i915 module: update changes from lts-v6.1.12-linux-230424T063740Z

Makefile

@@ -349,16 +349,10 @@ i915-y += \
 i915-y += i915_perf.o
 
 # Protected execution platform (PXP) support
-ifeq ($(call kver_ge,6,2,0),1)
 i915-y += \
 	pxp/intel_pxp.o \
 	pxp/intel_pxp_tee.o \
 	pxp/intel_pxp_huc.o
-else
-i915-y += \
-	pxp/intel_pxp.o \
-	pxp/intel_pxp_tee.o
-endif
 
 i915-$(CONFIG_DRM_I915_PXP) += \
 	pxp/intel_pxp_cmd.o \

drivers/gpu/drm/i915/display/intel_cx0_phy.c

@@ -802,7 +802,7 @@ static const struct intel_c20pll_state * const mtl_c20_dp_tables[] = {
  * HDMI link rates with 38.4 MHz reference clock.
  */
 
-static const struct intel_c10mpllb_state mtl_c10_hdmi_25_2 = {
+static const struct intel_c10mpllb_state __maybe_unused mtl_c10_hdmi_25_2 = {
 	.clock = 25200,
 	.pll[0] = 0x4,
 	.pll[1] = 0,
@@ -2065,7 +2065,7 @@ int intel_c20pll_calc_port_clock(struct intel_encoder *encoder,
 				 const struct intel_c20pll_state *pll_state)
 {
 	unsigned int frac_quot = 0, frac_rem = 0, frac_den = 1;
-	unsigned int multiplier, tx_clk_div, refclk = 38400;
+	unsigned int multiplier = 0, tx_clk_div = 0, refclk = 38400;
 
 	if (pll_state->mpllb[6] & C20_MPLLB_FRACEN) {
 		frac_quot = pll_state->mpllb[8];

drivers/gpu/drm/i915/display/intel_dpt.c

@@ -41,24 +41,24 @@ 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;
@@ -81,7 +81,7 @@ 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;
@@ -96,7 +96,7 @@ 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;
 
@@ -298,7 +298,7 @@ intel_dpt_create(struct intel_framebuffer *fb)
 	vm->vma_ops.bind_vma    = dpt_bind_vma;
 	vm->vma_ops.unbind_vma  = dpt_unbind_vma;
 
-	vm->pte_encode = gen8_ggtt_pte_encode;
+	vm->pte_encode = vm->gt->ggtt->vm.pte_encode;
 
 	dpt->obj = dpt_obj;
 

drivers/gpu/drm/i915/gem/i915_gem_create.c

@@ -244,6 +244,7 @@ struct create_ext {
 	unsigned int n_placements;
 	unsigned int placement_mask;
 	unsigned long flags;
+	unsigned int pat_index;
 };
 
 static void repr_placements(char *buf, size_t size,
@@ -393,11 +394,40 @@ static int ext_set_protected(struct i915_user_extension __user *base, void *data
 	return 0;
 }
 
+static int ext_set_pat(struct i915_user_extension __user *base, void *data)
+{
+	struct create_ext *ext_data = data;
+	struct drm_i915_private *i915 = ext_data->i915;
+	struct drm_i915_gem_create_ext_set_pat ext;
+	unsigned int max_pat_index;
+
+	BUILD_BUG_ON(sizeof(struct drm_i915_gem_create_ext_set_pat) !=
+		     offsetofend(struct drm_i915_gem_create_ext_set_pat, rsvd));
+
+	if (copy_from_user(&ext, base, sizeof(ext)))
+		return -EFAULT;
+
+	max_pat_index = INTEL_INFO(i915)->max_pat_index;
+
+	if (ext.pat_index > max_pat_index) {
+		drm_dbg(&i915->drm, "PAT index is invalid: %u\n",
+			ext.pat_index);
+		return -EINVAL;
+	}
+
+	ext_data->pat_index = ext.pat_index;
+
+	return 0;
+}
+
 static const i915_user_extension_fn create_extensions[] = {
 	[I915_GEM_CREATE_EXT_MEMORY_REGIONS] = ext_set_placements,
 	[I915_GEM_CREATE_EXT_PROTECTED_CONTENT] = ext_set_protected,
+	[I915_GEM_CREATE_EXT_SET_PAT] = ext_set_pat,
 };
 
+#define PAT_INDEX_NOT_SET	0xffff
+
 /**
  * Creates a new mm object and returns a handle to it.
  * @dev: drm device pointer
@@ -417,6 +447,8 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data,
 	if (args->flags & ~I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS)
 		return -EINVAL;
 
+	ext_data.pat_index = PAT_INDEX_NOT_SET;
+
 	ret = i915_user_extensions(u64_to_user_ptr(args->extensions),
 				   create_extensions,
 				   ARRAY_SIZE(create_extensions),
@@ -453,5 +485,11 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data,
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
+	if (ext_data.pat_index != PAT_INDEX_NOT_SET) {
+		i915_gem_object_set_pat_index(obj, ext_data.pat_index);
+		/* Mark pat_index is set by UMD */
+		obj->cache_level = I915_CACHE_INVAL;
+	}
+
 	return i915_gem_publish(obj, file, &args->size, &args->handle);
 }

drivers/gpu/drm/i915/gem/i915_gem_domain.c

@@ -27,8 +27,8 @@ 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);
+	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)
@@ -265,7 +265,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 {
 	int ret;
 
-	if (obj->cache_level == cache_level)
+	if (i915_gem_object_has_cache_level(obj, cache_level))
 		return 0;
 
 	ret = i915_gem_object_wait(obj,
@@ -276,10 +276,8 @@ 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,
@@ -304,20 +302,13 @@ 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:
+	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;
-		break;
-
-	case I915_CACHE_WT:
+	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;

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -644,7 +644,7 @@ static inline int use_cpu_reloc(const struct reloc_cache *cache,
 
 	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,
@@ -1325,8 +1325,10 @@ static void *reloc_iomap(struct i915_vma *batch,
 	offset = cache->node.start;
 	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);
+			i915_gem_object_get_dma_address(obj, page),
+			offset,
+			i915_gem_get_pat_index(ggtt->vm.i915, I915_CACHE_NONE),
+			0);
 	} else {
 		offset += page << PAGE_SHIFT;
 	}
@@ -1466,7 +1468,7 @@ 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);

drivers/gpu/drm/i915/gem/i915_gem_mman.c

@@ -384,7 +384,8 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 	}
 
 	/* Access to snoopable pages through the GTT is incoherent. */
-	if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(i915)) {
+	if (!(i915_gem_object_has_cache_level(obj, I915_CACHE_NONE) ||
+	      HAS_LLC(i915))) {
 		ret = -EFAULT;
 		goto err_unpin;
 	}

drivers/gpu/drm/i915/gem/i915_gem_object.c

@@ -45,6 +45,34 @@ static struct kmem_cache *slab_objects;
 
 static const struct drm_gem_object_funcs i915_gem_object_funcs;
 
+unsigned int i915_gem_get_pat_index(struct drm_i915_private *i915,
+				    enum i915_cache_level level)
+{
+	if (drm_WARN_ON(&i915->drm, level >= I915_MAX_CACHE_LEVEL))
+		return 0;
+
+	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)
+{
+	/*
+	 * cache_level == I915_CACHE_INVAL indicates the UMD's have set the
+	 * caching policy through pat_index, in which case the KMD should
+	 * leave the coherency to be managed by user space, simply return
+	 * true here.
+	 */
+	if (obj->cache_level == I915_CACHE_INVAL)
+		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;
@@ -124,7 +152,7 @@ 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 |
@@ -139,6 +167,37 @@ 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);
@@ -150,6 +209,12 @@ bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj)
 	if (!(obj->flags & I915_BO_ALLOC_USER))
 		return false;
 
+	/*
+	 * Always flush cache for UMD objects at creation time.
+	 */
+	if (obj->cache_level == I915_CACHE_INVAL)
+		return true;
+
 	/*
 	 * EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it
 	 * possible for userspace to bypass the GTT caching bits set by the

drivers/gpu/drm/i915/gem/i915_gem_object.h

@@ -20,6 +20,8 @@
 
 enum intel_region_id;
 
+#define obj_to_i915(obj__) to_i915((obj__)->base.dev)
+
 static inline bool i915_gem_object_size_2big(u64 size)
 {
 	struct drm_i915_gem_object *obj;
@@ -30,6 +32,10 @@ static inline bool i915_gem_object_size_2big(u64 size)
 	return false;
 }
 
+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);
@@ -760,6 +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);