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

5 files changed, 23 insertions, 13 deletions

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index d91d0ade8abd..61da4ed9d521 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -57,7 +57,10 @@ static void trash_stolen(struct drm_i915_private *i915)
 		u32 __iomem *s;
 		int x;
 
-		ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0);
+		ggtt->vm.insert_page(&ggtt->vm, dma, slot,
+				     i915_gem_get_pat_index(i915,
+							    I915_CACHE_NONE),
+				     0);
 
 		s = io_mapping_map_atomic_wc(&ggtt->iomap, slot);
 		for (x = 0; x < PAGE_SIZE / sizeof(u32); x++) {
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index f68ef4074088..f8fe3681c3dc 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -246,7 +246,7 @@ static int igt_evict_for_cache_color(void *arg)
 	struct drm_mm_node target = {
 		.start = I915_GTT_PAGE_SIZE * 2,
 		.size = I915_GTT_PAGE_SIZE,
-		.color = I915_CACHE_LLC,
+		.color = i915_gem_get_pat_index(gt->i915, I915_CACHE_LLC),
 	};
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
@@ -309,7 +309,7 @@ static int igt_evict_for_cache_color(void *arg)
 	/* Attempt to remove the first *pinned* vma, by removing the (empty)
 	 * neighbour -- this should fail.
 	 */
-	target.color = I915_CACHE_L3_LLC;
+	target.color = i915_gem_get_pat_index(gt->i915, I915_CACHE_L3_LLC);
 
 	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_for_node(&ggtt->vm, NULL, &target, 0);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 154801f1c468..36940ef10108 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -135,7 +135,7 @@ fake_dma_object(struct drm_i915_private *i915, u64 size)
 
 	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);
 
 	/* Preallocate the "backing storage" */
 	if (i915_gem_object_pin_pages_unlocked(obj))
@@ -359,7 +359,9 @@ alloc_vm_end:
 
 			with_intel_runtime_pm(vm->gt->uncore->rpm, wakeref)
 			  vm->insert_entries(vm, mock_vma_res,
-						   I915_CACHE_NONE, 0);
+					     i915_gem_get_pat_index(vm->i915,
+								    I915_CACHE_NONE),
+					     0);
 		}
 		count = n;
 
@@ -1377,7 +1379,10 @@ static int igt_ggtt_page(void *arg)
 
 		ggtt->vm.insert_page(&ggtt->vm,
 				     i915_gem_object_get_dma_address(obj, 0),
-				     offset, I915_CACHE_NONE, 0);
+				     offset,
+				     i915_gem_get_pat_index(i915,
+							    I915_CACHE_NONE),
+				     0);
 	}
 
 	order = i915_random_order(count, &prng);
@@ -1510,7 +1515,7 @@ static int reserve_gtt_with_resource(struct i915_vma *vma, u64 offset)
 	mutex_lock(&vm->mutex);
 	err = i915_gem_gtt_reserve(vm, NULL, &vma->node, obj->base.size,
 				   offset,
-				   obj->cache_level,
+				   obj->pat_index,
 				   0);
 	if (!err) {
 		i915_vma_resource_init_from_vma(vma_res, vma);
@@ -1690,7 +1695,7 @@ static int insert_gtt_with_resource(struct i915_vma *vma)
 
 	mutex_lock(&vm->mutex);
 	err = i915_gem_gtt_insert(vm, NULL, &vma->node, obj->base.size, 0,
-				  obj->cache_level, 0, vm->total, 0);
+				  obj->pat_index, 0, vm->total, 0);
 	if (!err) {
 		i915_vma_resource_init_from_vma(vma_res, vma);
 		vma->resource = vma_res;
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 3b18e5905c86..d985d9bae2e8 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -1070,7 +1070,9 @@ static int igt_lmem_write_cpu(void *arg)
 	/* Put the pages into a known state -- from the gpu for added fun */
 	intel_engine_pm_get(engine);
 	err = intel_context_migrate_clear(engine->gt->migrate.context, NULL,
-					  obj->mm.pages->sgl, I915_CACHE_NONE,
+					  obj->mm.pages->sgl,
+					  i915_gem_get_pat_index(i915,
+								 I915_CACHE_NONE),
 					  true, 0xdeadbeaf, &rq);
 	if (rq) {
 		dma_resv_add_fence(obj->base.resv, &rq->fence,
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index ece97e4faacb..a516c0aa88fd 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -27,21 +27,21 @@
 static void mock_insert_page(struct i915_address_space *vm,
 			     dma_addr_t addr,
 			     u64 offset,
-			     enum i915_cache_level level,
+			     unsigned int pat_index,
 			     u32 flags)
 {
 }
 
 static void mock_insert_entries(struct i915_address_space *vm,
 				struct i915_vma_resource *vma_res,
-				enum i915_cache_level level, u32 flags)
+				unsigned int pat_index, u32 flags)
 {
 }
 
 static void mock_bind_ppgtt(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)
 {
 	GEM_BUG_ON(flags & I915_VMA_GLOBAL_BIND);
@@ -94,7 +94,7 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
 static void mock_bind_ggtt(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)
 {
 }