Messages in this thread | | | Subject | Re: [PATCH] sched,kvm: Fix KVM preempt_notifier usage | From | Paolo Bonzini <> | Date | Fri, 3 Jul 2015 17:46:06 +0200 |
| |
On 03/07/2015 17:42, Peter Zijlstra wrote: > On Fri, Jul 03, 2015 at 05:38:42PM +0200, Paolo Bonzini wrote: >> So basically this. Can you reply with SoB and maybe Acked-by? > > Ah, thanks for doing that! > >> ------------- 8< --------------- >> From: Peter Zijlstra <peterz@infradead.org> >> Subject: [PATCH] sched, preempt_notifier: separate notifier registration from static_key inc/dec >> >> Commit 1cde2930e154 ("sched/preempt: Add static_key() to preempt_notifiers") >> had two problems. First, the preempt-notifier API needs to sleep with the >> addition of the static_key, we do however need to hold off preemption >> while modifying the preempt notifier list, otherwise a preemption could >> observe an inconsistent list state. KVM correctly registers and >> unregisters preempt notifiers with preemption disabled, so the sleep >> caused dmesg splats. >> >> Second, KVM registers and unregisters preemption notifiers very often >> (in vcpu_load/vcpu_put). With a single uniprocessor guest the static key >> would move between 0 and 1 continuously, hitting the slow path on every >> userspace exit. >> >> To fix this, wrap the static_key inc/dec in a new API, and call it from >> KVM. >> >> Fixes: 1cde2930e154 ("sched/preempt: Add static_key() to preempt_notifiers") >> Reported-by: Pontus Fuchs <pontus.fuchs@gmail.com> >> Reported-by: Takashi Iwai <tiwai@suse.de> > > Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Ok, I'm crossing fingers and including this in my pull request in order to preserve bisectability. Thanks.
Paolo
| |