[RFC 11/12] io_uring/rsrc: implement dmabuf regbuf import
Pavel Begunkov
asml.silence at gmail.com
Fri Jun 27 08:10:38 PDT 2025
Allow importing dmabuf backed registered buffers. It's an opt-in feature
for requests and they need to pass a flag allowing it. Furthermore,
the import will fail if the request's file doesn't match the file for
which the buffer for registered. This way, it's also limited to files
that support the feature by implementing the corresponding file op.
Suggested-by: David Wei <dw at davidwei.uk>
Suggested-by: Vishal Verma <vishal1.verma at intel.com>
Signed-off-by: Pavel Begunkov <asml.silence at gmail.com>
---
io_uring/rsrc.c | 53 ++++++++++++++++++++++++++++++++++++++++++-------
io_uring/rsrc.h | 16 ++++++++++++++-
2 files changed, 61 insertions(+), 8 deletions(-)
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index f44aa2670bc5..11107491145c 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1196,9 +1196,44 @@ static int io_import_kbuf(int ddir, struct iov_iter *iter,
return 0;
}
-static int io_import_fixed(int ddir, struct iov_iter *iter,
+static int io_import_dmabuf(struct io_kiocb *req,
+ int ddir, struct iov_iter *iter,
struct io_mapped_ubuf *imu,
- u64 buf_addr, size_t len)
+ size_t len, size_t offset)
+{
+ struct io_regbuf_dma *db = imu->priv;
+ struct dmavec *dmavec = db->dmav;
+ int i = 0, start_idx, nr_segs;
+ ssize_t len_left;
+
+ if (req->file != db->target_file)
+ return -EBADF;
+ if (!len)
+ return -EFAULT;
+
+ while (offset >= dmavec[i].len) {
+ offset -= dmavec[i].len;
+ i++;
+ }
+ start_idx = i;
+
+ len_left = len;
+ while (len_left > 0) {
+ len_left -= dmavec[i].len;
+ i++;
+ }
+
+ nr_segs = i - start_idx;
+ iov_iter_dma(iter, ddir, dmavec + start_idx, nr_segs, len);
+ iter->iov_offset = offset;
+ return 0;
+}
+
+static int io_import_fixed(struct io_kiocb *req,
+ int ddir, struct iov_iter *iter,
+ struct io_mapped_ubuf *imu,
+ u64 buf_addr, size_t len,
+ unsigned import_flags)
{
const struct bio_vec *bvec;
size_t folio_mask;
@@ -1214,8 +1249,11 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
offset = buf_addr - imu->ubuf;
- if (imu->flags & IO_IMU_F_DMA)
- return -EOPNOTSUPP;
+ if (imu->flags & IO_IMU_F_DMA) {
+ if (!(import_flags & IO_REGBUF_IMPORT_ALLOW_DMA))
+ return -EFAULT;
+ return io_import_dmabuf(req, ddir, iter, imu, len, offset);
+ }
if (imu->flags & IO_IMU_F_KBUF)
return io_import_kbuf(ddir, iter, imu, len, offset);
@@ -1269,16 +1307,17 @@ inline struct io_rsrc_node *io_find_buf_node(struct io_kiocb *req,
return NULL;
}
-int io_import_reg_buf(struct io_kiocb *req, struct iov_iter *iter,
+int __io_import_reg_buf(struct io_kiocb *req, struct iov_iter *iter,
u64 buf_addr, size_t len, int ddir,
- unsigned issue_flags)
+ unsigned issue_flags, unsigned import_flags)
{
struct io_rsrc_node *node;
node = io_find_buf_node(req, issue_flags);
if (!node)
return -EFAULT;
- return io_import_fixed(ddir, iter, node->buf, buf_addr, len);
+ return io_import_fixed(req, ddir, iter, node->buf, buf_addr, len,
+ import_flags);
}
/* Lock two rings at once. The rings must be different! */
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index f567ad82b76c..64b7444b7899 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -33,6 +33,10 @@ enum {
IO_IMU_F_DMA = 2,
};
+enum {
+ IO_REGBUF_IMPORT_ALLOW_DMA = 1,
+};
+
struct io_mapped_ubuf {
u64 ubuf;
unsigned int len;
@@ -65,9 +69,19 @@ int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr);
struct io_rsrc_node *io_find_buf_node(struct io_kiocb *req,
unsigned issue_flags);
+int __io_import_reg_buf(struct io_kiocb *req, struct iov_iter *iter,
+ u64 buf_addr, size_t len, int ddir,
+ unsigned issue_flags, unsigned import_flags);
+
+static inline
int io_import_reg_buf(struct io_kiocb *req, struct iov_iter *iter,
u64 buf_addr, size_t len, int ddir,
- unsigned issue_flags);
+ unsigned issue_flags)
+{
+ return __io_import_reg_buf(req, iter, buf_addr, len, ddir,
+ issue_flags, 0);
+}
+
int io_import_reg_vec(int ddir, struct iov_iter *iter,
struct io_kiocb *req, struct iou_vec *vec,
unsigned nr_iovs, unsigned issue_flags);
--
2.49.0
More information about the Linux-nvme
mailing list