[PATCH 4/4] drm/i915/guc: Refcount context during error capture

[Matthew Brost]

From: John Harrison <John.C.Harrison at Intel.com>

When i915 receives a context reset notification from GuC, it triggers
an error capture before resetting any outstanding requsts of that
context. Unfortunately, the error capture is not a time bound
operation. In certain situations it can take a long time, particularly
when multiple large LMEM buffers must be read back and eoncoded. If
this delay is longer than other timeouts (heartbeat, test recovery,
etc.) then a full GT reset can be triggered in the middle.

That can result in the context being reset by GuC actually being
destroyed before the error capture completes and the GuC submission
code resumes. Thus, the GuC side can start dereferencing stale
pointers and Bad Things ensue.

So add a refcount get of the context during the entire reset
operation. That way, the context can't be destroyed part way through
no matter what other resets or user interactions occur.

v2:
 (Matthew Brost)
  - Update patch to work with async error capture

Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
Signed-off-by: Matthew Brost <matthew.brost at intel.com>
---
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 24 +++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

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 1986a57b52cc..02917fc4d4a8 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -2888,6 +2888,8 @@ static void capture_worker_func(struct work_struct *w)
 	intel_engine_set_hung_context(engine, ce);
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
 		i915_capture_error_state(gt, ce->engine->mask);
+
+	intel_context_put(ce);
 }
 
 static void capture_error_state(struct intel_guc *guc,
@@ -2924,7 +2926,7 @@ static void guc_context_replay(struct intel_context *ce)
 	tasklet_hi_schedule(&sched_engine->tasklet);
 }
 
-static void guc_handle_context_reset(struct intel_guc *guc,
+static bool guc_handle_context_reset(struct intel_guc *guc,
 				     struct intel_context *ce)
 {
 	trace_intel_context_reset(ce);
@@ -2937,7 +2939,11 @@ static void guc_handle_context_reset(struct intel_guc *guc,
 		   !context_blocked(ce))) {
 		capture_error_state(guc, ce);
 		guc_context_replay(ce);
+
+		return false;
 	}
+
+	return true;
 }
 
 int intel_guc_context_reset_process_msg(struct intel_guc *guc,
@@ -2945,6 +2951,7 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc,
 {
 	struct intel_context *ce;
 	int desc_idx;
+	unsigned long flags;
 
 	if (unlikely(len != 1)) {
 		drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
@@ -2952,11 +2959,24 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc,
 	}
 
 	desc_idx = msg[0];
+
+	/*
+	 * The context lookup uses the xarray but lookups only require an RCU lock
+	 * not the full spinlock. So take the lock explicitly and keep it until the
+	 * context has been reference count locked to ensure it can't be destroyed
+	 * asynchronously until the reset is done.
+	 */
+	xa_lock_irqsave(&guc->context_lookup, flags);
 	ce = g2h_context_lookup(guc, desc_idx);
+	if (ce)
+		intel_context_get(ce);
+	xa_unlock_irqrestore(&guc->context_lookup, flags);
+
 	if (unlikely(!ce))
 		return -EPROTO;
 
-	guc_handle_context_reset(guc, ce);
+	if (guc_handle_context_reset(guc, ce))
+		intel_context_put(ce);
 
 	return 0;
 }
-- 
2.32.0