On Wed, Oct 07, 2026 at 02:42:44AM +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 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. >
Full disclosure Pavel incorporated some of my ideas wrt to locking cleanup which I shared off the list. So I can't in fairness give an RB but: Acked-by: Matthew Brost <[email protected]> For the series - I can give this and I have pulled to code + have Xe nvme + IGT setup showing this working: Tested-by: Matthew Brost <[email protected]> > Signed-off-by: Pavel Begunkov <[email protected]> > --- > drivers/dma-buf/Makefile | 2 +- > drivers/dma-buf/dma-buf-io.c | 183 +++++++++++++++++++++++++++++++++++ > include/linux/dma-buf-io.h | 105 ++++++++++++++++++++ > include/linux/fs.h | 2 + > 4 files changed, 291 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..9ba9c17f900a > --- /dev/null > +++ b/drivers/dma-buf/dma-buf-io.c > @@ -0,0 +1,183 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +/* > + * Common infrastructure for supporing dma-buf in the I/O path. > + * > + * Copyright (C) 2026 Pavel Begunkov <[email protected]> > + */ > +#include <linux/dma-buf-io.h> > +#include <linux/dma-resv.h> > + > +static void dma_buf_io_map_release(struct dma_buf_io_map *map) > +{ > + struct dma_buf_io_ctx *ctx = map->ctx; > + > + dma_resv_assert_held(ctx->dmabuf->resv); > + > + percpu_ref_exit(&map->refs); > + ctx->dev_ops->unmap(ctx, map); > +} > + > +static void dma_buf_io_map_refs_cb(struct percpu_ref *ref) > +{ > + struct dma_buf_io_map *map = container_of(ref, struct dma_buf_io_map, > refs); > + > + complete(&map->drained); > +} > + > +static void dma_buf_io_kill_map(struct dma_buf_io_ctx *ctx) > +{ > + struct dma_buf_io_map *map; > + > + dma_resv_assert_held(ctx->dmabuf->resv); > + > + map = rcu_dereference_protected(ctx->map, > + dma_resv_held(ctx->dmabuf->resv)); > + if (!map) > + return; > + > + rcu_assign_pointer(ctx->map, NULL); > + percpu_ref_kill(&map->refs); > + /* make sure the map is not visible via ctx->map */ > + synchronize_rcu_expedited(); > + wait_for_completion(&map->drained); > + dma_buf_io_map_release(map); > +} > + > +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_cb, 0, > GFP_KERNEL); > + if (ret) > + return ret; > + init_completion(&map->drained); > + map->min_seg_shift = seg_shift; > + map->ctx = ctx; > + return 0; > +} > +EXPORT_SYMBOL_NS_GPL(dma_buf_io_init_map, "DMA_BUF"); > + > +static 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; > + > + dma_resv_assert_held(dmabuf->resv); > + > + if (ctx->is_dead) > + return ERR_PTR(-ENOENT); > + > + map = __dma_buf_io_get_map(ctx); > + if (map) > + return map; > + > + map = ctx->dev_ops->map(ctx); > + if (IS_ERR(map)) > + return map; > + > + if (WARN_ON_ONCE(!map->min_seg_shift)) > + return ERR_PTR(-EFAULT); > + > + ret = dma_resv_wait_timeout(dmabuf->resv, DMA_RESV_USAGE_KERNEL, > + true, MAX_SCHEDULE_TIMEOUT); > + if (ret <= 0) { > + if (!ret) > + ret = -EAGAIN; > + dma_buf_io_map_release(map); > + return ERR_PTR(ret); > + } > + > + /* get a reference for the caller */ > + percpu_ref_get(&map->refs); > + rcu_assign_pointer(ctx->map, map); > + return map; > +} > + > +struct dma_buf_io_map *dma_buf_io_create_map(struct dma_buf_io_ctx *ctx) > +{ > + struct dma_buf_io_map *map; > + int ret; > + > + ret = dma_resv_lock_interruptible(ctx->dmabuf->resv, NULL); > + if (ret) > + return ERR_PTR(ret); > + > + map = __dma_buf_io_create_map(ctx); > + dma_resv_unlock(ctx->dmabuf->resv); > + return map; > +} > + > +static void dma_buf_io_ctx_shutdown(struct dma_buf_io_ctx *ctx) > +{ > + dma_resv_lock(ctx->dmabuf->resv, NULL); > + ctx->is_dead = true; > + dma_buf_io_kill_map(ctx); > + dma_resv_unlock(ctx->dmabuf->resv); > +} > + > +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 = kzalloc_obj(*ctx); > + if (!ctx) > + return -ENOMEM; > + ctx->dir = dir; > + ctx->dmabuf = dmabuf; > + get_dma_buf(dmabuf); > + > + 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_ctx_release(struct dma_buf_io_ctx *ctx) > +{ > + dma_buf_io_ctx_shutdown(ctx); > + > + if (WARN_ON_ONCE(rcu_dereference_protected(ctx->map, true))) > + return; > + > + ctx->dev_ops->release(ctx); > + dma_buf_put(ctx->dmabuf); > + kfree(ctx); > +} > + > +void dma_buf_io_invalidate_mappings(struct dma_buf_io_ctx *ctx) > +{ > + dma_buf_io_kill_map(ctx); > +} > +EXPORT_SYMBOL_NS_GPL(dma_buf_io_invalidate_mappings, "DMA_BUF"); > + > +void dma_buf_io_detach(struct dma_buf_io_ctx *ctx) > +{ > + dma_buf_io_ctx_shutdown(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..8ac338df51ff > --- /dev/null > +++ b/include/linux/dma-buf-io.h > @@ -0,0 +1,105 @@ > +/* 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; > +} > + > +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 >
