Messages in this thread | | | Subject | Re: [PATCH 3.0] perf,x86: fix kernel crash with PEBS/BTS after suspend/resume | From | Ben Hutchings <> | Date | Thu, 21 Mar 2013 02:41:46 +0000 |
| |
On Fri, 2013-03-15 at 18:57 -0600, Shuah Khan wrote: > This patch fixes a kernel crash when using precise sampling (PEBS) > after a suspend/resume. Turns out the CPU notifier code is not invoked > on CPU0 (BP). Therefore, the DS_AREA (used by PEBS) is not restored properly > by the kernel and keeps it power-on/resume value of 0 causing any PEBS > measurement to crash when running on CPU0. > > The workaround is to add a hook in the actual resume code to restore > the DS Area MSR value. It is invoked for all CPUS. So for all but CPU0, > the DS_AREA will be restored twice but this is harmless. > > Upstream commit id: 1d9d8639c063caf6efc2447f5f26aa637f844ff6 > > Reported-by: Linus Torvalds <torvalds@linux-foundation.org> > Signed-off-by: Stephane Eranian <eranian@google.com> > Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> > Signed-off-by: Shuah Khan <shuah.khan@hp.com> > CC: stable@vger.kernel.org 3.0 [...]
I've queued this up for 3.2 (though context was different again), along with the following fix-ups:
commit 2a6e06b2aed6995af401dcd4feb5e79a0c7ea554 Author: Linus Torvalds <torvalds@linux-foundation.org> Date: Sun Mar 17 15:44:43 2013 -0700
perf,x86: fix wrmsr_on_cpu() warning on suspend/resume
commit 6c4d3bc99b3341067775efd4d9d13cc8e655fd7c Author: David Rientjes <rientjes@google.com> Date: Sun Mar 17 15:49:10 2013 -0700
perf,x86: fix link failure for non-Intel configs
Ben.
-- Ben Hutchings It is easier to write an incorrect program than to understand a correct one. [unhandled content-type:application/pgp-signature] | |