drm/i915: use pat_index instead of cache_level

Currently the KMD is using enum i915_cache_level to set caching policy for
buffer objects. This is flaky because the PAT index which really controls
the caching behavior in PTE has far more levels than what's defined in the
enum. In addition, the PAT index is platform dependent, having to translate
between i915_cache_level and PAT index is not reliable, and makes the code
more complicated.

From UMD's perspective there is also a necessity to set caching policy for
performance fine tuning. It's much easier for the UMD to directly use PAT
index because the behavior of each PAT index is clearly defined in Bspec.
Having the abstracted i915_cache_level sitting in between would only cause
more ambiguity. PAT is expected to work much like MOCS already works today,
and by design userspace is expected to select the index that exactly
matches the desired behavior described in the hardware specification.

For these reasons this patch replaces i915_cache_level with PAT index. Also
note, the cache_level is not completely removed yet, because the KMD still
has the need of creating buffer objects with simple cache settings such as
cached, uncached, or writethrough. For kernel objects, cache_level is used
for simplicity and backward compatibility. For Pre-gen12 platforms PAT can
have 1:1 mapping to i915_cache_level, so these two are interchangeable. see
the use of LEGACY_CACHELEVEL.

One consequence of this change is that gen8_pte_encode is no longer working
for gen12 platforms due to the fact that gen12 platforms has different PAT
definitions. In the meantime the mtl_pte_encode introduced specfically for
MTL becomes generic for all gen12 platforms. This patch renames the MTL
PTE encode function into gen12_pte_encode and apply it to all gen12. Even
though this change looks unrelated, but separating them would temporarily
break gen12 PTE encoding, thus squash them in one patch.

Special note: this patch changes the way caching behavior is controlled in
the sense that some objects are left to be managed by userspace. For such
objects we need to be careful not to change the userspace settings.There
are kerneldoc and comments added around obj->cache_coherent, cache_dirty,
and how to bypass the checkings by i915_gem_object_has_cache_level. For
full understanding, these changes need to be looked at together with the
two follow-up patches, one disables the {set|get}_caching ioctl's and the
other adds set_pat extension to the GEM_CREATE uAPI.

Bspec: 63019

Cc: Chris Wilson <chris.p.wilson@linux.intel.com>
Signed-off-by: Fei Yang <fei.yang@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230509165200.1740-3-fei.yang@intel.com

36 files changed, 453 insertions, 238 deletions

diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c
index c5eacfdba1a5..7c5fddb203ba 100644
--- a/drivers/gpu/drm/i915/display/intel_dpt.c
+++ b/drivers/gpu/drm/i915/display/intel_dpt.c
@@ -43,24 +43,24 @@ static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
 static void dpt_insert_page(struct i915_address_space *vm,
 			    dma_addr_t addr,
 			    u64 offset,
-			    enum i915_cache_level level,
+			    unsigned int pat_index,
 			    u32 flags)
 {
 	struct i915_dpt *dpt = i915_vm_to_dpt(vm);
 	gen8_pte_t __iomem *base = dpt->iomem;
 
 	gen8_set_pte(base + offset / I915_GTT_PAGE_SIZE,
-		     vm->pte_encode(addr, level, flags));
+		     vm->pte_encode(addr, pat_index, flags));
 }
 
 static void dpt_insert_entries(struct i915_address_space *vm,
 			       struct i915_vma_resource *vma_res,
-			       enum i915_cache_level level,
+			       unsigned int pat_index,
 			       u32 flags)
 {
 	struct i915_dpt *dpt = i915_vm_to_dpt(vm);
 	gen8_pte_t __iomem *base = dpt->iomem;
-	const gen8_pte_t pte_encode = vm->pte_encode(0, level, flags);
+	const gen8_pte_t pte_encode = vm->pte_encode(0, pat_index, flags);
 	struct sgt_iter sgt_iter;
 	dma_addr_t addr;
 	int i;
@@ -83,7 +83,7 @@ static void dpt_clear_range(struct i915_address_space *vm,
 static void dpt_bind_vma(struct i915_address_space *vm,
 			 struct i915_vm_pt_stash *stash,
 			 struct i915_vma_resource *vma_res,
-			 enum i915_cache_level cache_level,
+			 unsigned int pat_index,
 			 u32 flags)
 {
 	u32 pte_flags;
@@ -98,7 +98,7 @@ static void dpt_bind_vma(struct i915_address_space *vm,
 	if (vma_res->bi.lmem)
 		pte_flags |= PTE_LM;
 
-	vm->insert_entries(vm, vma_res, cache_level, pte_flags);
+	vm->insert_entries(vm, vma_res, pat_index, pte_flags);
 
 	vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index d2d5a24301b2..05107a6efe45 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -27,8 +27,15 @@ static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj)
 	if (IS_DGFX(i915))
 		return false;
 
-	return !(obj->cache_level == I915_CACHE_NONE ||
-		 obj->cache_level == I915_CACHE_WT);
+	/*
+	 * For objects created by userspace through GEM_CREATE with pat_index
+	 * set by set_pat extension, i915_gem_object_has_cache_level() will
+	 * always return true, because the coherency of such object is managed
+	 * by userspace. Othereise the call here would fall back to checking
+	 * whether the object is un-cached or write-through.
+	 */
+	return !(i915_gem_object_has_cache_level(obj, I915_CACHE_NONE) ||
+		 i915_gem_object_has_cache_level(obj, I915_CACHE_WT));
 }
 
 bool i915_gem_cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
@@ -267,7 +274,13 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 {
 	int ret;
 
-	if (obj->cache_level == cache_level)
+	/*
+	 * For objects created by userspace through GEM_CREATE with pat_index
+	 * set by set_pat extension, simply return 0 here without touching
+	 * the cache setting, because such objects should have an immutable
+	 * cache setting by desgin and always managed by userspace.
+	 */
+	if (i915_gem_object_has_cache_level(obj, cache_level))
 		return 0;
 
 	ret = i915_gem_object_wait(obj,
@@ -278,10 +291,8 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		return ret;
 
 	/* Always invalidate stale cachelines */
-	if (obj->cache_level != cache_level) {
-		i915_gem_object_set_cache_coherency(obj, cache_level);
-		obj->cache_dirty = true;
-	}
+	i915_gem_object_set_cache_coherency(obj, cache_level);
+	obj->cache_dirty = true;
 
 	/* The cache-level will be applied when each vma is rebound. */
 	return i915_gem_object_unbind(obj,
@@ -306,20 +317,22 @@ int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	switch (obj->cache_level) {
-	case I915_CACHE_LLC:
-	case I915_CACHE_L3_LLC:
-		args->caching = I915_CACHING_CACHED;
-		break;
+	/*
+	 * This ioctl should be disabled for the objects with pat_index
+	 * set by user space.
+	 */
+	if (obj->pat_set_by_user) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
 
-	case I915_CACHE_WT:
+	if (i915_gem_object_has_cache_level(obj, I915_CACHE_LLC) ||
+	    i915_gem_object_has_cache_level(obj, I915_CACHE_L3_LLC))
+		args->caching = I915_CACHING_CACHED;
+	else if (i915_gem_object_has_cache_level(obj, I915_CACHE_WT))
 		args->caching = I915_CACHING_DISPLAY;
-		break;
-
-	default:
+	else
 		args->caching = I915_CACHING_NONE;
-		break;
-	}
 out:
 	rcu_read_unlock();
 	return err;
@@ -365,6 +378,15 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 		return -ENOENT;
 
 	/*
+	 * This ioctl should be disabled for the objects with pat_index
+	 * set by user space.
+	 */
+	if (obj->pat_set_by_user) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	/*
 	 * The caching mode of proxy object is handled by its generator, and
 	 * not allowed to be changed by userspace.
 	 */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 3aeede6aee4d..5fb459ea4294 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -640,9 +640,15 @@ static inline int use_cpu_reloc(const struct reloc_cache *cache,
 	if (DBG_FORCE_RELOC == FORCE_GTT_RELOC)
 		return false;
 
+	/*
+	 * For objects created by userspace through GEM_CREATE with pat_index
+	 * set by set_pat extension, i915_gem_object_has_cache_level() always
+	 * return true, otherwise the call would fall back to checking whether
+	 * the object is un-cached.
+	 */
 	return (cache->has_llc ||
 		obj->cache_dirty ||
-		obj->cache_level != I915_CACHE_NONE);
+		!i915_gem_object_has_cache_level(obj, I915_CACHE_NONE));
 }
 
 static int eb_reserve_vma(struct i915_execbuffer *eb,
@@ -1324,7 +1330,10 @@ static void *reloc_iomap(struct i915_vma *batch,
 	if (drm_mm_node_allocated(&cache->node)) {
 		ggtt->vm.insert_page(&ggtt->vm,
 				     i915_gem_object_get_dma_address(obj, page),
-				     offset, I915_CACHE_NONE, 0);
+				     offset,
+				     i915_gem_get_pat_index(ggtt->vm.i915,
+							    I915_CACHE_NONE),
+				     0);
 	} else {
 		offset += page << PAGE_SHIFT;
 	}
@@ -1464,7 +1473,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 			reloc_cache_unmap(&eb->reloc_cache);
 			mutex_lock(&vma->vm->mutex);
 			err = i915_vma_bind(target->vma,
-					    target->vma->obj->cache_level,
+					    target->vma->obj->pat_index,
 					    PIN_GLOBAL, NULL, NULL);
 			mutex_unlock(&vma->vm->mutex);
 			reloc_cache_remap(&eb->reloc_cache, ev->vma->obj);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 3dbacdf0911a..4e7a838ab7bd 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -383,7 +383,16 @@ retry:
 	}
 
 	/* Access to snoopable pages through the GTT is incoherent. */
-	if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(i915)) {
+	/*
+	 * For objects created by userspace through GEM_CREATE with pat_index
+	 * set by set_pat extension, coherency is managed by userspace, make
+	 * sure we don't fail handling the vm fault by calling
+	 * i915_gem_object_has_cache_level() which always return true for such
+	 * objects. Otherwise this helper function would fall back to checking
+	 * whether the object is un-cached.
+	 */
+	if (!(i915_gem_object_has_cache_level(obj, I915_CACHE_NONE) ||
+	      HAS_LLC(i915))) {
 		ret = -EFAULT;
 		goto err_unpin;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 8c70a0ec7d2f..46a19b099ec8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -54,6 +54,24 @@ unsigned int i915_gem_get_pat_index(struct drm_i915_private *i915,
 	return INTEL_INFO(i915)->cachelevel_to_pat[level];
 }
 
+bool i915_gem_object_has_cache_level(const struct drm_i915_gem_object *obj,
+				     enum i915_cache_level lvl)
+{
+	/*
+	 * In case the pat_index is set by user space, this kernel mode
+	 * driver should leave the coherency to be managed by user space,
+	 * simply return true here.
+	 */
+	if (obj->pat_set_by_user)
+		return true;
+
+	/*
+	 * Otherwise the pat_index should have been converted from cache_level
+	 * so that the following comparison is valid.
+	 */
+	return obj->pat_index == i915_gem_get_pat_index(obj_to_i915(obj), lvl);
+}
+
 struct drm_i915_gem_object *i915_gem_object_alloc(void)
 {
 	struct drm_i915_gem_object *obj;
@@ -133,7 +151,7 @@ void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj,
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 
-	obj->cache_level = cache_level;
+	obj->pat_index = i915_gem_get_pat_index(i915, cache_level);
 
 	if (cache_level != I915_CACHE_NONE)
 		obj->cache_coherent = (I915_BO_CACHE_COHERENT_FOR_READ |
@@ -148,6 +166,37 @@ void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj,
 		!IS_DGFX(i915);
 }
 
+/**
+ * i915_gem_object_set_pat_index - set PAT index to be used in PTE encode
+ * @obj: #drm_i915_gem_object
+ * @pat_index: PAT index
+ *
+ * This is a clone of i915_gem_object_set_cache_coherency taking pat index
+ * instead of cache_level as its second argument.
+ */
+void i915_gem_object_set_pat_index(struct drm_i915_gem_object *obj,
+				   unsigned int pat_index)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+
+	if (obj->pat_index == pat_index)
+		return;
+
+	obj->pat_index = pat_index;
+
+	if (pat_index != i915_gem_get_pat_index(i915, I915_CACHE_NONE))
+		obj->cache_coherent = (I915_BO_CACHE_COHERENT_FOR_READ |
+				       I915_BO_CACHE_COHERENT_FOR_WRITE);
+	else if (HAS_LLC(i915))
+		obj->cache_coherent = I915_BO_CACHE_COHERENT_FOR_READ;
+	else
+		obj->cache_coherent = 0;
+
+	obj->cache_dirty =
+		!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE) &&
+		!IS_DGFX(i915);
+}
+
 bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 284e1aa396cd..884a17275b3a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -34,6 +34,8 @@ static inline bool i915_gem_object_size_2big(u64 size)
 
 unsigned int i915_gem_get_pat_index(struct drm_i915_private *i915,
 				    enum i915_cache_level level);
+bool i915_gem_object_has_cache_level(const struct drm_i915_gem_object *obj,
+				     enum i915_cache_level lvl);
 void i915_gem_init__objects(struct drm_i915_private *i915);
 
 void i915_objects_module_exit(void);
@@ -764,6 +766,8 @@ bool i915_gem_object_has_unknown_state(struct drm_i915_gem_object *obj);
 
 void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj,
 					 unsigned int cache_level);
+void i915_gem_object_set_pat_index(struct drm_i915_gem_object *obj,
+				   unsigned int pat_index);
 bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj);
 void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj);
 void i915_gem_object_flush_if_display_locked(struct drm_i915_gem_object *obj);
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 bf0bd8e11355..e72c57716bee 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -364,15 +364,43 @@ struct drm_i915_gem_object {
 #define I915_BO_FLAG_STRUCT_PAGE BIT(0) /* Object backed by struct pages */
 #define I915_BO_FLAG_IOMEM       BIT(1) /* Object backed by IO memory */
 	/**
-	 * @cache_level: The desired GTT caching level.
+	 * @pat_index: The desired PAT index.
+	 *
+	 * See hardware specification for valid PAT indices for each platform.
+	 * This field replaces the @cache_level that contains a value of enum
+	 * i915_cache_level since PAT indices are being used by both userspace
+	 * and kernel mode driver for caching policy control after GEN12.
+	 * In the meantime platform specific tables are created to translate
+	 * i915_cache_level into pat index, for more details check the macros
+	 * defined i915/i915_pci.c, e.g. PVC_CACHELEVEL.
+	 * For backward compatibility, this field contains values exactly match
+	 * the entries of enum i915_cache_level for pre-GEN12 platforms (See
+	 * LEGACY_CACHELEVEL), so that the PTE encode functions for these
+	 * legacy platforms can stay the same.
+	 */
+	unsigned int pat_index:6;
+	/**
+	 * @pat_set_by_user: Indicate whether pat_index is set by user space
 	 *
-	 * See enum i915_cache_level for possible values, along with what
-	 * each does.
+	 * This field is set to false by default, only set to true if the
+	 * pat_index is set by user space. By design, user space is capable of
+	 * managing caching behavior by setting pat_index, in which case this
+	 * kernel mode driver should never touch the pat_index.
 	 */
-	unsigned int cache_level:3;
+	unsigned int pat_set_by_user:1;
 	/**
 	 * @cache_coherent:
 	 *
+	 * Note: with the change above which replaced @cache_level with pat_index,
+	 * the use of @cache_coherent is limited to the objects created by kernel
+	 * or by userspace without pat index specified.
+	 * Check for @pat_set_by_user to find out if an object has pat index set
+	 * by userspace. The ioctl's to change cache settings have also been
+	 * disabled for the objects with pat index set by userspace. Please don't
+	 * assume @cache_coherent having the flags set as describe here. A helper
+	 * function i915_gem_object_has_cache_level() provides one way to bypass
+	 * the use of this field.
+	 *
 	 * Track whether the pages are coherent with the GPU if reading or
 	 * writing through the CPU caches. The largely depends on the
 	 * @cache_level setting.
@@ -446,6 +474,16 @@ struct drm_i915_gem_object {
 	/**
 	 * @cache_dirty:
 	 *
+	 * Note: with the change above which replaced cache_level with pat_index,
+	 * the use of @cache_dirty is limited to the objects created by kernel
+	 * or by userspace without pat index specified.
+	 * Check for @pat_set_by_user to find out if an object has pat index set
+	 * by userspace. The ioctl's to change cache settings have also been
+	 * disabled for the objects with pat_index set by userspace. Please don't
+	 * assume @cache_dirty is set as describe here. Also see helper function
+	 * i915_gem_object_has_cache_level() for possible ways to bypass the use
+	 * of this field.
+	 *
 	 * Track if we are we dirty with writes through the CPU cache for this
 	 * object. As a result reading directly from main memory might yield
 	 * stale data.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index ee492d823f1b..3b094d36a0b0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -565,7 +565,9 @@ static void dbg_poison(struct i915_ggtt *ggtt,
 
 		ggtt->vm.insert_page(&ggtt->vm, addr,
 				     ggtt->error_capture.start,
-				     I915_CACHE_NONE, 0);
+				     i915_gem_get_pat_index(ggtt->vm.i915,
+							    I915_CACHE_NONE),
+				     0);
 		mb();
 
 		s = io_mapping_map_wc(&ggtt->iomap,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
index 69eb20ed4d47..7078af2f8f79 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
@@ -214,7 +214,8 @@ static struct dma_fence *i915_ttm_accel_move(struct ttm_buffer_object *bo,
 
 		intel_engine_pm_get(to_gt(i915)->migrate.context->engine);
 		ret = intel_context_migrate_clear(to_gt(i915)->migrate.context, deps,
-						  dst_st->sgl, dst_level,
+						  dst_st->sgl,
+						  i915_gem_get_pat_index(i915, dst_level),
 						  i915_ttm_gtt_binds_lmem(dst_mem),
 						  0, &rq);
 	} else {
@@ -228,9 +229,10 @@ static struct dma_fence *i915_ttm_accel_move(struct ttm_buffer_object *bo,
 		intel_engine_pm_get(to_gt(i915)->migrate.context->engine);
 		ret = intel_context_migrate_copy(to_gt(i915)->migrate.context,
 						 deps, src_rsgt->table.sgl,
-						 src_level,
+						 i915_gem_get_pat_index(i915, src_level),
 						 i915_ttm_gtt_binds_lmem(bo->resource),
-						 dst_st->sgl, dst_level,
+						 dst_st->sgl,
+						 i915_gem_get_pat_index(i915, dst_level),
 						 i915_ttm_gtt_binds_lmem(dst_mem),
 						 &rq);
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index cb5863f37f9d..763df437c20c 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -354,7 +354,7 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single)
 
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
-	obj->cache_level = I915_CACHE_NONE;
+	obj->pat_index = i915_gem_get_pat_index(i915, I915_CACHE_NONE);
 
 	return obj;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c
index fe6c37fd7859..a93a90b15907 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c
@@ -219,7 +219,7 @@ static int __igt_lmem_pages_migrate(struct intel_gt *gt,
 			continue;
 
 		err = intel_migrate_clear(&gt->migrate, &ww, deps,
-					  obj->mm.pages->sgl, obj->cache_level,
+					  obj->mm.pages->sgl, obj->pat_index,
 					  i915_gem_object_is_lmem(obj),
 					  0xdeadbeaf, &rq);
 		if (rq) {
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 56279908ed30..a93d8f9f8bc1 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -1222,7 +1222,7 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements,
 	}
 
 	err = intel_context_migrate_clear(to_gt(i915)->migrate.context, NULL,
-					  obj->mm.pages->sgl, obj->cache_level,
+					  obj->mm.pages->sgl, obj->pat_index,
 					  i915_gem_object_is_lmem(obj),
 					  expand32(POISON_INUSE), &rq);
 	i915_gem_object_unpin_pages(obj);
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
index 5aaacc53fa4c..c2bdc133c89a 100644
--- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -109,7 +109,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 
 static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct i915_vma_resource *vma_res,
-				      enum i915_cache_level cache_level,
+				      unsigned int pat_index,
 				      u32 flags)
 {
 	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
@@ -117,7 +117,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 	unsigned int first_entry = vma_res->start / I915_GTT_PAGE_SIZE;
 	unsigned int act_pt = first_entry / GEN6_PTES;
 	unsigned int act_pte = first_entry % GEN6_PTES;
-	const u32 pte_encode = vm->pte_encode(0, cache_level, flags);
+	const u32 pte_encode = vm->pte_encode(0, pat_index, flags);
 	struct sgt_dma iter = sgt_dma(vma_res);
 	gen6_pte_t *vaddr;
 
@@ -227,7 +227,9 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
 
 	vm->scratch[0]->encode =
 		vm->pte_encode(px_dma(vm->scratch[0]),
-			       I915_CACHE_NONE, PTE_READ_ONLY);
+			       i915_gem_get_pat_index(vm->i915,
+						      I915_CACHE_NONE),
+			       PTE_READ_ONLY);
 
 	vm->scratch[1] = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
 	if (IS_ERR(vm->scratch[1])) {
@@ -278,7 +280,7 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 static void pd_vma_bind(struct i915_address_space *vm,
 			struct i915_vm_pt_stash *stash,
 			struct i915_vma_resource *vma_res,
-			enum i915_cache_level cache_level,
+			unsigned int pat_index,
 			u32 unused)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index bb6998d67133..f948d33e5ec5 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -29,7 +29,7 @@ static u64 gen8_pde_encode(const dma_addr_t addr,
 }
 
 static u64 gen8_pte_encode(dma_addr_t addr,
-			   enum i915_cache_level level,
+			   unsigned int pat_index,
 			   u32 flags)
 {
 	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW;
@@ -40,7 +40,12 @@ static u64 gen8_pte_encode(dma_addr_t addr,
 	if (flags & PTE_LM)
 		pte |= GEN12_PPGTT_PTE_LM;
 
-	switch (level) {
+	/*
+	 * For pre-gen12 platforms pat_index is the same as enum
+	 * i915_cache_level, so the switch-case here is still valid.
+	 * See translation table defined by LEGACY_CACHELEVEL.
+	 */
+	switch (pat_index) {
 	case I915_CACHE_NONE:
 		pte |= PPAT_UNCACHED;
 		break;
@@ -55,9 +60,9 @@ static u64 gen8_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
-static u64 mtl_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags)
+static u64 gen12_pte_encode(dma_addr_t addr,
+			    unsigned int pat_index,
+			    u32 flags)
 {
 	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW;
 
@@ -67,24 +72,17 @@ static u64 mtl_pte_encode(dma_addr_t addr,
 	if (flags & PTE_LM)
 		pte |= GEN12_PPGTT_PTE_LM;
 
-	switch (level) {
-	case I915_CACHE_NONE:
-		pte |= GEN12_PPGTT_PTE_PAT1;
-		break;
-	case I915_CACHE_LLC:
-	case I915_CACHE_L3_LLC:
-		pte |= GEN12_PPGTT_PTE_PAT0 | GEN12_PPGTT_PTE_PAT1;
-		break;
-	case I915_CACHE_WT:
+	if (pat_index & BIT(0))
 		pte |= GEN12_PPGTT_PTE_PAT0;
-		break;
-	default:
-		/* This should never happen. Added to deal with the compile
-		 * error due to the addition of I915_MAX_CACHE_LEVEL. Will
-		 * be removed by the pat_index patch.
-		 */
-		break;
-	}
+
+	if (pat_index & BIT(1))
+		pte |= GEN12_PPGTT_PTE_PAT1;
+
+	if (pat_index & BIT(2))
+		pte |= GEN12_PPGTT_PTE_PAT2;
+
+	if (pat_index & BIT(3))
+		pte |= MTL_PPGTT_PTE_PAT3;
 
 	return pte;
 }
@@ -457,11 +455,11 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 		      struct i915_page_directory *pdp,
 		      struct sgt_dma *iter,
 		      u64 idx,
-		      enum i915_cache_level cache_level,
+		      unsigned int pat_index,