diff options
Diffstat (limited to 'include/trace')
-rw-r--r-- | include/trace/events/block.h | 33 | ||||
-rw-r--r-- | include/trace/events/ext4.h | 178 | ||||
-rw-r--r-- | include/trace/events/jbd2.h | 78 | ||||
-rw-r--r-- | include/trace/events/kmem.h | 163 | ||||
-rw-r--r-- | include/trace/events/power.h | 81 | ||||
-rw-r--r-- | include/trace/events/sched.h | 33 | ||||
-rw-r--r-- | include/trace/events/timer.h | 342 | ||||
-rw-r--r-- | include/trace/events/workqueue.h | 4 | ||||
-rw-r--r-- | include/trace/ftrace.h | 117 |
9 files changed, 972 insertions, 57 deletions
diff --git a/include/trace/events/block.h b/include/trace/events/block.h index d86af94691c..00405b5f624 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -488,6 +488,39 @@ TRACE_EVENT(block_remap, (unsigned long long)__entry->old_sector) ); +TRACE_EVENT(block_rq_remap, + + TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev, + sector_t from), + + TP_ARGS(q, rq, dev, from), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( sector_t, sector ) + __field( unsigned int, nr_sector ) + __field( dev_t, old_dev ) + __field( sector_t, old_sector ) + __array( char, rwbs, 6 ) + ), + + TP_fast_assign( + __entry->dev = disk_devt(rq->rq_disk); + __entry->sector = blk_rq_pos(rq); + __entry->nr_sector = blk_rq_sectors(rq); + __entry->old_dev = dev; + __entry->old_sector = from; + blk_fill_rwbs_rq(__entry->rwbs, rq); + ), + + TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, + MAJOR(__entry->old_dev), MINOR(__entry->old_dev), + (unsigned long long)__entry->old_sector) +); + #endif /* _TRACE_BLOCK_H */ /* This part must be outside protection */ diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index c1bd8f1e8b9..d09550bf3f9 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -11,6 +11,7 @@ struct ext4_allocation_context; struct ext4_allocation_request; struct ext4_prealloc_space; struct ext4_inode_info; +struct mpage_da_data; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) @@ -236,6 +237,7 @@ TRACE_EVENT(ext4_da_writepages, __field( char, for_kupdate ) __field( char, for_reclaim ) __field( char, range_cyclic ) + __field( pgoff_t, writeback_index ) ), TP_fast_assign( @@ -249,15 +251,17 @@ TRACE_EVENT(ext4_da_writepages, __entry->for_kupdate = wbc->for_kupdate; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; + __entry->writeback_index = inode->i_mapping->writeback_index; ), - TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d", + TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d writeback_index %lu", jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->nonblocking, __entry->for_kupdate, __entry->for_reclaim, - __entry->range_cyclic) + __entry->range_cyclic, + (unsigned long) __entry->writeback_index) ); TRACE_EVENT(ext4_da_write_pages, @@ -309,6 +313,7 @@ TRACE_EVENT(ext4_da_writepages_result, __field( char, encountered_congestion ) __field( char, more_io ) __field( char, no_nrwrite_index_update ) + __field( pgoff_t, writeback_index ) ), TP_fast_assign( @@ -320,14 +325,16 @@ TRACE_EVENT(ext4_da_writepages_result, __entry->encountered_congestion = wbc->encountered_congestion; __entry->more_io = wbc->more_io; __entry->no_nrwrite_index_update = wbc->no_nrwrite_index_update; + __entry->writeback_index = inode->i_mapping->writeback_index; ), - TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d", + TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d writeback_index %lu", jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, __entry->encountered_congestion, __entry->more_io, - __entry->no_nrwrite_index_update) + __entry->no_nrwrite_index_update, + (unsigned long) __entry->writeback_index) ); TRACE_EVENT(ext4_da_write_begin, @@ -737,6 +744,169 @@ TRACE_EVENT(ext4_alloc_da_blocks, __entry->data_blocks, __entry->meta_blocks) ); +TRACE_EVENT(ext4_mballoc_alloc, + TP_PROTO(struct ext4_allocation_context *ac), + + TP_ARGS(ac), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u16, found ) + __field( __u16, groups ) + __field( __u16, buddy ) + __field( __u16, flags ) + __field( __u16, tail ) + __field( __u8, cr ) + __field( __u32, orig_logical ) + __field( int, orig_start ) + __field( __u32, orig_group ) + __field( int, orig_len ) + __field( __u32, goal_logical ) + __field( int, goal_start ) + __field( __u32, goal_group ) + __field( int, goal_len ) + __field( __u32, result_logical ) + __field( int, result_start ) + __field( __u32, result_group ) + __field( int, result_len ) + ), + + TP_fast_assign( + __entry->dev = ac->ac_inode->i_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->found = ac->ac_found; + __entry->flags = ac->ac_flags; + __entry->groups = ac->ac_groups_scanned; + __entry->buddy = ac->ac_buddy; + __entry->tail = ac->ac_tail; + __entry->cr = ac->ac_criteria; + __entry->orig_logical = ac->ac_o_ex.fe_logical; + __entry->orig_start = ac->ac_o_ex.fe_start; + __entry->orig_group = ac->ac_o_ex.fe_group; + __entry->orig_len = ac->ac_o_ex.fe_len; + __entry->goal_logical = ac->ac_g_ex.fe_logical; + __entry->goal_start = ac->ac_g_ex.fe_start; + __entry->goal_group = ac->ac_g_ex.fe_group; + __entry->goal_len = ac->ac_g_ex.fe_len; + __entry->result_logical = ac->ac_f_ex.fe_logical; + __entry->result_start = ac->ac_f_ex.fe_start; + __entry->result_group = ac->ac_f_ex.fe_group; + __entry->result_len = ac->ac_f_ex.fe_len; + ), + + TP_printk("dev %s inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u " + "result %u/%d/%u@%u blks %u grps %u cr %u flags 0x%04x " + "tail %u broken %u", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->orig_group, __entry->orig_start, + __entry->orig_len, __entry->orig_logical, + __entry->goal_group, __entry->goal_start, + __entry->goal_len, __entry->goal_logical, + __entry->result_group, __entry->result_start, + __entry->result_len, __entry->result_logical, + __entry->found, __entry->groups, __entry->cr, + __entry->flags, __entry->tail, + __entry->buddy ? 1 << __entry->buddy : 0) +); + +TRACE_EVENT(ext4_mballoc_prealloc, + TP_PROTO(struct ext4_allocation_context *ac), + + TP_ARGS(ac), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u32, orig_logical ) + __field( int, orig_start ) + __field( __u32, orig_group ) + __field( int, orig_len ) + __field( __u32, result_logical ) + __field( int, result_start ) + __field( __u32, result_group ) + __field( int, result_len ) + ), + + TP_fast_assign( + __entry->dev = ac->ac_inode->i_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->orig_logical = ac->ac_o_ex.fe_logical; + __entry->orig_start = ac->ac_o_ex.fe_start; + __entry->orig_group = ac->ac_o_ex.fe_group; + __entry->orig_len = ac->ac_o_ex.fe_len; + __entry->result_logical = ac->ac_b_ex.fe_logical; + __entry->result_start = ac->ac_b_ex.fe_start; + __entry->result_group = ac->ac_b_ex.fe_group; + __entry->result_len = ac->ac_b_ex.fe_len; + ), + + TP_printk("dev %s inode %lu orig %u/%d/%u@%u result %u/%d/%u@%u", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->orig_group, __entry->orig_start, + __entry->orig_len, __entry->orig_logical, + __entry->result_group, __entry->result_start, + __entry->result_len, __entry->result_logical) +); + +TRACE_EVENT(ext4_mballoc_discard, + TP_PROTO(struct ext4_allocation_context *ac), + + TP_ARGS(ac), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u32, result_logical ) + __field( int, result_start ) + __field( __u32, result_group ) + __field( int, result_len ) + ), + + TP_fast_assign( + __entry->dev = ac->ac_inode->i_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->result_logical = ac->ac_b_ex.fe_logical; + __entry->result_start = ac->ac_b_ex.fe_start; + __entry->result_group = ac->ac_b_ex.fe_group; + __entry->result_len = ac->ac_b_ex.fe_len; + ), + + TP_printk("dev %s inode %lu extent %u/%d/%u@%u ", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->result_group, __entry->result_start, + __entry->result_len, __entry->result_logical) +); + +TRACE_EVENT(ext4_mballoc_free, + TP_PROTO(struct ext4_allocation_context *ac), + + TP_ARGS(ac), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u32, result_logical ) + __field( int, result_start ) + __field( __u32, result_group ) + __field( int, result_len ) + ), + + TP_fast_assign( + __entry->dev = ac->ac_inode->i_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->result_logical = ac->ac_b_ex.fe_logical; + __entry->result_start = ac->ac_b_ex.fe_start; + __entry->result_group = ac->ac_b_ex.fe_group; + __entry->result_len = ac->ac_b_ex.fe_len; + ), + + TP_printk("dev %s inode %lu extent %u/%d/%u@%u ", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->result_group, __entry->result_start, + __entry->result_len, __entry->result_logical) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index b851f0b4701..3c60b75adb9 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -7,6 +7,9 @@ #include <linux/jbd2.h> #include <linux/tracepoint.h> +struct transaction_chp_stats_s; +struct transaction_run_stats_s; + TRACE_EVENT(jbd2_checkpoint, TP_PROTO(journal_t *journal, int result), @@ -162,6 +165,81 @@ TRACE_EVENT(jbd2_submit_inode_data, jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino) ); +TRACE_EVENT(jbd2_run_stats, + TP_PROTO(dev_t dev, unsigned long tid, + struct transaction_run_stats_s *stats), + + TP_ARGS(dev, tid, stats), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( unsigned long, tid ) + __field( unsigned long, wait ) + __field( unsigned long, running ) + __field( unsigned long, locked ) + __field( unsigned long, flushing ) + __field( unsigned long, logging ) + __field( __u32, handle_count ) + __field( __u32, blocks ) + __field( __u32, blocks_logged ) + ), + + TP_fast_assign( + __entry->dev = dev; + __entry->tid = tid; + __entry->wait = stats->rs_wait; + __entry->running = stats->rs_running; + __entry->locked = stats->rs_locked; + __entry->flushing = stats->rs_flushing; + __entry->logging = stats->rs_logging; + __entry->handle_count = stats->rs_handle_count; + __entry->blocks = stats->rs_blocks; + __entry->blocks_logged = stats->rs_blocks_logged; + ), + + TP_printk("dev %s tid %lu wait %u running %u locked %u flushing %u " + "logging %u handle_count %u blocks %u blocks_logged %u", + jbd2_dev_to_name(__entry->dev), __entry->tid, + jiffies_to_msecs(__entry->wait), + jiffies_to_msecs(__entry->running), + jiffies_to_msecs(__entry->locked), + jiffies_to_msecs(__entry->flushing), + jiffies_to_msecs(__entry->logging), + __entry->handle_count, __entry->blocks, + __entry->blocks_logged) +); + +TRACE_EVENT(jbd2_checkpoint_stats, + TP_PROTO(dev_t dev, unsigned long tid, + struct transaction_chp_stats_s *stats), + + TP_ARGS(dev, tid, stats), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( unsigned long, tid ) + __field( unsigned long, chp_time ) + __field( __u32, forced_to_close ) + __field( __u32, written ) + __field( __u32, dropped ) + ), + + TP_fast_assign( + __entry->dev = dev; + __entry->tid = tid; + __entry->chp_time = stats->cs_chp_time; + __entry->forced_to_close= stats->cs_forced_to_close; + __entry->written = stats->cs_written; + __entry->dropped = stats->cs_dropped; + ), + + TP_printk("dev %s tid %lu chp_time %u forced_to_close %u " + "written %u dropped %u", + jbd2_dev_to_name(__entry->dev), __entry->tid, + jiffies_to_msecs(__entry->chp_time), + __entry->forced_to_close, __entry->written, __entry->dropped) +); + #endif /* _TRACE_JBD2_H */ /* This part must be outside protection */ diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 1493c541f9c..eaf46bdd18a 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -225,6 +225,169 @@ TRACE_EVENT(kmem_cache_free, TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr) ); + +TRACE_EVENT(mm_page_free_direct, + + TP_PROTO(struct page *page, unsigned int order), + + TP_ARGS(page, order), + + TP_STRUCT__entry( + __field( struct page *, page ) + __field( unsigned int, order ) + ), + + TP_fast_assign( + __entry->page = page; + __entry->order = order; + ), + + TP_printk("page=%p pfn=%lu order=%d", + __entry->page, + page_to_pfn(__entry->page), + __entry->order) +); + +TRACE_EVENT(mm_pagevec_free, + + TP_PROTO(struct page *page, int cold), + + TP_ARGS(page, cold), + + TP_STRUCT__entry( + __field( struct page *, page ) + __field( int, cold ) + ), + + TP_fast_assign( + __entry->page = page; + __entry->cold = cold; + ), + + TP_printk("page=%p pfn=%lu order=0 cold=%d", + __entry->page, + page_to_pfn(__entry->page), + __entry->cold) +); + +TRACE_EVENT(mm_page_alloc, + + TP_PROTO(struct page *page, unsigned int order, + gfp_t gfp_flags, int migratetype), + + TP_ARGS(page, order, gfp_flags, migratetype), + + TP_STRUCT__entry( + __field( struct page *, page ) + __field( unsigned int, order ) + __field( gfp_t, gfp_flags ) + __field( int, migratetype ) + ), + + TP_fast_assign( + __entry->page = page; + __entry->order = order; + __entry->gfp_flags = gfp_flags; + __entry->migratetype = migratetype; + ), + + TP_printk("page=%p pfn=%lu order=%d migratetype=%d gfp_flags=%s", + __entry->page, + page_to_pfn(__entry->page), + __entry->order, + __entry->migratetype, + show_gfp_flags(__entry->gfp_flags)) +); + +TRACE_EVENT(mm_page_alloc_zone_locked, + + TP_PROTO(struct page *page, unsigned int order, int migratetype), + + TP_ARGS(page, order, migratetype), + + TP_STRUCT__entry( + __field( struct page *, page ) + __field( unsigned int, order ) + __field( int, migratetype ) + ), + + TP_fast_assign( + __entry->page = page; + __entry->order = order; + __entry->migratetype = migratetype; + ), + + TP_printk("page=%p pfn=%lu order=%u migratetype=%d percpu_refill=%d", + __entry->page, + page_to_pfn(__entry->page), + __entry->order, + __entry->migratetype, + __entry->order == 0) +); + +TRACE_EVENT(mm_page_pcpu_drain, + + TP_PROTO(struct page *page, int order, int migratetype), + + TP_ARGS(page, order, migratetype), + + TP_STRUCT__entry( + __field( struct page *, page ) + __field( int, order ) + __field( int, migratetype ) + ), + + TP_fast_assign( + __entry->page = page; + __entry->order = order; + __entry->migratetype = migratetype; + ), + + TP_printk("page=%p pfn=%lu order=%d migratetype=%d", + __entry->page, + page_to_pfn(__entry->page), + __entry->order, + __entry->migratetype) +); + +TRACE_EVENT(mm_page_alloc_extfrag, + + TP_PROTO(struct page *page, + int alloc_order, int fallback_order, + int alloc_migratetype, int fallback_migratetype), + + TP_ARGS(page, + alloc_order, fallback_order, + alloc_migratetype, fallback_migratetype), + + TP_STRUCT__entry( + __field( struct page *, page ) + __field( int, alloc_order ) + __field( int, fallback_order ) + __field( int, alloc_migratetype ) + __field( int, fallback_migratetype ) + ), + + TP_fast_assign( + __entry->page = page; + __entry->alloc_order = alloc_order; + __entry->fallback_order = fallback_order; + __entry->alloc_migratetype = alloc_migratetype; + __entry->fallback_migratetype = fallback_migratetype; + ), + + TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", + __entry->page, + page_to_pfn(__entry->page), + __entry->alloc_order, + __entry->fallback_order, + pageblock_order, + __entry->alloc_migratetype, + __entry->fallback_migratetype, + __entry->fallback_order < pageblock_order, + __entry->alloc_migratetype == __entry->fallback_migratetype) +); + #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ diff --git a/include/trace/events/power.h b/include/trace/events/power.h new file mode 100644 index 00000000000..ea6d579261a --- /dev/null +++ b/include/trace/events/power.h @@ -0,0 +1,81 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM power + +#if !defined(_TRACE_POWER_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_POWER_H + +#include <linux/ktime.h> +#include <linux/tracepoint.h> + +#ifndef _TRACE_POWER_ENUM_ +#define _TRACE_POWER_ENUM_ +enum { + POWER_NONE = 0, + POWER_CSTATE = 1, + POWER_PSTATE = 2, +}; +#endif + + + +TRACE_EVENT(power_start, + + TP_PROTO(unsigned int type, unsigned int state), + + TP_ARGS(type, state), + + TP_STRUCT__entry( + __field( u64, type ) + __field( u64, state ) + ), + + TP_fast_assign( + __entry->type = type; + __entry->state = state; + ), + + TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long)__entry->state) +); + +TRACE_EVENT(power_end, + + TP_PROTO(int dummy), + + TP_ARGS(dummy), + + TP_STRUCT__entry( + __field( u64, dummy ) + ), + + TP_fast_assign( + __entry->dummy = 0xffff; + ), + + TP_printk("dummy=%lu", (unsigned long)__entry->dummy) + +); + + +TRACE_EVENT(power_frequency, + + TP_PROTO(unsigned int type, unsigned int state), + + TP_ARGS(type, state), + + TP_STRUCT__entry( + __field( u64, type ) + __field( u64, state ) + ), + + TP_fast_assign( + __entry->type = type; + __entry->state = state; + ), + + TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long) __entry->state) +); + +#endif /* _TRACE_POWER_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index b48f1ad7c94..4069c43f418 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -380,6 +380,39 @@ TRACE_EVENT(sched_stat_wait, ); /* + * Tracepoint for accounting runtime (time the task is executing + * on a CPU). + */ +TRACE_EVENT(sched_stat_runtime, + + TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime), + + TP_ARGS(tsk, runtime, vruntime), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( u64, runtime ) + __field( u64, vruntime ) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->runtime = runtime; + __entry->vruntime = vruntime; + ) + TP_perf_assign( + __perf_count(runtime); + ), + + TP_printk("task: %s:%d runtime: %Lu [ns], vruntime: %Lu [ns]", + __entry->comm, __entry->pid, + (unsigned long long)__entry->runtime, + (unsigned long long)__entry->vruntime) +); + +/* * Tracepoint for accounting sleep time (time the task is not runnable, * including iowait, see below). */ diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h new file mode 100644 index 00000000000..1844c48d640 --- /dev/null +++ b/include/trace/events/timer.h @@ -0,0 +1,342 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM timer + +#if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TIMER_H + +#include <linux/tracepoint.h> +#include <linux/hrtimer.h> +#include <linux/timer.h> + +/** + * timer_init - called when the timer is initialized + * @timer: pointer to struct timer_list + */ +TRACE_EVENT(timer_init, + + TP_PROTO(struct timer_list *timer), + + TP_ARGS(timer), + + TP_STRUCT__entry( + __field( void *, timer ) + ), + + TP_fast_assign( + __entry->timer = timer; + ), + + TP_printk("timer %p", __entry->timer) +); + +/** + * timer_start - called when the timer is started + * @timer: pointer to struct timer_list + * @expires: the timers expiry time + */ +TRACE_EVENT(timer_start, + + TP_PROTO(struct timer_list *timer, unsigned long expires), + + TP_ARGS(timer, expires), + + TP_STRUCT__entry( + __field( void *, timer ) + __field( void *, function ) + __field( unsigned long, expires ) + __field( unsigned long, now ) + ), + + TP_fast_assign( + __entry->timer = timer; + __entry->function = timer->function; + __entry->expires = expires; + __entry->now = jiffies; + ), + + TP_printk("timer %p: func %pf, expires %lu, timeout %ld", + __entry->timer, __entry->function, __entry->expires, + (long)__entry->expires - __entry->now) +); + +/** + * timer_expire_entry - called immediately before the timer callback + * @timer: pointer to struct timer_list + * + * Allows to determine the timer latency. + */ +TRACE_EVENT(timer_expire_entry, + + TP_PROTO(struct timer_list *timer), + + TP_ARGS(timer), + + TP_STRUCT__entry( + __field( void *, timer ) + __field( unsigned long, now ) + ), + + TP_fast_assign( + __entry->timer = timer; + __entry->now = jiffies; + ), + + TP_printk("timer %p: now %lu", __entry->timer, __entry->now) +); + +/** + * timer_expire_exit - called immediately after the timer callback returns + * @timer: pointer to struct timer_list + * + * When used in combination with the timer_expire_entry tracepoint we can + * determine the runtime of the timer callback function. + * + * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might + * be invalid. We solely track the pointer. + */ +TRACE_EVENT(timer_expire_exit, + + TP_PROTO(struct timer_list *timer), + + TP_ARGS(timer), + + TP_STRUCT__entry( + __field(void *, timer ) + ), + + TP_fast_assign( + __entry->timer = timer; + ), + + TP_printk("timer %p", __entry->timer) +); + +/** + * timer_cancel - called when the timer is canceled + * @timer: pointer to struct timer_list + */ +TRACE_EVENT(timer_cancel, + + TP_PROTO(struct timer_list *timer), + + TP_ARGS(timer), + + TP_STRUCT__entry( + __field( void *, timer ) + ), + + TP_fast_assign( + __entry->timer = timer; + ), + + TP_printk("timer %p", __entry->timer) +); + +/** + * hrtimer_init - called when the hrtimer is initialized + * @timer: pointer to struct hrtimer + * @clockid: the hrtimers clock + * @mode: the hrtimers mode + */ +TRACE_EVENT(hrtimer_init, + + TP_PROTO(struct hrtimer *timer, clockid_t clockid, + enum hrtimer_mode mode), + + TP_ARGS(timer, clockid, mode), + + TP_STRUCT__entry( + __field( void *, timer ) + __field( clockid_t, clockid ) + __field( enum hrtimer_mode, mode ) + ), + + TP_fast_assign( + __entry->timer = timer; + __entry->clockid = clockid; + __entry->mode = mode; + ), + + TP_printk("hrtimer %p, clockid %s, mode %s", __entry->timer, + __entry->clockid == CLOCK_REALTIME ? + "CLOCK_REALTIME" : "CLOCK_MONOTONIC", + __entry->mode == HRTIMER_MODE_ABS ? + "HRTIMER_MODE_ABS" : "HRTIMER_MODE_REL") +); + +/** + * hrtimer_start - called when the hrtimer is started + * @timer: pointer to struct hrtimer + */ +TRACE_EVENT(hrtimer_start, + + TP_PROTO(struct hrtimer *timer), + + TP_ARGS(timer), + + TP_STRUCT__entry( + __field( void *, timer ) + __field( void *, function ) + __field( s64, expires ) + __field( s64, softexpires ) + ), + + TP_fast_assign( + __entry->timer = timer; + __entry->function = timer->function; + __entry->expires = hrtimer_get_expires(timer).tv64; + __entry->softexpires = hrtimer_get_softexpires(timer).tv64; + ), + + TP_printk("hrtimer %p, func %pf, expires %llu, softexpires %llu", + __entry->timer, __entry->function, + (unsigned long long)ktime_to_ns((ktime_t) { + .tv64 = __entry->expires }), + (unsigned long long)ktime_to_ns((ktime_t) { + .tv64 = __entry->softexpires })) +); + +/** + * htimmer_expire_entry - called immediately before the hrtimer callback + * @timer: pointer to struct hrtimer + * @now: pointer to variable which contains current time of the + * timers base. + * + * Allows to determine the timer latency. + */ +TRACE_EVENT(hrtimer_expire_entry, + + TP_PROTO(struct hrtimer *timer, ktime_t *now), + + TP_ARGS(timer, now), + + TP_STRUCT__entry( + __field( void *, timer ) + __field( s64, now ) + ), + + TP_fast_assign( + __entry->timer = timer; + __entry->now = now->tv64; + ), + + TP_printk("hrtimer %p, now %llu", __entry->timer, + (unsigned long long)ktime_to_ns((ktime_t) { + .tv64 = __entry->now })) + ); + +/** + * hrtimer_expire_exit - called immediately after the hrtimer callback returns + * @timer: pointer to struct hrtimer + * + * When used in combination with the hrtimer_expire_entry tracepoint we can + * determine the runtime of the callback function. + */ +TRACE_EVENT(hrtimer_expire_exit, + + TP_PROTO(struct hrtimer *timer), + + TP_ARGS(timer), + + TP_STRUCT__entry( + __field( void *, timer ) + ), + + TP_fast_assign( + __entry->timer = timer; + ), + + TP_printk("hrtimer %p", __entry->timer) +); + +/** + * hrtimer_cancel - called when the hrtimer is canceled + * @timer: pointer to struct hrtimer + */ +TRACE_EVENT(hrtimer_cancel, + + TP_PROTO(struct hrtimer *timer), + + TP_ARGS(timer), + + TP_STRUCT__entry( + __field( void *, timer ) + ), + + TP_fast_assign( + __entry->timer = timer; + ), + + TP_printk("hrtimer %p", __entry->timer) +); + +/** + * itimer_state - called when itimer is started or canceled + * @which: name of the interval timer + * @value: the itimers value, itimer is canceled if value->it_value is + * zero, otherwise it is started + * @expires: the itimers expiry time + */ +TRACE_EVENT(itimer_state, + + TP_PROTO(int which, const struct itimerval *const value, + cputime_t expires), + + TP_ARGS(which, value, expires), + + TP_STRUCT__entry( + __field( int, which ) + __field( cputime_t, expires ) + __field( long, value_sec ) + __field( long, value_usec ) + __field( long, interval_sec ) + __field( long, interval_usec ) + ), + + TP_fast_assign( + __entry->which = which; + __entry->expires = expires; + __entry->value_sec = value->it_value.tv_sec; + __entry->value_usec = value->it_value.tv_usec; + __entry->interval_sec = value->it_interval.tv_sec; + __entry->interval_usec = value->it_interval.tv_usec; + ), + + TP_printk("which %d, expires %lu, it_value %lu.%lu, it_interval %lu.%lu", + __entry->which, __entry->expires, + __entry->value_sec, __entry->value_usec, + __entry->interval_sec, __entry->interval_usec) +); + +/** + * itimer_expire - called when itimer expires + * @which: type of the interval timer + * @pid: pid of the process which owns the timer + * @now: current time, used to calculate the latency of itimer + */ +TRACE_EVENT(itimer_expire, + + TP_PROTO(int which, struct pid *pid, cputime_t now), + + TP_ARGS(which, pid, now), + + TP_STRUCT__entry( + __field( int , which ) + __field( pid_t, pid ) + __field( cputime_t, now ) + ), + + TP_fast_assign( + __entry->which = which; + __entry->now = now; + __entry->pid = pid_nr(pid); + ), + + TP_printk("which %d, pid %d, now %lu", __entry->which, + (int) __entry->pid, __entry->now) +); + +#endif /* _TRACE_TIMER_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index fcfd9a1e4b9..e4612dbd7ba 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -26,7 +26,7 @@ TRACE_EVENT(workqueue_insertion, __entry->func = work->func; ), - TP_printk("thread=%s:%d func=%pF", __entry->thread_comm, + TP_printk("thread=%s:%d func=%pf", __entry->thread_comm, __entry->thread_pid, __entry->func) ); @@ -48,7 +48,7 @@ TRACE_EVENT(workqueue_execution, __entry->func = work->func; ), - TP_printk("thread=%s:%d func=%pF", __entry->thread_comm, + TP_printk("thread=%s:%d func=%pf", __entry->thread_comm, __entry->thread_pid, __entry->func) ); diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 72a3b437b82..cc0d9667e18 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -378,24 +378,18 @@ static inline int ftrace_get_offsets_##call( \ #ifdef CONFIG_EVENT_PROFILE /* - * Generate the functions needed for tracepoint perf_counter support. + * Generate the functions needed for tracepoint perf_event support. * * NOTE: The insertion profile callback (ftrace_profile_<call>) is defined later * - * static int ftrace_profile_enable_<call>(struct ftrace_event_call *event_call) + * static int ftrace_profile_enable_<call>(void) * { - * int ret = 0; - * - * if (!atomic_inc_return(&event_call->profile_count)) - * ret = register_trace_<call>(ftrace_profile_<call>); - * - * return ret; + * return register_trace_<call>(ftrace_profile_<call>); * } * - * static void ftrace_profile_disable_<call>(struct ftrace_event_call *event_call) + * static void ftrace_profile_disable_<call>(void) * { - * if (atomic_add_negative(-1, &event->call->profile_count)) - * unregister_trace_<call>(ftrace_profile_<call>); + * unregister_trace_<call>(ftrace_profile_<call>); * } * */ @@ -405,20 +399,14 @@ static inline int ftrace_get_offsets_##call( \ \ static void ftrace_profile_##call(proto); \ \ -static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \ +static int ftrace_profile_enable_##call(void) \ { \ - int ret = 0; \ - \ - if (!atomic_inc_return(&event_call->profile_count)) \ - ret = register_trace_##call(ftrace_profile_##call); \ - \ - return ret; \ + return register_trace_##call(ftrace_profile_##call); \ } \ \ -static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\ +static void ftrace_profile_disable_##call(void) \ { \ - if (atomic_add_negative(-1, &event_call->profile_count)) \ - unregister_trace_##call(ftrace_profile_##call); \ + unregister_trace_##call(ftrace_profile_##call); \ } #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) @@ -656,15 +644,16 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ * { * struct ftrace_data_offsets_<call> __maybe_unused __data_offsets; * struct ftrace_event_call *event_call = &event_<call>; - * extern void perf_tpcounter_event(int, u64, u64, void *, int); + * extern void perf_tp_event(int, u64, u64, void *, int); * struct ftrace_raw_##call *entry; * u64 __addr = 0, __count = 1; * unsigned long irq_flags; + * struct trace_entry *ent; * int __entry_size; * int __data_size; + * int __cpu * int pc; * - * local_save_flags(irq_flags); * pc = preempt_count(); * * __data_size = ftrace_get_offsets_<call>(&__data_offsets, args); @@ -675,25 +664,34 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ * sizeof(u64)); * __entry_size -= sizeof(u32); * - * do { - * char raw_data[__entry_size]; <- allocate our sample in the stack - * struct trace_entry *ent; + * // Protect the non nmi buffer + * // This also protects the rcu read side + * local_irq_save(irq_flags); + * __cpu = smp_processor_id(); + * + * if (in_nmi()) + * raw_data = rcu_dereference(trace_profile_buf_nmi); + * else + * raw_data = rcu_dereference(trace_profile_buf); + * + * if (!raw_data) + * goto end; * - * zero dead bytes from alignment to avoid stack leak to userspace: + * raw_data = per_cpu_ptr(raw_data, __cpu); * - * *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; - * entry = (struct ftrace_raw_<call> *)raw_data; - * ent = &entry->ent; - * tracing_generic_entry_update(ent, irq_flags, pc); - * ent->type = event_call->id; + * //zero dead bytes from alignment to avoid stack leak to userspace: + * *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; + * entry = (struct ftrace_raw_<call> *)raw_data; + * ent = &entry->ent; + * tracing_generic_entry_update(ent, irq_flags, pc); + * ent->type = event_call->id; * - * <tstruct> <- do some jobs with dynamic arrays + * <tstruct> <- do some jobs with dynamic arrays * - * <assign> <- affect our values + * <assign> <- affect our values * - * perf_tpcounter_event(event_call->id, __addr, __count, entry, - * __entry_size); <- submit them to perf counter - * } while (0); + * perf_tp_event(event_call->id, __addr, __count, entry, + * __entry_size); <- submit them to perf counter * * } */ @@ -712,15 +710,17 @@ static void ftrace_profile_##call(proto) \ { \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ struct ftrace_event_call *event_call = &event_##call; \ - extern void perf_tpcounter_event(int, u64, u64, void *, int); \ + extern void perf_tp_event(int, u64, u64, void *, int); \ struct ftrace_raw_##call *entry; \ u64 __addr = 0, __count = 1; \ unsigned long irq_flags; \ + struct trace_entry *ent; \ int __entry_size; \ int __data_size; \ + char *raw_data; \ + int __cpu; \ int pc; \ \ - local_save_flags(irq_flags); \ pc = preempt_count(); \ \ __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ @@ -728,23 +728,38 @@ static void ftrace_profile_##call(proto) \ sizeof(u64)); \ __entry_size -= sizeof(u32); \ \ - do { \ - char raw_data[__entry_size]; \ - struct trace_entry *ent; \ + if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE, \ + "profile buffer not large enough")) \ + return; \ + \ + local_irq_save(irq_flags); \ + __cpu = smp_processor_id(); \ \ - *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; \ - entry = (struct ftrace_raw_##call *)raw_data; \ - ent = &entry->ent; \ - tracing_generic_entry_update(ent, irq_flags, pc); \ - ent->type = event_call->id; \ + if (in_nmi()) \ + raw_data = rcu_dereference(trace_profile_buf_nmi); \ + else \ + raw_data = rcu_dereference(trace_profile_buf); \ \ - tstruct \ + if (!raw_data) \ + goto end; \ \ - { assign; } \ + raw_data = per_cpu_ptr(raw_data, __cpu); \ \ - perf_tpcounter_event(event_call->id, __addr, __count, entry,\ + *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; \ + entry = (struct ftrace_raw_##call *)raw_data; \ + ent = &entry->ent; \ + tracing_generic_entry_update(ent, irq_flags, pc); \ + ent->type = event_call->id; \ + \ + tstruct \ + \ + { assign; } \ + \ + perf_tp_event(event_call->id, __addr, __count, entry, \ __entry_size); \ - } while (0); \ + \ +end: \ + local_irq_restore(irq_flags); \ \ } |