From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.
===============
commit 176bed1de5bf977938cad26551969eca8f0883b1 upstream.
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.
js: 3.12 backport
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Jiri Slaby <jslaby@xxxxxxx>
---
mm/vmstat.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f7ca04482299..1dbd89d2fb9c 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1221,7 +1221,8 @@ int sysctl_stat_interval __read_mostly = HZ;
static void vmstat_update(struct work_struct *w)
{
refresh_cpu_vm_stats();
- schedule_delayed_work(&__get_cpu_var(vmstat_work),
+ schedule_delayed_work_on(smp_processor_id(),
+ &__get_cpu_var(vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
}
--
2.7.1
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html