Merge tag 'drm-intel-gt-next-2021-05-28' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:
- Add reworked uAPI for DG1 behind CONFIG_BROKEN (Matt A, Abdiel)

Driver Changes:

- Fix for Gitlab issues #3293 and #3450:
  Avoid kernel crash on older L-shape memory machines

- Add Wa_14010733141 (VDBox SFC reset) for Gen11+ (Aditya)
- Fix crash in auto_retire active retire callback due to
  misalignment (Stephane)
- Fix overlay active retire callback alignment (Tvrtko)
- Eliminate need to align active retire callbacks (Matt A, Ville,
  Daniel)
- Program FF_MODE2 tuning value for all Gen12 platforms (Caz)
- Add Wa_14011060649 for TGL,RKL,DG1 and ADLS (Swathi)
- Create stolen memory region from local memory on DG1 (CQ)
- Place PD in LMEM on dGFX (Matt A)
- Use WC when default state object is allocated in LMEM (Venkata)
- Determine the coherent map type based on object location (Venkata)
- Use lmem physical addresses for fb_mmap() on discrete (Mohammed)
- Bypass aperture on fbdev when LMEM is available (Anusha)
- Return error value when displayable BO not in LMEM for dGFX (Mohammed)
- Do release kernel context if breadcrumb measure fails (Janusz)
- Hide modparams for compiled-out features (Tvrtko)
- Apply Wa_22010271021 for all Gen11 platforms (Caz)
- Fix unlikely ref count race in arming the watchdog timer (Tvrtko)
- Check actual RC6 enable status in PMU (Tvrtko)
- Fix a double free in gen8_preallocate_top_level_pdp (Lv)
- Use trylock in shrinker for GGTT on BSW VT-d and BXT (Maarten)
- Remove erroneous i915_is_ggtt check for
  I915_GEM_OBJECT_UNBIND_VM_TRYLOCK (Maarten)

- Convert uAPI headers to real kerneldoc (Matt A)
- Clean up kerneldoc warnings headers (Matt A, Maarten)
- Fail driver if LMEM training failed (Matt R)
- Avoid div-by-zero on Gen2 (Ville)
- Read C0DRB3/C1DRB3 as 16 bits again and add _BW suffix (Ville)
- Remove reference to struct drm_device.pdev (Thomas)
- Increase separation between GuC and execlists code (Chris, Matt B)

- Use might_alloc() (Bernard)
- Split DGFX_FEATURES from GEN12_FEATURES (Lucas)
- Deduplicate Wa_22010271021 programming on (Jose)
- Drop duplicate WaDisable4x2SubspanOptimization:hsw (Tvrtko)
- Selftest improvements (Chris, Hsin-Yi, Tvrtko)
- Shuffle around init_memory_region for stolen (Matt)
- Typo fixes (wengjianfeng)

[airlied: fix conflict with fixes in i915_active.c]
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YLCbBR22BsQ/dpJB@jlahtine-mobl.ger.corp.intel.com

85 files changed, 1504 insertions, 534 deletions

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 384ff0bb6e19..422b59ebf6dc 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -11660,11 +11660,20 @@ intel_user_framebuffer_create(struct drm_device *dev,
 	struct drm_framebuffer *fb;
 	struct drm_i915_gem_object *obj;
 	struct drm_mode_fb_cmd2 mode_cmd = *user_mode_cmd;
+	struct drm_i915_private *i915;
 
 	obj = i915_gem_object_lookup(filp, mode_cmd.handles[0]);
 	if (!obj)
 		return ERR_PTR(-ENOENT);
 
+	/* object is backed with LMEM for discrete */
+	i915 = to_i915(obj->base.dev);
+	if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj)) {
+		/* object is "remote", not in local memory */
+		i915_gem_object_put(obj);
+		return ERR_PTR(-EREMOTE);
+	}
+
 	fb = intel_framebuffer_create(obj, &mode_cmd);
 	i915_gem_object_put(obj);
 
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index ccd00e65a5fe..4af40229f5ec 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -41,6 +41,8 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_fourcc.h>
 
+#include "gem/i915_gem_lmem.h"
+
 #include "i915_drv.h"
 #include "intel_display_types.h"
 #include "intel_fbdev.h"
@@ -137,14 +139,22 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 	size = mode_cmd.pitches[0] * mode_cmd.height;
 	size = PAGE_ALIGN(size);
 
-	/* If the FB is too big, just don't use it since fbdev is not very
-	 * important and we should probably use that space with FBC or other
-	 * features. */
 	obj = ERR_PTR(-ENODEV);
-	if (size * 2 < dev_priv->stolen_usable_size)
-		obj = i915_gem_object_create_stolen(dev_priv, size);
-	if (IS_ERR(obj))
-		obj = i915_gem_object_create_shmem(dev_priv, size);
+	if (HAS_LMEM(dev_priv)) {
+		obj = i915_gem_object_create_lmem(dev_priv, size,
+						  I915_BO_ALLOC_CONTIGUOUS);
+	} else {
+		/*
+		 * If the FB is too big, just don't use it since fbdev is not very
+		 * important and we should probably use that space with FBC or other
+		 * features.
+		 */
+		if (size * 2 < dev_priv->stolen_usable_size)
+			obj = i915_gem_object_create_stolen(dev_priv, size);
+		if (IS_ERR(obj))
+			obj = i915_gem_object_create_shmem(dev_priv, size);
+	}
+
 	if (IS_ERR(obj)) {
 		drm_err(&dev_priv->drm, "failed to allocate framebuffer\n");
 		return PTR_ERR(obj);
@@ -178,6 +188,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	unsigned long flags = 0;
 	bool prealloc = false;
 	void __iomem *vaddr;
+	struct drm_i915_gem_object *obj;
 	int ret;
 
 	if (intel_fb &&
@@ -232,13 +243,27 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->fbops = &intelfb_ops;
 
 	/* setup aperture base/size for vesafb takeover */
-	info->apertures->ranges[0].base = ggtt->gmadr.start;
-	info->apertures->ranges[0].size = ggtt->mappable_end;
+	obj = intel_fb_obj(&intel_fb->base);
+	if (i915_gem_object_is_lmem(obj)) {
+		struct intel_memory_region *mem = obj->mm.region;
+
+		info->apertures->ranges[0].base = mem->io_start;
+		info->apertures->ranges[0].size = mem->total;
+
+		/* Use fbdev's framebuffer from lmem for discrete */
+		info->fix.smem_start =
+			(unsigned long)(mem->io_start +
+					i915_gem_object_get_dma_address(obj, 0));
+		info->fix.smem_len = obj->base.size;
+	} else {
+		info->apertures->ranges[0].base = ggtt->gmadr.start;
+		info->apertures->ranges[0].size = ggtt->mappable_end;
 
-	/* Our framebuffer is the entirety of fbdev's system memory */
-	info->fix.smem_start =
-		(unsigned long)(ggtt->gmadr.start + vma->node.start);
-	info->fix.smem_len = vma->node.size;
+		/* Our framebuffer is the entirety of fbdev's system memory */
+		info->fix.smem_start =
+			(unsigned long)(ggtt->gmadr.start + vma->node.start);
+		info->fix.smem_len = vma->node.size;
+	}
 
 	vaddr = i915_vma_pin_iomap(vma);
 	if (IS_ERR(vaddr)) {
diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
index 8161d49e78ba..8e75debcce1a 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
@@ -211,7 +211,6 @@ static int frontbuffer_active(struct i915_active *ref)
 	return 0;
 }
 
-__i915_active_call
 static void frontbuffer_retire(struct i915_active *ref)
 {
 	struct intel_frontbuffer *front =
@@ -266,7 +265,8 @@ intel_frontbuffer_get(struct drm_i915_gem_object *obj)
 	atomic_set(&front->bits, 0);
 	i915_active_init(&front->write,
 			 frontbuffer_active,
-			 i915_active_may_sleep(frontbuffer_retire));
+			 frontbuffer_retire,
+			 I915_ACTIVE_RETIRE_SLEEPS);
 
 	spin_lock(&i915->fb_tracking.lock);
 	if (rcu_access_pointer(obj->frontbuffer)) {
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 46cba12be888..7e3f5c6ca484 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -384,8 +384,7 @@ static void intel_overlay_off_tail(struct intel_overlay *overlay)
 		i830_overlay_clock_gating(dev_priv, true);
 }
 
-__i915_active_call static void
-intel_overlay_last_flip_retire(struct i915_active *active)
+static void intel_overlay_last_flip_retire(struct i915_active *active)
 {
 	struct intel_overlay *overlay =
 		container_of(active, typeof(*overlay), last_flip);
@@ -1402,7 +1401,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv)
 	overlay->saturation = 146;
 
 	i915_active_init(&overlay->last_flip,
-			 NULL, intel_overlay_last_flip_retire);
+			 NULL, intel_overlay_last_flip_retire, 0);
 
 	ret = get_registers(overlay, OVERLAY_NEEDS_PHYSICAL(dev_priv));
 	if (ret)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index fd8ee52e17a4..188dee13e017 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1046,7 +1046,6 @@ struct context_barrier_task {
 	void *data;
 };
 
-__i915_active_call
 static void cb_retire(struct i915_active *base)
 {
 	struct context_barrier_task *cb = container_of(base, typeof(*cb), base);
@@ -1080,7 +1079,7 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 	if (!cb)
 		return -ENOMEM;
 
-	i915_active_init(&cb->base, NULL, cb_retire);
+	i915_active_init(&cb->base, NULL, cb_retire, 0);
 	err = i915_active_acquire(&cb->base);
 	if (err) {
 		kfree(cb);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c
index 45d60e3d98e3..548ddf39d853 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_create.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c
@@ -4,44 +4,102 @@
  */
 
 #include "gem/i915_gem_ioctls.h"
+#include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
 
 #include "i915_drv.h"
+#include "i915_trace.h"
+#include "i915_user_extensions.h"
+
+static u32 object_max_page_size(struct drm_i915_gem_object *obj)
+{
+	u32 max_page_size = 0;
+	int i;
+
+	for (i = 0; i < obj->mm.n_placements; i++) {
+		struct intel_memory_region *mr = obj->mm.placements[i];
+
+		GEM_BUG_ON(!is_power_of_2(mr->min_page_size));
+		max_page_size = max_t(u32, max_page_size, mr->min_page_size);
+	}
+
+	GEM_BUG_ON(!max_page_size);
+	return max_page_size;
+}
+
+static void object_set_placements(struct drm_i915_gem_object *obj,
+				  struct intel_memory_region **placements,
+				  unsigned int n_placements)
+{
+	GEM_BUG_ON(!n_placements);
+
+	/*
+	 * For the common case of one memory region, skip storing an
+	 * allocated array and just point at the region directly.
+	 */
+	if (n_placements == 1) {
+		struct intel_memory_region *mr = placements[0];
+		struct drm_i915_private *i915 = mr->i915;
+
+		obj->mm.placements = &i915->mm.regions[mr->id];
+		obj->mm.n_placements = 1;
+	} else {
+		obj->mm.placements = placements;
+		obj->mm.n_placements = n_placements;
+	}
+}
+
+static int i915_gem_publish(struct drm_i915_gem_object *obj,
+			    struct drm_file *file,
+			    u64 *size_p,
+			    u32 *handle_p)
+{
+	u64 size = obj->base.size;
+	int ret;
+
+	ret = drm_gem_handle_create(file, &obj->base, handle_p);
+	/* drop reference from allocate - handle holds it now */
+	i915_gem_object_put(obj);
+	if (ret)
+		return ret;
+
+	*size_p = size;
+	return 0;
+}
 
 static int
-i915_gem_create(struct drm_file *file,
-		struct intel_memory_region *mr,
-		u64 *size_p,
-		u32 *handle_p)
+i915_gem_setup(struct drm_i915_gem_object *obj, u64 size)
 {
-	struct drm_i915_gem_object *obj;
-	u32 handle;
-	u64 size;
+	struct intel_memory_region *mr = obj->mm.placements[0];
+	unsigned int flags;
 	int ret;
 
-	GEM_BUG_ON(!is_power_of_2(mr->min_page_size));
-	size = round_up(*size_p, mr->min_page_size);
+	size = round_up(size, object_max_page_size(obj));
 	if (size == 0)
 		return -EINVAL;
 
 	/* For most of the ABI (e.g. mmap) we think in system pages */
 	GEM_BUG_ON(!IS_ALIGNED(size, PAGE_SIZE));
 
-	/* Allocate the new object */
-	obj = i915_gem_object_create_region(mr, size, 0);
-	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+	if (i915_gem_object_size_2big(size))
+		return -E2BIG;
 
-	GEM_BUG_ON(size != obj->base.size);
+	/*
+	 * For now resort to CPU based clearing for device local-memory, in the
+	 * near future this will use the blitter engine for accelerated, GPU
+	 * based clearing.
+	 */
+	flags = 0;
+	if (mr->type == INTEL_MEMORY_LOCAL)
+		flags = I915_BO_ALLOC_CPU_CLEAR;
 
-	ret = drm_gem_handle_create(file, &obj->base, &handle);
-	/* drop reference from allocate - handle holds it now */
-	i915_gem_object_put(obj);
+	ret = mr->ops->init_object(mr, obj, size, flags);
 	if (ret)
 		return ret;
 
-	*handle_p = handle;
-	*size_p = size;
+	GEM_BUG_ON(size != obj->base.size);
+
+	trace_i915_gem_object_create(obj);
 	return 0;
 }
 
@@ -50,9 +108,12 @@ i915_gem_dumb_create(struct drm_file *file,
 		     struct drm_device *dev,
 		     struct drm_mode_create_dumb *args)
 {
+	struct drm_i915_gem_object *obj;
+	struct intel_memory_region *mr;
 	enum intel_memory_type mem_type;
 	int cpp = DIV_ROUND_UP(args->bpp, 8);
 	u32 format;
+	int ret;
 
 	switch (cpp) {
 	case 1:
@@ -85,10 +146,22 @@ i915_gem_dumb_create(struct drm_file *file,
 	if (HAS_LMEM(to_i915(dev)))
 		mem_type = INTEL_MEMORY_LOCAL;
 
-	return i915_gem_create(file,
-			       intel_memory_region_by_type(to_i915(dev),
-							   mem_type),
-			       &args->size, &args->handle);
+	obj = i915_gem_object_alloc();
+	if (!obj)
+		return -ENOMEM;
+
+	mr = intel_memory_region_by_type(to_i915(dev), mem_type);
+	object_set_placements(obj, &mr, 1);
+
+	ret = i915_gem_setup(obj, args->size);
+	if (ret)
+		goto object_free;
+
+	return i915_gem_publish(obj, file, &args->size, &args->handle);
+
+object_free:
+	i915_gem_object_free(obj);
+	return ret;
 }
 
 /**
@@ -103,11 +176,229 @@ i915_gem_create_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_create *args = data;
+	struct drm_i915_gem_object *obj;
+	struct intel_memory_region *mr;
+	int ret;
 
 	i915_gem_flush_free_objects(i915);
 
-	return i915_gem_create(file,
-			       intel_memory_region_by_type(i915,
-							   INTEL_MEMORY_SYSTEM),
-			       &args->size, &args->handle);
+	obj = i915_gem_object_alloc();
+	if (!obj)
+		return -ENOMEM;
+
+	mr = intel_memory_region_by_type(i915, INTEL_MEMORY_SYSTEM);
+	object_set_placements(obj, &mr, 1);
+
+	ret = i915_gem_setup(obj, args->size);
+	if (ret)
+		goto object_free;
+
+	return i915_gem_publish(obj, file, &args->size, &args->handle);
+
+object_free:
+	i915_gem_object_free(obj);
+	return ret;
+}
+
+struct create_ext {
+	struct drm_i915_private *i915;
+	struct drm_i915_gem_object *vanilla_object;
+};
+
+static void repr_placements(char *buf, size_t size,
+			    struct intel_memory_region **placements,
+			    int n_placements)
+{
+	int i;
+
+	buf[0] = '\0';
+
+	for (i = 0; i < n_placements; i++) {
+		struct intel_memory_region *mr = placements[i];
+		int r;
+
+		r = snprintf(buf, size, "\n  %s -> { class: %d, inst: %d }",
+			     mr->name, mr->type, mr->instance);
+		if (r >= size)
+			return;
+
+		buf += r;
+		size -= r;
+	}
+}
+
+static int set_placements(struct drm_i915_gem_create_ext_memory_regions *args,
+			  struct create_ext *ext_data)
+{
+	struct drm_i915_private *i915 = ext_data->i915;
+	struct drm_i915_gem_memory_class_instance __user *uregions =
+		u64_to_user_ptr(args->regions);
+	struct drm_i915_gem_object *obj = ext_data->vanilla_object;
+	struct intel_memory_region **placements;
+	u32 mask;
+	int i, ret = 0;
+
+	if (args->pad) {
+		drm_dbg(&i915->drm, "pad should be zero\n");
+		ret = -EINVAL;
+	}
+
+	if (!args->num_regions) {
+		drm_dbg(&i915->drm, "num_regions is zero\n");
+		ret = -EINVAL;
+	}
+
+	if (args->num_regions > ARRAY_SIZE(i915->mm.regions)) {
+		drm_dbg(&i915->drm, "num_regions is too large\n");
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	placements = kmalloc_array(args->num_regions,
+				   sizeof(struct intel_memory_region *),
+				   GFP_KERNEL);
+	if (!placements)
+		return -ENOMEM;
+
+	mask = 0;
+	for (i = 0; i < args->num_regions; i++) {
+		struct drm_i915_gem_memory_class_instance region;
+		struct intel_memory_region *mr;
+
+		if (copy_from_user(&region, uregions, sizeof(region))) {
+			ret = -EFAULT;
+			goto out_free;
+		}
+
+		mr = intel_memory_region_lookup(i915,
+						region.memory_class,
+						region.memory_instance);
+		if (!mr || mr->private) {
+			drm_dbg(&i915->drm, "Device is missing region { class: %d, inst: %d } at index = %d\n",
+				region.memory_class, region.memory_instance, i);
+			ret = -EINVAL;
+			goto out_dump;
+		}
+
+		if (mask & BIT(mr->id)) {
+			drm_dbg(&i915->drm, "Found duplicate placement %s -> { class: %d, inst: %d } at index = %d\n",
+				mr->name, region.memory_class,
+				region.memory_instance, i);
+			ret = -EINVAL;
+			goto out_dump;
+		}
+
+		placements[i] = mr;
+		mask |= BIT(mr->id);
+
+		++uregions;
+	}
+
+	if (obj->mm.placements) {
+		ret = -EINVAL;
+		goto out_dump;
+	}
+
+	object_set_placements(obj, placements, args->num_regions);
+	if (args->num_regions == 1)
+		kfree(placements);
+
+	return 0;
+
+out_dump:
+	if (1) {
+		char buf[256];
+
+		if (obj->mm.placements) {
+			repr_placements(buf,
+					sizeof(buf),
+					obj->mm.placements,
+					obj->mm.n_placements);
+			drm_dbg(&i915->drm,
+				"Placements were already set in previous EXT. Existing placements: %s\n",
+				buf);
+		}
+
+		repr_placements(buf, sizeof(buf), placements, i);
+		drm_dbg(&i915->drm, "New placements(so far validated): %s\n", buf);
+	}
+
+out_free:
+	kfree(placements);
+	return ret;
+}
+
+static int ext_set_placements(struct i915_user_extension __user *base,
+			      void *data)
+{
+	struct drm_i915_gem_create_ext_memory_regions ext;
+
+	if (!IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM))
+		return -ENODEV;
+
+	if (copy_from_user(&ext, base, sizeof(ext)))
+		return -EFAULT;
+
+	return set_placements(&ext, data);
+}
+
+static const i915_user_extension_fn create_extensions[] = {
+	[I915_GEM_CREATE_EXT_MEMORY_REGIONS] = ext_set_placements,
+};
+
+/**
+ * Creates a new mm object and returns a handle to it.
+ * @dev: drm device pointer
+ * @data: ioctl data blob
+ * @file: drm file pointer
+ */
+int
+i915_gem_create_ext_ioctl(struct drm_device *dev, void *data,
+			  struct drm_file *file)
+{
+	struct drm_i915_private *i915 = to_i915(dev);
+	struct drm_i915_gem_create_ext *args = data;
+	struct create_ext ext_data = { .i915 = i915 };
+	struct intel_memory_region **placements_ext;
+	struct drm_i915_gem_object *obj;
+	int ret;
+
+	if (args->flags)
+		return -EINVAL;
+
+	i915_gem_flush_free_objects(i915);
+
+	obj = i915_gem_object_alloc();
+	if (!obj)
+		return -ENOMEM;
+
+	ext_data.vanilla_object = obj;
+	ret = i915_user_extensions(u64_to_user_ptr(args->extensions),
+				   create_extensions,
+				   ARRAY_SIZE(create_extensions),
+				   &ext_data);
+	placements_ext = obj->mm.placements;
+	if (ret)
+		goto object_free;
+
+	if (!placements_ext) {
+		struct intel_memory_region *mr =
+			intel_memory_region_by_type(i915, INTEL_MEMORY_SYSTEM);
+
+		object_set_placements(obj, &mr, 1);
+	}
+
+	ret = i915_gem_setup(obj, args->size);
+	if (ret)
+		goto object_free;
+
+	return i915_gem_publish(obj, file, &args->size, &args->handle);
+
+object_free:
+	if (obj->mm.n_placements > 1)
+		kfree(placements_ext);
+	i915_gem_object_free(obj);
+	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h b/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h
index 7fd22f3efbef..28d6526e32ab 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h
@@ -14,6 +14,8 @@ int i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
 int i915_gem_create_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *file);
+int i915_gem_create_ext_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file);
 int i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file);
 int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
index ce1c83c13d05..f44bdd08f7cb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
@@ -17,9 +17,27 @@ const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = {
 	.release = i915_gem_object_release_memory_region,
 };
 
+void __iomem *
+i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
+			    unsigned long n,
+			    unsigned long size)
+{
+	resource_size_t offset;
+
+	GEM_BUG_ON(!i915_gem_object_is_contiguous(obj));
+
+	offset = i915_gem_object_get_dma_address(obj, n);
+	offset -= obj->mm.region->region.start;
+
+	return io_mapping_map_wc(&obj->mm.region->iomap, offset, size);
+}
+
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
 {
-	return obj->ops == &i915_gem_lmem_obj_ops;
+	struct intel_memory_region *mr = obj->mm.region;
+
+	return mr && (mr->type == INTEL_MEMORY_LOCAL ||
+		      mr->type == INTEL_MEMORY_STOLEN_LOCAL);
 }
 
 struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
index 036d53c01de9..fac6bc5a5ebb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
@@ -14,6 +14,11 @@ struct intel_memory_region;
 
 extern const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops;
 
+void __iomem *
+i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
+			    unsigned long n,
+			    unsigned long size);
+
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
 
 struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index ea74cbca95be..28144410df86 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -249,6 +249,9 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 		if (obj->ops->release)
 			obj->ops->release(obj);
 
+		if (obj->mm.n_placements > 1)
+			kfree(obj->mm.placements);
+
 		/* But keep the pointer alive for RCU-protected lookups */
 		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
 		cond_resched();
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 8e485cb3343c..0727d0c76aa0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -172,11 +172,13 @@ struct drm_i915_gem_object {
 #define I915_BO_ALLOC_CONTIGUOUS BIT(0)
 #define I915_BO_ALLOC_VOLATILE   BIT(1)
 #define I915_BO_ALLOC_STRUCT_PAGE BIT(2)
+#define I915_BO_ALLOC_CPU_CLEAR  BIT(3)
 #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \
 			     I915_BO_ALLOC_VOLATILE | \
-			     I915_BO_ALLOC_STRUCT_PAGE)
-#define I915_BO_READONLY         BIT(3)
-#define I915_TILING_QUIRK_BIT    4 /* unknown swizzling; do not release! */
+			     I915_BO_ALLOC_STRUCT_PAGE | \
+			     I915_BO_ALLOC_CPU_CLEAR)
+#define I915_BO_READONLY         BIT(4)
+#define I915_TILING_QUIRK_BIT    5 /* unknown swizzling; do not release! */
 
 	/*
 	 * Is the object to be mapped as read-only to the GPU
@@ -220,6 +222,12 @@ struct drm_i915_gem_object {
 		atomic_t shrink_pin;
 
 		/**
+		 * Priority list of potential placements for this object.
+		 */
+		struct intel_memory_region **placements;
+		int n_placements;
+
+		/**
 		 * Memory region for this object.
 		 */
 		struct intel_memory_region *region;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
index 6a84fb6dde24..ce8fcfc54079 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -95,6 +95,28 @@ i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
 	sg_mark_end(sg);
 	i915_sg_trim(st);
 
+	/* Intended for kernel internal use only */
+	if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) {
+		struct scatterlist *sg;
+		unsigned long i;
+
+		for_each_sg(st->sgl, sg, st->nents, i) {
+			unsigned int length;
+			void __iomem *vaddr;
+			dma_addr_t daddr;
+
+			daddr = sg_dma_address(sg);
+			daddr -= mem->region.start;
+			length = sg_dma_len(sg);
+
+			vaddr = io_mapping_map_wc(&mem->iomap, daddr, length);
+			memset64((void __force *)vaddr, 0, length / sizeof(u64));
+			io_mapping_unmap(vaddr);
+		}
+
+		wmb();
+	}
+
 	__i915_gem_object_set_pages(obj, st, sg_page_sizes);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index 4f9c8d3021ab..f4fb68e8955a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -38,15 +38,17 @@ static bool can_release_pages(struct drm_i915_gem_object *obj)
 }
 
 static bool unsafe_drop_pages(struct drm_i915_gem_object *obj,
-			      unsigned long shrink)
+			      unsigned long shrink, bool trylock_vm)
 {
 	unsigned long flags;
 
 	flags = 0;
 	if (shrink & I915_SHRINK_ACTIVE)
-		flags = I915_GEM_OBJECT_UNBIND_ACTIVE;
+		flags |= I915_GEM_OBJECT_UNBIND_ACTIVE;
 	if (!(shrink & I915_SHRINK_BOUND))
-		flags = I915_GEM_OBJECT_UNBIND_TEST;
+		flags |= I915_GEM_OBJECT_UNBIND_TEST;
+	if (trylock_vm)
+		flags |= I915_GEM_OBJECT_UNBIND_VM_TRYLOCK;
 
 	if (i915_gem_object_unbind(obj, flags) == 0)
 		return true;
@@ -117,6 +119,9 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww,
 	unsigned long scanned = 0;
 	int err;
 
+	/* CHV + VTD workaround use stop_machine(); need to trylock vm->mutex */
+	bool trylock_vm = !ww && intel_vm_no_concurrent_access_wa(i915);
+
 	trace_i915_gem_shrink(i915, target, shrink);
 
 	/*
@@ -204,7 +209,7 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww,
 			spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
 
 			err = 0;
-			if (unsafe_drop_pages(obj, shrink)) {
+			if (unsafe_drop_pages(obj, shrink, trylock_vm)) {
 				/* May arrive from get_pages on another bo */
 				if (!ww) {
 					if (!i915_gem_object_trylock(obj))
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index b0597de206de..b5553fc3ac4d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -10,6 +10,7 @@
 #include <drm/drm_mm.h>
 #include <drm/i915_drm.h>
 
+#include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
 #include "i915_drv.h"
 #include "i915_gem_stolen.h"
@@ -122,6 +123,14 @@ static int i915_adjust_stolen(struct drm_i915_private *i915,
 	}
 
 	/*
+	 * With stolen lmem, we don't need to check if the address range
+	 * overlaps with the non-stolen system memory range, since lmem is local
+	 * to the gpu.
+	 */
+	if (HAS_LMEM(i915))
+		return 0;
+
+	/*
 	 * Verify that nothing else uses this physical address. Stolen
 	 * memory should be reserved by the BIOS and hidden from the
 	 * kernel. So if the region is already marked as busy, something
@@ -374,8 +383,9 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915,
 	}
 }
 
-static int i915_gem_init_stolen(struct drm_i915_private *i915)
+static int i915_gem_init_stolen(struct intel_memory_region *mem)
 {
+	struct drm_i915_private *i915 = mem->i915;
 	struct intel_uncore *uncore = &i915->uncore;
 	resource_size_t reserved_base, stolen_top;
 	resource_size_t reserved_total, reserved_size;
@@ -396,10 +406,10 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915)
 		return 0;
 	}
 
-	if (resource_size(&intel_graphics_stolen_res) == 0)
+	if (resource_size(&mem->region) == 0)
 		return 0;
 
-	i915->dsm = intel_graphics_stolen_res;
+	i915->dsm = mem->region;
 
 	if (i915_adjust_stolen(i915, &i915->dsm))
 		return 0;
@@ -627,10 +637,17 @@ static int __i915_gem_object_create_stolen(struct intel_memory_region *mem,
 {
 	static struct lock_class_key lock_class;
 	unsigned int cache_level;
+	unsigned int flags;
 	int err;
 
+	/*
+	 * Stolen objects are always physically contiguous since we just
+	 * allocate one big block underneath using the drm_mm range allocator.
+	 */
+	flags = I915_BO_ALLOC_CONTIGUOUS;
+
 	drm_gem_private_object_init(&mem->i915->drm, &obj->base, stolen->size);
-	i915_gem_object_init(obj, &i915_gem_object_stolen_ops, &lock_class, 0);
+	i915_gem_object_init(obj, &i915_gem_object_stolen_ops, &lock_class, flags);
 
 	obj->stolen = stolen;
 	obj->read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
@@ -640,9 +657,11 @@ static int __i915_gem_object_create_stolen(struct intel_memory_region *mem,
 	if (WARN_ON(!i915_gem_object_trylock(obj)))
 		return -EBUSY;
 
+	i915_gem_object_init_memory_region(obj, mem);
+
 	err = i915_gem_object_pin_pages(obj);
-	if (!err)
-		i915_gem_object_init_memory_region(obj, mem);
+	if (err)
+		i915_gem_object_release_memory_region(obj);
 	i915_gem_object_unlock(obj);
 
 	return err;
@@ -667,7 +686,8 @@ static int _i915_gem_object_stolen_init(struct intel_memory_region *mem,
 	if (!stolen)
 		return -ENOMEM;
 
-	ret = i915_gem_stolen_insert_node(i915, stolen, size, 4096);
+	ret = i915_gem_stolen_insert_node(i915, stolen, size,
+					  mem->min_page_size);
 	if (ret)
 		goto err_free;
 
@@ -688,39 +708,126 @@ struct drm_i915_gem_object *
 i915_gem_object_create_stolen(struct drm_i915_private *i915,
 			      resource_size_t size)
 {
-	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_STOLEN_SMEM],
-					     size, I915_BO_ALLOC_CONTIGUOUS);
+	return i915_gem_object_create_region(i915->mm.stolen_region, size, 0);
 }
 
-static int init_stolen(struct intel_memory_region *mem)
+static int init_stolen_smem(struct intel_memory_region *mem)
 {
-	intel_memory_region_set_name(mem, "stolen");
-
 	/*
 	 * Initialise stolen early so that we may reserve preallocated
 	 * objects for the BIOS to KMS transition.
 	 */
-	return i915_gem_init_stolen(mem->i915);
+	return i915_gem_init_stolen(mem);
 }
 
-static void release_stolen(struct intel_memory_region *mem)
+static void release_stolen_smem(struct intel_memory_region *mem)
 {
 	i915_gem_cleanup_stolen(mem->i915);
 }
 
-static const struct intel_memory_region_ops i915_region_stolen_ops = {
-	.init = init_stolen,
-	.release = release_stolen,
+static const struct intel_memory_region_ops i915_region_stolen_smem_ops = {
+	.init = init_stolen_smem,
+	.release = release_stolen_smem,
 	.init_object = _i915_gem_object_stolen_init,
 };
 
-struct intel_memory_region *i915_gem_stolen_setup(struct drm_i915_private *i915)
+static int init_stolen_lmem(struct intel_memory_region *mem)
 {
-	return intel_memory_region_create(i915,
-					  intel_graphics_stolen_res.start,
-					  resource_size(&intel_graphics_stolen_res),
-					  PAGE_SIZE, 0,
-					  &i915_region_stolen_ops);
+	int err;
+
+	if (GEM_WARN_ON(resource_size(&mem->region) == 0))
+		return -ENODEV;
+
+	if (!io_mapping_init_wc(&mem->iomap,
+				mem->io_start,
+				resource_size(&mem->region)))
+		return -EIO;
+
+	/*
+	 * TODO: For stolen lmem we mostly just care about populating the dsm
+	 * related bits and setting up the drm_mm allocator for the range.
+	 * Perhaps split up i915_gem_init_stolen() for this.
+	 */
+	err = i915_gem_init_stolen(mem);
+	if (err)
+		goto err_fini;
+
+	return 0;
+
+err_fini:
+	io_mapping_fini(&mem->iomap);
+	return err;
+}
+
+static void release_stolen_lmem(struct intel_memory_region *mem)
+{
+	io_mapping_fini(&mem->iomap);
+	i915_gem_cleanup_stolen(mem->i915);
+}
+
+static const struct intel_memory_region_ops i915_region_stolen_lmem_ops = {
+	.init = init_stolen_lmem,
+	.release = release_stolen_lmem,
+	.init_object = _i915_gem_object_stolen_init,
+};
+
+struct intel_memory_region *
+i915_gem_stolen_lmem_setup(struct drm_i915_private *i915)
+{
+	struct intel_uncore *uncore = &i915->uncore;
+	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+	struct intel_memory_region *mem;
+	resource_size_t io_start;
+	resource_size_t lmem_size;
+	u64 lmem_base;
+
+	lmem_base = intel_uncore_read64(uncore, GEN12_DSMBASE);
+	if (GEM_WARN_ON(lmem_base >= pci_resource_len(pdev, 2)))
+		return ERR_PTR(-ENODEV);
+
+	lmem_size = pci_resource_len(pdev, 2) - lmem_base;
+	io_start = pci_resource_start(pdev, 2) + lmem_base;
+
+	mem = intel_memory_region_create(i915, lmem_base, lmem_size,
+					 I915_GTT_PAGE_SIZE_4K, io_start,
+					 &i915_region_stolen_lmem_ops);
+	if (IS_ERR(mem))
+		return mem;
+
+	/*
+	 * TODO: consider creating common helper to just print all the
+	 * interesting stuff from intel_memory_region, which we can use for all
+	 * our probed regions.
+	 */
+
+	drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n",
+		&mem->io_start);
+
+	intel_memory_region_set_name(mem, "stolen-local");
+
+	mem->private = true;
+
+	return mem;
+}
+
+struct intel_memory_region*
+i915_gem_stolen_smem_setup(struct drm_i915_private *i915)
+{
+	struct intel_memory_region *mem;
+
+	mem = intel_memory_region_create(i915,
+					 intel_graphics_stolen_res.start,
+					 resource_size(&intel_graphics_stolen_res),
+					 PAGE_SIZE, 0,
+					 &i915_region_stolen_smem_ops);
+	if (IS_ERR(mem))
+		return mem;
+
+	intel_memory_region_set_name(mem, "stolen-system");
+
+	mem->private = true;
+
+	return mem;
 }
 
 struct drm_i915_gem_object *
@@ -728,7 +835,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *i915,
 					       resource_size_t stolen_offset,
 					       resource_size_t size)
 {
-	struct intel_memory_region *mem = i915->mm.regions[INTEL_REGION_STOLEN_SMEM];
+	struct intel_memory_region *mem = i915->mm.stolen_region;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
 	int ret;
@@ -742,8 +849,8 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *i915,
 
 	/* KISS and expect everything to be page-aligned */
 	if (GEM_WARN_ON(size == 0) ||
-	    GEM_WARN_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE)) ||
-	    GEM_WARN_ON(!IS_ALIGNED(stolen_offset, I915_GTT_MIN_ALIGNMENT)))
+	    GEM_WARN_ON(!IS_ALIGNED(size, mem->min_page_size)) ||
+	    GEM_WARN_ON(!IS_ALIGNED(stolen_offset, mem->min_page_size)))
 		return ERR_PTR(-EINVAL);
 
 	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h
index b03489706796..2bec6c367b9c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h
@@ -21,7 +21,8 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
 					 u64 end);
 void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv,
 				 struct drm_mm_node *node);
-struct intel_memory_region *i915_gem_stolen_setup(struct drm_i915_private *i915);
+struct intel_memory_region *i915_gem_stolen_smem_setup(struct drm_i915_private *i915);
+struct intel_memory_region *i915_gem_stolen_lmem_setup(struct drm_i915_private *i915);
 struct drm_i915_gem_object *
 i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 			      resource_size_t size);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 5fef592390cb..ce70d0a3afb2 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -1740,7 +1740,6 @@ out:
 static int check_scratch_page(struct i915_gem_context *ctx, u32 *out)
 {
 	struct i915_address_space *vm;
-	struct page *page;
 	u32 *vaddr;
 	int err = 0;
 
@@ -1748,24 +1747,18 @@ static int check_scratch_page(struct i915_gem_context *ctx, u32 *out)
 	if (!vm)
 		return -ENODEV;
 
-	page = __px_page(vm->scratch[0]);
-	if (!page) {
+	if (!vm->scratch[0]) {
 		pr_err("No scratch page!\n");
 		return -EINVAL;
 	}
 
-	vaddr = kmap(page);
-	if (!vaddr) {
-		pr_err("No (mappable) scratch page!\n");
-		return -EINVAL;
-	}
+	vaddr = __px_vaddr(vm->scratch[0]);
 
 	memcpy(out, vaddr, sizeof(*out));
 	if (memchr_inv(vaddr, *out, PAGE_SIZE)) {
 		pr_err("Inconsistent initial state of scratch page!\n");
 		err = -EINVAL;
 	}
-	kunmap(page);
 
 	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 5cf6df49c333..05a3b29f545e 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -842,6 +842,24 @@ static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type)
 	return true;
 }
 
+static void object_set_placements(struct drm_i915_gem_object *obj,
+				  struct intel_memory_region **placements,
+				  unsigned int n_placements)
+{
+	GEM_BUG_ON(!n_placements);
+
+	if (n_placements == 1) {
+		struct drm_i915_private *i915 = to_i915(obj->base.dev);
+		struct intel_memory_region *mr = placements[0];
+
+		obj->mm.placements = &i915->mm.regions[mr->id];
+		obj->mm.n_placements = 1;
+	} else {
+		obj->mm.placements = placements;
+		obj->mm.n_placements = n_placements;
+	}
+}
+
 #define expand32(x) (((x) << 0) | ((x) << 8) | ((x) << 16) | ((x) << 24))
 static int __igt_mmap(struct drm_i915_private *i915,
 		      struct drm_i915_gem_object *obj,
@@ -950,6 +968,8 @@ static int igt_mmap(void *arg)
 			if (IS_ERR(obj))
 				return PTR_ERR(obj);
 
+			object_set_placements(obj, &mr, 1);
+
 			err = __igt_mmap(i915, obj, I915_MMAP_TYPE_GTT);
 			if (err == 0)
 				err = __igt_mmap(i915, obj, I915_MMAP_TYPE_WC);
@@ -1068,6 +1088,8 @@ static int igt_mmap_access(void *arg)
 		if (IS_ERR(obj))
 			return PTR_ERR(obj);
 
+		object_set_placements(obj, &mr, 1);
+
 		err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_GTT);
 		if (err == 0)
 			err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_WB);
@@ -1211,6 +1233,8 @@ static int igt_mmap_gpu(void *arg)
 		if (IS_ERR(obj))
 			return PTR_ERR(obj);
 
+		object_set_placements(obj, &mr, 1);
+
 		err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_GTT);
 		if (err == 0)
 			err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_WC);
@@ -1354,6 +1378,8 @@ static int igt_mmap_revoke(void *arg)
 		if (IS_ERR(obj))
 			return PTR_ERR(obj);
 
+		object_set_placements(obj, &mr, 1);
+
 		err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_GTT);
 		if (err == 0)
 			err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_WC);
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
index e08dff376339..1aee5e6b1b23 100644
--- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -96,9 +96,8 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 		 * entries back to scratch.
 		 */
 
-		vaddr = kmap_atomic_px(pt);
+		vaddr = px_vaddr(pt);
 		memset32(vaddr + pte, scratch_pte, count);
-		kunmap_atomic(vaddr);
 
 		pte = 0;
 	}
@@ -120,7 +119,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 
 	GEM_BUG_ON(!pd->entry[act_pt]);
 
-	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
+	vaddr = px_vaddr(i915_pt_entry(pd, act_pt));
 	do {
 		GEM_BUG_ON(sg_dma_len(iter.sg) < I915_GTT_PAGE_SIZE);
 		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
@@ -136,12 +135,10 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 		}
 
 		if (++act_pte == GEN6_PTES) {
-			kunmap_atomic(vaddr);
-			vaddr = kmap_atomic_px(i915_pt_entry(pd, ++act_pt));
+			vaddr = px_vaddr(i915_pt_entry(pd, ++act_pt));
 			act_pte = 0;
 		}
 	} while (1);
-	kunmap_atomic(vaddr);
 
 	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
 }
@@ -235,7 +232,7 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
 		goto err_scratch0;
 	}
 
-	ret = pin_pt_dma(vm, vm->scratch[1]);
+	ret = map_pt_dma(vm, vm->scratch[1]);
 	if (ret)
 		goto err_scratch1;
 
@@ -346,7 +343,7 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 	if (!vma)
 		return ERR_PTR(-ENOMEM);
 
-	i915_active_init(&vma->active, NULL, NULL);
+	i915_active_init(&vma->active, NULL, NULL, 0);
 
 	kref_init(&vma->ref);
 	mutex_init(&vma->pages_mutex);
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 74bf6fc8461f..e3a8924d2286 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -242,11 +242,10 @@ static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
 			    atomic_read(&pt->used));
 			GEM_BUG_ON(!count || count >= atomic_read(&pt->used));
 
-			vaddr = kmap_atomic_px(pt);
+			vaddr = px_vaddr(pt);
 			memset64(vaddr + gen8_pd_index(start, 0),
 				 vm->scratch[0]->encode,
 				 count);
-			kunmap_atomic(vaddr);
 
 			atomic_sub(count, &pt->used);
 			start += count;
@@ -375,7 +374,7 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 	gen8_pte_t *vaddr;
 
 	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
-	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
+	vaddr = px_vaddr(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
 	do {
 		GEM_BUG_ON(sg_dma_len(iter->sg) < I915_GTT_PAGE_SIZE);
 		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
@@ -402,12 +401,10 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 			}
 
 			clflush_cache_range(vaddr, PAGE_SIZE);
-			kunmap_atomic(vaddr);
-			vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
+			vaddr = px_vaddr(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
 		}
 	} while (1);
 	clflush_cache_range(vaddr, PAGE_SIZE);
-	kunmap_atomic(vaddr);
 
 	return idx;
 }
@@ -442,7 +439,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 			encode |= GEN8_PDE_PS_2M;
 			page_size = I915_GTT_PAGE_SIZE_2M;
 
-			vaddr = kmap_atomic_px(pd);
+			vaddr = px_vaddr(pd);
 		} else {
 			struct i915_page_table *pt =
 				i915_pt_entry(pd, __gen8_pte_index(start, 1));
@@ -457,7 +454,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 			     rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE))
 				maybe_64K = __gen8_pte_index(start, 1);
 
-			vaddr = kmap_atomic_px(pt);
+			vaddr = px_vaddr(pt);
 		}
 
 		do {
@@ -491,7 +488,6 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 		} while (rem >= page_size && index < I915_PDES);
 
 		clflush_cache_range(vaddr, PAGE_SIZE);
-		kunmap_atomic(vaddr);
 
 		/*
 		 * Is it safe to mark the 2M block as 64K? -- Either we have
@@ -505,9 +501,8 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 		      !iter->sg && IS_ALIGNED(vma->node.start +
 					      vma->node.size,
 					      I915_GTT_PAGE_SIZE_2M)))) {
-			vaddr = kmap_atomic_px(pd);
+			vaddr = px_vaddr(pd);
 			vaddr[maybe_64K] |= GEN8_PDE_IPS_64K;
-			kunmap_atomic(vaddr);
 			page_size = I915_GTT_PAGE_SIZE_64K;
 
 			/*
@@ -523,12 +518,11 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 				u16 i;
 
 				encode = vma->vm->scratch[0]->encode;
-				vaddr = kmap_atomic_px(i915_pt_entry(pd, maybe_64K));
+				vaddr = px_vaddr(i915_pt_entry(pd, maybe_64K));
 
 				for (i = 1; i < index; i += 16)
 					memset64(vaddr + i, encode, 15);
 
-				kunmap_atomic(vaddr);
 			}
 		}
 
@@ -602,7 +596,7 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 		if (IS_ERR(obj))
 			goto free_scratch;
 
-		ret = pin_pt_dma(vm, obj);
+		ret = map_pt_dma(vm, obj);
 		if (ret) {
 			i915_gem_object_put(obj);
 			goto free_scratch;
@@ -639,7 +633,7 @@ static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
 		if (IS_ERR(pde))
 			return PTR_ERR(pde);
 
-		err = pin_pt_dma(vm, pde->pt.base);
+		err = map_pt_dma(vm, pde->pt.base);
 		if (err) {
 			free_pd(vm, pde);
 			return err;
@@ -674,7 +668,7 @@ gen8_alloc_top_pd(struct i915_address_space *vm)
 		goto err_pd;
 	}
 
-	err = pin_pt_dma(vm, pd->pt.base);
+	err = map_pt_dma(vm, pd->pt.base);
 	if (err)
 		goto err_pd;
 
@@ -717,7 +711,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt)
 	 */
 	ppgtt->vm.has_read_only = !IS_GEN_RANGE(gt->i915, 11, 12);
 
-	ppgtt->vm.alloc_pt_dma = alloc_pt_dma;
+	if (HAS_LMEM(gt->i915))
+		ppgtt->vm.alloc_pt_dma = alloc_pt_lmem;
+	else
+		ppgtt->vm.alloc_pt_dma = alloc_pt_dma;
 
 	err = gen8_init_scratch(&ppgtt->vm);
 	if (err)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 17cf2640b082..4033184f13b9 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -326,7 +326,6 @@ void intel_context_unpin(struct intel_context *ce)
 	intel_context_put(ce);
 }
 
-__i915_active_call
 static void __intel_context_retire(struct i915_active *active)
 {
 	struct intel_context *ce = container_of(active, typeof(*ce), active);
@@ -385,7 +384,7 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
 	mutex_init(&ce->pin_mutex);
 
 	i915_active_init(&ce->active,
-			 __intel_context_active, __intel_context_retire);
+			 __intel_context_active, __intel_context_retire, 0);
 }
 
 void intel_context_fini(struct intel_context *ce)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 47ee8578e511..8d9184920c51 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -13,8 +13,9 @@
 #include "i915_reg.h"
 #include "i915_request.h"
 #include "i915_selftest.h"
-#include "gt/intel_timeline.h"
 #include "intel_engine_types.h"
+#include "intel_gt_types.h"
+#include "intel_timeline.h"
 #include "intel_workarounds.h"
 
 struct drm_printer;
@@ -262,6 +263,11 @@ void intel_engine_init_active(struct intel_engine_cs *engine,
 #define ENGINE_MOCK	1
 #define ENGINE_VIRTUAL	2
 
+static inline bool intel_engine_uses_guc(const struct intel_engine_cs *engine)
+{
+	return engine->gt->submission_method >= INTEL_SUBMISSION_GUC;
+}
+
 static inline bool
 intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 6dbdbde00f14..3f9a811eb02b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -255,6 +255,11 @@ static void intel_engine_sanitize_mmio(struct intel_engine_cs *engine)
 	intel_engine_set_hwsp_writemask(engine, ~0u);
 }
 
+static void nop_irq_handler(struct intel_engine_cs *engine, u16 iir)
+{
+	GEM_DEBUG_WARN_ON(iir);
+}
+
 static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 {
 	const struct engine_info *info = &intel_engines[id];
@@ -292,6 +297,8 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	engine->hw_id = info->hw_id;
 	engine->guc_id = MAKE_GUC_ID(info->class, info->instance);
 
+	engine->irq_handler = nop_irq_handler;
+
 	engine->class = info->class;
 	engine->instance = info->instance;
 	__sprint_engine_name(engine);
@@ -898,7 +905,7 @@ static int engine_init_common(struct intel_engine_cs *engine)
 	return 0;
 
 err_context:
-	intel_context_put(ce);
+	destroy_pinned_context(ce);
 	return ret;
 }
 
@@ -909,12 +916,16 @@ int intel_engines_init(struct intel_gt *gt)
 	enum intel_engine_id id;
 	int err;
 
-	if (intel_uc_uses_guc_submission(&gt->uc))
+	if (intel_uc_uses_guc_submission(&gt->uc)) {
+		gt->submission_method = INTEL_SUBMISSION_GUC;
 		setup = intel_guc_submission_setup;
-	else if (HAS_EXECLISTS(gt->i915))
+	} else if (HAS_EXECLISTS(gt->i915)) {
+		gt->submission_method = INTEL_SUBMISSION_ELSP;
 		setup = intel_execlists_submission_setup;
-	else
+	} else {
+		gt->submission_method = INTEL_SUBMISSION_RING;
 		setup = intel_ring_submission_setup;
+	}
 
 	for_each_engine(engine, gt, id) {
 		err = engine_setup_common(engine);
@@ -1479,7 +1490,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 		drm_printf(m, "\tIPEHR: 0x%08x\n", ENGINE_READ(engine, IPEHR));
 	}
 
-	if (intel_engine_in_guc_submission_mode(engine)) {
+	if (intel_engine_uses_guc(engine)) {
 		/* nothing to print yet */
 	} else if (HAS_EXECLISTS(dev_priv)) {
 		struct i915_request * const *port, *rq;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 7c9af86fdb1e..47f4397095e5 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -23,7 +23,7 @@ static void dbg_poison_ce(struct intel_context *ce)
 
 	if (ce->state) {
 		struct drm_i915_gem_object *obj = ce->state->obj;
-		int type = i915_coherent_map_type(ce->engine->i915);
+		int type = i915_coherent_map_type(ce->engine->i915, obj, true);
 		void *map;
 
 		if (!i915_gem_object_trylock(obj))
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 883bafc44902..9ef349cd5cea 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -402,6 +402,7 @@ struct intel_engine_cs {
 	u32		irq_enable_mask; /* bitmask to enable ring interrupt */
 	void		(*irq_enable)(struct intel_engine_cs *engine);
 	void		(*irq_disable)(struct intel_engine_cs *engine);
+	void		(*irq_handler)(struct intel_engine_cs *engine, u16 iir);
 
 	void		(*sanitize)(struct intel_engine_cs *engine);
 	int		(*resume)(struct intel_engine_cs *engine);
@@ -481,10 +482,9 @@ struct intel_engine_cs {
 #define I915_ENGINE_HAS_PREEMPTION   BIT(2)
 #define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
 #define I915_ENGINE_HAS_TIMESLICES   BIT(4)
-#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5)
-#define I915_ENGINE_IS_VIRTUAL       BIT(6)
-#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7)
-#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8)
+#define I915_ENGINE_IS_VIRTUAL       BIT(5)
+#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6)
+#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
 	unsigned int flags;
 
 	/*
@@ -594,12 +594,6 @@ intel_engine_has_timeslices(const struct intel_engine_cs *engine)
 }
 
 static inline bool
-intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine)
-{
-	return engine->flags & I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
-}
-
-static inline bool
 intel_engine_is_virtual(const struct intel_engine_cs *engine)
 {
 	return engine->flags & I915_ENGINE_IS_VIRTUAL;
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index de124870af44..8db200422950 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -118,6 +118,7 @@
 #include "intel_engine_stats.h"
 #include "intel_execlists_submission.h"
 #include "intel_gt.h"
+#include "intel_gt_irq.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
 #include "intel_lrc.h"
@@ -1768,7 +1769,6 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
 	 */
 	GEM_BUG_ON(!tasklet_is_locked(&execlists->tasklet) &&
 		   !reset_in_progress(execlists));
-	GEM_BUG_ON(!intel_engine_in_execlists_submission_mode(engine));
 
 	/*
 	 * Note that csb_write, csb_status may be either in HWSP or mmio.
@@ -2385,6 +2385,45 @@ static void execlists_submission_tasklet(struct tasklet_struct *t)
 	rcu_read_unlock();
 }
 
+static void execlists_irq_handler(struct intel_engine_cs *engine, u16 iir)
+{
+	bool tasklet = false;
+
+	if (unlikely(iir & GT_CS_MASTER_ERROR_INTERRUPT)) {
+		u32 eir;
+
+		/* Upper 16b are the enabling mask, rsvd for internal errors */
+		eir = ENGINE_READ(engine, RING_EIR) & GENMASK(15, 0);
+		ENGINE_TRACE(engine, "CS error: %x\n", eir);
+
+		/* Disable the error interrupt until after the reset */
+		if (likely(eir)) {
+			ENGINE_WRITE(engine, RING_EMR, ~0u);
+			ENGINE_WRITE(engine, RING_EIR, eir);
+			WRITE_ONCE(engine->execlists.error_interrupt, eir);
+			tasklet = true;
+		}
+	}
+
+	if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) {
+		WRITE_ONCE(engine->execlists.yield,
+			   ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI));
+		ENGINE_TRACE(engine, "semaphore yield: %08x\n",
+			     engine->execlists.yield);
+		if (del_timer(&engine->execlists.timer))
+			tasklet = true;
+	}
+
+	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
+		tasklet = true;
+
+	if (iir & GT_RENDER_USER_INTERRUPT)
+		intel_engine_signal_breadcrumbs(engine);
+
+	if (tasklet)
+		tasklet_hi_schedule(&engine->execlists.tasklet);
+}
+
 static void __execlists_kick(struct intel_engine_execlists *execlists)
 {
 	/* Kick the tasklet for some interrupt coalescing and reset handling */
@@ -3076,29 +3115,6 @@ static void execlists_set_default_submission(struct intel_engine_cs *engine)
 	engine->submit_request = execlists_submit_request;
 	engine->schedule = i915_schedule;
 	engine->execlists.tasklet.callback = execlists_submission_tasklet;
-
-	engine->reset.prepare = execlists_reset_prepare;
-	engine->reset.rewind = execlists_reset_rewind;
-	engine->reset.cancel = execlists_reset_cancel;
-	engine->reset.finish = execlists_reset_finish;
-
-	engine->park = execlists_park;
-	engine->unpark = NULL;
-
-	engine->flags |= I915_ENGINE_SUPPORTS_STATS;
-	if (!intel_vgpu_active(engine->i915)) {
-		engine->flags |= I915_ENGINE_HAS_SEMAPHORES;
-		if (can_preempt(engine)) {
-			engine->flags |= I915_ENGINE_HAS_PREEMPTION;
-			if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
-				engine->flags |= I915_ENGINE_HAS_TIMESLICES;
-		}
-	}
-
-	if (intel_engine_has_preemption(engine))
-		engine->emit_bb_start = gen8_emit_bb_start;
-	else
-		engine->emit_bb_start = gen8_emit_bb_start_noarb;
 }
 
 static void execlists_shutdown(struct intel_engine_cs *engine)
@@ -3129,6 +3145,14 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 	engine->cops = &execlists_context_ops;
 	engine->request_alloc = execlists_request_alloc;
 
+	engine->reset.prepare = execlists_reset_prepare;
+	engine->reset.rewind = execlists_reset_rewind;
+	engine->reset.cancel = execlists_reset_cancel;
+	engine->reset.finish = execlists_reset_finish;
+
+	engine->park = execlists_park;
+	engine->unpark = NULL;
+
 	engine->emit_flush = gen8_emit_flush_xcs;
 	engine->emit_init_breadcrumb = gen8_emit_init_breadcrumb;
 	engine->emit_fini_breadcrumb = gen8_emit_fini_breadcrumb_xcs;
@@ -3149,6 +3173,22 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 		 * until a more refined solution exists.
 		 */
 	}
+	intel_engine_set_irq_handler(engine, execlists_irq_handler);
+
+	engine->flags |= I915_ENGINE_SUPPORTS_STATS;
+	if (!intel_vgpu_active(engine->i915)) {
+		engine->flags |= I915_ENGINE_HAS_SEMAPHORES;
+		if (can_preempt(engine)) {
+			engine->flags |= I915_ENGINE_HAS_PREEMPTION;
+			if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+				engine->flags |= I915_ENGINE_HAS_TIMESLICES;
+		}
+	}
+
+	if (intel_engine_has_preemption(engine))
+		engine->emit_bb_start = gen8_emit_bb_start;
+	else
+		engine->emit_bb_start = gen8_emit_bb_start_noarb;
 }
 
 static void logical_ring_default_irqs(struct intel_engine_cs *engine)
@@ -3884,13 +3924,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
-bool
-intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine)
-{
-	return engine->set_default_submission ==
-	       execlists_set_default_submission;
-}
-
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_execlists.c"
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
index fd61dae820e9..4ca9b475e252 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
@@ -43,7 +43,4 @@ int intel_virtual_engine_attach_bond(struct intel_engine_cs *engine,
 				     const struct intel_engine_cs *master,
 				     const struct intel_engine_cs *sibling);
 
-bool
-intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine);
-
 #endif /* __INTEL_EXECLISTS_SUBMISSION_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 38742bf33fa3..35069ca5d7de 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -658,7 +658,7 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
 		goto err_ppgtt;
 
 	i915_gem_object_lock(ppgtt->vm.scratch[0], NULL);
-	err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash);
+	err = i915_vm_map_pt_stash(&ppgtt->vm, &stash);
 	i915_gem_object_unlock(ppgtt->vm.scratch[0]);
 	if (err)
 		goto err_stash;
@@ -907,9 +907,11 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
 
-	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
-	if (intel_ggtt_update_needs_vtd_wa(i915) ||
-	    IS_CHERRYVIEW(i915) /* fails with concurrent use/update */) {
+	/*
+	 * Serialize GTT updates with aperture access on BXT if VT-d is on,
+	 * and always on CHV.
+	 */
+	if (intel_vm_no_concurrent_access_wa(i915)) {
 		ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
 		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
 		ggtt->vm.bind_async_flags =
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
index 8a322594210c..7bf84cd21543 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
@@ -653,8 +653,8 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt)
 		 * banks of memory are paired and unswizzled on the
 		 * uneven portion, so leave that as unknown.
 		 */
-		if (intel_uncore_read16(uncore, C0DRB3) ==
-		    intel_uncore_read16(uncore, C1DRB3)) {
+		if (intel_uncore_read16(uncore, C0DRB3_BW) ==
+		    intel_uncore_read16(uncore, C1DRB3_BW)) {
 			swizzle_x = I915_BIT_6_SWIZZLE_9_10;
 			swizzle_y = I915_BIT_6_SWIZZLE_9;
 		}
@@ -867,7 +867,7 @@ void intel_ggtt_init_fences(struct i915_ggtt *ggtt)
 	for (i = 0; i < num_fences; i++) {
 		struct i915_fence_reg *fence = &ggtt->fence_regs[i];
 
-		i915_active_init(&fence->active, NULL, NULL);
+		i915_active_init(&fence->active, NULL, NULL, 0);
 		fence->ggtt = ggtt;
 		fence->id = i;
 		list_add_tail(&fence->link, &ggtt->fence_list);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
index c59468107598..aa0a59c5b614 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
@@ -98,7 +98,6 @@ static void pool_free_work(struct work_struct *wrk)
 				      round_jiffies_up_relative(HZ));
 }
 
-__i915_active_call
 static void pool_retire(struct i915_active *ref)
 {
 	struct intel_gt_buffer_pool_node *node =
@@ -154,7 +153,7 @@ node_create(struct intel_gt_buffer_pool *pool, size_t sz,
 	node->age = 0;
 	node->pool = pool;
 	node->pinned = false;
-	i915_active_init(&node->active, NULL, pool_retire);
+	i915_active_init(&node->active, NULL, pool_retire, 0);
 
 	obj = i915_gem_object_create_internal(gt->i915, sz);
 	if (IS_ERR(obj)) {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index 9fc6c912a4e5..d29126c458ba 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -20,48 +20,6 @@ static void guc_irq_handler(struct intel_guc *guc, u16 iir)
 		intel_guc_to_host_event_handler(guc);
 }
 
-static void
-cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
-{
-	bool tasklet = false;
-
-	if (unlikely(iir & GT_CS_MASTER_ERROR_INTERRUPT)) {
-		u32 eir;
-
-		/* Upper 16b are the enabling mask, rsvd for internal errors */
-		eir = ENGINE_READ(engine, RING_EIR) & GENMASK(15, 0);
-		ENGINE_TRACE(engine, "CS error: %x\n", eir);
-
-		/* Disable the error interrupt until after the reset */
-		if (likely(eir)) {
-			ENGINE_WRITE(engine, RING_EMR, ~0u);
-			ENGINE_WRITE(engine, RING_EIR, eir);
-			WRITE_ONCE(engine->execlists.error_interrupt, eir);
-			tasklet = true;
-		}
-	}
-
-	if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) {
-		WRITE_ONCE(engine->execlists.yield,
-			   ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI));
-		ENGINE_TRACE(engine, "semaphore yield: %08x\n",
-			     engine->execlists.yield);
-		if (del_timer(&engine->execlists.timer))
-			tasklet = true;
-	}
-
-	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
-		tasklet = true;
-
-	if (iir & GT_RENDER_USER_INTERRUPT) {
-		intel_engine_signal_breadcrumbs(engine);
-		tasklet |= intel_engine_needs_breadcrumb_tasklet(engine);
-	}
-
-	if (tasklet)
-		tasklet_hi_schedule(&engine->execlists.tasklet);
-}
-
 static u32
 gen11_gt_engine_identity(struct intel_gt *gt,
 			 const unsigned int bank, const unsigned int bit)
@@ -122,7 +80,7 @@ gen11_engine_irq_handler(struct intel_gt *gt, const u8 class,
 		engine = NULL;
 
 	if (likely(engine))
-		return cs_irq_handler(engine, iir);
+		return intel_engine_cs_irq(engine, iir);
 
 	WARN_ONCE(1, "unhandled engine interrupt class=0x%x, instance=0x%x\n",
 		  class, instance);
@@ -275,9 +233,12 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 void gen5_gt_irq_handler(struct intel_gt *gt, u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]);
+		intel_engine_cs_irq(gt->engine_class[RENDER_CLASS][0],
+				    gt_iir);
+
 	if (gt_iir & ILK_BSD_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]);
+		intel_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0],
+				    gt_iir);
 }
 
 static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir)
@@ -301,11 +262,16 @@ static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir)
 void gen6_gt_irq_handler(struct intel_gt *gt, u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]);
+		intel_engine_cs_irq(gt->engine_class[RENDER_CLASS][0],
+				    gt_iir);
+
 	if (gt_iir & GT_BSD_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]);
+		intel_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0],
+				    gt_iir >> 12);
+
 	if (gt_iir & GT_BLT_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[COPY_ENGINE_CLASS][0]);
+		intel_engine_cs_irq(gt->engine_class[COPY_ENGINE_CLASS][0],
+				    gt_iir >> 22);
 
 	if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
 		      GT_BSD_CS_ERROR_INTERRUPT |
@@ -324,10 +290,10 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl)
 	if (master_ctl & (GEN8_GT_RCS_IRQ | GEN8_GT_BCS_IRQ)) {
 		iir = raw_reg_read(regs, GEN8_GT_IIR(0));
 		if (likely(iir)) {
-			cs_irq_handler(gt->engine_class[RENDER_CLASS][0],
-				       iir >> GEN8_RCS_IRQ_SHIFT);
-			cs_irq_handler(gt->engine_class[COPY_ENGINE_CLASS][0],
-				       iir >> GEN8_BCS_IRQ_SHIFT);
+			intel_engine_cs_irq(gt->engine_class[RENDER_CLASS][0],
+					    iir >> GEN8_RCS_IRQ_SHIFT);
+			intel_engine_cs_irq(gt->engine_class[COPY_ENGINE_CLASS][0],
+					    iir >> GEN8_BCS_IRQ_SHIFT);
 			raw_reg_write(regs, GEN8_GT_IIR(0), iir);
 		}
 	}
@@ -335,10 +301,10 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl)
 	if (master_ctl & (GEN8_GT_VCS0_IRQ | GEN8_GT_VCS1_IRQ)) {
 		iir = raw_reg_read(regs, GEN8_GT_IIR(1));
 		if (likely(iir)) {
-			cs_irq_handler(gt->engine_class[VIDEO_DECODE_CLASS][0],
-				       iir >> GEN8_VCS0_IRQ_SHIFT);
-			cs_irq_handler(gt->engine_class[VIDEO_DECODE_CLASS][1],
-				       iir >> GEN8_VCS1_IRQ_SHIFT);
+			intel_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0],
+					    iir >> GEN8_VCS0_IRQ_SHIFT);
+			intel_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][1],
+					    iir >> GEN8_VCS1_IRQ_SHIFT);
 			raw_reg_write(regs, GEN8_GT_IIR(1), iir);
 		}
 	}
@@ -346,8 +312,8 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl)
 	if (master_ctl & GEN8_GT_VECS_IRQ) {
 		iir = raw_reg_read(regs, GEN8_GT_IIR(3));
 		if (likely(iir)) {
-			cs_irq_handler(gt->engine_class[VIDEO_ENHANCEMENT_CLASS][0],
-				       iir >> GEN8_VECS_IRQ_SHIFT);
+			intel_engine_cs_irq(gt->engine_class[VIDEO_ENHANCEMENT_CLASS][0],
+					    iir >> GEN8_VECS_IRQ_SHIFT);
 			raw_reg_write(regs, GEN8_GT_IIR(3), iir);
 		}
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.h b/drivers/gpu/drm/i915/gt/intel_gt_irq.h
index f667e976fb2b..41cad38668c5 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.h
@@ -8,6 +8,8 @@
 
 #include <linux/types.h>
 
+#include "intel_engine_types.h"
+
 struct intel_gt;
 
 #define GEN8_GT_IRQS (GEN8_GT_RCS_IRQ | \
@@ -39,4 +41,25 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl);
 void gen8_gt_irq_reset(struct intel_gt *gt);
 void gen8_gt_irq_postinstall(struct intel_gt *gt);
 
+static inline void intel_engine_cs_irq(struct intel_engine_cs *engine, u16 iir)
+{
+	if (iir)
+		engine->irq_handler(engine, iir);
+}
+
+static inline void
+intel_engine_set_irq_handler(struct intel_engine_cs *engine,
+			     void (*fn)(struct intel_engine_cs *engine,
+					u16 iir))
+{
+	/*
+	 * As the interrupt is live as allocate and setup the engines,
+	 * err on the side of caution and apply barriers to updating
+	 * the irq handler callback. This assures that when we do use
+	 * the engine, we will receive interrupts only to ourselves,
+	 * and not lose any.
+	 */
+	smp_store_mb(engine->irq_handler, fn);
+}
+
 #endif /* INTEL_GT_IRQ_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 0caf6ca0a784..fecfacf551d5 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -31,6 +31,12 @@ struct i915_ggtt;
 struct intel_engine_cs;
 struct intel_uncore;
 
+enum intel_submission_method {
+	INTEL_SUBMISSION_RING,
+	INTEL_SUBMISSION_ELSP,
+	INTEL_SUBMISSION_GUC,
+};
+
 struct intel_gt {
 	struct drm_i915_private *i915;
 	struct intel_uncore *uncore;
@@ -118,6 +124,7 @@ struct intel_gt {
 	struct intel_engine_cs *engine[I915_NUM_ENGINES];
 	struct intel_engine_cs *engine_class[MAX_ENGINE_CLASS + 1]
 					    [MAX_ENGINE_INSTANCE + 1];
+	enum intel_submission_method submission_method;
 
 	/*
 	 * Default address space (either GGTT or ppGTT depending on arch).
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 941f8af016d6..9b98f9d9faa3 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -7,10 +7,26 @@
 
 #include <linux/fault-inject.h>
 
+#include "gem/i915_gem_lmem.h"
 #include "i915_trace.h"
 #include "intel_gt.h"
 #include "intel_gtt.h"
 
+struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz)
+{
+	struct drm_i915_gem_object *obj;
+
+	obj = i915_gem_object_create_lmem(vm->i915, sz, 0);
+	/*
+	 * Ensure all paging structures for this vm share the same dma-resv
+	 * object underneath, with the idea that one object_lock() will lock
+	 * them all at once.
+	 */
+	if (!IS_ERR(obj))
+		obj->base.resv = &vm->resv;
+	return obj;
+}
+
 struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz)
 {
 	struct drm_i915_gem_object *obj;
@@ -19,33 +35,39 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz)
 		i915_gem_shrink_all(vm->i915);
 
 	obj = i915_gem_object_create_internal(vm->i915, sz);
-	/* ensure all dma objects have the same reservation class */
+	/*
+	 * Ensure all paging structures for this vm share the same dma-resv
+	 * object underneath, with the idea that one object_lock() will lock
+	 * them all at once.
+	 */
 	if (!IS_ERR(obj))
 		obj->base.resv = &vm->resv;
 	return obj;
 }
 
-int pin_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
+int map_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
 {
-	int err;
+	enum i915_map_type type;
+	void *vaddr;
 
-	i915_gem_object_lock(obj, NULL);
-	err = i915_gem_object_pin_pages(obj);
-	i915_gem_object_unlock(obj);
-	if (err)
-		return err;
+	type = i915_coherent_map_type(vm->i915, obj, true);
+	vaddr = i915_gem_object_pin_map_unlocked(obj, type);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
 
 	i915_gem_object_make_unshrinkable(obj);
 	return 0;
 }
 
-int pin_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
+int map_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
 {
-	int err;
+	enum i915_map_type type;
+	void *vaddr;
 
-	err = i915_gem_object_pin_pages(obj);
-	if (err)
-		return err;
+	type = i915_coherent_map_type(vm->i915, obj, true);
+	vaddr = i915_gem_object_pin_map(obj, type);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
 
 	i915_gem_object_make_unshrinkable(obj);
 	return 0;
@@ -132,7 +154,22 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass)
 	 */
 	mutex_init(&vm->mutex);
 	lockdep_set_subclass(&vm->mutex, subclass);
-	i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex);
+
+	if (!intel_vm_no_concurrent_access_wa(vm->i915)) {
+		i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex);
+	} else {
+		/*
+		 * CHV + BXT VTD workaround use stop_machine(),
+		 * which is allowed to allocate memory. This means &vm->mutex
+		 * is the outer lock, and in theory we can allocate memory inside
+		 * it through stop_machine().
+		 *
+		 * Add the annotation for this, we use trylock in shrinker.
+		 */
+		mutex_acquire(&vm->mutex.dep_map, 0, 0, _THIS_IP_);
+		might_alloc(GFP_KERNEL);
+		mutex_release(&vm->mutex.dep_map, _THIS_IP_);
+	}
 	dma_resv_init(&vm->resv);
 
 	GEM_BUG_ON(!vm->total);
@@ -155,6 +192,14 @@ void clear_pages(struct i915_vma *vma)
 	memset(&vma->page_sizes, 0, sizeof(vma->page_sizes));
 }
 
+void *__px_vaddr(struct drm_i915_gem_object *p)
+{
+	enum i915_map_type type;
+
+	GEM_BUG_ON(!i915_gem_object_has_pages(p));
+	return page_unpack_bits(p->mm.mapping, &type);
+}
+
 dma_addr_t __px_dma(struct drm_i915_gem_object *p)
 {
 	GEM_BUG_ON(!i915_gem_object_has_pages(p));
@@ -170,32 +215,22 @@ struct page *__px_page(struct drm_i915_gem_object *p)
 void
 fill_page_dma(struct drm_i915_gem_object *p, const u64 val, unsigned int count)
 {
-	struct page *page = __px_page(p);
-	void *vaddr;
+	void *vaddr = __px_vaddr(p);
 
-	vaddr = kmap(page);
 	memset64(vaddr, val, count);
 	clflush_cache_range(vaddr, PAGE_SIZE);
-	kunmap(page);
 }
 
 static void poison_scratch_page(struct drm_i915_gem_object *scratch)
 {
-	struct sgt_iter sgt;
-	struct page *page;
+	void *vaddr = __px_vaddr(scratch);
 	u8 val;
 
 	val = 0;
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		val = POISON_FREE;
 
-	for_each_sgt_page(page, sgt, scratch->mm.pages) {
-		void *vaddr;
-
-		vaddr = kmap(page);
-		memset(vaddr, val, PAGE_SIZE);
-		kunmap(page);
-	}
+	memset(vaddr, val, scratch->base.size);
 }
 
 int setup_scratch_page(struct i915_address_space *vm)
@@ -225,7 +260,7 @@ int setup_scratch_page(struct i915_address_space *vm)
 		if (IS_ERR(obj))
 			goto skip;
 
-		if (pin_pt_dma(vm, obj))
+		if (map_pt_dma(vm, obj))
 			goto skip_obj;
 
 		/* We need a single contiguous page for our scratch */
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index 79f565aeb8c0..ca00b45827b7 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -180,6 +180,9 @@ struct page *__px_page(struct drm_i915_gem_object *p);
 dma_addr_t __px_dma(struct drm_i915_gem_object *p);
 #define px_dma(px) (__px_dma(px_base(px)))
 
+void *__px_vaddr(struct drm_i915_gem_object *p);
+#define px_vaddr(px) (__px_vaddr(px_base(px)))
+
 #define px_pt(px) \
 	__px_choose_expr(px, struct i915_page_table *, __x, \
 	__px_choose_expr(px, struct i915_page_directory *, &__x->pt, \
@@ -516,8 +519,6 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt);
 void i915_ggtt_suspend(struct i915_ggtt *gtt);
 void i915_ggtt_resume(struct i915_ggtt *ggtt);
 
-#define kmap_atomic_px(px) kmap_atomic(__px_page(px_base(px)))
-
 void
 fill_page_dma(struct drm_i915_gem_object *p, const u64 val, unsigned int count);
 
@@ -531,12 +532,13 @@ int setup_scratch_page(struct i915_address_space *vm);
 void free_scratch(struct i915_address_space *vm);
 
 struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz);
+struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz);
 struct i915_page_table *alloc_pt(struct i915_address_space *vm);
 struct i915_page_directory *alloc_pd(struct i915_address_space *vm);
 struct i915_page_directory *__alloc_pd(int npde);
 
-int pin_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj);
-int pin_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj);
+int map_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj);
+int map_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj);
 
 void free_px(struct i915_address_space *vm,
 	     struct i915_page_table *pt, int lvl);
@@ -583,7 +585,7 @@ void setup_private_pat(struct intel_uncore *uncore);
 int i915_vm_alloc_pt_stash(struct i915_address_space *vm,
 			   struct i915_vm_pt_stash *stash,
 			   u64 size);
-int i915_vm_pin_pt_stash(struct i915_address_space *vm,
+int i915_vm_map_pt_stash(struct i915_address_space *vm,
 			 struct i915_vm_pt_stash *stash);
 void i915_vm_free_pt_stash(struct i915_address_space *vm,
 			   struct i915_vm_pt_stash *stash);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index e86897cde984..aafe2a4df496 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -903,7 +903,9 @@ lrc_pre_pin(struct intel_context *ce,
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	*vaddr = i915_gem_object_pin_map(ce->state->obj,
-					 i915_coherent_map_type(ce->engine->i915) |
+					 i915_coherent_map_type(ce->engine->i915,
+								ce->state->obj,
+								false) |
 					 I915_MAP_OVERRIDE);
 
 	return PTR_ERR_OR_ZERO(*vaddr);
diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
index 014ae8ac4480..4e3d80c2295c 100644
--- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -87,11 +87,10 @@ write_dma_entry(struct drm_i915_gem_object * const pdma,
 		const unsigned short idx,
 		const u64 encoded_entry)
 {
-	u64 * const vaddr = kmap_atomic(__px_page(pdma));
+	u64 * const vaddr = __px_vaddr(pdma);
 
 	vaddr[idx] = encoded_entry;
 	clflush_cache_range(&vaddr[idx], sizeof(u64));
-	kunmap_atomic(vaddr);
 }
 
 void
@@ -258,7 +257,7 @@ int i915_vm_alloc_pt_stash(struct i915_address_space *vm,
 	return 0;
 }
 
-int i915_vm_pin_pt_stash(struct i915_address_space *vm,
+int i915_vm_map_pt_stash(struct i915_address_space *vm,
 			 struct i915_vm_pt_stash *stash)
 {
 	struct i915_page_table *pt;
@@ -266,7 +265,7 @@ int i915_vm_pin_pt_stash(struct i915_address_space *vm,
 
 	for (n = 0; n < ARRAY_SIZE(stash->pt); n++) {
 		for (pt = stash->pt[n]; pt; pt = pt->stash) {
-			err = pin_pt_dma_locked(vm, pt->base);
+			err = map_pt_dma_locked(vm, pt->base);
 			if (err)
 				return err;
 		}
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index a377c4588aaa..8091846d955b 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -338,15 +338,69 @@ static int gen6_reset_engines(struct intel_gt *gt,
 	return gen6_hw_domain_reset(gt, hw_mask);
 }
 
-static int gen11_lock_sfc(struct intel_engine_cs *engine, u32 *hw_mask)
+static struct intel_engine_cs *find_sfc_paired_vecs_engine(struct intel_engine_cs *engine)
+{
+	int vecs_id;
+
+	GEM_BUG_ON(engine->class != VIDEO_DECODE_CLASS);
+
+	vecs_id = _VECS((engine->instance) / 2);
+
+	return engine->gt->engine[vecs_id];
+}
+
+struct sfc_lock_data {
+	i915_reg_t lock_reg;
+	i915_reg_t ack_reg;
+	i915_reg_t usage_reg;
+	u32 lock_bit;
+	u32 ack_bit;
+	u32 usage_bit;
+	u32 reset_bit;
+};
+
+static void get_sfc_forced_lock_data(struct intel_engine_cs *engine,
+				     struct sfc_lock_data *sfc_lock)
+{
+	switch (engine->class) {
+	default:
+		MISSING_CASE(engine->class);
+		fallthrough;
+	case VIDEO_DECODE_CLASS:
+		sfc_lock->lock_reg = GEN11_VCS_SFC_FORCED_LOCK(engine);
+		sfc_lock->lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
+
+		sfc_lock->ack_reg = GEN11_VCS_SFC_LOCK_STATUS(engine);
+		sfc_lock->ack_bit  = GEN11_VCS_SFC_LOCK_ACK_BIT;
+
+		sfc_lock->usage_reg = GEN11_VCS_SFC_LOCK_STATUS(engine);
+		sfc_lock->usage_bit = GEN11_VCS_SFC_USAGE_BIT;
+		sfc_lock->reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance);
+
+		break;
+	case VIDEO_ENHANCEMENT_CLASS:
+		sfc_lock->lock_reg = GEN11_VECS_SFC_FORCED_LOCK(engine);
+		sfc_lock->lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
+
+		sfc_lock->ack_reg = GEN11_VECS_SFC_LOCK_ACK(engine);
+		sfc_lock->ack_bit  = GEN11_VECS_SFC_LOCK_ACK_BIT;
+
+		sfc_lock->usage_reg = GEN11_VECS_SFC_USAGE(engine);
+		sfc_lock->usage_bit = GEN11_VECS_SFC_USAGE_BIT;
+		sfc_lock->reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance);
+
+		break;
+	}
+}
+
+static int gen11_lock_sfc(struct intel_engine_cs *engine,
+			  u32 *reset_mask,
+			  u32 *unlock_mask)
 {
 	struct intel_uncore *uncore = engine->uncore;
 	u8 vdbox_sfc_access = engine->gt->info.vdbox_sfc_access;
-	i915_reg_t sfc_forced_lock, sfc_forced_lock_ack;
-	u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit;
-	i915_reg_t sfc_usage;
-	u32 sfc_usage_bit;
-	u32 sfc_reset_bit;
+	struct sfc_lock_data sfc_lock;
+	bool lock_obtained, lock_to_other = false;
 	int ret;
 
 	switch (engine->class) {
@@ -354,53 +408,72 @@ static int gen11_lock_sfc(struct intel_engine_cs *engine, u32 *hw_mask)
 		if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
 			return 0;
 
-		sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
-		sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
-
-		sfc_forced_lock_ack = GEN11_VCS_SFC_LOCK_STATUS(engine);
-		sfc_forced_lock_ack_bit  = GEN11_VCS_SFC_LOCK_ACK_BIT;
+		fallthrough;
+	case VIDEO_ENHANCEMENT_CLASS:
+		get_sfc_forced_lock_data(engine, &sfc_lock);
 
-		sfc_usage = GEN11_VCS_SFC_LOCK_STATUS(engine);
-		sfc_usage_bit = GEN11_VCS_SFC_USAGE_BIT;
-		sfc_reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance);
 		break;
+	default:
+		return 0;
+	}
 
-	case VIDEO_ENHANCEMENT_CLASS:
-		sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
-		sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
+	if (!(intel_uncore_read_fw(uncore, sfc_lock.usage_reg) & sfc_lock.usage_bit)) {
+		struct intel_engine_cs *paired_vecs;
 
-		sfc_forced_lock_ack = GEN11_VECS_SFC_LOCK_ACK(engine);
-		sfc_forced_lock_ack_bit  = GEN11_VECS_SFC_LOCK_ACK_BIT;
+		if (engine->class != VIDEO_DECODE_CLASS ||
+		    !IS_GEN(engine->i915, 12))
+			return 0;
 
-		sfc_usage = GEN11_VECS_SFC_USAGE(engine);
-		sfc_usage_bit = GEN11_VECS_SFC_USAGE_BIT;
-		sfc_reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance);
-		break;
+		/*
+		 * Wa_14010733141
+		 *
+		 * If the VCS-MFX isn't using the SFC, we also need to check
+		 * whether VCS-HCP is using it.  If so, we need to issue a *VE*
+		 * forced lock on the VE engine that shares the same SFC.
+		 */
+		if (!(intel_uncore_read_fw(uncore,
+					   GEN12_HCP_SFC_LOCK_STATUS(engine)) &
+		      GEN12_HCP_SFC_USAGE_BIT))
+			return 0;
 
-	default:
-		return 0;
+		paired_vecs = find_sfc_paired_vecs_engine(engine);
+		get_sfc_forced_lock_data(paired_vecs, &sfc_lock);
+		lock_to_other = true;
+		*unlock_mask |= paired_vecs->mask;
+	} else {
+		*unlock_mask |= engine->mask;
 	}
 
 	/*
-	 * If the engine is using a SFC, tell the engine that a software reset
+	 * If the engine is using an SFC, tell the engine that a software reset
 	 * is going to happen. The engine will then try to force lock the SFC.
 	 * If SFC ends up being locked to the engine we want to reset, we have
 	 * to reset it as well (we will unlock it once the reset sequence is
 	 * completed).
 	 */
-	if (!(intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit))
-		return 0;
-
-	rmw_set_fw(uncore, sfc_forced_lock, sfc_forced_lock_bit);
+	rmw_set_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit);
 
 	ret = __intel_wait_for_register_fw(uncore,
-					   sfc_forced_lock_ack,
-					   sfc_forced_lock_ack_bit,
-					   sfc_forced_lock_ack_bit,
+					   sfc_lock.ack_reg,
+					   sfc_lock.ack_bit,
+					   sfc_lock.ack_bit,
 					   1000, 0, NULL);
 
-	/* Was the SFC released while we were trying to lock it? */
-	if (!(intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit))
+	/*
+	 * Was the SFC released while we were trying to lock it?
+	 *
+	 * We should reset both the engine and the SFC if:
+	 *  - We were locking the SFC to this engine and the lock succeeded
+	 *       OR
+	 *  - We were locking the SFC to a different engine (Wa_14010733141)
+	 *    but the SFC was released before the lock was obtained.
+	 *
+	 * Otherwise we need only reset the engine by itself and we can
+	 * leave the SFC alone.
+	 */
+	lock_obtained = (intel_uncore_read_fw(uncore, sfc_lock.usage_reg) &
+			sfc_lock.usage_bit) != 0;
+	if (lock_obtained == lock_to_other)
 		return 0;
 
 	if (ret) {
@@ -408,7 +481,7 @@ static int gen11_lock_sfc(struct intel_engine_cs *engine, u32 *hw_mask)
 		return ret;
 	}
 
-	*hw_mask |= sfc_reset_bit;
+	*reset_mask |= sfc_lock.reset_bit;
 	return 0;
 }
 
@@ -416,28 +489,19 @@ static void gen11_unlock_sfc(struct intel_engine_cs *engine)
 {
 	struct intel_uncore *uncore = engine->uncore;
 	u8 vdbox_sfc_access = engine->gt->info.vdbox_sfc_access;
-	i915_reg_t sfc_forced_lock;
-	u32 sfc_forced_lock_bit;
-
-	switch (engine->class) {
-	case VIDEO_DECODE_CLASS:
-		if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
-			return;
+	struct sfc_lock_data sfc_lock = {};
 
-		sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
-		sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
-		break;
-
-	case VIDEO_ENHANCEMENT_CLASS:
-		sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
-		sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
-		break;
+	if (engine->class != VIDEO_DECODE_CLASS &&
+	    engine->class != VIDEO_ENHANCEMENT_CLASS)
+		return;
 
-	default:
+	if (engine->class == VIDEO_DECODE_CLASS &&
+	    (BIT(engine->instance) & vdbox_sfc_access) == 0)
 		return;
-	}
 
-	rmw_clear_fw(uncore, sfc_forced_lock, sfc_forced_lock_bit);
+	get_sfc_forced_lock_data(engine, &sfc_lock);
+
+	rmw_clear_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit);
 }
 
 static int gen11_reset_engines(struct intel_gt *gt,
@@ -456,23 +520,23 @@ static int gen11_reset_engines(struct intel_gt *gt,
 	};
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t tmp;
-	u32 hw_mask;
+	u32 reset_mask, unlock_mask = 0;
 	int ret;
 
 	if (engine_mask == ALL_ENGINES) {
-		hw_mask = GEN11_GRDOM_FULL;
+		reset_mask = GEN11_GRDOM_FULL;
 	} else {
-		hw_mask = 0;
+		reset_mask = 0;
 		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask));
-			hw_mask |= hw_engine_mask[engine->id];
-			ret = gen11_lock_sfc(engine, &hw_mask);
+			reset_mask |= hw_engine_mask[engine->id];
+			ret = gen11_lock_sfc(engine, &reset_mask, &unlock_mask);
 			if (ret)
 				goto sfc_unlock;
 		}
 	}
 
-	ret = gen6_hw_domain_reset(gt, hw_mask);
+	ret = gen6_hw_domain_reset(gt, reset_mask);
 
 sfc_unlock:
 	/*
@@ -480,10 +544,14 @@ sfc_unlock:
 	 * gen11_lock_sfc to make sure that we clean properly if something
 	 * wrong happened during the lock (e.g. lock acquired after timeout
 	 * expiration).
+	 *
+	 * Due to Wa_14010733141, we may have locked an SFC to an engine that
+	 * wasn't being reset.  So instead of calling gen11_unlock_sfc()
+	 * on engine_mask, we instead call it on the mask of engines that our
+	 * gen11_lock_sfc() calls told us actually had locks attempted.
 	 */
-	if (engine_mask != ALL_ENGINES)
-		for_each_engine_masked(engine, gt, engine_mask, tmp)
-			gen11_unlock_sfc(engine);
+	for_each_engine_masked(engine, gt, unlock_mask, tmp)
+		gen11_unlock_sfc(engine);
 
 	return ret;
 }
@@ -1118,7 +1186,6 @@ static int intel_gt_reset_engine(struct intel_engine_cs *engine)
 int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg)
 {
 	struct intel_gt *gt = engine->gt;
-	bool uses_guc = intel_engine_in_guc_submission_mode(engine);
 	int ret;
 
 	ENGINE_TRACE(engine, "flags=%lx\n", gt->reset.flags);
@@ -1134,10 +1201,10 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg)
 			   "Resetting %s for %s\n", engine->name, msg);
 	atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
 
-	if (!uses_guc)
-		ret = intel_gt_reset_engine(engine);
-	else
+	if (intel_engine_uses_guc(engine))
 		ret = intel_guc_reset_engine(&engine->gt->uc.guc, engine);
+	else
+		ret = intel_gt_reset_engine(engine);
 	if (ret) {
 		/* If we fail here, we expect to fallback to a global reset */
 		ENGINE_TRACE(engine, "Failed to reset, err: %d\n", ret);
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index aee0a77c77e0..7c4d5158e03b 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -51,11 +51,14 @@ int intel_ring_pin(struct intel_ring *ring, struct i915_gem_ww_ctx *ww)
 	if (unlikely(ret))
 		goto err_unpin;
 
-	if (i915_vma_is_map_and_fenceable(vma))
+	if (i915_vma_is_map_and_fenceable(vma)) {
 		addr = (void __force *)i915_vma_pin_iomap(vma);
-	else
-		addr = i915_gem_object_pin_map(vma->obj,
-					       i915_coherent_map_type(vma->vm->i915));
+	} else {
+		int type = i915_coherent_map_type(vma->vm->i915, vma->obj, false);
+
+		addr = i915_gem_object_pin_map(vma->obj, type);
+	}
+
 	if (IS_ERR(addr)) {
 		ret = PTR_ERR(addr);
 		goto err_ring;
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 9585546556ee..2b6dffcc2262 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -12,6 +12,7 @@
 #include "intel_breadcrumbs.h"
 #include "intel_context.h"
 #include "intel_gt.h"
+#include "intel_gt_irq.h"
 #include "intel_reset.h"
 #include "intel_ring.h"
 #include "shmem_utils.h"
@@ -989,14 +990,10 @@ static void gen6_bsd_submit_request(struct i915_request *request)
 static void i9xx_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = i9xx_submit_request;
-
-	engine->park = NULL;
-	engine->unpark = NULL;
 }
 
 static void gen6_bsd_set_default_submission(struct intel_engine_cs *engine)
 {
-	i9xx_set_default_submission(engine);
 	engine->submit_request = gen6_bsd_submit_request;
 }
 
@@ -1021,10 +1018,17 @@ static void ring_release(struct intel_engine_cs *engine)
 	intel_timeline_put(engine->legacy.timeline);
 }
 
+static void irq_handler(struct intel_engine_cs *engine, u16 iir)
+{
+	intel_engine_signal_breadcrumbs(engine);
+}
+
 static void setup_irq(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *i915 = engine->i915;
 
+	intel_engine_set_irq_handler(engine, irq_handler);
+
 	if (INTEL_GEN(i915) >= 6) {
 		engine->irq_enable = gen6_irq_enable;
 		engine->irq_disable = gen6_irq_disable;
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 405d814e9040..97cab1b99871 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -1774,7 +1774,7 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
 		return;
 
 	if (pm_iir & PM_VEBOX_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine[VECS0]);
+		intel_engine_cs_irq(gt->engine[VECS0], pm_iir >> 10);
 
 	if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT)
 		DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir);
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index f19cf6d2fa85..c4a126c8caef 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -32,7 +32,6 @@ static struct i915_vma *hwsp_alloc(struct intel_gt *gt)
 	return vma;
 }
 
-__i915_active_call
 static void __timeline_retire(struct i915_active *active)
 {
 	struct intel_timeline *tl =
@@ -104,7 +103,8 @@ static int intel_timeline_init(struct intel_timeline *timeline,
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
-	i915_active_init(&timeline->active, __timeline_active, __timeline_retire);
+	i915_active_init(&timeline->active, __timeline_active,
+			 __timeline_retire, 0);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 2c6f7217469f..62cb9ee5bfc3 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -607,9 +607,38 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
 }
 
+/*
+ * These settings aren't actually workarounds, but general tuning settings that
+ * need to be programmed on several platforms.
+ */
+static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine,
+				     struct i915_wa_list *wal)
+{
+	/*
+	 * Although some platforms refer to it as Wa_1604555607, we need to
+	 * program it even on those that don't explicitly list that
+	 * workaround.
+	 *
+	 * Note that the programming of this register is further modified
+	 * according to the FF_MODE2 guidance given by Wa_1608008084:gen12.
+	 * Wa_1608008084 tells us the FF_MODE2 register will return the wrong
+	 * value when read. The default value for this register is zero for all
+	 * fields and there are no bit masks. So instead of doing a RMW we
+	 * should just write TDS timer value. For the same reason read
+	 * verification is ignored.
+	 */
+	wa_add(wal,
+	       FF_MODE2,
+	       FF_MODE2_TDS_TIMER_MASK,
+	       FF_MODE2_TDS_TIMER_128,
+	       0);
+}
+
 static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 				       struct i915_wa_list *wal)
 {
+	gen12_ctx_gt_tuning_init(engine, wal);
+
 	/*
 	 * Wa_1409142259:tgl
 	 * Wa_1409347922:tgl
@@ -628,27 +657,17 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_field_set(wal, GEN8_CS_CHICKEN1,
 			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
 			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
-}
-
-static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
-				     struct i915_wa_list *wal)
-{
-	gen12_ctx_workarounds_init(engine, wal);
 
 	/*
-	 * Wa_1604555607:tgl,rkl
+	 * Wa_16011163337
 	 *
-	 * Note that the implementation of this workaround is further modified
-	 * according to the FF_MODE2 guidance given by Wa_1608008084:gen12.
-	 * FF_MODE2 register will return the wrong value when read. The default
-	 * value for this register is zero for all fields and there are no bit
-	 * masks. So instead of doing a RMW we should just write the GS Timer
-	 * and TDS timer values for Wa_1604555607 and Wa_16011163337.
+	 * Like in gen12_ctx_gt_tuning_init(), read verification is ignored due
+	 * to Wa_1608008084.
 	 */
 	wa_add(wal,
 	       FF_MODE2,
-	       FF_MODE2_GS_TIMER_MASK | FF_MODE2_TDS_TIMER_MASK,
-	       FF_MODE2_GS_TIMER_224  | FF_MODE2_TDS_TIMER_128,
+	       FF_MODE2_GS_TIMER_MASK,
+	       FF_MODE2_GS_TIMER_224,
 	       0);
 }
 
@@ -664,16 +683,6 @@ static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine,
 	/* Wa_22010493298 */
 	wa_masked_en(wal, HIZ_CHICKEN,
 		     DG1_HZ_READ_SUPPRESSION_OPTIMIZATION_DISABLE);
-
-	/*
-	 * Wa_16011163337
-	 *
-	 * Like in tgl_ctx_workarounds_init(), read verification is ignored due
-	 * to Wa_1608008084.
-	 */
-	wa_add(wal,
-	       FF_MODE2,
-	       FF_MODE2_GS_TIMER_MASK, FF_MODE2_GS_TIMER_224, 0);
 }
 
 static void
@@ -690,9 +699,6 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
 
 	if (IS_DG1(i915))
 		dg1_ctx_workarounds_init(engine, wal);
-	else if (IS_ALDERLAKE_S(i915) || IS_ROCKETLAKE(i915) ||
-		 IS_TIGERLAKE(i915))
-		tgl_ctx_workarounds_init(engine, wal);
 	else if (IS_GEN(i915, 12))
 		gen12_ctx_workarounds_init(engine, wal);
 	else if (IS_GEN(i915, 11))
@@ -1078,11 +1084,37 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
 }
 
+/*
+ * Though there are per-engine instances of these registers,
+ * they retain their value through engine resets and should
+ * only be provided on the GT workaround list rather than
+ * the engine-specific workaround list.
+ */
+static void
+wa_14011060649(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	struct intel_engine_cs *engine;
+	struct intel_gt *gt = &i915->gt;
+	int id;
+
+	for_each_engine(engine, gt, id) {
+		if (engine->class != VIDEO_DECODE_CLASS ||
+		    (engine->instance % 2))
+			continue;
+
+		wa_write_or(wal, VDBOX_CGCTL3F10(engine->mmio_base),
+			    IECPUNIT_CLKGATE_DIS);
+	}
+}
+
 static void
 gen12_gt_workarounds_init(struct drm_i915_private *i915,
 			  struct i915_wa_list *wal)
 {
 	wa_init_mcr(i915, wal);
+
+	/* Wa_14011060649:tgl,rkl,dg1,adls */
+	wa_14011060649(i915, wal);
 }
 
 static void
@@ -1755,11 +1787,10 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN7_FF_THREAD_MODE,
 			    GEN12_FF_TESSELATION_DOP_GATE_DISABLE);
 
-		/* Wa_22010271021:ehl */
-		if (IS_JSL_EHL(i915))
-			wa_masked_en(wal,
-				     GEN9_CS_DEBUG_MODE1,
-				     FF_DOP_CLOCK_GATE_DISABLE);
+		/* Wa_22010271021 */
+		wa_masked_en(wal,
+			     GEN9_CS_DEBUG_MODE1,
+			     FF_DOP_CLOCK_GATE_DISABLE);
 	}
 
 	if (IS_GEN_RANGE(i915, 9, 12)) {
@@ -1828,9 +1859,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			      CACHE_MODE_0_GEN7,
 			      /* enable HiZ Raw Stall Optimization */
 			      HIZ_RAW_STALL_OPT_DISABLE);
-
-		/* WaDisable4x2SubspanOptimization:hsw */
-		wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
 	}
 
 	if (IS_VALLEYVIEW(i915)) {
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index e1ba03b93ffa..32589c6625e1 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -55,7 +55,7 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine)
 		kfree(ring);
 		return NULL;
 	}
-	i915_active_init(&ring->vma->active, NULL, NULL);
+	i915_active_init(&ring->vma->active, NULL, NULL, 0);
 	__set_bit(I915_VMA_GGTT_BIT, __i915_vma_flags(ring->vma));
 	__set_bit(DRM_MM_NODE_ALLOCATED_BIT, &ring->vma->node.flags);
 	ring->vma->node.size = sz;
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index b9bdd1d23243..26685b927169 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -88,7 +88,8 @@ static int __live_context_size(struct intel_engine_cs *engine)
 		goto err;
 
 	vaddr = i915_gem_object_pin_map_unlocked(ce->state->obj,
-						 i915_coherent_map_type(engine->i915));
+						 i915_coherent_map_type(engine->i915,
+									ce->state->obj, false));
 	if (IS_ERR(vaddr)) {
 		err = PTR_ERR(vaddr);
 		intel_context_unpin(ce);
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
index b2c369317bf1..4896e4ccad50 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -77,7 +77,7 @@ static struct pulse *pulse_create(void)
 		return p;
 
 	kref_init(&p->kref);
-	i915_active_init(&p->active, pulse_active, pulse_retire);
+	i915_active_init(&p->active, pulse_active, pulse_retire, 0);
 
 	return p;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 1081cd36a2bd..1f93591a8c69 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -4716,7 +4716,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_virtual_reset),
 	};
 
-	if (!HAS_EXECLISTS(i915))
+	if (i915->gt.submission_method != INTEL_SUBMISSION_ELSP)
 		return 0;
 
 	if (intel_gt_is_wedged(&i915->gt))
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 746985971c3a..5b63d4df8c93 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -69,7 +69,7 @@ static int hang_init(struct hang *h, struct intel_gt *gt)
 	h->seqno = memset(vaddr, 0xff, PAGE_SIZE);
 
 	vaddr = i915_gem_object_pin_map_unlocked(h->obj,
-						 i915_coherent_map_type(gt->i915));
+						 i915_coherent_map_type(gt->i915, h->obj, false));
 	if (IS_ERR(vaddr)) {
 		err = PTR_ERR(vaddr);
 		goto err_unpin_hws;
@@ -130,7 +130,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 		return ERR_CAST(obj);
 	}
 
-	vaddr = i915_gem_object_pin_map_unlocked(obj, i915_coherent_map_type(gt->i915));
+	vaddr = i915_gem_object_pin_map_unlocked(obj, i915_coherent_map_type(gt->i915, obj, false));
 	if (IS_ERR(vaddr)) {
 		i915_gem_object_put(obj);
 		i915_vm_put(vm);
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 85e7df6a5123..d8f6623524e8 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1221,7 +1221,9 @@ static int compare_isolation(struct intel_engine_cs *engine,
 	}
 
 	lrc = i915_gem_object_pin_map_unlocked(ce->state->obj,
-				      i915_coherent_map_type(engine->i915));
+					       i915_coherent_map_type(engine->i915,
+								      ce->state->obj,
+								      false));
 	if (IS_ERR(lrc)) {
 		err = PTR_ERR(lrc);
 		goto err_B1;
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c
index f097e420ac45..710f825f6e5a 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rc6.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c
@@ -34,6 +34,7 @@ int live_rc6_manual(void *arg)
 	struct intel_rc6 *rc6 = &gt->rc6;
 	u64 rc0_power, rc6_power;
 	intel_wakeref_t wakeref;
+	bool has_power;
 	ktime_t dt;
 	u64 res[2];
 	int err = 0;
@@ -50,6 +51,7 @@ int live_rc6_manual(void *arg)
 	if (IS_VALLEYVIEW(gt->i915) || IS_CHERRYVIEW(gt->i915))
 		return 0;
 
+	has_power = librapl_supported(gt->i915);
 	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
 	/* Force RC6 off for starters */
@@ -71,11 +73,14 @@ int live_rc6_manual(void *arg)
 		goto out_unlock;
 	}
 
-	rc0_power = div64_u64(NSEC_PER_SEC * rc0_power, ktime_to_ns(dt));
-	if (!rc0_power) {
-		pr_err("No power measured while in RC0\n");
-		err = -EINVAL;
-		goto out_unlock;
+	if (has_power) {
+		rc0_power = div64_u64(NSEC_PER_SEC * rc0_power,
+				      ktime_to_ns(dt));
+		if (!rc0_power) {
+			pr_err("No power measured while in RC0\n");
+			err = -EINVAL;
+			goto out_unlock;
+		}
 	}
 
 	/* Manually enter RC6 */
@@ -97,13 +102,16 @@ int live_rc6_manual(void *arg)
 		err = -EINVAL;
 	}
 
-	rc6_power = div64_u64(NSEC_PER_SEC * rc6_power, ktime_to_ns(dt));
-	pr_info("GPU consumed %llduW in RC0 and %llduW in RC6\n",
-		rc0_power, rc6_power);
-	if (2 * rc6_power > rc0_power) {
-		pr_err("GPU leaked energy while in RC6!\n");
-		err = -EINVAL;
-		goto out_unlock;
+	if (has_power) {
+		rc6_power = div64_u64(NSEC_PER_SEC * rc6_power,
+				      ktime_to_ns(dt));
+		pr_info("GPU consumed %llduW in RC0 and %llduW in RC6\n",
+			rc0_power, rc6_power);
+		if (2 * rc6_power > rc0_power) {
+			pr_err("GPU leaked energy while in RC6!\n");
+			err = -EINVAL;
+			goto out_unlock;
+		}
 	}
 
 	/* Restore what should have been the original state! */
diff --git a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c
index 99609271c3a7..c12e74171b63 100644
--- a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c
@@ -291,7 +291,7 @@ int intel_ring_submission_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_ctx_switch_wa),
 	};
 
-	if (HAS_EXECLISTS(i915))
+	if (i915->gt.submission_method > INTEL_SUBMISSION_RING)
 		return 0;
 
 	return intel_gt_live_subtests(tests, &i915->gt);
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index 967641fee42a..3ca1bd5793c3 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -606,7 +606,7 @@ int live_rps_frequency_cs(void *arg)
 	int err = 0;
 
 	/*
-	 * The premise is that the GPU does change freqency at our behest.
+	 * The premise is that the GPU does change frequency at our behest.
 	 * Let's check there is a correspondence between the requested
 	 * frequency, the actual frequency, and the observed clock rate.
 	 */
@@ -747,7 +747,7 @@ int live_rps_frequency_srm(void *arg)
 	int err = 0;
 
 	/*
-	 * The premise is that the GPU does change freqency at our behest.
+	 * The premise is that the GPU does change frequency at our behest.
 	 * Let's check there is a correspondence between the requested
 	 * frequency, the actual frequency, and the observed clock rate.
 	 */
@@ -1139,7 +1139,7 @@ int live_rps_power(void *arg)
 	if (!intel_rps_is_enabled(rps) || INTEL_GEN(gt->i915) < 6)
 		return 0;
 
-	if (!librapl_energy_uJ())
+	if (!librapl_supported(gt->i915))
 		return 0;
 
 	if (igt_spinner_init(&spin, gt))
diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c
index f8f02aab842b..0683b27a3890 100644
--- a/drivers/gpu/drm/i915/gt/shmem_utils.c
+++ b/drivers/gpu/drm/i915/gt/shmem_utils.c
@@ -8,6 +8,7 @@
 #include <linux/shmem_fs.h>
 
 #include "gem/i915_gem_object.h"
+#include "gem/i915_gem_lmem.h"
 #include "shmem_utils.h"
 
 struct file *shmem_create_from_data(const char *name, void *data, size_t len)
@@ -39,7 +40,8 @@ struct file *shmem_create_from_object(struct drm_i915_gem_object *obj)
 		return file;
 	}
 
-	ptr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB);
+	ptr = i915_gem_object_pin_map_unlocked(obj, i915_gem_object_is_lmem(obj) ?
+						I915_MAP_WC : I915_MAP_WB);
 	if (IS_ERR(ptr))
 		return ERR_CAST(ptr);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 78305b2ec89d..adae04c47aab 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -682,7 +682,9 @@ int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	vaddr = i915_gem_object_pin_map_unlocked(vma->obj, I915_MAP_WB);
+	vaddr = i915_gem_object_pin_map_unlocked(vma->obj,
+						 i915_coherent_map_type(guc_to_gt(guc)->i915,
+									vma->obj, true));
 	if (IS_ERR(vaddr)) {
 		i915_vma_unpin_and_release(&vma, 0);
 		return PTR_ERR(vaddr);
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 92688a9b6717..335719f17490 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -11,6 +11,7 @@
 #include "gt/intel_context.h"
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_irq.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_lrc.h"
 #include "gt/intel_mocs.h"
@@ -264,6 +265,14 @@ static void guc_submission_tasklet(struct tasklet_struct *t)
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
+static void cs_irq_handler(struct intel_engine_cs *engine, u16 iir)
+{
+	if (iir & GT_RENDER_USER_INTERRUPT) {
+		intel_engine_signal_breadcrumbs(engine);
+		tasklet_hi_schedule(&engine->execlists.tasklet);
+	}
+}
+
 static void guc_reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -608,35 +617,6 @@ static int guc_resume(struct intel_engine_cs *engine)
 static void guc_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = guc_submit_request;
-	engine->schedule = i915_schedule;
-	engine->execlists.tasklet.callback = guc_submission_tasklet;
-
-	engine->reset.prepare = guc_reset_prepare;
-	engine->reset.rewind = guc_reset_rewind;
-	engine->reset.cancel = guc_reset_cancel;
-	engine->reset.finish = guc_reset_finish;
-
-	engine->flags |= I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
-	engine->flags |= I915_ENGINE_HAS_PREEMPTION;
-
-	/*
-	 * TODO: GuC supports timeslicing and semaphores as well, but they're
-	 * handled by the firmware so some minor tweaks are required before
-	 * enabling.
-	 *
-	 * engine->flags |= I915_ENGINE_HAS_TIMESLICES;
-	 * engine->flags |= I915_ENGINE_HAS_SEMAPHORES;
-	 */
-
-	engine->emit_bb_start = gen8_emit_bb_start;
-
-	/*
-	 * For the breadcrumb irq to work we need the interrupts to stay
-	 * enabled. However, on all platforms on which we'll have support for
-	 * GuC submission we don't allow disabling the interrupts at runtime, so
-	 * we're always safe with the current flow.
-	 */
-	GEM_BUG_ON(engine->irq_enable || engine->irq_disable);
 }
 
 static void guc_release(struct intel_engine_cs *engine)
@@ -658,6 +638,13 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine)
 	engine->cops = &guc_context_ops;
 	engine->request_alloc = guc_request_alloc;
 
+	engine->schedule = i915_schedule;
+
+	engine->reset.prepare = guc_reset_prepare;
+	engine->reset.rewind = guc_reset_rewind;
+	engine->reset.cancel = guc_reset_cancel;
+	engine->reset.finish = guc_reset_finish;
+
 	engine->emit_flush = gen8_emit_flush_xcs;
 	engine->emit_init_breadcrumb = gen8_emit_init_breadcrumb;
 	engine->emit_fini_breadcrumb = gen8_emit_fini_breadcrumb_xcs;
@@ -666,6 +653,19 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine)
 		engine->emit_flush = gen12_emit_flush_xcs;
 	}
 	engine->set_default_submission = guc_set_default_submission;
+
+	engine->flags |= I915_ENGINE_HAS_PREEMPTION;
+
+	/*
+	 * TODO: GuC supports timeslicing and semaphores as well, but they're
+	 * handled by the firmware so some minor tweaks are required before
+	 * enabling.
+	 *
+	 * engine->flags |= I915_ENGINE_HAS_TIMESLICES;
+	 * engine->flags |= I915_ENGINE_HAS_SEMAPHORES;
+	 */
+
+	engine->emit_bb_start = gen8_emit_bb_start;
 }
 
 static void rcs_submission_override(struct intel_engine_cs *engine)
@@ -689,6 +689,7 @@ static void rcs_submission_override(struct intel_engine_cs *engine)
 static inline void guc_default_irqs(struct intel_engine_cs *engine)
 {
 	engine->irq_keep_mask = GT_RENDER_USER_INTERRUPT;
+	intel_engine_set_irq_handler(engine, cs_irq_handler);
 }
 
 int intel_guc_submission_setup(struct intel_engine_cs *engine)
@@ -753,8 +754,3 @@ void intel_guc_submission_init_early(struct intel_guc *guc)
 {
 	guc->submission_selected = __guc_submission_selected(guc);
 }
-
-bool intel_engine_in_guc_submission_mode(const struct intel_engine_cs *engine)
-{
-	return engine->set_default_submission == guc_set_default_submission;
-}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
index 5f7b9e6347d0..3f7005018939 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
@@ -20,7 +20,6 @@ void intel_guc_submission_fini(struct intel_guc *guc);
 int intel_guc_preempt_work_create(struct intel_guc *guc);
 void intel_guc_preempt_work_destroy(struct intel_guc *guc);
 int intel_guc_submission_setup(struct intel_engine_cs *engine);
-bool intel_engine_in_guc_submission_mode(const struct intel_engine_cs *engine);
 
 static inline bool intel_guc_submission_is_supported(struct intel_guc *guc)
 {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index 2126dd81ac38..56d2144dc6a0 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -82,7 +82,9 @@ static int intel_huc_rsa_data_create(struct intel_huc *huc)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	vaddr = i915_gem_object_pin_map_unlocked(vma->obj, I915_MAP_WB);
+	vaddr = i915_gem_object_pin_map_unlocked(vma->obj,
+						 i915_coherent_map_type(gt->i915,
+									vma->obj, true));
 	if (IS_ERR(vaddr)) {
 		i915_vma_unpin_and_release(&vma, 0);
 		return PTR_ERR(vaddr);
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index aa573b078ae7..b1aa1c482c32 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -343,18 +343,15 @@ out:
 void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
+			unsigned long flags,
 			struct lock_class_key *mkey,
 			struct lock_class_key *wkey)
 {
-	unsigned long bits;
-
 	debug_active_init(ref);
 
-	ref->flags = 0;
+	ref->flags = flags;
 	ref->active = active;
-	ref->retire = ptr_unpack_bits(retire, &bits, 2);
-	if (bits & I915_ACTIVE_MAY_SLEEP)
-		ref->flags |= I915_ACTIVE_RETIRE_SLEEPS;
+	ref->retire = retire;
 
 	spin_lock_init(&ref->tree_lock);
 	ref->tree = RB_ROOT;
@@ -1156,8 +1153,7 @@ static int auto_active(struct i915_active *ref)
 	return 0;
 }
 
-__i915_active_call static void
-auto_retire(struct i915_active *ref)
+static void auto_retire(struct i915_active *ref)
 {
 	i915_active_put(ref);
 }
@@ -1171,7 +1167,7 @@ struct i915_active *i915_active_create(void)
 		return NULL;
 
 	kref_init(&aa->ref);
-	i915_active_init(&aa->base, auto_active, auto_retire);
+	i915_active_init(&aa->base, auto_active, auto_retire, 0);
 
 	return &aa->base;
 }
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index fb165d3f01cf..d0feda68b874 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -152,15 +152,16 @@ i915_active_fence_isset(const struct i915_active_fence *active)
 void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
+			unsigned long flags,
 			struct lock_class_key *mkey,
 			struct lock_class_key *wkey);
 
 /* Specialise each class of i915_active to avoid impossible lockdep cycles. */
-#define i915_active_init(ref, active, retire) do {		\
-	static struct lock_class_key __mkey;				\
-	static struct lock_class_key __wkey;				\
-									\
-	__i915_active_init(ref, active, retire, &__mkey, &__wkey);	\
+#define i915_active_init(ref, active, retire, flags) do {			\
+	static struct lock_class_key __mkey;					\
+	static struct lock_class_key __wkey;					\
+										\
+	__i915_active_init(ref, active, retire, flags, &__mkey, &__wkey);	\
 } while (0)
 
 struct dma_fence *
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
index 6360c3e4b765..c149f348a972 100644
--- a/drivers/gpu/drm/i915/i915_active_types.h
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -24,11 +24,6 @@ struct i915_active_fence {
 
 struct active_node;
 
-#define I915_ACTIVE_MAY_SLEEP BIT(0)
-
-#define __i915_active_call __aligned(4)
-#define i915_active_may_sleep(fn) ptr_pack_bits(&(fn), I915_ACTIVE_MAY_SLEEP, 2)
-
 struct i915_active {
 	atomic_t count;
 	struct mutex mutex;
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index e6f1e93abbbb..5b4b2bd46e7c 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1369,6 +1369,20 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length,
 	return 0;
 }
 
+/**
+ * intel_engine_cmd_parser_alloc_jump_whitelist() - preallocate jump whitelist for intel_engine_cmd_parser()
+ * @batch_length: length of the commands in batch_obj
+ * @trampoline: Whether jump trampolines are used.
+ *
+ * Preallocates a jump whitelist for parsing the cmd buffer in intel_engine_cmd_parser().
+ * This has to be preallocated, because the command parser runs in signaling context,
+ * and may not allocate any memory.
+ *
+ * Return: NULL or pointer to a jump whitelist, or ERR_PTR() on failure. Use
+ * IS_ERR() to check for errors. Must bre freed() with kfree().
+ *
+ * NULL is a valid value, meaning no allocation was required.
+ */
 unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
 							    bool trampoline)
 {
@@ -1401,7 +1415,9 @@ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
  * @batch_offset: byte offset in the batch at which execution starts
  * @batch_length: length of the commands in batch_obj
  * @shadow: validated copy of the batch buffer in question
- * @trampoline: whether to emit a conditional trampoline at the end of the batch
+ * @jump_whitelist: buffer preallocated with intel_engine_cmd_parser_alloc_jump_whitelist()
+ * @shadow_map: mapping to @shadow vma
+ * @batch_map: mapping to @batch vma
  *
  * Parses the specified batch buffer looking for privilege violations as
  * described in the overview.
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index b654b7498bcd..8dd374691102 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -622,9 +622,9 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 		seq_printf(m, "DDC2 = 0x%08x\n",
 			   intel_uncore_read(uncore, DCC2));
 		seq_printf(m, "C0DRB3 = 0x%04x\n",
-			   intel_uncore_read16(uncore, C0DRB3));
+			   intel_uncore_read16(uncore, C0DRB3_BW));
 		seq_printf(m, "C1DRB3 = 0x%04x\n",
-			   intel_uncore_read16(uncore, C1DRB3));
+			   intel_uncore_read16(uncore, C1DRB3_BW));
 	} else if (INTEL_GEN(dev_priv) >= 6) {
 		seq_printf(m, "MAD_DIMM_C0 = 0x%08x\n",
 			   intel_uncore_read(uncore, MAD_DIMM_C0));
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index db513f93f0f5..5118dc8386b2 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1727,6 +1727,7 @@ static const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_ENTERVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(I915_GEM_LEAVEVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CREATE, i915_gem_create_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_CREATE_EXT, i915_gem_create_ext_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_RENDER_ALLOW),
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 501a75cd306c..9aee6a045590 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -77,6 +77,7 @@
 #include "gem/i915_gem_context_types.h"
 #include "gem/i915_gem_shrinker.h"
 #include "gem/i915_gem_stolen.h"
+#include "gem/i915_gem_lmem.h"
 
 #include "gt/intel_engine.h"
 #include "gt/intel_gt_types.h"
@@ -513,6 +514,13 @@ struct intel_l3_parity {
 };
 
 struct i915_gem_mm {
+	/*
+	 * Shortcut for the stolen region. This points to either
+	 * INTEL_REGION_STOLEN_SMEM for integrated platforms, or
+	 * INTEL_REGION_STOLEN_LMEM for discrete, or NULL if the device doesn't
+	 * support stolen.
+	 */
+	struct intel_memory_region *stolen_region;
 	/** Memory allocator for GTT stolen memory */
 	struct drm_mm stolen;
 	/** Protects the usage of the GTT stolen memory allocator. This is
@@ -1720,9 +1728,15 @@ static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv)
 }
 
 static inline bool
-intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *dev_priv)
+intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *i915)
 {
-	return IS_BROXTON(dev_priv) && intel_vtd_active();
+	return IS_BROXTON(i915) && intel_vtd_active();
+}
+
+static inline bool
+intel_vm_no_concurrent_access_wa(struct drm_i915_private *i915)
+{
+	return IS_CHERRYVIEW(i915) || intel_ggtt_update_needs_vtd_wa(i915);
 }
 
 /* i915_drv.c */
@@ -1802,6 +1816,7 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0)
 #define I915_GEM_OBJECT_UNBIND_BARRIER BIT(1)
 #define I915_GEM_OBJECT_UNBIND_TEST BIT(2)
+#define I915_GEM_OBJECT_UNBIND_VM_TRYLOCK BIT(3)
 
 void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
 
@@ -1934,9 +1949,15 @@ static inline int intel_hws_csb_write_index(struct drm_i915_private *i915)
 }
 
 static inline enum i915_map_type
-i915_coherent_map_type(struct drm_i915_private *i915)
+i915_coherent_map_type(struct drm_i915_private *i915,
+		       struct drm_i915_gem_object *obj, bool always_coherent)
 {
-	return HAS_LLC(i915) ? I915_MAP_WB : I915_MAP_WC;
+	if (i915_gem_object_is_lmem(obj))
+		return I915_MAP_WC;
+	if (HAS_LLC(i915) || always_coherent)
+		return I915_MAP_WB;
+	else
+		return I915_MAP_WC;
 }
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b3cedd20f365..cffd7f4f87dc 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -157,8 +157,18 @@ try_again:
 		if (vma) {
 			ret = -EBUSY;
 			if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE ||
-			    !i915_vma_is_active(vma))
-				ret = i915_vma_unbind(vma);
+			    !i915_vma_is_active(vma)) {
+				if (flags & I915_GEM_OBJECT_UNBIND_VM_TRYLOCK) {
+					if (mutex_trylock(&vma->vm->mutex)) {
+						ret = __i915_vma_unbind(vma);
+						mutex_unlock(&vma->vm->mutex);
+					} else {
+						ret = -EBUSY;
+					}
+				} else {
+					ret = i915_vma_unbind(vma);
+				}
+			}
 
 			__i915_vma_put(vma);
 		}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index d4611c643446..9ff511862848 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -4024,7 +4024,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		intel_uncore_write16(&dev_priv->uncore, GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]);
+			intel_engine_cs_irq(dev_priv->gt.engine[RCS0], iir);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i8xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -4132,7 +4132,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		intel_uncore_write(&dev_priv->uncore, GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]);
+			intel_engine_cs_irq(dev_priv->gt.engine[RCS0], iir);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -4277,10 +4277,12 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		intel_uncore_write(&dev_priv->uncore, GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]);
+			intel_engine_cs_irq(dev_priv->gt.engine[RCS0],
+					    iir);
 
 		if (iir & I915_BSD_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[VCS0]);
+			intel_engine_cs_irq(dev_priv->gt.engine[VCS0],
+					    iir >> 25);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index 14cd64cc61d0..4a114a5ad000 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -71,18 +71,18 @@ struct drm_printer;
 	param(int, fastboot, -1, 0600) \
 	param(int, enable_dpcd_backlight, -1, 0600) \
 	param(char *, force_probe, CONFIG_DRM_I915_FORCE_PROBE, 0400) \
-	param(unsigned long, fake_lmem_start, 0, 0400) \
-	param(unsigned int, request_timeout_ms, CONFIG_DRM_I915_REQUEST_TIMEOUT, 0600) \
+	param(unsigned long, fake_lmem_start, 0, IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM) ? 0400 : 0) \
+	param(unsigned int, request_timeout_ms, CONFIG_DRM_I915_REQUEST_TIMEOUT, CONFIG_DRM_I915_REQUEST_TIMEOUT ? 0600 : 0) \
 	/* leave bools at the end to not create holes */ \
 	param(bool, enable_hangcheck, true, 0600) \
 	param(bool, load_detect_test, false, 0600) \
 	param(bool, force_reset_modeset_test, false, 0600) \
-	param(bool, error_capture, true, 0600) \
+	param(bool, error_capture, true, IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) ? 0600 : 0) \
 	param(bool, disable_display, false, 0400) \
 	param(bool, verbose_state_checks, true, 0) \
 	param(bool, nuclear_pageflip, false, 0400) \
 	param(bool, enable_dp_mst, true, 0600) \
-	param(bool, enable_gvt, false, 0400)
+	param(bool, enable_gvt, false, IS_ENABLED(CONFIG_DRM_I915_GVT) ? 0400 : 0)
 
 #define MEMBER(T, member, ...) T member;
 struct i915_params {
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 1680062a2149..574881c0e339 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -908,7 +908,7 @@ static const struct intel_device_info rkl_info = {
 };
 
 #define DGFX_FEATURES \
-	.memory_regions = REGION_SMEM | REGION_LMEM, \
+	.memory_regions = REGION_SMEM | REGION_LMEM | REGION_STOLEN_LMEM, \
 	.has_master_unit_irq = 1, \
 	.has_llc = 0, \
 	.has_snoop = 1, \
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index de8ebc34af0f..cb03e4152d2d 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1257,11 +1257,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 	case 8:
 	case 9:
 	case 10:
-		if (intel_engine_in_execlists_submission_mode(ce->engine)) {
-			stream->specific_ctx_id_mask =
-				(1U << GEN8_CTX_ID_WIDTH) - 1;
-			stream->specific_ctx_id = stream->specific_ctx_id_mask;
-		} else {
+		if (intel_engine_uses_guc(ce->engine)) {
 			/*
 			 * When using GuC, the context descriptor we write in
 			 * i915 is read by GuC and rewritten before it's
@@ -1280,6 +1276,10 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 			 */
 			stream->specific_ctx_id_mask =
 				(1U << (GEN8_CTX_ID_WIDTH - 1)) - 1;
+		} else {
+			stream->specific_ctx_id_mask =
+				(1U << GEN8_CTX_ID_WIDTH) - 1;
+			stream->specific_ctx_id = stream->specific_ctx_id_mask;
 		}
 		break;
 
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 41651ac255fa..a75cd1db320b 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -476,6 +476,8 @@ engine_event_status(struct intel_engine_cs *engine,
 static int
 config_status(struct drm_i915_private *i915, u64 config)
 {
+	struct intel_gt *gt = &i915->gt;
+
 	switch (config) {
 	case I915_PMU_ACTUAL_FREQUENCY:
 		if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
@@ -489,7 +491,7 @@ config_status(struct drm_i915_private *i915, u64 config)
 	case I915_PMU_INTERRUPTS:
 		break;
 	case I915_PMU_RC6_RESIDENCY:
-		if (!HAS_RC6(i915))
+		if (!gt->rc6.supported)
 			return -ENODEV;
 		break;
 	case I915_PMU_SOFTWARE_GT_AWAKE_TIME:
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index fed337ad7b68..e49da36c62fb 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -419,11 +419,73 @@ static int query_perf_config(struct drm_i915_private *i915,
 	}
 }
 
+static int query_memregion_info(struct drm_i915_private *i915,
+				struct drm_i915_query_item *query_item)
+{
+	struct drm_i915_query_memory_regions __user *query_ptr =
+		u64_to_user_ptr(query_item->data_ptr);
+	struct drm_i915_memory_region_info __user *info_ptr =
+		&query_ptr->regions[0];
+	struct drm_i915_memory_region_info info = { };
+	struct drm_i915_query_memory_regions query;
+	struct intel_memory_region *mr;
+	u32 total_length;
+	int ret, id, i;
+
+	if (!IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM))
+		return -ENODEV;
+
+	if (query_item->flags != 0)
+		return -EINVAL;
+
+	total_length = sizeof(query);
+	for_each_memory_region(mr, i915, id) {
+		if (mr->private)
+			continue;
+
+		total_length += sizeof(info);
+	}
+
+	ret = copy_query_item(&query, sizeof(query), total_length, query_item);
+	if (ret != 0)
+		return ret;
+
+	if (query.num_regions)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(query.rsvd); i++) {
+		if (query.rsvd[i])
+			return -EINVAL;
+	}
+
+	for_each_memory_region(mr, i915, id) {
+		if (mr->private)
+			continue;
+
+		info.region.memory_class = mr->type;
+		info.region.memory_instance = mr->instance;
+		info.probed_size = mr->total;
+		info.unallocated_size = mr->avail;
+
+		if (__copy_to_user(info_ptr, &info, sizeof(info)))
+			return -EFAULT;
+
+		query.num_regions++;
+		info_ptr++;
+	}
+
+	if (__copy_to_user(query_ptr, &query, sizeof(query)))
+		return -EFAULT;
+
+	return total_length;
+}
+
 static int (* const i915_query_funcs[])(struct drm_i915_private *dev_priv,
 					struct drm_i915_query_item *query_item) = {
 	query_topology_info,
 	query_engine_info,
 	query_perf_config,
+	query_memregion_info,
 };
 
 int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 07cca3b423bc..c294e3f93bed 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -416,6 +416,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN11_VECS_SFC_USAGE(engine)		_MMIO((engine)->mmio_base + 0x2014)
 #define   GEN11_VECS_SFC_USAGE_BIT		(1 << 0)
 
+#define GEN12_HCP_SFC_FORCED_LOCK(engine)	_MMIO((engine)->mmio_base + 0x2910)
+#define   GEN12_HCP_SFC_FORCED_LOCK_BIT		REG_BIT(0)
+#define GEN12_HCP_SFC_LOCK_STATUS(engine)	_MMIO((engine)->mmio_base + 0x2914)
+#define   GEN12_HCP_SFC_LOCK_ACK_BIT		REG_BIT(1)
+#define   GEN12_HCP_SFC_USAGE_BIT			REG_BIT(0)
+
 #define GEN12_SFC_DONE(n)		_MMIO(0x1cc00 + (n) * 0x100)
 #define GEN12_SFC_DONE_MAX		4
 
@@ -487,6 +493,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GAB_CTL				_MMIO(0x24000)
 #define   GAB_CTL_CONT_AFTER_PAGEFAULT	(1 << 8)
 
+#define GU_CNTL				_MMIO(0x101010)
+#define   LMEM_INIT			REG_BIT(7)
+
 #define GEN6_STOLEN_RESERVED		_MMIO(0x1082C0)
 #define GEN6_STOLEN_RESERVED_ADDR_MASK	(0xFFF << 20)
 #define GEN7_STOLEN_RESERVED_ADDR_MASK	(0x3FFF << 18)
@@ -2715,6 +2724,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define RING_INDIRECT_CTX_OFFSET(base)	_MMIO((base) + 0x1c8) /* gen8+ */
 #define RING_CTX_TIMESTAMP(base)	_MMIO((base) + 0x3a8) /* gen8+ */
 
+#define VDBOX_CGCTL3F10(base)		_MMIO((base) + 0x3f10)
+#define   IECPUNIT_CLKGATE_DIS		REG_BIT(22)
+
 #define ERROR_GEN6	_MMIO(0x40a0)
 #define GEN7_ERR_INT	_MMIO(0x44040)
 #define   ERR_INT_POISON		(1 << 31)
@@ -3781,8 +3793,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define CSHRDDR3CTL_DDR3       (1 << 2)
 
 /* 965 MCH register controlling DRAM channel configuration */
-#define C0DRB3			_MMIO(MCHBAR_MIRROR_BASE + 0x206)
-#define C1DRB3			_MMIO(MCHBAR_MIRROR_BASE + 0x606)
+#define C0DRB3_BW		_MMIO(MCHBAR_MIRROR_BASE + 0x206)
+#define C1DRB3_BW		_MMIO(MCHBAR_MIRROR_BASE + 0x606)
 
 /* snb MCH registers for reading the DRAM channel configuration */
 #define MAD_DIMM_C0			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5004)
@@ -12208,6 +12220,7 @@ enum skl_power_gate {
 #define GEN12_GLOBAL_MOCS(i)	_MMIO(0x4000 + (i) * 4) /* Global MOCS regs */
 
 #define GEN12_GSMBASE			_MMIO(0x108100)
+#define GEN12_DSMBASE			_MMIO(0x1080C0)
 
 /* gamt regs */
 #define GEN8_L3_LRA_1_GPGPU _MMIO(0x4dd4)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index bec9c3652188..970d8f4986bb 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -929,7 +929,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	u32 seqno;
 	int ret;
 
-	might_sleep_if(gfpflags_allow_blocking(gfp));
+	might_alloc(gfp);
 
 	/* Check that the caller provided an already pinned context */
 	__intel_context_pin(ce);
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 07490db51cdc..a6cd0fa62847 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -27,6 +27,7 @@
 
 #include "display/intel_frontbuffer.h"
 
+#include "gem/i915_gem_lmem.h"
 #include "gt/intel_engine.h"
 #include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gt.h"
@@ -93,7 +94,6 @@ static int __i915_vma_active(struct i915_active *ref)
 	return i915_vma_tryget(active_to_vma(ref)) ? 0 : -ENOENT;
 }
 
-__i915_active_call
 static void __i915_vma_retire(struct i915_active *ref)
 {
 	i915_vma_put(active_to_vma(ref));
@@ -124,7 +124,7 @@ vma_create(struct drm_i915_gem_object *obj,
 	vma->size = obj->base.size;
 	vma->display_alignment = I915_GTT_MIN_ALIGNMENT;
 
-	i915_active_init(&vma->active, __i915_vma_active, __i915_vma_retire);
+	i915_active_init(&vma->active, __i915_vma_active, __i915_vma_retire, 0);
 
 	/* Declare ourselves safe for use inside shrinkers */
 	if (IS_ENABLED(CONFIG_LOCKDEP)) {
@@ -448,9 +448,11 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 	void __iomem *ptr;
 	int err;
 
-	if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
-		err = -ENODEV;
-		goto err;
+	if (!i915_gem_object_is_lmem(vma->obj)) {
+		if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
+			err = -ENODEV;
+			goto err;
+		}
 	}
 
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
@@ -458,9 +460,19 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 
 	ptr = READ_ONCE(vma->iomap);
 	if (ptr == NULL) {
-		ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->iomap,
-					vma->node.start,
-					vma->node.size);
+		/*
+		 * TODO: consider just using i915_gem_object_pin_map() for lmem
+		 * instead, which already supports mapping non-contiguous chunks
+		 * of pages, that way we can also drop the
+		 * I915_BO_ALLOC_CONTIGUOUS when allocating the object.
+		 */
+		if (i915_gem_object_is_lmem(vma->obj))
+			ptr = i915_gem_object_lmem_io_map(vma->obj, 0,
+							  vma->obj->base.size);
+		else
+			ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->iomap,
+						vma->node.start,
+						vma->node.size);
 		if (ptr == NULL) {
 			err = -ENOMEM;
 			goto err;
@@ -905,8 +917,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 			if (err)
 				goto err_fence;
 
-			err = i915_vm_pin_pt_stash(vma->vm,
-						   &work->stash);
+			err = i915_vm_map_pt_stash(vma->vm, &work->stash);
 			if (err)
 				goto err_fence;
 		}
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index bf837b6bb185..d98e8b81d322 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -22,9 +22,29 @@ static const struct {
 		.class = INTEL_MEMORY_STOLEN_SYSTEM,
 		.instance = 0,
 	},
+	[INTEL_REGION_STOLEN_LMEM] = {
+		.class = INTEL_MEMORY_STOLEN_LOCAL,
+		.instance = 0,
+	},
 };
 
 struct intel_memory_region *
+intel_memory_region_lookup(struct drm_i915_private *i915,
+			   u16 class, u16 instance)
+{
+	struct intel_memory_region *mr;
+	int id;
+
+	/* XXX: consider maybe converting to an rb tree at some point */
+	for_each_memory_region(mr, i915, id) {
+		if (mr->type == class && mr->instance == instance)
+			return mr;
+	}
+
+	return NULL;
+}
+
+struct intel_memory_region *
 intel_memory_region_by_type(struct drm_i915_private *i915,
 			    enum intel_memory_type mem_type)
 {
@@ -278,8 +298,15 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915)
 		case INTEL_MEMORY_SYSTEM:
 			mem = i915_gem_shmem_setup(i915);
 			break;
+		case INTEL_MEMORY_STOLEN_LOCAL:
+			mem = i915_gem_stolen_lmem_setup(i915);
+			if (!IS_ERR(mem))
+				i915->mm.stolen_region = mem;
+			break;
 		case INTEL_MEMORY_STOLEN_SYSTEM:
-			mem = i915_gem_stolen_setup(i915);
+			mem = i915_gem_stolen_smem_setup(i915);
+			if (!IS_ERR(mem))
+				i915->mm.stolen_region = mem;
 			break;
 		default:
 			continue;
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index edd49067c8ca..d24ce5a0b30b 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -11,6 +11,7 @@
 #include <linux/mutex.h>
 #include <linux/io-mapping.h>
 #include <drm/drm_mm.h>
+#include <drm/i915_drm.h>
 
 #include "i915_buddy.h"
 
@@ -19,25 +20,25 @@ struct drm_i915_gem_object;
 struct intel_memory_region;
 struct sg_table;
 
-/**
- *  Base memory type
- */
 enum intel_memory_type {
-	INTEL_MEMORY_SYSTEM = 0,
-	INTEL_MEMORY_LOCAL,
+	INTEL_MEMORY_SYSTEM = I915_MEMORY_CLASS_SYSTEM,
+	INTEL_MEMORY_LOCAL = I915_MEMORY_CLASS_DEVICE,
 	INTEL_MEMORY_STOLEN_SYSTEM,
+	INTEL_MEMORY_STOLEN_LOCAL,
 };
 
 enum intel_region_id {
 	INTEL_REGION_SMEM = 0,
 	INTEL_REGION_LMEM,
 	INTEL_REGION_STOLEN_SMEM,
+	INTEL_REGION_STOLEN_LMEM,
 	INTEL_REGION_UNKNOWN, /* Should be last */
 };
 
 #define REGION_SMEM     BIT(INTEL_REGION_SMEM)
 #define REGION_LMEM     BIT(INTEL_REGION_LMEM)
 #define REGION_STOLEN_SMEM   BIT(INTEL_REGION_STOLEN_SMEM)
+#define REGION_STOLEN_LMEM   BIT(INTEL_REGION_STOLEN_LMEM)
 
 #define I915_ALLOC_MIN_PAGE_SIZE  BIT(0)
 #define I915_ALLOC_CONTIGUOUS     BIT(1)
@@ -82,7 +83,8 @@ struct intel_memory_region {
 	u16 type;
 	u16 instance;
 	enum intel_region_id id;
-	char name[8];
+	char name[16];
+	bool private; /* not for userspace */
 
 	struct list_head reserved;
 
@@ -95,6 +97,10 @@ struct intel_memory_region {
 	} objects;
 };
 
+struct intel_memory_region *
+intel_memory_region_lookup(struct drm_i915_private *i915,
+			   u16 class, u16 instance);
+
 int intel_memory_region_init_buddy(struct intel_memory_region *mem);
 void intel_memory_region_release_buddy(struct intel_memory_region *mem);
 
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index ed5abe7be498..b4aaf8b7109f 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1917,6 +1917,18 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore)
 	if (ret)
 		return ret;
 
+	/*
+	 * The boot firmware initializes local memory and assesses its health.
+	 * If memory training fails, the punit will have been instructed to
+	 * keep the GT powered down; we won't be able to communicate with it
+	 * and we should not continue with driver initialization.
+	 */
+	if (IS_DGFX(i915) &&
+	    !(__raw_uncore_read32(uncore, GU_CNTL) & LMEM_INIT)) {
+		drm_err(&i915->drm, "LMEM not initialized by firmware\n");
+		return -ENODEV;
+	}
+
 	if (INTEL_GEN(i915) > 5 && !intel_vgpu_active(i915))
 		uncore->flags |= UNCORE_HAS_FORCEWAKE;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index 4002c984c2e0..61bf4560d8af 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -68,7 +68,7 @@ static struct live_active *__live_alloc(struct drm_i915_private *i915)
 		return NULL;
 
 	kref_init(&active->ref);
-	i915_active_init(&active->base, __live_active, __live_retire);
+	i915_active_init(&active->base, __live_active, __live_retire, 0);
 
 	return active;
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index dc394fb7ccfa..152d9ab135b1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -87,14 +87,14 @@ static void simulate_hibernate(struct drm_i915_private *i915)
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 }
 
-static int pm_prepare(struct drm_i915_private *i915)
+static int igt_pm_prepare(struct drm_i915_private *i915)
 {
 	i915_gem_suspend(i915);
 
 	return 0;
 }
 
-static void pm_suspend(struct drm_i915_private *i915)
+static void igt_pm_suspend(struct drm_i915_private *i915)
 {
 	intel_wakeref_t wakeref;
 
@@ -104,7 +104,7 @@ static void pm_suspend(struct drm_i915_private *i915)
 	}
 }
 
-static void pm_hibernate(struct drm_i915_private *i915)
+static void igt_pm_hibernate(struct drm_i915_private *i915)
 {
 	intel_wakeref_t wakeref;
 
@@ -116,7 +116,7 @@ static void pm_hibernate(struct drm_i915_private *i915)
 	}
 }
 
-static void pm_resume(struct drm_i915_private *i915)
+static void igt_pm_resume(struct drm_i915_private *i915)
 {
 	intel_wakeref_t wakeref;
 
@@ -148,16 +148,16 @@ static int igt_gem_suspend(void *arg)
 	if (err)
 		goto out;
 
-	err = pm_prepare(i915);
+	err = igt_pm_prepare(i915);
 	if (err)
 		goto out;
 
-	pm_suspend(i915);
+	igt_pm_suspend(i915);
 
 	/* Here be dragons! Note that with S3RST any S3 may become S4! */
 	simulate_hibernate(i915);
 
-	pm_resume(i915);
+	igt_pm_resume(i915);
 
 	err = switch_to_context(ctx);
 out:
@@ -183,16 +183,16 @@ static int igt_gem_hibernate(void *arg)
 	if (err)
 		goto out;
 
-	err = pm_prepare(i915);
+	err = igt_pm_prepare(i915);
 	if (err)
 		goto out;
 
-	pm_hibernate(i915);
+	igt_pm_hibernate(i915);
 
 	/* Here be dragons! */
 	simulate_hibernate(i915);
 
-	pm_resume(i915);
+	igt_pm_resume(i915);
 
 	err = switch_to_context(ctx);
 out:
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 45c6c0107c7c..0a1472bb12bc 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -186,7 +186,7 @@ retry:
 		if (err)
 			goto err_ppgtt_cleanup;
 
-		err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash);
+		err = i915_vm_map_pt_stash(&ppgtt->vm, &stash);
 		if (err) {
 			i915_vm_free_pt_stash(&ppgtt->vm, &stash);
 			goto err_ppgtt_cleanup;
@@ -208,7 +208,7 @@ retry:
 		if (err)
 			goto err_ppgtt_cleanup;
 
-		err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash);
+		err = i915_vm_map_pt_stash(&ppgtt->vm, &stash);
 		if (err) {
 			i915_vm_free_pt_stash(&ppgtt->vm, &stash);
 			goto err_ppgtt_cleanup;
@@ -325,11 +325,10 @@ retry:
 							   BIT_ULL(size)))
 					goto alloc_vm_end;
 
-				err = i915_vm_pin_pt_stash(vm, &stash);
+				err = i915_vm_map_pt_stash(vm, &stash);
 				if (!err)
 					vm->allocate_va_range(vm, &stash,
 							      addr, BIT_ULL(size));
-
 				i915_vm_free_pt_stash(vm, &stash);
 alloc_vm_end:
 				if (err == -EDEADLK) {
@@ -1968,10 +1967,9 @@ retry:
 			if (err)
 				goto end_ww;
 
-			err = i915_vm_pin_pt_stash(vm, &stash);
+			err = i915_vm_map_pt_stash(vm, &stash);
 			if (!err)
 				vm->allocate_va_range(vm, &stash, offset, chunk_size);
-
 			i915_vm_free_pt_stash(vm, &stash);
 end_ww:
 			if (err == -EDEADLK) {
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
index e9d86dab8677..bfb0290967a1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -307,7 +307,7 @@ static int live_noa_gpr(void *arg)
 	}
 
 	/* Poison the ce->vm so we detect writes not to the GGTT gt->scratch */
-	scratch = kmap(__px_page(ce->vm->scratch[0]));
+	scratch = __px_vaddr(ce->vm->scratch[0]);
 	memset(scratch, POISON_FREE, PAGE_SIZE);
 
 	rq = intel_context_create_request(ce);
@@ -405,7 +405,6 @@ static int live_noa_gpr(void *arg)
 out_rq:
 	i915_request_put(rq);
 out_ce:
-	kunmap(__px_page(ce->vm->scratch[0]));
 	intel_context_put(ce);
 out:
 	stream_destroy(stream);
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index 5fe7b80ca0bd..dd0607254a95 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -967,6 +967,9 @@ static int igt_vma_remapped_gtt(void *arg)
 	intel_wakeref_t wakeref;
 	int err = 0;
 
+	if (!i915_ggtt_has_aperture(&i915->ggtt))
+		return 0;
+
 	obj = i915_gem_object_create_internal(i915, 10 * 10 * PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c
index cfbbe415b57c..5fe397b7d1d9 100644
--- a/drivers/gpu/drm/i915/selftests/igt_spinner.c
+++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c
@@ -94,9 +94,9 @@ int igt_spinner_pin(struct igt_spinner *spin,
 	}
 
 	if (!spin->batch) {
-		unsigned int mode =
-			i915_coherent_map_type(spin->gt->i915);
+		unsigned int mode;
 
+		mode = i915_coherent_map_type(spin->gt->i915, spin->obj, false);
 		vaddr = igt_spinner_pin_obj(ce, ww, spin->obj, mode, &spin->batch_vma);
 		if (IS_ERR(vaddr))
 			return PTR_ERR(vaddr);
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index a5fc0bf3feb9..f85fd8cbfbf5 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -513,7 +513,7 @@ static int igt_cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 	if (err)
 		return err;
 
-	ptr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC);
+	ptr = i915_gem_object_pin_map(obj, I915_MAP_WC);
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
 
@@ -593,7 +593,9 @@ static int igt_gpu_write(struct i915_gem_context *ctx,
 		if (err)
 			break;
 
+		i915_gem_object_lock(obj, NULL);
 		err = igt_cpu_check(obj, dword, rng);
+		i915_gem_object_unlock(obj);
 		if (err)
 			break;
 	} while (!__igt_timeout(end_time, NULL));
@@ -629,6 +631,88 @@ out_put:
 	return err;
 }
 
+static int igt_lmem_create_cleared_cpu(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	I915_RND_STATE(prng);
+	IGT_TIMEOUT(end_time);
+	u32 size, i;
+	int err;
+
+	i915_gem_drain_freed_objects(i915);
+
+	size = max_t(u32, PAGE_SIZE, i915_prandom_u32_max_state(SZ_32M, &prng));
+	size = round_up(size, PAGE_SIZE);
+	i = 0;
+
+	do {
+		struct drm_i915_gem_object *obj;
+		unsigned int flags;
+		u32 dword, val;
+		void *vaddr;
+
+		/*
+		 * Alternate between cleared and uncleared allocations, while
+		 * also dirtying the pages each time to check that the pages are
+		 * always cleared if requested, since we should get some overlap
+		 * of the underlying pages, if not all, since we are the only
+		 * user.
+		 */
+
+		flags = I915_BO_ALLOC_CPU_CLEAR;
+		if (i & 1)
+			flags = 0;
+
+		obj = i915_gem_object_create_lmem(i915, size, flags);
+		if (IS_ERR(obj))
+			return PTR_ERR(obj);
+
+		i915_gem_object_lock(obj, NULL);
+		err = i915_gem_object_pin_pages(obj);
+		if (err)
+			goto out_put;
+
+		dword = i915_prandom_u32_max_state(PAGE_SIZE / sizeof(u32),
+						   &prng);
+
+		if (flags & I915_BO_ALLOC_CPU_CLEAR) {
+			err = igt_cpu_check(obj, dword, 0);
+			if (err) {
+				pr_err("%s failed with size=%u, flags=%u\n",
+				       __func__, size, flags);
+				goto out_unpin;
+			}
+		}
+
+		vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+		if (IS_ERR(vaddr)) {
+			err = PTR_ERR(vaddr);
+			goto out_unpin;
+		}
+
+		val = prandom_u32_state(&prng);
+
+		memset32(vaddr, val, obj->base.size / sizeof(u32));
+
+		i915_gem_object_flush_map(obj);
+		i915_gem_object_unpin_map(obj);
+out_unpin:
+		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj);
+out_put:
+		i915_gem_object_unlock(obj);
+		i915_gem_object_put(obj);
+
+		if (err)
+			break;
+		++i;
+	} while (!__igt_timeout(end_time, NULL));
+
+	pr_info("%s completed (%u) iterations\n", __func__, i);
+
+	return err;
+}
+
 static int igt_lmem_write_gpu(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -1043,6 +1127,7 @@ int intel_memory_region_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_lmem_create),
+		SUBTEST(igt_lmem_create_cleared_cpu),
 		SUBTEST(igt_lmem_write_cpu),
 		SUBTEST(igt_lmem_write_gpu),
 	};
diff --git a/drivers/gpu/drm/i915/selftests/librapl.c b/drivers/gpu/drm/i915/selftests/librapl.c
index 58710ac3f979..eb03b5b28bad 100644
--- a/drivers/gpu/drm/i915/selftests/librapl.c
+++ b/drivers/gpu/drm/i915/selftests/librapl.c
@@ -5,8 +5,18 @@
 
 #include <asm/msr.h>
 
+#include "i915_drv.h"
 #include "librapl.h"
 
+bool librapl_supported(const struct drm_i915_private *i915)
+{
+	/* Discrete cards require hwmon integration */
+	if (IS_DGFX(i915))
+		return false;
+
+	return librapl_energy_uJ();
+}
+
 u64 librapl_energy_uJ(void)
 {
 	unsigned long long power;
diff --git a/drivers/gpu/drm/i915/selftests/librapl.h b/drivers/gpu/drm/i915/selftests/librapl.h
index 887f3e91dd05..e3b24fad0a7a 100644
--- a/drivers/gpu/drm/i915/selftests/librapl.h
+++ b/drivers/gpu/drm/i915/selftests/librapl.h
@@ -8,6 +8,10 @@
 
 #include <linux/types.h>
 
+struct drm_i915_private;
+
+bool librapl_supported(const struct drm_i915_private *i915);
+
 u64 librapl_energy_uJ(void);
 
 #endif /* SELFTEST_LIBRAPL_H */