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

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>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220819123904.913750-1-matthew.auld@intel.com

1 files changed, 25 insertions, 129 deletions

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 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);
 }