[Intel-gfx] [PATCH 07/10] drm/i915/tdr: Add engine reset count to error state

Michel Thierry michel.thierry at intel.com
Thu Jan 12 04:18:14 UTC 2017


From: Arun Siluvery <arun.siluvery at linux.intel.com>

Driver maintains count of how many times a given engine is reset, useful to
capture this in error state also. It gives an idea of how engine is coping
up with the workloads it is executing before this error state.

A follow-up patch will provide this information in debugfs.

v2: s/engine_reset/reset_engine/ (Chris)
    Define count as unsigned int (Tvrtko)

Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
Signed-off-by: Michel Thierry <michel.thierry at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c       | 1 +
 drivers/gpu/drm/i915/i915_drv.h       | 8 ++++++++
 drivers/gpu/drm/i915/i915_gpu_error.c | 3 +++
 3 files changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 60a7a4874848..8799427b0a66 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1894,6 +1894,7 @@ int i915_reset_engine(struct intel_engine_cs *engine)
 	if (ret)
 		goto error;
 
+	error->reset_engine_count[engine->id]++;
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0c9386905011..872c5943d3a7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -941,6 +941,7 @@ struct drm_i915_error_state {
 		enum intel_engine_hangcheck_action hangcheck_action;
 		struct i915_address_space *vm;
 		int num_requests;
+		u32 reset_count;
 
 		/* position of active request inside the ring */
 		u32 rq_head, rq_post, rq_tail;
@@ -1555,6 +1556,7 @@ struct i915_gpu_error {
 
 	/* if available, engine-specific reset is tried before full gpu reset */
 	u32 reset_engine_mask;
+	u32 reset_engine_count[I915_NUM_ENGINES];
 
 	/**
 	 * Waitqueue to signal when a hang is detected. Used to for waiters
@@ -3337,6 +3339,12 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 	return READ_ONCE(error->reset_count);
 }
 
+static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
+					  struct intel_engine_cs *engine)
+{
+	return READ_ONCE(error->reset_engine_count[engine->id]);
+}
+
 void i915_gem_reset_prepare(struct drm_i915_private *dev_priv);
 void i915_gem_reset_finish(struct drm_i915_private *dev_priv);
 void i915_gem_set_wedged(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 396c6f0fd033..95dbc551bd92 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -453,6 +453,7 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 	err_printf(m, "  hangcheck action timestamp: %lu, %u ms ago\n",
 		   ee->hangcheck_timestamp,
 		   jiffies_to_msecs(jiffies - ee->hangcheck_timestamp));
+	err_printf(m, "  engine reset count: %u\n", ee->reset_count);
 
 	error_print_request(m, "  ELSP[0]: ", &ee->execlist[0]);
 	error_print_request(m, "  ELSP[1]: ", &ee->execlist[1]);
@@ -1170,6 +1171,8 @@ static void error_record_engine_registers(struct drm_i915_error_state *error,
 	ee->hangcheck_timestamp = engine->hangcheck.action_timestamp;
 	ee->hangcheck_action = engine->hangcheck.action;
 	ee->hangcheck_stalled = engine->hangcheck.stalled;
+	ee->reset_count = i915_reset_engine_count(&dev_priv->gpu_error,
+						  engine);
 
 	if (USES_PPGTT(dev_priv)) {
 		int i;
-- 
2.11.0



More information about the Intel-gfx mailing list