From f454c6940ed4bfc76670295534270ccebf366898 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Wed, 23 Apr 2014 01:09:04 +0300 Subject: [PATCH] drm/i915: get a runtime PM ref for the deferred GPU reset work Atm we can end up in the GPU reset deferred work in D3 state if the last runtime PM reference is dropped between detecting a hang/scheduling the work and executing the work. At least one such case I could trigger is the simulated reset via the i915_wedged debugfs entry. Fix this by getting an RPM reference around accessing the HW in the reset work. v2: - Instead of getting/putting the RPM reference in the reset work itself, get it already before scheduling the work. By this we also prevent going to D3 before the work gets to run, in addition to making sure that we run the work itself in D0. (Ville, Daniel) v3: - fix inverted logic fail when putting the RPM ref on behalf of a cancelled GPU reset work (Ville) v4: - Taking the RPM ref in the interrupt handler isn't really needed b/c it's already guaranteed that we hold an RPM ref until the end of the reset work in all cases we care about. So take the ref in the reset work (for cases like i915_wedged_set). (Daniel) Signed-off-by: Imre Deak Reviewed-by: Rodrigo Vivi Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 274c108dcb47..2446e61ea4d4 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2187,6 +2187,14 @@ static void i915_error_work_func(struct work_struct *work) kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE, reset_event); + /* + * In most cases it's guaranteed that we get here with an RPM + * reference held, for example because there is a pending GPU + * request that won't finish until the reset is done. This + * isn't the case at least when we get here by doing a + * simulated reset via debugs, so get an RPM reference. + */ + intel_runtime_pm_get(dev_priv); /* * All state reset _must_ be completed before we update the * reset counter, for otherwise waiters might miss the reset @@ -2197,6 +2205,8 @@ static void i915_error_work_func(struct work_struct *work) intel_display_handle_reset(dev); + intel_runtime_pm_put(dev_priv); + if (ret == 0) { /* * After all the gem state is reset, increment the reset