Commit fa2c3254 authored by Valentin Schneider's avatar Valentin Schneider Committed by Peter Zijlstra
Browse files

sched/tracing: Don't re-read p->state when emitting sched_switch event 



As of commit

  c6e7bd7a ("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: default avatarAbhijeet Dharmapurikar <adharmap@quicinc.com>
Signed-off-by: default avatarValentin Schneider <valentin.schneider@arm.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: default avatarSteven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20220120162520.570782-2-valentin.schneider@arm.com
parent 49bef33e

include/linux/sched.h

+8 −3
Original line number Diff line number Diff line
@@ -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";

include/trace/events/sched.h

+7 −4
Original line number Diff line number Diff line
@@ -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;

kernel/sched/core.c

+2 −2
Original line number Diff line number Diff line
@@ -4836,7 +4836,7 @@ static struct rq *finish_task_switch(struct task_struct *prev) 
{

	struct rq *rq = this_rq();

	struct mm_struct *mm = rq->prev_mm;

	long prev_state;

	unsigned int prev_state;



	/*

	 * The previous task will have left us with a preempt_count of 2
@@ -6300,7 +6300,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) 
		migrate_disable_switch(rq, prev);

		psi_sched_switch(prev, next, !task_on_rq_queued(prev));



		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);

		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);



		/* Also unlocks the rq: */

		rq = context_switch(rq, prev, next, &rf);

kernel/trace/fgraph.c

+3 −1
Original line number Diff line number Diff line
@@ -415,7 +415,9 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) 


static void

ftrace_graph_probe_sched_switch(void *ignore, bool preempt,

			struct task_struct *prev, struct task_struct *next)

				unsigned int prev_state,

				struct task_struct *prev,

				struct task_struct *next)

{

	unsigned long long timestamp;

	int index;

kernel/trace/ftrace.c

+3 −1
Original line number Diff line number Diff line
@@ -7347,7 +7347,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) 


static void

ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,

		    struct task_struct *prev, struct task_struct *next)

				     unsigned int prev_state,

				     struct task_struct *prev,

				     struct task_struct *next)

{

	struct trace_array *tr = data;

	struct trace_pid_list *pid_list;