| Message ID | 20181212134149.26981-5-chris@chris-wilson.co.uk (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [01/19] drm/i915: Return immediately if trylock fails for direct-reclaim | expand |
On 12/12/2018 13:41, Chris Wilson wrote: > After declaring a terminally wedged device, we allow ourselves to > recover on the next GPU reset (manually triggered), or resume. Check > that resetting a wedged device does work. > > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> > Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> > --- > .../gpu/drm/i915/selftests/intel_hangcheck.c | 23 +++++++++++++++++++ > 1 file changed, 23 insertions(+) > > diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c > index 805e40aff407..65c318d14077 100644 > --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c > +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c > @@ -385,6 +385,28 @@ static int igt_global_reset(void *arg) > return err; > } > > +static int igt_wedged_reset(void *arg) > +{ > + struct drm_i915_private *i915 = arg; > + > + /* Check that we can recover a wedged device with a GPU reset */ > + > + igt_global_reset_lock(i915); > + mutex_lock(&i915->drm.struct_mutex); > + > + i915_gem_set_wedged(i915); > + GEM_BUG_ON(!i915_terminally_wedged(&i915->gpu_error)); > + > + set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags); > + i915_reset(i915, ALL_ENGINES, NULL); > + GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags)); > + > + mutex_unlock(&i915->drm.struct_mutex); > + igt_global_reset_unlock(i915); > + > + return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0; > +} > + > static bool wait_for_idle(struct intel_engine_cs *engine) > { > return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0; > @@ -1452,6 +1474,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915) > { > static const struct i915_subtest tests[] = { > SUBTEST(igt_global_reset), /* attempt to recover GPU first */ > + SUBTEST(igt_wedged_reset), > SUBTEST(igt_hang_sanitycheck), > SUBTEST(igt_reset_idle_engine), > SUBTEST(igt_reset_active_engine), > Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Regards, Tvrtko
On 12/12/2018 13:41, Chris Wilson wrote: > After declaring a terminally wedged device, we allow ourselves to > recover on the next GPU reset (manually triggered), or resume. Check > that resetting a wedged device does work. > > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> > Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> > --- > .../gpu/drm/i915/selftests/intel_hangcheck.c | 23 +++++++++++++++++++ > 1 file changed, 23 insertions(+) > > diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c > index 805e40aff407..65c318d14077 100644 > --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c > +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c > @@ -385,6 +385,28 @@ static int igt_global_reset(void *arg) > return err; > } > > +static int igt_wedged_reset(void *arg) > +{ > + struct drm_i915_private *i915 = arg; > + > + /* Check that we can recover a wedged device with a GPU reset */ > + > + igt_global_reset_lock(i915); > + mutex_lock(&i915->drm.struct_mutex); rpm get? > + > + i915_gem_set_wedged(i915); > + GEM_BUG_ON(!i915_terminally_wedged(&i915->gpu_error)); > + > + set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags); > + i915_reset(i915, ALL_ENGINES, NULL); > + GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags)); > + > + mutex_unlock(&i915->drm.struct_mutex); > + igt_global_reset_unlock(i915); > + > + return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0; > +} > + > static bool wait_for_idle(struct intel_engine_cs *engine) > { > return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0; > @@ -1452,6 +1474,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915) > { > static const struct i915_subtest tests[] = { > SUBTEST(igt_global_reset), /* attempt to recover GPU first */ > + SUBTEST(igt_wedged_reset), > SUBTEST(igt_hang_sanitycheck), > SUBTEST(igt_reset_idle_engine), > SUBTEST(igt_reset_active_engine), >
Quoting Tvrtko Ursulin (2018-12-13 08:28:54) > > On 12/12/2018 13:41, Chris Wilson wrote: > > After declaring a terminally wedged device, we allow ourselves to > > recover on the next GPU reset (manually triggered), or resume. Check > > that resetting a wedged device does work. > > > > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> > > Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> > > --- > > .../gpu/drm/i915/selftests/intel_hangcheck.c | 23 +++++++++++++++++++ > > 1 file changed, 23 insertions(+) > > > > diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c > > index 805e40aff407..65c318d14077 100644 > > --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c > > +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c > > @@ -385,6 +385,28 @@ static int igt_global_reset(void *arg) > > return err; > > } > > > > +static int igt_wedged_reset(void *arg) > > +{ > > + struct drm_i915_private *i915 = arg; > > + > > + /* Check that we can recover a wedged device with a GPU reset */ > > + > > + igt_global_reset_lock(i915); > > + mutex_lock(&i915->drm.struct_mutex); > > rpm get? True. -Chris
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c index 805e40aff407..65c318d14077 100644 --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c @@ -385,6 +385,28 @@ static int igt_global_reset(void *arg) return err; } +static int igt_wedged_reset(void *arg) +{ + struct drm_i915_private *i915 = arg; + + /* Check that we can recover a wedged device with a GPU reset */ + + igt_global_reset_lock(i915); + mutex_lock(&i915->drm.struct_mutex); + + i915_gem_set_wedged(i915); + GEM_BUG_ON(!i915_terminally_wedged(&i915->gpu_error)); + + set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags); + i915_reset(i915, ALL_ENGINES, NULL); + GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags)); + + mutex_unlock(&i915->drm.struct_mutex); + igt_global_reset_unlock(i915); + + return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0; +} + static bool wait_for_idle(struct intel_engine_cs *engine) { return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0; @@ -1452,6 +1474,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(igt_global_reset), /* attempt to recover GPU first */ + SUBTEST(igt_wedged_reset), SUBTEST(igt_hang_sanitycheck), SUBTEST(igt_reset_idle_engine), SUBTEST(igt_reset_active_engine),
After declaring a terminally wedged device, we allow ourselves to recover on the next GPU reset (manually triggered), or resume. Check that resetting a wedged device does work. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> --- .../gpu/drm/i915/selftests/intel_hangcheck.c | 23 +++++++++++++++++++ 1 file changed, 23 insertions(+)