io_uring: fix up O_NONBLOCK handling for sockets
We've got two issues with the non-regular file handling for non-blocking IO: 1) We don't want to re-do a short read in full for a non-regular file, as we can't just read the data again. 2) For non-regular files that don't support non-blocking IO attempts, we need to punt to async context even if the file is opened as non-blocking. Otherwise the caller always gets -EAGAIN. Add two new request flags to handle these cases. One is just a cache of the inode S_ISREG() status, the other tells io_uring that we always need to punt this request to async context, even if REQ_F_NOWAIT is set. Cc: stable@vger.kernel.org Reported-by: Hrvoje Zeba <zeba.hrvoje@gmail.com> Tested-by: Hrvoje Zeba <zeba.hrvoje@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
parent
6333ff6e5a
commit
491381ce07
|
@ -322,6 +322,8 @@ struct io_kiocb {
|
|||
#define REQ_F_FAIL_LINK 256 /* fail rest of links */
|
||||
#define REQ_F_SHADOW_DRAIN 512 /* link-drain shadow req */
|
||||
#define REQ_F_TIMEOUT 1024 /* timeout request */
|
||||
#define REQ_F_ISREG 2048 /* regular file */
|
||||
#define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */
|
||||
u64 user_data;
|
||||
u32 result;
|
||||
u32 sequence;
|
||||
|
@ -914,26 +916,26 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
|
|||
return ret;
|
||||
}
|
||||
|
||||
static void kiocb_end_write(struct kiocb *kiocb)
|
||||
static void kiocb_end_write(struct io_kiocb *req)
|
||||
{
|
||||
if (kiocb->ki_flags & IOCB_WRITE) {
|
||||
struct inode *inode = file_inode(kiocb->ki_filp);
|
||||
/*
|
||||
* Tell lockdep we inherited freeze protection from submission
|
||||
* thread.
|
||||
*/
|
||||
if (req->flags & REQ_F_ISREG) {
|
||||
struct inode *inode = file_inode(req->file);
|
||||
|
||||
/*
|
||||
* Tell lockdep we inherited freeze protection from submission
|
||||
* thread.
|
||||
*/
|
||||
if (S_ISREG(inode->i_mode))
|
||||
__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
|
||||
file_end_write(kiocb->ki_filp);
|
||||
__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
|
||||
}
|
||||
file_end_write(req->file);
|
||||
}
|
||||
|
||||
static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
|
||||
{
|
||||
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
|
||||
|
||||
kiocb_end_write(kiocb);
|
||||
if (kiocb->ki_flags & IOCB_WRITE)
|
||||
kiocb_end_write(req);
|
||||
|
||||
if ((req->flags & REQ_F_LINK) && res != req->result)
|
||||
req->flags |= REQ_F_FAIL_LINK;
|
||||
|
@ -945,7 +947,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
|
|||
{
|
||||
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
|
||||
|
||||
kiocb_end_write(kiocb);
|
||||
if (kiocb->ki_flags & IOCB_WRITE)
|
||||
kiocb_end_write(req);
|
||||
|
||||
if ((req->flags & REQ_F_LINK) && res != req->result)
|
||||
req->flags |= REQ_F_FAIL_LINK;
|
||||
|
@ -1059,8 +1062,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
|
|||
if (!req->file)
|
||||
return -EBADF;
|
||||
|
||||
if (force_nonblock && !io_file_supports_async(req->file))
|
||||
force_nonblock = false;
|
||||
if (S_ISREG(file_inode(req->file)->i_mode))
|
||||
req->flags |= REQ_F_ISREG;
|
||||
|
||||
/*
|
||||
* If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
|
||||
* we know to async punt it even if it was opened O_NONBLOCK
|
||||
*/
|
||||
if (force_nonblock && !io_file_supports_async(req->file)) {
|
||||
req->flags |= REQ_F_MUST_PUNT;
|
||||
return -EAGAIN;
|
||||
}
|
||||
|
||||
kiocb->ki_pos = READ_ONCE(sqe->off);
|
||||
kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
|
||||
|
@ -1081,7 +1093,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
|
|||
return ret;
|
||||
|
||||
/* don't allow async punt if RWF_NOWAIT was requested */
|
||||
if (kiocb->ki_flags & IOCB_NOWAIT)
|
||||
if ((kiocb->ki_flags & IOCB_NOWAIT) ||
|
||||
(req->file->f_flags & O_NONBLOCK))
|
||||
req->flags |= REQ_F_NOWAIT;
|
||||
|
||||
if (force_nonblock)
|
||||
|
@ -1382,7 +1395,9 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
|
|||
* need async punt anyway, so it's more efficient to do it
|
||||
* here.
|
||||
*/
|
||||
if (force_nonblock && ret2 > 0 && ret2 < read_size)
|
||||
if (force_nonblock && !(req->flags & REQ_F_NOWAIT) &&
|
||||
(req->flags & REQ_F_ISREG) &&
|
||||
ret2 > 0 && ret2 < read_size)
|
||||
ret2 = -EAGAIN;
|
||||
/* Catch -EAGAIN return for forced non-blocking submission */
|
||||
if (!force_nonblock || ret2 != -EAGAIN) {
|
||||
|
@ -1447,7 +1462,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
|
|||
* released so that it doesn't complain about the held lock when
|
||||
* we return to userspace.
|
||||
*/
|
||||
if (S_ISREG(file_inode(file)->i_mode)) {
|
||||
if (req->flags & REQ_F_ISREG) {
|
||||
__sb_start_write(file_inode(file)->i_sb,
|
||||
SB_FREEZE_WRITE, true);
|
||||
__sb_writers_release(file_inode(file)->i_sb,
|
||||
|
@ -2282,7 +2297,13 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
|
|||
int ret;
|
||||
|
||||
ret = __io_submit_sqe(ctx, req, s, force_nonblock);
|
||||
if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
|
||||
|
||||
/*
|
||||
* We async punt it if the file wasn't marked NOWAIT, or if the file
|
||||
* doesn't support non-blocking read/write attempts
|
||||
*/
|
||||
if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
|
||||
(req->flags & REQ_F_MUST_PUNT))) {
|
||||
struct io_uring_sqe *sqe_copy;
|
||||
|
||||
sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL);
|
||||
|
|
Loading…
Reference in New Issue