From ec5e099d6e941668d121ea9ca7057f4fa00830b0 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 6 Apr 2016 18:43:22 -0700 Subject: perf: optimize perf_fetch_caller_regs avoid memset in perf_fetch_caller_regs, since it's the critical path of all tracepoints. It's called from perf_sw_event_sched, perf_event_task_sched_in and all of perf_trace_##call with this_cpu_ptr(&__perf_regs[..]) which are zero initialized by perpcu init logic and subsequent call to perf_arch_fetch_caller_regs initializes the same fields on all archs, so we can safely drop memset from all of the above cases and move it into perf_ftrace_function_call that calls it with stack allocated pt_regs. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/perf_event.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f291275ffd71..e89f7199c223 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -882,8 +882,6 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { - memset(regs, 0, sizeof(*regs)); - perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } -- cgit v1.2.3 From 1e1dcd93b468901e114f279c94a0b356adc5e7cd Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 6 Apr 2016 18:43:24 -0700 Subject: perf: split perf_trace_buf_prepare into alloc and update parts split allows to move expensive update of 'struct trace_entry' to later phase. Repurpose unused 1st argument of perf_tp_event() to indicate event type. While splitting use temp variable 'rctx' instead of '*rctx' to avoid unnecessary loads done by the compiler due to -fno-strict-aliasing Signed-off-by: Alexei Starovoitov Acked-by: Peter Zijlstra (Intel) Signed-off-by: David S. Miller --- include/linux/perf_event.h | 2 +- include/linux/trace_events.h | 8 ++++---- include/trace/perf.h | 8 ++++---- kernel/events/core.c | 6 ++++-- kernel/trace/trace_event_perf.c | 39 ++++++++++++++++++++------------------- kernel/trace/trace_kprobe.c | 10 ++++++---- kernel/trace/trace_syscalls.c | 13 +++++++------ kernel/trace/trace_uprobe.c | 5 +++-- 8 files changed, 49 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e89f7199c223..eb41b535ef38 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1016,7 +1016,7 @@ static inline bool perf_paranoid_kernel(void) } extern void perf_event_init(void); -extern void perf_tp_event(u64 addr, u64 count, void *record, +extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 0810f81b6db2..56f795e6a093 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -605,15 +605,15 @@ extern void perf_trace_del(struct perf_event *event, int flags); extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); -extern void *perf_trace_buf_prepare(int size, unsigned short type, - struct pt_regs **regs, int *rctxp); +void perf_trace_buf_update(void *record, u16 type); +void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); static inline void -perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, +perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, u64 count, struct pt_regs *regs, void *head, struct task_struct *task) { - perf_tp_event(addr, count, raw_data, size, regs, head, rctx, task); + perf_tp_event(type, count, raw_data, size, regs, head, rctx, task); } #endif diff --git a/include/trace/perf.h b/include/trace/perf.h index 6f7e37869065..77cd9043b7e4 100644 --- a/include/trace/perf.h +++ b/include/trace/perf.h @@ -53,8 +53,7 @@ perf_trace_##call(void *__data, proto) \ sizeof(u64)); \ __entry_size -= sizeof(u32); \ \ - entry = perf_trace_buf_prepare(__entry_size, \ - event_call->event.type, &__regs, &rctx); \ + entry = perf_trace_buf_alloc(__entry_size, &__regs, &rctx); \ if (!entry) \ return; \ \ @@ -64,8 +63,9 @@ perf_trace_##call(void *__data, proto) \ \ { assign; } \ \ - perf_trace_buf_submit(entry, __entry_size, rctx, 0, \ - __count, __regs, head, __task); \ + perf_trace_buf_submit(entry, __entry_size, rctx, \ + event_call->event.type, __count, __regs, \ + head, __task); \ } /* diff --git a/kernel/events/core.c b/kernel/events/core.c index de24fbce5277..d8512883c0a0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6987,7 +6987,7 @@ static int perf_tp_event_match(struct perf_event *event, return 1; } -void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, +void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task) { @@ -6999,9 +6999,11 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, .data = record, }; - perf_sample_data_init(&data, addr, 0); + perf_sample_data_init(&data, 0, 0); data.raw = &raw; + perf_trace_buf_update(record, event_type); + hlist_for_each_entry_rcu(event, head, hlist_entry) { if (perf_tp_event_match(event, &data, regs)) perf_swevent_event(event, count, &data, regs); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 7a68afca8249..5a927075977f 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -260,42 +260,43 @@ void perf_trace_del(struct perf_event *p_event, int flags) tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event); } -void *perf_trace_buf_prepare(int size, unsigned short type, - struct pt_regs **regs, int *rctxp) +void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp) { - struct trace_entry *entry; - unsigned long flags; char *raw_data; - int pc; + int rctx; BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long)); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "perf buffer not large enough")) + "perf buffer not large enough")) return NULL; - pc = preempt_count(); - - *rctxp = perf_swevent_get_recursion_context(); - if (*rctxp < 0) + *rctxp = rctx = perf_swevent_get_recursion_context(); + if (rctx < 0) return NULL; if (regs) - *regs = this_cpu_ptr(&__perf_regs[*rctxp]); - raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]); + *regs = this_cpu_ptr(&__perf_regs[rctx]); + raw_data = this_cpu_ptr(perf_trace_buf[rctx]); /* zero the dead bytes from align to not leak stack to user */ memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64)); + return raw_data; +} +EXPORT_SYMBOL_GPL(perf_trace_buf_alloc); +NOKPROBE_SYMBOL(perf_trace_buf_alloc); + +void perf_trace_buf_update(void *record, u16 type) +{ + struct trace_entry *entry = record; + int pc = preempt_count(); + unsigned long flags; - entry = (struct trace_entry *)raw_data; local_save_flags(flags); tracing_generic_entry_update(entry, flags, pc); entry->type = type; - - return raw_data; } -EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); -NOKPROBE_SYMBOL(perf_trace_buf_prepare); +NOKPROBE_SYMBOL(perf_trace_buf_update); #ifdef CONFIG_FUNCTION_TRACER static void @@ -319,13 +320,13 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, memset(®s, 0, sizeof(regs)); perf_fetch_caller_regs(®s); - entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx); + entry = perf_trace_buf_alloc(ENTRY_SIZE, NULL, &rctx); if (!entry) return; entry->ip = ip; entry->parent_ip = parent_ip; - perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0, + perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN, 1, ®s, head, NULL); #undef ENTRY_SIZE diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 919e0ddd8fcc..5546eec0505f 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1149,14 +1149,15 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); + entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) return; entry->ip = (unsigned long)tk->rp.kp.addr; memset(&entry[1], 0, dsize); store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); - perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); + perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, + head, NULL); } NOKPROBE_SYMBOL(kprobe_perf_func); @@ -1184,14 +1185,15 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); + entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) return; entry->func = (unsigned long)tk->rp.kp.addr; entry->ret_ip = (unsigned long)ri->ret_addr; store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); - perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); + perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, + head, NULL); } NOKPROBE_SYMBOL(kretprobe_perf_func); #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index e78f364cc192..b2b6efc083a4 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -587,15 +587,16 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) size = ALIGN(size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, - sys_data->enter_event->event.type, NULL, &rctx); + rec = perf_trace_buf_alloc(size, NULL, &rctx); if (!rec) return; rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); + perf_trace_buf_submit(rec, size, rctx, + sys_data->enter_event->event.type, 1, regs, + head, NULL); } static int perf_sysenter_enable(struct trace_event_call *call) @@ -660,14 +661,14 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, - sys_data->exit_event->event.type, NULL, &rctx); + rec = perf_trace_buf_alloc(size, NULL, &rctx); if (!rec) return; rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); + perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type, + 1, regs, head, NULL); } static int perf_sysexit_enable(struct trace_event_call *call) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 7915142c89e4..c53485441c88 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1131,7 +1131,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, if (hlist_empty(head)) goto out; - entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); + entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) goto out; @@ -1152,7 +1152,8 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, memset(data + len, 0, size - esize - len); } - perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); + perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, + head, NULL); out: preempt_enable(); } -- cgit v1.2.3 From 9940d67c93b5bb7ddcf862b41b1847cb728186c4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 6 Apr 2016 18:43:27 -0700 Subject: bpf: support bpf_get_stackid() and bpf_perf_event_output() in tracepoint programs needs two wrapper functions to fetch 'struct pt_regs *' to convert tracepoint bpf context into kprobe bpf context to reuse existing helper functions Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + kernel/bpf/stackmap.c | 2 +- kernel/trace/bpf_trace.c | 42 +++++++++++++++++++++++++++++++++++++++++- 3 files changed, 43 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 21ee41b92e8a..198f6ace70ec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -160,6 +160,7 @@ struct bpf_array { #define MAX_TAIL_CALL_CNT 32 u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); +u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); void bpf_fd_array_map_clear(struct bpf_map *map); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 499d9e933f8e..35114725cf30 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -116,7 +116,7 @@ free_smap: return ERR_PTR(err); } -static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) { struct pt_regs *regs = (struct pt_regs *) (long) r1; struct bpf_map *map = (struct bpf_map *) (long) r2; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 3e5ebe3254d2..413ec5614180 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -340,12 +340,52 @@ static struct bpf_prog_type_list kprobe_tl = { .type = BPF_PROG_TYPE_KPROBE, }; +static u64 bpf_perf_event_output_tp(u64 r1, u64 r2, u64 index, u64 r4, u64 size) +{ + /* + * r1 points to perf tracepoint buffer where first 8 bytes are hidden + * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it + * from there and call the same bpf_perf_event_output() helper + */ + u64 ctx = *(long *)r1; + + return bpf_perf_event_output(ctx, r2, index, r4, size); +} + +static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { + .func = bpf_perf_event_output_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_STACK, + .arg5_type = ARG_CONST_STACK_SIZE, +}; + +static u64 bpf_get_stackid_tp(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + u64 ctx = *(long *)r1; + + return bpf_get_stackid(ctx, r2, r3, r4, r5); +} + +static const struct bpf_func_proto bpf_get_stackid_proto_tp = { + .func = bpf_get_stackid_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_perf_event_output: + return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: - return NULL; + return &bpf_get_stackid_proto_tp; default: return tracing_func_proto(func_id); } -- cgit v1.2.3 From 32bbe0078afe86a8bf4c67c6b3477781b15e94dc Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 6 Apr 2016 18:43:28 -0700 Subject: bpf: sanitize bpf tracepoint access during bpf program loading remember the last byte of ctx access and at the time of attaching the program to tracepoint check that the program doesn't access bytes beyond defined in tracepoint fields This also disallows access to __dynamic_array fields, but can be relaxed in the future. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/linux/trace_events.h | 1 + kernel/bpf/verifier.c | 6 +++++- kernel/events/core.c | 8 ++++++++ kernel/trace/trace_events.c | 18 ++++++++++++++++++ 5 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 198f6ace70ec..b2365a6eba3d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -131,6 +131,7 @@ struct bpf_prog_type_list { struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; + u32 max_ctx_offset; const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 56f795e6a093..fe6441203b59 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -569,6 +569,7 @@ extern int trace_define_field(struct trace_event_call *call, const char *type, int is_signed, int filter_type); extern int trace_add_event_call(struct trace_event_call *call); extern int trace_remove_event_call(struct trace_event_call *call); +extern int trace_event_get_offsets(struct trace_event_call *call); #define is_signed_type(type) (((type)(-1)) < (type)1) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2e08f8e9b771..58792fed5678 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -652,8 +652,12 @@ static int check_ctx_access(struct verifier_env *env, int off, int size, enum bpf_access_type t) { if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t)) + env->prog->aux->ops->is_valid_access(off, size, t)) { + /* remember the offset of last byte accessed in ctx */ + if (env->prog->aux->max_ctx_offset < off + size) + env->prog->aux->max_ctx_offset = off + size; return 0; + } verbose("invalid bpf_context access off=%d size=%d\n", off, size); return -EACCES; diff --git a/kernel/events/core.c b/kernel/events/core.c index e5ffe97d6166..9a01019ff7c8 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7133,6 +7133,14 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) return -EINVAL; } + if (is_tracepoint) { + int off = trace_event_get_offsets(event->tp_event); + + if (prog->aux->max_ctx_offset > off) { + bpf_prog_put(prog); + return -EACCES; + } + } event->tp_event->prog = prog; return 0; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 05ddc0820771..ced963049e0a 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -204,6 +204,24 @@ static void trace_destroy_fields(struct trace_event_call *call) } } +/* + * run-time version of trace_event_get_offsets_() that returns the last + * accessible offset of trace fields excluding __dynamic_array bytes + */ +int trace_event_get_offsets(struct trace_event_call *call) +{ + struct ftrace_event_field *tail; + struct list_head *head; + + head = trace_get_fields(call); + /* + * head->next points to the last field with the largest offset, + * since it was added last by trace_define_field() + */ + tail = list_first_entry(head, struct ftrace_event_field, link); + return tail->offset + tail->size; +} + int trace_event_raw_init(struct trace_event_call *call) { int id; -- cgit v1.2.3