| Message ID | 1456256072-26003-1-git-send-email-kamal@canonical.com |
|---|---|
| State | New |
| Headers | show |
diff --git a/mm/vmstat.c b/mm/vmstat.c index f143e1d..eb4bc96 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1219,7 +1219,8 @@ int sysctl_stat_interval __read_mostly = HZ; static void vmstat_update(struct work_struct *w) { refresh_cpu_vm_stats(); - queue_delayed_work(vmstat_wq, &__get_cpu_var(vmstat_work), + queue_delayed_work_on(smp_processor_id(), vmstat_wq, + &__get_cpu_var(vmstat_work), round_jiffies_relative(sysctl_stat_interval)); }
This is a note to let you know that I have just added a patch titled vmstat: explicitly schedule per-cpu work on the CPU we need it to run on to the linux-3.13.y-queue branch of the 3.13.y-ckt extended stable tree which can be found at: http://kernel.ubuntu.com/git/ubuntu/linux.git/log/?h=linux-3.13.y-queue This patch is scheduled to be released in version 3.13.11-ckt36. If you, or anyone else, feels it should not be added to this tree, please reply to this email. For more information about the 3.13.y-ckt tree, see https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable Thanks. -Kamal ---8<------------------------------------------------------------ From c621c5b5fcc3e82d0a6c8a0e5c10b1ebf24ca5de Mon Sep 17 00:00:00 2001 From: Linus Torvalds <torvalds@linux-foundation.org> Date: Thu, 15 Oct 2015 13:01:50 -0700 Subject: vmstat: explicitly schedule per-cpu work on the CPU we need it to run on 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@linux.com> Cc: Tejun Heo <tj@kernel.org> Cc: Mike Galbraith <mgalbraith@suse.com> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jiri Slaby <jslaby@suse.cz> [ kamal: backport to 3.13-stable: use queue_delayed_work_on() ] Signed-off-by: Kamal Mostafa <kamal@canonical.com> --- mm/vmstat.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) -- 2.7.0