public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
* [Intel-gfx] [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
@ 2022-08-19 12:39 Matthew Auld
  2022-08-19 13:25 ` [Intel-gfx] ✗ Fi.CI.SPARSE: warning for " Patchwork
                   ` (3 more replies)
  0 siblings, 4 replies; 7+ messages in thread
From: Matthew Auld @ 2022-08-19 12:39 UTC (permalink / raw)
  To: intel-gfx; +Cc: Alan Previn

This reverts commit 6a079903847cce1dd06345127d2a32f26d2cd9c6.

Everything in CI using GuC is now timing out[1], and killing the machine
with this change (perhaps a deadlock?). CI was recently on fire due to
some changes coming in from -rc1, so likely the pre-merge CI results for
this series were invalid? For now just revert, unless GuC experts
already have a fix in mind.

[1] https://intel-gfx-ci.01.org/tree/drm-tip/index.html?

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c   |   2 +-
 drivers/gpu/drm/i915/gt/intel_context.h       |   8 -
 drivers/gpu/drm/i915/gt/intel_context_types.h |   7 -
 drivers/gpu/drm/i915/gt/uc/intel_guc.h        |  17 +-
 .../gpu/drm/i915/gt/uc/intel_guc_debugfs.c    |  60 -------
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 154 +++---------------
 drivers/gpu/drm/i915/i915_selftest.h          |   2 -
 7 files changed, 27 insertions(+), 223 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index df7fd1b019ec..dabdfe09f5e5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1454,7 +1454,7 @@ static void engines_idle_release(struct i915_gem_context *ctx,
 		int err;
 
 		/* serialises with execbuf */
-		intel_context_close(ce);
+		set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
 		if (!intel_context_pin_if_active(ce))
 			continue;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index f96420f0b5bb..8e2d70630c49 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -276,14 +276,6 @@ static inline bool intel_context_is_barrier(const struct intel_context *ce)
 	return test_bit(CONTEXT_BARRIER_BIT, &ce->flags);
 }
 
-static inline void intel_context_close(struct intel_context *ce)
-{
-	set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
-
-	if (ce->ops->close)
-		ce->ops->close(ce);
-}
-
 static inline bool intel_context_is_closed(const struct intel_context *ce)
 {
 	return test_bit(CONTEXT_CLOSED_BIT, &ce->flags);
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 86ac84e2edb9..04eacae1aca5 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -43,8 +43,6 @@ struct intel_context_ops {
 	void (*revoke)(struct intel_context *ce, struct i915_request *rq,
 		       unsigned int preempt_timeout_ms);
 
-	void (*close)(struct intel_context *ce);
-
 	int (*pre_pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr);
 	int (*pin)(struct intel_context *ce, void *vaddr);
 	void (*unpin)(struct intel_context *ce);
@@ -210,11 +208,6 @@ struct intel_context {
 		 * each priority bucket
 		 */
 		u32 prio_count[GUC_CLIENT_PRIORITY_NUM];
-		/**
-		 * @sched_disable_delay: worker to disable scheduling on this
-		 * context
-		 */
-		struct delayed_work sched_disable_delay;
 	} guc_state;
 
 	struct {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 944b549b8797..804133df1ac9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -112,10 +112,6 @@ struct intel_guc {
 		 * refs
 		 */
 		struct list_head guc_id_list;
-		/**
-		 * @guc_ids_in_use: Number single-lrc guc_ids in use
-		 */
-		u16 guc_ids_in_use;
 		/**
 		 * @destroyed_contexts: list of contexts waiting to be destroyed
 		 * (deregistered with the GuC)
@@ -136,16 +132,6 @@ struct intel_guc {
 		 * @reset_fail_mask: mask of engines that failed to reset
 		 */
 		intel_engine_mask_t reset_fail_mask;
-		/**
-		 * @sched_disable_delay_ms: schedule disable delay, in ms, for
-		 * contexts
-		 */
-		u64 sched_disable_delay_ms;
-		/**
-		 * @sched_disable_gucid_threshold: threshold of min remaining available
-		 * guc_ids before we start bypassing the schedule disable delay
-		 */
-		int sched_disable_gucid_threshold;
 	} submission_state;
 
 	/**
@@ -475,10 +461,9 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc);
 void intel_guc_submission_cancel_requests(struct intel_guc *guc);
 
 void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p);
-void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p);
 
 void intel_guc_write_barrier(struct intel_guc *guc);
 
-int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc);
+void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
index c91b150bb7ac..25f09a420561 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
@@ -71,72 +71,12 @@ static bool intel_eval_slpc_support(void *data)
 	return intel_guc_slpc_is_used(guc);
 }
 
-static int guc_sched_disable_delay_ms_get(void *data, u64 *val)
-{
-	struct intel_guc *guc = data;
-
-	if (!intel_guc_submission_is_used(guc))
-		return -ENODEV;
-
-	*val = guc->submission_state.sched_disable_delay_ms;
-
-	return 0;
-}
-
-static int guc_sched_disable_delay_ms_set(void *data, u64 val)
-{
-	struct intel_guc *guc = data;
-
-	if (!intel_guc_submission_is_used(guc))
-		return -ENODEV;
-
-	guc->submission_state.sched_disable_delay_ms = val;
-
-	return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_delay_ms_fops,
-			guc_sched_disable_delay_ms_get,
-			guc_sched_disable_delay_ms_set, "%lld\n");
-
-static int guc_sched_disable_gucid_threshold_get(void *data, u64 *val)
-{
-	struct intel_guc *guc = data;
-
-	if (!intel_guc_submission_is_used(guc))
-		return -ENODEV;
-
-	*val = guc->submission_state.sched_disable_gucid_threshold;
-	return 0;
-}
-
-static int guc_sched_disable_gucid_threshold_set(void *data, u64 val)
-{
-	struct intel_guc *guc = data;
-
-	if (!intel_guc_submission_is_used(guc))
-		return -ENODEV;
-
-	if (val > intel_guc_sched_disable_gucid_threshold_max(guc))
-		guc->submission_state.sched_disable_gucid_threshold =
-			intel_guc_sched_disable_gucid_threshold_max(guc);
-	else
-		guc->submission_state.sched_disable_gucid_threshold = val;
-
-	return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_gucid_threshold_fops,
-			guc_sched_disable_gucid_threshold_get,
-			guc_sched_disable_gucid_threshold_set, "%lld\n");
-
 void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root)
 {
 	static const struct intel_gt_debugfs_file files[] = {
 		{ "guc_info", &guc_info_fops, NULL },
 		{ "guc_registered_contexts", &guc_registered_contexts_fops, NULL },
 		{ "guc_slpc_info", &guc_slpc_info_fops, &intel_eval_slpc_support},
-		{ "guc_sched_disable_delay_ms", &guc_sched_disable_delay_ms_fops, NULL },
-		{ "guc_sched_disable_gucid_threshold", &guc_sched_disable_gucid_threshold_fops,
-		   NULL },
 	};
 
 	if (!intel_guc_is_supported(guc))
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 a0cebb4590e9..0d56b615bf78 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -65,13 +65,7 @@
  * corresponding G2H returns indicating the scheduling disable operation has
  * completed it is safe to unpin the context. While a disable is in flight it
  * isn't safe to resubmit the context so a fence is used to stall all future
- * requests of that context until the G2H is returned. Because this interaction
- * with the GuC takes a non-zero amount of time we delay the disabling of
- * scheduling after the pin count goes to zero by a configurable period of time
- * (see SCHED_DISABLE_DELAY_MS). The thought is this gives the user a window of
- * time to resubmit something on the context before doing this costly operation.
- * This delay is only done if the context isn't closed and the guc_id usage is
- * less than a threshold (see NUM_SCHED_DISABLE_GUC_IDS_THRESHOLD).
+ * requests of that context until the G2H is returned.
  *
  * Context deregistration:
  * Before a context can be destroyed or if we steal its guc_id we must
@@ -1995,9 +1989,6 @@ static int new_guc_id(struct intel_guc *guc, struct intel_context *ce)
 	if (unlikely(ret < 0))
 		return ret;
 
-	if (!intel_context_is_parent(ce))
-		++guc->submission_state.guc_ids_in_use;
-
 	ce->guc_id.id = ret;
 	return 0;
 }
@@ -2007,16 +1998,14 @@ static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce)
 	GEM_BUG_ON(intel_context_is_child(ce));
 
 	if (!context_guc_id_invalid(ce)) {
-		if (intel_context_is_parent(ce)) {
+		if (intel_context_is_parent(ce))
 			bitmap_release_region(guc->submission_state.guc_ids_bitmap,
 					      ce->guc_id.id,
 					      order_base_2(ce->parallel.number_children
 							   + 1));
-		} else {
-			--guc->submission_state.guc_ids_in_use;
+		else
 			ida_simple_remove(&guc->submission_state.guc_ids,
 					  ce->guc_id.id);
-		}
 		clr_ctx_id_mapping(guc, ce->guc_id.id);
 		set_context_guc_id_invalid(ce);
 	}
@@ -3004,98 +2993,41 @@ guc_context_revoke(struct intel_context *ce, struct i915_request *rq,
 	}
 }
 
-static void guc_context_sched_disable(struct intel_context *ce);
-
-static void do_sched_disable(struct intel_guc *guc, struct intel_context *ce,
-			     unsigned long flags)
-	__releases(ce->guc_state.lock)
+static void guc_context_sched_disable(struct intel_context *ce)
 {
+	struct intel_guc *guc = ce_to_guc(ce);
+	unsigned long flags;
 	struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm;
 	intel_wakeref_t wakeref;
+	u16 guc_id;
 
-	lockdep_assert_held(&ce->guc_state.lock);
-
-	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-
-	with_intel_runtime_pm(runtime_pm, wakeref)
-		guc_context_sched_disable(ce);
-}
-
-static bool bypass_sched_disable(struct intel_guc *guc,
-				 struct intel_context *ce)
-{
-	lockdep_assert_held(&ce->guc_state.lock);
 	GEM_BUG_ON(intel_context_is_child(ce));
 
-	if (submission_disabled(guc) || context_guc_id_invalid(ce) ||
-	    !ctx_id_mapped(guc, ce->guc_id.id)) {
-		clr_context_enabled(ce);
-		return true;
-	}
-
-	return !context_enabled(ce);
-}
-
-static void __delay_sched_disable(struct work_struct *wrk)
-{
-	struct intel_context *ce =
-		container_of(wrk, typeof(*ce), guc_state.sched_disable_delay.work);
-	struct intel_guc *guc = ce_to_guc(ce);
-	unsigned long flags;
-
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
 
-	if (bypass_sched_disable(guc, ce)) {
-		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-		intel_context_sched_disable_unpin(ce);
-	} else {
-		do_sched_disable(guc, ce, flags);
-	}
-}
-
-static bool guc_id_pressure(struct intel_guc *guc, struct intel_context *ce)
-{
-	/*
-	 * parent contexts are perma-pinned, if we are unpinning do schedule
-	 * disable immediately.
-	 */
-	if (intel_context_is_parent(ce))
-		return true;
-
 	/*
-	 * If we are beyond the threshold for avail guc_ids, do schedule disable immediately.
+	 * We have to check if the context has been disabled by another thread,
+	 * check if submssion has been disabled to seal a race with reset and
+	 * finally check if any more requests have been committed to the
+	 * context ensursing that a request doesn't slip through the
+	 * 'context_pending_disable' fence.
 	 */
-	return guc->submission_state.guc_ids_in_use >
-		guc->submission_state.sched_disable_gucid_threshold;
-}
-
-static void guc_context_sched_disable(struct intel_context *ce)
-{
-	struct intel_guc *guc = ce_to_guc(ce);
-	u64 delay = guc->submission_state.sched_disable_delay_ms;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ce->guc_state.lock, flags);
-
-	if (bypass_sched_disable(guc, ce)) {
-		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-		intel_context_sched_disable_unpin(ce);
-	} else if (!intel_context_is_closed(ce) && !guc_id_pressure(guc, ce) &&
-		   delay) {
+	if (unlikely(!context_enabled(ce) || submission_disabled(guc) ||
+		     context_has_committed_requests(ce))) {
+		clr_context_enabled(ce);
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-		mod_delayed_work(system_unbound_wq,
-				 &ce->guc_state.sched_disable_delay,
-				 msecs_to_jiffies(delay));
-	} else {
-		do_sched_disable(guc, ce, flags);
+		goto unpin;
 	}
-}
+	guc_id = prep_context_pending_disable(ce);
 
-static void guc_context_close(struct intel_context *ce)
-{
-	if (test_bit(CONTEXT_GUC_INIT, &ce->flags) &&
-	    cancel_delayed_work(&ce->guc_state.sched_disable_delay))
-		__delay_sched_disable(&ce->guc_state.sched_disable_delay.work);
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+	with_intel_runtime_pm(runtime_pm, wakeref)
+		__guc_context_sched_disable(guc, ce, guc_id);
+
+	return;
+unpin:
+	intel_context_sched_disable_unpin(ce);
 }
 
 static inline void guc_lrc_desc_unpin(struct intel_context *ce)
@@ -3414,8 +3346,6 @@ static void remove_from_context(struct i915_request *rq)
 static const struct intel_context_ops guc_context_ops = {
 	.alloc = guc_context_alloc,
 
-	.close = guc_context_close,
-
 	.pre_pin = guc_context_pre_pin,
 	.pin = guc_context_pin,
 	.unpin = guc_context_unpin,
@@ -3498,10 +3428,6 @@ static void guc_context_init(struct intel_context *ce)
 	rcu_read_unlock();
 
 	ce->guc_state.prio = map_i915_prio_to_guc_prio(prio);
-
-	INIT_DELAYED_WORK(&ce->guc_state.sched_disable_delay,
-			  __delay_sched_disable);
-
 	set_bit(CONTEXT_GUC_INIT, &ce->flags);
 }
 
@@ -3539,9 +3465,6 @@ static int guc_request_alloc(struct i915_request *rq)
 	if (unlikely(!test_bit(CONTEXT_GUC_INIT, &ce->flags)))
 		guc_context_init(ce);
 
-	if (cancel_delayed_work(&ce->guc_state.sched_disable_delay))
-		intel_context_sched_disable_unpin(ce);
-
 	/*
 	 * Call pin_guc_id here rather than in the pinning step as with
 	 * dma_resv, contexts can be repeatedly pinned / unpinned trashing the
@@ -3672,8 +3595,6 @@ static int guc_virtual_context_alloc(struct intel_context *ce)
 static const struct intel_context_ops virtual_guc_context_ops = {
 	.alloc = guc_virtual_context_alloc,
 
-	.close = guc_context_close,
-
 	.pre_pin = guc_virtual_context_pre_pin,
 	.pin = guc_virtual_context_pin,
 	.unpin = guc_virtual_context_unpin,
@@ -3763,8 +3684,6 @@ static void guc_child_context_destroy(struct kref *kref)
 static const struct intel_context_ops virtual_parent_context_ops = {
 	.alloc = guc_virtual_context_alloc,
 
-	.close = guc_context_close,
-
 	.pre_pin = guc_context_pre_pin,
 	.pin = guc_parent_context_pin,
 	.unpin = guc_parent_context_unpin,
@@ -4295,26 +4214,6 @@ static bool __guc_submission_selected(struct intel_guc *guc)
 	return i915->params.enable_guc & ENABLE_GUC_SUBMISSION;
 }
 
-int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc)
-{
-	return guc->submission_state.num_guc_ids - NUMBER_MULTI_LRC_GUC_ID(guc);
-}
-
-/*
- * This default value of 33 milisecs (+1 milisec round up) ensures 30fps or higher
- * workloads are able to enjoy the latency reduction when delaying the schedule-disable
- * operation. This matches the 30fps game-render + encode (real world) workload this
- * knob was tested against.
- */
-#define SCHED_DISABLE_DELAY_MS	34
-
-/*
- * A threshold of 75% is a reasonable starting point considering that real world apps
- * generally don't get anywhere near this.
- */
-#define NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(__guc) \
-	(((intel_guc_sched_disable_gucid_threshold_max(guc)) * 3) / 4)
-
 void intel_guc_submission_init_early(struct intel_guc *guc)
 {
 	xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ);
@@ -4331,10 +4230,7 @@ void intel_guc_submission_init_early(struct intel_guc *guc)
 	spin_lock_init(&guc->timestamp.lock);
 	INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping);
 
-	guc->submission_state.sched_disable_delay_ms = SCHED_DISABLE_DELAY_MS;
 	guc->submission_state.num_guc_ids = GUC_MAX_CONTEXT_ID;
-	guc->submission_state.sched_disable_gucid_threshold =
-		NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(guc);
 	guc->submission_supported = __guc_submission_supported(guc);
 	guc->submission_selected = __guc_submission_selected(guc);
 }
diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index bdf3e22c0a34..f54de0499be7 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -92,14 +92,12 @@ int __i915_subtests(const char *caller,
 			T, ARRAY_SIZE(T), data)
 #define i915_live_subtests(T, data) ({ \
 	typecheck(struct drm_i915_private *, data); \
-	(data)->gt[0]->uc.guc.submission_state.sched_disable_delay_ms = 0; \
 	__i915_subtests(__func__, \
 			__i915_live_setup, __i915_live_teardown, \
 			T, ARRAY_SIZE(T), data); \
 })
 #define intel_gt_live_subtests(T, data) ({ \
 	typecheck(struct intel_gt *, data); \
-	(data)->uc.guc.submission_state.sched_disable_delay_ms = 0; \
 	__i915_subtests(__func__, \
 			__intel_gt_live_setup, __intel_gt_live_teardown, \
 			T, ARRAY_SIZE(T), data); \
-- 
2.37.2


^ permalink raw reply related	[flat|nested] 7+ messages in thread

* [Intel-gfx] ✗ Fi.CI.SPARSE: warning for Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
  2022-08-19 12:39 [Intel-gfx] [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero" Matthew Auld
@ 2022-08-19 13:25 ` Patchwork
  2022-08-19 13:48 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
                   ` (2 subsequent siblings)
  3 siblings, 0 replies; 7+ messages in thread
From: Patchwork @ 2022-08-19 13:25 UTC (permalink / raw)
  To: Matthew Auld; +Cc: intel-gfx

== Series Details ==

Series: Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
URL   : https://patchwork.freedesktop.org/series/107502/
State : warning

== Summary ==

Error: dim sparse failed
Sparse version: v0.6.2
Fast mode used, each commit won't be checked separately.



^ permalink raw reply	[flat|nested] 7+ messages in thread

* [Intel-gfx] ✓ Fi.CI.BAT: success for Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
  2022-08-19 12:39 [Intel-gfx] [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero" Matthew Auld
  2022-08-19 13:25 ` [Intel-gfx] ✗ Fi.CI.SPARSE: warning for " Patchwork
@ 2022-08-19 13:48 ` Patchwork
  2022-08-19 15:46 ` [Intel-gfx] [PATCH] " John Harrison
  2022-08-20 13:13 ` [Intel-gfx] ✗ Fi.CI.IGT: failure for " Patchwork
  3 siblings, 0 replies; 7+ messages in thread
From: Patchwork @ 2022-08-19 13:48 UTC (permalink / raw)
  To: Matthew Auld; +Cc: intel-gfx

[-- Attachment #1: Type: text/plain, Size: 13155 bytes --]

== Series Details ==

Series: Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
URL   : https://patchwork.freedesktop.org/series/107502/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_12003 -> Patchwork_107502v1
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/index.html

Participating hosts (30 -> 31)
------------------------------

  Additional (6): fi-rkl-11600 bat-dg2-8 bat-adlm-1 bat-adlp-6 bat-jsl-3 bat-dg2-10 
  Missing    (5): fi-kbl-soraka bat-dg1-6 bat-dg1-5 fi-ilk-650 bat-rplp-1 

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_107502v1:

### IGT changes ###

#### Suppressed ####

  The following results come from untrusted machines, tests, or statuses.
  They do not affect the overall result.

  * igt@i915_selftest@live@gt_lrc:
    - {bat-dg2-9}:        NOTRUN -> [INCOMPLETE][1]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/bat-dg2-9/igt@i915_selftest@live@gt_lrc.html

  * igt@i915_selftest@live@workarounds:
    - {bat-dg2-10}:       NOTRUN -> [DMESG-FAIL][2]
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/bat-dg2-10/igt@i915_selftest@live@workarounds.html
    - {bat-dg2-9}:        NOTRUN -> [DMESG-FAIL][3]
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/bat-dg2-9/igt@i915_selftest@live@workarounds.html
    - {bat-dg2-8}:        NOTRUN -> [DMESG-FAIL][4]
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/bat-dg2-8/igt@i915_selftest@live@workarounds.html

  * igt@i915_suspend@basic-s3-without-i915:
    - {bat-dg2-8}:        NOTRUN -> [SKIP][5]
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/bat-dg2-8/igt@i915_suspend@basic-s3-without-i915.html

  * igt@runner@aborted:
    - {bat-adlm-1}:       NOTRUN -> [FAIL][6]
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/bat-adlm-1/igt@runner@aborted.html
    - {bat-adlp-6}:       NOTRUN -> [FAIL][7]
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/bat-adlp-6/igt@runner@aborted.html

  
Known issues
------------

  Here are the changes found in Patchwork_107502v1 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_huc_copy@huc-copy:
    - fi-rkl-11600:       NOTRUN -> [SKIP][8] ([i915#2190])
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@gem_huc_copy@huc-copy.html

  * igt@gem_lmem_swapping@basic:
    - fi-rkl-guc:         NOTRUN -> [SKIP][9] ([i915#4613]) +3 similar issues
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@gem_lmem_swapping@basic.html

  * igt@gem_lmem_swapping@parallel-random-engines:
    - fi-rkl-11600:       NOTRUN -> [SKIP][10] ([i915#4613]) +3 similar issues
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@gem_lmem_swapping@parallel-random-engines.html

  * igt@gem_tiled_pread_basic:
    - fi-rkl-11600:       NOTRUN -> [SKIP][11] ([i915#3282])
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@gem_tiled_pread_basic.html
    - fi-rkl-guc:         NOTRUN -> [SKIP][12] ([i915#3282])
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@gem_tiled_pread_basic.html

  * igt@i915_pm_backlight@basic-brightness:
    - fi-rkl-guc:         NOTRUN -> [SKIP][13] ([i915#3012])
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@i915_pm_backlight@basic-brightness.html
    - fi-rkl-11600:       NOTRUN -> [SKIP][14] ([i915#3012])
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@i915_pm_backlight@basic-brightness.html

  * igt@i915_selftest@live@execlists:
    - fi-bsw-kefka:       [PASS][15] -> [INCOMPLETE][16] ([i915#5847])
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/fi-bsw-kefka/igt@i915_selftest@live@execlists.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-bsw-kefka/igt@i915_selftest@live@execlists.html

  * igt@i915_selftest@live@gem:
    - fi-pnv-d510:        NOTRUN -> [DMESG-FAIL][17] ([i915#4528])
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-pnv-d510/igt@i915_selftest@live@gem.html

  * igt@i915_suspend@basic-s3-without-i915:
    - fi-rkl-11600:       NOTRUN -> [INCOMPLETE][18] ([i915#5982])
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@i915_suspend@basic-s3-without-i915.html

  * igt@kms_chamelium@hdmi-crc-fast:
    - fi-rkl-guc:         NOTRUN -> [SKIP][19] ([fdo#111827]) +8 similar issues
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@kms_chamelium@hdmi-crc-fast.html

  * igt@kms_chamelium@hdmi-hpd-fast:
    - fi-rkl-11600:       NOTRUN -> [SKIP][20] ([fdo#111827]) +7 similar issues
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@kms_chamelium@hdmi-hpd-fast.html

  * igt@kms_cursor_legacy@basic-busy-flip-before-cursor:
    - fi-rkl-11600:       NOTRUN -> [SKIP][21] ([i915#4103])
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@kms_cursor_legacy@basic-busy-flip-before-cursor.html
    - fi-rkl-guc:         NOTRUN -> [SKIP][22] ([i915#4103])
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@kms_cursor_legacy@basic-busy-flip-before-cursor.html

  * igt@kms_force_connector_basic@force-load-detect:
    - fi-rkl-11600:       NOTRUN -> [SKIP][23] ([fdo#109285] / [i915#4098])
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@kms_force_connector_basic@force-load-detect.html
    - fi-rkl-guc:         NOTRUN -> [SKIP][24] ([fdo#109285])
   [24]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@kms_force_connector_basic@force-load-detect.html

  * igt@kms_psr@primary_mmap_gtt:
    - fi-rkl-guc:         NOTRUN -> [SKIP][25] ([i915#1072]) +3 similar issues
   [25]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@kms_psr@primary_mmap_gtt.html

  * igt@kms_psr@sprite_plane_onoff:
    - fi-rkl-11600:       NOTRUN -> [SKIP][26] ([i915#1072]) +3 similar issues
   [26]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@kms_psr@sprite_plane_onoff.html

  * igt@kms_setmode@basic-clone-single-crtc:
    - fi-rkl-guc:         NOTRUN -> [SKIP][27] ([i915#3555] / [i915#4098])
   [27]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@kms_setmode@basic-clone-single-crtc.html
    - fi-rkl-11600:       NOTRUN -> [SKIP][28] ([i915#3555] / [i915#4098])
   [28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@kms_setmode@basic-clone-single-crtc.html

  * igt@prime_vgem@basic-fence-read:
    - fi-rkl-guc:         NOTRUN -> [SKIP][29] ([fdo#109295] / [i915#3291] / [i915#3708]) +2 similar issues
   [29]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@prime_vgem@basic-fence-read.html

  * igt@prime_vgem@basic-read:
    - fi-rkl-11600:       NOTRUN -> [SKIP][30] ([fdo#109295] / [i915#3291] / [i915#3708]) +2 similar issues
   [30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@prime_vgem@basic-read.html

  * igt@prime_vgem@basic-userptr:
    - fi-rkl-guc:         NOTRUN -> [SKIP][31] ([fdo#109295] / [i915#3301] / [i915#3708])
   [31]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@prime_vgem@basic-userptr.html
    - fi-rkl-11600:       NOTRUN -> [SKIP][32] ([fdo#109295] / [i915#3301] / [i915#3708])
   [32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-11600/igt@prime_vgem@basic-userptr.html

  * igt@runner@aborted:
    - fi-bsw-kefka:       NOTRUN -> [FAIL][33] ([fdo#109271] / [i915#4312])
   [33]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-bsw-kefka/igt@runner@aborted.html

  
#### Possible fixes ####

  * igt@core_auth@basic-auth:
    - fi-rkl-guc:         [TIMEOUT][34] -> [PASS][35] +3 similar issues
   [34]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/fi-rkl-guc/igt@core_auth@basic-auth.html
   [35]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@core_auth@basic-auth.html
    - {bat-dg2-9}:        [TIMEOUT][36] -> [PASS][37] +1 similar issue
   [36]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/bat-dg2-9/igt@core_auth@basic-auth.html
   [37]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/bat-dg2-9/igt@core_auth@basic-auth.html

  * igt@debugfs_test@read_all_entries:
    - {bat-dg2-9}:        [INCOMPLETE][38] -> [PASS][39]
   [38]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/bat-dg2-9/igt@debugfs_test@read_all_entries.html
   [39]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/bat-dg2-9/igt@debugfs_test@read_all_entries.html

  * igt@i915_module_load@load:
    - fi-rkl-guc:         [TIMEOUT][40] ([i915#6627]) -> [PASS][41]
   [40]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/fi-rkl-guc/igt@i915_module_load@load.html
   [41]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-rkl-guc/igt@i915_module_load@load.html

  * igt@i915_selftest@live@requests:
    - fi-pnv-d510:        [DMESG-FAIL][42] ([i915#4528]) -> [PASS][43]
   [42]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/fi-pnv-d510/igt@i915_selftest@live@requests.html
   [43]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/fi-pnv-d510/igt@i915_selftest@live@requests.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109285]: https://bugs.freedesktop.org/show_bug.cgi?id=109285
  [fdo#109295]: https://bugs.freedesktop.org/show_bug.cgi?id=109295
  [fdo#111827]: https://bugs.freedesktop.org/show_bug.cgi?id=111827
  [i915#1072]: https://gitlab.freedesktop.org/drm/intel/issues/1072
  [i915#1155]: https://gitlab.freedesktop.org/drm/intel/issues/1155
  [i915#2190]: https://gitlab.freedesktop.org/drm/intel/issues/2190
  [i915#2582]: https://gitlab.freedesktop.org/drm/intel/issues/2582
  [i915#3003]: https://gitlab.freedesktop.org/drm/intel/issues/3003
  [i915#3012]: https://gitlab.freedesktop.org/drm/intel/issues/3012
  [i915#3282]: https://gitlab.freedesktop.org/drm/intel/issues/3282
  [i915#3291]: https://gitlab.freedesktop.org/drm/intel/issues/3291
  [i915#3301]: https://gitlab.freedesktop.org/drm/intel/issues/3301
  [i915#3555]: https://gitlab.freedesktop.org/drm/intel/issues/3555
  [i915#3595]: https://gitlab.freedesktop.org/drm/intel/issues/3595
  [i915#3708]: https://gitlab.freedesktop.org/drm/intel/issues/3708
  [i915#4077]: https://gitlab.freedesktop.org/drm/intel/issues/4077
  [i915#4079]: https://gitlab.freedesktop.org/drm/intel/issues/4079
  [i915#4083]: https://gitlab.freedesktop.org/drm/intel/issues/4083
  [i915#4098]: https://gitlab.freedesktop.org/drm/intel/issues/4098
  [i915#4103]: https://gitlab.freedesktop.org/drm/intel/issues/4103
  [i915#4212]: https://gitlab.freedesktop.org/drm/intel/issues/4212
  [i915#4213]: https://gitlab.freedesktop.org/drm/intel/issues/4213
  [i915#4215]: https://gitlab.freedesktop.org/drm/intel/issues/4215
  [i915#4312]: https://gitlab.freedesktop.org/drm/intel/issues/4312
  [i915#4528]: https://gitlab.freedesktop.org/drm/intel/issues/4528
  [i915#4579]: https://gitlab.freedesktop.org/drm/intel/issues/4579
  [i915#4613]: https://gitlab.freedesktop.org/drm/intel/issues/4613
  [i915#4817]: https://gitlab.freedesktop.org/drm/intel/issues/4817
  [i915#4873]: https://gitlab.freedesktop.org/drm/intel/issues/4873
  [i915#5190]: https://gitlab.freedesktop.org/drm/intel/issues/5190
  [i915#5274]: https://gitlab.freedesktop.org/drm/intel/issues/5274
  [i915#5354]: https://gitlab.freedesktop.org/drm/intel/issues/5354
  [i915#5847]: https://gitlab.freedesktop.org/drm/intel/issues/5847
  [i915#5982]: https://gitlab.freedesktop.org/drm/intel/issues/5982
  [i915#6011]: https://gitlab.freedesktop.org/drm/intel/issues/6011
  [i915#6565]: https://gitlab.freedesktop.org/drm/intel/issues/6565
  [i915#6627]: https://gitlab.freedesktop.org/drm/intel/issues/6627


Build changes
-------------

  * Linux: CI_DRM_12003 -> Patchwork_107502v1

  CI-20190529: 20190529
  CI_DRM_12003: 5852b759ca0d67530d1dae6ab66c351e796fe39d @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_6632: a0ac4d449e551fd5c78b56f85cd534330ea60507 @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
  Patchwork_107502v1: 5852b759ca0d67530d1dae6ab66c351e796fe39d @ git://anongit.freedesktop.org/gfx-ci/linux


### Linux commits

f96b72cf4b50 Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/index.html

[-- Attachment #2: Type: text/html, Size: 14728 bytes --]

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [Intel-gfx] [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
  2022-08-19 12:39 [Intel-gfx] [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero" Matthew Auld
  2022-08-19 13:25 ` [Intel-gfx] ✗ Fi.CI.SPARSE: warning for " Patchwork
  2022-08-19 13:48 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
@ 2022-08-19 15:46 ` John Harrison
  2022-08-19 16:47   ` Teres Alexis, Alan Previn
  2022-08-20 13:13 ` [Intel-gfx] ✗ Fi.CI.IGT: failure for " Patchwork
  3 siblings, 1 reply; 7+ messages in thread
From: John Harrison @ 2022-08-19 15:46 UTC (permalink / raw)
  To: Matthew Auld, intel-gfx; +Cc: Alan Previn

On 8/19/2022 05:39, Matthew Auld wrote:
> This reverts commit 6a079903847cce1dd06345127d2a32f26d2cd9c6.
>
> Everything in CI using GuC is now timing out[1], and killing the machine
> with this change (perhaps a deadlock?). CI was recently on fire due to
> some changes coming in from -rc1, so likely the pre-merge CI results for
> this series were invalid? For now just revert, unless GuC experts
> already have a fix in mind.
>
> [1] https://intel-gfx-ci.01.org/tree/drm-tip/index.html?
>
> Signed-off-by: Matthew Auld <matthew.auld@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
> Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>

Given that CI was claiming a pass for the original patch set, no we 
don't have a fix in mind. It is most frustrating when CI says all green 
if the entire universe is so broken that no tests were even running :(.

John.


> ---
>   drivers/gpu/drm/i915/gem/i915_gem_context.c   |   2 +-
>   drivers/gpu/drm/i915/gt/intel_context.h       |   8 -
>   drivers/gpu/drm/i915/gt/intel_context_types.h |   7 -
>   drivers/gpu/drm/i915/gt/uc/intel_guc.h        |  17 +-
>   .../gpu/drm/i915/gt/uc/intel_guc_debugfs.c    |  60 -------
>   .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 154 +++---------------
>   drivers/gpu/drm/i915/i915_selftest.h          |   2 -
>   7 files changed, 27 insertions(+), 223 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> index df7fd1b019ec..dabdfe09f5e5 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> @@ -1454,7 +1454,7 @@ static void engines_idle_release(struct i915_gem_context *ctx,
>   		int err;
>   
>   		/* serialises with execbuf */
> -		intel_context_close(ce);
> +		set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
>   		if (!intel_context_pin_if_active(ce))
>   			continue;
>   
> diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
> index f96420f0b5bb..8e2d70630c49 100644
> --- a/drivers/gpu/drm/i915/gt/intel_context.h
> +++ b/drivers/gpu/drm/i915/gt/intel_context.h
> @@ -276,14 +276,6 @@ static inline bool intel_context_is_barrier(const struct intel_context *ce)
>   	return test_bit(CONTEXT_BARRIER_BIT, &ce->flags);
>   }
>   
> -static inline void intel_context_close(struct intel_context *ce)
> -{
> -	set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
> -
> -	if (ce->ops->close)
> -		ce->ops->close(ce);
> -}
> -
>   static inline bool intel_context_is_closed(const struct intel_context *ce)
>   {
>   	return test_bit(CONTEXT_CLOSED_BIT, &ce->flags);
> diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
> index 86ac84e2edb9..04eacae1aca5 100644
> --- a/drivers/gpu/drm/i915/gt/intel_context_types.h
> +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
> @@ -43,8 +43,6 @@ struct intel_context_ops {
>   	void (*revoke)(struct intel_context *ce, struct i915_request *rq,
>   		       unsigned int preempt_timeout_ms);
>   
> -	void (*close)(struct intel_context *ce);
> -
>   	int (*pre_pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr);
>   	int (*pin)(struct intel_context *ce, void *vaddr);
>   	void (*unpin)(struct intel_context *ce);
> @@ -210,11 +208,6 @@ struct intel_context {
>   		 * each priority bucket
>   		 */
>   		u32 prio_count[GUC_CLIENT_PRIORITY_NUM];
> -		/**
> -		 * @sched_disable_delay: worker to disable scheduling on this
> -		 * context
> -		 */
> -		struct delayed_work sched_disable_delay;
>   	} guc_state;
>   
>   	struct {
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> index 944b549b8797..804133df1ac9 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> @@ -112,10 +112,6 @@ struct intel_guc {
>   		 * refs
>   		 */
>   		struct list_head guc_id_list;
> -		/**
> -		 * @guc_ids_in_use: Number single-lrc guc_ids in use
> -		 */
> -		u16 guc_ids_in_use;
>   		/**
>   		 * @destroyed_contexts: list of contexts waiting to be destroyed
>   		 * (deregistered with the GuC)
> @@ -136,16 +132,6 @@ struct intel_guc {
>   		 * @reset_fail_mask: mask of engines that failed to reset
>   		 */
>   		intel_engine_mask_t reset_fail_mask;
> -		/**
> -		 * @sched_disable_delay_ms: schedule disable delay, in ms, for
> -		 * contexts
> -		 */
> -		u64 sched_disable_delay_ms;
> -		/**
> -		 * @sched_disable_gucid_threshold: threshold of min remaining available
> -		 * guc_ids before we start bypassing the schedule disable delay
> -		 */
> -		int sched_disable_gucid_threshold;
>   	} submission_state;
>   
>   	/**
> @@ -475,10 +461,9 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc);
>   void intel_guc_submission_cancel_requests(struct intel_guc *guc);
>   
>   void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p);
> -void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p);
>   
>   void intel_guc_write_barrier(struct intel_guc *guc);
>   
> -int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc);
> +void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p);
>   
>   #endif
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
> index c91b150bb7ac..25f09a420561 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
> @@ -71,72 +71,12 @@ static bool intel_eval_slpc_support(void *data)
>   	return intel_guc_slpc_is_used(guc);
>   }
>   
> -static int guc_sched_disable_delay_ms_get(void *data, u64 *val)
> -{
> -	struct intel_guc *guc = data;
> -
> -	if (!intel_guc_submission_is_used(guc))
> -		return -ENODEV;
> -
> -	*val = guc->submission_state.sched_disable_delay_ms;
> -
> -	return 0;
> -}
> -
> -static int guc_sched_disable_delay_ms_set(void *data, u64 val)
> -{
> -	struct intel_guc *guc = data;
> -
> -	if (!intel_guc_submission_is_used(guc))
> -		return -ENODEV;
> -
> -	guc->submission_state.sched_disable_delay_ms = val;
> -
> -	return 0;
> -}
> -DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_delay_ms_fops,
> -			guc_sched_disable_delay_ms_get,
> -			guc_sched_disable_delay_ms_set, "%lld\n");
> -
> -static int guc_sched_disable_gucid_threshold_get(void *data, u64 *val)
> -{
> -	struct intel_guc *guc = data;
> -
> -	if (!intel_guc_submission_is_used(guc))
> -		return -ENODEV;
> -
> -	*val = guc->submission_state.sched_disable_gucid_threshold;
> -	return 0;
> -}
> -
> -static int guc_sched_disable_gucid_threshold_set(void *data, u64 val)
> -{
> -	struct intel_guc *guc = data;
> -
> -	if (!intel_guc_submission_is_used(guc))
> -		return -ENODEV;
> -
> -	if (val > intel_guc_sched_disable_gucid_threshold_max(guc))
> -		guc->submission_state.sched_disable_gucid_threshold =
> -			intel_guc_sched_disable_gucid_threshold_max(guc);
> -	else
> -		guc->submission_state.sched_disable_gucid_threshold = val;
> -
> -	return 0;
> -}
> -DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_gucid_threshold_fops,
> -			guc_sched_disable_gucid_threshold_get,
> -			guc_sched_disable_gucid_threshold_set, "%lld\n");
> -
>   void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root)
>   {
>   	static const struct intel_gt_debugfs_file files[] = {
>   		{ "guc_info", &guc_info_fops, NULL },
>   		{ "guc_registered_contexts", &guc_registered_contexts_fops, NULL },
>   		{ "guc_slpc_info", &guc_slpc_info_fops, &intel_eval_slpc_support},
> -		{ "guc_sched_disable_delay_ms", &guc_sched_disable_delay_ms_fops, NULL },
> -		{ "guc_sched_disable_gucid_threshold", &guc_sched_disable_gucid_threshold_fops,
> -		   NULL },
>   	};
>   
>   	if (!intel_guc_is_supported(guc))
> 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 a0cebb4590e9..0d56b615bf78 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -65,13 +65,7 @@
>    * corresponding G2H returns indicating the scheduling disable operation has
>    * completed it is safe to unpin the context. While a disable is in flight it
>    * isn't safe to resubmit the context so a fence is used to stall all future
> - * requests of that context until the G2H is returned. Because this interaction
> - * with the GuC takes a non-zero amount of time we delay the disabling of
> - * scheduling after the pin count goes to zero by a configurable period of time
> - * (see SCHED_DISABLE_DELAY_MS). The thought is this gives the user a window of
> - * time to resubmit something on the context before doing this costly operation.
> - * This delay is only done if the context isn't closed and the guc_id usage is
> - * less than a threshold (see NUM_SCHED_DISABLE_GUC_IDS_THRESHOLD).
> + * requests of that context until the G2H is returned.
>    *
>    * Context deregistration:
>    * Before a context can be destroyed or if we steal its guc_id we must
> @@ -1995,9 +1989,6 @@ static int new_guc_id(struct intel_guc *guc, struct intel_context *ce)
>   	if (unlikely(ret < 0))
>   		return ret;
>   
> -	if (!intel_context_is_parent(ce))
> -		++guc->submission_state.guc_ids_in_use;
> -
>   	ce->guc_id.id = ret;
>   	return 0;
>   }
> @@ -2007,16 +1998,14 @@ static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce)
>   	GEM_BUG_ON(intel_context_is_child(ce));
>   
>   	if (!context_guc_id_invalid(ce)) {
> -		if (intel_context_is_parent(ce)) {
> +		if (intel_context_is_parent(ce))
>   			bitmap_release_region(guc->submission_state.guc_ids_bitmap,
>   					      ce->guc_id.id,
>   					      order_base_2(ce->parallel.number_children
>   							   + 1));
> -		} else {
> -			--guc->submission_state.guc_ids_in_use;
> +		else
>   			ida_simple_remove(&guc->submission_state.guc_ids,
>   					  ce->guc_id.id);
> -		}
>   		clr_ctx_id_mapping(guc, ce->guc_id.id);
>   		set_context_guc_id_invalid(ce);
>   	}
> @@ -3004,98 +2993,41 @@ guc_context_revoke(struct intel_context *ce, struct i915_request *rq,
>   	}
>   }
>   
> -static void guc_context_sched_disable(struct intel_context *ce);
> -
> -static void do_sched_disable(struct intel_guc *guc, struct intel_context *ce,
> -			     unsigned long flags)
> -	__releases(ce->guc_state.lock)
> +static void guc_context_sched_disable(struct intel_context *ce)
>   {
> +	struct intel_guc *guc = ce_to_guc(ce);
> +	unsigned long flags;
>   	struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm;
>   	intel_wakeref_t wakeref;
> +	u16 guc_id;
>   
> -	lockdep_assert_held(&ce->guc_state.lock);
> -
> -	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> -
> -	with_intel_runtime_pm(runtime_pm, wakeref)
> -		guc_context_sched_disable(ce);
> -}
> -
> -static bool bypass_sched_disable(struct intel_guc *guc,
> -				 struct intel_context *ce)
> -{
> -	lockdep_assert_held(&ce->guc_state.lock);
>   	GEM_BUG_ON(intel_context_is_child(ce));
>   
> -	if (submission_disabled(guc) || context_guc_id_invalid(ce) ||
> -	    !ctx_id_mapped(guc, ce->guc_id.id)) {
> -		clr_context_enabled(ce);
> -		return true;
> -	}
> -
> -	return !context_enabled(ce);
> -}
> -
> -static void __delay_sched_disable(struct work_struct *wrk)
> -{
> -	struct intel_context *ce =
> -		container_of(wrk, typeof(*ce), guc_state.sched_disable_delay.work);
> -	struct intel_guc *guc = ce_to_guc(ce);
> -	unsigned long flags;
> -
>   	spin_lock_irqsave(&ce->guc_state.lock, flags);
>   
> -	if (bypass_sched_disable(guc, ce)) {
> -		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> -		intel_context_sched_disable_unpin(ce);
> -	} else {
> -		do_sched_disable(guc, ce, flags);
> -	}
> -}
> -
> -static bool guc_id_pressure(struct intel_guc *guc, struct intel_context *ce)
> -{
> -	/*
> -	 * parent contexts are perma-pinned, if we are unpinning do schedule
> -	 * disable immediately.
> -	 */
> -	if (intel_context_is_parent(ce))
> -		return true;
> -
>   	/*
> -	 * If we are beyond the threshold for avail guc_ids, do schedule disable immediately.
> +	 * We have to check if the context has been disabled by another thread,
> +	 * check if submssion has been disabled to seal a race with reset and
> +	 * finally check if any more requests have been committed to the
> +	 * context ensursing that a request doesn't slip through the
> +	 * 'context_pending_disable' fence.
>   	 */
> -	return guc->submission_state.guc_ids_in_use >
> -		guc->submission_state.sched_disable_gucid_threshold;
> -}
> -
> -static void guc_context_sched_disable(struct intel_context *ce)
> -{
> -	struct intel_guc *guc = ce_to_guc(ce);
> -	u64 delay = guc->submission_state.sched_disable_delay_ms;
> -	unsigned long flags;
> -
> -	spin_lock_irqsave(&ce->guc_state.lock, flags);
> -
> -	if (bypass_sched_disable(guc, ce)) {
> -		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> -		intel_context_sched_disable_unpin(ce);
> -	} else if (!intel_context_is_closed(ce) && !guc_id_pressure(guc, ce) &&
> -		   delay) {
> +	if (unlikely(!context_enabled(ce) || submission_disabled(guc) ||
> +		     context_has_committed_requests(ce))) {
> +		clr_context_enabled(ce);
>   		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> -		mod_delayed_work(system_unbound_wq,
> -				 &ce->guc_state.sched_disable_delay,
> -				 msecs_to_jiffies(delay));
> -	} else {
> -		do_sched_disable(guc, ce, flags);
> +		goto unpin;
>   	}
> -}
> +	guc_id = prep_context_pending_disable(ce);
>   
> -static void guc_context_close(struct intel_context *ce)
> -{
> -	if (test_bit(CONTEXT_GUC_INIT, &ce->flags) &&
> -	    cancel_delayed_work(&ce->guc_state.sched_disable_delay))
> -		__delay_sched_disable(&ce->guc_state.sched_disable_delay.work);
> +	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> +
> +	with_intel_runtime_pm(runtime_pm, wakeref)
> +		__guc_context_sched_disable(guc, ce, guc_id);
> +
> +	return;
> +unpin:
> +	intel_context_sched_disable_unpin(ce);
>   }
>   
>   static inline void guc_lrc_desc_unpin(struct intel_context *ce)
> @@ -3414,8 +3346,6 @@ static void remove_from_context(struct i915_request *rq)
>   static const struct intel_context_ops guc_context_ops = {
>   	.alloc = guc_context_alloc,
>   
> -	.close = guc_context_close,
> -
>   	.pre_pin = guc_context_pre_pin,
>   	.pin = guc_context_pin,
>   	.unpin = guc_context_unpin,
> @@ -3498,10 +3428,6 @@ static void guc_context_init(struct intel_context *ce)
>   	rcu_read_unlock();
>   
>   	ce->guc_state.prio = map_i915_prio_to_guc_prio(prio);
> -
> -	INIT_DELAYED_WORK(&ce->guc_state.sched_disable_delay,
> -			  __delay_sched_disable);
> -
>   	set_bit(CONTEXT_GUC_INIT, &ce->flags);
>   }
>   
> @@ -3539,9 +3465,6 @@ static int guc_request_alloc(struct i915_request *rq)
>   	if (unlikely(!test_bit(CONTEXT_GUC_INIT, &ce->flags)))
>   		guc_context_init(ce);
>   
> -	if (cancel_delayed_work(&ce->guc_state.sched_disable_delay))
> -		intel_context_sched_disable_unpin(ce);
> -
>   	/*
>   	 * Call pin_guc_id here rather than in the pinning step as with
>   	 * dma_resv, contexts can be repeatedly pinned / unpinned trashing the
> @@ -3672,8 +3595,6 @@ static int guc_virtual_context_alloc(struct intel_context *ce)
>   static const struct intel_context_ops virtual_guc_context_ops = {
>   	.alloc = guc_virtual_context_alloc,
>   
> -	.close = guc_context_close,
> -
>   	.pre_pin = guc_virtual_context_pre_pin,
>   	.pin = guc_virtual_context_pin,
>   	.unpin = guc_virtual_context_unpin,
> @@ -3763,8 +3684,6 @@ static void guc_child_context_destroy(struct kref *kref)
>   static const struct intel_context_ops virtual_parent_context_ops = {
>   	.alloc = guc_virtual_context_alloc,
>   
> -	.close = guc_context_close,
> -
>   	.pre_pin = guc_context_pre_pin,
>   	.pin = guc_parent_context_pin,
>   	.unpin = guc_parent_context_unpin,
> @@ -4295,26 +4214,6 @@ static bool __guc_submission_selected(struct intel_guc *guc)
>   	return i915->params.enable_guc & ENABLE_GUC_SUBMISSION;
>   }
>   
> -int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc)
> -{
> -	return guc->submission_state.num_guc_ids - NUMBER_MULTI_LRC_GUC_ID(guc);
> -}
> -
> -/*
> - * This default value of 33 milisecs (+1 milisec round up) ensures 30fps or higher
> - * workloads are able to enjoy the latency reduction when delaying the schedule-disable
> - * operation. This matches the 30fps game-render + encode (real world) workload this
> - * knob was tested against.
> - */
> -#define SCHED_DISABLE_DELAY_MS	34
> -
> -/*
> - * A threshold of 75% is a reasonable starting point considering that real world apps
> - * generally don't get anywhere near this.
> - */
> -#define NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(__guc) \
> -	(((intel_guc_sched_disable_gucid_threshold_max(guc)) * 3) / 4)
> -
>   void intel_guc_submission_init_early(struct intel_guc *guc)
>   {
>   	xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ);
> @@ -4331,10 +4230,7 @@ void intel_guc_submission_init_early(struct intel_guc *guc)
>   	spin_lock_init(&guc->timestamp.lock);
>   	INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping);
>   
> -	guc->submission_state.sched_disable_delay_ms = SCHED_DISABLE_DELAY_MS;
>   	guc->submission_state.num_guc_ids = GUC_MAX_CONTEXT_ID;
> -	guc->submission_state.sched_disable_gucid_threshold =
> -		NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(guc);
>   	guc->submission_supported = __guc_submission_supported(guc);
>   	guc->submission_selected = __guc_submission_selected(guc);
>   }
> diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
> index bdf3e22c0a34..f54de0499be7 100644
> --- a/drivers/gpu/drm/i915/i915_selftest.h
> +++ b/drivers/gpu/drm/i915/i915_selftest.h
> @@ -92,14 +92,12 @@ int __i915_subtests(const char *caller,
>   			T, ARRAY_SIZE(T), data)
>   #define i915_live_subtests(T, data) ({ \
>   	typecheck(struct drm_i915_private *, data); \
> -	(data)->gt[0]->uc.guc.submission_state.sched_disable_delay_ms = 0; \
>   	__i915_subtests(__func__, \
>   			__i915_live_setup, __i915_live_teardown, \
>   			T, ARRAY_SIZE(T), data); \
>   })
>   #define intel_gt_live_subtests(T, data) ({ \
>   	typecheck(struct intel_gt *, data); \
> -	(data)->uc.guc.submission_state.sched_disable_delay_ms = 0; \
>   	__i915_subtests(__func__, \
>   			__intel_gt_live_setup, __intel_gt_live_teardown, \
>   			T, ARRAY_SIZE(T), data); \


^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [Intel-gfx] [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
  2022-08-19 15:46 ` [Intel-gfx] [PATCH] " John Harrison
@ 2022-08-19 16:47   ` Teres Alexis, Alan Previn
  2022-09-01 15:49     ` Teres Alexis, Alan Previn
  0 siblings, 1 reply; 7+ messages in thread
From: Teres Alexis, Alan Previn @ 2022-08-19 16:47 UTC (permalink / raw)
  To: Harrison, John C, Auld, Matthew, intel-gfx@lists.freedesktop.org

Will look into this - apologies for the trouble Matt. 
...alan

-----Original Message-----
From: Harrison, John C <john.c.harrison@intel.com> 
Sent: Friday, August 19, 2022 8:46 AM
To: Auld, Matthew <matthew.auld@intel.com>; intel-gfx@lists.freedesktop.org
Cc: Brost, Matthew <matthew.brost@intel.com>; Teres Alexis, Alan Previn <alan.previn.teres.alexis@intel.com>
Subject: Re: [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"

On 8/19/2022 05:39, Matthew Auld wrote:
> This reverts commit 6a079903847cce1dd06345127d2a32f26d2cd9c6.
>
> Everything in CI using GuC is now timing out[1], and killing the 
> machine with this change (perhaps a deadlock?). CI was recently on 
> fire due to some changes coming in from -rc1, so likely the pre-merge 
> CI results for this series were invalid? For now just revert, unless 
> GuC experts already have a fix in mind.
>
> [1] https://intel-gfx-ci.01.org/tree/drm-tip/index.html?
>
> Signed-off-by: Matthew Auld <matthew.auld@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
> Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>

Given that CI was claiming a pass for the original patch set, no we don't have a fix in mind. It is most frustrating when CI says all green if the entire universe is so broken that no tests were even running :(.

John.


> ---
>   drivers/gpu/drm/i915/gem/i915_gem_context.c   |   2 +-
>   drivers/gpu/drm/i915/gt/intel_context.h       |   8 -
>   drivers/gpu/drm/i915/gt/intel_context_types.h |   7 -
>   drivers/gpu/drm/i915/gt/uc/intel_guc.h        |  17 +-
>   .../gpu/drm/i915/gt/uc/intel_guc_debugfs.c    |  60 -------
>   .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 154 +++---------------
>   drivers/gpu/drm/i915/i915_selftest.h          |   2 -
>   7 files changed, 27 insertions(+), 223 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c 
> b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> index df7fd1b019ec..dabdfe09f5e5 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> @@ -1454,7 +1454,7 @@ static void engines_idle_release(struct i915_gem_context *ctx,
>   		int err;
>   
>   		/* serialises with execbuf */
> -		intel_context_close(ce);
> +		set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
>   		if (!intel_context_pin_if_active(ce))
>   			continue;
>   
> diff --git a/drivers/gpu/drm/i915/gt/intel_context.h 
> b/drivers/gpu/drm/i915/gt/intel_context.h
> index f96420f0b5bb..8e2d70630c49 100644
> --- a/drivers/gpu/drm/i915/gt/intel_context.h
> +++ b/drivers/gpu/drm/i915/gt/intel_context.h
> @@ -276,14 +276,6 @@ static inline bool intel_context_is_barrier(const struct intel_context *ce)
>   	return test_bit(CONTEXT_BARRIER_BIT, &ce->flags);
>   }
>   
> -static inline void intel_context_close(struct intel_context *ce) -{
> -	set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
> -
> -	if (ce->ops->close)
> -		ce->ops->close(ce);
> -}
> -
>   static inline bool intel_context_is_closed(const struct intel_context *ce)
>   {
>   	return test_bit(CONTEXT_CLOSED_BIT, &ce->flags); diff --git 
> a/drivers/gpu/drm/i915/gt/intel_context_types.h 
> b/drivers/gpu/drm/i915/gt/intel_context_types.h
> index 86ac84e2edb9..04eacae1aca5 100644
> --- a/drivers/gpu/drm/i915/gt/intel_context_types.h
> +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
> @@ -43,8 +43,6 @@ struct intel_context_ops {
>   	void (*revoke)(struct intel_context *ce, struct i915_request *rq,
>   		       unsigned int preempt_timeout_ms);
>   
> -	void (*close)(struct intel_context *ce);
> -
>   	int (*pre_pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr);
>   	int (*pin)(struct intel_context *ce, void *vaddr);
>   	void (*unpin)(struct intel_context *ce); @@ -210,11 +208,6 @@ 
> struct intel_context {
>   		 * each priority bucket
>   		 */
>   		u32 prio_count[GUC_CLIENT_PRIORITY_NUM];
> -		/**
> -		 * @sched_disable_delay: worker to disable scheduling on this
> -		 * context
> -		 */
> -		struct delayed_work sched_disable_delay;
>   	} guc_state;
>   
>   	struct {
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h 
> b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> index 944b549b8797..804133df1ac9 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> @@ -112,10 +112,6 @@ struct intel_guc {
>   		 * refs
>   		 */
>   		struct list_head guc_id_list;
> -		/**
> -		 * @guc_ids_in_use: Number single-lrc guc_ids in use
> -		 */
> -		u16 guc_ids_in_use;
>   		/**
>   		 * @destroyed_contexts: list of contexts waiting to be destroyed
>   		 * (deregistered with the GuC)
> @@ -136,16 +132,6 @@ struct intel_guc {
>   		 * @reset_fail_mask: mask of engines that failed to reset
>   		 */
>   		intel_engine_mask_t reset_fail_mask;
> -		/**
> -		 * @sched_disable_delay_ms: schedule disable delay, in ms, for
> -		 * contexts
> -		 */
> -		u64 sched_disable_delay_ms;
> -		/**
> -		 * @sched_disable_gucid_threshold: threshold of min remaining available
> -		 * guc_ids before we start bypassing the schedule disable delay
> -		 */
> -		int sched_disable_gucid_threshold;
>   	} submission_state;
>   
>   	/**
> @@ -475,10 +461,9 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc);
>   void intel_guc_submission_cancel_requests(struct intel_guc *guc);
>   
>   void intel_guc_load_status(struct intel_guc *guc, struct drm_printer 
> *p); -void intel_guc_dump_time_info(struct intel_guc *guc, struct 
> drm_printer *p);
>   
>   void intel_guc_write_barrier(struct intel_guc *guc);
>   
> -int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc 
> *guc);
> +void intel_guc_dump_time_info(struct intel_guc *guc, struct 
> +drm_printer *p);
>   
>   #endif
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c 
> b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
> index c91b150bb7ac..25f09a420561 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
> @@ -71,72 +71,12 @@ static bool intel_eval_slpc_support(void *data)
>   	return intel_guc_slpc_is_used(guc);
>   }
>   
> -static int guc_sched_disable_delay_ms_get(void *data, u64 *val) -{
> -	struct intel_guc *guc = data;
> -
> -	if (!intel_guc_submission_is_used(guc))
> -		return -ENODEV;
> -
> -	*val = guc->submission_state.sched_disable_delay_ms;
> -
> -	return 0;
> -}
> -
> -static int guc_sched_disable_delay_ms_set(void *data, u64 val) -{
> -	struct intel_guc *guc = data;
> -
> -	if (!intel_guc_submission_is_used(guc))
> -		return -ENODEV;
> -
> -	guc->submission_state.sched_disable_delay_ms = val;
> -
> -	return 0;
> -}
> -DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_delay_ms_fops,
> -			guc_sched_disable_delay_ms_get,
> -			guc_sched_disable_delay_ms_set, "%lld\n");
> -
> -static int guc_sched_disable_gucid_threshold_get(void *data, u64 
> *val) -{
> -	struct intel_guc *guc = data;
> -
> -	if (!intel_guc_submission_is_used(guc))
> -		return -ENODEV;
> -
> -	*val = guc->submission_state.sched_disable_gucid_threshold;
> -	return 0;
> -}
> -
> -static int guc_sched_disable_gucid_threshold_set(void *data, u64 val) 
> -{
> -	struct intel_guc *guc = data;
> -
> -	if (!intel_guc_submission_is_used(guc))
> -		return -ENODEV;
> -
> -	if (val > intel_guc_sched_disable_gucid_threshold_max(guc))
> -		guc->submission_state.sched_disable_gucid_threshold =
> -			intel_guc_sched_disable_gucid_threshold_max(guc);
> -	else
> -		guc->submission_state.sched_disable_gucid_threshold = val;
> -
> -	return 0;
> -}
> -DEFINE_SIMPLE_ATTRIBUTE(guc_sched_disable_gucid_threshold_fops,
> -			guc_sched_disable_gucid_threshold_get,
> -			guc_sched_disable_gucid_threshold_set, "%lld\n");
> -
>   void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root)
>   {
>   	static const struct intel_gt_debugfs_file files[] = {
>   		{ "guc_info", &guc_info_fops, NULL },
>   		{ "guc_registered_contexts", &guc_registered_contexts_fops, NULL },
>   		{ "guc_slpc_info", &guc_slpc_info_fops, &intel_eval_slpc_support},
> -		{ "guc_sched_disable_delay_ms", &guc_sched_disable_delay_ms_fops, NULL },
> -		{ "guc_sched_disable_gucid_threshold", &guc_sched_disable_gucid_threshold_fops,
> -		   NULL },
>   	};
>   
>   	if (!intel_guc_is_supported(guc))
> 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 a0cebb4590e9..0d56b615bf78 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -65,13 +65,7 @@
>    * corresponding G2H returns indicating the scheduling disable operation has
>    * completed it is safe to unpin the context. While a disable is in flight it
>    * isn't safe to resubmit the context so a fence is used to stall 
> all future
> - * requests of that context until the G2H is returned. Because this 
> interaction
> - * with the GuC takes a non-zero amount of time we delay the 
> disabling of
> - * scheduling after the pin count goes to zero by a configurable 
> period of time
> - * (see SCHED_DISABLE_DELAY_MS). The thought is this gives the user a 
> window of
> - * time to resubmit something on the context before doing this costly operation.
> - * This delay is only done if the context isn't closed and the guc_id 
> usage is
> - * less than a threshold (see NUM_SCHED_DISABLE_GUC_IDS_THRESHOLD).
> + * requests of that context until the G2H is returned.
>    *
>    * Context deregistration:
>    * Before a context can be destroyed or if we steal its guc_id we 
> must @@ -1995,9 +1989,6 @@ static int new_guc_id(struct intel_guc *guc, struct intel_context *ce)
>   	if (unlikely(ret < 0))
>   		return ret;
>   
> -	if (!intel_context_is_parent(ce))
> -		++guc->submission_state.guc_ids_in_use;
> -
>   	ce->guc_id.id = ret;
>   	return 0;
>   }
> @@ -2007,16 +1998,14 @@ static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce)
>   	GEM_BUG_ON(intel_context_is_child(ce));
>   
>   	if (!context_guc_id_invalid(ce)) {
> -		if (intel_context_is_parent(ce)) {
> +		if (intel_context_is_parent(ce))
>   			bitmap_release_region(guc->submission_state.guc_ids_bitmap,
>   					      ce->guc_id.id,
>   					      order_base_2(ce->parallel.number_children
>   							   + 1));
> -		} else {
> -			--guc->submission_state.guc_ids_in_use;
> +		else
>   			ida_simple_remove(&guc->submission_state.guc_ids,
>   					  ce->guc_id.id);
> -		}
>   		clr_ctx_id_mapping(guc, ce->guc_id.id);
>   		set_context_guc_id_invalid(ce);
>   	}
> @@ -3004,98 +2993,41 @@ guc_context_revoke(struct intel_context *ce, struct i915_request *rq,
>   	}
>   }
>   
> -static void guc_context_sched_disable(struct intel_context *ce);
> -
> -static void do_sched_disable(struct intel_guc *guc, struct intel_context *ce,
> -			     unsigned long flags)
> -	__releases(ce->guc_state.lock)
> +static void guc_context_sched_disable(struct intel_context *ce)
>   {
> +	struct intel_guc *guc = ce_to_guc(ce);
> +	unsigned long flags;
>   	struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm;
>   	intel_wakeref_t wakeref;
> +	u16 guc_id;
>   
> -	lockdep_assert_held(&ce->guc_state.lock);
> -
> -	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> -
> -	with_intel_runtime_pm(runtime_pm, wakeref)
> -		guc_context_sched_disable(ce);
> -}
> -
> -static bool bypass_sched_disable(struct intel_guc *guc,
> -				 struct intel_context *ce)
> -{
> -	lockdep_assert_held(&ce->guc_state.lock);
>   	GEM_BUG_ON(intel_context_is_child(ce));
>   
> -	if (submission_disabled(guc) || context_guc_id_invalid(ce) ||
> -	    !ctx_id_mapped(guc, ce->guc_id.id)) {
> -		clr_context_enabled(ce);
> -		return true;
> -	}
> -
> -	return !context_enabled(ce);
> -}
> -
> -static void __delay_sched_disable(struct work_struct *wrk) -{
> -	struct intel_context *ce =
> -		container_of(wrk, typeof(*ce), guc_state.sched_disable_delay.work);
> -	struct intel_guc *guc = ce_to_guc(ce);
> -	unsigned long flags;
> -
>   	spin_lock_irqsave(&ce->guc_state.lock, flags);
>   
> -	if (bypass_sched_disable(guc, ce)) {
> -		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> -		intel_context_sched_disable_unpin(ce);
> -	} else {
> -		do_sched_disable(guc, ce, flags);
> -	}
> -}
> -
> -static bool guc_id_pressure(struct intel_guc *guc, struct 
> intel_context *ce) -{
> -	/*
> -	 * parent contexts are perma-pinned, if we are unpinning do schedule
> -	 * disable immediately.
> -	 */
> -	if (intel_context_is_parent(ce))
> -		return true;
> -
>   	/*
> -	 * If we are beyond the threshold for avail guc_ids, do schedule disable immediately.
> +	 * We have to check if the context has been disabled by another thread,
> +	 * check if submssion has been disabled to seal a race with reset and
> +	 * finally check if any more requests have been committed to the
> +	 * context ensursing that a request doesn't slip through the
> +	 * 'context_pending_disable' fence.
>   	 */
> -	return guc->submission_state.guc_ids_in_use >
> -		guc->submission_state.sched_disable_gucid_threshold;
> -}
> -
> -static void guc_context_sched_disable(struct intel_context *ce) -{
> -	struct intel_guc *guc = ce_to_guc(ce);
> -	u64 delay = guc->submission_state.sched_disable_delay_ms;
> -	unsigned long flags;
> -
> -	spin_lock_irqsave(&ce->guc_state.lock, flags);
> -
> -	if (bypass_sched_disable(guc, ce)) {
> -		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> -		intel_context_sched_disable_unpin(ce);
> -	} else if (!intel_context_is_closed(ce) && !guc_id_pressure(guc, ce) &&
> -		   delay) {
> +	if (unlikely(!context_enabled(ce) || submission_disabled(guc) ||
> +		     context_has_committed_requests(ce))) {
> +		clr_context_enabled(ce);
>   		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> -		mod_delayed_work(system_unbound_wq,
> -				 &ce->guc_state.sched_disable_delay,
> -				 msecs_to_jiffies(delay));
> -	} else {
> -		do_sched_disable(guc, ce, flags);
> +		goto unpin;
>   	}
> -}
> +	guc_id = prep_context_pending_disable(ce);
>   
> -static void guc_context_close(struct intel_context *ce) -{
> -	if (test_bit(CONTEXT_GUC_INIT, &ce->flags) &&
> -	    cancel_delayed_work(&ce->guc_state.sched_disable_delay))
> -		__delay_sched_disable(&ce->guc_state.sched_disable_delay.work);
> +	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> +
> +	with_intel_runtime_pm(runtime_pm, wakeref)
> +		__guc_context_sched_disable(guc, ce, guc_id);
> +
> +	return;
> +unpin:
> +	intel_context_sched_disable_unpin(ce);
>   }
>   
>   static inline void guc_lrc_desc_unpin(struct intel_context *ce) @@ 
> -3414,8 +3346,6 @@ static void remove_from_context(struct i915_request *rq)
>   static const struct intel_context_ops guc_context_ops = {
>   	.alloc = guc_context_alloc,
>   
> -	.close = guc_context_close,
> -
>   	.pre_pin = guc_context_pre_pin,
>   	.pin = guc_context_pin,
>   	.unpin = guc_context_unpin,
> @@ -3498,10 +3428,6 @@ static void guc_context_init(struct intel_context *ce)
>   	rcu_read_unlock();
>   
>   	ce->guc_state.prio = map_i915_prio_to_guc_prio(prio);
> -
> -	INIT_DELAYED_WORK(&ce->guc_state.sched_disable_delay,
> -			  __delay_sched_disable);
> -
>   	set_bit(CONTEXT_GUC_INIT, &ce->flags);
>   }
>   
> @@ -3539,9 +3465,6 @@ static int guc_request_alloc(struct i915_request *rq)
>   	if (unlikely(!test_bit(CONTEXT_GUC_INIT, &ce->flags)))
>   		guc_context_init(ce);
>   
> -	if (cancel_delayed_work(&ce->guc_state.sched_disable_delay))
> -		intel_context_sched_disable_unpin(ce);
> -
>   	/*
>   	 * Call pin_guc_id here rather than in the pinning step as with
>   	 * dma_resv, contexts can be repeatedly pinned / unpinned trashing 
> the @@ -3672,8 +3595,6 @@ static int guc_virtual_context_alloc(struct intel_context *ce)
>   static const struct intel_context_ops virtual_guc_context_ops = {
>   	.alloc = guc_virtual_context_alloc,
>   
> -	.close = guc_context_close,
> -
>   	.pre_pin = guc_virtual_context_pre_pin,
>   	.pin = guc_virtual_context_pin,
>   	.unpin = guc_virtual_context_unpin, @@ -3763,8 +3684,6 @@ static 
> void guc_child_context_destroy(struct kref *kref)
>   static const struct intel_context_ops virtual_parent_context_ops = {
>   	.alloc = guc_virtual_context_alloc,
>   
> -	.close = guc_context_close,
> -
>   	.pre_pin = guc_context_pre_pin,
>   	.pin = guc_parent_context_pin,
>   	.unpin = guc_parent_context_unpin,
> @@ -4295,26 +4214,6 @@ static bool __guc_submission_selected(struct intel_guc *guc)
>   	return i915->params.enable_guc & ENABLE_GUC_SUBMISSION;
>   }
>   
> -int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc 
> *guc) -{
> -	return guc->submission_state.num_guc_ids - NUMBER_MULTI_LRC_GUC_ID(guc);
> -}
> -
> -/*
> - * This default value of 33 milisecs (+1 milisec round up) ensures 
> 30fps or higher
> - * workloads are able to enjoy the latency reduction when delaying 
> the schedule-disable
> - * operation. This matches the 30fps game-render + encode (real 
> world) workload this
> - * knob was tested against.
> - */
> -#define SCHED_DISABLE_DELAY_MS	34
> -
> -/*
> - * A threshold of 75% is a reasonable starting point considering that 
> real world apps
> - * generally don't get anywhere near this.
> - */
> -#define NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(__guc) \
> -	(((intel_guc_sched_disable_gucid_threshold_max(guc)) * 3) / 4)
> -
>   void intel_guc_submission_init_early(struct intel_guc *guc)
>   {
>   	xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ); @@ -4331,10 
> +4230,7 @@ void intel_guc_submission_init_early(struct intel_guc *guc)
>   	spin_lock_init(&guc->timestamp.lock);
>   	INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping);
>   
> -	guc->submission_state.sched_disable_delay_ms = SCHED_DISABLE_DELAY_MS;
>   	guc->submission_state.num_guc_ids = GUC_MAX_CONTEXT_ID;
> -	guc->submission_state.sched_disable_gucid_threshold =
> -		NUM_SCHED_DISABLE_GUCIDS_DEFAULT_THRESHOLD(guc);
>   	guc->submission_supported = __guc_submission_supported(guc);
>   	guc->submission_selected = __guc_submission_selected(guc);
>   }
> diff --git a/drivers/gpu/drm/i915/i915_selftest.h 
> b/drivers/gpu/drm/i915/i915_selftest.h
> index bdf3e22c0a34..f54de0499be7 100644
> --- a/drivers/gpu/drm/i915/i915_selftest.h
> +++ b/drivers/gpu/drm/i915/i915_selftest.h
> @@ -92,14 +92,12 @@ int __i915_subtests(const char *caller,
>   			T, ARRAY_SIZE(T), data)
>   #define i915_live_subtests(T, data) ({ \
>   	typecheck(struct drm_i915_private *, data); \
> -	(data)->gt[0]->uc.guc.submission_state.sched_disable_delay_ms = 0; \
>   	__i915_subtests(__func__, \
>   			__i915_live_setup, __i915_live_teardown, \
>   			T, ARRAY_SIZE(T), data); \
>   })
>   #define intel_gt_live_subtests(T, data) ({ \
>   	typecheck(struct intel_gt *, data); \
> -	(data)->uc.guc.submission_state.sched_disable_delay_ms = 0; \
>   	__i915_subtests(__func__, \
>   			__intel_gt_live_setup, __intel_gt_live_teardown, \
>   			T, ARRAY_SIZE(T), data); \


^ permalink raw reply	[flat|nested] 7+ messages in thread

* [Intel-gfx] ✗ Fi.CI.IGT: failure for Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
  2022-08-19 12:39 [Intel-gfx] [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero" Matthew Auld
                   ` (2 preceding siblings ...)
  2022-08-19 15:46 ` [Intel-gfx] [PATCH] " John Harrison
@ 2022-08-20 13:13 ` Patchwork
  3 siblings, 0 replies; 7+ messages in thread
From: Patchwork @ 2022-08-20 13:13 UTC (permalink / raw)
  To: Matthew Auld; +Cc: intel-gfx

[-- Attachment #1: Type: text/plain, Size: 34851 bytes --]

== Series Details ==

Series: Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
URL   : https://patchwork.freedesktop.org/series/107502/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_12003_full -> Patchwork_107502v1_full
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_107502v1_full absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_107502v1_full, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  

Participating hosts (10 -> 13)
------------------------------

  Additional (3): shard-rkl shard-dg1 shard-tglu 

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_107502v1_full:

### IGT changes ###

#### Possible regressions ####

  * igt@kms_flip@flip-vs-blocking-wf-vblank@d-edp1:
    - shard-tglb:         [PASS][1] -> [INCOMPLETE][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-tglb3/igt@kms_flip@flip-vs-blocking-wf-vblank@d-edp1.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-tglb7/igt@kms_flip@flip-vs-blocking-wf-vblank@d-edp1.html

  
Known issues
------------

  Here are the changes found in Patchwork_107502v1_full that come from known issues:

### CI changes ###

#### Issues hit ####

  * boot:
    - shard-snb:          ([PASS][3], [PASS][4], [PASS][5], [PASS][6], [PASS][7], [PASS][8], [PASS][9], [PASS][10], [PASS][11], [PASS][12], [PASS][13], [PASS][14], [PASS][15], [PASS][16], [PASS][17], [PASS][18], [PASS][19], [PASS][20], [PASS][21], [PASS][22], [PASS][23], [PASS][24], [PASS][25], [PASS][26], [PASS][27]) -> ([PASS][28], [PASS][29], [PASS][30], [PASS][31], [PASS][32], [PASS][33], [PASS][34], [PASS][35], [PASS][36], [PASS][37], [FAIL][38], [PASS][39], [PASS][40], [PASS][41], [PASS][42], [PASS][43], [PASS][44], [PASS][45], [PASS][46], [PASS][47], [PASS][48], [PASS][49], [PASS][50], [PASS][51], [PASS][52]) ([i915#4338])
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb6/boot.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb6/boot.html
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb6/boot.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb6/boot.html
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb6/boot.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb6/boot.html
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb5/boot.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb5/boot.html
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb5/boot.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb5/boot.html
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb5/boot.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb5/boot.html
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb4/boot.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb4/boot.html
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb4/boot.html
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb4/boot.html
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb4/boot.html
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb4/boot.html
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb4/boot.html
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb2/boot.html
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb2/boot.html
   [24]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb2/boot.html
   [25]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb2/boot.html
   [26]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb2/boot.html
   [27]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-snb2/boot.html
   [28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb6/boot.html
   [29]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb6/boot.html
   [30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb6/boot.html
   [31]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb6/boot.html
   [32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb6/boot.html
   [33]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb6/boot.html
   [34]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb5/boot.html
   [35]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb5/boot.html
   [36]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb5/boot.html
   [37]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb5/boot.html
   [38]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb5/boot.html
   [39]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb5/boot.html
   [40]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb5/boot.html
   [41]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb4/boot.html
   [42]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb4/boot.html
   [43]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb4/boot.html
   [44]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb4/boot.html
   [45]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb4/boot.html
   [46]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb4/boot.html
   [47]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb4/boot.html
   [48]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb2/boot.html
   [49]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb2/boot.html
   [50]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb2/boot.html
   [51]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb2/boot.html
   [52]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-snb2/boot.html

  

### IGT changes ###

#### Issues hit ####

  * igt@gem_eio@unwedge-stress:
    - shard-tglb:         [PASS][53] -> [FAIL][54] ([i915#5784])
   [53]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-tglb7/igt@gem_eio@unwedge-stress.html
   [54]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-tglb5/igt@gem_eio@unwedge-stress.html

  * igt@gem_exec_balancer@parallel-contexts:
    - shard-iclb:         [PASS][55] -> [SKIP][56] ([i915#4525]) +1 similar issue
   [55]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-iclb4/igt@gem_exec_balancer@parallel-contexts.html
   [56]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-iclb8/igt@gem_exec_balancer@parallel-contexts.html

  * igt@gem_exec_endless@dispatch@vcs0:
    - shard-tglb:         [PASS][57] -> [INCOMPLETE][58] ([i915#3778])
   [57]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-tglb7/igt@gem_exec_endless@dispatch@vcs0.html
   [58]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-tglb7/igt@gem_exec_endless@dispatch@vcs0.html

  * igt@gem_exec_fair@basic-deadline:
    - shard-kbl:          [PASS][59] -> [FAIL][60] ([i915#2846])
   [59]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-kbl7/igt@gem_exec_fair@basic-deadline.html
   [60]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@gem_exec_fair@basic-deadline.html
    - shard-glk:          NOTRUN -> [FAIL][61] ([i915#2846])
   [61]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk8/igt@gem_exec_fair@basic-deadline.html

  * igt@gem_exec_fair@basic-none-share@rcs0:
    - shard-glk:          [PASS][62] -> [FAIL][63] ([i915#2842])
   [62]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-glk3/igt@gem_exec_fair@basic-none-share@rcs0.html
   [63]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk3/igt@gem_exec_fair@basic-none-share@rcs0.html

  * igt@gem_exec_fair@basic-none-solo@rcs0:
    - shard-apl:          [PASS][64] -> [FAIL][65] ([i915#2842])
   [64]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-apl6/igt@gem_exec_fair@basic-none-solo@rcs0.html
   [65]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl3/igt@gem_exec_fair@basic-none-solo@rcs0.html

  * igt@gem_exec_fair@basic-pace-share@rcs0:
    - shard-tglb:         [PASS][66] -> [FAIL][67] ([i915#2842])
   [66]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-tglb7/igt@gem_exec_fair@basic-pace-share@rcs0.html
   [67]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-tglb5/igt@gem_exec_fair@basic-pace-share@rcs0.html

  * igt@gem_exec_fair@basic-pace-solo@rcs0:
    - shard-kbl:          [PASS][68] -> [FAIL][69] ([i915#2842])
   [68]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-kbl4/igt@gem_exec_fair@basic-pace-solo@rcs0.html
   [69]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@gem_exec_fair@basic-pace-solo@rcs0.html

  * igt@gem_exec_fair@basic-throttle@rcs0:
    - shard-iclb:         [PASS][70] -> [FAIL][71] ([i915#2842])
   [70]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-iclb5/igt@gem_exec_fair@basic-throttle@rcs0.html
   [71]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-iclb7/igt@gem_exec_fair@basic-throttle@rcs0.html

  * igt@gem_userptr_blits@vma-merge:
    - shard-glk:          NOTRUN -> [FAIL][72] ([i915#3318])
   [72]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk8/igt@gem_userptr_blits@vma-merge.html

  * igt@i915_pm_dc@dc6-psr:
    - shard-iclb:         [PASS][73] -> [FAIL][74] ([i915#454])
   [73]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-iclb1/igt@i915_pm_dc@dc6-psr.html
   [74]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-iclb6/igt@i915_pm_dc@dc6-psr.html

  * igt@kms_ccs@pipe-a-ccs-on-another-bo-y_tiled_gen12_mc_ccs:
    - shard-kbl:          NOTRUN -> [SKIP][75] ([fdo#109271] / [i915#3886]) +5 similar issues
   [75]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@kms_ccs@pipe-a-ccs-on-another-bo-y_tiled_gen12_mc_ccs.html

  * igt@kms_ccs@pipe-a-crc-primary-rotation-180-y_tiled_gen12_mc_ccs:
    - shard-glk:          NOTRUN -> [SKIP][76] ([fdo#109271] / [i915#3886]) +5 similar issues
   [76]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk8/igt@kms_ccs@pipe-a-crc-primary-rotation-180-y_tiled_gen12_mc_ccs.html

  * igt@kms_ccs@pipe-c-ccs-on-another-bo-y_tiled_gen12_mc_ccs:
    - shard-apl:          NOTRUN -> [SKIP][77] ([fdo#109271] / [i915#3886]) +4 similar issues
   [77]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl1/igt@kms_ccs@pipe-c-ccs-on-another-bo-y_tiled_gen12_mc_ccs.html

  * igt@kms_ccs@pipe-d-bad-pixel-format-4_tiled_dg2_mc_ccs:
    - shard-kbl:          NOTRUN -> [SKIP][78] ([fdo#109271]) +91 similar issues
   [78]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@kms_ccs@pipe-d-bad-pixel-format-4_tiled_dg2_mc_ccs.html

  * igt@kms_ccs@pipe-d-ccs-on-another-bo-yf_tiled_ccs:
    - shard-glk:          NOTRUN -> [SKIP][79] ([fdo#109271]) +51 similar issues
   [79]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk9/igt@kms_ccs@pipe-d-ccs-on-another-bo-yf_tiled_ccs.html

  * igt@kms_chamelium@dp-hpd-storm:
    - shard-kbl:          NOTRUN -> [SKIP][80] ([fdo#109271] / [fdo#111827]) +7 similar issues
   [80]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@kms_chamelium@dp-hpd-storm.html

  * igt@kms_chamelium@hdmi-frame-dump:
    - shard-apl:          NOTRUN -> [SKIP][81] ([fdo#109271] / [fdo#111827]) +2 similar issues
   [81]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl1/igt@kms_chamelium@hdmi-frame-dump.html
    - shard-glk:          NOTRUN -> [SKIP][82] ([fdo#109271] / [fdo#111827]) +4 similar issues
   [82]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk9/igt@kms_chamelium@hdmi-frame-dump.html

  * igt@kms_flip@flip-vs-suspend-interruptible@c-dp1:
    - shard-kbl:          [PASS][83] -> [DMESG-WARN][84] ([i915#180]) +4 similar issues
   [83]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-kbl1/igt@kms_flip@flip-vs-suspend-interruptible@c-dp1.html
   [84]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl4/igt@kms_flip@flip-vs-suspend-interruptible@c-dp1.html

  * igt@kms_flip_scaled_crc@flip-64bpp-yftile-to-16bpp-yftile-upscaling@pipe-a-valid-mode:
    - shard-iclb:         NOTRUN -> [SKIP][85] ([i915#2672]) +6 similar issues
   [85]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-iclb7/igt@kms_flip_scaled_crc@flip-64bpp-yftile-to-16bpp-yftile-upscaling@pipe-a-valid-mode.html

  * igt@kms_frontbuffer_tracking@psr-rgb101010-draw-mmap-cpu:
    - shard-apl:          NOTRUN -> [SKIP][86] ([fdo#109271]) +32 similar issues
   [86]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl1/igt@kms_frontbuffer_tracking@psr-rgb101010-draw-mmap-cpu.html

  * igt@kms_plane_alpha_blend@pipe-a-alpha-opaque-fb:
    - shard-glk:          NOTRUN -> [FAIL][87] ([fdo#108145] / [i915#265])
   [87]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk9/igt@kms_plane_alpha_blend@pipe-a-alpha-opaque-fb.html
    - shard-apl:          NOTRUN -> [FAIL][88] ([fdo#108145] / [i915#265])
   [88]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl1/igt@kms_plane_alpha_blend@pipe-a-alpha-opaque-fb.html

  * igt@kms_plane_alpha_blend@pipe-b-constant-alpha-max:
    - shard-kbl:          NOTRUN -> [FAIL][89] ([fdo#108145] / [i915#265])
   [89]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@kms_plane_alpha_blend@pipe-b-constant-alpha-max.html

  * igt@kms_plane_alpha_blend@pipe-c-alpha-transparent-fb:
    - shard-apl:          NOTRUN -> [FAIL][90] ([i915#265])
   [90]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl1/igt@kms_plane_alpha_blend@pipe-c-alpha-transparent-fb.html
    - shard-glk:          NOTRUN -> [FAIL][91] ([i915#265])
   [91]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk9/igt@kms_plane_alpha_blend@pipe-c-alpha-transparent-fb.html

  * igt@kms_plane_scaling@planes-upscale-factor-0-25-downscale-factor-0-5@pipe-b-edp-1:
    - shard-iclb:         [PASS][92] -> [SKIP][93] ([i915#5235]) +2 similar issues
   [92]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-iclb8/igt@kms_plane_scaling@planes-upscale-factor-0-25-downscale-factor-0-5@pipe-b-edp-1.html
   [93]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-iclb2/igt@kms_plane_scaling@planes-upscale-factor-0-25-downscale-factor-0-5@pipe-b-edp-1.html

  * igt@kms_psr2_sf@overlay-plane-move-continuous-sf:
    - shard-apl:          NOTRUN -> [SKIP][94] ([fdo#109271] / [i915#658]) +1 similar issue
   [94]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl1/igt@kms_psr2_sf@overlay-plane-move-continuous-sf.html

  * igt@kms_psr2_sf@plane-move-sf-dmg-area:
    - shard-kbl:          NOTRUN -> [SKIP][95] ([fdo#109271] / [i915#658])
   [95]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@kms_psr2_sf@plane-move-sf-dmg-area.html

  * igt@kms_psr2_su@frontbuffer-xrgb8888:
    - shard-glk:          NOTRUN -> [SKIP][96] ([fdo#109271] / [i915#658]) +2 similar issues
   [96]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk9/igt@kms_psr2_su@frontbuffer-xrgb8888.html

  * igt@kms_vblank@pipe-b-ts-continuation-suspend:
    - shard-glk:          NOTRUN -> [INCOMPLETE][97] ([i915#6598])
   [97]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk8/igt@kms_vblank@pipe-b-ts-continuation-suspend.html

  * igt@sysfs_clients@split-50:
    - shard-kbl:          NOTRUN -> [SKIP][98] ([fdo#109271] / [i915#2994])
   [98]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@sysfs_clients@split-50.html

  
#### Possible fixes ####

  * igt@gem_eio@unwedge-stress:
    - shard-iclb:         [TIMEOUT][99] ([i915#3070]) -> [PASS][100]
   [99]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-iclb5/igt@gem_eio@unwedge-stress.html
   [100]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-iclb7/igt@gem_eio@unwedge-stress.html

  * igt@gem_exec_balancer@parallel-balancer:
    - shard-iclb:         [SKIP][101] ([i915#4525]) -> [PASS][102]
   [101]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-iclb6/igt@gem_exec_balancer@parallel-balancer.html
   [102]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-iclb1/igt@gem_exec_balancer@parallel-balancer.html

  * igt@gem_exec_fair@basic-pace-share@rcs0:
    - shard-glk:          [FAIL][103] ([i915#2842]) -> [PASS][104]
   [103]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-glk9/igt@gem_exec_fair@basic-pace-share@rcs0.html
   [104]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk2/igt@gem_exec_fair@basic-pace-share@rcs0.html

  * igt@gem_exec_fair@basic-pace-solo@rcs0:
    - shard-iclb:         [FAIL][105] ([i915#2842]) -> [PASS][106]
   [105]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-iclb8/igt@gem_exec_fair@basic-pace-solo@rcs0.html
   [106]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-iclb2/igt@gem_exec_fair@basic-pace-solo@rcs0.html

  * igt@gem_exec_fair@basic-pace@vcs1:
    - shard-kbl:          [FAIL][107] ([i915#2842]) -> [PASS][108]
   [107]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-kbl1/igt@gem_exec_fair@basic-pace@vcs1.html
   [108]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl4/igt@gem_exec_fair@basic-pace@vcs1.html

  * igt@gem_workarounds@suspend-resume-fd:
    - shard-kbl:          [DMESG-WARN][109] ([i915#180]) -> [PASS][110] +7 similar issues
   [109]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-kbl4/igt@gem_workarounds@suspend-resume-fd.html
   [110]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@gem_workarounds@suspend-resume-fd.html

  * igt@gen9_exec_parse@allowed-all:
    - shard-glk:          [DMESG-WARN][111] ([i915#5566] / [i915#716]) -> [PASS][112] +1 similar issue
   [111]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-glk6/igt@gen9_exec_parse@allowed-all.html
   [112]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk8/igt@gen9_exec_parse@allowed-all.html

  * igt@gen9_exec_parse@allowed-single:
    - shard-apl:          [DMESG-WARN][113] ([i915#5566] / [i915#716]) -> [PASS][114]
   [113]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-apl1/igt@gen9_exec_parse@allowed-single.html
   [114]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl1/igt@gen9_exec_parse@allowed-single.html

  * igt@kms_flip@flip-vs-expired-vblank-interruptible@a-hdmi-a2:
    - shard-glk:          [FAIL][115] ([i915#79]) -> [PASS][116]
   [115]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-glk7/igt@kms_flip@flip-vs-expired-vblank-interruptible@a-hdmi-a2.html
   [116]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-glk5/igt@kms_flip@flip-vs-expired-vblank-interruptible@a-hdmi-a2.html

  * igt@kms_hdr@bpc-switch-dpms@pipe-a-dp-1:
    - shard-kbl:          [FAIL][117] ([i915#1188]) -> [PASS][118] +1 similar issue
   [117]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-kbl4/igt@kms_hdr@bpc-switch-dpms@pipe-a-dp-1.html
   [118]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl7/igt@kms_hdr@bpc-switch-dpms@pipe-a-dp-1.html

  * igt@kms_vblank@pipe-c-ts-continuation-suspend:
    - shard-kbl:          [INCOMPLETE][119] ([i915#4939]) -> [PASS][120]
   [119]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-kbl4/igt@kms_vblank@pipe-c-ts-continuation-suspend.html
   [120]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl1/igt@kms_vblank@pipe-c-ts-continuation-suspend.html

  
#### Warnings ####

  * igt@gem_exec_fair@basic-pace@rcs0:
    - shard-kbl:          [SKIP][121] ([fdo#109271]) -> [FAIL][122] ([i915#2842])
   [121]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-kbl1/igt@gem_exec_fair@basic-pace@rcs0.html
   [122]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-kbl4/igt@gem_exec_fair@basic-pace@rcs0.html

  * igt@kms_flip@flip-vs-suspend@a-dp1:
    - shard-apl:          [INCOMPLETE][123] ([i915#6598]) -> [INCOMPLETE][124] ([i915#1982] / [i915#6598])
   [123]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-apl7/igt@kms_flip@flip-vs-suspend@a-dp1.html
   [124]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl8/igt@kms_flip@flip-vs-suspend@a-dp1.html

  * igt@runner@aborted:
    - shard-apl:          ([FAIL][125], [FAIL][126]) ([fdo#109271] / [i915#3002] / [i915#4312] / [i915#5257] / [i915#6599]) -> [FAIL][127] ([i915#3002] / [i915#4312] / [i915#5257] / [i915#6599])
   [125]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-apl1/igt@runner@aborted.html
   [126]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12003/shard-apl8/igt@runner@aborted.html
   [127]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/shard-apl8/igt@runner@aborted.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109274]: https://bugs.freedesktop.org/show_bug.cgi?id=109274
  [fdo#109280]: https://bugs.freedesktop.org/show_bug.cgi?id=109280
  [fdo#109283]: https://bugs.freedesktop.org/show_bug.cgi?id=109283
  [fdo#109285]: https://bugs.freedesktop.org/show_bug.cgi?id=109285
  [fdo#109289]: https://bugs.freedesktop.org/show_bug.cgi?id=109289
  [fdo#109291]: https://bugs.freedesktop.org/show_bug.cgi?id=109291
  [fdo#109295]: https://bugs.freedesktop.org/show_bug.cgi?id=109295
  [fdo#109302]: https://bugs.freedesktop.org/show_bug.cgi?id=109302
  [fdo#109303]: https://bugs.freedesktop.org/show_bug.cgi?id=109303
  [fdo#109307]: https://bugs.freedesktop.org/show_bug.cgi?id=109307
  [fdo#109308]: https://bugs.freedesktop.org/show_bug.cgi?id=109308
  [fdo#109309]: https://bugs.freedesktop.org/show_bug.cgi?id=109309
  [fdo#109312]: https://bugs.freedesktop.org/show_bug.cgi?id=109312
  [fdo#109313]: https://bugs.freedesktop.org/show_bug.cgi?id=109313
  [fdo#109314]: https://bugs.freedesktop.org/show_bug.cgi?id=109314
  [fdo#109506]: https://bugs.freedesktop.org/show_bug.cgi?id=109506
  [fdo#109642]: https://bugs.freedesktop.org/show_bug.cgi?id=109642
  [fdo#110189]: https://bugs.freedesktop.org/show_bug.cgi?id=110189
  [fdo#110542]: https://bugs.freedesktop.org/show_bug.cgi?id=110542
  [fdo#111068]: https://bugs.freedesktop.org/show_bug.cgi?id=111068
  [fdo#111314]: https://bugs.freedesktop.org/show_bug.cgi?id=111314
  [fdo#111614]: https://bugs.freedesktop.org/show_bug.cgi?id=111614
  [fdo#111615]: https://bugs.freedesktop.org/show_bug.cgi?id=111615
  [fdo#111644]: https://bugs.freedesktop.org/show_bug.cgi?id=111644
  [fdo#111656]: https://bugs.freedesktop.org/show_bug.cgi?id=111656
  [fdo#111825]: https://bugs.freedesktop.org/show_bug.cgi?id=111825
  [fdo#111827]: https://bugs.freedesktop.org/show_bug.cgi?id=111827
  [fdo#112054]: https://bugs.freedesktop.org/show_bug.cgi?id=112054
  [fdo#112283]: https://bugs.freedesktop.org/show_bug.cgi?id=112283
  [i915#1063]: https://gitlab.freedesktop.org/drm/intel/issues/1063
  [i915#1072]: https://gitlab.freedesktop.org/drm/intel/issues/1072
  [i915#1155]: https://gitlab.freedesktop.org/drm/intel/issues/1155
  [i915#1188]: https://gitlab.freedesktop.org/drm/intel/issues/1188
  [i915#1257]: https://gitlab.freedesktop.org/drm/intel/issues/1257
  [i915#1397]: https://gitlab.freedesktop.org/drm/intel/issues/1397
  [i915#1755]: https://gitlab.freedesktop.org/drm/intel/issues/1755
  [i915#1769]: https://gitlab.freedesktop.org/drm/intel/issues/1769
  [i915#180]: https://gitlab.freedesktop.org/drm/intel/issues/180
  [i915#1839]: https://gitlab.freedesktop.org/drm/intel/issues/1839
  [i915#1845]: https://gitlab.freedesktop.org/drm/intel/issues/1845
  [i915#1849]: https://gitlab.freedesktop.org/drm/intel/issues/1849
  [i915#1902]: https://gitlab.freedesktop.org/drm/intel/issues/1902
  [i915#1982]: https://gitlab.freedesktop.org/drm/intel/issues/1982
  [i915#2190]: https://gitlab.freedesktop.org/drm/intel/issues/2190
  [i915#2410]: https://gitlab.freedesktop.org/drm/intel/issues/2410
  [i915#2433]: https://gitlab.freedesktop.org/drm/intel/issues/2433
  [i915#2437]: https://gitlab.freedesktop.org/drm/intel/issues/2437
  [i915#2527]: https://gitlab.freedesktop.org/drm/intel/issues/2527
  [i915#2530]: https://gitlab.freedesktop.org/drm/intel/issues/2530
  [i915#2582]: https://gitlab.freedesktop.org/drm/intel/issues/2582
  [i915#265]: https://gitlab.freedesktop.org/drm/intel/issues/265
  [i915#2658]: https://gitlab.freedesktop.org/drm/intel/issues/2658
  [i915#2672]: https://gitlab.freedesktop.org/drm/intel/issues/2672
  [i915#2681]: https://gitlab.freedesktop.org/drm/intel/issues/2681
  [i915#2705]: https://gitlab.freedesktop.org/drm/intel/issues/2705
  [i915#280]: https://gitlab.freedesktop.org/drm/intel/issues/280
  [i915#284]: https://gitlab.freedesktop.org/drm/intel/issues/284
  [i915#2842]: https://gitlab.freedesktop.org/drm/intel/issues/2842
  [i915#2846]: https://gitlab.freedesktop.org/drm/intel/issues/2846
  [i915#2856]: https://gitlab.freedesktop.org/drm/intel/issues/2856
  [i915#2994]: https://gitlab.freedesktop.org/drm/intel/issues/2994
  [i915#3002]: https://gitlab.freedesktop.org/drm/intel/issues/3002
  [i915#3070]: https://gitlab.freedesktop.org/drm/intel/issues/3070
  [i915#3116]: https://gitlab.freedesktop.org/drm/intel/issues/3116
  [i915#3281]: https://gitlab.freedesktop.org/drm/intel/issues/3281
  [i915#3282]: https://gitlab.freedesktop.org/drm/intel/issues/3282
  [i915#3297]: https://gitlab.freedesktop.org/drm/intel/issues/3297
  [i915#3299]: https://gitlab.freedesktop.org/drm/intel/issues/3299
  [i915#3318]: https://gitlab.freedesktop.org/drm/intel/issues/3318
  [i915#3323]: https://gitlab.freedesktop.org/drm/intel/issues/3323
  [i915#3361]: https://gitlab.freedesktop.org/drm/intel/issues/3361
  [i915#3458]: https://gitlab.freedesktop.org/drm/intel/issues/3458
  [i915#3469]: https://gitlab.freedesktop.org/drm/intel/issues/3469
  [i915#3528]: https://gitlab.freedesktop.org/drm/intel/issues/3528
  [i915#3539]: https://gitlab.freedesktop.org/drm/intel/issues/3539
  [i915#3546]: https://gitlab.freedesktop.org/drm/intel/issues/3546
  [i915#3555]: https://gitlab.freedesktop.org/drm/intel/issues/3555
  [i915#3558]: https://gitlab.freedesktop.org/drm/intel/issues/3558
  [i915#3637]: https://gitlab.freedesktop.org/drm/intel/issues/3637
  [i915#3638]: https://gitlab.freedesktop.org/drm/intel/issues/3638
  [i915#3689]: https://gitlab.freedesktop.org/drm/intel/issues/3689
  [i915#3708]: https://gitlab.freedesktop.org/drm/intel/issues/3708
  [i915#3742]: https://gitlab.freedesktop.org/drm/intel/issues/3742
  [i915#3778]: https://gitlab.freedesktop.org/drm/intel/issues/3778
  [i915#3804]: https://gitlab.freedesktop.org/drm/intel/issues/3804
  [i915#3826]: https://gitlab.freedesktop.org/drm/intel/issues/3826
  [i915#3828]: https://gitlab.freedesktop.org/drm/intel/issues/3828
  [i915#3886]: https://gitlab.freedesktop.org/drm/intel/issues/3886
  [i915#3936]: https://gitlab.freedesktop.org/drm/intel/issues/3936
  [i915#3952]: https://gitlab.freedesktop.org/drm/intel/issues/3952
  [i915#3966]: https://gitlab.freedesktop.org/drm/intel/issues/3966
  [i915#4016]: https://gitlab.freedesktop.org/drm/intel/issues/4016
  [i915#4032]: https://gitlab.freedesktop.org/drm/intel/issues/4032
  [i915#4036]: https://gitlab.freedesktop.org/drm/intel/issues/4036
  [i915#404]: https://gitlab.freedesktop.org/drm/intel/issues/404
  [i915#4070]: https://gitlab.freedesktop.org/drm/intel/issues/4070
  [i915#4077]: https://gitlab.freedesktop.org/drm/intel/issues/4077
  [i915#4078]: https://gitlab.freedesktop.org/drm/intel/issues/4078
  [i915#4079]: https://gitlab.freedesktop.org/drm/intel/issues/4079
  [i915#4083]: https://gitlab.freedesktop.org/drm/intel/issues/4083
  [i915#4098]: https://gitlab.freedesktop.org/drm/intel/issues/4098
  [i915#4103]: https://gitlab.freedesktop.org/drm/intel/issues/4103
  [i915#4212]: https://gitlab.freedesktop.org/drm/intel/issues/4212
  [i915#4213]: https://gitlab.freedesktop.org/drm/intel/issues/4213
  [i915#4215]: https://gitlab.freedesktop.org/drm/intel/issues/4215
  [i915#426]: https://gitlab.freedesktop.org/drm/intel/issues/426
  [i915#4270]: https://gitlab.freedesktop.org/drm/intel/issues/4270
  [i915#4312]: https://gitlab.freedesktop.org/drm/intel/issues/4312
  [i915#433]: https://gitlab.freedesktop.org/drm/intel/issues/433
  [i915#4338]: https://gitlab.freedesktop.org/drm/intel/issues/4338
  [i915#4369]: https://gitlab.freedesktop.org/drm/intel/issues/4369
  [i915#4387]: https://gitlab.freedesktop.org/drm/intel/issues/4387
  [i915#4494]: https://gitlab.freedesktop.org/drm/intel/issues/4494
  [i915#4525]: https://gitlab.freedesktop.org/drm/intel/issues/4525
  [i915#4538]: https://gitlab.freedesktop.org/drm/intel/issues/4538
  [i915#454]: https://gitlab.freedesktop.org/drm/intel/issues/454
  [i915#4565]: https://gitlab.freedesktop.org/drm/intel/issues/4565
  [i915#4613]: https://gitlab.freedesktop.org/drm/intel/issues/4613
  [i915#4767]: https://gitlab.freedesktop.org/drm/intel/issues/4767
  [i915#4771]: https://gitlab.freedesktop.org/drm/intel/issues/4771
  [i915#4812]: https://gitlab.freedesktop.org/drm/intel/issues/4812
  [i915#4818]: https://gitlab.freedesktop.org/drm/intel/issues/4818
  [i915#4833]: https://gitlab.freedesktop.org/drm/intel/issues/4833
  [i915#4852]: https://gitlab.freedesktop.org/drm/intel/issues/4852
  [i915#4853]: https://gitlab.freedesktop.org/drm/intel/issues/4853
  [i915#4855]: https://gitlab.freedesktop.org/drm/intel/issues/4855
  [i915#4859]: https://gitlab.freedesktop.org/drm/intel/issues/4859
  [i915#4860]: https://gitlab.freedesktop.org/drm/intel/issues/4860
  [i915#4874]: https://gitlab.freedesktop.org/drm/intel/issues/4874
  [i915#4879]: https://gitlab.freedesktop.org/drm/intel/issues/4879
  [i915#4880]: https://gitlab.freedesktop.org/drm/intel/issues/4880
  [i915#4881]: https://gitlab.freedesktop.org/drm/intel/issues/4881
  [i915#4883]: https://gitlab.freedesktop.org/drm/intel/issues/4883
  [i915#4884]: https://gitlab.freedesktop.org/drm/intel/issues/4884
  [i915#4885]: https://gitlab.freedesktop.org/drm/intel/issues/4885
  [i915#4893]: https://gitlab.freedesktop.org/drm/intel/issues/4893
  [i915#4939]: https://gitlab.freedesktop.org/drm/intel/issues/4939
  [i915#4941]: https://gitlab.freedesktop.org/drm/intel/issues/4941
  [i915#4957]: https://gitlab.freedesktop.org/drm/intel/issues/4957
  [i915#4958]: https://gitlab.freedesktop.org/drm/intel/issues/4958
  [i915#4991]: https://gitlab.freedesktop.org/drm/intel/issues/4991
  [i915#5122]: https://gitlab.freedesktop.org/drm/intel/issues/5122
  [i915#5176]: https://gitlab.freedesktop.org/drm/intel/issues/5176
  [i915#5235]: https://gitlab.freedesktop.org/drm/intel/issues/5235
  [i915#5257]: https://gitlab.freedesktop.org/drm/intel/issues/5257
  [i915#5286]: https://gitlab.freedesktop.org/drm/intel/issues/5286
  [i915#5287]: https://gitlab.freedesktop.org/drm/intel/issues/5287
  [i915#5288]: https://gitlab.freedesktop.org/drm/intel/issues/5288
  [i915#5289]: https://gitlab.freedesktop.org/drm/intel/issues/5289
  [i915#5325]: https://gitlab.freedesktop.org/drm/intel/issues/5325
  [i915#533]: https://gitlab.freedesktop.org/drm/intel/issues/533
  [i915#5439]: https://gitlab.freedesktop.org/drm/intel/issues/5439
  [i915#5461]: https://gitlab.freedesktop.org/drm/intel/issues/5461
  [i915#5563]: https://gitlab.freedesktop.org/drm/intel/issues/5563
  [i915#5566]: https://gitlab.freedesktop.org/drm/intel/issues/5566
  [i915#5723]: https://gitlab.freedesktop.org/drm/intel/issues/5723
  [i915#5784]: https://gitlab.freedesktop.org/drm/intel/issues/5784
  [i915#5982]: https://gitlab.freedesktop.org/drm/intel/issues/5982
  [i915#6011]: https://gitlab.freedesktop.org/drm/intel/issues/6011
  [i915#6095]: https://gitlab.freedesktop.org/drm/intel/issues/6095
  [i915#6245]: https://gitlab.freedesktop.org/drm/intel/issues/6245
  [i915#6268]: https://gitlab.freedesktop.org/drm/intel/issues/6268
  [i915#6301]: https://gitlab.freedesktop.org/drm/intel/issues/6301
  [i915#6331]: https://gitlab.freedesktop.org/drm/intel/issues/6331
  [i915#6335]: https://gitlab.freedesktop.org/drm/intel/issues/6335
  [i915#6412]: https://gitlab.freedesktop.org/drm/intel/issues/6412
  [i915#6433]: https://gitlab.freedesktop.org/drm/intel/issues/6433
  [i915#6458]: https://gitlab.freedesktop.org/drm/intel/issues/6458
  [i915#6463]: https://gitlab.freedesktop.org/drm/intel/issues/6463
  [i915#6493]: https://gitlab.freedesktop.org/drm/intel/issues/6493
  [i915#6524]: https://gitlab.freedesktop.org/drm/intel/issues/6524
  [i915#658]: https://gitlab.freedesktop.org/drm/intel/issues/658
  [i915#6590]: https://gitlab.freedesktop.org/drm/intel/issues/6590
  [i915#6598]: https://gitlab.freedesktop.org/drm/intel/issues/6598
  [i915#6599]: https://gitlab.freedesktop.org/drm/intel/issues/6599
  [i915#716]: https://gitlab.freedesktop.org/drm/intel/issues/716
  [i915#79]: https://gitlab.freedesktop.org/drm/intel/issues/79


Build changes
-------------

  * Linux: CI_DRM_12003 -> Patchwork_107502v1

  CI-20190529: 20190529
  CI_DRM_12003: 5852b759ca0d67530d1dae6ab66c351e796fe39d @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_6632: a0ac4d449e551fd5c78b56f85cd534330ea60507 @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
  Patchwork_107502v1: 5852b759ca0d67530d1dae6ab66c351e796fe39d @ git://anongit.freedesktop.org/gfx-ci/linux
  piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_107502v1/index.html

[-- Attachment #2: Type: text/html, Size: 29818 bytes --]

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [Intel-gfx] [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
  2022-08-19 16:47   ` Teres Alexis, Alan Previn
@ 2022-09-01 15:49     ` Teres Alexis, Alan Previn
  0 siblings, 0 replies; 7+ messages in thread
From: Teres Alexis, Alan Previn @ 2022-09-01 15:49 UTC (permalink / raw)
  To: Harrison, John C
  Cc: intel-gfx@lists.freedesktop.org, Auld, Matthew,
	Teres Alexis, Alan Previn

I think i found the problem - will trybot next before reposting a new rev.

was a terribly careless typo when rebasing from internal for drmtip:
guc_context_sched_disable called do_sched_disable which was supposed to call __guc_context_sched_disable (if the context
was really meant to be finally disabled) but instead called guc_context_sched_disable (no underscore) causing an
infinite loop for mid-disabling.

...alan

On Fri, 2022-08-19 at 16:47 +0000, Teres Alexis, Alan Previn wrote:
> Will look into this - apologies for the trouble Matt. 
> ...alan
> 
> -----Original Message-----
> From: Harrison, John C <john.c.harrison@intel.com> 
> Sent: Friday, August 19, 2022 8:46 AM
> To: Auld, Matthew <matthew.auld@intel.com>; intel-gfx@lists.freedesktop.org
> Cc: Brost, Matthew <matthew.brost@intel.com>; Teres Alexis, Alan Previn <alan.previn.teres.alexis@intel.com>
> Subject: Re: [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero"
> 
> On 8/19/2022 05:39, Matthew Auld wrote:
> > This reverts commit 6a079903847cce1dd06345127d2a32f26d2cd9c6.
> > 
> > Everything in CI using GuC is now timing out[1], and killing the 
> > machine with this change (perhaps a deadlock?). CI was recently on 
> > fire due to some changes coming in from -rc1, so likely the pre-merge 
> > CI results for this series were invalid? For now just revert, unless 
> > GuC experts already have a fix in mind.
> > 
> > [1] https://intel-gfx-ci.01.org/tree/drm-tip/index.html?
> > 
> > Signed-off-by: Matthew Auld <matthew.auld@intel.com>
> > Cc: Matthew Brost <matthew.brost@intel.com>
> > Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
> > Cc: John Harrison <John.C.Harrison@Intel.com>
> Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
> 
> Given that CI was claiming a pass for the original patch set, no we don't have a fix in mind. It is most frustrating when CI says all green if the entire universe is so broken that no tests were even running :(.
> 
> John.
> 
> 
> > ---
> >   drivers/gpu/drm/i915/gem/i915_gem_context.c   |   2 +-
> >   drivers/gpu/drm/i915/gt/intel_context.h       |   8 -
> >   drivers/gpu/drm/i915/gt/intel_context_types.h |   7 -
> >   drivers/gpu/drm/i915/gt/uc/intel_guc.h        |  17 +-
> >   .../gpu/drm/i915/gt/uc/intel_guc_debugfs.c    |  60 -------
> >   .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 154 +++---------------
> >   drivers/gpu/drm/i915/i915_selftest.h          |   2 -
> >   7 files changed, 27 insertions(+), 223 deletions(-)
> > 

^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2022-09-01 15:50 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2022-08-19 12:39 [Intel-gfx] [PATCH] Revert "drm/i915/guc: Add delay to disable scheduling after pin count goes to zero" Matthew Auld
2022-08-19 13:25 ` [Intel-gfx] ✗ Fi.CI.SPARSE: warning for " Patchwork
2022-08-19 13:48 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2022-08-19 15:46 ` [Intel-gfx] [PATCH] " John Harrison
2022-08-19 16:47   ` Teres Alexis, Alan Previn
2022-09-01 15:49     ` Teres Alexis, Alan Previn
2022-08-20 13:13 ` [Intel-gfx] ✗ Fi.CI.IGT: failure for " Patchwork

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox