On 1/18/2022 13:43, Matthew Brost wrote:
The G2H handler needs to be flushed during a GT reset but a G2H
indicating engine reset failure can trigger a GT reset. Add a worker to
trigger the GT when a engine reset failure is received to break this
s/a/an/
circular dependency.
Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
---
drivers/gpu/drm/i915/gt/uc/intel_guc.h | 5 ++++
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 23 +++++++++++++++----
2 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 9d26a86fe557a..60ea8deef5392 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -119,6 +119,11 @@ struct intel_guc {
* function as it might be in an atomic context (no sleeping)
*/
struct work_struct destroyed_worker;
+ /**
+ * @reset_worker: worker to trigger a GT reset after an engine
+ * reset fails
+ */
+ struct work_struct reset_worker;
} submission_state;
/**
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 23a40f10d376d..cdd8d691251ff 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1746,6 +1746,7 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc)
}
static void destroyed_worker_func(struct work_struct *w);
+static void reset_worker_func(struct work_struct *w);
/*
* Set up the memory resources to be shared with the GuC (via the GGTT)
@@ -1776,6 +1777,8 @@ int intel_guc_submission_init(struct intel_guc *guc)
INIT_LIST_HEAD(&guc->submission_state.destroyed_contexts);
INIT_WORK(&guc->submission_state.destroyed_worker,
destroyed_worker_func);
+ INIT_WORK(&guc->submission_state.reset_worker,
+ reset_worker_func);
guc->submission_state.guc_ids_bitmap =
bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID(guc), GFP_KERNEL);
@@ -4052,6 +4055,17 @@ guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance)
return gt->engine_class[engine_class][instance];
}
+static void reset_worker_func(struct work_struct *w)
+{
+ struct intel_guc *guc = container_of(w, struct intel_guc,
+ submission_state.reset_worker);
+ struct intel_gt *gt = guc_to_gt(guc);
+
+ intel_gt_handle_error(gt, ALL_ENGINES,
+ I915_ERROR_CAPTURE,
+ "GuC failed to reset a engine\n");
s/a/an/
+}
+
int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
const u32 *msg, u32 len)
{
@@ -4083,10 +4097,11 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
drm_err(>->i915->drm, "GuC engine reset request failed on %d:%d (%s) because 0x%08X",
guc_class, instance, engine->name, reason);
- intel_gt_handle_error(gt, engine->mask,
- I915_ERROR_CAPTURE,
- "GuC failed to reset %s (reason=0x%08x)\n",
- engine->name, reason);
The engine name and reason code are lost from the error capture? I guess
we still get it in the drm_err above, though. So probably not an issue.
We shouldn't be getting these from end users and any internal CI run is
only likely to give us the dmesg, not the error capture anyway! However,
still seems like it is work saving engine->mask in the submission_state
structure (ORing in, in case there are multiple resets). Clearing it
should be safe because once a GT reset has happened, we aren't getting
any more G2Hs. And we can't have multiple message handlers running
concurrently, right? So no need to protect the OR either.
John.
+ /*
+ * A GT reset flushes this worker queue (G2H handler) so we must use
+ * another worker to trigger a GT reset.
+ */
+ queue_work(system_unbound_wq, &guc->submission_state.reset_worker);
return 0;
}
