[PATCH v6 01/13] dma-buf: introduce initial file I/O infrastructure
Matthew Brost
matthew.brost at intel.com
Tue Sep 29 20:00:53 PDT 2026
On Mon, Sep 21, 2026 at 02:38:45PM +0100, Pavel Begunkov wrote:
> 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 support 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 the next map will only be attempted to be created
> once there is a new request that wants to use the dma-buf IO ctx.
>
> The primary task of the dma_buf_io_map object is to count requests
> using it and to 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.
>
> Signed-off-by: Pavel Begunkov <asml.silence at gmail.com>
> ---
> drivers/dma-buf/Makefile | 2 +-
> drivers/dma-buf/dma-buf-io.c | 219 +++++++++++++++++++++++++++++++++++
> include/linux/dma-buf-io.h | 113 ++++++++++++++++++
> include/linux/fs.h | 2 +
> 4 files changed, 335 insertions(+), 1 deletion(-)
> create mode 100644 drivers/dma-buf/dma-buf-io.c
> create mode 100644 include/linux/dma-buf-io.h
>
> diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
> index b25d7550bacf..523731b0f83e 100644
> --- a/drivers/dma-buf/Makefile
> +++ b/drivers/dma-buf/Makefile
> @@ -1,6 +1,6 @@
> # SPDX-License-Identifier: GPL-2.0-only
> obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
> - dma-fence-unwrap.o dma-resv.o dma-buf-mapping.o
> + dma-fence-unwrap.o dma-resv.o dma-buf-mapping.o dma-buf-io.o
> obj-$(CONFIG_DMABUF_HEAPS) += dma-heap.o
> obj-$(CONFIG_DMABUF_HEAPS) += heaps/
> obj-$(CONFIG_SYNC_FILE) += sync_file.o
> diff --git a/drivers/dma-buf/dma-buf-io.c b/drivers/dma-buf/dma-buf-io.c
> new file mode 100644
> index 000000000000..8312637a299f
> --- /dev/null
> +++ b/drivers/dma-buf/dma-buf-io.c
> @@ -0,0 +1,219 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * Common infrastructure for supporing dma-buf in the I/O path.
> + *
> + * Copyright (C) 2026 Pavel Begunkov <asml.silence at gmail.com>
> + */
> +#include <linux/dma-buf-io.h>
> +#include <linux/dma-resv.h>
> +
> +static void dma_buf_io_put_ctx(struct dma_buf_io_ctx *ctx)
> +{
> + might_sleep();
> +
> + if (WARN_ON_ONCE(rcu_dereference_protected(ctx->map, true)))
> + return;
> +
> + ctx->dev_ops->release(ctx);
> +
> + dma_buf_put(ctx->dmabuf);
> + mutex_destroy(&ctx->map_mutex);
> + mutex_destroy(&ctx->map_create_mutex);
> + kfree(ctx);
> +}
> +
> +static void dma_buf_io_map_release_work(struct work_struct *work)
> +{
> + struct dma_buf_io_map *map = container_of(work, struct dma_buf_io_map,
> + release_work);
> + struct dma_buf_io_ctx *ctx = map->ctx;
> + struct dma_buf *dmabuf = ctx->dmabuf;
> +
> + dma_resv_lock(dmabuf->resv, NULL);
> + ctx->dev_ops->unmap(ctx, map);
> + dma_resv_unlock(dmabuf->resv);
> +
> + percpu_ref_exit(&map->refs);
> + kfree(map);
> +
> + atomic_dec(&ctx->all_maps);
> + wake_up(&ctx->maps_wq);
> +}
> +
> +static void dma_buf_io_map_refs_release(struct percpu_ref *ref)
> +{
> + struct dma_buf_io_map *map = container_of(ref, struct dma_buf_io_map, refs);
> + struct dma_buf_io_ctx *ctx = map->ctx;
> +
> + /* There are no more requests using the map. */
> + atomic_dec(&ctx->active_maps);
> + wake_up(&ctx->maps_wq);
> +
> + /* might sleep, use a worker */
> + INIT_WORK(&map->release_work, dma_buf_io_map_release_work);
> + queue_work(system_percpu_wq, &map->release_work);
> +}
> +
> +static void dma_buf_io_wait_active_maps(struct dma_buf_io_ctx *ctx)
> +{
> + wait_event(ctx->maps_wq, atomic_read(&ctx->active_maps) == 0);
> +}
> +
> +static void dma_buf_io_wait_maps(struct dma_buf_io_ctx *ctx)
> +{
> + wait_event(ctx->maps_wq, atomic_read(&ctx->all_maps) == 0);
> +}
> +
> +int dma_buf_io_init_map(struct dma_buf_io_ctx *ctx, struct dma_buf_io_map *map,
> + struct sg_table *sgt)
> +{
> + unsigned seg_shift = ~0U;
> + struct scatterlist *sg;
> + unsigned long tmp;
> + int ret;
> +
> + for_each_sgtable_dma_sg(sgt, sg, tmp)
> + seg_shift = min(seg_shift, __ffs(sg_dma_len(sg)));
> +
> + ret = percpu_ref_init(&map->refs, dma_buf_io_map_refs_release, 0,
> + GFP_KERNEL);
> + if (ret)
> + return ret;
> + map->min_seg_shift = seg_shift;
> + map->ctx = ctx;
> + return 0;
> +}
> +EXPORT_SYMBOL_NS_GPL(dma_buf_io_init_map, "DMA_BUF");
> +
> +struct dma_buf_io_map *dma_buf_io_create_map(struct dma_buf_io_ctx *ctx)
> +{
> + struct dma_buf *dmabuf = ctx->dmabuf;
> + struct dma_buf_io_map *map;
> + long ret;
> +
> + guard(mutex)(&ctx->map_create_mutex);
> +
> + scoped_guard(mutex, &ctx->map_mutex) {
> + if (ctx->maps_killed)
> + return ERR_PTR(-ENOENT);
> + /* recheck under the lock in case it has already been re-created */
> + map = __dma_buf_io_get_map(ctx);
> + if (map)
> + return map;
> + }
> +
> + dma_buf_io_wait_active_maps(ctx);
> +
> + ret = dma_resv_lock_interruptible(dmabuf->resv, NULL);
> + if (ret)
> + return ERR_PTR(ret);
> +
> + ret = dma_resv_wait_timeout(dmabuf->resv, DMA_RESV_USAGE_KERNEL,
> + true, MAX_SCHEDULE_TIMEOUT);
> + if (ret <= 0) {
> + if (!ret)
> + ret = -EAGAIN;
> + dma_resv_unlock(dmabuf->resv);
> + return ERR_PTR(ret);
> + }
> +
> + map = ctx->dev_ops->map(ctx);
I'm playing around this code now.
I think you need the dma_resv_wait_timeout after the 'map'?
If a device doesn't support p2p ->map() will typically trigger an async
migrate to system memory and data will be moving but the map is valid -
Xe 100% does this, I checked AMDGPU and fairly confident it has the same
async behavior.
Matt
> + dma_resv_unlock(dmabuf->resv);
> +
> + if (IS_ERR(map))
> + return map;
> + if (WARN_ON_ONCE(!map->min_seg_shift))
> + return ERR_PTR(-EFAULT);
> +
> + atomic_inc(&ctx->active_maps);
> + atomic_inc(&ctx->all_maps);
> + /* get a reference for the caller */
> + percpu_ref_get(&map->refs);
> +
> + scoped_guard(mutex, &ctx->map_mutex)
> + rcu_assign_pointer(ctx->map, map);
> + return map;
> +}
> +
> +static void dma_buf_io_kill_maps(struct dma_buf_io_ctx *ctx, bool final)
> +{
> + struct dma_buf_io_map *map;
> +
> + scoped_guard(mutex, &ctx->map_mutex) {
> + if (final)
> + ctx->maps_killed = true;
> +
> + map = rcu_dereference_protected(ctx->map,
> + lockdep_is_held(&ctx->map_mutex));
> + if (!map)
> + return;
> + rcu_assign_pointer(ctx->map, NULL);
> + percpu_ref_kill(&map->refs);
> + }
> +}
> +
> +void dma_buf_io_invalidate_mappings(struct dma_buf_io_ctx *ctx)
> +{
> + dma_buf_io_kill_maps(ctx, false);
> + dma_buf_io_wait_active_maps(ctx);
> +}
> +EXPORT_SYMBOL_NS_GPL(dma_buf_io_invalidate_mappings, "DMA_BUF");
> +
> +void dma_buf_io_ctx_release(struct dma_buf_io_ctx *ctx)
> +{
> + /* Remove and wait for the last map, there should be no new ones. */
> + dma_buf_io_kill_maps(ctx, true);
> + dma_buf_io_wait_maps(ctx);
> + dma_buf_io_put_ctx(ctx);
> +}
> +
> +int dma_buf_io_ctx_create(struct file *file,
> + struct dma_buf *dmabuf,
> + enum dma_data_direction dir,
> + struct dma_buf_io_ctx **out_ctx)
> +{
> + struct dma_buf_io_ctx *ctx;
> + int ret;
> +
> + if (!file->f_op->init_dma_buf_io_ctx)
> + return -EOPNOTSUPP;
> +
> + ctx = kmalloc_obj(*ctx);
> + if (!ctx)
> + return -ENOMEM;
> +
> + memset(ctx, 0, sizeof(*ctx));
> + ctx->dir = dir;
> + ctx->dmabuf = dmabuf;
> + get_dma_buf(dmabuf);
> + mutex_init(&ctx->map_mutex);
> + mutex_init(&ctx->map_create_mutex);
> + atomic_set(&ctx->active_maps, 0);
> + atomic_set(&ctx->all_maps, 0);
> + init_waitqueue_head(&ctx->maps_wq);
> +
> + ret = file->f_op->init_dma_buf_io_ctx(file, ctx);
> + if (ret) {
> + kfree(ctx);
> + dma_buf_put(dmabuf);
> + return ret;
> + }
> +
> + if (WARN_ON_ONCE(!ctx->dev_ops ||
> + !ctx->dev_ops->map ||
> + !ctx->dev_ops->unmap ||
> + !ctx->dev_ops->release))
> + return -EINVAL;
> +
> + *out_ctx = ctx;
> + return 0;
> +}
> +
> +void dma_buf_io_detach(struct dma_buf_io_ctx *ctx)
> +{
> + guard(mutex)(&ctx->map_create_mutex);
> +
> + dma_buf_io_kill_maps(ctx, true);
> + dma_buf_io_wait_maps(ctx);
> +}
> +EXPORT_SYMBOL_NS_GPL(dma_buf_io_detach, "DMA_BUF");
> diff --git a/include/linux/dma-buf-io.h b/include/linux/dma-buf-io.h
> new file mode 100644
> index 000000000000..5ea92fc78582
> --- /dev/null
> +++ b/include/linux/dma-buf-io.h
> @@ -0,0 +1,113 @@
> +/* 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 work_struct release_work;
> + struct dma_buf_io_ctx *ctx;
> +};
> +
> +struct dma_buf_io_ctx {
> + struct dma_buf_io_map __rcu *map;
> + struct dma_buf *dmabuf;
> + enum dma_data_direction dir;
> +
> + /* synchronises map reassignment */
> + struct mutex map_mutex;
> + struct mutex map_create_mutex;
> + /* maps that may still be in use. */
> + atomic_t active_maps;
> + atomic_t all_maps;
> + struct wait_queue_head maps_wq;
> + bool maps_killed;
> +
> + 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;
> +}
> +
> +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);
> +}
> +
> +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 */
> --
> 2.54.0
>
More information about the Linux-nvme
mailing list