Merge tag 'drm-intel-gt-next-2024-06-12' of https://gitlab.freedesktop.org/drm/i915/kernel into drm-next

UAPI Changes:

- Support replaying GPU hangs with captured context image (Tvrtko Ursulin)

Driver Changes:

Fixes/improvements/new stuff:

- Automate CCS Mode setting during engine resets [gt] (Andi Shyti)
- Revert "drm/i915: Remove extra multi-gt pm-references" (Janusz Krzysztofik)
- Fix HAS_REGION() usage in intel_gt_probe_lmem() (Ville Syrjälä)
- Disarm breadcrumbs if engines are already idle [gt] (Chris Wilson)
- Shadow default engine context image in the context (Tvrtko Ursulin)
- Support replaying GPU hangs with captured context image (Tvrtko Ursulin)
- avoid FIELD_PREP warning [guc] (Arnd Bergmann)
- Fix CCS id's calculation for CCS mode setting [gt] (Andi Shyti)
- Increase FLR timeout from 3s to 9s (Andi Shyti)
- Update workaround 14018575942 [mtl] (Angus Chen)

Future platform enablement:

- Enable w/a 16021333562 for DG2, MTL and ARL [guc] (John Harrison)

Miscellaneous:

- Pass the region ID rather than a bitmask to HAS_REGION() (Ville Syrjälä)
- Remove counter productive REGION_* wrappers (Ville Syrjälä)
- Fix typo [gem/i915_gem_ttm_move] (Deming Wang)
- Delete the live_hearbeat_fast selftest [gt] (Krzysztof Niemiec)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Tvrtko Ursulin <tursulin@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Zmmazub+U9ewH9ts@linux

20 files changed, 219 insertions, 143 deletions

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index d8397065c3f0..1852e0804942 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -16,6 +16,23 @@ config DRM_I915_WERROR
 
 	  If in doubt, say "N".
 
+config DRM_I915_REPLAY_GPU_HANGS_API
+	bool "Enable GPU hang replay userspace API"
+	depends on DRM_I915
+	depends on EXPERT
+	default n
+	help
+	  Choose this option if you want to enable special and unstable
+	  userspace API used for replaying GPU hangs on a running system.
+
+	  This API is intended to be used by userspace graphics stack developers
+	  and provides no stability guarantees.
+
+	  The API needs to be activated at boot time using the
+	  enable_debug_only_api module parameter.
+
+	  If in doubt, say "N".
+
 config DRM_I915_DEBUG
 	bool "Enable additional driver debugging"
 	depends on DRM_I915
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 81f65cab1330..c0543c35cd6a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -78,6 +78,7 @@
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gpu_commands.h"
 #include "gt/intel_ring.h"
+#include "gt/shmem_utils.h"
 
 #include "pxp/intel_pxp.h"
 
@@ -957,6 +958,7 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
 	case I915_CONTEXT_PARAM_NO_ZEROMAP:
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 	case I915_CONTEXT_PARAM_RINGSIZE:
+	case I915_CONTEXT_PARAM_CONTEXT_IMAGE:
 	default:
 		ret = -EINVAL;
 		break;
@@ -2104,6 +2106,95 @@ static int get_protected(struct i915_gem_context *ctx,
 	return 0;
 }
 
+static int set_context_image(struct i915_gem_context *ctx,
+			     struct drm_i915_gem_context_param *args)
+{
+	struct i915_gem_context_param_context_image user;
+	struct intel_context *ce;
+	struct file *shmem_state;
+	unsigned long lookup;
+	void *state;
+	int ret = 0;
+
+	if (!IS_ENABLED(CONFIG_DRM_I915_REPLAY_GPU_HANGS_API))
+		return -EINVAL;
+
+	if (!ctx->i915->params.enable_debug_only_api)
+		return -EINVAL;
+
+	if (args->size < sizeof(user))
+		return -EINVAL;
+
+	if (copy_from_user(&user, u64_to_user_ptr(args->value), sizeof(user)))
+		return -EFAULT;
+
+	if (user.mbz)
+		return -EINVAL;
+
+	if (user.flags & ~(I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX))
+		return -EINVAL;
+
+	lookup = 0;
+	if (user.flags & I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX)
+		lookup |= LOOKUP_USER_INDEX;
+
+	ce = lookup_user_engine(ctx, lookup, &user.engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	if (user.size < ce->engine->context_size) {
+		ret = -EINVAL;
+		goto out_ce;
+	}
+
+	if (drm_WARN_ON_ONCE(&ctx->i915->drm,
+			     test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
+		/*
+		 * This is racy but for a debug only API, if userspace is keen
+		 * to create and configure contexts, while simultaneously using
+		 * them from a second thread, let them suffer by potentially not
+		 * executing with the context image they just raced to apply.
+		 */
+		ret = -EBUSY;
+		goto out_ce;
+	}
+
+	state = kmalloc(ce->engine->context_size, GFP_KERNEL);
+	if (!state) {
+		ret = -ENOMEM;
+		goto out_ce;
+	}
+
+	if (copy_from_user(state, u64_to_user_ptr(user.image),
+			   ce->engine->context_size)) {
+		ret = -EFAULT;
+		goto out_state;
+	}
+
+	shmem_state = shmem_create_from_data(ce->engine->name,
+					     state, ce->engine->context_size);
+	if (IS_ERR(shmem_state)) {
+		ret = PTR_ERR(shmem_state);
+		goto out_state;
+	}
+
+	if (intel_context_set_own_state(ce)) {
+		ret = -EBUSY;
+		fput(shmem_state);
+		goto out_state;
+	}
+
+	ce->default_state = shmem_state;
+
+	args->size = sizeof(user);
+
+out_state:
+	kfree(state);
+out_ce:
+	intel_context_put(ce);
+	return ret;
+}
+
 static int ctx_setparam(struct drm_i915_file_private *fpriv,
 			struct i915_gem_context *ctx,
 			struct drm_i915_gem_context_param *args)
@@ -2156,6 +2247,10 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv,
 		ret = set_persistence(ctx, args);
 		break;
 
+	case I915_CONTEXT_PARAM_CONTEXT_IMAGE:
+		ret = set_context_image(ctx, args);
+		break;
+
 	case I915_CONTEXT_PARAM_PROTECTED_CONTENT:
 	case I915_CONTEXT_PARAM_NO_ZEROMAP:
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
@@ -2500,6 +2595,7 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 	case I915_CONTEXT_PARAM_ENGINES:
 	case I915_CONTEXT_PARAM_RINGSIZE:
+	case I915_CONTEXT_PARAM_CONTEXT_IMAGE:
 	default:
 		ret = -EINVAL;
 		break;
@@ -2612,5 +2708,22 @@ int __init i915_gem_context_module_init(void)
 	if (!slab_luts)
 		return -ENOMEM;
 
+	if (IS_ENABLED(CONFIG_DRM_I915_REPLAY_GPU_HANGS_API)) {
+		pr_notice("**************************************************************\n");
+		pr_notice("**     NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE     **\n");
+		pr_notice("**                                                          **\n");
+		if (i915_modparams.enable_debug_only_api)
+			pr_notice("** i915.enable_debug_only_api is intended to be set         **\n");
+		else
+			pr_notice("** CONFIG_DRM_I915_REPLAY_GPU_HANGS_API builds are intended **\n");
+		pr_notice("** for specific userspace graphics stack developers only!   **\n");
+		pr_notice("**                                                          **\n");
+		pr_notice("** If you are seeing this message please report this to the **\n");
+		pr_notice("** provider of your kernel build.                           **\n");
+		pr_notice("**                                                          **\n");
+		pr_notice("**     NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE     **\n");
+		pr_notice("**************************************************************\n");
+	}
+
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
index 7078af2f8f79..03b00a03a634 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
@@ -155,7 +155,7 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj)
  * @bo: The ttm buffer object.
  *
  * This function prepares an object for move by removing all GPU bindings,
- * removing all CPU mapings and finally releasing the pages sg-table.
+ * removing all CPU mappings and finally releasing the pages sg-table.
  *
  * Return: 0 if successful, negative error code on error.
  */
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index a2f1245741bb..b1b8695ba7c9 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -27,6 +27,8 @@ static void rcu_context_free(struct rcu_head *rcu)
 	struct intel_context *ce = container_of(rcu, typeof(*ce), rcu);
 
 	trace_intel_context_free(ce);
+	if (intel_context_has_own_state(ce))
+		fput(ce->default_state);
 	kmem_cache_free(slab_ce, ce);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 25564c01507e..9f523999acd1 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -375,6 +375,28 @@ intel_context_clear_nopreempt(struct intel_context *ce)
 	clear_bit(CONTEXT_NOPREEMPT, &ce->flags);
 }
 
+#if IS_ENABLED(CONFIG_DRM_I915_REPLAY_GPU_HANGS_API)
+static inline bool intel_context_has_own_state(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_OWN_STATE, &ce->flags);
+}
+
+static inline bool intel_context_set_own_state(struct intel_context *ce)
+{
+	return test_and_set_bit(CONTEXT_OWN_STATE, &ce->flags);
+}
+#else
+static inline bool intel_context_has_own_state(const struct intel_context *ce)
+{
+	return false;
+}
+
+static inline bool intel_context_set_own_state(struct intel_context *ce)
+{
+	return true;
+}
+#endif
+
 u64 intel_context_get_total_runtime_ns(struct intel_context *ce);
 u64 intel_context_get_avg_runtime_ns(struct intel_context *ce);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index ed95a7b57cbb..98c7f6052069 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -99,6 +99,8 @@ struct intel_context {
 	struct i915_address_space *vm;
 	struct i915_gem_context __rcu *gem_context;
 
+	struct file *default_state;
+
 	/*
 	 * @signal_lock protects the list of requests that need signaling,
 	 * @signals. While there are any requests that need signaling,
@@ -131,6 +133,7 @@ struct intel_context {
 #define CONTEXT_IS_PARKING		12
 #define CONTEXT_EXITING			13
 #define CONTEXT_LOW_LATENCY		14
+#define CONTEXT_OWN_STATE		15
 
 	struct {
 		u64 timeout_us;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index b387146ede98..7bd5d2c29056 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1017,9 +1017,8 @@ void lrc_init_state(struct intel_context *ce,
 
 	set_redzone(state, engine);
 
-	if (engine->default_state) {
-		shmem_read(engine->default_state, 0,
-			   state, engine->context_size);
+	if (ce->default_state) {
+		shmem_read(ce->default_state, 0, state, engine->context_size);
 		__set_bit(CONTEXT_VALID_BIT, &ce->flags);
 		inhibit = false;
 	}
@@ -1131,6 +1130,9 @@ int lrc_alloc(struct intel_context *ce, struct intel_engine_cs *engine)
 
 	GEM_BUG_ON(ce->state);
 
+	if (!intel_context_has_own_state(ce))
+		ce->default_state = engine->default_state;
+
 	vma = __lrc_alloc_state(ce, engine);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 92085ffd23de..72277bc8322e 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -474,8 +474,7 @@ static int ring_context_init_default_state(struct intel_context *ce,
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
 
-	shmem_read(ce->engine->default_state, 0,
-		   vaddr, ce->engine->context_size);
+	shmem_read(ce->default_state, 0, vaddr, ce->engine->context_size);
 
 	i915_gem_object_flush_map(obj);
 	__i915_gem_object_release_map(obj);
@@ -491,7 +490,7 @@ static int ring_context_pre_pin(struct intel_context *ce,
 	struct i915_address_space *vm;
 	int err = 0;
 
-	if (ce->engine->default_state &&
+	if (ce->default_state &&
 	    !test_bit(CONTEXT_VALID_BIT, &ce->flags)) {
 		err = ring_context_init_default_state(ce, ww);
 		if (err)
@@ -570,6 +569,9 @@ static int ring_context_alloc(struct intel_context *ce)
 {
 	struct intel_engine_cs *engine = ce->engine;
 
+	if (!intel_context_has_own_state(ce))
+		ce->default_state = engine->default_state;
+
 	/* One ringbuffer to rule them all */
 	GEM_BUG_ON(!engine->legacy.ring);
 	ce->ring = engine->legacy.ring;
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 5a0f1b279a80..09a287c1aedd 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1590,6 +1590,14 @@ xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 	 */
 	wa_write_or(wal, XELPMP_GSC_MOD_CTRL, FORCE_MISS_FTLB);
 
+	/*
+	 * Wa_14018575942
+	 *
+	 * Issue is seen on media KPI test running on VDBOX engine
+	 * especially VP9 encoding WLs
+	 */
+	wa_write_or(wal, XELPMP_VDBX_MOD_CTRL, FORCE_MISS_FTLB);
+
 	/* Wa_22016670082 */
 	wa_write_or(wal, GEN12_SQCNT1, GEN12_STRICT_RAR_ENABLE);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
index ef014df4c4fc..9e4f0e417b3b 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -193,115 +193,6 @@ static int live_idle_pulse(void *arg)
 	return err;
 }
 
-static int cmp_u32(const void *_a, const void *_b)
-{
-	const u32 *a = _a, *b = _b;
-
-	return *a - *b;
-}
-
-static int __live_heartbeat_fast(struct intel_engine_cs *engine)
-{
-	const unsigned int error_threshold = max(20000u, jiffies_to_usecs(6));
-	struct intel_context *ce;
-	struct i915_request *rq;
-	ktime_t t0, t1;
-	u32 times[5];
-	int err;
-	int i;
-
-	ce = intel_context_create(engine);
-	if (IS_ERR(ce))
-		return PTR_ERR(ce);
-
-	intel_engine_pm_get(engine);
-
-	err = intel_engine_set_heartbeat(engine, 1);
-	if (err)
-		goto err_pm;
-
-	for (i = 0; i < ARRAY_SIZE(times); i++) {
-		do {
-			/* Manufacture a tick */
-			intel_engine_park_heartbeat(engine);
-			GEM_BUG_ON(engine->heartbeat.systole);
-			engine->serial++; /*  pretend we are not idle! */
-			intel_engine_unpark_heartbeat(engine);
-
-			flush_delayed_work(&engine->heartbeat.work);
-			if (!delayed_work_pending(&engine->heartbeat.work)) {
-				pr_err("%s: heartbeat %d did not start\n",
-				       engine->name, i);
-				err = -EINVAL;
-				goto err_pm;
-			}
-
-			rcu_read_lock();
-			rq = READ_ONCE(engine->heartbeat.systole);
-			if (rq)
-				rq = i915_request_get_rcu(rq);
-			rcu_read_unlock();
-		} while (!rq);
-
-		t0 = ktime_get();
-		while (rq == READ_ONCE(engine->heartbeat.systole))
-			yield(); /* work is on the local cpu! */
-		t1 = ktime_get();
-
-		i915_request_put(rq);
-		times[i] = ktime_us_delta(t1, t0);
-	}
-
-	sort(times, ARRAY_SIZE(times), sizeof(times[0]), cmp_u32, NULL);
-
-	pr_info("%s: Heartbeat delay: %uus [%u, %u]\n",
-		engine->name,
-		times[ARRAY_SIZE(times) / 2],
-		times[0],
-		times[ARRAY_SIZE(times) - 1]);
-
-	/*
-	 * Ideally, the upper bound on min work delay would be something like
-	 * 2 * 2 (worst), +1 for scheduling, +1 for slack. In practice, we
-	 * are, even with system_wq_highpri, at the mercy of the CPU scheduler
-	 * and may be stuck behind some slow work for many millisecond. Such
-	 * as our very own display workers.
-	 */
-	if (times[ARRAY_SIZE(times) / 2] > error_threshold) {
-		pr_err("%s: Heartbeat delay was %uus, expected less than %dus\n",
-		       engine->name,
-		       times[ARRAY_SIZE(times) / 2],
-		       error_threshold);
-		err = -EINVAL;
-	}
-
-	reset_heartbeat(engine);
-err_pm:
-	intel_engine_pm_put(engine);
-	intel_context_put(ce);
-	return err;
-}
-
-static int live_heartbeat_fast(void *arg)
-{
-	struct intel_gt *gt = arg;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int err = 0;
-
-	/* Check that the heartbeat ticks at the desired rate. */
-	if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL)
-		return 0;
-
-	for_each_engine(engine, gt, id) {
-		err = __live_heartbeat_fast(engine);
-		if (err)
-			break;
-	}
-
-	return err;
-}
-
 static int __live_heartbeat_off(struct intel_engine_cs *engine)
 {
 	int err;
@@ -372,7 +263,6 @@ int intel_heartbeat_live_selftests(struct drm_i915_private *i915)
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_idle_flush),
 		SUBTEST(live_idle_pulse),
-		SUBTEST(live_heartbeat_fast),
 		SUBTEST(live_heartbeat_off),
 	};
 	int saved_hangcheck;
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
index 525587cfe1af..37ff539a6963 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
@@ -106,6 +106,7 @@ enum {
  */
 enum {
 	GUC_WORKAROUND_KLV_SERIALIZED_RA_MODE				= 0x9001,
+	GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED		= 0x9002,
 };
 
 #endif /* _ABI_GUC_KLVS_ABI_H */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
index c606bb5e3b7b..7995f059f30d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
@@ -815,23 +815,23 @@ engine_instance_list:
 	return PAGE_ALIGN(total_size);
 }
 
-/* Wa_14019159160 */
-static u32 guc_waklv_ra_mode(struct intel_guc *guc, u32 offset, u32 remain)
+static void guc_waklv_enable_simple(struct intel_guc *guc,
+				    u32 klv_id, u32 *offset, u32 *remain)
 {
 	u32 size;
 	u32 klv_entry[] = {
 		/* 16:16 key/length */
-		FIELD_PREP(GUC_KLV_0_KEY, GUC_WORKAROUND_KLV_SERIALIZED_RA_MODE) |
+		FIELD_PREP(GUC_KLV_0_KEY, klv_id) |
 		FIELD_PREP(GUC_KLV_0_LEN, 0),
 		/* 0 dwords data */
 	};
 
 	size = sizeof(klv_entry);
-	GEM_BUG_ON(remain < size);
+	GEM_BUG_ON(*remain < size);
 
-	iosys_map_memcpy_to(&guc->ads_map, offset, klv_entry, size);
-
-	return size;
+	iosys_map_memcpy_to(&guc->ads_map, *offset, klv_entry, size);
+	*offset += size;
+	*remain -= size;
 }
 
 static void guc_waklv_init(struct intel_guc *guc)
@@ -850,11 +850,19 @@ static void guc_waklv_init(struct intel_guc *guc)
 	remain = guc_ads_waklv_size(guc);
 
 	/* Wa_14019159160 */
-	if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) {
-		size = guc_waklv_ra_mode(guc, offset, remain);
-		offset += size;
-		remain -= size;
-	}
+	if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)))
+		guc_waklv_enable_simple(guc,
+					GUC_WORKAROUND_KLV_SERIALIZED_RA_MODE,
+					&offset, &remain);
+
+	/* Wa_16021333562 */
+	if ((GUC_FIRMWARE_VER(guc) >= MAKE_GUC_VER(70, 21, 1)) &&
+	    (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)) ||
+	     IS_MEDIA_GT_IP_RANGE(gt, IP_VER(13, 0), IP_VER(13, 0)) ||
+	     IS_DG2(gt->i915)))
+		guc_waklv_enable_simple(guc,
+					GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED,
+					&offset, &remain);
 
 	size = guc_ads_waklv_size(guc) - remain;
 	if (!size)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d1d21d433766..d7723dd11c80 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -724,8 +724,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
  */
 #define HAS_64K_PAGES(i915) (INTEL_INFO(i915)->has_64k_pages)
 
-#define HAS_REGION(i915, i) (INTEL_INFO(i915)->memory_regions & (i))
-#define HAS_LMEM(i915) HAS_REGION(i915, REGION_LMEM)
+#define HAS_REGION(i915, id) (INTEL_INFO(i915)->memory_regions & BIT(id))
+#define HAS_LMEM(i915) HAS_REGION(i915, INTEL_REGION_LMEM_0)
 
 #define HAS_EXTRA_GT_LIST(i915)   (INTEL_INFO(i915)->extra_gt_list)
 
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 8c00169e3ab7..316e55f3e87b 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -131,6 +131,11 @@ i915_param_named_unsafe(lmem_size, uint, 0400,
 i915_param_named_unsafe(lmem_bar_size, uint, 0400,
 			"Set the lmem bar size(in MiB).");
 
+#if IS_ENABLED(CONFIG_DRM_I915_REPLAY_GPU_HANGS_API)
+i915_param_named(enable_debug_only_api, bool, 0400,
+		 "Enable support for unstable debug only userspace API. (default:false)");
+#endif
+
 static void _param_print_bool(struct drm_printer *p, const char *name,
 			      bool val)
 {
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index 2eb3f2115ff2..0fbcb5b6d7bf 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -63,7 +63,8 @@ struct drm_printer;
 	/* leave bools at the end to not create holes */ \
 	param(bool, enable_hangcheck, true, 0600) \
 	param(bool, error_capture, true, IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) ? 0600 : 0) \
-	param(bool, enable_gvt, false, IS_ENABLED(CONFIG_DRM_I915_GVT) ? 0400 : 0)
+	param(bool, enable_gvt, false, IS_ENABLED(CONFIG_DRM_I915_GVT) ? 0400 : 0) \
+	param(bool, enable_debug_only_api, false, IS_ENABLED(CONFIG_DRM_I915_REPLAY_GPU_HANGS_API) ? 0400 : 0)
 
 #define MEMBER(T, member, ...) T member;
 struct i915_params {
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 7058efa75324..ce4dfd65fafa 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -76,7 +76,7 @@ __diag_ignore_all("-Woverride-init", "Allow field initialization overrides for d
 	.__runtime.page_sizes = I915_GTT_PAGE_SIZE_4K
 
 #define GEN_DEFAULT_REGIONS \
-	.memory_regions = REGION_SMEM | REGION_STOLEN_SMEM
+	.memory_regions = BIT(INTEL_REGION_SMEM) | BIT(INTEL_REGION_STOLEN_SMEM)
 
 #define I830_FEATURES \
 	GEN(2), \
@@ -655,7 +655,7 @@ static const struct intel_device_info rkl_info = {
 };
 
 #define DGFX_FEATURES \
-	.memory_regions = REGION_SMEM | REGION_LMEM | REGION_STOLEN_LMEM, \
+	.memory_regions = BIT(INTEL_REGION_SMEM) | BIT(INTEL_REGION_LMEM_0) | BIT(INTEL_REGION_STOLEN_LMEM), \
 	.has_llc = 0, \
 	.has_pxp = 0, \
 	.has_snoop = 1, \
@@ -781,7 +781,7 @@ static const struct intel_device_info mtl_info = {
 	.has_snoop = 1,
 	.max_pat_index = 4,
 	.has_pxp = 1,
-	.memory_regions = REGION_SMEM | REGION_STOLEN_LMEM,
+	.memory_regions = BIT(INTEL_REGION_SMEM) | BIT(INTEL_REGION_STOLEN_LMEM),
 	.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(CCS0),
 	MTL_CACHELEVEL,
 };
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index 52d998e5c21a..172dfa7c3588 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -332,7 +332,7 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915)
 		struct intel_memory_region *mem = ERR_PTR(-ENODEV);
 		u16 type, instance;
 
-		if (!HAS_REGION(i915, BIT(i)))
+		if (!HAS_REGION(i915, i))
 			continue;
 
 		type = intel_region_map[i].class;
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 8c927e303c4a..5973b6fe13cf 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -38,11 +38,6 @@ enum intel_region_id {
 	INTEL_REGION_UNKNOWN, /* Should be last */
 };
 
-#define REGION_SMEM     BIT(INTEL_REGION_SMEM)
-#define REGION_LMEM     BIT(INTEL_REGION_LMEM_0)
-#define REGION_STOLEN_SMEM   BIT(INTEL_REGION_STOLEN_SMEM)
-#define REGION_STOLEN_LMEM   BIT(INTEL_REGION_STOLEN_LMEM)
-
 #define I915_ALLOC_CONTIGUOUS     BIT(0)
 
 #define for_each_memory_region(mr, i915, id) \
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 729409a4bada..2eba289d88ad 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -2614,12 +2614,19 @@ void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore,
 static void driver_initiated_flr(struct intel_uncore *uncore)
 {
 	struct drm_i915_private *i915 = uncore->i915;
-	const unsigned int flr_timeout_ms = 3000; /* specs recommend a 3s wait */
+	unsigned int flr_timeout_ms;
 	int ret;
 
 	drm_dbg(&i915->drm, "Triggering Driver-FLR\n");
 
 	/*
+	 * The specification recommends a 3 seconds FLR reset timeout. To be
+	 * cautious, we will extend this to 9 seconds, three times the specified
+	 * timeout.
+	 */
+	flr_timeout_ms = 9000;
+
+	/*
 	 * Make sure any pending FLR requests have cleared by waiting for the
 	 * FLR trigger bit to go to zero. Also clear GU_DEBUG's DRIVERFLR_STATUS
 	 * to make sure it's not still set from a prior attempt (it's a write to
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index af349fd9abc2..0bd29846873b 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -122,7 +122,7 @@ static const struct intel_device_info mock_info = {
 	.__runtime.page_sizes = (I915_GTT_PAGE_SIZE_4K |
 				 I915_GTT_PAGE_SIZE_64K |
 				 I915_GTT_PAGE_SIZE_2M),
-	.memory_regions = REGION_SMEM,
+	.memory_regions = BIT(INTEL_REGION_SMEM),
 	.platform_engine_mask = BIT(0),
 
 	/* simply use legacy cache level for mock device */