From fa2c3254d7cfff5f7a916ab928a562d1165f17bb Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 20 Jan 2022 16:25:19 +0000 Subject: sched/tracing: Don't re-read p->state when emitting sched_switch event As of commit c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") the following sequence becomes possible: p->__state = TASK_INTERRUPTIBLE; __schedule() deactivate_task(p); ttwu() READ !p->on_rq p->__state=TASK_WAKING trace_sched_switch() __trace_sched_switch_state() task_state_index() return 0; TASK_WAKING isn't in TASK_REPORT, so the task appears as TASK_RUNNING in the trace event. Prevent this by pushing the value read from __schedule() down the trace event. Reported-by: Abhijeet Dharmapurikar Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20220120162520.570782-2-valentin.schneider@arm.com --- include/linux/sched.h | 11 ++++++++--- include/trace/events/sched.h | 11 +++++++---- 2 files changed, 15 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index f00132e7ef6e..457c8a058b77 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1620,10 +1620,10 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) -static inline unsigned int task_state_index(struct task_struct *tsk) +static inline unsigned int __task_state_index(unsigned int tsk_state, + unsigned int tsk_exit_state) { - unsigned int tsk_state = READ_ONCE(tsk->__state); - unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); @@ -1633,6 +1633,11 @@ static inline unsigned int task_state_index(struct task_struct *tsk) return fls(state); } +static inline unsigned int task_state_index(struct task_struct *tsk) +{ + return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); +} + static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 94640482cfe7..65e786756321 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -187,7 +187,9 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, TP_ARGS(p)); #ifdef CREATE_TRACE_POINTS -static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p) +static inline long __trace_sched_switch_state(bool preempt, + unsigned int prev_state, + struct task_struct *p) { unsigned int state; @@ -208,7 +210,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * * it for left shift operation to get the correct task->state * mapping. */ - state = task_state_index(p); + state = __task_state_index(prev_state, p->exit_state); return state ? (1 << (state - 1)) : state; } @@ -220,10 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, + unsigned int prev_state, struct task_struct *prev, struct task_struct *next), - TP_ARGS(preempt, prev, next), + TP_ARGS(preempt, prev_state, prev, next), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) @@ -239,7 +242,7 @@ TRACE_EVENT(sched_switch, memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; - __entry->prev_state = __trace_sched_switch_state(preempt, prev); + __entry->prev_state = __trace_sched_switch_state(preempt, prev_state, prev); memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); __entry->next_pid = next->pid; __entry->next_prio = next->prio; -- cgit v1.2.3