Add an optional feature to open/accept directly into io_uring's fixed
file table bypassing the normal file table. Same behaviour if as the
snippet below, but in one operation:
sqe = io_uring_[open|accept]_prep();
io_uring_submit(sqe);
// ... once we get a CQE back
io_uring_register_files_update(uring_idx, (fd = cqe->res));
close((fd = cqe->res));
The idea is old, and was brough up and implemented a year ago by
Josh Triplett, though haven't sought the light.
The behaviour is controlled by setting sqe->file_index, where 0 implies
the old behaviour using normal file tables. If non-zero value is
specified, then it will behave as described and place the file into a
fixed file slot sqe->file_index - 1. A file table should be already
created, the slot should be valid and empty, otherwise the operation
will fail.
note: IOSQE_FIXED_FILE can't be used as a mode switch, because accept
takes a file, and it already uses the flag with a different meaning.
v2, since RFC:
- added attribution
- updated descriptions
- rebased
v3:
- EBADF if slot is already used (Josh Triplett)
- alias index with splice_fd_in (Josh Triplett)
- fix a bound check bug
v4:
- separate u32 fields to internally store indexes (Jens, Josh)
Pavel Begunkov (4):
net: add accept helper not installing fd
io_uring: openat directly into fixed fd table
io_uring: hand code io_accept() fd installing
io_uring: accept directly into fixed file table
fs/io_uring.c | 115 +++++++++++++++++++++++++++++-----
include/linux/socket.h | 3 +
include/uapi/linux/io_uring.h | 5 +-
net/socket.c | 71 +++++++++++----------
4 files changed, 143 insertions(+), 51 deletions(-)
--
2.32.0
As done with open opcodes, allow accept to skip installing fd into
processes' file tables and put it directly into io_uring's fixed file
table. Same restrictions and design as for open.
Suggested-by: Josh Triplett <[email protected]>
Signed-off-by: Pavel Begunkov <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
---
fs/io_uring.c | 24 ++++++++++++++++++------
1 file changed, 18 insertions(+), 6 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a3b1a50e2537..95fd7dc7cbe6 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -514,6 +514,7 @@ struct io_accept {
struct sockaddr __user *addr;
int __user *addr_len;
int flags;
+ u32 file_slot;
unsigned long nofile;
};
@@ -4802,7 +4803,7 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
- if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->splice_fd_in)
+ if (sqe->ioprio || sqe->len || sqe->buf_index)
return -EINVAL;
accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -4810,6 +4811,10 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
accept->flags = READ_ONCE(sqe->accept_flags);
accept->nofile = rlimit(RLIMIT_NOFILE);
+ accept->file_slot = READ_ONCE(sqe->file_index);
+ if (accept->file_slot && ((req->open.how.flags & O_CLOEXEC) ||
+ (accept->flags & SOCK_CLOEXEC)))
+ return -EINVAL;
if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
return -EINVAL;
if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK))
@@ -4822,28 +4827,35 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags)
struct io_accept *accept = &req->accept;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0;
+ bool fixed = !!accept->file_slot;
struct file *file;
int ret, fd;
if (req->file->f_flags & O_NONBLOCK)
req->flags |= REQ_F_NOWAIT;
- fd = __get_unused_fd_flags(accept->flags, accept->nofile);
- if (unlikely(fd < 0))
- return fd;
-
+ if (!fixed) {
+ fd = __get_unused_fd_flags(accept->flags, accept->nofile);
+ if (unlikely(fd < 0))
+ return fd;
+ }
file = do_accept(req->file, file_flags, accept->addr, accept->addr_len,
accept->flags);
if (IS_ERR(file)) {
+ if (!fixed)
+ put_unused_fd(fd);
ret = PTR_ERR(file);
if (ret == -EAGAIN && force_nonblock)
return -EAGAIN;
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
- } else {
+ } else if (!fixed) {
fd_install(fd, file);
ret = fd;
+ } else {
+ ret = io_install_fixed_file(req, file, issue_flags,
+ accept->file_slot - 1);
}
__io_req_complete(req, issue_flags, ret, 0);
return 0;
--
2.32.0
On 8/25/21 5:25 AM, Pavel Begunkov wrote:
> Add an optional feature to open/accept directly into io_uring's fixed
> file table bypassing the normal file table. Same behaviour if as the
> snippet below, but in one operation:
>
> sqe = io_uring_[open|accept]_prep();
> io_uring_submit(sqe);
> // ... once we get a CQE back
> io_uring_register_files_update(uring_idx, (fd = cqe->res));
> close((fd = cqe->res));
>
> The idea is old, and was brough up and implemented a year ago by
> Josh Triplett, though haven't sought the light.
>
> The behaviour is controlled by setting sqe->file_index, where 0 implies
> the old behaviour using normal file tables. If non-zero value is
> specified, then it will behave as described and place the file into a
> fixed file slot sqe->file_index - 1. A file table should be already
> created, the slot should be valid and empty, otherwise the operation
> will fail.
>
> note: IOSQE_FIXED_FILE can't be used as a mode switch, because accept
> takes a file, and it already uses the flag with a different meaning.
Updated the tree and picked you davem's ack as well.
--
Jens Axboe