[v5,05/18] drm/i915/tdr: Add support for per engine reset recovery

Submitted by Michel Thierry on March 25, 2017, 1:29 a.m.

Details

Message ID 20170325013010.36244-6-michel.thierry@intel.com
State New
Headers show
Series "Gen8+ engine-reset" ( rev: 1 ) in Intel GFX

Not browsing as part of any series.

Commit Message

Michel Thierry March 25, 2017, 1:29 a.m.
From: Arun Siluvery <arun.siluvery@linux.intel.com>

This change implements support for per-engine reset as an initial, less
intrusive hang recovery option to be attempted before falling back to the
legacy full GPU reset recovery mode if necessary. This is only supported
from Gen8 onwards.

Hangchecker determines which engines are hung and invokes error handler to
recover from it. Error handler schedules recovery for each of those engines
that are hung. The recovery procedure is as follows,
 - identifies the request that caused the hang and it is dropped
 - force engine to idle: this is done by issuing a reset request
 - reset and re-init engine
 - restart submissions to the engine

If engine reset fails then we fall back to heavy weight full gpu reset
which resets all engines and reinitiazes complete state of HW and SW.

v2: Rebase.
v3: s/*engine_reset*/*reset_engine*/; freeze engine and irqs before
calling i915_gem_reset_engine (Chris).
v4: Rebase, modify i915_gem_reset_prepare to use a ring mask and
reuse the function for reset_engine.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c         | 88 +++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_drv.h         | 11 +++--
 drivers/gpu/drm/i915/i915_gem.c         | 16 +++---
 drivers/gpu/drm/i915/i915_gem_request.c |  2 +-
 drivers/gpu/drm/i915/intel_uncore.c     | 20 ++++++++
 5 files changed, 122 insertions(+), 15 deletions(-)

Patch hide | download patch | download mbox

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c7eb43deb33e..9c7bdcf03c13 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1831,7 +1831,7 @@  void i915_reset_chip(struct drm_i915_private *dev_priv)
 
 	pr_notice("drm/i915: Resetting chip after gpu hang\n");
 	disable_irq(dev_priv->drm.irq);
-	ret = i915_gem_reset_prepare(dev_priv);
+	ret = i915_gem_reset_prepare(dev_priv, ALL_ENGINES);
 	if (ret) {
 		DRM_ERROR("GPU recovery failed\n");
 		intel_gpu_reset(dev_priv, ALL_ENGINES);
@@ -1873,7 +1873,7 @@  void i915_reset_chip(struct drm_i915_private *dev_priv)
 	i915_queue_hangcheck(dev_priv);
 
 finish:
-	i915_gem_reset_finish(dev_priv);
+	i915_gem_reset_finish(dev_priv, ALL_ENGINES);
 	enable_irq(dev_priv->drm.irq);
 
 wakeup:
@@ -1892,11 +1892,91 @@  void i915_reset_chip(struct drm_i915_private *dev_priv)
  *
  * Reset a specific GPU engine. Useful if a hang is detected.
  * Returns zero on successful reset or otherwise an error code.
+ *
+ * Caller must hold the struct_mutex.
+ *
+ * Procedure is:
+ *  - identifies the request that caused the hang and it is dropped
+ *  - force engine to idle: this is done by issuing a reset request
+ *  - reset engine
+ *  - restart submissions to the engine
  */
 int i915_reset_engine(struct intel_engine_cs *engine)
 {
-	/* FIXME: replace me with engine reset sequence */
-	return -ENODEV;
+	int ret;
+	struct drm_i915_private *dev_priv = engine->i915;
+	struct i915_gpu_error *error = &dev_priv->gpu_error;
+
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &error->flags));
+
+	if (!test_and_clear_bit(I915_RESET_HANDOFF, &error->flags))
+		return 0;
+
+	DRM_DEBUG_DRIVER("resetting %s\n", engine->name);
+
+	/*
+	 * We need to first idle the engine by issuing a reset request,
+	 * then perform soft reset and re-initialize hw state, for all of
+	 * this GT power need to be awake so ensure it does throughout the
+	 * process
+	 */
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+
+	disable_irq(dev_priv->drm.irq);
+	ret = i915_gem_reset_prepare(dev_priv, intel_engine_flag(engine));
+	if (ret) {
+		DRM_ERROR("Previous reset failed - promote to full reset\n");
+		goto error;
+	}
+
+	if (dev_priv->gt.active_requests)
+		engine_retire_requests(engine);
+
+	/*
+	 * the request that caused the hang is stuck on elsp, identify the
+	 * active request and drop it, adjust head to skip the offending
+	 * request to resume executing remaining requests in the queue.
+	 */
+	i915_gem_reset_engine(engine);
+
+	/* forcing engine to idle */
+	ret = intel_request_reset_engine(engine);
+	if (ret) {
+		DRM_ERROR("Failed to disable %s\n", engine->name);
+		goto error;
+	}
+
+	/* finally, reset engine */
+	ret = intel_gpu_reset(dev_priv, intel_engine_flag(engine));
+	if (ret) {
+		DRM_ERROR("Failed to reset %s, ret=%d\n", engine->name, ret);
+		intel_unrequest_reset_engine(engine);
+		goto error;
+	}
+
+	/* be sure the request reset bit gets cleared */
+	intel_unrequest_reset_engine(engine);
+
+	/* i915_gem_reset_prepare revoked the fences */
+	i915_gem_restore_fences(dev_priv);
+	i915_gem_reset_finish(dev_priv, intel_engine_flag(engine));
+
+	/* replay remaining requests in the queue */
+	ret = engine->init_hw(engine);
+	if (ret)
+		goto error;
+
+wakeup:
+	enable_irq(dev_priv->drm.irq);
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+	wake_up_bit(&error->flags, I915_RESET_HANDOFF);
+	return ret;
+
+error:
+	/* use full gpu reset to recover on error */
+	set_bit(I915_RESET_HANDOFF, &error->flags);
+	goto wakeup;
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b02393f33753..67201ecd98e5 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3044,6 +3044,8 @@  extern int intel_gpu_reset(struct drm_i915_private *dev_priv, u32 engine_mask);
 extern bool intel_has_gpu_reset(struct drm_i915_private *dev_priv);
 extern void i915_reset(struct drm_i915_private *dev_priv, u32 engine_mask);
 extern bool intel_has_reset_engine(struct drm_i915_private *dev_priv);
+extern int intel_request_reset_engine(struct intel_engine_cs *engine);
+extern void intel_unrequest_reset_engine(struct intel_engine_cs *engine);
 extern int intel_guc_reset(struct drm_i915_private *dev_priv);
 extern void intel_engine_init_hangcheck(struct intel_engine_cs *engine);
 extern void intel_hangcheck_init(struct drm_i915_private *dev_priv);
@@ -3420,7 +3422,7 @@  int __must_check i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno);
 
 struct drm_i915_gem_request *
 i915_gem_find_active_request(struct intel_engine_cs *engine);
-
+void engine_retire_requests(struct intel_engine_cs *engine);
 void i915_gem_retire_requests(struct drm_i915_private *dev_priv);
 
 static inline bool i915_reset_backoff(struct i915_gpu_error *error)
@@ -3448,11 +3450,14 @@  static inline u32 i915_reset_count(struct i915_gpu_error *error)
 	return READ_ONCE(error->reset_count);
 }
 
-int i915_gem_reset_prepare(struct drm_i915_private *dev_priv);
+int i915_gem_reset_prepare(struct drm_i915_private *dev_priv,
+			   unsigned int engine_mask);
 void i915_gem_reset(struct drm_i915_private *dev_priv);
-void i915_gem_reset_finish(struct drm_i915_private *dev_priv);
+void i915_gem_reset_finish(struct drm_i915_private *dev_priv,
+			   unsigned int engine_mask);
 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);
 
 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 9515daea6358..ba0bdae30d5a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2741,14 +2741,15 @@  static bool engine_stalled(struct intel_engine_cs *engine)
 	return true;
 }
 
-int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
+int i915_gem_reset_prepare(struct drm_i915_private *dev_priv,
+			   unsigned int engine_mask)
 {
 	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	unsigned int tmp;
 	int err = 0;
 
 	/* Ensure irq handler finishes, and not run again. */
-	for_each_engine(engine, dev_priv, id) {
+	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
 		struct drm_i915_gem_request *request;
 
 		/* Prevent the signaler thread from updating the request
@@ -2868,7 +2869,7 @@  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)
+void i915_gem_reset_engine(struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_request *request;
 
@@ -2914,14 +2915,15 @@  void i915_gem_reset(struct drm_i915_private *dev_priv)
 	}
 }
 
-void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
+void i915_gem_reset_finish(struct drm_i915_private *dev_priv,
+			   unsigned int engine_mask)
 {
 	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	unsigned int tmp;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	for_each_engine(engine, dev_priv, id) {
+	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
 		tasklet_enable(&engine->irq_tasklet);
 		kthread_unpark(engine->breadcrumbs.signaler);
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 5ecb5a7a0c64..180bd84614fc 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -1177,7 +1177,7 @@  long i915_wait_request(struct drm_i915_gem_request *req,
 	return timeout;
 }
 
-static void engine_retire_requests(struct intel_engine_cs *engine)
+void engine_retire_requests(struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_request *request, *next;
 	u32 seqno = intel_engine_get_seqno(engine);
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index be51b5a0689a..596b99dbbff8 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1781,6 +1781,26 @@  int intel_guc_reset(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
+/*
+ * On gen8+ a reset request has to be issued via the reset control register
+ * before a GPU engine can be reset in order to stop the command streamer
+ * and idle the engine. This replaces the legacy way of stopping an engine
+ * by writing to the stop ring bit in the MI_MODE register.
+ */
+int intel_request_reset_engine(struct intel_engine_cs *engine)
+{
+	return gen8_request_reset_engine(engine);
+}
+
+/*
+ * It is possible to back off from a previously issued reset request by simply
+ * clearing the reset request bit in the reset control register.
+ */
+void intel_unrequest_reset_engine(struct intel_engine_cs *engine)
+{
+	gen8_unrequest_reset_engine(engine);
+}
+
 bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv)
 {
 	return check_for_unclaimed_mmio(dev_priv);