From: John Harrison <John.C.Harrison@Intel.com>
Date: Tue, 14 Dec 2021 17:04:57 +0000 (-0800)
Subject: drm/i915/guc: Don't hog IRQs when destroying contexts
X-Git-Tag: v6.6.17~3937^2~16^2~1174
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=2406846ec497af081d7e7a7da0e9938b8136fe16;p=platform%2Fkernel%2Flinux-rpi.git

drm/i915/guc: Don't hog IRQs when destroying contexts

While attempting to debug a CT deadlock issue in various CI failures
(most easily reproduced with gem_ctx_create/basic-files), I was seeing
CPU deadlock errors being reported. This were because the context
destroy loop was blocking waiting on H2G space from inside an IRQ
spinlock. There no was deadlock as such, it's just that the H2G queue
was full of context destroy commands and GuC was taking a long time to
process them. However, the kernel was seeing the large amount of time
spent inside the IRQ lock as a dead CPU. Various Bad Things(tm) would
then happen (heartbeat failures, CT deadlock errors, outstanding H2G
WARNs, etc.).

Re-working the loop to only acquire the spinlock around the list
management (which is all it is meant to protect) rather than the
entire destroy operation seems to fix all the above issues.

v2:
 (John Harrison)
  - Fix typo in comment message

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211214170500.28569-5-matthew.brost@intel.com
---

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 7699407..e72d43a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -2644,7 +2644,6 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce)
 	unsigned long flags;
 	bool disabled;
 
-	lockdep_assert_held(&guc->submission_state.lock);
 	GEM_BUG_ON(!intel_gt_pm_is_awake(gt));
 	GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id.id));
 	GEM_BUG_ON(ce != __get_context(guc, ce->guc_id.id));
@@ -2660,7 +2659,7 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce)
 	}
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 	if (unlikely(disabled)) {
-		__release_guc_id(guc, ce);
+		release_guc_id(guc, ce);
 		__guc_context_destroy(ce);
 		return;
 	}
@@ -2694,36 +2693,48 @@ static void __guc_context_destroy(struct intel_context *ce)
 
 static void guc_flush_destroyed_contexts(struct intel_guc *guc)
 {
-	struct intel_context *ce, *cn;
+	struct intel_context *ce;
 	unsigned long flags;
 
 	GEM_BUG_ON(!submission_disabled(guc) &&
 		   guc_submission_initialized(guc));
 
-	spin_lock_irqsave(&guc->submission_state.lock, flags);
-	list_for_each_entry_safe(ce, cn,
-				 &guc->submission_state.destroyed_contexts,
-				 destroyed_link) {
-		list_del_init(&ce->destroyed_link);
-		__release_guc_id(guc, ce);
+	while (!list_empty(&guc->submission_state.destroyed_contexts)) {
+		spin_lock_irqsave(&guc->submission_state.lock, flags);
+		ce = list_first_entry_or_null(&guc->submission_state.destroyed_contexts,
+					      struct intel_context,
+					      destroyed_link);
+		if (ce)
+			list_del_init(&ce->destroyed_link);
+		spin_unlock_irqrestore(&guc->submission_state.lock, flags);
+
+		if (!ce)
+			break;
+
+		release_guc_id(guc, ce);
 		__guc_context_destroy(ce);
 	}
-	spin_unlock_irqrestore(&guc->submission_state.lock, flags);
 }
 
 static void deregister_destroyed_contexts(struct intel_guc *guc)
 {
-	struct intel_context *ce, *cn;
+	struct intel_context *ce;
 	unsigned long flags;
 
-	spin_lock_irqsave(&guc->submission_state.lock, flags);
-	list_for_each_entry_safe(ce, cn,
-				 &guc->submission_state.destroyed_contexts,
-				 destroyed_link) {
-		list_del_init(&ce->destroyed_link);
+	while (!list_empty(&guc->submission_state.destroyed_contexts)) {
+		spin_lock_irqsave(&guc->submission_state.lock, flags);
+		ce = list_first_entry_or_null(&guc->submission_state.destroyed_contexts,
+					      struct intel_context,
+					      destroyed_link);
+		if (ce)
+			list_del_init(&ce->destroyed_link);
+		spin_unlock_irqrestore(&guc->submission_state.lock, flags);
+
+		if (!ce)
+			break;
+
 		guc_lrc_desc_unpin(ce);
 	}
-	spin_unlock_irqrestore(&guc->submission_state.lock, flags);
 }
 
 static void destroyed_worker_func(struct work_struct *w)