dma-buf: introduce initial file I/O infrastructure

The goal is to be able to natively use dma-buf in the read-write / IO
path. This patch adds basic building blocks serving as a glue and API
between drivers and upper layer subsystems providing the uAPI. Later
patches implement it for NVMe raw block devices and expose it to the
user space via io_uring.

There are two main objects. struct dma_buf_io_ctx and struct
dma_buf_io_map. The ctx is used during initial registration and serves
as an interface between the upper layer user like io_uring and to the
importer subsystem / driver. The map represents the actual dma map
established for the target device[s] with dma_buf_map_attachment() and
stored in a device specific format. The context is created via a new
file operation ->init_dma_buf_io_ctx.

The ctx-map separation exists to facilitate map invalidation (see
dma_buf_io_invalidate_mappings()). A ctx can create
multiple maps during its lifetime, but there can only be no more than
one (active) map attached to it. Invalidation drops the active map
if present, and any new I/O request will try to create a new one.

The primary task of dma_buf_io_map is to count requests using it
and wait for their completion when we want to destroy the DMA map.

[un]mapping and any work with dma addresses is delegated to the
importer driver via an ops table stored in the ctx, see struct
dma_buf_io_ops. Only the target driver / subsystem knows about devices
it wants to use the dma-buf with, especially in case of multi-device
filesystems or stacking in the future.

Acked-by: Matthew Brost <matthew.brost@intel.com>
Tested-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://patch.msgid.link/49e24334953262e85d5616c9afde88c680e4f3a3.1791975048.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 127 insertions, 0 deletions

diff --git a/include/linux/dma-buf-io.h b/include/linux/dma-buf-io.h
new file mode 100644
index 000000000000..b9bbeca1744f
--- /dev/null
+++ b/include/linux/dma-buf-io.h
@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __DMA_BUF_IO_H__
+#define __DMA_BUF_IO_H__
+
+#include <linux/dma-buf.h>
+
+struct dma_buf_io_ctx;
+struct dma_buf_io_map;
+
+struct dma_buf_io_ops {
+	/*
+	 * Create a new map for the given ctx. Called with the reservation
+	 * lock held.
+	 */
+	struct dma_buf_io_map *(*map)(struct dma_buf_io_ctx *ctx);
+
+	/*
+	 * Clean up device specific parts of the @map. Called with the
+	 * reservation lock held.
+	 */
+	void (*unmap)(struct dma_buf_io_ctx *ctx, struct dma_buf_io_map *map);
+
+	/*
+	 * The user tries to destroy the ctx. Release all device specific
+	 * parts of the token.
+	 */
+	void (*release)(struct dma_buf_io_ctx *);
+};
+
+struct dma_buf_io_map {
+	/*
+	 * Counts attached requests and other users. Device specific unmapping
+	 * is deferred until all refs are dropped.
+	 */
+	struct percpu_ref		refs;
+	/*
+	 * Shift for the minimum segment size of the mapping.
+	 */
+	unsigned			min_seg_shift;
+
+	struct dma_buf_io_ctx		*ctx;
+	struct completion		drained;
+};
+
+struct dma_buf_io_ctx {
+	struct dma_buf_io_map __rcu		*map;
+	struct dma_buf				*dmabuf;
+	enum dma_data_direction			dir;
+	bool					is_dead;
+
+	void					*dev_priv;
+	const struct dma_buf_io_ops		*dev_ops;
+};
+
+int dma_buf_io_ctx_create(struct file *file,
+			   struct dma_buf *dmabuf,
+			   enum dma_data_direction dir,
+			   struct dma_buf_io_ctx **ctx);
+void dma_buf_io_ctx_release(struct dma_buf_io_ctx *ctx);
+
+struct dma_buf_io_map *dma_buf_io_create_map(struct dma_buf_io_ctx *ctx);
+
+static inline struct dma_buf_io_map *
+__dma_buf_io_get_map(struct dma_buf_io_ctx *ctx)
+{
+	struct dma_buf_io_map *map;
+
+	guard(rcu)();
+
+	map = rcu_dereference(ctx->map);
+	if (unlikely(!map || !percpu_ref_tryget_live_rcu(&map->refs)))
+		return NULL;
+
+	return map;
+}
+
+/**
+ * dma_buf_io_get_map - Create a new or reference an existing map.
+ * @ctx:	[in]	dma-buf I/O context
+ * @nowait:	[in]	specifies whether it's allowed to block
+ *
+ * Create a new or acquire an existing map. When succeeds, it returns
+ * a referenced map, which should eventually be put down with
+ * dma_buf_io_map_drop(). If @nowait is set and the function would block,
+ * it return -EAGAIN, and the caller is expected to retry from a context
+ * where blocking is allowed.
+ *
+ * Returns a map on success, or ERR_PTR encoded errno otherwise.
+ */
+static inline struct dma_buf_io_map *
+dma_buf_io_get_map(struct dma_buf_io_ctx *ctx, bool nowait)
+{
+	struct dma_buf_io_map *map;
+
+	map = __dma_buf_io_get_map(ctx);
+	if (likely(map))
+		return map;
+
+	if (nowait)
+		return ERR_PTR(-EAGAIN);
+	return dma_buf_io_create_map(ctx);
+}
+
+/**
+ * dma_buf_io_map_drop - Drop the map.
+ * @map:	[in]	dma-buf I/O map
+ *
+ * Put down a reference for the @map acquired via dma_buf_io_get_map().
+ * Should be called as soon as I/O is completed.
+ */
+static inline void dma_buf_io_map_drop(struct dma_buf_io_map *map)
+{
+	percpu_ref_put(&map->refs);
+}
+
+/*
+ * Device API
+ */
+
+void dma_buf_io_invalidate_mappings(struct dma_buf_io_ctx *ctx);
+int dma_buf_io_init_map(struct dma_buf_io_ctx *ctx, struct dma_buf_io_map *map,
+			struct sg_table *sgt);
+void dma_buf_io_detach(struct dma_buf_io_ctx *ctx);
+
+#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f9d1e05e8ae6..05c1ff495732 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1914,6 +1914,7 @@ struct dir_context {
 #define COPY_FILE_SPLICE		(1 << 0)
 
 struct io_uring_cmd;
+struct dma_buf_io_ctx;
 struct offset_ctx;
 
 struct file_operations {
@@ -1960,6 +1961,7 @@ struct file_operations {
 	int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *,
 				unsigned int poll_flags);
 	int (*mmap_prepare)(struct vm_area_desc *);
+	int (*init_dma_buf_io_ctx)(struct file *, struct dma_buf_io_ctx *);
 } __randomize_layout;
 
 /* Supports async buffered reads */