summaryrefslogtreecommitdiff
path: root/kernel/sched/stats.h
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2024-10-14 10:43:58 -0400
committerPeter Zijlstra <peterz@infradead.org>2024-10-26 09:28:38 +0200
commit1a6151017ee5a30cb2d959f110ab18fc49646467 (patch)
treeab5da0a6713ba7af603e1eae7bd7c9860f65bb2f /kernel/sched/stats.h
parent23f1178ad706a1aa69ac3dfaa6559f1fb876c14e (diff)
downloadlinux-next-1a6151017ee5a30cb2d959f110ab18fc49646467.tar.gz
linux-next-1a6151017ee5a30cb2d959f110ab18fc49646467.zip
sched: psi: pass enqueue/dequeue flags to psi callbacks directly
What psi needs to do on each enqueue and dequeue has gotten more subtle, and the generic sched code trying to distill this into a bool for the callbacks is awkward. Pass the flags directly and let psi parse them. For that to work, the #include "stats.h" (which has the psi callback implementations) needs to be below the flag definitions in "sched.h". Move that section further down, next to some of the other accounting stuff. This also puts the ENQUEUE_SAVE/RESTORE branch behind the psi jump label, slightly reducing overhead when PSI=y but runtime disabled. Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20241014144358.GB1021@cmpxchg.org
Diffstat (limited to 'kernel/sched/stats.h')
-rw-r--r--kernel/sched/stats.h29
1 files changed, 19 insertions, 10 deletions
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 767e098a3bd1..8ee0add5a48a 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -127,21 +127,25 @@ static inline void psi_account_irqtime(struct rq *rq, struct task_struct *curr,
* go through migration requeues. In this case, *sleeping* states need
* to be transferred.
*/
-static inline void psi_enqueue(struct task_struct *p, bool migrate)
+static inline void psi_enqueue(struct task_struct *p, int flags)
{
int clear = 0, set = 0;
if (static_branch_likely(&psi_disabled))
return;
+ /* Same runqueue, nothing changed for psi */
+ if (flags & ENQUEUE_RESTORE)
+ return;
+
if (p->se.sched_delayed) {
/* CPU migration of "sleeping" task */
- SCHED_WARN_ON(!migrate);
+ SCHED_WARN_ON(!(flags & ENQUEUE_MIGRATED));
if (p->in_memstall)
set |= TSK_MEMSTALL;
if (p->in_iowait)
set |= TSK_IOWAIT;
- } else if (migrate) {
+ } else if (flags & ENQUEUE_MIGRATED) {
/* CPU migration of runnable task */
set = TSK_RUNNING;
if (p->in_memstall)
@@ -158,17 +162,14 @@ static inline void psi_enqueue(struct task_struct *p, bool migrate)
psi_task_change(p, clear, set);
}
-static inline void psi_dequeue(struct task_struct *p, bool migrate)
+static inline void psi_dequeue(struct task_struct *p, int flags)
{
if (static_branch_likely(&psi_disabled))
return;
- /*
- * When migrating a task to another CPU, clear all psi
- * state. The enqueue callback above will work it out.
- */
- if (migrate)
- psi_task_change(p, p->psi_flags, 0);
+ /* Same runqueue, nothing changed for psi */
+ if (flags & DEQUEUE_SAVE)
+ return;
/*
* A voluntary sleep is a dequeue followed by a task switch. To
@@ -176,6 +177,14 @@ static inline void psi_dequeue(struct task_struct *p, bool migrate)
* TSK_RUNNING and TSK_IOWAIT for us when it moves TSK_ONCPU.
* Do nothing here.
*/
+ if (flags & DEQUEUE_SLEEP)
+ return;
+
+ /*
+ * When migrating a task to another CPU, clear all psi
+ * state. The enqueue callback above will work it out.
+ */
+ psi_task_change(p, p->psi_flags, 0);
}
static inline void psi_ttwu_dequeue(struct task_struct *p)