Handle NR_lazy in resched_curr(), by registering an intent to
reschedule at exit-to-user.
Given that the rescheduling is not imminent, skip the preempt folding
and the resched IPI.
Also, update set_nr_and_not_polling() to handle NR_lazy. Note that
there are no changes to set_nr_if_polling(), since lazy rescheduling
is not meaningful for idle.
And finally, now that there are two need-resched bits, enforce a
priority order while setting them.
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Originally-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/87jzshhexi.ffs@tglx/
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
kernel/sched/core.c | 41 +++++++++++++++++++++++++++++------------
1 file changed, 29 insertions(+), 12 deletions(-)
@@ -899,14 +899,14 @@ static inline void hrtick_rq_init(struct rq *rq)
#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
/*
- * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
+ * Atomically set TIF_NEED_RESCHED[_LAZY] and test for TIF_POLLING_NRFLAG,
* this avoids any races wrt polling state changes and thereby avoids
* spurious IPIs.
*/
-static inline bool set_nr_and_not_polling(struct task_struct *p)
+static inline bool set_nr_and_not_polling(struct task_struct *p, resched_t rs)
{
struct thread_info *ti = task_thread_info(p);
- return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
+ return !(fetch_or(&ti->flags, _tif_resched(rs)) & _TIF_POLLING_NRFLAG);
}
/*
@@ -931,9 +931,9 @@ static bool set_nr_if_polling(struct task_struct *p)
}
#else
-static inline bool set_nr_and_not_polling(struct task_struct *p)
+static inline bool set_nr_and_not_polling(struct task_struct *p, resched_t rs)
{
- set_tsk_need_resched(p, NR_now);
+ set_tsk_need_resched(p, rs);
return true;
}
@@ -1041,25 +1041,40 @@ void wake_up_q(struct wake_q_head *head)
void resched_curr(struct rq *rq)
{
struct task_struct *curr = rq->curr;
+ resched_t rs = NR_now;
int cpu;
lockdep_assert_rq_held(rq);
- if (test_tsk_need_resched(curr, NR_now))
+ /*
+ * TIF_NEED_RESCHED is the higher priority bit, so if it is already
+ * set, nothing more to be done. So, the only combinations we want to
+ * let in are:
+ *
+ * - . + (NR_now | NR_lazy)
+ * - NR_lazy + NR_now
+ *
+ * In the second case both flags would be set simultaneously.
+ */
+ if (test_tsk_need_resched(curr, NR_now) ||
+ (rs == NR_lazy && test_tsk_need_resched(curr, NR_lazy)))
return;
cpu = cpu_of(rq);
if (cpu == smp_processor_id()) {
- set_tsk_need_resched(curr, NR_now);
- set_preempt_need_resched();
+ set_tsk_need_resched(curr, rs);
+ if (rs == NR_now)
+ set_preempt_need_resched();
return;
}
- if (set_nr_and_not_polling(curr))
- smp_send_reschedule(cpu);
- else
+ if (set_nr_and_not_polling(curr, rs)) {
+ if (rs == NR_now)
+ smp_send_reschedule(cpu);
+ } else {
trace_sched_wake_idle_without_ipi(cpu);
+ }
}
void resched_cpu(int cpu)
@@ -1154,7 +1169,7 @@ static void wake_up_idle_cpu(int cpu)
* and testing of the above solutions didn't appear to report
* much benefits.
*/
- if (set_nr_and_not_polling(rq->idle))
+ if (set_nr_and_not_polling(rq->idle, NR_now))
smp_send_reschedule(cpu);
else
trace_sched_wake_idle_without_ipi(cpu);
@@ -6693,6 +6708,8 @@ static void __sched notrace __schedule(unsigned int sched_mode)
}
next = pick_next_task(rq, prev, &rf);
+
+ /* Clear both TIF_NEED_RESCHED, TIF_NEED_RESCHED_LAZY */
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
#ifdef CONFIG_SCHED_DEBUG