Commit e8901061 authored by Peter Zijlstra's avatar Peter Zijlstra

sched: Split DEQUEUE_SLEEP from deactivate_task()

As a preparation for dequeue_task() failing, and a second code-path
needing to take care of the 'success' path, split out the DEQEUE_SLEEP
path from deactivate_task().

Much thanks to Libo for spotting and fixing a TASK_ON_RQ_MIGRATING
ordering fail.
Fixed-by: default avatarLibo Chen <libo.chen@oracle.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: default avatarValentin Schneider <vschneid@redhat.com>
Tested-by: default avatarValentin Schneider <vschneid@redhat.com>
Link: https://lkml.kernel.org/r/20240727105029.086192709@infradead.org
parent fab4a808
...@@ -2036,12 +2036,23 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags) ...@@ -2036,12 +2036,23 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
void deactivate_task(struct rq *rq, struct task_struct *p, int flags) void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{ {
WRITE_ONCE(p->on_rq, (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING); WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
ASSERT_EXCLUSIVE_WRITER(p->on_rq); ASSERT_EXCLUSIVE_WRITER(p->on_rq);
/*
* Code explicitly relies on TASK_ON_RQ_MIGRATING begin set *before*
* dequeue_task() and cleared *after* enqueue_task().
*/
dequeue_task(rq, p, flags); dequeue_task(rq, p, flags);
} }
static void block_task(struct rq *rq, struct task_struct *p, int flags)
{
if (dequeue_task(rq, p, DEQUEUE_SLEEP | flags))
__block_task(rq, p);
}
/** /**
* task_curr - is this task currently executing on a CPU? * task_curr - is this task currently executing on a CPU?
* @p: the task in question. * @p: the task in question.
...@@ -6498,9 +6509,6 @@ static void __sched notrace __schedule(unsigned int sched_mode) ...@@ -6498,9 +6509,6 @@ static void __sched notrace __schedule(unsigned int sched_mode)
!(prev_state & TASK_NOLOAD) && !(prev_state & TASK_NOLOAD) &&
!(prev_state & TASK_FROZEN); !(prev_state & TASK_FROZEN);
if (prev->sched_contributes_to_load)
rq->nr_uninterruptible++;
/* /*
* __schedule() ttwu() * __schedule() ttwu()
* prev_state = prev->state; if (p->on_rq && ...) * prev_state = prev->state; if (p->on_rq && ...)
...@@ -6512,12 +6520,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) ...@@ -6512,12 +6520,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
* *
* After this, schedule() must not care about p->state any more. * After this, schedule() must not care about p->state any more.
*/ */
deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK); block_task(rq, prev, DEQUEUE_NOCLOCK);
if (prev->in_iowait) {
atomic_inc(&rq->nr_iowait);
delayacct_blkio_start();
}
} }
switch_count = &prev->nvcsw; switch_count = &prev->nvcsw;
} }
......
...@@ -68,6 +68,7 @@ ...@@ -68,6 +68,7 @@
#include <linux/wait_api.h> #include <linux/wait_api.h>
#include <linux/wait_bit.h> #include <linux/wait_bit.h>
#include <linux/workqueue_api.h> #include <linux/workqueue_api.h>
#include <linux/delayacct.h>
#include <trace/events/power.h> #include <trace/events/power.h>
#include <trace/events/sched.h> #include <trace/events/sched.h>
...@@ -2585,6 +2586,19 @@ static inline void sub_nr_running(struct rq *rq, unsigned count) ...@@ -2585,6 +2586,19 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
sched_update_tick_dependency(rq); sched_update_tick_dependency(rq);
} }
static inline void __block_task(struct rq *rq, struct task_struct *p)
{
WRITE_ONCE(p->on_rq, 0);
ASSERT_EXCLUSIVE_WRITER(p->on_rq);
if (p->sched_contributes_to_load)
rq->nr_uninterruptible++;
if (p->in_iowait) {
atomic_inc(&rq->nr_iowait);
delayacct_blkio_start();
}
}
extern void activate_task(struct rq *rq, struct task_struct *p, int flags); extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment