From 2357672c54c3f748f675446f8eba8b0432b1e7e2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:49 +0530 Subject: bpf: Introduce BPF support for kernel module function calls This change adds support on the kernel side to allow for BPF programs to call kernel module functions. Userspace will prepare an array of module BTF fds that is passed in during BPF_PROG_LOAD using fd_array parameter. In the kernel, the module BTFs are placed in the auxilliary struct for bpf_prog, and loaded as needed. The verifier then uses insn->off to index into the fd_array. insn->off 0 is reserved for vmlinux BTF (for backwards compat), so userspace must use an fd_array index > 0 for module kfunc support. kfunc_btf_tab is sorted based on offset in an array, and each offset corresponds to one descriptor, with a max limit up to 256 such module BTFs. We also change existing kfunc_tab to distinguish each element based on imm, off pair as each such call will now be distinct. Another change is to check_kfunc_call callback, which now include a struct module * pointer, this is to be used in later patch such that the kfunc_id and module pointer are matched for dynamically registered BTF sets from loadable modules, so that same kfunc_id in two modules doesn't lead to check_kfunc_call succeeding. For the duration of the check_kfunc_call, the reference to struct module exists, as it returns the pointer stored in kfunc_btf_tab. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-2-memxor@gmail.com --- include/linux/bpf.h | 8 +++++--- include/linux/bpf_verifier.h | 2 ++ 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1c7fd7c4c6d3..d604c8251d88 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -513,7 +513,7 @@ struct bpf_verifier_ops { const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); - bool (*check_kfunc_call)(u32 kfunc_btf_id); + bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner); }; struct bpf_prog_offload_ops { @@ -877,6 +877,7 @@ struct bpf_prog_aux { void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; struct bpf_kfunc_desc_tab *kfunc_tab; + struct bpf_kfunc_btf_tab *kfunc_btf_tab; u32 size_poke_tab; struct bpf_ksym ksym; const struct bpf_prog_ops *ops; @@ -1639,7 +1640,7 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id); +bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1860,7 +1861,8 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, return -ENOTSUPP; } -static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id) +static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, + struct module *owner) { return false; } diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5424124dbe36..c8a78e830fca 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -527,5 +527,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, const struct bpf_prog *tgt_prog, u32 btf_id, struct bpf_attach_target_info *tgt_info); +void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); + #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From 14f267d95fe4b08831a022c8e15a2eb8991edbf6 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:51 +0530 Subject: bpf: btf: Introduce helpers for dynamic BTF set registration This adds helpers for registering btf_id_set from modules and the bpf_check_mod_kfunc_call callback that can be used to look them up. With in kernel sets, the way this is supposed to work is, in kernel callback looks up within the in-kernel kfunc whitelist, and then defers to the dynamic BTF set lookup if it doesn't find the BTF id. If there is no in-kernel BTF id set, this callback can be used directly. Also fix includes for btf.h and bpfptr.h so that they can included in isolation. This is in preparation for their usage in tcp_bbr, tcp_cubic and tcp_dctcp modules in the next patch. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-4-memxor@gmail.com --- include/linux/bpfptr.h | 1 + include/linux/btf.h | 36 ++++++++++++++++++++++++++++++++++ kernel/bpf/btf.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 89 insertions(+) (limited to 'include') diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h index 546e27fc6d46..46e1757d06a3 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -3,6 +3,7 @@ #ifndef _LINUX_BPFPTR_H #define _LINUX_BPFPTR_H +#include #include typedef sockptr_t bpfptr_t; diff --git a/include/linux/btf.h b/include/linux/btf.h index 214fde93214b..6c4c61d821d7 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -5,6 +5,7 @@ #define _LINUX_BTF_H 1 #include +#include #include #include @@ -238,4 +239,39 @@ static inline const char *btf_name_by_offset(const struct btf *btf, } #endif +struct kfunc_btf_id_set { + struct list_head list; + struct btf_id_set *set; + struct module *owner; +}; + +struct kfunc_btf_id_list; + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES +void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s); +void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s); +bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, + struct module *owner); +#else +static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ +} +static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ +} +static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, + u32 kfunc_id, struct module *owner) +{ + return false; +} +#endif + +#define DEFINE_KFUNC_BTF_ID_SET(set, name) \ + struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ + THIS_MODULE } + #endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index c3d605b22473..62cbeb4951eb 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6343,3 +6343,55 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { }; BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) + +/* BTF ID set registration API for modules */ + +struct kfunc_btf_id_list { + struct list_head list; + struct mutex mutex; +}; + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + +void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ + mutex_lock(&l->mutex); + list_add(&s->list, &l->list); + mutex_unlock(&l->mutex); +} +EXPORT_SYMBOL_GPL(register_kfunc_btf_id_set); + +void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ + mutex_lock(&l->mutex); + list_del_init(&s->list); + mutex_unlock(&l->mutex); +} +EXPORT_SYMBOL_GPL(unregister_kfunc_btf_id_set); + +bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, + struct module *owner) +{ + struct kfunc_btf_id_set *s; + + if (!owner) + return false; + mutex_lock(&klist->mutex); + list_for_each_entry(s, &klist->list, list) { + if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) { + mutex_unlock(&klist->mutex); + return true; + } + } + mutex_unlock(&klist->mutex); + return false; +} + +#endif + +#define DEFINE_KFUNC_BTF_ID_LIST(name) \ + struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ + __MUTEX_INITIALIZER(name.mutex) }; \ + EXPORT_SYMBOL_GPL(name) -- cgit v1.2.3 From 0e32dfc80bae53b05e9eda7eaf259f30ab9ba43a Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:53 +0530 Subject: bpf: Enable TCP congestion control kfunc from modules This commit moves BTF ID lookup into the newly added registration helper, in a way that the bbr, cubic, and dctcp implementation set up their sets in the bpf_tcp_ca kfunc_btf_set list, while the ones not dependent on modules are looked up from the wrapper function. This lifts the restriction for them to be compiled as built in objects, and can be loaded as modules if required. Also modify Makefile.modfinal to call resolve_btfids for each module. Note that since kernel kfunc_ids never overlap with module kfunc_ids, we only match the owner for module btf id sets. See following commits for background on use of: CONFIG_X86 ifdef: 569c484f9995 (bpf: Limit static tcp-cc functions in the .BTF_ids list to x86) CONFIG_DYNAMIC_FTRACE ifdef: 7aae231ac93b (bpf: tcp: Limit calling some tcp cc functions to CONFIG_DYNAMIC_FTRACE) Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-6-memxor@gmail.com --- include/linux/btf.h | 2 ++ kernel/bpf/btf.c | 2 ++ net/ipv4/bpf_tcp_ca.c | 34 +++------------------------------- net/ipv4/tcp_bbr.c | 28 +++++++++++++++++++++++++++- net/ipv4/tcp_cubic.c | 26 +++++++++++++++++++++++++- net/ipv4/tcp_dctcp.c | 26 +++++++++++++++++++++++++- scripts/Makefile.modfinal | 1 + 7 files changed, 85 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index 6c4c61d821d7..1d56cd2bb362 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -274,4 +274,6 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ THIS_MODULE } +extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; + #endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 62cbeb4951eb..1460dff3c154 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6395,3 +6395,5 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ __MUTEX_INITIALIZER(name.mutex) }; \ EXPORT_SYMBOL_GPL(name) + +DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index b3afd3361f34..57709ac09fb2 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -223,41 +223,13 @@ BTF_ID(func, tcp_reno_cong_avoid) BTF_ID(func, tcp_reno_undo_cwnd) BTF_ID(func, tcp_slow_start) BTF_ID(func, tcp_cong_avoid_ai) -#ifdef CONFIG_X86 -#ifdef CONFIG_DYNAMIC_FTRACE -#if IS_BUILTIN(CONFIG_TCP_CONG_CUBIC) -BTF_ID(func, cubictcp_init) -BTF_ID(func, cubictcp_recalc_ssthresh) -BTF_ID(func, cubictcp_cong_avoid) -BTF_ID(func, cubictcp_state) -BTF_ID(func, cubictcp_cwnd_event) -BTF_ID(func, cubictcp_acked) -#endif -#if IS_BUILTIN(CONFIG_TCP_CONG_DCTCP) -BTF_ID(func, dctcp_init) -BTF_ID(func, dctcp_update_alpha) -BTF_ID(func, dctcp_cwnd_event) -BTF_ID(func, dctcp_ssthresh) -BTF_ID(func, dctcp_cwnd_undo) -BTF_ID(func, dctcp_state) -#endif -#if IS_BUILTIN(CONFIG_TCP_CONG_BBR) -BTF_ID(func, bbr_init) -BTF_ID(func, bbr_main) -BTF_ID(func, bbr_sndbuf_expand) -BTF_ID(func, bbr_undo_cwnd) -BTF_ID(func, bbr_cwnd_event) -BTF_ID(func, bbr_ssthresh) -BTF_ID(func, bbr_min_tso_segs) -BTF_ID(func, bbr_set_state) -#endif -#endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_X86 */ BTF_SET_END(bpf_tcp_ca_kfunc_ids) static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id, struct module *owner) { - return btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id); + if (btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id)) + return true; + return bpf_check_mod_kfunc_call(&bpf_tcp_ca_kfunc_list, kfunc_btf_id, owner); } static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = { diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6274462b86b4..ec5550089b4d 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -56,6 +56,8 @@ * otherwise TCP stack falls back to an internal pacing using one high * resolution timer per TCP socket and may use more resources. */ +#include +#include #include #include #include @@ -1152,14 +1154,38 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .set_state = bbr_set_state, }; +BTF_SET_START(tcp_bbr_kfunc_ids) +#ifdef CONFIG_X86 +#ifdef CONFIG_DYNAMIC_FTRACE +BTF_ID(func, bbr_init) +BTF_ID(func, bbr_main) +BTF_ID(func, bbr_sndbuf_expand) +BTF_ID(func, bbr_undo_cwnd) +BTF_ID(func, bbr_cwnd_event) +BTF_ID(func, bbr_ssthresh) +BTF_ID(func, bbr_min_tso_segs) +BTF_ID(func, bbr_set_state) +#endif +#endif +BTF_SET_END(tcp_bbr_kfunc_ids) + +static DEFINE_KFUNC_BTF_ID_SET(&tcp_bbr_kfunc_ids, tcp_bbr_kfunc_btf_set); + static int __init bbr_register(void) { + int ret; + BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); - return tcp_register_congestion_control(&tcp_bbr_cong_ops); + ret = tcp_register_congestion_control(&tcp_bbr_cong_ops); + if (ret) + return ret; + register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set); + return 0; } static void __exit bbr_unregister(void) { + unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set); tcp_unregister_congestion_control(&tcp_bbr_cong_ops); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 4a30deaa9a37..5e9d9c51164c 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -25,6 +25,8 @@ */ #include +#include +#include #include #include #include @@ -482,8 +484,25 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .name = "cubic", }; +BTF_SET_START(tcp_cubic_kfunc_ids) +#ifdef CONFIG_X86 +#ifdef CONFIG_DYNAMIC_FTRACE +BTF_ID(func, cubictcp_init) +BTF_ID(func, cubictcp_recalc_ssthresh) +BTF_ID(func, cubictcp_cong_avoid) +BTF_ID(func, cubictcp_state) +BTF_ID(func, cubictcp_cwnd_event) +BTF_ID(func, cubictcp_acked) +#endif +#endif +BTF_SET_END(tcp_cubic_kfunc_ids) + +static DEFINE_KFUNC_BTF_ID_SET(&tcp_cubic_kfunc_ids, tcp_cubic_kfunc_btf_set); + static int __init cubictcp_register(void) { + int ret; + BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); /* Precompute a bunch of the scaling factors that are used per-packet @@ -514,11 +533,16 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - return tcp_register_congestion_control(&cubictcp); + ret = tcp_register_congestion_control(&cubictcp); + if (ret) + return ret; + register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set); + return 0; } static void __exit cubictcp_unregister(void) { + unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set); tcp_unregister_congestion_control(&cubictcp); } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 79f705450c16..0d7ab3cc7b61 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -36,6 +36,8 @@ * Glenn Judd */ +#include +#include #include #include #include @@ -236,14 +238,36 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = { .name = "dctcp-reno", }; +BTF_SET_START(tcp_dctcp_kfunc_ids) +#ifdef CONFIG_X86 +#ifdef CONFIG_DYNAMIC_FTRACE +BTF_ID(func, dctcp_init) +BTF_ID(func, dctcp_update_alpha) +BTF_ID(func, dctcp_cwnd_event) +BTF_ID(func, dctcp_ssthresh) +BTF_ID(func, dctcp_cwnd_undo) +BTF_ID(func, dctcp_state) +#endif +#endif +BTF_SET_END(tcp_dctcp_kfunc_ids) + +static DEFINE_KFUNC_BTF_ID_SET(&tcp_dctcp_kfunc_ids, tcp_dctcp_kfunc_btf_set); + static int __init dctcp_register(void) { + int ret; + BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE); - return tcp_register_congestion_control(&dctcp); + ret = tcp_register_congestion_control(&dctcp); + if (ret) + return ret; + register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set); + return 0; } static void __exit dctcp_unregister(void) { + unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set); tcp_unregister_congestion_control(&dctcp); } diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index ff805777431c..1fb45b011e4b 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -41,6 +41,7 @@ quiet_cmd_btf_ko = BTF [M] $@ cmd_btf_ko = \ if [ -f vmlinux ]; then \ LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J --btf_base vmlinux $@; \ + $(RESOLVE_BTFIDS) -b vmlinux $@; \ else \ printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ fi; -- cgit v1.2.3 From c48e51c8b07aba8a18125221cb67a40cb1256bf2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:57 +0530 Subject: bpf: selftests: Add selftests for module kfunc support This adds selftests that tests the success and failure path for modules kfuncs (in presence of invalid kfunc calls) for both libbpf and gen_loader. It also adds a prog_test kfunc_btf_id_list so that we can add module BTF ID set from bpf_testmod. This also introduces a couple of test cases to verifier selftests for validating whether we get an error or not depending on if invalid kfunc call remains after elimination of unreachable instructions. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-10-memxor@gmail.com --- include/linux/btf.h | 1 + kernel/bpf/btf.c | 1 + net/bpf/test_run.c | 5 ++- tools/testing/selftests/bpf/Makefile | 7 ++-- .../selftests/bpf/bpf_testmod/bpf_testmod.c | 23 ++++++++++- .../selftests/bpf/prog_tests/ksyms_module.c | 29 +++++++------- .../selftests/bpf/prog_tests/ksyms_module_libbpf.c | 28 +++++++++++++ .../selftests/bpf/progs/test_ksyms_module.c | 46 ++++++++++++++++------ tools/testing/selftests/bpf/verifier/calls.c | 23 +++++++++++ 9 files changed, 132 insertions(+), 31 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index 1d56cd2bb362..203eef993d76 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -275,5 +275,6 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, THIS_MODULE } extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; +extern struct kfunc_btf_id_list prog_test_kfunc_list; #endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1460dff3c154..2ebffb9f57eb 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6397,3 +6397,4 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, EXPORT_SYMBOL_GPL(name) DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); +DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index b1f6f5237de6..529608784aa8 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -2,6 +2,7 @@ /* Copyright (c) 2017 Facebook */ #include +#include #include #include #include @@ -243,7 +244,9 @@ BTF_SET_END(test_sk_kfunc_ids) bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner) { - return btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id); + if (btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id)) + return true; + return bpf_check_mod_kfunc_call(&prog_test_kfunc_list, kfunc_id, owner); } static void *bpf_test_init(const union bpf_attr *kattr, u32 size, diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 5a94d0900d1b..c5c9a9f50d8d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -315,8 +315,9 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ linked_vars.skel.h linked_maps.skel.h LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ - test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c \ - trace_vprintk.c + test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c +# Generate both light skeleton and libbpf skeleton for these +LSKELS_EXTRA := test_ksyms_module.c SKEL_BLACKLIST += $$(LSKELS) test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o @@ -346,7 +347,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS) TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \ $$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\ $$(TRUNNER_BPF_SRCS))) -TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS)) +TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS) $$(LSKELS_EXTRA)) TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS)) TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 50fc5561110a..b892948dc134 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ +#include +#include #include #include #include @@ -13,6 +15,12 @@ DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123; +noinline void +bpf_testmod_test_mod_kfunc(int i) +{ + *(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i; +} + noinline int bpf_testmod_loop_test(int n) { int i, sum = 0; @@ -71,13 +79,26 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .write = bpf_testmod_test_write, }; +BTF_SET_START(bpf_testmod_kfunc_ids) +BTF_ID(func, bpf_testmod_test_mod_kfunc) +BTF_SET_END(bpf_testmod_kfunc_ids) + +static DEFINE_KFUNC_BTF_ID_SET(&bpf_testmod_kfunc_ids, bpf_testmod_kfunc_btf_set); + static int bpf_testmod_init(void) { - return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); + int ret; + + ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); + if (ret) + return ret; + register_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); + return 0; } static void bpf_testmod_exit(void) { + unregister_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c index 2cd5cded543f..831447878d7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c @@ -2,30 +2,29 @@ /* Copyright (c) 2021 Facebook */ #include -#include -#include +#include #include "test_ksyms_module.lskel.h" -static int duration; - void test_ksyms_module(void) { - struct test_ksyms_module* skel; + struct test_ksyms_module *skel; + int retval; int err; - skel = test_ksyms_module__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!env.has_testmod) { + test__skip(); return; + } - err = test_ksyms_module__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + skel = test_ksyms_module__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open_and_load")) + return; + err = bpf_prog_test_run(skel->progs.load.prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, (__u32 *)&retval, NULL); + if (!ASSERT_OK(err, "bpf_prog_test_run")) goto cleanup; - - usleep(1); - - ASSERT_EQ(skel->bss->triggered, true, "triggered"); - ASSERT_EQ(skel->bss->out_mod_ksym_global, 123, "global_ksym_val"); - + ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); cleanup: test_ksyms_module__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c new file mode 100644 index 000000000000..e6343ef63af9 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include "test_ksyms_module.skel.h" + +void test_ksyms_module_libbpf(void) +{ + struct test_ksyms_module *skel; + int retval, err; + + if (!env.has_testmod) { + test__skip(); + return; + } + + skel = test_ksyms_module__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open")) + return; + err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4, + sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); + if (!ASSERT_OK(err, "bpf_prog_test_run")) + goto cleanup; + ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); +cleanup: + test_ksyms_module__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_module.c b/tools/testing/selftests/bpf/progs/test_ksyms_module.c index d6a0b3086b90..0650d918c096 100644 --- a/tools/testing/selftests/bpf/progs/test_ksyms_module.c +++ b/tools/testing/selftests/bpf/progs/test_ksyms_module.c @@ -2,24 +2,48 @@ /* Copyright (c) 2021 Facebook */ #include "vmlinux.h" - #include +#define X_0(x) +#define X_1(x) x X_0(x) +#define X_2(x) x X_1(x) +#define X_3(x) x X_2(x) +#define X_4(x) x X_3(x) +#define X_5(x) x X_4(x) +#define X_6(x) x X_5(x) +#define X_7(x) x X_6(x) +#define X_8(x) x X_7(x) +#define X_9(x) x X_8(x) +#define X_10(x) x X_9(x) +#define REPEAT_256(Y) X_2(X_10(X_10(Y))) X_5(X_10(Y)) X_6(Y) + extern const int bpf_testmod_ksym_percpu __ksym; +extern void bpf_testmod_test_mod_kfunc(int i) __ksym; +extern void bpf_testmod_invalid_mod_kfunc(void) __ksym __weak; -int out_mod_ksym_global = 0; -bool triggered = false; +int out_bpf_testmod_ksym = 0; +const volatile int x = 0; -SEC("raw_tp/sys_enter") -int handler(const void *ctx) +SEC("tc") +int load(struct __sk_buff *skb) { - int *val; - __u32 cpu; - - val = (int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); - out_mod_ksym_global = *val; - triggered = true; + /* This will be kept by clang, but removed by verifier. Since it is + * marked as __weak, libbpf and gen_loader don't error out if BTF ID + * is not found for it, instead imm and off is set to 0 for it. + */ + if (x) + bpf_testmod_invalid_mod_kfunc(); + bpf_testmod_test_mod_kfunc(42); + out_bpf_testmod_ksym = *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); + return 0; +} +SEC("tc") +int load_256(struct __sk_buff *skb) +{ + /* this will fail if kfunc doesn't reuse its own btf fd index */ + REPEAT_256(bpf_testmod_test_mod_kfunc(42);); + bpf_testmod_test_mod_kfunc(42); return 0; } diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 336a749673d1..d7b74eb28333 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -1,3 +1,26 @@ +{ + "calls: invalid kfunc call not eliminated", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = REJECT, + .errstr = "invalid kernel function call not eliminated in verifier pass", +}, +{ + "calls: invalid kfunc call unreachable", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 0, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = ACCEPT, +}, { "calls: basic sanity", .insns = { -- cgit v1.2.3 From 65223741ae1b759a14cab84ba88888bb025f816d Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Mon, 4 Oct 2021 17:48:55 +0800 Subject: bpf: Support writable context for bare tracepoint Commit 9df1c28bb752 ("bpf: add writable context for raw tracepoints") supports writable context for tracepoint, but it misses the support for bare tracepoint which has no associated trace event. Bare tracepoint is defined by DECLARE_TRACE(), so adding a corresponding DECLARE_TRACE_WRITABLE() macro to generate a definition in __bpf_raw_tp_map section for bare tracepoint in a similar way to DEFINE_TRACE_WRITABLE(). Signed-off-by: Hou Tao Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211004094857.30868-2-hotforest@gmail.com --- include/trace/bpf_probe.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index a23be89119aa..a8e97f84b652 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -93,8 +93,7 @@ __section("__bpf_raw_tp_map") = { \ #define FIRST(x, ...) x -#undef DEFINE_EVENT_WRITABLE -#define DEFINE_EVENT_WRITABLE(template, call, proto, args, size) \ +#define __CHECK_WRITABLE_BUF_SIZE(call, proto, args, size) \ static inline void bpf_test_buffer_##call(void) \ { \ /* BUILD_BUG_ON() is ignored if the code is completely eliminated, but \ @@ -103,8 +102,12 @@ static inline void bpf_test_buffer_##call(void) \ */ \ FIRST(proto); \ (void)BUILD_BUG_ON_ZERO(size != sizeof(*FIRST(args))); \ -} \ -__DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size) +} + +#undef DEFINE_EVENT_WRITABLE +#define DEFINE_EVENT_WRITABLE(template, call, proto, args, size) \ + __CHECK_WRITABLE_BUF_SIZE(call, PARAMS(proto), PARAMS(args), size) \ + __DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size) #undef DEFINE_EVENT #define DEFINE_EVENT(template, call, proto, args) \ @@ -119,9 +122,17 @@ __DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size) __BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args)) \ __DEFINE_EVENT(call, call, PARAMS(proto), PARAMS(args), 0) +#undef DECLARE_TRACE_WRITABLE +#define DECLARE_TRACE_WRITABLE(call, proto, args, size) \ + __CHECK_WRITABLE_BUF_SIZE(call, PARAMS(proto), PARAMS(args), size) \ + __BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args)) \ + __DEFINE_EVENT(call, call, PARAMS(proto), PARAMS(args), size) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) +#undef DECLARE_TRACE_WRITABLE #undef DEFINE_EVENT_WRITABLE +#undef __CHECK_WRITABLE_BUF_SIZE #undef __DEFINE_EVENT #undef FIRST -- cgit v1.2.3 From 223f903e9c832699f4e5f422281a60756c1c6cfe Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 12 Oct 2021 09:48:38 -0700 Subject: bpf: Rename BTF_KIND_TAG to BTF_KIND_DECL_TAG Patch set [1] introduced BTF_KIND_TAG to allow tagging declarations for struct/union, struct/union field, var, func and func arguments and these tags will be encoded into dwarf. They are also encoded to btf by llvm for the bpf target. After BTF_KIND_TAG is introduced, we intended to use it for kernel __user attributes. But kernel __user is actually a type attribute. Upstream and internal discussion showed it is not a good idea to mix declaration attribute and type attribute. So we proposed to introduce btf_type_tag as a type attribute and existing btf_tag renamed to btf_decl_tag ([2]). This patch renamed BTF_KIND_TAG to BTF_KIND_DECL_TAG and some other declarations with *_tag to *_decl_tag to make it clear the tag is for declaration. In the future, BTF_KIND_TYPE_TAG might be introduced per [3]. [1] https://lore.kernel.org/bpf/20210914223004.244411-1-yhs@fb.com/ [2] https://reviews.llvm.org/D111588 [3] https://reviews.llvm.org/D111199 Fixes: b5ea834dde6b ("bpf: Support for new btf kind BTF_KIND_TAG") Fixes: 5b84bd10363e ("libbpf: Add support for BTF_KIND_TAG") Fixes: 5c07f2fec003 ("bpftool: Add support for BTF_KIND_TAG") Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211012164838.3345699-1-yhs@fb.com --- Documentation/bpf/btf.rst | 24 ++-- include/uapi/linux/btf.h | 8 +- kernel/bpf/btf.c | 44 +++--- tools/bpf/bpftool/btf.c | 6 +- tools/include/uapi/linux/btf.h | 8 +- tools/lib/bpf/btf.c | 36 ++--- tools/lib/bpf/btf.h | 12 +- tools/lib/bpf/btf_dump.c | 6 +- tools/lib/bpf/libbpf.c | 24 ++-- tools/lib/bpf/libbpf.map | 2 +- tools/lib/bpf/libbpf_internal.h | 4 +- tools/testing/selftests/bpf/README.rst | 4 +- tools/testing/selftests/bpf/btf_helpers.c | 8 +- tools/testing/selftests/bpf/prog_tests/btf.c | 160 ++++++++++----------- tools/testing/selftests/bpf/prog_tests/btf_write.c | 30 ++-- tools/testing/selftests/bpf/progs/tag.c | 6 +- tools/testing/selftests/bpf/test_btf.h | 4 +- 17 files changed, 193 insertions(+), 193 deletions(-) (limited to 'include') diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index 1bfe4072f5fc..9e5b4a98af76 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -85,7 +85,7 @@ sequentially and type id is assigned to each recognized type starting from id #define BTF_KIND_VAR 14 /* Variable */ #define BTF_KIND_DATASEC 15 /* Section */ #define BTF_KIND_FLOAT 16 /* Floating point */ - #define BTF_KIND_TAG 17 /* Tag */ + #define BTF_KIND_DECL_TAG 17 /* Decl Tag */ Note that the type section encodes debug info, not just pure types. ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram. @@ -107,7 +107,7 @@ Each type contains the following common data:: * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and TAG. + * FUNC, FUNC_PROTO and DECL_TAG. * "type" is a type_id referring to another type. */ union { @@ -466,30 +466,30 @@ map definition. No additional type data follow ``btf_type``. -2.2.17 BTF_KIND_TAG -~~~~~~~~~~~~~~~~~~~ +2.2.17 BTF_KIND_DECL_TAG +~~~~~~~~~~~~~~~~~~~~~~~~ ``struct btf_type`` encoding requirement: * ``name_off``: offset to a non-empty string * ``info.kind_flag``: 0 - * ``info.kind``: BTF_KIND_TAG + * ``info.kind``: BTF_KIND_DECL_TAG * ``info.vlen``: 0 * ``type``: ``struct``, ``union``, ``func`` or ``var`` -``btf_type`` is followed by ``struct btf_tag``.:: +``btf_type`` is followed by ``struct btf_decl_tag``.:: - struct btf_tag { + struct btf_decl_tag { __u32 component_idx; }; -The ``name_off`` encodes btf_tag attribute string. +The ``name_off`` encodes btf_decl_tag attribute string. The ``type`` should be ``struct``, ``union``, ``func`` or ``var``. -For ``var`` type, ``btf_tag.component_idx`` must be ``-1``. -For the other three types, if the btf_tag attribute is +For ``var`` type, ``btf_decl_tag.component_idx`` must be ``-1``. +For the other three types, if the btf_decl_tag attribute is applied to the ``struct``, ``union`` or ``func`` itself, -``btf_tag.component_idx`` must be ``-1``. Otherwise, +``btf_decl_tag.component_idx`` must be ``-1``. Otherwise, the attribute is applied to a ``struct``/``union`` member or -a ``func`` argument, and ``btf_tag.component_idx`` should be a +a ``func`` argument, and ``btf_decl_tag.component_idx`` should be a valid index (starting from 0) pointing to a member or an argument. 3. BTF Kernel API diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 642b6ecb37d7..deb12f755f0f 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO, VAR and TAG. + * FUNC, FUNC_PROTO, VAR and DECL_TAG. * "type" is a type_id referring to another type. */ union { @@ -74,7 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ - BTF_KIND_TAG = 17, /* Tag */ + BTF_KIND_DECL_TAG = 17, /* Decl Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -174,14 +174,14 @@ struct btf_var_secinfo { __u32 size; }; -/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe +/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe * additional information related to the tag applied location. * If component_idx == -1, the tag is applied to a struct, union, * variable or function. Otherwise, it is applied to a struct/union * member or a func argument, and component_idx indicates which member * or argument (0 ... vlen-1). */ -struct btf_tag { +struct btf_decl_tag { __s32 component_idx; }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2ebffb9f57eb..9059053088b9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -281,7 +281,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", - [BTF_KIND_TAG] = "TAG", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; const char *btf_type_str(const struct btf_type *t) @@ -460,12 +460,12 @@ static bool btf_type_is_datasec(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } -static bool btf_type_is_tag(const struct btf_type *t) +static bool btf_type_is_decl_tag(const struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_TAG; + return BTF_INFO_KIND(t->info) == BTF_KIND_DECL_TAG; } -static bool btf_type_is_tag_target(const struct btf_type *t) +static bool btf_type_is_decl_tag_target(const struct btf_type *t) { return btf_type_is_func(t) || btf_type_is_struct(t) || btf_type_is_var(t); @@ -549,7 +549,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || - btf_type_is_tag(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -576,7 +576,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t) btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || - btf_type_is_tag(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -630,9 +630,9 @@ static const struct btf_var *btf_type_var(const struct btf_type *t) return (const struct btf_var *)(t + 1); } -static const struct btf_tag *btf_type_tag(const struct btf_type *t) +static const struct btf_decl_tag *btf_type_decl_tag(const struct btf_type *t) { - return (const struct btf_tag *)(t + 1); + return (const struct btf_decl_tag *)(t + 1); } static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) @@ -3820,11 +3820,11 @@ static const struct btf_kind_operations float_ops = { .show = btf_df_show, }; -static s32 btf_tag_check_meta(struct btf_verifier_env *env, +static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { - const struct btf_tag *tag; + const struct btf_decl_tag *tag; u32 meta_needed = sizeof(*tag); s32 component_idx; const char *value; @@ -3852,7 +3852,7 @@ static s32 btf_tag_check_meta(struct btf_verifier_env *env, return -EINVAL; } - component_idx = btf_type_tag(t)->component_idx; + component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx < -1) { btf_verifier_log_type(env, t, "Invalid component_idx"); return -EINVAL; @@ -3863,7 +3863,7 @@ static s32 btf_tag_check_meta(struct btf_verifier_env *env, return meta_needed; } -static int btf_tag_resolve(struct btf_verifier_env *env, +static int btf_decl_tag_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *next_type; @@ -3874,7 +3874,7 @@ static int btf_tag_resolve(struct btf_verifier_env *env, u32 vlen; next_type = btf_type_by_id(btf, next_type_id); - if (!next_type || !btf_type_is_tag_target(next_type)) { + if (!next_type || !btf_type_is_decl_tag_target(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } @@ -3883,7 +3883,7 @@ static int btf_tag_resolve(struct btf_verifier_env *env, !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); - component_idx = btf_type_tag(t)->component_idx; + component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx != -1) { if (btf_type_is_var(next_type)) { btf_verifier_log_type(env, v->t, "Invalid component_idx"); @@ -3909,18 +3909,18 @@ static int btf_tag_resolve(struct btf_verifier_env *env, return 0; } -static void btf_tag_log(struct btf_verifier_env *env, const struct btf_type *t) +static void btf_decl_tag_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "type=%u component_idx=%d", t->type, - btf_type_tag(t)->component_idx); + btf_type_decl_tag(t)->component_idx); } -static const struct btf_kind_operations tag_ops = { - .check_meta = btf_tag_check_meta, - .resolve = btf_tag_resolve, +static const struct btf_kind_operations decl_tag_ops = { + .check_meta = btf_decl_tag_check_meta, + .resolve = btf_decl_tag_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, - .log_details = btf_tag_log, + .log_details = btf_decl_tag_log, .show = btf_df_show, }; @@ -4058,7 +4058,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, - [BTF_KIND_TAG] = &tag_ops, + [BTF_KIND_DECL_TAG] = &decl_tag_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -4143,7 +4143,7 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); - if (btf_type_is_tag(t)) + if (btf_type_is_decl_tag(t)) return btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 49743ad96851..7b68d4f65fe6 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -37,7 +37,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", - [BTF_KIND_TAG] = "TAG", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; struct btf_attach_table { @@ -348,8 +348,8 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf(" size=%u", t->size); break; } - case BTF_KIND_TAG: { - const struct btf_tag *tag = (const void *)(t + 1); + case BTF_KIND_DECL_TAG: { + const struct btf_decl_tag *tag = (const void *)(t + 1); if (json_output) { jsonw_uint_field(w, "type_id", t->type); diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 642b6ecb37d7..deb12f755f0f 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO, VAR and TAG. + * FUNC, FUNC_PROTO, VAR and DECL_TAG. * "type" is a type_id referring to another type. */ union { @@ -74,7 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ - BTF_KIND_TAG = 17, /* Tag */ + BTF_KIND_DECL_TAG = 17, /* Decl Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -174,14 +174,14 @@ struct btf_var_secinfo { __u32 size; }; -/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe +/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe * additional information related to the tag applied location. * If component_idx == -1, the tag is applied to a struct, union, * variable or function. Otherwise, it is applied to a struct/union * member or a func argument, and component_idx indicates which member * or argument (0 ... vlen-1). */ -struct btf_tag { +struct btf_decl_tag { __s32 component_idx; }; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 60fbd1c6d466..1f6dea11f600 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -309,8 +309,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); - case BTF_KIND_TAG: - return base_size + sizeof(struct btf_tag); + case BTF_KIND_DECL_TAG: + return base_size + sizeof(struct btf_decl_tag); default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; @@ -383,8 +383,8 @@ static int btf_bswap_type_rest(struct btf_type *t) v->size = bswap_32(v->size); } return 0; - case BTF_KIND_TAG: - btf_tag(t)->component_idx = bswap_32(btf_tag(t)->component_idx); + case BTF_KIND_DECL_TAG: + btf_decl_tag(t)->component_idx = bswap_32(btf_decl_tag(t)->component_idx); return 0; default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); @@ -596,7 +596,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_VAR: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -2569,7 +2569,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ } /* - * Append new BTF_KIND_TAG type with: + * Append new BTF_KIND_DECL_TAG type with: * - *value* - non-empty/non-NULL string; * - *ref_type_id* - referenced type ID, it might not exist yet; * - *component_idx* - -1 for tagging reference type, otherwise struct/union @@ -2578,7 +2578,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ * - >0, type ID of newly added BTF type; * - <0, on error. */ -int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, +int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, int component_idx) { struct btf_type *t; @@ -2593,7 +2593,7 @@ int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, if (btf_ensure_modifiable(btf)) return libbpf_err(-ENOMEM); - sz = sizeof(struct btf_type) + sizeof(struct btf_tag); + sz = sizeof(struct btf_type) + sizeof(struct btf_decl_tag); t = btf_add_type_mem(btf, sz); if (!t) return libbpf_err(-ENOMEM); @@ -2603,9 +2603,9 @@ int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, return value_off; t->name_off = value_off; - t->info = btf_type_info(BTF_KIND_TAG, 0, false); + t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false); t->type = ref_type_id; - btf_tag(t)->component_idx = component_idx; + btf_decl_tag(t)->component_idx = component_idx; return btf_commit_type(btf, sz); } @@ -3427,7 +3427,7 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) } /* Calculate type signature hash of INT or TAG. */ -static long btf_hash_int_tag(struct btf_type *t) +static long btf_hash_int_decl_tag(struct btf_type *t) { __u32 info = *(__u32 *)(t + 1); long h; @@ -3705,8 +3705,8 @@ static int btf_dedup_prep(struct btf_dedup *d) h = btf_hash_common(t); break; case BTF_KIND_INT: - case BTF_KIND_TAG: - h = btf_hash_int_tag(t); + case BTF_KIND_DECL_TAG: + h = btf_hash_int_decl_tag(t); break; case BTF_KIND_ENUM: h = btf_hash_enum(t); @@ -3761,11 +3761,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_FUNC_PROTO: case BTF_KIND_VAR: case BTF_KIND_DATASEC: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: return 0; case BTF_KIND_INT: - h = btf_hash_int_tag(t); + h = btf_hash_int_decl_tag(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; cand = btf_type_by_id(d->btf, cand_id); @@ -4382,13 +4382,13 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) } break; - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: ref_type_id = btf_dedup_ref_type(d, t->type); if (ref_type_id < 0) return ref_type_id; t->type = ref_type_id; - h = btf_hash_int_tag(t); + h = btf_hash_int_decl_tag(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; cand = btf_type_by_id(d->btf, cand_id); @@ -4671,7 +4671,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: return visit(&t->type, ctx); case BTF_KIND_ARRAY: { diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 864eb51753a1..4011e206e6f7 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -236,7 +236,7 @@ LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz); /* tag construction API */ -LIBBPF_API int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, +LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, int component_idx); struct btf_dedup_opts { @@ -426,9 +426,9 @@ static inline bool btf_is_float(const struct btf_type *t) return btf_kind(t) == BTF_KIND_FLOAT; } -static inline bool btf_is_tag(const struct btf_type *t) +static inline bool btf_is_decl_tag(const struct btf_type *t) { - return btf_kind(t) == BTF_KIND_TAG; + return btf_kind(t) == BTF_KIND_DECL_TAG; } static inline __u8 btf_int_encoding(const struct btf_type *t) @@ -499,10 +499,10 @@ btf_var_secinfos(const struct btf_type *t) return (struct btf_var_secinfo *)(t + 1); } -struct btf_tag; -static inline struct btf_tag *btf_tag(const struct btf_type *t) +struct btf_decl_tag; +static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t) { - return (struct btf_tag *)(t + 1); + return (struct btf_decl_tag *)(t + 1); } #ifdef __cplusplus diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index ad6df97295ae..5ef42f0abed1 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -316,7 +316,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: d->type_states[t->type].referenced = 1; break; @@ -584,7 +584,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) case BTF_KIND_FUNC: case BTF_KIND_VAR: case BTF_KIND_DATASEC: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: d->type_states[id].order_state = ORDERED; return 0; @@ -2217,7 +2217,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, case BTF_KIND_FWD: case BTF_KIND_FUNC: case BTF_KIND_FUNC_PROTO: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: err = btf_dump_unsupported_data(d, t, id); break; case BTF_KIND_INT: diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ae0889bebe32..63d738654ff6 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -195,8 +195,8 @@ enum kern_feature_id { FEAT_BTF_FLOAT, /* BPF perf link support */ FEAT_PERF_LINK, - /* BTF_KIND_TAG support */ - FEAT_BTF_TAG, + /* BTF_KIND_DECL_TAG support */ + FEAT_BTF_DECL_TAG, __FEAT_CNT, }; @@ -2024,7 +2024,7 @@ static const char *__btf_kind_str(__u16 kind) case BTF_KIND_VAR: return "var"; case BTF_KIND_DATASEC: return "datasec"; case BTF_KIND_FLOAT: return "float"; - case BTF_KIND_TAG: return "tag"; + case BTF_KIND_DECL_TAG: return "decl_tag"; default: return "unknown"; } } @@ -2524,9 +2524,9 @@ static bool btf_needs_sanitization(struct bpf_object *obj) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); - bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); - return !has_func || !has_datasec || !has_func_global || !has_float || !has_tag; + return !has_func || !has_datasec || !has_func_global || !has_float || !has_decl_tag; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) @@ -2535,15 +2535,15 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); - bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); struct btf_type *t; int i, j, vlen; for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - if ((!has_datasec && btf_is_var(t)) || (!has_tag && btf_is_tag(t))) { - /* replace VAR/TAG with INT */ + if ((!has_datasec && btf_is_var(t)) || (!has_decl_tag && btf_is_decl_tag(t))) { + /* replace VAR/DECL_TAG with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); /* * using size = 1 is the safest choice, 4 will be too @@ -4248,7 +4248,7 @@ static int probe_kern_btf_float(void) strs, sizeof(strs))); } -static int probe_kern_btf_tag(void) +static int probe_kern_btf_decl_tag(void) { static const char strs[] = "\0tag"; __u32 types[] = { @@ -4258,7 +4258,7 @@ static int probe_kern_btf_tag(void) BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), BTF_VAR_STATIC, /* attr */ - BTF_TYPE_TAG_ENC(1, 2, -1), + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), @@ -4481,8 +4481,8 @@ static struct kern_feature_desc { [FEAT_PERF_LINK] = { "BPF perf link support", probe_perf_link, }, - [FEAT_BTF_TAG] = { - "BTF_KIND_TAG support", probe_kern_btf_tag, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, }, }; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f270d25e4af3..e6fb1ba49369 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -394,5 +394,5 @@ LIBBPF_0.6.0 { bpf_object__prev_map; bpf_object__prev_program; btf__add_btf; - btf__add_tag; + btf__add_decl_tag; } LIBBPF_0.5.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index f7fd3944d46d..f6a5748dd318 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -69,8 +69,8 @@ #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) -#define BTF_TYPE_TAG_ENC(value, type, component_idx) \ - BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) +#define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) #ifndef likely #define likely(x) __builtin_expect(!!(x), 1) diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 554553acc6d9..5e287e445f75 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -204,7 +204,7 @@ __ https://reviews.llvm.org/D93563 btf_tag test and Clang version ============================== -The btf_tag selftest require LLVM support to recognize the btf_tag attribute. +The btf_tag selftest require LLVM support to recognize the btf_decl_tag attribute. It was introduced in `Clang 14`__. Without it, the btf_tag selftest will be skipped and you will observe: @@ -213,7 +213,7 @@ Without it, the btf_tag selftest will be skipped and you will observe: # btf_tag:SKIP -__ https://reviews.llvm.org/D106614 +__ https://reviews.llvm.org/D111588 Clang dependencies for static linking tests =========================================== diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c index ce103fb0ad1b..668cfa20bb1b 100644 --- a/tools/testing/selftests/bpf/btf_helpers.c +++ b/tools/testing/selftests/bpf/btf_helpers.c @@ -24,12 +24,12 @@ static const char * const btf_kind_str_mapping[] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", - [BTF_KIND_TAG] = "TAG", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; static const char *btf_kind_str(__u16 kind) { - if (kind > BTF_KIND_TAG) + if (kind > BTF_KIND_DECL_TAG) return "UNKNOWN"; return btf_kind_str_mapping[kind]; } @@ -178,9 +178,9 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id) case BTF_KIND_FLOAT: fprintf(out, " size=%u", t->size); break; - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: fprintf(out, " type_id=%u component_idx=%d", - t->type, btf_tag(t)->component_idx); + t->type, btf_decl_tag(t)->component_idx); break; default: break; diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index acd33d0cd5d9..fa67f25bbef5 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3662,15 +3662,15 @@ static struct btf_raw_test raw_tests[] = { }, { - .descr = "tag test #1, struct/member, well-formed", + .descr = "decl_tag test #1, struct/member, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_STRUCT_ENC(0, 2, 8), /* [2] */ BTF_MEMBER_ENC(NAME_TBD, 1, 0), BTF_MEMBER_ENC(NAME_TBD, 1, 32), - BTF_TAG_ENC(NAME_TBD, 2, -1), - BTF_TAG_ENC(NAME_TBD, 2, 0), - BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 1), BTF_END_RAW, }, BTF_STR_SEC("\0m1\0m2\0tag1\0tag2\0tag3"), @@ -3683,15 +3683,15 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #2, union/member, well-formed", + .descr = "decl_tag test #2, union/member, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_UNION_ENC(NAME_TBD, 2, 4), /* [2] */ BTF_MEMBER_ENC(NAME_TBD, 1, 0), BTF_MEMBER_ENC(NAME_TBD, 1, 0), - BTF_TAG_ENC(NAME_TBD, 2, -1), - BTF_TAG_ENC(NAME_TBD, 2, 0), - BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 1), BTF_END_RAW, }, BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), @@ -3704,13 +3704,13 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #3, variable, well-formed", + .descr = "decl_tag test #3, variable, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ BTF_VAR_ENC(NAME_TBD, 1, 1), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 2, -1), - BTF_TAG_ENC(NAME_TBD, 3, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0global\0tag1\0tag2"), @@ -3723,16 +3723,16 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #4, func/parameter, well-formed", + .descr = "decl_tag test #4, func/parameter, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 3, -1), - BTF_TAG_ENC(NAME_TBD, 3, 0), - BTF_TAG_ENC(NAME_TBD, 3, 1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 1), BTF_END_RAW, }, BTF_STR_SEC("\0arg1\0arg2\0f\0tag1\0tag2\0tag3"), @@ -3745,11 +3745,11 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #5, invalid value", + .descr = "decl_tag test #5, invalid value", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TAG_ENC(0, 2, -1), + BTF_DECL_TAG_ENC(0, 2, -1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag"), @@ -3764,10 +3764,10 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid value", }, { - .descr = "tag test #6, invalid target type", + .descr = "decl_tag test #6, invalid target type", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - BTF_TAG_ENC(NAME_TBD, 1, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 1, -1), BTF_END_RAW, }, BTF_STR_SEC("\0tag1"), @@ -3782,11 +3782,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid type", }, { - .descr = "tag test #7, invalid vlen", + .descr = "decl_tag test #7, invalid vlen", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 0, 1), 2), (0), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 1), 2), (0), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag1"), @@ -3801,11 +3801,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "vlen != 0", }, { - .descr = "tag test #8, invalid kflag", + .descr = "decl_tag test #8, invalid kflag", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 1, 0), 2), (-1), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag1"), @@ -3820,11 +3820,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid btf_info kind_flag", }, { - .descr = "tag test #9, var, invalid component_idx", + .descr = "decl_tag test #9, var, invalid component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag"), @@ -3839,13 +3839,13 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { - .descr = "tag test #10, struct member, invalid component_idx", + .descr = "decl_tag test #10, struct member, invalid component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_STRUCT_ENC(0, 2, 8), /* [2] */ BTF_MEMBER_ENC(NAME_TBD, 1, 0), BTF_MEMBER_ENC(NAME_TBD, 1, 32), - BTF_TAG_ENC(NAME_TBD, 2, 2), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 2), BTF_END_RAW, }, BTF_STR_SEC("\0m1\0m2\0tag"), @@ -3860,14 +3860,14 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { - .descr = "tag test #11, func parameter, invalid component_idx", + .descr = "decl_tag test #11, func parameter, invalid component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 3, 2), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 2), BTF_END_RAW, }, BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), @@ -3882,14 +3882,14 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { - .descr = "tag test #12, < -1 component_idx", + .descr = "decl_tag test #12, < -1 component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 3, -2), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -2), BTF_END_RAW, }, BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), @@ -6672,9 +6672,9 @@ const struct btf_dedup_test dedup_tests[] = { /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ /* tag -> [3] struct s */ - BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ /* tag -> [3] struct s, member 1 */ - BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ /* full copy of the above */ BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [9] */ @@ -6689,8 +6689,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_PTR_ENC(14), /* [13] */ BTF_CONST_ENC(9), /* [14] */ BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [15] */ - BTF_TAG_ENC(NAME_NTH(2), 11, -1), /* [16] */ - BTF_TAG_ENC(NAME_NTH(2), 11, 1), /* [17] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 11, -1), /* [16] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 11, 1), /* [17] */ BTF_END_RAW, }, BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"), @@ -6714,8 +6714,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_PTR_ENC(6), /* [5] */ /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [9] */ BTF_END_RAW, }, @@ -6841,8 +6841,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ - BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ - BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), @@ -6869,8 +6869,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ - BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ - BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), @@ -7036,14 +7036,14 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ /* tag -> t */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [6] */ /* tag -> func */ - BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [8] */ /* tag -> func arg a1 */ - BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [9] */ - BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [10] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), @@ -7056,9 +7056,9 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [7] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), @@ -7084,17 +7084,17 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), BTF_FUNC_ENC(NAME_NTH(3), 4), /* [5] */ /* tag -> f: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1), /* [7] */ /* tag -> f/a2: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [8] */ - BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1), /* [9] */ /* tag -> f: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 5, -1), /* [10] */ - BTF_TAG_ENC(NAME_NTH(6), 5, -1), /* [11] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 5, -1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 5, -1), /* [11] */ /* tag -> f/a2: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 5, 1), /* [12] */ - BTF_TAG_ENC(NAME_NTH(6), 5, 1), /* [13] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 5, 1), /* [12] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 5, 1), /* [13] */ BTF_END_RAW, }, BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), @@ -7106,12 +7106,12 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), BTF_FUNC_ENC(NAME_NTH(3), 2), /* [3] */ - BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [4] */ - BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [8] */ - BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1), /* [9] */ BTF_END_RAW, }, BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), @@ -7133,17 +7133,17 @@ const struct btf_dedup_test dedup_tests[] = { BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), /* tag -> t: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [4] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ /* tag -> t/m2: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ /* tag -> t: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [8] */ - BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1), /* [9] */ /* tag -> t/m2: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [10] */ - BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [11] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1), /* [11] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), @@ -7154,12 +7154,12 @@ const struct btf_dedup_test dedup_tests[] = { BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [2] */ BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), - BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [3] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [4] */ - BTF_TAG_ENC(NAME_NTH(6), 2, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(6), 2, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1), /* [3] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 2, 1), /* [8] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), @@ -7202,8 +7202,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); - case BTF_KIND_TAG: - return base_size + sizeof(struct btf_tag); + case BTF_KIND_DECL_TAG: + return base_size + sizeof(struct btf_decl_tag); default: fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind); return -EINVAL; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c index 886e0fc1efb1..b912eeb0b6b4 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_write.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c @@ -277,26 +277,26 @@ static void gen_btf(struct btf *btf) "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", "raw_dump"); - /* TAG */ - id = btf__add_tag(btf, "tag1", 16, -1); + /* DECL_TAG */ + id = btf__add_decl_tag(btf, "tag1", 16, -1); ASSERT_EQ(id, 18, "tag_id"); t = btf__type_by_id(btf, 18); ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value"); - ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind"); ASSERT_EQ(t->type, 16, "tag_type"); - ASSERT_EQ(btf_tag(t)->component_idx, -1, "tag_component_idx"); + ASSERT_EQ(btf_decl_tag(t)->component_idx, -1, "tag_component_idx"); ASSERT_STREQ(btf_type_raw_dump(btf, 18), - "[18] TAG 'tag1' type_id=16 component_idx=-1", "raw_dump"); + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", "raw_dump"); - id = btf__add_tag(btf, "tag2", 14, 1); + id = btf__add_decl_tag(btf, "tag2", 14, 1); ASSERT_EQ(id, 19, "tag_id"); t = btf__type_by_id(btf, 19); ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag2", "tag_value"); - ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind"); ASSERT_EQ(t->type, 14, "tag_type"); - ASSERT_EQ(btf_tag(t)->component_idx, 1, "tag_component_idx"); + ASSERT_EQ(btf_decl_tag(t)->component_idx, 1, "tag_component_idx"); ASSERT_STREQ(btf_type_raw_dump(btf, 19), - "[19] TAG 'tag2' type_id=14 component_idx=1", "raw_dump"); + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", "raw_dump"); } static void test_btf_add() @@ -336,8 +336,8 @@ static void test_btf_add() "[16] VAR 'var1' type_id=1, linkage=global-alloc", "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", - "[18] TAG 'tag1' type_id=16 component_idx=-1", - "[19] TAG 'tag2' type_id=14 component_idx=1"); + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1"); btf__free(btf); } @@ -389,8 +389,8 @@ static void test_btf_add_btf() "[16] VAR 'var1' type_id=1, linkage=global-alloc", "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", - "[18] TAG 'tag1' type_id=16 component_idx=-1", - "[19] TAG 'tag2' type_id=14 component_idx=1", + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", /* types appended from the second BTF */ "[20] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", @@ -418,8 +418,8 @@ static void test_btf_add_btf() "[35] VAR 'var1' type_id=20, linkage=global-alloc", "[36] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=20 offset=4 size=8", - "[37] TAG 'tag1' type_id=35 component_idx=-1", - "[38] TAG 'tag2' type_id=33 component_idx=1"); + "[37] DECL_TAG 'tag1' type_id=35 component_idx=-1", + "[38] DECL_TAG 'tag2' type_id=33 component_idx=1"); cleanup: btf__free(btf1); diff --git a/tools/testing/selftests/bpf/progs/tag.c b/tools/testing/selftests/bpf/progs/tag.c index b46b1bfac7da..672d19e7b120 100644 --- a/tools/testing/selftests/bpf/progs/tag.c +++ b/tools/testing/selftests/bpf/progs/tag.c @@ -8,9 +8,9 @@ #define __has_attribute(x) 0 #endif -#if __has_attribute(btf_tag) -#define __tag1 __attribute__((btf_tag("tag1"))) -#define __tag2 __attribute__((btf_tag("tag2"))) +#if __has_attribute(btf_decl_tag) +#define __tag1 __attribute__((btf_decl_tag("tag1"))) +#define __tag2 __attribute__((btf_decl_tag("tag2"))) volatile const bool skip_tests __tag1 __tag2 = false; #else #define __tag1 diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h index 0619e06d745e..32c7a57867da 100644 --- a/tools/testing/selftests/bpf/test_btf.h +++ b/tools/testing/selftests/bpf/test_btf.h @@ -69,7 +69,7 @@ #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) -#define BTF_TAG_ENC(value, type, component_idx) \ - BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) +#define BTF_DECL_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) #endif /* _TEST_BTF_H */ -- cgit v1.2.3 From 9eeb3aa33ae005526f672b394c1791578463513f Mon Sep 17 00:00:00 2001 From: Hengqi Chen Date: Thu, 21 Oct 2021 21:47:51 +0800 Subject: bpf: Add bpf_skc_to_unix_sock() helper The helper is used in tracing programs to cast a socket pointer to a unix_sock pointer. The return value could be NULL if the casting is illegal. Suggested-by: Yonghong Song Signed-off-by: Hengqi Chen Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211021134752.1223426-2-hengqi.chen@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 7 +++++++ kernel/trace/bpf_trace.c | 2 ++ net/core/filter.c | 23 +++++++++++++++++++++++ scripts/bpf_doc.py | 2 ++ tools/include/uapi/linux/bpf.h | 7 +++++++ 6 files changed, 42 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d604c8251d88..be3102b4554b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2093,6 +2093,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6fc59d61937a..22e7a3f38b9f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4909,6 +4909,12 @@ union bpf_attr { * Return * The number of bytes written to the buffer, or a negative error * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5089,6 +5095,7 @@ union bpf_attr { FN(task_pt_regs), \ FN(get_branch_snapshot), \ FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6b3153841a33..cbcd0d6fca7c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1608,6 +1608,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_to_tcp_request_sock_proto; case BPF_FUNC_skc_to_udp6_sock: return &bpf_skc_to_udp6_sock_proto; + case BPF_FUNC_skc_to_unix_sock: + return &bpf_skc_to_unix_sock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_tracing_proto; case BPF_FUNC_sk_storage_delete: diff --git a/net/core/filter.c b/net/core/filter.c index 4bace37a6a44..8e8d3b49c297 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10723,6 +10723,26 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; +BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk) +{ + /* unix_sock type is not generated in dwarf and hence btf, + * trigger an explicit type generation here. + */ + BTF_TYPE_EMIT(struct unix_sock); + if (sk && sk_fullsock(sk) && sk->sk_family == AF_UNIX) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { + .func = bpf_skc_to_unix_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], +}; + BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); @@ -10762,6 +10782,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; + case BPF_FUNC_skc_to_unix_sock: + func = &bpf_skc_to_unix_sock_proto; + break; default: return bpf_base_func_proto(func_id); } diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index 00ac7b79cddb..a6403ddf5de7 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -537,6 +537,7 @@ class PrinterHelpers(Printer): 'struct tcp_timewait_sock', 'struct tcp_request_sock', 'struct udp6_sock', + 'struct unix_sock', 'struct task_struct', 'struct __sk_buff', @@ -589,6 +590,7 @@ class PrinterHelpers(Printer): 'struct tcp_timewait_sock', 'struct tcp_request_sock', 'struct udp6_sock', + 'struct unix_sock', 'struct task_struct', 'struct path', 'struct btf_ptr', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6fc59d61937a..22e7a3f38b9f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4909,6 +4909,12 @@ union bpf_attr { * Return * The number of bytes written to the buffer, or a negative error * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5089,6 +5095,7 @@ union bpf_attr { FN(task_pt_regs), \ FN(get_branch_snapshot), \ FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From aba64c7da98330141dcdadd5612f088043a83696 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Wed, 20 Oct 2021 00:48:17 -0700 Subject: bpf: Add verified_insns to bpf_prog_info and fdinfo This stat is currently printed in the verifier log and not stored anywhere. To ease consumption of this data, add a field to bpf_prog_aux so it can be exposed via BPF_OBJ_GET_INFO_BY_FD and fdinfo. Signed-off-by: Dave Marchevsky Signed-off-by: Andrii Nakryiko Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20211020074818.1017682-2-davemarchevsky@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 8 ++++++-- kernel/bpf/verifier.c | 1 + tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be3102b4554b..31421c74ba08 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -887,6 +887,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ + u32 verified_insns; struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 22e7a3f38b9f..c10820037883 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5620,6 +5620,7 @@ struct bpf_prog_info { __u64 run_time_ns; __u64 run_cnt; __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e50c0bfdb7d..5beb321b3b3b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1848,7 +1848,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" - "recursion_misses:\t%llu\n", + "recursion_misses:\t%llu\n" + "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, @@ -1856,7 +1857,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) prog->aux->id, stats.nsecs, stats.cnt, - stats.misses); + stats.misses, + prog->aux->verified_insns); } #endif @@ -3625,6 +3627,8 @@ static int bpf_prog_get_info_by_fd(struct file *file, info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; + info.verified_insns = prog->aux->verified_insns; + if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 21cdff35a2f9..c6616e325803 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14033,6 +14033,7 @@ skip_full_check: env->verification_time = ktime_get_ns() - start_time; print_verification_stats(env); + env->prog->aux->verified_insns = env->insn_processed; if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 22e7a3f38b9f..c10820037883 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5620,6 +5620,7 @@ struct bpf_prog_info { __u64 run_time_ns; __u64 run_cnt; __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { -- cgit v1.2.3 From f941eadd8d6d4ee2f8c9aeab8e1da5e647533a7d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 26 Oct 2021 14:41:31 -0700 Subject: bpf: Avoid races in __bpf_prog_run() for 32bit arches __bpf_prog_run() can run from non IRQ contexts, meaning it could be re entered if interrupted. This calls for the irq safe variant of u64_stats_update_{begin|end}, or risk a deadlock. This patch is a nop on 64bit arches, fortunately. syzbot report: WARNING: inconsistent lock state 5.12.0-rc3-syzkaller #0 Not tainted -------------------------------- inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. udevd/4013 [HC0[0]:SC0[0]:HE1:SE1] takes: ff7c9dec (&(&pstats->syncp)->seq){+.?.}-{0:0}, at: sk_filter include/linux/filter.h:867 [inline] ff7c9dec (&(&pstats->syncp)->seq){+.?.}-{0:0}, at: do_one_broadcast net/netlink/af_netlink.c:1468 [inline] ff7c9dec (&(&pstats->syncp)->seq){+.?.}-{0:0}, at: netlink_broadcast_filtered+0x27c/0x4fc net/netlink/af_netlink.c:1520 {IN-SOFTIRQ-W} state was registered at: lock_acquire.part.0+0xf0/0x41c kernel/locking/lockdep.c:5510 lock_acquire+0x6c/0x74 kernel/locking/lockdep.c:5483 do_write_seqcount_begin_nested include/linux/seqlock.h:520 [inline] do_write_seqcount_begin include/linux/seqlock.h:545 [inline] u64_stats_update_begin include/linux/u64_stats_sync.h:129 [inline] bpf_prog_run_pin_on_cpu include/linux/filter.h:624 [inline] bpf_prog_run_clear_cb+0x1bc/0x270 include/linux/filter.h:755 run_filter+0xa0/0x17c net/packet/af_packet.c:2031 packet_rcv+0xc0/0x3e0 net/packet/af_packet.c:2104 dev_queue_xmit_nit+0x2bc/0x39c net/core/dev.c:2387 xmit_one net/core/dev.c:3588 [inline] dev_hard_start_xmit+0x94/0x518 net/core/dev.c:3609 sch_direct_xmit+0x11c/0x1f0 net/sched/sch_generic.c:313 qdisc_restart net/sched/sch_generic.c:376 [inline] __qdisc_run+0x194/0x7f8 net/sched/sch_generic.c:384 qdisc_run include/net/pkt_sched.h:136 [inline] qdisc_run include/net/pkt_sched.h:128 [inline] __dev_xmit_skb net/core/dev.c:3795 [inline] __dev_queue_xmit+0x65c/0xf84 net/core/dev.c:4150 dev_queue_xmit+0x14/0x18 net/core/dev.c:4215 neigh_resolve_output net/core/neighbour.c:1491 [inline] neigh_resolve_output+0x170/0x228 net/core/neighbour.c:1471 neigh_output include/net/neighbour.h:510 [inline] ip6_finish_output2+0x2e4/0x9fc net/ipv6/ip6_output.c:117 __ip6_finish_output net/ipv6/ip6_output.c:182 [inline] __ip6_finish_output+0x164/0x3f8 net/ipv6/ip6_output.c:161 ip6_finish_output+0x2c/0xb0 net/ipv6/ip6_output.c:192 NF_HOOK_COND include/linux/netfilter.h:290 [inline] ip6_output+0x74/0x294 net/ipv6/ip6_output.c:215 dst_output include/net/dst.h:448 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] NF_HOOK include/linux/netfilter.h:295 [inline] mld_sendpack+0x2a8/0x7e4 net/ipv6/mcast.c:1679 mld_send_cr net/ipv6/mcast.c:1975 [inline] mld_ifc_timer_expire+0x1e8/0x494 net/ipv6/mcast.c:2474 call_timer_fn+0xd0/0x570 kernel/time/timer.c:1431 expire_timers kernel/time/timer.c:1476 [inline] __run_timers kernel/time/timer.c:1745 [inline] run_timer_softirq+0x2e4/0x384 kernel/time/timer.c:1758 __do_softirq+0x204/0x7ac kernel/softirq.c:345 do_softirq_own_stack include/asm-generic/softirq_stack.h:10 [inline] invoke_softirq kernel/softirq.c:228 [inline] __irq_exit_rcu+0x1d8/0x200 kernel/softirq.c:422 irq_exit+0x10/0x3c kernel/softirq.c:446 __handle_domain_irq+0xb4/0x120 kernel/irq/irqdesc.c:692 handle_domain_irq include/linux/irqdesc.h:176 [inline] gic_handle_irq+0x84/0xac drivers/irqchip/irq-gic.c:370 __irq_svc+0x5c/0x94 arch/arm/kernel/entry-armv.S:205 debug_smp_processor_id+0x0/0x24 lib/smp_processor_id.c:53 rcu_read_lock_held_common kernel/rcu/update.c:108 [inline] rcu_read_lock_sched_held+0x24/0x7c kernel/rcu/update.c:123 trace_lock_acquire+0x24c/0x278 include/trace/events/lock.h:13 lock_acquire+0x3c/0x74 kernel/locking/lockdep.c:5481 rcu_lock_acquire include/linux/rcupdate.h:267 [inline] rcu_read_lock include/linux/rcupdate.h:656 [inline] avc_has_perm_noaudit+0x6c/0x260 security/selinux/avc.c:1150 selinux_inode_permission+0x140/0x220 security/selinux/hooks.c:3141 security_inode_permission+0x44/0x60 security/security.c:1268 inode_permission.part.0+0x5c/0x13c fs/namei.c:521 inode_permission fs/namei.c:494 [inline] may_lookup fs/namei.c:1652 [inline] link_path_walk.part.0+0xd4/0x38c fs/namei.c:2208 link_path_walk fs/namei.c:2189 [inline] path_lookupat+0x3c/0x1b8 fs/namei.c:2419 filename_lookup+0xa8/0x1a4 fs/namei.c:2453 user_path_at_empty+0x74/0x90 fs/namei.c:2733 do_readlinkat+0x5c/0x12c fs/stat.c:417 __do_sys_readlink fs/stat.c:450 [inline] sys_readlink+0x24/0x28 fs/stat.c:447 ret_fast_syscall+0x0/0x2c arch/arm/mm/proc-v7.S:64 0x7eaa4974 irq event stamp: 298277 hardirqs last enabled at (298277): [<802000d0>] no_work_pending+0x4/0x34 hardirqs last disabled at (298276): [<8020c9b8>] do_work_pending+0x9c/0x648 arch/arm/kernel/signal.c:676 softirqs last enabled at (298216): [<8020167c>] __do_softirq+0x584/0x7ac kernel/softirq.c:372 softirqs last disabled at (298201): [<8024dff4>] do_softirq_own_stack include/asm-generic/softirq_stack.h:10 [inline] softirqs last disabled at (298201): [<8024dff4>] invoke_softirq kernel/softirq.c:228 [inline] softirqs last disabled at (298201): [<8024dff4>] __irq_exit_rcu+0x1d8/0x200 kernel/softirq.c:422 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&pstats->syncp)->seq); lock(&(&pstats->syncp)->seq); *** DEADLOCK *** 1 lock held by udevd/4013: #0: 82b09c5c (rcu_read_lock){....}-{1:2}, at: sk_filter_trim_cap+0x54/0x434 net/core/filter.c:139 stack backtrace: CPU: 1 PID: 4013 Comm: udevd Not tainted 5.12.0-rc3-syzkaller #0 Hardware name: ARM-Versatile Express Backtrace: [<81802550>] (dump_backtrace) from [<818027c4>] (show_stack+0x18/0x1c arch/arm/kernel/traps.c:252) r7:00000080 r6:600d0093 r5:00000000 r4:82b58344 [<818027ac>] (show_stack) from [<81809e98>] (__dump_stack lib/dump_stack.c:79 [inline]) [<818027ac>] (show_stack) from [<81809e98>] (dump_stack+0xb8/0xe8 lib/dump_stack.c:120) [<81809de0>] (dump_stack) from [<81804a00>] (print_usage_bug.part.0+0x228/0x230 kernel/locking/lockdep.c:3806) r7:86bcb768 r6:81a0326c r5:830f96a8 r4:86bcb0c0 [<818047d8>] (print_usage_bug.part.0) from [<802bb1b8>] (print_usage_bug kernel/locking/lockdep.c:3776 [inline]) [<818047d8>] (print_usage_bug.part.0) from [<802bb1b8>] (valid_state kernel/locking/lockdep.c:3818 [inline]) [<818047d8>] (print_usage_bug.part.0) from [<802bb1b8>] (mark_lock_irq kernel/locking/lockdep.c:4021 [inline]) [<818047d8>] (print_usage_bug.part.0) from [<802bb1b8>] (mark_lock.part.0+0xc34/0x136c kernel/locking/lockdep.c:4478) r10:83278fe8 r9:82c6d748 r8:00000000 r7:82c6d2d4 r6:00000004 r5:86bcb768 r4:00000006 [<802ba584>] (mark_lock.part.0) from [<802bc644>] (mark_lock kernel/locking/lockdep.c:4442 [inline]) [<802ba584>] (mark_lock.part.0) from [<802bc644>] (mark_usage kernel/locking/lockdep.c:4391 [inline]) [<802ba584>] (mark_lock.part.0) from [<802bc644>] (__lock_acquire+0x9bc/0x3318 kernel/locking/lockdep.c:4854) r10:86bcb768 r9:86bcb0c0 r8:00000001 r7:00040000 r6:0000075a r5:830f96a8 r4:00000000 [<802bbc88>] (__lock_acquire) from [<802bfb90>] (lock_acquire.part.0+0xf0/0x41c kernel/locking/lockdep.c:5510) r10:00000000 r9:600d0013 r8:00000000 r7:00000000 r6:828a2680 r5:828a2680 r4:861e5bc8 [<802bfaa0>] (lock_acquire.part.0) from [<802bff28>] (lock_acquire+0x6c/0x74 kernel/locking/lockdep.c:5483) r10:8146137c r9:00000000 r8:00000001 r7:00000000 r6:00000000 r5:00000000 r4:ff7c9dec [<802bfebc>] (lock_acquire) from [<81381eb4>] (do_write_seqcount_begin_nested include/linux/seqlock.h:520 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (do_write_seqcount_begin include/linux/seqlock.h:545 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (u64_stats_update_begin include/linux/u64_stats_sync.h:129 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (__bpf_prog_run_save_cb include/linux/filter.h:727 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (bpf_prog_run_save_cb include/linux/filter.h:741 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (sk_filter_trim_cap+0x26c/0x434 net/core/filter.c:149) r10:a4095dd0 r9:ff7c9dd0 r8:e44be000 r7:8146137c r6:00000001 r5:8611ba80 r4:00000000 [<81381c48>] (sk_filter_trim_cap) from [<8146137c>] (sk_filter include/linux/filter.h:867 [inline]) [<81381c48>] (sk_filter_trim_cap) from [<8146137c>] (do_one_broadcast net/netlink/af_netlink.c:1468 [inline]) [<81381c48>] (sk_filter_trim_cap) from [<8146137c>] (netlink_broadcast_filtered+0x27c/0x4fc net/netlink/af_netlink.c:1520) r10:00000001 r9:833d6b1c r8:00000000 r7:8572f864 r6:8611ba80 r5:8698d800 r4:8572f800 [<81461100>] (netlink_broadcast_filtered) from [<81463e60>] (netlink_broadcast net/netlink/af_netlink.c:1544 [inline]) [<81461100>] (netlink_broadcast_filtered) from [<81463e60>] (netlink_sendmsg+0x3d0/0x478 net/netlink/af_netlink.c:1925) r10:00000000 r9:00000002 r8:8698d800 r7:000000b7 r6:8611b900 r5:861e5f50 r4:86aa3000 [<81463a90>] (netlink_sendmsg) from [<81321f54>] (sock_sendmsg_nosec net/socket.c:654 [inline]) [<81463a90>] (netlink_sendmsg) from [<81321f54>] (sock_sendmsg+0x3c/0x4c net/socket.c:674) r10:00000000 r9:861e5dd4 r8:00000000 r7:86570000 r6:00000000 r5:86570000 r4:861e5f50 [<81321f18>] (sock_sendmsg) from [<813234d0>] (____sys_sendmsg+0x230/0x29c net/socket.c:2350) r5:00000040 r4:861e5f50 [<813232a0>] (____sys_sendmsg) from [<8132549c>] (___sys_sendmsg+0xac/0xe4 net/socket.c:2404) r10:00000128 r9:861e4000 r8:00000000 r7:00000000 r6:86570000 r5:861e5f50 r4:00000000 [<813253f0>] (___sys_sendmsg) from [<81325684>] (__sys_sendmsg net/socket.c:2433 [inline]) [<813253f0>] (___sys_sendmsg) from [<81325684>] (__do_sys_sendmsg net/socket.c:2442 [inline]) [<813253f0>] (___sys_sendmsg) from [<81325684>] (sys_sendmsg+0x58/0xa0 net/socket.c:2440) r8:80200224 r7:00000128 r6:00000000 r5:7eaa541c r4:86570000 [<8132562c>] (sys_sendmsg) from [<80200060>] (ret_fast_syscall+0x0/0x2c arch/arm/mm/proc-v7.S:64) Exception stack(0x861e5fa8 to 0x861e5ff0) 5fa0: 00000000 00000000 0000000c 7eaa541c 00000000 00000000 5fc0: 00000000 00000000 76fbf840 00000128 00000000 0000008f 7eaa541c 000563f8 5fe0: 00056110 7eaa53e0 00036cec 76c9bf44 r6:76fbf840 r5:00000000 r4:00000000 Fixes: 492ecee892c2 ("bpf: enable program stats") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211026214133.3114279-2-eric.dumazet@gmail.com --- include/linux/filter.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 47f80adbe744..2fffe9cc50f9 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -612,13 +612,14 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; u64 start = sched_clock(); + unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); stats = this_cpu_ptr(prog->stats); - u64_stats_update_begin(&stats->syncp); + flags = u64_stats_update_begin_irqsave(&stats->syncp); stats->cnt++; stats->nsecs += sched_clock() - start; - u64_stats_update_end(&stats->syncp); + u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); } -- cgit v1.2.3 From 61a0abaee2092eee69e44fe60336aa2f5b578938 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 26 Oct 2021 14:41:33 -0700 Subject: bpf: Use u64_stats_t in struct bpf_prog_stats Commit 316580b69d0a ("u64_stats: provide u64_stats_t type") fixed possible load/store tearing on 64bit arches. For instance the following C code stats->nsecs += sched_clock() - start; Could be rightfully implemented like this by a compiler, confusing concurrent readers a lot: stats->nsecs += sched_clock(); // arbitrary delay stats->nsecs -= start; Signed-off-by: Eric Dumazet Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211026214133.3114279-4-eric.dumazet@gmail.com --- include/linux/filter.h | 10 +++++----- kernel/bpf/syscall.c | 18 ++++++++++++------ kernel/bpf/trampoline.c | 6 +++--- 3 files changed, 20 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 2fffe9cc50f9..9782e3245852 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -553,9 +553,9 @@ struct bpf_binary_header { }; struct bpf_prog_stats { - u64 cnt; - u64 nsecs; - u64 misses; + u64_stats_t cnt; + u64_stats_t nsecs; + u64_stats_t misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); @@ -617,8 +617,8 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, ret = dfunc(ctx, prog->insnsi, prog->bpf_func); stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); - stats->cnt++; - stats->nsecs += sched_clock() - start; + u64_stats_inc(&stats->cnt); + u64_stats_add(&stats->nsecs, sched_clock() - start); u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5beb321b3b3b..3e1c024ce3ed 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1804,8 +1804,14 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) return 0; } +struct bpf_prog_kstats { + u64 nsecs; + u64 cnt; + u64 misses; +}; + static void bpf_prog_get_stats(const struct bpf_prog *prog, - struct bpf_prog_stats *stats) + struct bpf_prog_kstats *stats) { u64 nsecs = 0, cnt = 0, misses = 0; int cpu; @@ -1818,9 +1824,9 @@ static void bpf_prog_get_stats(const struct bpf_prog *prog, st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin_irq(&st->syncp); - tnsecs = st->nsecs; - tcnt = st->cnt; - tmisses = st->misses; + tnsecs = u64_stats_read(&st->nsecs); + tcnt = u64_stats_read(&st->cnt); + tmisses = u64_stats_read(&st->misses); } while (u64_stats_fetch_retry_irq(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; @@ -1836,7 +1842,7 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); @@ -3577,7 +3583,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_prog_info info; u32 info_len = attr->info.info_len; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index e5963de368ed..e98de5e73ba5 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -545,7 +545,7 @@ static void notrace inc_misses_counter(struct bpf_prog *prog) stats = this_cpu_ptr(prog->stats); u64_stats_update_begin(&stats->syncp); - stats->misses++; + u64_stats_inc(&stats->misses); u64_stats_update_end(&stats->syncp); } @@ -590,8 +590,8 @@ static void notrace update_prog_stats(struct bpf_prog *prog, stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); - stats->cnt++; - stats->nsecs += sched_clock() - start; + u64_stats_inc(&stats->cnt); + u64_stats_add(&stats->nsecs, sched_clock() - start); u64_stats_update_end_irqrestore(&stats->syncp, flags); } } -- cgit v1.2.3 From 9330986c03006ab1d33d243b7cfe598a7a3c1baa Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 27 Oct 2021 16:45:00 -0700 Subject: bpf: Add bloom filter map implementation This patch adds the kernel-side changes for the implementation of a bpf bloom filter map. The bloom filter map supports peek (determining whether an element is present in the map) and push (adding an element to the map) operations.These operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_UPDATE_ELEM -> push The bloom filter map does not have keys, only values. In light of this, the bloom filter map's API matches that of queue stack maps: user applications use BPF_MAP_LOOKUP_ELEM/BPF_MAP_UPDATE_ELEM which correspond internally to bpf_map_peek_elem/bpf_map_push_elem, and bpf programs must use the bpf_map_peek_elem and bpf_map_push_elem APIs to query or add an element to the bloom filter map. When the bloom filter map is created, it must be created with a key_size of 0. For updates, the user will pass in the element to add to the map as the value, with a NULL key. For lookups, the user will pass in the element to query in the map as the value, with a NULL key. In the verifier layer, this requires us to modify the argument type of a bloom filter's BPF_FUNC_map_peek_elem call to ARG_PTR_TO_MAP_VALUE; as well, in the syscall layer, we need to copy over the user value so that in bpf_map_peek_elem, we know which specific value to query. A few things to please take note of: * If there are any concurrent lookups + updates, the user is responsible for synchronizing this to ensure no false negative lookups occur. * The number of hashes to use for the bloom filter is configurable from userspace. If no number is specified, the default used will be 5 hash functions. The benchmarks later in this patchset can help compare the performance of using different number of hashes on different entry sizes. In general, using more hashes decreases both the false positive rate and the speed of a lookup. * Deleting an element in the bloom filter map is not supported. * The bloom filter map may be used as an inner map. * The "max_entries" size that is specified at map creation time is used to approximate a reasonable bitmap size for the bloom filter, and is not otherwise strictly enforced. If the user wishes to insert more entries into the bloom filter than "max_entries", they may do so but they should be aware that this may lead to a higher false positive rate. Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211027234504.30744-2-joannekoong@fb.com --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 9 ++ kernel/bpf/Makefile | 2 +- kernel/bpf/bloom_filter.c | 195 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 24 ++++- kernel/bpf/verifier.c | 19 +++- tools/include/uapi/linux/bpf.h | 9 ++ 8 files changed, 253 insertions(+), 7 deletions(-) create mode 100644 kernel/bpf/bloom_filter.c (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 31421c74ba08..50105e0b8fcc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -169,6 +169,7 @@ struct bpf_map { u32 value_size; u32 max_entries; u32 map_flags; + u64 map_extra; /* any per-map-type extra fields */ int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9c81724e4b98..c4424ac2fa02 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -125,6 +125,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 7f33098ca63f..cf6ca339f3cd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -7,7 +7,7 @@ endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o -obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c new file mode 100644 index 000000000000..7c50232b7571 --- /dev/null +++ b/kernel/bpf/bloom_filter.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include +#include +#include +#include +#include +#include + +#define BLOOM_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) + +struct bpf_bloom_filter { + struct bpf_map map; + u32 bitset_mask; + u32 hash_seed; + /* If the size of the values in the bloom filter is u32 aligned, + * then it is more performant to use jhash2 as the underlying hash + * function, else we use jhash. This tracks the number of u32s + * in an u32-aligned value size. If the value size is not u32 aligned, + * this will be 0. + */ + u32 aligned_u32_count; + u32 nr_hash_funcs; + unsigned long bitset[]; +}; + +static u32 hash(struct bpf_bloom_filter *bloom, void *value, + u32 value_size, u32 index) +{ + u32 h; + + if (bloom->aligned_u32_count) + h = jhash2(value, bloom->aligned_u32_count, + bloom->hash_seed + index); + else + h = jhash(value, value_size, bloom->hash_seed + index); + + return h & bloom->bitset_mask; +} + +static int peek_elem(struct bpf_map *map, void *value) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + if (!test_bit(h, bloom->bitset)) + return -ENOENT; + } + + return 0; +} + +static int push_elem(struct bpf_map *map, void *value, u64 flags) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + if (flags != BPF_ANY) + return -EINVAL; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + set_bit(h, bloom->bitset); + } + + return 0; +} + +static int pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static struct bpf_map *map_alloc(union bpf_attr *attr) +{ + u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_bloom_filter *bloom; + + if (!bpf_capable()) + return ERR_PTR(-EPERM); + + if (attr->key_size != 0 || attr->value_size == 0 || + attr->max_entries == 0 || + attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || + (attr->map_extra & ~0xF)) + return ERR_PTR(-EINVAL); + + /* The lower 4 bits of map_extra specify the number of hash functions */ + nr_hash_funcs = attr->map_extra & 0xF; + if (nr_hash_funcs == 0) + /* Default to using 5 hash functions if unspecified */ + nr_hash_funcs = 5; + + /* For the bloom filter, the optimal bit array size that minimizes the + * false positive probability is n * k / ln(2) where n is the number of + * expected entries in the bloom filter and k is the number of hash + * functions. We use 7 / 5 to approximate 1 / ln(2). + * + * We round this up to the nearest power of two to enable more efficient + * hashing using bitmasks. The bitmask will be the bit array size - 1. + * + * If this overflows a u32, the bit array size will have 2^32 (4 + * GB) bits. + */ + if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || + check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || + nr_bits > (1UL << 31)) { + /* The bit array size is 2^32 bits but to avoid overflowing the + * u32, we use U32_MAX, which will round up to the equivalent + * number of bytes + */ + bitset_bytes = BITS_TO_BYTES(U32_MAX); + bitset_mask = U32_MAX; + } else { + if (nr_bits <= BITS_PER_LONG) + nr_bits = BITS_PER_LONG; + else + nr_bits = roundup_pow_of_two(nr_bits); + bitset_bytes = BITS_TO_BYTES(nr_bits); + bitset_mask = nr_bits - 1; + } + + bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); + + if (!bloom) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&bloom->map, attr); + + bloom->nr_hash_funcs = nr_hash_funcs; + bloom->bitset_mask = bitset_mask; + + /* Check whether the value size is u32-aligned */ + if ((attr->value_size & (sizeof(u32) - 1)) == 0) + bloom->aligned_u32_count = + attr->value_size / sizeof(u32); + + if (!(attr->map_flags & BPF_F_ZERO_SEED)) + bloom->hash_seed = get_random_int(); + + return &bloom->map; +} + +static void map_free(struct bpf_map *map) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + + bpf_map_area_free(bloom); +} + +static void *lookup_elem(struct bpf_map *map, void *key) +{ + /* The eBPF program should use map_peek_elem instead */ + return ERR_PTR(-EINVAL); +} + +static int update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + /* The eBPF program should use map_push_elem instead */ + return -EINVAL; +} + +static int check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + /* Bloom filter maps are keyless */ + return btf_type_is_void(key_type) ? 0 : -EINVAL; +} + +static int bpf_bloom_btf_id; +const struct bpf_map_ops bloom_filter_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = map_alloc, + .map_free = map_free, + .map_push_elem = push_elem, + .map_peek_elem = peek_elem, + .map_pop_elem = pop_elem, + .map_lookup_elem = lookup_elem, + .map_update_elem = update_elem, + .map_check_btf = check_btf, + .map_btf_name = "bpf_bloom_filter", + .map_btf_id = &bpf_bloom_btf_id, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3e1c024ce3ed..f7c2c6354add 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -199,7 +199,8 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { rcu_read_lock(); @@ -238,7 +239,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ @@ -348,6 +350,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); + map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) @@ -553,6 +556,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" + "map_extra:\t%#llx\n" "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", @@ -561,6 +565,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, + (unsigned long long)map->map_extra, bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); @@ -810,7 +815,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id +#define BPF_MAP_CREATE_LAST_FIELD map_extra /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -831,6 +836,10 @@ static int map_create(union bpf_attr *attr) return -EINVAL; } + if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_extra != 0) + return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -1080,6 +1089,14 @@ static int map_lookup_elem(union bpf_attr *attr) if (!value) goto free_key; + if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { + if (copy_from_user(value, uvalue, value_size)) + err = -EFAULT; + else + err = bpf_map_copy_value(map, key, value, attr->flags); + goto free_value; + } + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -3881,6 +3898,7 @@ static int bpf_map_get_info_by_fd(struct file *file, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6616e325803..3c8aa7df1773 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5002,7 +5002,10 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env, return -EINVAL; } break; - + case BPF_MAP_TYPE_BLOOM_FILTER: + if (meta->func_id == BPF_FUNC_map_peek_elem) + *arg_type = ARG_PTR_TO_MAP_VALUE; + break; default: break; } @@ -5577,6 +5580,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_task_storage_delete) goto error; break; + case BPF_MAP_TYPE_BLOOM_FILTER: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -5644,13 +5652,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; - case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_pop_elem: - case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK && + map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) + goto error; + break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { -- cgit v1.2.3 From d6aef08a872b9e23eecc92d0e92393473b13c497 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 28 Oct 2021 12:04:54 +0530 Subject: bpf: Add bpf_kallsyms_lookup_name helper This helper allows us to get the address of a kernel symbol from inside a BPF_PROG_TYPE_SYSCALL prog (used by gen_loader), so that we can relocate typeless ksym vars. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211028063501.2239335-2-memxor@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 16 ++++++++++++++++ kernel/bpf/syscall.c | 27 +++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 16 ++++++++++++++++ 4 files changed, 60 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 50105e0b8fcc..6deebf8bf78f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2110,6 +2110,7 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; +extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8bead4aa3ad0..bd0c9f0487f6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4923,6 +4923,21 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *unix_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5104,6 +5119,7 @@ union bpf_attr { FN(get_branch_snapshot), \ FN(trace_vprintk), \ FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f7c2c6354add..e12a217ead34 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4781,6 +4781,31 @@ static const struct bpf_func_proto bpf_sys_close_proto = { .arg1_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) +{ + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + if (!bpf_dump_raw_ok(current_cred())) + return -EPERM; + + *res = kallsyms_lookup_name(name); + return *res ? 0 : -ENOENT; +} + +const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { + .func = bpf_kallsyms_lookup_name, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; + static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -4791,6 +4816,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; + case BPF_FUNC_kallsyms_lookup_name: + return &bpf_kallsyms_lookup_name_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8bead4aa3ad0..bd0c9f0487f6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4923,6 +4923,21 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *unix_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5104,6 +5119,7 @@ union bpf_attr { FN(get_branch_snapshot), \ FN(trace_vprintk), \ FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 7303524e04af49a47991e19f895c3b8cdc3796c7 Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Fri, 29 Oct 2021 22:12:14 +0800 Subject: skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian Signed-off-by: Daniel Borkmann Reviewed-by: Cong Wang Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com --- include/linux/skmsg.h | 18 ++++++++++++++++-- net/core/skmsg.c | 43 +++++++++++++++++++++++++++++++++---------- 2 files changed, 49 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 14ab0c0bc924..94e2a1f6e58d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -508,8 +508,22 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) #if IS_ENABLED(CONFIG_NET_SOCK_MSG) -/* We only have one bit so far. */ -#define BPF_F_PTR_MASK ~(BPF_F_INGRESS) +#define BPF_F_STRPARSER (1UL << 1) + +/* We only have two bits so far. */ +#define BPF_F_PTR_MASK ~(BPF_F_INGRESS | BPF_F_STRPARSER) + +static inline bool skb_bpf_strparser(const struct sk_buff *skb) +{ + unsigned long sk_redir = skb->_sk_redir; + + return sk_redir & BPF_F_STRPARSER; +} + +static inline void skb_bpf_set_strparser(struct sk_buff *skb) +{ + skb->_sk_redir |= BPF_F_STRPARSER; +} static inline bool skb_bpf_ingress(const struct sk_buff *skb) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2d6249b28928..9701a1404ccb 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -494,6 +494,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, } static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, + u32 off, u32 len, struct sk_psock *psock, struct sock *sk, struct sk_msg *msg) @@ -507,11 +508,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, */ if (skb_linearize(skb)) return -EAGAIN; - num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); + num_sge = skb_to_sgvec(skb, msg->sg.data, off, len); if (unlikely(num_sge < 0)) return num_sge; - copied = skb->len; + copied = len; msg->sg.start = 0; msg->sg.size = copied; msg->sg.end = num_sge; @@ -522,9 +523,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, return copied; } -static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb); +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len); -static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len) { struct sock *sk = psock->sk; struct sk_msg *msg; @@ -535,7 +538,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * correctly. */ if (unlikely(skb->sk == sk)) - return sk_psock_skb_ingress_self(psock, skb); + return sk_psock_skb_ingress_self(psock, skb, off, len); msg = sk_psock_create_ingress_msg(sk, skb); if (!msg) return -EAGAIN; @@ -547,7 +550,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * into user buffers. */ skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; @@ -557,7 +560,8 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * skb. In this case we do not need to check memory limits or skb_set_owner_r * because the skb is already accounted for here. */ -static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb) +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len) { struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); struct sock *sk = psock->sk; @@ -567,7 +571,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb return -EAGAIN; sk_msg_init(msg); skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; @@ -581,7 +585,7 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } - return sk_psock_skb_ingress(psock, skb); + return sk_psock_skb_ingress(psock, skb, off, len); } static void sk_psock_skb_state(struct sk_psock *psock, @@ -624,6 +628,12 @@ static void sk_psock_backlog(struct work_struct *work) while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; off = 0; + if (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); @@ -863,6 +873,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) * return code, but then didn't set a redirect interface. */ if (unlikely(!sk_other)) { + skb_bpf_redirect_clear(skb); sock_drop(from->sk, skb); return -EIO; } @@ -930,6 +941,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, { struct sock *sk_other; int err = 0; + u32 len, off; switch (verdict) { case __SK_PASS: @@ -937,6 +949,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { + skb_bpf_redirect_clear(skb); goto out_free; } @@ -949,7 +962,15 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { - err = sk_psock_skb_ingress_self(psock, skb); + len = skb->len; + off = 0; + if (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } + err = sk_psock_skb_ingress_self(psock, skb, off, len); } if (err < 0) { spin_lock_bh(&psock->ingress_lock); @@ -1015,6 +1036,8 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); + if (ret == SK_PASS) + skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } -- cgit v1.2.3 From 31a645aea4f8da5bb190ce322c6e5aacaef13855 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Mon, 25 Oct 2021 14:40:22 +0800 Subject: bpf: Factor out a helper to prepare trampoline for struct_ops prog Factor out a helper bpf_struct_ops_prepare_trampoline() to prepare trampoline for BPF_PROG_TYPE_STRUCT_OPS prog. It will be used by .test_run callback in following patch. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20211025064025.2567443-2-houtao1@huawei.com --- include/linux/bpf.h | 4 ++++ kernel/bpf/bpf_struct_ops.c | 29 +++++++++++++++++++---------- 2 files changed, 23 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6deebf8bf78f..aabd3540aaaf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1000,6 +1000,10 @@ bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, + struct bpf_prog *prog, + const struct btf_func_model *model, + void *image, void *image_end); static inline bool bpf_try_module_get(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 9abcc33f02cf..44be101f2562 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -312,6 +312,20 @@ static int check_zero_holes(const struct btf_type *t, void *data) return 0; } +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, + struct bpf_prog *prog, + const struct btf_func_model *model, + void *image, void *image_end) +{ + u32 flags; + + tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; + tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; + flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0; + return arch_prepare_bpf_trampoline(NULL, image, image_end, + model, flags, tprogs, NULL); +} + static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { @@ -323,7 +337,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_tramp_progs *tprogs = NULL; void *udata, *kdata; int prog_fd, err = 0; - void *image; + void *image, *image_end; u32 i; if (flags) @@ -363,12 +377,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, udata = &uvalue->data; kdata = &kvalue->data; image = st_map->image; + image_end = st_map->image + PAGE_SIZE; for_each_member(i, t, member) { const struct btf_type *mtype, *ptype; struct bpf_prog *prog; u32 moff; - u32 flags; moff = btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); @@ -430,14 +444,9 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, goto reset_unlock; } - tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; - tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; - flags = st_ops->func_models[i].ret_size > 0 ? - BPF_TRAMP_F_RET_FENTRY_RET : 0; - err = arch_prepare_bpf_trampoline(NULL, image, - st_map->image + PAGE_SIZE, - &st_ops->func_models[i], - flags, tprogs, NULL); + err = bpf_struct_ops_prepare_trampoline(tprogs, prog, + &st_ops->func_models[i], + image, image_end); if (err < 0) goto reset_unlock; -- cgit v1.2.3 From 35346ab64132d0f5919b06932d708c0d10360553 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Mon, 25 Oct 2021 14:40:23 +0800 Subject: bpf: Factor out helpers for ctx access checking Factor out two helpers to check the read access of ctx for raw tp and BTF function. bpf_tracing_ctx_access() is used to check the read access to argument is valid, and bpf_tracing_btf_ctx_access() checks whether the btf type of argument is valid besides the checking of argument read. bpf_tracing_btf_ctx_access() will be used by the following patch. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20211025064025.2567443-3-houtao1@huawei.com --- include/linux/bpf.h | 23 +++++++++++++++++++++++ kernel/trace/bpf_trace.c | 16 ++-------------- net/ipv4/bpf_tcp_ca.c | 9 +-------- 3 files changed, 26 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aabd3540aaaf..67f71e7def56 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1650,6 +1650,29 @@ bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); + +static inline bool bpf_tracing_ctx_access(int off, int size, + enum bpf_access_type type) +{ + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + return true; +} + +static inline bool bpf_tracing_btf_ctx_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (!bpf_tracing_ctx_access(off, size, type)) + return false; + return btf_ctx_access(off, size, type, prog, info); +} + int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cbcd0d6fca7c..7396488793ff 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1646,13 +1646,7 @@ static bool raw_tp_prog_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - return true; + return bpf_tracing_ctx_access(off, size, type); } static bool tracing_prog_is_valid_access(int off, int size, @@ -1660,13 +1654,7 @@ static bool tracing_prog_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - return btf_ctx_access(off, size, type, prog, info); + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); } int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog, diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 57709ac09fb2..2cf02b4d77fb 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -81,14 +81,7 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - - if (!btf_ctx_access(off, size, type, prog, info)) + if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info)) return false; if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) -- cgit v1.2.3 From c196906d50e360d82ed9aa5596a9d0ce89b7ab78 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Mon, 25 Oct 2021 14:40:24 +0800 Subject: bpf: Add dummy BPF STRUCT_OPS for test purpose Currently the test of BPF STRUCT_OPS depends on the specific bpf implementation of tcp_congestion_ops, but it can not cover all basic functionalities (e.g, return value handling), so introduce a dummy BPF STRUCT_OPS for test purpose. Loading a bpf_dummy_ops implementation from userspace is prohibited, and its only purpose is to run BPF_PROG_TYPE_STRUCT_OPS program through bpf(BPF_PROG_TEST_RUN). Now programs for test_1() & test_2() are supported. The following three cases are exercised in bpf_dummy_struct_ops_test_run(): (1) test and check the value returned from state arg in test_1(state) The content of state is copied from userspace pointer and copied back after calling test_1(state). The user pointer is saved in an u64 array and the array address is passed through ctx_in. (2) test and check the return value of test_1(NULL) Just simulate the case in which an invalid input argument is passed in. (3) test multiple arguments passing in test_2(state, ...) 5 arguments are passed through ctx_in in form of u64 array. The first element of array is userspace pointer of state and others 4 arguments follow. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20211025064025.2567443-4-houtao1@huawei.com --- include/linux/bpf.h | 16 +++ kernel/bpf/bpf_struct_ops.c | 3 + kernel/bpf/bpf_struct_ops_types.h | 3 + net/bpf/Makefile | 3 + net/bpf/bpf_dummy_struct_ops.c | 200 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 225 insertions(+) create mode 100644 net/bpf/bpf_dummy_struct_ops.c (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 67f71e7def56..c098089c1b54 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1018,6 +1018,22 @@ static inline void bpf_module_put(const void *data, struct module *owner) else module_put(owner); } + +#ifdef CONFIG_NET +/* Define it here to avoid the use of forward declaration */ +struct bpf_dummy_ops_state { + int val; +}; + +struct bpf_dummy_ops { + int (*test_1)(struct bpf_dummy_ops_state *cb); + int (*test_2)(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2, + char a3, unsigned long a4); +}; + +int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +#endif #else static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 44be101f2562..8ecfe4752769 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -93,6 +93,9 @@ const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; const struct bpf_prog_ops bpf_struct_ops_prog_ops = { +#ifdef CONFIG_NET + .test_run = bpf_struct_ops_test_run, +#endif }; static const struct btf_type *module_type; diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h index 066d83ea1c99..5678a9ddf817 100644 --- a/kernel/bpf/bpf_struct_ops_types.h +++ b/kernel/bpf/bpf_struct_ops_types.h @@ -2,6 +2,9 @@ /* internal file - do not include directly */ #ifdef CONFIG_BPF_JIT +#ifdef CONFIG_NET +BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) +#endif #ifdef CONFIG_INET #include BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) diff --git a/net/bpf/Makefile b/net/bpf/Makefile index 1c0a98d8c28f..1ebe270bde23 100644 --- a/net/bpf/Makefile +++ b/net/bpf/Makefile @@ -1,2 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_BPF_SYSCALL) := test_run.o +ifeq ($(CONFIG_BPF_JIT),y) +obj-$(CONFIG_BPF_SYSCALL) += bpf_dummy_struct_ops.o +endif diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c new file mode 100644 index 000000000000..fbc896323bec --- /dev/null +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021. Huawei Technologies Co., Ltd + */ +#include +#include +#include +#include + +extern struct bpf_struct_ops bpf_bpf_dummy_ops; + +/* A common type for test_N with return value in bpf_dummy_ops */ +typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); + +struct bpf_dummy_ops_test_args { + u64 args[MAX_BPF_FUNC_ARGS]; + struct bpf_dummy_ops_state state; +}; + +static struct bpf_dummy_ops_test_args * +dummy_ops_init_args(const union bpf_attr *kattr, unsigned int nr) +{ + __u32 size_in; + struct bpf_dummy_ops_test_args *args; + void __user *ctx_in; + void __user *u_state; + + size_in = kattr->test.ctx_size_in; + if (size_in != sizeof(u64) * nr) + return ERR_PTR(-EINVAL); + + args = kzalloc(sizeof(*args), GFP_KERNEL); + if (!args) + return ERR_PTR(-ENOMEM); + + ctx_in = u64_to_user_ptr(kattr->test.ctx_in); + if (copy_from_user(args->args, ctx_in, size_in)) + goto out; + + /* args[0] is 0 means state argument of test_N will be NULL */ + u_state = u64_to_user_ptr(args->args[0]); + if (u_state && copy_from_user(&args->state, u_state, + sizeof(args->state))) + goto out; + + return args; +out: + kfree(args); + return ERR_PTR(-EFAULT); +} + +static int dummy_ops_copy_args(struct bpf_dummy_ops_test_args *args) +{ + void __user *u_state; + + u_state = u64_to_user_ptr(args->args[0]); + if (u_state && copy_to_user(u_state, &args->state, sizeof(args->state))) + return -EFAULT; + + return 0; +} + +static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args) +{ + dummy_ops_test_ret_fn test = (void *)image; + struct bpf_dummy_ops_state *state = NULL; + + /* state needs to be NULL if args[0] is 0 */ + if (args->args[0]) + state = &args->state; + return test(state, args->args[1], args->args[2], + args->args[3], args->args[4]); +} + +int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + const struct bpf_struct_ops *st_ops = &bpf_bpf_dummy_ops; + const struct btf_type *func_proto; + struct bpf_dummy_ops_test_args *args; + struct bpf_tramp_progs *tprogs; + void *image = NULL; + unsigned int op_idx; + int prog_ret; + int err; + + if (prog->aux->attach_btf_id != st_ops->type_id) + return -EOPNOTSUPP; + + func_proto = prog->aux->attach_func_proto; + args = dummy_ops_init_args(kattr, btf_type_vlen(func_proto)); + if (IS_ERR(args)) + return PTR_ERR(args); + + tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); + if (!tprogs) { + err = -ENOMEM; + goto out; + } + + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) { + err = -ENOMEM; + goto out; + } + set_vm_flush_reset_perms(image); + + op_idx = prog->expected_attach_type; + err = bpf_struct_ops_prepare_trampoline(tprogs, prog, + &st_ops->func_models[op_idx], + image, image + PAGE_SIZE); + if (err < 0) + goto out; + + set_memory_ro((long)image, 1); + set_memory_x((long)image, 1); + prog_ret = dummy_ops_call_op(image, args); + + err = dummy_ops_copy_args(args); + if (err) + goto out; + if (put_user(prog_ret, &uattr->test.retval)) + err = -EFAULT; +out: + kfree(args); + bpf_jit_free_exec(image); + kfree(tprogs); + return err; +} + +static int bpf_dummy_init(struct btf *btf) +{ + return 0; +} + +static bool bpf_dummy_ops_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); +} + +static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id) +{ + const struct btf_type *state; + s32 type_id; + int err; + + type_id = btf_find_by_name_kind(btf, "bpf_dummy_ops_state", + BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + + state = btf_type_by_id(btf, type_id); + if (t != state) { + bpf_log(log, "only access to bpf_dummy_ops_state is supported\n"); + return -EACCES; + } + + err = btf_struct_access(log, btf, t, off, size, atype, next_btf_id); + if (err < 0) + return err; + + return atype == BPF_READ ? err : NOT_INIT; +} + +static const struct bpf_verifier_ops bpf_dummy_verifier_ops = { + .is_valid_access = bpf_dummy_ops_is_valid_access, + .btf_struct_access = bpf_dummy_ops_btf_struct_access, +}; + +static int bpf_dummy_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + return -EOPNOTSUPP; +} + +static int bpf_dummy_reg(void *kdata) +{ + return -EOPNOTSUPP; +} + +static void bpf_dummy_unreg(void *kdata) +{ +} + +struct bpf_struct_ops bpf_bpf_dummy_ops = { + .verifier_ops = &bpf_dummy_verifier_ops, + .init = bpf_dummy_init, + .init_member = bpf_dummy_init_member, + .reg = bpf_dummy_reg, + .unreg = bpf_dummy_unreg, + .name = "bpf_dummy_ops", +}; -- cgit v1.2.3 From 8845b4681bf44b9d2d2badf2c67cf476e42a86bd Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Fri, 29 Oct 2021 15:49:08 -0700 Subject: bpf: Add alignment padding for "map_extra" + consolidate holes This patch makes 2 changes regarding alignment padding for the "map_extra" field. 1) In the kernel header, "map_extra" and "btf_value_type_id" are rearranged to consolidate the hole. Before: struct bpf_map { ... u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ /* XXX 4 bytes hole, try to pack */ u64 map_extra; /* 48 8 */ int spin_lock_off; /* 56 4 */ int timer_off; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ u32 id; /* 64 4 */ int numa_node; /* 68 4 */ ... bool frozen; /* 117 1 */ /* XXX 10 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ ... struct work_struct work; /* 144 72 */ /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */ struct mutex freeze_mutex; /* 216 144 */ /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */ u64 writecnt; /* 360 8 */ /* size: 384, cachelines: 6, members: 26 */ /* sum members: 354, holes: 2, sum holes: 14 */ /* padding: 16 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 10 */ } __attribute__((__aligned__(64))); After: struct bpf_map { ... u32 max_entries; /* 36 4 */ u64 map_extra; /* 40 8 */ u32 map_flags; /* 48 4 */ int spin_lock_off; /* 52 4 */ int timer_off; /* 56 4 */ u32 id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ int numa_node; /* 64 4 */ ... bool frozen /* 113 1 */ /* XXX 14 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ ... struct work_struct work; /* 144 72 */ /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */ struct mutex freeze_mutex; /* 216 144 */ /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */ u64 writecnt; /* 360 8 */ /* size: 384, cachelines: 6, members: 26 */ /* sum members: 354, holes: 1, sum holes: 14 */ /* padding: 16 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 14 */ } __attribute__((__aligned__(64))); 2) Add alignment padding to the bpf_map_info struct More details can be found in commit 36f9814a494a ("bpf: fix uapi hole for 32 bit compat applications") Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211029224909.1721024-3-joannekoong@fb.com --- include/linux/bpf.h | 6 +++--- include/uapi/linux/bpf.h | 1 + tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c098089c1b54..f6743d4bb531 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -168,23 +168,23 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; - u32 map_flags; u64 map_extra; /* any per-map-type extra fields */ + u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; + u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif char name[BPF_OBJ_NAME_LEN]; - u32 btf_vmlinux_value_type_id; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ - /* 22 bytes hole */ + /* 14 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bd0c9f0487f6..ba5af15e25f5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5662,6 +5662,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ __u64 map_extra; } __attribute__((aligned(8))); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bd0c9f0487f6..ba5af15e25f5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5662,6 +5662,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ __u64 map_extra; } __attribute__((aligned(8))); -- cgit v1.2.3