diff options
| author | Valentin Schneider <valentin.schneider@arm.com> | 2022-01-20 17:25:19 +0100 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2022-03-01 16:18:39 +0100 |
| commit | fa2c3254d7cfff5f7a916ab928a562d1165f17bb (patch) | |
| tree | 678cc10a62564212f526fc4a65ea345fde95794e /include/trace/events/sched.h | |
| parent | sched/rt: Plug rt_mutex_setprio() vs push_rt_task() race (diff) | |
| download | linux-fa2c3254d7cfff5f7a916ab928a562d1165f17bb.tar.xz linux-fa2c3254d7cfff5f7a916ab928a562d1165f17bb.zip | |
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 <adharmap@quicinc.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20220120162520.570782-2-valentin.schneider@arm.com
Diffstat (limited to 'include/trace/events/sched.h')
| -rw-r--r-- | include/trace/events/sched.h | 11 |
1 files changed, 7 insertions, 4 deletions
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; |