[Intel-gfx] [PATCH v5 5/5] drm/i915: Watchdog timeout: Include threshold value in error state

[Carlos Santa]

From: Michel Thierry <michel.thierry at intel.com>

Save the watchdog threshold (in us) as part of the engine state.

v2: Only do it for gen8+ (and prevent a missing-case warn).
v3: use ctx->__engine.
v4: Rebase.
v5: Rebase.
v6: Rebase, use intel_context_lookup()

Cc: Antonio Argenziano <antonio.argenziano at intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin at linux.intel.com>
Signed-off-by: Michel Thierry <michel.thierry at intel.com>
Signed-off-by: Carlos Santa <carlos.santa at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h       |  2 ++
 drivers/gpu/drm/i915/i915_gpu_error.c | 14 ++++++++++----
 drivers/gpu/drm/i915/i915_gpu_error.h |  1 +
 3 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5324397c3801..5dbb3938e159 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3118,6 +3118,8 @@ i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id)
 	return ctx;
 }
 
+u32 watchdog_to_us(struct drm_i915_private *i915, u32 value_in_clock_counts);
+
 int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file);
 int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 26bac517e383..1f8d29bf00d0 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -454,9 +454,11 @@ 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, prio %d, guilty %d active %d\n",
+	err_printf(m, "%s%s[%d] user_handle %d hw_id %d, prio %d, guilty %d active %d, watchdog %dus\n",
 		   header, ctx->comm, ctx->pid, ctx->handle, ctx->hw_id,
-		   ctx->sched_attr.priority, ctx->guilty, ctx->active);
+		   ctx->sched_attr.priority, 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,
@@ -1316,8 +1318,11 @@ 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)
 {
+	struct drm_i915_private *dev_priv = ctx->i915;
+
 	if (ctx->pid) {
 		struct task_struct *task;
 
@@ -1335,6 +1340,7 @@ static void record_context(struct drm_i915_error_context *e,
 	e->sched_attr = ctx->sched;
 	e->guilty = atomic_read(&ctx->guilty_count);
 	e->active = atomic_read(&ctx->active_count);
+	e->watchdog_threshold = intel_context_lookup(ctx, dev_priv->engine[engine_id])->watchdog_threshold;
 }
 
 static void request_record_user_bo(struct i915_request *request,
@@ -1418,7 +1424,7 @@ static void gem_record_rings(struct i915_gpu_state *error)
 
 			ee->vm = ctx->ppgtt ? &ctx->ppgtt->vm : &ggtt->vm;
 
-			record_context(&ee->context, ctx);
+			record_context(&ee->context, ctx, engine->id);
 
 			/* We need to copy these to an anonymous buffer
 			 * as the simplest method to avoid being overwritten
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 6cf6a8679b26..439a31f5db3b 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -120,6 +120,7 @@ struct i915_gpu_state {
 			u32 hw_id;
 			int active;
 			int guilty;
+			int watchdog_threshold;
 			struct i915_sched_attr sched_attr;
 		} context;
 
-- 
2.17.1