diff options
Diffstat (limited to 'include/trace/events/sched.h')
| -rw-r--r-- | include/trace/events/sched.h | 219 |
1 files changed, 160 insertions, 59 deletions
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 6ba596b07a7..0a68d5ae584 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/tracepoint.h> +#include <linux/binfmts.h> /* * Tracepoint for calling kthread_stop, performed to end a kthread: @@ -56,7 +57,7 @@ DECLARE_EVENT_CLASS(sched_wakeup_template, TP_PROTO(struct task_struct *p, int success), - TP_ARGS(p, success), + TP_ARGS(__perf_task(p), success), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) @@ -99,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p) /* * For all intents and purposes a preempted task is a running task. */ - if (task_thread_info(p)->preempt_count & PREEMPT_ACTIVE) + if (task_preempt_count(p) & PREEMPT_ACTIVE) state = TASK_RUNNING | TASK_STATE_MAX; #endif @@ -143,7 +144,7 @@ TRACE_EVENT(sched_switch, __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|", { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" }, { 16, "Z" }, { 32, "X" }, { 64, "x" }, - { 128, "W" }) : "R", + { 128, "K" }, { 256, "W" }, { 512, "P" }) : "R", __entry->prev_state & TASK_STATE_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); @@ -276,6 +277,32 @@ TRACE_EVENT(sched_process_fork, ); /* + * Tracepoint for exec: + */ +TRACE_EVENT(sched_process_exec, + + TP_PROTO(struct task_struct *p, pid_t old_pid, + struct linux_binprm *bprm), + + TP_ARGS(p, old_pid, bprm), + + TP_STRUCT__entry( + __string( filename, bprm->filename ) + __field( pid_t, pid ) + __field( pid_t, old_pid ) + ), + + TP_fast_assign( + __assign_str(filename, bprm->filename); + __entry->pid = p->pid; + __entry->old_pid = old_pid; + ), + + TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename), + __entry->pid, __entry->old_pid) +); + +/* * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE * adding sched_stat support to SCHED_FIFO/RR would be welcome. */ @@ -283,7 +310,7 @@ DECLARE_EVENT_CLASS(sched_stat_template, TP_PROTO(struct task_struct *tsk, u64 delay), - TP_ARGS(tsk, delay), + TP_ARGS(__perf_task(tsk), __perf_count(delay)), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) @@ -295,9 +322,6 @@ DECLARE_EVENT_CLASS(sched_stat_template, memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; __entry->delay = delay; - ) - TP_perf_assign( - __perf_count(delay); ), TP_printk("comm=%s pid=%d delay=%Lu [ns]", @@ -341,11 +365,11 @@ DEFINE_EVENT(sched_stat_template, sched_stat_blocked, * Tracepoint for accounting runtime (time the task is executing * on a CPU). */ -TRACE_EVENT(sched_stat_runtime, +DECLARE_EVENT_CLASS(sched_stat_runtime, TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime), - TP_ARGS(tsk, runtime, vruntime), + TP_ARGS(tsk, __perf_count(runtime), vruntime), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) @@ -359,9 +383,6 @@ TRACE_EVENT(sched_stat_runtime, __entry->pid = tsk->pid; __entry->runtime = runtime; __entry->vruntime = vruntime; - ) - TP_perf_assign( - __perf_count(runtime); ), TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]", @@ -370,85 +391,165 @@ TRACE_EVENT(sched_stat_runtime, (unsigned long long)__entry->vruntime) ); -#ifdef CREATE_TRACE_POINTS -static inline u64 trace_get_sleeptime(struct task_struct *tsk) -{ -#ifdef CONFIG_SCHEDSTATS - u64 block, sleep; - - block = tsk->se.statistics.block_start; - sleep = tsk->se.statistics.sleep_start; - tsk->se.statistics.block_start = 0; - tsk->se.statistics.sleep_start = 0; - - return block ? block : sleep ? sleep : 0; -#else - return 0; -#endif -} -#endif +DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime, + TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime), + TP_ARGS(tsk, runtime, vruntime)); /* - * Tracepoint for accounting sleeptime (time the task is sleeping - * or waiting for I/O). + * Tracepoint for showing priority inheritance modifying a tasks + * priority. */ -TRACE_EVENT(sched_stat_sleeptime, +TRACE_EVENT(sched_pi_setprio, - TP_PROTO(struct task_struct *tsk, u64 now), + TP_PROTO(struct task_struct *tsk, int newprio), - TP_ARGS(tsk, now), + TP_ARGS(tsk, newprio), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) - __field( u64, sleeptime ) + __field( int, oldprio ) + __field( int, newprio ) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; - __entry->sleeptime = trace_get_sleeptime(tsk); - __entry->sleeptime = __entry->sleeptime ? - now - __entry->sleeptime : 0; - ) - TP_perf_assign( - __perf_count(__entry->sleeptime); + __entry->oldprio = tsk->prio; + __entry->newprio = newprio; ), - TP_printk("comm=%s pid=%d sleeptime=%Lu [ns]", + TP_printk("comm=%s pid=%d oldprio=%d newprio=%d", __entry->comm, __entry->pid, - (unsigned long long)__entry->sleeptime) + __entry->oldprio, __entry->newprio) +); + +#ifdef CONFIG_DETECT_HUNG_TASK +TRACE_EVENT(sched_process_hang, + TP_PROTO(struct task_struct *tsk), + TP_ARGS(tsk), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + ), + + TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid) +); +#endif /* CONFIG_DETECT_HUNG_TASK */ + +DECLARE_EVENT_CLASS(sched_move_task_template, + + TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), + + TP_ARGS(tsk, src_cpu, dst_cpu), + + TP_STRUCT__entry( + __field( pid_t, pid ) + __field( pid_t, tgid ) + __field( pid_t, ngid ) + __field( int, src_cpu ) + __field( int, src_nid ) + __field( int, dst_cpu ) + __field( int, dst_nid ) + ), + + TP_fast_assign( + __entry->pid = task_pid_nr(tsk); + __entry->tgid = task_tgid_nr(tsk); + __entry->ngid = task_numa_group_id(tsk); + __entry->src_cpu = src_cpu; + __entry->src_nid = cpu_to_node(src_cpu); + __entry->dst_cpu = dst_cpu; + __entry->dst_nid = cpu_to_node(dst_cpu); + ), + + TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d", + __entry->pid, __entry->tgid, __entry->ngid, + __entry->src_cpu, __entry->src_nid, + __entry->dst_cpu, __entry->dst_nid) ); /* - * Tracepoint for showing priority inheritance modifying a tasks - * priority. + * Tracks migration of tasks from one runqueue to another. Can be used to + * detect if automatic NUMA balancing is bouncing between nodes */ -TRACE_EVENT(sched_pi_setprio, +DEFINE_EVENT(sched_move_task_template, sched_move_numa, + TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), - TP_PROTO(struct task_struct *tsk, int newprio), + TP_ARGS(tsk, src_cpu, dst_cpu) +); - TP_ARGS(tsk, newprio), +DEFINE_EVENT(sched_move_task_template, sched_stick_numa, + TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), + + TP_ARGS(tsk, src_cpu, dst_cpu) +); + +TRACE_EVENT(sched_swap_numa, + + TP_PROTO(struct task_struct *src_tsk, int src_cpu, + struct task_struct *dst_tsk, int dst_cpu), + + TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu), TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, oldprio ) - __field( int, newprio ) + __field( pid_t, src_pid ) + __field( pid_t, src_tgid ) + __field( pid_t, src_ngid ) + __field( int, src_cpu ) + __field( int, src_nid ) + __field( pid_t, dst_pid ) + __field( pid_t, dst_tgid ) + __field( pid_t, dst_ngid ) + __field( int, dst_cpu ) + __field( int, dst_nid ) ), TP_fast_assign( - memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); - __entry->pid = tsk->pid; - __entry->oldprio = tsk->prio; - __entry->newprio = newprio; + __entry->src_pid = task_pid_nr(src_tsk); + __entry->src_tgid = task_tgid_nr(src_tsk); + __entry->src_ngid = task_numa_group_id(src_tsk); + __entry->src_cpu = src_cpu; + __entry->src_nid = cpu_to_node(src_cpu); + __entry->dst_pid = task_pid_nr(dst_tsk); + __entry->dst_tgid = task_tgid_nr(dst_tsk); + __entry->dst_ngid = task_numa_group_id(dst_tsk); + __entry->dst_cpu = dst_cpu; + __entry->dst_nid = cpu_to_node(dst_cpu); ), - TP_printk("comm=%s pid=%d oldprio=%d newprio=%d", - __entry->comm, __entry->pid, - __entry->oldprio, __entry->newprio) + TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d", + __entry->src_pid, __entry->src_tgid, __entry->src_ngid, + __entry->src_cpu, __entry->src_nid, + __entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid, + __entry->dst_cpu, __entry->dst_nid) ); +/* + * Tracepoint for waking a polling cpu without an IPI. + */ +TRACE_EVENT(sched_wake_idle_without_ipi, + + TP_PROTO(int cpu), + + TP_ARGS(cpu), + + TP_STRUCT__entry( + __field( int, cpu ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + ), + + TP_printk("cpu=%d", __entry->cpu) +); #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ |