[v9,20/21] drm/i915: Watchdog timeout: Include threshold value in error state

Submitted by Michel Thierry on June 15, 2017, 8:18 p.m.

Details

Message ID 20170615201828.23144-21-michel.thierry@intel.com
State New
Headers show
Series "Gen8+ engine-reset" ( rev: 13 ) in Intel GFX

Not browsing as part of any series.

Commit Message

Michel Thierry June 15, 2017, 8:18 p.m.
Save the watchdog threshold (in us) as part of the engine state.

v2: Only do it for gen8+ (and prevent a missing-case warn).

Signed-off-by: Michel Thierry <michel.thierry@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h       |  1 +
 drivers/gpu/drm/i915/i915_gpu_error.c | 12 ++++++++----
 2 files changed, 9 insertions(+), 4 deletions(-)

Patch hide | download patch | download mbox

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8d9bf4c303b6..b11bd181ff4c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -963,6 +963,7 @@  struct i915_gpu_state {
 			int ban_score;
 			int active;
 			int guilty;
+			int watchdog_threshold;
 		} context;
 
 		struct drm_i915_error_object {
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index ebd5501ec134..515fedb61751 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -388,9 +388,11 @@  static void error_print_context(struct drm_i915_error_state_buf *m,
 				const char *header,
 				const struct drm_i915_error_context *ctx)
 {
-	err_printf(m, "%s%s[%d] user_handle %d hw_id %d, ban score %d guilty %d active %d\n",
+	err_printf(m, "%s%s[%d] user_handle %d hw_id %d, ban score %d guilty %d active %d, watchdog %dus\n",
 		   header, ctx->comm, ctx->pid, ctx->handle, ctx->hw_id,
-		   ctx->ban_score, ctx->guilty, ctx->active);
+		   ctx->ban_score, ctx->guilty, ctx->active,
+		   INTEL_GEN(m->i915) >= 8 ?
+			watchdog_to_us(m->i915, ctx->watchdog_threshold) : 0);
 }
 
 static void error_print_engine(struct drm_i915_error_state_buf *m,
@@ -1349,7 +1351,8 @@  static void error_record_engine_execlists(struct intel_engine_cs *engine,
 }
 
 static void record_context(struct drm_i915_error_context *e,
-			   struct i915_gem_context *ctx)
+			   struct i915_gem_context *ctx,
+			   u32 engine_id)
 {
 	if (ctx->pid) {
 		struct task_struct *task;
@@ -1368,6 +1371,7 @@  static void record_context(struct drm_i915_error_context *e,
 	e->ban_score = ctx->ban_score;
 	e->guilty = ctx->guilty_count;
 	e->active = ctx->active_count;
+	e->watchdog_threshold =	ctx->engine[engine_id].watchdog_threshold;
 }
 
 static void request_record_user_bo(struct drm_i915_gem_request *request,
@@ -1431,7 +1435,7 @@  static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			ee->vm = request->ctx->ppgtt ?
 				&request->ctx->ppgtt->base : &ggtt->base;
 
-			record_context(&ee->context, request->ctx);
+			record_context(&ee->context, request->ctx, engine->id);
 
 			/* We need to copy these to an anonymous buffer
 			 * as the simplest method to avoid being overwritten