diff options
Diffstat (limited to 'kernel/trace')
-rw-r--r-- | kernel/trace/Kconfig | 6 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 141 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 4 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 20 | ||||
-rw-r--r-- | kernel/trace/trace.c | 48 | ||||
-rw-r--r-- | kernel/trace/trace.h | 20 | ||||
-rw-r--r-- | kernel/trace/trace_benchmark.c | 4 | ||||
-rw-r--r-- | kernel/trace/trace_entries.h | 8 | ||||
-rw-r--r-- | kernel/trace/trace_events.c | 36 | ||||
-rw-r--r-- | kernel/trace/trace_events_filter.c | 38 | ||||
-rw-r--r-- | kernel/trace/trace_events_hist.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace_events_trigger.c | 21 | ||||
-rw-r--r-- | kernel/trace/trace_export.c | 9 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 31 | ||||
-rw-r--r-- | kernel/trace/trace_stack.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace_uprobe.c | 57 |
16 files changed, 346 insertions, 113 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index c4f0f2e..dd6c0a2 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -110,11 +110,7 @@ config GENERIC_TRACER # config TRACING_SUPPORT bool - # PPC32 has no irqflags tracing support, but it can use most of the - # tracers anyway, they were tested to build and work. Note that new - # exceptions to this list aren't welcomed, better implement the - # irqflags tracing for your architecture. - depends on TRACE_IRQFLAGS_SUPPORT || PPC32 + depends on TRACE_IRQFLAGS_SUPPORT depends on STACKTRACE_SUPPORT default y diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d88e96d..0ae6829 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -14,12 +14,14 @@ #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/kprobes.h> +#include <linux/syscalls.h> #include <linux/error-injection.h> #include "trace_probe.h" #include "trace.h" u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); /** * trace_call_bpf - invoke BPF program @@ -474,8 +476,6 @@ BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; - if (unlikely(in_interrupt())) - return -EINVAL; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; @@ -564,6 +564,10 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_str_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; +#endif default: return NULL; } @@ -577,6 +581,8 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE @@ -664,6 +670,25 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack_tp, void *, tp_buff, void *, buf, u32, size, + u64, flags) +{ + struct pt_regs *regs = *(struct pt_regs **)tp_buff; + + return bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); +} + +static const struct bpf_func_proto bpf_get_stack_proto_tp = { + .func = bpf_get_stack_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -672,6 +697,8 @@ tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_tp; default: return tracing_func_proto(func_id, prog); } @@ -734,6 +761,8 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_tp; case BPF_FUNC_perf_prog_read_value: return &bpf_perf_prog_read_value_proto; default: @@ -744,7 +773,7 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) /* * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp * to avoid potential recursive reuse issue when/if tracepoints are added - * inside bpf_*_event_output and/or bpf_get_stack_id + * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack */ static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs); BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args, @@ -787,6 +816,26 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args, + void *, buf, u32, size, u64, flags) +{ + struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + + perf_fetch_caller_regs(regs); + return bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); +} + +static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { + .func = bpf_get_stack_raw_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -795,6 +844,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_raw_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_raw_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_raw_tp; default: return tracing_func_proto(func_id, prog); } @@ -833,8 +884,14 @@ static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type return false; if (type != BPF_READ) return false; - if (off % size != 0) - return false; + if (off % size != 0) { + if (sizeof(unsigned long) != 4) + return false; + if (size != 8) + return false; + if (off % size != 4) + return false; + } switch (off) { case bpf_ctx_range(struct bpf_perf_event_data, sample_period): @@ -959,6 +1016,8 @@ void perf_event_detach_bpf_prog(struct perf_event *event) old_array = event->tp_event->prog_array; ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array); + if (ret == -ENOENT) + goto unlock; if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { @@ -977,6 +1036,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) { struct perf_event_query_bpf __user *uquery = info; struct perf_event_query_bpf query = {}; + u32 *ids, prog_cnt, ids_len; int ret; if (!capable(CAP_SYS_ADMIN)) @@ -985,16 +1045,32 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) return -EINVAL; if (copy_from_user(&query, uquery, sizeof(query))) return -EFAULT; - if (query.ids_len > BPF_TRACE_MAX_PROGS) + + ids_len = query.ids_len; + if (ids_len > BPF_TRACE_MAX_PROGS) return -E2BIG; + ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN); + if (!ids) + return -ENOMEM; + /* + * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which + * is required when user only wants to check for uquery->prog_cnt. + * There is no need to check for it since the case is handled + * gracefully in bpf_prog_array_copy_info. + */ mutex_lock(&bpf_event_mutex); ret = bpf_prog_array_copy_info(event->tp_event->prog_array, - uquery->ids, - query.ids_len, - &uquery->prog_cnt); + ids, + ids_len, + &prog_cnt); mutex_unlock(&bpf_event_mutex); + if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) || + copy_to_user(uquery->ids, ids, ids_len * sizeof(u32))) + ret = -EFAULT; + + kfree(ids); return ret; } @@ -1100,3 +1176,50 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) mutex_unlock(&bpf_event_mutex); return err; } + +int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, + u32 *fd_type, const char **buf, + u64 *probe_offset, u64 *probe_addr) +{ + bool is_tracepoint, is_syscall_tp; + struct bpf_prog *prog; + int flags, err = 0; + + prog = event->prog; + if (!prog) + return -ENOENT; + + /* not supporting BPF_PROG_TYPE_PERF_EVENT yet */ + if (prog->type == BPF_PROG_TYPE_PERF_EVENT) + return -EOPNOTSUPP; + + *prog_id = prog->aux->id; + flags = event->tp_event->flags; + is_tracepoint = flags & TRACE_EVENT_FL_TRACEPOINT; + is_syscall_tp = is_syscall_trace_event(event->tp_event); + + if (is_tracepoint || is_syscall_tp) { + *buf = is_tracepoint ? event->tp_event->tp->name + : event->tp_event->name; + *fd_type = BPF_FD_TYPE_TRACEPOINT; + *probe_offset = 0x0; + *probe_addr = 0x0; + } else { + /* kprobe/uprobe */ + err = -EOPNOTSUPP; +#ifdef CONFIG_KPROBE_EVENTS + if (flags & TRACE_EVENT_FL_KPROBE) + err = bpf_get_kprobe_info(event, fd_type, buf, + probe_offset, probe_addr, + event->attr.type == PERF_TYPE_TRACEPOINT); +#endif +#ifdef CONFIG_UPROBE_EVENTS + if (flags & TRACE_EVENT_FL_UPROBE) + err = bpf_get_uprobe_info(event, fd_type, buf, + probe_offset, + event->attr.type == PERF_TYPE_TRACEPOINT); +#endif + } + + return err; +} diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 16bbf06..8d83bcf 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5514,10 +5514,10 @@ static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer) ftrace_create_filter_files(&global_ops, d_tracer); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - trace_create_file("set_graph_function", 0444, d_tracer, + trace_create_file("set_graph_function", 0644, d_tracer, NULL, &ftrace_graph_fops); - trace_create_file("set_graph_notrace", 0444, d_tracer, + trace_create_file("set_graph_notrace", 0644, d_tracer, NULL, &ftrace_graph_notrace_fops); #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c9cb976..6a46af2 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -809,7 +809,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); * * You can see, it is legitimate for the previous pointer of * the head (or any page) not to point back to itself. But only - * temporarially. + * temporarily. */ #define RB_PAGE_NORMAL 0UL @@ -906,7 +906,7 @@ static void rb_list_head_clear(struct list_head *list) } /* - * rb_head_page_dactivate - clears head page ptr (for free list) + * rb_head_page_deactivate - clears head page ptr (for free list) */ static void rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer) @@ -1780,7 +1780,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, put_online_cpus(); } else { - /* Make sure this CPU has been intitialized */ + /* Make sure this CPU has been initialized */ if (!cpumask_test_cpu(cpu_id, buffer->cpumask)) goto out; @@ -2325,7 +2325,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, /* * If we need to add a timestamp, then we - * add it to the start of the resevered space. + * add it to the start of the reserved space. */ if (unlikely(info->add_timestamp)) { bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer); @@ -2681,7 +2681,7 @@ trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) * ring_buffer_nest_start - Allow to trace while nested * @buffer: The ring buffer to modify * - * The ring buffer has a safty mechanism to prevent recursion. + * The ring buffer has a safety mechanism to prevent recursion. * But there may be a case where a trace needs to be done while * tracing something else. In this case, calling this function * will allow this function to nest within a currently active @@ -2699,7 +2699,7 @@ void ring_buffer_nest_start(struct ring_buffer *buffer) preempt_disable_notrace(); cpu = raw_smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; - /* This is the shift value for the above recusive locking */ + /* This is the shift value for the above recursive locking */ cpu_buffer->nest += NESTED_BITS; } @@ -2718,7 +2718,7 @@ void ring_buffer_nest_end(struct ring_buffer *buffer) /* disabled by ring_buffer_nest_start() */ cpu = raw_smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; - /* This is the shift value for the above recusive locking */ + /* This is the shift value for the above recursive locking */ cpu_buffer->nest -= NESTED_BITS; preempt_enable_notrace(); } @@ -2907,7 +2907,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, * @buffer: the ring buffer to reserve from * @length: the length of the data to reserve (excluding event header) * - * Returns a reseverd event on the ring buffer to copy directly to. + * Returns a reserved event on the ring buffer to copy directly to. * The user of this interface will need to get the body to write into * and can use the ring_buffer_event_data() interface. * @@ -3009,7 +3009,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, * This function lets the user discard an event in the ring buffer * and then that event will not be read later. * - * This function only works if it is called before the the item has been + * This function only works if it is called before the item has been * committed. It will try to free the event from the ring buffer * if another event has not been added behind it. * @@ -4127,7 +4127,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume); * through the buffer. Memory is allocated, buffer recording * is disabled, and the iterator pointer is returned to the caller. * - * Disabling buffer recordng prevents the reading from being + * Disabling buffer recording prevents the reading from being * corrupted. This is not a consuming read, so a producer is not * expected. * diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index dfbcf9e..108ce3e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -893,7 +893,7 @@ int __trace_bputs(unsigned long ip, const char *str) EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT -static void tracing_snapshot_instance(struct trace_array *tr) +void tracing_snapshot_instance(struct trace_array *tr) { struct tracer *tracer = tr->current_trace; unsigned long flags; @@ -949,7 +949,7 @@ static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, struct trace_buffer *size_buf, int cpu_id); static void set_buffer_entries(struct trace_buffer *buf, unsigned long val); -static int alloc_snapshot(struct trace_array *tr) +int tracing_alloc_snapshot_instance(struct trace_array *tr) { int ret; @@ -995,7 +995,7 @@ int tracing_alloc_snapshot(void) struct trace_array *tr = &global_trace; int ret; - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); WARN_ON(ret < 0); return ret; @@ -1165,7 +1165,7 @@ static struct { { trace_clock, "perf", 1 }, { ktime_get_mono_fast_ns, "mono", 1 }, { ktime_get_raw_fast_ns, "mono_raw", 1 }, - { ktime_get_mono_fast_ns, "boot", 1 }, + { ktime_get_boot_fast_ns, "boot", 1 }, ARCH_TRACE_CLOCKS }; @@ -4395,8 +4395,7 @@ static int trace_set_options(struct trace_array *tr, char *option) { char *cmp; int neg = 0; - int ret = -ENODEV; - int i; + int ret; size_t orig_len = strlen(option); cmp = strstrip(option); @@ -4408,16 +4407,12 @@ static int trace_set_options(struct trace_array *tr, char *option) mutex_lock(&trace_types_lock); - for (i = 0; trace_options[i]; i++) { - if (strcmp(cmp, trace_options[i]) == 0) { - ret = set_tracer_flag(tr, 1 << i, !neg); - break; - } - } - + ret = match_string(trace_options, -1, cmp); /* If no option could be set, test the specific tracer options */ - if (!trace_options[i]) + if (ret < 0) ret = set_tracer_option(tr, cmp, neg); + else + ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); @@ -5408,7 +5403,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) #ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) goto out; } @@ -6074,6 +6069,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, { struct trace_array *tr = filp->private_data; struct ring_buffer_event *event; + enum event_trigger_type tt = ETT_NONE; struct ring_buffer *buffer; struct print_entry *entry; unsigned long irq_flags; @@ -6122,6 +6118,12 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, written = cnt; len = cnt; + if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) { + /* do not add \n before testing triggers, but add \0 */ + entry->buf[cnt] = '\0'; + tt = event_triggers_call(tr->trace_marker_file, entry, event); + } + if (entry->buf[cnt - 1] != '\n') { entry->buf[cnt] = '\n'; entry->buf[cnt + 1] = '\0'; @@ -6130,6 +6132,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, __buffer_unlock_commit(buffer, event); + if (tt) + event_triggers_post_call(tr->trace_marker_file, tt); + if (written > 0) *fpos += written; @@ -6451,7 +6456,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, } #endif if (!tr->allocated_snapshot) { - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) break; } @@ -7179,7 +7184,7 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, return ret; out_reg: - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) goto out; @@ -7896,6 +7901,7 @@ static __init void create_trace_instances(struct dentry *d_tracer) static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) { + struct trace_event_file *file; int cpu; trace_create_file("available_tracers", 0444, d_tracer, @@ -7928,6 +7934,12 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("trace_marker", 0220, d_tracer, tr, &tracing_mark_fops); + file = __find_event_file(tr, "ftrace", "print"); + if (file && file->dir) + trace_create_file("trigger", 0644, file->dir, file, + &event_trigger_fops); + tr->trace_marker_file = file; + trace_create_file("trace_marker_raw", 0220, d_tracer, tr, &tracing_mark_raw_fops); @@ -8111,6 +8123,8 @@ static __init int tracer_init_tracefs(void) if (IS_ERR(d_tracer)) return 0; + event_trace_init(); + init_tracer_tracefs(&global_trace, d_tracer); ftrace_init_tracefs_toplevel(&global_trace, d_tracer); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6fb46a0..630c5a2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -259,6 +259,7 @@ struct trace_array { struct trace_options *topts; struct list_head systems; struct list_head events; + struct trace_event_file *trace_marker_file; cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ int ref; #ifdef CONFIG_FUNCTION_TRACER @@ -1334,7 +1335,7 @@ event_trigger_unlock_commit(struct trace_event_file *file, trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc); if (tt) - event_triggers_post_call(file, tt, entry, event); + event_triggers_post_call(file, tt); } /** @@ -1367,7 +1368,7 @@ event_trigger_unlock_commit_regs(struct trace_event_file *file, irq_flags, pc, regs); if (tt) - event_triggers_post_call(file, tt, entry, event); + event_triggers_post_call(file, tt); } #define FILTER_PRED_INVALID ((unsigned short)-1) @@ -1451,9 +1452,13 @@ trace_find_event_field(struct trace_event_call *call, char *name); extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); +extern int event_trace_init(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); +extern struct trace_event_file *__find_event_file(struct trace_array *tr, + const char *system, + const char *event); extern struct trace_event_file *find_event_file(struct trace_array *tr, const char *system, const char *event); @@ -1817,6 +1822,17 @@ static inline void __init trace_event_init(void) { } static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { } #endif +#ifdef CONFIG_TRACER_SNAPSHOT +void tracing_snapshot_instance(struct trace_array *tr); +int tracing_alloc_snapshot_instance(struct trace_array *tr); +#else +static inline void tracing_snapshot_instance(struct trace_array *tr) { } +static inline int tracing_alloc_snapshot_instance(struct trace_array *tr) +{ + return 0; +} +#endif + extern struct trace_iterator *tracepoint_print_iter; #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c index 22fee76..80e0b2a 100644 --- a/kernel/trace/trace_benchmark.c +++ b/kernel/trace/trace_benchmark.c @@ -159,13 +159,13 @@ static int benchmark_event_kthread(void *arg) * wants to run, schedule in, but if the CPU is idle, * we'll keep burning cycles. * - * Note the _rcu_qs() version of cond_resched() will + * Note the tasks_rcu_qs() version of cond_resched() will * notify synchronize_rcu_tasks() that this thread has * passed a quiescent state for rcu_tasks. Otherwise * this thread will never voluntarily schedule which would * block synchronize_rcu_tasks() indefinitely. */ - cond_resched(); + cond_resched_tasks_rcu_qs(); } return 0; diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e954ae3..1d67464 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -230,7 +230,7 @@ FTRACE_ENTRY(bprint, bprint_entry, FILTER_OTHER ); -FTRACE_ENTRY(print, print_entry, +FTRACE_ENTRY_REG(print, print_entry, TRACE_PRINT, @@ -242,7 +242,9 @@ FTRACE_ENTRY(print, print_entry, F_printk("%ps: %s", (void *)__entry->ip, __entry->buf), - FILTER_OTHER + FILTER_OTHER, + + ftrace_event_register ); FTRACE_ENTRY(raw_data, raw_data_entry, @@ -356,7 +358,7 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __field( unsigned int, seqnum ) ), - F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n", + F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n", __entry->seqnum, __entry->tv_sec, __entry->tv_nsec, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 05c7172..14ff4ff 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2007,16 +2007,18 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) return -1; } } - trace_create_file("filter", 0644, file->dir, file, - &ftrace_event_filter_fops); /* * Only event directories that can be enabled should have - * triggers. + * triggers or filters. */ - if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) + if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) { + trace_create_file("filter", 0644, file->dir, file, + &ftrace_event_filter_fops); + trace_create_file("trigger", 0644, file->dir, file, &event_trigger_fops); + } #ifdef CONFIG_HIST_TRIGGERS trace_create_file("hist", 0444, file->dir, file, @@ -2473,8 +2475,9 @@ __trace_add_event_dirs(struct trace_array *tr) } } +/* Returns any file that matches the system and event */ struct trace_event_file * -find_event_file(struct trace_array *tr, const char *system, const char *event) +__find_event_file(struct trace_array *tr, const char *system, const char *event) { struct trace_event_file *file; struct trace_event_call *call; @@ -2485,10 +2488,7 @@ find_event_file(struct trace_array *tr, const char *system, const char *event) call = file->event_call; name = trace_event_name(call); - if (!name || !call->class || !call->class->reg) - continue; - - if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + if (!name || !call->class) continue; if (strcmp(event, name) == 0 && @@ -2498,6 +2498,20 @@ find_event_file(struct trace_array *tr, const char *system, const char *event) return NULL; } +/* Returns valid trace event files that match system and event */ +struct trace_event_file * +find_event_file(struct trace_array *tr, const char *system, const char *event) +{ + struct trace_event_file *file; + + file = __find_event_file(tr, system, event); + if (!file || !file->event_call->class->reg || + file->event_call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + return NULL; + + return file; +} + #ifdef CONFIG_DYNAMIC_FTRACE /* Avoid typos */ @@ -3132,7 +3146,7 @@ static __init int event_trace_enable_again(void) early_initcall(event_trace_enable_again); -static __init int event_trace_init(void) +__init int event_trace_init(void) { struct trace_array *tr; struct dentry *d_tracer; @@ -3177,8 +3191,6 @@ void __init trace_event_init(void) event_trace_enable(); } -fs_initcall(event_trace_init); - #ifdef CONFIG_FTRACE_STARTUP_TEST static DEFINE_SPINLOCK(test_spinlock); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 9b4716b..0171407 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -750,28 +750,32 @@ static int filter_pred_none(struct filter_pred *pred, void *event) * * Note: * - @str might not be NULL-terminated if it's of type DYN_STRING - * or STATIC_STRING + * or STATIC_STRING, unless @len is zero. */ static int regex_match_full(char *str, struct regex *r, int len) { - if (strncmp(str, r->pattern, len) == 0) - return 1; - return 0; + /* len of zero means str is dynamic and ends with '\0' */ + if (!len) + return strcmp(str, r->pattern) == 0; + + return strncmp(str, r->pattern, len) == 0; } static int regex_match_front(char *str, struct regex *r, int len) { - if (strncmp(str, r->pattern, r->len) == 0) - return 1; - return 0; + if (len && len < r->len) + return 0; + + return strncmp(str, r->pattern, r->len) == 0; } static int regex_match_middle(char *str, struct regex *r, int len) { - if (strnstr(str, r->pattern, len)) - return 1; - return 0; + if (!len) + return strstr(str, r->pattern) != NULL; + + return strnstr(str, r->pattern, len) != NULL; } static int regex_match_end(char *str, struct regex *r, int len) @@ -1499,14 +1503,14 @@ static int process_preds(struct trace_event_call *call, return ret; } - if (!nr_preds) { - prog = NULL; - } else { - prog = predicate_parse(filter_string, nr_parens, nr_preds, + if (!nr_preds) + return -EINVAL; + + prog = predicate_parse(filter_string, nr_parens, nr_preds, parse_pred, call, pe); - if (IS_ERR(prog)) - return PTR_ERR(prog); - } + if (IS_ERR(prog)) + return PTR_ERR(prog); + rcu_assign_pointer(filter->prog, prog); return 0; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0d7b3ff..046c716 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2466,6 +2466,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, else if (strcmp(modifier, "usecs") == 0) *flags |= HIST_FIELD_FL_TIMESTAMP_USECS; else { + hist_err("Invalid field modifier: ", modifier); field = ERR_PTR(-EINVAL); goto out; } @@ -2481,6 +2482,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, else { field = trace_find_event_field(file->event_call, field_name); if (!field || !field->size) { + hist_err("Couldn't find field: ", field_name); field = ERR_PTR(-EINVAL); goto out; } @@ -2863,7 +2865,7 @@ static struct trace_event_file *event_file(struct trace_array *tr, { struct trace_event_file *file; - file = find_event_file(tr, system, event_name); + file = __find_event_file(tr, system, event_name); if (!file) return ERR_PTR(-EINVAL); @@ -4913,6 +4915,16 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field) seq_printf(m, "%s", field_name); } else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP) seq_puts(m, "common_timestamp"); + + if (hist_field->flags) { + if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) && + !(hist_field->flags & HIST_FIELD_FL_EXPR)) { + const char *flags = get_hist_field_flags(hist_field); + + if (flags) + seq_printf(m, ".%s", flags); + } + } } static int event_hist_trigger_print(struct seq_file *m, diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index d251cab..d182496 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -97,7 +97,6 @@ EXPORT_SYMBOL_GPL(event_triggers_call); * event_triggers_post_call - Call 'post_triggers' for a trace event * @file: The trace_event_file associated with the event * @tt: enum event_trigger_type containing a set bit for each trigger to invoke - * @rec: The trace entry for the event * * For each trigger associated with an event, invoke the trigger * function registered with the associated trigger command, if the @@ -108,8 +107,7 @@ EXPORT_SYMBOL_GPL(event_triggers_call); */ void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt, - void *rec, struct ring_buffer_event *event) + enum event_trigger_type tt) { struct event_trigger_data *data; @@ -117,7 +115,7 @@ event_triggers_post_call(struct trace_event_file *file, if (data->paused) continue; if (data->cmd_ops->trigger_type & tt) - data->ops->func(data, rec, event); + data->ops->func(data, NULL, NULL); } } EXPORT_SYMBOL_GPL(event_triggers_post_call); @@ -483,9 +481,10 @@ clear_event_triggers(struct trace_array *tr) struct trace_event_file *file; list_for_each_entry(file, &tr->events, list) { - struct event_trigger_data *data; - list_for_each_entry_rcu(data, &file->triggers, list) { + struct event_trigger_data *data, *n; + list_for_each_entry_safe(data, n, &file->triggers, list) { trace_event_trigger_enable_disable(file, 0); + list_del_rcu(&data->list); if (data->ops->free) data->ops->free(data->ops, data); } @@ -642,6 +641,7 @@ event_trigger_callback(struct event_command *cmd_ops, trigger_data->count = -1; trigger_data->ops = trigger_ops; trigger_data->cmd_ops = cmd_ops; + trigger_data->private_data = file; INIT_LIST_HEAD(&trigger_data->list); INIT_LIST_HEAD(&trigger_data->named_list); @@ -1053,7 +1053,12 @@ static void snapshot_trigger(struct event_trigger_data *data, void *rec, struct ring_buffer_event *event) { - tracing_snapshot(); + struct trace_event_file *file = data->private_data; + + if (file) + tracing_snapshot_instance(file->tr); + else + tracing_snapshot(); } static void @@ -1076,7 +1081,7 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops, { int ret = register_trigger(glob, ops, data, file); - if (ret > 0 && tracing_alloc_snapshot() != 0) { + if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) { unregister_trigger(glob, ops, data, file); ret = 0; } diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 548e62e..45630a7 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -14,6 +14,13 @@ #include "trace_output.h" +/* Stub function for events with triggers */ +static int ftrace_event_register(struct trace_event_call *call, + enum trace_reg type, void *data) +{ + return 0; +} + #undef TRACE_SYSTEM #define TRACE_SYSTEM ftrace @@ -117,7 +124,7 @@ static void __always_unused ____ftrace_check_##name(void) \ #undef __dynamic_array #define __dynamic_array(type, item) \ - ret = trace_define_field(event_call, #type, #item, \ + ret = trace_define_field(event_call, #type "[]", #item, \ offsetof(typeof(field), item), \ 0, is_signed_type(type), filter_type);\ if (ret) \ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 1cd3fb4..daa8157 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -512,8 +512,6 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) if (ret == 0) tk->tp.flags |= TP_FLAG_REGISTERED; else { - pr_warn("Could not insert probe at %s+%lu: %d\n", - trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret); if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) { pr_warn("This probe might be able to register after target module is loaded. Continue.\n"); ret = 0; @@ -1289,6 +1287,35 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, head, NULL); } NOKPROBE_SYMBOL(kretprobe_perf_func); + +int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, + const char **symbol, u64 *probe_offset, + u64 *probe_addr, bool perf_type_tracepoint) +{ + const char *pevent = trace_event_name(event->tp_event); + const char *group = event->tp_event->class->system; + struct trace_kprobe *tk; + + if (perf_type_tracepoint) + tk = find_trace_kprobe(pevent, group); + else + tk = event->tp_event->data; + if (!tk) + return -EINVAL; + + *fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE + : BPF_FD_TYPE_KPROBE; + if (tk->symbol) { + *symbol = tk->symbol; + *probe_offset = tk->rp.kp.offset; + *probe_addr = 0; + } else { + *symbol = NULL; + *probe_offset = 0; + *probe_addr = (unsigned long)tk->rp.kp.addr; + } + return 0; +} #endif /* CONFIG_PERF_EVENTS */ /* diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 3c7bfc4..4237eba 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -472,7 +472,7 @@ static __init int stack_trace_init(void) NULL, &stack_trace_fops); #ifdef CONFIG_DYNAMIC_FTRACE - trace_create_file("stack_trace_filter", 0444, d_tracer, + trace_create_file("stack_trace_filter", 0644, d_tracer, &trace_ops, &stack_trace_filter_fops); #endif diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 34fd0e0..bf89a51 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -55,6 +55,7 @@ struct trace_uprobe { struct list_head list; struct trace_uprobe_filter filter; struct uprobe_consumer consumer; + struct path path; struct inode *inode; char *filename; unsigned long offset; @@ -289,7 +290,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu) for (i = 0; i < tu->tp.nr_args; i++) traceprobe_free_probe_arg(&tu->tp.args[i]); - iput(tu->inode); + path_put(&tu->path); kfree(tu->tp.call.class->system); kfree(tu->tp.call.name); kfree(tu->filename); @@ -363,7 +364,6 @@ end: static int create_trace_uprobe(int argc, char **argv) { struct trace_uprobe *tu; - struct inode *inode; char *arg, *event, *group, *filename; char buf[MAX_EVENT_NAME_LEN]; struct path path; @@ -371,7 +371,6 @@ static int create_trace_uprobe(int argc, char **argv) bool is_delete, is_return; int i, ret; - inode = NULL; ret = 0; is_delete = false; is_return = false; @@ -437,21 +436,16 @@ static int create_trace_uprobe(int argc, char **argv) } /* Find the last occurrence, in case the path contains ':' too. */ arg = strrchr(argv[1], ':'); - if (!arg) { - ret = -EINVAL; - goto fail_address_parse; - } + if (!arg) + return -EINVAL; *arg++ = '\0'; filename = argv[1]; ret = kern_path(filename, LOOKUP_FOLLOW, &path); if (ret) - goto fail_address_parse; - - inode = igrab(d_real_inode(path.dentry)); - path_put(&path); + return ret; - if (!inode || !S_ISREG(inode->i_mode)) { + if (!d_is_reg(path.dentry)) { ret = -EINVAL; goto fail_address_parse; } @@ -490,7 +484,7 @@ static int create_trace_uprobe(int argc, char **argv) goto fail_address_parse; } tu->offset = offset; - tu->inode = inode; + tu->path = path; tu->filename = kstrdup(filename, GFP_KERNEL); if (!tu->filename) { @@ -558,7 +552,7 @@ error: return ret; fail_address_parse: - iput(inode); + path_put(&path); pr_info("Failed to parse address or file.\n"); @@ -922,6 +916,7 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, goto err_flags; tu->consumer.filter = filter; + tu->inode = d_real_inode(tu->path.dentry); ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); if (ret) goto err_buffer; @@ -967,6 +962,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file) WARN_ON(!uprobe_filter_is_empty(&tu->filter)); uprobe_unregister(tu->inode, tu->offset, &tu->consumer); + tu->inode = NULL; tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE; uprobe_buffer_disable(); @@ -1165,6 +1161,28 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, { __uprobe_perf_func(tu, func, regs, ucb, dsize); } + +int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, + const char **filename, u64 *probe_offset, + bool perf_type_tracepoint) +{ + const char *pevent = trace_event_name(event->tp_event); + const char *group = event->tp_event->class->system; + struct trace_uprobe *tu; + + if (perf_type_tracepoint) + tu = find_probe_event(pevent, group); + else + tu = event->tp_event->data; + if (!tu) + return -EINVAL; + + *fd_type = is_ret_probe(tu) ? BPF_FD_TYPE_URETPROBE + : BPF_FD_TYPE_UPROBE; + *filename = tu->filename; + *probe_offset = tu->offset; + return 0; +} #endif /* CONFIG_PERF_EVENTS */ static int @@ -1337,7 +1355,6 @@ struct trace_event_call * create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) { struct trace_uprobe *tu; - struct inode *inode; struct path path; int ret; @@ -1345,11 +1362,8 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) if (ret) return ERR_PTR(ret); - inode = igrab(d_inode(path.dentry)); - path_put(&path); - - if (!inode || !S_ISREG(inode->i_mode)) { - iput(inode); + if (!d_is_reg(path.dentry)) { + path_put(&path); return ERR_PTR(-EINVAL); } @@ -1364,11 +1378,12 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) if (IS_ERR(tu)) { pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); + path_put(&path); return ERR_CAST(tu); } tu->offset = offs; - tu->inode = inode; + tu->path = path; tu->filename = kstrdup(name, GFP_KERNEL); init_trace_event_call(tu, &tu->tp.call); |