Currently, creating an io_uring with IORING_SETUP_IOPOLL requires all
requests issued to it to support iopoll. This prevents, for example,
using ublk zero-copy together with IORING_SETUP_IOPOLL, as ublk
zero-copy buffer registrations are performed using a uring_cmd. There's
no technical reason why these non-iopoll uring_cmds can't be supported.
They will either complete synchronously or via an external mechanism
that calls io_uring_cmd_done(), so they don't need to be polled.
Allow uring_cmd requests to be issued to IORING_SETUP_IOPOLL io_urings
even if their files don't implement ->uring_cmd_iopoll(). For these
uring_cmd requests, skip initializing struct io_kiocb's iopoll fields,
don't insert the request into iopoll_list, and take the
io_req_complete_defer() or io_req_task_work_add() path in
__io_uring_cmd_done() instead of setting the iopoll_completed flag. Also
allow io_uring_cmd_mark_cancelable() to be called on these uring_cmds.
Assert that io_uring_cmd_mark_cancelable() is only called on
non-IORING_SETUP_IOPOLL io_urings or uring_cmds to files that don't
implement ->uring_cmd_iopoll().
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
---
io_uring/io_uring.c | 4 +++-
io_uring/uring_cmd.c | 11 +++++------
2 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index c45af82dda3d..4e68a5168894 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1417,11 +1417,13 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
if (ret == IOU_ISSUE_SKIP_COMPLETE) {
ret = 0;
/* If the op doesn't have a file, we're not polling for it */
- if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue)
+ if ((req->ctx->flags & IORING_SETUP_IOPOLL) &&
+ def->iopoll_queue && (!io_is_uring_cmd(req) ||
+ req->file->f_op->uring_cmd_iopoll))
io_iopoll_req_issued(req, issue_flags);
}
return ret;
}
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index ee7b49f47cb5..8df52e8f1c1b 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -108,12 +108,12 @@ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
* Doing cancelations on IOPOLL requests are not supported. Both
* because they can't get canceled in the block stack, but also
* because iopoll completion data overlaps with the hash_node used
* for tracking.
*/
- if (ctx->flags & IORING_SETUP_IOPOLL)
- return;
+ WARN_ON_ONCE(ctx->flags & IORING_SETUP_IOPOLL &&
+ req->file->f_op->uring_cmd_iopoll);
if (!(cmd->flags & IORING_URING_CMD_CANCELABLE)) {
cmd->flags |= IORING_URING_CMD_CANCELABLE;
io_ring_submit_lock(ctx, issue_flags);
hlist_add_head(&req->hash_node, &ctx->cancelable_uring_cmd);
@@ -165,11 +165,12 @@ void __io_uring_cmd_done(struct io_uring_cmd *ioucmd, s32 ret, u64 res2,
if (req->ctx->flags & IORING_SETUP_CQE_MIXED)
req->cqe.flags |= IORING_CQE_F_32;
io_req_set_cqe32_extra(req, res2, 0);
}
io_req_uring_cleanup(req, issue_flags);
- if (req->ctx->flags & IORING_SETUP_IOPOLL) {
+ if (req->ctx->flags & IORING_SETUP_IOPOLL &&
+ req->file->f_op->uring_cmd_iopoll) {
/* order with io_iopoll_req_issued() checking ->iopoll_complete */
smp_store_release(&req->iopoll_completed, 1);
} else if (issue_flags & IO_URING_F_COMPLETE_DEFER) {
if (WARN_ON_ONCE(issue_flags & IO_URING_F_UNLOCKED))
return;
@@ -255,13 +256,11 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
issue_flags |= IO_URING_F_SQE128;
if (ctx->flags & (IORING_SETUP_CQE32 | IORING_SETUP_CQE_MIXED))
issue_flags |= IO_URING_F_CQE32;
if (io_is_compat(ctx))
issue_flags |= IO_URING_F_COMPAT;
- if (ctx->flags & IORING_SETUP_IOPOLL) {
- if (!file->f_op->uring_cmd_iopoll)
- return -EOPNOTSUPP;
+ if (ctx->flags & IORING_SETUP_IOPOLL && file->f_op->uring_cmd_iopoll) {
issue_flags |= IO_URING_F_IOPOLL;
req->iopoll_completed = 0;
if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) {
/* make sure every req only blocks once */
req->flags &= ~REQ_F_IOPOLL_STATE;
--
2.45.2On Thu, Feb 12, 2026 at 7:21 PM Caleb Sander Mateos
<csander@purestorage.com> wrote:
>
> Currently, creating an io_uring with IORING_SETUP_IOPOLL requires all
> requests issued to it to support iopoll. This prevents, for example,
> using ublk zero-copy together with IORING_SETUP_IOPOLL, as ublk
> zero-copy buffer registrations are performed using a uring_cmd. There's
> no technical reason why these non-iopoll uring_cmds can't be supported.
> They will either complete synchronously or via an external mechanism
> that calls io_uring_cmd_done(), so they don't need to be polled.
>
> Allow uring_cmd requests to be issued to IORING_SETUP_IOPOLL io_urings
> even if their files don't implement ->uring_cmd_iopoll(). For these
> uring_cmd requests, skip initializing struct io_kiocb's iopoll fields,
> don't insert the request into iopoll_list, and take the
> io_req_complete_defer() or io_req_task_work_add() path in
> __io_uring_cmd_done() instead of setting the iopoll_completed flag. Also
> allow io_uring_cmd_mark_cancelable() to be called on these uring_cmds.
> Assert that io_uring_cmd_mark_cancelable() is only called on
> non-IORING_SETUP_IOPOLL io_urings or uring_cmds to files that don't
> implement ->uring_cmd_iopoll().
>
> Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
> ---
> io_uring/io_uring.c | 4 +++-
> io_uring/uring_cmd.c | 11 +++++------
> 2 files changed, 8 insertions(+), 7 deletions(-)
>
> diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
> index c45af82dda3d..4e68a5168894 100644
> --- a/io_uring/io_uring.c
> +++ b/io_uring/io_uring.c
> @@ -1417,11 +1417,13 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
>
> if (ret == IOU_ISSUE_SKIP_COMPLETE) {
> ret = 0;
>
> /* If the op doesn't have a file, we're not polling for it */
> - if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue)
> + if ((req->ctx->flags & IORING_SETUP_IOPOLL) &&
> + def->iopoll_queue && (!io_is_uring_cmd(req) ||
> + req->file->f_op->uring_cmd_iopoll))
> io_iopoll_req_issued(req, issue_flags);
> }
> return ret;
> }
>
> diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
> index ee7b49f47cb5..8df52e8f1c1b 100644
> --- a/io_uring/uring_cmd.c
> +++ b/io_uring/uring_cmd.c
> @@ -108,12 +108,12 @@ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
> * Doing cancelations on IOPOLL requests are not supported. Both
> * because they can't get canceled in the block stack, but also
> * because iopoll completion data overlaps with the hash_node used
> * for tracking.
> */
> - if (ctx->flags & IORING_SETUP_IOPOLL)
> - return;
> + WARN_ON_ONCE(ctx->flags & IORING_SETUP_IOPOLL &&
> + req->file->f_op->uring_cmd_iopoll);
>
> if (!(cmd->flags & IORING_URING_CMD_CANCELABLE)) {
> cmd->flags |= IORING_URING_CMD_CANCELABLE;
> io_ring_submit_lock(ctx, issue_flags);
> hlist_add_head(&req->hash_node, &ctx->cancelable_uring_cmd);
> @@ -165,11 +165,12 @@ void __io_uring_cmd_done(struct io_uring_cmd *ioucmd, s32 ret, u64 res2,
> if (req->ctx->flags & IORING_SETUP_CQE_MIXED)
> req->cqe.flags |= IORING_CQE_F_32;
> io_req_set_cqe32_extra(req, res2, 0);
> }
> io_req_uring_cleanup(req, issue_flags);
> - if (req->ctx->flags & IORING_SETUP_IOPOLL) {
> + if (req->ctx->flags & IORING_SETUP_IOPOLL &&
> + req->file->f_op->uring_cmd_iopoll) {
I do worry that the pointer chasing here may be expensive, ->file and
->f_op could both be uncached. Would it make sense to add a flag to
req->flags to indicate whether a request should actually be IOPOLLed?
Thanks,
Caleb
> /* order with io_iopoll_req_issued() checking ->iopoll_complete */
> smp_store_release(&req->iopoll_completed, 1);
> } else if (issue_flags & IO_URING_F_COMPLETE_DEFER) {
> if (WARN_ON_ONCE(issue_flags & IO_URING_F_UNLOCKED))
> return;
> @@ -255,13 +256,11 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
> issue_flags |= IO_URING_F_SQE128;
> if (ctx->flags & (IORING_SETUP_CQE32 | IORING_SETUP_CQE_MIXED))
> issue_flags |= IO_URING_F_CQE32;
> if (io_is_compat(ctx))
> issue_flags |= IO_URING_F_COMPAT;
> - if (ctx->flags & IORING_SETUP_IOPOLL) {
> - if (!file->f_op->uring_cmd_iopoll)
> - return -EOPNOTSUPP;
> + if (ctx->flags & IORING_SETUP_IOPOLL && file->f_op->uring_cmd_iopoll) {
> issue_flags |= IO_URING_F_IOPOLL;
> req->iopoll_completed = 0;
> if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) {
> /* make sure every req only blocks once */
> req->flags &= ~REQ_F_IOPOLL_STATE;
> --
> 2.45.2
>
On 2/17/26 7:18 PM, Caleb Sander Mateos wrote:
> On Thu, Feb 12, 2026 at 7:21?PM Caleb Sander Mateos
> <csander@purestorage.com> wrote:
>>
>> Currently, creating an io_uring with IORING_SETUP_IOPOLL requires all
>> requests issued to it to support iopoll. This prevents, for example,
>> using ublk zero-copy together with IORING_SETUP_IOPOLL, as ublk
>> zero-copy buffer registrations are performed using a uring_cmd. There's
>> no technical reason why these non-iopoll uring_cmds can't be supported.
>> They will either complete synchronously or via an external mechanism
>> that calls io_uring_cmd_done(), so they don't need to be polled.
>>
>> Allow uring_cmd requests to be issued to IORING_SETUP_IOPOLL io_urings
>> even if their files don't implement ->uring_cmd_iopoll(). For these
>> uring_cmd requests, skip initializing struct io_kiocb's iopoll fields,
>> don't insert the request into iopoll_list, and take the
>> io_req_complete_defer() or io_req_task_work_add() path in
>> __io_uring_cmd_done() instead of setting the iopoll_completed flag. Also
>> allow io_uring_cmd_mark_cancelable() to be called on these uring_cmds.
>> Assert that io_uring_cmd_mark_cancelable() is only called on
>> non-IORING_SETUP_IOPOLL io_urings or uring_cmds to files that don't
>> implement ->uring_cmd_iopoll().
>>
>> Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
>> ---
>> io_uring/io_uring.c | 4 +++-
>> io_uring/uring_cmd.c | 11 +++++------
>> 2 files changed, 8 insertions(+), 7 deletions(-)
>>
>> diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
>> index c45af82dda3d..4e68a5168894 100644
>> --- a/io_uring/io_uring.c
>> +++ b/io_uring/io_uring.c
>> @@ -1417,11 +1417,13 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
>>
>> if (ret == IOU_ISSUE_SKIP_COMPLETE) {
>> ret = 0;
>>
>> /* If the op doesn't have a file, we're not polling for it */
>> - if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue)
>> + if ((req->ctx->flags & IORING_SETUP_IOPOLL) &&
>> + def->iopoll_queue && (!io_is_uring_cmd(req) ||
>> + req->file->f_op->uring_cmd_iopoll))
>> io_iopoll_req_issued(req, issue_flags);
>> }
>> return ret;
>> }
>>
>> diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
>> index ee7b49f47cb5..8df52e8f1c1b 100644
>> --- a/io_uring/uring_cmd.c
>> +++ b/io_uring/uring_cmd.c
>> @@ -108,12 +108,12 @@ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
>> * Doing cancelations on IOPOLL requests are not supported. Both
>> * because they can't get canceled in the block stack, but also
>> * because iopoll completion data overlaps with the hash_node used
>> * for tracking.
>> */
>> - if (ctx->flags & IORING_SETUP_IOPOLL)
>> - return;
>> + WARN_ON_ONCE(ctx->flags & IORING_SETUP_IOPOLL &&
>> + req->file->f_op->uring_cmd_iopoll);
>>
>> if (!(cmd->flags & IORING_URING_CMD_CANCELABLE)) {
>> cmd->flags |= IORING_URING_CMD_CANCELABLE;
>> io_ring_submit_lock(ctx, issue_flags);
>> hlist_add_head(&req->hash_node, &ctx->cancelable_uring_cmd);
>> @@ -165,11 +165,12 @@ void __io_uring_cmd_done(struct io_uring_cmd *ioucmd, s32 ret, u64 res2,
>> if (req->ctx->flags & IORING_SETUP_CQE_MIXED)
>> req->cqe.flags |= IORING_CQE_F_32;
>> io_req_set_cqe32_extra(req, res2, 0);
>> }
>> io_req_uring_cleanup(req, issue_flags);
>> - if (req->ctx->flags & IORING_SETUP_IOPOLL) {
>> + if (req->ctx->flags & IORING_SETUP_IOPOLL &&
>> + req->file->f_op->uring_cmd_iopoll) {
>
> I do worry that the pointer chasing here may be expensive, ->file and
> ->f_op could both be uncached. Would it make sense to add a flag to
> req->flags to indicate whether a request should actually be IOPOLLed?
I think adding a REQ_F flag for that similar to what is done for NOWAIT
etc would be a good idea.
--
Jens Axboe
© 2016 - 2026 Red Hat, Inc.