[Mesa-dev] [RFC 9/9] drm/i915: Add engine reset count in get-reset-stats ioctl

[Michel Thierry]

Users/tests relying on the total reset count will start seeing a smaller
number since most of the hangs can be handled by engine reset.
Note that if reset engine x, context a running on engine y will be unaware
and unaffected.

To start the discussion, include just a total engine reset count. If it
is deemed useful, it can be extended to report each engine separately.

Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: mesa-dev at lists.freedesktop.org
Signed-off-by: Michel Thierry <michel.thierry at intel.com>
---
 drivers/gpu/drm/i915/i915_gem_context.c | 14 +++++++++++---
 include/uapi/drm/i915_drm.h             |  3 ++-
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 1822d338c7aa..7f89ff21e2e5 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -1339,9 +1339,11 @@ int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_reset_stats *args = data;
 	struct i915_gem_context *ctx;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int ret;
 
-	if (args->flags || args->pad)
+	if (args->flags)
 		return -EINVAL;
 
 	if (args->ctx_id == DEFAULT_CONTEXT_HANDLE && !capable(CAP_SYS_ADMIN))
@@ -1357,10 +1359,16 @@ int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
 		return PTR_ERR(ctx);
 	}
 
-	if (capable(CAP_SYS_ADMIN))
+	if (capable(CAP_SYS_ADMIN)) {
 		args->reset_count = i915_reset_count(&dev_priv->gpu_error);
-	else
+		for_each_engine(engine, dev_priv, id)
+			args->engine_reset_count +=
+				i915_engine_reset_count(&dev_priv->gpu_error,
+							engine);
+	} else {
 		args->reset_count = 0;
+		args->engine_reset_count = 0;
+	}
 
 	args->batch_active = ctx->guilty_count;
 	args->batch_pending = ctx->active_count;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 1110e628c239..172ce188a8cb 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1201,7 +1201,8 @@ struct drm_i915_reset_stats {
 	/* Number of batches lost pending for execution, for this context */
 	__u32 batch_pending;
 
-	__u32 pad;
+	/* Number of engine resets since boot/module reload, for all contexts */
+	__u32 engine_reset_count;
 };
 
 struct drm_i915_gem_userptr {
-- 
2.11.0