u32 val; + } mangle; + const struct ip_tunnel_info *tunnel; /* FLOW_ACTION_TUNNEL_ENCAP */ + u32 csum_flags; /* FLOW_ACTION_CSUM */ + u32 mark; /* FLOW_ACTION_MARK */ + }; +}; + +struct flow_action { + unsigned int num_entries; + struct flow_action_entry entries[0]; +}; + +static inline bool flow_action_has_entries(const struct flow_action *action) +{ + return action->num_entries; +} + +#define flow_action_for_each(__i, __act, __actions) \ + for (__i = 0, __act = &(__actions)->entries[0]; __i < (__actions)->num_entries; __act = &(__actions)->entries[__i++]) + struct flow_rule { struct flow_match match; + struct flow_action action; }; -struct flow_rule *flow_rule_alloc(void); +struct flow_rule *flow_rule_alloc(unsigned int num_actions); static inline bool flow_rule_match_key(const struct flow_rule *rule, enum flow_dissector_key_id key) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 04b64523cc32..74a7582ad47c 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -622,6 +622,7 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop); +unsigned int tcf_exts_num_actions(struct tcf_exts *exts); enum tc_block_command { TC_BLOCK_BIND, diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 2fbf6903d2f6..c3a00eac4804 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -3,9 +3,19 @@ #include #include -struct flow_rule *flow_rule_alloc(void) +struct flow_rule *flow_rule_alloc(unsigned int num_actions) { - return kzalloc(sizeof(struct flow_rule), GFP_KERNEL); + struct flow_rule *rule; + + rule = kzalloc(sizeof(struct flow_rule) + + sizeof(struct flow_action_entry) * num_actions, + GFP_KERNEL); + if (!rule) + return NULL; + + rule->action.num_entries = num_actions; + + return rule; } EXPORT_SYMBOL(flow_rule_alloc); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e2b5cb2eb34e..57713c63ac56 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -31,6 +31,7 @@ #include #include #include +#include extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; @@ -2515,6 +2516,22 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, } EXPORT_SYMBOL(tc_setup_cb_call); +unsigned int tcf_exts_num_actions(struct tcf_exts *exts) +{ + unsigned int num_acts = 0; + struct tc_action *act; + int i; + + tcf_exts_for_each_action(i, act, exts) { + if (is_tcf_pedit(act)) + num_acts += tcf_pedit_nkeys(act); + else + num_acts++; + } + return num_acts; +} +EXPORT_SYMBOL(tcf_exts_num_actions); + static __net_init int tcf_net_init(struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index aaffea0b66e9..0062c9133a22 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -381,7 +381,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, bool skip_sw = tc_skip_sw(f->flags); int err; - cls_flower.rule = flow_rule_alloc(); + cls_flower.rule = flow_rule_alloc(tcf_exts_num_actions(&f->exts)); if (!cls_flower.rule) return -ENOMEM; @@ -1469,7 +1469,8 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, if (tc_skip_hw(f->flags)) continue; - cls_flower.rule = flow_rule_alloc(); + cls_flower.rule = + flow_rule_alloc(tcf_exts_num_actions(&f->exts)); if (!cls_flower.rule) return -ENOMEM; @@ -1508,7 +1509,7 @@ static int fl_hw_create_tmplt(struct tcf_chain *chain, struct tcf_block *block = chain->block; struct tcf_exts dummy_exts = { 0, }; - cls_flower.rule = flow_rule_alloc(); + cls_flower.rule = flow_rule_alloc(0); if (!cls_flower.rule) return -ENOMEM; -- cgit v1.2.3 From 3a7b68617de749d930b5503c3c5f30a17524f0bd Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 2 Feb 2019 12:50:46 +0100 Subject: cls_api: add translator to flow_action representation This patch implements a new function to translate from native TC action to the new flow_action representation. Moreover, this patch also updates cls_flower to use this new function. Signed-off-by: Pablo Neira Ayuso Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 2 + net/sched/cls_api.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++ net/sched/cls_flower.c | 14 +++++++ 3 files changed, 115 insertions(+) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 74a7582ad47c..c470c100b926 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -620,6 +620,8 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } #endif /* CONFIG_NET_CLS_IND */ +int tc_setup_flow_action(struct flow_action *flow_action, + const struct tcf_exts *exts); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop); unsigned int tcf_exts_num_actions(struct tcf_exts *exts); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 57713c63ac56..02cf6d2fa0e1 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -32,6 +32,13 @@ #include #include #include +#include +#include +#include +#include +#include +#include +#include extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; @@ -2516,6 +2523,98 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, } EXPORT_SYMBOL(tc_setup_cb_call); +int tc_setup_flow_action(struct flow_action *flow_action, + const struct tcf_exts *exts) +{ + const struct tc_action *act; + int i, j, k; + + if (!exts) + return 0; + + j = 0; + tcf_exts_for_each_action(i, act, exts) { + struct flow_action_entry *entry; + + entry = &flow_action->entries[j]; + if (is_tcf_gact_ok(act)) { + entry->id = FLOW_ACTION_ACCEPT; + } else if (is_tcf_gact_shot(act)) { + entry->id = FLOW_ACTION_DROP; + } else if (is_tcf_gact_trap(act)) { + entry->id = FLOW_ACTION_TRAP; + } else if (is_tcf_gact_goto_chain(act)) { + entry->id = FLOW_ACTION_GOTO; + entry->chain_index = tcf_gact_goto_chain_index(act); + } else if (is_tcf_mirred_egress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_egress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_vlan(act)) { + switch (tcf_vlan_action(act)) { + case TCA_VLAN_ACT_PUSH: + entry->id = FLOW_ACTION_VLAN_PUSH; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + case TCA_VLAN_ACT_POP: + entry->id = FLOW_ACTION_VLAN_POP; + break; + case TCA_VLAN_ACT_MODIFY: + entry->id = FLOW_ACTION_VLAN_MANGLE; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + default: + goto err_out; + } + } else if (is_tcf_tunnel_set(act)) { + entry->id = FLOW_ACTION_TUNNEL_ENCAP; + entry->tunnel = tcf_tunnel_info(act); + } else if (is_tcf_tunnel_release(act)) { + entry->id = FLOW_ACTION_TUNNEL_DECAP; + entry->tunnel = tcf_tunnel_info(act); + } else if (is_tcf_pedit(act)) { + for (k = 0; k < tcf_pedit_nkeys(act); k++) { + switch (tcf_pedit_cmd(act, k)) { + case TCA_PEDIT_KEY_EX_CMD_SET: + entry->id = FLOW_ACTION_MANGLE; + break; + case TCA_PEDIT_KEY_EX_CMD_ADD: + entry->id = FLOW_ACTION_ADD; + break; + default: + goto err_out; + } + entry->mangle.htype = tcf_pedit_htype(act, k); + entry->mangle.mask = tcf_pedit_mask(act, k); + entry->mangle.val = tcf_pedit_val(act, k); + entry->mangle.offset = tcf_pedit_offset(act, k); + entry = &flow_action->entries[++j]; + } + } else if (is_tcf_csum(act)) { + entry->id = FLOW_ACTION_CSUM; + entry->csum_flags = tcf_csum_update_flags(act); + } else if (is_tcf_skbedit_mark(act)) { + entry->id = FLOW_ACTION_MARK; + entry->mark = tcf_skbedit_mark(act); + } else { + goto err_out; + } + + if (!is_tcf_pedit(act)) + j++; + } + return 0; +err_out: + return -EOPNOTSUPP; +} +EXPORT_SYMBOL(tc_setup_flow_action); + unsigned int tcf_exts_num_actions(struct tcf_exts *exts) { unsigned int num_acts = 0; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0062c9133a22..48c54ef52a98 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -394,6 +394,12 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); + if (err) { + kfree(cls_flower.rule); + return err; + } + err = tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw); kfree(cls_flower.rule); @@ -1483,6 +1489,14 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, cls_flower.rule->match.mask = &mask->key; cls_flower.rule->match.key = &f->mkey; cls_flower.exts = &f->exts; + + err = tc_setup_flow_action(&cls_flower.rule->action, + &f->exts); + if (err) { + kfree(cls_flower.rule); + return err; + } + cls_flower.classid = f->res.classid; err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); -- cgit v1.2.3 From 3b1903ef97c080a80ead3a6a2305f55108e08269 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 2 Feb 2019 12:50:47 +0100 Subject: flow_offload: add statistics retrieval infrastructure and use it This patch provides the flow_stats structure that acts as container for tc_cls_flower_offload, then we can use to restore the statistics on the existing TC actions. Hence, tcf_exts_stats_update() is not used from drivers anymore. Signed-off-by: Pablo Neira Ayuso Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 4 ++-- drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 2 +- drivers/net/ethernet/netronome/nfp/flower/offload.c | 5 ++--- include/net/flow_offload.h | 14 ++++++++++++++ include/net/pkt_cls.h | 1 + net/sched/cls_flower.c | 4 ++++ 8 files changed, 28 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 90a2170c5138..6a87434b7173 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1396,8 +1396,8 @@ static int bnxt_tc_get_flow_stats(struct bnxt *bp, lastused = flow->lastused; spin_unlock(&flow->stats_lock); - tcf_exts_stats_update(tc_flow_cmd->exts, stats.bytes, stats.packets, - lastused); + flow_stats_update(&tc_flow_cmd->stats, stats.bytes, stats.packets, + lastused); return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 39c5af5dad3d..8a2d66ee1d7b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -807,9 +807,9 @@ int cxgb4_tc_flower_stats(struct net_device *dev, if (ofld_stats->packet_count != packets) { if (ofld_stats->prev_packet_count != packets) ofld_stats->last_used = jiffies; - tcf_exts_stats_update(cls->exts, bytes - ofld_stats->byte_count, - packets - ofld_stats->packet_count, - ofld_stats->last_used); + flow_stats_update(&cls->stats, bytes - ofld_stats->byte_count, + packets - ofld_stats->packet_count, + ofld_stats->last_used); ofld_stats->packet_count = packets; ofld_stats->byte_count = bytes; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 1c8e8da166bd..c4c6bbcafc68 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3071,7 +3071,7 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); out: - tcf_exts_stats_update(f->exts, bytes, packets, lastuse); + flow_stats_update(&f->stats, bytes, packets, lastuse); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index a20379e29e02..c090ecb62041 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -460,7 +460,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp, if (err) goto err_rule_get_stats; - tcf_exts_stats_update(f->exts, bytes, packets, lastuse); + flow_stats_update(&f->stats, bytes, packets, lastuse); mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 74f7ff292052..fe1469d201af 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -554,9 +554,8 @@ nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev, ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id); spin_lock_bh(&priv->stats_lock); - tcf_exts_stats_update(flow->exts, priv->stats[ctx_id].bytes, - priv->stats[ctx_id].pkts, - priv->stats[ctx_id].used); + flow_stats_update(&flow->stats, priv->stats[ctx_id].bytes, + priv->stats[ctx_id].pkts, priv->stats[ctx_id].used); priv->stats[ctx_id].pkts = 0; priv->stats[ctx_id].bytes = 0; diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index dabc819b6cc9..f9ce39992dbd 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -179,4 +179,18 @@ static inline bool flow_rule_match_key(const struct flow_rule *rule, return dissector_uses_key(rule->match.dissector, key); } +struct flow_stats { + u64 pkts; + u64 bytes; + u64 lastused; +}; + +static inline void flow_stats_update(struct flow_stats *flow_stats, + u64 bytes, u64 pkts, u64 lastused) +{ + flow_stats->pkts = pkts; + flow_stats->bytes = bytes; + flow_stats->lastused = lastused; +} + #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index c470c100b926..bea1b1c3ea9b 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -765,6 +765,7 @@ struct tc_cls_flower_offload { enum tc_fl_command command; unsigned long cookie; struct flow_rule *rule; + struct flow_stats stats; struct tcf_exts *exts; u32 classid; }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 48c54ef52a98..8ec85056aa0d 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -429,6 +429,10 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) cls_flower.classid = f->res.classid; tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + + tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes, + cls_flower.stats.pkts, + cls_flower.stats.lastused); } static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, -- cgit v1.2.3 From 2cd173e6d542f8e96369608db849b71135d65afb Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 2 Feb 2019 12:50:49 +0100 Subject: cls_flower: don't expose TC actions to drivers anymore Now that drivers have been converted to use the flow action infrastructure, remove this field from the tc_cls_flower_offload structure. Signed-off-by: Pablo Neira Ayuso Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 1 - net/sched/cls_flower.c | 5 ----- 2 files changed, 6 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index bea1b1c3ea9b..cb8be396a11f 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -766,7 +766,6 @@ struct tc_cls_flower_offload { unsigned long cookie; struct flow_rule *rule; struct flow_stats stats; - struct tcf_exts *exts; u32 classid; }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 8ec85056aa0d..c5d1db3a3db7 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -391,7 +391,6 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.rule->match.dissector = &f->mask->dissector; cls_flower.rule->match.mask = &f->mask->key; cls_flower.rule->match.key = &f->mkey; - cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); @@ -425,7 +424,6 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL); cls_flower.command = TC_CLSFLOWER_STATS; cls_flower.cookie = (unsigned long) f; - cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); @@ -1492,7 +1490,6 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, cls_flower.rule->match.dissector = &mask->dissector; cls_flower.rule->match.mask = &mask->key; cls_flower.rule->match.key = &f->mkey; - cls_flower.exts = &f->exts; err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); @@ -1525,7 +1522,6 @@ static int fl_hw_create_tmplt(struct tcf_chain *chain, { struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = chain->block; - struct tcf_exts dummy_exts = { 0, }; cls_flower.rule = flow_rule_alloc(0); if (!cls_flower.rule) @@ -1537,7 +1533,6 @@ static int fl_hw_create_tmplt(struct tcf_chain *chain, cls_flower.rule->match.dissector = &tmplt->dissector; cls_flower.rule->match.mask = &tmplt->mask; cls_flower.rule->match.key = &tmplt->dummy_key; - cls_flower.exts = &dummy_exts; /* We don't care if driver (any of them) fails to handle this * call. It serves just as a hint for it. -- cgit v1.2.3 From 8bec2833fb28d7c8fcc25127190abbe3eb0ca260 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 2 Feb 2019 12:50:50 +0100 Subject: flow_offload: add wake-up-on-lan and queue to flow_action These actions need to be added to support the ethtool_rx_flow interface. The queue action includes a field to specify the RSS context, that is set via FLOW_RSS flow type flag and the rss_context field in struct ethtool_rxnfc, plus the corresponding queue index. FLOW_RSS implies that rss_context is non-zero, therefore, queue.ctx == 0 means that FLOW_RSS was not set. Also add a field to store the vf index which is stored in the ethtool_rxnfc ring_cookie field. Signed-off-by: Pablo Neira Ayuso Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/flow_offload.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index f9ce39992dbd..23166caa0da5 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -116,6 +116,8 @@ enum flow_action_id { FLOW_ACTION_ADD, FLOW_ACTION_CSUM, FLOW_ACTION_MARK, + FLOW_ACTION_WAKE, + FLOW_ACTION_QUEUE, }; /* This is mirroring enum pedit_header_type definition for easy mapping between @@ -150,6 +152,11 @@ struct flow_action_entry { const struct ip_tunnel_info *tunnel; /* FLOW_ACTION_TUNNEL_ENCAP */ u32 csum_flags; /* FLOW_ACTION_CSUM */ u32 mark; /* FLOW_ACTION_MARK */ + struct { /* FLOW_ACTION_QUEUE */ + u32 ctx; + u32 index; + u8 vf; + } queue; }; }; -- cgit v1.2.3 From eca4205f9ec3bea2d5aad0493c19f5d2675a20fc Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 2 Feb 2019 12:50:51 +0100 Subject: ethtool: add ethtool_rx_flow_spec to flow_rule structure translator This patch adds a function to translate the ethtool_rx_flow_spec structure to the flow_rule representation. This allows us to reuse code from the driver side given that both flower and ethtool_rx_flow interfaces use the same representation. This patch also includes support for the flow type flags FLOW_EXT, FLOW_MAC_EXT and FLOW_RSS. The ethtool_rx_flow_spec_input wrapper structure is used to convey the rss_context field, that is away from the ethtool_rx_flow_spec structure, and the ethtool_rx_flow_spec structure. Signed-off-by: Pablo Neira Ayuso Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/ethtool.h | 15 +++ net/core/ethtool.c | 241 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 256 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index afd9596ce636..19a8de5326fb 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -400,4 +400,19 @@ struct ethtool_ops { void (*get_ethtool_phy_stats)(struct net_device *, struct ethtool_stats *, u64 *); }; + +struct ethtool_rx_flow_rule { + struct flow_rule *rule; + unsigned long priv[0]; +}; + +struct ethtool_rx_flow_spec_input { + const struct ethtool_rx_flow_spec *fs; + u32 rss_ctx; +}; + +struct ethtool_rx_flow_rule * +ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input); +void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *rule); + #endif /* _LINUX_ETHTOOL_H */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 45c0a6e3d6ad..0fbf39239b29 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -29,6 +29,7 @@ #include #include #include +#include /* * Some useful ethtool_ops methods that're device independent. @@ -2820,3 +2821,243 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) return rc; } + +struct ethtool_rx_flow_key { + struct flow_dissector_key_basic basic; + union { + struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; + }; + struct flow_dissector_key_ports tp; + struct flow_dissector_key_ip ip; + struct flow_dissector_key_vlan vlan; + struct flow_dissector_key_eth_addrs eth_addrs; +} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ + +struct ethtool_rx_flow_match { + struct flow_dissector dissector; + struct ethtool_rx_flow_key key; + struct ethtool_rx_flow_key mask; +}; + +struct ethtool_rx_flow_rule * +ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) +{ + const struct ethtool_rx_flow_spec *fs = input->fs; + static struct in6_addr zero_addr = {}; + struct ethtool_rx_flow_match *match; + struct ethtool_rx_flow_rule *flow; + struct flow_action_entry *act; + + flow = kzalloc(sizeof(struct ethtool_rx_flow_rule) + + sizeof(struct ethtool_rx_flow_match), GFP_KERNEL); + if (!flow) + return ERR_PTR(-ENOMEM); + + /* ethtool_rx supports only one single action per rule. */ + flow->rule = flow_rule_alloc(1); + if (!flow->rule) { + kfree(flow); + return ERR_PTR(-ENOMEM); + } + + match = (struct ethtool_rx_flow_match *)flow->priv; + flow->rule->match.dissector = &match->dissector; + flow->rule->match.mask = &match->mask; + flow->rule->match.key = &match->key; + + match->mask.basic.n_proto = htons(0xffff); + + switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: { + const struct ethtool_tcpip4_spec *v4_spec, *v4_m_spec; + + match->key.basic.n_proto = htons(ETH_P_IP); + + v4_spec = &fs->h_u.tcp_ip4_spec; + v4_m_spec = &fs->m_u.tcp_ip4_spec; + + if (v4_m_spec->ip4src) { + match->key.ipv4.src = v4_spec->ip4src; + match->mask.ipv4.src = v4_m_spec->ip4src; + } + if (v4_m_spec->ip4dst) { + match->key.ipv4.dst = v4_spec->ip4dst; + match->mask.ipv4.dst = v4_m_spec->ip4dst; + } + if (v4_m_spec->ip4src || + v4_m_spec->ip4dst) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); + match->dissector.offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] = + offsetof(struct ethtool_rx_flow_key, ipv4); + } + if (v4_m_spec->psrc) { + match->key.tp.src = v4_spec->psrc; + match->mask.tp.src = v4_m_spec->psrc; + } + if (v4_m_spec->pdst) { + match->key.tp.dst = v4_spec->pdst; + match->mask.tp.dst = v4_m_spec->pdst; + } + if (v4_m_spec->psrc || + v4_m_spec->pdst) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_PORTS); + match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = + offsetof(struct ethtool_rx_flow_key, tp); + } + if (v4_m_spec->tos) { + match->key.ip.tos = v4_spec->tos; + match->mask.ip.tos = v4_m_spec->tos; + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IP); + match->dissector.offset[FLOW_DISSECTOR_KEY_IP] = + offsetof(struct ethtool_rx_flow_key, ip); + } + } + break; + case TCP_V6_FLOW: + case UDP_V6_FLOW: { + const struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec; + + match->key.basic.n_proto = htons(ETH_P_IPV6); + + v6_spec = &fs->h_u.tcp_ip6_spec; + v6_m_spec = &fs->m_u.tcp_ip6_spec; + if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + memcpy(&match->key.ipv6.src, v6_spec->ip6src, + sizeof(match->key.ipv6.src)); + memcpy(&match->mask.ipv6.src, v6_m_spec->ip6src, + sizeof(match->mask.ipv6.src)); + } + if (memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) { + memcpy(&match->key.ipv6.dst, v6_spec->ip6dst, + sizeof(match->key.ipv6.dst)); + memcpy(&match->mask.ipv6.dst, v6_m_spec->ip6dst, + sizeof(match->mask.ipv6.dst)); + } + if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) || + memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); + match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] = + offsetof(struct ethtool_rx_flow_key, ipv6); + } + if (v6_m_spec->psrc) { + match->key.tp.src = v6_spec->psrc; + match->mask.tp.src = v6_m_spec->psrc; + } + if (v6_m_spec->pdst) { + match->key.tp.dst = v6_spec->pdst; + match->mask.tp.dst = v6_m_spec->pdst; + } + if (v6_m_spec->psrc || + v6_m_spec->pdst) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_PORTS); + match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = + offsetof(struct ethtool_rx_flow_key, tp); + } + if (v6_m_spec->tclass) { + match->key.ip.tos = v6_spec->tclass; + match->mask.ip.tos = v6_m_spec->tclass; + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IP); + match->dissector.offset[FLOW_DISSECTOR_KEY_IP] = + offsetof(struct ethtool_rx_flow_key, ip); + } + } + break; + default: + ethtool_rx_flow_rule_destroy(flow); + return ERR_PTR(-EINVAL); + } + + switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + match->key.basic.ip_proto = IPPROTO_TCP; + break; + case UDP_V4_FLOW: + case UDP_V6_FLOW: + match->key.basic.ip_proto = IPPROTO_UDP; + break; + } + match->mask.basic.ip_proto = 0xff; + + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] = + offsetof(struct ethtool_rx_flow_key, basic); + + if (fs->flow_type & FLOW_EXT) { + const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext; + const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext; + + if (ext_m_spec->vlan_etype && + ext_m_spec->vlan_tci) { + match->key.vlan.vlan_tpid = ext_h_spec->vlan_etype; + match->mask.vlan.vlan_tpid = ext_m_spec->vlan_etype; + + match->key.vlan.vlan_id = + ntohs(ext_h_spec->vlan_tci) & 0x0fff; + match->mask.vlan.vlan_id = + ntohs(ext_m_spec->vlan_tci) & 0x0fff; + + match->key.vlan.vlan_priority = + (ntohs(ext_h_spec->vlan_tci) & 0xe000) >> 13; + match->mask.vlan.vlan_priority = + (ntohs(ext_m_spec->vlan_tci) & 0xe000) >> 13; + + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_VLAN); + match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = + offsetof(struct ethtool_rx_flow_key, vlan); + } + } + if (fs->flow_type & FLOW_MAC_EXT) { + const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext; + const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext; + + if (ext_m_spec->h_dest) { + memcpy(match->key.eth_addrs.dst, ext_h_spec->h_dest, + ETH_ALEN); + memcpy(match->mask.eth_addrs.dst, ext_m_spec->h_dest, + ETH_ALEN); + + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + match->dissector.offset[FLOW_DISSECTOR_KEY_ETH_ADDRS] = + offsetof(struct ethtool_rx_flow_key, eth_addrs); + } + } + + act = &flow->rule->action.entries[0]; + switch (fs->ring_cookie) { + case RX_CLS_FLOW_DISC: + act->id = FLOW_ACTION_DROP; + break; + case RX_CLS_FLOW_WAKE: + act->id = FLOW_ACTION_WAKE; + break; + default: + act->id = FLOW_ACTION_QUEUE; + if (fs->flow_type & FLOW_RSS) + act->queue.ctx = input->rss_ctx; + + act->queue.vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie); + act->queue.index = ethtool_get_flow_spec_ring(fs->ring_cookie); + break; + } + + return flow; +} +EXPORT_SYMBOL(ethtool_rx_flow_rule_create); + +void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *flow) +{ + kfree(flow->rule); + kfree(flow); +} +EXPORT_SYMBOL(ethtool_rx_flow_rule_destroy); -- cgit v1.2.3 From 57186a5f43d093e769076a4f1bf043351d8668a0 Mon Sep 17 00:00:00 2001 From: Nir Dotan Date: Mon, 4 Feb 2019 18:47:45 +0000 Subject: devlink: add hardware errors tracing facility Define a tracepoint and allow user to trace messages in case of an hardware error code for hardware associated with devlink instance. Signed-off-by: Nir Dotan Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/trace/events/devlink.h | 33 +++++++++++++++++++++++++++++++++ net/core/devlink.c | 1 + 2 files changed, 34 insertions(+) (limited to 'include') diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 44acfbca1266..40705364a50f 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -46,6 +46,35 @@ TRACE_EVENT(devlink_hwmsg, (int) __entry->len, __get_dynamic_array(buf), __entry->len) ); +/* + * Tracepoint for devlink hardware error: + */ +TRACE_EVENT(devlink_hwerr, + TP_PROTO(const struct devlink *devlink, int err, const char *msg), + + TP_ARGS(devlink, err, msg), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(driver_name, devlink->dev->driver->name) + __field(int, err) + __string(msg, msg) + ), + + TP_fast_assign( + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(driver_name, devlink->dev->driver->name); + __entry->err = err; + __assign_str(msg, msg); + ), + + TP_printk("bus_name=%s dev_name=%s driver_name=%s err=%d %s", + __get_str(bus_name), __get_str(dev_name), + __get_str(driver_name), __entry->err, __get_str(msg)) +); + #endif /* _TRACE_DEVLINK_H */ /* This part must be outside protection */ @@ -64,6 +93,10 @@ static inline void trace_devlink_hwmsg(const struct devlink *devlink, { } +static inline void trace_devlink_hwerr(const struct devlink *devlink, + int err, const char *msg) +{ +} #endif /* _TRACE_DEVLINK_H */ #endif diff --git a/net/core/devlink.c b/net/core/devlink.c index 52bf27491fb8..cd0d393bc62d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -81,6 +81,7 @@ struct devlink_dpipe_header devlink_dpipe_header_ipv6 = { EXPORT_SYMBOL(devlink_dpipe_header_ipv6); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); +EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); static LIST_HEAD(devlink_list); -- cgit v1.2.3 From d6abc5969463359c366d459247b90366fcd6f5c5 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 6 Feb 2019 09:45:35 -0800 Subject: net: Introduce ndo_get_port_parent_id() In preparation for getting rid of switchdev_ops, create a dedicated NDO operation for getting the port's parent identifier. There are essentially two classes of drivers that need to implement getting the port's parent ID which are VF/PF drivers with a built-in switch, and pure switchdev drivers such as mlxsw, ocelot, dsa etc. We introduce a helper function: dev_get_port_parent_id() which supports recursion into the lower devices to obtain the first port's parent ID. Convert the bridge, core and ipv4 multicast routing code to check for such ndo_get_port_parent_id() and call the helper function when valid before falling back to switchdev_port_attr_get(). This will allow us to convert all relevant drivers in one go instead of having to implement both switchdev_port_attr_get() and ndo_get_port_parent_id() operations, then get rid of switchdev_port_attr_get(). Acked-by: Jiri Pirko Signed-off-by: Florian Fainelli Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 ++++++++ net/bridge/br_switchdev.c | 9 ++++++-- net/core/dev.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++ net/core/net-sysfs.c | 7 +++++- net/core/rtnetlink.c | 6 ++++- net/ipv4/ipmr.c | 8 ++++++- 6 files changed, 91 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ba57d0ba425e..1d95e634f3fe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1188,6 +1188,10 @@ struct dev_ifalias { * not implement this, it is assumed that the hw is not able to have * multiple net devices on single physical port. * + * int (*ndo_get_port_parent_id)(struct net_device *dev, + * struct netdev_phys_item_id *ppid) + * Called to get the parent ID of the physical port of this device. + * * void (*ndo_udp_tunnel_add)(struct net_device *dev, * struct udp_tunnel_info *ti); * Called by UDP tunnel to notify a driver about the UDP port and socket @@ -1412,6 +1416,8 @@ struct net_device_ops { bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); + int (*ndo_get_port_parent_id)(struct net_device *dev, + struct netdev_phys_item_id *ppid); int (*ndo_get_phys_port_name)(struct net_device *dev, char *name, size_t len); void (*ndo_udp_tunnel_add)(struct net_device *dev, @@ -3651,6 +3657,9 @@ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); +int dev_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid, bool recurse); +bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); int dev_change_proto_down(struct net_device *dev, bool proto_down); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 4d2b9eb7604a..06b0ae44585f 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -14,7 +14,8 @@ static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) /* dev is yet to be added to the port list. */ list_for_each_entry(p, &br->port_list, list) { - if (switchdev_port_same_parent_id(dev, p->dev)) + if (netdev_port_same_parent_id(dev, p->dev) || + switchdev_port_same_parent_id(dev, p->dev)) return p->offload_fwd_mark; } @@ -23,6 +24,7 @@ static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) int nbp_switchdev_mark_set(struct net_bridge_port *p) { + const struct net_device_ops *ops = p->dev->netdev_ops; struct switchdev_attr attr = { .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, @@ -31,7 +33,10 @@ int nbp_switchdev_mark_set(struct net_bridge_port *p) ASSERT_RTNL(); - err = switchdev_port_attr_get(p->dev, &attr); + if (ops->ndo_get_port_parent_id) + err = dev_get_port_parent_id(p->dev, &attr.u.ppid, true); + else + err = switchdev_port_attr_get(p->dev, &attr); if (err) { if (err == -EOPNOTSUPP) return 0; diff --git a/net/core/dev.c b/net/core/dev.c index bfa4be42afff..8c6d5cf8a308 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7877,6 +7877,63 @@ int dev_get_phys_port_name(struct net_device *dev, } EXPORT_SYMBOL(dev_get_phys_port_name); +/** + * dev_get_port_parent_id - Get the device's port parent identifier + * @dev: network device + * @ppid: pointer to a storage for the port's parent identifier + * @recurse: allow/disallow recursion to lower devices + * + * Get the devices's port parent identifier + */ +int dev_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid, + bool recurse) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct netdev_phys_item_id first = { }; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (ops->ndo_get_port_parent_id) + return ops->ndo_get_port_parent_id(dev, ppid); + + if (!recurse) + return err; + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = dev_get_port_parent_id(lower_dev, ppid, recurse); + if (err) + break; + if (!first.id_len) + first = *ppid; + else if (memcmp(&first, ppid, sizeof(*ppid))) + return -ENODATA; + } + + return err; +} +EXPORT_SYMBOL(dev_get_port_parent_id); + +/** + * netdev_port_same_parent_id - Indicate if two network devices have + * the same port parent identifier + * @a: first network device + * @b: second network device + */ +bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) +{ + struct netdev_phys_item_id a_id = { }; + struct netdev_phys_item_id b_id = { }; + + if (dev_get_port_parent_id(a, &a_id, true) || + dev_get_port_parent_id(b, &b_id, true)) + return false; + + return netdev_phys_item_id_same(&a_id, &b_id); +} +EXPORT_SYMBOL(netdev_port_same_parent_id); + /** * dev_change_proto_down - update protocol port state information * @dev: device diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ff9fd2bb4ce4..4eace9f1dcf9 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -495,6 +495,7 @@ static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); + const struct net_device_ops *ops = netdev->netdev_ops; ssize_t ret = -EINVAL; if (!rtnl_trylock()) @@ -507,7 +508,11 @@ static ssize_t phys_switch_id_show(struct device *dev, .flags = SWITCHDEV_F_NO_RECURSE, }; - ret = switchdev_port_attr_get(netdev, &attr); + if (ops->ndo_get_port_parent_id) + ret = dev_get_port_parent_id(netdev, &attr.u.ppid, + false); + else + ret = switchdev_port_attr_get(netdev, &attr); if (!ret) ret = sprintf(buf, "%*phN\n", attr.u.ppid.id_len, attr.u.ppid.id); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f5a98082ac7a..90dd02c1f561 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1146,6 +1146,7 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { + const struct net_device_ops *ops = dev->netdev_ops; int err; struct switchdev_attr attr = { .orig_dev = dev, @@ -1153,7 +1154,10 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) .flags = SWITCHDEV_F_NO_RECURSE, }; - err = switchdev_port_attr_get(dev, &attr); + if (ops->ndo_get_port_parent_id) + err = dev_get_port_parent_id(dev, &attr.u.ppid, false); + else + err = switchdev_port_attr_get(dev, &attr); if (err) { if (err == -EOPNOTSUPP) return 0; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index fb99002c3d4e..c71bcc42d66d 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -837,6 +837,7 @@ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { + const struct net_device_ops *ops; int vifi = vifc->vifc_vifi; struct switchdev_attr attr = { .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, @@ -920,7 +921,12 @@ static int vif_add(struct net *net, struct mr_table *mrt, (VIFF_TUNNEL | VIFF_REGISTER)); attr.orig_dev = dev; - if (!switchdev_port_attr_get(dev, &attr)) { + ops = dev->netdev_ops; + if (ops->ndo_get_port_parent_id && + !dev_get_port_parent_id(dev, &attr.u.ppid, true)) { + memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len); + v->dev_parent_id.id_len = attr.u.ppid.id_len; + } else if (!switchdev_port_attr_get(dev, &attr)) { memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len); v->dev_parent_id.id_len = attr.u.ppid.id_len; } else { -- cgit v1.2.3 From bccb30254a4a02ee370dd23b2afbd25d7a78bc34 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 6 Feb 2019 09:45:46 -0800 Subject: net: Get rid of SWITCHDEV_ATTR_ID_PORT_PARENT_ID Now that we have a dedicated NDO for getting a port's parent ID, get rid of SWITCHDEV_ATTR_ID_PORT_PARENT_ID and convert all callers to use the NDO exclusively. This is a preliminary change to getting rid of switchdev_ops eventually. Signed-off-by: Florian Fainelli Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/switchdev.h | 11 ----------- net/bridge/br_switchdev.c | 14 +++----------- net/core/net-sysfs.c | 19 ++++--------------- net/core/rtnetlink.c | 16 +++------------- net/ipv4/ipmr.c | 19 +++++-------------- net/switchdev/switchdev.c | 20 -------------------- 6 files changed, 15 insertions(+), 84 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 63843ae5dc81..5e87b54c5dc5 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -43,7 +43,6 @@ static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) enum switchdev_attr_id { SWITCHDEV_ATTR_ID_UNDEFINED, - SWITCHDEV_ATTR_ID_PORT_PARENT_ID, SWITCHDEV_ATTR_ID_PORT_STP_STATE, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT, @@ -61,7 +60,6 @@ struct switchdev_attr { void *complete_priv; void (*complete)(struct net_device *dev, int err, void *priv); union { - struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ unsigned long brport_flags_support; /* PORT_BRIDGE_FLAGS_SUPPORT */ @@ -208,9 +206,6 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); -bool switchdev_port_same_parent_id(struct net_device *a, - struct net_device *b); - int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), @@ -295,12 +290,6 @@ call_switchdev_blocking_notifiers(unsigned long val, return NOTIFY_DONE; } -static inline bool switchdev_port_same_parent_id(struct net_device *a, - struct net_device *b) -{ - return false; -} - static inline int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 06b0ae44585f..db9e8ab96d48 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -14,8 +14,7 @@ static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) /* dev is yet to be added to the port list. */ list_for_each_entry(p, &br->port_list, list) { - if (netdev_port_same_parent_id(dev, p->dev) || - switchdev_port_same_parent_id(dev, p->dev)) + if (netdev_port_same_parent_id(dev, p->dev)) return p->offload_fwd_mark; } @@ -24,19 +23,12 @@ static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) int nbp_switchdev_mark_set(struct net_bridge_port *p) { - const struct net_device_ops *ops = p->dev->netdev_ops; - struct switchdev_attr attr = { - .orig_dev = p->dev, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; + struct netdev_phys_item_id ppid = { }; int err; ASSERT_RTNL(); - if (ops->ndo_get_port_parent_id) - err = dev_get_port_parent_id(p->dev, &attr.u.ppid, true); - else - err = switchdev_port_attr_get(p->dev, &attr); + err = dev_get_port_parent_id(p->dev, &ppid, true); if (err) { if (err == -EOPNOTSUPP) return 0; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4eace9f1dcf9..7c5061123ead 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -495,27 +494,17 @@ static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); - const struct net_device_ops *ops = netdev->netdev_ops; ssize_t ret = -EINVAL; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { - struct switchdev_attr attr = { - .orig_dev = netdev, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - .flags = SWITCHDEV_F_NO_RECURSE, - }; - - if (ops->ndo_get_port_parent_id) - ret = dev_get_port_parent_id(netdev, &attr.u.ppid, - false); - else - ret = switchdev_port_attr_get(netdev, &attr); + struct netdev_phys_item_id ppid = { }; + + ret = dev_get_port_parent_id(netdev, &ppid, false); if (!ret) - ret = sprintf(buf, "%*phN\n", attr.u.ppid.id_len, - attr.u.ppid.id); + ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 90dd02c1f561..a51cab95ba64 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -46,7 +46,6 @@ #include #include -#include #include #include #include @@ -1146,26 +1145,17 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { - const struct net_device_ops *ops = dev->netdev_ops; + struct netdev_phys_item_id ppid = { }; int err; - struct switchdev_attr attr = { - .orig_dev = dev, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - .flags = SWITCHDEV_F_NO_RECURSE, - }; - if (ops->ndo_get_port_parent_id) - err = dev_get_port_parent_id(dev, &attr.u.ppid, false); - else - err = switchdev_port_attr_get(dev, &attr); + err = dev_get_port_parent_id(dev, &ppid, false); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } - if (nla_put(skb, IFLA_PHYS_SWITCH_ID, attr.u.ppid.id_len, - attr.u.ppid.id)) + if (nla_put(skb, IFLA_PHYS_SWITCH_ID, ppid.id_len, ppid.id)) return -EMSGSIZE; return 0; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c71bcc42d66d..e536970557dd 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -67,7 +67,6 @@ #include #include #include -#include #include @@ -837,11 +836,8 @@ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { - const struct net_device_ops *ops; + struct netdev_phys_item_id ppid = { }; int vifi = vifc->vifc_vifi; - struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; @@ -920,15 +916,10 @@ static int vif_add(struct net *net, struct mr_table *mrt, vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), (VIFF_TUNNEL | VIFF_REGISTER)); - attr.orig_dev = dev; - ops = dev->netdev_ops; - if (ops->ndo_get_port_parent_id && - !dev_get_port_parent_id(dev, &attr.u.ppid, true)) { - memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len); - v->dev_parent_id.id_len = attr.u.ppid.id_len; - } else if (!switchdev_port_attr_get(dev, &attr)) { - memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len); - v->dev_parent_id.id_len = attr.u.ppid.id_len; + err = dev_get_port_parent_id(dev, &ppid, true); + if (err == 0) { + memcpy(v->dev_parent_id.id, ppid.id, ppid.id_len); + v->dev_parent_id.id_len = ppid.id_len; } else { v->dev_parent_id.id_len = 0; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index cd78253de31d..7e1357db33d7 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -592,26 +592,6 @@ int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev, } EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers); -bool switchdev_port_same_parent_id(struct net_device *a, - struct net_device *b) -{ - struct switchdev_attr a_attr = { - .orig_dev = a, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; - struct switchdev_attr b_attr = { - .orig_dev = b, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; - - if (switchdev_port_attr_get(a, &a_attr) || - switchdev_port_attr_get(b, &b_attr)) - return false; - - return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid); -} -EXPORT_SYMBOL_GPL(switchdev_port_same_parent_id); - static int __switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), -- cgit v1.2.3 From 4d5f007eedb74d71a7bde2bff69b6a31ad8ab427 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 2 Jan 2019 13:28:47 +0100 Subject: time: make adjtime compat handling available for 32 bit We want to reuse the compat_timex handling on 32-bit architectures the same way we are using the compat handling for timespec when moving to 64-bit time_t. Move all definitions related to compat_timex out of the compat code into the normal timekeeping code, along with a rename to old_timex32, corresponding to the timespec/timeval structures, and make it controlled by CONFIG_COMPAT_32BIT_TIME, which 32-bit architectures will then select. Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 35 ++--------------------- include/linux/time32.h | 32 ++++++++++++++++++++- kernel/compat.c | 64 ------------------------------------------ kernel/time/posix-timers.c | 14 ++-------- kernel/time/time.c | 70 +++++++++++++++++++++++++++++++++++++++++++--- 5 files changed, 102 insertions(+), 113 deletions(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index 056be0d03722..657ca6abd855 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -132,37 +132,6 @@ struct compat_tms { compat_clock_t tms_cstime; }; -struct compat_timex { - compat_uint_t modes; - compat_long_t offset; - compat_long_t freq; - compat_long_t maxerror; - compat_long_t esterror; - compat_int_t status; - compat_long_t constant; - compat_long_t precision; - compat_long_t tolerance; - struct old_timeval32 time; - compat_long_t tick; - compat_long_t ppsfreq; - compat_long_t jitter; - compat_int_t shift; - compat_long_t stabil; - compat_long_t jitcnt; - compat_long_t calcnt; - compat_long_t errcnt; - compat_long_t stbcnt; - compat_int_t tai; - - compat_int_t:32; compat_int_t:32; compat_int_t:32; compat_int_t:32; - compat_int_t:32; compat_int_t:32; compat_int_t:32; compat_int_t:32; - compat_int_t:32; compat_int_t:32; compat_int_t:32; -}; - -struct timex; -int compat_get_timex(struct timex *, const struct compat_timex __user *); -int compat_put_timex(struct compat_timex __user *, const struct timex *); - #define _COMPAT_NSIG_WORDS (_COMPAT_NSIG / _COMPAT_NSIG_BPW) typedef struct { @@ -808,7 +777,7 @@ asmlinkage long compat_sys_gettimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_settimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); -asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); +asmlinkage long compat_sys_adjtimex(struct old_timex32 __user *utp); /* kernel/timer.c */ asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); @@ -911,7 +880,7 @@ asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); asmlinkage long compat_sys_clock_adjtime(clockid_t which_clock, - struct compat_timex __user *tp); + struct old_timex32 __user *tp); asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags); asmlinkage ssize_t compat_sys_process_vm_readv(compat_pid_t pid, diff --git a/include/linux/time32.h b/include/linux/time32.h index 118b9977080c..820a22e2b98b 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -10,6 +10,7 @@ */ #include +#include #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) @@ -35,13 +36,42 @@ struct old_utimbuf32 { old_time32_t modtime; }; +struct old_timex32 { + u32 modes; + s32 offset; + s32 freq; + s32 maxerror; + s32 esterror; + s32 status; + s32 constant; + s32 precision; + s32 tolerance; + struct old_timeval32 time; + s32 tick; + s32 ppsfreq; + s32 jitter; + s32 shift; + s32 stabil; + s32 jitcnt; + s32 calcnt; + s32 errcnt; + s32 stbcnt; + s32 tai; + + s32:32; s32:32; s32:32; s32:32; + s32:32; s32:32; s32:32; s32:32; + s32:32; s32:32; s32:32; +}; + extern int get_old_timespec32(struct timespec64 *, const void __user *); extern int put_old_timespec32(const struct timespec64 *, void __user *); extern int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits); extern int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits); - +struct timex; +int get_old_timex32(struct timex *, const struct old_timex32 __user *); +int put_old_timex32(struct old_timex32 __user *, const struct timex *); #if __BITS_PER_LONG == 64 diff --git a/kernel/compat.c b/kernel/compat.c index f01affa17e22..d8a36c6ad7c9 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -30,69 +29,6 @@ #include -int compat_get_timex(struct timex *txc, const struct compat_timex __user *utp) -{ - struct compat_timex tx32; - - memset(txc, 0, sizeof(struct timex)); - if (copy_from_user(&tx32, utp, sizeof(struct compat_timex))) - return -EFAULT; - - txc->modes = tx32.modes; - txc->offset = tx32.offset; - txc->freq = tx32.freq; - txc->maxerror = tx32.maxerror; - txc->esterror = tx32.esterror; - txc->status = tx32.status; - txc->constant = tx32.constant; - txc->precision = tx32.precision; - txc->tolerance = tx32.tolerance; - txc->time.tv_sec = tx32.time.tv_sec; - txc->time.tv_usec = tx32.time.tv_usec; - txc->tick = tx32.tick; - txc->ppsfreq = tx32.ppsfreq; - txc->jitter = tx32.jitter; - txc->shift = tx32.shift; - txc->stabil = tx32.stabil; - txc->jitcnt = tx32.jitcnt; - txc->calcnt = tx32.calcnt; - txc->errcnt = tx32.errcnt; - txc->stbcnt = tx32.stbcnt; - - return 0; -} - -int compat_put_timex(struct compat_timex __user *utp, const struct timex *txc) -{ - struct compat_timex tx32; - - memset(&tx32, 0, sizeof(struct compat_timex)); - tx32.modes = txc->modes; - tx32.offset = txc->offset; - tx32.freq = txc->freq; - tx32.maxerror = txc->maxerror; - tx32.esterror = txc->esterror; - tx32.status = txc->status; - tx32.constant = txc->constant; - tx32.precision = txc->precision; - tx32.tolerance = txc->tolerance; - tx32.time.tv_sec = txc->time.tv_sec; - tx32.time.tv_usec = txc->time.tv_usec; - tx32.tick = txc->tick; - tx32.ppsfreq = txc->ppsfreq; - tx32.jitter = txc->jitter; - tx32.shift = txc->shift; - tx32.stabil = txc->stabil; - tx32.jitcnt = txc->jitcnt; - tx32.calcnt = txc->calcnt; - tx32.errcnt = txc->errcnt; - tx32.stbcnt = txc->stbcnt; - tx32.tai = txc->tai; - if (copy_to_user(utp, &tx32, sizeof(struct compat_timex))) - return -EFAULT; - return 0; -} - static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv) { return (!access_ok(ctv, sizeof(*ctv)) || diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 0e84bb72a3da..8955f32f2a36 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1123,12 +1123,8 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, return err; } -#endif - -#ifdef CONFIG_COMPAT - COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, - struct compat_timex __user *, utp) + struct old_timex32 __user *, utp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timex ktx; @@ -1139,22 +1135,18 @@ COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, if (!kc->clock_adj) return -EOPNOTSUPP; - err = compat_get_timex(&ktx, utp); + err = get_old_timex32(&ktx, utp); if (err) return err; err = kc->clock_adj(which_clock, &ktx); if (err >= 0) - err = compat_put_timex(utp, &ktx); + err = put_old_timex32(utp, &ktx); return err; } -#endif - -#ifdef CONFIG_COMPAT_32BIT_TIME - COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, struct old_timespec32 __user *, tp) { diff --git a/kernel/time/time.c b/kernel/time/time.c index 2edb5088a70b..2d013bc2b271 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -278,20 +278,82 @@ SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p) return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME +int get_old_timex32(struct timex *txc, const struct old_timex32 __user *utp) +{ + struct old_timex32 tx32; + + memset(txc, 0, sizeof(struct timex)); + if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) + return -EFAULT; + + txc->modes = tx32.modes; + txc->offset = tx32.offset; + txc->freq = tx32.freq; + txc->maxerror = tx32.maxerror; + txc->esterror = tx32.esterror; + txc->status = tx32.status; + txc->constant = tx32.constant; + txc->precision = tx32.precision; + txc->tolerance = tx32.tolerance; + txc->time.tv_sec = tx32.time.tv_sec; + txc->time.tv_usec = tx32.time.tv_usec; + txc->tick = tx32.tick; + txc->ppsfreq = tx32.ppsfreq; + txc->jitter = tx32.jitter; + txc->shift = tx32.shift; + txc->stabil = tx32.stabil; + txc->jitcnt = tx32.jitcnt; + txc->calcnt = tx32.calcnt; + txc->errcnt = tx32.errcnt; + txc->stbcnt = tx32.stbcnt; + + return 0; +} + +int put_old_timex32(struct old_timex32 __user *utp, const struct timex *txc) +{ + struct old_timex32 tx32; + + memset(&tx32, 0, sizeof(struct old_timex32)); + tx32.modes = txc->modes; + tx32.offset = txc->offset; + tx32.freq = txc->freq; + tx32.maxerror = txc->maxerror; + tx32.esterror = txc->esterror; + tx32.status = txc->status; + tx32.constant = txc->constant; + tx32.precision = txc->precision; + tx32.tolerance = txc->tolerance; + tx32.time.tv_sec = txc->time.tv_sec; + tx32.time.tv_usec = txc->time.tv_usec; + tx32.tick = txc->tick; + tx32.ppsfreq = txc->ppsfreq; + tx32.jitter = txc->jitter; + tx32.shift = txc->shift; + tx32.stabil = txc->stabil; + tx32.jitcnt = txc->jitcnt; + tx32.calcnt = txc->calcnt; + tx32.errcnt = txc->errcnt; + tx32.stbcnt = txc->stbcnt; + tx32.tai = txc->tai; + if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) + return -EFAULT; + return 0; +} -COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp) +COMPAT_SYSCALL_DEFINE1(adjtimex, struct old_timex32 __user *, utp) { struct timex txc; int err, ret; - err = compat_get_timex(&txc, utp); + err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); - err = compat_put_timex(utp, &txc); + err = put_old_timex32(utp, &txc); if (err) return err; -- cgit v1.2.3 From 2c620ff93d9fbd5d644760d4c21d389078ec1080 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Mon, 2 Jul 2018 22:44:20 -0700 Subject: time: Add struct __kernel_timex struct timex uses struct timeval internally. struct timeval is not y2038 safe. Introduce a new UAPI type struct __kernel_timex that is y2038 safe. struct __kernel_timex uses a timeval type that is similar to struct __kernel_timespec which preserves the same structure size across 32 bit and 64 bit ABIs. struct __kernel_timex also restructures other members of the structure to make the structure the same on 64 bit and 32 bit architectures. Note that struct __kernel_timex is the same as struct timex on a 64 bit architecture. The above solution is similar to other new y2038 syscalls that are being introduced: both 32 bit and 64 bit ABIs have a common entry, and the compat entry supports the old 32 bit syscall interface. Alternatives considered were: 1. Add new time type to struct timex that makes use of padded bits. This time type could be based on the struct __kernel_timespec. modes will use a flag to notify which time structure should be used internally. This needs some application level changes on both 64 bit and 32 bit architectures. Although 64 bit machines could continue to use the older timeval structure without any changes. 2. Add a new u8 type to struct timex that makes use of padded bits. This can be used to save higher order tv_sec bits. modes will use a flag to notify presence of such a type. This will need some application level changes on 32 bit architectures. 3. Add a new compat_timex structure that differs in only the size of the time type; keep rest of struct timex the same. This requires extra syscalls to manage all 3 cases on 64 bit architectures. This will not need any application level changes but will add more complexity from kernel side. Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/timex.h | 7 +++++++ include/uapi/linux/timex.h | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) (limited to 'include') diff --git a/include/linux/timex.h b/include/linux/timex.h index 39c25dbebfe8..7f40e9e42ecc 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -53,6 +53,13 @@ #ifndef _LINUX_TIMEX_H #define _LINUX_TIMEX_H +/* CONFIG_64BIT_TIME enables new 64 bit time_t syscalls in the compat path + * and 32-bit emulation. + */ +#ifndef CONFIG_64BIT_TIME +#define __kernel_timex timex +#endif + #include #define ADJ_ADJTIME 0x8000 /* switch between adjtime/adjtimex modes */ diff --git a/include/uapi/linux/timex.h b/include/uapi/linux/timex.h index 92685d826444..a1c6b73016a5 100644 --- a/include/uapi/linux/timex.h +++ b/include/uapi/linux/timex.h @@ -92,6 +92,47 @@ struct timex { int :32; int :32; int :32; }; +struct __kernel_timex_timeval { + __kernel_time64_t tv_sec; + long long tv_usec; +}; + +#ifndef __kernel_timex +struct __kernel_timex { + unsigned int modes; /* mode selector */ + int :32; /* pad */ + long long offset; /* time offset (usec) */ + long long freq; /* frequency offset (scaled ppm) */ + long long maxerror;/* maximum error (usec) */ + long long esterror;/* estimated error (usec) */ + int status; /* clock command/status */ + int :32; /* pad */ + long long constant;/* pll time constant */ + long long precision;/* clock precision (usec) (read only) */ + long long tolerance;/* clock frequency tolerance (ppm) + * (read only) + */ + struct __kernel_timex_timeval time; /* (read only, except for ADJ_SETOFFSET) */ + long long tick; /* (modified) usecs between clock ticks */ + + long long ppsfreq;/* pps frequency (scaled ppm) (ro) */ + long long jitter; /* pps jitter (us) (ro) */ + int shift; /* interval duration (s) (shift) (ro) */ + int :32; /* pad */ + long long stabil; /* pps stability (scaled ppm) (ro) */ + long long jitcnt; /* jitter limit exceeded (ro) */ + long long calcnt; /* calibration intervals (ro) */ + long long errcnt; /* calibration errors (ro) */ + long long stbcnt; /* stability limit exceeded (ro) */ + + int tai; /* TAI offset (ro) */ + + int :32; int :32; int :32; int :32; + int :32; int :32; int :32; int :32; + int :32; int :32; int :32; +}; +#endif + /* * Mode codes (timex.mode) */ -- cgit v1.2.3 From 50b93f30f6d8672f9ec80e90af94d733f11a20e0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 1 Jan 2019 17:34:39 +0100 Subject: time: fix sys_timer_settime prototype A small typo has crept into the y2038 conversion of the timer_settime system call. So far this was completely harmless, but once we start using the new version, this has to be fixed. Fixes: 6ff847350702 ("time: Change types to new y2038 safe __kernel_itimerspec") Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 938d8908b9e0..baa4b70b02d3 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -591,7 +591,7 @@ asmlinkage long sys_timer_gettime(timer_t timer_id, asmlinkage long sys_timer_getoverrun(timer_t timer_id); asmlinkage long sys_timer_settime(timer_t timer_id, int flags, const struct __kernel_itimerspec __user *new_setting, - struct itimerspec __user *old_setting); + struct __kernel_itimerspec __user *old_setting); asmlinkage long sys_timer_delete(timer_t timer_id); asmlinkage long sys_clock_settime(clockid_t which_clock, const struct __kernel_timespec __user *tp); -- cgit v1.2.3 From 1a596398a3d75f966b75f428e992cf1f242f9a5b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 3 Jan 2019 21:12:39 +0100 Subject: sparc64: add custom adjtimex/clock_adjtime functions sparc64 is the only architecture on Linux that has a 'timeval' definition with a 32-bit tv_usec but a 64-bit tv_sec. This causes problems for sparc32 compat mode when we convert it to use the new __kernel_timex type that has the same layout as all other 64-bit architectures. To avoid adding sparc64 specific code into the generic adjtimex implementation, this adds a wrapper in the sparc64 system call handling that converts the sparc64 'timex' into the new '__kernel_timex'. At this point, the two structures are defined to be identical, but that will change in the next step once we convert sparc32. Signed-off-by: Arnd Bergmann --- arch/sparc/kernel/sys_sparc_64.c | 59 +++++++++++++++++++++++++++++++++- arch/sparc/kernel/syscalls/syscall.tbl | 6 ++-- include/linux/timex.h | 2 ++ kernel/time/posix-timers.c | 24 +++++++------- 4 files changed, 76 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 1c079e7bab09..37de18a11207 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -28,8 +28,9 @@ #include #include #include - +#include #include + #include #include @@ -544,6 +545,62 @@ out_unlock: return err; } +SYSCALL_DEFINE1(sparc_adjtimex, struct timex __user *, txc_p) +{ + struct timex txc; /* Local copy of parameter */ + struct timex *kt = (void *)&txc; + int ret; + + /* Copy the user data space into the kernel copy + * structure. But bear in mind that the structures + * may change + */ + if (copy_from_user(&txc, txc_p, sizeof(struct timex))) + return -EFAULT; + + /* + * override for sparc64 specific timeval type: tv_usec + * is 32 bit wide instead of 64-bit in __kernel_timex + */ + kt->time.tv_usec = txc.time.tv_usec; + ret = do_adjtimex(kt); + txc.time.tv_usec = kt->time.tv_usec; + + return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret; +} + +SYSCALL_DEFINE2(sparc_clock_adjtime, const clockid_t, which_clock,struct timex __user *, txc_p) +{ + struct timex txc; /* Local copy of parameter */ + struct timex *kt = (void *)&txc; + int ret; + + if (!IS_ENABLED(CONFIG_POSIX_TIMERS)) { + pr_err_once("process %d (%s) attempted a POSIX timer syscall " + "while CONFIG_POSIX_TIMERS is not set\n", + current->pid, current->comm); + + return -ENOSYS; + } + + /* Copy the user data space into the kernel copy + * structure. But bear in mind that the structures + * may change + */ + if (copy_from_user(&txc, txc_p, sizeof(struct timex))) + return -EFAULT; + + /* + * override for sparc64 specific timeval type: tv_usec + * is 32 bit wide instead of 64-bit in __kernel_timex + */ + kt->time.tv_usec = txc.time.tv_usec; + ret = do_clock_adjtime(which_clock, kt); + txc.time.tv_usec = kt->time.tv_usec; + + return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret; +} + SYSCALL_DEFINE5(utrap_install, utrap_entry_t, type, utrap_handler_t, new_p, utrap_handler_t, new_d, utrap_handler_t __user *, old_p, diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 6992d17cce37..e63cd013cc77 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -258,7 +258,8 @@ 216 64 sigreturn sys_nis_syscall 217 common clone sys_clone 218 common ioprio_get sys_ioprio_get -219 common adjtimex sys_adjtimex compat_sys_adjtimex +219 32 adjtimex sys_adjtimex compat_sys_adjtimex +219 64 adjtimex sys_sparc_adjtimex 220 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask 220 64 sigprocmask sys_nis_syscall 221 common create_module sys_ni_syscall @@ -377,7 +378,8 @@ 331 common prlimit64 sys_prlimit64 332 common name_to_handle_at sys_name_to_handle_at 333 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -334 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +334 32 clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +334 64 clock_adjtime sys_sparc_clock_adjtime 335 common syncfs sys_syncfs 336 common sendmmsg sys_sendmmsg compat_sys_sendmmsg 337 common setns sys_setns diff --git a/include/linux/timex.h b/include/linux/timex.h index 7f40e9e42ecc..a15e6aeb8d49 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -159,6 +159,8 @@ extern unsigned long tick_nsec; /* SHIFTED_HZ period (nsec) */ #define NTP_INTERVAL_LENGTH (NSEC_PER_SEC/NTP_INTERVAL_FREQ) extern int do_adjtimex(struct timex *); +extern int do_clock_adjtime(const clockid_t which_clock, struct timex * ktx); + extern void hardpps(const struct timespec64 *, const struct timespec64 *); int read_current_timer(unsigned long *timer_val); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 8955f32f2a36..8f7f1dd95940 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1047,22 +1047,28 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, return error; } -SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, - struct timex __user *, utx) +int do_clock_adjtime(const clockid_t which_clock, struct timex * ktx) { const struct k_clock *kc = clockid_to_kclock(which_clock); - struct timex ktx; - int err; if (!kc) return -EINVAL; if (!kc->clock_adj) return -EOPNOTSUPP; + return kc->clock_adj(which_clock, ktx); +} + +SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, + struct timex __user *, utx) +{ + struct timex ktx; + int err; + if (copy_from_user(&ktx, utx, sizeof(ktx))) return -EFAULT; - err = kc->clock_adj(which_clock, &ktx); + err = do_clock_adjtime(which_clock, &ktx); if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx))) return -EFAULT; @@ -1126,20 +1132,14 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, struct old_timex32 __user *, utp) { - const struct k_clock *kc = clockid_to_kclock(which_clock); struct timex ktx; int err; - if (!kc) - return -EINVAL; - if (!kc->clock_adj) - return -EOPNOTSUPP; - err = get_old_timex32(&ktx, utp); if (err) return err; - err = kc->clock_adj(which_clock, &ktx); + err = do_clock_adjtime(which_clock, &ktx); if (err >= 0) err = put_old_timex32(utp, &ktx); -- cgit v1.2.3 From ead25417f82ed7f8a21da4dcefc768169f7da884 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Mon, 2 Jul 2018 22:44:21 -0700 Subject: timex: use __kernel_timex internally struct timex is not y2038 safe. Replace all uses of timex with y2038 safe __kernel_timex. Note that struct __kernel_timex is an ABI interface definition. We could define a new structure based on __kernel_timex that is only available internally instead. Right now, there isn't a strong motivation for this as the structure is isolated to a few defined struct timex interfaces and such a structure would be exactly the same as struct timex. The patch was generated by the following coccinelle script: virtual patch @depends on patch forall@ identifier ts; expression e; @@ ( - struct timex ts; + struct __kernel_timex ts; | - struct timex ts = {}; + struct __kernel_timex ts = {}; | - struct timex ts = e; + struct __kernel_timex ts = e; | - struct timex *ts; + struct __kernel_timex *ts; | (memset \| copy_from_user \| copy_to_user \)(..., - sizeof(struct timex)) + sizeof(struct __kernel_timex)) ) @depends on patch forall@ identifier ts; identifier fn; @@ fn(..., - struct timex *ts, + struct __kernel_timex *ts, ...) { ... } @depends on patch forall@ identifier ts; identifier fn; @@ fn(..., - struct timex *ts) { + struct __kernel_timex *ts) { ... } Signed-off-by: Deepa Dinamani Cc: linux-alpha@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Arnd Bergmann --- arch/alpha/kernel/osf_sys.c | 5 +++-- arch/sparc/kernel/sys_sparc_64.c | 4 ++-- drivers/ptp/ptp_clock.c | 2 +- include/linux/posix-clock.h | 2 +- include/linux/time32.h | 6 +++--- include/linux/timex.h | 4 ++-- kernel/time/ntp.c | 18 ++++++++++-------- kernel/time/ntp_internal.h | 2 +- kernel/time/posix-clock.c | 2 +- kernel/time/posix-timers.c | 8 ++++---- kernel/time/posix-timers.h | 2 +- kernel/time/time.c | 14 +++++++------- kernel/time/timekeeping.c | 4 ++-- 13 files changed, 38 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 792586038808..bf497b8b0ec6 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1253,7 +1253,7 @@ struct timex32 { SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p) { - struct timex txc; + struct __kernel_timex txc; int ret; /* copy relevant bits of struct timex. */ @@ -1270,7 +1270,8 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p) if (copy_to_user(txc_p, &txc, offsetof(struct timex32, time)) || (copy_to_user(&txc_p->tick, &txc.tick, sizeof(struct timex32) - offsetof(struct timex32, tick))) || - (put_tv_to_tv32(&txc_p->time, &txc.time))) + (put_user(txc.time.tv_sec, &txc_p->time.tv_sec)) || + (put_user(txc.time.tv_usec, &txc_p->time.tv_usec))) return -EFAULT; return ret; diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 37de18a11207..9825ca6a6020 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -548,7 +548,7 @@ out_unlock: SYSCALL_DEFINE1(sparc_adjtimex, struct timex __user *, txc_p) { struct timex txc; /* Local copy of parameter */ - struct timex *kt = (void *)&txc; + struct __kernel_timex *kt = (void *)&txc; int ret; /* Copy the user data space into the kernel copy @@ -572,7 +572,7 @@ SYSCALL_DEFINE1(sparc_adjtimex, struct timex __user *, txc_p) SYSCALL_DEFINE2(sparc_clock_adjtime, const clockid_t, which_clock,struct timex __user *, txc_p) { struct timex txc; /* Local copy of parameter */ - struct timex *kt = (void *)&txc; + struct __kernel_timex *kt = (void *)&txc; int ret; if (!IS_ENABLED(CONFIG_POSIX_TIMERS)) { diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 48f3594a7458..79bd102c9bbc 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -124,7 +124,7 @@ static int ptp_clock_gettime(struct posix_clock *pc, struct timespec64 *tp) return err; } -static int ptp_clock_adjtime(struct posix_clock *pc, struct timex *tx) +static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) { struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); struct ptp_clock_info *ops; diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index 3a3bc71017d5..18674d7d5b1c 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -51,7 +51,7 @@ struct posix_clock; struct posix_clock_operations { struct module *owner; - int (*clock_adjtime)(struct posix_clock *pc, struct timex *tx); + int (*clock_adjtime)(struct posix_clock *pc, struct __kernel_timex *tx); int (*clock_gettime)(struct posix_clock *pc, struct timespec64 *ts); diff --git a/include/linux/time32.h b/include/linux/time32.h index 820a22e2b98b..0a1f302a1753 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -69,9 +69,9 @@ extern int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits); extern int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits); -struct timex; -int get_old_timex32(struct timex *, const struct old_timex32 __user *); -int put_old_timex32(struct old_timex32 __user *, const struct timex *); +struct __kernel_timex; +int get_old_timex32(struct __kernel_timex *, const struct old_timex32 __user *); +int put_old_timex32(struct old_timex32 __user *, const struct __kernel_timex *); #if __BITS_PER_LONG == 64 diff --git a/include/linux/timex.h b/include/linux/timex.h index a15e6aeb8d49..4aff9f0d1367 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -158,8 +158,8 @@ extern unsigned long tick_nsec; /* SHIFTED_HZ period (nsec) */ #define NTP_INTERVAL_FREQ (HZ) #define NTP_INTERVAL_LENGTH (NSEC_PER_SEC/NTP_INTERVAL_FREQ) -extern int do_adjtimex(struct timex *); -extern int do_clock_adjtime(const clockid_t which_clock, struct timex * ktx); +extern int do_adjtimex(struct __kernel_timex *); +extern int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * ktx); extern void hardpps(const struct timespec64 *, const struct timespec64 *); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 36a2bef00125..92a90014a925 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -188,13 +188,13 @@ static inline int is_error_status(int status) && (status & (STA_PPSWANDER|STA_PPSERROR))); } -static inline void pps_fill_timex(struct timex *txc) +static inline void pps_fill_timex(struct __kernel_timex *txc) { txc->ppsfreq = shift_right((pps_freq >> PPM_SCALE_INV_SHIFT) * PPM_SCALE_INV, NTP_SCALE_SHIFT); txc->jitter = pps_jitter; if (!(time_status & STA_NANO)) - txc->jitter /= NSEC_PER_USEC; + txc->jitter = pps_jitter / NSEC_PER_USEC; txc->shift = pps_shift; txc->stabil = pps_stabil; txc->jitcnt = pps_jitcnt; @@ -220,7 +220,7 @@ static inline int is_error_status(int status) return status & (STA_UNSYNC|STA_CLOCKERR); } -static inline void pps_fill_timex(struct timex *txc) +static inline void pps_fill_timex(struct __kernel_timex *txc) { /* PPS is not implemented, so these are zero */ txc->ppsfreq = 0; @@ -633,7 +633,7 @@ void ntp_notify_cmos_timer(void) /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(const struct timex *txc) +static inline void process_adj_status(const struct __kernel_timex *txc) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; @@ -656,7 +656,8 @@ static inline void process_adj_status(const struct timex *txc) } -static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai) +static inline void process_adjtimex_modes(const struct __kernel_timex *txc, + s32 *time_tai) { if (txc->modes & ADJ_STATUS) process_adj_status(txc); @@ -707,7 +708,8 @@ static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ -int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) +int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, + s32 *time_tai) { int result; @@ -729,7 +731,7 @@ int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, NTP_SCALE_SHIFT); if (!(time_status & STA_NANO)) - txc->offset /= NSEC_PER_USEC; + txc->offset = (u32)txc->offset / NSEC_PER_USEC; } result = time_state; /* mostly `TIME_OK' */ @@ -754,7 +756,7 @@ int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) txc->time.tv_sec = (time_t)ts->tv_sec; txc->time.tv_usec = ts->tv_nsec; if (!(time_status & STA_NANO)) - txc->time.tv_usec /= NSEC_PER_USEC; + txc->time.tv_usec = ts->tv_nsec / NSEC_PER_USEC; /* Handle leapsec adjustments */ if (unlikely(ts->tv_sec >= ntp_next_leap_sec)) { diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index c24b0e13f011..40e6122e634e 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -8,6 +8,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern ktime_t ntp_get_next_leap(void); extern int second_overflow(time64_t secs); -extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai); +extern int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, s32 *time_tai); extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 425bbfce6819..ec960bb939fd 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -228,7 +228,7 @@ static void put_clock_desc(struct posix_clock_desc *cd) fput(cd->fp); } -static int pc_clock_adjtime(clockid_t id, struct timex *tx) +static int pc_clock_adjtime(clockid_t id, struct __kernel_timex *tx) { struct posix_clock_desc cd; int err; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 8f7f1dd95940..2d84b3db1ade 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -179,7 +179,7 @@ static int posix_clock_realtime_set(const clockid_t which_clock, } static int posix_clock_realtime_adj(const clockid_t which_clock, - struct timex *t) + struct __kernel_timex *t) { return do_adjtimex(t); } @@ -1047,7 +1047,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, return error; } -int do_clock_adjtime(const clockid_t which_clock, struct timex * ktx) +int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * ktx) { const struct k_clock *kc = clockid_to_kclock(which_clock); @@ -1062,7 +1062,7 @@ int do_clock_adjtime(const clockid_t which_clock, struct timex * ktx) SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, struct timex __user *, utx) { - struct timex ktx; + struct __kernel_timex ktx; int err; if (copy_from_user(&ktx, utx, sizeof(ktx))) @@ -1132,7 +1132,7 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, struct old_timex32 __user *, utp) { - struct timex ktx; + struct __kernel_timex ktx; int err; err = get_old_timex32(&ktx, utp); diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index ddb21145211a..de5daa6d975a 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -8,7 +8,7 @@ struct k_clock { const struct timespec64 *tp); int (*clock_get)(const clockid_t which_clock, struct timespec64 *tp); - int (*clock_adj)(const clockid_t which_clock, struct timex *tx); + int (*clock_adj)(const clockid_t which_clock, struct __kernel_timex *tx); int (*timer_create)(struct k_itimer *timer); int (*nsleep)(const clockid_t which_clock, int flags, const struct timespec64 *); diff --git a/kernel/time/time.c b/kernel/time/time.c index 2d013bc2b271..d179d33f639a 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -265,25 +265,25 @@ COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p) { - struct timex txc; /* Local copy of parameter */ + struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ - if (copy_from_user(&txc, txc_p, sizeof(struct timex))) + if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); - return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret; + return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } #ifdef CONFIG_COMPAT_32BIT_TIME -int get_old_timex32(struct timex *txc, const struct old_timex32 __user *utp) +int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) { struct old_timex32 tx32; - memset(txc, 0, sizeof(struct timex)); + memset(txc, 0, sizeof(struct __kernel_timex)); if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) return -EFAULT; @@ -311,7 +311,7 @@ int get_old_timex32(struct timex *txc, const struct old_timex32 __user *utp) return 0; } -int put_old_timex32(struct old_timex32 __user *utp, const struct timex *txc) +int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) { struct old_timex32 tx32; @@ -344,7 +344,7 @@ int put_old_timex32(struct old_timex32 __user *utp, const struct timex *txc) COMPAT_SYSCALL_DEFINE1(adjtimex, struct old_timex32 __user *, utp) { - struct timex txc; + struct __kernel_timex txc; int err, ret; err = get_old_timex32(&txc, utp); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index ac5dbf2cd4a2..f986e1918d12 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2234,7 +2234,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ -static int timekeeping_validate_timex(const struct timex *txc) +static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ @@ -2300,7 +2300,7 @@ static int timekeeping_validate_timex(const struct timex *txc) /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ -int do_adjtimex(struct timex *txc) +int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; -- cgit v1.2.3 From 3876ced476c8ec17265d1739467e726ada88b660 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Mon, 2 Jul 2018 22:44:22 -0700 Subject: timex: change syscalls to use struct __kernel_timex struct timex is not y2038 safe. Switch all the syscall apis to use y2038 safe __kernel_timex. Note that sys_adjtimex() does not have a y2038 safe solution. C libraries can implement it by calling clock_adjtime(CLOCK_REALTIME, ...). Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 6 +++--- kernel/time/posix-timers.c | 2 +- kernel/time/time.c | 4 +++- 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index baa4b70b02d3..09330d5bda0c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -54,7 +54,7 @@ struct __sysctl_args; struct sysinfo; struct timespec; struct timeval; -struct timex; +struct __kernel_timex; struct timezone; struct tms; struct utimbuf; @@ -695,7 +695,7 @@ asmlinkage long sys_gettimeofday(struct timeval __user *tv, struct timezone __user *tz); asmlinkage long sys_settimeofday(struct timeval __user *tv, struct timezone __user *tz); -asmlinkage long sys_adjtimex(struct timex __user *txc_p); +asmlinkage long sys_adjtimex(struct __kernel_timex __user *txc_p); /* kernel/timer.c */ asmlinkage long sys_getpid(void); @@ -870,7 +870,7 @@ asmlinkage long sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); asmlinkage long sys_clock_adjtime(clockid_t which_clock, - struct timex __user *tx); + struct __kernel_timex __user *tx); asmlinkage long sys_syncfs(int fd); asmlinkage long sys_setns(int fd, int nstype); asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg, diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 2d84b3db1ade..de79f85ae14f 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1060,7 +1060,7 @@ int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * ktx) } SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, - struct timex __user *, utx) + struct __kernel_timex __user *, utx) { struct __kernel_timex ktx; int err; diff --git a/kernel/time/time.c b/kernel/time/time.c index d179d33f639a..78b5c8f1495a 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -263,7 +263,8 @@ COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, } #endif -SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p) +#if !defined(CONFIG_64BIT_TIME) || defined(CONFIG_64BIT) +SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { struct __kernel_timex txc; /* Local copy of parameter */ int ret; @@ -277,6 +278,7 @@ SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p) ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } +#endif #ifdef CONFIG_COMPAT_32BIT_TIME int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) -- cgit v1.2.3 From 8dabe7245bbc134f2cfcc12cde75c019dab924cc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 7 Jan 2019 00:33:08 +0100 Subject: y2038: syscalls: rename y2038 compat syscalls A lot of system calls that pass a time_t somewhere have an implementation using a COMPAT_SYSCALL_DEFINEx() on 64-bit architectures, and have been reworked so that this implementation can now be used on 32-bit architectures as well. The missing step is to redefine them using the regular SYSCALL_DEFINEx() to get them out of the compat namespace and make it possible to build them on 32-bit architectures. Any system call that ends in 'time' gets a '32' suffix on its name for that version, while the others get a '_time32' suffix, to distinguish them from the normal version, which takes a 64-bit time argument in the future. In this step, only 64-bit architectures are changed, doing this rename first lets us avoid touching the 32-bit architectures twice. Acked-by: Catalin Marinas Signed-off-by: Arnd Bergmann --- arch/arm64/include/asm/unistd32.h | 48 ++++++++++---------- arch/mips/kernel/syscalls/syscall_n32.tbl | 50 ++++++++++----------- arch/mips/kernel/syscalls/syscall_o32.tbl | 52 +++++++++++----------- arch/parisc/kernel/syscalls/syscall.tbl | 54 +++++++++++------------ arch/powerpc/kernel/syscalls/syscall.tbl | 52 +++++++++++----------- arch/s390/kernel/syscalls/syscall.tbl | 52 +++++++++++----------- arch/sparc/kernel/syscalls/syscall.tbl | 52 +++++++++++----------- arch/x86/entry/syscalls/syscall_32.tbl | 52 +++++++++++----------- fs/aio.c | 10 ++--- fs/select.c | 4 +- fs/timerfd.c | 4 +- fs/utimes.c | 10 ++--- include/linux/compat.h | 73 ++----------------------------- include/linux/syscalls.h | 57 ++++++++++++++++++++++++ include/uapi/asm-generic/unistd.h | 44 +++++++++---------- ipc/mqueue.c | 16 +++---- ipc/sem.c | 2 +- kernel/futex.c | 2 +- kernel/sched/core.c | 5 +-- kernel/signal.c | 2 +- kernel/sys_ni.c | 18 ++++---- kernel/time/hrtimer.c | 2 +- kernel/time/posix-stubs.c | 25 ++++++----- kernel/time/posix-timers.c | 32 +++++++------- kernel/time/time.c | 8 ++-- net/compat.c | 2 +- 26 files changed, 361 insertions(+), 367 deletions(-) (limited to 'include') diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index d10cce69a4b0..1ded82857161 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -270,7 +270,7 @@ __SYSCALL(__NR_uname, sys_newuname) /* 123 was sys_modify_ldt */ __SYSCALL(123, sys_ni_syscall) #define __NR_adjtimex 124 -__SYSCALL(__NR_adjtimex, compat_sys_adjtimex) +__SYSCALL(__NR_adjtimex, sys_adjtimex_time32) #define __NR_mprotect 125 __SYSCALL(__NR_mprotect, sys_mprotect) #define __NR_sigprocmask 126 @@ -344,9 +344,9 @@ __SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) #define __NR_sched_get_priority_min 160 __SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) #define __NR_sched_rr_get_interval 161 -__SYSCALL(__NR_sched_rr_get_interval, compat_sys_sched_rr_get_interval) +__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32) #define __NR_nanosleep 162 -__SYSCALL(__NR_nanosleep, compat_sys_nanosleep) +__SYSCALL(__NR_nanosleep, sys_nanosleep_time32) #define __NR_mremap 163 __SYSCALL(__NR_mremap, sys_mremap) #define __NR_setresuid 164 @@ -376,7 +376,7 @@ __SYSCALL(__NR_rt_sigprocmask, compat_sys_rt_sigprocmask) #define __NR_rt_sigpending 176 __SYSCALL(__NR_rt_sigpending, compat_sys_rt_sigpending) #define __NR_rt_sigtimedwait 177 -__SYSCALL(__NR_rt_sigtimedwait, compat_sys_rt_sigtimedwait) +__SYSCALL(__NR_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32) #define __NR_rt_sigqueueinfo 178 __SYSCALL(__NR_rt_sigqueueinfo, compat_sys_rt_sigqueueinfo) #define __NR_rt_sigsuspend 179 @@ -502,7 +502,7 @@ __SYSCALL(__NR_tkill, sys_tkill) #define __NR_sendfile64 239 __SYSCALL(__NR_sendfile64, sys_sendfile64) #define __NR_futex 240 -__SYSCALL(__NR_futex, compat_sys_futex) +__SYSCALL(__NR_futex, sys_futex_time32) #define __NR_sched_setaffinity 241 __SYSCALL(__NR_sched_setaffinity, compat_sys_sched_setaffinity) #define __NR_sched_getaffinity 242 @@ -512,7 +512,7 @@ __SYSCALL(__NR_io_setup, compat_sys_io_setup) #define __NR_io_destroy 244 __SYSCALL(__NR_io_destroy, sys_io_destroy) #define __NR_io_getevents 245 -__SYSCALL(__NR_io_getevents, compat_sys_io_getevents) +__SYSCALL(__NR_io_getevents, sys_io_getevents_time32) #define __NR_io_submit 246 __SYSCALL(__NR_io_submit, compat_sys_io_submit) #define __NR_io_cancel 247 @@ -538,21 +538,21 @@ __SYSCALL(__NR_set_tid_address, sys_set_tid_address) #define __NR_timer_create 257 __SYSCALL(__NR_timer_create, compat_sys_timer_create) #define __NR_timer_settime 258 -__SYSCALL(__NR_timer_settime, compat_sys_timer_settime) +__SYSCALL(__NR_timer_settime, sys_timer_settime32) #define __NR_timer_gettime 259 -__SYSCALL(__NR_timer_gettime, compat_sys_timer_gettime) +__SYSCALL(__NR_timer_gettime, sys_timer_gettime32) #define __NR_timer_getoverrun 260 __SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) #define __NR_timer_delete 261 __SYSCALL(__NR_timer_delete, sys_timer_delete) #define __NR_clock_settime 262 -__SYSCALL(__NR_clock_settime, compat_sys_clock_settime) +__SYSCALL(__NR_clock_settime, sys_clock_settime32) #define __NR_clock_gettime 263 -__SYSCALL(__NR_clock_gettime, compat_sys_clock_gettime) +__SYSCALL(__NR_clock_gettime, sys_clock_gettime32) #define __NR_clock_getres 264 -__SYSCALL(__NR_clock_getres, compat_sys_clock_getres) +__SYSCALL(__NR_clock_getres, sys_clock_getres_time32) #define __NR_clock_nanosleep 265 -__SYSCALL(__NR_clock_nanosleep, compat_sys_clock_nanosleep) +__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep_time32) #define __NR_statfs64 266 __SYSCALL(__NR_statfs64, compat_sys_aarch32_statfs64) #define __NR_fstatfs64 267 @@ -560,7 +560,7 @@ __SYSCALL(__NR_fstatfs64, compat_sys_aarch32_fstatfs64) #define __NR_tgkill 268 __SYSCALL(__NR_tgkill, sys_tgkill) #define __NR_utimes 269 -__SYSCALL(__NR_utimes, compat_sys_utimes) +__SYSCALL(__NR_utimes, sys_utimes_time32) #define __NR_arm_fadvise64_64 270 __SYSCALL(__NR_arm_fadvise64_64, compat_sys_aarch32_fadvise64_64) #define __NR_pciconfig_iobase 271 @@ -574,9 +574,9 @@ __SYSCALL(__NR_mq_open, compat_sys_mq_open) #define __NR_mq_unlink 275 __SYSCALL(__NR_mq_unlink, sys_mq_unlink) #define __NR_mq_timedsend 276 -__SYSCALL(__NR_mq_timedsend, compat_sys_mq_timedsend) +__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend_time32) #define __NR_mq_timedreceive 277 -__SYSCALL(__NR_mq_timedreceive, compat_sys_mq_timedreceive) +__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive_time32) #define __NR_mq_notify 278 __SYSCALL(__NR_mq_notify, compat_sys_mq_notify) #define __NR_mq_getsetattr 279 @@ -646,7 +646,7 @@ __SYSCALL(__NR_request_key, sys_request_key) #define __NR_keyctl 311 __SYSCALL(__NR_keyctl, compat_sys_keyctl) #define __NR_semtimedop 312 -__SYSCALL(__NR_semtimedop, compat_sys_semtimedop) +__SYSCALL(__NR_semtimedop, sys_semtimedop_time32) #define __NR_vserver 313 __SYSCALL(__NR_vserver, sys_ni_syscall) #define __NR_ioprio_set 314 @@ -674,7 +674,7 @@ __SYSCALL(__NR_mknodat, sys_mknodat) #define __NR_fchownat 325 __SYSCALL(__NR_fchownat, sys_fchownat) #define __NR_futimesat 326 -__SYSCALL(__NR_futimesat, compat_sys_futimesat) +__SYSCALL(__NR_futimesat, sys_futimesat_time32) #define __NR_fstatat64 327 __SYSCALL(__NR_fstatat64, sys_fstatat64) #define __NR_unlinkat 328 @@ -692,9 +692,9 @@ __SYSCALL(__NR_fchmodat, sys_fchmodat) #define __NR_faccessat 334 __SYSCALL(__NR_faccessat, sys_faccessat) #define __NR_pselect6 335 -__SYSCALL(__NR_pselect6, compat_sys_pselect6) +__SYSCALL(__NR_pselect6, compat_sys_pselect6_time32) #define __NR_ppoll 336 -__SYSCALL(__NR_ppoll, compat_sys_ppoll) +__SYSCALL(__NR_ppoll, compat_sys_ppoll_time32) #define __NR_unshare 337 __SYSCALL(__NR_unshare, sys_unshare) #define __NR_set_robust_list 338 @@ -718,7 +718,7 @@ __SYSCALL(__NR_epoll_pwait, compat_sys_epoll_pwait) #define __NR_kexec_load 347 __SYSCALL(__NR_kexec_load, compat_sys_kexec_load) #define __NR_utimensat 348 -__SYSCALL(__NR_utimensat, compat_sys_utimensat) +__SYSCALL(__NR_utimensat, sys_utimensat_time32) #define __NR_signalfd 349 __SYSCALL(__NR_signalfd, compat_sys_signalfd) #define __NR_timerfd_create 350 @@ -728,9 +728,9 @@ __SYSCALL(__NR_eventfd, sys_eventfd) #define __NR_fallocate 352 __SYSCALL(__NR_fallocate, compat_sys_aarch32_fallocate) #define __NR_timerfd_settime 353 -__SYSCALL(__NR_timerfd_settime, compat_sys_timerfd_settime) +__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime32) #define __NR_timerfd_gettime 354 -__SYSCALL(__NR_timerfd_gettime, compat_sys_timerfd_gettime) +__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime32) #define __NR_signalfd4 355 __SYSCALL(__NR_signalfd4, compat_sys_signalfd4) #define __NR_eventfd2 356 @@ -752,7 +752,7 @@ __SYSCALL(__NR_rt_tgsigqueueinfo, compat_sys_rt_tgsigqueueinfo) #define __NR_perf_event_open 364 __SYSCALL(__NR_perf_event_open, sys_perf_event_open) #define __NR_recvmmsg 365 -__SYSCALL(__NR_recvmmsg, compat_sys_recvmmsg) +__SYSCALL(__NR_recvmmsg, compat_sys_recvmmsg_time32) #define __NR_accept4 366 __SYSCALL(__NR_accept4, sys_accept4) #define __NR_fanotify_init 367 @@ -766,7 +766,7 @@ __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) #define __NR_open_by_handle_at 371 __SYSCALL(__NR_open_by_handle_at, compat_sys_open_by_handle_at) #define __NR_clock_adjtime 372 -__SYSCALL(__NR_clock_adjtime, compat_sys_clock_adjtime) +__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime32) #define __NR_syncfs 373 __SYSCALL(__NR_syncfs, sys_syncfs) #define __NR_sendmmsg 374 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index cc134b1211aa..6d1e019817c8 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -41,7 +41,7 @@ 31 n32 dup sys_dup 32 n32 dup2 sys_dup2 33 n32 pause sys_pause -34 n32 nanosleep compat_sys_nanosleep +34 n32 nanosleep sys_nanosleep_time32 35 n32 getitimer compat_sys_getitimer 36 n32 setitimer compat_sys_setitimer 37 n32 alarm sys_alarm @@ -133,11 +133,11 @@ 123 n32 capget sys_capget 124 n32 capset sys_capset 125 n32 rt_sigpending compat_sys_rt_sigpending -126 n32 rt_sigtimedwait compat_sys_rt_sigtimedwait +126 n32 rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 127 n32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo 128 n32 rt_sigsuspend compat_sys_rt_sigsuspend 129 n32 sigaltstack compat_sys_sigaltstack -130 n32 utime compat_sys_utime +130 n32 utime sys_utime32 131 n32 mknod sys_mknod 132 n32 personality sys_32_personality 133 n32 ustat compat_sys_ustat @@ -152,7 +152,7 @@ 142 n32 sched_getscheduler sys_sched_getscheduler 143 n32 sched_get_priority_max sys_sched_get_priority_max 144 n32 sched_get_priority_min sys_sched_get_priority_min -145 n32 sched_rr_get_interval compat_sys_sched_rr_get_interval +145 n32 sched_rr_get_interval sys_sched_rr_get_interval_time32 146 n32 mlock sys_mlock 147 n32 munlock sys_munlock 148 n32 mlockall sys_mlockall @@ -161,7 +161,7 @@ 151 n32 pivot_root sys_pivot_root 152 n32 _sysctl compat_sys_sysctl 153 n32 prctl sys_prctl -154 n32 adjtimex compat_sys_adjtimex +154 n32 adjtimex sys_adjtimex_time32 155 n32 setrlimit compat_sys_setrlimit 156 n32 chroot sys_chroot 157 n32 sync sys_sync @@ -202,7 +202,7 @@ 191 n32 fremovexattr sys_fremovexattr 192 n32 tkill sys_tkill 193 n32 reserved193 sys_ni_syscall -194 n32 futex compat_sys_futex +194 n32 futex sys_futex_time32 195 n32 sched_setaffinity compat_sys_sched_setaffinity 196 n32 sched_getaffinity compat_sys_sched_getaffinity 197 n32 cacheflush sys_cacheflush @@ -210,7 +210,7 @@ 199 n32 sysmips __sys_sysmips 200 n32 io_setup compat_sys_io_setup 201 n32 io_destroy sys_io_destroy -202 n32 io_getevents compat_sys_io_getevents +202 n32 io_getevents sys_io_getevents_time32 203 n32 io_submit compat_sys_io_submit 204 n32 io_cancel sys_io_cancel 205 n32 exit_group sys_exit_group @@ -223,29 +223,29 @@ 212 n32 fcntl64 compat_sys_fcntl64 213 n32 set_tid_address sys_set_tid_address 214 n32 restart_syscall sys_restart_syscall -215 n32 semtimedop compat_sys_semtimedop +215 n32 semtimedop sys_semtimedop_time32 216 n32 fadvise64 sys_fadvise64_64 217 n32 statfs64 compat_sys_statfs64 218 n32 fstatfs64 compat_sys_fstatfs64 219 n32 sendfile64 sys_sendfile64 220 n32 timer_create compat_sys_timer_create -221 n32 timer_settime compat_sys_timer_settime -222 n32 timer_gettime compat_sys_timer_gettime +221 n32 timer_settime sys_timer_settime32 +222 n32 timer_gettime sys_timer_gettime32 223 n32 timer_getoverrun sys_timer_getoverrun 224 n32 timer_delete sys_timer_delete -225 n32 clock_settime compat_sys_clock_settime -226 n32 clock_gettime compat_sys_clock_gettime -227 n32 clock_getres compat_sys_clock_getres -228 n32 clock_nanosleep compat_sys_clock_nanosleep +225 n32 clock_settime sys_clock_settime32 +226 n32 clock_gettime sys_clock_gettime32 +227 n32 clock_getres sys_clock_getres_time32 +228 n32 clock_nanosleep sys_clock_nanosleep_time32 229 n32 tgkill sys_tgkill -230 n32 utimes compat_sys_utimes +230 n32 utimes sys_utimes_time32 231 n32 mbind compat_sys_mbind 232 n32 get_mempolicy compat_sys_get_mempolicy 233 n32 set_mempolicy compat_sys_set_mempolicy 234 n32 mq_open compat_sys_mq_open 235 n32 mq_unlink sys_mq_unlink -236 n32 mq_timedsend compat_sys_mq_timedsend -237 n32 mq_timedreceive compat_sys_mq_timedreceive +236 n32 mq_timedsend sys_mq_timedsend_time32 +237 n32 mq_timedreceive sys_mq_timedreceive_time32 238 n32 mq_notify compat_sys_mq_notify 239 n32 mq_getsetattr compat_sys_mq_getsetattr 240 n32 vserver sys_ni_syscall @@ -263,7 +263,7 @@ 252 n32 mkdirat sys_mkdirat 253 n32 mknodat sys_mknodat 254 n32 fchownat sys_fchownat -255 n32 futimesat compat_sys_futimesat +255 n32 futimesat sys_futimesat_time32 256 n32 newfstatat sys_newfstatat 257 n32 unlinkat sys_unlinkat 258 n32 renameat sys_renameat @@ -272,8 +272,8 @@ 261 n32 readlinkat sys_readlinkat 262 n32 fchmodat sys_fchmodat 263 n32 faccessat sys_faccessat -264 n32 pselect6 compat_sys_pselect6 -265 n32 ppoll compat_sys_ppoll +264 n32 pselect6 compat_sys_pselect6_time32 +265 n32 ppoll compat_sys_ppoll_time32 266 n32 unshare sys_unshare 267 n32 splice sys_splice 268 n32 sync_file_range sys_sync_file_range @@ -287,14 +287,14 @@ 276 n32 epoll_pwait compat_sys_epoll_pwait 277 n32 ioprio_set sys_ioprio_set 278 n32 ioprio_get sys_ioprio_get -279 n32 utimensat compat_sys_utimensat +279 n32 utimensat sys_utimensat_time32 280 n32 signalfd compat_sys_signalfd 281 n32 timerfd sys_ni_syscall 282 n32 eventfd sys_eventfd 283 n32 fallocate sys_fallocate 284 n32 timerfd_create sys_timerfd_create -285 n32 timerfd_gettime compat_sys_timerfd_gettime -286 n32 timerfd_settime compat_sys_timerfd_settime +285 n32 timerfd_gettime sys_timerfd_gettime32 +286 n32 timerfd_settime sys_timerfd_settime32 287 n32 signalfd4 compat_sys_signalfd4 288 n32 eventfd2 sys_eventfd2 289 n32 epoll_create1 sys_epoll_create1 @@ -306,14 +306,14 @@ 295 n32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo 296 n32 perf_event_open sys_perf_event_open 297 n32 accept4 sys_accept4 -298 n32 recvmmsg compat_sys_recvmmsg +298 n32 recvmmsg compat_sys_recvmmsg_time32 299 n32 getdents64 sys_getdents64 300 n32 fanotify_init sys_fanotify_init 301 n32 fanotify_mark sys_fanotify_mark 302 n32 prlimit64 sys_prlimit64 303 n32 name_to_handle_at sys_name_to_handle_at 304 n32 open_by_handle_at sys_open_by_handle_at -305 n32 clock_adjtime compat_sys_clock_adjtime +305 n32 clock_adjtime sys_clock_adjtime32 306 n32 syncfs sys_syncfs 307 n32 sendmmsg compat_sys_sendmmsg 308 n32 setns sys_setns diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index fa47ea8cc6ef..e9fec7bac5a9 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -20,7 +20,7 @@ 10 o32 unlink sys_unlink 11 o32 execve sys_execve compat_sys_execve 12 o32 chdir sys_chdir -13 o32 time sys_time compat_sys_time +13 o32 time sys_time sys_time32 14 o32 mknod sys_mknod 15 o32 chmod sys_chmod 16 o32 lchown sys_lchown @@ -33,13 +33,13 @@ 22 o32 umount sys_oldumount 23 o32 setuid sys_setuid 24 o32 getuid sys_getuid -25 o32 stime sys_stime compat_sys_stime +25 o32 stime sys_stime sys_stime32 26 o32 ptrace sys_ptrace compat_sys_ptrace 27 o32 alarm sys_alarm # 28 was sys_fstat 28 o32 unused28 sys_ni_syscall 29 o32 pause sys_pause -30 o32 utime sys_utime compat_sys_utime +30 o32 utime sys_utime sys_utime32 31 o32 stty sys_ni_syscall 32 o32 gtty sys_ni_syscall 33 o32 access sys_access @@ -135,7 +135,7 @@ 121 o32 setdomainname sys_setdomainname 122 o32 uname sys_newuname 123 o32 modify_ldt sys_ni_syscall -124 o32 adjtimex sys_adjtimex compat_sys_adjtimex +124 o32 adjtimex sys_adjtimex sys_adjtimex_time32 125 o32 mprotect sys_mprotect 126 o32 sigprocmask sys_sigprocmask compat_sys_sigprocmask 127 o32 create_module sys_ni_syscall @@ -176,8 +176,8 @@ 162 o32 sched_yield sys_sched_yield 163 o32 sched_get_priority_max sys_sched_get_priority_max 164 o32 sched_get_priority_min sys_sched_get_priority_min -165 o32 sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval -166 o32 nanosleep sys_nanosleep compat_sys_nanosleep +165 o32 sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 +166 o32 nanosleep sys_nanosleep sys_nanosleep_time32 167 o32 mremap sys_mremap 168 o32 accept sys_accept 169 o32 bind sys_bind @@ -208,7 +208,7 @@ 194 o32 rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 195 o32 rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 196 o32 rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -197 o32 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +197 o32 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 198 o32 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 199 o32 rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 200 o32 pread64 sys_pread64 sys_32_pread @@ -249,12 +249,12 @@ 235 o32 fremovexattr sys_fremovexattr 236 o32 tkill sys_tkill 237 o32 sendfile64 sys_sendfile64 -238 o32 futex sys_futex compat_sys_futex +238 o32 futex sys_futex sys_futex_time32 239 o32 sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 240 o32 sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity 241 o32 io_setup sys_io_setup compat_sys_io_setup 242 o32 io_destroy sys_io_destroy -243 o32 io_getevents sys_io_getevents compat_sys_io_getevents +243 o32 io_getevents sys_io_getevents sys_io_getevents_time32 244 o32 io_submit sys_io_submit compat_sys_io_submit 245 o32 io_cancel sys_io_cancel 246 o32 exit_group sys_exit_group @@ -269,23 +269,23 @@ 255 o32 statfs64 sys_statfs64 compat_sys_statfs64 256 o32 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 257 o32 timer_create sys_timer_create compat_sys_timer_create -258 o32 timer_settime sys_timer_settime compat_sys_timer_settime -259 o32 timer_gettime sys_timer_gettime compat_sys_timer_gettime +258 o32 timer_settime sys_timer_settime sys_timer_settime32 +259 o32 timer_gettime sys_timer_gettime sys_timer_gettime32 260 o32 timer_getoverrun sys_timer_getoverrun 261 o32 timer_delete sys_timer_delete -262 o32 clock_settime sys_clock_settime compat_sys_clock_settime -263 o32 clock_gettime sys_clock_gettime compat_sys_clock_gettime -264 o32 clock_getres sys_clock_getres compat_sys_clock_getres -265 o32 clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +262 o32 clock_settime sys_clock_settime sys_clock_settime32 +263 o32 clock_gettime sys_clock_gettime sys_clock_gettime32 +264 o32 clock_getres sys_clock_getres sys_clock_getres_time32 +265 o32 clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 266 o32 tgkill sys_tgkill -267 o32 utimes sys_utimes compat_sys_utimes +267 o32 utimes sys_utimes sys_utimes_time32 268 o32 mbind sys_mbind compat_sys_mbind 269 o32 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy 270 o32 set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy 271 o32 mq_open sys_mq_open compat_sys_mq_open 272 o32 mq_unlink sys_mq_unlink -273 o32 mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend -274 o32 mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +273 o32 mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 +274 o32 mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 275 o32 mq_notify sys_mq_notify compat_sys_mq_notify 276 o32 mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 277 o32 vserver sys_ni_syscall @@ -303,7 +303,7 @@ 289 o32 mkdirat sys_mkdirat 290 o32 mknodat sys_mknodat 291 o32 fchownat sys_fchownat -292 o32 futimesat sys_futimesat compat_sys_futimesat +292 o32 futimesat sys_futimesat sys_futimesat_time32 293 o32 fstatat64 sys_fstatat64 sys_newfstatat 294 o32 unlinkat sys_unlinkat 295 o32 renameat sys_renameat @@ -312,8 +312,8 @@ 298 o32 readlinkat sys_readlinkat 299 o32 fchmodat sys_fchmodat 300 o32 faccessat sys_faccessat -301 o32 pselect6 sys_pselect6 compat_sys_pselect6 -302 o32 ppoll sys_ppoll compat_sys_ppoll +301 o32 pselect6 sys_pselect6 compat_sys_pselect6_time32 +302 o32 ppoll sys_ppoll compat_sys_ppoll_time32 303 o32 unshare sys_unshare 304 o32 splice sys_splice 305 o32 sync_file_range sys_sync_file_range sys32_sync_file_range @@ -327,14 +327,14 @@ 313 o32 epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait 314 o32 ioprio_set sys_ioprio_set 315 o32 ioprio_get sys_ioprio_get -316 o32 utimensat sys_utimensat compat_sys_utimensat +316 o32 utimensat sys_utimensat sys_utimensat_time32 317 o32 signalfd sys_signalfd compat_sys_signalfd 318 o32 timerfd sys_ni_syscall 319 o32 eventfd sys_eventfd 320 o32 fallocate sys_fallocate sys32_fallocate 321 o32 timerfd_create sys_timerfd_create -322 o32 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime -323 o32 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime +322 o32 timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 +323 o32 timerfd_settime sys_timerfd_settime sys_timerfd_settime32 324 o32 signalfd4 sys_signalfd4 compat_sys_signalfd4 325 o32 eventfd2 sys_eventfd2 326 o32 epoll_create1 sys_epoll_create1 @@ -346,13 +346,13 @@ 332 o32 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo 333 o32 perf_event_open sys_perf_event_open 334 o32 accept4 sys_accept4 -335 o32 recvmmsg sys_recvmmsg compat_sys_recvmmsg +335 o32 recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 336 o32 fanotify_init sys_fanotify_init 337 o32 fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark 338 o32 prlimit64 sys_prlimit64 339 o32 name_to_handle_at sys_name_to_handle_at 340 o32 open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -341 o32 clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +341 o32 clock_adjtime sys_clock_adjtime sys_clock_adjtime32 342 o32 syncfs sys_syncfs 343 o32 sendmmsg sys_sendmmsg compat_sys_sendmmsg 344 o32 setns sys_setns diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 71873bb72782..f7440427d459 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -20,7 +20,7 @@ 10 common unlink sys_unlink 11 common execve sys_execve compat_sys_execve 12 common chdir sys_chdir -13 common time sys_time compat_sys_time +13 common time sys_time sys_time32 14 common mknod sys_mknod 15 common chmod sys_chmod 16 common lchown sys_lchown @@ -32,12 +32,12 @@ 22 common bind sys_bind 23 common setuid sys_setuid 24 common getuid sys_getuid -25 common stime sys_stime compat_sys_stime +25 common stime sys_stime sys_stime32 26 common ptrace sys_ptrace compat_sys_ptrace 27 common alarm sys_alarm 28 common fstat sys_newfstat compat_sys_newfstat 29 common pause sys_pause -30 common utime sys_utime compat_sys_utime +30 common utime sys_utime sys_utime32 31 common connect sys_connect 32 common listen sys_listen 33 common access sys_access @@ -133,7 +133,7 @@ 121 common setdomainname sys_setdomainname 122 common sendfile sys_sendfile compat_sys_sendfile 123 common recvfrom sys_recvfrom -124 common adjtimex sys_adjtimex compat_sys_adjtimex +124 common adjtimex sys_adjtimex sys_adjtimex_time32 125 common mprotect sys_mprotect 126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask # 127 was create_module @@ -171,8 +171,8 @@ 158 common sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep compat_sys_nanosleep +161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep sys_nanosleep_time32 163 common mremap sys_mremap 164 common setresuid sys_setresuid 165 common getresuid sys_getresuid @@ -187,7 +187,7 @@ 174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 180 common chown sys_chown @@ -223,14 +223,14 @@ 207 64 readahead sys_readahead 208 common tkill sys_tkill 209 common sendfile64 sys_sendfile64 compat_sys_sendfile64 -210 common futex sys_futex compat_sys_futex +210 common futex sys_futex sys_futex_time32 211 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 212 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity # 213 was set_thread_area # 214 was get_thread_area 215 common io_setup sys_io_setup compat_sys_io_setup 216 common io_destroy sys_io_destroy -217 common io_getevents sys_io_getevents compat_sys_io_getevents +217 common io_getevents sys_io_getevents sys_io_getevents_time32 218 common io_submit sys_io_submit compat_sys_io_submit 219 common io_cancel sys_io_cancel # 220 was alloc_hugepages @@ -241,11 +241,11 @@ 225 common epoll_ctl sys_epoll_ctl 226 common epoll_wait sys_epoll_wait 227 common remap_file_pages sys_remap_file_pages -228 common semtimedop sys_semtimedop compat_sys_semtimedop +228 common semtimedop sys_semtimedop sys_semtimedop_time32 229 common mq_open sys_mq_open compat_sys_mq_open 230 common mq_unlink sys_mq_unlink -231 common mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend -232 common mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +231 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 +232 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 233 common mq_notify sys_mq_notify compat_sys_mq_notify 234 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 235 common waitid sys_waitid compat_sys_waitid @@ -265,14 +265,14 @@ 248 common lremovexattr sys_lremovexattr 249 common fremovexattr sys_fremovexattr 250 common timer_create sys_timer_create compat_sys_timer_create -251 common timer_settime sys_timer_settime compat_sys_timer_settime -252 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +251 common timer_settime sys_timer_settime sys_timer_settime32 +252 common timer_gettime sys_timer_gettime sys_timer_gettime32 253 common timer_getoverrun sys_timer_getoverrun 254 common timer_delete sys_timer_delete -255 common clock_settime sys_clock_settime compat_sys_clock_settime -256 common clock_gettime sys_clock_gettime compat_sys_clock_gettime -257 common clock_getres sys_clock_getres compat_sys_clock_getres -258 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +255 common clock_settime sys_clock_settime sys_clock_settime32 +256 common clock_gettime sys_clock_gettime sys_clock_gettime32 +257 common clock_getres sys_clock_getres sys_clock_getres_time32 +258 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 259 common tgkill sys_tgkill 260 common mbind sys_mbind compat_sys_mbind 261 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy @@ -287,13 +287,13 @@ 270 common inotify_add_watch sys_inotify_add_watch 271 common inotify_rm_watch sys_inotify_rm_watch 272 common migrate_pages sys_migrate_pages -273 common pselect6 sys_pselect6 compat_sys_pselect6 -274 common ppoll sys_ppoll compat_sys_ppoll +273 common pselect6 sys_pselect6 compat_sys_pselect6_time32 +274 common ppoll sys_ppoll compat_sys_ppoll_time32 275 common openat sys_openat compat_sys_openat 276 common mkdirat sys_mkdirat 277 common mknodat sys_mknodat 278 common fchownat sys_fchownat -279 common futimesat sys_futimesat compat_sys_futimesat +279 common futimesat sys_futimesat sys_futimesat_time32 280 common fstatat64 sys_fstatat64 281 common unlinkat sys_unlinkat 282 common renameat sys_renameat @@ -316,15 +316,15 @@ 298 common statfs64 sys_statfs64 compat_sys_statfs64 299 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 300 common kexec_load sys_kexec_load compat_sys_kexec_load -301 common utimensat sys_utimensat compat_sys_utimensat +301 common utimensat sys_utimensat sys_utimensat_time32 302 common signalfd sys_signalfd compat_sys_signalfd # 303 was timerfd 304 common eventfd sys_eventfd 305 32 fallocate parisc_fallocate 305 64 fallocate sys_fallocate 306 common timerfd_create sys_timerfd_create -307 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime -308 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +307 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 +308 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 309 common signalfd4 sys_signalfd4 compat_sys_signalfd4 310 common eventfd2 sys_eventfd2 311 common epoll_create1 sys_epoll_create1 @@ -335,12 +335,12 @@ 316 common pwritev sys_pwritev compat_sys_pwritev 317 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo 318 common perf_event_open sys_perf_event_open -319 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +319 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 320 common accept4 sys_accept4 321 common prlimit64 sys_prlimit64 322 common fanotify_init sys_fanotify_init 323 common fanotify_mark sys_fanotify_mark sys32_fanotify_mark -324 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +324 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 325 common name_to_handle_at sys_name_to_handle_at 326 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at 327 common syncfs sys_syncfs @@ -352,7 +352,7 @@ 333 common finit_module sys_finit_module 334 common sched_setattr sys_sched_setattr 335 common sched_getattr sys_sched_getattr -336 common utimes sys_utimes compat_sys_utimes +336 common utimes sys_utimes sys_utimes_time32 337 common renameat2 sys_renameat2 338 common seccomp sys_seccomp 339 common getrandom sys_getrandom diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 7555874ce39c..86650dcd2185 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -20,7 +20,7 @@ 10 common unlink sys_unlink 11 nospu execve sys_execve compat_sys_execve 12 common chdir sys_chdir -13 common time sys_time compat_sys_time +13 common time sys_time sys_time32 14 common mknod sys_mknod 15 common chmod sys_chmod 16 common lchown sys_lchown @@ -36,14 +36,14 @@ 22 spu umount sys_ni_syscall 23 common setuid sys_setuid 24 common getuid sys_getuid -25 common stime sys_stime compat_sys_stime +25 common stime sys_stime sys_stime32 26 nospu ptrace sys_ptrace compat_sys_ptrace 27 common alarm sys_alarm 28 32 oldfstat sys_fstat sys_ni_syscall 28 64 oldfstat sys_ni_syscall 28 spu oldfstat sys_ni_syscall 29 nospu pause sys_pause -30 nospu utime sys_utime compat_sys_utime +30 nospu utime sys_utime sys_utime32 31 common stty sys_ni_syscall 32 common gtty sys_ni_syscall 33 common access sys_access @@ -157,7 +157,7 @@ 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common modify_ldt sys_ni_syscall -124 common adjtimex sys_adjtimex compat_sys_adjtimex +124 common adjtimex sys_adjtimex sys_adjtimex_time32 125 common mprotect sys_mprotect 126 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask 126 64 sigprocmask sys_ni_syscall @@ -198,8 +198,8 @@ 158 common sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep compat_sys_nanosleep +161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep sys_nanosleep_time32 163 common mremap sys_mremap 164 common setresuid sys_setresuid 165 common getresuid sys_getresuid @@ -213,7 +213,7 @@ 173 nospu rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 174 nospu rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 175 nospu rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -176 nospu rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +176 nospu rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 179 common pread64 sys_pread64 compat_sys_pread64 @@ -260,7 +260,7 @@ 218 common removexattr sys_removexattr 219 common lremovexattr sys_lremovexattr 220 common fremovexattr sys_fremovexattr -221 common futex sys_futex compat_sys_futex +221 common futex sys_futex sys_futex_time32 222 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 223 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity # 224 unused @@ -268,7 +268,7 @@ 226 32 sendfile64 sys_sendfile64 compat_sys_sendfile64 227 common io_setup sys_io_setup compat_sys_io_setup 228 common io_destroy sys_io_destroy -229 common io_getevents sys_io_getevents compat_sys_io_getevents +229 common io_getevents sys_io_getevents sys_io_getevents_time32 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address @@ -280,19 +280,19 @@ 238 common epoll_wait sys_epoll_wait 239 common remap_file_pages sys_remap_file_pages 240 common timer_create sys_timer_create compat_sys_timer_create -241 common timer_settime sys_timer_settime compat_sys_timer_settime -242 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +241 common timer_settime sys_timer_settime sys_timer_settime32 +242 common timer_gettime sys_timer_gettime sys_timer_gettime32 243 common timer_getoverrun sys_timer_getoverrun 244 common timer_delete sys_timer_delete -245 common clock_settime sys_clock_settime compat_sys_clock_settime -246 common clock_gettime sys_clock_gettime compat_sys_clock_gettime -247 common clock_getres sys_clock_getres compat_sys_clock_getres -248 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +245 common clock_settime sys_clock_settime sys_clock_settime32 +246 common clock_gettime sys_clock_gettime sys_clock_gettime32 +247 common clock_getres sys_clock_getres sys_clock_getres_time32 +248 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 249 32 swapcontext ppc_swapcontext ppc32_swapcontext 249 64 swapcontext ppc64_swapcontext 249 spu swapcontext sys_ni_syscall 250 common tgkill sys_tgkill -251 common utimes sys_utimes compat_sys_utimes +251 common utimes sys_utimes sys_utimes_time32 252 common statfs64 sys_statfs64 compat_sys_statfs64 253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 254 32 fadvise64_64 ppc_fadvise64_64 @@ -308,8 +308,8 @@ 261 nospu set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy 262 nospu mq_open sys_mq_open compat_sys_mq_open 263 nospu mq_unlink sys_mq_unlink -264 nospu mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend -265 nospu mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +264 nospu mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 +265 nospu mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 266 nospu mq_notify sys_mq_notify compat_sys_mq_notify 267 nospu mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 268 nospu kexec_load sys_kexec_load compat_sys_kexec_load @@ -324,8 +324,8 @@ 277 nospu inotify_rm_watch sys_inotify_rm_watch 278 nospu spu_run sys_spu_run 279 nospu spu_create sys_spu_create -280 nospu pselect6 sys_pselect6 compat_sys_pselect6 -281 nospu ppoll sys_ppoll compat_sys_ppoll +280 nospu pselect6 sys_pselect6 compat_sys_pselect6_time32 +281 nospu ppoll sys_ppoll compat_sys_ppoll_time32 282 common unshare sys_unshare 283 common splice sys_splice 284 common tee sys_tee @@ -334,7 +334,7 @@ 287 common mkdirat sys_mkdirat 288 common mknodat sys_mknodat 289 common fchownat sys_fchownat -290 common futimesat sys_futimesat compat_sys_futimesat +290 common futimesat sys_futimesat sys_futimesat_time32 291 32 fstatat64 sys_fstatat64 291 64 newfstatat sys_newfstatat 291 spu newfstatat sys_newfstatat @@ -350,15 +350,15 @@ 301 common move_pages sys_move_pages compat_sys_move_pages 302 common getcpu sys_getcpu 303 nospu epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -304 common utimensat sys_utimensat compat_sys_utimensat +304 common utimensat sys_utimensat sys_utimensat_time32 305 common signalfd sys_signalfd compat_sys_signalfd 306 common timerfd_create sys_timerfd_create 307 common eventfd sys_eventfd 308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2 309 nospu fallocate sys_fallocate compat_sys_fallocate 310 nospu subpage_prot sys_subpage_prot -311 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime -312 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +311 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 +312 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 313 common signalfd4 sys_signalfd4 compat_sys_signalfd4 314 common eventfd2 sys_eventfd2 315 common epoll_create1 sys_epoll_create1 @@ -389,11 +389,11 @@ 340 common getsockopt sys_getsockopt compat_sys_getsockopt 341 common sendmsg sys_sendmsg compat_sys_sendmsg 342 common recvmsg sys_recvmsg compat_sys_recvmsg -343 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +343 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 344 common accept4 sys_accept4 345 common name_to_handle_at sys_name_to_handle_at 346 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -347 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +347 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 348 common syncfs sys_syncfs 349 common sendmmsg sys_sendmmsg compat_sys_sendmmsg 350 common setns sys_setns diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 620e222003ca..285201cf1f83 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -20,7 +20,7 @@ 10 common unlink sys_unlink sys_unlink 11 common execve sys_execve compat_sys_execve 12 common chdir sys_chdir sys_chdir -13 32 time - compat_sys_time +13 32 time - sys_time32 14 common mknod sys_mknod sys_mknod 15 common chmod sys_chmod sys_chmod 16 32 lchown - sys_lchown16 @@ -30,11 +30,11 @@ 22 common umount sys_oldumount sys_oldumount 23 32 setuid - sys_setuid16 24 32 getuid - sys_getuid16 -25 32 stime - compat_sys_stime +25 32 stime - sys_stime32 26 common ptrace sys_ptrace compat_sys_ptrace 27 common alarm sys_alarm sys_alarm 29 common pause sys_pause sys_pause -30 common utime sys_utime compat_sys_utime +30 common utime sys_utime sys_utime32 33 common access sys_access sys_access 34 common nice sys_nice sys_nice 36 common sync sys_sync sys_sync @@ -112,7 +112,7 @@ 120 common clone sys_clone sys_clone 121 common setdomainname sys_setdomainname sys_setdomainname 122 common uname sys_newuname sys_newuname -124 common adjtimex sys_adjtimex compat_sys_adjtimex +124 common adjtimex sys_adjtimex sys_adjtimex_time32 125 common mprotect sys_mprotect sys_mprotect 126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask 127 common create_module - - @@ -150,8 +150,8 @@ 158 common sched_yield sys_sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep compat_sys_nanosleep +161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep sys_nanosleep_time32 163 common mremap sys_mremap sys_mremap 164 32 setresuid - sys_setresuid16 165 32 getresuid - sys_getresuid16 @@ -165,7 +165,7 @@ 174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 180 common pread64 sys_pread64 compat_sys_s390_pread64 @@ -246,13 +246,13 @@ 235 common fremovexattr sys_fremovexattr sys_fremovexattr 236 common gettid sys_gettid sys_gettid 237 common tkill sys_tkill sys_tkill -238 common futex sys_futex compat_sys_futex +238 common futex sys_futex sys_futex_time32 239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity 241 common tgkill sys_tgkill sys_tgkill 243 common io_setup sys_io_setup compat_sys_io_setup 244 common io_destroy sys_io_destroy sys_io_destroy -245 common io_getevents sys_io_getevents compat_sys_io_getevents +245 common io_getevents sys_io_getevents sys_io_getevents_time32 246 common io_submit sys_io_submit compat_sys_io_submit 247 common io_cancel sys_io_cancel sys_io_cancel 248 common exit_group sys_exit_group sys_exit_group @@ -262,14 +262,14 @@ 252 common set_tid_address sys_set_tid_address sys_set_tid_address 253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64 254 common timer_create sys_timer_create compat_sys_timer_create -255 common timer_settime sys_timer_settime compat_sys_timer_settime -256 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +255 common timer_settime sys_timer_settime sys_timer_settime32 +256 common timer_gettime sys_timer_gettime sys_timer_gettime32 257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun 258 common timer_delete sys_timer_delete sys_timer_delete -259 common clock_settime sys_clock_settime compat_sys_clock_settime -260 common clock_gettime sys_clock_gettime compat_sys_clock_gettime -261 common clock_getres sys_clock_getres compat_sys_clock_getres -262 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +259 common clock_settime sys_clock_settime sys_clock_settime32 +260 common clock_gettime sys_clock_gettime sys_clock_gettime32 +261 common clock_getres sys_clock_getres sys_clock_getres_time32 +262 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 264 32 fadvise64_64 - compat_sys_s390_fadvise64_64 265 common statfs64 sys_statfs64 compat_sys_statfs64 266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 @@ -279,8 +279,8 @@ 270 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy 271 common mq_open sys_mq_open compat_sys_mq_open 272 common mq_unlink sys_mq_unlink sys_mq_unlink -273 common mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend -274 common mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +273 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 +274 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 275 common mq_notify sys_mq_notify compat_sys_mq_notify 276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 277 common kexec_load sys_kexec_load compat_sys_kexec_load @@ -298,7 +298,7 @@ 289 common mkdirat sys_mkdirat sys_mkdirat 290 common mknodat sys_mknodat sys_mknodat 291 common fchownat sys_fchownat sys_fchownat -292 common futimesat sys_futimesat compat_sys_futimesat +292 common futimesat sys_futimesat sys_futimesat_time32 293 32 fstatat64 - compat_sys_s390_fstatat64 293 64 newfstatat sys_newfstatat - 294 common unlinkat sys_unlinkat sys_unlinkat @@ -308,8 +308,8 @@ 298 common readlinkat sys_readlinkat sys_readlinkat 299 common fchmodat sys_fchmodat sys_fchmodat 300 common faccessat sys_faccessat sys_faccessat -301 common pselect6 sys_pselect6 compat_sys_pselect6 -302 common ppoll sys_ppoll compat_sys_ppoll +301 common pselect6 sys_pselect6 compat_sys_pselect6_time32 +302 common ppoll sys_ppoll compat_sys_ppoll_time32 303 common unshare sys_unshare sys_unshare 304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list 305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list @@ -320,15 +320,15 @@ 310 common move_pages sys_move_pages compat_sys_move_pages 311 common getcpu sys_getcpu sys_getcpu 312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -313 common utimes sys_utimes compat_sys_utimes +313 common utimes sys_utimes sys_utimes_time32 314 common fallocate sys_fallocate compat_sys_s390_fallocate -315 common utimensat sys_utimensat compat_sys_utimensat +315 common utimensat sys_utimensat sys_utimensat_time32 316 common signalfd sys_signalfd compat_sys_signalfd 317 common timerfd - - 318 common eventfd sys_eventfd sys_eventfd 319 common timerfd_create sys_timerfd_create sys_timerfd_create -320 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime -321 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +320 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 +321 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 322 common signalfd4 sys_signalfd4 compat_sys_signalfd4 323 common eventfd2 sys_eventfd2 sys_eventfd2 324 common inotify_init1 sys_inotify_init1 sys_inotify_init1 @@ -344,7 +344,7 @@ 334 common prlimit64 sys_prlimit64 sys_prlimit64 335 common name_to_handle_at sys_name_to_handle_at sys_name_to_handle_at 336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -337 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +337 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 338 common syncfs sys_syncfs sys_syncfs 339 common setns sys_setns sys_setns 340 common process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv @@ -364,7 +364,7 @@ 354 common execveat sys_execveat compat_sys_execveat 355 common userfaultfd sys_userfaultfd sys_userfaultfd 356 common membarrier sys_membarrier sys_membarrier -357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg 359 common socket sys_socket sys_socket 360 common socketpair sys_socketpair sys_socketpair diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index e63cd013cc77..7cb05b50aeaa 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -44,7 +44,7 @@ 28 common sigaltstack sys_sigaltstack compat_sys_sigaltstack 29 32 pause sys_pause 29 64 pause sys_nis_syscall -30 common utime sys_utime compat_sys_utime +30 common utime sys_utime sys_utime32 31 32 lchown32 sys_lchown 32 32 fchown32 sys_fchown 33 common access sys_access @@ -128,7 +128,7 @@ 102 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 103 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 104 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -105 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +105 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 106 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 107 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 108 32 setresuid32 sys_setresuid @@ -168,11 +168,11 @@ 135 common socketpair sys_socketpair 136 common mkdir sys_mkdir 137 common rmdir sys_rmdir -138 common utimes sys_utimes compat_sys_utimes +138 common utimes sys_utimes sys_utimes_time32 139 common stat64 sys_stat64 compat_sys_stat64 140 common sendfile64 sys_sendfile64 141 common getpeername sys_getpeername -142 common futex sys_futex compat_sys_futex +142 common futex sys_futex sys_futex_time32 143 common gettid sys_gettid 144 common getrlimit sys_getrlimit compat_sys_getrlimit 145 common setrlimit sys_setrlimit compat_sys_setrlimit @@ -258,7 +258,7 @@ 216 64 sigreturn sys_nis_syscall 217 common clone sys_clone 218 common ioprio_get sys_ioprio_get -219 32 adjtimex sys_adjtimex compat_sys_adjtimex +219 32 adjtimex sys_adjtimex sys_adjtimex_time32 219 64 adjtimex sys_sparc_adjtimex 220 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask 220 64 sigprocmask sys_nis_syscall @@ -272,9 +272,9 @@ 228 common setfsuid sys_setfsuid16 229 common setfsgid sys_setfsgid16 230 common _newselect sys_select compat_sys_select -231 32 time sys_time compat_sys_time +231 32 time sys_time sys_time32 232 common splice sys_splice -233 common stime sys_stime compat_sys_stime +233 common stime sys_stime sys_stime32 234 common statfs64 sys_statfs64 compat_sys_statfs64 235 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 236 common _llseek sys_llseek @@ -289,8 +289,8 @@ 245 common sched_yield sys_sched_yield 246 common sched_get_priority_max sys_sched_get_priority_max 247 common sched_get_priority_min sys_sched_get_priority_min -248 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval -249 common nanosleep sys_nanosleep compat_sys_nanosleep +248 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 +249 common nanosleep sys_nanosleep sys_nanosleep_time32 250 32 mremap sys_mremap 250 64 mremap sys_64_mremap 251 common _sysctl sys_sysctl compat_sys_sysctl @@ -299,14 +299,14 @@ 254 32 nfsservctl sys_ni_syscall sys_nis_syscall 254 64 nfsservctl sys_nis_syscall 255 common sync_file_range sys_sync_file_range compat_sys_sync_file_range -256 common clock_settime sys_clock_settime compat_sys_clock_settime -257 common clock_gettime sys_clock_gettime compat_sys_clock_gettime -258 common clock_getres sys_clock_getres compat_sys_clock_getres -259 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +256 common clock_settime sys_clock_settime sys_clock_settime32 +257 common clock_gettime sys_clock_gettime sys_clock_gettime32 +258 common clock_getres sys_clock_getres sys_clock_getres_time32 +259 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 260 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity 261 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity -262 common timer_settime sys_timer_settime compat_sys_timer_settime -263 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +262 common timer_settime sys_timer_settime sys_timer_settime32 +263 common timer_gettime sys_timer_gettime sys_timer_gettime32 264 common timer_getoverrun sys_timer_getoverrun 265 common timer_delete sys_timer_delete 266 common timer_create sys_timer_create compat_sys_timer_create @@ -316,11 +316,11 @@ 269 common io_destroy sys_io_destroy 270 common io_submit sys_io_submit compat_sys_io_submit 271 common io_cancel sys_io_cancel -272 common io_getevents sys_io_getevents compat_sys_io_getevents +272 common io_getevents sys_io_getevents sys_io_getevents_time32 273 common mq_open sys_mq_open compat_sys_mq_open 274 common mq_unlink sys_mq_unlink -275 common mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend -276 common mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +275 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 +276 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 277 common mq_notify sys_mq_notify compat_sys_mq_notify 278 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 279 common waitid sys_waitid compat_sys_waitid @@ -332,7 +332,7 @@ 285 common mkdirat sys_mkdirat 286 common mknodat sys_mknodat 287 common fchownat sys_fchownat -288 common futimesat sys_futimesat compat_sys_futimesat +288 common futimesat sys_futimesat sys_futimesat_time32 289 common fstatat64 sys_fstatat64 compat_sys_fstatat64 290 common unlinkat sys_unlinkat 291 common renameat sys_renameat @@ -341,8 +341,8 @@ 294 common readlinkat sys_readlinkat 295 common fchmodat sys_fchmodat 296 common faccessat sys_faccessat -297 common pselect6 sys_pselect6 compat_sys_pselect6 -298 common ppoll sys_ppoll compat_sys_ppoll +297 common pselect6 sys_pselect6 compat_sys_pselect6_time32 +298 common ppoll sys_ppoll compat_sys_ppoll_time32 299 common unshare sys_unshare 300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list 301 common get_robust_list sys_get_robust_list compat_sys_get_robust_list @@ -354,13 +354,13 @@ 307 common move_pages sys_move_pages compat_sys_move_pages 308 common getcpu sys_getcpu 309 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -310 common utimensat sys_utimensat compat_sys_utimensat +310 common utimensat sys_utimensat sys_utimensat_time32 311 common signalfd sys_signalfd compat_sys_signalfd 312 common timerfd_create sys_timerfd_create 313 common eventfd sys_eventfd 314 common fallocate sys_fallocate compat_sys_fallocate -315 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime -316 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +315 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 +316 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 317 common signalfd4 sys_signalfd4 compat_sys_signalfd4 318 common eventfd2 sys_eventfd2 319 common epoll_create1 sys_epoll_create1 @@ -372,13 +372,13 @@ 325 common pwritev sys_pwritev compat_sys_pwritev 326 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo 327 common perf_event_open sys_perf_event_open -328 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +328 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 329 common fanotify_init sys_fanotify_init 330 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark 331 common prlimit64 sys_prlimit64 332 common name_to_handle_at sys_name_to_handle_at 333 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -334 32 clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +334 32 clock_adjtime sys_clock_adjtime sys_clock_adjtime32 334 64 clock_adjtime sys_sparc_clock_adjtime 335 common syncfs sys_syncfs 336 common sendmmsg sys_sendmmsg compat_sys_sendmmsg diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 2be1d0eb7754..7705d5ecad25 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -24,7 +24,7 @@ 10 i386 unlink sys_unlink __ia32_sys_unlink 11 i386 execve sys_execve __ia32_compat_sys_execve 12 i386 chdir sys_chdir __ia32_sys_chdir -13 i386 time sys_time __ia32_compat_sys_time +13 i386 time sys_time __ia32_sys_time32 14 i386 mknod sys_mknod __ia32_sys_mknod 15 i386 chmod sys_chmod __ia32_sys_chmod 16 i386 lchown sys_lchown16 __ia32_sys_lchown16 @@ -36,12 +36,12 @@ 22 i386 umount sys_oldumount __ia32_sys_oldumount 23 i386 setuid sys_setuid16 __ia32_sys_setuid16 24 i386 getuid sys_getuid16 __ia32_sys_getuid16 -25 i386 stime sys_stime __ia32_compat_sys_stime +25 i386 stime sys_stime __ia32_sys_stime32 26 i386 ptrace sys_ptrace __ia32_compat_sys_ptrace 27 i386 alarm sys_alarm __ia32_sys_alarm 28 i386 oldfstat sys_fstat __ia32_sys_fstat 29 i386 pause sys_pause __ia32_sys_pause -30 i386 utime sys_utime __ia32_compat_sys_utime +30 i386 utime sys_utime __ia32_sys_utime32 31 i386 stty 32 i386 gtty 33 i386 access sys_access __ia32_sys_access @@ -135,7 +135,7 @@ 121 i386 setdomainname sys_setdomainname __ia32_sys_setdomainname 122 i386 uname sys_newuname __ia32_sys_newuname 123 i386 modify_ldt sys_modify_ldt __ia32_sys_modify_ldt -124 i386 adjtimex sys_adjtimex __ia32_compat_sys_adjtimex +124 i386 adjtimex sys_adjtimex __ia32_sys_adjtimex_time32 125 i386 mprotect sys_mprotect __ia32_sys_mprotect 126 i386 sigprocmask sys_sigprocmask __ia32_compat_sys_sigprocmask 127 i386 create_module @@ -172,8 +172,8 @@ 158 i386 sched_yield sys_sched_yield __ia32_sys_sched_yield 159 i386 sched_get_priority_max sys_sched_get_priority_max __ia32_sys_sched_get_priority_max 160 i386 sched_get_priority_min sys_sched_get_priority_min __ia32_sys_sched_get_priority_min -161 i386 sched_rr_get_interval sys_sched_rr_get_interval __ia32_compat_sys_sched_rr_get_interval -162 i386 nanosleep sys_nanosleep __ia32_compat_sys_nanosleep +161 i386 sched_rr_get_interval sys_sched_rr_get_interval __ia32_sys_sched_rr_get_interval_time32 +162 i386 nanosleep sys_nanosleep __ia32_sys_nanosleep_time32 163 i386 mremap sys_mremap __ia32_sys_mremap 164 i386 setresuid sys_setresuid16 __ia32_sys_setresuid16 165 i386 getresuid sys_getresuid16 __ia32_sys_getresuid16 @@ -188,7 +188,7 @@ 174 i386 rt_sigaction sys_rt_sigaction __ia32_compat_sys_rt_sigaction 175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending __ia32_compat_sys_rt_sigpending -177 i386 rt_sigtimedwait sys_rt_sigtimedwait __ia32_compat_sys_rt_sigtimedwait +177 i386 rt_sigtimedwait sys_rt_sigtimedwait __ia32_compat_sys_rt_sigtimedwait_time32 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo __ia32_compat_sys_rt_sigqueueinfo 179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_sys_rt_sigsuspend 180 i386 pread64 sys_pread64 __ia32_compat_sys_x86_pread @@ -251,14 +251,14 @@ 237 i386 fremovexattr sys_fremovexattr __ia32_sys_fremovexattr 238 i386 tkill sys_tkill __ia32_sys_tkill 239 i386 sendfile64 sys_sendfile64 __ia32_sys_sendfile64 -240 i386 futex sys_futex __ia32_compat_sys_futex +240 i386 futex sys_futex __ia32_sys_futex_time32 241 i386 sched_setaffinity sys_sched_setaffinity __ia32_compat_sys_sched_setaffinity 242 i386 sched_getaffinity sys_sched_getaffinity __ia32_compat_sys_sched_getaffinity 243 i386 set_thread_area sys_set_thread_area __ia32_sys_set_thread_area 244 i386 get_thread_area sys_get_thread_area __ia32_sys_get_thread_area 245 i386 io_setup sys_io_setup __ia32_compat_sys_io_setup 246 i386 io_destroy sys_io_destroy __ia32_sys_io_destroy -247 i386 io_getevents sys_io_getevents __ia32_compat_sys_io_getevents +247 i386 io_getevents sys_io_getevents __ia32_sys_io_getevents_time32 248 i386 io_submit sys_io_submit __ia32_compat_sys_io_submit 249 i386 io_cancel sys_io_cancel __ia32_sys_io_cancel 250 i386 fadvise64 sys_fadvise64 __ia32_compat_sys_x86_fadvise64 @@ -271,18 +271,18 @@ 257 i386 remap_file_pages sys_remap_file_pages __ia32_sys_remap_file_pages 258 i386 set_tid_address sys_set_tid_address __ia32_sys_set_tid_address 259 i386 timer_create sys_timer_create __ia32_compat_sys_timer_create -260 i386 timer_settime sys_timer_settime __ia32_compat_sys_timer_settime -261 i386 timer_gettime sys_timer_gettime __ia32_compat_sys_timer_gettime +260 i386 timer_settime sys_timer_settime __ia32_sys_timer_settime32 +261 i386 timer_gettime sys_timer_gettime __ia32_sys_timer_gettime32 262 i386 timer_getoverrun sys_timer_getoverrun __ia32_sys_timer_getoverrun 263 i386 timer_delete sys_timer_delete __ia32_sys_timer_delete -264 i386 clock_settime sys_clock_settime __ia32_compat_sys_clock_settime -265 i386 clock_gettime sys_clock_gettime __ia32_compat_sys_clock_gettime -266 i386 clock_getres sys_clock_getres __ia32_compat_sys_clock_getres -267 i386 clock_nanosleep sys_clock_nanosleep __ia32_compat_sys_clock_nanosleep +264 i386 clock_settime sys_clock_settime __ia32_sys_clock_settime32 +265 i386 clock_gettime sys_clock_gettime __ia32_sys_clock_gettime32 +266 i386 clock_getres sys_clock_getres __ia32_sys_clock_getres_time32 +267 i386 clock_nanosleep sys_clock_nanosleep __ia32_sys_clock_nanosleep_time32 268 i386 statfs64 sys_statfs64 __ia32_compat_sys_statfs64 269 i386 fstatfs64 sys_fstatfs64 __ia32_compat_sys_fstatfs64 270 i386 tgkill sys_tgkill __ia32_sys_tgkill -271 i386 utimes sys_utimes __ia32_compat_sys_utimes +271 i386 utimes sys_utimes __ia32_sys_utimes_time32 272 i386 fadvise64_64 sys_fadvise64_64 __ia32_compat_sys_x86_fadvise64_64 273 i386 vserver 274 i386 mbind sys_mbind __ia32_sys_mbind @@ -290,8 +290,8 @@ 276 i386 set_mempolicy sys_set_mempolicy __ia32_sys_set_mempolicy 277 i386 mq_open sys_mq_open __ia32_compat_sys_mq_open 278 i386 mq_unlink sys_mq_unlink __ia32_sys_mq_unlink -279 i386 mq_timedsend sys_mq_timedsend __ia32_compat_sys_mq_timedsend -280 i386 mq_timedreceive sys_mq_timedreceive __ia32_compat_sys_mq_timedreceive +279 i386 mq_timedsend sys_mq_timedsend __ia32_sys_mq_timedsend_time32 +280 i386 mq_timedreceive sys_mq_timedreceive __ia32_sys_mq_timedreceive_time32 281 i386 mq_notify sys_mq_notify __ia32_compat_sys_mq_notify 282 i386 mq_getsetattr sys_mq_getsetattr __ia32_compat_sys_mq_getsetattr 283 i386 kexec_load sys_kexec_load __ia32_compat_sys_kexec_load @@ -310,7 +310,7 @@ 296 i386 mkdirat sys_mkdirat __ia32_sys_mkdirat 297 i386 mknodat sys_mknodat __ia32_sys_mknodat 298 i386 fchownat sys_fchownat __ia32_sys_fchownat -299 i386 futimesat sys_futimesat __ia32_compat_sys_futimesat +299 i386 futimesat sys_futimesat __ia32_sys_futimesat_time32 300 i386 fstatat64 sys_fstatat64 __ia32_compat_sys_x86_fstatat 301 i386 unlinkat sys_unlinkat __ia32_sys_unlinkat 302 i386 renameat sys_renameat __ia32_sys_renameat @@ -319,8 +319,8 @@ 305 i386 readlinkat sys_readlinkat __ia32_sys_readlinkat 306 i386 fchmodat sys_fchmodat __ia32_sys_fchmodat 307 i386 faccessat sys_faccessat __ia32_sys_faccessat -308 i386 pselect6 sys_pselect6 __ia32_compat_sys_pselect6 -309 i386 ppoll sys_ppoll __ia32_compat_sys_ppoll +308 i386 pselect6 sys_pselect6 __ia32_compat_sys_pselect6_time32 +309 i386 ppoll sys_ppoll __ia32_compat_sys_ppoll_time32 310 i386 unshare sys_unshare __ia32_sys_unshare 311 i386 set_robust_list sys_set_robust_list __ia32_compat_sys_set_robust_list 312 i386 get_robust_list sys_get_robust_list __ia32_compat_sys_get_robust_list @@ -331,13 +331,13 @@ 317 i386 move_pages sys_move_pages __ia32_compat_sys_move_pages 318 i386 getcpu sys_getcpu __ia32_sys_getcpu 319 i386 epoll_pwait sys_epoll_pwait __ia32_sys_epoll_pwait -320 i386 utimensat sys_utimensat __ia32_compat_sys_utimensat +320 i386 utimensat sys_utimensat __ia32_sys_utimensat_time32 321 i386 signalfd sys_signalfd __ia32_compat_sys_signalfd 322 i386 timerfd_create sys_timerfd_create __ia32_sys_timerfd_create 323 i386 eventfd sys_eventfd __ia32_sys_eventfd 324 i386 fallocate sys_fallocate __ia32_compat_sys_x86_fallocate -325 i386 timerfd_settime sys_timerfd_settime __ia32_compat_sys_timerfd_settime -326 i386 timerfd_gettime sys_timerfd_gettime __ia32_compat_sys_timerfd_gettime +325 i386 timerfd_settime sys_timerfd_settime __ia32_sys_timerfd_settime32 +326 i386 timerfd_gettime sys_timerfd_gettime __ia32_sys_timerfd_gettime32 327 i386 signalfd4 sys_signalfd4 __ia32_compat_sys_signalfd4 328 i386 eventfd2 sys_eventfd2 __ia32_sys_eventfd2 329 i386 epoll_create1 sys_epoll_create1 __ia32_sys_epoll_create1 @@ -348,13 +348,13 @@ 334 i386 pwritev sys_pwritev __ia32_compat_sys_pwritev 335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo __ia32_compat_sys_rt_tgsigqueueinfo 336 i386 perf_event_open sys_perf_event_open __ia32_sys_perf_event_open -337 i386 recvmmsg sys_recvmmsg __ia32_compat_sys_recvmmsg +337 i386 recvmmsg sys_recvmmsg __ia32_compat_sys_recvmmsg_time32 338 i386 fanotify_init sys_fanotify_init __ia32_sys_fanotify_init 339 i386 fanotify_mark sys_fanotify_mark __ia32_compat_sys_fanotify_mark 340 i386 prlimit64 sys_prlimit64 __ia32_sys_prlimit64 341 i386 name_to_handle_at sys_name_to_handle_at __ia32_sys_name_to_handle_at 342 i386 open_by_handle_at sys_open_by_handle_at __ia32_compat_sys_open_by_handle_at -343 i386 clock_adjtime sys_clock_adjtime __ia32_compat_sys_clock_adjtime +343 i386 clock_adjtime sys_clock_adjtime __ia32_sys_clock_adjtime32 344 i386 syncfs sys_syncfs __ia32_sys_syncfs 345 i386 sendmmsg sys_sendmmsg __ia32_compat_sys_sendmmsg 346 i386 setns sys_setns __ia32_sys_setns diff --git a/fs/aio.c b/fs/aio.c index b906ff70c90f..4394d3fe116a 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -2198,11 +2198,11 @@ SYSCALL_DEFINE6(io_pgetevents_time32, #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id, - compat_long_t, min_nr, - compat_long_t, nr, - struct io_event __user *, events, - struct old_timespec32 __user *, timeout) +SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id, + __s32, min_nr, + __s32, nr, + struct io_event __user *, events, + struct old_timespec32 __user *, timeout) { struct timespec64 t; int ret; diff --git a/fs/select.c b/fs/select.c index d0f35dbc0e8f..6cbc9ff56ba0 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1379,7 +1379,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, +COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { @@ -1402,7 +1402,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, #endif #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, +COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { diff --git a/fs/timerfd.c b/fs/timerfd.c index 803ca070d42e..6a6fc8aa1de7 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -560,7 +560,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, +SYSCALL_DEFINE4(timerfd_settime32, int, ufd, int, flags, const struct old_itimerspec32 __user *, utmr, struct old_itimerspec32 __user *, otmr) { @@ -577,7 +577,7 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, return ret; } -COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd, +SYSCALL_DEFINE2(timerfd_gettime32, int, ufd, struct old_itimerspec32 __user *, otmr) { struct itimerspec64 kotmr; diff --git a/fs/utimes.c b/fs/utimes.c index bdcf2daf39c1..350c9c16ace1 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -224,8 +224,8 @@ SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) * of sys_utimes. */ #ifdef __ARCH_WANT_SYS_UTIME32 -COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, - struct old_utimbuf32 __user *, t) +SYSCALL_DEFINE2(utime32, const char __user *, filename, + struct old_utimbuf32 __user *, t) { struct timespec64 tv[2]; @@ -240,7 +240,7 @@ COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, } #endif -COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) +SYSCALL_DEFINE4(utimensat_time32, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) { struct timespec64 tv[2]; @@ -276,14 +276,14 @@ static long do_compat_futimesat(unsigned int dfd, const char __user *filename, return do_utimes(dfd, filename, t ? tv : NULL, 0); } -COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, +SYSCALL_DEFINE3(futimesat_time32, unsigned int, dfd, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(dfd, filename, t); } -COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct old_timeval32 __user *, t) +SYSCALL_DEFINE2(utimes_time32, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(AT_FDCWD, filename, t); } diff --git a/include/linux/compat.h b/include/linux/compat.h index 657ca6abd855..ebddcb6cfcf8 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -520,11 +520,6 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p); asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr, u32 __user *iocb); -asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id, - compat_long_t min_nr, - compat_long_t nr, - struct io_event __user *events, - struct old_timespec32 __user *timeout); asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, @@ -617,7 +612,7 @@ asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, compat_size_t count); /* fs/select.c */ -asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, +asmlinkage long compat_sys_pselect6_time32(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timespec32 __user *tsp, @@ -627,7 +622,7 @@ asmlinkage long compat_sys_pselect6_time64(int n, compat_ulong_t __user *inp, compat_ulong_t __user *exp, struct __kernel_timespec __user *tsp, void __user *sig); -asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, +asmlinkage long compat_sys_ppoll_time32(struct pollfd __user *ufds, unsigned int nfds, struct old_timespec32 __user *tsp, const compat_sigset_t __user *sigmask, @@ -657,19 +652,6 @@ asmlinkage long compat_sys_newfstat(unsigned int fd, /* fs/sync.c: No generic prototype for sync_file_range and sync_file_range2 */ -/* fs/timerfd.c */ -asmlinkage long compat_sys_timerfd_gettime(int ufd, - struct old_itimerspec32 __user *otmr); -asmlinkage long compat_sys_timerfd_settime(int ufd, int flags, - const struct old_itimerspec32 __user *utmr, - struct old_itimerspec32 __user *otmr); - -/* fs/utimes.c */ -asmlinkage long compat_sys_utimensat(unsigned int dfd, - const char __user *filename, - struct old_timespec32 __user *t, - int flags); - /* kernel/exit.c */ asmlinkage long compat_sys_waitid(int, compat_pid_t, struct compat_siginfo __user *, int, @@ -678,9 +660,6 @@ asmlinkage long compat_sys_waitid(int, compat_pid_t, /* kernel/futex.c */ -asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, - struct old_timespec32 __user *utime, u32 __user *uaddr2, - u32 val3); asmlinkage long compat_sys_set_robust_list(struct compat_robust_list_head __user *head, compat_size_t len); @@ -688,10 +667,6 @@ asmlinkage long compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, compat_size_t __user *len_ptr); -/* kernel/hrtimer.c */ -asmlinkage long compat_sys_nanosleep(struct old_timespec32 __user *rqtp, - struct old_timespec32 __user *rmtp); - /* kernel/itimer.c */ asmlinkage long compat_sys_getitimer(int which, struct compat_itimerval __user *it); @@ -709,20 +684,6 @@ asmlinkage long compat_sys_kexec_load(compat_ulong_t entry, asmlinkage long compat_sys_timer_create(clockid_t which_clock, struct compat_sigevent __user *timer_event_spec, timer_t __user *created_timer_id); -asmlinkage long compat_sys_timer_gettime(timer_t timer_id, - struct old_itimerspec32 __user *setting); -asmlinkage long compat_sys_timer_settime(timer_t timer_id, int flags, - struct old_itimerspec32 __user *new, - struct old_itimerspec32 __user *old); -asmlinkage long compat_sys_clock_settime(clockid_t which_clock, - struct old_timespec32 __user *tp); -asmlinkage long compat_sys_clock_gettime(clockid_t which_clock, - struct old_timespec32 __user *tp); -asmlinkage long compat_sys_clock_getres(clockid_t which_clock, - struct old_timespec32 __user *tp); -asmlinkage long compat_sys_clock_nanosleep(clockid_t which_clock, int flags, - struct old_timespec32 __user *rqtp, - struct old_timespec32 __user *rmtp); /* kernel/ptrace.c */ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, @@ -735,8 +696,6 @@ asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid, asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); -asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, - struct old_timespec32 __user *interval); /* kernel/signal.c */ asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, @@ -754,7 +713,7 @@ asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); -asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese, +asmlinkage long compat_sys_rt_sigtimedwait_time32(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, struct old_timespec32 __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait_time64(compat_sigset_t __user *uthese, @@ -777,7 +736,6 @@ asmlinkage long compat_sys_gettimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_settimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); -asmlinkage long compat_sys_adjtimex(struct old_timex32 __user *utp); /* kernel/timer.c */ asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); @@ -786,14 +744,6 @@ asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); asmlinkage long compat_sys_mq_open(const char __user *u_name, int oflag, compat_mode_t mode, struct compat_mq_attr __user *u_attr); -asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes, - const char __user *u_msg_ptr, - compat_size_t msg_len, unsigned int msg_prio, - const struct old_timespec32 __user *u_abs_timeout); -asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes, - char __user *u_msg_ptr, - compat_size_t msg_len, unsigned int __user *u_msg_prio, - const struct old_timespec32 __user *u_abs_timeout); asmlinkage long compat_sys_mq_notify(mqd_t mqdes, const struct compat_sigevent __user *u_notification); asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, @@ -809,8 +759,6 @@ asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, /* ipc/sem.c */ asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); -asmlinkage long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, - unsigned nsems, const struct old_timespec32 __user *timeout); /* ipc/shm.c */ asmlinkage long compat_sys_shmctl(int first, int second, void __user *uptr); @@ -868,7 +816,7 @@ asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, asmlinkage long compat_sys_recvmmsg_time64(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, struct __kernel_timespec __user *timeout); -asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, +asmlinkage long compat_sys_recvmmsg_time32(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, struct old_timespec32 __user *timeout); asmlinkage long compat_sys_wait4(compat_pid_t pid, @@ -879,8 +827,6 @@ asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); -asmlinkage long compat_sys_clock_adjtime(clockid_t which_clock, - struct old_timex32 __user *tp); asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags); asmlinkage ssize_t compat_sys_process_vm_readv(compat_pid_t pid, @@ -921,8 +867,6 @@ asmlinkage long compat_sys_pwritev64v2(unsigned long fd, /* __ARCH_WANT_SYSCALL_NO_AT */ asmlinkage long compat_sys_open(const char __user *filename, int flags, umode_t mode); -asmlinkage long compat_sys_utimes(const char __user *filename, - struct old_timeval32 __user *t); /* __ARCH_WANT_SYSCALL_NO_FLAGS */ asmlinkage long compat_sys_signalfd(int ufd, @@ -936,12 +880,6 @@ asmlinkage long compat_sys_newlstat(const char __user *filename, struct compat_stat __user *statbuf); /* __ARCH_WANT_SYSCALL_DEPRECATED */ -asmlinkage long compat_sys_time(old_time32_t __user *tloc); -asmlinkage long compat_sys_utime(const char __user *filename, - struct old_utimbuf32 __user *t); -asmlinkage long compat_sys_futimesat(unsigned int dfd, - const char __user *filename, - struct old_timeval32 __user *t); asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp); @@ -976,9 +914,6 @@ asmlinkage long compat_sys_sigaction(int sig, struct compat_old_sigaction __user *oact); #endif -/* obsolete: kernel/time/time.c */ -asmlinkage long compat_sys_stime(old_time32_t __user *tptr); - /* obsolete: net/socket.c */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 09330d5bda0c..94369f5bd8e5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -297,6 +297,11 @@ asmlinkage long sys_io_getevents(aio_context_t ctx_id, long nr, struct io_event __user *events, struct __kernel_timespec __user *timeout); +asmlinkage long sys_io_getevents_time32(__u32 ctx_id, + __s32 min_nr, + __s32 nr, + struct io_event __user *events, + struct old_timespec32 __user *timeout); asmlinkage long sys_io_pgetevents(aio_context_t ctx_id, long min_nr, long nr, @@ -522,11 +527,19 @@ asmlinkage long sys_timerfd_settime(int ufd, int flags, const struct __kernel_itimerspec __user *utmr, struct __kernel_itimerspec __user *otmr); asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user *otmr); +asmlinkage long sys_timerfd_gettime32(int ufd, + struct old_itimerspec32 __user *otmr); +asmlinkage long sys_timerfd_settime32(int ufd, int flags, + const struct old_itimerspec32 __user *utmr, + struct old_itimerspec32 __user *otmr); /* fs/utimes.c */ asmlinkage long sys_utimensat(int dfd, const char __user *filename, struct __kernel_timespec __user *utimes, int flags); +asmlinkage long sys_utimensat_time32(unsigned int dfd, + const char __user *filename, + struct old_timespec32 __user *t, int flags); /* kernel/acct.c */ asmlinkage long sys_acct(const char __user *name); @@ -555,6 +568,9 @@ asmlinkage long sys_unshare(unsigned long unshare_flags); asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, struct __kernel_timespec __user *utime, u32 __user *uaddr2, u32 val3); +asmlinkage long sys_futex_time32(u32 __user *uaddr, int op, u32 val, + struct old_timespec32 __user *utime, u32 __user *uaddr2, + u32 val3); asmlinkage long sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, size_t __user *len_ptr); @@ -564,6 +580,8 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, /* kernel/hrtimer.c */ asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp, struct __kernel_timespec __user *rmtp); +asmlinkage long sys_nanosleep_time32(struct old_timespec32 __user *rqtp, + struct old_timespec32 __user *rmtp); /* kernel/itimer.c */ asmlinkage long sys_getitimer(int which, struct itimerval __user *value); @@ -602,6 +620,20 @@ asmlinkage long sys_clock_getres(clockid_t which_clock, asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags, const struct __kernel_timespec __user *rqtp, struct __kernel_timespec __user *rmtp); +asmlinkage long sys_timer_gettime32(timer_t timer_id, + struct old_itimerspec32 __user *setting); +asmlinkage long sys_timer_settime32(timer_t timer_id, int flags, + struct old_itimerspec32 __user *new, + struct old_itimerspec32 __user *old); +asmlinkage long sys_clock_settime32(clockid_t which_clock, + struct old_timespec32 __user *tp); +asmlinkage long sys_clock_gettime32(clockid_t which_clock, + struct old_timespec32 __user *tp); +asmlinkage long sys_clock_getres_time32(clockid_t which_clock, + struct old_timespec32 __user *tp); +asmlinkage long sys_clock_nanosleep_time32(clockid_t which_clock, int flags, + struct old_timespec32 __user *rqtp, + struct old_timespec32 __user *rmtp); /* kernel/printk.c */ asmlinkage long sys_syslog(int type, char __user *buf, int len); @@ -627,6 +659,8 @@ asmlinkage long sys_sched_get_priority_max(int policy); asmlinkage long sys_sched_get_priority_min(int policy); asmlinkage long sys_sched_rr_get_interval(pid_t pid, struct __kernel_timespec __user *interval); +asmlinkage long sys_sched_rr_get_interval_time32(pid_t pid, + struct old_timespec32 __user *interval); /* kernel/signal.c */ asmlinkage long sys_restart_syscall(void); @@ -696,6 +730,7 @@ asmlinkage long sys_gettimeofday(struct timeval __user *tv, asmlinkage long sys_settimeofday(struct timeval __user *tv, struct timezone __user *tz); asmlinkage long sys_adjtimex(struct __kernel_timex __user *txc_p); +asmlinkage long sys_adjtimex_time32(struct old_timex32 __user *txc_p); /* kernel/timer.c */ asmlinkage long sys_getpid(void); @@ -714,6 +749,14 @@ asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct __kernel_timespec __user *abs_timeout); asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification); asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat); +asmlinkage long sys_mq_timedreceive_time32(mqd_t mqdes, + char __user *u_msg_ptr, + unsigned int msg_len, unsigned int __user *u_msg_prio, + const struct old_timespec32 __user *u_abs_timeout); +asmlinkage long sys_mq_timedsend_time32(mqd_t mqdes, + const char __user *u_msg_ptr, + unsigned int msg_len, unsigned int msg_prio, + const struct old_timespec32 __user *u_abs_timeout); /* ipc/msg.c */ asmlinkage long sys_msgget(key_t key, int msgflg); @@ -731,6 +774,9 @@ asmlinkage long sys_old_semctl(int semid, int semnum, int cmd, unsigned long arg asmlinkage long sys_semtimedop(int semid, struct sembuf __user *sops, unsigned nsops, const struct __kernel_timespec __user *timeout); +asmlinkage long sys_semtimedop_time32(int semid, struct sembuf __user *sops, + unsigned nsops, + const struct old_timespec32 __user *timeout); asmlinkage long sys_semop(int semid, struct sembuf __user *sops, unsigned nsops); @@ -871,6 +917,8 @@ asmlinkage long sys_open_by_handle_at(int mountdirfd, int flags); asmlinkage long sys_clock_adjtime(clockid_t which_clock, struct __kernel_timex __user *tx); +asmlinkage long sys_clock_adjtime32(clockid_t which_clock, + struct old_timex32 __user *tx); asmlinkage long sys_syncfs(int fd); asmlinkage long sys_setns(int fd, int nstype); asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg, @@ -1006,6 +1054,7 @@ asmlinkage long sys_alarm(unsigned int seconds); asmlinkage long sys_getpgrp(void); asmlinkage long sys_pause(void); asmlinkage long sys_time(time_t __user *tloc); +asmlinkage long sys_time32(old_time32_t __user *tloc); #ifdef __ARCH_WANT_SYS_UTIME asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times); @@ -1014,6 +1063,13 @@ asmlinkage long sys_utimes(char __user *filename, asmlinkage long sys_futimesat(int dfd, const char __user *filename, struct timeval __user *utimes); #endif +asmlinkage long sys_futimesat_time32(unsigned int dfd, + const char __user *filename, + struct old_timeval32 __user *t); +asmlinkage long sys_utime32(const char __user *filename, + struct old_utimbuf32 __user *t); +asmlinkage long sys_utimes_time32(const char __user *filename, + struct old_timeval32 __user *t); asmlinkage long sys_creat(const char __user *pathname, umode_t mode); asmlinkage long sys_getdents(unsigned int fd, struct linux_dirent __user *dirent, @@ -1038,6 +1094,7 @@ asmlinkage long sys_fork(void); /* obsolete: kernel/time/time.c */ asmlinkage long sys_stime(time_t __user *tptr); +asmlinkage long sys_stime32(old_time32_t __user *tptr); /* obsolete: kernel/signal.c */ asmlinkage long sys_sigpending(old_sigset_t __user *uset); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 509484dbfd5d..153b55b94234 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -39,7 +39,7 @@ __SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit) #define __NR_io_cancel 3 __SYSCALL(__NR_io_cancel, sys_io_cancel) #define __NR_io_getevents 4 -__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents) +__SC_COMP(__NR_io_getevents, sys_io_getevents, sys_io_getevents_time32) /* fs/xattr.c */ #define __NR_setxattr 5 @@ -223,9 +223,9 @@ __SYSCALL(__NR3264_sendfile, sys_sendfile64) /* fs/select.c */ #define __NR_pselect6 72 -__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6) +__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6_time32) #define __NR_ppoll 73 -__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll) +__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll_time32) /* fs/signalfd.c */ #define __NR_signalfd4 74 @@ -271,14 +271,14 @@ __SC_COMP(__NR_sync_file_range, sys_sync_file_range, \ __SYSCALL(__NR_timerfd_create, sys_timerfd_create) #define __NR_timerfd_settime 86 __SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \ - compat_sys_timerfd_settime) + sys_timerfd_settime32) #define __NR_timerfd_gettime 87 __SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \ - compat_sys_timerfd_gettime) + sys_timerfd_gettime32) /* fs/utimes.c */ #define __NR_utimensat 88 -__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat) +__SC_COMP(__NR_utimensat, sys_utimensat, sys_utimensat_time32) /* kernel/acct.c */ #define __NR_acct 89 @@ -310,7 +310,7 @@ __SYSCALL(__NR_unshare, sys_unshare) /* kernel/futex.c */ #define __NR_futex 98 -__SC_COMP(__NR_futex, sys_futex, compat_sys_futex) +__SC_COMP(__NR_futex, sys_futex, sys_futex_time32) #define __NR_set_robust_list 99 __SC_COMP(__NR_set_robust_list, sys_set_robust_list, \ compat_sys_set_robust_list) @@ -320,7 +320,7 @@ __SC_COMP(__NR_get_robust_list, sys_get_robust_list, \ /* kernel/hrtimer.c */ #define __NR_nanosleep 101 -__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep) +__SC_COMP(__NR_nanosleep, sys_nanosleep, sys_nanosleep_time32) /* kernel/itimer.c */ #define __NR_getitimer 102 @@ -342,22 +342,22 @@ __SYSCALL(__NR_delete_module, sys_delete_module) #define __NR_timer_create 107 __SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create) #define __NR_timer_gettime 108 -__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime) +__SC_COMP(__NR_timer_gettime, sys_timer_gettime, sys_timer_gettime32) #define __NR_timer_getoverrun 109 __SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) #define __NR_timer_settime 110 -__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime) +__SC_COMP(__NR_timer_settime, sys_timer_settime, sys_timer_settime32) #define __NR_timer_delete 111 __SYSCALL(__NR_timer_delete, sys_timer_delete) #define __NR_clock_settime 112 -__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime) +__SC_COMP(__NR_clock_settime, sys_clock_settime, sys_clock_settime32) #define __NR_clock_gettime 113 -__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime) +__SC_COMP(__NR_clock_gettime, sys_clock_gettime, sys_clock_gettime32) #define __NR_clock_getres 114 -__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres) +__SC_COMP(__NR_clock_getres, sys_clock_getres, sys_clock_getres_time32) #define __NR_clock_nanosleep 115 __SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \ - compat_sys_clock_nanosleep) + sys_clock_nanosleep_time32) /* kernel/printk.c */ #define __NR_syslog 116 @@ -390,7 +390,7 @@ __SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) __SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) #define __NR_sched_rr_get_interval 127 __SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \ - compat_sys_sched_rr_get_interval) + sys_sched_rr_get_interval_time32) /* kernel/signal.c */ #define __NR_restart_syscall 128 @@ -413,7 +413,7 @@ __SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask) __SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending) #define __NR_rt_sigtimedwait 137 __SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \ - compat_sys_rt_sigtimedwait) + compat_sys_rt_sigtimedwait_time32) #define __NR_rt_sigqueueinfo 138 __SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \ compat_sys_rt_sigqueueinfo) @@ -486,7 +486,7 @@ __SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday) #define __NR_settimeofday 170 __SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday) #define __NR_adjtimex 171 -__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex) +__SC_COMP(__NR_adjtimex, sys_adjtimex, sys_adjtimex_time32) /* kernel/timer.c */ #define __NR_getpid 172 @@ -512,10 +512,10 @@ __SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open) #define __NR_mq_unlink 181 __SYSCALL(__NR_mq_unlink, sys_mq_unlink) #define __NR_mq_timedsend 182 -__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend) +__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, sys_mq_timedsend_time32) #define __NR_mq_timedreceive 183 __SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \ - compat_sys_mq_timedreceive) + sys_mq_timedreceive_time32) #define __NR_mq_notify 184 __SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify) #define __NR_mq_getsetattr 185 @@ -537,7 +537,7 @@ __SYSCALL(__NR_semget, sys_semget) #define __NR_semctl 191 __SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl) #define __NR_semtimedop 192 -__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop) +__SC_COMP(__NR_semtimedop, sys_semtimedop, sys_semtimedop_time32) #define __NR_semop 193 __SYSCALL(__NR_semop, sys_semop) @@ -659,7 +659,7 @@ __SYSCALL(__NR_perf_event_open, sys_perf_event_open) #define __NR_accept4 242 __SYSCALL(__NR_accept4, sys_accept4) #define __NR_recvmmsg 243 -__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg) +__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg_time32) /* * Architectures may provide up to 16 syscalls of their own @@ -681,7 +681,7 @@ __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) __SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \ compat_sys_open_by_handle_at) #define __NR_clock_adjtime 266 -__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime) +__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, sys_clock_adjtime32) #define __NR_syncfs 267 __SYSCALL(__NR_syncfs, sys_syncfs) #define __NR_setns 268 diff --git a/ipc/mqueue.c b/ipc/mqueue.c index c595bed7bfcb..c839bf83231d 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1471,10 +1471,10 @@ static int compat_prepare_timeout(const struct old_timespec32 __user *p, return 0; } -COMPAT_SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, - const char __user *, u_msg_ptr, - compat_size_t, msg_len, unsigned int, msg_prio, - const struct old_timespec32 __user *, u_abs_timeout) +SYSCALL_DEFINE5(mq_timedsend_time32, mqd_t, mqdes, + const char __user *, u_msg_ptr, + unsigned int, msg_len, unsigned int, msg_prio, + const struct old_timespec32 __user *, u_abs_timeout) { struct timespec64 ts, *p = NULL; if (u_abs_timeout) { @@ -1486,10 +1486,10 @@ COMPAT_SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, return do_mq_timedsend(mqdes, u_msg_ptr, msg_len, msg_prio, p); } -COMPAT_SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, - char __user *, u_msg_ptr, - compat_size_t, msg_len, unsigned int __user *, u_msg_prio, - const struct old_timespec32 __user *, u_abs_timeout) +SYSCALL_DEFINE5(mq_timedreceive_time32, mqd_t, mqdes, + char __user *, u_msg_ptr, + unsigned int, msg_len, unsigned int __user *, u_msg_prio, + const struct old_timespec32 __user *, u_abs_timeout) { struct timespec64 ts, *p = NULL; if (u_abs_timeout) { diff --git a/ipc/sem.c b/ipc/sem.c index d1efff3a81bb..80909464acff 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2250,7 +2250,7 @@ long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, return do_semtimedop(semid, tsems, nsops, NULL); } -COMPAT_SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsems, +SYSCALL_DEFINE4(semtimedop_time32, int, semid, struct sembuf __user *, tsems, unsigned int, nsops, const struct old_timespec32 __user *, timeout) { diff --git a/kernel/futex.c b/kernel/futex.c index be3bff2315ff..caead6c113d4 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3812,7 +3812,7 @@ err_unlock: #endif /* CONFIG_COMPAT */ #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, +SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a674c7db2f29..62862419cd05 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5252,9 +5252,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval, - compat_pid_t, pid, - struct old_timespec32 __user *, interval) +SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid, + struct old_timespec32 __user *, interval) { struct timespec64 t; int retval = sched_rr_get_interval(pid, &t); diff --git a/kernel/signal.c b/kernel/signal.c index e1d7ad8e6ab1..af27629918cf 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3397,7 +3397,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time64, compat_sigset_t __user *, uthese, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, +COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time32, compat_sigset_t __user *, uthese, struct compat_siginfo __user *, uinfo, struct old_timespec32 __user *, uts, compat_size_t, sigsetsize) { diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index ce04431a40d1..85e5ccec0955 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -42,9 +42,11 @@ COND_SYSCALL(io_destroy); COND_SYSCALL(io_submit); COND_SYSCALL_COMPAT(io_submit); COND_SYSCALL(io_cancel); +COND_SYSCALL(io_getevents_time32); COND_SYSCALL(io_getevents); +COND_SYSCALL(io_pgetevents_time32); COND_SYSCALL(io_pgetevents); -COND_SYSCALL_COMPAT(io_getevents); +COND_SYSCALL_COMPAT(io_pgetevents_time32); COND_SYSCALL_COMPAT(io_pgetevents); /* fs/xattr.c */ @@ -114,9 +116,9 @@ COND_SYSCALL_COMPAT(signalfd4); /* fs/timerfd.c */ COND_SYSCALL(timerfd_create); COND_SYSCALL(timerfd_settime); -COND_SYSCALL_COMPAT(timerfd_settime); +COND_SYSCALL(timerfd_settime32); COND_SYSCALL(timerfd_gettime); -COND_SYSCALL_COMPAT(timerfd_gettime); +COND_SYSCALL(timerfd_gettime32); /* fs/utimes.c */ @@ -135,7 +137,7 @@ COND_SYSCALL(capset); /* kernel/futex.c */ COND_SYSCALL(futex); -COND_SYSCALL_COMPAT(futex); +COND_SYSCALL(futex_time32); COND_SYSCALL(set_robust_list); COND_SYSCALL_COMPAT(set_robust_list); COND_SYSCALL(get_robust_list); @@ -187,9 +189,9 @@ COND_SYSCALL(mq_open); COND_SYSCALL_COMPAT(mq_open); COND_SYSCALL(mq_unlink); COND_SYSCALL(mq_timedsend); -COND_SYSCALL_COMPAT(mq_timedsend); +COND_SYSCALL(mq_timedsend_time32); COND_SYSCALL(mq_timedreceive); -COND_SYSCALL_COMPAT(mq_timedreceive); +COND_SYSCALL(mq_timedreceive_time32); COND_SYSCALL(mq_notify); COND_SYSCALL_COMPAT(mq_notify); COND_SYSCALL(mq_getsetattr); @@ -211,7 +213,7 @@ COND_SYSCALL(old_semctl); COND_SYSCALL(semctl); COND_SYSCALL_COMPAT(semctl); COND_SYSCALL(semtimedop); -COND_SYSCALL_COMPAT(semtimedop); +COND_SYSCALL(semtimedop_time32); COND_SYSCALL(semop); /* ipc/shm.c */ @@ -288,7 +290,7 @@ COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); COND_SYSCALL(recvmmsg); COND_SYSCALL(recvmmsg_time32); -COND_SYSCALL_COMPAT(recvmmsg); +COND_SYSCALL_COMPAT(recvmmsg_time32); COND_SYSCALL_COMPAT(recvmmsg_time64); /* diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index f5cfa1b73d6f..0f5f96075110 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1771,7 +1771,7 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(nanosleep, struct old_timespec32 __user *, rqtp, +SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index a51895486e5e..67df65f887ac 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -45,6 +45,7 @@ SYS_NI(timer_delete); SYS_NI(clock_adjtime); SYS_NI(getitimer); SYS_NI(setitimer); +SYS_NI(clock_adjtime32); #ifdef __ARCH_WANT_SYS_ALARM SYS_NI(alarm); #endif @@ -150,16 +151,16 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, #ifdef CONFIG_COMPAT COMPAT_SYS_NI(timer_create); -COMPAT_SYS_NI(clock_adjtime); -COMPAT_SYS_NI(timer_settime); -COMPAT_SYS_NI(timer_gettime); COMPAT_SYS_NI(getitimer); COMPAT_SYS_NI(setitimer); #endif #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYS_NI(timer_settime32); +SYS_NI(timer_gettime32); + +SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock, + struct old_timespec32 __user *, tp) { struct timespec64 new_tp; @@ -171,8 +172,8 @@ COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, return do_sys_settimeofday64(&new_tp, NULL); } -COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { int ret; struct timespec64 kernel_tp; @@ -186,8 +187,8 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, return 0; } -COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { struct timespec64 rtn_tp = { .tv_sec = 0, @@ -206,9 +207,9 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, } } -COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, - struct old_timespec32 __user *, rqtp, - struct old_timespec32 __user *, rmtp) +SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, + struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { struct timespec64 t; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index de79f85ae14f..29176635991f 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -730,8 +730,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct old_itimerspec32 __user *, setting) +SYSCALL_DEFINE2(timer_gettime32, timer_t, timer_id, + struct old_itimerspec32 __user *, setting) { struct itimerspec64 cur_setting; @@ -903,9 +903,9 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - struct old_itimerspec32 __user *, new, - struct old_itimerspec32 __user *, old) +SYSCALL_DEFINE4(timer_settime32, timer_t, timer_id, int, flags, + struct old_itimerspec32 __user *, new, + struct old_itimerspec32 __user *, old) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old ? &old_spec : NULL; @@ -1096,8 +1096,8 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_settime32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1111,8 +1111,8 @@ COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, return kc->clock_set(which_clock, &ts); } -COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1129,8 +1129,8 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, return err; } -COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, - struct old_timex32 __user *, utp) +SYSCALL_DEFINE2(clock_adjtime32, clockid_t, which_clock, + struct old_timex32 __user *, utp) { struct __kernel_timex ktx; int err; @@ -1147,8 +1147,8 @@ COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, return err; } -COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1204,9 +1204,9 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, - struct old_timespec32 __user *, rqtp, - struct old_timespec32 __user *, rmtp) +SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, + struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 t; diff --git a/kernel/time/time.c b/kernel/time/time.c index 78b5c8f1495a..6261f969dcb7 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -98,11 +98,11 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr) #endif /* __ARCH_WANT_SYS_TIME */ -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME #ifdef __ARCH_WANT_COMPAT_SYS_TIME /* old_time32_t is a 32 bit "long" and needs to get converted. */ -COMPAT_SYSCALL_DEFINE1(time, old_time32_t __user *, tloc) +SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; @@ -116,7 +116,7 @@ COMPAT_SYSCALL_DEFINE1(time, old_time32_t __user *, tloc) return i; } -COMPAT_SYSCALL_DEFINE1(stime, old_time32_t __user *, tptr) +SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; @@ -344,7 +344,7 @@ int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex return 0; } -COMPAT_SYSCALL_DEFINE1(adjtimex, struct old_timex32 __user *, utp) +SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { struct __kernel_timex txc; int err, ret; diff --git a/net/compat.c b/net/compat.c index 959d1c51826d..2fef7b9db434 100644 --- a/net/compat.c +++ b/net/compat.c @@ -822,7 +822,7 @@ COMPAT_SYSCALL_DEFINE5(recvmmsg_time64, int, fd, struct compat_mmsghdr __user *, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg, +COMPAT_SYSCALL_DEFINE5(recvmmsg_time32, int, fd, struct compat_mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct old_timespec32 __user *, timeout) { -- cgit v1.2.3 From 00bf25d693e7f69497cb7f61d46ef99fe295a8a5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 1 Jan 2019 01:13:32 +0100 Subject: y2038: use time32 syscall names on 32-bit This is the big flip, where all 32-bit architectures set COMPAT_32BIT_TIME and use the _time32 system calls from the former compat layer instead of the system calls that take __kernel_timespec and similar arguments. The temporary redirects for __kernel_timespec, __kernel_itimerspec and __kernel_timex can get removed with this. It would be easy to split this commit by architecture, but with the new generated system call tables, it's easy enough to do it all at once, which makes it a little easier to check that the changes are the same in each table. Acked-by: Geert Uytterhoeven Signed-off-by: Arnd Bergmann --- arch/Kconfig | 2 +- arch/arm/kernel/sys_oabi-compat.c | 8 +-- arch/arm/tools/syscall.tbl | 46 ++++++++-------- arch/m68k/kernel/syscalls/syscall.tbl | 42 +++++++-------- arch/microblaze/kernel/syscalls/syscall.tbl | 46 ++++++++-------- arch/mips/kernel/syscalls/syscall_o32.tbl | 44 ++++++++-------- arch/parisc/kernel/syscalls/syscall.tbl | 69 ++++++++++++++++-------- arch/powerpc/kernel/syscalls/syscall.tbl | 82 +++++++++++++++++++++-------- arch/sh/kernel/syscalls/syscall.tbl | 42 +++++++-------- arch/sparc/kernel/syscalls/syscall.tbl | 64 ++++++++++++++-------- arch/x86/entry/syscalls/syscall_32.tbl | 44 ++++++++-------- arch/xtensa/kernel/syscalls/syscall.tbl | 44 ++++++++-------- include/uapi/asm-generic/unistd.h | 56 ++++++++++---------- 13 files changed, 335 insertions(+), 254 deletions(-) (limited to 'include') diff --git a/arch/Kconfig b/arch/Kconfig index 4cfb6de48f79..46db715a7f42 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -759,7 +759,7 @@ config 64BIT_TIME handling. config COMPAT_32BIT_TIME - def_bool (!64BIT && 64BIT_TIME) || COMPAT + def_bool !64BIT || COMPAT help This enables 32 bit time_t support in addition to 64 bit time_t support. This is relevant on all 32-bit architectures, and 64-bit architectures diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 92ab36f38795..acd054a42ba2 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -317,10 +317,10 @@ struct oabi_sembuf { asmlinkage long sys_oabi_semtimedop(int semid, struct oabi_sembuf __user *tsops, unsigned nsops, - const struct timespec __user *timeout) + const struct old_timespec32 __user *timeout) { struct sembuf *sops; - struct timespec local_timeout; + struct old_timespec32 local_timeout; long err; int i; @@ -350,7 +350,7 @@ asmlinkage long sys_oabi_semtimedop(int semid, } else { mm_segment_t fs = get_fs(); set_fs(KERNEL_DS); - err = sys_semtimedop(semid, sops, nsops, timeout); + err = sys_semtimedop_time32(semid, sops, nsops, timeout); set_fs(fs); } kfree(sops); @@ -375,7 +375,7 @@ asmlinkage int sys_oabi_ipc(uint call, int first, int second, int third, return sys_oabi_semtimedop(first, (struct oabi_sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); + (const struct old_timespec32 __user *)fifth); default: return sys_ipc(call, first, second, third, ptr, fifth); } diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index b54b7f2bc24a..200f4b878a46 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -137,7 +137,7 @@ 121 common setdomainname sys_setdomainname 122 common uname sys_newuname # 123 was sys_modify_ldt -124 common adjtimex sys_adjtimex +124 common adjtimex sys_adjtimex_time32 125 common mprotect sys_mprotect 126 common sigprocmask sys_sigprocmask # 127 was sys_create_module @@ -174,8 +174,8 @@ 158 common sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 163 common mremap sys_mremap 164 common setresuid sys_setresuid16 165 common getresuid sys_getresuid16 @@ -190,7 +190,7 @@ 174 common rt_sigaction sys_rt_sigaction 175 common rt_sigprocmask sys_rt_sigprocmask 176 common rt_sigpending sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 178 common rt_sigqueueinfo sys_rt_sigqueueinfo 179 common rt_sigsuspend sys_rt_sigsuspend 180 common pread64 sys_pread64 sys_oabi_pread64 @@ -254,12 +254,12 @@ 237 common fremovexattr sys_fremovexattr 238 common tkill sys_tkill 239 common sendfile64 sys_sendfile64 -240 common futex sys_futex +240 common futex sys_futex_time32 241 common sched_setaffinity sys_sched_setaffinity 242 common sched_getaffinity sys_sched_getaffinity 243 common io_setup sys_io_setup 244 common io_destroy sys_io_destroy -245 common io_getevents sys_io_getevents +245 common io_getevents sys_io_getevents_time32 246 common io_submit sys_io_submit 247 common io_cancel sys_io_cancel 248 common exit_group sys_exit_group @@ -272,14 +272,14 @@ # 255 for get_thread_area 256 common set_tid_address sys_set_tid_address 257 common timer_create sys_timer_create -258 common timer_settime sys_timer_settime -259 common timer_gettime sys_timer_gettime +258 common timer_settime sys_timer_settime32 +259 common timer_gettime sys_timer_gettime32 260 common timer_getoverrun sys_timer_getoverrun 261 common timer_delete sys_timer_delete -262 common clock_settime sys_clock_settime -263 common clock_gettime sys_clock_gettime -264 common clock_getres sys_clock_getres -265 common clock_nanosleep sys_clock_nanosleep +262 common clock_settime sys_clock_settime32 +263 common clock_gettime sys_clock_gettime32 +264 common clock_getres sys_clock_getres_time32 +265 common clock_nanosleep sys_clock_nanosleep_time32 266 common statfs64 sys_statfs64_wrapper 267 common fstatfs64 sys_fstatfs64_wrapper 268 common tgkill sys_tgkill @@ -290,8 +290,8 @@ 273 common pciconfig_write sys_pciconfig_write 274 common mq_open sys_mq_open 275 common mq_unlink sys_mq_unlink -276 common mq_timedsend sys_mq_timedsend -277 common mq_timedreceive sys_mq_timedreceive +276 common mq_timedsend sys_mq_timedsend_time32 +277 common mq_timedreceive sys_mq_timedreceive_time32 278 common mq_notify sys_mq_notify 279 common mq_getsetattr sys_mq_getsetattr 280 common waitid sys_waitid @@ -326,7 +326,7 @@ 309 common add_key sys_add_key 310 common request_key sys_request_key 311 common keyctl sys_keyctl -312 common semtimedop sys_semtimedop sys_oabi_semtimedop +312 common semtimedop sys_semtimedop_time32 sys_oabi_semtimedop 313 common vserver 314 common ioprio_set sys_ioprio_set 315 common ioprio_get sys_ioprio_get @@ -349,8 +349,8 @@ 332 common readlinkat sys_readlinkat 333 common fchmodat sys_fchmodat 334 common faccessat sys_faccessat -335 common pselect6 sys_pselect6 -336 common ppoll sys_ppoll +335 common pselect6 sys_pselect6_time32 +336 common ppoll sys_ppoll_time32 337 common unshare sys_unshare 338 common set_robust_list sys_set_robust_list 339 common get_robust_list sys_get_robust_list @@ -362,13 +362,13 @@ 345 common getcpu sys_getcpu 346 common epoll_pwait sys_epoll_pwait 347 common kexec_load sys_kexec_load -348 common utimensat sys_utimensat +348 common utimensat sys_utimensat_time32 349 common signalfd sys_signalfd 350 common timerfd_create sys_timerfd_create 351 common eventfd sys_eventfd 352 common fallocate sys_fallocate -353 common timerfd_settime sys_timerfd_settime -354 common timerfd_gettime sys_timerfd_gettime +353 common timerfd_settime sys_timerfd_settime32 +354 common timerfd_gettime sys_timerfd_gettime32 355 common signalfd4 sys_signalfd4 356 common eventfd2 sys_eventfd2 357 common epoll_create1 sys_epoll_create1 @@ -379,14 +379,14 @@ 362 common pwritev sys_pwritev 363 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo 364 common perf_event_open sys_perf_event_open -365 common recvmmsg sys_recvmmsg +365 common recvmmsg sys_recvmmsg_time32 366 common accept4 sys_accept4 367 common fanotify_init sys_fanotify_init 368 common fanotify_mark sys_fanotify_mark 369 common prlimit64 sys_prlimit64 370 common name_to_handle_at sys_name_to_handle_at 371 common open_by_handle_at sys_open_by_handle_at -372 common clock_adjtime sys_clock_adjtime +372 common clock_adjtime sys_clock_adjtime32 373 common syncfs sys_syncfs 374 common sendmmsg sys_sendmmsg 375 common setns sys_setns @@ -413,6 +413,6 @@ 396 common pkey_free sys_pkey_free 397 common statx sys_statx 398 common rseq sys_rseq -399 common io_pgetevents sys_io_pgetevents +399 common io_pgetevents sys_io_pgetevents_time32 400 common migrate_pages sys_migrate_pages 401 common kexec_file_load sys_kexec_file_load diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index bffffb202f8a..01529dce1d2e 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -131,7 +131,7 @@ 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common cacheflush sys_cacheflush -124 common adjtimex sys_adjtimex +124 common adjtimex sys_adjtimex_time32 125 common mprotect sys_mprotect 126 common sigprocmask sys_sigprocmask 127 common create_module sys_ni_syscall @@ -168,8 +168,8 @@ 158 common sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 163 common mremap sys_mremap 164 common setresuid sys_setresuid16 165 common getresuid sys_getresuid16 @@ -184,7 +184,7 @@ 174 common rt_sigaction sys_rt_sigaction 175 common rt_sigprocmask sys_rt_sigprocmask 176 common rt_sigpending sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 178 common rt_sigqueueinfo sys_rt_sigqueueinfo 179 common rt_sigsuspend sys_rt_sigsuspend 180 common pread64 sys_pread64 @@ -242,7 +242,7 @@ 232 common removexattr sys_removexattr 233 common lremovexattr sys_lremovexattr 234 common fremovexattr sys_fremovexattr -235 common futex sys_futex +235 common futex sys_futex_time32 236 common sendfile64 sys_sendfile64 237 common mincore sys_mincore 238 common madvise sys_madvise @@ -250,7 +250,7 @@ 240 common readahead sys_readahead 241 common io_setup sys_io_setup 242 common io_destroy sys_io_destroy -243 common io_getevents sys_io_getevents +243 common io_getevents sys_io_getevents_time32 244 common io_submit sys_io_submit 245 common io_cancel sys_io_cancel 246 common fadvise64 sys_fadvise64 @@ -262,14 +262,14 @@ 252 common remap_file_pages sys_remap_file_pages 253 common set_tid_address sys_set_tid_address 254 common timer_create sys_timer_create -255 common timer_settime sys_timer_settime -256 common timer_gettime sys_timer_gettime +255 common timer_settime sys_timer_settime32 +256 common timer_gettime sys_timer_gettime32 257 common timer_getoverrun sys_timer_getoverrun 258 common timer_delete sys_timer_delete -259 common clock_settime sys_clock_settime -260 common clock_gettime sys_clock_gettime -261 common clock_getres sys_clock_getres -262 common clock_nanosleep sys_clock_nanosleep +259 common clock_settime sys_clock_settime32 +260 common clock_gettime sys_clock_gettime32 +261 common clock_getres sys_clock_getres_time32 +262 common clock_nanosleep sys_clock_nanosleep_time32 263 common statfs64 sys_statfs64 264 common fstatfs64 sys_fstatfs64 265 common tgkill sys_tgkill @@ -280,8 +280,8 @@ 270 common set_mempolicy sys_set_mempolicy 271 common mq_open sys_mq_open 272 common mq_unlink sys_mq_unlink -273 common mq_timedsend sys_mq_timedsend -274 common mq_timedreceive sys_mq_timedreceive +273 common mq_timedsend sys_mq_timedsend_time32 +274 common mq_timedreceive sys_mq_timedreceive_time32 275 common mq_notify sys_mq_notify 276 common mq_getsetattr sys_mq_getsetattr 277 common waitid sys_waitid @@ -308,8 +308,8 @@ 298 common readlinkat sys_readlinkat 299 common fchmodat sys_fchmodat 300 common faccessat sys_faccessat -301 common pselect6 sys_pselect6 -302 common ppoll sys_ppoll +301 common pselect6 sys_pselect6_time32 +302 common ppoll sys_ppoll_time32 303 common unshare sys_unshare 304 common set_robust_list sys_set_robust_list 305 common get_robust_list sys_get_robust_list @@ -323,13 +323,13 @@ 313 common kexec_load sys_kexec_load 314 common getcpu sys_getcpu 315 common epoll_pwait sys_epoll_pwait -316 common utimensat sys_utimensat +316 common utimensat sys_utimensat_time32 317 common signalfd sys_signalfd 318 common timerfd_create sys_timerfd_create 319 common eventfd sys_eventfd 320 common fallocate sys_fallocate -321 common timerfd_settime sys_timerfd_settime -322 common timerfd_gettime sys_timerfd_gettime +321 common timerfd_settime sys_timerfd_settime32 +322 common timerfd_gettime sys_timerfd_gettime32 323 common signalfd4 sys_signalfd4 324 common eventfd2 sys_eventfd2 325 common epoll_create1 sys_epoll_create1 @@ -349,7 +349,7 @@ 339 common prlimit64 sys_prlimit64 340 common name_to_handle_at sys_name_to_handle_at 341 common open_by_handle_at sys_open_by_handle_at -342 common clock_adjtime sys_clock_adjtime +342 common clock_adjtime sys_clock_adjtime32 343 common syncfs sys_syncfs 344 common setns sys_setns 345 common process_vm_readv sys_process_vm_readv @@ -378,7 +378,7 @@ 368 common recvfrom sys_recvfrom 369 common recvmsg sys_recvmsg 370 common shutdown sys_shutdown -371 common recvmmsg sys_recvmmsg +371 common recvmmsg sys_recvmmsg_time32 372 common sendmmsg sys_sendmmsg 373 common userfaultfd sys_userfaultfd 374 common membarrier sys_membarrier diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 7cc0f9554da3..492ff5c35b68 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -131,7 +131,7 @@ 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common modify_ldt sys_ni_syscall -124 common adjtimex sys_adjtimex +124 common adjtimex sys_adjtimex_time32 125 common mprotect sys_mprotect 126 common sigprocmask sys_sigprocmask 127 common create_module sys_ni_syscall @@ -168,8 +168,8 @@ 158 common sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 163 common mremap sys_mremap 164 common setresuid sys_setresuid 165 common getresuid sys_getresuid @@ -184,7 +184,7 @@ 174 common rt_sigaction sys_rt_sigaction 175 common rt_sigprocmask sys_rt_sigprocmask 176 common rt_sigpending sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 178 common rt_sigqueueinfo sys_rt_sigqueueinfo 179 common rt_sigsuspend sys_rt_sigsuspend 180 common pread64 sys_pread64 @@ -247,14 +247,14 @@ 237 common fremovexattr sys_fremovexattr 238 common tkill sys_tkill 239 common sendfile64 sys_sendfile64 -240 common futex sys_futex +240 common futex sys_futex_time32 241 common sched_setaffinity sys_sched_setaffinity 242 common sched_getaffinity sys_sched_getaffinity 243 common set_thread_area sys_ni_syscall 244 common get_thread_area sys_ni_syscall 245 common io_setup sys_io_setup 246 common io_destroy sys_io_destroy -247 common io_getevents sys_io_getevents +247 common io_getevents sys_io_getevents_time32 248 common io_submit sys_io_submit 249 common io_cancel sys_io_cancel 250 common fadvise64 sys_fadvise64 @@ -267,14 +267,14 @@ 257 common remap_file_pages sys_remap_file_pages 258 common set_tid_address sys_set_tid_address 259 common timer_create sys_timer_create -260 common timer_settime sys_timer_settime -261 common timer_gettime sys_timer_gettime +260 common timer_settime sys_timer_settime32 +261 common timer_gettime sys_timer_gettime32 262 common timer_getoverrun sys_timer_getoverrun 263 common timer_delete sys_timer_delete -264 common clock_settime sys_clock_settime -265 common clock_gettime sys_clock_gettime -266 common clock_getres sys_clock_getres -267 common clock_nanosleep sys_clock_nanosleep +264 common clock_settime sys_clock_settime32 +265 common clock_gettime sys_clock_gettime32 +266 common clock_getres sys_clock_getres_time32 +267 common clock_nanosleep sys_clock_nanosleep_time32 268 common statfs64 sys_statfs64 269 common fstatfs64 sys_fstatfs64 270 common tgkill sys_tgkill @@ -286,8 +286,8 @@ 276 common set_mempolicy sys_set_mempolicy 277 common mq_open sys_mq_open 278 common mq_unlink sys_mq_unlink -279 common mq_timedsend sys_mq_timedsend -280 common mq_timedreceive sys_mq_timedreceive +279 common mq_timedsend sys_mq_timedsend_time32 +280 common mq_timedreceive sys_mq_timedreceive_time32 281 common mq_notify sys_mq_notify 282 common mq_getsetattr sys_mq_getsetattr 283 common kexec_load sys_kexec_load @@ -315,8 +315,8 @@ 305 common readlinkat sys_readlinkat 306 common fchmodat sys_fchmodat 307 common faccessat sys_faccessat -308 common pselect6 sys_pselect6 -309 common ppoll sys_ppoll +308 common pselect6 sys_pselect6_time32 +309 common ppoll sys_ppoll_time32 310 common unshare sys_unshare 311 common set_robust_list sys_set_robust_list 312 common get_robust_list sys_get_robust_list @@ -327,14 +327,14 @@ 317 common move_pages sys_move_pages 318 common getcpu sys_getcpu 319 common epoll_pwait sys_epoll_pwait -320 common utimensat sys_utimensat +320 common utimensat sys_utimensat_time32 321 common signalfd sys_signalfd 322 common timerfd_create sys_timerfd_create 323 common eventfd sys_eventfd 324 common fallocate sys_fallocate -325 common semtimedop sys_semtimedop -326 common timerfd_settime sys_timerfd_settime -327 common timerfd_gettime sys_timerfd_gettime +325 common semtimedop sys_semtimedop_time32 +326 common timerfd_settime sys_timerfd_settime32 +327 common timerfd_gettime sys_timerfd_gettime32 328 common semctl sys_old_semctl 329 common semget sys_semget 330 common semop sys_semop @@ -374,13 +374,13 @@ 364 common pwritev sys_pwritev 365 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo 366 common perf_event_open sys_perf_event_open -367 common recvmmsg sys_recvmmsg +367 common recvmmsg sys_recvmmsg_time32 368 common fanotify_init sys_fanotify_init 369 common fanotify_mark sys_fanotify_mark 370 common prlimit64 sys_prlimit64 371 common name_to_handle_at sys_name_to_handle_at 372 common open_by_handle_at sys_open_by_handle_at -373 common clock_adjtime sys_clock_adjtime +373 common clock_adjtime sys_clock_adjtime32 374 common syncfs sys_syncfs 375 common setns sys_setns 376 common sendmmsg sys_sendmmsg @@ -406,5 +406,5 @@ 396 common pkey_alloc sys_pkey_alloc 397 common pkey_free sys_pkey_free 398 common statx sys_statx -399 common io_pgetevents sys_io_pgetevents +399 common io_pgetevents sys_io_pgetevents_time32 400 common rseq sys_rseq diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index e9fec7bac5a9..5642d93b64c0 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -135,7 +135,7 @@ 121 o32 setdomainname sys_setdomainname 122 o32 uname sys_newuname 123 o32 modify_ldt sys_ni_syscall -124 o32 adjtimex sys_adjtimex sys_adjtimex_time32 +124 o32 adjtimex sys_adjtimex_time32 125 o32 mprotect sys_mprotect 126 o32 sigprocmask sys_sigprocmask compat_sys_sigprocmask 127 o32 create_module sys_ni_syscall @@ -176,8 +176,8 @@ 162 o32 sched_yield sys_sched_yield 163 o32 sched_get_priority_max sys_sched_get_priority_max 164 o32 sched_get_priority_min sys_sched_get_priority_min -165 o32 sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 -166 o32 nanosleep sys_nanosleep sys_nanosleep_time32 +165 o32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +166 o32 nanosleep sys_nanosleep_time32 167 o32 mremap sys_mremap 168 o32 accept sys_accept 169 o32 bind sys_bind @@ -208,7 +208,7 @@ 194 o32 rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 195 o32 rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 196 o32 rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -197 o32 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 +197 o32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 198 o32 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 199 o32 rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 200 o32 pread64 sys_pread64 sys_32_pread @@ -249,12 +249,12 @@ 235 o32 fremovexattr sys_fremovexattr 236 o32 tkill sys_tkill 237 o32 sendfile64 sys_sendfile64 -238 o32 futex sys_futex sys_futex_time32 +238 o32 futex sys_futex_time32 239 o32 sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 240 o32 sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity 241 o32 io_setup sys_io_setup compat_sys_io_setup 242 o32 io_destroy sys_io_destroy -243 o32 io_getevents sys_io_getevents sys_io_getevents_time32 +243 o32 io_getevents sys_io_getevents_time32 244 o32 io_submit sys_io_submit compat_sys_io_submit 245 o32 io_cancel sys_io_cancel 246 o32 exit_group sys_exit_group @@ -269,14 +269,14 @@ 255 o32 statfs64 sys_statfs64 compat_sys_statfs64 256 o32 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 257 o32 timer_create sys_timer_create compat_sys_timer_create -258 o32 timer_settime sys_timer_settime sys_timer_settime32 -259 o32 timer_gettime sys_timer_gettime sys_timer_gettime32 +258 o32 timer_settime sys_timer_settime32 +259 o32 timer_gettime sys_timer_gettime32 260 o32 timer_getoverrun sys_timer_getoverrun 261 o32 timer_delete sys_timer_delete -262 o32 clock_settime sys_clock_settime sys_clock_settime32 -263 o32 clock_gettime sys_clock_gettime sys_clock_gettime32 -264 o32 clock_getres sys_clock_getres sys_clock_getres_time32 -265 o32 clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 +262 o32 clock_settime sys_clock_settime32 +263 o32 clock_gettime sys_clock_gettime32 +264 o32 clock_getres sys_clock_getres_time32 +265 o32 clock_nanosleep sys_clock_nanosleep_time32 266 o32 tgkill sys_tgkill 267 o32 utimes sys_utimes sys_utimes_time32 268 o32 mbind sys_mbind compat_sys_mbind @@ -284,8 +284,8 @@ 270 o32 set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy 271 o32 mq_open sys_mq_open compat_sys_mq_open 272 o32 mq_unlink sys_mq_unlink -273 o32 mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 -274 o32 mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 +273 o32 mq_timedsend sys_mq_timedsend_time32 +274 o32 mq_timedreceive sys_mq_timedreceive_time32 275 o32 mq_notify sys_mq_notify compat_sys_mq_notify 276 o32 mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 277 o32 vserver sys_ni_syscall @@ -312,8 +312,8 @@ 298 o32 readlinkat sys_readlinkat 299 o32 fchmodat sys_fchmodat 300 o32 faccessat sys_faccessat -301 o32 pselect6 sys_pselect6 compat_sys_pselect6_time32 -302 o32 ppoll sys_ppoll compat_sys_ppoll_time32 +301 o32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +302 o32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 303 o32 unshare sys_unshare 304 o32 splice sys_splice 305 o32 sync_file_range sys_sync_file_range sys32_sync_file_range @@ -327,14 +327,14 @@ 313 o32 epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait 314 o32 ioprio_set sys_ioprio_set 315 o32 ioprio_get sys_ioprio_get -316 o32 utimensat sys_utimensat sys_utimensat_time32 +316 o32 utimensat sys_utimensat_time32 317 o32 signalfd sys_signalfd compat_sys_signalfd 318 o32 timerfd sys_ni_syscall 319 o32 eventfd sys_eventfd 320 o32 fallocate sys_fallocate sys32_fallocate 321 o32 timerfd_create sys_timerfd_create -322 o32 timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 -323 o32 timerfd_settime sys_timerfd_settime sys_timerfd_settime32 +322 o32 timerfd_gettime sys_timerfd_gettime32 +323 o32 timerfd_settime sys_timerfd_settime32 324 o32 signalfd4 sys_signalfd4 compat_sys_signalfd4 325 o32 eventfd2 sys_eventfd2 326 o32 epoll_create1 sys_epoll_create1 @@ -346,13 +346,13 @@ 332 o32 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo 333 o32 perf_event_open sys_perf_event_open 334 o32 accept4 sys_accept4 -335 o32 recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 +335 o32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 336 o32 fanotify_init sys_fanotify_init 337 o32 fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark 338 o32 prlimit64 sys_prlimit64 339 o32 name_to_handle_at sys_name_to_handle_at 340 o32 open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -341 o32 clock_adjtime sys_clock_adjtime sys_clock_adjtime32 +341 o32 clock_adjtime sys_clock_adjtime32 342 o32 syncfs sys_syncfs 343 o32 sendmmsg sys_sendmmsg compat_sys_sendmmsg 344 o32 setns sys_setns @@ -379,7 +379,7 @@ 365 o32 pkey_free sys_pkey_free 366 o32 statx sys_statx 367 o32 rseq sys_rseq -368 o32 io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +368 o32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents # room for arch specific calls 393 o32 semget sys_semget 394 o32 semctl sys_semctl compat_sys_semctl diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index f7440427d459..b110c7371b08 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -133,7 +133,8 @@ 121 common setdomainname sys_setdomainname 122 common sendfile sys_sendfile compat_sys_sendfile 123 common recvfrom sys_recvfrom -124 common adjtimex sys_adjtimex sys_adjtimex_time32 +124 32 adjtimex sys_adjtimex_time32 +124 64 adjtimex sys_adjtimex 125 common mprotect sys_mprotect 126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask # 127 was create_module @@ -171,8 +172,10 @@ 158 common sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 -162 common nanosleep sys_nanosleep sys_nanosleep_time32 +161 32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +161 64 sched_rr_get_interval sys_sched_rr_get_interval +162 32 nanosleep sys_nanosleep_time32 +162 64 nanosleep sys_nanosleep 163 common mremap sys_mremap 164 common setresuid sys_setresuid 165 common getresuid sys_getresuid @@ -187,7 +190,8 @@ 174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 +177 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +177 64 rt_sigtimedwait sys_rt_sigtimedwait 178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 180 common chown sys_chown @@ -223,14 +227,16 @@ 207 64 readahead sys_readahead 208 common tkill sys_tkill 209 common sendfile64 sys_sendfile64 compat_sys_sendfile64 -210 common futex sys_futex sys_futex_time32 +210 32 futex sys_futex_time32 +210 64 futex sys_futex 211 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 212 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity # 213 was set_thread_area # 214 was get_thread_area 215 common io_setup sys_io_setup compat_sys_io_setup 216 common io_destroy sys_io_destroy -217 common io_getevents sys_io_getevents sys_io_getevents_time32 +217 32 io_getevents sys_io_getevents_time32 +217 64 io_getevents sys_io_getevents 218 common io_submit sys_io_submit compat_sys_io_submit 219 common io_cancel sys_io_cancel # 220 was alloc_hugepages @@ -241,11 +247,14 @@ 225 common epoll_ctl sys_epoll_ctl 226 common epoll_wait sys_epoll_wait 227 common remap_file_pages sys_remap_file_pages -228 common semtimedop sys_semtimedop sys_semtimedop_time32 +228 32 semtimedop sys_semtimedop_time32 +228 64 semtimedop sys_semtimedop 229 common mq_open sys_mq_open compat_sys_mq_open 230 common mq_unlink sys_mq_unlink -231 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 -232 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 +231 32 mq_timedsend sys_mq_timedsend_time32 +231 64 mq_timedsend sys_mq_timedsend +232 32 mq_timedreceive sys_mq_timedreceive_time32 +232 64 mq_timedreceive sys_mq_timedreceive 233 common mq_notify sys_mq_notify compat_sys_mq_notify 234 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 235 common waitid sys_waitid compat_sys_waitid @@ -265,14 +274,20 @@ 248 common lremovexattr sys_lremovexattr 249 common fremovexattr sys_fremovexattr 250 common timer_create sys_timer_create compat_sys_timer_create -251 common timer_settime sys_timer_settime sys_timer_settime32 -252 common timer_gettime sys_timer_gettime sys_timer_gettime32 +251 32 timer_settime sys_timer_settime32 +251 64 timer_settime sys_timer_settime +252 32 timer_gettime sys_timer_gettime32 +252 64 timer_gettime sys_timer_gettime 253 common timer_getoverrun sys_timer_getoverrun 254 common timer_delete sys_timer_delete -255 common clock_settime sys_clock_settime sys_clock_settime32 -256 common clock_gettime sys_clock_gettime sys_clock_gettime32 -257 common clock_getres sys_clock_getres sys_clock_getres_time32 -258 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 +255 32 clock_settime sys_clock_settime32 +255 64 clock_settime sys_clock_settime +256 32 clock_gettime sys_clock_gettime32 +256 64 clock_gettime sys_clock_gettime +257 32 clock_getres sys_clock_getres_time32 +257 64 clock_getres sys_clock_getres +258 32 clock_nanosleep sys_clock_nanosleep_time32 +258 64 clock_nanosleep sys_clock_nanosleep 259 common tgkill sys_tgkill 260 common mbind sys_mbind compat_sys_mbind 261 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy @@ -287,8 +302,10 @@ 270 common inotify_add_watch sys_inotify_add_watch 271 common inotify_rm_watch sys_inotify_rm_watch 272 common migrate_pages sys_migrate_pages -273 common pselect6 sys_pselect6 compat_sys_pselect6_time32 -274 common ppoll sys_ppoll compat_sys_ppoll_time32 +273 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +273 64 pselect6 sys_pselect6 +274 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +274 64 ppoll sys_ppoll 275 common openat sys_openat compat_sys_openat 276 common mkdirat sys_mkdirat 277 common mknodat sys_mknodat @@ -316,15 +333,18 @@ 298 common statfs64 sys_statfs64 compat_sys_statfs64 299 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 300 common kexec_load sys_kexec_load compat_sys_kexec_load -301 common utimensat sys_utimensat sys_utimensat_time32 +301 32 utimensat sys_utimensat_time32 +301 64 utimensat sys_utimensat 302 common signalfd sys_signalfd compat_sys_signalfd # 303 was timerfd 304 common eventfd sys_eventfd 305 32 fallocate parisc_fallocate 305 64 fallocate sys_fallocate 306 common timerfd_create sys_timerfd_create -307 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 -308 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 +307 32 timerfd_settime sys_timerfd_settime32 +307 64 timerfd_settime sys_timerfd_settime +308 32 timerfd_gettime sys_timerfd_gettime32 +308 64 timerfd_gettime sys_timerfd_gettime 309 common signalfd4 sys_signalfd4 compat_sys_signalfd4 310 common eventfd2 sys_eventfd2 311 common epoll_create1 sys_epoll_create1 @@ -335,12 +355,14 @@ 316 common pwritev sys_pwritev compat_sys_pwritev 317 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo 318 common perf_event_open sys_perf_event_open -319 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 +319 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +319 64 recvmmsg sys_recvmmsg 320 common accept4 sys_accept4 321 common prlimit64 sys_prlimit64 322 common fanotify_init sys_fanotify_init 323 common fanotify_mark sys_fanotify_mark sys32_fanotify_mark -324 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 +324 32 clock_adjtime sys_clock_adjtime32 +324 64 clock_adjtime sys_clock_adjtime 325 common name_to_handle_at sys_name_to_handle_at 326 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at 327 common syncfs sys_syncfs @@ -366,7 +388,8 @@ 347 common preadv2 sys_preadv2 compat_sys_preadv2 348 common pwritev2 sys_pwritev2 compat_sys_pwritev2 349 common statx sys_statx -350 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +350 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +350 64 io_pgetevents sys_io_pgetevents 351 common pkey_mprotect sys_pkey_mprotect 352 common pkey_alloc sys_pkey_alloc 353 common pkey_free sys_pkey_free diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 86650dcd2185..2a8b060f73b3 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -157,7 +157,9 @@ 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common modify_ldt sys_ni_syscall -124 common adjtimex sys_adjtimex sys_adjtimex_time32 +124 32 adjtimex sys_adjtimex_time32 +124 64 adjtimex sys_adjtimex +124 spu adjtimex sys_adjtimex 125 common mprotect sys_mprotect 126 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask 126 64 sigprocmask sys_ni_syscall @@ -198,8 +200,12 @@ 158 common sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 -162 common nanosleep sys_nanosleep sys_nanosleep_time32 +161 32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +161 64 sched_rr_get_interval sys_sched_rr_get_interval +161 spu sched_rr_get_interval sys_sched_rr_get_interval +162 32 nanosleep sys_nanosleep_time32 +162 64 nanosleep sys_nanosleep +162 spu nanosleep sys_nanosleep 163 common mremap sys_mremap 164 common setresuid sys_setresuid 165 common getresuid sys_getresuid @@ -213,7 +219,8 @@ 173 nospu rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 174 nospu rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 175 nospu rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -176 nospu rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 +176 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 179 common pread64 sys_pread64 compat_sys_pread64 @@ -260,7 +267,9 @@ 218 common removexattr sys_removexattr 219 common lremovexattr sys_lremovexattr 220 common fremovexattr sys_fremovexattr -221 common futex sys_futex sys_futex_time32 +221 32 futex sys_futex_time32 +221 64 futex sys_futex +221 spu futex sys_futex 222 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 223 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity # 224 unused @@ -268,7 +277,9 @@ 226 32 sendfile64 sys_sendfile64 compat_sys_sendfile64 227 common io_setup sys_io_setup compat_sys_io_setup 228 common io_destroy sys_io_destroy -229 common io_getevents sys_io_getevents sys_io_getevents_time32 +229 32 io_getevents sys_io_getevents_time32 +229 64 io_getevents sys_io_getevents +229 spu io_getevents sys_io_getevents 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address @@ -280,14 +291,26 @@ 238 common epoll_wait sys_epoll_wait 239 common remap_file_pages sys_remap_file_pages 240 common timer_create sys_timer_create compat_sys_timer_create -241 common timer_settime sys_timer_settime sys_timer_settime32 -242 common timer_gettime sys_timer_gettime sys_timer_gettime32 +241 32 timer_settime sys_timer_settime32 +241 64 timer_settime sys_timer_settime +241 spu timer_settime sys_timer_settime +242 32 timer_gettime sys_timer_gettime32 +242 64 timer_gettime sys_timer_gettime +242 spu timer_gettime sys_timer_gettime 243 common timer_getoverrun sys_timer_getoverrun 244 common timer_delete sys_timer_delete -245 common clock_settime sys_clock_settime sys_clock_settime32 -246 common clock_gettime sys_clock_gettime sys_clock_gettime32 -247 common clock_getres sys_clock_getres sys_clock_getres_time32 -248 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 +245 32 clock_settime sys_clock_settime32 +245 64 clock_settime sys_clock_settime +245 spu clock_settime sys_clock_settime +246 32 clock_gettime sys_clock_gettime32 +246 64 clock_gettime sys_clock_gettime +246 spu clock_gettime sys_clock_gettime +247 32 clock_getres sys_clock_getres_time32 +247 64 clock_getres sys_clock_getres +247 spu clock_getres sys_clock_getres +248 32 clock_nanosleep sys_clock_nanosleep_time32 +248 64 clock_nanosleep sys_clock_nanosleep +248 spu clock_nanosleep sys_clock_nanosleep 249 32 swapcontext ppc_swapcontext ppc32_swapcontext 249 64 swapcontext ppc64_swapcontext 249 spu swapcontext sys_ni_syscall @@ -308,8 +331,10 @@ 261 nospu set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy 262 nospu mq_open sys_mq_open compat_sys_mq_open 263 nospu mq_unlink sys_mq_unlink -264 nospu mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 -265 nospu mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 +264 32 mq_timedsend sys_mq_timedsend_time32 +264 64 mq_timedsend sys_mq_timedsend +265 32 mq_timedreceive sys_mq_timedreceive_time32 +265 64 mq_timedreceive sys_mq_timedreceive 266 nospu mq_notify sys_mq_notify compat_sys_mq_notify 267 nospu mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 268 nospu kexec_load sys_kexec_load compat_sys_kexec_load @@ -324,8 +349,10 @@ 277 nospu inotify_rm_watch sys_inotify_rm_watch 278 nospu spu_run sys_spu_run 279 nospu spu_create sys_spu_create -280 nospu pselect6 sys_pselect6 compat_sys_pselect6_time32 -281 nospu ppoll sys_ppoll compat_sys_ppoll_time32 +280 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +280 64 pselect6 sys_pselect6 +281 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +281 64 ppoll sys_ppoll 282 common unshare sys_unshare 283 common splice sys_splice 284 common tee sys_tee @@ -350,15 +377,21 @@ 301 common move_pages sys_move_pages compat_sys_move_pages 302 common getcpu sys_getcpu 303 nospu epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -304 common utimensat sys_utimensat sys_utimensat_time32 +304 32 utimensat sys_utimensat_time32 +304 64 utimensat sys_utimensat +304 spu utimensat sys_utimensat 305 common signalfd sys_signalfd compat_sys_signalfd 306 common timerfd_create sys_timerfd_create 307 common eventfd sys_eventfd 308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2 309 nospu fallocate sys_fallocate compat_sys_fallocate 310 nospu subpage_prot sys_subpage_prot -311 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 -312 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 +311 32 timerfd_settime sys_timerfd_settime32 +311 64 timerfd_settime sys_timerfd_settime +311 spu timerfd_settime sys_timerfd_settime +312 32 timerfd_gettime sys_timerfd_gettime32 +312 64 timerfd_gettime sys_timerfd_gettime +312 spu timerfd_gettime sys_timerfd_gettime 313 common signalfd4 sys_signalfd4 compat_sys_signalfd4 314 common eventfd2 sys_eventfd2 315 common epoll_create1 sys_epoll_create1 @@ -389,11 +422,15 @@ 340 common getsockopt sys_getsockopt compat_sys_getsockopt 341 common sendmsg sys_sendmsg compat_sys_sendmsg 342 common recvmsg sys_recvmsg compat_sys_recvmsg -343 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 +343 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +343 64 recvmmsg sys_recvmmsg +343 spu recvmmsg sys_recvmmsg 344 common accept4 sys_accept4 345 common name_to_handle_at sys_name_to_handle_at 346 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -347 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 +347 32 clock_adjtime sys_clock_adjtime32 +347 64 clock_adjtime sys_clock_adjtime +347 spu clock_adjtime sys_clock_adjtime 348 common syncfs sys_syncfs 349 common sendmmsg sys_sendmmsg compat_sys_sendmmsg 350 common setns sys_setns @@ -425,7 +462,8 @@ 385 nospu pkey_free sys_pkey_free 386 nospu pkey_mprotect sys_pkey_mprotect 387 nospu rseq sys_rseq -388 nospu io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +388 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +388 64 io_pgetevents sys_io_pgetevents # room for arch specific syscalls 392 64 semtimedop sys_semtimedop 393 common semget sys_semget diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index cafa63c6a932..a08a5312cd12 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -131,7 +131,7 @@ 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common cacheflush sys_cacheflush -124 common adjtimex sys_adjtimex +124 common adjtimex sys_adjtimex_time32 125 common mprotect sys_mprotect 126 common sigprocmask sys_sigprocmask # 127 was create_module @@ -168,8 +168,8 @@ 158 common sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 163 common mremap sys_mremap 164 common setresuid sys_setresuid16 165 common getresuid sys_getresuid16 @@ -184,7 +184,7 @@ 174 common rt_sigaction sys_rt_sigaction 175 common rt_sigprocmask sys_rt_sigprocmask 176 common rt_sigpending sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 178 common rt_sigqueueinfo sys_rt_sigqueueinfo 179 common rt_sigsuspend sys_rt_sigsuspend 180 common pread64 sys_pread_wrapper @@ -247,14 +247,14 @@ 237 common fremovexattr sys_fremovexattr 238 common tkill sys_tkill 239 common sendfile64 sys_sendfile64 -240 common futex sys_futex +240 common futex sys_futex_time32 241 common sched_setaffinity sys_sched_setaffinity 242 common sched_getaffinity sys_sched_getaffinity # 243 is reserved for set_thread_area # 244 is reserved for get_thread_area 245 common io_setup sys_io_setup 246 common io_destroy sys_io_destroy -247 common io_getevents sys_io_getevents +247 common io_getevents sys_io_getevents_time32 248 common io_submit sys_io_submit 249 common io_cancel sys_io_cancel 250 common fadvise64 sys_fadvise64 @@ -267,14 +267,14 @@ 257 common remap_file_pages sys_remap_file_pages 258 common set_tid_address sys_set_tid_address 259 common timer_create sys_timer_create -260 common timer_settime sys_timer_settime -261 common timer_gettime sys_timer_gettime +260 common timer_settime sys_timer_settime32 +261 common timer_gettime sys_timer_gettime32 262 common timer_getoverrun sys_timer_getoverrun 263 common timer_delete sys_timer_delete -264 common clock_settime sys_clock_settime -265 common clock_gettime sys_clock_gettime -266 common clock_getres sys_clock_getres -267 common clock_nanosleep sys_clock_nanosleep +264 common clock_settime sys_clock_settime32 +265 common clock_gettime sys_clock_gettime32 +266 common clock_getres sys_clock_getres_time32 +267 common clock_nanosleep sys_clock_nanosleep_time32 268 common statfs64 sys_statfs64 269 common fstatfs64 sys_fstatfs64 270 common tgkill sys_tgkill @@ -286,8 +286,8 @@ 276 common set_mempolicy sys_set_mempolicy 277 common mq_open sys_mq_open 278 common mq_unlink sys_mq_unlink -279 common mq_timedsend sys_mq_timedsend -280 common mq_timedreceive sys_mq_timedreceive +279 common mq_timedsend sys_mq_timedsend_time32 +280 common mq_timedreceive sys_mq_timedreceive_time32 281 common mq_notify sys_mq_notify 282 common mq_getsetattr sys_mq_getsetattr 283 common kexec_load sys_kexec_load @@ -315,8 +315,8 @@ 305 common readlinkat sys_readlinkat 306 common fchmodat sys_fchmodat 307 common faccessat sys_faccessat -308 common pselect6 sys_pselect6 -309 common ppoll sys_ppoll +308 common pselect6 sys_pselect6_time32 +309 common ppoll sys_ppoll_time32 310 common unshare sys_unshare 311 common set_robust_list sys_set_robust_list 312 common get_robust_list sys_get_robust_list @@ -327,13 +327,13 @@ 317 common move_pages sys_move_pages 318 common getcpu sys_getcpu 319 common epoll_pwait sys_epoll_pwait -320 common utimensat sys_utimensat +320 common utimensat sys_utimensat_time32 321 common signalfd sys_signalfd 322 common timerfd_create sys_timerfd_create 323 common eventfd sys_eventfd 324 common fallocate sys_fallocate -325 common timerfd_settime sys_timerfd_settime -326 common timerfd_gettime sys_timerfd_gettime +325 common timerfd_settime sys_timerfd_settime32 +326 common timerfd_gettime sys_timerfd_gettime32 327 common signalfd4 sys_signalfd4 328 common eventfd2 sys_eventfd2 329 common epoll_create1 sys_epoll_create1 @@ -364,11 +364,11 @@ 354 common getsockopt sys_getsockopt 355 common sendmsg sys_sendmsg 356 common recvmsg sys_recvmsg -357 common recvmmsg sys_recvmmsg +357 common recvmmsg sys_recvmmsg_time32 358 common accept4 sys_accept4 359 common name_to_handle_at sys_name_to_handle_at 360 common open_by_handle_at sys_open_by_handle_at -361 common clock_adjtime sys_clock_adjtime +361 common clock_adjtime sys_clock_adjtime32 362 common syncfs sys_syncfs 363 common sendmmsg sys_sendmmsg 364 common setns sys_setns diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 7cb05b50aeaa..dc1e08040b39 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -128,7 +128,8 @@ 102 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 103 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 104 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -105 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 +105 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +105 64 rt_sigtimedwait sys_rt_sigtimedwait 106 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 107 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 108 32 setresuid32 sys_setresuid @@ -172,7 +173,8 @@ 139 common stat64 sys_stat64 compat_sys_stat64 140 common sendfile64 sys_sendfile64 141 common getpeername sys_getpeername -142 common futex sys_futex sys_futex_time32 +142 32 futex sys_futex_time32 +142 64 futex sys_futex 143 common gettid sys_gettid 144 common getrlimit sys_getrlimit compat_sys_getrlimit 145 common setrlimit sys_setrlimit compat_sys_setrlimit @@ -258,7 +260,7 @@ 216 64 sigreturn sys_nis_syscall 217 common clone sys_clone 218 common ioprio_get sys_ioprio_get -219 32 adjtimex sys_adjtimex sys_adjtimex_time32 +219 32 adjtimex sys_adjtimex_time32 219 64 adjtimex sys_sparc_adjtimex 220 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask 220 64 sigprocmask sys_nis_syscall @@ -289,8 +291,10 @@ 245 common sched_yield sys_sched_yield 246 common sched_get_priority_max sys_sched_get_priority_max 247 common sched_get_priority_min sys_sched_get_priority_min -248 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 -249 common nanosleep sys_nanosleep sys_nanosleep_time32 +248 32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +248 64 sched_rr_get_interval sys_sched_rr_get_interval +249 32 nanosleep sys_nanosleep_time32 +249 64 nanosleep sys_nanosleep 250 32 mremap sys_mremap 250 64 mremap sys_64_mremap 251 common _sysctl sys_sysctl compat_sys_sysctl @@ -299,14 +303,20 @@ 254 32 nfsservctl sys_ni_syscall sys_nis_syscall 254 64 nfsservctl sys_nis_syscall 255 common sync_file_range sys_sync_file_range compat_sys_sync_file_range -256 common clock_settime sys_clock_settime sys_clock_settime32 -257 common clock_gettime sys_clock_gettime sys_clock_gettime32 -258 common clock_getres sys_clock_getres sys_clock_getres_time32 -259 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 +256 32 clock_settime sys_clock_settime32 +256 64 clock_settime sys_clock_settime +257 32 clock_gettime sys_clock_gettime32 +257 64 clock_gettime sys_clock_gettime +258 32 clock_getres sys_clock_getres_time32 +258 64 clock_getres sys_clock_getres +259 32 clock_nanosleep sys_clock_nanosleep_time32 +259 64 clock_nanosleep sys_clock_nanosleep 260 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity 261 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity -262 common timer_settime sys_timer_settime sys_timer_settime32 -263 common timer_gettime sys_timer_gettime sys_timer_gettime32 +262 32 timer_settime sys_timer_settime32 +262 64 timer_settime sys_timer_settime +263 32 timer_gettime sys_timer_gettime32 +263 64 timer_gettime sys_timer_gettime 264 common timer_getoverrun sys_timer_getoverrun 265 common timer_delete sys_timer_delete 266 common timer_create sys_timer_create compat_sys_timer_create @@ -316,11 +326,14 @@ 269 common io_destroy sys_io_destroy 270 common io_submit sys_io_submit compat_sys_io_submit 271 common io_cancel sys_io_cancel -272 common io_getevents sys_io_getevents sys_io_getevents_time32 +272 32 io_getevents sys_io_getevents_time32 +272 64 io_getevents sys_io_getevents 273 common mq_open sys_mq_open compat_sys_mq_open 274 common mq_unlink sys_mq_unlink -275 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 -276 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 +275 32 mq_timedsend sys_mq_timedsend_time32 +275 64 mq_timedsend sys_mq_timedsend +276 32 mq_timedreceive sys_mq_timedreceive_time32 +276 64 mq_timedreceive sys_mq_timedreceive 277 common mq_notify sys_mq_notify compat_sys_mq_notify 278 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 279 common waitid sys_waitid compat_sys_waitid @@ -341,8 +354,10 @@ 294 common readlinkat sys_readlinkat 295 common fchmodat sys_fchmodat 296 common faccessat sys_faccessat -297 common pselect6 sys_pselect6 compat_sys_pselect6_time32 -298 common ppoll sys_ppoll compat_sys_ppoll_time32 +297 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +297 64 pselect6 sys_pselect6 +298 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +298 64 ppoll sys_ppoll 299 common unshare sys_unshare 300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list 301 common get_robust_list sys_get_robust_list compat_sys_get_robust_list @@ -354,13 +369,16 @@ 307 common move_pages sys_move_pages compat_sys_move_pages 308 common getcpu sys_getcpu 309 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -310 common utimensat sys_utimensat sys_utimensat_time32 +310 32 utimensat sys_utimensat_time32 +310 64 utimensat sys_utimensat 311 common signalfd sys_signalfd compat_sys_signalfd 312 common timerfd_create sys_timerfd_create 313 common eventfd sys_eventfd 314 common fallocate sys_fallocate compat_sys_fallocate -315 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 -316 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 +315 32 timerfd_settime sys_timerfd_settime32 +315 64 timerfd_settime sys_timerfd_settime +316 32 timerfd_gettime sys_timerfd_gettime32 +316 64 timerfd_gettime sys_timerfd_gettime 317 common signalfd4 sys_signalfd4 compat_sys_signalfd4 318 common eventfd2 sys_eventfd2 319 common epoll_create1 sys_epoll_create1 @@ -372,13 +390,14 @@ 325 common pwritev sys_pwritev compat_sys_pwritev 326 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo 327 common perf_event_open sys_perf_event_open -328 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 +328 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +328 64 recvmmsg sys_recvmmsg 329 common fanotify_init sys_fanotify_init 330 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark 331 common prlimit64 sys_prlimit64 332 common name_to_handle_at sys_name_to_handle_at 333 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -334 32 clock_adjtime sys_clock_adjtime sys_clock_adjtime32 +334 32 clock_adjtime sys_clock_adjtime32 334 64 clock_adjtime sys_sparc_clock_adjtime 335 common syncfs sys_syncfs 336 common sendmmsg sys_sendmmsg compat_sys_sendmmsg @@ -408,7 +427,8 @@ 358 common preadv2 sys_preadv2 compat_sys_preadv2 359 common pwritev2 sys_pwritev2 compat_sys_pwritev2 360 common statx sys_statx -361 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +361 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +361 64 io_pgetevents sys_io_pgetevents 362 common pkey_mprotect sys_pkey_mprotect 363 common pkey_alloc sys_pkey_alloc 364 common pkey_free sys_pkey_free diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 7705d5ecad25..28888d6b7f61 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -135,7 +135,7 @@ 121 i386 setdomainname sys_setdomainname __ia32_sys_setdomainname 122 i386 uname sys_newuname __ia32_sys_newuname 123 i386 modify_ldt sys_modify_ldt __ia32_sys_modify_ldt -124 i386 adjtimex sys_adjtimex __ia32_sys_adjtimex_time32 +124 i386 adjtimex sys_adjtimex_time32 __ia32_sys_adjtimex_time32 125 i386 mprotect sys_mprotect __ia32_sys_mprotect 126 i386 sigprocmask sys_sigprocmask __ia32_compat_sys_sigprocmask 127 i386 create_module @@ -172,8 +172,8 @@ 158 i386 sched_yield sys_sched_yield __ia32_sys_sched_yield 159 i386 sched_get_priority_max sys_sched_get_priority_max __ia32_sys_sched_get_priority_max 160 i386 sched_get_priority_min sys_sched_get_priority_min __ia32_sys_sched_get_priority_min -161 i386 sched_rr_get_interval sys_sched_rr_get_interval __ia32_sys_sched_rr_get_interval_time32 -162 i386 nanosleep sys_nanosleep __ia32_sys_nanosleep_time32 +161 i386 sched_rr_get_interval sys_sched_rr_get_interval_time32 __ia32_sys_sched_rr_get_interval_time32 +162 i386 nanosleep sys_nanosleep_time32 __ia32_sys_nanosleep_time32 163 i386 mremap sys_mremap __ia32_sys_mremap 164 i386 setresuid sys_setresuid16 __ia32_sys_setresuid16 165 i386 getresuid sys_getresuid16 __ia32_sys_getresuid16 @@ -188,7 +188,7 @@ 174 i386 rt_sigaction sys_rt_sigaction __ia32_compat_sys_rt_sigaction 175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending __ia32_compat_sys_rt_sigpending -177 i386 rt_sigtimedwait sys_rt_sigtimedwait __ia32_compat_sys_rt_sigtimedwait_time32 +177 i386 rt_sigtimedwait sys_rt_sigtimedwait_time32 __ia32_compat_sys_rt_sigtimedwait_time32 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo __ia32_compat_sys_rt_sigqueueinfo 179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_sys_rt_sigsuspend 180 i386 pread64 sys_pread64 __ia32_compat_sys_x86_pread @@ -251,14 +251,14 @@ 237 i386 fremovexattr sys_fremovexattr __ia32_sys_fremovexattr 238 i386 tkill sys_tkill __ia32_sys_tkill 239 i386 sendfile64 sys_sendfile64 __ia32_sys_sendfile64 -240 i386 futex sys_futex __ia32_sys_futex_time32 +240 i386 futex sys_futex_time32 __ia32_sys_futex_time32 241 i386 sched_setaffinity sys_sched_setaffinity __ia32_compat_sys_sched_setaffinity 242 i386 sched_getaffinity sys_sched_getaffinity __ia32_compat_sys_sched_getaffinity 243 i386 set_thread_area sys_set_thread_area __ia32_sys_set_thread_area 244 i386 get_thread_area sys_get_thread_area __ia32_sys_get_thread_area 245 i386 io_setup sys_io_setup __ia32_compat_sys_io_setup 246 i386 io_destroy sys_io_destroy __ia32_sys_io_destroy -247 i386 io_getevents sys_io_getevents __ia32_sys_io_getevents_time32 +247 i386 io_getevents sys_io_getevents_time32 __ia32_sys_io_getevents_time32 248 i386 io_submit sys_io_submit __ia32_compat_sys_io_submit 249 i386 io_cancel sys_io_cancel __ia32_sys_io_cancel 250 i386 fadvise64 sys_fadvise64 __ia32_compat_sys_x86_fadvise64 @@ -271,14 +271,14 @@ 257 i386 remap_file_pages sys_remap_file_pages __ia32_sys_remap_file_pages 258 i386 set_tid_address sys_set_tid_address __ia32_sys_set_tid_address 259 i386 timer_create sys_timer_create __ia32_compat_sys_timer_create -260 i386 timer_settime sys_timer_settime __ia32_sys_timer_settime32 -261 i386 timer_gettime sys_timer_gettime __ia32_sys_timer_gettime32 +260 i386 timer_settime sys_timer_settime32 __ia32_sys_timer_settime32 +261 i386 timer_gettime sys_timer_gettime32 __ia32_sys_timer_gettime32 262 i386 timer_getoverrun sys_timer_getoverrun __ia32_sys_timer_getoverrun 263 i386 timer_delete sys_timer_delete __ia32_sys_timer_delete -264 i386 clock_settime sys_clock_settime __ia32_sys_clock_settime32 -265 i386 clock_gettime sys_clock_gettime __ia32_sys_clock_gettime32 -266 i386 clock_getres sys_clock_getres __ia32_sys_clock_getres_time32 -267 i386 clock_nanosleep sys_clock_nanosleep __ia32_sys_clock_nanosleep_time32 +264 i386 clock_settime sys_clock_settime32 __ia32_sys_clock_settime32 +265 i386 clock_gettime sys_clock_gettime32 __ia32_sys_clock_gettime32 +266 i386 clock_getres sys_clock_getres_time32 __ia32_sys_clock_getres_time32 +267 i386 clock_nanosleep sys_clock_nanosleep_time32 __ia32_sys_clock_nanosleep_time32 268 i386 statfs64 sys_statfs64 __ia32_compat_sys_statfs64 269 i386 fstatfs64 sys_fstatfs64 __ia32_compat_sys_fstatfs64 270 i386 tgkill sys_tgkill __ia32_sys_tgkill @@ -290,8 +290,8 @@ 276 i386 set_mempolicy sys_set_mempolicy __ia32_sys_set_mempolicy 277 i386 mq_open sys_mq_open __ia32_compat_sys_mq_open 278 i386 mq_unlink sys_mq_unlink __ia32_sys_mq_unlink -279 i386 mq_timedsend sys_mq_timedsend __ia32_sys_mq_timedsend_time32 -280 i386 mq_timedreceive sys_mq_timedreceive __ia32_sys_mq_timedreceive_time32 +279 i386 mq_timedsend sys_mq_timedsend_time32 __ia32_sys_mq_timedsend_time32 +280 i386 mq_timedreceive sys_mq_timedreceive_time32 __ia32_sys_mq_timedreceive_time32 281 i386 mq_notify sys_mq_notify __ia32_compat_sys_mq_notify 282 i386 mq_getsetattr sys_mq_getsetattr __ia32_compat_sys_mq_getsetattr 283 i386 kexec_load sys_kexec_load __ia32_compat_sys_kexec_load @@ -319,8 +319,8 @@ 305 i386 readlinkat sys_readlinkat __ia32_sys_readlinkat 306 i386 fchmodat sys_fchmodat __ia32_sys_fchmodat 307 i386 faccessat sys_faccessat __ia32_sys_faccessat -308 i386 pselect6 sys_pselect6 __ia32_compat_sys_pselect6_time32 -309 i386 ppoll sys_ppoll __ia32_compat_sys_ppoll_time32 +308 i386 pselect6 sys_pselect6_time32 __ia32_compat_sys_pselect6_time32 +309 i386 ppoll sys_ppoll_time32 __ia32_compat_sys_ppoll_time32 310 i386 unshare sys_unshare __ia32_sys_unshare 311 i386 set_robust_list sys_set_robust_list __ia32_compat_sys_set_robust_list 312 i386 get_robust_list sys_get_robust_list __ia32_compat_sys_get_robust_list @@ -331,13 +331,13 @@ 317 i386 move_pages sys_move_pages __ia32_compat_sys_move_pages 318 i386 getcpu sys_getcpu __ia32_sys_getcpu 319 i386 epoll_pwait sys_epoll_pwait __ia32_sys_epoll_pwait -320 i386 utimensat sys_utimensat __ia32_sys_utimensat_time32 +320 i386 utimensat sys_utimensat_time32 __ia32_sys_utimensat_time32 321 i386 signalfd sys_signalfd __ia32_compat_sys_signalfd 322 i386 timerfd_create sys_timerfd_create __ia32_sys_timerfd_create 323 i386 eventfd sys_eventfd __ia32_sys_eventfd 324 i386 fallocate sys_fallocate __ia32_compat_sys_x86_fallocate -325 i386 timerfd_settime sys_timerfd_settime __ia32_sys_timerfd_settime32 -326 i386 timerfd_gettime sys_timerfd_gettime __ia32_sys_timerfd_gettime32 +325 i386 timerfd_settime sys_timerfd_settime32 __ia32_sys_timerfd_settime32 +326 i386 timerfd_gettime sys_timerfd_gettime32 __ia32_sys_timerfd_gettime32 327 i386 signalfd4 sys_signalfd4 __ia32_compat_sys_signalfd4 328 i386 eventfd2 sys_eventfd2 __ia32_sys_eventfd2 329 i386 epoll_create1 sys_epoll_create1 __ia32_sys_epoll_create1 @@ -348,13 +348,13 @@ 334 i386 pwritev sys_pwritev __ia32_compat_sys_pwritev 335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo __ia32_compat_sys_rt_tgsigqueueinfo 336 i386 perf_event_open sys_perf_event_open __ia32_sys_perf_event_open -337 i386 recvmmsg sys_recvmmsg __ia32_compat_sys_recvmmsg_time32 +337 i386 recvmmsg sys_recvmmsg_time32 __ia32_compat_sys_recvmmsg_time32 338 i386 fanotify_init sys_fanotify_init __ia32_sys_fanotify_init 339 i386 fanotify_mark sys_fanotify_mark __ia32_compat_sys_fanotify_mark 340 i386 prlimit64 sys_prlimit64 __ia32_sys_prlimit64 341 i386 name_to_handle_at sys_name_to_handle_at __ia32_sys_name_to_handle_at 342 i386 open_by_handle_at sys_open_by_handle_at __ia32_compat_sys_open_by_handle_at -343 i386 clock_adjtime sys_clock_adjtime __ia32_sys_clock_adjtime32 +343 i386 clock_adjtime sys_clock_adjtime32 __ia32_sys_clock_adjtime32 344 i386 syncfs sys_syncfs __ia32_sys_syncfs 345 i386 sendmmsg sys_sendmmsg __ia32_compat_sys_sendmmsg 346 i386 setns sys_setns __ia32_sys_setns @@ -396,7 +396,7 @@ 382 i386 pkey_free sys_pkey_free __ia32_sys_pkey_free 383 i386 statx sys_statx __ia32_sys_statx 384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl -385 i386 io_pgetevents sys_io_pgetevents __ia32_compat_sys_io_pgetevents +385 i386 io_pgetevents sys_io_pgetevents_time32 __ia32_compat_sys_io_pgetevents 386 i386 rseq sys_rseq __ia32_sys_rseq # don't use numbers 387 through 392, add new calls at the end 393 i386 semget sys_semget __ia32_sys_semget diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index c699e014e0dd..6f05bc8f015a 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -174,7 +174,7 @@ 158 common capget sys_capget 159 common capset sys_capset 160 common ptrace sys_ptrace -161 common semtimedop sys_semtimedop +161 common semtimedop sys_semtimedop_time32 162 common semget sys_semget 163 common semop sys_semop 164 common semctl sys_old_semctl @@ -206,11 +206,11 @@ 188 common setrlimit sys_setrlimit 189 common getrlimit sys_getrlimit 190 common getrusage sys_getrusage -191 common futex sys_futex +191 common futex sys_futex_time32 192 common gettimeofday sys_gettimeofday 193 common settimeofday sys_settimeofday -194 common adjtimex sys_adjtimex -195 common nanosleep sys_nanosleep +194 common adjtimex sys_adjtimex_time32 +195 common nanosleep sys_nanosleep_time32 196 common getgroups sys_getgroups 197 common setgroups sys_setgroups 198 common sethostname sys_sethostname @@ -234,7 +234,7 @@ 215 common sched_getscheduler sys_sched_getscheduler 216 common sched_get_priority_max sys_sched_get_priority_max 217 common sched_get_priority_min sys_sched_get_priority_min -218 common sched_rr_get_interval sys_sched_rr_get_interval +218 common sched_rr_get_interval sys_sched_rr_get_interval_time32 219 common sched_yield sys_sched_yield 222 common available222 sys_ni_syscall # Signal Handling @@ -244,14 +244,14 @@ 226 common rt_sigaction sys_rt_sigaction 227 common rt_sigprocmask sys_rt_sigprocmask 228 common rt_sigpending sys_rt_sigpending -229 common rt_sigtimedwait sys_rt_sigtimedwait +229 common rt_sigtimedwait sys_rt_sigtimedwait_time32 230 common rt_sigqueueinfo sys_rt_sigqueueinfo 231 common rt_sigsuspend sys_rt_sigsuspend # Message 232 common mq_open sys_mq_open 233 common mq_unlink sys_mq_unlink -234 common mq_timedsend sys_mq_timedsend -235 common mq_timedreceive sys_mq_timedreceive +234 common mq_timedsend sys_mq_timedsend_time32 +235 common mq_timedreceive sys_mq_timedreceive_time32 236 common mq_notify sys_mq_notify 237 common mq_getsetattr sys_mq_getsetattr 238 common available238 sys_ni_syscall @@ -259,17 +259,17 @@ # IO 240 common io_destroy sys_io_destroy 241 common io_submit sys_io_submit -242 common io_getevents sys_io_getevents +242 common io_getevents sys_io_getevents_time32 243 common io_cancel sys_io_cancel -244 common clock_settime sys_clock_settime -245 common clock_gettime sys_clock_gettime -246 common clock_getres sys_clock_getres -247 common clock_nanosleep sys_clock_nanosleep +244 common clock_settime sys_clock_settime32 +245 common clock_gettime sys_clock_gettime32 +246 common clock_getres sys_clock_getres_time32 +247 common clock_nanosleep sys_clock_nanosleep_time32 # Timer 248 common timer_create sys_timer_create 249 common timer_delete sys_timer_delete -250 common timer_settime sys_timer_settime -251 common timer_gettime sys_timer_gettime +250 common timer_settime sys_timer_settime32 +251 common timer_gettime sys_timer_gettime32 252 common timer_getoverrun sys_timer_getoverrun # System 253 common reserved253 sys_ni_syscall @@ -291,8 +291,8 @@ 269 common tee sys_tee 270 common vmsplice sys_vmsplice 271 common available271 sys_ni_syscall -272 common pselect6 sys_pselect6 -273 common ppoll sys_ppoll +272 common pselect6 sys_pselect6_time32 +273 common ppoll sys_ppoll_time32 274 common epoll_pwait sys_epoll_pwait 275 common epoll_create1 sys_epoll_create1 276 common inotify_init sys_inotify_init @@ -316,7 +316,7 @@ 293 common linkat sys_linkat 294 common symlinkat sys_symlinkat 295 common readlinkat sys_readlinkat -296 common utimensat sys_utimensat +296 common utimensat sys_utimensat_time32 297 common fchownat sys_fchownat 298 common futimesat sys_futimesat 299 common fstatat64 sys_fstatat64 @@ -327,14 +327,14 @@ 304 common signalfd sys_signalfd # 305 was timerfd 306 common eventfd sys_eventfd -307 common recvmmsg sys_recvmmsg +307 common recvmmsg sys_recvmmsg_time32 308 common setns sys_setns 309 common signalfd4 sys_signalfd4 310 common dup3 sys_dup3 311 common pipe2 sys_pipe2 312 common timerfd_create sys_timerfd_create -313 common timerfd_settime sys_timerfd_settime -314 common timerfd_gettime sys_timerfd_gettime +313 common timerfd_settime sys_timerfd_settime32 +314 common timerfd_gettime sys_timerfd_gettime32 315 common available315 sys_ni_syscall 316 common eventfd2 sys_eventfd2 317 common preadv sys_preadv @@ -349,7 +349,7 @@ 326 common sync_file_range2 sys_sync_file_range2 327 common perf_event_open sys_perf_event_open 328 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo -329 common clock_adjtime sys_clock_adjtime +329 common clock_adjtime sys_clock_adjtime32 330 common prlimit64 sys_prlimit64 331 common kcmp sys_kcmp 332 common finit_module sys_finit_module diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 153b55b94234..ab1831769030 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -39,7 +39,7 @@ __SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit) #define __NR_io_cancel 3 __SYSCALL(__NR_io_cancel, sys_io_cancel) #define __NR_io_getevents 4 -__SC_COMP(__NR_io_getevents, sys_io_getevents, sys_io_getevents_time32) +__SC_3264(__NR_io_getevents, sys_io_getevents_time32, sys_io_getevents) /* fs/xattr.c */ #define __NR_setxattr 5 @@ -223,9 +223,9 @@ __SYSCALL(__NR3264_sendfile, sys_sendfile64) /* fs/select.c */ #define __NR_pselect6 72 -__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6_time32) +__SC_COMP_3264(__NR_pselect6, sys_pselect6_time32, sys_pselect6, compat_sys_pselect6_time32) #define __NR_ppoll 73 -__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll_time32) +__SC_COMP_3264(__NR_ppoll, sys_ppoll_time32, sys_ppoll, compat_sys_ppoll_time32) /* fs/signalfd.c */ #define __NR_signalfd4 74 @@ -270,15 +270,15 @@ __SC_COMP(__NR_sync_file_range, sys_sync_file_range, \ #define __NR_timerfd_create 85 __SYSCALL(__NR_timerfd_create, sys_timerfd_create) #define __NR_timerfd_settime 86 -__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \ - sys_timerfd_settime32) +__SC_3264(__NR_timerfd_settime, sys_timerfd_settime32, \ + sys_timerfd_settime) #define __NR_timerfd_gettime 87 -__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \ - sys_timerfd_gettime32) +__SC_3264(__NR_timerfd_gettime, sys_timerfd_gettime32, \ + sys_timerfd_gettime) /* fs/utimes.c */ #define __NR_utimensat 88 -__SC_COMP(__NR_utimensat, sys_utimensat, sys_utimensat_time32) +__SC_3264(__NR_utimensat, sys_utimensat_time32, sys_utimensat) /* kernel/acct.c */ #define __NR_acct 89 @@ -310,7 +310,7 @@ __SYSCALL(__NR_unshare, sys_unshare) /* kernel/futex.c */ #define __NR_futex 98 -__SC_COMP(__NR_futex, sys_futex, sys_futex_time32) +__SC_3264(__NR_futex, sys_futex_time32, sys_futex) #define __NR_set_robust_list 99 __SC_COMP(__NR_set_robust_list, sys_set_robust_list, \ compat_sys_set_robust_list) @@ -320,7 +320,7 @@ __SC_COMP(__NR_get_robust_list, sys_get_robust_list, \ /* kernel/hrtimer.c */ #define __NR_nanosleep 101 -__SC_COMP(__NR_nanosleep, sys_nanosleep, sys_nanosleep_time32) +__SC_3264(__NR_nanosleep, sys_nanosleep_time32, sys_nanosleep) /* kernel/itimer.c */ #define __NR_getitimer 102 @@ -342,22 +342,22 @@ __SYSCALL(__NR_delete_module, sys_delete_module) #define __NR_timer_create 107 __SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create) #define __NR_timer_gettime 108 -__SC_COMP(__NR_timer_gettime, sys_timer_gettime, sys_timer_gettime32) +__SC_3264(__NR_timer_gettime, sys_timer_gettime32, sys_timer_gettime) #define __NR_timer_getoverrun 109 __SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) #define __NR_timer_settime 110 -__SC_COMP(__NR_timer_settime, sys_timer_settime, sys_timer_settime32) +__SC_3264(__NR_timer_settime, sys_timer_settime32, sys_timer_settime) #define __NR_timer_delete 111 __SYSCALL(__NR_timer_delete, sys_timer_delete) #define __NR_clock_settime 112 -__SC_COMP(__NR_clock_settime, sys_clock_settime, sys_clock_settime32) +__SC_3264(__NR_clock_settime, sys_clock_settime32, sys_clock_settime) #define __NR_clock_gettime 113 -__SC_COMP(__NR_clock_gettime, sys_clock_gettime, sys_clock_gettime32) +__SC_3264(__NR_clock_gettime, sys_clock_gettime32, sys_clock_gettime) #define __NR_clock_getres 114 -__SC_COMP(__NR_clock_getres, sys_clock_getres, sys_clock_getres_time32) +__SC_3264(__NR_clock_getres, sys_clock_getres_time32, sys_clock_getres) #define __NR_clock_nanosleep 115 -__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \ - sys_clock_nanosleep_time32) +__SC_3264(__NR_clock_nanosleep, sys_clock_nanosleep_time32, \ + sys_clock_nanosleep) /* kernel/printk.c */ #define __NR_syslog 116 @@ -389,8 +389,8 @@ __SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) #define __NR_sched_get_priority_min 126 __SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) #define __NR_sched_rr_get_interval 127 -__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \ - sys_sched_rr_get_interval_time32) +__SC_3264(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32, \ + sys_sched_rr_get_interval) /* kernel/signal.c */ #define __NR_restart_syscall 128 @@ -412,8 +412,8 @@ __SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask) #define __NR_rt_sigpending 136 __SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending) #define __NR_rt_sigtimedwait 137 -__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \ - compat_sys_rt_sigtimedwait_time32) +__SC_COMP_3264(__NR_rt_sigtimedwait, sys_rt_sigtimedwait_time32, \ + sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32) #define __NR_rt_sigqueueinfo 138 __SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \ compat_sys_rt_sigqueueinfo) @@ -486,7 +486,7 @@ __SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday) #define __NR_settimeofday 170 __SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday) #define __NR_adjtimex 171 -__SC_COMP(__NR_adjtimex, sys_adjtimex, sys_adjtimex_time32) +__SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex) /* kernel/timer.c */ #define __NR_getpid 172 @@ -512,10 +512,10 @@ __SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open) #define __NR_mq_unlink 181 __SYSCALL(__NR_mq_unlink, sys_mq_unlink) #define __NR_mq_timedsend 182 -__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, sys_mq_timedsend_time32) +__SC_3264(__NR_mq_timedsend, sys_mq_timedsend_time32, sys_mq_timedsend) #define __NR_mq_timedreceive 183 -__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \ - sys_mq_timedreceive_time32) +__SC_3264(__NR_mq_timedreceive, sys_mq_timedreceive_time32, \ + sys_mq_timedreceive) #define __NR_mq_notify 184 __SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify) #define __NR_mq_getsetattr 185 @@ -659,7 +659,7 @@ __SYSCALL(__NR_perf_event_open, sys_perf_event_open) #define __NR_accept4 242 __SYSCALL(__NR_accept4, sys_accept4) #define __NR_recvmmsg 243 -__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg_time32) +__SC_COMP_3264(__NR_recvmmsg, sys_recvmmsg_time32, sys_recvmmsg, compat_sys_recvmmsg_time32) /* * Architectures may provide up to 16 syscalls of their own @@ -681,7 +681,7 @@ __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) __SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \ compat_sys_open_by_handle_at) #define __NR_clock_adjtime 266 -__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, sys_clock_adjtime32) +__SC_3264(__NR_clock_adjtime, sys_clock_adjtime32, sys_clock_adjtime) #define __NR_syncfs 267 __SYSCALL(__NR_syncfs, sys_syncfs) #define __NR_setns 268 @@ -735,7 +735,7 @@ __SYSCALL(__NR_pkey_free, sys_pkey_free) #define __NR_statx 291 __SYSCALL(__NR_statx, sys_statx) #define __NR_io_pgetevents 292 -__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) +__SC_COMP_3264(__NR_io_pgetevents, sys_io_pgetevents_time32, sys_io_pgetevents, compat_sys_io_pgetevents) #define __NR_rseq 293 __SYSCALL(__NR_rseq, sys_rseq) #define __NR_kexec_file_load 294 -- cgit v1.2.3 From c70a772fda11570ebddecbce1543a3fda008db4a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 7 Jan 2019 00:00:34 +0100 Subject: y2038: remove struct definition redirects We now use 64-bit time_t on all architectures, so the __kernel_timex, __kernel_timeval and __kernel_timespec redirects can be removed after having served their purpose. This makes it all much less confusing, as the __kernel_* types now always refer to the same layout based on 64-bit time_t across all 32-bit and 64-bit architectures. Signed-off-by: Arnd Bergmann --- include/linux/time64.h | 8 -------- include/linux/timex.h | 7 ------- include/uapi/linux/time.h | 4 ---- include/uapi/linux/timex.h | 2 -- 4 files changed, 21 deletions(-) (limited to 'include') diff --git a/include/linux/time64.h b/include/linux/time64.h index 05634afba0db..f38d382ffec1 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -7,14 +7,6 @@ typedef __s64 time64_t; typedef __u64 timeu64_t; -/* CONFIG_64BIT_TIME enables new 64 bit time_t syscalls in the compat path - * and 32-bit emulation. - */ -#ifndef CONFIG_64BIT_TIME -#define __kernel_timespec timespec -#define __kernel_itimerspec itimerspec -#endif - #include struct timespec64 { diff --git a/include/linux/timex.h b/include/linux/timex.h index 4aff9f0d1367..ce0859763670 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -53,13 +53,6 @@ #ifndef _LINUX_TIMEX_H #define _LINUX_TIMEX_H -/* CONFIG_64BIT_TIME enables new 64 bit time_t syscalls in the compat path - * and 32-bit emulation. - */ -#ifndef CONFIG_64BIT_TIME -#define __kernel_timex timex -#endif - #include #define ADJ_ADJTIME 0x8000 /* switch between adjtime/adjtimex modes */ diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index 6b56a2208be7..b03f8717c312 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -42,19 +42,15 @@ struct itimerval { struct timeval it_value; /* current value */ }; -#ifndef __kernel_timespec struct __kernel_timespec { __kernel_time64_t tv_sec; /* seconds */ long long tv_nsec; /* nanoseconds */ }; -#endif -#ifndef __kernel_itimerspec struct __kernel_itimerspec { struct __kernel_timespec it_interval; /* timer period */ struct __kernel_timespec it_value; /* timer expiration */ }; -#endif /* * legacy timeval structure, only embedded in structures that diff --git a/include/uapi/linux/timex.h b/include/uapi/linux/timex.h index a1c6b73016a5..9f517f9010bb 100644 --- a/include/uapi/linux/timex.h +++ b/include/uapi/linux/timex.h @@ -97,7 +97,6 @@ struct __kernel_timex_timeval { long long tv_usec; }; -#ifndef __kernel_timex struct __kernel_timex { unsigned int modes; /* mode selector */ int :32; /* pad */ @@ -131,7 +130,6 @@ struct __kernel_timex { int :32; int :32; int :32; int :32; int :32; int :32; int :32; }; -#endif /* * Mode codes (timex.mode) -- cgit v1.2.3 From 48166e6ea47d23984f0b481ca199250e1ce0730a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 10 Jan 2019 12:45:11 +0100 Subject: y2038: add 64-bit time_t syscalls to all 32-bit architectures This adds 21 new system calls on each ABI that has 32-bit time_t today. All of these have the exact same semantics as their existing counterparts, and the new ones all have macro names that end in 'time64' for clarification. This gets us to the point of being able to safely use a C library that has 64-bit time_t in user space. There are still a couple of loose ends to tie up in various areas of the code, but this is the big one, and should be entirely uncontroversial at this point. In particular, there are four system calls (getitimer, setitimer, waitid, and getrusage) that don't have a 64-bit counterpart yet, but these can all be safely implemented in the C library by wrapping around the existing system calls because the 32-bit time_t they pass only counts elapsed time, not time since the epoch. They will be dealt with later. Signed-off-by: Arnd Bergmann Acked-by: Heiko Carstens Acked-by: Geert Uytterhoeven Acked-by: Catalin Marinas --- arch/alpha/kernel/syscalls/syscall.tbl | 2 ++ arch/arm/tools/syscall.tbl | 21 ++++++++++++++ arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 41 +++++++++++++++++++++++++++ arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 20 +++++++++++++ arch/microblaze/kernel/syscalls/syscall.tbl | 21 ++++++++++++++ arch/mips/kernel/syscalls/syscall_n32.tbl | 21 ++++++++++++++ arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 20 +++++++++++++ arch/parisc/kernel/syscalls/syscall.tbl | 21 ++++++++++++++ arch/powerpc/kernel/syscalls/syscall.tbl | 20 +++++++++++++ arch/s390/kernel/syscalls/syscall.tbl | 20 +++++++++++++ arch/sh/kernel/syscalls/syscall.tbl | 20 +++++++++++++ arch/sparc/kernel/syscalls/syscall.tbl | 20 +++++++++++++ arch/x86/entry/syscalls/syscall_32.tbl | 20 +++++++++++++ arch/xtensa/kernel/syscalls/syscall.tbl | 21 ++++++++++++++ include/uapi/asm-generic/unistd.h | 44 ++++++++++++++++++++++++++++- scripts/checksyscalls.sh | 40 ++++++++++++++++++++++++++ 19 files changed, 374 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 340b88dd397e..63ed39cbd3bd 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -461,3 +461,5 @@ 530 common getegid sys_getegid 531 common geteuid sys_geteuid 532 common getppid sys_getppid +# all other architectures have common numbers for new syscall, alpha +# is the exception. diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index a96d9b5ee04e..9016f4081bb9 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -416,3 +416,24 @@ 399 common io_pgetevents sys_io_pgetevents_time32 400 common migrate_pages sys_migrate_pages 401 common kexec_file_load sys_kexec_file_load +# 402 is unused +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 2c30e6f145ff..d1dd93436e1e 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 402 +#define __NR_compat_syscalls 424 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 1ded82857161..5590f2623690 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -825,6 +825,47 @@ __SYSCALL(__NR_io_pgetevents, compat_sys_io_pgetevents) __SYSCALL(__NR_migrate_pages, compat_sys_migrate_pages) #define __NR_kexec_file_load 401 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) +/* 402 is unused */ +#define __NR_clock_gettime64 403 +__SYSCALL(__NR_clock_gettime64, sys_clock_gettime) +#define __NR_clock_settime64 404 +__SYSCALL(__NR_clock_settime64, sys_clock_settime) +#define __NR_clock_adjtime64 405 +__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime) +#define __NR_clock_getres_time64 406 +__SYSCALL(__NR_clock_getres_time64, sys_clock_getres) +#define __NR_clock_nanosleep_time64 407 +__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep) +#define __NR_timer_gettime64 408 +__SYSCALL(__NR_timer_gettime64, sys_timer_gettime) +#define __NR_timer_settime64 409 +__SYSCALL(__NR_timer_settime64, sys_timer_settime) +#define __NR_timerfd_gettime64 410 +__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime) +#define __NR_timerfd_settime64 411 +__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime) +#define __NR_utimensat_time64 412 +__SYSCALL(__NR_utimensat_time64, sys_utimensat) +#define __NR_pselect6_time64 413 +__SYSCALL(__NR_pselect6_time64, compat_sys_pselect6_time64) +#define __NR_ppoll_time64 414 +__SYSCALL(__NR_ppoll_time64, compat_sys_ppoll_time64) +#define __NR_io_pgetevents_time64 416 +__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +#define __NR_recvmmsg_time64 417 +__SYSCALL(__NR_recvmmsg_time64, compat_sys_recvmmsg_time64) +#define __NR_mq_timedsend_time64 418 +__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend) +#define __NR_mq_timedreceive_time64 419 +__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive) +#define __NR_semtimedop_time64 420 +__SYSCALL(__NR_semtimedop_time64, sys_semtimedop) +#define __NR_rt_sigtimedwait_time64 421 +__SYSCALL(__NR_rt_sigtimedwait_time64, compat_sys_rt_sigtimedwait_time64) +#define __NR_futex_time64 422 +__SYSCALL(__NR_futex_time64, sys_futex) +#define __NR_sched_rr_get_interval_time64 423 +__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 52319006de0d..ab9cda5f6136 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -343,3 +343,4 @@ 331 common pkey_alloc sys_pkey_alloc 332 common pkey_free sys_pkey_free 333 common rseq sys_rseq +# 334 through 423 are reserved to sync up with other architectures diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 253bd2a069bd..125c14178979 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -403,3 +403,23 @@ 400 common msgsnd sys_msgsnd 401 common msgrcv sys_msgrcv 402 common msgctl sys_msgctl +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 44a87649d681..8ee3a8c18498 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -408,3 +408,24 @@ 398 common statx sys_statx 399 common io_pgetevents sys_io_pgetevents_time32 400 common rseq sys_rseq +# 401 and 402 are unused +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 6d1e019817c8..15f4117900ee 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -341,3 +341,24 @@ 330 n32 statx sys_statx 331 n32 rseq sys_rseq 332 n32 io_pgetevents compat_sys_io_pgetevents +# 333 through 402 are unassigned to sync up with generic numbers +403 n32 clock_gettime64 sys_clock_gettime +404 n32 clock_settime64 sys_clock_settime +405 n32 clock_adjtime64 sys_clock_adjtime +406 n32 clock_getres_time64 sys_clock_getres +407 n32 clock_nanosleep_time64 sys_clock_nanosleep +408 n32 timer_gettime64 sys_timer_gettime +409 n32 timer_settime64 sys_timer_settime +410 n32 timerfd_gettime64 sys_timerfd_gettime +411 n32 timerfd_settime64 sys_timerfd_settime +412 n32 utimensat_time64 sys_utimensat +413 n32 pselect6_time64 compat_sys_pselect6_time64 +414 n32 ppoll_time64 compat_sys_ppoll_time64 +416 n32 io_pgetevents_time64 sys_io_pgetevents +417 n32 recvmmsg_time64 compat_sys_recvmmsg_time64 +418 n32 mq_timedsend_time64 sys_mq_timedsend +419 n32 mq_timedreceive_time64 sys_mq_timedreceive +420 n32 semtimedop_time64 sys_semtimedop +421 n32 rt_sigtimedwait_time64 compat_sys_rt_sigtimedwait_time64 +422 n32 futex_time64 sys_futex +423 n32 sched_rr_get_interval_time64 sys_sched_rr_get_interval diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index af0da757a7b2..c85502e67b44 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -337,3 +337,4 @@ 326 n64 statx sys_statx 327 n64 rseq sys_rseq 328 n64 io_pgetevents sys_io_pgetevents +# 329 through 423 are reserved to sync up with other architectures diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 54312c5b5343..2e063d0f837e 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -391,3 +391,23 @@ 400 o32 msgsnd sys_msgsnd compat_sys_msgsnd 401 o32 msgrcv sys_msgrcv compat_sys_msgrcv 402 o32 msgctl sys_msgctl compat_sys_msgctl +403 o32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 o32 clock_settime64 sys_clock_settime sys_clock_settime +405 o32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 o32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 o32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 o32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 o32 timer_settime64 sys_timer_settime sys_timer_settime +410 o32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 o32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 o32 utimensat_time64 sys_utimensat sys_utimensat +413 o32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 o32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 o32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +417 o32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 o32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 o32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 o32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 o32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 o32 futex_time64 sys_futex sys_futex +423 o32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 7eff3dc3d613..b26766c6647d 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -399,3 +399,24 @@ 352 common pkey_alloc sys_pkey_alloc 353 common pkey_free sys_pkey_free 354 common rseq sys_rseq +# 355 through 402 are unassigned to sync up with generic numbers +403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 32 clock_settime64 sys_clock_settime sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 32 timer_settime64 sys_timer_settime sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 500edbf9e8a6..b18abb0c3dae 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -485,3 +485,23 @@ 400 common msgsnd sys_msgsnd compat_sys_msgsnd 401 common msgrcv sys_msgrcv compat_sys_msgrcv 402 common msgctl sys_msgctl compat_sys_msgctl +403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 32 clock_settime64 sys_clock_settime sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 32 timer_settime64 sys_timer_settime sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 285201cf1f83..02579f95f391 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -406,3 +406,23 @@ 400 common msgsnd sys_msgsnd compat_sys_msgsnd 401 common msgrcv sys_msgrcv compat_sys_msgrcv 402 common msgctl sys_msgctl compat_sys_msgctl +403 32 clock_gettime64 - sys_clock_gettime +404 32 clock_settime64 - sys_clock_settime +405 32 clock_adjtime64 - sys_clock_adjtime +406 32 clock_getres_time64 - sys_clock_getres +407 32 clock_nanosleep_time64 - sys_clock_nanosleep +408 32 timer_gettime64 - sys_timer_gettime +409 32 timer_settime64 - sys_timer_settime +410 32 timerfd_gettime64 - sys_timerfd_gettime +411 32 timerfd_settime64 - sys_timerfd_settime +412 32 utimensat_time64 - sys_utimensat +413 32 pselect6_time64 - compat_sys_pselect6_time64 +414 32 ppoll_time64 - compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 - sys_io_pgetevents +417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 - sys_mq_timedsend +419 32 mq_timedreceive_time64 - sys_mq_timedreceive +420 32 semtimedop_time64 - sys_semtimedop +421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 - sys_futex +423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 06d768c3cc4c..bfda678576e4 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -406,3 +406,23 @@ 400 common msgsnd sys_msgsnd 401 common msgrcv sys_msgrcv 402 common msgctl sys_msgctl +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 99c40abd8878..b9a5a04b2d2c 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -449,3 +449,23 @@ 400 common msgsnd sys_msgsnd compat_sys_msgsnd 401 common msgrcv sys_msgrcv compat_sys_msgrcv 402 common msgctl sys_msgctl compat_sys_msgctl +403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 32 clock_settime64 sys_clock_settime sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 32 timer_settime64 sys_timer_settime sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 8c47c1191a53..955ab6a3b61f 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -409,3 +409,23 @@ 400 i386 msgsnd sys_msgsnd __ia32_compat_sys_msgsnd 401 i386 msgrcv sys_msgrcv __ia32_compat_sys_msgrcv 402 i386 msgctl sys_msgctl __ia32_compat_sys_msgctl +403 i386 clock_gettime64 sys_clock_gettime __ia32_sys_clock_gettime +404 i386 clock_settime64 sys_clock_settime __ia32_sys_clock_settime +405 i386 clock_adjtime64 sys_clock_adjtime __ia32_sys_clock_adjtime +406 i386 clock_getres_time64 sys_clock_getres __ia32_sys_clock_getres +407 i386 clock_nanosleep_time64 sys_clock_nanosleep __ia32_sys_clock_nanosleep +408 i386 timer_gettime64 sys_timer_gettime __ia32_sys_timer_gettime +409 i386 timer_settime64 sys_timer_settime __ia32_sys_timer_settime +410 i386 timerfd_gettime64 sys_timerfd_gettime __ia32_sys_timerfd_gettime +411 i386 timerfd_settime64 sys_timerfd_settime __ia32_sys_timerfd_settime +412 i386 utimensat_time64 sys_utimensat __ia32_sys_utimensat +413 i386 pselect6_time64 sys_pselect6 __ia32_compat_sys_pselect6_time64 +414 i386 ppoll_time64 sys_ppoll __ia32_compat_sys_ppoll_time64 +416 i386 io_pgetevents_time64 sys_io_pgetevents __ia32_sys_io_pgetevents +417 i386 recvmmsg_time64 sys_recvmmsg __ia32_compat_sys_recvmmsg_time64 +418 i386 mq_timedsend_time64 sys_mq_timedsend __ia32_sys_mq_timedsend +419 i386 mq_timedreceive_time64 sys_mq_timedreceive __ia32_sys_mq_timedreceive +420 i386 semtimedop_time64 sys_semtimedop __ia32_sys_semtimedop +421 i386 rt_sigtimedwait_time64 sys_rt_sigtimedwait __ia32_compat_sys_rt_sigtimedwait_time64 +422 i386 futex_time64 sys_futex __ia32_sys_futex +423 i386 sched_rr_get_interval_time64 sys_sched_rr_get_interval __ia32_sys_sched_rr_get_interval diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 482673389e21..6af49929de85 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -373,3 +373,24 @@ 350 common pkey_free sys_pkey_free 351 common statx sys_statx 352 common rseq sys_rseq +# 353 through 402 are unassigned to sync up with generic numbers +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index ab1831769030..acf9a07ab2ff 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -741,9 +741,51 @@ __SYSCALL(__NR_rseq, sys_rseq) #define __NR_kexec_file_load 294 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) /* 295 through 402 are unassigned to sync up with generic numbers, don't use */ +#if __BITS_PER_LONG == 32 +#define __NR_clock_gettime64 403 +__SYSCALL(__NR_clock_gettime64, sys_clock_gettime) +#define __NR_clock_settime64 404 +__SYSCALL(__NR_clock_settime64, sys_clock_settime) +#define __NR_clock_adjtime64 405 +__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime) +#define __NR_clock_getres_time64 406 +__SYSCALL(__NR_clock_getres_time64, sys_clock_getres) +#define __NR_clock_nanosleep_time64 407 +__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep) +#define __NR_timer_gettime64 408 +__SYSCALL(__NR_timer_gettime64, sys_timer_gettime) +#define __NR_timer_settime64 409 +__SYSCALL(__NR_timer_settime64, sys_timer_settime) +#define __NR_timerfd_gettime64 410 +__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime) +#define __NR_timerfd_settime64 411 +__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime) +#define __NR_utimensat_time64 412 +__SYSCALL(__NR_utimensat_time64, sys_utimensat) +#define __NR_pselect6_time64 413 +__SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) +#define __NR_ppoll_time64 414 +__SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) +#define __NR_io_pgetevents_time64 416 +__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +#define __NR_recvmmsg_time64 417 +__SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) +#define __NR_mq_timedsend_time64 418 +__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend) +#define __NR_mq_timedreceive_time64 419 +__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive) +#define __NR_semtimedop_time64 420 +__SYSCALL(__NR_semtimedop_time64, sys_semtimedop) +#define __NR_rt_sigtimedwait_time64 421 +__SC_COMP(__NR_rt_sigtimedwait_time64, sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time64) +#define __NR_futex_time64 422 +__SYSCALL(__NR_futex_time64, sys_futex) +#define __NR_sched_rr_get_interval_time64 423 +__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval) +#endif #undef __NR_syscalls -#define __NR_syscalls 295 +#define __NR_syscalls 424 /* * 32 bit systems traditionally used different diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh index cf931003395f..cc70a64fa81f 100755 --- a/scripts/checksyscalls.sh +++ b/scripts/checksyscalls.sh @@ -84,6 +84,26 @@ cat << EOF #define __IGNORE_statfs64 #define __IGNORE_llseek #define __IGNORE_mmap2 +#define __IGNORE_clock_gettime64 +#define __IGNORE_clock_settime64 +#define __IGNORE_clock_adjtime64 +#define __IGNORE_clock_getres_time64 +#define __IGNORE_clock_nanosleep_time64 +#define __IGNORE_timer_gettime64 +#define __IGNORE_timer_settime64 +#define __IGNORE_timerfd_gettime64 +#define __IGNORE_timerfd_settime64 +#define __IGNORE_utimensat_time64 +#define __IGNORE_pselect6_time64 +#define __IGNORE_ppoll_time64 +#define __IGNORE_io_pgetevents_time64 +#define __IGNORE_recvmmsg_time64 +#define __IGNORE_mq_timedsend_time64 +#define __IGNORE_mq_timedreceive_time64 +#define __IGNORE_semtimedop_time64 +#define __IGNORE_rt_sigtimedwait_time64 +#define __IGNORE_futex_time64 +#define __IGNORE_sched_rr_get_interval_time64 #else #define __IGNORE_sendfile #define __IGNORE_ftruncate @@ -98,6 +118,26 @@ cat << EOF #define __IGNORE_statfs #define __IGNORE_lseek #define __IGNORE_mmap +#define __IGNORE_clock_gettime +#define __IGNORE_clock_settime +#define __IGNORE_clock_adjtime +#define __IGNORE_clock_getres +#define __IGNORE_clock_nanosleep +#define __IGNORE_timer_gettime +#define __IGNORE_timer_settime +#define __IGNORE_timerfd_gettime +#define __IGNORE_timerfd_settime +#define __IGNORE_utimensat +#define __IGNORE_pselect6 +#define __IGNORE_ppoll +#define __IGNORE_io_pgetevents +#define __IGNORE_recvmmsg +#define __IGNORE_mq_timedsend +#define __IGNORE_mq_timedreceiv +#define __IGNORE_semtimedop +#define __IGNORE_rt_sigtimedwait +#define __IGNORE_futex +#define __IGNORE_sched_rr_get_interval #endif /* i386-specific or historical system calls */ -- cgit v1.2.3 From a4f342b9607d8c2034d3135cbbb11b4028be3678 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 4 Feb 2019 11:09:48 +0000 Subject: PM / OPP: Introduce a power estimation helper The Energy Model (EM) framework provides an API to let drivers register the active power of CPUs. The drivers are expected to provide a callback method which estimates the power consumed by a CPU at each available performance levels. How exactly this should be implemented, however, depends on the platform. On some systems, PM_OPP knows the voltage and frequency at which CPUs can run. When coupled with the CPU 'capacitance' (as provided by the 'dynamic-power-coefficient' devicetree binding), it is possible to estimate the dynamic power consumption of a CPU as P = C * V^2 * f, with C its capacitance and V and f respectively the voltage and frequency of the OPP. The Intelligent Power Allocator (IPA) thermal governor already implements that estimation method, in the thermal framework. However, this power estimation method can be applied to any platform where all the parameters are known (C, V and f), and not only those suffering thermal issues. As such, the code implementing this feature can be re-used to also populate the EM framework now used by EAS. As a first step, introduce in PM_OPP a helper function which CPUFreq drivers can use to register into the EM framework. This duplicates the power estimation done in IPA until it can be migrated to using the EM framework. This will be done later, once the EM framework has support for at least all platforms currently supported by IPA. Signed-off-by: Quentin Perret Tested-by: Matthias Kaehlcke Reviewed-by: Matthias Kaehlcke Signed-off-by: Viresh Kumar --- drivers/opp/of.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_opp.h | 6 +++ 2 files changed, 105 insertions(+) (limited to 'include') diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 06f0f632ec47..cd58959e5158 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "opp.h" @@ -1047,3 +1048,101 @@ struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp) return of_node_get(opp->np); } EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node); + +/* + * Callback function provided to the Energy Model framework upon registration. + * This computes the power estimated by @CPU at @kHz if it is the frequency + * of an existing OPP, or at the frequency of the first OPP above @kHz otherwise + * (see dev_pm_opp_find_freq_ceil()). This function updates @kHz to the ceiled + * frequency and @mW to the associated power. The power is estimated as + * P = C * V^2 * f with C being the CPU's capacitance and V and f respectively + * the voltage and frequency of the OPP. + * + * Returns -ENODEV if the CPU device cannot be found, -EINVAL if the power + * calculation failed because of missing parameters, 0 otherwise. + */ +static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz, + int cpu) +{ + struct device *cpu_dev; + struct dev_pm_opp *opp; + struct device_node *np; + unsigned long mV, Hz; + u32 cap; + u64 tmp; + int ret; + + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return -ENODEV; + + np = of_node_get(cpu_dev->of_node); + if (!np) + return -EINVAL; + + ret = of_property_read_u32(np, "dynamic-power-coefficient", &cap); + of_node_put(np); + if (ret) + return -EINVAL; + + Hz = *kHz * 1000; + opp = dev_pm_opp_find_freq_ceil(cpu_dev, &Hz); + if (IS_ERR(opp)) + return -EINVAL; + + mV = dev_pm_opp_get_voltage(opp) / 1000; + dev_pm_opp_put(opp); + if (!mV) + return -EINVAL; + + tmp = (u64)cap * mV * mV * (Hz / 1000000); + do_div(tmp, 1000000000); + + *mW = (unsigned long)tmp; + *kHz = Hz / 1000; + + return 0; +} + +/** + * dev_pm_opp_of_register_em() - Attempt to register an Energy Model + * @cpus : CPUs for which an Energy Model has to be registered + * + * This checks whether the "dynamic-power-coefficient" devicetree property has + * been specified, and tries to register an Energy Model with it if it has. + */ +void dev_pm_opp_of_register_em(struct cpumask *cpus) +{ + struct em_data_callback em_cb = EM_DATA_CB(_get_cpu_power); + int ret, nr_opp, cpu = cpumask_first(cpus); + struct device *cpu_dev; + struct device_node *np; + u32 cap; + + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return; + + nr_opp = dev_pm_opp_get_opp_count(cpu_dev); + if (nr_opp <= 0) + return; + + np = of_node_get(cpu_dev->of_node); + if (!np) + return; + + /* + * Register an EM only if the 'dynamic-power-coefficient' property is + * set in devicetree. It is assumed the voltage values are known if that + * property is set since it is useless otherwise. If voltages are not + * known, just let the EM registration fail with an error to alert the + * user about the inconsistent configuration. + */ + ret = of_property_read_u32(np, "dynamic-power-coefficient", &cap); + of_node_put(np); + if (ret || !cap) + return; + + em_register_perf_domain(cpus, nr_opp, &em_cb); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_of_register_em); diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 0a2a88e5a383..1470c57933cf 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -322,6 +322,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpuma struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); int of_get_required_opp_performance_state(struct device_node *np, int index); +void dev_pm_opp_of_register_em(struct cpumask *cpus); #else static inline int dev_pm_opp_of_add_table(struct device *dev) { @@ -360,6 +361,11 @@ static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp) { return NULL; } + +static inline void dev_pm_opp_of_register_em(struct cpumask *cpus) +{ +} + static inline int of_get_required_opp_performance_state(struct device_node *np, int index) { return -ENOTSUPP; -- cgit v1.2.3 From 752b5da2359fee342d5264e2c10352daf5b9a199 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 21 Jan 2019 16:45:46 +0100 Subject: phy: dphy: Remove unused header The videomode.h header inclusion is an artifact from the patches development, remove it. Suggested-by: Sakari Ailus Acked-by: Sakari Ailus Signed-off-by: Maxime Ripard Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy-mipi-dphy.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/phy/phy-mipi-dphy.h b/include/linux/phy/phy-mipi-dphy.h index c08aacc0ac35..9cf97cd1d303 100644 --- a/include/linux/phy/phy-mipi-dphy.h +++ b/include/linux/phy/phy-mipi-dphy.h @@ -6,8 +6,6 @@ #ifndef __PHY_MIPI_DPHY_H_ #define __PHY_MIPI_DPHY_H_ -#include