[Bug 56691] New: Using Intel Pstates driver causes panics during high loads

[Bug 56691] New: Using Intel Pstates driver causes panics during high loads

[bugzilla-daemon]

https://bugzilla.kernel.org/show_bug.cgi?id=56691

           Summary: Using Intel Pstates driver causes panics during high
                    loads
           Product: Power Management
           Version: 2.5
    Kernel Version: 3.9-rc
          Platform: All
        OS/Version: Linux
              Tree: Mainline
            Status: NEW
          Severity: normal
          Priority: P1
         Component: cpufreq
        AssignedTo: cpufreq@vger.kernel.org
        ReportedBy: mike@fireburn.co.uk
                CC: rui.zhang@intel.com
        Regression: No


I've already had a conversation via email with Zhang about this

The driver has been broken throughout the 3.9 rc series

As the issue only manifests during high loads after long periods of time I've
been able to bisect the issue

I've taken screenshots of the panics

Disabling the pstates driver stops the panics

The first snapshots date back to the 7th March but the issue was noticed before
this

I update from Linus' tree nightly

-- 
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.

[Bug 56691] Using Intel Pstates driver causes panics during high loads

[bugzilla-daemon]

https://bugzilla.kernel.org/show_bug.cgi?id=56691





--- Comment #1 from Mike Lothian <mike@fireburn.co.uk>  2013-04-16 17:34:59 ---
Created an attachment (id=98881)
 --> (https://bugzilla.kernel.org/attachment.cgi?id=98881)
Panic Screenshots

-- 
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.

[Bug 56691] Using Intel Pstates driver causes panics during high loads

[bugzilla-daemon]

https://bugzilla.kernel.org/show_bug.cgi?id=56691


Dirk Brandewie <dirk.brandewie@gmail.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |dirk.brandewie@gmail.com




--- Comment #2 from Dirk Brandewie <dirk.brandewie@gmail.com>  2013-04-16 17:45:39 ---
This is the same bug as reported by Redhat 
https://bugzilla.redhat.com/show_bug.cgi?id=952244

I took a long time to reproduce and catch it in the act and get debug info :-(

The fix missed rc6 by a few hours but is in rc7. 

--Dirk
Author: Dirk Brandewie <dirk.brandewie@gmail.com>  2013-04-04 10:35:35
Committer: Rafael J. Wysocki <rafael.j.wysocki@intel.com>  2013-04-08 13:09:23
Parent: 05e99c8cf9d4e53ef6e016815db40a89a6156529 (intel-pstate: Use #defines
instead of hard-coded values.)
Branches: master, pstate, pstate.stgit, remotes/linux-pm/bleeding-edge,
remotes/linux-pm/fixes, remotes/linux-pm/linux-next, remotes/next/akpm,
remotes/next/akpm-base, remotes/next/master, remotes/next/stable,
remotes/origin/master, test_next
Follows: v3.9-rc6
Precedes: pm-3.9-rc7

    cpufreq / intel_pstate: Set timer timeout correctly

    The current calculation of the delay time is wrong and a cut and
    paste error from a previous experimental driver.  This can result in
    the timeout being set to jiffies + 1 which setup the driver to race
    with itself if the APIC timer interrupt happens at just the right
    time.

    References: https://bugzilla.redhat.com/show_bug.cgi?id=920289
    Reported-by: Adam Williamson <awilliam@redhat.com>
    Reported-and-tested-by: Parag Warudkar <parag.lkml@gmail.com>
    Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com>
    Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

------------------------ drivers/cpufreq/intel_pstate.c
------------------------
index ad72922..6133ef5 100644
@@ -502,7 +502,6 @@ static inline void intel_pstate_set_sample_time(struct
cpudata *cpu)

     sample_time = cpu->pstate_policy->sample_rate_ms;
     delay = msecs_to_jiffies(sample_time);
-    delay -= jiffies % delay;
     mod_timer_pinned(&cpu->timer, jiffies + delay);
 }

-- 
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.

[Bug 56691] Using Intel Pstates driver causes panics during high loads

[bugzilla-daemon]

https://bugzilla.kernel.org/show_bug.cgi?id=56691





--- Comment #3 from Mike Lothian <mike@fireburn.co.uk>  2013-04-16 18:03:20 ---
Sorry I didn't notice that commit 

I'll turn pstates back on and see if I have any issues

-- 
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.

[Bug 56691] Using Intel Pstates driver causes panics during high loads

[bugzilla-daemon]

https://bugzilla.kernel.org/show_bug.cgi?id=56691


Lan Tianyu <tianyu.lan@intel.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |tianyu.lan@intel.com
         AssignedTo|cpufreq@vger.kernel.org     |tianyu.lan@intel.com




-- 
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.