drm/gpuvm: add an abstraction for a VM / BO combination

Add an abstraction layer between the drm_gpuva mappings of a particular
drm_gem_object and this GEM object itself. The abstraction represents a
combination of a drm_gem_object and drm_gpuvm. The drm_gem_object holds
a list of drm_gpuvm_bo structures (the structure representing this
abstraction), while each drm_gpuvm_bo contains list of mappings of this
GEM object.

This has multiple advantages:

1) We can use the drm_gpuvm_bo structure to attach it to various lists
   of the drm_gpuvm. This is useful for tracking external and evicted
   objects per VM, which is introduced in subsequent patches.

2) Finding mappings of a certain drm_gem_object mapped in a certain
   drm_gpuvm becomes much cheaper.

3) Drivers can derive and extend the structure to easily represent
   driver specific states of a BO for a certain GPUVM.

The idea of this abstraction was taken from amdgpu, hence the credit for
this idea goes to the developers of amdgpu.

Cc: Christian König <christian.koenig@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231108001259.15123-11-dakr@redhat.com

drivers/gpu/drm/nouveau/nouveau_uvmm.c

@@ -62,6 +62,8 @@ struct bind_job_op {
 	enum vm_bind_op op;
 	u32 flags;
 
+	struct drm_gpuvm_bo *vm_bo;
+
 	struct {
 		u64 addr;
 		u64 range;
@@ -1101,22 +1103,28 @@ bind_validate_region(struct nouveau_job *job)
 }
 
 static void
-bind_link_gpuvas(struct drm_gpuva_ops *ops, struct nouveau_uvma_prealloc *new)
+bind_link_gpuvas(struct bind_job_op *bop)
 {
+	struct nouveau_uvma_prealloc *new = &bop->new;
+	struct drm_gpuvm_bo *vm_bo = bop->vm_bo;
+	struct drm_gpuva_ops *ops = bop->ops;
 	struct drm_gpuva_op *op;
 
 	drm_gpuva_for_each_op(op, ops) {
 		switch (op->op) {
 		case DRM_GPUVA_OP_MAP:
-			drm_gpuva_link(&new->map->va);
+			drm_gpuva_link(&new->map->va, vm_bo);
 			break;
-		case DRM_GPUVA_OP_REMAP:
+		case DRM_GPUVA_OP_REMAP: {
+			struct drm_gpuva *va = op->remap.unmap->va;
+
 			if (op->remap.prev)
-				drm_gpuva_link(&new->prev->va);
+				drm_gpuva_link(&new->prev->va, va->vm_bo);
 			if (op->remap.next)
-				drm_gpuva_link(&new->next->va);
-			drm_gpuva_unlink(op->remap.unmap->va);
+				drm_gpuva_link(&new->next->va, va->vm_bo);
+			drm_gpuva_unlink(va);
 			break;
+		}
 		case DRM_GPUVA_OP_UNMAP:
 			drm_gpuva_unlink(op->unmap.va);
 			break;
@@ -1138,10 +1146,17 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job)
 
 	list_for_each_op(op, &bind_job->ops) {
 		if (op->op == OP_MAP) {
-			op->gem.obj = drm_gem_object_lookup(job->file_priv,
+			struct drm_gem_object *obj = op->gem.obj =
+				drm_gem_object_lookup(job->file_priv,
 						      op->gem.handle);
-			if (!op->gem.obj)
+			if (!obj)
 				return -ENOENT;
+
+			dma_resv_lock(obj->resv, NULL);
+			op->vm_bo = drm_gpuvm_bo_obtain(&uvmm->base, obj);
+			dma_resv_unlock(obj->resv);
+			if (IS_ERR(op->vm_bo))
+				return PTR_ERR(op->vm_bo);
 		}
 
 		ret = bind_validate_op(job, op);
@@ -1352,7 +1367,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job)
 		case OP_UNMAP_SPARSE:
 		case OP_MAP:
 		case OP_UNMAP:
-			bind_link_gpuvas(op->ops, &op->new);
+			bind_link_gpuvas(op);
 			break;
 		default:
 			break;
@@ -1499,6 +1514,12 @@ nouveau_uvmm_bind_job_free_work_fn(struct work_struct *work)
 		if (!IS_ERR_OR_NULL(op->ops))
 			drm_gpuva_ops_free(&uvmm->base, op->ops);
 
+		if (!IS_ERR_OR_NULL(op->vm_bo)) {
+			dma_resv_lock(obj->resv, NULL);
+			drm_gpuvm_bo_put(op->vm_bo);
+			dma_resv_unlock(obj->resv);
+		}
+
 		if (obj)
 			drm_gem_object_put(obj);
 	}
@@ -1752,32 +1773,38 @@ void
 nouveau_uvmm_bo_map_all(struct nouveau_bo *nvbo, struct nouveau_mem *mem)
 {
 	struct drm_gem_object *obj = &nvbo->bo.base;
+	struct drm_gpuvm_bo *vm_bo;
 	struct drm_gpuva *va;
 
 	dma_resv_assert_held(obj->resv);
 
-	drm_gem_for_each_gpuva(va, obj) {
+	drm_gem_for_each_gpuvm_bo(vm_bo, obj) {
+		drm_gpuvm_bo_for_each_va(va, vm_bo) {
 			struct nouveau_uvma *uvma = uvma_from_va(va);
 
 			nouveau_uvma_map(uvma, mem);
 			drm_gpuva_invalidate(va, false);
 		}
+	}
 }
 
 void
 nouveau_uvmm_bo_unmap_all(struct nouveau_bo *nvbo)
 {
 	struct drm_gem_object *obj = &nvbo->bo.base;
+	struct drm_gpuvm_bo *vm_bo;
 	struct drm_gpuva *va;
 
 	dma_resv_assert_held(obj->resv);
 
-	drm_gem_for_each_gpuva(va, obj) {
+	drm_gem_for_each_gpuvm_bo(vm_bo, obj) {
+		drm_gpuvm_bo_for_each_va(va, vm_bo) {
 			struct nouveau_uvma *uvma = uvma_from_va(va);
 
 			nouveau_uvma_unmap(uvma);
 			drm_gpuva_invalidate(va, true);
 		}
+	}
 }
 
 static void

include/drm/drm_gem.h

@@ -580,7 +580,7 @@ int drm_gem_evict(struct drm_gem_object *obj);
  * drm_gem_gpuva_init() - initialize the gpuva list of a GEM object
  * @obj: the &drm_gem_object
  *
- * This initializes the &drm_gem_object's &drm_gpuva list.
+ * This initializes the &drm_gem_object's &drm_gpuvm_bo list.
  *
  * Calling this function is only necessary for drivers intending to support the
  * &drm_driver_feature DRIVER_GEM_GPUVA.
@@ -593,28 +593,28 @@ static inline void drm_gem_gpuva_init(struct drm_gem_object *obj)
 }
 
 /**
- * drm_gem_for_each_gpuva() - iternator to walk over a list of gpuvas
- * @entry__: &drm_gpuva structure to assign to in each iteration step
- * @obj__: the &drm_gem_object the &drm_gpuvas to walk are associated with
+ * drm_gem_for_each_gpuvm_bo() - iterator to walk over a list of &drm_gpuvm_bo
+ * @entry__: &drm_gpuvm_bo structure to assign to in each iteration step
+ * @obj__: the &drm_gem_object the &drm_gpuvm_bo to walk are associated with
  *
- * This iterator walks over all &drm_gpuva structures associated with the
- * &drm_gpuva_manager.
+ * This iterator walks over all &drm_gpuvm_bo structures associated with the
+ * &drm_gem_object.
  */
-#define drm_gem_for_each_gpuva(entry__, obj__) \
-	list_for_each_entry(entry__, &(obj__)->gpuva.list, gem.entry)
+#define drm_gem_for_each_gpuvm_bo(entry__, obj__) \
+	list_for_each_entry(entry__, &(obj__)->gpuva.list, list.entry.gem)
 
 /**
- * drm_gem_for_each_gpuva_safe() - iternator to safely walk over a list of
- * gpuvas
- * @entry__: &drm_gpuva structure to assign to in each iteration step
- * @next__: &next &drm_gpuva to store the next step
- * @obj__: the &drm_gem_object the &drm_gpuvas to walk are associated with
+ * drm_gem_for_each_gpuvm_bo_safe() - iterator to safely walk over a list of
+ * &drm_gpuvm_bo
+ * @entry__: &drm_gpuvm_bostructure to assign to in each iteration step
+ * @next__: &next &drm_gpuvm_bo to store the next step
+ * @obj__: the &drm_gem_object the &drm_gpuvm_bo to walk are associated with
  *
- * This iterator walks over all &drm_gpuva structures associated with the
+ * This iterator walks over all &drm_gpuvm_bo structures associated with the
  * &drm_gem_object. It is implemented with list_for_each_entry_safe(), hence
  * it is save against removal of elements.
  */
-#define drm_gem_for_each_gpuva_safe(entry__, next__, obj__) \
-	list_for_each_entry_safe(entry__, next__, &(obj__)->gpuva.list, gem.entry)
+#define drm_gem_for_each_gpuvm_bo_safe(entry__, next__, obj__) \
+	list_for_each_entry_safe(entry__, next__, &(obj__)->gpuva.list, list.entry.gem)
 
 #endif /* __DRM_GEM_H__ */

include/drm/drm_gpuvm.h

@@ -25,6 +25,7 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/dma-resv.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <linux/types.h>
@@ -33,6 +34,7 @@
 #include <drm/drm_gem.h>
 
 struct drm_gpuvm;
+struct drm_gpuvm_bo;
 struct drm_gpuvm_ops;
 
 /**
@@ -73,6 +75,12 @@ struct drm_gpuva {
 	 */
 	struct drm_gpuvm *vm;
 
+	/**
+	 * @vm_bo: the &drm_gpuvm_bo abstraction for the mapped
+	 * &drm_gem_object
+	 */
+	struct drm_gpuvm_bo *vm_bo;
+
 	/**
 	 * @flags: the &drm_gpuva_flags for this mapping
 	 */
@@ -108,7 +116,7 @@ struct drm_gpuva {
 		struct drm_gem_object *obj;
 
 		/**
-		 * @entry: the &list_head to attach this object to a &drm_gem_object
+		 * @entry: the &list_head to attach this object to a &drm_gpuvm_bo
 		 */
 		struct list_head entry;
 	} gem;
@@ -141,7 +149,7 @@ struct drm_gpuva {
 int drm_gpuva_insert(struct drm_gpuvm *gpuvm, struct drm_gpuva *va);
 void drm_gpuva_remove(struct drm_gpuva *va);
 
-void drm_gpuva_link(struct drm_gpuva *va);
+void drm_gpuva_link(struct drm_gpuva *va, struct drm_gpuvm_bo *vm_bo);
 void drm_gpuva_unlink(struct drm_gpuva *va);
 
 struct drm_gpuva *drm_gpuva_find(struct drm_gpuvm *gpuvm,
@@ -188,10 +196,16 @@ static inline bool drm_gpuva_invalidated(struct drm_gpuva *va)
  * enum drm_gpuvm_flags - flags for struct drm_gpuvm
  */
 enum drm_gpuvm_flags {
+	/**
+	 * @DRM_GPUVM_RESV_PROTECTED: GPUVM is protected externally by the
+	 * GPUVM's &dma_resv lock
+	 */
+	DRM_GPUVM_RESV_PROTECTED = BIT(0),
+
 	/**
 	 * @DRM_GPUVM_USERBITS: user defined bits
 	 */
-	DRM_GPUVM_USERBITS = BIT(0),
+	DRM_GPUVM_USERBITS = BIT(1),
 };
 
 /**
@@ -302,6 +316,19 @@ bool drm_gpuvm_interval_empty(struct drm_gpuvm *gpuvm, u64 addr, u64 range);
 struct drm_gem_object *
 drm_gpuvm_resv_object_alloc(struct drm_device *drm);
 
+/**
+ * drm_gpuvm_resv_protected() - indicates whether &DRM_GPUVM_RESV_PROTECTED is
+ * set
+ * @gpuvm: the &drm_gpuvm
+ *
+ * Returns: true if &DRM_GPUVM_RESV_PROTECTED is set, false otherwise.
+ */
+static inline bool
+drm_gpuvm_resv_protected(struct drm_gpuvm *gpuvm)
+{
+	return gpuvm->flags & DRM_GPUVM_RESV_PROTECTED;
+}
+
 /**
  * drm_gpuvm_resv() - returns the &drm_gpuvm's &dma_resv
  * @gpuvm__: the &drm_gpuvm
@@ -320,6 +347,12 @@ drm_gpuvm_resv_object_alloc(struct drm_device *drm);
  */
 #define drm_gpuvm_resv_obj(gpuvm__) ((gpuvm__)->r_obj)
 
+#define drm_gpuvm_resv_held(gpuvm__) \
+	dma_resv_held(drm_gpuvm_resv(gpuvm__))
+
+#define drm_gpuvm_resv_assert_held(gpuvm__) \
+	dma_resv_assert_held(drm_gpuvm_resv(gpuvm__))
+
 #define drm_gpuvm_resv_held(gpuvm__) \
 	dma_resv_held(drm_gpuvm_resv(gpuvm__))
 
@@ -404,6 +437,125 @@ __drm_gpuva_next(struct drm_gpuva *va)
 #define drm_gpuvm_for_each_va_safe(va__, next__, gpuvm__) \
 	list_for_each_entry_safe(va__, next__, &(gpuvm__)->rb.list, rb.entry)
 
+/**
+ * struct drm_gpuvm_bo - structure representing a &drm_gpuvm and
+ * &drm_gem_object combination
+ *
+ * This structure is an abstraction representing a &drm_gpuvm and
+ * &drm_gem_object combination. It serves as an indirection to accelerate
+ * iterating all &drm_gpuvas within a &drm_gpuvm backed by the same
+ * &drm_gem_object.
+ *
+ * Furthermore it is used cache evicted GEM objects for a certain GPU-VM to
+ * accelerate validation.
+ *
+ * Typically, drivers want to create an instance of a struct drm_gpuvm_bo once
+ * a GEM object is mapped first in a GPU-VM and release the instance once the
+ * last mapping of the GEM object in this GPU-VM is unmapped.
+ */
+struct drm_gpuvm_bo {
+	/**
+	 * @vm: The &drm_gpuvm the @obj is mapped in. This is a reference
+	 * counted pointer.
+	 */
+	struct drm_gpuvm *vm;
+
+	/**
+	 * @obj: The &drm_gem_object being mapped in @vm. This is a reference
+	 * counted pointer.
+	 */
+	struct drm_gem_object *obj;
+
+	/**
+	 * @kref: The reference count for this &drm_gpuvm_bo.
+	 */
+	struct kref kref;
+
+	/**
+	 * @list: Structure containing all &list_heads.
+	 */
+	struct {
+		/**
+		 * @gpuva: The list of linked &drm_gpuvas.
+		 *
+		 * It is safe to access entries from this list as long as the
+		 * GEM's gpuva lock is held. See also struct drm_gem_object.
+		 */
+		struct list_head gpuva;
+
+		/**
+		 * @entry: Structure containing all &list_heads serving as
+		 * entry.
+		 */
+		struct {
+			/**
+			 * @gem: List entry to attach to the &drm_gem_objects
+			 * gpuva list.
+			 */
+			struct list_head gem;
+		} entry;
+	} list;
+};
+
+struct drm_gpuvm_bo *
+drm_gpuvm_bo_create(struct drm_gpuvm *gpuvm,
+		    struct drm_gem_object *obj);
+
+struct drm_gpuvm_bo *
+drm_gpuvm_bo_obtain(struct drm_gpuvm *gpuvm,
+		    struct drm_gem_object *obj);
+struct drm_gpuvm_bo *
+drm_gpuvm_bo_obtain_prealloc(struct drm_gpuvm_bo *vm_bo);
+
+/**
+ * drm_gpuvm_bo_get() - acquire a struct drm_gpuvm_bo reference
+ * @vm_bo: the &drm_gpuvm_bo to acquire the reference of
+ *
+ * This function acquires an additional reference to @vm_bo. It is illegal to
+ * call this without already holding a reference. No locks required.
+ */
+static inline struct drm_gpuvm_bo *
+drm_gpuvm_bo_get(struct drm_gpuvm_bo *vm_bo)
+{
+	kref_get(&vm_bo->kref);
+	return vm_bo;
+}
+
+void drm_gpuvm_bo_put(struct drm_gpuvm_bo *vm_bo);
+
+struct drm_gpuvm_bo *
+drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm,
+		  struct drm_gem_object *obj);
+
+/**
+ * drm_gpuvm_bo_for_each_va() - iterator to walk over a list of &drm_gpuva
+ * @va__: &drm_gpuva structure to assign to in each iteration step
+ * @vm_bo__: the &drm_gpuvm_bo the &drm_gpuva to walk are associated with
+ *
+ * This iterator walks over all &drm_gpuva structures associated with the
+ * &drm_gpuvm_bo.
+ *
+ * The caller must hold the GEM's gpuva lock.
+ */
+#define drm_gpuvm_bo_for_each_va(va__, vm_bo__) \
+	list_for_each_entry(va__, &(vm_bo)->list.gpuva, gem.entry)
+
+/**
+ * drm_gpuvm_bo_for_each_va_safe() - iterator to safely walk over a list of
+ * &drm_gpuva
+ * @va__: &drm_gpuva structure to assign to in each iteration step
+ * @next__: &next &drm_gpuva to store the next step
+ * @vm_bo__: the &drm_gpuvm_bo the &drm_gpuva to walk are associated with
+ *
+ * This iterator walks over all &drm_gpuva structures associated with the
+ * &drm_gpuvm_bo. It is implemented with list_for_each_entry_safe(), hence
+ * it is save against removal of elements.
+ *
+ * The caller must hold the GEM's gpuva lock.
+ */
+#define drm_gpuvm_bo_for_each_va_safe(va__, next__, vm_bo__) \
+	list_for_each_entry_safe(va__, next__, &(vm_bo)->list.gpuva, gem.entry)
+
 /**
  * enum drm_gpuva_op_type - GPU VA operation type
  *
@@ -673,8 +825,7 @@ drm_gpuvm_prefetch_ops_create(struct drm_gpuvm *gpuvm,
 				 u64 addr, u64 range);
 
 struct drm_gpuva_ops *
-drm_gpuvm_gem_unmap_ops_create(struct drm_gpuvm *gpuvm,
-			       struct drm_gem_object *obj);
+drm_gpuvm_bo_unmap_ops_create(struct drm_gpuvm_bo *vm_bo);
 
 void drm_gpuva_ops_free(struct drm_gpuvm *gpuvm,
 			struct drm_gpuva_ops *ops);
@@ -726,6 +877,30 @@ struct drm_gpuvm_ops {
 	 */
 	void (*op_free)(struct drm_gpuva_op *op);
 
+	/**
+	 * @vm_bo_alloc: called when the &drm_gpuvm allocates
+	 * a struct drm_gpuvm_bo
+	 *
+	 * Some drivers may want to embed struct drm_gpuvm_bo into driver
+	 * specific structures. By implementing this callback drivers can
+	 * allocate memory accordingly.
+	 *
+	 * This callback is optional.
+	 */
+	struct drm_gpuvm_bo *(*vm_bo_alloc)(void);
+
+	/**
+	 * @vm_bo_free: called when the &drm_gpuvm frees a
+	 * struct drm_gpuvm_bo
+	 *
+	 * Some drivers may want to embed struct drm_gpuvm_bo into driver
+	 * specific structures. By implementing this callback drivers can
+	 * free the previously allocated memory accordingly.
+	 *
+	 * This callback is optional.
+	 */
+	void (*vm_bo_free)(struct drm_gpuvm_bo *vm_bo);
+
 	/**
 	 * @sm_step_map: called from &drm_gpuvm_sm_map to finally insert the
 	 * mapping once all previous steps were completed