Merge tag 'drm-intel-gt-next-2023-06-08' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- I915_GEM_CREATE_EXT_SET_PAT for Mesa on Meteorlake.

Driver Changes:

Fixes/improvements/new stuff:

- Use large rings for compute contexts (Chris Wilson)
- Better logging/debug of unexpected GuC communication issues (Michal Wajdeczko)
- Clear out entire reports after reading if not power of 2 size (Ashutosh Dixit)
- Limit lmem allocation size to succeed on SmallBars (Andrzej Hajda)
- perf/OA capture robustness improvements on DG2 (Umesh Nerlige Ramappa)
- Fix error code in intel_gsc_uc_heci_cmd_submit_nonpriv() (Dan Carpenter)

Future platform enablement:

- Add workaround 14016712196 (Tejas Upadhyay)
- HuC loading for MTL (Daniele Ceraolo Spurio)
- Allow user to set cache at BO creation (Fei Yang)

Miscellaneous:

- Use system include style for drm headers (Jani Nikula)
- Drop legacy CTB definitions (Michal Wajdeczko)
- Turn off the timer to sample frequencies when GT is parked (Ashutosh Dixit)
- Make PMU sample array two-dimensional (Ashutosh Dixit)
- Use the correct error value when kernel_context() fails (Andi Shyti)
- Fix second parameter type of pre-gen8 pte_encode callbacks (Nathan Chancellor)
- Fix parameter in gmch_ggtt_insert_{entries, page}() (Nathan Chancellor)
- Fix size_t format specifier in gsccs_send_message() (Nathan Chancellor)
- Use the fdinfo helper (Tvrtko Ursulin)
- Add some missing error propagation (Tvrtko Ursulin)
- Reduce I915_MAX_GT to 2 (Matt Atwood)
- Rename I915_PMU_MAX_GTS to I915_PMU_MAX_GT (Matt Atwood)
- Remove some obsolete definitions (John Harrison)

Merges:

- Merge drm/drm-next into drm-intel-gt-next (Tvrtko Ursulin)

Signed-off-by: Dave Airlie <[email protected]>
From: Tvrtko Ursulin <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/ZIH09fqe5v5yArsu@tursulin-desk

Author: airlied

drivers/gpu/drm/i915/Kconfig.debug

@@ -157,6 +157,7 @@ config DRM_I915_SW_FENCE_CHECK_DAG
 config DRM_I915_DEBUG_GUC
 	bool "Enable additional driver debugging for GuC"
 	depends on DRM_I915
+	select STACKDEPOT
 	default n
 	help
 	  Choose this option to turn on extra driver debugging that may affect

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -964,7 +964,11 @@ static int intel_context_set_gem(struct intel_context *ce,
 	RCU_INIT_POINTER(ce->gem_context, ctx);
 
 	GEM_BUG_ON(intel_context_is_pinned(ce));
-	ce->ring_size = SZ_16K;
+
+	if (ce->engine->class == COMPUTE_CLASS)
+		ce->ring_size = SZ_512K;
+	else
+		ce->ring_size = SZ_16K;
 
 	i915_vm_put(ce->vm);
 	ce->vm = i915_gem_context_get_eb_vm(ctx);

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

@@ -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 +395,43 @@ 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));
+
+	/* Limiting the extension only to Meteor Lake */
+	if (!IS_METEORLAKE(i915))
+		return -ENODEV;
+
+	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 +451,7 @@ 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 +488,11 @@ 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->pat_set_by_user = true;
+	}
+
 	return i915_gem_publish(obj, file, &args->size, &args->handle);
 }

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

@@ -208,6 +208,12 @@ bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj)
 	if (!(obj->flags & I915_BO_ALLOC_USER))
 		return false;
 
+	/*
+	 * Always flush cache for UMD objects at creation time.
+	 */
+	if (obj->pat_set_by_user)
+		return true;
+
 	/*
 	 * EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it
 	 * possible for userspace to bypass the GTT caching bits set by the

drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c

@@ -348,8 +348,10 @@ static int live_parallel_switch(void *arg)
 				continue;
 
 			ce = intel_context_create(data[m].ce[0]->engine);
-			if (IS_ERR(ce))
+			if (IS_ERR(ce)) {
+				err = PTR_ERR(ce);
 				goto out;
+			}
 
 			err = intel_context_pin(ce);
 			if (err) {
@@ -369,8 +371,10 @@ static int live_parallel_switch(void *arg)
 
 		worker = kthread_create_worker(0, "igt/parallel:%s",
 					       data[n].ce[0]->engine->name);
-		if (IS_ERR(worker))
+		if (IS_ERR(worker)) {
+			err = PTR_ERR(worker);
 			goto out;
+		}
 
 		data[n].worker = worker;
 	}
@@ -399,8 +403,10 @@ static int live_parallel_switch(void *arg)
 			}
 		}
 
-		if (igt_live_test_end(&t))
-			err = -EIO;
+		if (igt_live_test_end(&t)) {
+			err = err ?: -EIO;
+			break;
+		}
 	}
 
 out:

drivers/gpu/drm/i915/gt/gen8_engine_cs.c

@@ -177,14 +177,40 @@ u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv
 	return cs;
 }
 
+static int mtl_dummy_pipe_control(struct i915_request *rq)
+{
+	/* Wa_14016712196 */
+	if (IS_MTL_GRAPHICS_STEP(rq->engine->i915, M, STEP_A0, STEP_B0) ||
+	    IS_MTL_GRAPHICS_STEP(rq->engine->i915, P, STEP_A0, STEP_B0)) {
+		u32 *cs;
+
+		/* dummy PIPE_CONTROL + depth flush */
+		cs = intel_ring_begin(rq, 6);
+		if (IS_ERR(cs))
+			return PTR_ERR(cs);
+		cs = gen12_emit_pipe_control(cs,
+					     0,
+					     PIPE_CONTROL_DEPTH_CACHE_FLUSH,
+					     LRC_PPHWSP_SCRATCH_ADDR);
+		intel_ring_advance(rq, cs);
+	}
+
+	return 0;
+}
+
 int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 {
 	struct intel_engine_cs *engine = rq->engine;
 
 	if (mode & EMIT_FLUSH) {
 		u32 flags = 0;
+		int err;
 		u32 *cs;
 
+		err = mtl_dummy_pipe_control(rq);
+		if (err)
+			return err;
+
 		flags |= PIPE_CONTROL_TILE_CACHE_FLUSH;
 		flags |= PIPE_CONTROL_FLUSH_L3;
 		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
@@ -217,6 +243,11 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 	if (mode & EMIT_INVALIDATE) {
 		u32 flags = 0;
 		u32 *cs, count;
+		int err;
+
+		err = mtl_dummy_pipe_control(rq);
+		if (err)
+			return err;
 
 		flags |= PIPE_CONTROL_COMMAND_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_TLB_INVALIDATE;
@@ -733,6 +764,13 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 		     PIPE_CONTROL_DC_FLUSH_ENABLE |
 		     PIPE_CONTROL_FLUSH_ENABLE);
 
+	/* Wa_14016712196 */
+	if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) ||
+	    IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0))
+		/* dummy PIPE_CONTROL + depth flush */
+		cs = gen12_emit_pipe_control(cs, 0,
+					     PIPE_CONTROL_DEPTH_CACHE_FLUSH, 0);
+
 	if (GRAPHICS_VER(i915) == 12 && GRAPHICS_VER_FULL(i915) < IP_VER(12, 50))
 		/* Wa_1409600907 */
 		flags |= PIPE_CONTROL_DEPTH_STALL;

drivers/gpu/drm/i915/gt/intel_ggtt.c

@@ -1015,16 +1015,16 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 /*
  * For pre-gen8 platforms pat_index is the same as enum i915_cache_level,
- * so these PTE encode functions are left with using cache_level.
+ * so the switch-case statements in these PTE encode functions are still valid.
  * See translation table LEGACY_CACHELEVEL.
  */
 static u64 snb_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
+			  unsigned int pat_index,
 			  u32 flags)
 {
 	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
 
-	switch (level) {
+	switch (pat_index) {
 	case I915_CACHE_L3_LLC:
 	case I915_CACHE_LLC:
 		pte |= GEN6_PTE_CACHE_LLC;
@@ -1033,19 +1033,19 @@ static u64 snb_pte_encode(dma_addr_t addr,
 		pte |= GEN6_PTE_UNCACHED;
 		break;
 	default:
-		MISSING_CASE(level);
+		MISSING_CASE(pat_index);
 	}
 
 	return pte;
 }
 
 static u64 ivb_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
+			  unsigned int pat_index,
 			  u32 flags)
 {
 	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
 
-	switch (level) {
+	switch (pat_index) {
 	case I915_CACHE_L3_LLC:
 		pte |= GEN7_PTE_CACHE_L3_LLC;
 		break;
@@ -1056,46 +1056,46 @@ static u64 ivb_pte_encode(dma_addr_t addr,
 		pte |= GEN6_PTE_UNCACHED;
 		break;
 	default:
-		MISSING_CASE(level);
+		MISSING_CASE(pat_index);
 	}
 
 	return pte;
 }
 
 static u64 byt_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
+			  unsigned int pat_index,
 			  u32 flags)
 {
 	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
 
 	if (!(flags & PTE_READ_ONLY))
 		pte |= BYT_PTE_WRITEABLE;
 
-	if (level != I915_CACHE_NONE)
+	if (pat_index != I915_CACHE_NONE)
 		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
 
 	return pte;
 }
 
 static u64 hsw_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
+			  unsigned int pat_index,
 			  u32 flags)
 {
 	gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
 
-	if (level != I915_CACHE_NONE)
+	if (pat_index != I915_CACHE_NONE)
 		pte |= HSW_WB_LLC_AGE3;
 
 	return pte;
 }
 
 static u64 iris_pte_encode(dma_addr_t addr,
-			   enum i915_cache_level level,
+			   unsigned int pat_index,
 			   u32 flags)
 {
 	gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
 
-	switch (level) {
+	switch (pat_index) {
 	case I915_CACHE_NONE:
 		break;
 	case I915_CACHE_WT:
@@ -1326,6 +1326,9 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt)
 		ggtt->vm.scratch_range(&ggtt->vm, ggtt->error_capture.start,
 				       ggtt->error_capture.size);
 
+	list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
+		intel_uc_resume_mappings(&gt->uc);
+
 	ggtt->invalidate(ggtt);
 
 	if (flush)

drivers/gpu/drm/i915/gt/intel_ggtt_gmch.c

@@ -18,21 +18,21 @@
 static void gmch_ggtt_insert_page(struct i915_address_space *vm,
 				  dma_addr_t addr,
 				  u64 offset,
-				  enum i915_cache_level cache_level,
+				  unsigned int pat_index,
 				  u32 unused)
 {
-	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+	unsigned int flags = (pat_index == I915_CACHE_NONE) ?
 		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
 
 	intel_gmch_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);
 }
 
 static void gmch_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct i915_vma_resource *vma_res,
-				     enum i915_cache_level cache_level,
+				     unsigned int pat_index,
 				     u32 unused)
 {
-	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+	unsigned int flags = (pat_index == I915_CACHE_NONE) ?
 		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
 
 	intel_gmch_gtt_insert_sg_entries(vma_res->bi.pages, vma_res->start >> PAGE_SHIFT,

drivers/gpu/drm/i915/gt/selftest_execlists.c

@@ -1530,22 +1530,26 @@ static int live_busywait_preempt(void *arg)
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	enum intel_engine_id id;
-	int err = -ENOMEM;
 	u32 *map;
+	int err;
 
 	/*
 	 * Verify that even without HAS_LOGICAL_RING_PREEMPTION, we can
 	 * preempt the busywaits used to synchronise between rings.
 	 */
 
 	ctx_hi = kernel_context(gt->i915, NULL);
-	if (!ctx_hi)
-		return -ENOMEM;
+	if (IS_ERR(ctx_hi))
+		return PTR_ERR(ctx_hi);
+
 	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
 
 	ctx_lo = kernel_context(gt->i915, NULL);
-	if (!ctx_lo)
+	if (IS_ERR(ctx_lo)) {
+		err = PTR_ERR(ctx_lo);
 		goto err_ctx_hi;
+	}
+
 	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
 
 	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);

drivers/gpu/drm/i915/gt/selftest_tlb.c

@@ -190,11 +190,18 @@ pte_tlbinv(struct intel_context *ce,
 
 static struct drm_i915_gem_object *create_lmem(struct intel_gt *gt)
 {
+	struct intel_memory_region *mr = gt->i915->mm.regions[INTEL_REGION_LMEM_0];
+	resource_size_t size = SZ_1G;
+
 	/*
 	 * Allocation of largest possible page size allows to test all types
-	 * of pages.
+	 * of pages. To succeed with both allocations, especially in case of Small
+	 * BAR, try to allocate no more than quarter of mappable memory.
 	 */
-	return i915_gem_object_create_lmem(gt->i915, SZ_1G, I915_BO_ALLOC_CONTIGUOUS);
+	if (mr && size > mr->io_size / 4)
+		size = mr->io_size / 4;
+
+	return i915_gem_object_create_lmem(gt->i915, size, I915_BO_ALLOC_CONTIGUOUS);
 }
 
 static struct drm_i915_gem_object *create_smem(struct intel_gt *gt)