diff options
author | Chris Wilson <chris@chris-wilson.co.uk> | 2018-03-07 08:42:26 -0500 |
---|---|---|
committer | Joonas Lahtinen <joonas.lahtinen@linux.intel.com> | 2018-03-16 08:35:35 -0400 |
commit | 73e2232aa3253d77935112bfc218700f6a2f1000 (patch) | |
tree | e7cd5ca947a0e1df1bd4e1ef8abdb794945a2e3c /drivers | |
parent | 7e9d3a4a1b21fd8a595774697f4047e7505deea6 (diff) |
drm/i915: Only call tasklet_kill() on the first prepare_reset
tasklet_kill() will spin waiting for the current tasklet to be executed.
However, if tasklet_disable() has been called, then the tasklet is never
executed but permanently put back onto the runlist until
tasklet_enable() is called. Ergo, we cannot use tasklet_kill() inside a
disable/enable pair. This is the case when we call set-wedge from inside
i915_reset(), and another request was submitted to us concurrent to the
reset.
Fixes: 963ddd63c314 ("drm/i915: Suspend submission tasklets around wedging")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180307134226.25492-6-chris@chris-wilson.co.uk
(cherry picked from commit 68ad361285a9cc73b259f59adbaafde196c15987)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/gpu/drm/i915/i915_gem.c | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 8d913d833ab9..0359d6f870b4 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c | |||
@@ -2940,8 +2940,16 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine) | |||
2940 | * calling engine->init_hw() and also writing the ELSP. | 2940 | * calling engine->init_hw() and also writing the ELSP. |
2941 | * Turning off the execlists->tasklet until the reset is over | 2941 | * Turning off the execlists->tasklet until the reset is over |
2942 | * prevents the race. | 2942 | * prevents the race. |
2943 | * | ||
2944 | * Note that this needs to be a single atomic operation on the | ||
2945 | * tasklet (flush existing tasks, prevent new tasks) to prevent | ||
2946 | * a race between reset and set-wedged. It is not, so we do the best | ||
2947 | * we can atm and make sure we don't lock the machine up in the more | ||
2948 | * common case of recursively being called from set-wedged from inside | ||
2949 | * i915_reset. | ||
2943 | */ | 2950 | */ |
2944 | tasklet_kill(&engine->execlists.tasklet); | 2951 | if (!atomic_read(&engine->execlists.tasklet.count)) |
2952 | tasklet_kill(&engine->execlists.tasklet); | ||
2945 | tasklet_disable(&engine->execlists.tasklet); | 2953 | tasklet_disable(&engine->execlists.tasklet); |
2946 | 2954 | ||
2947 | /* | 2955 | /* |