Merge tag 'topic/i915-ttm-2021-06-11' of git://anongit.freedesktop.or…

…g/drm/drm-misc into drm-intel-gt-next

drm-misc and drm-intel pull request for topic/i915-ttm:
- Convert i915 lmem handling to ttm.
- Add a patch to temporarily add a driver_private member to vma_node.
- Use this to allow mixed object mmap handling for i915.

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/eb71ee2d-3413-6ca8-0b7c-a58695f00b77@linux.intel.com

drivers/gpu/drm/drm_gem.c

@@ -1148,15 +1148,6 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		return -EACCES;
 	}
 
-	if (node->readonly) {
-		if (vma->vm_flags & VM_WRITE) {
-			drm_gem_object_put(obj);
-			return -EINVAL;
-		}
-
-		vma->vm_flags &= ~VM_MAYWRITE;
-	}
-
 	ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT,
 			       vma);
 

drivers/gpu/drm/i915/Makefile

@@ -155,6 +155,7 @@ gem-y += \
 	gem/i915_gem_stolen.o \
 	gem/i915_gem_throttle.o \
 	gem/i915_gem_tiling.o \
+	gem/i915_gem_ttm.o \
 	gem/i915_gem_userptr.o \
 	gem/i915_gem_wait.o \
 	gem/i915_gemfs.o

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

@@ -11771,7 +11771,7 @@ intel_user_framebuffer_create(struct drm_device *dev,
 
 	/* object is backed with LMEM for discrete */
 	i915 = to_i915(obj->base.dev);
-	if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj)) {
+	if (HAS_LMEM(i915) && !i915_gem_object_validates_to_lmem(obj)) {
 		/* object is "remote", not in local memory */
 		i915_gem_object_put(obj);
 		return ERR_PTR(-EREMOTE);

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

@@ -85,13 +85,10 @@ i915_gem_setup(struct drm_i915_gem_object *obj, u64 size)
 		return -E2BIG;
 
 	/*
-	 * For now resort to CPU based clearing for device local-memory, in the
-	 * near future this will use the blitter engine for accelerated, GPU
-	 * based clearing.
+	 * I915_BO_ALLOC_USER will make sure the object is cleared before
+	 * any user access.
 	 */
-	flags = 0;
-	if (mr->type == INTEL_MEMORY_LOCAL)
-		flags = I915_BO_ALLOC_CPU_CLEAR;
+	flags = I915_BO_ALLOC_USER;
 
 	ret = mr->ops->init_object(mr, obj, size, flags);
 	if (ret)

drivers/gpu/drm/i915/gem/i915_gem_lmem.c

@@ -4,74 +4,10 @@
  */
 
 #include "intel_memory_region.h"
-#include "intel_region_ttm.h"
 #include "gem/i915_gem_region.h"
 #include "gem/i915_gem_lmem.h"
 #include "i915_drv.h"
 
-static void lmem_put_pages(struct drm_i915_gem_object *obj,
-			   struct sg_table *pages)
-{
-	intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
-	obj->mm.dirty = false;
-	sg_free_table(pages);
-	kfree(pages);
-}
-
-static int lmem_get_pages(struct drm_i915_gem_object *obj)
-{
-	unsigned int flags;
-	struct sg_table *pages;
-
-	flags = I915_ALLOC_MIN_PAGE_SIZE;
-	if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
-		flags |= I915_ALLOC_CONTIGUOUS;
-
-	obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region,
-							 obj->base.size,
-							 flags);
-	if (IS_ERR(obj->mm.st_mm_node))
-		return PTR_ERR(obj->mm.st_mm_node);
-
-	/* Range manager is always contigous */
-	if (obj->mm.region->is_range_manager)
-		obj->flags |= I915_BO_ALLOC_CONTIGUOUS;
-	pages = intel_region_ttm_node_to_st(obj->mm.region, obj->mm.st_mm_node);
-	if (IS_ERR(pages)) {
-		intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
-		return PTR_ERR(pages);
-	}
-
-	__i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl));
-
-	if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) {
-		void __iomem *vaddr =
-			i915_gem_object_lmem_io_map(obj, 0, obj->base.size);
-
-		if (!vaddr) {
-			struct sg_table *pages =
-				__i915_gem_object_unset_pages(obj);
-
-			if (!IS_ERR_OR_NULL(pages))
-				lmem_put_pages(obj, pages);
-		}
-
-		memset_io(vaddr, 0, obj->base.size);
-		io_mapping_unmap(vaddr);
-	}
-
-	return 0;
-}
-
-const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = {
-	.name = "i915_gem_object_lmem",
-	.flags = I915_GEM_OBJECT_HAS_IOMEM,
-
-	.get_pages = lmem_get_pages,
-	.put_pages = lmem_put_pages,
-	.release = i915_gem_object_release_memory_region,
-};
-
 void __iomem *
 i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
 			    unsigned long n,
@@ -87,10 +23,50 @@ i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
 	return io_mapping_map_wc(&obj->mm.region->iomap, offset, size);
 }
 
+/**
+ * i915_gem_object_validates_to_lmem - Whether the object is resident in
+ * lmem when pages are present.
+ * @obj: The object to check.
+ *
+ * Migratable objects residency may change from under us if the object is
+ * not pinned or locked. This function is intended to be used to check whether
+ * the object can only reside in lmem when pages are present.
+ *
+ * Return: Whether the object is always resident in lmem when pages are
+ * present.
+ */
+bool i915_gem_object_validates_to_lmem(struct drm_i915_gem_object *obj)
+{
+	struct intel_memory_region *mr = READ_ONCE(obj->mm.region);
+
+	return !i915_gem_object_migratable(obj) &&
+		mr && (mr->type == INTEL_MEMORY_LOCAL ||
+		       mr->type == INTEL_MEMORY_STOLEN_LOCAL);
+}
+
+/**
+ * i915_gem_object_is_lmem - Whether the object is resident in
+ * lmem
+ * @obj: The object to check.
+ *
+ * Even if an object is allowed to migrate and change memory region,
+ * this function checks whether it will always be present in lmem when
+ * valid *or* if that's not the case, whether it's currently resident in lmem.
+ * For migratable and evictable objects, the latter only makes sense when
+ * the object is locked.
+ *
+ * Return: Whether the object migratable but resident in lmem, or not
+ * migratable and will be present in lmem when valid.
+ */
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
 {
-	struct intel_memory_region *mr = obj->mm.region;
+	struct intel_memory_region *mr = READ_ONCE(obj->mm.region);
 
+#ifdef CONFIG_LOCKDEP
+	if (i915_gem_object_migratable(obj) &&
+	    i915_gem_object_evictable(obj))
+		assert_object_held(obj);
+#endif
 	return mr && (mr->type == INTEL_MEMORY_LOCAL ||
 		      mr->type == INTEL_MEMORY_STOLEN_LOCAL);
 }
@@ -103,23 +79,3 @@ i915_gem_object_create_lmem(struct drm_i915_private *i915,
 	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM],
 					     size, flags);
 }
-
-int __i915_gem_lmem_object_init(struct intel_memory_region *mem,
-				struct drm_i915_gem_object *obj,
-				resource_size_t size,
-				unsigned int flags)
-{
-	static struct lock_class_key lock_class;
-	struct drm_i915_private *i915 = mem->i915;
-
-	drm_gem_private_object_init(&i915->drm, &obj->base, size);
-	i915_gem_object_init(obj, &i915_gem_lmem_obj_ops, &lock_class, flags);
-
-	obj->read_domains = I915_GEM_DOMAIN_WC | I915_GEM_DOMAIN_GTT;
-
-	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
-
-	i915_gem_object_init_memory_region(obj, mem);
-
-	return 0;
-}

drivers/gpu/drm/i915/gem/i915_gem_lmem.h

@@ -26,9 +26,4 @@ i915_gem_object_create_lmem(struct drm_i915_private *i915,
 			    resource_size_t size,
 			    unsigned int flags);
 
-int __i915_gem_lmem_object_init(struct intel_memory_region *mem,
-				struct drm_i915_gem_object *obj,
-				resource_size_t size,
-				unsigned int flags);
-
 #endif /* !__I915_GEM_LMEM_H */

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

@@ -19,6 +19,7 @@
 #include "i915_gem_mman.h"
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
+#include "i915_gem_ttm.h"
 #include "i915_vma.h"
 
 static inline bool
@@ -623,6 +624,8 @@ mmap_offset_attach(struct drm_i915_gem_object *obj,
 	struct i915_mmap_offset *mmo;
 	int err;
 
+	GEM_BUG_ON(obj->ops->mmap_offset || obj->ops->mmap_ops);
+
 	mmo = lookup_mmo(obj, mmap_type);
 	if (mmo)
 		goto out;
@@ -665,40 +668,47 @@ mmap_offset_attach(struct drm_i915_gem_object *obj,
 }
 
 static int
-__assign_mmap_offset(struct drm_file *file,
-		     u32 handle,
+__assign_mmap_offset(struct drm_i915_gem_object *obj,
 		     enum i915_mmap_type mmap_type,
-		     u64 *offset)
+		     u64 *offset, struct drm_file *file)
 {
-	struct drm_i915_gem_object *obj;
 	struct i915_mmap_offset *mmo;
-	int err;
 
-	obj = i915_gem_object_lookup(file, handle);
-	if (!obj)
-		return -ENOENT;
+	if (i915_gem_object_never_mmap(obj))
+		return -ENODEV;
 
-	if (i915_gem_object_never_mmap(obj)) {
-		err = -ENODEV;
-		goto out;
+	if (obj->ops->mmap_offset)  {
+		*offset = obj->ops->mmap_offset(obj);
+		return 0;
 	}
 
 	if (mmap_type != I915_MMAP_TYPE_GTT &&
 	    !i915_gem_object_has_struct_page(obj) &&
-	    !i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_IOMEM)) {
-		err = -ENODEV;
-		goto out;
-	}
+	    !i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_IOMEM))
+		return -ENODEV;
 
 	mmo = mmap_offset_attach(obj, mmap_type, file);
-	if (IS_ERR(mmo)) {
-		err = PTR_ERR(mmo);
-		goto out;
-	}
+	if (IS_ERR(mmo))
+		return PTR_ERR(mmo);
 
 	*offset = drm_vma_node_offset_addr(&mmo->vma_node);
-	err = 0;
-out:
+	return 0;
+}
+
+static int
+__assign_mmap_offset_handle(struct drm_file *file,
+			    u32 handle,
+			    enum i915_mmap_type mmap_type,
+			    u64 *offset)
+{
+	struct drm_i915_gem_object *obj;
+	int err;
+
+	obj = i915_gem_object_lookup(file, handle);
+	if (!obj)
+		return -ENOENT;
+
+	err = __assign_mmap_offset(obj, mmap_type, offset, file);
 	i915_gem_object_put(obj);
 	return err;
 }
@@ -718,7 +728,7 @@ i915_gem_dumb_mmap_offset(struct drm_file *file,
 	else
 		mmap_type = I915_MMAP_TYPE_GTT;
 
-	return __assign_mmap_offset(file, handle, mmap_type, offset);
+	return __assign_mmap_offset_handle(file, handle, mmap_type, offset);
 }
 
 /**
@@ -786,7 +796,7 @@ i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	return __assign_mmap_offset(file, args->handle, type, &args->offset);
+	return __assign_mmap_offset_handle(file, args->handle, type, &args->offset);
 }
 
 static void vm_open(struct vm_area_struct *vma)
@@ -890,8 +900,18 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		 * destroyed and will be invalid when the vma manager lock
 		 * is released.
 		 */
-		mmo = container_of(node, struct i915_mmap_offset, vma_node);
-		obj = i915_gem_object_get_rcu(mmo->obj);
+		if (!node->driver_private) {
+			mmo = container_of(node, struct i915_mmap_offset, vma_node);
+			obj = i915_gem_object_get_rcu(mmo->obj);
+
+			GEM_BUG_ON(obj && obj->ops->mmap_ops);
+		} else {
+			obj = i915_gem_object_get_rcu
+				(container_of(node, struct drm_i915_gem_object,
+					      base.vma_node));
+
+			GEM_BUG_ON(obj && !obj->ops->mmap_ops);
+		}
 	}
 	drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
 	rcu_read_unlock();
@@ -913,7 +933,9 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	}
 
 	vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
-	vma->vm_private_data = mmo;
+
+	if (i915_gem_object_has_iomem(obj))
+		vma->vm_flags |= VM_IO;
 
 	/*
 	 * We keep the ref on mmo->obj, not vm_file, but we require
@@ -927,6 +949,15 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	/* Drop the initial creation reference, the vma is now holding one. */
 	fput(anon);
 
+	if (obj->ops->mmap_ops) {
+		vma->vm_page_prot = pgprot_decrypted(vm_get_page_prot(vma->vm_flags));
+		vma->vm_ops = obj->ops->mmap_ops;
+		vma->vm_private_data = node->driver_private;
+		return 0;
+	}
+
+	vma->vm_private_data = mmo;
+
 	switch (mmo->mmap_type) {
 	case I915_MMAP_TYPE_WC:
 		vma->vm_page_prot =