iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sched/psi: Update poll => rtpoll in relevant comments

Browse Source 
The PSI trigger code is now making a distinction between privileged and
unprivileged triggers, after the following commit:

 65457b74aa94 ("sched/psi: Rename existing poll members in preparation")

But some comments have not been modified along with the code, so they
need to be updated.

This will help readers better understand the code.

Signed-off-by: Fan Yu <fan.yu9@zte.com.cn>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Peter Ziljstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/202310161920399921184@zte.com.cn
This commit is contained in:
Fan Yu 2023-10-16 19:20:39 +08:00 committed by Ingo Molnar
parent 1b8a955dd3
commit 7b3d8df549
1 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
kernel/sched/psi.c
View File

@ -596,7 +596,7 @@ static void init_rtpoll_triggers(struct psi_group *group, u64 now)
group->rtpoll_next_update = now + group->rtpoll_min_period; group->rtpoll_next_update = now + group->rtpoll_min_period;
} }
/* Schedule polling if it's not already scheduled or forced. */ /* Schedule rtpolling if it's not already scheduled or forced. */
static void psi_schedule_rtpoll_work(struct psi_group *group, unsigned long delay, static void psi_schedule_rtpoll_work(struct psi_group *group, unsigned long delay,
bool force) bool force)
{ {
@ -636,37 +636,37 @@ static void psi_rtpoll_work(struct psi_group *group)
if (now > group->rtpoll_until) { if (now > group->rtpoll_until) {
/* /*
* We are either about to start or might stop polling if no * We are either about to start or might stop rtpolling if no
* state change was recorded. Resetting poll_scheduled leaves * state change was recorded. Resetting rtpoll_scheduled leaves
* a small window for psi_group_change to sneak in and schedule * a small window for psi_group_change to sneak in and schedule
* an immediate poll_work before we get to rescheduling. One * an immediate rtpoll_work before we get to rescheduling. One
* potential extra wakeup at the end of the polling window * potential extra wakeup at the end of the rtpolling window
* should be negligible and polling_next_update still keeps * should be negligible and rtpoll_next_update still keeps
* updates correctly on schedule. * updates correctly on schedule.
*/ */
atomic_set(&group->rtpoll_scheduled, 0); atomic_set(&group->rtpoll_scheduled, 0);
/* /*
* A task change can race with the poll worker that is supposed to * A task change can race with the rtpoll worker that is supposed to
* report on it. To avoid missing events, ensure ordering between * report on it. To avoid missing events, ensure ordering between
* poll_scheduled and the task state accesses, such that if the poll * rtpoll_scheduled and the task state accesses, such that if the
* worker misses the state update, the task change is guaranteed to * rtpoll worker misses the state update, the task change is
* reschedule the poll worker: * guaranteed to reschedule the rtpoll worker:
* *
* poll worker: * rtpoll worker:
* atomic_set(poll_scheduled, 0) * atomic_set(rtpoll_scheduled, 0)
* smp_mb() * smp_mb()
* LOAD states * LOAD states
* *
* task change: * task change:
* STORE states * STORE states
* if atomic_xchg(poll_scheduled, 1) == 0: * if atomic_xchg(rtpoll_scheduled, 1) == 0:
* schedule poll worker * schedule rtpoll worker
* *
* The atomic_xchg() implies a full barrier. * The atomic_xchg() implies a full barrier.
*/ */
smp_mb(); smp_mb();
} else { } else {
/* Polling window is not over, keep rescheduling */ /* The rtpolling window is not over, keep rescheduling */
force_reschedule = true; force_reschedule = true;
} }
@ -674,7 +674,7 @@ static void psi_rtpoll_work(struct psi_group *group)
collect_percpu_times(group, PSI_POLL, &changed_states); collect_percpu_times(group, PSI_POLL, &changed_states);
if (changed_states & group->rtpoll_states) { if (changed_states & group->rtpoll_states) {
/* Initialize trigger windows when entering polling mode */ /* Initialize trigger windows when entering rtpolling mode */
if (now > group->rtpoll_until) if (now > group->rtpoll_until)
init_rtpoll_triggers(group, now); init_rtpoll_triggers(group, now);