diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index dabdfe09f5e51438c7d9b203194316f48b71b1d9..df7fd1b019ec3e2281d42d6bac92107e00aba95c 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 */
-		set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
+		intel_context_close(ce);
 		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 8e2d70630c49e82c456bf9499b0da5deb952ceda..f96420f0b5bb9ac4607711cd5b0ebe3df8beb5ed 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -276,6 +276,14 @@ 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 04eacae1aca55e4784c5d7f18d602f09af4eebe9..86ac84e2edb94614db55697e127972cd28c65c45 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -43,6 +43,8 @@ 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);
@@ -208,6 +210,11 @@ 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 804133df1ac9b4ce1b51462b0ac04110f5b94a68..944b549b87978d72525a32560a1266fb177c760a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -112,6 +112,10 @@ 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)
@@ -132,6 +136,16 @@ 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;
 
 	/**
@@ -461,9 +475,10 @@ 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);
 
-void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p);
+int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc);
 
 #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 25f09a420561bf410c52b18e5b3b2b6c8020830b..c91b150bb7acf2ee0452d4ab5131110db73ee3a0 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c
@@ -71,12 +71,72 @@ 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 0d56b615bf78e7b779e1f40e6bfe1d50661ace11..a0cebb4590e9f49b35d537e409b0105715bad624 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -65,7 +65,13 @@
  * 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
@@ -1989,6 +1995,9 @@ 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;
 }
@@ -1998,14 +2007,16 @@ 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);
 	}
@@ -2993,41 +3004,98 @@ guc_context_revoke(struct intel_context *ce, struct i915_request *rq,
 	}
 }
 
-static void guc_context_sched_disable(struct intel_context *ce)
+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);
+
+	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);
 
-	/*
-	 * 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.
-	 */
-	if (unlikely(!context_enabled(ce) || submission_disabled(guc) ||
-		     context_has_committed_requests(ce))) {
-		clr_context_enabled(ce);
+	if (bypass_sched_disable(guc, ce)) {
 		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-		goto unpin;
+		intel_context_sched_disable_unpin(ce);
+	} else {
+		do_sched_disable(guc, ce, flags);
 	}
-	guc_id = prep_context_pending_disable(ce);
+}
 
-	spin_unlock_irqrestore(&ce->guc_state.lock, 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;
 
-	with_intel_runtime_pm(runtime_pm, wakeref)
-		__guc_context_sched_disable(guc, ce, guc_id);
+	/*
+	 * 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);
+		mod_delayed_work(system_unbound_wq,
+				 &ce->guc_state.sched_disable_delay,
+				 msecs_to_jiffies(delay));
+	} else {
+		do_sched_disable(guc, ce, flags);
+	}
+}
 
-	return;
-unpin:
-	intel_context_sched_disable_unpin(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);
 }
 
 static inline void guc_lrc_desc_unpin(struct intel_context *ce)
@@ -3346,6 +3414,8 @@ 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,
@@ -3428,6 +3498,10 @@ 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,
+			  __delay_sched_disable);
+
 	set_bit(CONTEXT_GUC_INIT, &ce->flags);
 }
 
@@ -3465,6 +3539,9 @@ 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
@@ -3595,6 +3672,8 @@ 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,
@@ -3684,6 +3763,8 @@ 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,
@@ -4214,6 +4295,26 @@ 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);
@@ -4230,7 +4331,10 @@ 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);
 }
diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index f54de0499be72c978a9e0e84066f6c0456d19139..bdf3e22c0a34d96253eb2c8741b8b4ed9e3d7113 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -92,12 +92,14 @@ 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); \