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.
v2: s/engine_reset/reset_engine/, use union in uapi to not break compatibility.
Cc: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
Signed-off-by: Michel Thierry <michel.thierry@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_context.c | 14 +++++++++++---
include/uapi/drm/i915_drm.h | 6 +++++-
2 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index d46a69d3d390..e98d9daa3f00 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -1074,9 +1074,11 @@ 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))
@@ -1092,10 +1094,16 @@ 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->reset_engine_count +=
+ i915_reset_engine_count(&dev_priv->gpu_error,
+ engine);
+ } else {
args->reset_count = 0;
+ args->reset_engine_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 f24a80d2d42e..fadedefba6db 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1278,7 +1278,11 @@ struct drm_i915_reset_stats {
/* Number of batches lost pending for execution, for this context */
__u32 batch_pending;
- __u32 pad;
+ union {
+ __u32 pad;
+ /* Engine resets since boot/module reload, for all contexts */
+ __u32 reset_engine_count;
+ };
};
struct drm_i915_gem_userptr {
--
2.11.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
