1 files changed, 293 insertions, 47 deletions

diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index ef968eba6fe6..7e193bca8bab 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -70,6 +70,18 @@
  * &drm_gem_object, such as the &drm_gem_object containing the root page table,
  * but it can also be a 'dummy' object, which can be allocated with
  * drm_gpuvm_resv_object_alloc().
+ *
+ * In order to connect a struct drm_gpuva its backing &drm_gem_object each
+ * &drm_gem_object maintains a list of &drm_gpuvm_bo structures, and each
+ * &drm_gpuvm_bo contains a list of &drm_gpuva structures.
+ *
+ * A &drm_gpuvm_bo is an abstraction that represents a combination of a
+ * &drm_gpuvm and a &drm_gem_object. Every such combination should be unique.
+ * This is ensured by the API through drm_gpuvm_bo_obtain() and
+ * drm_gpuvm_bo_obtain_prealloc() which first look into the corresponding
+ * &drm_gem_object list of &drm_gpuvm_bos for an existing instance of this
+ * particular combination. If not existent a new instance is created and linked
+ * to the &drm_gem_object.
  */
 
 /**
@@ -395,21 +407,28 @@
 /**
  * DOC: Locking
  *
- * Generally, the GPU VA manager does not take care of locking itself, it is
- * the drivers responsibility to take care about locking. Drivers might want to
- * protect the following operations: inserting, removing and iterating
- * &drm_gpuva objects as well as generating all kinds of operations, such as
- * split / merge or prefetch.
- *
- * The GPU VA manager also does not take care of the locking of the backing
- * &drm_gem_object buffers GPU VA lists by itself; drivers are responsible to
- * enforce mutual exclusion using either the GEMs dma_resv lock or alternatively
- * a driver specific external lock. For the latter see also
- * drm_gem_gpuva_set_lock().
- *
- * However, the GPU VA manager contains lockdep checks to ensure callers of its
- * API hold the corresponding lock whenever the &drm_gem_objects GPU VA list is
- * accessed by functions such as drm_gpuva_link() or drm_gpuva_unlink().
+ * In terms of managing &drm_gpuva entries DRM GPUVM does not take care of
+ * locking itself, it is the drivers responsibility to take care about locking.
+ * Drivers might want to protect the following operations: inserting, removing
+ * and iterating &drm_gpuva objects as well as generating all kinds of
+ * operations, such as split / merge or prefetch.
+ *
+ * DRM GPUVM also does not take care of the locking of the backing
+ * &drm_gem_object buffers GPU VA lists and &drm_gpuvm_bo abstractions by
+ * itself; drivers are responsible to enforce mutual exclusion using either the
+ * GEMs dma_resv lock or alternatively a driver specific external lock. For the
+ * latter see also drm_gem_gpuva_set_lock().
+ *
+ * However, DRM GPUVM contains lockdep checks to ensure callers of its API hold
+ * the corresponding lock whenever the &drm_gem_objects GPU VA list is accessed
+ * by functions such as drm_gpuva_link() or drm_gpuva_unlink(), but also
+ * drm_gpuvm_bo_obtain() and drm_gpuvm_bo_put().
+ *
+ * The latter is required since on creation and destruction of a &drm_gpuvm_bo
+ * the &drm_gpuvm_bo is attached / removed from the &drm_gem_objects gpuva list.
+ * Subsequent calls to drm_gpuvm_bo_obtain() for the same &drm_gpuvm and
+ * &drm_gem_object must be able to observe previous creations and destructions
+ * of &drm_gpuvm_bos in order to keep instances unique.
  */
 
 /**
@@ -439,6 +458,7 @@
  *	{
  *		struct drm_gpuva_ops *ops;
  *		struct drm_gpuva_op *op
+ *		struct drm_gpuvm_bo *vm_bo;
  *
  *		driver_lock_va_space();
  *		ops = drm_gpuvm_sm_map_ops_create(gpuvm, addr, range,
@@ -446,6 +466,10 @@
  *		if (IS_ERR(ops))
  *			return PTR_ERR(ops);
  *
+ *		vm_bo = drm_gpuvm_bo_obtain(gpuvm, obj);
+ *		if (IS_ERR(vm_bo))
+ *			return PTR_ERR(vm_bo);
+ *
  *		drm_gpuva_for_each_op(op, ops) {
  *			struct drm_gpuva *va;
  *
@@ -458,7 +482,7 @@
  *
  *				driver_vm_map();
  *				drm_gpuva_map(gpuvm, va, &op->map);
- *				drm_gpuva_link(va);
+ *				drm_gpuva_link(va, vm_bo);
  *
  *				break;
  *			case DRM_GPUVA_OP_REMAP: {
@@ -485,11 +509,11 @@
  *				driver_vm_remap();
  *				drm_gpuva_remap(prev, next, &op->remap);
  *
- *				drm_gpuva_unlink(va);
  *				if (prev)
- *					drm_gpuva_link(prev);
+ *					drm_gpuva_link(prev, va->vm_bo);
  *				if (next)
- *					drm_gpuva_link(next);
+ *					drm_gpuva_link(next, va->vm_bo);
+ *				drm_gpuva_unlink(va);
  *
  *				break;
  *			}
@@ -505,6 +529,7 @@
  *				break;
  *			}
  *		}
+ *		drm_gpuvm_bo_put(vm_bo);
  *		driver_unlock_va_space();
  *
  *		return 0;
@@ -514,6 +539,7 @@
  *
  *	struct driver_context {
  *		struct drm_gpuvm *gpuvm;
+ *		struct drm_gpuvm_bo *vm_bo;
  *		struct drm_gpuva *new_va;
  *		struct drm_gpuva *prev_va;
  *		struct drm_gpuva *next_va;
@@ -534,6 +560,7 @@
  *				  struct drm_gem_object *obj, u64 offset)
  *	{
  *		struct driver_context ctx;
+ *		struct drm_gpuvm_bo *vm_bo;
  *		struct drm_gpuva_ops *ops;
  *		struct drm_gpuva_op *op;
  *		int ret = 0;
@@ -543,16 +570,23 @@
  *		ctx.new_va = kzalloc(sizeof(*ctx.new_va), GFP_KERNEL);
  *		ctx.prev_va = kzalloc(sizeof(*ctx.prev_va), GFP_KERNEL);
  *		ctx.next_va = kzalloc(sizeof(*ctx.next_va), GFP_KERNEL);
- *		if (!ctx.new_va || !ctx.prev_va || !ctx.next_va) {
+ *		ctx.vm_bo = drm_gpuvm_bo_create(gpuvm, obj);
+ *		if (!ctx.new_va || !ctx.prev_va || !ctx.next_va || !vm_bo) {
  *			ret = -ENOMEM;
  *			goto out;
  *		}
  *
+ *		// Typically protected with a driver specific GEM gpuva lock
+ *		// used in the fence signaling path for drm_gpuva_link() and
+ *		// drm_gpuva_unlink(), hence pre-allocate.
+ *		ctx.vm_bo = drm_gpuvm_bo_obtain_prealloc(ctx.vm_bo);
+ *
  *		driver_lock_va_space();
  *		ret = drm_gpuvm_sm_map(gpuvm, &ctx, addr, range, obj, offset);
  *		driver_unlock_va_space();
  *
  *	out:
+ *		drm_gpuvm_bo_put(ctx.vm_bo);
  *		kfree(ctx.new_va);
  *		kfree(ctx.prev_va);
  *		kfree(ctx.next_va);
@@ -565,7 +599,7 @@
  *
  *		drm_gpuva_map(ctx->vm, ctx->new_va, &op->map);
  *
- *		drm_gpuva_link(ctx->new_va);
+ *		drm_gpuva_link(ctx->new_va, ctx->vm_bo);
  *
  *		// prevent the new GPUVA from being freed in
  *		// driver_mapping_create()
@@ -577,22 +611,23 @@
  *	int driver_gpuva_remap(struct drm_gpuva_op *op, void *__ctx)
  *	{
  *		struct driver_context *ctx = __ctx;
+ *		struct drm_gpuva *va = op->remap.unmap->va;
  *
  *		drm_gpuva_remap(ctx->prev_va, ctx->next_va, &op->remap);
  *
- *		drm_gpuva_unlink(op->remap.unmap->va);
- *		kfree(op->remap.unmap->va);
- *
  *		if (op->remap.prev) {
- *			drm_gpuva_link(ctx->prev_va);
+ *			drm_gpuva_link(ctx->prev_va, va->vm_bo);
  *			ctx->prev_va = NULL;
  *		}
  *
  *		if (op->remap.next) {
- *			drm_gpuva_link(ctx->next_va);
+ *			drm_gpuva_link(ctx->next_va, va->vm_bo);
  *			ctx->next_va = NULL;
  *		}
  *
+ *		drm_gpuva_unlink(va);
+ *		kfree(va);
+ *
  *		return 0;
  *	}
  *
@@ -815,6 +850,199 @@ drm_gpuvm_put(struct drm_gpuvm *gpuvm)
 }
 EXPORT_SYMBOL_GPL(drm_gpuvm_put);
 
+/**
+ * drm_gpuvm_bo_create() - create a new instance of struct drm_gpuvm_bo
+ * @gpuvm: The &drm_gpuvm the @obj is mapped in.
+ * @obj: The &drm_gem_object being mapped in the @gpuvm.
+ *
+ * If provided by the driver, this function uses the &drm_gpuvm_ops
+ * vm_bo_alloc() callback to allocate.
+ *
+ * Returns: a pointer to the &drm_gpuvm_bo on success, NULL on failure
+ */
+struct drm_gpuvm_bo *
+drm_gpuvm_bo_create(struct drm_gpuvm *gpuvm,
+		    struct drm_gem_object *obj)
+{
+	const struct drm_gpuvm_ops *ops = gpuvm->ops;
+	struct drm_gpuvm_bo *vm_bo;
+
+	if (ops && ops->vm_bo_alloc)
+		vm_bo = ops->vm_bo_alloc();
+	else
+		vm_bo = kzalloc(sizeof(*vm_bo), GFP_KERNEL);
+
+	if (unlikely(!vm_bo))
+		return NULL;
+
+	vm_bo->vm = drm_gpuvm_get(gpuvm);
+	vm_bo->obj = obj;
+	drm_gem_object_get(obj);
+
+	kref_init(&vm_bo->kref);
+	INIT_LIST_HEAD(&vm_bo->list.gpuva);
+	INIT_LIST_HEAD(&vm_bo->list.entry.gem);
+
+	return vm_bo;
+}
+EXPORT_SYMBOL_GPL(drm_gpuvm_bo_create);
+
+static void
+drm_gpuvm_bo_destroy(struct kref *kref)
+{
+	struct drm_gpuvm_bo *vm_bo = container_of(kref, struct drm_gpuvm_bo,
+						  kref);
+	struct drm_gpuvm *gpuvm = vm_bo->vm;
+	const struct drm_gpuvm_ops *ops = gpuvm->ops;
+	struct drm_gem_object *obj = vm_bo->obj;
+	bool lock = !drm_gpuvm_resv_protected(gpuvm);
+
+	if (!lock)
+		drm_gpuvm_resv_assert_held(gpuvm);
+
+	drm_gem_gpuva_assert_lock_held(obj);
+	list_del(&vm_bo->list.entry.gem);
+
+	if (ops && ops->vm_bo_free)
+		ops->vm_bo_free(vm_bo);
+	else
+		kfree(vm_bo);
+
+	drm_gpuvm_put(gpuvm);
+	drm_gem_object_put(obj);
+}
+
+/**
+ * drm_gpuvm_bo_put() - drop a struct drm_gpuvm_bo reference
+ * @vm_bo: the &drm_gpuvm_bo to release the reference of
+ *
+ * This releases a reference to @vm_bo.
+ *
+ * If the reference count drops to zero, the &gpuvm_bo is destroyed, which
+ * includes removing it from the GEMs gpuva list. Hence, if a call to this
+ * function can potentially let the reference count drop to zero the caller must
+ * hold the dma-resv or driver specific GEM gpuva lock.
+ *
+ * This function may only be called from non-atomic context.
+ */
+void
+drm_gpuvm_bo_put(struct drm_gpuvm_bo *vm_bo)
+{
+	might_sleep();
+
+	if (vm_bo)
+		kref_put(&vm_bo->kref, drm_gpuvm_bo_destroy);
+}
+EXPORT_SYMBOL_GPL(drm_gpuvm_bo_put);
+
+static struct drm_gpuvm_bo *
+__drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm,
+		    struct drm_gem_object *obj)
+{
+	struct drm_gpuvm_bo *vm_bo;
+
+	drm_gem_gpuva_assert_lock_held(obj);
+	drm_gem_for_each_gpuvm_bo(vm_bo, obj)
+		if (vm_bo->vm == gpuvm)
+			return vm_bo;
+
+	return NULL;
+}
+
+/**
+ * drm_gpuvm_bo_find() - find the &drm_gpuvm_bo for the given
+ * &drm_gpuvm and &drm_gem_object
+ * @gpuvm: The &drm_gpuvm the @obj is mapped in.
+ * @obj: The &drm_gem_object being mapped in the @gpuvm.
+ *
+ * Find the &drm_gpuvm_bo representing the combination of the given
+ * &drm_gpuvm and &drm_gem_object. If found, increases the reference
+ * count of the &drm_gpuvm_bo accordingly.
+ *
+ * Returns: a pointer to the &drm_gpuvm_bo on success, NULL on failure
+ */
+struct drm_gpuvm_bo *
+drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm,
+		  struct drm_gem_object *obj)
+{
+	struct drm_gpuvm_bo *vm_bo = __drm_gpuvm_bo_find(gpuvm, obj);
+
+	return vm_bo ? drm_gpuvm_bo_get(vm_bo) : NULL;
+}
+EXPORT_SYMBOL_GPL(drm_gpuvm_bo_find);
+
+/**
+ * drm_gpuvm_bo_obtain() - obtains and instance of the &drm_gpuvm_bo for the
+ * given &drm_gpuvm and &drm_gem_object
+ * @gpuvm: The &drm_gpuvm the @obj is mapped in.
+ * @obj: The &drm_gem_object being mapped in the @gpuvm.
+ *
+ * Find the &drm_gpuvm_bo representing the combination of the given
+ * &drm_gpuvm and &drm_gem_object. If found, increases the reference
+ * count of the &drm_gpuvm_bo accordingly. If not found, allocates a new
+ * &drm_gpuvm_bo.
+ *
+ * A new &drm_gpuvm_bo is added to the GEMs gpuva list.
+ *
+ * Returns: a pointer to the &drm_gpuvm_bo on success, an ERR_PTR on failure
+ */
+struct drm_gpuvm_bo *
+drm_gpuvm_bo_obtain(struct drm_gpuvm *gpuvm,
+		    struct drm_gem_object *obj)
+{
+	struct drm_gpuvm_bo *vm_bo;
+
+	vm_bo = drm_gpuvm_bo_find(gpuvm, obj);
+	if (vm_bo)
+		return vm_bo;
+
+	vm_bo = drm_gpuvm_bo_create(gpuvm, obj);
+	if (!vm_bo)
+		return ERR_PTR(-ENOMEM);
+
+	drm_gem_gpuva_assert_lock_held(obj);
+	list_add_tail(&vm_bo->list.entry.gem, &obj->gpuva.list);
+
+	return vm_bo;
+}
+EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain);
+
+/**
+ * drm_gpuvm_bo_obtain_prealloc() - obtains and instance of the &drm_gpuvm_bo
+ * for the given &drm_gpuvm and &drm_gem_object
+ * @__vm_bo: A pre-allocated struct drm_gpuvm_bo.
+ *
+ * Find the &drm_gpuvm_bo representing the combination of the given
+ * &drm_gpuvm and &drm_gem_object. If found, increases the reference
+ * count of the found &drm_gpuvm_bo accordingly, while the @__vm_bo reference
+ * count is decreased. If not found @__vm_bo is returned without further
+ * increase of the reference count.
+ *
+ * A new &drm_gpuvm_bo is added to the GEMs gpuva list.
+ *
+ * Returns: a pointer to the found &drm_gpuvm_bo or @__vm_bo if no existing
+ * &drm_gpuvm_bo was found
+ */
+struct drm_gpuvm_bo *
+drm_gpuvm_bo_obtain_prealloc(struct drm_gpuvm_bo *__vm_bo)
+{
+	struct drm_gpuvm *gpuvm = __vm_bo->vm;
+	struct drm_gem_object *obj = __vm_bo->obj;
+	struct drm_gpuvm_bo *vm_bo;
+
+	vm_bo = drm_gpuvm_bo_find(gpuvm, obj);
+	if (vm_bo) {
+		drm_gpuvm_bo_put(__vm_bo);
+		return vm_bo;
+	}
+
+	drm_gem_gpuva_assert_lock_held(obj);
+	list_add_tail(&__vm_bo->list.entry.gem, &obj->gpuva.list);
+
+	return __vm_bo;
+}
+EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain_prealloc);
+
 static int
 __drm_gpuva_insert(struct drm_gpuvm *gpuvm,
 		   struct drm_gpuva *va)
@@ -916,24 +1144,33 @@ EXPORT_SYMBOL_GPL(drm_gpuva_remove);
 /**
  * drm_gpuva_link() - link a &drm_gpuva
  * @va: the &drm_gpuva to link
+ * @vm_bo: the &drm_gpuvm_bo to add the &drm_gpuva to
  *
- * This adds the given &va to the GPU VA list of the &drm_gem_object it is
- * associated with.
+ * This adds the given &va to the GPU VA list of the &drm_gpuvm_bo and the
+ * &drm_gpuvm_bo to the &drm_gem_object it is associated with.
+ *
+ * For every &drm_gpuva entry added to the &drm_gpuvm_bo an additional
+ * reference of the latter is taken.
  *
  * This function expects the caller to protect the GEM's GPUVA list against
- * concurrent access using the GEMs dma_resv lock.
+ * concurrent access using either the GEMs dma_resv lock or a driver specific
+ * lock set through drm_gem_gpuva_set_lock().
  */
 void
-drm_gpuva_link(struct drm_gpuva *va)
+drm_gpuva_link(struct drm_gpuva *va, struct drm_gpuvm_bo *vm_bo)
 {
 	struct drm_gem_object *obj = va->gem.obj;
+	struct drm_gpuvm *gpuvm = va->vm;
 
 	if (unlikely(!obj))
 		return;
 
-	drm_gem_gpuva_assert_lock_held(obj);
+	drm_WARN_ON(gpuvm->drm, obj != vm_bo->obj);
 
-	list_add_tail(&va->gem.entry, &obj->gpuva.list);
+	va->vm_bo = drm_gpuvm_bo_get(vm_bo);
+
+	drm_gem_gpuva_assert_lock_held(obj);
+	list_add_tail(&va->gem.entry, &vm_bo->list.gpuva);
 }
 EXPORT_SYMBOL_GPL(drm_gpuva_link);
 
@@ -944,20 +1181,31 @@ EXPORT_SYMBOL_GPL(drm_gpuva_link);
  * This removes the given &va from the GPU VA list of the &drm_gem_object it is
  * associated with.
  *
+ * This removes the given &va from the GPU VA list of the &drm_gpuvm_bo and
+ * the &drm_gpuvm_bo from the &drm_gem_object it is associated with in case
+ * this call unlinks the last &drm_gpuva from the &drm_gpuvm_bo.
+ *
+ * For every &drm_gpuva entry removed from the &drm_gpuvm_bo a reference of
+ * the latter is dropped.
+ *
  * This function expects the caller to protect the GEM's GPUVA list against
- * concurrent access using the GEMs dma_resv lock.
+ * concurrent access using either the GEMs dma_resv lock or a driver specific
+ * lock set through drm_gem_gpuva_set_lock().
  */
 void
 drm_gpuva_unlink(struct drm_gpuva *va)
 {
 	struct drm_gem_object *obj = va->gem.obj;
+	struct drm_gpuvm_bo *vm_bo = va->vm_bo;
 
 	if (unlikely(!obj))
 		return;
 
 	drm_gem_gpuva_assert_lock_held(obj);
-
 	list_del_init(&va->gem.entry);
+
+	va->vm_bo = NULL;
+	drm_gpuvm_bo_put(vm_bo);
 }
 EXPORT_SYMBOL_GPL(drm_gpuva_unlink);
 
@@ -1102,10 +1350,10 @@ drm_gpuva_remap(struct drm_gpuva *prev,
 		struct drm_gpuva *next,
 		struct drm_gpuva_op_remap *op)
 {
-	struct drm_gpuva *curr = op->unmap->va;
-	struct drm_gpuvm *gpuvm = curr->vm;
+	struct drm_gpuva *va = op->unmap->va;
+	struct drm_gpuvm *gpuvm = va->vm;
 
-	drm_gpuva_remove(curr);
+	drm_gpuva_remove(va);
 
 	if (op->prev) {
 		drm_gpuva_init_from_op(prev, op->prev);
@@ -1747,9 +1995,8 @@ err_free_ops:
 EXPORT_SYMBOL_GPL(drm_gpuvm_prefetch_ops_create);
 
 /**
- * drm_gpuvm_gem_unmap_ops_create() - creates the &drm_gpuva_ops to unmap a GEM
- * @gpuvm: the &drm_gpuvm representing the GPU VA space
- * @obj: the &drm_gem_object to unmap
+ * drm_gpuvm_bo_unmap_ops_create() - creates the &drm_gpuva_ops to unmap a GEM
+ * @vm_bo: the &drm_gpuvm_bo abstraction
  *
  * This function creates a list of operations to perform unmapping for every
  * GPUVA attached to a GEM.
@@ -1766,15 +2013,14 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_prefetch_ops_create);
  * Returns: a pointer to the &drm_gpuva_ops on success, an ERR_PTR on failure
  */
 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)
 {
 	struct drm_gpuva_ops *ops;
 	struct drm_gpuva_op *op;
 	struct drm_gpuva *va;
 	int ret;
 
-	drm_gem_gpuva_assert_lock_held(obj);
+	drm_gem_gpuva_assert_lock_held(vm_bo->obj);
 
 	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
 	if (!ops)
@@ -1782,8 +2028,8 @@ drm_gpuvm_gem_unmap_ops_create(struct drm_gpuvm *gpuvm,
 
 	INIT_LIST_HEAD(&ops->list);
 
-	drm_gem_for_each_gpuva(va, obj) {
-		op = gpuva_op_alloc(gpuvm);
+	drm_gpuvm_bo_for_each_va(va, vm_bo) {
+		op = gpuva_op_alloc(vm_bo->vm);
 		if (!op) {
 			ret = -ENOMEM;
 			goto err_free_ops;
@@ -1797,10 +2043,10 @@ drm_gpuvm_gem_unmap_ops_create(struct drm_gpuvm *gpuvm,
 	return ops;
 
 err_free_ops:
-	drm_gpuva_ops_free(gpuvm, ops);
+	drm_gpuva_ops_free(vm_bo->vm, ops);
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL_GPL(drm_gpuvm_gem_unmap_ops_create);
+EXPORT_SYMBOL_GPL(drm_gpuvm_bo_unmap_ops_create);
 
 /**
  * drm_gpuva_ops_free() - free the given &drm_gpuva_ops