summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-10-15 13:01:50 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-10-15 13:01:50 -0700
commit176bed1de5bf977938cad26551969eca8f0883b1 (patch)
tree45adb32e0c98e146ada11f1db777dfd0eced1bbc /mm
parent995e2fe9a4904c0b83c4eead7db42f5d52b09a85 (diff)
vmstat: explicitly schedule per-cpu work on the CPU we need it to run on
The vmstat code uses "schedule_delayed_work_on()" to do the initial startup of the delayed work on the right CPU, but then once it was started it would use the non-cpu-specific "schedule_delayed_work()" to re-schedule it on that CPU. That just happened to schedule it on the same CPU historically (well, in almost all situations), but the code _requires_ this work to be per-cpu, and should say so explicitly rather than depend on the non-cpu-specific scheduling to schedule on the current CPU. The timer code is being changed to not be as single-minded in always running things on the calling CPU. See also commit 874bbfe600a6 ("workqueue: make sure delayed work run in local cpu") that for now maintains the local CPU guarantees just in case there are other broken users that depended on the accidental behavior. Cc: Christoph Lameter <cl@linux.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/vmstat.c7
1 files changed, 4 insertions, 3 deletions
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4f5cd974e11a..fbf14485a049 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1363,15 +1363,16 @@ static cpumask_var_t cpu_stat_off;
static void vmstat_update(struct work_struct *w)
{
- if (refresh_cpu_vm_stats())
+ if (refresh_cpu_vm_stats()) {
/*
* Counters were updated so we expect more updates
* to occur in the future. Keep on running the
* update worker thread.
*/
- schedule_delayed_work(this_cpu_ptr(&vmstat_work),
+ schedule_delayed_work_on(smp_processor_id(),
+ this_cpu_ptr(&vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
- else {
+ } else {
/*
* We did not update any counters so the app may be in
* a mode where it does not cause counter updates.