diff options
Diffstat (limited to 'kernel/trace')
| -rw-r--r-- | kernel/trace/blktrace.c | 4 | ||||
| -rw-r--r-- | kernel/trace/bpf_trace.c | 107 | ||||
| -rw-r--r-- | kernel/trace/ftrace.c | 32 | ||||
| -rw-r--r-- | kernel/trace/ring_buffer.c | 12 | ||||
| -rw-r--r-- | kernel/trace/trace.c | 10 | ||||
| -rw-r--r-- | kernel/trace/trace.h | 57 | ||||
| -rw-r--r-- | kernel/trace/trace_events_filter.c | 9 | ||||
| -rw-r--r-- | kernel/trace/trace_events_trigger.c | 6 | ||||
| -rw-r--r-- | kernel/trace/trace_functions_graph.c | 53 | ||||
| -rw-r--r-- | kernel/trace/trace_irqsoff.c | 2 | ||||
| -rw-r--r-- | kernel/trace/trace_kprobe.c | 2 | ||||
| -rw-r--r-- | kernel/trace/trace_probe.c | 2 | ||||
| -rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 2 |
13 files changed, 245 insertions, 53 deletions
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2868d85f1fb1..fac0ddf8a8e2 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -764,9 +764,9 @@ blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return NULL; - if (!bio->bi_css) + if (!bio->bi_blkg) return NULL; - return cgroup_get_kernfs_id(bio->bi_css->cgroup); + return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); } #else static union kernfs_node_id * diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 08fcfe440c63..9ddb6fddb4e0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -17,6 +17,43 @@ #include "trace_probe.h" #include "trace.h" +#ifdef CONFIG_MODULES +struct bpf_trace_module { + struct module *module; + struct list_head list; +}; + +static LIST_HEAD(bpf_trace_modules); +static DEFINE_MUTEX(bpf_module_mutex); + +static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) +{ + struct bpf_raw_event_map *btp, *ret = NULL; + struct bpf_trace_module *btm; + unsigned int i; + + mutex_lock(&bpf_module_mutex); + list_for_each_entry(btm, &bpf_trace_modules, list) { + for (i = 0; i < btm->module->num_bpf_raw_events; ++i) { + btp = &btm->module->bpf_raw_events[i]; + if (!strcmp(btp->tp->name, name)) { + if (try_module_get(btm->module)) + ret = btp; + goto out; + } + } + } +out: + mutex_unlock(&bpf_module_mutex); + return ret; +} +#else +static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) +{ + return NULL; +} +#endif /* CONFIG_MODULES */ + 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); @@ -196,11 +233,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, i++; } else if (fmt[i] == 'p' || fmt[i] == 's') { mod[fmt_cnt]++; - i++; - if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) + /* disallow any further format extensions */ + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) return -EINVAL; fmt_cnt++; - if (fmt[i - 1] == 's') { + if (fmt[i] == 's') { if (str_seen) /* allow only one '%s' per fmt string */ return -EINVAL; @@ -1074,7 +1113,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) extern struct bpf_raw_event_map __start__bpf_raw_tp[]; extern struct bpf_raw_event_map __stop__bpf_raw_tp[]; -struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name) +struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name) { struct bpf_raw_event_map *btp = __start__bpf_raw_tp; @@ -1082,7 +1121,16 @@ struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name) if (!strcmp(btp->tp->name, name)) return btp; } - return NULL; + + return bpf_get_raw_tracepoint_module(name); +} + +void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) +{ + struct module *mod = __module_address((unsigned long)btp); + + if (mod) + module_put(mod); } static __always_inline @@ -1220,3 +1268,52 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, return err; } + +#ifdef CONFIG_MODULES +int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module) +{ + struct bpf_trace_module *btm, *tmp; + struct module *mod = module; + + if (mod->num_bpf_raw_events == 0 || + (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING)) + return 0; + + mutex_lock(&bpf_module_mutex); + + switch (op) { + case MODULE_STATE_COMING: + btm = kzalloc(sizeof(*btm), GFP_KERNEL); + if (btm) { + btm->module = module; + list_add(&btm->list, &bpf_trace_modules); + } + break; + case MODULE_STATE_GOING: + list_for_each_entry_safe(btm, tmp, &bpf_trace_modules, list) { + if (btm->module == module) { + list_del(&btm->list); + kfree(btm); + break; + } + } + break; + } + + mutex_unlock(&bpf_module_mutex); + + return 0; +} + +static struct notifier_block bpf_module_nb = { + .notifier_call = bpf_event_notify, +}; + +int __init bpf_event_init(void) +{ + register_module_notifier(&bpf_module_nb); + return 0; +} + +fs_initcall(bpf_event_init); +#endif /* CONFIG_MODULES */ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f536f601bd46..f0ff24173a0b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -173,7 +173,7 @@ static void ftrace_sync(struct work_struct *work) { /* * This function is just a stub to implement a hard force - * of synchronize_sched(). This requires synchronizing + * of synchronize_rcu(). This requires synchronizing * tasks even in userspace and idle. * * Yes, function tracing is rude. @@ -817,7 +817,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { - int index = trace->depth; + int index = current->curr_ret_stack; function_profile_call(trace->func, 0, NULL, NULL); @@ -852,7 +852,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace) if (!fgraph_graph_time) { int index; - index = trace->depth; + index = current->curr_ret_stack; /* Append this call time to the parent time to subtract */ if (index) @@ -934,7 +934,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, ftrace_profile_enabled = 0; /* * unregister_ftrace_profiler calls stop_machine - * so this acts like an synchronize_sched. + * so this acts like an synchronize_rcu. */ unregister_ftrace_profiler(); } @@ -1086,7 +1086,7 @@ struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr) /* * Some of the ops may be dynamically allocated, - * they are freed after a synchronize_sched(). + * they are freed after a synchronize_rcu(). */ preempt_disable_notrace(); @@ -1286,7 +1286,7 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash) { if (!hash || hash == EMPTY_HASH) return; - call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu); + call_rcu(&hash->rcu, __free_ftrace_hash_rcu); } void ftrace_free_filter(struct ftrace_ops *ops) @@ -1501,7 +1501,7 @@ static bool hash_contains_ip(unsigned long ip, * the ip is not in the ops->notrace_hash. * * This needs to be called with preemption disabled as - * the hashes are freed with call_rcu_sched(). + * the hashes are freed with call_rcu(). */ static int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) @@ -4496,7 +4496,7 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, if (ftrace_enabled && !ftrace_hash_empty(hash)) ftrace_run_modify_code(&probe->ops, FTRACE_UPDATE_CALLS, &old_hash_ops); - synchronize_sched(); + synchronize_rcu(); hlist_for_each_entry_safe(entry, tmp, &hhd, hlist) { hlist_del(&entry->hlist); @@ -5314,7 +5314,7 @@ ftrace_graph_release(struct inode *inode, struct file *file) mutex_unlock(&graph_lock); /* Wait till all users are no longer using the old hash */ - synchronize_sched(); + synchronize_rcu(); free_ftrace_hash(old_hash); } @@ -5460,6 +5460,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops) if (ops->flags & FTRACE_OPS_FL_ENABLED) ftrace_shutdown(ops, 0); ops->flags |= FTRACE_OPS_FL_DELETED; + ftrace_free_filter(ops); mutex_unlock(&ftrace_lock); } @@ -5707,7 +5708,7 @@ void ftrace_release_mod(struct module *mod) list_for_each_entry_safe(mod_map, n, &ftrace_mod_maps, list) { if (mod_map->mod == mod) { list_del_rcu(&mod_map->list); - call_rcu_sched(&mod_map->rcu, ftrace_free_mod_map); + call_rcu(&mod_map->rcu, ftrace_free_mod_map); break; } } @@ -5927,7 +5928,7 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, struct ftrace_mod_map *mod_map; const char *ret = NULL; - /* mod_map is freed via call_rcu_sched() */ + /* mod_map is freed via call_rcu() */ preempt_disable(); list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) { ret = ftrace_func_address_lookup(mod_map, addr, size, off, sym); @@ -6262,7 +6263,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, /* * Some of the ops may be dynamically allocated, - * they must be freed after a synchronize_sched(). + * they must be freed after a synchronize_rcu(). */ preempt_disable_notrace(); @@ -6433,7 +6434,7 @@ static void clear_ftrace_pids(struct trace_array *tr) rcu_assign_pointer(tr->function_pids, NULL); /* Wait till all users are no longer using pid filtering */ - synchronize_sched(); + synchronize_rcu(); trace_free_pid_list(pid_list); } @@ -6580,7 +6581,7 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf, rcu_assign_pointer(tr->function_pids, pid_list); if (filtered_pids) { - synchronize_sched(); + synchronize_rcu(); trace_free_pid_list(filtered_pids); } else if (pid_list) { /* Register a probe to set whether to ignore the tracing of a task */ @@ -6814,6 +6815,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* Make sure the tasks see the -1 first: */ smp_wmb(); t->ret_stack = ret_stack_list[start++]; @@ -7038,6 +7040,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* * The idle task has no parent, it either has its own * stack or no stack at all. @@ -7068,6 +7071,7 @@ void ftrace_graph_init_task(struct task_struct *t) /* Make sure we do not use the parent ret_stack */ t->ret_stack = NULL; t->curr_ret_stack = -1; + t->curr_ret_depth = -1; if (ftrace_graph_active) { struct ftrace_ret_stack *ret_stack; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 65bd4616220d..4f3247a53259 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1834,7 +1834,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, * There could have been a race between checking * record_disable and incrementing it. */ - synchronize_sched(); + synchronize_rcu(); for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; rb_check_pages(cpu_buffer); @@ -3151,7 +3151,7 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) * This prevents all writes to the buffer. Any attempt to write * to the buffer after this will fail and return NULL. * - * The caller should call synchronize_sched() after this. + * The caller should call synchronize_rcu() after this. */ void ring_buffer_record_disable(struct ring_buffer *buffer) { @@ -3253,7 +3253,7 @@ bool ring_buffer_record_is_set_on(struct ring_buffer *buffer) * This prevents all writes to the buffer. Any attempt to write * to the buffer after this will fail and return NULL. * - * The caller should call synchronize_sched() after this. + * The caller should call synchronize_rcu() after this. */ void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu) { @@ -4191,7 +4191,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_prepare); void ring_buffer_read_prepare_sync(void) { - synchronize_sched(); + synchronize_rcu(); } EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync); @@ -4363,7 +4363,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) atomic_inc(&cpu_buffer->record_disabled); /* Make sure all commits have finished */ - synchronize_sched(); + synchronize_rcu(); raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); @@ -4496,7 +4496,7 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, goto out; /* - * We can't do a synchronize_sched here because this + * We can't do a synchronize_rcu here because this * function can be called in atomic context. * Normally this will be called from the same CPU as cpu. * If not it's up to the caller to protect this. diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ff1c4b20cd0a..51612b4a603f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1681,7 +1681,7 @@ void tracing_reset(struct trace_buffer *buf, int cpu) ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ - synchronize_sched(); + synchronize_rcu(); ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); @@ -1698,7 +1698,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf) ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ - synchronize_sched(); + synchronize_rcu(); buf->time_start = buffer_ftrace_now(buf, buf->cpu); @@ -2250,7 +2250,7 @@ void trace_buffered_event_disable(void) preempt_enable(); /* Wait for all current users to finish */ - synchronize_sched(); + synchronize_rcu(); for_each_tracing_cpu(cpu) { free_page((unsigned long)per_cpu(trace_buffered_event, cpu)); @@ -5398,7 +5398,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) if (tr->current_trace->reset) tr->current_trace->reset(tr); - /* Current trace needs to be nop_trace before synchronize_sched */ + /* Current trace needs to be nop_trace before synchronize_rcu */ tr->current_trace = &nop_trace; #ifdef CONFIG_TRACER_MAX_TRACE @@ -5412,7 +5412,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) * The update_max_tr is called from interrupts disabled * so a synchronized_sched() is sufficient. */ - synchronize_sched(); + synchronize_rcu(); free_snapshot(tr); } #endif diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3b8c0e24ab30..447bd96ee658 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -512,12 +512,44 @@ enum { * can only be modified by current, we can reuse trace_recursion. */ TRACE_IRQ_BIT, + + /* Set if the function is in the set_graph_function file */ + TRACE_GRAPH_BIT, + + /* + * In the very unlikely case that an interrupt came in + * at a start of graph tracing, and we want to trace + * the function in that interrupt, the depth can be greater + * than zero, because of the preempted start of a previous + * trace. In an even more unlikely case, depth could be 2 + * if a softirq interrupted the start of graph tracing, + * followed by an interrupt preempting a start of graph + * tracing in the softirq, and depth can even be 3 + * if an NMI came in at the start of an interrupt function + * that preempted a softirq start of a function that + * preempted normal context!!!! Luckily, it can't be + * greater than 3, so the next two bits are a mask + * of what the depth is when we set TRACE_GRAPH_BIT + */ + + TRACE_GRAPH_DEPTH_START_BIT, + TRACE_GRAPH_DEPTH_END_BIT, }; #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) #define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) #define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) +#define trace_recursion_depth() \ + (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) +#define trace_recursion_set_depth(depth) \ + do { \ + current->trace_recursion &= \ + ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ + current->trace_recursion |= \ + ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ + } while (0) + #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT @@ -843,8 +875,9 @@ extern void __trace_graph_return(struct trace_array *tr, extern struct ftrace_hash *ftrace_graph_hash; extern struct ftrace_hash *ftrace_graph_notrace_hash; -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { + unsigned long addr = trace->func; int ret = 0; preempt_disable_notrace(); @@ -855,6 +888,14 @@ static inline int ftrace_graph_addr(unsigned long addr) } if (ftrace_lookup_ip(ftrace_graph_hash, addr)) { + + /* + * This needs to be cleared on the return functions + * when the depth is zero. + */ + trace_recursion_set(TRACE_GRAPH_BIT); + trace_recursion_set_depth(trace->depth); + /* * If no irqs are to be traced, but a set_graph_function * is set, and called by an interrupt handler, we still @@ -872,6 +913,13 @@ out: return ret; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ + if (trace_recursion_test(TRACE_GRAPH_BIT) && + trace->depth == trace_recursion_depth()) + trace_recursion_clear(TRACE_GRAPH_BIT); +} + static inline int ftrace_graph_notrace_addr(unsigned long addr) { int ret = 0; @@ -885,7 +933,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) return ret; } #else -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { return 1; } @@ -894,6 +942,8 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) { return 0; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ } #endif /* CONFIG_DYNAMIC_FTRACE */ extern unsigned int fgraph_max_depth; @@ -901,7 +951,8 @@ extern unsigned int fgraph_max_depth; static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace) { /* trace it when it is-nested-in or is a function enabled. */ - return !(trace->depth || ftrace_graph_addr(trace->func)) || + return !(trace_recursion_test(TRACE_GRAPH_BIT) || + ftrace_graph_addr(trace)) || (trace->depth < 0) || (fgraph_max_depth && trace->depth >= fgraph_max_depth); } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 84a65173b1e9..27821480105e 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -570,11 +570,13 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, } } + kfree(op_stack); + kfree(inverts); return prog; out_free: kfree(op_stack); - kfree(prog_stack); kfree(inverts); + kfree(prog_stack); return ERR_PTR(ret); } @@ -1614,7 +1616,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir, /* * The calls can still be using the old filters. - * Do a synchronize_sched() and to ensure all calls are + * Do a synchronize_rcu() and to ensure all calls are * done with them before we free them. */ tracepoint_synchronize_unregister(); @@ -1718,6 +1720,7 @@ static int create_filter(struct trace_event_call *call, err = process_preds(call, filter_string, *filterp, pe); if (err && set_str) append_filter_err(pe, *filterp); + create_filter_finish(pe); return err; } @@ -1845,7 +1848,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, if (filter) { /* * No event actually uses the system filter - * we can free it without synchronize_sched(). + * we can free it without synchronize_rcu(). */ __free_filter(system->filter); system->filter = filter; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2152d1e530cb..cd12ecb66eb9 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -732,8 +732,10 @@ int set_trigger_filter(char *filter_str, /* The filter is for the 'trigger' event, not the triggered event */ ret = create_event_filter(file->event_call, filter_str, false, &filter); - if (ret) - goto out; + /* + * If create_event_filter() fails, filter still needs to be freed. + * Which the calling code will do with data->filter. + */ assign: tmp = rcu_access_pointer(data->filter); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 169b3c44ee97..086af4f5c3e8 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -118,8 +118,8 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, struct trace_seq *s, u32 flags); /* Add a function return address to the trace stack on thread info.*/ -int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, +static int +ftrace_push_return_trace(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { unsigned long long calltime; @@ -177,9 +177,31 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, #ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR current->ret_stack[index].retp = retp; #endif - *depth = current->curr_ret_stack; + return 0; +} + +int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp) +{ + struct ftrace_graph_ent trace; + + trace.func = func; + trace.depth = ++current->curr_ret_depth; + + if (ftrace_push_return_trace(ret, func, + frame_pointer, retp)) + goto out; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + goto out_ret; return 0; + out_ret: + current->curr_ret_stack--; + out: + current->curr_ret_depth--; + return -EBUSY; } /* Retrieve a function return address to the trace stack on thread info.*/ @@ -241,7 +263,13 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, trace->func = current->ret_stack[index].func; trace->calltime = current->ret_stack[index].calltime; trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; + trace->depth = current->curr_ret_depth--; + /* + * We still want to trace interrupts coming in if + * max_depth is set to 1. Make sure the decrement is + * seen before ftrace_graph_return. + */ + barrier(); } /* @@ -255,6 +283,12 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) ftrace_pop_return_trace(&trace, &ret, frame_pointer); trace.rettime = trace_clock_local(); + ftrace_graph_return(&trace); + /* + * The ftrace_graph_return() may still access the current + * ret_stack structure, we need to make sure the update of + * curr_ret_stack is after that. + */ barrier(); current->curr_ret_stack--; /* @@ -267,13 +301,6 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) return ret; } - /* - * The trace should run after decrementing the ret counter - * in case an interrupt were to come in. We don't want to - * lose the interrupt if max_depth is set. - */ - ftrace_graph_return(&trace); - if (unlikely(!ret)) { ftrace_graph_stop(); WARN_ON(1); @@ -482,6 +509,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace) int cpu; int pc; + ftrace_graph_addr_finish(trace); + local_irq_save(flags); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->trace_buffer.data, cpu); @@ -505,6 +534,8 @@ void set_graph_array(struct trace_array *tr) static void trace_graph_thresh_return(struct ftrace_graph_ret *trace) { + ftrace_graph_addr_finish(trace); + if (tracing_thresh && (trace->rettime - trace->calltime < tracing_thresh)) return; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index b7357f9f82a3..98ea6d28df15 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -208,6 +208,8 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_dec(tr, &data, &flags)) return; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index fec67188c4d2..adc153ab51c0 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -333,7 +333,7 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) * event_call related objects, which will be accessed in * the kprobe_trace_func/kretprobe_trace_func. */ - synchronize_sched(); + synchronize_rcu(); kfree(link); /* Ignored if link == NULL */ } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 3ef15a6683c0..bd30e9398d2a 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -535,7 +535,7 @@ int traceprobe_update_arg(struct probe_arg *arg) if (code[1].op != FETCH_OP_IMM) return -EINVAL; - tmp = strpbrk("+-", code->data); + tmp = strpbrk(code->data, "+-"); if (tmp) c = *tmp; ret = traceprobe_split_symbol_offset(code->data, diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index a86b303e6c67..7d04b9890755 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -270,6 +270,8 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_preempt_disable(tr, &data, &pc)) return; |