Merge drm/drm-next into drm-intel-next

Catch up with 6.3-rc cycle...

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

11 files changed, 131 insertions, 51 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 454e73a433c8..6d639ca24dfb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1096,16 +1096,15 @@ static struct i915_gem_engines *alloc_engines(unsigned int count)
 static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx,
 						struct intel_sseu rcs_sseu)
 {
-	const struct intel_gt *gt = to_gt(ctx->i915);
+	const unsigned int max = I915_NUM_ENGINES;
 	struct intel_engine_cs *engine;
 	struct i915_gem_engines *e, *err;
-	enum intel_engine_id id;
 
-	e = alloc_engines(I915_NUM_ENGINES);
+	e = alloc_engines(max);
 	if (!e)
 		return ERR_PTR(-ENOMEM);
 
-	for_each_engine(engine, gt, id) {
+	for_each_uabi_engine(engine, ctx->i915) {
 		struct intel_context *ce;
 		struct intel_sseu sseu = {};
 		int ret;
@@ -1113,7 +1112,7 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx,
 		if (engine->legacy_idx == INVALID_ENGINE)
 			continue;
 
-		GEM_BUG_ON(engine->legacy_idx >= I915_NUM_ENGINES);
+		GEM_BUG_ON(engine->legacy_idx >= max);
 		GEM_BUG_ON(e->engines[engine->legacy_idx]);
 
 		ce = intel_context_create(engine);
@@ -1861,11 +1860,19 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv,
 	vm = ctx->vm;
 	GEM_BUG_ON(!vm);
 
+	/*
+	 * Get a reference for the allocated handle.  Once the handle is
+	 * visible in the vm_xa table, userspace could try to close it
+	 * from under our feet, so we need to hold the extra reference
+	 * first.
+	 */
+	i915_vm_get(vm);
+
 	err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL);
-	if (err)
+	if (err) {
+		i915_vm_put(vm);
 		return err;
-
-	i915_vm_get(vm);
+	}
 
 	GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
 	args->value = id;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 94d86ee24693..9dce2957b4e5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -3486,6 +3486,13 @@ err_request:
 				   eb.composite_fence :
 				   &eb.requests[0]->fence);
 
+	if (unlikely(eb.gem_context->syncobj)) {
+		drm_syncobj_replace_fence(eb.gem_context->syncobj,
+					  eb.composite_fence ?
+					  eb.composite_fence :
+					  &eb.requests[0]->fence);
+	}
+
 	if (out_fence) {
 		if (err == 0) {
 			fd_install(out_fence_fd, out_fence->file);
@@ -3497,13 +3504,6 @@ err_request:
 		}
 	}
 
-	if (unlikely(eb.gem_context->syncobj)) {
-		drm_syncobj_replace_fence(eb.gem_context->syncobj,
-					  eb.composite_fence ?
-					  eb.composite_fence :
-					  &eb.requests[0]->fence);
-	}
-
 	if (!out_fence && eb.composite_fence)
 		dma_fence_put(eb.composite_fence);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 4f69bff63068..d3c1dee16af2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -697,7 +697,7 @@ insert:
 	GEM_BUG_ON(lookup_mmo(obj, mmap_type) != mmo);
 out:
 	if (file)
-		drm_vma_node_allow(&mmo->vma_node, file);
+		drm_vma_node_allow_once(&mmo->vma_node, file);
 	return mmo;
 
 err:
@@ -979,7 +979,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 			i915_gem_object_put(obj);
 			return -EINVAL;
 		}
-		vma->vm_flags &= ~VM_MAYWRITE;
+		vm_flags_clear(vma, VM_MAYWRITE);
 	}
 
 	anon = mmap_singleton(to_i915(dev));
@@ -988,7 +988,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		return PTR_ERR(anon);
 	}
 
-	vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
+	vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO);
 
 	/*
 	 * We keep the ref on mmo->obj, not vm_file, but we require
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 114443096841..37d1efcd3ca6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -596,7 +596,7 @@ static int shmem_object_init(struct intel_memory_region *mem,
 	mapping_set_gfp_mask(mapping, mask);
 	GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM));
 
-	i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, 0);
+	i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, flags);
 	obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE;
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index 90a967374b1a..d8e06e783e30 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -909,7 +909,7 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
 		dsm_base = intel_uncore_read64(uncore, GEN12_DSMBASE) & GEN12_BDSM_MASK;
 		if (WARN_ON(lmem_size < dsm_base))
 			return ERR_PTR(-ENODEV);
-		dsm_size = lmem_size - dsm_base;
+		dsm_size = ALIGN_DOWN(lmem_size - dsm_base, SZ_1M);
 	}
 
 	io_size = dsm_size;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index 04bb909acdec..a049ca0b7980 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -305,10 +305,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 	spin_unlock(&obj->vma.lock);
 
 	obj->tiling_and_stride = tiling | stride;
-	i915_gem_object_unlock(obj);
-
-	/* Force the fence to be reacquired for GTT access */
-	i915_gem_object_release_mmap_gtt(obj);
 
 	/* Try to preallocate memory required to save swizzling on put-pages */
 	if (i915_gem_object_needs_bit17_swizzle(obj)) {
@@ -321,6 +317,11 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 		obj->bit_17 = NULL;
 	}
 
+	i915_gem_object_unlock(obj);
+
+	/* Force the fence to be reacquired for GTT access */
+	i915_gem_object_release_mmap_gtt(obj);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 8cfed1bef629..341b94672abc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -274,8 +274,6 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
 {
 	struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915),
 						     bdev);
-	struct ttm_resource_manager *man =
-		ttm_manager_type(bo->bdev, bo->resource->mem_type);
 	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
 	unsigned long ccs_pages = 0;
 	enum ttm_caching caching;
@@ -289,8 +287,8 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
 	if (!i915_tt)
 		return NULL;
 
-	if (obj->flags & I915_BO_ALLOC_CPU_CLEAR &&
-	    man->use_tt)
+	if (obj->flags & I915_BO_ALLOC_CPU_CLEAR && (!bo->resource ||
+	    ttm_manager_type(bo->bdev, bo->resource->mem_type)->use_tt))
 		page_flags |= TTM_TT_FLAG_ZERO_ALLOC;
 
 	caching = i915_ttm_select_tt_caching(obj);
@@ -474,7 +472,7 @@ static int i915_ttm_shrink(struct drm_i915_gem_object *obj, unsigned int flags)
 	struct ttm_placement place = {};
 	int ret;
 
-	if (!bo->ttm || bo->resource->mem_type != TTM_PL_SYSTEM)
+	if (!bo->ttm || i915_ttm_cpu_maps_iomem(bo->resource))
 		return 0;
 
 	GEM_BUG_ON(!i915_tt->is_shmem);
@@ -513,7 +511,13 @@ static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo)
 {
 	struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
 
-	if (bo->resource && !i915_ttm_is_ghost_object(bo)) {
+	/*
+	 * This gets called twice by ttm, so long as we have a ttm resource or
+	 * ttm_tt then we can still safely call this. Due to pipeline-gutting,
+	 * we maybe have NULL bo->resource, but in that case we should always
+	 * have a ttm alive (like if the pages are swapped out).
+	 */
+	if ((bo->resource || bo->ttm) && !i915_ttm_is_ghost_object(bo)) {
 		__i915_gem_object_pages_fini(obj);
 		i915_ttm_free_cached_io_rsgt(obj);
 	}
@@ -1058,7 +1062,27 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 	}
 
-	if (!i915_ttm_resource_mappable(bo->resource)) {
+	/*
+	 * This must be swapped out with shmem ttm_tt (pipeline-gutting).
+	 * Calling ttm_bo_validate() here with TTM_PL_SYSTEM should only go as
+	 * far as far doing a ttm_bo_move_null(), which should skip all the
+	 * other junk.
+	 */
+	if (!bo->resource) {
+		struct ttm_operation_ctx ctx = {
+			.interruptible = true,
+			.no_wait_gpu = true, /* should be idle already */
+		};
+		int err;
+
+		GEM_BUG_ON(!bo->ttm || !(bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED));
+
+		err = ttm_bo_validate(bo, i915_ttm_sys_placement(), &ctx);
+		if (err) {
+			dma_resv_unlock(bo->base.resv);
+			return VM_FAULT_SIGBUS;
+		}
+	} else if (!i915_ttm_resource_mappable(bo->resource)) {
 		int err = -ENODEV;
 		int i;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h
index 2a94a99ef76b..f8f6bed1b297 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h
@@ -98,7 +98,7 @@ static inline bool i915_ttm_gtt_binds_lmem(struct ttm_resource *mem)
 static inline bool i915_ttm_cpu_maps_iomem(struct ttm_resource *mem)
 {
 	/* Once / if we support GGTT, this is also false for cached ttm_tts */
-	return mem->mem_type != I915_PL_SYSTEM;
+	return mem && mem->mem_type != I915_PL_SYSTEM;
 }
 
 bool i915_ttm_resource_mappable(struct ttm_resource *res);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
index 2ebaaf4d663c..d030182ca176 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
@@ -103,7 +103,27 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj)
 {
 	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
 	unsigned int cache_level;
+	unsigned int mem_flags;
 	unsigned int i;
+	int mem_type;
+
+	/*
+	 * We might have been purged (or swapped out) if the resource is NULL,
+	 * in which case the SYSTEM placement is the closest match to describe
+	 * the current domain. If the object is ever used in this state then we
+	 * will require moving it again.
+	 */
+	if (!bo->resource) {
+		mem_flags = I915_BO_FLAG_STRUCT_PAGE;
+		mem_type = I915_PL_SYSTEM;
+		cache_level = I915_CACHE_NONE;
+	} else {
+		mem_flags = i915_ttm_cpu_maps_iomem(bo->resource) ? I915_BO_FLAG_IOMEM :
+			I915_BO_FLAG_STRUCT_PAGE;
+		mem_type = bo->resource->mem_type;
+		cache_level = i915_ttm_cache_level(to_i915(bo->base.dev), bo->resource,
+						   bo->ttm);
+	}
 
 	/*
 	 * If object was moved to an allowable region, update the object
@@ -111,11 +131,11 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj)
 	 * in an allowable region, it's evicted and we don't update the
 	 * object region.
 	 */
-	if (intel_region_to_ttm_type(obj->mm.region) != bo->resource->mem_type) {
+	if (intel_region_to_ttm_type(obj->mm.region) != mem_type) {
 		for (i = 0; i < obj->mm.n_placements; ++i) {
 			struct intel_memory_region *mr = obj->mm.placements[i];
 
-			if (intel_region_to_ttm_type(mr) == bo->resource->mem_type &&
+			if (intel_region_to_ttm_type(mr) == mem_type &&
 			    mr != obj->mm.region) {
 				i915_gem_object_release_memory_region(obj);
 				i915_gem_object_init_memory_region(obj, mr);
@@ -125,12 +145,8 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj)
 	}
 
 	obj->mem_flags &= ~(I915_BO_FLAG_STRUCT_PAGE | I915_BO_FLAG_IOMEM);
+	obj->mem_flags |= mem_flags;
 
-	obj->mem_flags |= i915_ttm_cpu_maps_iomem(bo->resource) ? I915_BO_FLAG_IOMEM :
-		I915_BO_FLAG_STRUCT_PAGE;
-
-	cache_level = i915_ttm_cache_level(to_i915(bo->base.dev), bo->resource,
-					   bo->ttm);
 	i915_gem_object_set_cache_coherency(obj, cache_level);
 }
 
@@ -565,6 +581,32 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
 		return 0;
 	}
 
+	if (!bo->resource) {
+		if (dst_mem->mem_type != TTM_PL_SYSTEM) {
+			hop->mem_type = TTM_PL_SYSTEM;
+			hop->flags = TTM_PL_FLAG_TEMPORARY;
+			return -EMULTIHOP;
+		}
+
+		/*
+		 * This is only reached when first creating the object, or if
+		 * the object was purged or swapped out (pipeline-gutting). For
+		 * the former we can safely skip all of the below since we are
+		 * only using a dummy SYSTEM placement here. And with the latter
+		 * we will always re-enter here with bo->resource set correctly
+		 * (as per the above), since this is part of a multi-hop
+		 * sequence, where at the end we can do the move for real.
+		 *
+		 * The special case here is when the dst_mem is TTM_PL_SYSTEM,
+		 * which doens't require any kind of move, so it should be safe
+		 * to skip all the below and call ttm_bo_move_null() here, where
+		 * the caller in __i915_ttm_get_pages() will take care of the
+		 * rest, since we should have a valid ttm_tt.
+		 */
+		ttm_bo_move_null(bo, dst_mem);
+		return 0;
+	}
+
 	ret = i915_ttm_move_notify(bo);
 	if (ret)
 		return ret;
@@ -669,6 +711,10 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
 
 	assert_object_held(dst);
 	assert_object_held(src);
+
+	if (GEM_WARN_ON(!src_bo->resource || !dst_bo->resource))
+		return -EINVAL;
+
 	i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
 
 	ret = dma_resv_reserve_fences(src_bo->base.resv, 1);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
index 7e67742bc65e..dfe39c8e74d8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
@@ -53,7 +53,7 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply,
 	unsigned int flags;
 	int err = 0;
 
-	if (bo->resource->mem_type == I915_PL_SYSTEM || obj->ttm.backup)
+	if (!i915_ttm_cpu_maps_iomem(bo->resource) || obj->ttm.backup)
 		return 0;
 
 	if (pm_apply->allow_gpu && i915_gem_object_evictable(obj))
@@ -187,7 +187,10 @@ static int i915_ttm_restore(struct i915_gem_apply_to_region *apply,
 		return err;
 
 	/* Content may have been swapped. */
-	err = ttm_tt_populate(backup_bo->bdev, backup_bo->ttm, &ctx);
+	if (!backup_bo->resource)
+		err = ttm_bo_validate(backup_bo, i915_ttm_sys_placement(), &ctx);
+	if (!err)
+		err = ttm_tt_populate(backup_bo->bdev, backup_bo->ttm, &ctx);
 	if (!err) {
 		err = i915_gem_obj_copy_ttm(obj, backup, pm_apply->allow_gpu,
 					    false);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index 3bb1f7f0110e..ff81af4c8202 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -108,31 +108,30 @@ struct tiled_blits {
 	u32 height;
 };
 
-static bool supports_x_tiling(const struct drm_i915_private *i915)
+static bool fastblit_supports_x_tiling(const struct drm_i915_private *i915)
 {
 	int gen = GRAPHICS_VER(i915);
 
+	/* XY_FAST_COPY_BLT does not exist on pre-gen9 platforms */
+	drm_WARN_ON(&i915->drm, gen < 9);
+
 	if (gen < 12)
 		return true;
 
-	if (!HAS_LMEM(i915) || IS_DG1(i915))
+	if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 50))
 		return false;
 
-	return true;
+	return HAS_DISPLAY(i915);
 }
 
 static bool fast_blit_ok(const struct blit_buffer *buf)
 {
-	int gen = GRAPHICS_VER(buf->vma->vm->i915);
-
-	if (gen < 9)
+	/* XY_FAST_COPY_BLT does not exist on pre-gen9 platforms */
+	if (GRAPHICS_VER(buf->vma->vm->i915) < 9)
 		return false;
 
-	if (gen < 12)
-		return true;
-
 	/* filter out platforms with unsupported X-tile support in fastblit */
-	if (buf->tiling == CLIENT_TILING_X && !supports_x_tiling(buf->vma->vm->i915))
+	if (buf->tiling == CLIENT_TILING_X && !fastblit_supports_x_tiling(buf->vma->vm->i915))
 		return false;
 
 	return true;