drm/i915: Fix request ref counting during error capture & debugfs dump

When GuC support was added to error capture, the reference counting
around the request object was broken. Fix it up.

The context based search manages the spinlocking around the search
internally. So it needs to grab the reference count internally as
well. The execlist only request based search relies on external
locking, so it needs an external reference count but within the
spinlock not outside it.

The only other caller of the context based search is the code for
dumping engine state to debugfs. That code wasn't previously getting
an explicit reference at all as it does everything while holding the
execlist specific spinlock. So, that needs updaing as well as that
spinlock doesn't help when using GuC submission. Rather than trying to
conditionally get/put depending on submission model, just change it to
always do the get/put.

v2: Explicitly document adding an extra blank line in some dense code
(Andy Shevchenko). Fix multiple potential null pointer derefs in case
of no request found (some spotted by Tvrtko, but there was more!).
Also fix a leaked request in case of !started and another in
__guc_reset_context now that intel_context_find_active_request is
actually reference counting the returned request.
v3: Add a _get suffix to intel_context_find_active_request now that it
grabs a reference (Daniele).
v4: Split the intel_guc_find_hung_context change to a separate patch
and rename intel_context_find_active_request_get to
intel_context_get_active_request (Tvrtko).
v5: s/locking/reference counting/ in commit message (Tvrtko)

Fixes: dc0dad3 ("drm/i915/guc: Fix for error capture after full GPU reset with GuC")
Fixes: 573ba12 ("drm/i915/guc: Capture error state on context reset")
Signed-off-by: John Harrison <[email protected]>
Reviewed-by: Daniele Ceraolo Spurio <[email protected]>
Acked-by: Tvrtko Ursulin <[email protected]>
Cc: Matthew Brost <[email protected]>
Cc: Jani Nikula <[email protected]>
Cc: Joonas Lahtinen <[email protected]>
Cc: Rodrigo Vivi <[email protected]>
Cc: Andrzej Hajda <[email protected]>
Cc: Matthew Auld <[email protected]>
Cc: Matt Roper <[email protected]>
Cc: Umesh Nerlige Ramappa <[email protected]>
Cc: Michael Cheng <[email protected]>
Cc: Lucas De Marchi <[email protected]>
Cc: Tejas Upadhyay <[email protected]>
Cc: Andy Shevchenko <[email protected]>
Cc: Aravind Iddamsetty <[email protected]>
Cc: Alan Previn <[email protected]>
Cc: Bruce Chang <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
(cherry picked from commit 3700e35)
Signed-off-by: Rodrigo Vivi <[email protected]>

Author: johnharr-intel

drivers/gpu/drm/i915/gt/intel_context.c

@@ -528,7 +528,7 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
 	return rq;
 }
 
-struct i915_request *intel_context_find_active_request(struct intel_context *ce)
+struct i915_request *intel_context_get_active_request(struct intel_context *ce)
 {
 	struct intel_context *parent = intel_context_to_parent(ce);
 	struct i915_request *rq, *active = NULL;
@@ -552,6 +552,8 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce)
 
 		active = rq;
 	}
+	if (active)
+		active = i915_request_get_rcu(active);
 	spin_unlock_irqrestore(&parent->guc_state.lock, flags);
 
 	return active;

drivers/gpu/drm/i915/gt/intel_context.h

@@ -268,8 +268,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 
 struct i915_request *intel_context_create_request(struct intel_context *ce);
 
-struct i915_request *
-intel_context_find_active_request(struct intel_context *ce);
+struct i915_request *intel_context_get_active_request(struct intel_context *ce);
 
 static inline bool intel_context_is_barrier(const struct intel_context *ce)
 {

drivers/gpu/drm/i915/gt/intel_engine_cs.c

@@ -2217,9 +2217,11 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d
 	if (guc) {
 		ce = intel_engine_get_hung_context(engine);
 		if (ce)
-			hung_rq = intel_context_find_active_request(ce);
+			hung_rq = intel_context_get_active_request(ce);
 	} else {
 		hung_rq = intel_engine_execlist_find_hung_request(engine);
+		if (hung_rq)
+			hung_rq = i915_request_get_rcu(hung_rq);
 	}
 
 	if (hung_rq)
@@ -2230,6 +2232,8 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d
 	else
 		intel_engine_dump_active_requests(&engine->sched_engine->requests,
 						  hung_rq, m);
+	if (hung_rq)
+		i915_request_put(hung_rq);
 }
 
 void intel_engine_dump(struct intel_engine_cs *engine,

drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c

@@ -1702,7 +1702,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st
 			goto next_context;
 
 		guilty = false;
-		rq = intel_context_find_active_request(ce);
+		rq = intel_context_get_active_request(ce);
 		if (!rq) {
 			head = ce->ring->tail;
 			goto out_replay;
@@ -1715,6 +1715,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st
 		head = intel_ring_wrap(ce->ring, rq->head);
 
 		__i915_request_reset(rq, guilty);
+		i915_request_put(rq);
 out_replay:
 		guc_reset_state(ce, head, guilty);
 next_context:

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -1607,7 +1607,7 @@ capture_engine(struct intel_engine_cs *engine,
 	ce = intel_engine_get_hung_context(engine);
 	if (ce) {
 		intel_engine_clear_hung_context(engine);
-		rq = intel_context_find_active_request(ce);
+		rq = intel_context_get_active_request(ce);
 		if (!rq || !i915_request_started(rq))
 			goto no_request_capture;
 	} else {
@@ -1618,21 +1618,18 @@ capture_engine(struct intel_engine_cs *engine,
 		if (!intel_uc_uses_guc_submission(&engine->gt->uc)) {
 			spin_lock_irqsave(&engine->sched_engine->lock, flags);
 			rq = intel_engine_execlist_find_hung_request(engine);
+			if (rq)
+				rq = i915_request_get_rcu(rq);
 			spin_unlock_irqrestore(&engine->sched_engine->lock,
 					       flags);
 		}
 	}
-	if (rq)
-		rq = i915_request_get_rcu(rq);
-
 	if (!rq)
 		goto no_request_capture;
 
 	capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL);
-	if (!capture) {
-		i915_request_put(rq);
+	if (!capture)
 		goto no_request_capture;
-	}
 	if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
 		intel_guc_capture_get_matching_node(engine->gt, ee, ce);
 
@@ -1642,6 +1639,8 @@ capture_engine(struct intel_engine_cs *engine,
 	return ee;
 
 no_request_capture:
+	if (rq)
+		i915_request_put(rq);
 	kfree(ee);
 	return NULL;
 }