Merge tag 'drm-intel-gt-next-2023-12-08' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

-   drm/i915: Implement fdinfo memory stats printing

    Use the newly added drm_print_memory_stats helper to show memory
    utilisation of our objects in drm/driver specific fdinfo output.

    To collect the stats we walk the per memory regions object lists
    and accumulate object size into the respective drm_memory_stats
    categories.

Cross-subsystem Changes:

- Backmerge of drm-next (to bring drm-intel-next for PXP changes)

Driver Changes:

- Wa_18028616096 now applies to all DG2 (Matt R)
- Drop Wa_22014600077 on all DG2 (Matt R)
- Add new ATS-M device ID (Haridhar)
- More Meteorlake (MTL) workarounds (Matt R, Dnyaneshwar, Jonathan,
  Gustavo, Radhakrishna)
- PMU WARN_ON cleanup on driver unbind (Umesh)
- Limit GGTT WC flushing workaround to pre BXT/ICL platforms
- Complement implementation for Wa_16018031267 / Wa_16018063123
  (Andrzej, Jonathan, Nirmoy, Chris)

- Properly print internal GSC engine in trace logs (Tvrtko)
- Track gt pm wakerefs (Andrzej)
- Fix null deref bugs on perf code when perf is disabled (Harshit,
  Tvrtko)
- Fix __i915_request_create memory leak on driver unbind (Andrzej)
- Remove spurious unsupported HuC message on MTL (Daniele)
- Read a shadowed mmio register for ggtt flush (Vinay)
- Add missing new-line to GT_TRACE (Andrzej)
- Add drm_dbgs for critical PXP events (Alan)
- Skip pxp init if gt is wedged (Zhanjun)

- Replace custom intel runtime_pm tracker with ref_tracker library
  (Andrzej)
- Compiler warning/static checker/coding style cleanups (Arnd, Nirmoy,
  Soumya, Gilbert, Dorcas, Kunwu, Sam, Tvrtko)
- Code structure and helper cleanups (Jani, Tvrtko, Andi)
- Selftest improvements (John, Tvrtko, Andrzej)

Signed-off-by: Dave Airlie <airlied@redhat.com>

# Conflicts:
#	drivers/gpu/drm/i915/gt/intel_gt_mcr.c
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZXNBcsSwJEVsq9On@jlahtine-mobl.ger.corp.intel.com

77 files changed, 1232 insertions, 635 deletions

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 2d21930d5501..5b7162076850 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -24,7 +24,9 @@ config DRM_I915_DEBUG
 	select DEBUG_FS
 	select PREEMPT_COUNT
 	select I2C_CHARDEV
+	select REF_TRACKER
 	select STACKDEPOT
+	select STACKTRACE
 	select DRM_DP_AUX_CHARDEV
 	select X86_MSR # used by igt/pm_rpm
 	select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
@@ -38,6 +40,7 @@ config DRM_I915_DEBUG
 	select DRM_I915_DEBUG_GEM_ONCE
 	select DRM_I915_DEBUG_MMIO
 	select DRM_I915_DEBUG_RUNTIME_PM
+	select DRM_I915_DEBUG_WAKEREF
 	select DRM_I915_SW_FENCE_DEBUG_OBJECTS
 	select DRM_I915_SELFTEST
 	default n
@@ -231,7 +234,9 @@ config DRM_I915_DEBUG_RUNTIME_PM
 	bool "Enable extra state checking for runtime PM"
 	depends on DRM_I915
 	default n
+	select REF_TRACKER
 	select STACKDEPOT
+	select STACKTRACE
 	help
 	  Choose this option to turn on extra state checking for the
 	  runtime PM functionality. This may introduce overhead during
@@ -240,3 +245,16 @@ config DRM_I915_DEBUG_RUNTIME_PM
 	  Recommended for driver developers only.
 
 	  If in doubt, say "N"
+
+config DRM_I915_DEBUG_WAKEREF
+	bool "Enable extra tracking for wakerefs"
+	depends on DRM_I915
+	select REF_TRACKER
+	select STACKDEPOT
+	select STACKTRACE
+	help
+	  Choose this option to turn on extra state checking and usage
+	  tracking for the wakerefPM functionality. This may introduce
+	  overhead during driver runtime.
+
+	  If in doubt, say "N"
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index f23080a4368d..5f091502719b 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -405,7 +405,7 @@ print_async_put_domains_state(struct i915_power_domains *power_domains)
 						     struct drm_i915_private,
 						     display.power.domains);
 
-	drm_dbg(&i915->drm, "async_put_wakeref %u\n",
+	drm_dbg(&i915->drm, "async_put_wakeref %lu\n",
 		power_domains->async_put_wakeref);
 
 	print_power_domains(power_domains, "async_put_domains[0]",
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index e38f06a6e56e..dcbfe32fd30c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -279,7 +279,8 @@ static int proto_context_set_protected(struct drm_i915_private *i915,
 }
 
 static struct i915_gem_proto_context *
-proto_context_create(struct drm_i915_private *i915, unsigned int flags)
+proto_context_create(struct drm_i915_file_private *fpriv,
+		     struct drm_i915_private *i915, unsigned int flags)
 {
 	struct i915_gem_proto_context *pc, *err;
 
@@ -287,6 +288,7 @@ proto_context_create(struct drm_i915_private *i915, unsigned int flags)
 	if (!pc)
 		return ERR_PTR(-ENOMEM);
 
+	pc->fpriv = fpriv;
 	pc->num_user_engines = -1;
 	pc->user_engines = NULL;
 	pc->user_flags = BIT(UCONTEXT_BANNABLE) |
@@ -1622,6 +1624,7 @@ i915_gem_create_context(struct drm_i915_private *i915,
 			err = PTR_ERR(ppgtt);
 			goto err_ctx;
 		}
+		ppgtt->vm.fpriv = pc->fpriv;
 		vm = &ppgtt->vm;
 	}
 	if (vm)
@@ -1741,7 +1744,7 @@ int i915_gem_context_open(struct drm_i915_private *i915,
 	/* 0 reserved for invalid/unassigned ppgtt */
 	xa_init_flags(&file_priv->vm_xa, XA_FLAGS_ALLOC1);
 
-	pc = proto_context_create(i915, 0);
+	pc = proto_context_create(file_priv, i915, 0);
 	if (IS_ERR(pc)) {
 		err = PTR_ERR(pc);
 		goto err;
@@ -1823,6 +1826,7 @@ int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,
 
 	GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
 	args->vm_id = id;
+	ppgtt->vm.fpriv = file_priv;
 	return 0;
 
 err_put:
@@ -2285,7 +2289,8 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 		return -EIO;
 	}
 
-	ext_data.pc = proto_context_create(i915, args->flags);
+	ext_data.pc = proto_context_create(file->driver_priv, i915,
+					   args->flags);
 	if (IS_ERR(ext_data.pc))
 		return PTR_ERR(ext_data.pc);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index cb78214a7dcd..c573c067779f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -188,6 +188,9 @@ struct i915_gem_proto_engine {
  * CONTEXT_CREATE_SET_PARAM during GEM_CONTEXT_CREATE.
  */
 struct i915_gem_proto_context {
+	/** @fpriv: Client which creates the context */
+	struct drm_i915_file_private *fpriv;
+
 	/** @vm: See &i915_gem_context.vm */
 	struct i915_address_space *vm;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index ccc077b74d2d..81a57dd52dfd 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -254,6 +254,8 @@ struct i915_execbuffer {
 	struct intel_gt *gt; /* gt for the execbuf */
 	struct intel_context *context; /* logical state for the request */
 	struct i915_gem_context *gem_context; /** caller's context */
+	intel_wakeref_t wakeref;
+	intel_wakeref_t wakeref_gt0;
 
 	/** our requests to build */
 	struct i915_request *requests[MAX_ENGINE_INSTANCE + 1];
@@ -1679,7 +1681,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb)
 		urelocs = u64_to_user_ptr(eb->exec[i].relocs_ptr);
 		size = nreloc * sizeof(*relocs);
 
-		relocs = kvmalloc_array(size, 1, GFP_KERNEL);
+		relocs = kvmalloc_array(1, size, GFP_KERNEL);
 		if (!relocs) {
 			err = -ENOMEM;
 			goto err;
@@ -2720,13 +2722,13 @@ eb_select_engine(struct i915_execbuffer *eb)
 
 	for_each_child(ce, child)
 		intel_context_get(child);
-	intel_gt_pm_get(gt);
+	eb->wakeref = intel_gt_pm_get(ce->engine->gt);
 	/*
 	 * Keep GT0 active on MTL so that i915_vma_parked() doesn't
 	 * free VMAs while execbuf ioctl is validating VMAs.
 	 */
 	if (gt->info.id)
-		intel_gt_pm_get(to_gt(gt->i915));
+		eb->wakeref_gt0 = intel_gt_pm_get(to_gt(gt->i915));
 
 	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
 		err = intel_context_alloc_state(ce);
@@ -2766,9 +2768,9 @@ eb_select_engine(struct i915_execbuffer *eb)
 
 err:
 	if (gt->info.id)
-		intel_gt_pm_put(to_gt(gt->i915));
+		intel_gt_pm_put(to_gt(gt->i915), eb->wakeref_gt0);
 
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(ce->engine->gt, eb->wakeref);
 	for_each_child(ce, child)
 		intel_context_put(child);
 	intel_context_put(ce);
@@ -2786,8 +2788,8 @@ eb_put_engine(struct i915_execbuffer *eb)
 	 * i915_vma_parked() from interfering while execbuf validates vmas.
 	 */
 	if (eb->gt->info.id)
-		intel_gt_pm_put(to_gt(eb->gt->i915));
-	intel_gt_pm_put(eb->gt);
+		intel_gt_pm_put(to_gt(eb->gt->i915), eb->wakeref_gt0);
+	intel_gt_pm_put(eb->context->engine->gt, eb->wakeref);
 	for_each_child(eb->context, child)
 		intel_context_put(child);
 	intel_context_put(eb->context);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index c26d87555825..25eeeb863209 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -106,6 +106,10 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 
 	INIT_LIST_HEAD(&obj->mm.link);
 
+#ifdef CONFIG_PROC_FS
+	INIT_LIST_HEAD(&obj->client_link);
+#endif
+
 	INIT_LIST_HEAD(&obj->lut_list);
 	spin_lock_init(&obj->lut_lock);
 
@@ -293,6 +297,10 @@ void __i915_gem_free_object_rcu(struct rcu_head *head)
 		container_of(head, typeof(*obj), rcu);
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 
+	/* We need to keep this alive for RCU read access from fdinfo. */
+	if (obj->mm.n_placements > 1)
+		kfree(obj->mm.placements);
+
 	i915_gem_object_free(obj);
 
 	GEM_BUG_ON(!atomic_read(&i915->mm.free_count));
@@ -389,9 +397,6 @@ void __i915_gem_free_object(struct drm_i915_gem_object *obj)
 	if (obj->ops->release)
 		obj->ops->release(obj);
 
-	if (obj->mm.n_placements > 1)
-		kfree(obj->mm.placements);
-
 	if (obj->shares_resv_from)
 		i915_vm_resv_put(obj->shares_resv_from);
 
@@ -442,6 +447,8 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj)
 
 	GEM_BUG_ON(i915_gem_object_is_framebuffer(obj));
 
+	i915_drm_client_remove_object(obj);
+
 	/*
 	 * Before we free the object, make sure any pure RCU-only
 	 * read-side critical sections are complete, e.g.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 2292404007c8..0c5cdab278b6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -302,6 +302,18 @@ struct drm_i915_gem_object {
 	 */
 	struct i915_address_space *shares_resv_from;
 
+#ifdef CONFIG_PROC_FS
+	/**
+	 * @client: @i915_drm_client which created the object
+	 */
+	struct i915_drm_client *client;
+
+	/**
+	 * @client_link: Link into @i915_drm_client.objects_list
+	 */
+	struct list_head client_link;
+#endif
+
 	union {
 		struct rcu_head rcu;
 		struct llist_node freed;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index 1a766d8e7cce..8c88075eeab2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -386,6 +386,27 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915,
 
 	drm_dbg(&i915->drm, "GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val);
 
+	/* Wa_14019821291 */
+	if (MEDIA_VER_FULL(i915) == IP_VER(13, 0)) {
+		/*
+		 * This workaround is primarily implemented by the BIOS.  We
+		 * just need to figure out whether the BIOS has applied the
+		 * workaround (meaning the programmed address falls within
+		 * the DSM) and, if so, reserve that part of the DSM to
+		 * prevent accidental reuse.  The DSM location should be just
+		 * below the WOPCM.
+		 */
+		u64 gscpsmi_base = intel_uncore_read64_2x32(uncore,
+							    MTL_GSCPSMI_BASEADDR_LSB,
+							    MTL_GSCPSMI_BASEADDR_MSB);
+		if (gscpsmi_base >= i915->dsm.stolen.start &&
+		    gscpsmi_base < i915->dsm.stolen.end) {
+			*base = gscpsmi_base;
+			*size = i915->dsm.stolen.end - gscpsmi_base;
+			return;
+		}
+	}
+
 	switch (reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK) {
 	case GEN8_STOLEN_RESERVED_1M:
 		*size = 1024 * 1024;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 3bef1beec7cb..3fd68a099a85 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -85,6 +85,7 @@ out:
 
 static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
 {
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	u32 __iomem *map;
 	int err = 0;
@@ -99,7 +100,7 @@ static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	intel_gt_pm_get(vma->vm->gt);
+	wakeref = intel_gt_pm_get(vma->vm->gt);
 
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
@@ -112,12 +113,13 @@ static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
 	i915_vma_unpin_iomap(vma);
 
 out_rpm:
-	intel_gt_pm_put(vma->vm->gt);
+	intel_gt_pm_put(vma->vm->gt, wakeref);
 	return err;
 }
 
 static int gtt_get(struct context *ctx, unsigned long offset, u32 *v)
 {
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	u32 __iomem *map;
 	int err = 0;
@@ -132,7 +134,7 @@ static int gtt_get(struct context *ctx, unsigned long offset, u32 *v)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	intel_gt_pm_get(vma->vm->gt);
+	wakeref = intel_gt_pm_get(vma->vm->gt);
 
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
@@ -145,7 +147,7 @@ static int gtt_get(struct context *ctx, unsigned long offset, u32 *v)
 	i915_vma_unpin_iomap(vma);
 
 out_rpm:
-	intel_gt_pm_put(vma->vm->gt);
+	intel_gt_pm_put(vma->vm->gt, wakeref);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 72957a36a36b..2c51a2c452fc 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -630,14 +630,14 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 static void disable_retire_worker(struct drm_i915_private *i915)
 {
 	i915_gem_driver_unregister__shrinker(i915);
-	intel_gt_pm_get(to_gt(i915));
+	intel_gt_pm_get_untracked(to_gt(i915));
 	cancel_delayed_work_sync(&to_gt(i915)->requests.retire_work);
 }
 
 static void restore_retire_worker(struct drm_i915_private *i915)
 {
 	igt_flush_test(i915);
-	intel_gt_pm_put(to_gt(i915));
+	intel_gt_pm_put_untracked(to_gt(i915));
 	i915_gem_driver_register__shrinker(i915);
 }
 
@@ -778,6 +778,7 @@ err_obj:
 
 static int gtt_set(struct drm_i915_gem_object *obj)
 {
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	void __iomem *map;
 	int err = 0;
@@ -786,7 +787,7 @@ static int gtt_set(struct drm_i915_gem_object *obj)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	intel_gt_pm_get(vma->vm->gt);
+	wakeref = intel_gt_pm_get(vma->vm->gt);
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
 	if (IS_ERR(map)) {
@@ -798,12 +799,13 @@ static int gtt_set(struct drm_i915_gem_object *obj)
 	i915_vma_unpin_iomap(vma);
 
 out:
-	intel_gt_pm_put(vma->vm->gt);
+	intel_gt_pm_put(vma->vm->gt, wakeref);
 	return err;
 }
 
 static int gtt_check(struct drm_i915_gem_object *obj)
 {
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	void __iomem *map;
 	int err = 0;
@@ -812,7 +814,7 @@ static int gtt_check(struct drm_i915_gem_object *obj)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	intel_gt_pm_get(vma->vm->gt);
+	wakeref = intel_gt_pm_get(vma->vm->gt);
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
 	if (IS_ERR(map)) {
@@ -828,7 +830,7 @@ static int gtt_check(struct drm_i915_gem_object *obj)
 	i915_vma_unpin_iomap(vma);
 
 out:
-	intel_gt_pm_put(vma->vm->gt);
+	intel_gt_pm_put(vma->vm->gt, wakeref);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index e199d7dbb876..2b0327cc47c2 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -83,7 +83,7 @@ live_context(struct drm_i915_private *i915, struct file *file)
 	int err;
 	u32 id;
 
-	pc = proto_context_create(i915, 0);
+	pc = proto_context_create(fpriv, i915, 0);
 	if (IS_ERR(pc))
 		return ERR_CAST(pc);
 
@@ -152,7 +152,7 @@ kernel_context(struct drm_i915_private *i915,
 	struct i915_gem_context *ctx;
 	struct i915_gem_proto_context *pc;
 
-	pc = proto_context_create(i915, 0);
+	pc = proto_context_create(NULL, i915, 0);
 	if (IS_ERR(pc))
 		return ERR_CAST(pc);
 
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 9895e18df043..fa46d2308b0e 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -5,6 +5,7 @@
 
 #include <linux/log2.h>
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_lmem.h"
 
 #include "gen8_ppgtt.h"
@@ -222,6 +223,9 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 
+	if (vm->rsvd.obj)
+		i915_gem_object_put(vm->rsvd.obj);
+
 	if (intel_vgpu_active(vm->i915))
 		gen8_ppgtt_notify_vgt(ppgtt, false);
 
@@ -950,6 +954,41 @@ err_pd:
 	return ERR_PTR(err);
 }
 
+static int gen8_init_rsvd(struct i915_address_space *vm)
+{
+	struct drm_i915_private *i915 = vm->i915;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int ret;
+
+	/* The memory will be used only by GPU. */
+	obj = i915_gem_object_create_lmem(i915, PAGE_SIZE,
+					  I915_BO_ALLOC_VOLATILE |
+					  I915_BO_ALLOC_GPU_ONLY);
+	if (IS_ERR(obj))
+		obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto unref;
+	}
+
+	ret = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_HIGH);
+	if (ret)
+		goto unref;
+
+	vm->rsvd.vma = i915_vma_make_unshrinkable(vma);
+	vm->rsvd.obj = obj;
+	vm->total -= vma->node.size;
+	return 0;
+unref:
+	i915_gem_object_put(obj);
+	return ret;
+}
+
 /*
  * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
  * with a net effect resembling a 2-level page table in normal x86 terms. Each
@@ -1031,6 +1070,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 	if (intel_vgpu_active(gt->i915))
 		gen8_ppgtt_notify_vgt(ppgtt, true);
 
+	err = gen8_init_rsvd(&ppgtt->vm);
+	if (err)
+		goto err_put;
+
 	return ppgtt;
 
 err_put:
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index ecc990ec1b95..d650beb8ed22 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -28,11 +28,14 @@ static void irq_disable(struct intel_breadcrumbs *b)
 
 static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 {
+	intel_wakeref_t wakeref;
+
 	/*
 	 * Since we are waiting on a request, the GPU should be busy
 	 * and should have its own rpm reference.
 	 */
-	if (GEM_WARN_ON(!intel_gt_pm_get_if_awake(b->irq_engine->gt)))
+	wakeref = intel_gt_pm_get_if_awake(b->irq_engine->gt);
+	if (GEM_WARN_ON(!wakeref))
 		return;
 
 	/*
@@ -41,7 +44,7 @@ static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 	 * which we can add a new waiter and avoid the cost of re-enabling
 	 * the irq.
 	 */
-	WRITE_ONCE(b->irq_armed, true);
+	WRITE_ONCE(b->irq_armed, wakeref);
 
 	/* Requests may have completed before we could enable the interrupt. */
 	if (!b->irq_enabled++ && b->irq_enable(b))
@@ -61,12 +64,14 @@ static void intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 
 static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
 {
+	intel_wakeref_t wakeref = b->irq_armed;
+
 	GEM_BUG_ON(!b->irq_enabled);
 	if (!--b->irq_enabled)
 		b->irq_disable(b);
 
-	WRITE_ONCE(b->irq_armed, false);
-	intel_gt_pm_put_async(b->irq_engine->gt);
+	WRITE_ONCE(b->irq_armed, 0);
+	intel_gt_pm_put_async(b->irq_engine->gt, wakeref);
 }
 
 static void intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
index 72dfd3748c4c..bdf09fd67b6e 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
@@ -13,6 +13,7 @@
 #include <linux/types.h>
 
 #include "intel_engine_types.h"
+#include "intel_wakeref.h"
 
 /*
  * Rather than have every client wait upon all user interrupts,
@@ -43,7 +44,7 @@ struct intel_breadcrumbs {
 	spinlock_t irq_lock; /* protects the interrupt from hardirq context */
 	struct irq_work irq_work; /* for use from inside irq_lock */
 	unsigned int irq_enabled;
-	bool irq_armed;
+	intel_wakeref_t irq_armed;
 
 	/* Not all breadcrumbs are attached to physical HW */
 	intel_engine_mask_t	engine_mask;
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index a53b26178f0a..a2f1245741bb 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -6,6 +6,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
 
+#include "i915_drm_client.h"
 #include "i915_drv.h"
 #include "i915_trace.h"
 
@@ -50,6 +51,7 @@ intel_context_create(struct intel_engine_cs *engine)
 
 int intel_context_alloc_state(struct intel_context *ce)
 {
+	struct i915_gem_context *ctx;
 	int err = 0;
 
 	if (mutex_lock_interruptible(&ce->pin_mutex))
@@ -66,6 +68,18 @@ int intel_context_alloc_state(struct intel_context *ce)
 			goto unlock;
 
 		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+
+		rcu_read_lock();
+		ctx = rcu_dereference(ce->gem_context);
+		if (ctx && !kref_get_unless_zero(&ctx->ref))
+			ctx = NULL;
+		rcu_read_unlock();
+		if (ctx) {
+			if (ctx->client)
+				i915_drm_client_add_context_objects(ctx->client,
+								    ce);
+			i915_gem_context_put(ctx);
+		}
 	}
 
 unlock:
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index a80e3b7c24ff..25564c01507e 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -212,7 +212,7 @@ static inline void intel_context_enter(struct intel_context *ce)
 		return;
 
 	ce->ops->enter(ce);
-	intel_gt_pm_get(ce->vm->gt);
+	ce->wakeref = intel_gt_pm_get(ce->vm->gt);
 }
 
 static inline void intel_context_mark_active(struct intel_context *ce)
@@ -229,7 +229,7 @@ static inline void intel_context_exit(struct intel_context *ce)
 	if (--ce->active_count)
 		return;
 
-	intel_gt_pm_put_async(ce->vm->gt);
+	intel_gt_pm_put_async(ce->vm->gt, ce->wakeref);
 	ce->ops->exit(ce);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index aceaac28a33e..7eccbd70d89f 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -17,6 +17,7 @@
 #include "i915_utils.h"
 #include "intel_engine_types.h"
 #include "intel_sseu.h"
+#include "intel_wakeref.h"
 
 #include "uc/intel_guc_fwif.h"
 
@@ -112,6 +113,7 @@ struct intel_context {
 	u32 ring_size;
 	struct intel_ring *ring;
 	struct intel_timeline *timeline;
+	intel_wakeref_t wakeref;
 
 	unsigned long flags;
 #define CONTEXT_BARRIER_BIT		0
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 4a11219e560e..40687806d22a 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -47,7 +47,7 @@
 #define GEN9_LR_CONTEXT_RENDER_SIZE	(22 * PAGE_SIZE)
 #define GEN11_LR_CONTEXT_RENDER_SIZE	(14 * PAGE_SIZE)
 
-#define GEN8_LR_CONTEXT_OTHER_SIZE	( 2 * PAGE_SIZE)
+#define GEN8_LR_CONTEXT_OTHER_SIZE	(2 * PAGE_SIZE)
 
 #define MAX_MMIO_BASES 3
 struct engine_info {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index 9a527e1f5be6..1a8e2b7db013 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -188,7 +188,7 @@ static void heartbeat(struct work_struct *wrk)
 			 * low latency and no jitter] the chance to naturally
 			 * complete before being preempted.
 			 */
-			attr.priority = 0;
+			attr.priority = I915_PRIORITY_NORMAL;
 			if (rq->sched.attr.priority >= attr.priority)
 				attr.priority = I915_PRIORITY_HEARTBEAT;
 			if (rq->sched.attr.priority >= attr.priority)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index e91fc881dbf1..96bdb93a948d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -63,7 +63,7 @@ static int __engine_unpark(struct intel_wakeref *wf)
 
 	ENGINE_TRACE(engine, "\n");
 
-	intel_gt_pm_get(engine->gt);
+	engine->wakeref_track = intel_gt_pm_get(engine->gt);
 
 	/* Discard stale context state from across idling */
 	ce = engine->kernel_context;
@@ -122,6 +122,7 @@ __queue_and_release_pm(struct i915_request *rq,
 	 */
 	GEM_BUG_ON(rq->context->active_count != 1);
 	__intel_gt_pm_get(engine->gt);
+	rq->context->wakeref = intel_wakeref_track(&engine->gt->wakeref);
 
 	/*
 	 * We have to serialise all potential retirement paths with our
@@ -285,7 +286,7 @@ static int __engine_park(struct intel_wakeref *wf)
 		engine->park(engine);
 
 	/* While gt calls i915_vma_parked(), we have to break the lock cycle */
-	intel_gt_pm_put_async(engine->gt);
+	intel_gt_pm_put_async(engine->gt, engine->wakeref_track);
 	return 0;
 }
 
@@ -296,7 +297,7 @@ static const struct intel_wakeref_ops wf_ops = {
 
 void intel_engine_init__pm(struct intel_engine_cs *engine)
 {
-	intel_wakeref_init(&engine->wakeref, engine->i915, &wf_ops);
+	intel_wakeref_init(&engine->wakeref, engine->i915, &wf_ops, engine->name);
 	intel_engine_init_heartbeat(engine);
 
 	intel_gsc_idle_msg_enable(engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
index fdd4ddd3a978..a8eac59e3779 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
@@ -118,9 +118,15 @@
 #define   CCID_EXTENDED_STATE_RESTORE		BIT(2)
 #define   CCID_EXTENDED_STATE_SAVE		BIT(3)
 #define RING_BB_PER_CTX_PTR(base)		_MMIO((base) + 0x1c0) /* gen8+ */
+#define   PER_CTX_BB_FORCE			BIT(2)
+#define   PER_CTX_BB_VALID			BIT(0)
+
 #define RING_INDIRECT_CTX(base)			_MMIO((base) + 0x1c4) /* gen8+ */
 #define RING_INDIRECT_CTX_OFFSET(base)		_MMIO((base) + 0x1c8) /* gen8+ */
 #define ECOSKPD(base)				_MMIO((base) + 0x1d0)
+#define   XEHP_BLITTER_SCHEDULING_MODE_MASK	REG_GENMASK(12, 11)
+#define   XEHP_BLITTER_ROUND_ROBIN_MODE		\
+		REG_FIELD_PREP(XEHP_BLITTER_SCHEDULING_MODE_MASK, 1)
 #define   ECO_CONSTANT_BUFFER_SR_DISABLE	REG_BIT(4)
 #define   ECO_GATING_CX_ONLY			REG_BIT(3)
 #define   GEN6_BLITTER_FBC_NOTIFY		REG_BIT(3)
@@ -257,5 +263,7 @@
 #define VDBOX_CGCTL3F18(base)			_MMIO((base) + 0x3f18)
 #define   ALNUNIT_CLKGATE_DIS			REG_BIT(13)
 
+#define VDBOX_CGCTL3F1C(base)			_MMIO((base) + 0x3f1c)
+#define   MFXPIPE_CLKGATE_DIS			REG_BIT(3)
 
 #endif /* __INTEL_ENGINE_REGS__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 8769760257fd..960e6be2042f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -446,7 +446,9 @@ struct intel_engine_cs {
 	unsigned long serial;
 
 	unsigned long wakeref_serial;
+	intel_wakeref_t wakeref_track;
 	struct intel_wakeref wakeref;
+
 	struct file *default_state;
 
 	struct {
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index e8f42ec6b1b4..42aade0faf2d 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -630,7 +630,7 @@ static void __execlists_schedule_out(struct i915_request * const rq,
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
 	if (engine->fw_domain && !--engine->fw_active)
 		intel_uncore_forcewake_put(engine->uncore, engine->fw_domain);
-	intel_gt_pm_put_async(engine->gt);
+	intel_gt_pm_put_async_untracked(engine->gt);
 
 	/*
 	 * If this is part of a virtual engine, its next request may
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 15fc8e4703f4..21a7e3191c18 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -245,16 +245,15 @@ static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
 	gen8_ggtt_invalidate(ggtt);
 
 	list_for_each_entry(gt, &ggtt->gt_list, ggtt_link) {
-		if (intel_guc_tlb_invalidation_is_available(&gt->uc.guc)) {
+		if (intel_guc_tlb_invalidation_is_available(&gt->uc.guc))
 			guc_ggtt_ct_invalidate(gt);
-		} else if (GRAPHICS_VER(i915) >= 12) {
+		else if (GRAPHICS_VER(i915) >= 12)
 			intel_uncore_write_fw(gt->uncore,
 					      GEN12_GUC_TLB_INV_CR,
 					      GEN12_GUC_TLB_INV_CR_INVALIDATE);
-		} else {
+		else
 			intel_uncore_write_fw(gt->uncore,
 					      GEN8_GTCR, GEN8_GTCR_INVALIDATE);
-		}
 	}
 }
 
@@ -297,7 +296,7 @@ static bool should_update_ggtt_with_bind(struct i915_ggtt *ggtt)
 	return intel_gt_is_bind_context_ready(gt);
 }
 
-static struct intel_context *gen8_ggtt_bind_get_ce(struct i915_ggtt *ggtt)
+static struct intel_context *gen8_ggtt_bind_get_ce(struct i915_ggtt *ggtt, intel_wakeref_t *wakeref)
 {
 	struct intel_context *ce;
 	struct intel_gt *gt = ggtt->vm.gt;
@@ -314,7 +313,8 @@ static struct intel_context *gen8_ggtt_bind_get_ce(struct i915_ggtt *ggtt)
 	 * would conflict with fs_reclaim trying to allocate memory while
 	 * doing rpm_resume().
 	 */
-	if (!intel_gt_pm_get_if_awake(gt))
+	*wakeref = intel_gt_pm_get_if_awake(gt);
+	if (!*wakeref)
 		return NULL;
 
 	intel_engine_pm_get(ce->engine);
@@ -322,10 +322,10 @@ static struct intel_context *gen8_ggtt_bind_get_ce(struct i915_ggtt *ggtt)
 	return ce;
 }
 
-static void gen8_ggtt_bind_put_ce(struct intel_context *ce)
+static void gen8_ggtt_bind_put_ce(struct intel_context *ce, intel_wakeref_t wakeref)
 {
 	intel_engine_pm_put(ce->engine);
-	intel_gt_pm_put(ce->engine->gt);
+	intel_gt_pm_put(ce->engine->gt, wakeref);
 }
 
 static bool gen8_ggtt_bind_ptes(struct i915_ggtt *ggtt, u32 offset,
@@ -338,12 +338,13 @@ static bool gen8_ggtt_bind_ptes(struct i915_ggtt *ggtt, u32 offset,
 	struct sgt_iter iter;
 	struct i915_request *rq;
 	struct intel_context *ce;
+	intel_wakeref_t wakeref;
 	u32 *cs;
 
 	if (!num_entries)
 		return true;
 
-	ce = gen8_ggtt_bind_get_ce(ggtt);
+	ce = gen8_ggtt_bind_get_ce(ggtt, &wakeref);
 	if (!ce)
 		return false;
 
@@ -419,13 +420,13 @@ queue_err_rq:
 		offset += n_ptes;
 	}
 
-	gen8_ggtt_bind_put_ce(ce);
+	gen8_ggtt_bind_put_ce(ce, wakeref);
 	return true;
 
 err_rq:
 	i915_request_put(rq);
 put_ce:
-	gen8_ggtt_bind_put_ce(ce);
+	gen8_ggtt_bind_put_ce(ce, wakeref);
 	return false;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index ba1186fc524f..a425db5ed3a2 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -451,7 +451,7 @@ void intel_gt_flush_ggtt_writes(struct intel_gt *gt)
 
 		spin_lock_irqsave(&uncore->lock, flags);
 		intel_uncore_posting_read_fw(uncore,
-					     RING_HEAD(RENDER_RING_BASE));
+					     RING_TAIL(RENDER_RING_BASE));
 		spin_unlock_irqrestore(&uncore->lock, flags);
 	}
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index e1f13735f530..608f5c872928 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -82,6 +82,10 @@ struct drm_printer;
 		  ##__VA_ARGS__);					\
 } while (0)
 
+#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \
+	IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 55), IP_VER(12, 71)) && \
+	engine->class == COPY_ENGINE_CLASS && engine->instance == 0)
+
 static inline bool gt_is_root(struct intel_gt *gt)
 {
 	return !gt->info.id;
@@ -114,6 +118,11 @@ static inline struct intel_gt *gsc_to_gt(struct intel_gsc *gsc)
 	return container_of(gsc, struct intel_gt, gsc);
 }
 
+static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc)
+{
+	return guc_to_gt(guc)->i915;
+}
+
 void intel_gt_common_init_early(struct intel_gt *gt);
 int intel_root_gt_init_early(struct drm_i915_private *i915);
 int intel_gt_assign_ggtt(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index 34913912d8ae..e253750a51c5 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -388,8 +388,7 @@ void intel_gt_mcr_lock(struct intel_gt *gt, unsigned long *flags)
 		 * registers.  This wakeref will be released in the unlock
 		 * routine.
 		 *
-		 * This is expected to become a formally documented/numbered
-		 * workaround soon.
+		 * Wa_22018931422
 		 */
 		intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_GT);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index f5899d503e23..220ac4f92edf 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -28,19 +28,20 @@
 static void user_forcewake(struct intel_gt *gt, bool suspend)
 {
 	int count = atomic_read(&gt->user_wakeref);
+	intel_wakeref_t wakeref;
 
 	/* Inside suspend/resume so single threaded, no races to worry about. */
 	if (likely(!count))
 		return;
 
-	intel_gt_pm_get(gt);
+	wakeref = intel_gt_pm_get(gt);
 	if (suspend) {
 		GEM_BUG_ON(count > atomic_read(&gt->wakeref.count));
 		atomic_sub(count, &gt->wakeref.count);
 	} else {
 		atomic_add(count, &gt->wakeref.count);
 	}
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 }
 
 static void runtime_begin(struct intel_gt *gt)
@@ -138,7 +139,7 @@ void intel_gt_pm_init_early(struct intel_gt *gt)
 	 * runtime_pm is per-device rather than per-tile, so this is still the
 	 * correct structure.
 	 */
-	intel_wakeref_init(&gt->wakeref, gt->i915, &wf_ops);
+	intel_wakeref_init(&gt->wakeref, gt->i915, &wf_ops, "GT");
 	seqcount_mutex_init(&gt->stats.lock, &gt->wakeref.mutex);
 }
 
@@ -167,7 +168,7 @@ static void gt_sanitize(struct intel_gt *gt, bool force)
 	enum intel_engine_id id;
 	intel_wakeref_t wakeref;
 
-	GT_TRACE(gt, "force:%s", str_yes_no(force));
+	GT_TRACE(gt, "force:%s\n", str_yes_no(force));
 
 	/* Use a raw wakeref to avoid calling intel_display_power_get early */
 	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
@@ -236,6 +237,7 @@ int intel_gt_resume(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err;
 
 	err = intel_gt_has_unrecoverable_error(gt);
@@ -252,7 +254,7 @@ int intel_gt_resume(struct intel_gt *gt)
 	 */
 	gt_sanitize(gt, true);
 
-	intel_gt_pm_get(gt);
+	wakeref = intel_gt_pm_get(gt);
 
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	intel_rc6_sanitize(&gt->rc6);
@@ -295,7 +297,7 @@ int intel_gt_resume(struct intel_gt *gt)
 
 out_fw:
 	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 	intel_gt_bind_context_set_ready(gt);
 	return err;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index b1eeb5b33918..911fd0160221 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -16,19 +16,28 @@ static inline bool intel_gt_pm_is_awake(const struct intel_gt *gt)
 	return intel_wakeref_is_active(&gt->wakeref);
 }
 
-static inline void intel_gt_pm_get(struct intel_gt *gt)
+static inline void intel_gt_pm_get_untracked(struct intel_gt *gt)
 {
 	intel_wakeref_get(&gt->wakeref);
 }
 
+static inline intel_wakeref_t intel_gt_pm_get(struct intel_gt *gt)
+{
+	intel_gt_pm_get_untracked(gt);
+	return intel_wakeref_track(&gt->wakeref);
+}
+
 static inline void __intel_gt_pm_get(struct intel_gt *gt)
 {
 	__intel_wakeref_get(&gt->wakeref);
 }
 
-static inline bool intel_gt_pm_get_if_awake(struct intel_gt *gt)
+static inline intel_wakeref_t intel_gt_pm_get_if_awake(struct intel_gt *gt)
 {
-	return intel_wakeref_get_if_active(&gt->wakeref);
+	if (!intel_wakeref_get_if_active(&gt->wakeref))
+		return 0;
+
+	return intel_wakeref_track(&gt->wakeref);
 }
 
 static inline void intel_gt_pm_might_get(struct intel_gt *gt)
@@ -36,12 +45,18 @@ static inline void intel_gt_pm_might_get(struct intel_gt *gt)
 	intel_wakeref_might_get(&gt->wakeref);
 }
 
-static inline void intel_gt_pm_put(struct intel_gt *gt)
+static inline void intel_gt_pm_put_untracked(struct intel_gt *gt)
 {
 	intel_wakeref_put(&gt->wakeref);
 }
 
-static inline void intel_gt_pm_put_async(struct intel_gt *gt)
+static inline void intel_gt_pm_put(struct intel_gt *gt, intel_wakeref_t handle)
+{
+	intel_wakeref_untrack(&gt->wakeref, handle);
+	intel_gt_pm_put_untracked(gt);
+}
+
+static inline void intel_gt_pm_put_async_untracked(struct intel_gt *gt)
 {
 	intel_wakeref_put_async(&gt->wakeref);
 }
@@ -51,9 +66,14 @@ static inline void intel_gt_pm_might_put(struct intel_gt *gt)
 	intel_wakeref_might_put(&gt->wakeref);
 }
 
-#define with_intel_gt_pm(gt, tmp) \
-	for (tmp = 1, intel_gt_pm_get(gt); tmp; \
-	     intel_gt_pm_put(gt), tmp = 0)
+static inline void intel_gt_pm_put_async(struct intel_gt *gt, intel_wakeref_t handle)
+{
+	intel_wakeref_untrack(&gt->wakeref, handle);
+	intel_gt_pm_put_async_untracked(gt);
+}
+
+#define with_intel_gt_pm(gt, wf) \
+	for (wf = intel_gt_pm_get(gt); wf; intel_gt_pm_put(gt, wf), wf = 0)
 
 /**
  * with_intel_gt_pm_if_awake - if GT is PM awake, get a reference to prevent
@@ -64,7 +84,7 @@ static inline void intel_gt_pm_might_put(struct intel_gt *gt)
  * @wf: pointer to a temporary wakeref.
  */
 #define with_intel_gt_pm_if_awake(gt, wf) \
-	for (wf = intel_gt_pm_get_if_awake(gt); wf; intel_gt_pm_put_async(gt), wf = 0)
+	for (wf = intel_gt_pm_get_if_awake(gt); wf; intel_gt_pm_put_async(gt, wf), wf = 0)
 
 static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
index f900cc68d6d9..7114c116e928 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
@@ -27,7 +27,7 @@
 void intel_gt_pm_debugfs_forcewake_user_open(struct intel_gt *gt)
 {
 	atomic_inc(&gt->user_wakeref);
-	intel_gt_pm_get(gt);
+	intel_gt_pm_get_untracked(gt);
 	if (GRAPHICS_VER(gt->i915) >= 6)
 		intel_uncore_forcewake_user_get(gt->uncore);
 }
@@ -36,7 +36,7 @@ void intel_gt_pm_debugfs_forcewake_user_release(struct intel_gt *gt)
 {
 	if (GRAPHICS_VER(gt->i915) >= 6)
 		intel_uncore_forcewake_user_put(gt->uncore);
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put_untracked(gt);
 	atomic_dec(&gt->user_wakeref);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index eecd0a87a647..9de41703fae5 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -537,6 +537,9 @@
 #define XEHP_SQCM				MCR_REG(0x8724)
 #define   EN_32B_ACCESS				REG_BIT(30)
 
+#define MTL_GSCPSMI_BASEADDR_LSB		_MMIO(0x880c)
+#define MTL_GSCPSMI_BASEADDR_MSB		_MMIO(0x8810)
+
 #define HSW_IDICR				_MMIO(0x9008)
 #define   IDIHASHMSK(x)				(((x) & 0x3f) << 16)
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 4fbed27ef0ec..86f73fe558ca 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -63,6 +63,9 @@ struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz)
 	if (!IS_ERR(obj)) {
 		obj->base.resv = i915_vm_resv_get(vm);
 		obj->shares_resv_from = vm;
+
+		if (vm->fpriv)
+			i915_drm_client_add_object(vm->fpriv->client, obj);
 	}
 
 	return obj;
@@ -84,6 +87,9 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz)
 	if (!IS_ERR(obj)) {
 		obj->base.resv = i915_vm_resv_get(vm);
 		obj->shares_resv_from = vm;
+
+		if (vm->fpriv)
+			i915_drm_client_add_object(vm->fpriv->client, obj);
 	}
 
 	return obj;
@@ -95,6 +101,16 @@ int map_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
 	void *vaddr;
 
 	type = intel_gt_coherent_map_type(vm->gt, obj, true);
+	/*
+	 * FIXME: It is suspected that some Address Translation Service (ATS)
+	 * issue on IOMMU is causing CAT errors to occur on some MTL workloads.
+	 * Applying a write barrier to the ppgtt set entry functions appeared
+	 * to have no effect, so we must temporarily use I915_MAP_WC here on
+	 * MTL until a proper ATS solution is found.
+	 */
+	if (IS_METEORLAKE(vm->i915))
+		type = I915_MAP_WC;
+
 	vaddr = i915_gem_object_pin_map_unlocked(obj, type);
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
@@ -109,6 +125,16 @@ int map_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object
 	void *vaddr;
 
 	type = intel_gt_coherent_map_type(vm->gt, obj, true);
+	/*
+	 * FIXME: It is suspected that some Address Translation Service (ATS)
+	 * issue on IOMMU is causing CAT errors to occur on some MTL workloads.
+	 * Applying a write barrier to the ppgtt set entry functions appeared
+	 * to have no effect, so we must temporarily use I915_MAP_WC here on
+	 * MTL until a proper ATS solution is found.
+	 */
+	if (IS_METEORLAKE(vm->i915))
+		type = I915_MAP_WC;
+
 	vaddr = i915_gem_object_pin_map(obj, type);
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index b471edac2699..6b85222ee3ea 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -249,8 +249,13 @@ struct i915_address_space {
 	struct work_struct release_work;
 
 	struct drm_mm mm;
+	struct {
+		struct drm_i915_gem_object *obj;
+		struct i915_vma *vma;
+	} rsvd;
 	struct intel_gt *gt;
 	struct drm_i915_private *i915;
+	struct drm_i915_file_private *fpriv;
 	struct device *dma;
 	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
 	u64 reserved;		/* size addr space reserved */
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index eaf66d903166..7c367ba8d9dc 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -829,6 +829,18 @@ lrc_ring_indirect_offset_default(const struct intel_engine_cs *engine)
 }
 
 static void
+lrc_setup_bb_per_ctx(u32 *regs,
+		     const struct intel_engine_cs *engine,
+		     u32 ctx_bb_ggtt_addr)
+{
+	GEM_BUG_ON(lrc_ring_wa_bb_per_ctx(engine) == -1);
+	regs[lrc_ring_wa_bb_per_ctx(engine) + 1] =
+		ctx_bb_ggtt_addr |
+		PER_CTX_BB_FORCE |
+		PER_CTX_BB_VALID;
+}
+
+static void
 lrc_setup_indirect_ctx(u32 *regs,
 		       const struct intel_engine_cs *engine,
 		       u32 ctx_bb_ggtt_addr,
@@ -1020,7 +1032,13 @@ static u32 context_wa_bb_offset(const struct intel_context *ce)
 	return PAGE_SIZE * ce->wa_bb_page;
 }
 
-static u32 *context_indirect_bb(const struct intel_context *ce)
+/*
+ * per_ctx below determines which WABB section is used.
+ * When true, the function returns the location of the
+ * PER_CTX_BB.  When false, the function returns the
+ * location of the INDIRECT_CTX.
+ */
+static u32 *context_wabb(const struct intel_context *ce, bool per_ctx)
 {
 	void *ptr;
 
@@ -1029,6 +1047,7 @@ static u32 *context_indirect_bb(const struct intel_context *ce)
 	ptr = ce->lrc_reg_state;
 	ptr -= LRC_STATE_OFFSET; /* back to start of context image */
 	ptr += context_wa_bb_offset(ce);
+	ptr += per_ctx ? PAGE_SIZE : 0;
 
 	return ptr;
 }
@@ -1105,7 +1124,8 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine)
 
 	if (GRAPHICS_VER(engine->i915) >= 12) {
 		ce->wa_bb_page = context_size / PAGE_SIZE;
-		context_size += PAGE_SIZE;
+		/* INDIRECT_CTX and PER_CTX_BB need separate pages. */
+		context_size += PAGE_SIZE * 2;
 	}
 
 	if (intel_context_is_parent(ce) && intel_engine_uses_guc(engine)) {
@@ -1407,12 +1427,85 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs)
 	return gen12_emit_aux_table_inv(ce->engine, cs);
 }
 
+static u32 *xehp_emit_fastcolor_blt_wabb(const struct intel_context *ce, u32 *cs)
+{
+	struct intel_gt *gt = ce->engine->gt;
+	int mocs = gt->mocs.uc_index << 1;
+
+	/**
+	 * Wa_16018031267 / Wa_16018063123 requires that SW forces the
+	 * main copy engine arbitration into round robin mode.  We
+	 * additionally need to submit the following WABB blt command
+	 * to produce 4 subblits with each subblit generating 0 byte
+	 * write requests as WABB:
+	 *
+	 * XY_FASTCOLOR_BLT
+	 *  BG0    -> 5100000E
+	 *  BG1    -> 0000003F (Dest pitch)
+	 *  BG2    -> 00000000 (X1, Y1) = (0, 0)
+	 *  BG3    -> 00040001 (X2, Y2) = (1, 4)
+	 *  BG4    -> scratch
+	 *  BG5    -> scratch
+	 *  BG6-12 -> 00000000
+	 *  BG13   -> 20004004 (Surf. Width= 2,Surf. Height = 5 )
+	 *  BG14   -> 00000010 (Qpitch = 4)
+	 *  BG15   -> 00000000
+	 */
+	*cs++ = XY_FAST_COLOR_BLT_CMD | (16 - 2);
+	*cs++ = FIELD_PREP(XY_FAST_COLOR_BLT_MOCS_MASK, mocs) | 0x3f;
+	*cs++ = 0;
+	*cs++ = 4 << 16 | 1;
+	*cs++ = lower_32_bits(i915_vma_offset(ce->vm->rsvd.vma));
+	*cs++ = upper_32_bits(i915_vma_offset(ce->vm->rsvd.vma));
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0x20004004;
+	*cs++ = 0x10;
+	*cs++ = 0;
+
+	return cs;
+}
+
+static u32 *
+xehp_emit_per_ctx_bb(const struct intel_context *ce, u32 *cs)
+{
+	/* Wa_16018031267, Wa_16018063123 */
+	if (NEEDS_FASTCOLOR_BLT_WABB(ce->engine))
+		cs = xehp_emit_fastcolor_blt_wabb(ce, cs);
+
+	return cs;
+}
+
+static void
+setup_per_ctx_bb(const struct intel_context *ce,
+		 const struct intel_engine_cs *engine,
+		 u32 *(*emit)(const struct intel_context *, u32 *))
+{
+	/* Place PER_CTX_BB on next page after INDIRECT_CTX */
+	u32 * const start = context_wabb(ce, true);
+	u32 *cs;
+
+	cs = emit(ce, start);
+
+	/* PER_CTX_BB must manually terminate */
+	*cs++ = MI_BATCH_BUFFER_END;
+
+	GEM_BUG_ON(cs - start > I915_GTT_PAGE_SIZE / sizeof(*cs));
+	lrc_setup_bb_per_ctx(ce->lrc_reg_state, engine,
+			     lrc_indirect_bb(ce) + PAGE_SIZE);
+}
+
 static void
 setup_indirect_ctx_bb(const struct intel_context *ce,
 		      const struct intel_engine_cs *engine,
 		      u32 *(*emit)(const struct intel_context *, u32 *))
 {
-	u32 * const start = context_indirect_bb(ce);
+	u32 * const start = context_wabb(ce, false);
 	u32 *cs;
 
 	cs = emit(ce, start);
@@ -1511,6 +1604,7 @@ u32 lrc_update_regs(const struct intel_context *ce,
 		/* Mutually exclusive wrt to global indirect bb */
 		GEM_BUG_ON(engine->wa_ctx.indirect_ctx.size);
 		setup_indirect_ctx_bb(ce, engine, fn);
+		setup_per_ctx_bb(ce, engine, xehp_emit_per_ctx_bb);
 	}
 
 	return lrc_descriptor(ce) | CTX_DESC_FORCE_RESTORE;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index d5ed904f355d..6801f8b95c53 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1293,7 +1293,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg)
 	if (msg)
 		drm_notice(&engine->i915->drm,
 			   "Resetting %s for %s\n", engine->name, msg);
-	atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
+	i915_increase_reset_engine_count(&engine->i915->gpu_error, engine);
 
 	ret = intel_gt_reset_engine(engine);
 	if (ret) {
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index f602895f6d0d..6a3246240e81 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -849,13 +849,12 @@ void intel_sseu_print_topology(struct drm_i915_private *i915,
 			       const struct sseu_dev_info *sseu,
 			       struct drm_printer *p)
 {
-	if (sseu->max_slices == 0) {
+	if (sseu->max_slices == 0)
 		drm_printf(p, "Unavailable\n");
-	} else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+	else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
 		sseu_print_xehp_topology(sseu, p);
-	} else {
+	else
 		sseu_print_hsw_topology(sseu, p);
-	}
 }
 
 void intel_sseu_print_ss_info(const char *type,
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 192ac0e59afa..4cbf9e512645 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1663,8 +1663,22 @@ xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 }
 
 static void
+wa_16021867713(struct intel_gt *gt, struct i915_wa_list *wal)
+{
+	struct intel_engine_cs *engine;
+	int id;
+
+	for_each_engine(engine, gt, id)
+		if (engine->class == VIDEO_DECODE_CLASS)
+			wa_write_or(wal, VDBOX_CGCTL3F1C(engine->mmio_base),
+				    MFXPIPE_CLKGATE_DIS);
+}
+
+static void
 xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 {
+	wa_16021867713(gt, wal);
+
 	/*
 	 * Wa_14018778641
 	 * Wa_18018781329
@@ -1674,6 +1688,9 @@ 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_22016670082 */
+	wa_write_or(wal, GEN12_SQCNT1, GEN12_STRICT_RAR_ENABLE);
+
 	debug_dump_steering(gt);
 }
 
@@ -2340,14 +2357,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			   0, true);
 	}
 
-	if (IS_DG2_G11(i915) || IS_DG2_G10(i915)) {
-		/* Wa_22014600077:dg2 */
-		wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0,
-			   _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH),
-			   0 /* Wa_14012342262 write-only reg, so skip verification */,
-			   true);
-	}
-
 	if (IS_DG2(i915) || IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) ||
 	    IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
 		/*
@@ -2782,6 +2791,11 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			 RING_SEMA_WAIT_POLL(engine->mmio_base),
 			 1);
 	}
+	/* Wa_16018031267, Wa_16018063123 */
+	if (NEEDS_FASTCOLOR_BLT_WABB(engine))
+		wa_masked_field_set(wal, ECOSKPD(engine->mmio_base),
+				    XEHP_BLITTER_SCHEDULING_MODE_MASK,
+				    XEHP_BLITTER_ROUND_ROBIN_MODE);
 }
 
 static void
@@ -2915,6 +2929,9 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
 		 * Wa_22015475538:dg2
 		 */
 		wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8);
+
+		/* Wa_18028616096 */
+		wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, UGM_FRAGMENT_THRESHOLD_TO_3);
 	}
 
 	if (IS_DG2_G11(i915)) {
@@ -2943,11 +2960,6 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
 			   true);
 	}
 
-	if (IS_DG2_G10(i915) || IS_DG2_G12(i915)) {
-		/* Wa_18028616096 */
-		wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, UGM_FRAGMENT_THRESHOLD_TO_3);
-	}
-
 	if (IS_XEHPSDV(i915)) {
 		/* Wa_1409954639 */
 		wa_mcr_masked_en(wal,
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
index 86cecf7a1105..5ffa5e30f419 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
@@ -21,20 +21,22 @@ static int cmp_u32(const void *A, const void *B)
 	return *a - *b;
 }
 
-static void perf_begin(struct intel_gt *gt)
+static intel_wakeref_t perf_begin(struct intel_gt *gt)
 {
-	intel_gt_pm_get(gt);
+	intel_wakeref_t wakeref = intel_gt_pm_get(gt);
 
 	/* Boost gpufreq to max [waitboost] and keep it fixed */
 	atomic_inc(&gt->rps.num_waiters);
 	queue_work(gt->i915->unordered_wq, &gt->rps.work);
 	flush_work(&gt->rps.work);
+
+	return wakeref;
 }
 
-static int perf_end(struct intel_gt *gt)
+static int perf_end(struct intel_gt *gt, intel_wakeref_t wakeref)
 {
 	atomic_dec(&gt->rps.num_waiters);
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 
 	return igt_flush_test(gt->i915);
 }
@@ -133,12 +135,13 @@ static int perf_mi_bb_start(void *arg)
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	if (GRAPHICS_VER(gt->i915) < 4) /* Any CS_TIMESTAMP? */
 		return 0;
 
-	perf_begin(gt);
+	wakeref = perf_begin(gt);
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce = engine->kernel_context;
 		struct i915_vma *batch;
@@ -207,7 +210,7 @@ out:
 		pr_info("%s: MI_BB_START cycles: %u\n",
 			engine->name, trifilter(cycles));
 	}
-	if (perf_end(gt))
+	if (perf_end(gt, wakeref))
 		err = -EIO;
 
 	return err;
@@ -260,12 +263,13 @@ static int perf_mi_noop(void *arg)
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	if (GRAPHICS_VER(gt->i915) < 4) /* Any CS_TIMESTAMP? */
 		return 0;
 
-	perf_begin(gt);
+	wakeref = perf_begin(gt);
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce = engine->kernel_context;
 		struct i915_vma *base, *nop;
@@ -364,7 +368,7 @@ out:
 		pr_info("%s: 16K MI_NOOP cycles: %u\n",
 			engine->name, trifilter(cycles));
 	}
-	if (perf_end(gt))
+	if (perf_end(gt, wakeref))
 		err = -EIO;
 
 	return err;
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
index 273d440a53e3..bc441ce7b380 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -84,7 +84,7 @@ static struct pulse *pulse_create(void)
 
 static void pulse_unlock_wait(struct pulse *p)
 {
-	i915_active_unlock_wait(&p->active);
+	wait_var_event_timeout(&p->active, i915_active_is_idle(&p->active), HZ);
 }
 
 static int __live_idle_pulse(struct intel_engine_cs *engine,
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
index 0971241707ce..33351deeea4f 100644
--- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -81,6 +81,7 @@ static int live_gt_clocks(void *arg)
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	if (!gt->clock_frequency) { /* unknown */
@@ -91,7 +92,7 @@ static int live_gt_clocks(void *arg)
 	if (GRAPHICS_VER(gt->i915) < 4) /* Any CS_TIMESTAMP? */
 		return 0;
 
-	intel_gt_pm_get(gt);
+	wakeref = intel_gt_pm_get(gt);
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 
 	for_each_engine(engine, gt, id) {
@@ -128,7 +129,7 @@ static int live_gt_clocks(void *arg)
 	}
 
 	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 5f826b6dcf5d..e17b8777d21d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1555,7 +1555,7 @@ static int live_lrc_isolation(void *arg)
 	return err;
 }
 
-static int indirect_ctx_submit_req(struct intel_context *ce)
+static int wabb_ctx_submit_req(struct intel_context *ce)
 {
 	struct i915_request *rq;
 	int err = 0;
@@ -1579,7 +1579,8 @@ static int indirect_ctx_submit_req(struct intel_context *ce)
 #define CTX_BB_CANARY_INDEX  (CTX_BB_CANARY_OFFSET / sizeof(u32))
 
 static u32 *
-emit_indirect_ctx_bb_canary(const struct intel_context *ce, u32 *cs)
+emit_wabb_ctx_canary(const struct intel_context *ce,
+		     u32 *cs, bool per_ctx)
 {
 	*cs++ = MI_STORE_REGISTER_MEM_GEN8 |
 		MI_SRM_LRM_GLOBAL_GTT |
@@ -1587,26 +1588,43 @@ emit_indirect_ctx_bb_canary(const struct intel_context *ce, u32 *cs)
 	*cs++ = i915_mmio_reg_offset(RING_START(0));
 	*cs++ = i915_ggtt_offset(ce->state) +
 		context_wa_bb_offset(ce) +
-		CTX_BB_CANARY_OFFSET;
+		CTX_BB_CANARY_OFFSET +
+		(per_ctx ? PAGE_SIZE : 0);
 	*cs++ = 0;
 
 	return cs;
 }
 
+static u32 *
+emit_indirect_ctx_bb_canary(const struct intel_context *ce, u32 *cs)
+{
+	return emit_wabb_ctx_canary(ce, cs, false);
+}
+
+static u32 *
+emit_per_ctx_bb_canary(const struct intel_context *ce, u32 *cs)
+{
+	return emit_wabb_ctx_canary(ce, cs, true);
+}
+
 static void
-indirect_ctx_bb_setup(struct intel_context *ce)
+wabb_ctx_setup(struct intel_context *ce, bool per_ctx)
 {
-	u32 *cs = context_indirect_bb(ce);
+	u32 *cs = context_wabb(ce, per_ctx);
 
 	cs[CTX_BB_CANARY_INDEX] = 0xdeadf00d;
 
-	setup_indirect_ctx_bb(ce, ce->engine, emit_indirect_ctx_bb_canary);
+	if (per_ctx)
+		setup_per_ctx_bb(ce, ce->engine, emit_per_ctx_bb_canary);
+	else
+		setup_indirect_ctx_bb(ce, ce->engine, emit_indirect_ctx_bb_canary);
 }
 
-static bool check_ring_start(struct intel_context *ce)
+static bool check_ring_start(struct intel_context *ce, bool per_ctx)
 {
 	const u32 * const ctx_bb = (void *)(ce->lrc_reg_state) -
-		LRC_STATE_OFFSET + context_wa_bb_offset(ce);
+		LRC_STATE_OFFSET + context_wa_bb_offset(ce) +
+		(per_ctx ? PAGE_SIZE : 0);
 
 	if (ctx_bb[CTX_BB_CANARY_INDEX] == ce->lrc_reg_state[CTX_RING_START])
 		return true;
@@ -1618,21 +1636,21 @@ static bool check_ring_start(struct intel_context *ce)
 	return false;
 }
 
-static int indirect_ctx_bb_check(struct intel_context *ce)
+static int wabb_ctx_check(struct intel_context *ce, bool per_ctx)
 {
 	int err;
 
-	err = indirect_ctx_submit_req(ce);
+	err = wabb_ctx_submit_req(ce);
 	if (err)
 		return err;
 
-	if (!check_ring_start(ce))
+	if (!check_ring_start(ce, per_ctx))
 		return -EINVAL;
 
 	return 0;
 }
 
-static int __live_lrc_indirect_ctx_bb(struct intel_engine_cs *engine)
+static int __lrc_wabb_ctx(struct intel_engine_cs *engine, bool per_ctx)
 {
 	struct intel_context *a, *b;
 	int err;
@@ -1667,14 +1685,14 @@ static int __live_lrc_indirect_ctx_bb(struct intel_engine_cs *engine)
 	 * As ring start is restored apriori of starting the indirect ctx bb and
 	 * as it will be different for each context, it fits to this purpose.
 	 */
-	indirect_ctx_bb_setup(a);
-	indirect_ctx_bb_setup(b);
+	wabb_ctx_setup(a, per_ctx);
+	wabb_ctx_setup(b, per_ctx);
 
-	err = indirect_ctx_bb_check(a);
+	err = wabb_ctx_check(a, per_ctx);
 	if (err)
 		goto unpin_b;
 
-	err = indirect_ctx_bb_check(b);
+	err = wabb_ctx_check(b, per_ctx);
 
 unpin_b:
 	intel_context_unpin(b);
@@ -1688,7 +1706,7 @@ put_a:
 	return err;
 }
 
-static int live_lrc_indirect_ctx_bb(void *arg)
+static int lrc_wabb_ctx(void *arg, bool per_ctx)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
@@ -1697,7 +1715,7 @@ static int live_lrc_indirect_ctx_bb(void *arg)
 
 	for_each_engine(engine, gt, id) {
 		intel_engine_pm_get(engine);
-		err = __live_lrc_indirect_ctx_bb(engine);
+		err = __lrc_wabb_ctx(engine, per_ctx);
 		intel_engine_pm_put(engine);
 
 		if (igt_flush_test(gt->i915))
@@ -1710,6 +1728,16 @@ static int live_lrc_indirect_ctx_bb(void *arg)
 	return err;
 }
 
+static int live_lrc_indirect_ctx_bb(void *arg)
+{
+	return lrc_wabb_ctx(arg, false);
+}
+
+static int live_lrc_per_ctx_bb(void *arg)
+{
+	return lrc_wabb_ctx(arg, true);
+}
+
 static void garbage_reset(struct intel_engine_cs *engine,
 			  struct i915_request *rq)
 {
@@ -1947,6 +1975,7 @@ int intel_lrc_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_lrc_garbage),
 		SUBTEST(live_pphwsp_runtime),
 		SUBTEST(live_lrc_indirect_ctx_bb),
+		SUBTEST(live_lrc_per_ctx_bb),
 	};
 
 	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index 79aa6ac66ad2..f40de408cd3a 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -261,11 +261,12 @@ static int igt_atomic_reset(void *arg)
 {
 	struct intel_gt *gt = arg;
 	const typeof(*igt_atomic_phases) *p;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	/* Check that the resets are usable from atomic context */
 
-	intel_gt_pm_get(gt);
+	wakeref = intel_gt_pm_get(gt);
 	igt_global_reset_lock(gt);
 
 	/* Flush any requests before we get started and check basics */
@@ -296,7 +297,7 @@ static int igt_atomic_reset(void *arg)
 
 unlock:
 	igt_global_reset_unlock(gt);
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 
 	return err;
 }
@@ -307,6 +308,7 @@ static int igt_atomic_engine_reset(void *arg)
 	const typeof(*igt_atomic_phases) *p;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	/* Check that the resets are usable from atomic context */
@@ -317,7 +319,7 @@ static int igt_atomic_engine_reset(void *arg)
 	if (intel_uc_uses_guc_submission(&gt->uc))
 		return 0;
 
-	intel_gt_pm_get(gt);
+	wakeref = intel_gt_pm_get(gt);
 	igt_global_reset_lock(gt);
 
 	/* Flush any requests before we get started and check basics */
@@ -365,7 +367,7 @@ static int igt_atomic_engine_reset(void *arg)
 
 out_unlock:
 	igt_global_reset_unlock(gt);
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index fb30f733b036..dcef8d498919 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -224,6 +224,7 @@ int live_rps_clock_interval(void *arg)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	struct igt_spinner spin;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	if (!intel_rps_is_enabled(rps) || GRAPHICS_VER(gt->i915) < 6)
@@ -236,7 +237,7 @@ int live_rps_clock_interval(void *arg)
 	saved_work = rps->work.func;
 	rps->work.func = dummy_rps_work;
 
-	intel_gt_pm_get(gt);
+	wakeref = intel_gt_pm_get(gt);
 	intel_rps_disable(&gt->rps);
 
 	intel_gt_check_clock_frequency(gt);
@@ -355,7 +356,7 @@ int live_rps_clock_interval(void *arg)
 	}
 
 	intel_rps_enable(&gt->rps);
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 
 	igt_spinner_fini(&spin);
 
@@ -376,6 +377,7 @@ int live_rps_control(void *arg)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	struct igt_spinner spin;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	/*
@@ -398,7 +400,7 @@ int live_rps_control(void *arg)
 	saved_work = rps->work.func;
 	rps->work.func = dummy_rps_work;
 
-	intel_gt_pm_get(gt);
+	wakeref = intel_gt_pm_get(gt);
 	for_each_engine(engine, gt, id) {
 		struct i915_request *rq;
 		ktime_t min_dt, max_dt;
@@ -488,7 +490,7 @@ int live_rps_control(void *arg)
 			break;
 		}
 	}
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 
 	igt_spinner_fini(&spin);
 
@@ -1023,6 +1025,7 @@ int live_rps_interrupt(void *arg)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	struct igt_spinner spin;
+	intel_wakeref_t wakeref;
 	u32 pm_events;
 	int err = 0;
 
@@ -1033,9 +1036,9 @@ int live_rps_interrupt(void *arg)
 	if (!intel_rps_has_interrupts(rps) || GRAPHICS_VER(gt->i915) < 6)
 		return 0;
 
-	intel_gt_pm_get(gt);
-	pm_events = rps->pm_events;
-	intel_gt_pm_put(gt);
+	pm_events = 0;
+	with_intel_gt_pm(gt, wakeref)
+		pm_events = rps->pm_events;
 	if (!pm_events) {
 		pr_err("No RPS PM events registered, but RPS is enabled?\n");
 		return -ENODEV;
diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c
index 952c8d52d68a..302d0540295d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_slpc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c
@@ -266,6 +266,7 @@ static int run_test(struct intel_gt *gt, int test_type)
 	struct intel_rps *rps = &gt->rps;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	struct igt_spinner spin;
 	u32 slpc_min_freq, slpc_max_freq;
 	int err = 0;
@@ -311,7 +312,7 @@ static int run_test(struct intel_gt *gt, int test_type)
 	}
 
 	intel_gt_pm_wait_for_idle(gt);
-	intel_gt_pm_get(gt);
+	wakeref = intel_gt_pm_get(gt);
 	for_each_engine(engine, gt, id) {
 		struct i915_request *rq;
 		u32 max_act_freq;
@@ -397,7 +398,7 @@ static int run_test(struct intel_gt *gt, int test_type)
 	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(gt, wakeref);
 	igt_spinner_fini(&spin);
 	intel_gt_pm_wait_for_idle(gt);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_proxy.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_proxy.c
index 5f138de3c14f..40817ebcca71 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_proxy.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_proxy.c
@@ -322,6 +322,7 @@ static int i915_gsc_proxy_component_bind(struct device *i915_kdev,
 	gsc->proxy.component = data;
 	gsc->proxy.component->mei_dev = mei_kdev;
 	mutex_unlock(&gsc->proxy.mutex);
+	gt_dbg(gt, "GSC proxy mei component bound\n");
 
 	return 0;
 }
@@ -342,6 +343,7 @@ static void i915_gsc_proxy_component_unbind(struct device *i915_kdev,
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
 		intel_uncore_rmw(gt->uncore, HECI_H_CSR(MTL_GSC_HECI2_BASE),
 				 HECI_H_CSR_IE | HECI_H_CSR_RST, 0);
+	gt_dbg(gt, "GSC proxy mei component unbound\n");
 }
 
 static const struct component_ops i915_gsc_proxy_component_ops = {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 3f3df1166b86..2b450c43bbd7 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -330,7 +330,7 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc)
 
 static u32 guc_ctl_devid(struct intel_guc *guc)
 {
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 
 	return (INTEL_DEVID(i915) << 16) | INTEL_REVID(i915);
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 2b6dfe62c8f2..e22c12ce245a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -297,6 +297,10 @@ struct intel_guc {
 	 * @number_guc_id_stolen: The number of guc_ids that have been stolen
 	 */
 	int number_guc_id_stolen;
+	/**
+	 * @fast_response_selftest: Backdoor to CT handler for fast response selftest
+	 */
+	u32 fast_response_selftest;
 #endif
 };
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
index a4da0208c883..a1cd40d80517 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
@@ -355,7 +355,7 @@ guc_capture_alloc_steered_lists(struct intel_guc *guc,
 static const struct __guc_mmio_reg_descr_group *
 guc_capture_get_device_reglist(struct intel_guc *guc)
 {
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 	const struct __guc_mmio_reg_descr_group *lists;
 
 	if (GRAPHICS_VER(i915) >= 12)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index 89e314b3756b..0d5197c0824a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -265,7 +265,7 @@ int intel_guc_ct_init(struct intel_guc_ct *ct)
 	u32 *cmds;
 	int err;
 
-	err = i915_inject_probe_error(guc_to_gt(guc)->i915, -ENXIO);
+	err = i915_inject_probe_error(guc_to_i915(guc), -ENXIO);
 	if (err)
 		return err;
 
@@ -1076,6 +1076,15 @@ static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 		found = true;
 		break;
 	}
+
+#ifdef CONFIG_DRM_I915_SELFTEST
+	if (!found && ct_to_guc(ct)->fast_response_selftest) {
+		CT_DEBUG(ct, "Assuming unsolicited response due to FAST_REQUEST selftest\n");
+		ct_to_guc(ct)->fast_response_selftest++;
+		found = true;
+	}
+#endif
+
 	if (!found) {
 		CT_ERROR(ct, "Unsolicited response message: len %u, data %#x (fence %u, last %u)\n",
 			 len, hxg[0], fence, ct->requests.last_fence);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
index 55bc8b55fbc0..bf16351c9349 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
@@ -520,7 +520,7 @@ void intel_guc_log_init_early(struct intel_guc_log *log)
 static int guc_log_relay_create(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 	struct rchan *guc_log_relay_chan;
 	size_t n_subbufs, subbuf_size;
 	int ret;
@@ -573,7 +573,7 @@ static void guc_log_relay_destroy(struct intel_guc_log *log)
 static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 	intel_wakeref_t wakeref;
 
 	_guc_log_copy_debuglogs_for_relay(log);
@@ -589,7 +589,7 @@ static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log)
 static u32 __get_default_log_level(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 
 	/* A negative value means "use platform/config default" */
 	if (i915->params.guc_log_level < 0) {
@@ -664,7 +664,7 @@ void intel_guc_log_destroy(struct intel_guc_log *log)
 int intel_guc_log_set_level(struct intel_guc_log *log, u32 level)
 {
 	struct intel_guc *guc = log_to_guc(log);
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 	intel_wakeref_t wakeref;
 	int ret = 0;
 
@@ -796,7 +796,7 @@ void intel_guc_log_relay_flush(struct intel_guc_log *log)
 static void guc_log_relay_stop(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 
 	if (!log->relay.started)
 		return;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c
index 1adec6de223c..9df7927304ae 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c
@@ -14,7 +14,7 @@ static bool __guc_rc_supported(struct intel_guc *guc)
 {
 	/* GuC RC is unavailable for pre-Gen12 */
 	return guc->submission_supported &&
-		GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12;
+		GRAPHICS_VER(guc_to_i915(guc)) >= 12;
 }
 
 static bool __guc_rc_selected(struct intel_guc *guc)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
index 2dfb07cc4b33..3e681ab6fbf9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
@@ -34,7 +34,7 @@ static bool __detect_slpc_supported(struct intel_guc *guc)
 {
 	/* GuC SLPC is unavailable for pre-Gen12 */
 	return guc->submission_supported &&
-		GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12;
+		GRAPHICS_VER(guc_to_i915(guc)) >= 12;
 }
 
 static bool __guc_slpc_selected(struct intel_guc *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 d37698bd6b91..a259f1118c5a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1107,7 +1107,7 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
 			if (deregister)
 				guc_signal_context_fence(ce);
 			if (destroyed) {
-				intel_gt_pm_put_async(guc_to_gt(guc));
+				intel_gt_pm_put_async_untracked(guc_to_gt(guc));
 				release_guc_id(guc, ce);
 				__guc_context_destroy(ce);
 			}
@@ -1303,6 +1303,7 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now)
 	unsigned long flags;
 	u32 reset_count;
 	bool in_reset;
+	intel_wakeref_t wakeref;
 
 	spin_lock_irqsave(&guc->timestamp.lock, flags);
 
@@ -1325,7 +1326,8 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now)
 	 * start_gt_clk is derived from GuC state. To get a consistent
 	 * view of activity, we query the GuC state only if gt is awake.
 	 */
-	if (!in_reset && intel_gt_pm_get_if_awake(gt)) {
+	wakeref = in_reset ? 0 : intel_gt_pm_get_if_awake(gt);
+	if (wakeref) {
 		stats_saved = *stats;
 		gt_stamp_saved = guc->timestamp.gt_stamp;
 		/*
@@ -1334,7 +1336,7 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now)
 		 */
 		guc_update_engine_gt_clks(engine);
 		guc_update_pm_timestamp(guc, now);
-		intel_gt_pm_put_async(gt);
+		intel_gt_pm_put_async(gt, wakeref);
 		if (i915_reset_count(gpu_error) != reset_count) {
 			*stats = stats_saved;
 			guc->timestamp.gt_stamp = gt_stamp_saved;
@@ -3385,9 +3387,9 @@ static void destroyed_worker_func(struct work_struct *w)
 	struct intel_guc *guc = container_of(w, struct intel_guc,
 					     submission_state.destroyed_worker);
 	struct intel_gt *gt = guc_to_gt(guc);
-	int tmp;
+	intel_wakeref_t wakeref;
 
-	with_intel_gt_pm(gt, tmp)
+	with_intel_gt_pm(gt, wakeref)
 		deregister_destroyed_contexts(guc);
 }
 
@@ -4624,12 +4626,12 @@ static bool __guc_submission_supported(struct intel_guc *guc)
 {
 	/* GuC submission is unavailable for pre-Gen11 */
 	return intel_guc_is_supported(guc) &&
-	       GRAPHICS_VER(guc_to_gt(guc)->i915) >= 11;
+	       GRAPHICS_VER(guc_to_i915(guc)) >= 11;
 }
 
 static bool __guc_submission_selected(struct intel_guc *guc)
 {
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 
 	if (!intel_guc_submission_is_supported(guc))
 		return false;
@@ -4894,7 +4896,7 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc,
 		intel_context_put(ce);
 	} else if (context_destroyed(ce)) {
 		/* Context has been destroyed */
-		intel_gt_pm_put_async(guc_to_gt(guc));
+		intel_gt_pm_put_async_untracked(guc_to_gt(guc));
 		release_guc_id(guc, ce);
 		__guc_context_destroy(ce);
 	}
@@ -5001,7 +5003,8 @@ static void capture_error_state(struct intel_guc *guc,
 			if (match) {
 				intel_engine_set_hung_context(e, ce);
 				engine_mask |= e->mask;
-				atomic_inc(&i915->gpu_error.reset_engine_count[e->uabi_class]);
+				i915_increase_reset_engine_count(&i915->gpu_error,
+								 e);
 			}
 		}
 
@@ -5013,7 +5016,7 @@ static void capture_error_state(struct intel_guc *guc,
 	} else {
 		intel_engine_set_hung_context(ce->engine, ce);
 		engine_mask = ce->engine->mask;
-		atomic_inc(&i915->gpu_error.reset_engine_count[ce->engine->uabi_class]);
+		i915_increase_reset_engine_count(&i915->gpu_error, ce->engine);
 	}
 
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 27f6561dd731..3872d309ed31 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -106,11 +106,6 @@ static void __confirm_options(struct intel_uc *uc)
 		gt_info(gt,  "Incompatible option enable_guc=%d - %s\n",
 			i915->params.enable_guc, "GuC is not supported!");
 
-	if (i915->params.enable_guc & ENABLE_GUC_LOAD_HUC &&
-	    !intel_uc_supports_huc(uc))
-		gt_info(gt, "Incompatible option enable_guc=%d - %s\n",
-			i915->params.enable_guc, "HuC is not supported!");
-
 	if (i915->params.enable_guc & ENABLE_GUC_SUBMISSION &&
 	    !intel_uc_supports_guc_submission(uc))
 		gt_info(gt, "Incompatible option enable_guc=%d - %s\n",
diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
index bfb72143566f..c900aac85adb 100644
--- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
@@ -286,11 +286,126 @@ err_wakeref:
 	return ret;
 }
 
+/*
+ * Send a context schedule H2G message with an invalid context id.
+ * This should generate a GUC_RESULT_INVALID_CONTEXT response.
+ */
+static int bad_h2g(struct intel_guc *guc)
+{
+	u32 action[] = {
+	   INTEL_GUC_ACTION_SCHED_CONTEXT,
+	   0x12345678,
+	};
+
+	return intel_guc_send_nb(guc, action, ARRAY_SIZE(action), 0);
+}
+
+/*
+ * Set a spinner running to make sure the system is alive and active,
+ * then send a bad but asynchronous H2G command and wait to see if an
+ * error response is returned. If no response is received or if the
+ * spinner dies then the test will fail.
+ */
+#define FAST_RESPONSE_TIMEOUT_MS	1000
+static int intel_guc_fast_request(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_context *ce;
+	struct igt_spinner spin;
+	struct i915_request *rq;
+	intel_wakeref_t wakeref;
+	struct intel_engine_cs *engine = intel_selftest_find_any_engine(gt);
+	bool spinning = false;
+	int ret = 0;
+
+	if (!engine)
+		return 0;
+
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce)) {
+		ret = PTR_ERR(ce);
+		gt_err(gt, "Failed to create spinner request: %pe\n", ce);
+		goto err_pm;
+	}
+
+	ret = igt_spinner_init(&spin, engine->gt);
+	if (ret) {
+		gt_err(gt, "Failed to create spinner: %pe\n", ERR_PTR(ret));
+		goto err_pm;
+	}
+	spinning = true;
+
+	rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK);
+	intel_context_put(ce);
+	if (IS_ERR(rq)) {
+		ret = PTR_ERR(rq);
+		gt_err(gt, "Failed to create spinner request: %pe\n", rq);
+		goto err_spin;
+	}
+
+	ret = request_add_spin(rq, &spin);
+	if (ret) {
+		gt_err(gt, "Failed to add Spinner request: %pe\n", ERR_PTR(ret));
+		goto err_rq;
+	}
+
+	gt->uc.guc.fast_response_selftest = 1;
+
+	ret = bad_h2g(&gt->uc.guc);
+	if (ret) {
+		gt_err(gt, "Failed to send H2G: %pe\n", ERR_PTR(ret));
+		goto err_rq;
+	}
+
+	ret = wait_for(gt->uc.guc.fast_response_selftest != 1 || i915_request_completed(rq),
+		       FAST_RESPONSE_TIMEOUT_MS);
+	if (ret) {
+		gt_err(gt, "Request wait failed: %pe\n", ERR_PTR(ret));
+		goto err_rq;
+	}
+
+	if (i915_request_completed(rq)) {
+		gt_err(gt, "Spinner died waiting for fast request error!\n");
+		ret = -EIO;
+		goto err_rq;
+	}
+
+	if (gt->uc.guc.fast_response_selftest != 2) {
+		gt_err(gt, "Unexpected fast response count: %d\n",
+		       gt->uc.guc.fast_response_selftest);
+		goto err_rq;
+	}
+
+	igt_spinner_end(&spin);
+	spinning = false;
+
+	ret = intel_selftest_wait_for_rq(rq);
+	if (ret) {
+		gt_err(gt, "Request failed to complete: %pe\n", ERR_PTR(ret));
+		goto err_rq;
+	}
+
+err_rq:
+	i915_request_put(rq);
+
+err_spin:
+	if (spinning)
+		igt_spinner_end(&spin);
+	igt_spinner_fini(&spin);
+
+err_pm:
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+	return ret;
+}
+
 int intel_guc_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(intel_guc_scrub_ctbs),
 		SUBTEST(intel_guc_steal_guc_ids),
+		SUBTEST(intel_guc_fast_request),
 	};
 	struct intel_gt *gt = to_gt(i915);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c
index 34b5d952e2bc..26fdc392fce6 100644
--- a/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c
@@ -74,7 +74,7 @@ static int intel_hang_guc(void *arg)
 		goto err;
 	}
 
-	rq = igt_spinner_create_request(&spin, ce, MI_NOOP);
+	rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK);
 	intel_context_put(ce);
 	if (IS_ERR(rq)) {
 		ret = PTR_ERR(rq);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index bfe92d2402ea..db99c2ef66db 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -51,6 +51,7 @@
 #include "i915_debugfs.h"
 #include "i915_debugfs_params.h"
 #include "i915_driver.h"
+#include "i915_gpu_error.h"
 #include "i915_irq.h"
 #include "i915_reg.h"
 #include "i915_scheduler.h"
@@ -299,107 +300,6 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
-static ssize_t gpu_state_read(struct file *file, char __user *ubuf,
-			      size_t count, loff_t *pos)
-{
-	struct i915_gpu_coredump *error;
-	ssize_t ret;
-	void *buf;
-
-	error = file->private_data;
-	if (!error)
-		return 0;
-
-	/* Bounce buffer required because of kernfs __user API convenience. */
-	buf = kmalloc(count, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	ret = i915_gpu_coredump_copy_to_buffer(error, buf, *pos, count);
-	if (ret <= 0)
-		goto out;
-
-	if (!copy_to_user(ubuf, buf, ret))
-		*pos += ret;
-	else
-		ret = -EFAULT;
-
-out:
-	kfree(buf);
-	return ret;
-}
-
-static int gpu_state_release(struct inode *inode, struct file *file)
-{
-	i915_gpu_coredump_put(file->private_data);
-	return 0;
-}
-
-static int i915_gpu_info_open(struct inode *inode, struct file *file)
-{
-	struct drm_i915_private *i915 = inode->i_private;
-	struct i915_gpu_coredump *gpu;
-	intel_wakeref_t wakeref;
-
-	gpu = NULL;
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		gpu = i915_gpu_coredump(to_gt(i915), ALL_ENGINES, CORE_DUMP_FLAG_NONE);
-
-	if (IS_ERR(gpu))
-		return PTR_ERR(gpu);
-
-	file->private_data = gpu;
-	return 0;
-}
-
-static const struct file_operations i915_gpu_info_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_gpu_info_open,
-	.read = gpu_state_read,
-	.llseek = default_llseek,
-	.release = gpu_state_release,
-};
-
-static ssize_t
-i915_error_state_write(struct file *filp,
-		       const char __user *ubuf,
-		       size_t cnt,
-		       loff_t *ppos)
-{
-	struct i915_gpu_coredump *error = filp->private_data;
-
-	if (!error)
-		return 0;
-
-	drm_dbg(&error->i915->drm, "Resetting error state\n");
-	i915_reset_error_state(error->i915);
-
-	return cnt;
-}
-
-static int i915_error_state_open(struct inode *inode, struct file *file)
-{
-	struct i915_gpu_coredump *error;
-
-	error = i915_first_error_state(inode->i_private);
-	if (IS_ERR(error))
-		return PTR_ERR(error);
-
-	file->private_data  = error;
-	return 0;
-}
-
-static const struct file_operations i915_error_state_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_error_state_open,
-	.read = gpu_state_read,
-	.write = i915_error_state_write,
-	.llseek = default_llseek,
-	.release = gpu_state_release,
-};
-#endif
-
 static int i915_frequency_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *i915 = node_to_i915(m->private);
@@ -839,10 +739,6 @@ static const struct i915_debugfs_files {
 	{"i915_perf_noa_delay", &i915_perf_noa_delay_fops},
 	{"i915_wedged", &i915_wedged_fops},
 	{"i915_gem_drop_caches", &i915_drop_caches_fops},
-#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
-	{"i915_error_state", &i915_error_state_fops},
-	{"i915_gpu_info", &i915_gpu_info_fops},
-#endif
 };
 
 void i915_debugfs_register(struct drm_i915_private *dev_priv)
@@ -865,4 +761,6 @@ void i915_debugfs_register(struct drm_i915_private *dev_priv)
 	drm_debugfs_create_files(i915_debugfs_list,
 				 ARRAY_SIZE(i915_debugfs_list),
 				 minor->debugfs_root, minor);
+
+	i915_gpu_error_debugfs_register(dev_priv);
 }
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index 2a1faf403965..c7d7c3b7ecc6 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -798,7 +798,9 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		goto out_cleanup_modeset2;
 
-	intel_pxp_init(i915);
+	ret = intel_pxp_init(i915);
+	if (ret != -ENODEV)
+		drm_dbg(&i915->drm, "pxp init failed with %d\n", ret);
 
 	ret = intel_display_driver_probe(i915);
 	if (ret)
@@ -1033,7 +1035,7 @@ void i915_driver_shutdown(struct drm_i915_private *i915)
 	intel_power_domains_driver_remove(i915);
 	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 
-	intel_runtime_pm_driver_release(&i915->runtime_pm);
+	intel_runtime_pm_driver_last_release(&i915->runtime_pm);
 }
 
 static bool suspend_to_idle(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 2a44b3876cb5..fa6852713bee 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -28,6 +28,10 @@ struct i915_drm_client *i915_drm_client_alloc(void)
 	kref_init(&client->kref);
 	spin_lock_init(&client->ctx_lock);
 	INIT_LIST_HEAD(&client->ctx_list);
+#ifdef CONFIG_PROC_FS
+	spin_lock_init(&client->objects_lock);
+	INIT_LIST_HEAD(&client->objects_list);
+#endif
 
 	return client;
 }
@@ -41,6 +45,68 @@ void __i915_drm_client_free(struct kref *kref)
 }
 
 #ifdef CONFIG_PROC_FS
+static void
+obj_meminfo(struct drm_i915_gem_object *obj,
+	    struct drm_memory_stats stats[INTEL_REGION_UNKNOWN])
+{
+	const enum intel_region_id id = obj->mm.region ?
+					obj->mm.region->id : INTEL_REGION_SMEM;
+	const u64 sz = obj->base.size;
+
+	if (obj->base.handle_count > 1)
+		stats[id].shared += sz;
+	else
+		stats[id].private += sz;
+
+	if (i915_gem_object_has_pages(obj)) {
+		stats[id].resident += sz;
+
+		if (!dma_resv_test_signaled(obj->base.resv,
+					    DMA_RESV_USAGE_BOOKKEEP))
+			stats[id].active += sz;
+		else if (i915_gem_object_is_shrinkable(obj) &&
+			 obj->mm.madv == I915_MADV_DONTNEED)
+			stats[id].purgeable += sz;
+	}
+}
+
+static void show_meminfo(struct drm_printer *p, struct drm_file *file)
+{
+	struct drm_memory_stats stats[INTEL_REGION_UNKNOWN] = {};
+	struct drm_i915_file_private *fpriv = file->driver_priv;
+	struct i915_drm_client *client = fpriv->client;
+	struct drm_i915_private *i915 = fpriv->i915;
+	struct drm_i915_gem_object *obj;
+	struct intel_memory_region *mr;
+	struct list_head __rcu *pos;
+	unsigned int id;
+
+	/* Public objects. */
+	spin_lock(&file->table_lock);
+	idr_for_each_entry(&file->object_idr, obj, id)
+		obj_meminfo(obj, stats);
+	spin_unlock(&file->table_lock);
+
+	/* Internal objects. */
+	rcu_read_lock();
+	list_for_each_rcu(pos, &client->objects_list) {
+		obj = i915_gem_object_get_rcu(list_entry(pos, typeof(*obj),
+							 client_link));
+		if (!obj)
+			continue;
+		obj_meminfo(obj, stats);
+		i915_gem_object_put(obj);
+	}
+	rcu_read_unlock();
+
+	for_each_memory_region(mr, i915, id)
+		drm_print_memory_stats(p,
+				       &stats[id],
+				       DRM_GEM_OBJECT_RESIDENT |
+				       DRM_GEM_OBJECT_PURGEABLE,
+				       mr->uabi_name);
+}
+
 static const char * const uabi_class_names[] = {
 	[I915_ENGINE_CLASS_RENDER] = "render",
 	[I915_ENGINE_CLASS_COPY] = "copy",
@@ -102,10 +168,52 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file)
 	 * ******************************************************************
 	 */
 
+	show_meminfo(p, file);
+
 	if (GRAPHICS_VER(i915) < 8)
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(uabi_class_names); i++)
 		show_client_class(p, i915, file_priv->client, i);
 }
+
+void i915_drm_client_add_object(struct i915_drm_client *client,
+				struct drm_i915_gem_object *obj)
+{
+	unsigned long flags;
+
+	GEM_WARN_ON(obj->client);
+	GEM_WARN_ON(!list_empty(&obj->client_link));
+
+	spin_lock_irqsave(&client->objects_lock, flags);
+	obj->client = i915_drm_client_get(client);
+	list_add_tail_rcu(&obj->client_link, &client->objects_list);
+	spin_unlock_irqrestore(&client->objects_lock, flags);
+}
+
+void i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
+{
+	struct i915_drm_client *client = fetch_and_zero(&obj->client);
+	unsigned long flags;
+
+	/* Object may not be associated with a client. */
+	if (!client)
+		return;
+
+	spin_lock_irqsave(&client->objects_lock, flags);
+	list_del_rcu(&obj->client_link);
+	spin_unlock_irqrestore(&client->objects_lock, flags);
+
+	i915_drm_client_put(client);
+}
+
+void i915_drm_client_add_context_objects(struct i915_drm_client *client,
+					 struct intel_context *ce)
+{
+	if (ce->state)
+		i915_drm_client_add_object(client, ce->state->obj);
+
+	if (ce->ring != ce->engine->legacy.ring && ce->ring->vma)
+		i915_drm_client_add_object(client, ce->ring->vma->obj);
+}
 #endif
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 67816c912bca..a439dd789936 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -12,6 +12,10 @@
 
 #include <uapi/drm/i915_drm.h>
 
+#include "i915_file_private.h"
+#include "gem/i915_gem_object_types.h"
+#include "gt/intel_context_types.h"
+
 #define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
 
 struct drm_file;
@@ -25,6 +29,20 @@ struct i915_drm_client {
 	spinlock_t ctx_lock; /* For add/remove from ctx_list. */
 	struct list_head ctx_list; /* List of contexts belonging to client. */
 
+#ifdef CONFIG_PROC_FS
+	/**
+	 * @objects_lock: lock protecting @objects_list
+	 */
+	spinlock_t objects_lock;
+
+	/**
+	 * @objects_list: list of objects created by this client
+	 *
+	 * Protected by @objects_lock.
+	 */
+	struct list_head objects_list;
+#endif
+
 	/**
 	 * @past_runtime: Accumulation of pphwsp runtimes from closed contexts.
 	 */
@@ -49,4 +67,28 @@ struct i915_drm_client *i915_drm_client_alloc(void);
 
 void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file);
 
+#ifdef CONFIG_PROC_FS
+void i915_drm_client_add_object(struct i915_drm_client *client,
+				struct drm_i915_gem_object *obj);
+void i915_drm_client_remove_object(struct drm_i915_gem_object *obj);
+void i915_drm_client_add_context_objects(struct i915_drm_client *client,
+					 struct intel_context *ce);
+#else
+static inline void i915_drm_client_add_object(struct i915_drm_client *client,
+					      struct drm_i915_gem_object *obj)
+{
+}
+
+static inline void
+i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
+{
+}
+
+static inline void
+i915_drm_client_add_context_objects(struct i915_drm_client *client,
+				    struct intel_context *ce)
+{
+}
+#endif
+
 #endif /* !__I915_DRM_CLIENT_H__ */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0971f4976324..d04660b60046 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -57,6 +57,7 @@
 #include "i915_memcpy.h"
 #include "i915_reg.h"
 #include "i915_scatterlist.h"
+#include "i915_sysfs.h"
 #include "i915_utils.h"
 
 #define ALLOW_FAIL (__GFP_KSWAPD_RECLAIM | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
@@ -520,7 +521,7 @@ __find_vma(struct i915_vma_coredump *vma, const char *name)
 	return NULL;
 }
 
-struct i915_vma_coredump *
+static struct i915_vma_coredump *
 intel_gpu_error_find_batch(const struct intel_engine_coredump *ee)
 {
 	return __find_vma(ee->vma, "batch");
@@ -609,9 +610,9 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 	va_end(args);
 }
 
-void intel_gpu_error_print_vma(struct drm_i915_error_state_buf *m,
-			       const struct intel_engine_cs *engine,
-			       const struct i915_vma_coredump *vma)
+static void intel_gpu_error_print_vma(struct drm_i915_error_state_buf *m,
+				      const struct intel_engine_cs *engine,
+				      const struct i915_vma_coredump *vma)
 {
 	char out[ASCII85_BUFSZ];
 	struct page *page;
@@ -2140,7 +2141,7 @@ __i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask, u32 du
 	return error;
 }
 
-struct i915_gpu_coredump *
+static struct i915_gpu_coredump *
 i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask, u32 dump_flags)
 {
 	static DEFINE_MUTEX(capture_mutex);
@@ -2211,7 +2212,7 @@ void i915_capture_error_state(struct intel_gt *gt,
 	i915_gpu_coredump_put(error);
 }
 
-struct i915_gpu_coredump *
+static struct i915_gpu_coredump *
 i915_first_error_state(struct drm_i915_private *i915)
 {
 	struct i915_gpu_coredump *error;
@@ -2378,3 +2379,184 @@ void intel_klog_error_capture(struct intel_gt *gt,
 	drm_info(&i915->drm, "[Capture/%d.%d] Dumped %zd bytes\n", l_count, line++, pos_err);
 }
 #endif
+
+static ssize_t gpu_state_read(struct file *file, char __user *ubuf,
+			      size_t count, loff_t *pos)
+{
+	struct i915_gpu_coredump *error;
+	ssize_t ret;
+	void *buf;
+
+	error = file->private_data;
+	if (!error)
+		return 0;
+
+	/* Bounce buffer required because of kernfs __user API convenience. */
+	buf = kmalloc(count, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = i915_gpu_coredump_copy_to_buffer(error, buf, *pos, count);
+	if (ret <= 0)
+		goto out;
+
+	if (!copy_to_user(ubuf, buf, ret))
+		*pos += ret;
+	else
+		ret = -EFAULT;
+
+out:
+	kfree(buf);
+	return ret;
+}
+
+static int gpu_state_release(struct inode *inode, struct file *file)
+{
+	i915_gpu_coredump_put(file->private_data);
+	return 0;
+}
+
+static int i915_gpu_info_open(struct inode *inode, struct file *file)
+{
+	struct drm_i915_private *i915 = inode->i_private;
+	struct i915_gpu_coredump *gpu;
+	intel_wakeref_t wakeref;
+
+	gpu = NULL;
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+		gpu = i915_gpu_coredump(to_gt(i915), ALL_ENGINES, CORE_DUMP_FLAG_NONE);
+
+	if (IS_ERR(gpu))
+		return PTR_ERR(gpu);
+
+	file->private_data = gpu;
+	return 0;
+}
+
+static const struct file_operations i915_gpu_info_fops = {
+	.owner = THIS_MODULE,
+	.open = i915_gpu_info_open,
+	.read = gpu_state_read,
+	.llseek = default_llseek,
+	.release = gpu_state_release,
+};
+
+static ssize_t
+i915_error_state_write(struct file *filp,
+		       const char __user *ubuf,
+		       size_t cnt,
+		       loff_t *ppos)
+{
+	struct i915_gpu_coredump *error = filp->private_data;
+
+	if (!error)
+		return 0;
+
+	drm_dbg(&error->i915->drm, "Resetting error state\n");
+	i915_reset_error_state(error->i915);
+
+	return cnt;
+}
+
+static int i915_error_state_open(struct inode *inode, struct file *file)
+{
+	struct i915_gpu_coredump *error;
+
+	error = i915_first_error_state(inode->i_private);
+	if (IS_ERR(error))
+		return PTR_ERR(error);
+
+	file->private_data  = error;
+	return 0;
+}
+
+static const struct file_operations i915_error_state_fops = {
+	.owner = THIS_MODULE,
+	.open = i915_error_state_open,
+	.read = gpu_state_read,
+	.write = i915_error_state_write,
+	.llseek = default_llseek,
+	.release = gpu_state_release,
+};
+
+void i915_gpu_error_debugfs_register(struct drm_i915_private *i915)
+{
+	struct drm_minor *minor = i915->drm.primary;
+
+	debugfs_create_file("i915_error_state", 0644, minor->debugfs_root, i915,
+			    &i915_error_state_fops);
+	debugfs_create_file("i915_gpu_info", 0644, minor->debugfs_root, i915,
+			    &i915_gpu_info_fops);
+}
+
+static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *attr, char *buf,
+				loff_t off, size_t count)
+{
+
+	struct device *kdev = kobj_to_dev(kobj);
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
+	struct i915_gpu_coredump *gpu;
+	ssize_t ret = 0;
+
+	/*
+	 * FIXME: Concurrent clients triggering resets and reading + clearing
+	 * dumps can cause inconsistent sysfs reads when a user calls in with a
+	 * non-zero offset to complete a prior partial read but the
+	 * gpu_coredump has been cleared or replaced.
+	 */
+
+	gpu = i915_first_error_state(i915);
+	if (IS_ERR(gpu)) {
+		ret = PTR_ERR(gpu);
+	} else if (gpu) {
+		ret = i915_gpu_coredump_copy_to_buffer(gpu, buf, off, count);
+		i915_gpu_coredump_put(gpu);
+	} else {
+		const char *str = "No error state collected\n";
+		size_t len = strlen(str);
+
+		if (off < len) {
+			ret = min_t(size_t, count, len - off);
+			memcpy(buf, str + off, ret);
+		}
+	}
+
+	return ret;
+}
+
+static ssize_t error_state_write(struct file *file, struct kobject *kobj,
+				 struct bin_attribute *attr, char *buf,
+				 loff_t off, size_t count)
+{
+	struct device *kdev = kobj_to_dev(kobj);
+	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
+
+	drm_dbg(&dev_priv->drm, "Resetting error state\n");
+	i915_reset_error_state(dev_priv);
+
+	return count;
+}
+
+static const struct bin_attribute error_state_attr = {
+	.attr.name = "error",
+	.attr.mode = S_IRUSR | S_IWUSR,
+	.size = 0,
+	.read = error_state_read,
+	.write = error_state_write,
+};
+
+void i915_gpu_error_sysfs_setup(struct drm_i915_private *i915)
+{
+	struct device *kdev = i915->drm.primary->kdev;
+
+	if (sysfs_create_bin_file(&kdev->kobj, &error_state_attr))
+		drm_err(&i915->drm, "error_state sysfs setup failed\n");
+}
+
+void i915_gpu_error_sysfs_teardown(struct drm_i915_private *i915)
+{
+	struct device *kdev = i915->drm.primary->kdev;
+
+	sysfs_remove_bin_file(&kdev->kobj, &error_state_attr);
+}
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 4ce227f7e1e1..7c255bb1c319 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -17,6 +17,7 @@
 #include "display/intel_display_device.h"
 #include "display/intel_display_params.h"
 #include "gt/intel_engine.h"
+#include "gt/intel_engine_types.h"
 #include "gt/intel_gt_types.h"
 #include "gt/uc/intel_uc_fw.h"
 
@@ -234,7 +235,7 @@ struct i915_gpu_error {
 	atomic_t reset_count;
 
 	/** Number of times an engine has been reset */
-	atomic_t reset_engine_count[I915_NUM_ENGINES];
+	atomic_t reset_engine_count[MAX_ENGINE_CLASS];
 };
 
 struct drm_i915_error_state_buf {
@@ -257,7 +258,14 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
 					  const struct intel_engine_cs *engine)
 {
-	return atomic_read(&error->reset_engine_count[engine->uabi_class]);
+	return atomic_read(&error->reset_engine_count[engine->class]);
+}
+
+static inline void
+i915_increase_reset_engine_count(struct i915_gpu_error *error,
+				 const struct intel_engine_cs *engine)
+{
+	atomic_inc(&error->reset_engine_count[engine->class]);
 }
 
 #define CORE_DUMP_FLAG_NONE           0x0
@@ -277,14 +285,7 @@ static inline void intel_klog_error_capture(struct intel_gt *gt,
 
 __printf(2, 3)
 void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
-void intel_gpu_error_print_vma(struct drm_i915_error_state_buf *m,
-			       const struct intel_engine_cs *engine,
-			       const struct i915_vma_coredump *vma);
-struct i915_vma_coredump *
-intel_gpu_error_find_batch(const struct intel_engine_coredump *ee);
-
-struct i915_gpu_coredump *i915_gpu_coredump(struct intel_gt *gt,
-					    intel_engine_mask_t engine_mask, u32 dump_flags);
+
 void i915_capture_error_state(struct intel_gt *gt,
 			      intel_engine_mask_t engine_mask, u32 dump_flags);
 
@@ -332,10 +333,13 @@ static inline void i915_gpu_coredump_put(struct i915_gpu_coredump *gpu)
 		kref_put(&gpu->ref, __i915_gpu_coredump_free);
 }
 
-struct i915_gpu_coredump *i915_first_error_state(struct drm_i915_private *i915);
 void i915_reset_error_state(struct drm_i915_private *i915);
 void i915_disable_error_state(struct drm_i915_private *i915, int err);
 
+void i915_gpu_error_debugfs_register(struct drm_i915_private *i915);
+void i915_gpu_error_sysfs_setup(struct drm_i915_private *i915);
+void i915_gpu_error_sysfs_teardown(struct drm_i915_private *i915);
+
 #else
 
 __printf(2, 3)
@@ -403,12 +407,6 @@ static inline void i915_gpu_coredump_put(struct i915_gpu_coredump *gpu)
 {
 }
 
-static inline struct i915_gpu_coredump *
-i915_first_error_state(struct drm_i915_private *i915)
-{
-	return ERR_PTR(-ENODEV);
-}
-
 static inline void i915_reset_error_state(struct drm_i915_private *i915)
 {
 }
@@ -418,6 +416,18 @@ static inline void i915_disable_error_state(struct drm_i915_private *i915,
 {
 }
 
+static inline void i915_gpu_error_debugfs_register(struct drm_i915_private *i915)
+{
+}
+
+static inline void i915_gpu_error_sysfs_setup(struct drm_i915_private *i915)
+{
+}
+
+static inline void i915_gpu_error_sysfs_teardown(struct drm_i915_private *i915)
+{
+}
+
 #endif /* IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) */
 
 #endif /* _I915_GPU_ERROR_H_ */
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index f861863eb7c1..21eb0c5b320d 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -31,6 +31,16 @@
 static cpumask_t i915_pmu_cpumask;
 static unsigned int i915_pmu_target_cpu = -1;
 
+static struct i915_pmu *event_to_pmu(struct perf_event *event)
+{
+	return container_of(event->pmu, struct i915_pmu, base);
+}
+
+static struct drm_i915_private *pmu_to_i915(struct i915_pmu *pmu)
+{
+	return container_of(pmu, struct drm_i915_private, pmu);
+}
+
 static u8 engine_config_sample(u64 config)
 {
 	return config & I915_PMU_SAMPLE_MASK;
@@ -141,7 +151,7 @@ static u32 frequency_enabled_mask(void)
 
 static bool pmu_needs_timer(struct i915_pmu *pmu)
 {
-	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 	u32 enable;
 
 	/*
@@ -213,19 +223,19 @@ static u64 get_rc6(struct intel_gt *gt)
 	struct drm_i915_private *i915 = gt->i915;
 	const unsigned int gt_id = gt->info.id;
 	struct i915_pmu *pmu = &i915->pmu;
+	intel_wakeref_t wakeref;
 	unsigned long flags;
-	bool awake = false;
 	u64 val;
 
-	if (intel_gt_pm_get_if_awake(gt)) {
+	wakeref = intel_gt_pm_get_if_awake(gt);
+	if (wakeref) {
 		val = __get_rc6(gt);
-		intel_gt_pm_put_async(gt);
-		awake = true;
+		intel_gt_pm_put_async(gt, wakeref);
 	}
 
 	spin_lock_irqsave(&pmu->lock, flags);
 
-	if (awake) {
+	if (wakeref) {
 		store_sample(pmu, gt_id, __I915_SAMPLE_RC6, val);
 	} else {
 		/*
@@ -251,7 +261,7 @@ static u64 get_rc6(struct intel_gt *gt)
 
 static void init_rc6(struct i915_pmu *pmu)
 {
-	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 	struct intel_gt *gt;
 	unsigned int i;
 
@@ -429,12 +439,14 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 	const unsigned int gt_id = gt->info.id;
 	struct i915_pmu *pmu = &i915->pmu;
 	struct intel_rps *rps = &gt->rps;
+	intel_wakeref_t wakeref;
 
 	if (!frequency_sampling_enabled(pmu, gt_id))
 		return;
 
 	/* Report 0/0 (actual/requested) frequency while parked. */
-	if (!intel_gt_pm_get_if_awake(gt))
+	wakeref = intel_gt_pm_get_if_awake(gt);
+	if (!wakeref)
 		return;
 
 	if (pmu->enable & config_mask(__I915_PMU_ACTUAL_FREQUENCY(gt_id))) {
@@ -463,14 +475,13 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 				period_ns / 1000);
 	}
 
-	intel_gt_pm_put_async(gt);
+	intel_gt_pm_put_async(gt, wakeref);
 }
 
 static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 {
-	struct drm_i915_private *i915 =
-		container_of(hrtimer, struct drm_i915_private, pmu.timer);
-	struct i915_pmu *pmu = &i915->pmu;
+	struct i915_pmu *pmu = container_of(hrtimer, struct i915_pmu, timer);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 	unsigned int period_ns;
 	struct intel_gt *gt;
 	unsigned int i;
@@ -505,8 +516,8 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 
 static void i915_pmu_event_destroy(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = event_to_pmu(event);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 
 	drm_WARN_ON(&i915->drm, event->parent);
 
@@ -572,8 +583,8 @@ config_status(struct drm_i915_private *i915, u64 config)
 
 static int engine_event_init(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = event_to_pmu(event);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 	struct intel_engine_cs *engine;
 
 	engine = intel_engine_lookup_user(i915, engine_event_class(event),
@@ -586,9 +597,8 @@ static int engine_event_init(struct perf_event *event)
 
 static int i915_pmu_event_init(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
-	struct i915_pmu *pmu = &i915->pmu;
+	struct i915_pmu *pmu = event_to_pmu(event);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 	int ret;
 
 	if (pmu->closed)
@@ -628,9 +638,8 @@ static int i915_pmu_event_init(struct perf_event *event)
 
 static u64 __i915_pmu_event_read(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
-	struct i915_pmu *pmu = &i915->pmu;
+	struct i915_pmu *pmu = event_to_pmu(event);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 	u64 val = 0;
 
 	if (is_engine_event(event)) {
@@ -686,10 +695,8 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 
 static void i915_pmu_event_read(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = event_to_pmu(event);
 	struct hw_perf_event *hwc = &event->hw;
-	struct i915_pmu *pmu = &i915->pmu;
 	u64 prev, new;
 
 	if (pmu->closed) {
@@ -707,10 +714,9 @@ static void i915_pmu_event_read(struct perf_event *event)
 
 static void i915_pmu_enable(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = event_to_pmu(event);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 	const unsigned int bit = event_bit(event);
-	struct i915_pmu *pmu = &i915->pmu;
 	unsigned long flags;
 
 	if (bit == -1)
@@ -771,10 +777,9 @@ update:
 
 static void i915_pmu_disable(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = event_to_pmu(event);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 	const unsigned int bit = event_bit(event);
-	struct i915_pmu *pmu = &i915->pmu;
 	unsigned long flags;
 
 	if (bit == -1)
@@ -818,9 +823,7 @@ static void i915_pmu_disable(struct perf_event *event)
 
 static void i915_pmu_event_start(struct perf_event *event, int flags)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
-	struct i915_pmu *pmu = &i915->pmu;
+	struct i915_pmu *pmu = event_to_pmu(event);
 
 	if (pmu->closed)
 		return;
@@ -848,9 +851,7 @@ out:
 
 static int i915_pmu_event_add(struct perf_event *event, int flags)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
-	struct i915_pmu *pmu = &i915->pmu;
+	struct i915_pmu *pmu = event_to_pmu(event);
 
 	if (pmu->closed)
 		return -ENODEV;
@@ -982,7 +983,7 @@ add_pmu_attr(struct perf_pmu_events_attr *attr, const char *name,
 static struct attribute **
 create_event_attributes(struct i915_pmu *pmu)
 {
-	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
+	struct drm_i915_private *i915 = pmu_to_i915(pmu);
 	static const struct {
 		unsigned int counter;
 		const char *name;
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index e88bb4f04305..613decd47760 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -155,81 +155,6 @@ static const struct bin_attribute dpf_attrs_1 = {
 	.private = (void *)1
 };
 
-#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
-
-static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *attr, char *buf,
-				loff_t off, size_t count)
-{
-
-	struct device *kdev = kobj_to_dev(kobj);
-	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
-	struct i915_gpu_coredump *gpu;
-	ssize_t ret = 0;
-
-	/*
-	 * FIXME: Concurrent clients triggering resets and reading + clearing
-	 * dumps can cause inconsistent sysfs reads when a user calls in with a
-	 * non-zero offset to complete a prior partial read but the
-	 * gpu_coredump has been cleared or replaced.
-	 */
-
-	gpu = i915_first_error_state(i915);
-	if (IS_ERR(gpu)) {
-		ret = PTR_ERR(gpu);
-	} else if (gpu) {
-		ret = i915_gpu_coredump_copy_to_buffer(gpu, buf, off, count);
-		i915_gpu_coredump_put(gpu);
-	} else {
-		const char *str = "No error state collected\n";
-		size_t len = strlen(str);
-
-		if (off < len) {
-			ret = min_t(size_t, count, len - off);
-			memcpy(buf, str + off, ret);
-		}
-	}
-
-	return ret;
-}
-
-static ssize_t error_state_write(struct file *file, struct kobject *kobj,
-				 struct bin_attribute *attr, char *buf,
-				 loff_t off, size_t count)
-{
-	struct device *kdev = kobj_to_dev(kobj);
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-
-	drm_dbg(&dev_priv->drm, "Resetting error state\n");
-	i915_reset_error_state(dev_priv);
-
-	return count;
-}
-
-static const struct bin_attribute error_state_attr = {
-	.attr.name = "error",
-	.attr.mode = S_IRUSR | S_IWUSR,
-	.size = 0,
-	.read = error_state_read,
-	.write = error_state_write,
-};
-
-static void i915_setup_error_capture(struct device *kdev)
-{
-	if (sysfs_create_bin_file(&kdev->kobj, &error_state_attr))
-		drm_err(&kdev_minor_to_i915(kdev)->drm,
-			"error_state sysfs setup failed\n");
-}
-
-static void i915_teardown_error_capture(struct device *kdev)
-{
-	sysfs_remove_bin_file(&kdev->kobj, &error_state_attr);
-}
-#else
-static void i915_setup_error_capture(struct device *kdev) {}
-static void i915_teardown_error_capture(struct device *kdev) {}
-#endif
-
 void i915_setup_sysfs(struct drm_i915_private *dev_priv)
 {
 	struct device *kdev = dev_priv->drm.primary->kdev;
@@ -255,7 +180,7 @@ void i915_setup_sysfs(struct drm_i915_private *dev_priv)
 		drm_warn(&dev_priv->drm,
 			 "failed to register GT sysfs directory\n");
 
-	i915_setup_error_capture(kdev);
+	i915_gpu_error_sysfs_setup(dev_priv);
 
 	intel_engines_add_sysfs(dev_priv);
 }
@@ -264,7 +189,7 @@ void i915_teardown_sysfs(struct drm_i915_private *dev_priv)
 {
 	struct device *kdev = dev_priv->drm.primary->kdev;
 
-	i915_teardown_error_capture(kdev);
+	i915_gpu_error_sysfs_teardown(dev_priv);
 
 	device_remove_bin_file(kdev,  &dpf_attrs_1);
 	device_remove_bin_file(kdev,  &dpf_attrs);
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index 3d1fdea9811d..60a03340bbd4 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -216,6 +216,22 @@ static int intel_memory_region_memtest(struct intel_memory_region *mem,
 	return err;
 }
 
+static const char *region_type_str(u16 type)
+{
+	switch (type) {
+	case INTEL_MEMORY_SYSTEM:
+		return "system";
+	case INTEL_MEMORY_LOCAL:
+		return "local";
+	case INTEL_MEMORY_STOLEN_LOCAL:
+		return "stolen-local";
+	case INTEL_MEMORY_STOLEN_SYSTEM:
+		return "stolen-system";
+	default:
+		return "unknown";
+	}
+}
+
 struct intel_memory_region *
 intel_memory_region_create(struct drm_i915_private *i915,
 			   resource_size_t start,
@@ -244,6 +260,9 @@ intel_memory_region_create(struct drm_i915_private *i915,
 	mem->type = type;
 	mem->instance = instance;
 
+	snprintf(mem->uabi_name, sizeof(mem->uabi_name), "%s%u",
+		 region_type_str(type), instance);
+
 	mutex_init(&mem->objects.lock);
 	INIT_LIST_HEAD(&mem->objects.list);
 
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 2953ed5c3248..9ba36454e51b 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -80,6 +80,7 @@ struct intel_memory_region {
 	u16 instance;
 	enum intel_region_id id;
 	char name[16];
+	char uabi_name[16];
 	bool private; /* not for userspace */
 
 	struct {
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 156cb1536b47..860b51b56a92 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -57,182 +57,37 @@ static struct drm_i915_private *rpm_to_i915(struct intel_runtime_pm *rpm)
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
 
-#include <linux/sort.h>
-
-#define STACKDEPTH 8
-
-static noinline depot_stack_handle_t __save_depot_stack(void)
-{
-	unsigned long entries[STACKDEPTH];
-	unsigned int n;
-
-	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
-	return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN);
-}
-
 static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
 {
-	spin_lock_init(&rpm->debug.lock);
-	stack_depot_init();
+	ref_tracker_dir_init(&rpm->debug, INTEL_REFTRACK_DEAD_COUNT, dev_name(rpm->kdev));
 }
 
-static noinline depot_stack_handle_t
+static intel_wakeref_t
 track_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
 {
-	depot_stack_handle_t stack, *stacks;
-	unsigned long flags;
-
-	if (rpm->no_wakeref_tracking)
+	if (!rpm->available || rpm->no_wakeref_tracking)
 		return -1;
 
-	stack = __save_depot_stack();
-	if (!stack)
-		return -1;
-
-	spin_lock_irqsave(&rpm->debug.lock, flags);
-
-	if (!rpm->debug.count)
-		rpm->debug.last_acquire = stack;
-
-	stacks = krealloc(rpm->debug.owners,
-			  (rpm->debug.count + 1) * sizeof(*stacks),
-			  GFP_NOWAIT | __GFP_NOWARN);
-	if (stacks) {
-		stacks[rpm->debug.count++] = stack;
-		rpm->debug.owners = stacks;
-	} else {
-		stack = -1;
-	}
-
-	spin_unlock_irqrestore(&rpm->debug.lock, flags);
-
-	return stack;
+	return intel_ref_tracker_alloc(&rpm->debug);
 }
 
 static void untrack_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm,
-					     depot_stack_handle_t stack)
-{
-	struct drm_i915_private *i915 = container_of(rpm,
-						     struct drm_i915_private,
-						     runtime_pm);
-	unsigned long flags, n;
-	bool found = false;
-
-	if (unlikely(stack == -1))
-		return;
-
-	spin_lock_irqsave(&rpm->debug.lock, flags);
-	for (n = rpm->debug.count; n--; ) {
-		if (rpm->debug.owners[n] == stack) {
-			memmove(rpm->debug.owners + n,
-				rpm->debug.owners + n + 1,
-				(--rpm->debug.count - n) * sizeof(stack));
-			found = true;
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&rpm->debug.lock, flags);
-
-	if (drm_WARN(&i915->drm, !found,
-		     "Unmatched wakeref (tracking %lu), count %u\n",
-		     rpm->debug.count, atomic_read(&rpm->wakeref_count))) {
-		char *buf;
-
-		buf = kmalloc(PAGE_SIZE, GFP_NOWAIT | __GFP_NOWARN);
-		if (!buf)
-			return;
-
-		stack_depot_snprint(stack, buf, PAGE_SIZE, 2);
-		DRM_DEBUG_DRIVER("wakeref %x from\n%s", stack, buf);
-
-		stack = READ_ONCE(rpm->debug.last_release);
-		if (stack) {
-			stack_depot_snprint(stack, buf, PAGE_SIZE, 2);
-			DRM_DEBUG_DRIVER("wakeref last released at\n%s", buf);
-		}
-
-		kfree(buf);
-	}
-}
-
-static int cmphandle(const void *_a, const void *_b)
-{
-	const depot_stack_handle_t * const a = _a, * const b = _b;
-
-	if (*a < *b)
-		return -1;
-	else if (*a > *b)
-		return 1;
-	else
-		return 0;
-}
-
-static void
-__print_intel_runtime_pm_wakeref(struct drm_printer *p,
-				 const struct intel_runtime_pm_debug *dbg)
+					     intel_wakeref_t wakeref)
 {
-	unsigned long i;
-	char *buf;
-
-	buf = kmalloc(PAGE_SIZE, GFP_NOWAIT | __GFP_NOWARN);
-	if (!buf)
+	if (!rpm->available || rpm->no_wakeref_tracking)
 		return;
 
-	if (dbg->last_acquire) {
-		stack_depot_snprint(dbg->last_acquire, buf, PAGE_SIZE, 2);
-		drm_printf(p, "Wakeref last acquired:\n%s", buf);
-	}
-
-	if (dbg->last_release) {
-		stack_depot_snprint(dbg->last_release, buf, PAGE_SIZE, 2);
-		drm_printf(p, "Wakeref last released:\n%s", buf);
-	}
-
-	drm_printf(p, "Wakeref count: %lu\n", dbg->count);
-
-	sort(dbg->owners, dbg->count, sizeof(*dbg->owners), cmphandle, NULL);
-
-	for (i = 0; i < dbg->count; i++) {
-		depot_stack_handle_t stack = dbg->owners[i];
-		unsigned long rep;
-
-		rep = 1;
-		while (i + 1 < dbg->count && dbg->owners[i + 1] == stack)
-			rep++, i++;
-		stack_depot_snprint(stack, buf, PAGE_SIZE, 2);
-		drm_printf(p, "Wakeref x%lu taken at:\n%s", rep, buf);
-	}
-
-	kfree(buf);
-}
-
-static noinline void
-__untrack_all_wakerefs(struct intel_runtime_pm_debug *debug,
-		       struct intel_runtime_pm_debug *saved)
-{
-	*saved = *debug;
-
-	debug->owners = NULL;
-	debug->count = 0;
-	debug->last_release = __save_depot_stack();
+	intel_ref_tracker_free(&rpm->debug, wakeref);
 }
 
-static void
-dump_and_free_wakeref_tracking(struct intel_runtime_pm_debug *debug)
+static void untrack_all_intel_runtime_pm_wakerefs(struct intel_runtime_pm *rpm)
 {
-	if (debug->count) {
-		struct drm_printer p = drm_debug_printer("i915");
-
-		__print_intel_runtime_pm_wakeref(&p, debug);
-	}
-
-	kfree(debug->owners);
+	ref_tracker_dir_exit(&rpm->debug);
 }
 
 static noinline void
 __intel_wakeref_dec_and_check_tracking(struct intel_runtime_pm *rpm)
 {
-	struct intel_runtime_pm_debug dbg = {};
 	unsigned long flags;
 
 	if (!atomic_dec_and_lock_irqsave(&rpm->wakeref_count,
@@ -240,60 +95,14 @@ __intel_wakeref_dec_and_check_tracking(struct intel_runtime_pm *rpm)
 					 flags))
 		return;
 
-	__untrack_all_wakerefs(&rpm->debug, &dbg);
+	ref_tracker_dir_print_locked(&rpm->debug, INTEL_REFTRACK_PRINT_LIMIT);
 	spin_unlock_irqrestore(&rpm->debug.lock, flags);
-
-	dump_and_free_wakeref_tracking(&dbg);
-}
-
-static noinline void
-untrack_all_intel_runtime_pm_wakerefs(struct intel_runtime_pm *rpm)
-{
-	struct intel_runtime_pm_debug dbg = {};
-	unsigned long flags;
-
-	spin_lock_irqsave(&rpm->debug.lock, flags);
-	__untrack_all_wakerefs(&rpm->debug, &dbg);
-	spin_unlock_irqrestore(&rpm->debug.lock, flags);
-
-	dump_and_free_wakeref_tracking(&dbg);
 }
 
 void print_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm,
 				    struct drm_printer *p)
 {
-	struct intel_runtime_pm_debug dbg = {};
-
-	do {
-		unsigned long alloc = dbg.count;
-		depot_stack_handle_t *s;
-
-		spin_lock_irq(&rpm->debug.lock);
-		dbg.count = rpm->debug.count;
-		if (dbg.count <= alloc) {
-			memcpy(dbg.owners,
-			       rpm->debug.owners,
-			       dbg.count * sizeof(*s));
-		}
-		dbg.last_acquire = rpm->debug.last_acquire;
-		dbg.last_release = rpm->debug.last_release;
-		spin_unlock_irq(&rpm->debug.lock);
-		if (dbg.count <= alloc)
-			break;
-
-		s = krealloc(dbg.owners,
-			     dbg.count * sizeof(*s),
-			     GFP_NOWAIT | __GFP_NOWARN);
-		if (!s)
-			goto out;
-
-		dbg.owners = s;
-	} while (1);
-
-	__print_intel_runtime_pm_wakeref(p, &dbg);
-
-out:
-	kfree(dbg.owners);
+	intel_ref_tracker_show(&rpm->debug, p);
 }
 
 #else
@@ -302,14 +111,14 @@ static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
 {
 }
 
-static depot_stack_handle_t
+static intel_wakeref_t
 track_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
 {
 	return -1;
 }
 
 static void untrack_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm,
-					     intel_wakeref_t wref)
+					     intel_wakeref_t wakeref)
 {
 }
 
@@ -636,7 +445,11 @@ void intel_runtime_pm_driver_release(struct intel_runtime_pm *rpm)
 		 "i915 raw-wakerefs=%d wakelocks=%d on cleanup\n",
 		 intel_rpm_raw_wakeref_count(count),
 		 intel_rpm_wakelock_count(count));
+}
 
+void intel_runtime_pm_driver_last_release(struct intel_runtime_pm *rpm)
+{
+	intel_runtime_pm_driver_release(rpm);
 	untrack_all_intel_runtime_pm_wakerefs(rpm);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.h b/drivers/gpu/drm/i915/intel_runtime_pm.h
index be43614c73fd..de3579d399e1 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.h
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.h
@@ -75,15 +75,7 @@ struct intel_runtime_pm {
 	 * paired rpm_put) we can remove corresponding pairs of and keep
 	 * the array trimmed to active wakerefs.
 	 */
-	struct intel_runtime_pm_debug {
-		spinlock_t lock;
-
-		depot_stack_handle_t last_acquire;
-		depot_stack_handle_t last_release;
-
-		depot_stack_handle_t *owners;
-		unsigned long count;
-	} debug;
+	struct ref_tracker_dir debug;
 #endif
 };
 
@@ -187,6 +179,7 @@ void intel_runtime_pm_init_early(struct intel_runtime_pm *rpm);
 void intel_runtime_pm_enable(struct intel_runtime_pm *rpm);
 void intel_runtime_pm_disable(struct intel_runtime_pm *rpm);
 void intel_runtime_pm_driver_release(struct intel_runtime_pm *rpm);
+void intel_runtime_pm_driver_last_release(struct intel_runtime_pm *rpm);
 
 intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm);
 intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm);
diff --git a/drivers/gpu/drm/i915/intel_wakeref.c b/drivers/gpu/drm/i915/intel_wakeref.c
index 623a69089386..dea2f63184f8 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.c
+++ b/drivers/gpu/drm/i915/intel_wakeref.c
@@ -99,7 +99,8 @@ static void __intel_wakeref_put_work(struct work_struct *wrk)
 void __intel_wakeref_init(struct intel_wakeref *wf,
 			  struct drm_i915_private *i915,
 			  const struct intel_wakeref_ops *ops,
-			  struct intel_wakeref_lockclass *key)
+			  struct intel_wakeref_lockclass *key,
+			  const char *name)
 {
 	wf->i915 = i915;
 	wf->ops = ops;
@@ -111,6 +112,10 @@ void __intel_wakeref_init(struct intel_wakeref *wf,
 	INIT_DELAYED_WORK(&wf->work, __intel_wakeref_put_work);
 	lockdep_init_map(&wf->work.work.lockdep_map,
 			 "wakeref.work", &key->work, 0);
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_WAKEREF)
+	ref_tracker_dir_init(&wf->debug, INTEL_REFTRACK_DEAD_COUNT, name);
+#endif
 }
 
 int intel_wakeref_wait_for_idle(struct intel_wakeref *wf)
@@ -191,3 +196,31 @@ void intel_wakeref_auto_fini(struct intel_wakeref_auto *wf)
 	intel_wakeref_auto(wf, 0);
 	INTEL_WAKEREF_BUG_ON(wf->wakeref);
 }
+
+void intel_ref_tracker_show(struct ref_tracker_dir *dir,
+			    struct drm_printer *p)
+{
+	const size_t buf_size = PAGE_SIZE;
+	char *buf, *sb, *se;
+	size_t count;
+
+	buf = kmalloc(buf_size, GFP_NOWAIT);
+	if (!buf)
+		return;
+
+	count = ref_tracker_dir_snprint(dir, buf, buf_size);
+	if (!count)
+		goto free;
+	/* printk does not like big buffers, so we split it */
+	for (sb = buf; *sb; sb = se + 1) {
+		se = strchrnul(sb, '\n');
+		drm_printf(p, "%.*s", (int)(se - sb + 1), sb);
+		if (!*se)
+			break;
+	}
+	if (count >= buf_size)
+		drm_printf(p, "\n...dropped %zd extra bytes of leak report.\n",
+			   count + 1 - buf_size);
+free:
+	kfree(buf);
+}
diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h
index ec881b097368..68aa3be48251 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.h
+++ b/drivers/gpu/drm/i915/intel_wakeref.h
@@ -7,16 +7,25 @@
 #ifndef INTEL_WAKEREF_H
 #define INTEL_WAKEREF_H
 
+#include <drm/drm_print.h>
+
 #include <linux/atomic.h>
 #include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/lockdep.h>
 #include <linux/mutex.h>
 #include <linux/refcount.h>
+#include <linux/ref_tracker.h>
+#include <linux/slab.h>
 #include <linux/stackdepot.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 
+typedef unsigned long intel_wakeref_t;
+
+#define INTEL_REFTRACK_DEAD_COUNT 16
+#define INTEL_REFTRACK_PRINT_LIMIT 16
+
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 #define INTEL_WAKEREF_BUG_ON(expr) BUG_ON(expr)
 #else
@@ -26,8 +35,6 @@
 struct intel_runtime_pm;
 struct intel_wakeref;
 
-typedef depot_stack_handle_t intel_wakeref_t;
-
 struct intel_wakeref_ops {
 	int (*get)(struct intel_wakeref *wf);
 	int (*put)(struct intel_wakeref *wf);
@@ -43,6 +50,10 @@ struct intel_wakeref {
 	const struct intel_wakeref_ops *ops;
 
 	struct delayed_work work;
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_WAKEREF)
+	struct ref_tracker_dir debug;
+#endif
 };
 
 struct intel_wakeref_lockclass {
@@ -53,11 +64,12 @@ struct intel_wakeref_lockclass {
 void __intel_wakeref_init(struct intel_wakeref *wf,
 			  struct drm_i915_private *i915,
 			  const struct intel_wakeref_ops *ops,
-			  struct intel_wakeref_lockclass *key);
-#define intel_wakeref_init(wf, i915, ops) do {				\
+			  struct intel_wakeref_lockclass *key,
+			  const char *name);
+#define intel_wakeref_init(wf, i915, ops, name) do {			\
 	static struct intel_wakeref_lockclass __key;			\
 									\
-	__intel_wakeref_init((wf), (i915), (ops), &__key);		\
+	__intel_wakeref_init((wf), (i915), (ops), &__key, name);	\
 } while (0)
 
 int __intel_wakeref_get_first(struct intel_wakeref *wf);
@@ -261,6 +273,57 @@ __intel_wakeref_defer_park(struct intel_wakeref *wf)
  */
 int intel_wakeref_wait_for_idle(struct intel_wakeref *wf);
 
+#define INTEL_WAKEREF_DEF ((intel_wakeref_t)(-1))
+
+static inline intel_wakeref_t intel_ref_tracker_alloc(struct ref_tracker_dir *dir)
+{
+	struct ref_tracker *user = NULL;
+
+	ref_tracker_alloc(dir, &user, GFP_NOWAIT);
+
+	return (intel_wakeref_t)user ?: INTEL_WAKEREF_DEF;
+}
+
+static inline void intel_ref_tracker_free(struct ref_tracker_dir *dir,
+					  intel_wakeref_t handle)
+{
+	struct ref_tracker *user;
+
+	user = (handle == INTEL_WAKEREF_DEF) ? NULL : (void *)handle;
+
+	ref_tracker_free(dir, &user);
+}
+
+void intel_ref_tracker_show(struct ref_tracker_dir *dir,
+			    struct drm_printer *p);
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_WAKEREF)
+
+static inline intel_wakeref_t intel_wakeref_track(struct intel_wakeref *wf)
+{
+	return intel_ref_tracker_alloc(&wf->debug);
+}
+
+static inline void intel_wakeref_untrack(struct intel_wakeref *wf,
+					 intel_wakeref_t handle)
+{
+	intel_ref_tracker_free(&wf->debug, handle);
+}
+
+#else
+
+static inline intel_wakeref_t intel_wakeref_track(struct intel_wakeref *wf)
+{
+	return -1;
+}
+
+static inline void intel_wakeref_untrack(struct intel_wakeref *wf,
+					 intel_wakeref_t handle)
+{
+}
+
+#endif
+
 struct intel_wakeref_auto {
 	struct drm_i915_private *i915;
 	struct timer_list timer;
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c
index dc327cf40b5a..75278e78ca90 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c
@@ -199,6 +199,9 @@ int intel_pxp_init(struct drm_i915_private *i915)
 	struct intel_gt *gt;
 	bool is_full_feature = false;
 
+	if (intel_gt_is_wedged(to_gt(i915)))
+		return -ENOTCONN;
+
 	/*
 	 * NOTE: Get the ctrl_gt before checking intel_pxp_is_supported since
 	 * we still need it if PXP's backend tee transport is needed.
@@ -303,6 +306,8 @@ static int __pxp_global_teardown_final(struct intel_pxp *pxp)
 
 	if (!pxp->arb_is_valid)
 		return 0;
+
+	drm_dbg(&pxp->ctrl_gt->i915->drm, "PXP: teardown for suspend/fini");
 	/*
 	 * To ensure synchronous and coherent session teardown completion
 	 * in response to suspend or shutdown triggers, don't use a worker.
@@ -324,6 +329,8 @@ static int __pxp_global_teardown_restart(struct intel_pxp *pxp)
 
 	if (pxp->arb_is_valid)
 		return 0;
+
+	drm_dbg(&pxp->ctrl_gt->i915->drm, "PXP: teardown for restart");
 	/*
 	 * The arb-session is currently inactive and we are doing a reset and restart
 	 * due to a runtime event. Use the worker that was designed for this.
@@ -332,8 +339,11 @@ static int __pxp_global_teardown_restart(struct intel_pxp *pxp)
 
 	timeout = intel_pxp_get_backend_timeout_ms(pxp);
 
-	if (!wait_for_completion_timeout(&pxp->termination, msecs_to_jiffies(timeout)))
+	if (!wait_for_completion_timeout(&pxp->termination, msecs_to_jiffies(timeout))) {
+		drm_dbg(&pxp->ctrl_gt->i915->drm, "PXP: restart backend timed out (%d ms)",
+			timeout);
 		return -ETIMEDOUT;
+	}
 
 	return 0;
 }
@@ -414,10 +424,12 @@ int intel_pxp_start(struct intel_pxp *pxp)
 	int ret = 0;
 
 	ret = intel_pxp_get_readiness_status(pxp, PXP_READINESS_TIMEOUT);
-	if (ret < 0)
+	if (ret < 0) {
+		drm_dbg(&pxp->ctrl_gt->i915->drm, "PXP: tried but not-avail (%d)", ret);
 		return ret;
-	else if (ret > 1)
+	} else if (ret > 1) {
 		return -EIO; /* per UAPI spec, user may retry later */
+	}
 
 	mutex_lock(&pxp->arb_mutex);
 
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c
index 91e9622c07d0..d81750b9bdda 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c
@@ -40,11 +40,12 @@ void intel_pxp_irq_handler(struct intel_pxp *pxp, u16 iir)
 		   GEN12_DISPLAY_APP_TERMINATED_PER_FW_REQ_INTERRUPT)) {
 		/* immediately mark PXP as inactive on termination */
 		intel_pxp_mark_termination_in_progress(pxp);
-		pxp->session_events |= PXP_TERMINATION_REQUEST | PXP_INVAL_REQUIRED;
+		pxp->session_events |= PXP_TERMINATION_REQUEST | PXP_INVAL_REQUIRED |
+				       PXP_EVENT_TYPE_IRQ;
 	}
 
 	if (iir & GEN12_DISPLAY_STATE_RESET_COMPLETE_INTERRUPT)
-		pxp->session_events |= PXP_TERMINATION_COMPLETE;
+		pxp->session_events |= PXP_TERMINATION_COMPLETE | PXP_EVENT_TYPE_IRQ;
 
 	if (pxp->session_events)
 		queue_work(system_unbound_wq, &pxp->session_work);
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c
index 0a3e66b0265e..091c86e03d1a 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c
@@ -137,8 +137,10 @@ void intel_pxp_terminate(struct intel_pxp *pxp, bool post_invalidation_needs_res
 static void pxp_terminate_complete(struct intel_pxp *pxp)
 {
 	/* Re-create the arb session after teardown handle complete */
-	if (fetch_and_zero(&pxp->hw_state_invalidated))
+	if (fetch_and_zero(&pxp->hw_state_invalidated)) {
+		drm_dbg(&pxp->ctrl_gt->i915->drm, "PXP: creating arb_session after invalidation");
 		pxp_create_arb_session(pxp);
+	}
 
 	complete_all(&pxp->termination);
 }
@@ -157,6 +159,8 @@ static void pxp_session_work(struct work_struct *work)
 	if (!events)
 		return;
 
+	drm_dbg(&gt->i915->drm, "PXP: processing event-flags 0x%08x", events);
+
 	if (events & PXP_INVAL_REQUIRED)
 		intel_pxp_invalidate(pxp);
 
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h
index 7e11fa8034b2..07864b584cf4 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h
@@ -124,6 +124,7 @@ struct intel_pxp {
 #define PXP_TERMINATION_REQUEST  BIT(0)
 #define PXP_TERMINATION_COMPLETE BIT(1)
 #define PXP_INVAL_REQUIRED       BIT(2)
+#define PXP_EVENT_TYPE_IRQ       BIT(3)
 };
 
 #endif /* __INTEL_PXP_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c
index 4ddc6d902752..7d41874a49c5 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c
@@ -37,8 +37,9 @@ int igt_live_test_begin(struct igt_live_test *t,
 		}
 
 		for_each_engine(engine, gt, id)
-			t->reset_engine[id] =
-			i915_reset_engine_count(&i915->gpu_error, engine);
+			t->reset_engine[i][id] =
+				i915_reset_engine_count(&i915->gpu_error,
+							engine);
 	}
 
 	t->reset_global = i915_reset_count(&i915->gpu_error);
@@ -66,14 +67,14 @@ int igt_live_test_end(struct igt_live_test *t)
 
 	for_each_gt(gt, i915, i) {
 		for_each_engine(engine, gt, id) {
-			if (t->reset_engine[id] ==
+			if (t->reset_engine[i][id] ==
 			    i915_reset_engine_count(&i915->gpu_error, engine))
 				continue;
 
 			gt_err(gt, "%s(%s): engine '%s' was reset %d times!\n",
 			       t->func, t->name, engine->name,
 			       i915_reset_engine_count(&i915->gpu_error, engine) -
-			       t->reset_engine[id]);
+			       t->reset_engine[i][id]);
 			return -EIO;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.h b/drivers/gpu/drm/i915/selftests/igt_live_test.h
index 36ed42736c52..83e3ad430922 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.h
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.h
@@ -7,6 +7,7 @@
 #ifndef IGT_LIVE_TEST_H
 #define IGT_LIVE_TEST_H
 
+#include "gt/intel_gt_defines.h" /* for I915_MAX_GT */
 #include "gt/intel_engine.h" /* for I915_NUM_ENGINES */
 
 struct drm_i915_private;
@@ -17,7 +18,7 @@ struct igt_live_test {
 	const char *name;
 
 	unsigned int reset_global;
-	unsigned int reset_engine[I915_NUM_ENGINES];
+	unsigned int reset_engine[I915_MAX_GT][I915_NUM_ENGINES];
 };
 
 /*
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 1c9ea6ab3eb9..fcf1849aa47c 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -738,7 +738,8 @@
 	INTEL_DG2_G12_IDS(info)
 
 #define INTEL_ATS_M150_IDS(info) \
-	INTEL_VGA_DEVICE(0x56C0, info)
+	INTEL_VGA_DEVICE(0x56C0, info), \
+	INTEL_VGA_DEVICE(0x56C2, info)
 
 #define INTEL_ATS_M75_IDS(info) \
 	INTEL_VGA_DEVICE(0x56C1, info)