From a5aa5ce300597224ec76dacc8e63ba3ad7a18bbd Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sat, 20 Feb 2021 15:17:12 -0800 Subject: smp: Inline on_each_cpu_cond() and on_each_cpu() Simplify the code and avoid having an additional function on the stack by inlining on_each_cpu_cond() and on_each_cpu(). Suggested-by: Peter Zijlstra Signed-off-by: Nadav Amit [ Minor edits. ] Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210220231712.2475218-10-namit@vmware.com --- include/linux/smp.h | 50 ++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 36 insertions(+), 14 deletions(-) (limited to 'include/linux/smp.h') diff --git a/include/linux/smp.h b/include/linux/smp.h index 70c6f6284dcf..84a0b4828f66 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -50,30 +50,52 @@ extern unsigned int total_cpus; int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, int wait); +void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait, const struct cpumask *mask); + +int smp_call_function_single_async(int cpu, call_single_data_t *csd); + /* * Call a function on all processors */ -void on_each_cpu(smp_call_func_t func, void *info, int wait); +static inline void on_each_cpu(smp_call_func_t func, void *info, int wait) +{ + on_each_cpu_cond_mask(NULL, func, info, wait, cpu_online_mask); +} -/* - * Call a function on processors specified by mask, which might include - * the local one. +/** + * on_each_cpu_mask(): Run a function on processors specified by + * cpumask, which may include the local processor. + * @mask: The set of cpus to run on (only runs on online subset). + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. + * + * If @wait is true, then returns once @func has returned. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. The + * exception is that it may be used during early boot while + * early_boot_irqs_disabled is set. */ -void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, - void *info, bool wait); +static inline void on_each_cpu_mask(const struct cpumask *mask, + smp_call_func_t func, void *info, bool wait) +{ + on_each_cpu_cond_mask(NULL, func, info, wait, mask); +} /* * Call a function on each processor for which the supplied function * cond_func returns a positive value. This may include the local - * processor. + * processor. May be used during early boot while early_boot_irqs_disabled is + * set. Use local_irq_save/restore() instead of local_irq_disable/enable(). */ -void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, - void *info, bool wait); - -void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, - void *info, bool wait, const struct cpumask *mask); - -int smp_call_function_single_async(int cpu, call_single_data_t *csd); +static inline void on_each_cpu_cond(smp_cond_func_t cond_func, + smp_call_func_t func, void *info, bool wait) +{ + on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask); +} #ifdef CONFIG_SMP -- cgit v1.2.3 From 1139aeb1c521eb4a050920ce6c64c36c4f2a3ab7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 5 May 2021 23:12:42 +0200 Subject: smp: Fix smp_call_function_single_async prototype As of commit 966a967116e6 ("smp: Avoid using two cache lines for struct call_single_data"), the smp code prefers 32-byte aligned call_single_data objects for performance reasons, but the block layer includes an instance of this structure in the main 'struct request' that is more senstive to size than to performance here, see 4ccafe032005 ("block: unalign call_single_data in struct request"). The result is a violation of the calling conventions that clang correctly points out: block/blk-mq.c:630:39: warning: passing 8-byte aligned argument to 32-byte aligned parameter 2 of 'smp_call_function_single_async' may result in an unaligned pointer access [-Walign-mismatch] smp_call_function_single_async(cpu, &rq->csd); It does seem that the usage of the call_single_data without cache line alignment should still be allowed by the smp code, so just change the function prototype so it accepts both, but leave the default alignment unchanged for the other users. This seems better to me than adding a local hack to shut up an otherwise correct warning in the caller. Signed-off-by: Arnd Bergmann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Jens Axboe Link: https://lkml.kernel.org/r/20210505211300.3174456-1-arnd@kernel.org --- include/linux/smp.h | 2 +- kernel/smp.c | 26 +++++++++++++------------- kernel/up.c | 2 +- 3 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux/smp.h') diff --git a/include/linux/smp.h b/include/linux/smp.h index 84a0b4828f66..f0d3ef654207 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -53,7 +53,7 @@ int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask); -int smp_call_function_single_async(int cpu, call_single_data_t *csd); +int smp_call_function_single_async(int cpu, struct __call_single_data *csd); /* * Call a function on all processors diff --git a/kernel/smp.c b/kernel/smp.c index e21074900006..52bf159ec400 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -211,7 +211,7 @@ static u64 cfd_seq_inc(unsigned int src, unsigned int dst, unsigned int type) } while (0) /* Record current CSD work for current CPU, NULL to erase. */ -static void __csd_lock_record(call_single_data_t *csd) +static void __csd_lock_record(struct __call_single_data *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ @@ -226,13 +226,13 @@ static void __csd_lock_record(call_single_data_t *csd) /* Or before unlock, as the case may be. */ } -static __always_inline void csd_lock_record(call_single_data_t *csd) +static __always_inline void csd_lock_record(struct __call_single_data *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) __csd_lock_record(csd); } -static int csd_lock_wait_getcpu(call_single_data_t *csd) +static int csd_lock_wait_getcpu(struct __call_single_data *csd) { unsigned int csd_type; @@ -282,7 +282,7 @@ static const char *csd_lock_get_type(unsigned int type) return (type >= ARRAY_SIZE(seq_type)) ? "?" : seq_type[type]; } -static void csd_lock_print_extended(call_single_data_t *csd, int cpu) +static void csd_lock_print_extended(struct __call_single_data *csd, int cpu) { struct cfd_seq_local *seq = &per_cpu(cfd_seq_local, cpu); unsigned int srccpu = csd->node.src; @@ -321,7 +321,7 @@ static void csd_lock_print_extended(call_single_data_t *csd, int cpu) * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ -static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id) +static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *ts1, int *bug_id) { int cpu = -1; int cpux; @@ -387,7 +387,7 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ -static void __csd_lock_wait(call_single_data_t *csd) +static void __csd_lock_wait(struct __call_single_data *csd) { int bug_id = 0; u64 ts0, ts1; @@ -401,7 +401,7 @@ static void __csd_lock_wait(call_single_data_t *csd) smp_acquire__after_ctrl_dep(); } -static __always_inline void csd_lock_wait(call_single_data_t *csd) +static __always_inline void csd_lock_wait(struct __call_single_data *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) { __csd_lock_wait(csd); @@ -431,17 +431,17 @@ static void __smp_call_single_queue_debug(int cpu, struct llist_node *node) #else #define cfd_seq_store(var, src, dst, type) -static void csd_lock_record(call_single_data_t *csd) +static void csd_lock_record(struct __call_single_data *csd) { } -static __always_inline void csd_lock_wait(call_single_data_t *csd) +static __always_inline void csd_lock_wait(struct __call_single_data *csd) { smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #endif -static __always_inline void csd_lock(call_single_data_t *csd) +static __always_inline void csd_lock(struct __call_single_data *csd) { csd_lock_wait(csd); csd->node.u_flags |= CSD_FLAG_LOCK; @@ -454,7 +454,7 @@ static __always_inline void csd_lock(call_single_data_t *csd) smp_wmb(); } -static __always_inline void csd_unlock(call_single_data_t *csd) +static __always_inline void csd_unlock(struct __call_single_data *csd) { WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK)); @@ -501,7 +501,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ -static int generic_exec_single(int cpu, call_single_data_t *csd) +static int generic_exec_single(int cpu, struct __call_single_data *csd) { if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; @@ -784,7 +784,7 @@ EXPORT_SYMBOL(smp_call_function_single); * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. */ -int smp_call_function_single_async(int cpu, call_single_data_t *csd) +int smp_call_function_single_async(int cpu, struct __call_single_data *csd) { int err = 0; diff --git a/kernel/up.c b/kernel/up.c index bf20b4a9af60..c7321307923a 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -25,7 +25,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, } EXPORT_SYMBOL(smp_call_function_single); -int smp_call_function_single_async(int cpu, call_single_data_t *csd) +int smp_call_function_single_async(int cpu, struct __call_single_data *csd) { unsigned long flags; -- cgit v1.2.3 From 6f1f942cd5fbbe308f912fc84e3f10fbc8113a68 Mon Sep 17 00:00:00 2001 From: He Ying Date: Thu, 6 May 2021 18:04:57 -0700 Subject: smp: kernel/panic.c - silence warnings We found these warnings in kernel/panic.c by using sparse tool: warning: symbol 'panic_smp_self_stop' was not declared. warning: symbol 'nmi_panic_self_stop' was not declared. warning: symbol 'crash_smp_send_stop' was not declared. To avoid them, add declarations for these three functions in include/linux/smp.h. Link: https://lkml.kernel.org/r/20210316084150.75201-1-heying24@huawei.com Signed-off-by: He Ying Reported-by: Hulk Robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/smp.h') diff --git a/include/linux/smp.h b/include/linux/smp.h index 84a0b4828f66..669e35c03be2 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -55,6 +55,14 @@ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, int smp_call_function_single_async(int cpu, call_single_data_t *csd); +/* + * Cpus stopping functions in panic. All have default weak definitions. + * Architecture-dependent code may override them. + */ +void panic_smp_self_stop(void); +void nmi_panic_self_stop(struct pt_regs *regs); +void crash_smp_send_stop(void); + /* * Call a function on all processors */ -- cgit v1.2.3