Skip to contentSkip to conversation

drm/i915/mtl: Define MOCS and PAT tables for MTL

PATCH In review [email protected] 3 participants 16 messages Apr 7, 2023 – Apr 11, 2023

Subsystems (4)
lore
Share & tools
lore
#0 lore raw

cover drm/i915/mtl: Define MOCS and PAT tables for MTL

From: Fei Yang <[email protected]>

The series includes patches needed to enable MTL.
Also add new extension for GEM_CREATE uAPI to let
user space set cache policy for buffer objects.

Fei Yang (8):
drm/i915/mtl: Define MOCS and PAT tables for MTL drm/i915/mtl: enforce mtl PTE encode drm/i915/mtl: workaround coherency issue for Media drm/i915/mtl: end support for set caching ioctl drm/i915: preparation for using PAT index drm/i915: use pat_index instead of cache_level drm/i915: making mtl pte encode generic for gen12 drm/i915: Allow user to set cache at BO creation

 drivers/gpu/drm/i915/display/intel_dpt.c      | 14 ++--
 drivers/gpu/drm/i915/gem/i915_gem_create.c    | 36 ++++++++
 drivers/gpu/drm/i915/gem/i915_gem_domain.c    | 30 +++----
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 10 ++-
 drivers/gpu/drm/i915/gem/i915_gem_mman.c      |  3 +-
 drivers/gpu/drm/i915/gem/i915_gem_object.c    | 61 +++++++++++++-
 drivers/gpu/drm/i915/gem/i915_gem_object.h    |  8 ++
 .../gpu/drm/i915/gem/i915_gem_object_types.h  | 26 +++++-
 drivers/gpu/drm/i915/gem/i915_gem_pages.c     |  5 +-
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c     |  9 +-
 drivers/gpu/drm/i915/gem/i915_gem_shrinker.c  |  2 -
 drivers/gpu/drm/i915/gem/i915_gem_stolen.c    |  4 +-
 drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c  | 16 ++--
 .../gpu/drm/i915/gem/selftests/huge_pages.c   |  2 +-
 .../drm/i915/gem/selftests/i915_gem_migrate.c |  2 +-
 .../drm/i915/gem/selftests/i915_gem_mman.c    |  2 +-
 drivers/gpu/drm/i915/gt/gen6_ppgtt.c          | 10 ++-
 drivers/gpu/drm/i915/gt/gen8_ppgtt.c          | 81 +++++++++++++-----
 drivers/gpu/drm/i915/gt/gen8_ppgtt.h          |  6 +-
 drivers/gpu/drm/i915/gt/intel_ggtt.c          | 84 +++++++++++++------
 drivers/gpu/drm/i915/gt/intel_gtt.c           | 23 ++++-
 drivers/gpu/drm/i915/gt/intel_gtt.h           | 38 ++++++---
 drivers/gpu/drm/i915/gt/intel_migrate.c       | 47 ++++++-----
 drivers/gpu/drm/i915/gt/intel_migrate.h       | 13 ++-
 drivers/gpu/drm/i915/gt/intel_mocs.c          | 76 ++++++++++++++++-
 drivers/gpu/drm/i915/gt/intel_ppgtt.c         |  6 +-
 drivers/gpu/drm/i915/gt/selftest_migrate.c    | 47 ++++++-----
 drivers/gpu/drm/i915/gt/selftest_mocs.c       |  2 +-
 drivers/gpu/drm/i915/gt/selftest_reset.c      |  8 +-
 drivers/gpu/drm/i915/gt/selftest_timeline.c   |  2 +-
 drivers/gpu/drm/i915/gt/selftest_tlb.c        |  4 +-
 drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c     | 13 +++
 drivers/gpu/drm/i915/gt/uc/intel_guc.c        |  7 ++
 drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c     | 18 ++--
 drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c      | 10 ++-
 drivers/gpu/drm/i915/i915_debugfs.c           | 55 +++++++++---
 drivers/gpu/drm/i915/i915_gem.c               | 16 +++-
 drivers/gpu/drm/i915/i915_gpu_error.c         |  8 +-
 drivers/gpu/drm/i915/i915_pci.c               | 76 +++++++++++++++--
 drivers/gpu/drm/i915/i915_vma.c               | 16 ++--
 drivers/gpu/drm/i915/i915_vma.h               |  2 +-
 drivers/gpu/drm/i915/i915_vma_types.h         |  2 -
 drivers/gpu/drm/i915/intel_device_info.h      |  5 ++
 drivers/gpu/drm/i915/selftests/i915_gem.c     |  5 +-
 .../gpu/drm/i915/selftests/i915_gem_evict.c   |  4 +-
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 15 ++--
 .../drm/i915/selftests/intel_memory_region.c  |  4 +-
 .../gpu/drm/i915/selftests/mock_gem_device.c  |  6 ++
 drivers/gpu/drm/i915/selftests/mock_gtt.c     |  8 +-
 include/uapi/drm/i915_drm.h                   | 36 ++++++++
 tools/include/uapi/drm/i915_drm.h             | 36 ++++++++
 51 files changed, 788 insertions(+), 231 deletions(-)
Signature · 1 line
2.25.1
#7 lore raw

PATCH 3/8 drm/i915/mtl: workaround coherency issue for Media

From: Fei Yang <[email protected]>

This patch implements Wa_22016122933.

In MTL, memory writes initiated by Media tile update the whole cache line even for partial writes. This creates a coherency problem for cacheable memory if both CPU and GPU are writing data to different locations within a single cache line. CTB communication is impacted by this issue because the head and tail pointers are adjacent words within a cache line (see struct guc_ct_buffer_desc), where one is written by GuC and the other by the host. This patch circumvents the issue by making CPU/GPU shared memory uncacheable (WC on CPU side, and PAT index 2 for GPU). Also for CTB which is being updated by both CPU and GuC, mfence instruction is added to make sure the CPU writes are visible to GPU right away (flush the write combining buffer).

While fixing the CTB issue, we noticed some random GSC firmware loading failure because the share buffers are cacheable (WB) on CPU side but uncached on GPU side. To fix these issues we need to map such shared buffers as WC on CPU side. Since such allocations are not all done through GuC allocator, to avoid too many code changes, the i915_coherent_map_type() is now hard coded to return WC for MTL.

BSpec: 45101

---
 drivers/gpu/drm/i915/gem/i915_gem_pages.c |  5 ++++-
 drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c | 13 +++++++++++++
 drivers/gpu/drm/i915/gt/uc/intel_guc.c    |  7 +++++++
 drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 18 ++++++++++++------
 4 files changed, 36 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/gem/i915_gem_pages.c +4 -1
index ecd86130b74f..89fc8ea6bcfc 100644
@@ -469,7 +469,10 @@ enum i915_map_type i915_coherent_map_type(struct drm_i915_private *i915,
 					  struct drm_i915_gem_object *obj,
 					  bool always_coherent)
 {
-	if (i915_gem_object_is_lmem(obj))
+	/*
+	 * Wa_22016122933: always return I915_MAP_WC for MTL
+	 */
+	if (i915_gem_object_is_lmem(obj) || IS_METEORLAKE(i915))
 		return I915_MAP_WC;
 	if (HAS_LLC(i915) || always_coherent)
 		return I915_MAP_WB;
drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c +13 -0
index 1d9fdfb11268..236673c02f9a 100644
@@ -110,6 +110,13 @@ static int gsc_fw_load_prepare(struct intel_gsc_uc *gsc)
 	if (obj->base.size < gsc->fw.size)
 		return -ENOSPC;
 
+	/*
+	 * Wa_22016122933: For MTL the shared memory needs to be mapped
+	 * as WC on CPU side and UC (PAT index 2) on GPU side
+	 */
+	if (IS_METEORLAKE(i915))
+		i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
+
 	dst = i915_gem_object_pin_map_unlocked(obj,
 					       i915_coherent_map_type(i915, obj, true));
 	if (IS_ERR(dst))
@@ -125,6 +132,12 @@ static int gsc_fw_load_prepare(struct intel_gsc_uc *gsc)
 	memset(dst, 0, obj->base.size);
 	memcpy(dst, src, gsc->fw.size);
 
+	/*
+	 * Wa_22016122933: Making sure the data in dst is
+	 * visible to GSC right away
+	 */
+	intel_guc_write_barrier(&gt->uc.guc);
+
 	i915_gem_object_unpin_map(gsc->fw.obj);
 	i915_gem_object_unpin_map(obj);
 
drivers/gpu/drm/i915/gt/uc/intel_guc.c +7 -0
index d76508fa3af7..f9bddaa876d9 100644
@@ -743,6 +743,13 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
+	/*
+	 * Wa_22016122933: For MTL the shared memory needs to be mapped
+	 * as WC on CPU side and UC (PAT index 2) on GPU side
+	 */
+	if (IS_METEORLAKE(gt->i915))
+		i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
+
 	vma = i915_vma_instance(obj, &gt->ggtt->vm, NULL);
 	if (IS_ERR(vma))
 		goto err;
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +12 -6
index 1803a633ed64..98e682b7df07 100644
@@ -415,12 +415,6 @@ static int ct_write(struct intel_guc_ct *ct,
 	}
 	GEM_BUG_ON(tail > size);
 
-	/*
-	 * make sure H2G buffer update and LRC tail update (if this triggering a
-	 * submission) are visible before updating the descriptor tail
-	 */
-	intel_guc_write_barrier(ct_to_guc(ct));
-
 	/* update local copies */
 	ctb->tail = tail;
 	GEM_BUG_ON(atomic_read(&ctb->space) < len + GUC_CTB_HDR_LEN);
@@ -429,6 +423,12 @@ static int ct_write(struct intel_guc_ct *ct,
 	/* now update descriptor */
 	WRITE_ONCE(desc->tail, tail);
 
+	/*
+	 * make sure H2G buffer update and LRC tail update (if this triggering a
+	 * submission) are visible before updating the descriptor tail
+	 */
+	intel_guc_write_barrier(ct_to_guc(ct));
+
 	return 0;
 
 corrupted:
@@ -902,6 +902,12 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 	/* now update descriptor */
 	WRITE_ONCE(desc->head, head);
 
+	/*
+	 * Wa_22016122933: Making sure the head update is
+	 * visible to GuC right away
+	 */
+	intel_guc_write_barrier(ct_to_guc(ct));
+
 	return available - len;
 
 corrupted:
Signature · 1 line
2.25.1
#10 lore raw

PATCH 6/8 drm/i915: use pat_index instead of cache_level

In reply to [email protected]

From: Fei Yang <[email protected]>

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. Haivng the abstracted i915_cache_level sitting in between would only cause more ambiguity.

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 these simple cases, using cache_level would help simplify the code.

Cc Chris Wilson <[email protected]>
Cc Matt Roper <[email protected]>
---
 drivers/gpu/drm/i915/display/intel_dpt.c      | 12 +--
 drivers/gpu/drm/i915/gem/i915_gem_domain.c    | 27 ++----
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 10 ++-
 drivers/gpu/drm/i915/gem/i915_gem_mman.c      |  3 +-
 drivers/gpu/drm/i915/gem/i915_gem_object.c    | 52 +++++++++++-
 drivers/gpu/drm/i915/gem/i915_gem_object.h    |  4 +
 .../gpu/drm/i915/gem/i915_gem_object_types.h  | 25 +++++-
 drivers/gpu/drm/i915/gem/i915_gem_stolen.c    |  4 +-
 drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c  | 16 ++--
 .../gpu/drm/i915/gem/selftests/huge_pages.c   |  2 +-
 .../drm/i915/gem/selftests/i915_gem_migrate.c |  2 +-
 .../drm/i915/gem/selftests/i915_gem_mman.c    |  2 +-
 drivers/gpu/drm/i915/gt/gen6_ppgtt.c          | 10 ++-
 drivers/gpu/drm/i915/gt/gen8_ppgtt.c          | 76 ++++++++---------
 drivers/gpu/drm/i915/gt/gen8_ppgtt.h          |  3 +-
 drivers/gpu/drm/i915/gt/intel_ggtt.c          | 82 +++++++++----------
 drivers/gpu/drm/i915/gt/intel_gtt.h           | 20 ++---
 drivers/gpu/drm/i915/gt/intel_migrate.c       | 47 ++++++-----
 drivers/gpu/drm/i915/gt/intel_migrate.h       | 13 ++-
 drivers/gpu/drm/i915/gt/intel_ppgtt.c         |  6 +-
 drivers/gpu/drm/i915/gt/selftest_migrate.c    | 47 ++++++-----
 drivers/gpu/drm/i915/gt/selftest_reset.c      |  8 +-
 drivers/gpu/drm/i915/gt/selftest_timeline.c   |  2 +-
 drivers/gpu/drm/i915/gt/selftest_tlb.c        |  4 +-
 drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c      | 10 ++-
 drivers/gpu/drm/i915/i915_debugfs.c           | 55 ++++++++++---
 drivers/gpu/drm/i915/i915_gem.c               | 16 +++-
 drivers/gpu/drm/i915/i915_gpu_error.c         |  8 +-
 drivers/gpu/drm/i915/i915_vma.c               | 16 ++--
 drivers/gpu/drm/i915/i915_vma.h               |  2 +-
 drivers/gpu/drm/i915/i915_vma_types.h         |  2 -
 drivers/gpu/drm/i915/selftests/i915_gem.c     |  5 +-
 .../gpu/drm/i915/selftests/i915_gem_evict.c   |  4 +-
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 15 ++--
 .../drm/i915/selftests/intel_memory_region.c  |  4 +-
 drivers/gpu/drm/i915/selftests/mock_gtt.c     |  8 +-
 36 files changed, 383 insertions(+), 239 deletions(-)
drivers/gpu/drm/i915/display/intel_dpt.c +6 -6
index c5eacfdba1a5..7c5fddb203ba 100644
@@ -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;
 
drivers/gpu/drm/i915/gem/i915_gem_domain.c +9 -18
index bb3575b1479f..d5fd4c9cd9f8 100644
@@ -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)
@@ -267,7 +267,7 @@ 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,
@@ -278,10 +278,8 @@ 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 +304,13 @@ 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 +6 -4
index 3aeede6aee4d..d42915516636 100644
@@ -642,7 +642,7 @@ 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,
@@ -1323,8 +1323,10 @@ 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;
 	}
@@ -1464,7 +1466,7 @@ 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 +2 -1
index d3c1dee16af2..6c242f9ffc75 100644
@@ -383,7 +383,8 @@ 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 +51 -1

70 lines not on this page · raw message

drivers/gpu/drm/i915/gem/i915_gem_object.h +4 -0
index 4c92e17b4337..6f00aab10015 100644
@@ -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);
drivers/gpu/drm/i915/gem/i915_gem_object_types.h +22 -3
index 890f3ad497c5..862b5c1d2d21 100644
@@ -195,6 +195,7 @@ enum i915_cache_level {
 	 */
 	I915_CACHE_WT,
 	I915_MAX_CACHE_LEVEL,
+	I915_CACHE_INVAL,
 };
 
 enum i915_map_type {
@@ -351,10 +352,28 @@ 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 used to contain a value of enum i915_cache_level. It's
+	 * changed to an unsigned int because PAT indices are being used by
+	 * both UMD and KMD for caching policy control after GEN12.
+	 * For backward compatibility, this field will continue to contain
+	 * value of i915_cache_level for pre-GEN12 platforms so that the PTE
+	 * encode functions for these legacy platforms can stay the same.
+	 * 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.
+	 */
+	unsigned int pat_index:6;
+	/**
+	 * @cache_level: Indicate whether pat_index is set by UMD
 	 *
-	 * See enum i915_cache_level for possible values, along with what
-	 * each does.
+	 * This used to hold desired GTT caching level, but is now replaced by
+	 * pat_index. It's kept here for KMD to tell whether the pat_index is
+	 * set by UMD or converted from enum i915_cache_level.
+	 * This field should be 0 by default, but I915_CACHE_INVAL if the
+	 * pat_index is set by UMD.
 	 */
 	unsigned int cache_level:3;
 	/**
drivers/gpu/drm/i915/gem/i915_gem_stolen.c +3 -1
index 8ac376c24aa2..9f379141f966 100644
@@ -557,7 +557,9 @@ 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,
drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c +9 -7
index dd188dfcc423..dffd4a8f2dde 100644
@@ -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 {
@@ -227,12 +228,13 @@ static struct dma_fence *i915_ttm_accel_move(struct ttm_buffer_object *bo,
 		src_level = i915_ttm_cache_level(i915, bo->resource, src_ttm);
 		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_ttm_gtt_binds_lmem(bo->resource),
-						 dst_st->sgl, dst_level,
-						 i915_ttm_gtt_binds_lmem(dst_mem),
-						 &rq);
+					deps, src_rsgt->table.sgl,
+					i915_gem_get_pat_index(i915, src_level),
+					i915_ttm_gtt_binds_lmem(bo->resource),
+					dst_st->sgl,
+					i915_gem_get_pat_index(i915, dst_level),
+					i915_ttm_gtt_binds_lmem(dst_mem),
+					&rq);
 
 		i915_refct_sgt_put(src_rsgt);
 	}
drivers/gpu/drm/i915/gem/selftests/huge_pages.c +1 -1
index defece0bcb81..ebb68ac9cd5e 100644
@@ -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;
 }
drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c +1 -1
index fe6c37fd7859..a93a90b15907 100644
@@ -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) {
drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +1 -1
index 56279908ed30..a93d8f9f8bc1 100644
@@ -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);
drivers/gpu/drm/i915/gt/gen6_ppgtt.c +6 -4
index 5aaacc53fa4c..c2bdc133c89a 100644
@@ -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);
drivers/gpu/drm/i915/gt/gen8_ppgtt.c +39 -37

185 lines not on this page · raw message

drivers/gpu/drm/i915/gt/gen8_ppgtt.h +1 -2
index 6b8ce7f4d25a..98e260e1a081 100644
@@ -10,13 +10,12 @@
 
 struct i915_address_space;
 struct intel_gt;
-enum i915_cache_level;
 
 struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 				     unsigned long lmem_pt_obj_flags);
 
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
-			 enum i915_cache_level level,
+			 unsigned int pat_index,
 			 u32 flags);
 u64 mtl_ggtt_pte_encode(dma_addr_t addr,
 			unsigned int pat_index,
drivers/gpu/drm/i915/gt/intel_ggtt.c +40 -42

229 lines not on this page · raw message

drivers/gpu/drm/i915/gt/intel_gtt.h +9 -11
index b632167eaf2e..12bd4398ad38 100644
@@ -165,8 +165,6 @@ typedef u64 gen8_pte_t;
 #define MTL_2_COH_1W	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 2)
 #define MTL_0_COH_NON	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 0)
 
-enum i915_cache_level;
-
 struct drm_i915_gem_object;
 struct i915_fence_reg;
 struct i915_vma;
@@ -234,7 +232,7 @@ struct i915_vma_ops {
 	void (*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);
 	/*
 	 * Unmap an object from an address space. This usually consists of
@@ -306,7 +304,7 @@ struct i915_address_space {
 		(*alloc_scratch_dma)(struct i915_address_space *vm, int sz);
 
 	u64 (*pte_encode)(dma_addr_t addr,
-			  enum i915_cache_level level,
+			  unsigned int pat_index,
 			  u32 flags); /* Create a valid PTE */
 #define PTE_READ_ONLY	BIT(0)
 #define PTE_LM		BIT(1)
@@ -321,20 +319,20 @@ struct i915_address_space {
 	void (*insert_page)(struct i915_address_space *vm,
 			    dma_addr_t addr,
 			    u64 offset,
-			    enum i915_cache_level cache_level,
+			    unsigned int pat_index,
 			    u32 flags);
 	void (*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);
 	void (*raw_insert_page)(struct i915_address_space *vm,
 				dma_addr_t addr,
 				u64 offset,
-				enum i915_cache_level cache_level,
+				unsigned int pat_index,
 				u32 flags);
 	void (*raw_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);
 	void (*cleanup)(struct i915_address_space *vm);
 
@@ -581,7 +579,7 @@ void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt,
 void intel_ggtt_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);
 void intel_ggtt_unbind_vma(struct i915_address_space *vm,
 			   struct i915_vma_resource *vma_res);
@@ -639,7 +637,7 @@ void
 __set_pd_entry(struct i915_page_directory * const pd,
 	       const unsigned short idx,
 	       struct i915_page_table *pt,
-	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level));
+	       u64 (*encode)(const dma_addr_t, const unsigned int pat_index));
 
 #define set_pd_entry(pd, idx, to) \
 	__set_pd_entry((pd), (idx), px_pt(to), gen8_pde_encode)
@@ -659,7 +657,7 @@ void gen6_ggtt_invalidate(struct i915_ggtt *ggtt);
 void ppgtt_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);
 void ppgtt_unbind_vma(struct i915_address_space *vm,
 		      struct i915_vma_resource *vma_res);
drivers/gpu/drm/i915/gt/intel_migrate.c +26 -21

156 lines not on this page · raw message

drivers/gpu/drm/i915/gt/intel_migrate.h +6 -7
index ccc677ec4aa3..11fc09a00c4b 100644
@@ -16,7 +16,6 @@ struct i915_request;
 struct i915_gem_ww_ctx;
 struct intel_gt;
 struct scatterlist;
-enum i915_cache_level;
 
 int intel_migrate_init(struct intel_migrate *m, struct intel_gt *gt);
 
@@ -26,20 +25,20 @@ int intel_migrate_copy(struct intel_migrate *m,
 		       struct i915_gem_ww_ctx *ww,
 		       const struct i915_deps *deps,
 		       struct scatterlist *src,
-		       enum i915_cache_level src_cache_level,
+		       unsigned int src_pat_index,
 		       bool src_is_lmem,
 		       struct scatterlist *dst,
-		       enum i915_cache_level dst_cache_level,
+		       unsigned int dst_pat_index,
 		       bool dst_is_lmem,
 		       struct i915_request **out);
 
 int intel_context_migrate_copy(struct intel_context *ce,
 			       const struct i915_deps *deps,
 			       struct scatterlist *src,
-			       enum i915_cache_level src_cache_level,
+			       unsigned int src_pat_index,
 			       bool src_is_lmem,
 			       struct scatterlist *dst,
-			       enum i915_cache_level dst_cache_level,
+			       unsigned int dst_pat_index,
 			       bool dst_is_lmem,
 			       struct i915_request **out);
 
@@ -48,7 +47,7 @@ intel_migrate_clear(struct intel_migrate *m,
 		    struct i915_gem_ww_ctx *ww,
 		    const struct i915_deps *deps,
 		    struct scatterlist *sg,
-		    enum i915_cache_level cache_level,
+		    unsigned int pat_index,
 		    bool is_lmem,
 		    u32 value,
 		    struct i915_request **out);
@@ -56,7 +55,7 @@ int
 intel_context_migrate_clear(struct intel_context *ce,
 			    const struct i915_deps *deps,
 			    struct scatterlist *sg,
-			    enum i915_cache_level cache_level,
+			    unsigned int pat_index,
 			    bool is_lmem,
 			    u32 value,
 			    struct i915_request **out);
drivers/gpu/drm/i915/gt/intel_ppgtt.c +3 -3
index 7ecfa672f738..f0da3555c6db 100644
@@ -98,7 +98,7 @@ void
 __set_pd_entry(struct i915_page_directory * const pd,
 	       const unsigned short idx,
 	       struct i915_page_table * const to,
-	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level))
+	       u64 (*encode)(const dma_addr_t, const unsigned int))
 {
 	/* Each thread pre-pins the pd, and we may have a thread per pde. */
 	GEM_BUG_ON(atomic_read(px_used(pd)) > NALLOC * I915_PDES);
@@ -181,7 +181,7 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt,
 void ppgtt_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;
@@ -199,7 +199,7 @@ void ppgtt_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);
 	wmb();
 }
 
drivers/gpu/drm/i915/gt/selftest_migrate.c +25 -22

156 lines not on this page · raw message

drivers/gpu/drm/i915/gt/selftest_reset.c +6 -2
index a9e0a91bc0e0..79aa6ac66ad2 100644
@@ -86,7 +86,9 @@ __igt_reset_stolen(struct intel_gt *gt,
 
 		ggtt->vm.insert_page(&ggtt->vm, dma,
 				     ggtt->error_capture.start,
-				     I915_CACHE_NONE, 0);
+				     i915_gem_get_pat_index(gt->i915,
+							    I915_CACHE_NONE),
+				     0);
 		mb();
 
 		s = io_mapping_map_wc(&ggtt->iomap,
@@ -127,7 +129,9 @@ __igt_reset_stolen(struct intel_gt *gt,
 
 		ggtt->vm.insert_page(&ggtt->vm, dma,
 				     ggtt->error_capture.start,
-				     I915_CACHE_NONE, 0);
+				     i915_gem_get_pat_index(gt->i915,
+							    I915_CACHE_NONE),
+				     0);
 		mb();
 
 		s = io_mapping_map_wc(&ggtt->iomap,
drivers/gpu/drm/i915/gt/selftest_timeline.c +1 -1
index 9f536c251179..39c3ec12df1a 100644
@@ -836,7 +836,7 @@ static int setup_watcher(struct hwsp_watcher *w, struct intel_gt *gt,
 		return PTR_ERR(obj);
 
 	/* keep the same cache settings as timeline */
-	i915_gem_object_set_cache_coherency(obj, tl->hwsp_ggtt->obj->cache_level);
+	i915_gem_object_set_pat_index(obj, tl->hwsp_ggtt->obj->pat_index);
 	w->map = i915_gem_object_pin_map_unlocked(obj,
 						  page_unmask_bits(tl->hwsp_ggtt->obj->mm.mapping));
 	if (IS_ERR(w->map)) {
drivers/gpu/drm/i915/gt/selftest_tlb.c +3 -1
index e6cac1f15d6e..4493c8518e91 100644
@@ -36,6 +36,8 @@ pte_tlbinv(struct intel_context *ce,
 	   u64 length,
 	   struct rnd_state *prng)
 {
+	const unsigned int pat_index =
+		i915_gem_get_pat_index(ce->vm->i915, I915_CACHE_NONE);
 	struct drm_i915_gem_object *batch;
 	struct drm_mm_node vb_node;
 	struct i915_request *rq;
@@ -155,7 +157,7 @@ pte_tlbinv(struct intel_context *ce,
 		/* Flip the PTE between A and B */
 		if (i915_gem_object_is_lmem(vb->obj))
 			pte_flags |= PTE_LM;
-		ce->vm->insert_entries(ce->vm, &vb_res, 0, pte_flags);
+		ce->vm->insert_entries(ce->vm, &vb_res, pat_index, pte_flags);
 
 		/* Flush the PTE update to concurrent HW */
 		tlbinv(ce->vm, addr & -length, length);
drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +8 -2
index 264c952f777b..31182915f3d2 100644
@@ -876,9 +876,15 @@ static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw)
 		pte_flags |= PTE_LM;
 
 	if (ggtt->vm.raw_insert_entries)
-		ggtt->vm.raw_insert_entries(&ggtt->vm, dummy, I915_CACHE_NONE, pte_flags);
+		ggtt->vm.raw_insert_entries(&ggtt->vm, dummy,
+					    i915_gem_get_pat_index(ggtt->vm.i915,
+								   I915_CACHE_NONE),
+					    pte_flags);
 	else
-		ggtt->vm.insert_entries(&ggtt->vm, dummy, I915_CACHE_NONE, pte_flags);
+		ggtt->vm.insert_entries(&ggtt->vm, dummy,
+					i915_gem_get_pat_index(ggtt->vm.i915,
+							       I915_CACHE_NONE),
+					pte_flags);
 }
 
 static void uc_fw_unbind_ggtt(struct intel_uc_fw *uc_fw)
drivers/gpu/drm/i915/i915_debugfs.c +45 -10

73 lines not on this page · raw message

drivers/gpu/drm/i915/i915_gem.c +12 -4
index 0a78bdbd36b1..f95fc134d71e 100644
@@ -420,8 +420,12 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 		page_length = remain < page_length ? remain : page_length;
 		if (drm_mm_node_allocated(&node)) {
 			ggtt->vm.insert_page(&ggtt->vm,
-					     i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
-					     node.start, I915_CACHE_NONE, 0);
+					i915_gem_object_get_dma_address(obj,
+							offset >> PAGE_SHIFT),
+					node.start,
+					i915_gem_get_pat_index(i915,
+							       I915_CACHE_NONE),
+					0);
 		} else {
 			page_base += offset & PAGE_MASK;
 		}
@@ -598,8 +602,12 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 			/* flush the write before we modify the GGTT */
 			intel_gt_flush_ggtt_writes(ggtt->vm.gt);
 			ggtt->vm.insert_page(&ggtt->vm,
-					     i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
-					     node.start, I915_CACHE_NONE, 0);
+					i915_gem_object_get_dma_address(obj,
+							offset >> PAGE_SHIFT),
+					node.start,
+					i915_gem_get_pat_index(i915,
+							       I915_CACHE_NONE),
+					0);
 			wmb(); /* flush modifications to the GGTT (insert_page) */
 		} else {
 			page_base += offset & PAGE_MASK;
drivers/gpu/drm/i915/i915_gpu_error.c +6 -2
index f020c0086fbc..54f17ba3b03c 100644
@@ -1117,10 +1117,14 @@ i915_vma_coredump_create(const struct intel_gt *gt,
 			mutex_lock(&ggtt->error_mutex);
 			if (ggtt->vm.raw_insert_page)
 				ggtt->vm.raw_insert_page(&ggtt->vm, dma, slot,
-							 I915_CACHE_NONE, 0);
+						i915_gem_get_pat_index(gt->i915,
+							I915_CACHE_NONE),
+						0);
 			else
 				ggtt->vm.insert_page(&ggtt->vm, dma, slot,
-						     I915_CACHE_NONE, 0);
+						i915_gem_get_pat_index(gt->i915,
+							I915_CACHE_NONE),
+						0);
 			mb();
 
 			s = io_mapping_map_wc(&ggtt->iomap, slot, PAGE_SIZE);
drivers/gpu/drm/i915/i915_vma.c +8 -8
index 20a44788999e..a814775a363d 100644
@@ -315,7 +315,7 @@ struct i915_vma_work {
 	struct i915_vma_resource *vma_res;
 	struct drm_i915_gem_object *obj;
 	struct i915_sw_dma_fence_cb cb;
-	enum i915_cache_level cache_level;
+	unsigned int pat_index;
 	unsigned int flags;
 };
 
@@ -334,7 +334,7 @@ static void __vma_bind(struct dma_fence_work *work)
 		return;
 
 	vma_res->ops->bind_vma(vma_res->vm, &vw->stash,
-			       vma_res, vw->cache_level, vw->flags);
+			       vma_res, vw->pat_index, vw->flags);
 }
 
 static void __vma_release(struct dma_fence_work *work)
@@ -426,7 +426,7 @@ i915_vma_resource_init_from_vma(struct i915_vma_resource *vma_res,
 /**
  * i915_vma_bind - Sets up PTEs for an VMA in it's corresponding address space.
  * @vma: VMA to map
- * @cache_level: mapping cache level
+ * @pat_index: PAT index to set in PTE
  * @flags: flags like global or local mapping
  * @work: preallocated worker for allocating and binding the PTE
  * @vma_res: pointer to a preallocated vma resource. The resource is either
@@ -437,7 +437,7 @@ i915_vma_resource_init_from_vma(struct i915_vma_resource *vma_res,
  * Note that DMA addresses are also the only part of the SG table we care about.
  */
 int i915_vma_bind(struct i915_vma *vma,
-		  enum i915_cache_level cache_level,
+		  unsigned int pat_index,
 		  u32 flags,
 		  struct i915_vma_work *work,
 		  struct i915_vma_resource *vma_res)
@@ -507,7 +507,7 @@ int i915_vma_bind(struct i915_vma *vma,
 		struct dma_fence *prev;
 
 		work->vma_res = i915_vma_resource_get(vma->resource);
-		work->cache_level = cache_level;
+		work->pat_index = pat_index;
 		work->flags = bind_flags;
 
 		/*
@@ -537,7 +537,7 @@ int i915_vma_bind(struct i915_vma *vma,
 
 			return ret;
 		}
-		vma->ops->bind_vma(vma->vm, NULL, vma->resource, cache_level,
+		vma->ops->bind_vma(vma->vm, NULL, vma->resource, pat_index,
 				   bind_flags);
 	}
 
@@ -814,7 +814,7 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 	color = 0;
 
 	if (i915_vm_has_cache_coloring(vma->vm))
-		color = vma->obj->cache_level;
+		color = vma->obj->pat_index;
 
 	if (flags & PIN_OFFSET_FIXED) {
 		u64 offset = flags & PIN_OFFSET_MASK;
@@ -1518,7 +1518,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 
 	GEM_BUG_ON(!vma->pages);
 	err = i915_vma_bind(vma,
-			    vma->obj->cache_level,
+			    vma->obj->pat_index,
 			    flags, work, vma_res);
 	vma_res = NULL;
 	if (err)
drivers/gpu/drm/i915/i915_vma.h +1 -1
index ed5c9d682a1b..31a8f8aa5558 100644
@@ -250,7 +250,7 @@ i915_vma_compare(struct i915_vma *vma,
 
 struct i915_vma_work *i915_vma_work(void);
 int i915_vma_bind(struct i915_vma *vma,
-		  enum i915_cache_level cache_level,
+		  unsigned int pat_index,
 		  u32 flags,
 		  struct i915_vma_work *work,
 		  struct i915_vma_resource *vma_res);
drivers/gpu/drm/i915/i915_vma_types.h +0 -2
index 77fda2244d16..64472b7f0e77 100644
@@ -32,8 +32,6 @@
 
 #include "gem/i915_gem_object_types.h"
 
-enum i915_cache_level;
-
 /**
  * DOC: Global GTT views
  *
drivers/gpu/drm/i915/selftests/i915_gem.c +4 -1
index d91d0ade8abd..bde981a8f23f 100644
@@ -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++) {
drivers/gpu/drm/i915/selftests/i915_gem_evict.c +2 -2
index 37068542aafe..f13a4d265814 100644
@@ -245,7 +245,7 @@ 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;
@@ -308,7 +308,7 @@ 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);
drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +10 -5
index 5361ce70d3f2..0b6350eb4dad 100644
@@ -133,7 +133,7 @@ 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))
@@ -357,7 +357,9 @@ static int lowlevel_hole(struct i915_address_space *vm,
 
 			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;
 
@@ -1375,7 +1377,10 @@ 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);
@@ -1508,7 +1513,7 @@ 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);
@@ -1688,7 +1693,7 @@ 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;
drivers/gpu/drm/i915/selftests/intel_memory_region.c +3 -1
index 3b18e5905c86..cce180114d0c 100644
@@ -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,
drivers/gpu/drm/i915/selftests/mock_gtt.c +4 -4
index ece97e4faacb..a516c0aa88fd 100644
@@ -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)
 {
 }
Signature · 1 line
2.25.1
#11 lore raw

PATCH 7/8 drm/i915: making mtl pte encode generic for gen12

In reply to [email protected]

From: Fei Yang <[email protected]>

PTE encode is platform dependent. After replacing cache_level with pat_index, the newly introduced mtl_pte_encode is actually generic for all gen12 platforms, thus rename it to gen12_pte_encode and apply it to all gen12 platforms.

Cc Chris Wilson <[email protected]>
Cc Matt Roper <[email protected]>
Cc Andi Shyti <[email protected]>
---
 drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/gt/gen8_ppgtt.c +3 -3
index f76ec2cb29ef..e393e20b5894 100644
@@ -60,7 +60,7 @@ static u64 gen8_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
-static u64 mtl_pte_encode(dma_addr_t addr,
+static u64 gen12_pte_encode(dma_addr_t addr,
 			  unsigned int pat_index,
 			  u32 flags)
 {
@@ -999,8 +999,8 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 	 */
 	ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
 
-	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70))
-		ppgtt->vm.pte_encode = mtl_pte_encode;
+	if (GRAPHICS_VER(gt->i915) >= 12)
+		ppgtt->vm.pte_encode = gen12_pte_encode;
 	else
 		ppgtt->vm.pte_encode = gen8_pte_encode;
 
Signature · 1 line
2.25.1
#12 lore raw

PATCH 8/8 drm/i915: Allow user to set cache at BO creation

In reply to [email protected]

From: Fei Yang <[email protected]>

To comply with the design that buffer objects shall have immutable cache setting through out its life cycle, {set, get}_caching ioctl's are no longer supported from MTL onward. With that change caching policy can only be set at object creation time. The current code applies a default (platform dependent) cache setting for all objects. However this is not optimal for performance tuning. The patch extends the existing gem_create uAPI to let user set PAT index for the object at creation time.
The new extension is platform independent, so UMD's can switch to using this extension for older platforms as well, while {set, get}_caching are still supported on these legacy paltforms for compatibility reason.

Cc Chris Wilson <[email protected]>
Cc Matt Roper <[email protected]>
Cc Andi Shyti <[email protected]>
---
 drivers/gpu/drm/i915/gem/i915_gem_create.c | 36 ++++++++++++++++++++++
 include/uapi/drm/i915_drm.h                | 36 ++++++++++++++++++++++
 tools/include/uapi/drm/i915_drm.h          | 36 ++++++++++++++++++++++
 3 files changed, 108 insertions(+)
drivers/gpu/drm/i915/gem/i915_gem_create.c +36 -0
index bfe1dbda4cb7..723c3ddd6c74 100644
@@ -245,6 +245,7 @@ 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,
@@ -394,11 +395,39 @@ 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
 /**
  * i915_gem_create_ext_ioctl - Creates a new mm object and returns a handle to it.
  * @dev: drm device pointer
@@ -418,6 +447,7 @@ 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),
@@ -454,5 +484,11 @@ 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);
 }
include/uapi/drm/i915_drm.h +36 -0
index dba7c5a5b25e..03c5c314846e 100644
@@ -3630,9 +3630,13 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
 	 * struct drm_i915_gem_create_ext_protected_content.
+	 *
+	 * For I915_GEM_CREATE_EXT_SET_PAT usage see
+	 * struct drm_i915_gem_create_ext_set_pat.
 	 */
 #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
 #define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
+#define I915_GEM_CREATE_EXT_SET_PAT 2
 	__u64 extensions;
 };
 
@@ -3747,6 +3751,38 @@ struct drm_i915_gem_create_ext_protected_content {
 	__u32 flags;
 };
 
+/**
+ * struct drm_i915_gem_create_ext_set_pat - The
+ * I915_GEM_CREATE_EXT_SET_PAT extension.
+ *
+ * If this extension is provided, the specified caching policy (PAT index) is
+ * applied to the buffer object.
+ *
+ * Below is an example on how to create an object with specific caching policy:
+ *
+ * .. code-block:: C
+ *
+ *      struct drm_i915_gem_create_ext_set_pat set_pat_ext = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_SET_PAT },
+ *              .pat_index = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = PAGE_SIZE,
+ *              .extensions = (uintptr_t)&set_pat_ext,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ */
+struct drm_i915_gem_create_ext_set_pat {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+	/** @pat_index: PAT index to be set */
+	__u32 pat_index;
+	/** @rsvd: reserved for future use */
+	__u32 rsvd;
+};
+
 /* ID of the protected content session managed by i915 when PXP is active */
 #define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
 
tools/include/uapi/drm/i915_drm.h +36 -0
index 8df261c5ab9b..8cdcdb5fac26 100644
@@ -3607,9 +3607,13 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
 	 * struct drm_i915_gem_create_ext_protected_content.
+	 *
+	 * For I915_GEM_CREATE_EXT_SET_PAT usage see
+	 * struct drm_i915_gem_create_ext_set_pat.
 	 */
 #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
 #define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
+#define I915_GEM_CREATE_EXT_SET_PAT 2
 	__u64 extensions;
 };
 
@@ -3724,6 +3728,38 @@ struct drm_i915_gem_create_ext_protected_content {
 	__u32 flags;
 };
 
+/**
+ * struct drm_i915_gem_create_ext_set_pat - The
+ * I915_GEM_CREATE_EXT_SET_PAT extension.
+ *
+ * If this extension is provided, the specified caching policy (PAT index) is
+ * applied to the buffer object.
+ *
+ * Below is an example on how to create an object with specific caching policy:
+ *
+ * .. code-block:: C
+ *
+ *      struct drm_i915_gem_create_ext_set_pat set_pat_ext = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_SET_PAT },
+ *              .pat_index = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = PAGE_SIZE,
+ *              .extensions = (uintptr_t)&set_pat_ext,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ */
+struct drm_i915_gem_create_ext_set_pat {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+	/** @pat_index: PAT index to be set */
+	__u32 pat_index;
+	/** @rsvd: reserved for future use */
+	__u32 rsvd;
+};
+
 /* ID of the protected content session managed by i915 when PXP is active */
 #define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
 
Signature · 1 line
2.25.1
#6 lore raw

PATCH 2/8 drm/i915/mtl: enforce mtl PTE encode

In reply to [email protected]

From: Fei Yang <[email protected]>

PTE encode functions are platform dependent. This patch ensures the correct PTE encode function is used by calling pte_encode function pointer instead of the hardcoded gen8 version of PTE encode.

---
 drivers/gpu/drm/i915/display/intel_dpt.c |  2 +-
 drivers/gpu/drm/i915/gt/gen8_ppgtt.c     | 17 ++++++++++-------
 drivers/gpu/drm/i915/gt/intel_ggtt.c     |  9 ++++++---
 3 files changed, 17 insertions(+), 11 deletions(-)
drivers/gpu/drm/i915/display/intel_dpt.c +1 -1
index b8027392144d..c5eacfdba1a5 100644
@@ -300,7 +300,7 @@ 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;
 	dpt->obj->is_dpt = true;
drivers/gpu/drm/i915/gt/gen8_ppgtt.c +10 -7
index df4073d32114..11b91e0453c8 100644
@@ -455,7 +455,7 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 		      u32 flags)
 {
 	struct i915_page_directory *pd;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	const gen8_pte_t pte_encode = ppgtt->vm.pte_encode(0, cache_level, flags);
 	gen8_pte_t *vaddr;
 
 	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
@@ -608,7 +608,7 @@ static void gen8_ppgtt_insert_huge(struct i915_address_space *vm,
 				   enum i915_cache_level cache_level,
 				   u32 flags)
 {
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	const gen8_pte_t pte_encode = vm->pte_encode(0, cache_level, flags);
 	unsigned int rem = sg_dma_len(iter->sg);
 	u64 start = vma_res->start;
 
@@ -771,7 +771,7 @@ static void gen8_ppgtt_insert_entry(struct i915_address_space *vm,
 	GEM_BUG_ON(pt->is_compact);
 
 	vaddr = px_vaddr(pt);
-	vaddr[gen8_pd_index(idx, 0)] = gen8_pte_encode(addr, level, flags);
+	vaddr[gen8_pd_index(idx, 0)] = vm->pte_encode(addr, level, flags);
 	drm_clflush_virt_range(&vaddr[gen8_pd_index(idx, 0)], sizeof(*vaddr));
 }
 
@@ -801,7 +801,7 @@ static void __xehpsdv_ppgtt_insert_entry_lm(struct i915_address_space *vm,
 	}
 
 	vaddr = px_vaddr(pt);
-	vaddr[gen8_pd_index(idx, 0) / 16] = gen8_pte_encode(addr, level, flags);
+	vaddr[gen8_pd_index(idx, 0) / 16] = vm->pte_encode(addr, level, flags);
 }
 
 static void xehpsdv_ppgtt_insert_entry(struct i915_address_space *vm,
@@ -848,8 +848,8 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 		pte_flags |= PTE_LM;
 
 	vm->scratch[0]->encode =
-		gen8_pte_encode(px_dma(vm->scratch[0]),
-				I915_CACHE_NONE, pte_flags);
+		vm->pte_encode(px_dma(vm->scratch[0]),
+			       I915_CACHE_NONE, pte_flags);
 
 	for (i = 1; i <= vm->top; i++) {
 		struct drm_i915_gem_object *obj;
@@ -991,7 +991,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 	 */
 	ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
 
-	ppgtt->vm.pte_encode = gen8_pte_encode;
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70))
+		ppgtt->vm.pte_encode = mtl_pte_encode;
+	else
+		ppgtt->vm.pte_encode = gen8_pte_encode;
 
 	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
 	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
drivers/gpu/drm/i915/gt/intel_ggtt.c +6 -3
index 4a16bfcde1de..ba3109338aee 100644
@@ -274,7 +274,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 	gen8_pte_t __iomem *pte =
 		(gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
 
-	gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, flags));
+	gen8_set_pte(pte, ggtt->vm.pte_encode(addr, level, flags));
 
 	ggtt->invalidate(ggtt);
 }
@@ -284,8 +284,8 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     enum i915_cache_level level,
 				     u32 flags)
 {
-	const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, flags);
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	const gen8_pte_t pte_encode = ggtt->vm.pte_encode(0, level, flags);
 	gen8_pte_t __iomem *gte;
 	gen8_pte_t __iomem *end;
 	struct sgt_iter iter;
@@ -1008,7 +1008,10 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->vm.vma_ops.bind_vma    = intel_ggtt_bind_vma;
 	ggtt->vm.vma_ops.unbind_vma  = intel_ggtt_unbind_vma;
 
-	ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+		ggtt->vm.pte_encode = mtl_ggtt_pte_encode;
+	else
+		ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
 
 	return ggtt_probe_common(ggtt, size);
 }
Signature · 1 line
2.25.1
#8 lore raw

PATCH 4/8 drm/i915/mtl: end support for set caching ioctl

In reply to [email protected]

From: Fei Yang <[email protected]>

The design is to keep Buffer Object's caching policy immutable through out its life cycle. This patch ends the support for set caching ioctl from MTL onward. While doing that we also set BO's to be 1-way coherent at creation time because GPU is no longer automatically snooping CPU cache.

---
 drivers/gpu/drm/i915/gem/i915_gem_domain.c | 3 +++
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c  | 9 ++++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)
drivers/gpu/drm/i915/gem/i915_gem_domain.c +3 -0
index d2d5a24301b2..bb3575b1479f 100644
@@ -337,6 +337,9 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 	if (IS_DGFX(i915))
 		return -ENODEV;
 
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+		return -EOPNOTSUPP;
+
 	switch (args->caching) {
 	case I915_CACHING_NONE:
 		level = I915_CACHE_NONE;
drivers/gpu/drm/i915/gem/i915_gem_shmem.c +8 -1
index 37d1efcd3ca6..e602c323896b 100644
@@ -601,7 +601,14 @@ static int shmem_object_init(struct intel_memory_region *mem,
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 
-	if (HAS_LLC(i915))
+	/*
+	 * MTL doesn't snooping CPU cache by default for GPU access (namely
+	 * 1-way coherency). However some UMD's are currently depending on
+	 * that. Make 1-way coherent the default setting for MTL. A follow
+	 * up patch will extend the GEM_CREATE uAPI to allow UMD's specify
+	 * caching mode at BO creation time
+	 */
+	if (HAS_LLC(i915) || (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)))
 		/* On some devices, we can have the GPU use the LLC (the CPU
 		 * cache) for about a 10% performance improvement
 		 * compared to uncached.  Graphics requests other than
Signature · 1 line
2.25.1
#9 lore raw

PATCH 5/8 drm/i915: preparation for using PAT index

In reply to [email protected]

From: Fei Yang <[email protected]>

This patch is a preparation for replacing enum i915_cache_level with PAT index. Caching policy for buffer objects is set through the PAT index in PTE, the old i915_cache_level is not sufficient to represent all caching modes supported by the hardware.

Preparing the transition by adding some platform dependent data structures and helper functions to translate the cache_level to pat_index.

cachelevel_to_pat: a platform dependent array mapping cache_level to
pat_index.

max_pat_index: the maximum PAT index supported by the hardware. Needed for
validating the PAT index passed in from user space.

i915_gem_get_pat_index: function to convert cache_level to PAT index.

obj_to_i915(obj): macro moved to header file for wider usage.

I915_MAX_CACHE_LEVEL: upper bound of i915_cache_level for the
convenience of coding.

Cc Chris Wilson <[email protected]>
Cc Matt Roper <[email protected]>
Cc Andi Shyti <[email protected]>
---
 drivers/gpu/drm/i915/gem/i915_gem_object.c    |  9 +++
 drivers/gpu/drm/i915/gem/i915_gem_object.h    |  4 +
 .../gpu/drm/i915/gem/i915_gem_object_types.h  |  1 +
 drivers/gpu/drm/i915/gem/i915_gem_shrinker.c  |  2 -
 drivers/gpu/drm/i915/gt/gen8_ppgtt.c          |  6 ++
 drivers/gpu/drm/i915/gt/intel_ggtt.c          |  6 ++
 drivers/gpu/drm/i915/i915_pci.c               | 75 +++++++++++++++++--
 drivers/gpu/drm/i915/intel_device_info.h      |  5 ++
 .../gpu/drm/i915/selftests/mock_gem_device.c  |  6 ++
 9 files changed, 104 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/gem/i915_gem_object.c +9 -0
index 4666bb82f312..8c70a0ec7d2f 100644
@@ -45,6 +45,15 @@ 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];
+}
+
 struct drm_i915_gem_object *i915_gem_object_alloc(void)
 {
 	struct drm_i915_gem_object *obj;
drivers/gpu/drm/i915/gem/i915_gem_object.h +4 -0
index 885ccde9dc3c..4c92e17b4337 100644
@@ -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 +32,8 @@ 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);
 void i915_gem_init__objects(struct drm_i915_private *i915);
 
 void i915_objects_module_exit(void);
drivers/gpu/drm/i915/gem/i915_gem_object_types.h +1 -0
index 5dcbbef31d44..890f3ad497c5 100644
@@ -194,6 +194,7 @@ enum i915_cache_level {
 	 * engine.
 	 */
 	I915_CACHE_WT,
+	I915_MAX_CACHE_LEVEL,
 };
 
 enum i915_map_type {
drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +0 -2
index b1672e054b21..214763942aa2 100644
@@ -460,8 +460,6 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
 	fs_reclaim_release(GFP_KERNEL);
 }
 
-#define obj_to_i915(obj__) to_i915((obj__)->base.dev)
-
 /**
  * i915_gem_object_make_unshrinkable - Hide the object from the shrinker. By
  * default all object types that support shrinking(see IS_SHRINKABLE), will also
drivers/gpu/drm/i915/gt/gen8_ppgtt.c +6 -0
index 11b91e0453c8..7a4b1d1afce9 100644
@@ -78,6 +78,12 @@ static u64 mtl_pte_encode(dma_addr_t addr,
 	case I915_CACHE_WT:
 		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;
 	}
 
 	return pte;
drivers/gpu/drm/i915/gt/intel_ggtt.c +6 -0
index ba3109338aee..91056b9a60a9 100644
@@ -242,6 +242,12 @@ u64 mtl_ggtt_pte_encode(dma_addr_t addr,
 	case I915_CACHE_WT:
 		pte |= MTL_GGTT_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;
 	}
 
 	return pte;
drivers/gpu/drm/i915/i915_pci.c +67 -8

225 lines not on this page · raw message

drivers/gpu/drm/i915/intel_device_info.h +5 -0
index 080a4557899b..d737dd601a6e 100644
@@ -35,6 +35,8 @@
 #include "gt/intel_context_types.h"
 #include "gt/intel_sseu.h"
 
+#include "gem/i915_gem_object_types.h"
+
 struct drm_printer;
 struct drm_i915_private;
 struct intel_gt_definition;
@@ -308,6 +310,9 @@ struct intel_device_info {
 	 * Initial runtime info. Do not access outside of i915_driver_create().
 	 */
 	const struct intel_runtime_info __runtime;
+
+	u32 cachelevel_to_pat[I915_MAX_CACHE_LEVEL];
+	u32 max_pat_index;
 };
 
 struct intel_driver_caps {
drivers/gpu/drm/i915/selftests/mock_gem_device.c +6 -0
index f6a7c0bd2955..bc28f7afa54a 100644
@@ -124,6 +124,7 @@ struct drm_i915_private *mock_gem_device(void)
 #endif
 	struct drm_i915_private *i915;
 	struct pci_dev *pdev;
+	unsigned int i;
 	int ret;
 
 	pdev = kzalloc(sizeof(*pdev), GFP_KERNEL);
@@ -180,6 +181,11 @@ struct drm_i915_private *mock_gem_device(void)
 		I915_GTT_PAGE_SIZE_2M;
 
 	RUNTIME_INFO(i915)->memory_regions = REGION_SMEM;
+
+	/* simply use legacy cache level for mock device */
+	for (i = 0; i < I915_MAX_CACHE_LEVEL; i++)
+		mkwrite_device_info(i915)->cachelevel_to_pat[i] = i;
+
 	intel_memory_regions_hw_probe(i915);
 
 	spin_lock_init(&i915->gpu_error.lock);
Signature · 1 line
2.25.1
#1 lore raw

PATCH 1/8 drm/i915/mtl: Define MOCS and PAT tables for MTL

In reply to [email protected]

From: Fei Yang <[email protected]>

On MTL, GT can no longer allocate on LLC - only the CPU can. This, along with addition of support for ADM/L4 cache calls a MOCS/PAT table update. Also defines PTE encode functions for MTL as it has different PAT index definition than previous platforms.

BSpec: 44509, 45101, 44235

---
 drivers/gpu/drm/i915/gt/gen8_ppgtt.c    | 28 +++++++++
 drivers/gpu/drm/i915/gt/gen8_ppgtt.h    |  3 +
 drivers/gpu/drm/i915/gt/intel_ggtt.c    | 27 +++++++++
 drivers/gpu/drm/i915/gt/intel_gtt.c     | 23 +++++++-
 drivers/gpu/drm/i915/gt/intel_gtt.h     | 20 ++++++-
 drivers/gpu/drm/i915/gt/intel_mocs.c    | 76 +++++++++++++++++++++++--
 drivers/gpu/drm/i915/gt/selftest_mocs.c |  2 +-
 drivers/gpu/drm/i915/i915_pci.c         |  1 +
 8 files changed, 173 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/gt/gen8_ppgtt.c +28 -0
index 4daaa6f55668..df4073d32114 100644
@@ -55,6 +55,34 @@ 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)
+{
+	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW;
+
+	if (unlikely(flags & PTE_READ_ONLY))
+		pte &= ~GEN8_PAGE_RW;
+
+	if (flags & PTE_LM)
+		pte |= GEN12_PPGTT_PTE_LM | GEN12_PPGTT_PTE_NC;
+
+	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:
+		pte |= GEN12_PPGTT_PTE_PAT0;
+		break;
+	}
+
+	return pte;
+}
+
 static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 {
 	struct drm_i915_private *i915 = ppgtt->vm.i915;
drivers/gpu/drm/i915/gt/gen8_ppgtt.h +3 -0
index f541d19264b4..6b8ce7f4d25a 100644
@@ -18,5 +18,8 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
 			 enum i915_cache_level level,
 			 u32 flags);
+u64 mtl_ggtt_pte_encode(dma_addr_t addr,
+			unsigned int pat_index,
+			u32 flags);
 
 #endif
drivers/gpu/drm/i915/gt/intel_ggtt.c +27 -0
index 3c7f1ed92f5b..4a16bfcde1de 100644
@@ -220,6 +220,33 @@ static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
 	}
 }
 
+u64 mtl_ggtt_pte_encode(dma_addr_t addr,
+			enum i915_cache_level level,
+			u32 flags)
+{
+	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT;
+
+	GEM_BUG_ON(addr & ~GEN12_GGTT_PTE_ADDR_MASK);
+
+	if (flags & PTE_LM)
+		pte |= GEN12_GGTT_PTE_LM;
+
+	switch (level) {
+	case I915_CACHE_NONE:
+		pte |= MTL_GGTT_PTE_PAT1;
+		break;
+	case I915_CACHE_LLC:
+	case I915_CACHE_L3_LLC:
+		pte |= MTL_GGTT_PTE_PAT0 | MTL_GGTT_PTE_PAT1;
+		break;
+	case I915_CACHE_WT:
+		pte |= MTL_GGTT_PTE_PAT0;
+		break;
+	}
+
+	return pte;
+}
+
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
 			 enum i915_cache_level level,
 			 u32 flags)
drivers/gpu/drm/i915/gt/intel_gtt.c +22 -1
index 4f436ba7a3c8..1e1b34e22cf5 100644
@@ -468,6 +468,25 @@ void gtt_write_workarounds(struct intel_gt *gt)
 	}
 }
 
+static void mtl_setup_private_ppat(struct intel_uncore *uncore)
+{
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(0),
+			   MTL_PPAT_L4_0_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(1),
+			   MTL_PPAT_L4_1_WT);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(2),
+			   MTL_PPAT_L4_3_UC);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(3),
+			   MTL_PPAT_L4_0_WB | MTL_2_COH_1W);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(4),
+			   MTL_PPAT_L4_0_WB | MTL_3_COH_2W);
+
+	/*
+	 * Remaining PAT entries are left at the hardware-default
+	 * fully-cached setting
+	 */
+}
+
 static void tgl_setup_private_ppat(struct intel_uncore *uncore)
 {
 	/* TGL doesn't support LLC or AGE settings */
@@ -603,7 +622,9 @@ void setup_private_pat(struct intel_gt *gt)
 
 	GEM_BUG_ON(GRAPHICS_VER(i915) < 8);
 
-	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+	if (IS_METEORLAKE(i915))
+		mtl_setup_private_ppat(uncore);
+	else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
 		xehp_setup_private_ppat(gt);
 	else if (GRAPHICS_VER(i915) >= 12)
 		tgl_setup_private_ppat(uncore);
drivers/gpu/drm/i915/gt/intel_gtt.h +19 -1
index 69ce55f517f5..b632167eaf2e 100644
@@ -88,9 +88,18 @@ typedef u64 gen8_pte_t;
 #define BYT_PTE_SNOOPED_BY_CPU_CACHES	REG_BIT(2)
 #define BYT_PTE_WRITEABLE		REG_BIT(1)
 
+#define GEN12_PPGTT_PTE_PAT3    BIT_ULL(62)
 #define GEN12_PPGTT_PTE_LM	BIT_ULL(11)
+#define GEN12_PPGTT_PTE_PAT2    BIT_ULL(7)
+#define GEN12_PPGTT_PTE_NC      BIT_ULL(5)
+#define GEN12_PPGTT_PTE_PAT1    BIT_ULL(4)
+#define GEN12_PPGTT_PTE_PAT0    BIT_ULL(3)
 
-#define GEN12_GGTT_PTE_LM	BIT_ULL(1)
+#define GEN12_GGTT_PTE_LM		BIT_ULL(1)
+#define MTL_GGTT_PTE_PAT0		BIT_ULL(52)
+#define MTL_GGTT_PTE_PAT1		BIT_ULL(53)
+#define GEN12_GGTT_PTE_ADDR_MASK	GENMASK_ULL(45, 12)
+#define MTL_GGTT_PTE_PAT_MASK		GENMASK_ULL(53, 52)
 
 #define GEN12_PDE_64K BIT(6)
 #define GEN12_PTE_PS64 BIT(8)
@@ -147,6 +156,15 @@ typedef u64 gen8_pte_t;
 #define GEN8_PDE_IPS_64K BIT(11)
 #define GEN8_PDE_PS_2M   BIT(7)
 
+#define MTL_PPAT_L4_CACHE_POLICY_MASK	REG_GENMASK(3, 2)
+#define MTL_PAT_INDEX_COH_MODE_MASK	REG_GENMASK(1, 0)
+#define MTL_PPAT_L4_3_UC	REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 3)
+#define MTL_PPAT_L4_1_WT	REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 1)
+#define MTL_PPAT_L4_0_WB	REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 0)
+#define MTL_3_COH_2W	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 3)
+#define MTL_2_COH_1W	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 2)
+#define MTL_0_COH_NON	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 0)
+
 enum i915_cache_level;
 
 struct drm_i915_gem_object;
drivers/gpu/drm/i915/gt/intel_mocs.c +72 -4

119 lines not on this page · raw message

drivers/gpu/drm/i915/gt/selftest_mocs.c +1 -1
index ca009a6a13bd..730796346514 100644
@@ -137,7 +137,7 @@ static int read_mocs_table(struct i915_request *rq,
 		return 0;
 
 	if (HAS_GLOBAL_MOCS_REGISTERS(rq->engine->i915))
-		addr = global_mocs_offset();
+		addr = global_mocs_offset(rq->engine->gt);
 	else
 		addr = mocs_offset(rq->engine);
 
drivers/gpu/drm/i915/i915_pci.c +1 -0
index cddb6e197972..025d32c0b161 100644
@@ -1146,6 +1146,7 @@ static const struct intel_device_info mtl_info = {
 	.has_flat_ccs = 0,
 	.has_gmd_id = 1,
 	.has_guc_deprivilege = 1,
+	.has_llc = 0,
 	.has_mslice_steering = 0,
 	.has_snoop = 1,
 	.__runtime.memory_regions = REGION_SMEM | REGION_STOLEN_LMEM,
Signature · 1 line
2.25.1
#13 lore raw

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for drm/i915/mtl: Define MOCS and PAT tables for MTL (rev2)

In reply to [email protected]
== Series Details ==

== Series Details ==

Series: drm/i915/mtl: Define MOCS and PAT tables for MTL (rev2)
URL : https://patchwork.freedesktop.org/series/115980/
State : warning

== Summary ==

Error: dim checkpatch failed
30f069e7ed60 drm/i915/mtl: Define MOCS and PAT tables for MTL
-:86: WARNING:AVOID_BUG: Do not crash the kernel unless it is absolutely unavoidable--use WARN_ON_ONCE() plus recovery code (if feasible) instead of BUG() or variants #86: FILE: drivers/gpu/drm/i915/gt/intel_ggtt.c:229:
+ GEM_BUG_ON(addr & ~GEN12_GGTT_PTE_ADDR_MASK);

total: 0 errors, 1 warnings, 0 checks, 278 lines checked
af63be507ed7 drm/i915/mtl: enforce mtl PTE encode
09deb641c224 drm/i915/mtl: workaround coherency issue for Media
82f2bc853551 drm/i915/mtl: end support for set caching ioctl
10958b9a7f6b drm/i915: preparation for using PAT index
a7f3b6eddaf0 drm/i915: use pat_index instead of cache_level
-:22: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #22:
cached, uncached, or writethrough. For these simple cases, using cache_level

-:663: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #663: FILE: drivers/gpu/drm/i915/gt/gen8_ppgtt.c:878:
+ i915_gem_get_pat_index(vm->i915,
+ I915_CACHE_NONE));

-:933: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #933: FILE: drivers/gpu/drm/i915/gt/intel_ggtt.c:1303:
+ i915_gem_get_pat_index(vm->i915,
+ I915_CACHE_NONE),

-:1631: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #1631: FILE: drivers/gpu/drm/i915/i915_gem.c:424:
+ i915_gem_object_get_dma_address(obj,
+ offset >> PAGE_SHIFT),

-:1646: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #1646: FILE: drivers/gpu/drm/i915/i915_gem.c:606:
+ i915_gem_object_get_dma_address(obj,
+ offset >> PAGE_SHIFT),

-:1664: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #1664: FILE: drivers/gpu/drm/i915/i915_gpu_error.c:1121:
+ i915_gem_get_pat_index(gt->i915,
+ I915_CACHE_NONE),

-:1670: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #1670: FILE: drivers/gpu/drm/i915/i915_gpu_error.c:1126:
+ i915_gem_get_pat_index(gt->i915,
+ I915_CACHE_NONE),

-:1788: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #1788: FILE: drivers/gpu/drm/i915/selftests/i915_gem.c:62:
+ i915_gem_get_pat_index(i915,
+ I915_CACHE_NONE),

-:1834: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #1834: FILE: drivers/gpu/drm/i915/selftests/i915_gem_gtt.c:361:
+ i915_gem_get_pat_index(vm->i915,
+ I915_CACHE_NONE),

-:1846: ERROR:CODE_INDENT: code indent should use tabs where possible #1846: FILE: drivers/gpu/drm/i915/selftests/i915_gem_gtt.c:1382:
+^I^I^I^I^I I915_CACHE_NONE),$

-:1846: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #1846: FILE: drivers/gpu/drm/i915/selftests/i915_gem_gtt.c:1382:
+ i915_gem_get_pat_index(i915,
+ I915_CACHE_NONE),

-:1880: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #1880: FILE: drivers/gpu/drm/i915/selftests/intel_memory_region.c:1075:
+ i915_gem_get_pat_index(i915,
+ I915_CACHE_NONE),

total: 1 errors, 1 warnings, 10 checks, 1610 lines checked 7da7b8aa70ef drm/i915: making mtl pte encode generic for gen12 -:26: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #26: FILE: drivers/gpu/drm/i915/gt/gen8_ppgtt.c:64:
+static u64 gen12_pte_encode(dma_addr_t addr,
unsigned int pat_index,

total: 0 errors, 0 warnings, 1 checks, 18 lines checked e47d0e4f8bf7 drm/i915: Allow user to set cache at BO creation

#15 lore raw

[Intel-gfx] ✗ Fi.CI.BAT: failure for drm/i915/mtl: Define MOCS and PAT tables for MTL (rev2)

In reply to [email protected]
== Series Details ==

== Series Details ==

Series: drm/i915/mtl: Define MOCS and PAT tables for MTL (rev2)
URL : https://patchwork.freedesktop.org/series/115980/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_12982 -> Patchwork_115980v2
====================================================

Summary
-------

**FAILURE**

Serious unknown changes coming with Patchwork_115980v2 absolutely need to be verified manually.

If you think the reported changes have nothing to do with the changes introduced in Patchwork_115980v2, please notify your bug team to allow them to document this new failure mode, which will reduce false positives in CI.

External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/index.html

Participating hosts (37 -> 36)
------------------------------

Missing (1): fi-snb-2520m

Possible new issues
-------------------

Here are the unknown changes that may have been introduced in Patchwork_115980v2:

### IGT changes ###

#### Possible regressions ####

* igt@i915_selftest@live@execlists:
- fi-glk-j4005: [PASS][1] -> [ABORT][2]
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12982/fi-glk-j4005/igt@i915_selftest@[email protected]
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/fi-glk-j4005/igt@i915_selftest@[email protected]

* igt@i915_selftest@live@gt_engines:
- fi-glk-j4005: [PASS][3] -> [FAIL][4]
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12982/fi-glk-j4005/igt@i915_selftest@live@gt_engines.html
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/fi-glk-j4005/igt@i915_selftest@live@gt_engines.html

* igt@i915_selftest@live@gt_mocs:
- fi-glk-j4005: [PASS][5] -> [DMESG-FAIL][6] +2 similar issues
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12982/fi-glk-j4005/igt@i915_selftest@live@gt_mocs.html
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/fi-glk-j4005/igt@i915_selftest@live@gt_mocs.html

* igt@i915_selftest@live@workarounds:
- fi-apl-guc: [PASS][7] -> [DMESG-FAIL][8] +2 similar issues
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12982/fi-apl-guc/igt@i915_selftest@[email protected]
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/fi-apl-guc/igt@i915_selftest@[email protected]

Known issues
------------

Here are the changes found in Patchwork_115980v2 that come from known issues:

### IGT changes ###

#### Issues hit ####

* igt@i915_selftest@live@mman:
- bat-rpls-2: [PASS][9] -> [TIMEOUT][10] ([i915#6794])
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12982/bat-rpls-2/igt@i915_selftest@[email protected]
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/bat-rpls-2/igt@i915_selftest@[email protected]

* igt@i915_selftest@live@reset:
- bat-rpls-1: [PASS][11] -> [ABORT][12] ([i915#4983] / [i915#7981])
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12982/bat-rpls-1/igt@i915_selftest@[email protected]
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/bat-rpls-1/igt@i915_selftest@[email protected]

* igt@kms_pipe_crc_basic@read-crc:
- bat-adlp-9: NOTRUN -> [SKIP][13] ([i915#3546]) +1 similar issue
[13]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/bat-adlp-9/igt@[email protected]

#### Possible fixes ####

* igt@kms_pipe_crc_basic@nonblocking-crc-frame-sequence@pipe-c-dp-1:
- bat-dg2-8: [FAIL][14] ([i915#7932]) -> [PASS][15] +1 similar issue
[14]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12982/bat-dg2-8/igt@kms_pipe_crc_basic@[email protected]
[15]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/bat-dg2-8/igt@kms_pipe_crc_basic@[email protected]

[i915#3546]: https://gitlab.freedesktop.org/drm/intel/issues/3546
[i915#4983]: https://gitlab.freedesktop.org/drm/intel/issues/4983
[i915#6794]: https://gitlab.freedesktop.org/drm/intel/issues/6794
[i915#7932]: https://gitlab.freedesktop.org/drm/intel/issues/7932
[i915#7981]: https://gitlab.freedesktop.org/drm/intel/issues/7981

Build changes
-------------

* Linux: CI_DRM_12982 -> Patchwork_115980v2

CI-20190529: 20190529
CI_DRM_12982: 16847a8a3017f37ce0b583d7af30f33ec286d0df @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_7244: ce91d123cc294609ce00499121469bb7b6f96c70 @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
Patchwork_115980v2: 16847a8a3017f37ce0b583d7af30f33ec286d0df @ git://anongit.freedesktop.org/gfx-ci/linux

### Linux commits

4c6d85b25638 drm/i915: Allow user to set cache at BO creation 7be2d21981be drm/i915: making mtl pte encode generic for gen12 c05663839669 drm/i915: use pat_index instead of cache_level 413fb18f029b drm/i915: preparation for using PAT index af6623097042 drm/i915/mtl: end support for set caching ioctl 780cd0ad2350 drm/i915/mtl: workaround coherency issue for Media dd62bbdfa894 drm/i915/mtl: enforce mtl PTE encode 327b1fe76b30 drm/i915/mtl: Define MOCS and PAT tables for MTL

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_115980v2/index.html

#2 lore raw
In reply to [email protected]
Quoted 7 lines · On Fri, Apr 07, 2023 at 12:12:29AM -0700, [email protected] wrote:

From: Fei Yang <[email protected]>

On MTL, GT can no longer allocate on LLC - only the CPU can. This, along with addition of support for ADM/L4 cache calls a MOCS/PAT table update. Also defines PTE encode functions for MTL as it has different PAT index definition than previous platforms.

It might be best to keep the PTE encoding as a separate patch from the MOCS/PAT tables. It's a different enough topic that it probably deserves a patch of its own.

Quoted 119 lines

BSpec: 44509, 45101, 44235

---
 drivers/gpu/drm/i915/gt/gen8_ppgtt.c    | 28 +++++++++
 drivers/gpu/drm/i915/gt/gen8_ppgtt.h    |  3 +
 drivers/gpu/drm/i915/gt/intel_ggtt.c    | 27 +++++++++
 drivers/gpu/drm/i915/gt/intel_gtt.c     | 23 +++++++-
 drivers/gpu/drm/i915/gt/intel_gtt.h     | 20 ++++++-
 drivers/gpu/drm/i915/gt/intel_mocs.c    | 76 +++++++++++++++++++++++--
 drivers/gpu/drm/i915/gt/selftest_mocs.c |  2 +-
 drivers/gpu/drm/i915/i915_pci.c         |  1 +
 8 files changed, 173 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/gt/gen8_ppgtt.c +28 -0
index 4daaa6f55668..df4073d32114 100644
@@ -55,6 +55,34 @@ 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)
+{
+	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW;
+
+	if (unlikely(flags & PTE_READ_ONLY))
+		pte &= ~GEN8_PAGE_RW;
+
+	if (flags & PTE_LM)
+		pte |= GEN12_PPGTT_PTE_LM | GEN12_PPGTT_PTE_NC;
+
+	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:
+		pte |= GEN12_PPGTT_PTE_PAT0;
+		break;
+	}
+
+	return pte;
+}
+
 static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 {
 	struct drm_i915_private *i915 = ppgtt->vm.i915;
drivers/gpu/drm/i915/gt/gen8_ppgtt.h +3 -0
index f541d19264b4..6b8ce7f4d25a 100644
@@ -18,5 +18,8 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
 			 enum i915_cache_level level,
 			 u32 flags);
+u64 mtl_ggtt_pte_encode(dma_addr_t addr,
+			unsigned int pat_index,
+			u32 flags);
 
 #endif
drivers/gpu/drm/i915/gt/intel_ggtt.c +27 -0
index 3c7f1ed92f5b..4a16bfcde1de 100644
@@ -220,6 +220,33 @@ static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
 	}
 }
 
+u64 mtl_ggtt_pte_encode(dma_addr_t addr,
+			enum i915_cache_level level,
+			u32 flags)
+{
+	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT;
+
+	GEM_BUG_ON(addr & ~GEN12_GGTT_PTE_ADDR_MASK);
+
+	if (flags & PTE_LM)
+		pte |= GEN12_GGTT_PTE_LM;
+
+	switch (level) {
+	case I915_CACHE_NONE:
+		pte |= MTL_GGTT_PTE_PAT1;
+		break;
+	case I915_CACHE_LLC:
+	case I915_CACHE_L3_LLC:
+		pte |= MTL_GGTT_PTE_PAT0 | MTL_GGTT_PTE_PAT1;
+		break;
+	case I915_CACHE_WT:
+		pte |= MTL_GGTT_PTE_PAT0;
+		break;
+	}
+
+	return pte;
+}
+
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
 			 enum i915_cache_level level,
 			 u32 flags)
drivers/gpu/drm/i915/gt/intel_gtt.c +2 -0
index 4f436ba7a3c8..1e1b34e22cf5 100644
@@ -468,6 +468,25 @@ void gtt_write_workarounds(struct intel_gt *gt)
 	}
 }
 
+static void mtl_setup_private_ppat(struct intel_uncore *uncore)
+{

drivers/gpu/drm/i915/gt/intel_gtt.c void gtt_write_workarounds(struct intel_gt *gt) · line 482

Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_gtt.c +10 -0
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(0),
+			   MTL_PPAT_L4_0_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(1),
+			   MTL_PPAT_L4_1_WT);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(2),
+			   MTL_PPAT_L4_3_UC);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(3),
+			   MTL_PPAT_L4_0_WB | MTL_2_COH_1W);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(4),
+			   MTL_PPAT_L4_0_WB | MTL_3_COH_2W);

These registers are multicast registers on the primary GT. We need to use XEHP_PAT_INDEX and the MCR-aware functions on the primary GT.

Although we're not programming the higher PAT entries on MTL (yet), there's also a jump in the MMIO offsets that we should incorporate into the PAT_INDEX macro to future-proof the code.

Quoted 11 lines
drivers/gpu/drm/i915/gt/intel_gtt.c +7 -0
+
+	/*
+	 * Remaining PAT entries are left at the hardware-default
+	 * fully-cached setting
+	 */
+}
+
 static void tgl_setup_private_ppat(struct intel_uncore *uncore)
 {
 	/* TGL doesn't support LLC or AGE settings */

drivers/gpu/drm/i915/gt/intel_gtt.c void setup_private_pat(struct intel_gt *gt) · line 626

Quoted 6 lines
drivers/gpu/drm/i915/gt/intel_gtt.c +2 -1
@@ -603,7 +622,9 @@ void setup_private_pat(struct intel_gt *gt)
 
 	GEM_BUG_ON(GRAPHICS_VER(i915) < 8);
 
-	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+	if (IS_METEORLAKE(i915))
+		mtl_setup_private_ppat(uncore);

We need to handle the primary GT and media GT separately since the media GT registers are unicast whereas primary are multicast.

See
https://gitlab.freedesktop.org/drm/xe/kernel/-/blob/drm-xe-next/drivers/gpu/drm/xe/xe_pat.c
for how this was handled in the Xe driver.

Quoted 9 lines
drivers/gpu/drm/i915/gt/intel_gtt.c +1 -0
+	else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
 		xehp_setup_private_ppat(gt);
 	else if (GRAPHICS_VER(i915) >= 12)
 		tgl_setup_private_ppat(uncore);
drivers/gpu/drm/i915/gt/intel_gtt.h +0 -0
index 69ce55f517f5..b632167eaf2e 100644

drivers/gpu/drm/i915/gt/intel_gtt.h typedef u64 gen8_pte_t; · line 96

Quoted 9 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +5 -0
@@ -88,9 +88,18 @@ typedef u64 gen8_pte_t;
 #define BYT_PTE_SNOOPED_BY_CPU_CACHES	REG_BIT(2)
 #define BYT_PTE_WRITEABLE		REG_BIT(1)
 
+#define GEN12_PPGTT_PTE_PAT3    BIT_ULL(62)
 #define GEN12_PPGTT_PTE_LM	BIT_ULL(11)
+#define GEN12_PPGTT_PTE_PAT2    BIT_ULL(7)
+#define GEN12_PPGTT_PTE_NC      BIT_ULL(5)
+#define GEN12_PPGTT_PTE_PAT1    BIT_ULL(4)
+#define GEN12_PPGTT_PTE_PAT0    BIT_ULL(3)

Which bspec page is this from? The PPGTT descriptions in the bspec are kind of hard to track down.

But if these only apply to MTL, why are they labelled as "GEN12?"

Quoted 12 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +5 -1
-#define GEN12_GGTT_PTE_LM	BIT_ULL(1)
+#define GEN12_GGTT_PTE_LM		BIT_ULL(1)
+#define MTL_GGTT_PTE_PAT0		BIT_ULL(52)
+#define MTL_GGTT_PTE_PAT1		BIT_ULL(53)
+#define GEN12_GGTT_PTE_ADDR_MASK	GENMASK_ULL(45, 12)
+#define MTL_GGTT_PTE_PAT_MASK		GENMASK_ULL(53, 52)
 
 #define GEN12_PDE_64K BIT(6)
 #define GEN12_PTE_PS64 BIT(8)
@@ -147,6 +156,15 @@ typedef u64 gen8_pte_t;
 #define GEN8_PDE_IPS_64K BIT(11)

drivers/gpu/drm/i915/gt/intel_gtt.h typedef u64 gen8_pte_t; · line 166

Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +8 -0
 #define GEN8_PDE_PS_2M   BIT(7)
 
+#define MTL_PPAT_L4_CACHE_POLICY_MASK	REG_GENMASK(3, 2)
+#define MTL_PAT_INDEX_COH_MODE_MASK	REG_GENMASK(1, 0)
+#define MTL_PPAT_L4_3_UC	REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 3)
+#define MTL_PPAT_L4_1_WT	REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 1)
+#define MTL_PPAT_L4_0_WB	REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 0)
+#define MTL_3_COH_2W	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 3)
+#define MTL_2_COH_1W	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 2)
+#define MTL_0_COH_NON	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 0)

The values for these definitions don't seem to be aligned.

Quoted 9 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +1 -0
+
 enum i915_cache_level;
 
 struct drm_i915_gem_object;
drivers/gpu/drm/i915/gt/intel_mocs.c +0 -0
index 69b489e8dfed..89570f137b2c 100644

drivers/gpu/drm/i915/gt/intel_mocs.c struct drm_i915_mocs_table { · line 44

Quoted 5 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +2 -0
@@ -40,6 +40,10 @@ struct drm_i915_mocs_table {
 #define LE_COS(value)		((value) << 15)
 #define LE_SSE(value)		((value) << 17)
 
+/* Defines for the tables (GLOB_MOCS_0 - GLOB_MOCS_16) */
+#define _L4_CACHEABILITY(value)	((value) << 2)

We should use REG_GENMASK + REG_FIELD_PREP for new code, which will help ensure that we don't try to pack a value into a field that's too big to fit.

drivers/gpu/drm/i915/gt/intel_mocs.c struct drm_i915_mocs_table { · line 45

Quoted 1 line
drivers/gpu/drm/i915/gt/intel_mocs.c +1 -0
+#define IG_PAT(value)		((value) << 8)

Do we need this one parameterized? It's just a boolean flag, so

        #define IG_PAT          REG_BIT(8)

would be fine (and then don't include the flag on the entries where it isn't set.

Quoted 13 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +2 -0
+
 /* Defines for the tables (LNCFMOCS0 - LNCFMOCS31) - two entries per word */
 #define L3_ESC(value)		((value) << 0)
 #define L3_SCC(value)		((value) << 1)
@@ -50,6 +54,7 @@ struct drm_i915_mocs_table {
 /* Helper defines */
 #define GEN9_NUM_MOCS_ENTRIES	64  /* 63-64 are reserved, but configured. */
 #define PVC_NUM_MOCS_ENTRIES	3
+#define MTL_NUM_MOCS_ENTRIES	16
 
 /* (e)LLC caching options */
 /*

drivers/gpu/drm/i915/gt/intel_mocs.c struct drm_i915_mocs_table { · line 84

Quoted 7 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +4 -0
@@ -73,6 +78,12 @@ struct drm_i915_mocs_table {
 #define L3_2_RESERVED		_L3_CACHEABILITY(2)
 #define L3_3_WB			_L3_CACHEABILITY(3)
 
+/* L4 caching options */
+#define L4_0_WB			_L4_CACHEABILITY(0)
+#define L4_1_WT			_L4_CACHEABILITY(1)
+#define L4_2_RESERVED		_L4_CACHEABILITY(2)

This definition is unnecessary and unused.

drivers/gpu/drm/i915/gt/intel_mocs.c static const struct drm_i915_mocs_entry pvc_mocs_table[] = { · line 430

Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +3 -0
+#define L4_3_UC			_L4_CACHEABILITY(3)
+
 #define MOCS_ENTRY(__idx, __control_value, __l3cc_value) \
 	[__idx] = { \
 		.control_value = __control_value, \
@@ -416,6 +427,57 @@ static const struct drm_i915_mocs_entry pvc_mocs_table[] = {
 	MOCS_ENTRY(2, 0, L3_3_WB),
 };
 
+static const struct drm_i915_mocs_entry mtl_mocs_table[] = {

The entries below with WB L4 cache don't include L4_0_WB. That works out okay since the value is 0, but it seems like it would still be worth including it, just to make the table meaning more clear.

Conversely, I'd drop the "IG_PAT(0)" on entry 0 since that's just a simple boolean flag, so the "0" there is easier to misread than just not including it at all.

Quoted 69 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +57 -1
+	/* Error - Reserved for Non-Use */
+	MOCS_ENTRY(0,
+		   IG_PAT(0),
+		   L3_LKUP(1) | L3_3_WB),
+	/* Cached - L3 + L4 */
+	MOCS_ENTRY(1,
+		   IG_PAT(1),
+		   L3_LKUP(1) | L3_3_WB),
+	/* L4 - GO:L3 */
+	MOCS_ENTRY(2,
+		   IG_PAT(1),
+		   L3_LKUP(1) | L3_1_UC),
+	/* Uncached - GO:L3 */
+	MOCS_ENTRY(3,
+		   IG_PAT(1) | L4_3_UC,
+		   L3_LKUP(1) | L3_1_UC),
+	/* L4 - GO:Mem */
+	MOCS_ENTRY(4,
+		   IG_PAT(1),
+		   L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+	/* Uncached - GO:Mem */
+	MOCS_ENTRY(5,
+		   IG_PAT(1) | L4_3_UC,
+		   L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+	/* L4 - L3:NoLKUP; GO:L3 */
+	MOCS_ENTRY(6,
+		   IG_PAT(1),
+		   L3_1_UC),
+	/* Uncached - L3:NoLKUP; GO:L3 */
+	MOCS_ENTRY(7,
+		   IG_PAT(1) | L4_3_UC,
+		   L3_1_UC),
+	/* L4 - L3:NoLKUP; GO:Mem */
+	MOCS_ENTRY(8,
+		   IG_PAT(1),
+		   L3_GLBGO(1) | L3_1_UC),
+	/* Uncached - L3:NoLKUP; GO:Mem */
+	MOCS_ENTRY(9,
+		   IG_PAT(1) | L4_3_UC,
+		   L3_GLBGO(1) | L3_1_UC),
+	/* Display - L3; L4:WT */
+	MOCS_ENTRY(14,
+		   IG_PAT(1) | L4_1_WT,
+		   L3_LKUP(1) | L3_3_WB),
+	/* CCS - Non-Displayable */
+	MOCS_ENTRY(15,
+		   IG_PAT(1),
+		   L3_GLBGO(1) | L3_1_UC),
+};
+
 enum {
 	HAS_GLOBAL_MOCS = BIT(0),
 	HAS_ENGINE_MOCS = BIT(1),
@@ -445,7 +507,13 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915,
 	memset(table, 0, sizeof(struct drm_i915_mocs_table));
 
 	table->unused_entries_index = I915_MOCS_PTE;
-	if (IS_PONTEVECCHIO(i915)) {
+	if (IS_METEORLAKE(i915)) {
+		table->size = ARRAY_SIZE(mtl_mocs_table);
+		table->table = mtl_mocs_table;
+		table->n_entries = MTL_NUM_MOCS_ENTRIES;
+		table->uc_index = 9;
+		table->unused_entries_index = 1;
+	} else if (IS_PONTEVECCHIO(i915)) {
 		table->size = ARRAY_SIZE(pvc_mocs_table);
 		table->table = pvc_mocs_table;
 		table->n_entries = PVC_NUM_MOCS_ENTRIES;

drivers/gpu/drm/i915/gt/intel_mocs.c void intel_mocs_init_engine(struct intel_engine_cs *engine) · line 719

Quoted 8 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +2 -2
@@ -646,9 +714,9 @@ void intel_mocs_init_engine(struct intel_engine_cs *engine)
 		init_l3cc_table(engine->gt, &table);
 }
 
-static u32 global_mocs_offset(void)
+static u32 global_mocs_offset(struct intel_gt *gt)
 {
-	return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0));
+	return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0)) + gt->uncore->gsi_offset;

Isn't this going to double-apply the GSI offset in __init_mocs_table?

We do need to handle the offset manually in read_mocs_table() since those reads are done with an MI_STORE_REGISTER_MEM instruction.

Handling the GSI offset properly deserves its own patch with a dedicated commit message explaining the details.

Quoted 30 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +1 -1
 }
 
 void intel_set_mocs_index(struct intel_gt *gt)
@@ -671,7 +739,7 @@ void intel_mocs_init(struct intel_gt *gt)
 	 */
 	flags = get_mocs_settings(gt->i915, &table);
 	if (flags & HAS_GLOBAL_MOCS)
-		__init_mocs_table(gt->uncore, &table, global_mocs_offset());
+		__init_mocs_table(gt->uncore, &table, global_mocs_offset(gt));
 
 	/*
 	 * Initialize the L3CC table as part of mocs initalization to make
drivers/gpu/drm/i915/gt/selftest_mocs.c +1 -1
index ca009a6a13bd..730796346514 100644
@@ -137,7 +137,7 @@ static int read_mocs_table(struct i915_request *rq,
 		return 0;
 
 	if (HAS_GLOBAL_MOCS_REGISTERS(rq->engine->i915))
-		addr = global_mocs_offset();
+		addr = global_mocs_offset(rq->engine->gt);
 	else
 		addr = mocs_offset(rq->engine);
 
drivers/gpu/drm/i915/i915_pci.c +0 -0
index cddb6e197972..025d32c0b161 100644

drivers/gpu/drm/i915/i915_pci.c static const struct intel_device_info mtl_info = { · line 1149

Quoted 4 lines
drivers/gpu/drm/i915/i915_pci.c +1 -0
@@ -1146,6 +1146,7 @@ static const struct intel_device_info mtl_info = {
 	.has_flat_ccs = 0,
 	.has_gmd_id = 1,
 	.has_guc_deprivilege = 1,
+	.has_llc = 0,

This should also be in its own patch since it isn't directly related to the MOCS / PAT tables.

Matt

Quoted 6 lines
drivers/gpu/drm/i915/i915_pci.c +0 -0
 	.has_mslice_steering = 0,
 	.has_snoop = 1,
 	.__runtime.memory_regions = REGION_SMEM | REGION_STOLEN_LMEM,
Signature · 1 line
2.25.1
Signature · 4 lines
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation
author
#3 lore raw
Quoted 5 lines

Subject: Re: [Intel-gfx] [PATCH 1/8] drm/i915/mtl: Define MOCS and PAT tables for MTL

Quoted 2 lines · On Fri, Apr 07, 2023 at 12:12:29AM -0700…

From: Fei Yang [email protected]<mailto:[email protected]>

Quoted 8 lines
Quoted 4 lines

On MTL, GT can no longer allocate on LLC - only the CPU can. This, along with addition of support for ADM/L4 cache calls a MOCS/PAT table update. Also defines PTE encode functions for MTL as it has different PAT index definition than previous platforms.

It might be best to keep the PTE encoding as a separate patch from the MOCS/PAT tables. It's a different enough topic that it probably deserves a patch of its own.

Will update in the next revision.

Quoted 123 lines
Quoted 123 lines

BSpec: 44509, 45101, 44235

Cc: Matt Roper [email protected]<mailto:[email protected]>
Cc: Lucas De Marchi [email protected]<mailto:[email protected]>
Signed-off-by: Madhumitha Tolakanahalli Pradeep [email protected]<mailto:[email protected]>

---
 drivers/gpu/drm/i915/gt/gen8_ppgtt.c    | 28 +++++++++
 drivers/gpu/drm/i915/gt/gen8_ppgtt.h    |  3 +
 drivers/gpu/drm/i915/gt/intel_ggtt.c    | 27 +++++++++
 drivers/gpu/drm/i915/gt/intel_gtt.c     | 23 +++++++-
 drivers/gpu/drm/i915/gt/intel_gtt.h     | 20 ++++++-
 drivers/gpu/drm/i915/gt/intel_mocs.c    | 76 +++++++++++++++++++++++--
 drivers/gpu/drm/i915/gt/selftest_mocs.c |  2 +-
 drivers/gpu/drm/i915/i915_pci.c         |  1 +
 8 files changed, 173 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/gt/gen8_ppgtt.c +28 -0
index 4daaa6f55668..df4073d32114 100644
@@ -55,6 +55,34 @@ 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)
+{
+       gen8_pte_t pte = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW;
+
+       if (unlikely(flags & PTE_READ_ONLY))
+                      pte &= ~GEN8_PAGE_RW;
+
+       if (flags & PTE_LM)
+                      pte |= GEN12_PPGTT_PTE_LM | GEN12_PPGTT_PTE_NC;
+
+       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:
+                      pte |= GEN12_PPGTT_PTE_PAT0;
+                      break;
+       }
+
+       return pte;
+}
+
 static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool
 create)  {
         struct drm_i915_private *i915 = ppgtt->vm.i915; diff --git

a/drivers/gpu/drm/i915/gt/gen8_ppgtt.h
b/drivers/gpu/drm/i915/gt/gen8_ppgtt.h
index f541d19264b4..6b8ce7f4d25a 100644

drivers/gpu/drm/i915/gt/gen8_ppgtt.h +3 -0
@@ -18,5 +18,8 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt
 *gt,
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
                                        enum i915_cache_level level,
                                        u32 flags);
+u64 mtl_ggtt_pte_encode(dma_addr_t addr,
+                                     unsigned int pat_index,
+                                     u32 flags);
 

#endif

drivers/gpu/drm/i915/gt/intel_ggtt.c +27 -0
index 3c7f1ed92f5b..4a16bfcde1de 100644
@@ -220,6 +220,33 @@ static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
         }
 }
 
+u64 mtl_ggtt_pte_encode(dma_addr_t addr,
+                                     enum i915_cache_level level,
+                                     u32 flags)
+{
+       gen8_pte_t pte = addr | GEN8_PAGE_PRESENT;
+
+       GEM_BUG_ON(addr & ~GEN12_GGTT_PTE_ADDR_MASK);
+
+       if (flags & PTE_LM)
+                      pte |= GEN12_GGTT_PTE_LM;
+
+       switch (level) {
+       case I915_CACHE_NONE:
+                      pte |= MTL_GGTT_PTE_PAT1;
+                      break;
+       case I915_CACHE_LLC:
+       case I915_CACHE_L3_LLC:
+                      pte |= MTL_GGTT_PTE_PAT0 | MTL_GGTT_PTE_PAT1;
+                      break;
+       case I915_CACHE_WT:
+                      pte |= MTL_GGTT_PTE_PAT0;
+                      break;
+       }
+
+       return pte;
+}
+
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
                                        enum i915_cache_level level,
                                        u32 flags)
drivers/gpu/drm/i915/gt/intel_gtt.c +0 -0
index 4f436ba7a3c8..1e1b34e22cf5 100644
@@ -468,6 +468,25 @@ void gtt_write_workarounds(struct intel_gt *gt)
         }
 }
 
Quoted 14 lines

drivers/gpu/drm/i915/gt/intel_gtt.c void gtt_write_workarounds(struct intel_gt *gt) · line 482

Quoted 11 lines
drivers/gpu/drm/i915/gt/intel_gtt.c +11 -0
+static void mtl_setup_private_ppat(struct intel_uncore *uncore) {
+       intel_uncore_write(uncore, GEN12_PAT_INDEX(0),
+                                        MTL_PPAT_L4_0_WB);
+       intel_uncore_write(uncore, GEN12_PAT_INDEX(1),
+                                        MTL_PPAT_L4_1_WT);
+       intel_uncore_write(uncore, GEN12_PAT_INDEX(2),
+                                        MTL_PPAT_L4_3_UC);
+       intel_uncore_write(uncore, GEN12_PAT_INDEX(3),
+                                        MTL_PPAT_L4_0_WB | MTL_2_COH_1W);
+       intel_uncore_write(uncore, GEN12_PAT_INDEX(4),
+                                        MTL_PPAT_L4_0_WB | MTL_3_COH_2W);

These registers are multicast registers on the primary GT. We need to use XEHP_PAT_INDEX and the MCR-aware functions on the primary GT.

The multicast change has been merged to a different branch and not validated extensively on MTL so far. Will post to mailing list after proper validation.

Quoted 15 lines

Although we're not programming the higher PAT entries on MTL (yet), there's also a jump in the MMIO offsets that we should incorporate into the PAT_INDEX macro to future-proof the code.

Quoted 11 lines
drivers/gpu/drm/i915/gt/intel_gtt.c +7 -0
+
+       /*
+       * Remaining PAT entries are left at the hardware-default
+       * fully-cached setting
+       */
+}
+
 static void tgl_setup_private_ppat(struct intel_uncore *uncore)  {
         /* TGL doesn't support LLC or AGE settings */ @@ -603,7 +622,9 @@
 void setup_private_pat(struct intel_gt *gt)
Quoted 8 lines

drivers/gpu/drm/i915/gt/intel_gtt.c void setup_private_pat(struct intel_gt *gt) · line 626

Quoted 5 lines
drivers/gpu/drm/i915/gt/intel_gtt.c +2 -1
         GEM_BUG_ON(GRAPHICS_VER(i915) < 8);
 
-        if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+       if (IS_METEORLAKE(i915))
+                      mtl_setup_private_ppat(uncore);

We need to handle the primary GT and media GT separately since the media GT registers are unicast whereas primary are multicast.

Same as above.

Quoted 17 lines

See
https://gitlab.freedesktop.org/drm/xe/kernel/-/blob/drm-xe-next/drivers/gpu/drm/xe/xe_pat.c
for how this was handled in the Xe driver.

Quoted 13 lines
drivers/gpu/drm/i915/gt/intel_gtt.c +1 -0
+       else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
                        xehp_setup_private_ppat(gt);
         else if (GRAPHICS_VER(i915) >= 12)
                        tgl_setup_private_ppat(uncore);
drivers/gpu/drm/i915/gt/intel_gtt.h +0 -0
index 69ce55f517f5..b632167eaf2e 100644
@@ -88,9 +88,18 @@ typedef u64 gen8_pte_t;
 #define BYT_PTE_SNOOPED_BY_CPU_CACHES             REG_BIT(2)
 #define BYT_PTE_WRITEABLE                            REG_BIT(1)
 
Quoted 9 lines

drivers/gpu/drm/i915/gt/intel_gtt.h typedef u64 gen8_pte_t; · line 96

Quoted 6 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +5 -0
+#define GEN12_PPGTT_PTE_PAT3    BIT_ULL(62)
 #define GEN12_PPGTT_PTE_LM          BIT_ULL(11)
+#define GEN12_PPGTT_PTE_PAT2    BIT_ULL(7)
+#define GEN12_PPGTT_PTE_NC      BIT_ULL(5)
+#define GEN12_PPGTT_PTE_PAT1    BIT_ULL(4)
+#define GEN12_PPGTT_PTE_PAT0    BIT_ULL(3)

Which bspec page is this from? The PPGTT descriptions in the bspec are kind of hard to track down.

https://gfxspecs.intel.com/Predator/Home/Index/53521
PAT_Index[2:0] = {PAT, PCD, PWT} = BIT(7, 4, 3)
PAT_Index[3] = BIT(62)
PAT_Index[4] = BIT(61)

Quoted 1 line

But if these only apply to MTL, why are they labelled as "GEN12?"

These apply to GEN12plus.

Quoted 14 lines
Quoted 14 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +5 -1
-#define GEN12_GGTT_PTE_LM           BIT_ULL(1)
+#define GEN12_GGTT_PTE_LM                         BIT_ULL(1)
+#define MTL_GGTT_PTE_PAT0                          BIT_ULL(52)
+#define MTL_GGTT_PTE_PAT1                          BIT_ULL(53)
+#define GEN12_GGTT_PTE_ADDR_MASK       GENMASK_ULL(45, 12)
+#define MTL_GGTT_PTE_PAT_MASK                               GENMASK_ULL(53, 52)
 
 #define GEN12_PDE_64K BIT(6)
 #define GEN12_PTE_PS64 BIT(8)
@@ -147,6 +156,15 @@ typedef u64 gen8_pte_t;  #define GEN8_PDE_IPS_64K
 BIT(11)
 #define GEN8_PDE_PS_2M   BIT(7)
 
Quoted 10 lines

drivers/gpu/drm/i915/gt/intel_gtt.h typedef u64 gen8_pte_t; · line 166

Quoted 8 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +8 -0
+#define MTL_PPAT_L4_CACHE_POLICY_MASK             REG_GENMASK(3, 2)
+#define MTL_PAT_INDEX_COH_MODE_MASK              REG_GENMASK(1, 0)
+#define MTL_PPAT_L4_3_UC               REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 3)
+#define MTL_PPAT_L4_1_WT               REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 1)
+#define MTL_PPAT_L4_0_WB               REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 0)
+#define MTL_3_COH_2W     REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 3)
+#define MTL_2_COH_1W     REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 2)
+#define MTL_0_COH_NON   REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 0)

The values for these definitions don't seem to be aligned.

These are aligned with https://gfxspecs.intel.com/Predator/Home/Index/45101

Quoted 13 lines
Quoted 13 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +1 -0
+
 enum i915_cache_level;
 
 struct drm_i915_gem_object;
drivers/gpu/drm/i915/gt/intel_mocs.c +0 -0
index 69b489e8dfed..89570f137b2c 100644
@@ -40,6 +40,10 @@ struct drm_i915_mocs_table {
 #define LE_COS(value)                           ((value) << 15)
 #define LE_SSE(value)                            ((value) << 17)
 
Quoted 7 lines

drivers/gpu/drm/i915/gt/intel_mocs.c struct drm_i915_mocs_table { · line 44

Quoted 2 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +2 -0
+/* Defines for the tables (GLOB_MOCS_0 - GLOB_MOCS_16) */
+#define _L4_CACHEABILITY(value)    ((value) << 2)

We should use REG_GENMASK + REG_FIELD_PREP for new code, which will help ensure that we don't try to pack a value into a field that's too big to fit.

Quoted 1 line
drivers/gpu/drm/i915/gt/intel_mocs.c +1 -0
+#define IG_PAT(value)                          ((value) << 8)

This is used in defining MOCS table. I think it's easier to read with IG_PAT(0) and IG_PAT(1), than with and without IG_PAT.

Quoted 119 lines

Do we need this one parameterized? It's just a boolean flag, so

       #define IG_PAT          REG_BIT(8)

would be fine (and then don't include the flag on the entries where it isn't set.

Quoted 13 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +2 -0
+
 /* Defines for the tables (LNCFMOCS0 - LNCFMOCS31) - two entries per word */
 #define L3_ESC(value)                            ((value) << 0)
 #define L3_SCC(value)                           ((value) << 1)
@@ -50,6 +54,7 @@ struct drm_i915_mocs_table {
 /* Helper defines */
 #define GEN9_NUM_MOCS_ENTRIES               64  /* 63-64 are reserved, but configured. */
 #define PVC_NUM_MOCS_ENTRIES   3
+#define MTL_NUM_MOCS_ENTRIES 16
 
 /* (e)LLC caching options */
 /*

drivers/gpu/drm/i915/gt/intel_mocs.c struct drm_i915_mocs_table { · line 84

Quoted 7 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +4 -0
@@ -73,6 +78,12 @@ struct drm_i915_mocs_table {
 #define L3_2_RESERVED                       _L3_CACHEABILITY(2)
 #define L3_3_WB                                    _L3_CACHEABILITY(3)
 
+/* L4 caching options */
+#define L4_0_WB                                  _L4_CACHEABILITY(0)
+#define L4_1_WT                                   _L4_CACHEABILITY(1)
+#define L4_2_RESERVED                      _L4_CACHEABILITY(2)

This definition is unnecessary and unused.

Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +2 -0
+#define L4_3_UC                                   _L4_CACHEABILITY(3)
+
 #define MOCS_ENTRY(__idx, __control_value, __l3cc_value) \
         [__idx] = { \
                        .control_value = __control_value, \ @@ -416,6 +427,57 @@ static
const struct drm_i915_mocs_entry pvc_mocs_table[] = {
         MOCS_ENTRY(2, 0, L3_3_WB),

};

+static const struct drm_i915_mocs_entry mtl_mocs_table[] = {

The entries below with WB L4 cache don't include L4_0_WB. That works out okay since the value is 0, but it seems like it would still be worth including it, just to make the table meaning more clear.

Conversely, I'd drop the "IG_PAT(0)" on entry 0 since that's just a simple boolean flag, so the "0" there is easier to misread than just not including it at all.

Quoted 71 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +57 -1
+       /* Error - Reserved for Non-Use */
+       MOCS_ENTRY(0,
+                         IG_PAT(0),
+                         L3_LKUP(1) | L3_3_WB),
+       /* Cached - L3 + L4 */
+       MOCS_ENTRY(1,
+                         IG_PAT(1),
+                         L3_LKUP(1) | L3_3_WB),
+       /* L4 - GO:L3 */
+       MOCS_ENTRY(2,
+                         IG_PAT(1),
+                         L3_LKUP(1) | L3_1_UC),
+       /* Uncached - GO:L3 */
+       MOCS_ENTRY(3,
+                         IG_PAT(1) | L4_3_UC,
+                         L3_LKUP(1) | L3_1_UC),
+       /* L4 - GO:Mem */
+       MOCS_ENTRY(4,
+                         IG_PAT(1),
+                         L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+       /* Uncached - GO:Mem */
+       MOCS_ENTRY(5,
+                         IG_PAT(1) | L4_3_UC,
+                         L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+       /* L4 - L3:NoLKUP; GO:L3 */
+       MOCS_ENTRY(6,
+                         IG_PAT(1),
+                         L3_1_UC),
+       /* Uncached - L3:NoLKUP; GO:L3 */
+       MOCS_ENTRY(7,
+                         IG_PAT(1) | L4_3_UC,
+                         L3_1_UC),
+       /* L4 - L3:NoLKUP; GO:Mem */
+       MOCS_ENTRY(8,
+                         IG_PAT(1),
+                         L3_GLBGO(1) | L3_1_UC),
+       /* Uncached - L3:NoLKUP; GO:Mem */
+       MOCS_ENTRY(9,
+                         IG_PAT(1) | L4_3_UC,
+                         L3_GLBGO(1) | L3_1_UC),
+       /* Display - L3; L4:WT */
+       MOCS_ENTRY(14,
+                         IG_PAT(1) | L4_1_WT,
+                         L3_LKUP(1) | L3_3_WB),
+       /* CCS - Non-Displayable */
+       MOCS_ENTRY(15,
+                         IG_PAT(1),
+                         L3_GLBGO(1) | L3_1_UC),
+};
+
 enum {
         HAS_GLOBAL_MOCS = BIT(0),
         HAS_ENGINE_MOCS = BIT(1),
@@ -445,7 +507,13 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915,
         memset(table, 0, sizeof(struct drm_i915_mocs_table));
 
         table->unused_entries_index = I915_MOCS_PTE;
-        if (IS_PONTEVECCHIO(i915)) {
+       if (IS_METEORLAKE(i915)) {
+                      table->size = ARRAY_SIZE(mtl_mocs_table);
+                      table->table = mtl_mocs_table;
+                      table->n_entries = MTL_NUM_MOCS_ENTRIES;
+                      table->uc_index = 9;
+                      table->unused_entries_index = 1;
+       } else if (IS_PONTEVECCHIO(i915)) {
                        table->size = ARRAY_SIZE(pvc_mocs_table);
                        table->table = pvc_mocs_table;
                        table->n_entries = PVC_NUM_MOCS_ENTRIES; @@ -646,9 +714,9 @@ void

intel_mocs_init_engine(struct intel_engine_cs *engine)

                        init_l3cc_table(engine->gt, &table);  }
Quoted 8 lines

drivers/gpu/drm/i915/gt/intel_mocs.c void intel_mocs_init_engine(struct intel_engine_cs *engine)

Quoted 6 lines
drivers/gpu/drm/i915/gt/intel_mocs.c +3 -2
-static u32 global_mocs_offset(void)
+static u32 global_mocs_offset(struct intel_gt *gt)
 {
-        return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0));
+       return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0)) +
+gt->uncore->gsi_offset;

Isn't this going to double-apply the GSI offset in __init_mocs_table?

Good point. Not sure if there are test cases to validate this, but do need to double check.

Quoted 32 lines

We do need to handle the offset manually in read_mocs_table() since those reads are done with an MI_STORE_REGISTER_MEM instruction.

Handling the GSI offset properly deserves its own patch with a dedicated commit message explaining the details.

Quoted 26 lines

}

void intel_set_mocs_index(struct intel_gt *gt) @@ -671,7 +739,7 @@
void intel_mocs_init(struct intel_gt *gt)

          */
         flags = get_mocs_settings(gt->i915, &table);
         if (flags & HAS_GLOBAL_MOCS)
drivers/gpu/drm/i915/gt/intel_mocs.c +1 -1
-                       __init_mocs_table(gt->uncore, &table, global_mocs_offset());
+                      __init_mocs_table(gt->uncore, &table, global_mocs_offset(gt));
 
         /*
          * Initialize the L3CC table as part of mocs initalization to make
drivers/gpu/drm/i915/gt/selftest_mocs.c +1 -1
index ca009a6a13bd..730796346514 100644
@@ -137,7 +137,7 @@ static int read_mocs_table(struct i915_request *rq,
                        return 0;
 
         if (HAS_GLOBAL_MOCS_REGISTERS(rq->engine->i915))
-                       addr = global_mocs_offset();
+                      addr = global_mocs_offset(rq->engine->gt);
         else
                        addr = mocs_offset(rq->engine);
 
Quoted 13 lines

drivers/gpu/drm/i915/i915_pci.c static const struct intel_device_info mtl_info = { · line 1149

Quoted 10 lines
(quoted diff) +0 -0

b/drivers/gpu/drm/i915/i915_pci.c index cddb6e197972..025d32c0b161 100644

drivers/gpu/drm/i915/i915_pci.c +1 -0
@@ -1146,6 +1146,7 @@ static const struct intel_device_info mtl_info = {
         .has_flat_ccs = 0,
         .has_gmd_id = 1,
         .has_guc_deprivilege = 1,
+       .has_llc = 0,

This should also be in its own patch since it isn't directly related to the MOCS / PAT tables.

Will update in the next revision.

Quoted 15 lines

Matt

Quoted 6 lines
drivers/gpu/drm/i915/i915_pci.c +0 -1
         .has_mslice_steering = 0,
         .has_snoop = 1,
         .__runtime.memory_regions = REGION_SMEM | REGION_STOLEN_LMEM,
--

2.25.1

--
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation

#4 lore raw

On Mon, Apr 10, 2023 at 08:55:16PM -0700, Yang, Fei wrote:
...

Quoted 32 lines
Quoted 31 lines
Quoted 22 lines
(quoted diff) +0 -0

b/drivers/gpu/drm/i915/gt/intel_gtt.h

index 69ce55f517f5..b632167eaf2e 100644

--- a/drivers/gpu/drm/i915/gt/intel_gtt.h

+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h

drivers/gpu/drm/i915/gt/intel_gtt.h +0 -0
@@ -88,9 +88,18 @@ typedef u64 gen8_pte_t;
 
   #define BYT_PTE_SNOOPED_BY_CPU_CACHES             REG_BIT(2)
 
   #define BYT_PTE_WRITEABLE                            REG_BIT(1)
 

+#define GEN12_PPGTT_PTE_PAT3    BIT_ULL(62)

  #define GEN12_PPGTT_PTE_LM          BIT_ULL(11)

drivers/gpu/drm/i915/gt/intel_gtt.h typedef u64 gen8_pte_t;

Quoted 7 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +4 -0
+#define GEN12_PPGTT_PTE_PAT2    BIT_ULL(7)
 
+#define GEN12_PPGTT_PTE_NC      BIT_ULL(5)
 
+#define GEN12_PPGTT_PTE_PAT1    BIT_ULL(4)
 
+#define GEN12_PPGTT_PTE_PAT0    BIT_ULL(3)

Quoted 7 lines
Quoted 3 lines

Which bspec page is this from?  The PPGTT descriptions in

the bspec are kind of hard to track down.

    

   [9]https://gfxspecs.intel.com/Predator/Home/Index/53521

The bspec tagging is a bit bizarre in this area, but I don't believe this page is intended to apply to MTL. Note that this page is inside a section specifically listed as "57b VA Support" --- i.e., this general section is for platforms like PVC rather than MTL. MTL only has 48b virtual address space (bspec 55416), so I think one of the pages in the 48b sections is what we should be referencing instead.

If they screwed up and put MTL-specific details only on a PVC-specific page of the bspec, we should probably file a bspec issue about that to get it fixed.

Quoted 14 lines
   PAT_Index[2:0] = {PAT, PCD, PWT} = BIT(7, 4, 3)

   PAT_Index[3] = BIT(62)

   PAT_Index[4] = BIT(61)

    

   > But if these only apply to MTL, why are they labelled as "GEN12?"

    

   These apply to GEN12plus.

That's not what your patch is doing; you're using them in a function that only gets called on MTL. So the question is whether these definitions truly applied to older platforms like TGL/RKL/ADL/etc too (and we need to go back and fix that code), or whether they're Xe_LPG-specific, in which case the "GEN12_" prefix is incorrect.

Also, handling the MTL-specific PTE encoding later in the series, after the transition from cache_level to PAT index, might be best since then you can just implement it correctly at the time the code is introduced; no need to add the cache_level implementation first (which can't even use all the bits) just to come back a few patches later and replace it all with PAT code.

Quoted 53 lines
    

   >> 

   >> -#define GEN12_GGTT_PTE_LM           BIT_ULL(1)

   >> +#define GEN12_GGTT_PTE_LM                         BIT_ULL(1)

   >> +#define MTL_GGTT_PTE_PAT0                          BIT_ULL(52)

   >> +#define MTL_GGTT_PTE_PAT1                          BIT_ULL(53)

   >> +#define GEN12_GGTT_PTE_ADDR_MASK       GENMASK_ULL(45, 12)

   >> +#define MTL_GGTT_PTE_PAT_MASK                              
   GENMASK_ULL(53, 52)

   >> 

   >>  #define GEN12_PDE_64K BIT(6)

   >>  #define GEN12_PTE_PS64 BIT(8)

   >> @@ -147,6 +156,15 @@ typedef u64 gen8_pte_t;  #define GEN8_PDE_IPS_64K

   >> BIT(11)

   >>  #define GEN8_PDE_PS_2M   BIT(7)

   >> 

   >> +#define MTL_PPAT_L4_CACHE_POLICY_MASK             REG_GENMASK(3, 2)

   >> +#define MTL_PAT_INDEX_COH_MODE_MASK              REG_GENMASK(1, 0)

   >> +#define MTL_PPAT_L4_3_UC              
   REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 3)

   >> +#define MTL_PPAT_L4_1_WT              
   REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 1)

   >> +#define MTL_PPAT_L4_0_WB              
   REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 0)

   >> +#define MTL_3_COH_2W     REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK,
   3)

   >> +#define MTL_2_COH_1W     REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK,
   2)

   >> +#define MTL_0_COH_NON   REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 0)
Quoted 8 lines
   > 

   >The values for these definitions don't seem to be aligned.

    

   These are aligned with
   [10]https://gfxspecs.intel.com/Predator/Home/Index/45101

I mean spacing aligned. If your tabstops are set to 8, then the values don't line up visually.

Matt

Signature · 4 lines
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation
author
#5 lore raw
Quoted 49 lines

Subject: Re: [Intel-gfx] [PATCH 1/8] drm/i915/mtl: Define MOCS and PAT tables for MTL

On Mon, Apr 10, 2023 at 08:55:16PM -0700, Yang, Fei wrote:
...

Quoted 30 lines
Quoted 29 lines
Quoted 29 lines
(quoted diff) +0 -0

b/drivers/gpu/drm/i915/gt/intel_gtt.h

index 69ce55f517f5..b632167eaf2e 100644

--- a/drivers/gpu/drm/i915/gt/intel_gtt.h

+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h

(quoted diff) +5 -0
@@ -88,9 +88,18 @@ typedef u64 gen8_pte_t;
 
 #define BYT_PTE_SNOOPED_BY_CPU_CACHES             REG_BIT(2)
 
 #define BYT_PTE_WRITEABLE                            REG_BIT(1)
 
 
 
+#define GEN12_PPGTT_PTE_PAT3    BIT_ULL(62)
 
 #define GEN12_PPGTT_PTE_LM          BIT_ULL(11)
 
+#define GEN12_PPGTT_PTE_PAT2    BIT_ULL(7)
 
+#define GEN12_PPGTT_PTE_NC      BIT_ULL(5)
 
+#define GEN12_PPGTT_PTE_PAT1    BIT_ULL(4)
 
+#define GEN12_PPGTT_PTE_PAT0    BIT_ULL(3)
Quoted 7 lines
Quoted 3 lines

Which bspec page is this from? The PPGTT descriptions in

the bspec are kind of hard to track down.

   [9]https://gfxspecs.intel.com/Predator/Home/Index/53521

The bspec tagging is a bit bizarre in this area, but I don't believe this page is intended to apply to MTL. Note that this page is inside a section specifically listed as "57b VA Support" --- i.e., this general section is for platforms like PVC rather than MTL. MTL only has 48b virtual address space (bspec 55416), so I think one of the pages in the 48b sections is what we should be referencing instead.

Quoted 3 lines

If they screwed up and put MTL-specific details only on a PVC-specific page of the bspec, we should probably file a bspec issue about that to get it fixed.

The Bspec is a bit confusing on these. Looked at the Bsec with filter set to TGL/ADL/MTL/ALL respectively. Here are the differences,

Quoted 1 line
Quoted 1 line
   PAT_Index[2:0] = {PAT, PCD, PWT} = BIT(7, 4, 3)

These 3 PAT index bits are defined for all gen12+.

Quoted 1 line
Quoted 1 line
   PAT_Index[3] = BIT(62)

PAT_Index[3] is defined for MTL/ARL, will update this one to MTL_xxx

Quoted 1 line
Quoted 1 line
   PAT_Index[4] = BIT(61)

PAT_Index[4] shows up only when there is no filter set. And this bit is marked as [NOT VALID FOR SPEC: GENERALASSETSXE], not sure how to interpret this, but seems like it should not be used at all. Any suggestion?

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines

But if these only apply to MTL, why are they labelled as "GEN12?"

These apply to GEN12plus.

That's not what your patch is doing; you're using them in a function that only gets called on MTL.

That PTE encode will be generalized to gen12 in a patch after after the pat_index change.

Quoted 4 lines

So the question is whether these
definitions truly applied to older platforms like TGL/RKL/ADL/etc too (and we need to go back and fix that code), or whether they're Xe_LPG-specific, in which case the "GEN12_" prefix is incorrect.

The only difference is that MTL has PAT[3] defined, so we can still apply the same PTE encode function for all gen12+.

Quoted 6 lines

Also, handling the MTL-specific PTE encoding later in the series, after the transition from cache_level to PAT index, might be best since then you can just implement it correctly at the time the code is introduced; no need to add the cache_level implementation first (which can't even use all the bits) just to come back a few patches later and replace it all with PAT code.

I will squash the PTE encode patches.

Quoted 29 lines
Quoted 29 lines
Quoted 10 lines

drivers/gpu/drm/i915/gt/intel_gtt.h typedef u64 gen8_pte_t; #define

Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_gtt.h +5 -1
-#define GEN12_GGTT_PTE_LM           BIT_ULL(1)
+#define GEN12_GGTT_PTE_LM                         BIT_ULL(1)
+#define MTL_GGTT_PTE_PAT0                          BIT_ULL(52)
+#define MTL_GGTT_PTE_PAT1                          BIT_ULL(53)
+#define GEN12_GGTT_PTE_ADDR_MASK       GENMASK_ULL(45, 12)
+#define MTL_GGTT_PTE_PAT_MASK          GENMASK_ULL(53, 52)
 
 #define GEN12_PDE_64K BIT(6)
 #define GEN12_PTE_PS64 BIT(8)
@@ -147,6 +156,15 @@ typedef u64 gen8_pte_t;  #define

GEN8_PDE_IPS_64K

Quoted 5 lines

Review typedef u64 gen8_pte_t; #define · line 160

Quoted 5 lines
(quoted diff) +1 -0
 BIT(11)
 
 #define GEN8_PDE_PS_2M   BIT(7)
 
+#define MTL_PPAT_L4_CACHE_POLICY_MASK

REG_GENMASK(3, 2)

Quoted 1 line

Review typedef u64 gen8_pte_t; #define · line 161

Quoted 1 line
(quoted diff) +1 -0
+#define MTL_PAT_INDEX_COH_MODE_MASK              REG_GENMASK(1,

0)

Quoted 1 line

Review typedef u64 gen8_pte_t; #define · line 162

Quoted 1 line
(quoted diff) +1 -0
+#define MTL_PPAT_L4_3_UC

REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 3)

Quoted 1 line

Review typedef u64 gen8_pte_t; #define · line 163

Quoted 1 line
(quoted diff) +1 -0
+#define MTL_PPAT_L4_1_WT

REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 1)

Quoted 1 line

Review typedef u64 gen8_pte_t; #define · line 164

Quoted 1 line
(quoted diff) +1 -0
+#define MTL_PPAT_L4_0_WB

REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 0)

Quoted 1 line

Review typedef u64 gen8_pte_t; #define · line 165

Quoted 1 line
(quoted diff) +1 -0
+#define MTL_3_COH_2W     REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK,

3)

Quoted 1 line
Quoted 1 line
(quoted diff) +1 -0
+#define MTL_2_COH_1W     REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK,
Quoted 8 lines
Quoted 7 lines
   2)
Quoted 1 line

Review typedef u64 gen8_pte_t; #define · line 167

Quoted 1 line
(quoted diff) +1 -0
+#define MTL_0_COH_NON

REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 0)

Quoted 2 lines

The values for these definitions don't seem to be aligned.

These are aligned with [10]https://gfxspecs.intel.com/Predator/Home/Index/45101

I mean spacing aligned. If your tabstops are set to 8, then the values don't line up visually.

Hmm... the three COH macro's are aligned, are you saying they should aligned with those PPAT macro's as well?

Quoted 2 lines

Matt