Merge drm/drm-next into drm-intel-next

Catch up on 6.1-rc cycle in order to solve the intel_backlight
conflict on linux-next.

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

1 files changed, 315 insertions, 71 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 5929518b7772..1b8b8ad27f26 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -6,6 +6,7 @@
 #include <linux/circ_buf.h>
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_lmem.h"
 #include "gt/gen8_engine_cs.h"
 #include "gt/intel_breadcrumbs.h"
 #include "gt/intel_context.h"
@@ -66,7 +67,13 @@
  * 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.
+ * 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).
  *
  * Context deregistration:
  * Before a context can be destroyed or if we steal its guc_id we must
@@ -164,7 +171,8 @@ guc_create_parallel(struct intel_engine_cs **engines,
 #define SCHED_STATE_PENDING_ENABLE			BIT(5)
 #define SCHED_STATE_REGISTERED				BIT(6)
 #define SCHED_STATE_POLICY_REQUIRED			BIT(7)
-#define SCHED_STATE_BLOCKED_SHIFT			8
+#define SCHED_STATE_CLOSED				BIT(8)
+#define SCHED_STATE_BLOCKED_SHIFT			9
 #define SCHED_STATE_BLOCKED		BIT(SCHED_STATE_BLOCKED_SHIFT)
 #define SCHED_STATE_BLOCKED_MASK	(0xfff << SCHED_STATE_BLOCKED_SHIFT)
 
@@ -174,12 +182,20 @@ static inline void init_sched_state(struct intel_context *ce)
 	ce->guc_state.sched_state &= SCHED_STATE_BLOCKED_MASK;
 }
 
+/*
+ * Kernel contexts can have SCHED_STATE_REGISTERED after suspend.
+ * A context close can race with the submission path, so SCHED_STATE_CLOSED
+ * can be set immediately before we try to register.
+ */
+#define SCHED_STATE_VALID_INIT \
+	(SCHED_STATE_BLOCKED_MASK | \
+	 SCHED_STATE_CLOSED | \
+	 SCHED_STATE_REGISTERED)
+
 __maybe_unused
 static bool sched_state_is_init(struct intel_context *ce)
 {
-	/* Kernel contexts can have SCHED_STATE_REGISTERED after suspend. */
-	return !(ce->guc_state.sched_state &
-		 ~(SCHED_STATE_BLOCKED_MASK | SCHED_STATE_REGISTERED));
+	return !(ce->guc_state.sched_state & ~SCHED_STATE_VALID_INIT);
 }
 
 static inline bool
@@ -320,6 +336,17 @@ static inline void clr_context_policy_required(struct intel_context *ce)
 	ce->guc_state.sched_state &= ~SCHED_STATE_POLICY_REQUIRED;
 }
 
+static inline bool context_close_done(struct intel_context *ce)
+{
+	return ce->guc_state.sched_state & SCHED_STATE_CLOSED;
+}
+
+static inline void set_context_close_done(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->guc_state.lock);
+	ce->guc_state.sched_state |= SCHED_STATE_CLOSED;
+}
+
 static inline u32 context_blocked(struct intel_context *ce)
 {
 	return (ce->guc_state.sched_state & SCHED_STATE_BLOCKED_MASK) >>
@@ -344,25 +371,6 @@ static inline void decr_context_blocked(struct intel_context *ce)
 	ce->guc_state.sched_state -= SCHED_STATE_BLOCKED;
 }
 
-static inline bool context_has_committed_requests(struct intel_context *ce)
-{
-	return !!ce->guc_state.number_committed_requests;
-}
-
-static inline void incr_context_committed_requests(struct intel_context *ce)
-{
-	lockdep_assert_held(&ce->guc_state.lock);
-	++ce->guc_state.number_committed_requests;
-	GEM_BUG_ON(ce->guc_state.number_committed_requests < 0);
-}
-
-static inline void decr_context_committed_requests(struct intel_context *ce)
-{
-	lockdep_assert_held(&ce->guc_state.lock);
-	--ce->guc_state.number_committed_requests;
-	GEM_BUG_ON(ce->guc_state.number_committed_requests < 0);
-}
-
 static struct intel_context *
 request_to_scheduling_context(struct i915_request *rq)
 {
@@ -685,7 +693,7 @@ static int __guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 	 * Corner case where requests were sitting in the priority list or a
 	 * request resubmitted after the context was banned.
 	 */
-	if (unlikely(intel_context_is_banned(ce))) {
+	if (unlikely(!intel_context_is_schedulable(ce))) {
 		i915_request_put(i915_request_mark_eio(rq));
 		intel_engine_signal_breadcrumbs(ce->engine);
 		return 0;
@@ -871,15 +879,15 @@ static int guc_wq_item_append(struct intel_guc *guc,
 			      struct i915_request *rq)
 {
 	struct intel_context *ce = request_to_scheduling_context(rq);
-	int ret = 0;
+	int ret;
 
-	if (likely(!intel_context_is_banned(ce))) {
-		ret = __guc_wq_item_append(rq);
+	if (unlikely(!intel_context_is_schedulable(ce)))
+		return 0;
 
-		if (unlikely(ret == -EBUSY)) {
-			guc->stalled_request = rq;
-			guc->submission_stall_reason = STALL_MOVE_LRC_TAIL;
-		}
+	ret = __guc_wq_item_append(rq);
+	if (unlikely(ret == -EBUSY)) {
+		guc->stalled_request = rq;
+		guc->submission_stall_reason = STALL_MOVE_LRC_TAIL;
 	}
 
 	return ret;
@@ -898,7 +906,7 @@ static bool multi_lrc_submit(struct i915_request *rq)
 	 * submitting all the requests generated in parallel.
 	 */
 	return test_bit(I915_FENCE_FLAG_SUBMIT_PARALLEL, &rq->fence.flags) ||
-		intel_context_is_banned(ce);
+	       !intel_context_is_schedulable(ce);
 }
 
 static int guc_dequeue_one_context(struct intel_guc *guc)
@@ -967,7 +975,7 @@ register_context:
 		struct intel_context *ce = request_to_scheduling_context(last);
 
 		if (unlikely(!ctx_id_mapped(guc, ce->guc_id.id) &&
-			     !intel_context_is_banned(ce))) {
+			     intel_context_is_schedulable(ce))) {
 			ret = try_context_registration(ce, false);
 			if (unlikely(ret == -EPIPE)) {
 				goto deadlk;
@@ -1068,6 +1076,12 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
 
 		xa_unlock(&guc->context_lookup);
 
+		if (test_bit(CONTEXT_GUC_INIT, &ce->flags) &&
+		    (cancel_delayed_work(&ce->guc_state.sched_disable_delay_work))) {
+			/* successful cancel so jump straight to close it */
+			intel_context_sched_disable_unpin(ce);
+		}
+
 		spin_lock(&ce->guc_state.lock);
 
 		/*
@@ -1439,7 +1453,12 @@ void intel_guc_busyness_park(struct intel_gt *gt)
 	if (!guc_submission_initialized(guc))
 		return;
 
-	cancel_delayed_work(&guc->timestamp.work);
+	/*
+	 * There is a race with suspend flow where the worker runs after suspend
+	 * and causes an unclaimed register access warning. Cancel the worker
+	 * synchronously here.
+	 */
+	cancel_delayed_work_sync(&guc->timestamp.work);
 
 	/*
 	 * Before parking, we should sample engine busyness stats if we need to.
@@ -1533,8 +1552,8 @@ void intel_guc_submission_reset_prepare(struct intel_guc *guc)
 	__reset_guc_busyness_stats(guc);
 
 	/* Flush IRQ handler */
-	spin_lock_irq(&guc_to_gt(guc)->irq_lock);
-	spin_unlock_irq(&guc_to_gt(guc)->irq_lock);
+	spin_lock_irq(guc_to_gt(guc)->irq_lock);
+	spin_unlock_irq(guc_to_gt(guc)->irq_lock);
 
 	guc_flush_submissions(guc);
 	guc_flush_destroyed_contexts(guc);
@@ -1572,7 +1591,7 @@ static void guc_reset_state(struct intel_context *ce, u32 head, bool scrub)
 {
 	struct intel_engine_cs *engine = __context_to_physical_engine(ce);
 
-	if (intel_context_is_banned(ce))
+	if (!intel_context_is_schedulable(ce))
 		return;
 
 	GEM_BUG_ON(!intel_context_is_pinned(ce));
@@ -1869,7 +1888,7 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	if (guc->submission_initialized)
 		return 0;
 
-	if (guc->fw.major_ver_found < 70) {
+	if (GET_UC_VER(guc) < MAKE_UC_VER(70, 0, 0)) {
 		ret = guc_lrc_desc_pool_create_v69(guc);
 		if (ret)
 			return ret;
@@ -1990,6 +2009,9 @@ 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;
 }
@@ -1999,14 +2021,16 @@ 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
+		} else {
+			--guc->submission_state.guc_ids_in_use;
 			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);
 	}
@@ -2304,7 +2328,7 @@ static int register_context(struct intel_context *ce, bool loop)
 	GEM_BUG_ON(intel_context_is_child(ce));
 	trace_intel_context_register(ce);
 
-	if (guc->fw.major_ver_found >= 70)
+	if (GET_UC_VER(guc) >= MAKE_UC_VER(70, 0, 0))
 		ret = register_context_v70(guc, ce, loop);
 	else
 		ret = register_context_v69(guc, ce, loop);
@@ -2316,7 +2340,7 @@ static int register_context(struct intel_context *ce, bool loop)
 		set_context_registered(ce);
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 
-		if (guc->fw.major_ver_found >= 70)
+		if (GET_UC_VER(guc) >= MAKE_UC_VER(70, 0, 0))
 			guc_context_policy_init_v70(ce, loop);
 	}
 
@@ -2425,6 +2449,10 @@ static int guc_context_policy_init_v70(struct intel_context *ce, bool loop)
 	int ret;
 
 	/* NB: For both of these, zero means disabled. */
+	GEM_BUG_ON(overflows_type(engine->props.timeslice_duration_ms * 1000,
+				  execution_quantum));
+	GEM_BUG_ON(overflows_type(engine->props.preempt_timeout_ms * 1000,
+				  preemption_timeout));
 	execution_quantum = engine->props.timeslice_duration_ms * 1000;
 	preemption_timeout = engine->props.preempt_timeout_ms * 1000;
 
@@ -2458,6 +2486,10 @@ static void guc_context_policy_init_v69(struct intel_engine_cs *engine,
 		desc->policy_flags |= CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE_V69;
 
 	/* NB: For both of these, zero means disabled. */
+	GEM_BUG_ON(overflows_type(engine->props.timeslice_duration_ms * 1000,
+				  desc->execution_quantum));
+	GEM_BUG_ON(overflows_type(engine->props.preempt_timeout_ms * 1000,
+				  desc->preemption_timeout));
 	desc->execution_quantum = engine->props.timeslice_duration_ms * 1000;
 	desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000;
 }
@@ -2922,7 +2954,7 @@ static void __guc_context_set_preemption_timeout(struct intel_guc *guc,
 						 u16 guc_id,
 						 u32 preemption_timeout)
 {
-	if (guc->fw.major_ver_found >= 70) {
+	if (GET_UC_VER(guc) >= MAKE_UC_VER(70, 0, 0)) {
 		struct context_policy policy;
 
 		__guc_context_policy_start_klv(&policy, guc_id);
@@ -2994,41 +3026,104 @@ 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)
 {
-	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);
+	guc_id = prep_context_pending_disable(ce);
+
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+	with_intel_runtime_pm(runtime_pm, wakeref)
+		__guc_context_sched_disable(guc, ce, guc_id);
+}
+
+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.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)
+{
 	/*
-	 * 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.
+	 * parent contexts are perma-pinned, if we are unpinning do schedule
+	 * disable immediately.
 	 */
-	if (unlikely(!context_enabled(ce) || submission_disabled(guc) ||
-		     context_has_committed_requests(ce))) {
-		clr_context_enabled(ce);
+	if (intel_context_is_parent(ce))
+		return true;
+
+	/*
+	 * If we are beyond the threshold for avail guc_ids, do schedule disable immediately.
+	 */
+	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) {
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-		goto unpin;
+		mod_delayed_work(system_unbound_wq,
+				 &ce->guc_state.sched_disable_delay_work,
+				 msecs_to_jiffies(delay));
+	} else {
+		do_sched_disable(guc, ce, flags);
 	}
-	guc_id = prep_context_pending_disable(ce);
+}
 
-	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+static void guc_context_close(struct intel_context *ce)
+{
+	unsigned long flags;
 
-	with_intel_runtime_pm(runtime_pm, wakeref)
-		__guc_context_sched_disable(guc, ce, guc_id);
+	if (test_bit(CONTEXT_GUC_INIT, &ce->flags) &&
+	    cancel_delayed_work(&ce->guc_state.sched_disable_delay_work))
+		__delay_sched_disable(&ce->guc_state.sched_disable_delay_work.work);
 
-	return;
-unpin:
-	intel_context_sched_disable_unpin(ce);
+	spin_lock_irqsave(&ce->guc_state.lock, flags);
+	set_context_close_done(ce);
+	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 }
 
 static inline void guc_lrc_desc_unpin(struct intel_context *ce)
@@ -3067,7 +3162,6 @@ static void __guc_context_destroy(struct intel_context *ce)
 		   ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_HIGH] ||
 		   ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_KMD_NORMAL] ||
 		   ce->guc_state.prio_count[GUC_CLIENT_PRIORITY_NORMAL]);
-	GEM_BUG_ON(ce->guc_state.number_committed_requests);
 
 	lrc_fini(ce);
 	intel_context_fini(ce);
@@ -3187,7 +3281,7 @@ static int guc_context_alloc(struct intel_context *ce)
 static void __guc_context_set_prio(struct intel_guc *guc,
 				   struct intel_context *ce)
 {
-	if (guc->fw.major_ver_found >= 70) {
+	if (GET_UC_VER(guc) >= MAKE_UC_VER(70, 0, 0)) {
 		struct context_policy policy;
 
 		__guc_context_policy_start_klv(&policy, ce->guc_id.id);
@@ -3336,8 +3430,6 @@ static void remove_from_context(struct i915_request *rq)
 
 	guc_prio_fini(rq, ce);
 
-	decr_context_committed_requests(ce);
-
 	spin_unlock_irq(&ce->guc_state.lock);
 
 	atomic_dec(&ce->guc_id.ref);
@@ -3347,6 +3439,8 @@ 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,
@@ -3429,6 +3523,10 @@ 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_work,
+			  __delay_sched_disable);
+
 	set_bit(CONTEXT_GUC_INIT, &ce->flags);
 }
 
@@ -3467,6 +3565,26 @@ static int guc_request_alloc(struct i915_request *rq)
 		guc_context_init(ce);
 
 	/*
+	 * If the context gets closed while the execbuf is ongoing, the context
+	 * close code will race with the below code to cancel the delayed work.
+	 * If the context close wins the race and cancels the work, it will
+	 * immediately call the sched disable (see guc_context_close), so there
+	 * is a chance we can get past this check while the sched_disable code
+	 * is being executed. To make sure that code completes before we check
+	 * the status further down, we wait for the close process to complete.
+	 * Else, this code path could send a request down thinking that the
+	 * context is still in a schedule-enable mode while the GuC ends up
+	 * dropping the request completely because the disable did go from the
+	 * context_close path right to GuC just prior. In the event the CT is
+	 * full, we could potentially need to wait up to 1.5 seconds.
+	 */
+	if (cancel_delayed_work_sync(&ce->guc_state.sched_disable_delay_work))
+		intel_context_sched_disable_unpin(ce);
+	else if (intel_context_is_closed(ce))
+		if (wait_for(context_close_done(ce), 1500))
+			drm_warn(&guc_to_gt(guc)->i915->drm,
+				 "timed out waiting on context sched close before realloc\n");
+	/*
 	 * Call pin_guc_id here rather than in the pinning step as with
 	 * dma_resv, contexts can be repeatedly pinned / unpinned trashing the
 	 * guc_id and creating horrible race conditions. This is especially bad
@@ -3520,7 +3638,6 @@ out:
 
 		list_add_tail(&rq->guc_fence_link, &ce->guc_state.fences);
 	}
-	incr_context_committed_requests(ce);
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 
 	return 0;
@@ -3596,6 +3713,8 @@ 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,
@@ -3685,6 +3804,8 @@ 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,
@@ -4004,6 +4125,13 @@ static inline void guc_init_lrc_mapping(struct intel_guc *guc)
 	xa_destroy(&guc->context_lookup);
 
 	/*
+	 * A reset might have occurred while we had a pending stalled request,
+	 * so make sure we clean that up.
+	 */
+	guc->stalled_request = NULL;
+	guc->submission_stall_reason = STALL_NONE;
+
+	/*
 	 * Some contexts might have been pinned before we enabled GuC
 	 * submission, so we need to add them to the GuC bookeeping.
 	 * Also, after a reset the of the GuC we want to make sure that the
@@ -4082,7 +4210,7 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine)
 
 	engine->emit_bb_start = gen8_emit_bb_start;
 	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
-		engine->emit_bb_start = gen125_emit_bb_start;
+		engine->emit_bb_start = xehp_emit_bb_start;
 }
 
 static void rcs_submission_override(struct intel_engine_cs *engine)
@@ -4166,6 +4294,98 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine)
 	return 0;
 }
 
+struct scheduling_policy {
+	/* internal data */
+	u32 max_words, num_words;
+	u32 count;
+	/* API data */
+	struct guc_update_scheduling_policy h2g;
+};
+
+static u32 __guc_scheduling_policy_action_size(struct scheduling_policy *policy)
+{
+	u32 *start = (void *)&policy->h2g;
+	u32 *end = policy->h2g.data + policy->num_words;
+	size_t delta = end - start;
+
+	return delta;
+}
+
+static struct scheduling_policy *__guc_scheduling_policy_start_klv(struct scheduling_policy *policy)
+{
+	policy->h2g.header.action = INTEL_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV;
+	policy->max_words = ARRAY_SIZE(policy->h2g.data);
+	policy->num_words = 0;
+	policy->count = 0;
+
+	return policy;
+}
+
+static void __guc_scheduling_policy_add_klv(struct scheduling_policy *policy,
+					    u32 action, u32 *data, u32 len)
+{
+	u32 *klv_ptr = policy->h2g.data + policy->num_words;
+
+	GEM_BUG_ON((policy->num_words + 1 + len) > policy->max_words);
+	*(klv_ptr++) = FIELD_PREP(GUC_KLV_0_KEY, action) |
+		       FIELD_PREP(GUC_KLV_0_LEN, len);
+	memcpy(klv_ptr, data, sizeof(u32) * len);
+	policy->num_words += 1 + len;
+	policy->count++;
+}
+
+static int __guc_action_set_scheduling_policies(struct intel_guc *guc,
+						struct scheduling_policy *policy)
+{
+	int ret;
+
+	ret = intel_guc_send(guc, (u32 *)&policy->h2g,
+			     __guc_scheduling_policy_action_size(policy));
+	if (ret < 0)
+		return ret;
+
+	if (ret != policy->count) {
+		drm_warn(&guc_to_gt(guc)->i915->drm, "GuC global scheduler policy processed %d of %d KLVs!",
+			 ret, policy->count);
+		if (ret > policy->count)
+			return -EPROTO;
+	}
+
+	return 0;
+}
+
+static int guc_init_global_schedule_policy(struct intel_guc *guc)
+{
+	struct scheduling_policy policy;
+	struct intel_gt *gt = guc_to_gt(guc);
+	intel_wakeref_t wakeref;
+	int ret = 0;
+
+	if (GET_UC_VER(guc) < MAKE_UC_VER(70, 3, 0))
+		return 0;
+
+	__guc_scheduling_policy_start_klv(&policy);
+
+	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref) {
+		u32 yield[] = {
+			GLOBAL_SCHEDULE_POLICY_RC_YIELD_DURATION,
+			GLOBAL_SCHEDULE_POLICY_RC_YIELD_RATIO,
+		};
+
+		__guc_scheduling_policy_add_klv(&policy,
+						GUC_SCHEDULING_POLICIES_KLV_ID_RENDER_COMPUTE_YIELD,
+						yield, ARRAY_SIZE(yield));
+
+		ret = __guc_action_set_scheduling_policies(guc, &policy);
+		if (ret)
+			i915_probe_error(gt->i915,
+					 "Failed to configure global scheduling policies: %pe!\n",
+					 ERR_PTR(ret));
+	}
+
+	return ret;
+}
+
 void intel_guc_submission_enable(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
@@ -4178,6 +4398,7 @@ void intel_guc_submission_enable(struct intel_guc *guc)
 
 	guc_init_lrc_mapping(guc);
 	guc_init_engine_stats(guc);
+	guc_init_global_schedule_policy(guc);
 }
 
 void intel_guc_submission_disable(struct intel_guc *guc)
@@ -4208,6 +4429,26 @@ 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);
@@ -4224,7 +4465,10 @@ 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);
 }
@@ -4413,12 +4657,12 @@ static void guc_handle_context_reset(struct intel_guc *guc,
 {
 	trace_intel_context_reset(ce);
 
-	if (likely(!intel_context_is_banned(ce))) {
+	if (likely(intel_context_is_schedulable(ce))) {
 		capture_error_state(guc, ce);
 		guc_context_replay(ce);
 	} else {
 		drm_info(&guc_to_gt(guc)->i915->drm,
-			 "Ignoring context reset notification of banned context 0x%04X on %s",
+			 "Ignoring context reset notification of exiting context 0x%04X on %s",
 			 ce->guc_id.id, ce->engine->name);
 	}
 }