diff options
Diffstat (limited to 'kernel/trace')
| -rw-r--r-- | kernel/trace/Kconfig | 22 | ||||
| -rw-r--r-- | kernel/trace/blktrace.c | 283 | ||||
| -rw-r--r-- | kernel/trace/bpf_trace.c | 100 | ||||
| -rw-r--r-- | kernel/trace/ftrace.c | 497 | ||||
| -rw-r--r-- | kernel/trace/ring_buffer.c | 24 | ||||
| -rw-r--r-- | kernel/trace/ring_buffer_benchmark.c | 2 | ||||
| -rw-r--r-- | kernel/trace/trace.c | 521 | ||||
| -rw-r--r-- | kernel/trace/trace.h | 39 | ||||
| -rw-r--r-- | kernel/trace/trace_event_perf.c | 4 | ||||
| -rw-r--r-- | kernel/trace/trace_events.c | 81 | ||||
| -rw-r--r-- | kernel/trace/trace_events_filter.c | 6 | ||||
| -rw-r--r-- | kernel/trace/trace_functions_graph.c | 2 | ||||
| -rw-r--r-- | kernel/trace/trace_kprobe.c | 15 | ||||
| -rw-r--r-- | kernel/trace/trace_mmiotrace.c | 1 | ||||
| -rw-r--r-- | kernel/trace/trace_output.c | 48 | ||||
| -rw-r--r-- | kernel/trace/trace_sched_switch.c | 72 | ||||
| -rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 8 | ||||
| -rw-r--r-- | kernel/trace/trace_selftest.c | 2 | ||||
| -rw-r--r-- | kernel/trace/trace_stack.c | 21 | ||||
| -rw-r--r-- | kernel/trace/trace_syscalls.c | 57 | ||||
| -rw-r--r-- | kernel/trace/trace_uprobe.c | 2 | ||||
| -rw-r--r-- | kernel/trace/tracing_map.c | 11 |
22 files changed, 1369 insertions, 449 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 7e06f04e98fe..434c840e2d82 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -667,30 +667,30 @@ config RING_BUFFER_STARTUP_TEST If unsure, say N -config TRACE_ENUM_MAP_FILE - bool "Show enum mappings for trace events" +config TRACE_EVAL_MAP_FILE + bool "Show eval mappings for trace events" depends on TRACING help - The "print fmt" of the trace events will show the enum names instead - of their values. This can cause problems for user space tools that - use this string to parse the raw data as user space does not know + The "print fmt" of the trace events will show the enum/sizeof names + instead of their values. This can cause problems for user space tools + that use this string to parse the raw data as user space does not know how to convert the string to its value. To fix this, there's a special macro in the kernel that can be used - to convert the enum into its value. If this macro is used, then the - print fmt strings will have the enums converted to their values. + to convert an enum/sizeof into its value. If this macro is used, then + the print fmt strings will be converted to their values. If something does not get converted properly, this option can be - used to show what enums the kernel tried to convert. + used to show what enums/sizeof the kernel tried to convert. - This option is for debugging the enum conversions. A file is created - in the tracing directory called "enum_map" that will show the enum + This option is for debugging the conversions. A file is created + in the tracing directory called "eval_map" that will show the names matched with their values and what trace event system they belong too. Normally, the mapping of the strings to values will be freed after boot up or module load. With this option, they will not be freed, as - they are needed for the "enum_map" file. Enabling this option will + they are needed for the "eval_map" file. Enabling this option will increase the memory footprint of the running kernel. If unsure, say N diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 193c5f5e3f79..45a3928544ce 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -27,6 +27,7 @@ #include <linux/time.h> #include <linux/uaccess.h> #include <linux/list.h> +#include <linux/blk-cgroup.h> #include "../../block/blk.h" @@ -46,10 +47,16 @@ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock); /* Select an alternative, minimalistic output than the original one */ #define TRACE_BLK_OPT_CLASSIC 0x1 +#define TRACE_BLK_OPT_CGROUP 0x2 +#define TRACE_BLK_OPT_CGNAME 0x4 static struct tracer_opt blk_tracer_opts[] = { /* Default disable the minimalistic output */ { TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) }, +#ifdef CONFIG_BLK_CGROUP + { TRACER_OPT(blk_cgroup, TRACE_BLK_OPT_CGROUP) }, + { TRACER_OPT(blk_cgname, TRACE_BLK_OPT_CGNAME) }, +#endif { } }; @@ -68,7 +75,8 @@ static void blk_unregister_tracepoints(void); * Send out a notify message. */ static void trace_note(struct blk_trace *bt, pid_t pid, int action, - const void *data, size_t len) + const void *data, size_t len, + union kernfs_node_id *cgid) { struct blk_io_trace *t; struct ring_buffer_event *event = NULL; @@ -76,12 +84,13 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, int pc = 0; int cpu = smp_processor_id(); bool blk_tracer = blk_tracer_enabled; + ssize_t cgid_len = cgid ? sizeof(*cgid) : 0; if (blk_tracer) { buffer = blk_tr->trace_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, - sizeof(*t) + len, + sizeof(*t) + len + cgid_len, 0, pc); if (!event) return; @@ -92,17 +101,19 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, if (!bt->rchan) return; - t = relay_reserve(bt->rchan, sizeof(*t) + len); + t = relay_reserve(bt->rchan, sizeof(*t) + len + cgid_len); if (t) { t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->time = ktime_to_ns(ktime_get()); record_it: t->device = bt->dev; - t->action = action; + t->action = action | (cgid ? __BLK_TN_CGROUP : 0); t->pid = pid; t->cpu = cpu; - t->pdu_len = len; - memcpy((void *) t + sizeof(*t), data, len); + t->pdu_len = len + cgid_len; + if (cgid) + memcpy((void *)t + sizeof(*t), cgid, cgid_len); + memcpy((void *) t + sizeof(*t) + cgid_len, data, len); if (blk_tracer) trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc); @@ -122,7 +133,7 @@ static void trace_note_tsk(struct task_struct *tsk) spin_lock_irqsave(&running_trace_lock, flags); list_for_each_entry(bt, &running_trace_list, running_list) { trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, - sizeof(tsk->comm)); + sizeof(tsk->comm), NULL); } spin_unlock_irqrestore(&running_trace_lock, flags); } @@ -139,11 +150,12 @@ static void trace_note_time(struct blk_trace *bt) words[1] = now.tv_nsec; local_irq_save(flags); - trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words)); + trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), NULL); local_irq_restore(flags); } -void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) +void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, + const char *fmt, ...) { int n; va_list args; @@ -167,7 +179,14 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); - trace_note(bt, 0, BLK_TN_MESSAGE, buf, n); + if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) + blkcg = NULL; +#ifdef CONFIG_BLK_CGROUP + trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, + blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : NULL); +#else + trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, NULL); +#endif local_irq_restore(flags); } EXPORT_SYMBOL_GPL(__trace_note_message); @@ -204,7 +223,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), */ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, int op, int op_flags, u32 what, int error, int pdu_len, - void *pdu_data) + void *pdu_data, union kernfs_node_id *cgid) { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; @@ -215,6 +234,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, pid_t pid; int cpu, pc = 0; bool blk_tracer = blk_tracer_enabled; + ssize_t cgid_len = cgid ? sizeof(*cgid) : 0; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; @@ -229,6 +249,8 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); + if (cgid) + what |= __BLK_TA_CGROUP; pid = tsk->pid; if (act_log_check(bt, what, sector, pid)) @@ -241,7 +263,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, buffer = blk_tr->trace_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, - sizeof(*t) + pdu_len, + sizeof(*t) + pdu_len + cgid_len, 0, pc); if (!event) return; @@ -258,7 +280,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, * from coming in and stepping on our toes. */ local_irq_save(flags); - t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len); + t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len + cgid_len); if (t) { sequence = per_cpu_ptr(bt->sequence, cpu); @@ -280,10 +302,12 @@ record_it: t->action = what; t->device = bt->dev; t->error = error; - t->pdu_len = pdu_len; + t->pdu_len = pdu_len + cgid_len; + if (cgid_len) + memcpy((void *)t + sizeof(*t), cgid, cgid_len); if (pdu_len) - memcpy((void *) t + sizeof(*t), pdu_data, pdu_len); + memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len); if (blk_tracer) { trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc); @@ -359,7 +383,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer, return PTR_ERR(msg); bt = filp->private_data; - __trace_note_message(bt, "%s", msg); + __trace_note_message(bt, NULL, "%s", msg); kfree(msg); return count; @@ -624,6 +648,12 @@ int blk_trace_startstop(struct request_queue *q, int start) } EXPORT_SYMBOL_GPL(blk_trace_startstop); +/* + * When reading or writing the blktrace sysfs files, the references to the + * opened sysfs or device files should prevent the underlying block device + * from being removed. So no further delete protection is really needed. + */ + /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device @@ -641,7 +671,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); switch (cmd) { case BLKTRACESETUP: @@ -667,7 +697,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) break; } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); return ret; } @@ -684,6 +714,36 @@ void blk_trace_shutdown(struct request_queue *q) } } +#ifdef CONFIG_BLK_CGROUP +static union kernfs_node_id * +blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) +{ + struct blk_trace *bt = q->blk_trace; + + if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) + return NULL; + + if (!bio->bi_css) + return NULL; + return cgroup_get_kernfs_id(bio->bi_css->cgroup); +} +#else +static union kernfs_node_id * +blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) +{ + return NULL; +} +#endif + +static union kernfs_node_id * +blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) +{ + if (!rq->bio) + return NULL; + /* Use the first bio */ + return blk_trace_bio_get_cgid(q, rq->bio); +} + /* * blktrace probes */ @@ -694,13 +754,15 @@ void blk_trace_shutdown(struct request_queue *q) * @error: return status to log * @nr_bytes: number of completed bytes * @what: the action + * @cgid: the cgroup info * * Description: * Records an action against a request. Will log the bio offset + size. * **/ static void blk_add_trace_rq(struct request *rq, int error, - unsigned int nr_bytes, u32 what) + unsigned int nr_bytes, u32 what, + union kernfs_node_id *cgid) { struct blk_trace *bt = rq->q->blk_trace; @@ -713,32 +775,36 @@ static void blk_add_trace_rq(struct request *rq, int error, 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, error, 0, NULL); + rq->cmd_flags, what, error, 0, NULL, cgid); } static void blk_add_trace_rq_insert(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT); + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT, + blk_trace_request_get_cgid(q, rq)); } static void blk_add_trace_rq_issue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE); + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE, + blk_trace_request_get_cgid(q, rq)); } static void blk_add_trace_rq_requeue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE); + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE, + blk_trace_request_get_cgid(q, rq)); } static void blk_add_trace_rq_complete(void *ignore, struct request *rq, int error, unsigned int nr_bytes) { - blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE); + blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE, + blk_trace_request_get_cgid(rq->q, rq)); } /** @@ -753,7 +819,7 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq, * **/ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, - u32 what, int error) + u32 what, int error, union kernfs_node_id *cgid) { struct blk_trace *bt = q->blk_trace; @@ -761,20 +827,22 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, return; __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_opf, what, error, 0, NULL); + bio_op(bio), bio->bi_opf, what, error, 0, NULL, cgid); } static void blk_add_trace_bio_bounce(void *ignore, struct request_queue *q, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0); + blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_bio_complete(void *ignore, struct request_queue *q, struct bio *bio, int error) { - blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error); + blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_bio_backmerge(void *ignore, @@ -782,7 +850,8 @@ static void blk_add_trace_bio_backmerge(void *ignore, struct request *rq, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0); + blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_bio_frontmerge(void *ignore, @@ -790,13 +859,15 @@ static void blk_add_trace_bio_frontmerge(void *ignore, struct request *rq, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0); + blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_bio_queue(void *ignore, struct request_queue *q, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0); + blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_getrq(void *ignore, @@ -804,13 +875,14 @@ static void blk_add_trace_getrq(void *ignore, struct bio *bio, int rw) { if (bio) - blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); + blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0, + blk_trace_bio_get_cgid(q, bio)); else { struct blk_trace *bt = q->blk_trace; if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, - NULL); + NULL, NULL); } } @@ -820,13 +892,14 @@ static void blk_add_trace_sleeprq(void *ignore, struct bio *bio, int rw) { if (bio) - blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); + blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0, + blk_trace_bio_get_cgid(q, bio)); else { struct blk_trace *bt = q->blk_trace; if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, - 0, 0, NULL); + 0, 0, NULL, NULL); } } @@ -835,7 +908,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q) struct blk_trace *bt = q->blk_trace; if (bt) - __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL); + __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, @@ -852,7 +925,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, else what = BLK_TA_UNPLUG_TIMER; - __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu); + __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL); } } @@ -867,8 +940,8 @@ static void blk_add_trace_split(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, - BLK_TA_SPLIT, bio->bi_error, sizeof(rpdu), - &rpdu); + BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), + &rpdu, blk_trace_bio_get_cgid(q, bio)); } } @@ -896,12 +969,12 @@ static void blk_add_trace_bio_remap(void *ignore, return; r.device_from = cpu_to_be32(dev); - r.device_to = cpu_to_be32(bio->bi_bdev->bd_dev); + r.device_to = cpu_to_be32(bio_dev(bio)); r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_error, - sizeof(r), &r); + bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, + sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); } /** @@ -934,7 +1007,7 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, - sizeof(r), &r); + sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); } /** @@ -958,7 +1031,8 @@ 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, 0, len, data); + BLK_TA_DRV_DATA, 0, len, data, + blk_trace_request_get_cgid(q, rq)); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1031,7 +1105,7 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) int i = 0; int tc = t->action >> BLK_TC_SHIFT; - if (t->action == BLK_TN_MESSAGE) { + if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { rwbs[i++] = 'N'; goto out; } @@ -1066,9 +1140,21 @@ const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) return (const struct blk_io_trace *)ent; } -static inline const void *pdu_start(const struct trace_entry *ent) +static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg) +{ + return (void *)(te_blk_io_trace(ent) + 1) + + (has_cg ? sizeof(union kernfs_node_id) : 0); +} + +static inline const void *cgid_start(const struct trace_entry *ent) { - return te_blk_io_trace(ent) + 1; + return (void *)(te_blk_io_trace(ent) + 1); +} + +static inline int pdu_real_len(const struct trace_entry *ent, bool has_cg) +{ + return te_blk_io_trace(ent)->pdu_len - + (has_cg ? sizeof(union kernfs_node_id) : 0); } static inline u32 t_action(const struct trace_entry *ent) @@ -1096,16 +1182,16 @@ static inline __u16 t_error(const struct trace_entry *ent) return te_blk_io_trace(ent)->error; } -static __u64 get_pdu_int(const struct trace_entry *ent) +static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg) { - const __u64 *val = pdu_start(ent); + const __u64 *val = pdu_start(ent, has_cg); return be64_to_cpu(*val); } static void get_pdu_remap(const struct trace_entry *ent, - struct blk_io_trace_remap *r) + struct blk_io_trace_remap *r, bool has_cg) { - const struct blk_io_trace_remap *__r = pdu_start(ent); + const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); __u64 sector_from = __r->sector_from; r->device_from = be32_to_cpu(__r->device_from); @@ -1113,9 +1199,11 @@ static void get_pdu_remap(const struct trace_entry *ent, r->sector_from = be64_to_cpu(sector_from); } -typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act); +typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act, + bool has_cg); -static void blk_log_action_classic(struct trace_iterator *iter, const char *act) +static void blk_log_action_classic(struct trace_iterator *iter, const char *act, + bool has_cg) { char rwbs[RWBS_LEN]; unsigned long long ts = iter->ts; @@ -1131,24 +1219,43 @@ static void blk_log_action_classic(struct trace_iterator *iter, const char *act) secs, nsec_rem, iter->ent->pid, act, rwbs); } -static void blk_log_action(struct trace_iterator *iter, const char *act) +static void blk_log_action(struct trace_iterator *iter, const char *act, + bool has_cg) { char rwbs[RWBS_LEN]; const struct blk_io_trace *t = te_blk_io_trace(iter->ent); fill_rwbs(rwbs, t); - trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", - MAJOR(t->device), MINOR(t->device), act, rwbs); -} - -static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent) + if (has_cg) { + const union kernfs_node_id *id = cgid_start(iter->ent); + + if (blk_tracer_flags.val & TRACE_BLK_OPT_CGNAME) { + char blkcg_name_buf[NAME_MAX + 1] = "<...>"; + + cgroup_path_from_kernfs_id(id, blkcg_name_buf, + sizeof(blkcg_name_buf)); + trace_seq_printf(&iter->seq, "%3d,%-3d %s %2s %3s ", + MAJOR(t->device), MINOR(t->device), + blkcg_name_buf, act, rwbs); + } else + trace_seq_printf(&iter->seq, + "%3d,%-3d %x,%-x %2s %3s ", + MAJOR(t->device), MINOR(t->device), + id->ino, id->generation, act, rwbs); + } else + trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", + MAJOR(t->device), MINOR(t->device), act, rwbs); +} + +static void blk_log_dump_pdu(struct trace_seq *s, + const struct trace_entry *ent, bool has_cg) { const unsigned char *pdu_buf; int pdu_len; int i, end; - pdu_buf = pdu_start(ent); - pdu_len = te_blk_io_trace(ent)->pdu_len; + pdu_buf = pdu_start(ent, has_cg); + pdu_len = pdu_real_len(ent, has_cg); if (!pdu_len) return; @@ -1179,7 +1286,7 @@ static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent) trace_seq_puts(s, ") "); } -static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; @@ -1187,7 +1294,7 @@ static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent) if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { trace_seq_printf(s, "%u ", t_bytes(ent)); - blk_log_dump_pdu(s, ent); + blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%s]\n", cmd); } else { if (t_sec(ent)) @@ -1199,10 +1306,10 @@ static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent) } static void blk_log_with_error(struct trace_seq *s, - const struct trace_entry *ent) + const struct trace_entry *ent, bool has_cg) { if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { - blk_log_dump_pdu(s, ent); + blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%d]\n", t_error(ent)); } else { if (t_sec(ent)) @@ -1215,18 +1322,18 @@ static void blk_log_with_error(struct trace_seq *s, } } -static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { struct blk_io_trace_remap r = { .device_from = 0, }; - get_pdu_remap(ent, &r); + get_pdu_remap(ent, &r, has_cg); trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", t_sector(ent), t_sec(ent), MAJOR(r.device_from), MINOR(r.device_from), (unsigned long long)r.sector_from); } -static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; @@ -1235,30 +1342,31 @@ static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent) trace_seq_printf(s, "[%s]\n", cmd); } -static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); - trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent)); + trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent, has_cg)); } -static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent), - get_pdu_int(ent), cmd); + get_pdu_int(ent, has_cg), cmd); } -static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent, + bool has_cg) { - const struct blk_io_trace *t = te_blk_io_trace(ent); - trace_seq_putmem(s, t + 1, t->pdu_len); + trace_seq_putmem(s, pdu_start(ent, has_cg), + pdu_real_len(ent, has_cg)); trace_seq_putc(s, '\n'); } @@ -1298,7 +1406,8 @@ static void blk_tracer_reset(struct trace_array *tr) static const struct { const char *act[2]; - void (*print)(struct trace_seq *s, const struct trace_entry *ent); + void (*print)(struct trace_seq *s, const struct trace_entry *ent, + bool has_cg); } what2act[] = { [__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic }, [__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic }, @@ -1326,23 +1435,25 @@ static enum print_line_t print_one_line(struct trace_iterator *iter, u16 what; bool long_act; blk_log_action_t *log_action; + bool has_cg; t = te_blk_io_trace(iter->ent); - what = t->action & ((1 << BLK_TC_SHIFT) - 1); + what = (t->action & ((1 << BLK_TC_SHIFT) - 1)) & ~__BLK_TA_CGROUP; long_act = !!(tr->trace_flags & TRACE_ITER_VERBOSE); log_action = classic ? &blk_log_action_classic : &blk_log_action; + has_cg = t->action & __BLK_TA_CGROUP; - if (t->action == BLK_TN_MESSAGE) { - log_action(iter, long_act ? "message" : "m"); - blk_log_msg(s, iter->ent); + if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { + log_action(iter, long_act ? "message" : "m", has_cg); + blk_log_msg(s, iter->ent, has_cg); return trace_handle_return(s); } if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act))) trace_seq_printf(s, "Unknown action %x\n", what); else { - log_action(iter, what2act[what].act[long_act]); - what2act[what].print(s, iter->ent); + log_action(iter, what2act[what].act[long_act], has_cg); + what2act[what].print(s, iter->ent, has_cg); } return trace_handle_return(s); @@ -1622,7 +1733,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!q->blk_trace); @@ -1641,7 +1752,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: @@ -1683,7 +1794,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { if (value) @@ -1709,7 +1820,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 460a031c77e5..dc498b605d5d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -122,8 +122,8 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) } /* - * limited trace_printk() - * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed + * Only limited trace_printk() conversion specifiers allowed: + * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s */ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) @@ -198,15 +198,42 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, i++; } - if (fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') + if (fmt[i] != 'i' && fmt[i] != 'd' && + fmt[i] != 'u' && fmt[i] != 'x') return -EINVAL; fmt_cnt++; } - return __trace_printk(1/* fake ip will not be printed */, fmt, - mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1, - mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2, - mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3); +/* Horrid workaround for getting va_list handling working with different + * argument type combinations generically for 32 and 64 bit archs. + */ +#define __BPF_TP_EMIT() __BPF_ARG3_TP() +#define __BPF_TP(...) \ + __trace_printk(1 /* Fake ip will not be printed. */, \ + fmt, ##__VA_ARGS__) + +#define __BPF_ARG1_TP(...) \ + ((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64)) \ + ? __BPF_TP(arg1, ##__VA_ARGS__) \ + : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32)) \ + ? __BPF_TP((long)arg1, ##__VA_ARGS__) \ + : __BPF_TP((u32)arg1, ##__VA_ARGS__))) + +#define __BPF_ARG2_TP(...) \ + ((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64)) \ + ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__) \ + : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32)) \ + ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__) \ + : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__))) + +#define __BPF_ARG3_TP(...) \ + ((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64)) \ + ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__) \ + : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32)) \ + ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__) \ + : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__))) + + return __BPF_TP_EMIT(); } static const struct bpf_func_proto bpf_trace_printk_proto = { @@ -234,7 +261,8 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; - struct perf_event *event; + u64 value = 0; + int err; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; @@ -247,21 +275,14 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) if (!ee) return -ENOENT; - event = ee->event; - if (unlikely(event->attr.type != PERF_TYPE_HARDWARE && - event->attr.type != PERF_TYPE_RAW)) - return -EINVAL; - - /* make sure event is local and doesn't have pmu::count */ - if (unlikely(event->oncpu != cpu || event->pmu->count)) - return -EINVAL; - + err = perf_event_read_local(ee->event, &value); /* - * we don't know if the function is run successfully by the - * return value. It can be judged in other places, such as - * eBPF programs. + * this api is ugly since we miss [-22..-2] range of valid + * counter values, but that's uapi */ - return perf_event_read_local(event); + if (err) + return err; + return value; } static const struct bpf_func_proto bpf_perf_event_read_proto = { @@ -272,14 +293,16 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; +static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd); + static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, u64 flags, struct perf_raw_record *raw) { struct bpf_array *array = container_of(map, struct bpf_array, map); + struct perf_sample_data *sd = this_cpu_ptr(&bpf_sd); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; - struct perf_sample_data sample_data; struct bpf_event_entry *ee; struct perf_event *event; @@ -300,9 +323,9 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; - perf_sample_data_init(&sample_data, 0, 0); - sample_data.raw = raw; - perf_event_output(event, &sample_data, regs); + perf_sample_data_init(sd, 0, 0); + sd->raw = raw; + perf_event_output(event, sd, regs); return 0; } @@ -483,7 +506,7 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func /* bpf+kprobe programs can access fields of 'struct pt_regs' */ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct pt_regs)) return false; @@ -566,7 +589,7 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) } static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) return false; @@ -585,40 +608,47 @@ const struct bpf_verifier_ops tracepoint_prog_ops = { }; static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { + const int size_sp = FIELD_SIZEOF(struct bpf_perf_event_data, + sample_period); + if (off < 0 || off >= sizeof(struct bpf_perf_event_data)) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; - if (off == offsetof(struct bpf_perf_event_data, sample_period)) { - if (size != sizeof(u64)) + + switch (off) { + case bpf_ctx_range(struct bpf_perf_event_data, sample_period): + bpf_ctx_record_field_size(info, size_sp); + if (!bpf_ctx_narrow_access_ok(off, size, size_sp)) return false; - } else { + break; + default: if (size != sizeof(long)) return false; } + return true; } static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, - struct bpf_prog *prog) + struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_perf_event_data, sample_period): - BUILD_BUG_ON(FIELD_SIZEOF(struct perf_sample_data, period) != sizeof(u64)); - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, data), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, - offsetof(struct perf_sample_data, period)); + bpf_target_off(struct perf_sample_data, period, 8, + target_size)); break; default: *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b308be30dfb9..8319e09e15b9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -113,7 +113,7 @@ static int ftrace_disabled __read_mostly; static DEFINE_MUTEX(ftrace_lock); -static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; @@ -169,8 +169,11 @@ int ftrace_nr_registered_ops(void) mutex_lock(&ftrace_lock); - for (ops = ftrace_ops_list; - ops != &ftrace_list_end; ops = ops->next) + for (ops = rcu_dereference_protected(ftrace_ops_list, + lockdep_is_held(&ftrace_lock)); + ops != &ftrace_list_end; + ops = rcu_dereference_protected(ops->next, + lockdep_is_held(&ftrace_lock))) cnt++; mutex_unlock(&ftrace_lock); @@ -275,10 +278,11 @@ static void update_ftrace_function(void) * If there's only one ftrace_ops registered, the ftrace_ops_list * will point to the ops we want. */ - set_function_trace_op = ftrace_ops_list; + set_function_trace_op = rcu_dereference_protected(ftrace_ops_list, + lockdep_is_held(&ftrace_lock)); /* If there's no ftrace_ops registered, just call the stub function */ - if (ftrace_ops_list == &ftrace_list_end) { + if (set_function_trace_op == &ftrace_list_end) { func = ftrace_stub; /* @@ -286,7 +290,8 @@ static void update_ftrace_function(void) * recursion safe and not dynamic and the arch supports passing ops, * then have the mcount trampoline call the function directly. */ - } else if (ftrace_ops_list->next == &ftrace_list_end) { + } else if (rcu_dereference_protected(ftrace_ops_list->next, + lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) { func = ftrace_ops_get_list_func(ftrace_ops_list); } else { @@ -348,9 +353,11 @@ int using_ftrace_ops_list_func(void) return ftrace_trace_function == ftrace_ops_list_func; } -static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) +static void add_ftrace_ops(struct ftrace_ops __rcu **list, + struct ftrace_ops *ops) { - ops->next = *list; + rcu_assign_pointer(ops->next, *list); + /* * We are entering ops into the list but another * CPU might be walking that list. We need to make sure @@ -360,7 +367,8 @@ static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) rcu_assign_pointer(*list, ops); } -static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) +static int remove_ftrace_ops(struct ftrace_ops __rcu **list, + struct ftrace_ops *ops) { struct ftrace_ops **p; @@ -368,7 +376,10 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) * If we are removing the last function, then simply point * to the ftrace_stub. */ - if (*list == ops && ops->next == &ftrace_list_end) { + if (rcu_dereference_protected(*list, + lockdep_is_held(&ftrace_lock)) == ops && + rcu_dereference_protected(ops->next, + lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) { *list = &ftrace_list_end; return 0; } @@ -878,6 +889,10 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace) function_profile_call(trace->func, 0, NULL, NULL); + /* If function graph is shutting down, ret_stack can be NULL */ + if (!current->ret_stack) + return 0; + if (index >= 0 && index < FTRACE_RETFUNC_DEPTH) current->ret_stack[index].subtime = 0; @@ -1293,6 +1308,28 @@ static void ftrace_hash_clear(struct ftrace_hash *hash) FTRACE_WARN_ON(hash->count); } +static void free_ftrace_mod(struct ftrace_mod_load *ftrace_mod) +{ + list_del(&ftrace_mod->list); + kfree(ftrace_mod->module); + kfree(ftrace_mod->func); + kfree(ftrace_mod); +} + +static void clear_ftrace_mod_list(struct list_head *head) +{ + struct ftrace_mod_load *p, *n; + + /* stack tracer isn't supported yet */ + if (!head) + return; + + mutex_lock(&ftrace_lock); + list_for_each_entry_safe(p, n, head, list) + free_ftrace_mod(p); + mutex_unlock(&ftrace_lock); +} + static void free_ftrace_hash(struct ftrace_hash *hash) { if (!hash || hash == EMPTY_HASH) @@ -1346,6 +1383,35 @@ static struct ftrace_hash *alloc_ftrace_hash(int size_bits) return hash; } + +static int ftrace_add_mod(struct trace_array *tr, + const char *func, const char *module, + int enable) +{ + struct ftrace_mod_load *ftrace_mod; + struct list_head *mod_head = enable ? &tr->mod_trace : &tr->mod_notrace; + + ftrace_mod = kzalloc(sizeof(*ftrace_mod), GFP_KERNEL); + if (!ftrace_mod) + return -ENOMEM; + + ftrace_mod->func = kstrdup(func, GFP_KERNEL); + ftrace_mod->module = kstrdup(module, GFP_KERNEL); + ftrace_mod->enable = enable; + + if (!ftrace_mod->func || !ftrace_mod->module) + goto out_free; + + list_add(&ftrace_mod->list, mod_head); + + return 0; + + out_free: + free_ftrace_mod(ftrace_mod); + + return -ENOMEM; +} + static struct ftrace_hash * alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) { @@ -1359,6 +1425,9 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) if (!new_hash) return NULL; + if (hash) + new_hash->flags = hash->flags; + /* Empty hash? */ if (ftrace_hash_empty(hash)) return new_hash; @@ -1403,7 +1472,7 @@ __ftrace_hash_move(struct ftrace_hash *src) /* * If the new source is empty, just return the empty_hash. */ - if (!src->count) + if (ftrace_hash_empty(src)) return EMPTY_HASH; /* @@ -1420,6 +1489,8 @@ __ftrace_hash_move(struct ftrace_hash *src) if (!new_hash) return NULL; + new_hash->flags = src->flags; + size = 1 << src->size_bits; for (i = 0; i < size; i++) { hhd = &src->buckets[i]; @@ -1513,8 +1584,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) return 0; #endif - hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash); - hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash); + rcu_assign_pointer(hash.filter_hash, ops->func_hash->filter_hash); + rcu_assign_pointer(hash.notrace_hash, ops->func_hash->notrace_hash); if (hash_contains_ip(ip, &hash)) ret = 1; @@ -1650,7 +1721,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, struct dyn_ftrace *rec; bool update = false; int count = 0; - int all = 0; + int all = false; /* Only update if the ops has been registered */ if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) @@ -1671,7 +1742,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, hash = ops->func_hash->filter_hash; other_hash = ops->func_hash->notrace_hash; if (ftrace_hash_empty(hash)) - all = 1; + all = true; } else { inc = !inc; hash = ops->func_hash->notrace_hash; @@ -2757,13 +2828,14 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) if (!command || !ftrace_enabled) { /* - * If these are per_cpu ops, they still need their - * per_cpu field freed. Since, function tracing is + * If these are dynamic or per_cpu ops, they still + * need their data freed. Since, function tracing is * not currently active, we can just free them * without synchronizing all CPUs. */ - if (ops->flags & FTRACE_OPS_FL_PER_CPU) - per_cpu_ops_free(ops); + if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) + goto free_ops; + return 0; } @@ -2784,7 +2856,8 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) * If there's no more ops registered with ftrace, run a * sanity check to make sure all rec flags are cleared. */ - if (ftrace_ops_list == &ftrace_list_end) { + if (rcu_dereference_protected(ftrace_ops_list, + lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) { struct ftrace_page *pg; struct dyn_ftrace *rec; @@ -2828,6 +2901,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) if (IS_ENABLED(CONFIG_PREEMPT)) synchronize_rcu_tasks(); + free_ops: arch_ftrace_trampoline_free(ops); if (ops->flags & FTRACE_OPS_FL_PER_CPU) @@ -3061,6 +3135,7 @@ ftrace_allocate_pages(unsigned long num_to_init) struct ftrace_iterator { loff_t pos; loff_t func_pos; + loff_t mod_pos; struct ftrace_page *pg; struct dyn_ftrace *func; struct ftrace_func_probe *probe; @@ -3068,6 +3143,8 @@ struct ftrace_iterator { struct trace_parser parser; struct ftrace_hash *hash; struct ftrace_ops *ops; + struct trace_array *tr; + struct list_head *mod_list; int pidx; int idx; unsigned flags; @@ -3152,13 +3229,13 @@ static void *t_probe_start(struct seq_file *m, loff_t *pos) if (!(iter->flags & FTRACE_ITER_DO_PROBES)) return NULL; - if (iter->func_pos > *pos) + if (iter->mod_pos > *pos) return NULL; iter->probe = NULL; iter->probe_entry = NULL; iter->pidx = 0; - for (l = 0; l <= (*pos - iter->func_pos); ) { + for (l = 0; l <= (*pos - iter->mod_pos); ) { p = t_probe_next(m, &l); if (!p) break; @@ -3197,6 +3274,82 @@ t_probe_show(struct seq_file *m, struct ftrace_iterator *iter) } static void * +t_mod_next(struct seq_file *m, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + struct trace_array *tr = iter->tr; + + (*pos)++; + iter->pos = *pos; + + iter->mod_list = iter->mod_list->next; + + if (iter->mod_list == &tr->mod_trace || + iter->mod_list == &tr->mod_notrace) { + iter->flags &= ~FTRACE_ITER_MOD; + return NULL; + } + + iter->mod_pos = *pos; + + return iter; +} + +static void *t_mod_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + void *p = NULL; + loff_t l; + + if (iter->func_pos > *pos) + return NULL; + + iter->mod_pos = iter->func_pos; + + /* probes are only available if tr is set */ + if (!iter->tr) + return NULL; + + for (l = 0; l <= (*pos - iter->func_pos); ) { + p = t_mod_next(m, &l); + if (!p) + break; + } + if (!p) { + iter->flags &= ~FTRACE_ITER_MOD; + return t_probe_start(m, pos); + } + + /* Only set this if we have an item */ + iter->flags |= FTRACE_ITER_MOD; + + return iter; +} + +static int +t_mod_show(struct seq_file *m, struct ftrace_iterator *iter) +{ + struct ftrace_mod_load *ftrace_mod; + struct trace_array *tr = iter->tr; + + if (WARN_ON_ONCE(!iter->mod_list) || + iter->mod_list == &tr->mod_trace || + iter->mod_list == &tr->mod_notrace) + return -EIO; + + ftrace_mod = list_entry(iter->mod_list, struct ftrace_mod_load, list); + + if (ftrace_mod->func) + seq_printf(m, "%s", ftrace_mod->func); + else + seq_putc(m, '*'); + + seq_printf(m, ":mod:%s\n", ftrace_mod->module); + + return 0; +} + +static void * t_func_next(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; @@ -3237,7 +3390,7 @@ 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 */ + loff_t l = *pos; /* t_probe_start() must use original pos */ void *ret; if (unlikely(ftrace_disabled)) @@ -3246,16 +3399,19 @@ t_next(struct seq_file *m, void *v, loff_t *pos) if (iter->flags & FTRACE_ITER_PROBE) return t_probe_next(m, pos); + if (iter->flags & FTRACE_ITER_MOD) + return t_mod_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); + return t_mod_start(m, &l); } ret = t_func_next(m, pos); if (!ret) - return t_probe_start(m, &l); + return t_mod_start(m, &l); return ret; } @@ -3264,7 +3420,7 @@ static void reset_iter_read(struct ftrace_iterator *iter) { iter->pos = 0; iter->func_pos = 0; - iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_PROBE); + iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_PROBE | FTRACE_ITER_MOD); } static void *t_start(struct seq_file *m, loff_t *pos) @@ -3293,15 +3449,15 @@ static void *t_start(struct seq_file *m, loff_t *pos) ftrace_hash_empty(iter->hash)) { iter->func_pos = 1; /* Account for the message */ if (*pos > 0) - return t_probe_start(m, pos); + return t_mod_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; /* reset in case of seek/pread */ iter->flags &= ~FTRACE_ITER_PROBE; return iter; } - if (iter->flags & FTRACE_ITER_PROBE) - return t_probe_start(m, pos); + if (iter->flags & FTRACE_ITER_MOD) + return t_mod_start(m, pos); /* * Unfortunately, we need to restart at ftrace_pages_start @@ -3317,7 +3473,7 @@ static void *t_start(struct seq_file *m, loff_t *pos) } if (!p) - return t_probe_start(m, pos); + return t_mod_start(m, pos); return iter; } @@ -3351,6 +3507,9 @@ static int t_show(struct seq_file *m, void *v) if (iter->flags & FTRACE_ITER_PROBE) return t_probe_show(m, iter); + if (iter->flags & FTRACE_ITER_MOD) + return t_mod_show(m, iter); + if (iter->flags & FTRACE_ITER_PRINTALL) { if (iter->flags & FTRACE_ITER_NOTRACE) seq_puts(m, "#### no functions disabled ####\n"); @@ -3457,6 +3616,8 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, { struct ftrace_iterator *iter; struct ftrace_hash *hash; + struct list_head *mod_head; + struct trace_array *tr = ops->private; int ret = 0; ftrace_ops_init(ops); @@ -3475,21 +3636,29 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, iter->ops = ops; iter->flags = flag; + iter->tr = tr; mutex_lock(&ops->func_hash->regex_lock); - if (flag & FTRACE_ITER_NOTRACE) + if (flag & FTRACE_ITER_NOTRACE) { hash = ops->func_hash->notrace_hash; - else + mod_head = tr ? &tr->mod_notrace : NULL; + } else { hash = ops->func_hash->filter_hash; + mod_head = tr ? &tr->mod_trace : NULL; + } + + iter->mod_list = mod_head; if (file->f_mode & FMODE_WRITE) { const int size_bits = FTRACE_HASH_DEFAULT_BITS; - if (file->f_flags & O_TRUNC) + if (file->f_flags & O_TRUNC) { iter->hash = alloc_ftrace_hash(size_bits); - else + clear_ftrace_mod_list(mod_head); + } else { iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash); + } if (!iter->hash) { trace_parser_put(&iter->parser); @@ -3665,7 +3834,7 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod) int exclude_mod = 0; int found = 0; int ret; - int clear_filter; + int clear_filter = 0; if (func) { func_g.type = filter_parse_regex(func, len, &func_g.search, @@ -3761,6 +3930,165 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops, return ret; } +static bool module_exists(const char *module) +{ + /* All modules have the symbol __this_module */ + const char this_mod[] = "__this_module"; + const int modname_size = MAX_PARAM_PREFIX_LEN + sizeof(this_mod) + 1; + char modname[modname_size + 1]; + unsigned long val; + int n; + + n = snprintf(modname, modname_size + 1, "%s:%s", module, this_mod); + + if (n > modname_size) + return false; + + val = module_kallsyms_lookup_name(modname); + return val != 0; +} + +static int cache_mod(struct trace_array *tr, + const char *func, char *module, int enable) +{ + struct ftrace_mod_load *ftrace_mod, *n; + struct list_head *head = enable ? &tr->mod_trace : &tr->mod_notrace; + int ret; + + mutex_lock(&ftrace_lock); + + /* We do not cache inverse filters */ + if (func[0] == '!') { + func++; + ret = -EINVAL; + + /* Look to remove this hash */ + list_for_each_entry_safe(ftrace_mod, n, head, list) { + if (strcmp(ftrace_mod->module, module) != 0) + continue; + + /* no func matches all */ + if (strcmp(func, "*") == 0 || + (ftrace_mod->func && + strcmp(ftrace_mod->func, func) == 0)) { + ret = 0; + free_ftrace_mod(ftrace_mod); + continue; + } + } + goto out; + } + + ret = -EINVAL; + /* We only care about modules that have not been loaded yet */ + if (module_exists(module)) + goto out; + + /* Save this string off, and execute it when the module is loaded */ + ret = ftrace_add_mod(tr, func, module, enable); + out: + mutex_unlock(&ftrace_lock); + + return ret; +} + +static int +ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, + int reset, int enable); + +#ifdef CONFIG_MODULES +static void process_mod_list(struct list_head *head, struct ftrace_ops *ops, + char *mod, bool enable) +{ + struct ftrace_mod_load *ftrace_mod, *n; + struct ftrace_hash **orig_hash, *new_hash; + LIST_HEAD(process_mods); + char *func; + int ret; + + mutex_lock(&ops->func_hash->regex_lock); + + if (enable) + orig_hash = &ops->func_hash->filter_hash; + else + orig_hash = &ops->func_hash->notrace_hash; + + new_hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, + *orig_hash); + if (!new_hash) + goto out; /* warn? */ + + mutex_lock(&ftrace_lock); + + list_for_each_entry_safe(ftrace_mod, n, head, list) { + + if (strcmp(ftrace_mod->module, mod) != 0) + continue; + + if (ftrace_mod->func) + func = kstrdup(ftrace_mod->func, GFP_KERNEL); + else + func = kstrdup("*", GFP_KERNEL); + + if (!func) /* warn? */ + continue; + + list_del(&ftrace_mod->list); + list_add(&ftrace_mod->list, &process_mods); + + /* Use the newly allocated func, as it may be "*" */ + kfree(ftrace_mod->func); + ftrace_mod->func = func; + } + + mutex_unlock(&ftrace_lock); + + list_for_each_entry_safe(ftrace_mod, n, &process_mods, list) { + + func = ftrace_mod->func; + + /* Grabs ftrace_lock, which is why we have this extra step */ + match_records(new_hash, func, strlen(func), mod); + free_ftrace_mod(ftrace_mod); + } + + if (enable && list_empty(head)) + new_hash->flags &= ~FTRACE_HASH_FL_MOD; + + mutex_lock(&ftrace_lock); + + ret = ftrace_hash_move_and_update_ops(ops, orig_hash, + new_hash, enable); + mutex_unlock(&ftrace_lock); + + out: + mutex_unlock(&ops->func_hash->regex_lock); + + free_ftrace_hash(new_hash); +} + +static void process_cached_mods(const char *mod_name) +{ + struct trace_array *tr; + char *mod; + + mod = kstrdup(mod_name, GFP_KERNEL); + if (!mod) + return; + + mutex_lock(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (!list_empty(&tr->mod_trace)) + process_mod_list(&tr->mod_trace, tr->ops, mod, true); + if (!list_empty(&tr->mod_notrace)) + process_mod_list(&tr->mod_notrace, tr->ops, mod, false); + } + mutex_unlock(&trace_types_lock); + + kfree(mod); +} +#endif + /* * We register the module command as a template to show others how * to register the a command as well. @@ -3768,10 +4096,16 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops, static int ftrace_mod_callback(struct trace_array *tr, struct ftrace_hash *hash, - char *func, char *cmd, char *module, int enable) + char *func_orig, char *cmd, char *module, int enable) { + char *func; int ret; + /* match_records() modifies func, and we need the original */ + func = kstrdup(func_orig, GFP_KERNEL); + if (!func) + return -ENOMEM; + /* * cmd == 'mod' because we only registered this func * for the 'mod' ftrace_func_command. @@ -3780,8 +4114,10 @@ ftrace_mod_callback(struct trace_array *tr, struct ftrace_hash *hash, * parameter. */ ret = match_records(hash, func, strlen(func), module); + kfree(func); + if (!ret) - return -EINVAL; + return cache_mod(tr, func_orig, module, enable); if (ret < 0) return ret; return 0; @@ -4618,9 +4954,6 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata; static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer); -static unsigned long save_global_trampoline; -static unsigned long save_global_flags; - static int __init set_graph_function(char *str) { strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); @@ -4725,9 +5058,11 @@ int ftrace_regex_release(struct inode *inode, struct file *file) if (file->f_mode & FMODE_WRITE) { filter_hash = !!(iter->flags & FTRACE_ITER_FILTER); - if (filter_hash) + if (filter_hash) { orig_hash = &iter->ops->func_hash->filter_hash; - else + if (iter->tr && !list_empty(&iter->tr->mod_trace)) + iter->hash->flags |= FTRACE_HASH_FL_MOD; + } else orig_hash = &iter->ops->func_hash->notrace_hash; mutex_lock(&ftrace_lock); @@ -5354,10 +5689,51 @@ static int referenced_filters(struct dyn_ftrace *rec) return cnt; } +static void +clear_mod_from_hash(struct ftrace_page *pg, struct ftrace_hash *hash) +{ + struct ftrace_func_entry *entry; + struct dyn_ftrace *rec; + int i; + + if (ftrace_hash_empty(hash)) + return; + + for (i = 0; i < pg->index; i++) { + rec = &pg->records[i]; + entry = __ftrace_lookup_ip(hash, rec->ip); + /* + * Do not allow this rec to match again. + * Yeah, it may waste some memory, but will be removed + * if/when the hash is modified again. + */ + if (entry) + entry->ip = 0; + } +} + +/* Clear any records from hashs */ +static void clear_mod_from_hashes(struct ftrace_page *pg) +{ + struct trace_array *tr; + + mutex_lock(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (!tr->ops || !tr->ops->func_hash) + continue; + mutex_lock(&tr->ops->func_hash->regex_lock); + clear_mod_from_hash(pg, tr->ops->func_hash->filter_hash); + clear_mod_from_hash(pg, tr->ops->func_hash->notrace_hash); + mutex_unlock(&tr->ops->func_hash->regex_lock); + } + mutex_unlock(&trace_types_lock); +} + void ftrace_release_mod(struct module *mod) { struct dyn_ftrace *rec; struct ftrace_page **last_pg; + struct ftrace_page *tmp_page = NULL; struct ftrace_page *pg; int order; @@ -5385,15 +5761,27 @@ void ftrace_release_mod(struct module *mod) if (pg == ftrace_pages) ftrace_pages = next_to_ftrace_page(last_pg); + ftrace_update_tot_cnt -= 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->next = tmp_page; + tmp_page = pg; } else last_pg = &pg->next; } out_unlock: mutex_unlock(&ftrace_lock); + + for (pg = tmp_page; pg; pg = tmp_page) { + + /* Needs to be called outside of ftrace_lock */ + clear_mod_from_hashes(pg); + + order = get_count_order(pg->size / ENTRIES_PER_PAGE); + free_pages((unsigned long)pg->records, order); + tmp_page = pg->next; + kfree(pg); + } } void ftrace_module_enable(struct module *mod) @@ -5463,6 +5851,8 @@ void ftrace_module_enable(struct module *mod) out_unlock: mutex_unlock(&ftrace_lock); + + process_cached_mods(mod->name); } void ftrace_module_init(struct module *mod) @@ -5501,6 +5891,7 @@ void __init ftrace_free_init_mem(void) if (!rec) continue; pg->index--; + ftrace_update_tot_cnt--; if (!pg->index) { *last_pg = pg->next; order = get_count_order(pg->size / ENTRIES_PER_PAGE); @@ -5567,6 +5958,8 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) void ftrace_init_trace_array(struct trace_array *tr) { INIT_LIST_HEAD(&tr->func_probes); + INIT_LIST_HEAD(&tr->mod_trace); + INIT_LIST_HEAD(&tr->mod_notrace); } #else @@ -6127,7 +6520,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, if (ftrace_enabled) { /* we are starting ftrace again */ - if (ftrace_ops_list != &ftrace_list_end) + if (rcu_dereference_protected(ftrace_ops_list, + lockdep_is_held(&ftrace_lock)) != &ftrace_list_end) update_ftrace_function(); ftrace_startup_sysctl(); @@ -6411,17 +6805,6 @@ void unregister_ftrace_graph(void) unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * Function graph does not allocate the trampoline, but - * other global_ops do. We need to reset the ALLOC_TRAMP flag - * if one was used. - */ - global_ops.trampoline = save_global_trampoline; - if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP) - global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP; -#endif - out: mutex_unlock(&ftrace_lock); } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 4ae268e687fe..81279c6602ff 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1136,12 +1136,12 @@ static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu) for (i = 0; i < nr_pages; i++) { struct page *page; /* - * __GFP_NORETRY flag makes sure that the allocation fails - * gracefully without invoking oom-killer and the system is - * not destabilized. + * __GFP_RETRY_MAYFAIL flag makes sure that the allocation fails + * gracefully without invoking oom-killer and the system is not + * destabilized. */ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), - GFP_KERNEL | __GFP_NORETRY, + GFP_KERNEL | __GFP_RETRY_MAYFAIL, cpu_to_node(cpu)); if (!bpage) goto free_pages; @@ -1149,7 +1149,7 @@ static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu) list_add(&bpage->list, pages); page = alloc_pages_node(cpu_to_node(cpu), - GFP_KERNEL | __GFP_NORETRY, 0); + GFP_KERNEL | __GFP_RETRY_MAYFAIL, 0); if (!page) goto free_pages; bpage->page = page_address(page); @@ -4386,15 +4386,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); * the page that was allocated, with the read page of the buffer. * * Returns: - * The page allocated, or NULL on error. + * The page allocated, or ERR_PTR */ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu) { - struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_per_cpu *cpu_buffer; struct buffer_data_page *bpage = NULL; unsigned long flags; struct page *page; + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return ERR_PTR(-ENODEV); + + cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); @@ -4412,7 +4416,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu) page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); if (!page) - return NULL; + return ERR_PTR(-ENOMEM); bpage = page_address(page); @@ -4467,8 +4471,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); * * for example: * rpage = ring_buffer_alloc_read_page(buffer, cpu); - * if (!rpage) - * return error; + * if (IS_ERR(rpage)) + * return PTR_ERR(rpage); * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0); * if (ret >= 0) * process_page(rpage, ret); diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 9fbcaf567886..68ee79afe31c 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -113,7 +113,7 @@ static enum event_status read_page(int cpu) int i; bpage = ring_buffer_alloc_read_page(buffer, cpu); - if (!bpage) + if (IS_ERR(bpage)) return EVENT_DROPPED; ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 091e801145c9..752e5daf0896 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -87,7 +87,7 @@ dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) * tracing is active, only save the comm when a trace event * occurred. */ -static DEFINE_PER_CPU(bool, trace_cmdline_save); +static DEFINE_PER_CPU(bool, trace_taskinfo_save); /* * Kill all tracing for good (never come back). @@ -120,41 +120,41 @@ enum ftrace_dump_mode ftrace_dump_on_oops; /* When set, tracing will stop when a WARN*() is hit */ int __disable_trace_on_warning; -#ifdef CONFIG_TRACE_ENUM_MAP_FILE -/* Map of enums to their values, for "enum_map" file */ -struct trace_enum_map_head { +#ifdef CONFIG_TRACE_EVAL_MAP_FILE +/* Map of enums to their values, for "eval_map" file */ +struct trace_eval_map_head { struct module *mod; unsigned long length; }; -union trace_enum_map_item; +union trace_eval_map_item; -struct trace_enum_map_tail { +struct trace_eval_map_tail { /* * "end" is first and points to NULL as it must be different - * than "mod" or "enum_string" + * than "mod" or "eval_string" */ - union trace_enum_map_item *next; + union trace_eval_map_item *next; const char *end; /* points to NULL */ }; -static DEFINE_MUTEX(trace_enum_mutex); +static DEFINE_MUTEX(trace_eval_mutex); /* - * The trace_enum_maps are saved in an array with two extra elements, + * The trace_eval_maps are saved in an array with two extra elements, * one at the beginning, and one at the end. The beginning item contains * the count of the saved maps (head.length), and the module they * belong to if not built in (head.mod). The ending item contains a - * pointer to the next array of saved enum_map items. + * pointer to the next array of saved eval_map items. */ -union trace_enum_map_item { - struct trace_enum_map map; - struct trace_enum_map_head head; - struct trace_enum_map_tail tail; +union trace_eval_map_item { + struct trace_eval_map map; + struct trace_eval_map_head head; + struct trace_eval_map_tail tail; }; -static union trace_enum_map_item *trace_enum_maps; -#endif /* CONFIG_TRACE_ENUM_MAP_FILE */ +static union trace_eval_map_item *trace_eval_maps; +#endif /* CONFIG_TRACE_EVAL_MAP_FILE */ static int tracing_set_tracer(struct trace_array *tr, const char *buf); @@ -790,7 +790,7 @@ EXPORT_SYMBOL_GPL(tracing_on); static __always_inline void __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) { - __this_cpu_write(trace_cmdline_save, true); + __this_cpu_write(trace_taskinfo_save, true); /* If this is the temp buffer, we need to commit fully */ if (this_cpu_read(trace_buffered_event) == event) { @@ -1141,9 +1141,9 @@ unsigned long nsecs_to_usecs(unsigned long nsecs) /* * TRACE_FLAGS is defined as a tuple matching bit masks with strings. - * It uses C(a, b) where 'a' is the enum name and 'b' is the string that + * It uses C(a, b) where 'a' is the eval (enum) name and 'b' is the string that * matches it. By defining "C(a, b) b", TRACE_FLAGS becomes a list - * of strings in the order that the enums were defined. + * of strings in the order that the evals (enum) were defined. */ #undef C #define C(a, b) b @@ -1702,6 +1702,9 @@ void tracing_reset_all_online_cpus(void) struct trace_array *tr; list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (!tr->clear_trace) + continue; + tr->clear_trace = false; tracing_reset_online_cpus(&tr->trace_buffer); #ifdef CONFIG_TRACER_MAX_TRACE tracing_reset_online_cpus(&tr->max_buffer); @@ -1709,6 +1712,8 @@ void tracing_reset_all_online_cpus(void) } } +static int *tgid_map; + #define SAVED_CMDLINES_DEFAULT 128 #define NO_CMDLINE_MAP UINT_MAX static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; @@ -1722,7 +1727,7 @@ struct saved_cmdlines_buffer { static struct saved_cmdlines_buffer *savedcmd; /* temporary disable recording */ -static atomic_t trace_record_cmdline_disabled __read_mostly; +static atomic_t trace_record_taskinfo_disabled __read_mostly; static inline char *get_saved_cmdlines(int idx) { @@ -1910,13 +1915,15 @@ static void tracing_stop_tr(struct trace_array *tr) raw_spin_unlock_irqrestore(&tr->start_lock, flags); } -void trace_stop_cmdline_recording(void); - static int trace_save_cmdline(struct task_struct *tsk) { unsigned pid, idx; - if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT)) + /* treat recording of idle task as a success */ + if (!tsk->pid) + return 1; + + if (unlikely(tsk->pid > PID_MAX_DEFAULT)) return 0; /* @@ -1992,16 +1999,107 @@ void trace_find_cmdline(int pid, char comm[]) preempt_enable(); } -void tracing_record_cmdline(struct task_struct *tsk) +int trace_find_tgid(int pid) +{ + if (unlikely(!tgid_map || !pid || pid > PID_MAX_DEFAULT)) + return 0; + + return tgid_map[pid]; +} + +static int trace_save_tgid(struct task_struct *tsk) +{ + /* treat recording of idle task as a success */ + if (!tsk->pid) + return 1; + + if (unlikely(!tgid_map || tsk->pid > PID_MAX_DEFAULT)) + return 0; + + tgid_map[tsk->pid] = tsk->tgid; + return 1; +} + +static bool tracing_record_taskinfo_skip(int flags) +{ + if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID)))) + return true; + if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on()) + return true; + if (!__this_cpu_read(trace_taskinfo_save)) + return true; + return false; +} + +/** + * tracing_record_taskinfo - record the task info of a task + * + * @task - task to record + * @flags - TRACE_RECORD_CMDLINE for recording comm + * - TRACE_RECORD_TGID for recording tgid + */ +void tracing_record_taskinfo(struct task_struct *task, int flags) +{ + bool done; + + if (tracing_record_taskinfo_skip(flags)) + return; + + /* + * Record as much task information as possible. If some fail, continue + * to try to record the others. + */ + done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(task); + done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(task); + + /* If recording any information failed, retry again soon. */ + if (!done) + return; + + __this_cpu_write(trace_taskinfo_save, false); +} + +/** + * tracing_record_taskinfo_sched_switch - record task info for sched_switch + * + * @prev - previous task during sched_switch + * @next - next task during sched_switch + * @flags - TRACE_RECORD_CMDLINE for recording comm + * TRACE_RECORD_TGID for recording tgid + */ +void tracing_record_taskinfo_sched_switch(struct task_struct *prev, + struct task_struct *next, int flags) { - if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on()) + bool done; + + if (tracing_record_taskinfo_skip(flags)) return; - if (!__this_cpu_read(trace_cmdline_save)) + /* + * Record as much task information as possible. If some fail, continue + * to try to record the others. + */ + done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(prev); + done &= !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(next); + done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(prev); + done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(next); + + /* If recording any information failed, retry again soon. */ + if (!done) return; - if (trace_save_cmdline(tsk)) - __this_cpu_write(trace_cmdline_save, false); + __this_cpu_write(trace_taskinfo_save, false); +} + +/* Helpers to record a specific task information */ +void tracing_record_cmdline(struct task_struct *task) +{ + tracing_record_taskinfo(task, TRACE_RECORD_CMDLINE); +} + +void tracing_record_tgid(struct task_struct *task) +{ + tracing_record_taskinfo(task, TRACE_RECORD_TGID); } /* @@ -2704,11 +2802,17 @@ static char *get_trace_buf(void) if (!buffer || buffer->nesting >= 4) return NULL; - return &buffer->buffer[buffer->nesting++][0]; + buffer->nesting++; + + /* Interrupts must see nesting incremented before we use the buffer */ + barrier(); + return &buffer->buffer[buffer->nesting][0]; } static void put_trace_buf(void) { + /* Don't let the decrement of nesting leak before this */ + barrier(); this_cpu_dec(trace_percpu_buffer->nesting); } @@ -3146,7 +3250,7 @@ static void *s_start(struct seq_file *m, loff_t *pos) #endif if (!iter->snapshot) - atomic_inc(&trace_record_cmdline_disabled); + atomic_inc(&trace_record_taskinfo_disabled); if (*pos != iter->pos) { iter->ent = NULL; @@ -3191,7 +3295,7 @@ static void s_stop(struct seq_file *m, void *p) #endif if (!iter->snapshot) - atomic_dec(&trace_record_cmdline_disabled); + atomic_dec(&trace_record_taskinfo_disabled); trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); @@ -3248,23 +3352,38 @@ static void print_event_info(struct trace_buffer *buf, struct seq_file *m) seq_puts(m, "#\n"); } -static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m) +static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m, + unsigned int flags) { + bool tgid = flags & TRACE_ITER_RECORD_TGID; + print_event_info(buf, m); - seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n" - "# | | | | |\n"); + + seq_printf(m, "# TASK-PID CPU# %s TIMESTAMP FUNCTION\n", tgid ? "TGID " : ""); + seq_printf(m, "# | | | %s | |\n", tgid ? " | " : ""); } -static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m) +static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m, + unsigned int flags) { - print_event_info(buf, m); - seq_puts(m, "# _-----=> irqs-off\n" - "# / _----=> need-resched\n" - "# | / _---=> hardirq/softirq\n" - "# || / _--=> preempt-depth\n" - "# ||| / delay\n" - "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n" - "# | | | |||| | |\n"); + bool tgid = flags & TRACE_ITER_RECORD_TGID; + const char tgid_space[] = " "; + const char space[] = " "; + + seq_printf(m, "# %s _-----=> irqs-off\n", + tgid ? tgid_space : space); + seq_printf(m, "# %s / _----=> need-resched\n", + tgid ? tgid_space : space); + seq_printf(m, "# %s| / _---=> hardirq/softirq\n", + tgid ? tgid_space : space); + seq_printf(m, "# %s|| / _--=> preempt-depth\n", + tgid ? tgid_space : space); + seq_printf(m, "# %s||| / delay\n", + tgid ? tgid_space : space); + seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n", + tgid ? " TGID " : space); + seq_printf(m, "# | | | %s|||| | |\n", + tgid ? " | " : space); } void @@ -3580,9 +3699,11 @@ void trace_default_header(struct seq_file *m) } else { if (!(trace_flags & TRACE_ITER_VERBOSE)) { if (trace_flags & TRACE_ITER_IRQ_INFO) - print_func_help_header_irq(iter->trace_buffer, m); + print_func_help_header_irq(iter->trace_buffer, + m, trace_flags); else - print_func_help_header(iter->trace_buffer, m); + print_func_help_header(iter->trace_buffer, m, + trace_flags); } } } @@ -3899,11 +4020,17 @@ static int tracing_open(struct inode *inode, struct file *file) /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { int cpu = tracing_get_cpu(inode); + struct trace_buffer *trace_buf = &tr->trace_buffer; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (tr->current_trace->print_max) + trace_buf = &tr->max_buffer; +#endif if (cpu == RING_BUFFER_ALL_CPUS) - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(trace_buf); else - tracing_reset(&tr->trace_buffer, cpu); + tracing_reset(trace_buf, cpu); } if (file->f_mode & FMODE_READ) { @@ -4238,6 +4365,18 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) if (mask == TRACE_ITER_RECORD_CMD) trace_event_enable_cmd_record(enabled); + if (mask == TRACE_ITER_RECORD_TGID) { + if (!tgid_map) + tgid_map = kzalloc((PID_MAX_DEFAULT + 1) * sizeof(*tgid_map), + GFP_KERNEL); + if (!tgid_map) { + tr->trace_flags &= ~TRACE_ITER_RECORD_TGID; + return -ENOMEM; + } + + trace_event_enable_tgid_record(enabled); + } + if (mask == TRACE_ITER_EVENT_FORK) trace_event_follow_fork(tr, enabled); @@ -4473,7 +4612,8 @@ static const char readme_msg[] = #endif #if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) "\t accepts: event-definitions (one definition per line)\n" - "\t Format: p|r[:[<group>/]<event>] <place> [<args>]\n" + "\t Format: p[:[<group>/]<event>] <place> [<args>]\n" + "\t r[maxactive][:[<group>/]<event>] <place> [<args>]\n" "\t -:[<group>/]<event>\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" @@ -4597,6 +4737,76 @@ static const struct file_operations tracing_readme_fops = { .llseek = generic_file_llseek, }; +static void *saved_tgids_next(struct seq_file *m, void *v, loff_t *pos) +{ + int *ptr = v; + + if (*pos || m->count) + ptr++; + + (*pos)++; + + for (; ptr <= &tgid_map[PID_MAX_DEFAULT]; ptr++) { + if (trace_find_tgid(*ptr)) + return ptr; + } + + return NULL; +} + +static void *saved_tgids_start(struct seq_file *m, loff_t *pos) +{ + void *v; + loff_t l = 0; + + if (!tgid_map) + return NULL; + + v = &tgid_map[0]; + while (l <= *pos) { + v = saved_tgids_next(m, v, &l); + if (!v) + return NULL; + } + + return v; +} + +static void saved_tgids_stop(struct seq_file *m, void *v) +{ +} + +static int saved_tgids_show(struct seq_file *m, void *v) +{ + int pid = (int *)v - tgid_map; + + seq_printf(m, "%d %d\n", pid, trace_find_tgid(pid)); + return 0; +} + +static const struct seq_operations tracing_saved_tgids_seq_ops = { + .start = saved_tgids_start, + .stop = saved_tgids_stop, + .next = saved_tgids_next, + .show = saved_tgids_show, +}; + +static int tracing_saved_tgids_open(struct inode *inode, struct file *filp) +{ + if (tracing_disabled) + return -ENODEV; + + return seq_open(filp, &tracing_saved_tgids_seq_ops); +} + + +static const struct file_operations tracing_saved_tgids_fops = { + .open = tracing_saved_tgids_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos) { unsigned int *ptr = v; @@ -4746,11 +4956,11 @@ static const struct file_operations tracing_saved_cmdlines_size_fops = { .write = tracing_saved_cmdlines_size_write, }; -#ifdef CONFIG_TRACE_ENUM_MAP_FILE -static union trace_enum_map_item * -update_enum_map(union trace_enum_map_item *ptr) +#ifdef CONFIG_TRACE_EVAL_MAP_FILE +static union trace_eval_map_item * +update_eval_map(union trace_eval_map_item *ptr) { - if (!ptr->map.enum_string) { + if (!ptr->map.eval_string) { if (ptr->tail.next) { ptr = ptr->tail.next; /* Set ptr to the next real item (skip head) */ @@ -4761,15 +4971,15 @@ update_enum_map(union trace_enum_map_item *ptr) return ptr; } -static void *enum_map_next(struct seq_file *m, void *v, loff_t *pos) +static void *eval_map_next(struct seq_file *m, void *v, loff_t *pos) { - union trace_enum_map_item *ptr = v; + union trace_eval_map_item *ptr = v; /* * Paranoid! If ptr points to end, we don't want to increment past it. * This really should never happen. */ - ptr = update_enum_map(ptr); + ptr = update_eval_map(ptr); if (WARN_ON_ONCE(!ptr)) return NULL; @@ -4777,104 +4987,104 @@ static void *enum_map_next(struct seq_file *m, void *v, loff_t *pos) (*pos)++; - ptr = update_enum_map(ptr); + ptr = update_eval_map(ptr); return ptr; } -static void *enum_map_start(struct seq_file *m, loff_t *pos) +static void *eval_map_start(struct seq_file *m, loff_t *pos) { - union trace_enum_map_item *v; + union trace_eval_map_item *v; loff_t l = 0; - mutex_lock(&trace_enum_mutex); + mutex_lock(&trace_eval_mutex); - v = trace_enum_maps; + v = trace_eval_maps; if (v) v++; while (v && l < *pos) { - v = enum_map_next(m, v, &l); + v = eval_map_next(m, v, &l); } return v; } -static void enum_map_stop(struct seq_file *m, void *v) +static void eval_map_stop(struct seq_file *m, void *v) { - mutex_unlock(&trace_enum_mutex); + mutex_unlock(&trace_eval_mutex); } -static int enum_map_show(struct seq_file *m, void *v) +static int eval_map_show(struct seq_file *m, void *v) { - union trace_enum_map_item *ptr = v; + union trace_eval_map_item *ptr = v; seq_printf(m, "%s %ld (%s)\n", - ptr->map.enum_string, ptr->map.enum_value, + ptr->map.eval_string, ptr->map.eval_value, ptr->map.system); return 0; } -static const struct seq_operations tracing_enum_map_seq_ops = { - .start = enum_map_start, - .next = enum_map_next, - .stop = enum_map_stop, - .show = enum_map_show, +static const struct seq_operations tracing_eval_map_seq_ops = { + .start = eval_map_start, + .next = eval_map_next, + .stop = eval_map_stop, + .show = eval_map_show, }; -static int tracing_enum_map_open(struct inode *inode, struct file *filp) +static int tracing_eval_map_open(struct inode *inode, struct file *filp) { if (tracing_disabled) return -ENODEV; - return seq_open(filp, &tracing_enum_map_seq_ops); + return seq_open(filp, &tracing_eval_map_seq_ops); } -static const struct file_operations tracing_enum_map_fops = { - .open = tracing_enum_map_open, +static const struct file_operations tracing_eval_map_fops = { + .open = tracing_eval_map_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; -static inline union trace_enum_map_item * -trace_enum_jmp_to_tail(union trace_enum_map_item *ptr) +static inline union trace_eval_map_item * +trace_eval_jmp_to_tail(union trace_eval_map_item *ptr) { /* Return tail of array given the head */ return ptr + ptr->head.length + 1; } static void -trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start, +trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, int len) { - struct trace_enum_map **stop; - struct trace_enum_map **map; - union trace_enum_map_item *map_array; - union trace_enum_map_item *ptr; + struct trace_eval_map **stop; + struct trace_eval_map **map; + union trace_eval_map_item *map_array; + union trace_eval_map_item *ptr; stop = start + len; /* - * The trace_enum_maps contains the map plus a head and tail item, + * The trace_eval_maps contains the map plus a head and tail item, * where the head holds the module and length of array, and the * tail holds a pointer to the next list. */ map_array = kmalloc(sizeof(*map_array) * (len + 2), GFP_KERNEL); if (!map_array) { - pr_warn("Unable to allocate trace enum mapping\n"); + pr_warn("Unable to allocate trace eval mapping\n"); return; } - mutex_lock(&trace_enum_mutex); + mutex_lock(&trace_eval_mutex); - if (!trace_enum_maps) - trace_enum_maps = map_array; + if (!trace_eval_maps) + trace_eval_maps = map_array; else { - ptr = trace_enum_maps; + ptr = trace_eval_maps; for (;;) { - ptr = trace_enum_jmp_to_tail(ptr); + ptr = trace_eval_jmp_to_tail(ptr); if (!ptr->tail.next) break; ptr = ptr->tail.next; @@ -4892,34 +5102,34 @@ trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start, } memset(map_array, 0, sizeof(*map_array)); - mutex_unlock(&trace_enum_mutex); + mutex_unlock(&trace_eval_mutex); } -static void trace_create_enum_file(struct dentry *d_tracer) +static void trace_create_eval_file(struct dentry *d_tracer) { - trace_create_file("enum_map", 0444, d_tracer, - NULL, &tracing_enum_map_fops); + trace_create_file("eval_map", 0444, d_tracer, + NULL, &tracing_eval_map_fops); } -#else /* CONFIG_TRACE_ENUM_MAP_FILE */ -static inline void trace_create_enum_file(struct dentry *d_tracer) { } -static inline void trace_insert_enum_map_file(struct module *mod, - struct trace_enum_map **start, int len) { } -#endif /* !CONFIG_TRACE_ENUM_MAP_FILE */ +#else /* CONFIG_TRACE_EVAL_MAP_FILE */ +static inline void trace_create_eval_file(struct dentry *d_tracer) { } +static inline void trace_insert_eval_map_file(struct module *mod, + struct trace_eval_map **start, int len) { } +#endif /* !CONFIG_TRACE_EVAL_MAP_FILE */ -static void trace_insert_enum_map(struct module *mod, - struct trace_enum_map **start, int len) +static void trace_insert_eval_map(struct module *mod, + struct trace_eval_map **start, int len) { - struct trace_enum_map **map; + struct trace_eval_map **map; if (len <= 0) return; map = start; - trace_event_enum_update(map, len); + trace_event_eval_update(map, len); - trace_insert_enum_map_file(mod, start, len); + trace_insert_eval_map_file(mod, start, len); } static ssize_t @@ -5154,6 +5364,13 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) if (t == tr->current_trace) goto out; + /* Some tracers won't work on kernel command line */ + if (system_state < SYSTEM_RUNNING && t->noboot) { + pr_warn("Tracer '%s' is not allowed on command line, ignored\n", + t->name); + goto out; + } + /* Some tracers are only allowed for the top level buffer */ if (!trace_ok_for_array(t, tr)) { ret = -EINVAL; @@ -5463,7 +5680,7 @@ static int tracing_wait_pipe(struct file *filp) * * iter->pos will be 0 if we haven't read anything. */ - if (!tracing_is_on() && iter->pos) + if (!tracer_tracing_is_on(iter->tr) && iter->pos) break; mutex_unlock(&iter->mutex); @@ -6025,7 +6242,7 @@ static int tracing_set_clock(struct trace_array *tr, const char *clockstr) tracing_reset_online_cpus(&tr->trace_buffer); #ifdef CONFIG_TRACER_MAX_TRACE - if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer) + if (tr->max_buffer.buffer) ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); tracing_reset_online_cpus(&tr->max_buffer); #endif @@ -6403,7 +6620,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; - ssize_t ret; + ssize_t ret = 0; ssize_t size; if (!count) @@ -6417,10 +6634,15 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (!info->spare) { info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, iter->cpu_file); - info->spare_cpu = iter->cpu_file; + if (IS_ERR(info->spare)) { + ret = PTR_ERR(info->spare); + info->spare = NULL; + } else { + info->spare_cpu = iter->cpu_file; + } } if (!info->spare) - return -ENOMEM; + return ret; /* Do we have previous read data to read? */ if (info->read < PAGE_SIZE) @@ -6595,8 +6817,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, ref->ref = 1; ref->buffer = iter->trace_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); - if (!ref->page) { - ret = -ENOMEM; + if (IS_ERR(ref->page)) { + ret = PTR_ERR(ref->page); + ref->page = NULL; kfree(ref); break; } @@ -6739,33 +6962,18 @@ static const struct file_operations tracing_stats_fops = { #ifdef CONFIG_DYNAMIC_FTRACE -int __weak ftrace_arch_read_dyn_info(char *buf, int size) -{ - return 0; -} - static ssize_t tracing_read_dyn_info(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - static char ftrace_dyn_info_buffer[1024]; - static DEFINE_MUTEX(dyn_info_mutex); unsigned long *p = filp->private_data; - char *buf = ftrace_dyn_info_buffer; - int size = ARRAY_SIZE(ftrace_dyn_info_buffer); + char buf[64]; /* Not too big for a shallow stack */ int r; - mutex_lock(&dyn_info_mutex); - r = sprintf(buf, "%ld ", *p); - - r += ftrace_arch_read_dyn_info(buf+r, (size-1)-r); + r = scnprintf(buf, 63, "%ld", *p); buf[r++] = '\n'; - r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); - - mutex_unlock(&dyn_info_mutex); - - return r; + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static const struct file_operations tracing_dyn_info_fops = { @@ -7594,6 +7802,7 @@ static int instance_rmdir(const char *name) } kfree(tr->topts); + free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); kfree(tr); @@ -7737,21 +7946,21 @@ struct dentry *tracing_init_dentry(void) return NULL; } -extern struct trace_enum_map *__start_ftrace_enum_maps[]; -extern struct trace_enum_map *__stop_ftrace_enum_maps[]; +extern struct trace_eval_map *__start_ftrace_eval_maps[]; +extern struct trace_eval_map *__stop_ftrace_eval_maps[]; -static void __init trace_enum_init(void) +static void __init trace_eval_init(void) { int len; - len = __stop_ftrace_enum_maps - __start_ftrace_enum_maps; - trace_insert_enum_map(NULL, __start_ftrace_enum_maps, len); + len = __stop_ftrace_eval_maps - __start_ftrace_eval_maps; + trace_insert_eval_map(NULL, __start_ftrace_eval_maps, len); } #ifdef CONFIG_MODULES -static void trace_module_add_enums(struct module *mod) +static void trace_module_add_evals(struct module *mod) { - if (!mod->num_trace_enums) + if (!mod->num_trace_evals) return; /* @@ -7761,40 +7970,40 @@ static void trace_module_add_enums(struct module *mod) if (trace_module_has_bad_taint(mod)) return; - trace_insert_enum_map(mod, mod->trace_enums, mod->num_trace_enums); + trace_insert_eval_map(mod, mod->trace_evals, mod->num_trace_evals); } -#ifdef CONFIG_TRACE_ENUM_MAP_FILE -static void trace_module_remove_enums(struct module *mod) +#ifdef CONFIG_TRACE_EVAL_MAP_FILE +static void trace_module_remove_evals(struct module *mod) { - union trace_enum_map_item *map; - union trace_enum_map_item **last = &trace_enum_maps; + union trace_eval_map_item *map; + union trace_eval_map_item **last = &trace_eval_maps; - if (!mod->num_trace_enums) + if (!mod->num_trace_evals) return; - mutex_lock(&trace_enum_mutex); + mutex_lock(&trace_eval_mutex); - map = trace_enum_maps; + map = trace_eval_maps; while (map) { if (map->head.mod == mod) break; - map = trace_enum_jmp_to_tail(map); + map = trace_eval_jmp_to_tail(map); last = &map->tail.next; map = map->tail.next; } if (!map) goto out; - *last = trace_enum_jmp_to_tail(map)->tail.next; + *last = trace_eval_jmp_to_tail(map)->tail.next; kfree(map); out: - mutex_unlock(&trace_enum_mutex); + mutex_unlock(&trace_eval_mutex); } #else -static inline void trace_module_remove_enums(struct module *mod) { } -#endif /* CONFIG_TRACE_ENUM_MAP_FILE */ +static inline void trace_module_remove_evals(struct module *mod) { } +#endif /* CONFIG_TRACE_EVAL_MAP_FILE */ static int trace_module_notify(struct notifier_block *self, unsigned long val, void *data) @@ -7803,10 +8012,10 @@ static int trace_module_notify(struct notifier_block *self, switch (val) { case MODULE_STATE_COMING: - trace_module_add_enums(mod); + trace_module_add_evals(mod); break; case MODULE_STATE_GOING: - trace_module_remove_enums(mod); + trace_module_remove_evals(mod); break; } @@ -7844,9 +8053,12 @@ static __init int tracer_init_tracefs(void) trace_create_file("saved_cmdlines_size", 0644, d_tracer, NULL, &tracing_saved_cmdlines_size_fops); - trace_enum_init(); + trace_create_file("saved_tgids", 0444, d_tracer, + NULL, &tracing_saved_tgids_fops); - trace_create_enum_file(d_tracer); + trace_eval_init(); + + trace_create_eval_file(d_tracer); #ifdef CONFIG_MODULES register_module_notifier(&trace_module_nb); @@ -8109,6 +8321,7 @@ __init static int tracer_alloc_buffers(void) if (ret < 0) goto out_free_cpumask; /* Used for event triggers */ + ret = -ENOMEM; temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE); if (!temp_buffer) goto out_rm_hp_state; @@ -8223,4 +8436,4 @@ __init static int clear_boot_tracer(void) } fs_initcall(tracer_init_tracefs); -late_initcall(clear_boot_tracer); +late_initcall_sync(clear_boot_tracer); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 39fd77330aab..652c682707cd 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -245,6 +245,7 @@ struct trace_array { int stop_count; int clock_id; int nr_topts; + bool clear_trace; struct tracer *current_trace; unsigned int trace_flags; unsigned char trace_flags_index[TRACE_FLAGS_MAX_SIZE]; @@ -263,7 +264,10 @@ struct trace_array { struct ftrace_ops *ops; struct trace_pid_list __rcu *function_pids; #ifdef CONFIG_DYNAMIC_FTRACE + /* All of these are protected by the ftrace_lock */ struct list_head func_probes; + struct list_head mod_trace; + struct list_head mod_notrace; #endif /* function tracing enabled */ int function_enabled; @@ -440,6 +444,8 @@ struct tracer { #ifdef CONFIG_TRACER_MAX_TRACE bool use_max_tr; #endif + /* True if tracer cannot be enabled in kernel param */ + bool noboot; }; @@ -637,6 +643,9 @@ void set_graph_array(struct trace_array *tr); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); +void tracing_start_tgid_record(void); +void tracing_stop_tgid_record(void); + int register_tracer(struct tracer *type); int is_tracing_stopped(void); @@ -697,6 +706,7 @@ static inline void __trace_stack(struct trace_array *tr, unsigned long flags, extern u64 ftrace_now(int cpu); extern void trace_find_cmdline(int pid, char comm[]); +extern int trace_find_tgid(int pid); extern void trace_event_follow_fork(struct trace_array *tr, bool enable); #ifdef CONFIG_DYNAMIC_FTRACE @@ -761,10 +771,24 @@ enum print_line_t print_trace_line(struct trace_iterator *iter); extern char trace_find_mark(unsigned long long duration); +struct ftrace_hash; + +struct ftrace_mod_load { + struct list_head list; + char *func; + char *module; + int enable; +}; + +enum { + FTRACE_HASH_FL_MOD = (1 << 0), +}; + struct ftrace_hash { unsigned long size_bits; struct hlist_head *buckets; unsigned long count; + unsigned long flags; struct rcu_head rcu; }; @@ -773,7 +797,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip); static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash) { - return !hash || !hash->count; + return !hash || !(hash->count || (hash->flags & FTRACE_HASH_FL_MOD)); } /* Standard output formatting function used for function return traces */ @@ -1107,6 +1131,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, C(CONTEXT_INFO, "context-info"), /* Print pid/cpu/time */ \ C(LATENCY_FMT, "latency-format"), \ C(RECORD_CMD, "record-cmd"), \ + C(RECORD_TGID, "record-tgid"), \ C(OVERWRITE, "overwrite"), \ C(STOP_ON_FREE, "disable_on_free"), \ C(IRQ_INFO, "irq-info"), \ @@ -1188,9 +1213,9 @@ struct ftrace_event_field { struct event_filter { int n_preds; /* Number assigned */ int a_preds; /* allocated */ - struct filter_pred *preds; - struct filter_pred *root; - char *filter_string; + struct filter_pred __rcu *preds; + struct filter_pred __rcu *root; + char *filter_string; }; struct event_subsystem { @@ -1423,6 +1448,8 @@ struct ftrace_event_field * trace_find_event_field(struct trace_event_call *call, char *name); extern void trace_event_enable_cmd_record(bool enable); +extern void trace_event_enable_tgid_record(bool enable); + extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); @@ -1773,10 +1800,10 @@ static inline const char *get_syscall_name(int syscall) #ifdef CONFIG_EVENT_TRACING void trace_event_init(void); -void trace_event_enum_update(struct trace_enum_map **map, int len); +void trace_event_eval_update(struct trace_eval_map **map, int len); #else static inline void __init trace_event_init(void) { } -static inline void trace_event_enum_update(struct trace_enum_map **map, int len) { } +static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { } #endif extern struct trace_iterator *tracepoint_print_iter; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 562fa69df5d3..13ba2d3f6a91 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -306,6 +306,7 @@ static void perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *pt_regs) { + struct perf_event *event; struct ftrace_entry *entry; struct hlist_head *head; struct pt_regs regs; @@ -329,8 +330,9 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, entry->ip = ip; entry->parent_ip = parent_ip; + event = container_of(ops, struct perf_event, ftrace_ops); perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN, - 1, ®s, head, NULL); + 1, ®s, head, NULL, event); #undef ENTRY_SIZE } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e7973e10398c..87468398b9ed 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -343,6 +343,28 @@ void trace_event_enable_cmd_record(bool enable) mutex_unlock(&event_mutex); } +void trace_event_enable_tgid_record(bool enable) +{ + struct trace_event_file *file; + struct trace_array *tr; + + mutex_lock(&event_mutex); + do_for_each_event_file(tr, file) { + if (!(file->flags & EVENT_FILE_FL_ENABLED)) + continue; + + if (enable) { + tracing_start_tgid_record(); + set_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags); + } else { + tracing_stop_tgid_record(); + clear_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, + &file->flags); + } + } while_for_each_event_file(); + mutex_unlock(&event_mutex); +} + static int __ftrace_event_enable_disable(struct trace_event_file *file, int enable, int soft_disable) { @@ -381,6 +403,12 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, tracing_stop_cmdline_record(); clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } + + if (file->flags & EVENT_FILE_FL_RECORDED_TGID) { + tracing_stop_tgid_record(); + clear_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags); + } + call->class->reg(call, TRACE_REG_UNREGISTER, file); } /* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */ @@ -407,18 +435,30 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, } if (!(file->flags & EVENT_FILE_FL_ENABLED)) { + bool cmd = false, tgid = false; /* Keep the event disabled, when going to SOFT_MODE. */ if (soft_disable) set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags); if (tr->trace_flags & TRACE_ITER_RECORD_CMD) { + cmd = true; tracing_start_cmdline_record(); set_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } + + if (tr->trace_flags & TRACE_ITER_RECORD_TGID) { + tgid = true; + tracing_start_tgid_record(); + set_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags); + } + ret = call->class->reg(call, TRACE_REG_REGISTER, file); if (ret) { - tracing_stop_cmdline_record(); + if (cmd) + tracing_stop_cmdline_record(); + if (tgid) + tracing_stop_tgid_record(); pr_info("event trace: Could not enable event " "%s\n", trace_event_name(call)); break; @@ -426,7 +466,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, set_bit(EVENT_FILE_FL_ENABLED_BIT, &file->flags); /* WAS_ENABLED gets set but never cleared. */ - call->flags |= TRACE_EVENT_FL_WAS_ENABLED; + set_bit(EVENT_FILE_FL_WAS_ENABLED_BIT, &file->flags); } break; } @@ -2018,6 +2058,10 @@ static void event_remove(struct trace_event_call *call) do_for_each_event_file(tr, file) { if (file->event_call != call) continue; + + if (file->flags & EVENT_FILE_FL_WAS_ENABLED) + tr->clear_trace = true; + ftrace_event_enable_disable(file, 0); /* * The do_for_each_event_file() is @@ -2067,18 +2111,18 @@ __register_event(struct trace_event_call *call, struct module *mod) return 0; } -static char *enum_replace(char *ptr, struct trace_enum_map *map, int len) +static char *eval_replace(char *ptr, struct trace_eval_map *map, int len) { int rlen; int elen; - /* Find the length of the enum value as a string */ - elen = snprintf(ptr, 0, "%ld", map->enum_value); + /* Find the length of the eval value as a string */ + elen = snprintf(ptr, 0, "%ld", map->eval_value); /* Make sure there's enough room to replace the string with the value */ if (len < elen) return NULL; - snprintf(ptr, elen + 1, "%ld", map->enum_value); + snprintf(ptr, elen + 1, "%ld", map->eval_value); /* Get the rest of the string of ptr */ rlen = strlen(ptr + len); @@ -2090,11 +2134,11 @@ static char *enum_replace(char *ptr, struct trace_enum_map *map, int len) } static void update_event_printk(struct trace_event_call *call, - struct trace_enum_map *map) + struct trace_eval_map *map) { char *ptr; int quote = 0; - int len = strlen(map->enum_string); + int len = strlen(map->eval_string); for (ptr = call->print_fmt; *ptr; ptr++) { if (*ptr == '\\') { @@ -2125,16 +2169,16 @@ static void update_event_printk(struct trace_event_call *call, continue; } if (isalpha(*ptr) || *ptr == '_') { - if (strncmp(map->enum_string, ptr, len) == 0 && + if (strncmp(map->eval_string, ptr, len) == 0 && !isalnum(ptr[len]) && ptr[len] != '_') { - ptr = enum_replace(ptr, map, len); - /* Hmm, enum string smaller than value */ + ptr = eval_replace(ptr, map, len); + /* enum/sizeof string smaller than value */ if (WARN_ON_ONCE(!ptr)) return; /* - * No need to decrement here, as enum_replace() + * No need to decrement here, as eval_replace() * returns the pointer to the character passed - * the enum, and two enums can not be placed + * the eval, and two evals can not be placed * back to back without something in between. * We can skip that something in between. */ @@ -2165,7 +2209,7 @@ static void update_event_printk(struct trace_event_call *call, } } -void trace_event_enum_update(struct trace_enum_map **map, int len) +void trace_event_eval_update(struct trace_eval_map **map, int len) { struct trace_event_call *call, *p; const char *last_system = NULL; @@ -2356,15 +2400,11 @@ static void trace_module_add_events(struct module *mod) static void trace_module_remove_events(struct module *mod) { struct trace_event_call *call, *p; - bool clear_trace = false; down_write(&trace_event_sem); list_for_each_entry_safe(call, p, &ftrace_events, list) { - if (call->mod == mod) { - if (call->flags & TRACE_EVENT_FL_WAS_ENABLED) - clear_trace = true; + if (call->mod == mod) __trace_remove_event_call(call); - } } up_write(&trace_event_sem); @@ -2376,8 +2416,7 @@ static void trace_module_remove_events(struct module *mod) * over from this module may be passed to the new module events and * unexpected results may occur. */ - if (clear_trace) - tracing_reset_all_online_cpus(); + tracing_reset_all_online_cpus(); } static int trace_module_notify(struct notifier_block *self, diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 59a411ff60c7..61e7f0678d33 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -702,7 +702,7 @@ static void append_filter_err(struct filter_parse_state *ps, int pos = ps->lasterr_pos; char *buf, *pbuf; - buf = (char *)__get_free_page(GFP_TEMPORARY); + buf = (char *)__get_free_page(GFP_KERNEL); if (!buf) return; @@ -1959,6 +1959,10 @@ static int create_filter(struct trace_event_call *call, if (err && set_str) append_filter_err(ps, filter); } + if (err && !set_str) { + free_event_filter(filter); + filter = NULL; + } create_filter_finish(ps); *filterp = filter; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index d56123cdcc89..b8f1f54731af 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -1543,7 +1543,7 @@ fs_initcall(init_graph_tracefs); static __init int init_graph_trace(void) { - max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1); + max_bytes_for_cpu = snprintf(NULL, 0, "%u", nr_cpu_ids - 1); if (!register_trace_event(&graph_trace_entry_event)) { pr_warn("Warning: could not register graph trace events\n"); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index b53c8d369163..8a907e12b6b9 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -598,6 +598,14 @@ static struct notifier_block trace_kprobe_module_nb = { .priority = 1 /* Invoked after kprobe module callback */ }; +/* Convert certain expected symbols into '_' when generating event names */ +static inline void sanitize_event_name(char *name) +{ + while (*name++ != '\0') + if (*name == ':' || *name == '.') + *name = '_'; +} + static int create_trace_kprobe(int argc, char **argv) { /* @@ -720,7 +728,7 @@ static int create_trace_kprobe(int argc, char **argv) return ret; } if (offset && is_return && - !function_offset_within_entry(NULL, symbol, offset)) { + !kprobe_on_func_entry(NULL, symbol, offset)) { pr_info("Given offset is not valid for return probe.\n"); return -EINVAL; } @@ -736,6 +744,7 @@ static int create_trace_kprobe(int argc, char **argv) else snprintf(buf, MAX_EVENT_NAME_LEN, "%c_0x%p", is_return ? 'r' : 'p', addr); + sanitize_event_name(buf); event = buf; } tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive, @@ -1191,7 +1200,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) memset(&entry[1], 0, dsize); store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, - head, NULL); + head, NULL, NULL); } NOKPROBE_SYMBOL(kprobe_perf_func); @@ -1227,7 +1236,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, entry->ret_ip = (unsigned long)ri->ret_addr; store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, - head, NULL); + head, NULL, NULL); } NOKPROBE_SYMBOL(kretprobe_perf_func); #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index cd7480d0a201..dca78fc48439 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -282,6 +282,7 @@ static struct tracer mmio_tracer __read_mostly = .close = mmio_close, .read = mmio_read, .print_line = mmio_print_line, + .noboot = true, }; __init static int init_mmio_trace(void) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 08f9bab8089e..c738e764e2a5 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -340,31 +340,41 @@ static inline const char *kretprobed(const char *name) static void seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) { -#ifdef CONFIG_KALLSYMS char str[KSYM_SYMBOL_LEN]; +#ifdef CONFIG_KALLSYMS const char *name; kallsyms_lookup(address, NULL, NULL, NULL, str); name = kretprobed(str); - trace_seq_printf(s, fmt, name); + if (name && strlen(name)) { + trace_seq_printf(s, fmt, name); + return; + } #endif + snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address); + trace_seq_printf(s, fmt, str); } static void seq_print_sym_offset(struct trace_seq *s, const char *fmt, unsigned long address) { -#ifdef CONFIG_KALLSYMS char str[KSYM_SYMBOL_LEN]; +#ifdef CONFIG_KALLSYMS const char *name; sprint_symbol(str, address); name = kretprobed(str); - trace_seq_printf(s, fmt, name); + if (name && strlen(name)) { + trace_seq_printf(s, fmt, name); + return; + } #endif + snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address); + trace_seq_printf(s, fmt, str); } #ifndef CONFIG_64BIT @@ -587,6 +597,15 @@ int trace_print_context(struct trace_iterator *iter) trace_seq_printf(s, "%16s-%-5d [%03d] ", comm, entry->pid, iter->cpu); + if (tr->trace_flags & TRACE_ITER_RECORD_TGID) { + unsigned int tgid = trace_find_tgid(entry->pid); + + if (!tgid) + trace_seq_printf(s, "(-----) "); + else + trace_seq_printf(s, "(%5d) ", tgid); + } + if (tr->trace_flags & TRACE_ITER_IRQ_INFO) trace_print_lat_fmt(s, entry); @@ -637,15 +656,6 @@ int trace_print_lat_context(struct trace_iterator *iter) return !trace_seq_has_overflowed(s); } -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - /** * ftrace_find_event - find a registered event * @type: the type of event to look for @@ -911,8 +921,8 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, trace_assign_type(field, iter->ent); - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); + T = __task_state_to_char(field->next_state); + S = __task_state_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", @@ -947,8 +957,8 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -983,8 +993,8 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); SEQ_PUT_HEX_FIELD(s, field->prev_pid); SEQ_PUT_HEX_FIELD(s, field->prev_prio); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 4c896a0101bd..b341c02730be 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -12,27 +12,38 @@ #include "trace.h" -static int sched_ref; +#define RECORD_CMDLINE 1 +#define RECORD_TGID 2 + +static int sched_cmdline_ref; +static int sched_tgid_ref; static DEFINE_MUTEX(sched_register_mutex); static void probe_sched_switch(void *ignore, bool preempt, struct task_struct *prev, struct task_struct *next) { - if (unlikely(!sched_ref)) - return; + int flags; + + flags = (RECORD_TGID * !!sched_tgid_ref) + + (RECORD_CMDLINE * !!sched_cmdline_ref); - tracing_record_cmdline(prev); - tracing_record_cmdline(next); + if (!flags) + return; + tracing_record_taskinfo_sched_switch(prev, next, flags); } static void probe_sched_wakeup(void *ignore, struct task_struct *wakee) { - if (unlikely(!sched_ref)) - return; + int flags; + + flags = (RECORD_TGID * !!sched_tgid_ref) + + (RECORD_CMDLINE * !!sched_cmdline_ref); - tracing_record_cmdline(current); + if (!flags) + return; + tracing_record_taskinfo(current, flags); } static int tracing_sched_register(void) @@ -75,28 +86,61 @@ static void tracing_sched_unregister(void) unregister_trace_sched_wakeup(probe_sched_wakeup, NULL); } -static void tracing_start_sched_switch(void) +static void tracing_start_sched_switch(int ops) { + bool sched_register = (!sched_cmdline_ref && !sched_tgid_ref); mutex_lock(&sched_register_mutex); - if (!(sched_ref++)) + + switch (ops) { + case RECORD_CMDLINE: + sched_cmdline_ref++; + break; + + case RECORD_TGID: + sched_tgid_ref++; + break; + } + + if (sched_register && (sched_cmdline_ref || sched_tgid_ref)) tracing_sched_register(); mutex_unlock(&sched_register_mutex); } -static void tracing_stop_sched_switch(void) +static void tracing_stop_sched_switch(int ops) { mutex_lock(&sched_register_mutex); - if (!(--sched_ref)) + + switch (ops) { + case RECORD_CMDLINE: + sched_cmdline_ref--; + break; + + case RECORD_TGID: + sched_tgid_ref--; + break; + } + + if (!sched_cmdline_ref && !sched_tgid_ref) tracing_sched_unregister(); mutex_unlock(&sched_register_mutex); } void tracing_start_cmdline_record(void) { - tracing_start_sched_switch(); + tracing_start_sched_switch(RECORD_CMDLINE); } void tracing_stop_cmdline_record(void) { - tracing_stop_sched_switch(); + tracing_stop_sched_switch(RECORD_CMDLINE); +} + +void tracing_start_tgid_record(void) +{ + tracing_start_sched_switch(RECORD_TGID); +} + +void tracing_stop_tgid_record(void) +{ + tracing_stop_sched_switch(RECORD_TGID); } diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ddec53b67646..0c331978b1a6 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -397,10 +397,10 @@ tracing_sched_switch_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; - entry->prev_state = prev->state; + entry->prev_state = __get_task_state(prev); entry->next_pid = next->pid; entry->next_prio = next->prio; - entry->next_state = next->state; + entry->next_state = __get_task_state(next); entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) @@ -425,10 +425,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; - entry->prev_state = curr->state; + entry->prev_state = __get_task_state(curr); entry->next_pid = wakee->pid; entry->next_prio = wakee->prio; - entry->next_state = wakee->state; + entry->next_state = __get_task_state(wakee); entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index cb917cebae29..b17ec642793b 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -273,7 +273,7 @@ static int trace_selftest_ops(struct trace_array *tr, int cnt) goto out_free; if (cnt > 1) { if (trace_selftest_test_global_cnt == 0) - goto out; + goto out_free; } if (trace_selftest_test_dyn_cnt == 0) goto out_free; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index b4a751e8f9d6..49cb41412eec 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -96,23 +96,9 @@ 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); - /* - * RCU may not be watching, make it see us. - * The stack trace code uses rcu_sched. - */ - rcu_irq_enter(); - /* In case another CPU set the tracer_frame on us */ if (unlikely(!frame_size)) this_size -= tracer_frame; @@ -205,7 +191,6 @@ check_stack(unsigned long ip, unsigned long *stack) } out: - rcu_irq_exit(); arch_spin_unlock(&stack_trace_max_lock); local_irq_restore(flags); } @@ -406,6 +391,8 @@ static const struct file_operations stack_trace_fops = { .release = seq_release, }; +#ifdef CONFIG_DYNAMIC_FTRACE + static int stack_trace_filter_open(struct inode *inode, struct file *file) { @@ -423,6 +410,8 @@ static const struct file_operations stack_trace_filter_fops = { .release = ftrace_regex_release, }; +#endif /* CONFIG_DYNAMIC_FTRACE */ + int stack_trace_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -477,8 +466,10 @@ static __init int stack_trace_init(void) trace_create_file("stack_trace", 0444, d_tracer, NULL, &stack_trace_fops); +#ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("stack_trace_filter", 0444, d_tracer, &trace_ops, &stack_trace_filter_fops); +#endif if (stack_trace_filter_buf[0]) ftrace_set_early_filter(&trace_ops, stack_trace_filter_buf, 1); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 5e10395da88e..696afe72d3b1 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -559,11 +559,29 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls); static int sys_perf_refcount_enter; static int sys_perf_refcount_exit; +static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs, + struct syscall_metadata *sys_data, + struct syscall_trace_enter *rec) { + struct syscall_tp_t { + unsigned long long regs; + unsigned long syscall_nr; + unsigned long args[SYSCALL_DEFINE_MAXARGS]; + } param; + int i; + + *(struct pt_regs **)¶m = regs; + param.syscall_nr = rec->nr; + for (i = 0; i < sys_data->nb_args; i++) + param.args[i] = rec->args[i]; + return trace_call_bpf(prog, ¶m); +} + static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) { struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; struct hlist_head *head; + struct bpf_prog *prog; int syscall_nr; int rctx; int size; @@ -578,8 +596,9 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) if (!sys_data) return; + prog = READ_ONCE(sys_data->enter_event->prog); head = this_cpu_ptr(sys_data->enter_event->perf_events); - if (hlist_empty(head)) + if (!prog && hlist_empty(head)) return; /* get the size after alignment with the u32 buffer size field */ @@ -594,9 +613,16 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); + + if ((prog && !perf_call_bpf_enter(prog, regs, sys_data, rec)) || + hlist_empty(head)) { + perf_swevent_put_recursion_context(rctx); + return; + } + perf_trace_buf_submit(rec, size, rctx, sys_data->enter_event->event.type, 1, regs, - head, NULL); + head, NULL, NULL); } static int perf_sysenter_enable(struct trace_event_call *call) @@ -633,11 +659,26 @@ static void perf_sysenter_disable(struct trace_event_call *call) mutex_unlock(&syscall_trace_lock); } +static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs, + struct syscall_trace_exit *rec) { + struct syscall_tp_t { + unsigned long long regs; + unsigned long syscall_nr; + unsigned long ret; + } param; + + *(struct pt_regs **)¶m = regs; + param.syscall_nr = rec->nr; + param.ret = rec->ret; + return trace_call_bpf(prog, ¶m); +} + static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) { struct syscall_metadata *sys_data; struct syscall_trace_exit *rec; struct hlist_head *head; + struct bpf_prog *prog; int syscall_nr; int rctx; int size; @@ -652,8 +693,9 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) if (!sys_data) return; + prog = READ_ONCE(sys_data->exit_event->prog); head = this_cpu_ptr(sys_data->exit_event->perf_events); - if (hlist_empty(head)) + if (!prog && hlist_empty(head)) return; /* We can probably do that at build time */ @@ -666,8 +708,15 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); + + if ((prog && !perf_call_bpf_exit(prog, regs, rec)) || + hlist_empty(head)) { + perf_swevent_put_recursion_context(rctx); + return; + } + perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type, - 1, regs, head, NULL); + 1, regs, head, NULL, NULL); } static int perf_sysexit_enable(struct trace_event_call *call) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index a7581fec9681..4525e0271a53 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1156,7 +1156,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, } perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, - head, NULL); + head, NULL, NULL); out: preempt_enable(); } diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 0a689bbb78ef..305039b122fa 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -221,16 +221,19 @@ void tracing_map_array_free(struct tracing_map_array *a) if (!a) return; - if (!a->pages) { - kfree(a); - return; - } + if (!a->pages) + goto free; for (i = 0; i < a->n_pages; i++) { if (!a->pages[i]) break; free_page((unsigned long)a->pages[i]); } + + kfree(a->pages); + + free: + kfree(a); } struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, |