commit bcb0fda3c2da9fe4721d3e73d80e778c038e7d27 upstream.
The IOPOLL path posts CQEs when the io_kiocb is marked as completed, so it cannot rely on the usual retry that non-IOPOLL requests do for read/write requests.
If -EAGAIN is received and the request should be retried, go through the normal completion path and let the normal flush logic catch it and reissue it, like what is done for !IOPOLL reads or writes.
Fixes: d803d123948f ("io_uring/rw: handle -EAGAIN retry at IO completion time") Reported-by: John Garry john.g.garry@oracle.com Link: https://lore.kernel.org/io-uring/2b43ccfa-644d-4a09-8f8f-39ad71810f41@oracle... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sumanth Gavini sumanth.gavini@yahoo.com --- io_uring/rw.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/io_uring/rw.c b/io_uring/rw.c index 4ff3442ac2ee..6a84c4a39ce9 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -326,11 +326,10 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) if (kiocb->ki_flags & IOCB_WRITE) io_req_end_write(req); if (unlikely(res != req->cqe.res)) { - if (res == -EAGAIN && io_rw_should_reissue(req)) { + if (res == -EAGAIN && io_rw_should_reissue(req)) req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; - return; - } - req->cqe.res = res; + else + req->cqe.res = res; }
/* order with io_iopoll_complete() checking ->iopoll_completed */
Hi,
Thanks for your patch.
FYI: kernel test robot notices the stable kernel rule is not satisfied.
The check is based on https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html#opti...
Rule: The upstream commit ID must be specified with a separate line above the commit text. Subject: [PATCH 6.6] io_uring/rw: ensure reissue path is correctly handled for IOPOLL Link: https://lore.kernel.org/stable/20250809182636.209767-1-sumanth.gavini%40yaho...
Please ignore this mail if the patch is not relevant for upstream.
commit bcb0fda3c2da9fe4721d3e73d80e778c038e7d27 upstream.
The IOPOLL path posts CQEs when the io_kiocb is marked as completed, so it cannot rely on the usual retry that non-IOPOLL requests do for read/write requests.
If -EAGAIN is received and the request should be retried, go through the normal completion path and let the normal flush logic catch it and reissue it, like what is done for !IOPOLL reads or writes.
Fixes: d803d123948f ("io_uring/rw: handle -EAGAIN retry at IO completion time") Reported-by: John Garry john.g.garry@oracle.com Link: https://lore.kernel.org/io-uring/2b43ccfa-644d-4a09-8f8f-39ad71810f41@oracle... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sumanth Gavini sumanth.gavini@yahoo.com --- Changes in v2: - Removed the extra space before commit-id in message, No codes changes - Link to v1:https://lore.kernel.org/all/20250809182636.209767-1-sumanth.gavini@yahoo.com...
--- io_uring/rw.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/io_uring/rw.c b/io_uring/rw.c index 4ff3442ac2ee..6a84c4a39ce9 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -326,11 +326,10 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) if (kiocb->ki_flags & IOCB_WRITE) io_req_end_write(req); if (unlikely(res != req->cqe.res)) { - if (res == -EAGAIN && io_rw_should_reissue(req)) { + if (res == -EAGAIN && io_rw_should_reissue(req)) req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; - return; - } - req->cqe.res = res; + else + req->cqe.res = res; }
/* order with io_iopoll_complete() checking ->iopoll_completed */
[ Sasha's backport helper bot ]
Hi,
✅ All tests passed successfully. No issues detected. No action required from the submitter.
The upstream commit SHA1 provided is correct: bcb0fda3c2da9fe4721d3e73d80e778c038e7d27
WARNING: Author mismatch between patch and upstream commit: Backport author: Sumanth Gavini sumanth.gavini@yahoo.com Commit author: Jens Axboe axboe@kernel.dk
Status in newer kernel trees: 6.15.y | Present (exact SHA1) 6.12.y | Not found
Note: The patch differs from the upstream commit: --- 1: bcb0fda3c2da ! 1: 941165821178 io_uring/rw: ensure reissue path is correctly handled for IOPOLL @@ ## Metadata ## -Author: Jens Axboe axboe@kernel.dk +Author: Sumanth Gavini sumanth.gavini@yahoo.com
## Commit message ## io_uring/rw: ensure reissue path is correctly handled for IOPOLL
+ commit bcb0fda3c2da9fe4721d3e73d80e778c038e7d27 upstream. + The IOPOLL path posts CQEs when the io_kiocb is marked as completed, so it cannot rely on the usual retry that non-IOPOLL requests do for read/write requests. @@ Commit message Reported-by: John Garry john.g.garry@oracle.com Link: https://lore.kernel.org/io-uring/2b43ccfa-644d-4a09-8f8f-39ad71810f41@oracle... Signed-off-by: Jens Axboe axboe@kernel.dk + Signed-off-by: Sumanth Gavini sumanth.gavini@yahoo.com
## io_uring/rw.c ## @@ io_uring/rw.c: static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) @@ io_uring/rw.c: static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) if (unlikely(res != req->cqe.res)) { - if (res == -EAGAIN && io_rw_should_reissue(req)) { + if (res == -EAGAIN && io_rw_should_reissue(req)) - req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE; + req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; - return; - } - req->cqe.res = res;
---
Results of testing on various branches:
| Branch | Patch Apply | Build Test | |---------------------------|-------------|------------| | origin/linux-6.6.y | Success | Success |
On Sat, Aug 09, 2025 at 03:54:18PM -0500, Sumanth Gavini wrote:
commit bcb0fda3c2da9fe4721d3e73d80e778c038e7d27 upstream.
The IOPOLL path posts CQEs when the io_kiocb is marked as completed, so it cannot rely on the usual retry that non-IOPOLL requests do for read/write requests.
If -EAGAIN is received and the request should be retried, go through the normal completion path and let the normal flush logic catch it and reissue it, like what is done for !IOPOLL reads or writes.
Fixes: d803d123948f ("io_uring/rw: handle -EAGAIN retry at IO completion time") Reported-by: John Garry john.g.garry@oracle.com Link: https://lore.kernel.org/io-uring/2b43ccfa-644d-4a09-8f8f-39ad71810f41@oracle... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sumanth Gavini sumanth.gavini@yahoo.com
Changes in v2:
- Removed the extra space before commit-id in message, No codes changes
- Link to v1:https://lore.kernel.org/all/20250809182636.209767-1-sumanth.gavini@yahoo.com...
We can not take patches ONLY for older kernel trees and not newer ones, otherwise you will have a regression when moving to a newer one. I've dropped this now, please submit for all relevant trees.
thanks,
greg k-h
[ Sasha's backport helper bot ]
Hi,
✅ All tests passed successfully. No issues detected. No action required from the submitter.
Found matching upstream commit: bcb0fda3c2da9fe4721d3e73d80e778c038e7d27
WARNING: Author mismatch between patch and found commit: Backport author: Sumanth Gavini sumanth.gavini@yahoo.com Commit author: Jens Axboe axboe@kernel.dk
Status in newer kernel trees: 6.15.y | Present (exact SHA1) 6.12.y | Not found
Note: The patch differs from the upstream commit: --- 1: bcb0fda3c2da ! 1: 9067ba27246b io_uring/rw: ensure reissue path is correctly handled for IOPOLL @@ ## Metadata ## -Author: Jens Axboe axboe@kernel.dk +Author: Sumanth Gavini sumanth.gavini@yahoo.com
## Commit message ## io_uring/rw: ensure reissue path is correctly handled for IOPOLL
+ commit bcb0fda3c2da9fe4721d3e73d80e778c038e7d27 upstream. + The IOPOLL path posts CQEs when the io_kiocb is marked as completed, so it cannot rely on the usual retry that non-IOPOLL requests do for read/write requests. @@ Commit message Reported-by: John Garry john.g.garry@oracle.com Link: https://lore.kernel.org/io-uring/2b43ccfa-644d-4a09-8f8f-39ad71810f41@oracle... Signed-off-by: Jens Axboe axboe@kernel.dk + Signed-off-by: Sumanth Gavini sumanth.gavini@yahoo.com
## io_uring/rw.c ## @@ io_uring/rw.c: static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) @@ io_uring/rw.c: static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) if (unlikely(res != req->cqe.res)) { - if (res == -EAGAIN && io_rw_should_reissue(req)) { + if (res == -EAGAIN && io_rw_should_reissue(req)) - req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE; + req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; - return; - } - req->cqe.res = res;
---
Results of testing on various branches:
| Branch | Patch Apply | Build Test | |---------------------------|-------------|------------| | origin/linux-6.6.y | Success | Success |
linux-stable-mirror@lists.linaro.org
-
Greg KH -
kernel test robot -
Sasha Levin -
Sumanth Gavini