diff options
Diffstat (limited to 'kernel/trace')
-rw-r--r-- | kernel/trace/Kconfig | 5 | ||||
-rw-r--r-- | kernel/trace/blktrace.c | 39 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 32 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 1037 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 64 | ||||
-rw-r--r-- | kernel/trace/ring_buffer_benchmark.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace.c | 289 | ||||
-rw-r--r-- | kernel/trace/trace.h | 84 | ||||
-rw-r--r-- | kernel/trace/trace_benchmark.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace_entries.h | 6 | ||||
-rw-r--r-- | kernel/trace/trace_events.c | 151 | ||||
-rw-r--r-- | kernel/trace/trace_functions.c | 227 | ||||
-rw-r--r-- | kernel/trace/trace_hwlat.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 53 | ||||
-rw-r--r-- | kernel/trace/trace_output.c | 9 | ||||
-rw-r--r-- | kernel/trace/trace_stack.c | 35 |
16 files changed, 1406 insertions, 655 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d4a06e714645..7e06f04e98fe 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -134,7 +134,8 @@ config FUNCTION_TRACER select KALLSYMS select GENERIC_TRACER select CONTEXT_SWITCH_TRACER - select GLOB + select GLOB + select TASKS_RCU if PREEMPT help Enable the kernel to trace every kernel function. This is done by using a compiler feature to insert a small, 5-byte No-Operation @@ -455,7 +456,7 @@ config UPROBE_EVENTS select UPROBES select PROBE_EVENTS select TRACING - default n + default y help This allows the user to add tracing events on top of userspace dynamic events (similar to tracepoints) on the fly via the trace diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index b2058a7f94bd..193c5f5e3f79 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -690,8 +690,8 @@ void blk_trace_shutdown(struct request_queue *q) /** * blk_add_trace_rq - Add a trace for a request oriented action - * @q: queue the io is for * @rq: the source request + * @error: return status to log * @nr_bytes: number of completed bytes * @what: the action * @@ -699,10 +699,10 @@ void blk_trace_shutdown(struct request_queue *q) * Records an action against a request. Will log the bio offset + size. * **/ -static void blk_add_trace_rq(struct request_queue *q, struct request *rq, +static void blk_add_trace_rq(struct request *rq, int error, unsigned int nr_bytes, u32 what) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt = rq->q->blk_trace; if (likely(!bt)) return; @@ -713,40 +713,32 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, what |= BLK_TC_ACT(BLK_TC_FS); __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), - rq->cmd_flags, what, rq->errors, 0, NULL); -} - -static void blk_add_trace_rq_abort(void *ignore, - struct request_queue *q, struct request *rq) -{ - blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT); + rq->cmd_flags, what, error, 0, NULL); } static void blk_add_trace_rq_insert(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT); + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT); } static void blk_add_trace_rq_issue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE); + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE); } static void blk_add_trace_rq_requeue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE); + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE); } -static void blk_add_trace_rq_complete(void *ignore, - struct request_queue *q, - struct request *rq, - unsigned int nr_bytes) +static void blk_add_trace_rq_complete(void *ignore, struct request *rq, + int error, unsigned int nr_bytes) { - blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE); + blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE); } /** @@ -941,7 +933,7 @@ static void blk_add_trace_rq_remap(void *ignore, r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), - rq_data_dir(rq), 0, BLK_TA_REMAP, !!rq->errors, + rq_data_dir(rq), 0, BLK_TA_REMAP, 0, sizeof(r), &r); } @@ -966,7 +958,7 @@ void blk_add_driver_data(struct request_queue *q, return; __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, - BLK_TA_DRV_DATA, rq->errors, len, data); + BLK_TA_DRV_DATA, 0, len, data); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -974,8 +966,6 @@ static void blk_register_tracepoints(void) { int ret; - ret = register_trace_block_rq_abort(blk_add_trace_rq_abort, NULL); - WARN_ON(ret); ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); WARN_ON(ret); ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); @@ -1028,7 +1018,6 @@ static void blk_unregister_tracepoints(void) unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); - unregister_trace_block_rq_abort(blk_add_trace_rq_abort, NULL); tracepoint_synchronize_unregister(); } @@ -1673,14 +1662,14 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, goto out; if (attr == &dev_attr_act_mask) { - if (sscanf(buf, "%llx", &value) != 1) { + if (kstrtoull(buf, 0, &value)) { /* Assume it is a list of trace category names */ ret = blk_trace_str2mask(buf); if (ret < 0) goto out; value = ret; } - } else if (sscanf(buf, "%llu", &value) != 1) + } else if (kstrtoull(buf, 0, &value)) goto out; ret = -ENXIO; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cee9802cf3e0..460a031c77e5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -96,7 +96,7 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, if (unlikely(in_interrupt() || current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; - if (unlikely(segment_eq(get_fs(), KERNEL_DS))) + if (unlikely(uaccess_kernel())) return -EPERM; if (!access_ok(VERIFY_WRITE, unsafe_ptr, size)) return -EPERM; @@ -501,16 +501,11 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type return true; } -static const struct bpf_verifier_ops kprobe_prog_ops = { +const struct bpf_verifier_ops kprobe_prog_ops = { .get_func_proto = kprobe_prog_func_proto, .is_valid_access = kprobe_prog_is_valid_access, }; -static struct bpf_prog_type_list kprobe_tl __ro_after_init = { - .ops = &kprobe_prog_ops, - .type = BPF_PROG_TYPE_KPROBE, -}; - BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, u64, flags, void *, data, u64, size) { @@ -584,16 +579,11 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type return true; } -static const struct bpf_verifier_ops tracepoint_prog_ops = { +const struct bpf_verifier_ops tracepoint_prog_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = tp_prog_is_valid_access, }; -static struct bpf_prog_type_list tracepoint_tl __ro_after_init = { - .ops = &tracepoint_prog_ops, - .type = BPF_PROG_TYPE_TRACEPOINT, -}; - static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, enum bpf_reg_type *reg_type) { @@ -642,22 +632,8 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -static const struct bpf_verifier_ops perf_event_prog_ops = { +const struct bpf_verifier_ops perf_event_prog_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; - -static struct bpf_prog_type_list perf_event_tl __ro_after_init = { - .ops = &perf_event_prog_ops, - .type = BPF_PROG_TYPE_PERF_EVENT, -}; - -static int __init register_kprobe_prog_ops(void) -{ - bpf_register_prog_type(&kprobe_tl); - bpf_register_prog_type(&tracepoint_tl); - bpf_register_prog_type(&perf_event_tl); - return 0; -} -late_initcall(register_kprobe_prog_ops); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b9691ee8f6c1..9e5841dc14b5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -36,6 +36,7 @@ #include <trace/events/sched.h> +#include <asm/sections.h> #include <asm/setup.h> #include "trace_output.h" @@ -1095,22 +1096,20 @@ static bool update_all_ops; # error Dynamic ftrace depends on MCOUNT_RECORD #endif -static struct hlist_head ftrace_func_hash[FTRACE_FUNC_HASHSIZE] __read_mostly; - -struct ftrace_func_probe { - struct hlist_node node; - struct ftrace_probe_ops *ops; - unsigned long flags; - unsigned long ip; - void *data; - struct list_head free_list; -}; - struct ftrace_func_entry { struct hlist_node hlist; unsigned long ip; }; +struct ftrace_func_probe { + struct ftrace_probe_ops *probe_ops; + struct ftrace_ops ops; + struct trace_array *tr; + struct list_head list; + void *data; + int ref; +}; + /* * We make these constant because no one should touch them, * but they are used as the default "empty hash", to avoid allocating @@ -1271,7 +1270,7 @@ static void remove_hash_entry(struct ftrace_hash *hash, struct ftrace_func_entry *entry) { - hlist_del(&entry->hlist); + hlist_del_rcu(&entry->hlist); hash->count--; } @@ -2807,18 +2806,28 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) * callers are done before leaving this function. * The same goes for freeing the per_cpu data of the per_cpu * ops. - * - * Again, normal synchronize_sched() is not good enough. - * We need to do a hard force of sched synchronization. - * This is because we use preempt_disable() to do RCU, but - * the function tracers can be called where RCU is not watching - * (like before user_exit()). We can not rely on the RCU - * infrastructure to do the synchronization, thus we must do it - * ourselves. */ if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) { + /* + * We need to do a hard force of sched synchronization. + * This is because we use preempt_disable() to do RCU, but + * the function tracers can be called where RCU is not watching + * (like before user_exit()). We can not rely on the RCU + * infrastructure to do the synchronization, thus we must do it + * ourselves. + */ schedule_on_each_cpu(ftrace_sync); + /* + * When the kernel is preeptive, tasks can be preempted + * while on a ftrace trampoline. Just scheduling a task on + * a CPU is not good enough to flush them. Calling + * synchornize_rcu_tasks() will wait for those tasks to + * execute and either schedule voluntarily or enter user space. + */ + if (IS_ENABLED(CONFIG_PREEMPT)) + synchronize_rcu_tasks(); + arch_ftrace_trampoline_free(ops); if (ops->flags & FTRACE_OPS_FL_PER_CPU) @@ -3055,34 +3064,63 @@ struct ftrace_iterator { struct ftrace_page *pg; struct dyn_ftrace *func; struct ftrace_func_probe *probe; + struct ftrace_func_entry *probe_entry; struct trace_parser parser; struct ftrace_hash *hash; struct ftrace_ops *ops; - int hidx; + int pidx; int idx; unsigned flags; }; static void * -t_hash_next(struct seq_file *m, loff_t *pos) +t_probe_next(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; + struct trace_array *tr = iter->ops->private; + struct list_head *func_probes; + struct ftrace_hash *hash; + struct list_head *next; struct hlist_node *hnd = NULL; struct hlist_head *hhd; + int size; (*pos)++; iter->pos = *pos; - if (iter->probe) - hnd = &iter->probe->node; - retry: - if (iter->hidx >= FTRACE_FUNC_HASHSIZE) + if (!tr) return NULL; - hhd = &ftrace_func_hash[iter->hidx]; + func_probes = &tr->func_probes; + if (list_empty(func_probes)) + return NULL; + + if (!iter->probe) { + next = func_probes->next; + iter->probe = list_entry(next, struct ftrace_func_probe, list); + } + + if (iter->probe_entry) + hnd = &iter->probe_entry->hlist; + + hash = iter->probe->ops.func_hash->filter_hash; + size = 1 << hash->size_bits; + + retry: + if (iter->pidx >= size) { + if (iter->probe->list.next == func_probes) + return NULL; + next = iter->probe->list.next; + iter->probe = list_entry(next, struct ftrace_func_probe, list); + hash = iter->probe->ops.func_hash->filter_hash; + size = 1 << hash->size_bits; + iter->pidx = 0; + } + + hhd = &hash->buckets[iter->pidx]; if (hlist_empty(hhd)) { - iter->hidx++; + iter->pidx++; hnd = NULL; goto retry; } @@ -3092,7 +3130,7 @@ t_hash_next(struct seq_file *m, loff_t *pos) else { hnd = hnd->next; if (!hnd) { - iter->hidx++; + iter->pidx++; goto retry; } } @@ -3100,26 +3138,28 @@ t_hash_next(struct seq_file *m, loff_t *pos) if (WARN_ON_ONCE(!hnd)) return NULL; - iter->probe = hlist_entry(hnd, struct ftrace_func_probe, node); + iter->probe_entry = hlist_entry(hnd, struct ftrace_func_entry, hlist); return iter; } -static void *t_hash_start(struct seq_file *m, loff_t *pos) +static void *t_probe_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; void *p = NULL; loff_t l; - if (!(iter->flags & FTRACE_ITER_DO_HASH)) + if (!(iter->flags & FTRACE_ITER_DO_PROBES)) return NULL; if (iter->func_pos > *pos) return NULL; - iter->hidx = 0; + iter->probe = NULL; + iter->probe_entry = NULL; + iter->pidx = 0; for (l = 0; l <= (*pos - iter->func_pos); ) { - p = t_hash_next(m, &l); + p = t_probe_next(m, &l); if (!p) break; } @@ -3127,50 +3167,42 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos) return NULL; /* Only set this if we have an item */ - iter->flags |= FTRACE_ITER_HASH; + iter->flags |= FTRACE_ITER_PROBE; return iter; } static int -t_hash_show(struct seq_file *m, struct ftrace_iterator *iter) +t_probe_show(struct seq_file *m, struct ftrace_iterator *iter) { - struct ftrace_func_probe *rec; + struct ftrace_func_entry *probe_entry; + struct ftrace_probe_ops *probe_ops; + struct ftrace_func_probe *probe; - rec = iter->probe; - if (WARN_ON_ONCE(!rec)) + probe = iter->probe; + probe_entry = iter->probe_entry; + + if (WARN_ON_ONCE(!probe || !probe_entry)) return -EIO; - if (rec->ops->print) - return rec->ops->print(m, rec->ip, rec->ops, rec->data); + probe_ops = probe->probe_ops; - seq_printf(m, "%ps:%ps", (void *)rec->ip, (void *)rec->ops->func); + if (probe_ops->print) + return probe_ops->print(m, probe_entry->ip, probe_ops, probe->data); - if (rec->data) - seq_printf(m, ":%p", rec->data); - seq_putc(m, '\n'); + seq_printf(m, "%ps:%ps\n", (void *)probe_entry->ip, + (void *)probe_ops->func); return 0; } static void * -t_next(struct seq_file *m, void *v, loff_t *pos) +t_func_next(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; - struct ftrace_ops *ops = iter->ops; struct dyn_ftrace *rec = NULL; - if (unlikely(ftrace_disabled)) - return NULL; - - if (iter->flags & FTRACE_ITER_HASH) - return t_hash_next(m, pos); - (*pos)++; - iter->pos = iter->func_pos = *pos; - - if (iter->flags & FTRACE_ITER_PRINTALL) - return t_hash_start(m, pos); retry: if (iter->idx >= iter->pg->index) { @@ -3181,11 +3213,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos) } } else { rec = &iter->pg->records[iter->idx++]; - if (((iter->flags & FTRACE_ITER_FILTER) && - !(ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))) || - - ((iter->flags & FTRACE_ITER_NOTRACE) && - !ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) || + if (((iter->flags & (FTRACE_ITER_FILTER | FTRACE_ITER_NOTRACE)) && + !ftrace_lookup_ip(iter->hash, rec->ip)) || ((iter->flags & FTRACE_ITER_ENABLED) && !(rec->flags & FTRACE_FL_ENABLED))) { @@ -3196,24 +3225,51 @@ t_next(struct seq_file *m, void *v, loff_t *pos) } if (!rec) - return t_hash_start(m, pos); + return NULL; + iter->pos = iter->func_pos = *pos; iter->func = rec; return iter; } +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + loff_t l = *pos; /* t_hash_start() must use original pos */ + void *ret; + + if (unlikely(ftrace_disabled)) + return NULL; + + if (iter->flags & FTRACE_ITER_PROBE) + return t_probe_next(m, pos); + + if (iter->flags & FTRACE_ITER_PRINTALL) { + /* next must increment pos, and t_probe_start does not */ + (*pos)++; + return t_probe_start(m, &l); + } + + ret = t_func_next(m, pos); + + if (!ret) + return t_probe_start(m, &l); + + return ret; +} + static void reset_iter_read(struct ftrace_iterator *iter) { iter->pos = 0; iter->func_pos = 0; - iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_HASH); + iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_PROBE); } static void *t_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; - struct ftrace_ops *ops = iter->ops; void *p = NULL; loff_t l; @@ -3233,20 +3289,19 @@ static void *t_start(struct seq_file *m, loff_t *pos) * off, we can short cut and just print out that all * functions are enabled. */ - if ((iter->flags & FTRACE_ITER_FILTER && - ftrace_hash_empty(ops->func_hash->filter_hash)) || - (iter->flags & FTRACE_ITER_NOTRACE && - ftrace_hash_empty(ops->func_hash->notrace_hash))) { + if ((iter->flags & (FTRACE_ITER_FILTER | FTRACE_ITER_NOTRACE)) && + ftrace_hash_empty(iter->hash)) { + iter->func_pos = 1; /* Account for the message */ if (*pos > 0) - return t_hash_start(m, pos); + return t_probe_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; /* reset in case of seek/pread */ - iter->flags &= ~FTRACE_ITER_HASH; + iter->flags &= ~FTRACE_ITER_PROBE; return iter; } - if (iter->flags & FTRACE_ITER_HASH) - return t_hash_start(m, pos); + if (iter->flags & FTRACE_ITER_PROBE) + return t_probe_start(m, pos); /* * Unfortunately, we need to restart at ftrace_pages_start @@ -3256,13 +3311,13 @@ static void *t_start(struct seq_file *m, loff_t *pos) iter->pg = ftrace_pages_start; iter->idx = 0; for (l = 0; l <= *pos; ) { - p = t_next(m, p, &l); + p = t_func_next(m, &l); if (!p) break; } if (!p) - return t_hash_start(m, pos); + return t_probe_start(m, pos); return iter; } @@ -3293,8 +3348,8 @@ static int t_show(struct seq_file *m, void *v) struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec; - if (iter->flags & FTRACE_ITER_HASH) - return t_hash_show(m, iter); + if (iter->flags & FTRACE_ITER_PROBE) + return t_probe_show(m, iter); if (iter->flags & FTRACE_ITER_PRINTALL) { if (iter->flags & FTRACE_ITER_NOTRACE) @@ -3355,12 +3410,13 @@ ftrace_avail_open(struct inode *inode, struct file *file) return -ENODEV; iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); - if (iter) { - iter->pg = ftrace_pages_start; - iter->ops = &global_ops; - } + if (!iter) + return -ENOMEM; - return iter ? 0 : -ENOMEM; + iter->pg = ftrace_pages_start; + iter->ops = &global_ops; + + return 0; } static int @@ -3369,13 +3425,14 @@ ftrace_enabled_open(struct inode *inode, struct file *file) struct ftrace_iterator *iter; iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); - if (iter) { - iter->pg = ftrace_pages_start; - iter->flags = FTRACE_ITER_ENABLED; - iter->ops = &global_ops; - } + if (!iter) + return -ENOMEM; - return iter ? 0 : -ENOMEM; + iter->pg = ftrace_pages_start; + iter->flags = FTRACE_ITER_ENABLED; + iter->ops = &global_ops; + + return 0; } /** @@ -3440,7 +3497,8 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, ret = -ENOMEM; goto out_unlock; } - } + } else + iter->hash = hash; if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; @@ -3470,7 +3528,7 @@ ftrace_filter_open(struct inode *inode, struct file *file) struct ftrace_ops *ops = inode->i_private; return ftrace_regex_open(ops, - FTRACE_ITER_FILTER | FTRACE_ITER_DO_HASH, + FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES, inode, file); } @@ -3573,22 +3631,20 @@ ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g, /* blank module name to match all modules */ if (!mod_g->len) { /* blank module globbing: modname xor exclude_mod */ - if ((!exclude_mod) != (!modname)) + if (!exclude_mod != !modname) goto func_match; return 0; } - /* not matching the module */ - if (!modname || !mod_matches) { - if (exclude_mod) - goto func_match; - else - return 0; - } - - if (mod_matches && exclude_mod) + /* + * exclude_mod is set to trace everything but the given + * module. If it is set and the module matches, then + * return 0. If it is not set, and the module doesn't match + * also return 0. Otherwise, check the function to see if + * that matches. + */ + if (!mod_matches == !exclude_mod) return 0; - func_match: /* blank search means to match all funcs in the mod */ if (!func_g->len) @@ -3654,6 +3710,56 @@ ftrace_match_records(struct ftrace_hash *hash, char *buff, int len) return match_records(hash, buff, len, NULL); } +static void ftrace_ops_update_code(struct ftrace_ops *ops, + struct ftrace_ops_hash *old_hash) +{ + struct ftrace_ops *op; + + if (!ftrace_enabled) + return; + + if (ops->flags & FTRACE_OPS_FL_ENABLED) { + ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash); + return; + } + + /* + * If this is the shared global_ops filter, then we need to + * check if there is another ops that shares it, is enabled. + * If so, we still need to run the modify code. + */ + if (ops->func_hash != &global_ops.local_hash) + return; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op->func_hash == &global_ops.local_hash && + op->flags & FTRACE_OPS_FL_ENABLED) { + ftrace_run_modify_code(op, FTRACE_UPDATE_CALLS, old_hash); + /* Only need to do this once */ + return; + } + } while_for_each_ftrace_op(op); +} + +static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops, + struct ftrace_hash **orig_hash, + struct ftrace_hash *hash, + int enable) +{ + struct ftrace_ops_hash old_hash_ops; + struct ftrace_hash *old_hash; + int ret; + + old_hash = *orig_hash; + old_hash_ops.filter_hash = ops->func_hash->filter_hash; + old_hash_ops.notrace_hash = ops->func_hash->notrace_hash; + ret = ftrace_hash_move(ops, enable, orig_hash, hash); + if (!ret) { + ftrace_ops_update_code(ops, &old_hash_ops); + free_ftrace_hash_rcu(old_hash); + } + return ret; +} /* * We register the module command as a template to show others how @@ -3661,7 +3767,7 @@ ftrace_match_records(struct ftrace_hash *hash, char *buff, int len) */ static int -ftrace_mod_callback(struct ftrace_hash *hash, +ftrace_mod_callback(struct trace_array *tr, struct ftrace_hash *hash, char *func, char *cmd, char *module, int enable) { int ret; @@ -3695,16 +3801,11 @@ core_initcall(ftrace_mod_cmd_init); static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) { - struct ftrace_func_probe *entry; - struct hlist_head *hhd; - unsigned long key; + struct ftrace_probe_ops *probe_ops; + struct ftrace_func_probe *probe; - key = hash_long(ip, FTRACE_HASH_BITS); - - hhd = &ftrace_func_hash[key]; - - if (hlist_empty(hhd)) - return; + probe = container_of(op, struct ftrace_func_probe, ops); + probe_ops = probe->probe_ops; /* * Disable preemption for these calls to prevent a RCU grace @@ -3712,210 +3813,340 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, * on the hash. rcu_read_lock is too dangerous here. */ preempt_disable_notrace(); - hlist_for_each_entry_rcu_notrace(entry, hhd, node) { - if (entry->ip == ip) - entry->ops->func(ip, parent_ip, &entry->data); - } + probe_ops->func(ip, parent_ip, probe->tr, probe_ops, probe->data); preempt_enable_notrace(); } -static struct ftrace_ops trace_probe_ops __read_mostly = -{ - .func = function_trace_probe_call, - .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_OPS_HASH(trace_probe_ops) +struct ftrace_func_map { + struct ftrace_func_entry entry; + void *data; }; -static int ftrace_probe_registered; +struct ftrace_func_mapper { + struct ftrace_hash hash; +}; -static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash) +/** + * allocate_ftrace_func_mapper - allocate a new ftrace_func_mapper + * + * Returns a ftrace_func_mapper descriptor that can be used to map ips to data. + */ +struct ftrace_func_mapper *allocate_ftrace_func_mapper(void) { - int ret; - int i; + struct ftrace_hash *hash; - if (ftrace_probe_registered) { - /* still need to update the function call sites */ - if (ftrace_enabled) - ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS, - old_hash); - return; - } + /* + * The mapper is simply a ftrace_hash, but since the entries + * in the hash are not ftrace_func_entry type, we define it + * as a separate structure. + */ + hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS); + return (struct ftrace_func_mapper *)hash; +} - for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { - struct hlist_head *hhd = &ftrace_func_hash[i]; - if (hhd->first) - break; - } - /* Nothing registered? */ - if (i == FTRACE_FUNC_HASHSIZE) - return; +/** + * ftrace_func_mapper_find_ip - Find some data mapped to an ip + * @mapper: The mapper that has the ip maps + * @ip: the instruction pointer to find the data for + * + * Returns the data mapped to @ip if found otherwise NULL. The return + * is actually the address of the mapper data pointer. The address is + * returned for use cases where the data is no bigger than a long, and + * the user can use the data pointer as its data instead of having to + * allocate more memory for the reference. + */ +void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper, + unsigned long ip) +{ + struct ftrace_func_entry *entry; + struct ftrace_func_map *map; - ret = ftrace_startup(&trace_probe_ops, 0); + entry = ftrace_lookup_ip(&mapper->hash, ip); + if (!entry) + return NULL; - ftrace_probe_registered = 1; + map = (struct ftrace_func_map *)entry; + return &map->data; } -static void __disable_ftrace_function_probe(void) +/** + * ftrace_func_mapper_add_ip - Map some data to an ip + * @mapper: The mapper that has the ip maps + * @ip: The instruction pointer address to map @data to + * @data: The data to map to @ip + * + * Returns 0 on succes otherwise an error. + */ +int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper, + unsigned long ip, void *data) { - int i; + struct ftrace_func_entry *entry; + struct ftrace_func_map *map; - if (!ftrace_probe_registered) - return; + entry = ftrace_lookup_ip(&mapper->hash, ip); + if (entry) + return -EBUSY; - for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { - struct hlist_head *hhd = &ftrace_func_hash[i]; - if (hhd->first) - return; - } + map = kmalloc(sizeof(*map), GFP_KERNEL); + if (!map) + return -ENOMEM; - /* no more funcs left */ - ftrace_shutdown(&trace_probe_ops, 0); + map->entry.ip = ip; + map->data = data; - ftrace_probe_registered = 0; -} + __add_hash_entry(&mapper->hash, &map->entry); + return 0; +} -static void ftrace_free_entry(struct ftrace_func_probe *entry) +/** + * ftrace_func_mapper_remove_ip - Remove an ip from the mapping + * @mapper: The mapper that has the ip maps + * @ip: The instruction pointer address to remove the data from + * + * Returns the data if it is found, otherwise NULL. + * Note, if the data pointer is used as the data itself, (see + * ftrace_func_mapper_find_ip(), then the return value may be meaningless, + * if the data pointer was set to zero. + */ +void *ftrace_func_mapper_remove_ip(struct ftrace_func_mapper *mapper, + unsigned long ip) { - if (entry->ops->free) - entry->ops->free(entry->ops, entry->ip, &entry->data); + struct ftrace_func_entry *entry; + struct ftrace_func_map *map; + void *data; + + entry = ftrace_lookup_ip(&mapper->hash, ip); + if (!entry) + return NULL; + + map = (struct ftrace_func_map *)entry; + data = map->data; + + remove_hash_entry(&mapper->hash, entry); kfree(entry); + + return data; +} + +/** + * free_ftrace_func_mapper - free a mapping of ips and data + * @mapper: The mapper that has the ip maps + * @free_func: A function to be called on each data item. + * + * This is used to free the function mapper. The @free_func is optional + * and can be used if the data needs to be freed as well. + */ +void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper, + ftrace_mapper_func free_func) +{ + struct ftrace_func_entry *entry; + struct ftrace_func_map *map; + struct hlist_head *hhd; + int size = 1 << mapper->hash.size_bits; + int i; + + if (free_func && mapper->hash.count) { + for (i = 0; i < size; i++) { + hhd = &mapper->hash.buckets[i]; + hlist_for_each_entry(entry, hhd, hlist) { + map = (struct ftrace_func_map *)entry; + free_func(map); + } + } + } + free_ftrace_hash(&mapper->hash); +} + +static void release_probe(struct ftrace_func_probe *probe) +{ + struct ftrace_probe_ops *probe_ops; + + mutex_lock(&ftrace_lock); + + WARN_ON(probe->ref <= 0); + + /* Subtract the ref that was used to protect this instance */ + probe->ref--; + + if (!probe->ref) { + probe_ops = probe->probe_ops; + /* + * Sending zero as ip tells probe_ops to free + * the probe->data itself + */ + if (probe_ops->free) + probe_ops->free(probe_ops, probe->tr, 0, probe->data); + list_del(&probe->list); + kfree(probe); + } + mutex_unlock(&ftrace_lock); +} + +static void acquire_probe_locked(struct ftrace_func_probe *probe) +{ + /* + * Add one ref to keep it from being freed when releasing the + * ftrace_lock mutex. + */ + probe->ref++; } int -register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, - void *data) +register_ftrace_function_probe(char *glob, struct trace_array *tr, + struct ftrace_probe_ops *probe_ops, + void *data) { - struct ftrace_ops_hash old_hash_ops; - struct ftrace_func_probe *entry; - struct ftrace_glob func_g; - struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash; - struct ftrace_hash *old_hash = *orig_hash; + struct ftrace_func_entry *entry; + struct ftrace_func_probe *probe; + struct ftrace_hash **orig_hash; + struct ftrace_hash *old_hash; struct ftrace_hash *hash; - struct ftrace_page *pg; - struct dyn_ftrace *rec; - int not; - unsigned long key; int count = 0; + int size; int ret; + int i; - func_g.type = filter_parse_regex(glob, strlen(glob), - &func_g.search, ¬); - func_g.len = strlen(func_g.search); - - /* we do not support '!' for function probes */ - if (WARN_ON(not)) + if (WARN_ON(!tr)) return -EINVAL; - mutex_lock(&trace_probe_ops.func_hash->regex_lock); + /* We do not support '!' for function probes */ + if (WARN_ON(glob[0] == '!')) + return -EINVAL; - old_hash_ops.filter_hash = old_hash; - /* Probes only have filters */ - old_hash_ops.notrace_hash = NULL; - hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash); - if (!hash) { - count = -ENOMEM; - goto out; + mutex_lock(&ftrace_lock); + /* Check if the probe_ops is already registered */ + list_for_each_entry(probe, &tr->func_probes, list) { + if (probe->probe_ops == probe_ops) + break; } - - if (unlikely(ftrace_disabled)) { - count = -ENODEV; - goto out; + if (&probe->list == &tr->func_probes) { + probe = kzalloc(sizeof(*probe), GFP_KERNEL); + if (!probe) { + mutex_unlock(&ftrace_lock); + return -ENOMEM; + } + probe->probe_ops = probe_ops; + probe->ops.func = function_trace_probe_call; + probe->tr = tr; + ftrace_ops_init(&probe->ops); + list_add(&probe->list, &tr->func_probes); } - mutex_lock(&ftrace_lock); + acquire_probe_locked(probe); - do_for_each_ftrace_rec(pg, rec) { + mutex_unlock(&ftrace_lock); - if (rec->flags & FTRACE_FL_DISABLED) - continue; + mutex_lock(&probe->ops.func_hash->regex_lock); - if (!ftrace_match_record(rec, &func_g, NULL, 0)) - continue; + orig_hash = &probe->ops.func_hash->filter_hash; + old_hash = *orig_hash; + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash); - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) { - /* If we did not process any, then return error */ - if (!count) - count = -ENOMEM; - goto out_unlock; - } + ret = ftrace_match_records(hash, glob, strlen(glob)); - count++; + /* Nothing found? */ + if (!ret) + ret = -EINVAL; - entry->data = data; + if (ret < 0) + goto out; - /* - * The caller might want to do something special - * for each function we find. We call the callback - * to give the caller an opportunity to do so. - */ - if (ops->init) { - if (ops->init(ops, rec->ip, &entry->data) < 0) { - /* caller does not like this func */ - kfree(entry); + size = 1 << hash->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { + if (ftrace_lookup_ip(old_hash, entry->ip)) continue; + /* + * The caller might want to do something special + * for each function we find. We call the callback + * to give the caller an opportunity to do so. + */ + if (probe_ops->init) { + ret = probe_ops->init(probe_ops, tr, + entry->ip, data, + &probe->data); + if (ret < 0) { + if (probe_ops->free && count) + probe_ops->free(probe_ops, tr, + 0, probe->data); + probe->data = NULL; + goto out; + } } + count++; } + } - ret = enter_record(hash, rec, 0); - if (ret < 0) { - kfree(entry); - count = ret; - goto out_unlock; - } - - entry->ops = ops; - entry->ip = rec->ip; - - key = hash_long(entry->ip, FTRACE_HASH_BITS); - hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]); + mutex_lock(&ftrace_lock); - } while_for_each_ftrace_rec(); + if (!count) { + /* Nothing was added? */ + ret = -EINVAL; + goto out_unlock; + } - ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + ret = ftrace_hash_move_and_update_ops(&probe->ops, orig_hash, + hash, 1); + if (ret < 0) + goto err_unlock; - __enable_ftrace_function_probe(&old_hash_ops); + /* One ref for each new function traced */ + probe->ref += count; - if (!ret) - free_ftrace_hash_rcu(old_hash); - else - count = ret; + if (!(probe->ops.flags & FTRACE_OPS_FL_ENABLED)) + ret = ftrace_startup(&probe->ops, 0); out_unlock: mutex_unlock(&ftrace_lock); + + if (!ret) + ret = count; out: - mutex_unlock(&trace_probe_ops.func_hash->regex_lock); + mutex_unlock(&probe->ops.func_hash->regex_lock); free_ftrace_hash(hash); - return count; -} + release_probe(probe); -enum { - PROBE_TEST_FUNC = 1, - PROBE_TEST_DATA = 2 -}; + return ret; -static void -__unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, - void *data, int flags) + err_unlock: + if (!probe_ops->free || !count) + goto out_unlock; + + /* Failed to do the move, need to call the free functions */ + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { + if (ftrace_lookup_ip(old_hash, entry->ip)) + continue; + probe_ops->free(probe_ops, tr, entry->ip, probe->data); + } + } + goto out_unlock; +} + +int +unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, + struct ftrace_probe_ops *probe_ops) { - struct ftrace_func_entry *rec_entry; - struct ftrace_func_probe *entry; - struct ftrace_func_probe *p; + struct ftrace_ops_hash old_hash_ops; + struct ftrace_func_entry *entry; + struct ftrace_func_probe *probe; struct ftrace_glob func_g; - struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash; - struct ftrace_hash *old_hash = *orig_hash; - struct list_head free_list; - struct ftrace_hash *hash; + struct ftrace_hash **orig_hash; + struct ftrace_hash *old_hash; + struct ftrace_hash *hash = NULL; struct hlist_node *tmp; + struct hlist_head hhd; char str[KSYM_SYMBOL_LEN]; - int i, ret; + int count = 0; + int i, ret = -ENODEV; + int size; - if (glob && (strcmp(glob, "*") == 0 || !strlen(glob))) + if (!glob || !strlen(glob) || !strcmp(glob, "*")) func_g.search = NULL; - else if (glob) { + else { int not; func_g.type = filter_parse_regex(glob, strlen(glob), @@ -3925,86 +4156,112 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, /* we do not support '!' for function probes */ if (WARN_ON(not)) - return; + return -EINVAL; } - mutex_lock(&trace_probe_ops.func_hash->regex_lock); + mutex_lock(&ftrace_lock); + /* Check if the probe_ops is already registered */ + list_for_each_entry(probe, &tr->func_probes, list) { + if (probe->probe_ops == probe_ops) + break; + } + if (&probe->list == &tr->func_probes) + goto err_unlock_ftrace; - hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); - if (!hash) - /* Hmm, should report this somehow */ - goto out_unlock; + ret = -EINVAL; + if (!(probe->ops.flags & FTRACE_OPS_FL_INITIALIZED)) + goto err_unlock_ftrace; - INIT_LIST_HEAD(&free_list); + acquire_probe_locked(probe); - for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { - struct hlist_head *hhd = &ftrace_func_hash[i]; + mutex_unlock(&ftrace_lock); - hlist_for_each_entry_safe(entry, tmp, hhd, node) { + mutex_lock(&probe->ops.func_hash->regex_lock); - /* break up if statements for readability */ - if ((flags & PROBE_TEST_FUNC) && entry->ops != ops) - continue; + orig_hash = &probe->ops.func_hash->filter_hash; + old_hash = *orig_hash; - if ((flags & PROBE_TEST_DATA) && entry->data != data) - continue; + if (ftrace_hash_empty(old_hash)) + goto out_unlock; + + old_hash_ops.filter_hash = old_hash; + /* Probes only have filters */ + old_hash_ops.notrace_hash = NULL; + + ret = -ENOMEM; + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash); + if (!hash) + goto out_unlock; + + INIT_HLIST_HEAD(&hhd); + + size = 1 << hash->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry_safe(entry, tmp, &hash->buckets[i], hlist) { - /* do this last, since it is the most expensive */ if (func_g.search) { kallsyms_lookup(entry->ip, NULL, NULL, NULL, str); if (!ftrace_match(str, &func_g)) continue; } - - rec_entry = ftrace_lookup_ip(hash, entry->ip); - /* It is possible more than one entry had this ip */ - if (rec_entry) - free_hash_entry(hash, rec_entry); - - hlist_del_rcu(&entry->node); - list_add(&entry->free_list, &free_list); + count++; + remove_hash_entry(hash, entry); + hlist_add_head(&entry->hlist, &hhd); } } + + /* Nothing found? */ + if (!count) { + ret = -EINVAL; + goto out_unlock; + } + mutex_lock(&ftrace_lock); - __disable_ftrace_function_probe(); - /* - * Remove after the disable is called. Otherwise, if the last - * probe is removed, a null hash means *all enabled*. - */ - ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + + WARN_ON(probe->ref < count); + + probe->ref -= count; + + if (ftrace_hash_empty(hash)) + ftrace_shutdown(&probe->ops, 0); + + ret = ftrace_hash_move_and_update_ops(&probe->ops, orig_hash, + hash, 1); + + /* still need to update the function call sites */ + if (ftrace_enabled && !ftrace_hash_empty(hash)) + ftrace_run_modify_code(&probe->ops, FTRACE_UPDATE_CALLS, + &old_hash_ops); synchronize_sched(); - if (!ret) - free_ftrace_hash_rcu(old_hash); - list_for_each_entry_safe(entry, p, &free_list, free_list) { - list_del(&entry->free_list); - ftrace_free_entry(entry); + hlist_for_each_entry_safe(entry, tmp, &hhd, hlist) { + hlist_del(&entry->hlist); + if (probe_ops->free) + probe_ops->free(probe_ops, tr, entry->ip, probe->data); + kfree(entry); } mutex_unlock(&ftrace_lock); out_unlock: - mutex_unlock(&trace_probe_ops.func_hash->regex_lock); + mutex_unlock(&probe->ops.func_hash->regex_lock); free_ftrace_hash(hash); -} -void -unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, - void *data) -{ - __unregister_ftrace_function_probe(glob, ops, data, - PROBE_TEST_FUNC | PROBE_TEST_DATA); -} + release_probe(probe); -void -unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops) -{ - __unregister_ftrace_function_probe(glob, ops, NULL, PROBE_TEST_FUNC); + return ret; + + err_unlock_ftrace: + mutex_unlock(&ftrace_lock); + return ret; } -void unregister_ftrace_function_probe_all(char *glob) +void clear_ftrace_function_probes(struct trace_array *tr) { - __unregister_ftrace_function_probe(glob, NULL, NULL, 0); + struct ftrace_func_probe *probe, *n; + + list_for_each_entry_safe(probe, n, &tr->func_probes, list) + unregister_ftrace_function_probe_func(NULL, tr, probe->probe_ops); } static LIST_HEAD(ftrace_commands); @@ -4056,9 +4313,11 @@ __init int unregister_ftrace_command(struct ftrace_func_command *cmd) return ret; } -static int ftrace_process_regex(struct ftrace_hash *hash, +static int ftrace_process_regex(struct ftrace_iterator *iter, char *buff, int len, int enable) { + struct ftrace_hash *hash = iter->hash; + struct trace_array *tr = iter->ops->private; char *func, *command, *next = buff; struct ftrace_func_command *p; int ret = -EINVAL; @@ -4078,10 +4337,13 @@ static int ftrace_process_regex(struct ftrace_hash *hash, command = strsep(&next, ":"); + if (WARN_ON_ONCE(!tr)) + return -EINVAL; + mutex_lock(&ftrace_cmd_mutex); list_for_each_entry(p, &ftrace_commands, list) { if (strcmp(p->name, command) == 0) { - ret = p->func(hash, func, command, next, enable); + ret = p->func(tr, hash, func, command, next, enable); goto out_unlock; } } @@ -4118,7 +4380,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, if (read >= 0 && trace_parser_loaded(parser) && !trace_parser_cont(parser)) { - ret = ftrace_process_regex(iter->hash, parser->buffer, + ret = ftrace_process_regex(iter, parser->buffer, parser->idx, enable); trace_parser_clear(parser); if (ret < 0) @@ -4163,44 +4425,11 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return add_hash_entry(hash, ip); } -static void ftrace_ops_update_code(struct ftrace_ops *ops, - struct ftrace_ops_hash *old_hash) -{ - struct ftrace_ops *op; - - if (!ftrace_enabled) - return; - - if (ops->flags & FTRACE_OPS_FL_ENABLED) { - ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash); - return; - } - - /* - * If this is the shared global_ops filter, then we need to - * check if there is another ops that shares it, is enabled. - * If so, we still need to run the modify code. - */ - if (ops->func_hash != &global_ops.local_hash) - return; - - do_for_each_ftrace_op(op, ftrace_ops_list) { - if (op->func_hash == &global_ops.local_hash && - op->flags & FTRACE_OPS_FL_ENABLED) { - ftrace_run_modify_code(op, FTRACE_UPDATE_CALLS, old_hash); - /* Only need to do this once */ - return; - } - } while_for_each_ftrace_op(op); -} - static int ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, unsigned long ip, int remove, int reset, int enable) { struct ftrace_hash **orig_hash; - struct ftrace_ops_hash old_hash_ops; - struct ftrace_hash *old_hash; struct ftrace_hash *hash; int ret; @@ -4235,14 +4464,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, } mutex_lock(&ftrace_lock); - old_hash = *orig_hash; - old_hash_ops.filter_hash = ops->func_hash->filter_hash; - old_hash_ops.notrace_hash = ops->func_hash->notrace_hash; - ret = ftrace_hash_move(ops, enable, orig_hash, hash); - if (!ret) { - ftrace_ops_update_code(ops, &old_hash_ops); - free_ftrace_hash_rcu(old_hash); - } + ret = ftrace_hash_move_and_update_ops(ops, orig_hash, hash, enable); mutex_unlock(&ftrace_lock); out_regex_unlock: @@ -4481,10 +4703,8 @@ static void __init set_ftrace_early_filters(void) int ftrace_regex_release(struct inode *inode, struct file *file) { struct seq_file *m = (struct seq_file *)file->private_data; - struct ftrace_ops_hash old_hash_ops; struct ftrace_iterator *iter; struct ftrace_hash **orig_hash; - struct ftrace_hash *old_hash; struct trace_parser *parser; int filter_hash; int ret; @@ -4514,16 +4734,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file) orig_hash = &iter->ops->func_hash->notrace_hash; mutex_lock(&ftrace_lock); - old_hash = *orig_hash; - old_hash_ops.filter_hash = iter->ops->func_hash->filter_hash; - old_hash_ops.notrace_hash = iter->ops->func_hash->notrace_hash; - ret = ftrace_hash_move(iter->ops, filter_hash, - orig_hash, iter->hash); - if (!ret) { - ftrace_ops_update_code(iter->ops, &old_hash_ops); - free_ftrace_hash_rcu(old_hash); - } + ret = ftrace_hash_move_and_update_ops(iter->ops, orig_hash, + iter->hash, filter_hash); mutex_unlock(&ftrace_lock); + } else { + /* For read only, the hash is the ops hash */ + iter->hash = NULL; } mutex_unlock(&iter->ops->func_hash->regex_lock); @@ -4847,7 +5063,7 @@ ftrace_graph_release(struct inode *inode, struct file *file) } out: - kfree(fgd->new_hash); + free_ftrace_hash(fgd->new_hash); kfree(fgd); return ret; @@ -5262,6 +5478,50 @@ void ftrace_module_init(struct module *mod) } #endif /* CONFIG_MODULES */ +void __init ftrace_free_init_mem(void) +{ + unsigned long start = (unsigned long)(&__init_begin); + unsigned long end = (unsigned long)(&__init_end); + struct ftrace_page **last_pg = &ftrace_pages_start; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + struct dyn_ftrace key; + int order; + + key.ip = start; + key.flags = end; /* overload flags, as it is unsigned long */ + + mutex_lock(&ftrace_lock); + + for (pg = ftrace_pages_start; pg; last_pg = &pg->next, pg = *last_pg) { + if (end < pg->records[0].ip || + start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) + continue; + again: + rec = bsearch(&key, pg->records, pg->index, + sizeof(struct dyn_ftrace), + ftrace_cmp_recs); + if (!rec) + continue; + pg->index--; + if (!pg->index) { + *last_pg = pg->next; + order = get_count_order(pg->size / ENTRIES_PER_PAGE); + free_pages((unsigned long)pg->records, order); + kfree(pg); + pg = container_of(last_pg, struct ftrace_page, next); + if (!(*last_pg)) + ftrace_pages = pg; + continue; + } + memmove(rec, rec + 1, + (pg->index - (rec - pg->records)) * sizeof(*rec)); + /* More than one function may be in this block */ + goto again; + } + mutex_unlock(&ftrace_lock); +} + void __init ftrace_init(void) { extern unsigned long __start_mcount_loc[]; @@ -5304,25 +5564,13 @@ void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops) static void ftrace_update_trampoline(struct ftrace_ops *ops) { - -/* - * Currently there's no safe way to free a trampoline when the kernel - * is configured with PREEMPT. That is because a task could be preempted - * when it jumped to the trampoline, it may be preempted for a long time - * depending on the system load, and currently there's no way to know - * when it will be off the trampoline. If the trampoline is freed - * too early, when the task runs again, it will be executing on freed - * memory and crash. - */ -#ifdef CONFIG_PREEMPT - /* Currently, only non dynamic ops can have a trampoline */ - if (ops->flags & FTRACE_OPS_FL_DYNAMIC) - return; -#endif - arch_ftrace_update_trampoline(ops); } +void ftrace_init_trace_array(struct trace_array *tr) +{ + INIT_LIST_HEAD(&tr->func_probes); +} #else static struct ftrace_ops global_ops = { @@ -5377,6 +5625,7 @@ __init void ftrace_init_global_array_ops(struct trace_array *tr) { tr->ops = &global_ops; tr->ops->private = tr; + ftrace_init_trace_array(tr); } void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func) @@ -5531,6 +5780,43 @@ ftrace_filter_pid_sched_switch_probe(void *data, bool preempt, trace_ignore_this_task(pid_list, next)); } +static void +ftrace_pid_follow_sched_process_fork(void *data, + struct task_struct *self, + struct task_struct *task) +{ + struct trace_pid_list *pid_list; + struct trace_array *tr = data; + + pid_list = rcu_dereference_sched(tr->function_pids); + trace_filter_add_remove_task(pid_list, self, task); +} + +static void +ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task) +{ + struct trace_pid_list *pid_list; + struct trace_array *tr = data; + + pid_list = rcu_dereference_sched(tr->function_pids); + trace_filter_add_remove_task(pid_list, NULL, task); +} + +void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) +{ + if (enable) { + register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork, + tr); + register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit, + tr); + } else { + unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork, + tr); + unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit, + tr); + } +} + static void clear_ftrace_pids(struct trace_array *tr) { struct trace_pid_list *pid_list; @@ -5554,6 +5840,15 @@ static void clear_ftrace_pids(struct trace_array *tr) trace_free_pid_list(pid_list); } +void ftrace_clear_pids(struct trace_array *tr) +{ + mutex_lock(&ftrace_lock); + + clear_ftrace_pids(tr); + + mutex_unlock(&ftrace_lock); +} + static void ftrace_pid_reset(struct trace_array *tr) { mutex_lock(&ftrace_lock); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 96fc3c043ad6..4ae268e687fe 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -438,6 +438,7 @@ struct ring_buffer_per_cpu { raw_spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; struct lock_class_key lock_key; + struct buffer_data_page *free_page; unsigned long nr_pages; unsigned int current_context; struct list_head *pages; @@ -3405,11 +3406,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); int ring_buffer_iter_empty(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + struct buffer_page *head_page; + struct buffer_page *commit_page; + unsigned commit; cpu_buffer = iter->cpu_buffer; - return iter->head_page == cpu_buffer->commit_page && - iter->head == rb_commit_index(cpu_buffer); + /* Remember, trace recording is off when iterator is in use */ + reader = cpu_buffer->reader_page; + head_page = cpu_buffer->head_page; + commit_page = cpu_buffer->commit_page; + commit = rb_page_commit(commit_page); + + return ((iter->head_page == commit_page && iter->head == commit) || + (iter->head_page == reader && commit_page == head_page && + head_page->read == commit && + iter->head == rb_page_commit(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); @@ -4377,9 +4390,25 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); */ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu) { - struct buffer_data_page *bpage; + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct buffer_data_page *bpage = NULL; + unsigned long flags; struct page *page; + local_irq_save(flags); + arch_spin_lock(&cpu_buffer->lock); + + if (cpu_buffer->free_page) { + bpage = cpu_buffer->free_page; + cpu_buffer->free_page = NULL; + } + + arch_spin_unlock(&cpu_buffer->lock); + local_irq_restore(flags); + + if (bpage) + goto out; + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); if (!page) @@ -4387,6 +4416,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu) bpage = page_address(page); + out: rb_init_page(bpage); return bpage; @@ -4396,13 +4426,29 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); /** * ring_buffer_free_read_page - free an allocated read page * @buffer: the buffer the page was allocate for + * @cpu: the cpu buffer the page came from * @data: the page to free * * Free a page allocated from ring_buffer_alloc_read_page. */ -void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data) +void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data) { - free_page((unsigned long)data); + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct buffer_data_page *bpage = data; + unsigned long flags; + + local_irq_save(flags); + arch_spin_lock(&cpu_buffer->lock); + + if (!cpu_buffer->free_page) { + cpu_buffer->free_page = bpage; + bpage = NULL; + } + + arch_spin_unlock(&cpu_buffer->lock); + local_irq_restore(flags); + + free_page((unsigned long)bpage); } EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); @@ -4826,9 +4872,9 @@ static __init int test_ringbuffer(void) rb_data[cpu].cnt = cpu; rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu], "rbtester/%d", cpu); - if (WARN_ON(!rb_threads[cpu])) { + if (WARN_ON(IS_ERR(rb_threads[cpu]))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_threads[cpu]); goto out_free; } @@ -4838,9 +4884,9 @@ static __init int test_ringbuffer(void) /* Now create the rb hammer! */ rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer"); - if (WARN_ON(!rb_hammer)) { + if (WARN_ON(IS_ERR(rb_hammer))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_hammer); goto out_free; } diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index c190a4d5013c..9fbcaf567886 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -171,7 +171,7 @@ static enum event_status read_page(int cpu) } } } - ring_buffer_free_read_page(buffer, bpage); + ring_buffer_free_read_page(buffer, cpu, bpage); if (ret < 0) return EVENT_DROPPED; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f35109514a01..1122f151466f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -257,7 +257,7 @@ unsigned long long ns2usecs(u64 nsec) /* trace_flags that are default zero for instances */ #define ZEROED_TRACE_FLAGS \ - TRACE_ITER_EVENT_FORK + (TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK) /* * The global_trace is the descriptor that holds the top-level tracing @@ -757,7 +757,7 @@ __trace_buffer_lock_reserve(struct ring_buffer *buffer, return event; } -static void tracer_tracing_on(struct trace_array *tr) +void tracer_tracing_on(struct trace_array *tr) { if (tr->trace_buffer.buffer) ring_buffer_record_on(tr->trace_buffer.buffer); @@ -894,23 +894,8 @@ int __trace_bputs(unsigned long ip, const char *str) EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT -/** - * trace_snapshot - take a snapshot of the current buffer. - * - * This causes a swap between the snapshot buffer and the current live - * tracing buffer. You can use this to take snapshots of the live - * trace when some condition is triggered, but continue to trace. - * - * Note, make sure to allocate the snapshot with either - * a tracing_snapshot_alloc(), or by doing it manually - * with: echo 1 > /sys/kernel/debug/tracing/snapshot - * - * If the snapshot buffer is not allocated, it will stop tracing. - * Basically making a permanent snapshot. - */ -void tracing_snapshot(void) +static void tracing_snapshot_instance(struct trace_array *tr) { - struct trace_array *tr = &global_trace; struct tracer *tracer = tr->current_trace; unsigned long flags; @@ -938,6 +923,27 @@ void tracing_snapshot(void) update_max_tr(tr, current, smp_processor_id()); local_irq_restore(flags); } + +/** + * trace_snapshot - take a snapshot of the current buffer. + * + * This causes a swap between the snapshot buffer and the current live + * tracing buffer. You can use this to take snapshots of the live + * trace when some condition is triggered, but continue to trace. + * + * Note, make sure to allocate the snapshot with either + * a tracing_snapshot_alloc(), or by doing it manually + * with: echo 1 > /sys/kernel/debug/tracing/snapshot + * + * If the snapshot buffer is not allocated, it will stop tracing. + * Basically making a permanent snapshot. + */ +void tracing_snapshot(void) +{ + struct trace_array *tr = &global_trace; + + tracing_snapshot_instance(tr); +} EXPORT_SYMBOL_GPL(tracing_snapshot); static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, @@ -1039,7 +1045,7 @@ void tracing_snapshot_alloc(void) EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); #endif /* CONFIG_TRACER_SNAPSHOT */ -static void tracer_tracing_off(struct trace_array *tr) +void tracer_tracing_off(struct trace_array *tr) { if (tr->trace_buffer.buffer) ring_buffer_record_off(tr->trace_buffer.buffer); @@ -1424,6 +1430,28 @@ static int wait_on_pipe(struct trace_iterator *iter, bool full) } #ifdef CONFIG_FTRACE_STARTUP_TEST +static bool selftests_can_run; + +struct trace_selftests { + struct list_head list; + struct tracer *type; +}; + +static LIST_HEAD(postponed_selftests); + +static int save_selftest(struct tracer *type) +{ + struct trace_selftests *selftest; + + selftest = kmalloc(sizeof(*selftest), GFP_KERNEL); + if (!selftest) + return -ENOMEM; + + selftest->type = type; + list_add(&selftest->list, &postponed_selftests); + return 0; +} + static int run_tracer_selftest(struct tracer *type) { struct trace_array *tr = &global_trace; @@ -1434,6 +1462,14 @@ static int run_tracer_selftest(struct tracer *type) return 0; /* + * If a tracer registers early in boot up (before scheduling is + * initialized and such), then do not run its selftests yet. + * Instead, run it a little later in the boot process. + */ + if (!selftests_can_run) + return save_selftest(type); + + /* * Run a selftest on this tracer. * Here we reset the trace buffer, and set the current * tracer to be this tracer. The tracer can then run some @@ -1482,6 +1518,47 @@ static int run_tracer_selftest(struct tracer *type) printk(KERN_CONT "PASSED\n"); return 0; } + +static __init int init_trace_selftests(void) +{ + struct trace_selftests *p, *n; + struct tracer *t, **last; + int ret; + + selftests_can_run = true; + + mutex_lock(&trace_types_lock); + + if (list_empty(&postponed_selftests)) + goto out; + + pr_info("Running postponed tracer tests:\n"); + + list_for_each_entry_safe(p, n, &postponed_selftests, list) { + ret = run_tracer_selftest(p->type); + /* If the test fails, then warn and remove from available_tracers */ + if (ret < 0) { + WARN(1, "tracer: %s failed selftest, disabling\n", + p->type->name); + last = &trace_types; + for (t = trace_types; t; t = t->next) { + if (t == p->type) { + *last = t->next; + break; + } + last = &t->next; + } + } + list_del(&p->list); + kfree(p); + } + + out: + mutex_unlock(&trace_types_lock); + + return 0; +} +core_initcall(init_trace_selftests); #else static inline int run_tracer_selftest(struct tracer *type) { @@ -1899,7 +1976,7 @@ static void __trace_find_cmdline(int pid, char comm[]) map = savedcmd->map_pid_to_cmdline[pid]; if (map != NO_CMDLINE_MAP) - strcpy(comm, get_saved_cmdlines(map)); + strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN); else strcpy(comm, "<...>"); } @@ -1927,6 +2004,18 @@ void tracing_record_cmdline(struct task_struct *tsk) __this_cpu_write(trace_cmdline_save, false); } +/* + * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq + * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function + * simplifies those functions and keeps them in sync. + */ +enum print_line_t trace_handle_return(struct trace_seq *s) +{ + return trace_seq_has_overflowed(s) ? + TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED; +} +EXPORT_SYMBOL_GPL(trace_handle_return); + void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, int pc) @@ -2479,7 +2568,36 @@ static inline void ftrace_trace_stack(struct trace_array *tr, void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { - __ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL); + struct ring_buffer *buffer = tr->trace_buffer.buffer; + + if (rcu_is_watching()) { + __ftrace_trace_stack(buffer, flags, skip, pc, NULL); + return; + } + + /* + * When an NMI triggers, RCU is enabled via rcu_nmi_enter(), + * but if the above rcu_is_watching() failed, then the NMI + * triggered someplace critical, and rcu_irq_enter() should + * not be called from NMI. + */ + if (unlikely(in_nmi())) + return; + + /* + * It is possible that a function is being traced in a + * location that RCU is not watching. A call to + * rcu_irq_enter() will make sure that it is, but there's + * a few internal rcu functions that could be traced + * where that wont work either. In those cases, we just + * do nothing. + */ + if (unlikely(rcu_irq_enter_disabled())) + return; + + rcu_irq_enter_irqson(); + __ftrace_trace_stack(buffer, flags, skip, pc, NULL); + rcu_irq_exit_irqson(); } /** @@ -3222,13 +3340,14 @@ static void test_cpu_buff_start(struct trace_iterator *iter) if (!(iter->iter_flags & TRACE_FILE_ANNOTATE)) return; - if (iter->started && cpumask_test_cpu(iter->cpu, iter->started)) + if (cpumask_available(iter->started) && + cpumask_test_cpu(iter->cpu, iter->started)) return; if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries) return; - if (iter->started) + if (cpumask_available(iter->started)) cpumask_set_cpu(iter->cpu, iter->started); /* Don't print started cpu buffer for the first entry of the trace */ @@ -4122,6 +4241,9 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) if (mask == TRACE_ITER_EVENT_FORK) trace_event_follow_fork(tr, enabled); + if (mask == TRACE_ITER_FUNC_FORK) + ftrace_pid_follow_fork(tr, enabled); + if (mask == TRACE_ITER_OVERWRITE) { ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled); #ifdef CONFIG_TRACER_MAX_TRACE @@ -4355,6 +4477,7 @@ static const char readme_msg[] = "\t -:[<group>/]<event>\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" + "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n" #endif #ifdef CONFIG_UPROBE_EVENTS "\t place: <path>:<offset>\n" @@ -5529,7 +5652,6 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .partial = partial_def, .nr_pages = 0, /* This gets updated below. */ .nr_pages_max = PIPE_DEF_BUFFERS, - .flags = flags, .ops = &tracing_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, }; @@ -5962,6 +6084,7 @@ static int tracing_clock_open(struct inode *inode, struct file *file) struct ftrace_buffer_info { struct trace_iterator iter; void *spare; + unsigned int spare_cpu; unsigned int read; }; @@ -6291,9 +6414,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return -EBUSY; #endif - if (!info->spare) + if (!info->spare) { info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, iter->cpu_file); + info->spare_cpu = iter->cpu_file; + } if (!info->spare) return -ENOMEM; @@ -6353,7 +6478,8 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) __trace_array_put(iter->tr); if (info->spare) - ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare); + ring_buffer_free_read_page(iter->trace_buffer->buffer, + info->spare_cpu, info->spare); kfree(info); mutex_unlock(&trace_types_lock); @@ -6364,6 +6490,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) struct buffer_ref { struct ring_buffer *buffer; void *page; + int cpu; int ref; }; @@ -6375,7 +6502,7 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, if (--ref->ref) return; - ring_buffer_free_read_page(ref->buffer, ref->page); + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); kfree(ref); buf->private = 0; } @@ -6409,7 +6536,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) if (--ref->ref) return; - ring_buffer_free_read_page(ref->buffer, ref->page); + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); kfree(ref); spd->partial[i].private = 0; } @@ -6427,7 +6554,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .pages = pages_def, .partial = partial_def, .nr_pages_max = PIPE_DEF_BUFFERS, - .flags = flags, .ops = &buffer_pipe_buf_ops, .spd_release = buffer_spd_release, }; @@ -6474,11 +6600,13 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, kfree(ref); break; } + ref->cpu = iter->cpu_file; r = ring_buffer_read_page(ref->buffer, &ref->page, len, iter->cpu_file, 1); if (r < 0) { - ring_buffer_free_read_page(ref->buffer, ref->page); + ring_buffer_free_read_page(ref->buffer, ref->cpu, + ref->page); kfree(ref); break; } @@ -6649,43 +6777,89 @@ static const struct file_operations tracing_dyn_info_fops = { #if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) static void -ftrace_snapshot(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_snapshot(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - tracing_snapshot(); + tracing_snapshot_instance(tr); } static void -ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - unsigned long *count = (long *)data; + struct ftrace_func_mapper *mapper = data; + long *count = NULL; - if (!*count) - return; + if (mapper) + count = (long *)ftrace_func_mapper_find_ip(mapper, ip); + + if (count) { + + if (*count <= 0) + return; - if (*count != -1) (*count)--; + } - tracing_snapshot(); + tracing_snapshot_instance(tr); } static int ftrace_snapshot_print(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data) { - long count = (long)data; + struct ftrace_func_mapper *mapper = data; + long *count = NULL; seq_printf(m, "%ps:", (void *)ip); seq_puts(m, "snapshot"); - if (count == -1) - seq_puts(m, ":unlimited\n"); + if (mapper) + count = (long *)ftrace_func_mapper_find_ip(mapper, ip); + + if (count) + seq_printf(m, ":count=%ld\n", *count); else - seq_printf(m, ":count=%ld\n", count); + seq_puts(m, ":unlimited\n"); return 0; } +static int +ftrace_snapshot_init(struct ftrace_probe_ops *ops, struct trace_array *tr, + unsigned long ip, void *init_data, void **data) +{ + struct ftrace_func_mapper *mapper = *data; + + if (!mapper) { + mapper = allocate_ftrace_func_mapper(); + if (!mapper) + return -ENOMEM; + *data = mapper; + } + + return ftrace_func_mapper_add_ip(mapper, ip, init_data); +} + +static void +ftrace_snapshot_free(struct ftrace_probe_ops *ops, struct trace_array *tr, + unsigned long ip, void *data) +{ + struct ftrace_func_mapper *mapper = data; + + if (!ip) { + if (!mapper) + return; + free_ftrace_func_mapper(mapper, NULL); + return; + } + + ftrace_func_mapper_remove_ip(mapper, ip); +} + static struct ftrace_probe_ops snapshot_probe_ops = { .func = ftrace_snapshot, .print = ftrace_snapshot_print, @@ -6694,10 +6868,12 @@ static struct ftrace_probe_ops snapshot_probe_ops = { static struct ftrace_probe_ops snapshot_count_probe_ops = { .func = ftrace_count_snapshot, .print = ftrace_snapshot_print, + .init = ftrace_snapshot_init, + .free = ftrace_snapshot_free, }; static int -ftrace_trace_snapshot_callback(struct ftrace_hash *hash, +ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enable) { struct ftrace_probe_ops *ops; @@ -6711,10 +6887,8 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash, ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; - if (glob[0] == '!') { - unregister_ftrace_function_probe_func(glob+1, ops); - return 0; - } + if (glob[0] == '!') + return unregister_ftrace_function_probe_func(glob+1, tr, ops); if (!param) goto out_reg; @@ -6733,11 +6907,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash, return ret; out_reg: - ret = register_ftrace_function_probe(glob, ops, count); + ret = alloc_snapshot(tr); + if (ret < 0) + goto out; - if (ret >= 0) - alloc_snapshot(&global_trace); + ret = register_ftrace_function_probe(glob, tr, ops, count); + out: return ret < 0 ? ret : 0; } @@ -7346,6 +7522,8 @@ static int instance_mkdir(const char *name) goto out_free_tr; } + ftrace_init_trace_array(tr); + init_tracer_tracefs(tr, tr->dir); init_trace_flags_index(tr); __update_tracer_options(tr); @@ -7401,7 +7579,9 @@ static int instance_rmdir(const char *name) } tracing_set_nop(tr); + clear_ftrace_function_probes(tr); event_trace_del_tracer(tr); + ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); tracefs_remove_recursive(tr->dir); free_trace_buffers(tr); @@ -7965,6 +8145,9 @@ __init static int tracer_alloc_buffers(void) register_tracer(&nop_trace); + /* Function tracing may start here (via kernel command line) */ + init_function_trace(); + /* All seems OK, enable tracing */ tracing_disabled = 0; @@ -7999,7 +8182,7 @@ out: return ret; } -void __init trace_init(void) +void __init early_trace_init(void) { if (tracepoint_printk) { tracepoint_print_iter = @@ -8010,6 +8193,10 @@ void __init trace_init(void) static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); +} + +void __init trace_init(void) +{ trace_event_init(); } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ae1cce91fead..39fd77330aab 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -262,6 +262,9 @@ struct trace_array { #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops *ops; struct trace_pid_list __rcu *function_pids; +#ifdef CONFIG_DYNAMIC_FTRACE + struct list_head func_probes; +#endif /* function tracing enabled */ int function_enabled; #endif @@ -579,6 +582,8 @@ void tracing_reset_all_online_cpus(void); int tracing_open_generic(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); int tracer_tracing_is_on(struct trace_array *tr); +void tracer_tracing_on(struct trace_array *tr); +void tracer_tracing_off(struct trace_array *tr); struct dentry *trace_create_file(const char *name, umode_t mode, struct dentry *parent, @@ -696,6 +701,9 @@ extern void trace_event_follow_fork(struct trace_array *tr, bool enable); #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; +void ftrace_init_trace_array(struct trace_array *tr); +#else +static inline void ftrace_init_trace_array(struct trace_array *tr) { } #endif #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func extern int DYN_FTRACE_TEST_NAME(void); @@ -880,6 +888,14 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags) extern struct list_head ftrace_pids; #ifdef CONFIG_FUNCTION_TRACER +struct ftrace_func_command { + struct list_head list; + char *name; + int (*func)(struct trace_array *tr, + struct ftrace_hash *hash, + char *func, char *cmd, + char *params, int enable); +}; extern bool ftrace_filter_param __initdata; static inline int ftrace_trace_task(struct trace_array *tr) { @@ -896,6 +912,9 @@ int using_ftrace_ops_list_func(void); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d_tracer); +void ftrace_clear_pids(struct trace_array *tr); +int init_function_trace(void); +void ftrace_pid_follow_fork(struct trace_array *tr, bool enable); #else static inline int ftrace_trace_task(struct trace_array *tr) { @@ -914,15 +933,76 @@ ftrace_init_global_array_ops(struct trace_array *tr) { } static inline void ftrace_reset_array_ops(struct trace_array *tr) { } static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { } static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { } +static inline void ftrace_clear_pids(struct trace_array *tr) { } +static inline int init_function_trace(void) { return 0; } +static inline void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) { } /* ftace_func_t type is not defined, use macro instead of static inline */ #define ftrace_init_array_ops(tr, func) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER */ #if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) + +struct ftrace_probe_ops { + void (*func)(unsigned long ip, + unsigned long parent_ip, + struct trace_array *tr, + struct ftrace_probe_ops *ops, + void *data); + int (*init)(struct ftrace_probe_ops *ops, + struct trace_array *tr, + unsigned long ip, void *init_data, + void **data); + void (*free)(struct ftrace_probe_ops *ops, + struct trace_array *tr, + unsigned long ip, void *data); + int (*print)(struct seq_file *m, + unsigned long ip, + struct ftrace_probe_ops *ops, + void *data); +}; + +struct ftrace_func_mapper; +typedef int (*ftrace_mapper_func)(void *data); + +struct ftrace_func_mapper *allocate_ftrace_func_mapper(void); +void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper, + unsigned long ip); +int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper, + unsigned long ip, void *data); +void *ftrace_func_mapper_remove_ip(struct ftrace_func_mapper *mapper, + unsigned long ip); +void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper, + ftrace_mapper_func free_func); + +extern int +register_ftrace_function_probe(char *glob, struct trace_array *tr, + struct ftrace_probe_ops *ops, void *data); +extern int +unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, + struct ftrace_probe_ops *ops); +extern void clear_ftrace_function_probes(struct trace_array *tr); + +int register_ftrace_command(struct ftrace_func_command *cmd); +int unregister_ftrace_command(struct ftrace_func_command *cmd); + void ftrace_create_filter_files(struct ftrace_ops *ops, struct dentry *parent); void ftrace_destroy_filter_files(struct ftrace_ops *ops); #else +struct ftrace_func_command; + +static inline __init int register_ftrace_command(struct ftrace_func_command *cmd) +{ + return -EINVAL; +} +static inline __init int unregister_ftrace_command(char *cmd_name) +{ + return -EINVAL; +} +static inline void clear_ftrace_function_probes(struct trace_array *tr) +{ +} + /* * The ops parameter passed in is usually undefined. * This must be a macro. @@ -987,11 +1067,13 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, #ifdef CONFIG_FUNCTION_TRACER # define FUNCTION_FLAGS \ - C(FUNCTION, "function-trace"), + C(FUNCTION, "function-trace"), \ + C(FUNC_FORK, "function-fork"), # define FUNCTION_DEFAULT_FLAGS TRACE_ITER_FUNCTION #else # define FUNCTION_FLAGS # define FUNCTION_DEFAULT_FLAGS 0UL +# define TRACE_ITER_FUNC_FORK 0UL #endif #ifdef CONFIG_STACKTRACE diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c index e49fbe901cfc..16a8cf02eee9 100644 --- a/kernel/trace/trace_benchmark.c +++ b/kernel/trace/trace_benchmark.c @@ -153,10 +153,18 @@ static int benchmark_event_kthread(void *arg) trace_do_benchmark(); /* - * We don't go to sleep, but let others - * run as well. + * We don't go to sleep, but let others run as well. + * This is bascially a "yield()" to let any task that + * 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 + * 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_rcu_qs(); } return 0; diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index c203ac4df791..adcdbbeae010 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -348,14 +348,14 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __field( u64, duration ) __field( u64, outer_duration ) __field( u64, nmi_total_ts ) - __field_struct( struct timespec, timestamp ) - __field_desc( long, timestamp, tv_sec ) + __field_struct( struct timespec64, timestamp ) + __field_desc( s64, timestamp, tv_sec ) __field_desc( long, timestamp, tv_nsec ) __field( unsigned int, nmi_count ) __field( unsigned int, seqnum ) ), - F_printk("cnt:%u\tts:%010lu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n", + F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-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 93116549a284..e7973e10398c 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2460,15 +2460,8 @@ struct event_probe_data { bool enable; }; -static void -event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data) +static void update_event_probe(struct event_probe_data *data) { - struct event_probe_data **pdata = (struct event_probe_data **)_data; - struct event_probe_data *data = *pdata; - - if (!data) - return; - if (data->enable) clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &data->file->flags); else @@ -2476,77 +2469,141 @@ event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data) } static void -event_enable_count_probe(unsigned long ip, unsigned long parent_ip, void **_data) +event_enable_probe(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - struct event_probe_data **pdata = (struct event_probe_data **)_data; - struct event_probe_data *data = *pdata; + struct ftrace_func_mapper *mapper = data; + struct event_probe_data *edata; + void **pdata; - if (!data) + pdata = ftrace_func_mapper_find_ip(mapper, ip); + if (!pdata || !*pdata) + return; + + edata = *pdata; + update_event_probe(edata); +} + +static void +event_enable_count_probe(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) +{ + struct ftrace_func_mapper *mapper = data; + struct event_probe_data *edata; + void **pdata; + + pdata = ftrace_func_mapper_find_ip(mapper, ip); + if (!pdata || !*pdata) return; - if (!data->count) + edata = *pdata; + + if (!edata->count) return; /* Skip if the event is in a state we want to switch to */ - if (data->enable == !(data->file->flags & EVENT_FILE_FL_SOFT_DISABLED)) + if (edata->enable == !(edata->file->flags & EVENT_FILE_FL_SOFT_DISABLED)) return; - if (data->count != -1) - (data->count)--; + if (edata->count != -1) + (edata->count)--; - event_enable_probe(ip, parent_ip, _data); + update_event_probe(edata); } static int event_enable_print(struct seq_file *m, unsigned long ip, - struct ftrace_probe_ops *ops, void *_data) + struct ftrace_probe_ops *ops, void *data) { - struct event_probe_data *data = _data; + struct ftrace_func_mapper *mapper = data; + struct event_probe_data *edata; + void **pdata; + + pdata = ftrace_func_mapper_find_ip(mapper, ip); + + if (WARN_ON_ONCE(!pdata || !*pdata)) + return 0; + + edata = *pdata; seq_printf(m, "%ps:", (void *)ip); seq_printf(m, "%s:%s:%s", - data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, - data->file->event_call->class->system, - trace_event_name(data->file->event_call)); + edata->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, + edata->file->event_call->class->system, + trace_event_name(edata->file->event_call)); - if (data->count == -1) + if (edata->count == -1) seq_puts(m, ":unlimited\n"); else - seq_printf(m, ":count=%ld\n", data->count); + seq_printf(m, ":count=%ld\n", edata->count); return 0; } static int -event_enable_init(struct ftrace_probe_ops *ops, unsigned long ip, - void **_data) +event_enable_init(struct ftrace_probe_ops *ops, struct trace_array *tr, + unsigned long ip, void *init_data, void **data) { - struct event_probe_data **pdata = (struct event_probe_data **)_data; - struct event_probe_data *data = *pdata; + struct ftrace_func_mapper *mapper = *data; + struct event_probe_data *edata = init_data; + int ret; + + if (!mapper) { + mapper = allocate_ftrace_func_mapper(); + if (!mapper) + return -ENODEV; + *data = mapper; + } + + ret = ftrace_func_mapper_add_ip(mapper, ip, edata); + if (ret < 0) + return ret; + + edata->ref++; - data->ref++; + return 0; +} + +static int free_probe_data(void *data) +{ + struct event_probe_data *edata = data; + + edata->ref--; + if (!edata->ref) { + /* Remove the SOFT_MODE flag */ + __ftrace_event_enable_disable(edata->file, 0, 1); + module_put(edata->file->event_call->mod); + kfree(edata); + } return 0; } static void -event_enable_free(struct ftrace_probe_ops *ops, unsigned long ip, - void **_data) +event_enable_free(struct ftrace_probe_ops *ops, struct trace_array *tr, + unsigned long ip, void *data) { - struct event_probe_data **pdata = (struct event_probe_data **)_data; - struct event_probe_data *data = *pdata; + struct ftrace_func_mapper *mapper = data; + struct event_probe_data *edata; - if (WARN_ON_ONCE(data->ref <= 0)) + if (!ip) { + if (!mapper) + return; + free_ftrace_func_mapper(mapper, free_probe_data); return; - - data->ref--; - if (!data->ref) { - /* Remove the SOFT_MODE flag */ - __ftrace_event_enable_disable(data->file, 0, 1); - module_put(data->file->event_call->mod); - kfree(data); } - *pdata = NULL; + + edata = ftrace_func_mapper_remove_ip(mapper, ip); + + if (WARN_ON_ONCE(!edata)) + return; + + if (WARN_ON_ONCE(edata->ref <= 0)) + return; + + free_probe_data(edata); } static struct ftrace_probe_ops event_enable_probe_ops = { @@ -2578,10 +2635,9 @@ static struct ftrace_probe_ops event_disable_count_probe_ops = { }; static int -event_enable_func(struct ftrace_hash *hash, +event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enabled) { - struct trace_array *tr = top_trace_array(); struct trace_event_file *file; struct ftrace_probe_ops *ops; struct event_probe_data *data; @@ -2619,12 +2675,12 @@ event_enable_func(struct ftrace_hash *hash, ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops; if (glob[0] == '!') { - unregister_ftrace_function_probe_func(glob+1, ops); - ret = 0; + ret = unregister_ftrace_function_probe_func(glob+1, tr, ops); goto out; } ret = -ENOMEM; + data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) goto out; @@ -2661,7 +2717,8 @@ event_enable_func(struct ftrace_hash *hash, ret = __ftrace_event_enable_disable(file, 1, 1); if (ret < 0) goto out_put; - ret = register_ftrace_function_probe(glob, ops, data); + + ret = register_ftrace_function_probe(glob, tr, ops, data); /* * The above returns on success the # of functions enabled, * but if it didn't find any functions it returns zero. diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 0efa00d80623..a3bddbfd0874 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -267,10 +267,14 @@ static struct tracer function_trace __tracer_data = }; #ifdef CONFIG_DYNAMIC_FTRACE -static void update_traceon_count(void **data, bool on) +static void update_traceon_count(struct ftrace_probe_ops *ops, + unsigned long ip, + struct trace_array *tr, bool on, + void *data) { - long *count = (long *)data; - long old_count = *count; + struct ftrace_func_mapper *mapper = data; + long *count; + long old_count; /* * Tracing gets disabled (or enabled) once per count. @@ -301,23 +305,22 @@ static void update_traceon_count(void **data, bool on) * setting the tracing_on file. But we currently don't care * about that. */ - if (!old_count) + count = (long *)ftrace_func_mapper_find_ip(mapper, ip); + old_count = *count; + + if (old_count <= 0) return; /* Make sure we see count before checking tracing state */ smp_rmb(); - if (on == !!tracing_is_on()) + if (on == !!tracer_tracing_is_on(tr)) return; if (on) - tracing_on(); + tracer_tracing_on(tr); else - tracing_off(); - - /* unlimited? */ - if (old_count == -1) - return; + tracer_tracing_off(tr); /* Make sure tracing state is visible before updating count */ smp_wmb(); @@ -326,33 +329,41 @@ static void update_traceon_count(void **data, bool on) } static void -ftrace_traceon_count(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_traceon_count(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - update_traceon_count(data, 1); + update_traceon_count(ops, ip, tr, 1, data); } static void -ftrace_traceoff_count(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_traceoff_count(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - update_traceon_count(data, 0); + update_traceon_count(ops, ip, tr, 0, data); } static void -ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_traceon(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - if (tracing_is_on()) + if (tracer_tracing_is_on(tr)) return; - tracing_on(); + tracer_tracing_on(tr); } static void -ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_traceoff(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - if (!tracing_is_on()) + if (!tracer_tracing_is_on(tr)) return; - tracing_off(); + tracer_tracing_off(tr); } /* @@ -364,144 +375,218 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data) */ #define STACK_SKIP 4 +static __always_inline void trace_stack(struct trace_array *tr) +{ + unsigned long flags; + int pc; + + local_save_flags(flags); + pc = preempt_count(); + + __trace_stack(tr, flags, STACK_SKIP, pc); +} + static void -ftrace_stacktrace(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_stacktrace(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - trace_dump_stack(STACK_SKIP); + trace_stack(tr); } static void -ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - long *count = (long *)data; + struct ftrace_func_mapper *mapper = data; + long *count; long old_count; long new_count; + if (!tracing_is_on()) + return; + + /* unlimited? */ + if (!mapper) { + trace_stack(tr); + return; + } + + count = (long *)ftrace_func_mapper_find_ip(mapper, ip); + /* * Stack traces should only execute the number of times the * user specified in the counter. */ do { - - if (!tracing_is_on()) - return; - old_count = *count; if (!old_count) return; - /* unlimited? */ - if (old_count == -1) { - trace_dump_stack(STACK_SKIP); - return; - } - new_count = old_count - 1; new_count = cmpxchg(count, old_count, new_count); if (new_count == old_count) - trace_dump_stack(STACK_SKIP); + trace_stack(tr); + + if (!tracing_is_on()) + return; } while (new_count != old_count); } -static int update_count(void **data) +static int update_count(struct ftrace_probe_ops *ops, unsigned long ip, + void *data) { - unsigned long *count = (long *)data; + struct ftrace_func_mapper *mapper = data; + long *count = NULL; - if (!*count) - return 0; + if (mapper) + count = (long *)ftrace_func_mapper_find_ip(mapper, ip); - if (*count != -1) + if (count) { + if (*count <= 0) + return 0; (*count)--; + } return 1; } static void -ftrace_dump_probe(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_dump_probe(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - if (update_count(data)) + if (update_count(ops, ip, data)) ftrace_dump(DUMP_ALL); } /* Only dump the current CPU buffer. */ static void -ftrace_cpudump_probe(unsigned long ip, unsigned long parent_ip, void **data) +ftrace_cpudump_probe(unsigned long ip, unsigned long parent_ip, + struct trace_array *tr, struct ftrace_probe_ops *ops, + void *data) { - if (update_count(data)) + if (update_count(ops, ip, data)) ftrace_dump(DUMP_ORIG); } static int ftrace_probe_print(const char *name, struct seq_file *m, - unsigned long ip, void *data) + unsigned long ip, struct ftrace_probe_ops *ops, + void *data) { - long count = (long)data; + struct ftrace_func_mapper *mapper = data; + long *count = NULL; seq_printf(m, "%ps:%s", (void *)ip, name); - if (count == -1) - seq_puts(m, ":unlimited\n"); + if (mapper) + count = (long *)ftrace_func_mapper_find_ip(mapper, ip); + + if (count) + seq_printf(m, ":count=%ld\n", *count); else - seq_printf(m, ":count=%ld\n", count); + seq_puts(m, ":unlimited\n"); return 0; } static int ftrace_traceon_print(struct seq_file *m, unsigned long ip, - struct ftrace_probe_ops *ops, void *data) + struct ftrace_probe_ops *ops, + void *data) { - return ftrace_probe_print("traceon", m, ip, data); + return ftrace_probe_print("traceon", m, ip, ops, data); } static int ftrace_traceoff_print(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data) { - return ftrace_probe_print("traceoff", m, ip, data); + return ftrace_probe_print("traceoff", m, ip, ops, data); } static int ftrace_stacktrace_print(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data) { - return ftrace_probe_print("stacktrace", m, ip, data); + return ftrace_probe_print("stacktrace", m, ip, ops, data); } static int ftrace_dump_print(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data) { - return ftrace_probe_print("dump", m, ip, data); + return ftrace_probe_print("dump", m, ip, ops, data); } static int ftrace_cpudump_print(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data) { - return ftrace_probe_print("cpudump", m, ip, data); + return ftrace_probe_print("cpudump", m, ip, ops, data); +} + + +static int +ftrace_count_init(struct ftrace_probe_ops *ops, struct trace_array *tr, + unsigned long ip, void *init_data, void **data) +{ + struct ftrace_func_mapper *mapper = *data; + + if (!mapper) { + mapper = allocate_ftrace_func_mapper(); + if (!mapper) + return -ENOMEM; + *data = mapper; + } + + return ftrace_func_mapper_add_ip(mapper, ip, init_data); +} + +static void +ftrace_count_free(struct ftrace_probe_ops *ops, struct trace_array *tr, + unsigned long ip, void *data) +{ + struct ftrace_func_mapper *mapper = data; + + if (!ip) { + free_ftrace_func_mapper(mapper, NULL); + return; + } + + ftrace_func_mapper_remove_ip(mapper, ip); } static struct ftrace_probe_ops traceon_count_probe_ops = { .func = ftrace_traceon_count, .print = ftrace_traceon_print, + .init = ftrace_count_init, + .free = ftrace_count_free, }; static struct ftrace_probe_ops traceoff_count_probe_ops = { .func = ftrace_traceoff_count, .print = ftrace_traceoff_print, + .init = ftrace_count_init, + .free = ftrace_count_free, }; static struct ftrace_probe_ops stacktrace_count_probe_ops = { .func = ftrace_stacktrace_count, .print = ftrace_stacktrace_print, + .init = ftrace_count_init, + .free = ftrace_count_free, }; static struct ftrace_probe_ops dump_probe_ops = { .func = ftrace_dump_probe, .print = ftrace_dump_print, + .init = ftrace_count_init, + .free = ftrace_count_free, }; static struct ftrace_probe_ops cpudump_probe_ops = { @@ -525,7 +610,8 @@ static struct ftrace_probe_ops stacktrace_probe_ops = { }; static int -ftrace_trace_probe_callback(struct ftrace_probe_ops *ops, +ftrace_trace_probe_callback(struct trace_array *tr, + struct ftrace_probe_ops *ops, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enable) { @@ -537,10 +623,8 @@ ftrace_trace_probe_callback(struct ftrace_probe_ops *ops, if (!enable) return -EINVAL; - if (glob[0] == '!') { - unregister_ftrace_function_probe_func(glob+1, ops); - return 0; - } + if (glob[0] == '!') + return unregister_ftrace_function_probe_func(glob+1, tr, ops); if (!param) goto out_reg; @@ -559,13 +643,13 @@ ftrace_trace_probe_callback(struct ftrace_probe_ops *ops, return ret; out_reg: - ret = register_ftrace_function_probe(glob, ops, count); + ret = register_ftrace_function_probe(glob, tr, ops, count); return ret < 0 ? ret : 0; } static int -ftrace_trace_onoff_callback(struct ftrace_hash *hash, +ftrace_trace_onoff_callback(struct trace_array *tr, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enable) { struct ftrace_probe_ops *ops; @@ -576,24 +660,24 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash, else ops = param ? &traceoff_count_probe_ops : &traceoff_probe_ops; - return ftrace_trace_probe_callback(ops, hash, glob, cmd, + return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd, param, enable); } static int -ftrace_stacktrace_callback(struct ftrace_hash *hash, +ftrace_stacktrace_callback(struct trace_array *tr, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enable) { struct ftrace_probe_ops *ops; ops = param ? &stacktrace_count_probe_ops : &stacktrace_probe_ops; - return ftrace_trace_probe_callback(ops, hash, glob, cmd, + return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd, param, enable); } static int -ftrace_dump_callback(struct ftrace_hash *hash, +ftrace_dump_callback(struct trace_array *tr, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enable) { struct ftrace_probe_ops *ops; @@ -601,12 +685,12 @@ ftrace_dump_callback(struct ftrace_hash *hash, ops = &dump_probe_ops; /* Only dump once. */ - return ftrace_trace_probe_callback(ops, hash, glob, cmd, + return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd, "1", enable); } static int -ftrace_cpudump_callback(struct ftrace_hash *hash, +ftrace_cpudump_callback(struct trace_array *tr, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enable) { struct ftrace_probe_ops *ops; @@ -614,7 +698,7 @@ ftrace_cpudump_callback(struct ftrace_hash *hash, ops = &cpudump_probe_ops; /* Only dump once. */ - return ftrace_trace_probe_callback(ops, hash, glob, cmd, + return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd, "1", enable); } @@ -687,9 +771,8 @@ static inline int init_func_cmd_traceon(void) } #endif /* CONFIG_DYNAMIC_FTRACE */ -static __init int init_function_trace(void) +__init int init_function_trace(void) { init_func_cmd_traceon(); return register_tracer(&function_trace); } -core_initcall(init_function_trace); diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 21ea6ae77d93..d7c8e4ec3d9d 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -79,12 +79,12 @@ static u64 last_tracing_thresh = DEFAULT_LAT_THRESHOLD * NSEC_PER_USEC; /* Individual latency samples are stored here when detected. */ struct hwlat_sample { - u64 seqnum; /* unique sequence */ - u64 duration; /* delta */ - u64 outer_duration; /* delta (outer loop) */ - u64 nmi_total_ts; /* Total time spent in NMIs */ - struct timespec timestamp; /* wall time */ - int nmi_count; /* # NMIs during this sample */ + u64 seqnum; /* unique sequence */ + u64 duration; /* delta */ + u64 outer_duration; /* delta (outer loop) */ + u64 nmi_total_ts; /* Total time spent in NMIs */ + struct timespec64 timestamp; /* wall time */ + int nmi_count; /* # NMIs during this sample */ }; /* keep the global state somewhere. */ @@ -250,7 +250,7 @@ static int get_sample(void) s.seqnum = hwlat_data.count; s.duration = sample; s.outer_duration = outer_sample; - s.timestamp = CURRENT_TIME; + ktime_get_real_ts64(&s.timestamp); s.nmi_total_ts = nmi_total_ts; s.nmi_count = nmi_count; trace_hwlat_sample(&s); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5f688cc724f0..c129fca6ec99 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -25,6 +25,7 @@ #include "trace_probe.h" #define KPROBE_EVENT_SYSTEM "kprobes" +#define KRETPROBE_MAXACTIVE_MAX 4096 /** * Kprobe event core functions @@ -282,6 +283,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, void *addr, const char *symbol, unsigned long offs, + int maxactive, int nargs, bool is_return) { struct trace_kprobe *tk; @@ -309,6 +311,8 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, else tk->rp.kp.pre_handler = kprobe_dispatcher; + tk->rp.maxactive = maxactive; + if (!event || !is_good_name(event)) { ret = -EINVAL; goto error; @@ -598,8 +602,10 @@ static int create_trace_kprobe(int argc, char **argv) { /* * Argument syntax: - * - Add kprobe: p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS] - * - Add kretprobe: r[:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS] + * - Add kprobe: + * p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS] + * - Add kretprobe: + * r[MAXACTIVE][:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS] * Fetch args: * $retval : fetch return value * $stack : fetch stack address @@ -619,6 +625,7 @@ static int create_trace_kprobe(int argc, char **argv) int i, ret = 0; bool is_return = false, is_delete = false; char *symbol = NULL, *event = NULL, *group = NULL; + int maxactive = 0; char *arg; unsigned long offset = 0; void *addr = NULL; @@ -637,8 +644,28 @@ static int create_trace_kprobe(int argc, char **argv) return -EINVAL; } - if (argv[0][1] == ':') { - event = &argv[0][2]; + event = strchr(&argv[0][1], ':'); + if (event) { + event[0] = '\0'; + event++; + } + if (is_return && isdigit(argv[0][1])) { + ret = kstrtouint(&argv[0][1], 0, &maxactive); + if (ret) { + pr_info("Failed to parse maxactive.\n"); + return ret; + } + /* kretprobes instances are iterated over via a list. The + * maximum should stay reasonable. + */ + if (maxactive > KRETPROBE_MAXACTIVE_MAX) { + pr_info("Maxactive is too big (%d > %d).\n", + maxactive, KRETPROBE_MAXACTIVE_MAX); + return -E2BIG; + } + } + + if (event) { if (strchr(event, '/')) { group = event; event = strchr(group, '/') + 1; @@ -681,10 +708,6 @@ static int create_trace_kprobe(int argc, char **argv) return -EINVAL; } if (isdigit(argv[1][0])) { - if (is_return) { - pr_info("Return probe point must be a symbol.\n"); - return -EINVAL; - } /* an address specified */ ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); if (ret) { @@ -700,8 +723,9 @@ static int create_trace_kprobe(int argc, char **argv) pr_info("Failed to parse symbol.\n"); return ret; } - if (offset && is_return) { - pr_info("Return probe must be used without offset.\n"); + if (offset && is_return && + !function_offset_within_entry(NULL, symbol, offset)) { + pr_info("Given offset is not valid for return probe.\n"); return -EINVAL; } } @@ -718,8 +742,8 @@ static int create_trace_kprobe(int argc, char **argv) is_return ? 'r' : 'p', addr); event = buf; } - tk = alloc_trace_kprobe(group, event, addr, symbol, offset, argc, - is_return); + tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive, + argc, is_return); if (IS_ERR(tk)) { pr_info("Failed to allocate trace_probe.(%d)\n", (int)PTR_ERR(tk)); @@ -1511,6 +1535,11 @@ static __init int kprobe_trace_self_tests_init(void) end: release_all_trace_kprobes(); + /* + * Wait for the optimizer work to finish. Otherwise it might fiddle + * with probes in already freed __init text. + */ + wait_for_kprobe_optimizer(); if (warn) pr_cont("NG: Some tests are failed. Please check them.\n"); else diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 02a4aeb22c47..08f9bab8089e 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -4,7 +4,6 @@ * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> * */ - #include <linux/module.h> #include <linux/mutex.h> #include <linux/ftrace.h> @@ -1161,11 +1160,11 @@ trace_hwlat_print(struct trace_iterator *iter, int flags, trace_assign_type(field, entry); - trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%ld.%09ld", + trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%lld.%09ld", field->seqnum, field->duration, field->outer_duration, - field->timestamp.tv_sec, + (long long)field->timestamp.tv_sec, field->timestamp.tv_nsec); if (field->nmi_count) { @@ -1195,10 +1194,10 @@ trace_hwlat_raw(struct trace_iterator *iter, int flags, trace_assign_type(field, iter->ent); - trace_seq_printf(s, "%llu %lld %ld %09ld %u\n", + trace_seq_printf(s, "%llu %lld %lld %09ld %u\n", field->duration, field->outer_duration, - field->timestamp.tv_sec, + (long long)field->timestamp.tv_sec, field->timestamp.tv_nsec, field->seqnum); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 5fb1f2c87e6b..76aa04d4c925 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -35,7 +35,7 @@ unsigned long stack_trace_max_size; arch_spinlock_t stack_trace_max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; -static DEFINE_PER_CPU(int, trace_active); +DEFINE_PER_CPU(int, disable_stack_tracer); static DEFINE_MUTEX(stack_sysctl_mutex); int stack_tracer_enabled; @@ -96,6 +96,14 @@ check_stack(unsigned long ip, unsigned long *stack) if (in_nmi()) return; + /* + * There's a slight chance that we are tracing inside the + * RCU infrastructure, and rcu_irq_enter() will not work + * as expected. + */ + if (unlikely(rcu_irq_enter_disabled())) + return; + local_irq_save(flags); arch_spin_lock(&stack_trace_max_lock); @@ -207,13 +215,12 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) { unsigned long stack; - int cpu; preempt_disable_notrace(); - cpu = raw_smp_processor_id(); /* no atomic needed, we only modify this variable by this cpu */ - if (per_cpu(trace_active, cpu)++ != 0) + __this_cpu_inc(disable_stack_tracer); + if (__this_cpu_read(disable_stack_tracer) != 1) goto out; ip += MCOUNT_INSN_SIZE; @@ -221,7 +228,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip, check_stack(ip, &stack); out: - per_cpu(trace_active, cpu)--; + __this_cpu_dec(disable_stack_tracer); /* prevent recursion in schedule */ preempt_enable_notrace(); } @@ -253,7 +260,6 @@ stack_max_size_write(struct file *filp, const char __user *ubuf, long *ptr = filp->private_data; unsigned long val, flags; int ret; - int cpu; ret = kstrtoul_from_user(ubuf, count, 10, &val); if (ret) @@ -264,16 +270,15 @@ stack_max_size_write(struct file *filp, const char __user *ubuf, /* * In case we trace inside arch_spin_lock() or after (NMI), * we will cause circular lock, so we also need to increase - * the percpu trace_active here. + * the percpu disable_stack_tracer here. */ - cpu = smp_processor_id(); - per_cpu(trace_active, cpu)++; + __this_cpu_inc(disable_stack_tracer); arch_spin_lock(&stack_trace_max_lock); *ptr = val; arch_spin_unlock(&stack_trace_max_lock); - per_cpu(trace_active, cpu)--; + __this_cpu_dec(disable_stack_tracer); local_irq_restore(flags); return count; @@ -307,12 +312,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos) static void *t_start(struct seq_file *m, loff_t *pos) { - int cpu; - local_irq_disable(); - cpu = smp_processor_id(); - per_cpu(trace_active, cpu)++; + __this_cpu_inc(disable_stack_tracer); arch_spin_lock(&stack_trace_max_lock); @@ -324,12 +326,9 @@ static void *t_start(struct seq_file *m, loff_t *pos) static void t_stop(struct seq_file *m, void *p) { - int cpu; - arch_spin_unlock(&stack_trace_max_lock); - cpu = smp_processor_id(); - per_cpu(trace_active, cpu)--; + __this_cpu_dec(disable_stack_tracer); local_irq_enable(); } |