diff options
| -rw-r--r-- | drivers/gpu/drm/i915/i915_drv.c | 50 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/i915_drv.h | 5 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/i915_gem.c | 93 |
3 files changed, 110 insertions, 38 deletions
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index e5b31e29382c..2ecac000e5da 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1923,11 +1923,57 @@ error: * * Reset a specific GPU engine. Useful if a hang is detected. * Returns zero on successful reset or otherwise an error code. + * + * Procedure is: + * - identifies the request that caused the hang and it is dropped + * - reset engine (which will force the engine to idle) + * - re-init/configure engine */ int i915_reset_engine(struct intel_engine_cs *engine) { - /* FIXME: replace me with engine reset sequence */ - return -ENODEV; + struct i915_gpu_error *error = &engine->i915->gpu_error; + struct drm_i915_gem_request *active_request; + int ret; + + GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags)); + + DRM_DEBUG_DRIVER("resetting %s\n", engine->name); + + active_request = i915_gem_reset_prepare_engine(engine); + if (IS_ERR(active_request)) { + DRM_DEBUG_DRIVER("Previous reset failed, promote to full reset\n"); + ret = PTR_ERR(active_request); + goto out; + } + + /* + * The request that caused the hang is stuck on elsp, we know the + * active request and can drop it, adjust head to skip the offending + * request to resume executing remaining requests in the queue. + */ + i915_gem_reset_engine(engine, active_request); + + /* Finally, reset just this engine. */ + ret = intel_gpu_reset(engine->i915, intel_engine_flag(engine)); + + i915_gem_reset_finish_engine(engine); + + if (ret) { + /* If we fail here, we expect to fallback to a global reset */ + DRM_DEBUG_DRIVER("Failed to reset %s, ret=%d\n", + engine->name, ret); + goto out; + } + + /* + * The engine and its registers (and workarounds in case of render) + * have been reset to their default values. Follow the init_ring + * process to program RING_MODE, HWSP and re-enable submission. + */ + ret = engine->init_hw(engine); + +out: + return ret; } static int i915_pm_suspend(struct device *kdev) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 4220abe1f28b..152e30750dd4 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3474,11 +3474,16 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error) return READ_ONCE(error->reset_count); } +struct drm_i915_gem_request * +i915_gem_reset_prepare_engine(struct intel_engine_cs *engine); int i915_gem_reset_prepare(struct drm_i915_private *dev_priv); void i915_gem_reset(struct drm_i915_private *dev_priv); +void i915_gem_reset_finish_engine(struct intel_engine_cs *engine); void i915_gem_reset_finish(struct drm_i915_private *dev_priv); void i915_gem_set_wedged(struct drm_i915_private *dev_priv); bool i915_gem_unset_wedged(struct drm_i915_private *dev_priv); +void i915_gem_reset_engine(struct intel_engine_cs *engine, + struct drm_i915_gem_request *request); void i915_gem_init_mmio(struct drm_i915_private *i915); int __must_check i915_gem_init(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 37d1cbf82beb..1353491c1010 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2831,45 +2831,61 @@ static bool engine_stalled(struct intel_engine_cs *engine) return true; } +/* + * Ensure irq handler finishes, and not run again. + * Also return the active request so that we only search for it once. + */ +struct drm_i915_gem_request * +i915_gem_reset_prepare_engine(struct intel_engine_cs *engine) +{ + struct drm_i915_gem_request *request = NULL; + + /* Prevent the signaler thread from updating the request + * state (by calling dma_fence_signal) as we are processing + * the reset. The write from the GPU of the seqno is + * asynchronous and the signaler thread may see a different + * value to us and declare the request complete, even though + * the reset routine have picked that request as the active + * (incomplete) request. This conflict is not handled + * gracefully! + */ + kthread_park(engine->breadcrumbs.signaler); + + /* Prevent request submission to the hardware until we have + * completed the reset in i915_gem_reset_finish(). If a request + * is completed by one engine, it may then queue a request + * to a second via its engine->irq_tasklet *just* as we are + * calling engine->init_hw() and also writing the ELSP. + * Turning off the engine->irq_tasklet until the reset is over + * prevents the race. + */ + tasklet_kill(&engine->irq_tasklet); + tasklet_disable(&engine->irq_tasklet); + + if (engine->irq_seqno_barrier) + engine->irq_seqno_barrier(engine); + + if (engine_stalled(engine)) { + request = i915_gem_find_active_request(engine); + if (request && request->fence.error == -EIO) + request = ERR_PTR(-EIO); /* Previous reset failed! */ + } + + return request; +} + int i915_gem_reset_prepare(struct drm_i915_private *dev_priv) { struct intel_engine_cs *engine; + struct drm_i915_gem_request *request; enum intel_engine_id id; int err = 0; - /* Ensure irq handler finishes, and not run again. */ for_each_engine(engine, dev_priv, id) { - struct drm_i915_gem_request *request = NULL; - - /* Prevent the signaler thread from updating the request - * state (by calling dma_fence_signal) as we are processing - * the reset. The write from the GPU of the seqno is - * asynchronous and the signaler thread may see a different - * value to us and declare the request complete, even though - * the reset routine have picked that request as the active - * (incomplete) request. This conflict is not handled - * gracefully! - */ - kthread_park(engine->breadcrumbs.signaler); - - /* Prevent request submission to the hardware until we have - * completed the reset in i915_gem_reset_finish(). If a request - * is completed by one engine, it may then queue a request - * to a second via its engine->irq_tasklet *just* as we are - * calling engine->init_hw() and also writing the ELSP. - * Turning off the engine->irq_tasklet until the reset is over - * prevents the race. - */ - tasklet_kill(&engine->irq_tasklet); - tasklet_disable(&engine->irq_tasklet); - - if (engine->irq_seqno_barrier) - engine->irq_seqno_barrier(engine); - - if (engine_stalled(engine)) { - request = i915_gem_find_active_request(engine); - if (request && request->fence.error == -EIO) - err = -EIO; /* Previous reset failed! */ + request = i915_gem_reset_prepare_engine(engine); + if (IS_ERR(request)) { + err = PTR_ERR(request); + continue; } engine->hangcheck.active_request = request; @@ -2960,8 +2976,8 @@ static bool i915_gem_reset_request(struct drm_i915_gem_request *request) return guilty; } -static void i915_gem_reset_engine(struct intel_engine_cs *engine, - struct drm_i915_gem_request *request) +void i915_gem_reset_engine(struct intel_engine_cs *engine, + struct drm_i915_gem_request *request) { if (request && i915_gem_reset_request(request)) { DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n", @@ -3004,6 +3020,12 @@ void i915_gem_reset(struct drm_i915_private *dev_priv) } } +void i915_gem_reset_finish_engine(struct intel_engine_cs *engine) +{ + tasklet_enable(&engine->irq_tasklet); + kthread_unpark(engine->breadcrumbs.signaler); +} + void i915_gem_reset_finish(struct drm_i915_private *dev_priv) { struct intel_engine_cs *engine; @@ -3013,8 +3035,7 @@ void i915_gem_reset_finish(struct drm_i915_private *dev_priv) for_each_engine(engine, dev_priv, id) { engine->hangcheck.active_request = NULL; - tasklet_enable(&engine->irq_tasklet); - kthread_unpark(engine->breadcrumbs.signaler); + i915_gem_reset_finish_engine(engine); } } |