[PATCH v3] io_uring/net: Allow to do vectorized send

[PATCH v3] io_uring/net: Allow to do vectorized send

[norman.maurer]

From: Norman Maurer <norman_maurer@apple.com>

At the moment you have to use sendmsg for vectorized send.
While this works it's suboptimal as it also means you need to
allocate a struct msghdr that needs to be kept alive until a
submission happens. We can remove this limitation by just
allowing to use send directly.

Signed-off-by: Norman Maurer <norman_maurer@apple.com>
---
Changes since v1: Simplify flag check and fix line length of commit message
Changes since v2: Adjust SENDMSG_FLAGS  

---
 include/uapi/linux/io_uring.h | 4 ++++
 io_uring/net.c                | 9 ++++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index b8a0e70ee2fd..6957dc539d83 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -392,12 +392,16 @@ enum io_uring_op {
  *				the starting buffer ID in cqe->flags as per
  *				usual for provided buffer usage. The buffers
  *				will be	contiguous from the starting buffer ID.
+ *
+ * IORING_SEND_VECTORIZED	If set, SEND[_ZC] will take a pointer to a io_vec
+ * 				to allow vectorized send operations.
  */
 #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
 #define IORING_RECV_MULTISHOT		(1U << 1)
 #define IORING_RECVSEND_FIXED_BUF	(1U << 2)
 #define IORING_SEND_ZC_REPORT_USAGE	(1U << 3)
 #define IORING_RECVSEND_BUNDLE		(1U << 4)
+#define IORING_SEND_VECTORIZED		(1U << 5)
 
 /*
  * cqe.res for IORING_CQE_F_NOTIF if
diff --git a/io_uring/net.c b/io_uring/net.c
index ba2d0abea349..3ce5478438f0 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -382,6 +382,10 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	}
 	if (req->flags & REQ_F_BUFFER_SELECT)
 		return 0;
+
+	if (sr->flags & IORING_SEND_VECTORIZED)
+               return io_net_import_vec(req, kmsg, sr->buf, sr->len, ITER_SOURCE);
+
 	return import_ubuf(ITER_SOURCE, sr->buf, sr->len, &kmsg->msg.msg_iter);
 }
 
@@ -409,7 +413,7 @@ static int io_sendmsg_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe
 	return io_net_import_vec(req, kmsg, msg.msg_iov, msg.msg_iovlen, ITER_SOURCE);
 }
 
-#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE)
+#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE | IORING_SEND_VECTORIZED)
 
 int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
@@ -420,6 +424,9 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	sr->flags = READ_ONCE(sqe->ioprio);
 	if (sr->flags & ~SENDMSG_FLAGS)
 		return -EINVAL;
+	if (req->opcode == IORING_OP_SENDMSG && sr->flags & IORING_SEND_VECTORIZED)
+		return -EINVAL;
+
 	sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
 	if (sr->msg_flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
-- 
2.39.5 (Apple Git-154)

Re: [PATCH v3] io_uring/net: Allow to do vectorized send

[Jens Axboe]

On 7/29/25 12:59 AM, norman.maurer@googlemail.com wrote:
> From: Norman Maurer <norman_maurer@apple.com>
> 
> At the moment you have to use sendmsg for vectorized send.
> While this works it's suboptimal as it also means you need to
> allocate a struct msghdr that needs to be kept alive until a
> submission happens. We can remove this limitation by just
> allowing to use send directly.
> 
> Signed-off-by: Norman Maurer <norman_maurer@apple.com>
> ---
> Changes since v1: Simplify flag check and fix line length of commit message
> Changes since v2: Adjust SENDMSG_FLAGS  
> 
> ---
>  include/uapi/linux/io_uring.h | 4 ++++
>  io_uring/net.c                | 9 ++++++++-
>  2 files changed, 12 insertions(+), 1 deletion(-)
> 
> diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
> index b8a0e70ee2fd..6957dc539d83 100644
> --- a/include/uapi/linux/io_uring.h
> +++ b/include/uapi/linux/io_uring.h
> @@ -392,12 +392,16 @@ enum io_uring_op {
>   *				the starting buffer ID in cqe->flags as per
>   *				usual for provided buffer usage. The buffers
>   *				will be	contiguous from the starting buffer ID.
> + *
> + * IORING_SEND_VECTORIZED	If set, SEND[_ZC] will take a pointer to a io_vec
> + * 				to allow vectorized send operations.
>   */
>  #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
>  #define IORING_RECV_MULTISHOT		(1U << 1)
>  #define IORING_RECVSEND_FIXED_BUF	(1U << 2)
>  #define IORING_SEND_ZC_REPORT_USAGE	(1U << 3)
>  #define IORING_RECVSEND_BUNDLE		(1U << 4)
> +#define IORING_SEND_VECTORIZED		(1U << 5)
>  
>  /*
>   * cqe.res for IORING_CQE_F_NOTIF if
> diff --git a/io_uring/net.c b/io_uring/net.c
> index ba2d0abea349..3ce5478438f0 100644
> --- a/io_uring/net.c
> +++ b/io_uring/net.c
> @@ -382,6 +382,10 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>  	}
>  	if (req->flags & REQ_F_BUFFER_SELECT)
>  		return 0;
> +
> +	if (sr->flags & IORING_SEND_VECTORIZED)
> +               return io_net_import_vec(req, kmsg, sr->buf, sr->len, ITER_SOURCE);
> +
>  	return import_ubuf(ITER_SOURCE, sr->buf, sr->len, &kmsg->msg.msg_iter);
>  }
>  
> @@ -409,7 +413,7 @@ static int io_sendmsg_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe
>  	return io_net_import_vec(req, kmsg, msg.msg_iov, msg.msg_iovlen, ITER_SOURCE);
>  }
>  
> -#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE)
> +#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE | IORING_SEND_VECTORIZED)
>  
>  int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>  {
> @@ -420,6 +424,9 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>  	sr->flags = READ_ONCE(sqe->ioprio);
>  	if (sr->flags & ~SENDMSG_FLAGS)
>  		return -EINVAL;
> +	if (req->opcode == IORING_OP_SENDMSG && sr->flags & IORING_SEND_VECTORIZED)
> +		return -EINVAL;
> +
>  	sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
>  	if (sr->msg_flags & MSG_DONTWAIT)
>  		req->flags |= REQ_F_NOWAIT;

I think this looks simple enough, but after pondering this a bit, I also
think we can just skip the check right above here. OP_SENDMSG is, by
definition, working on IORING_SEND_VECTORIZED data. Hence returning
-EINVAL from that seems a bit redundant. Maybe just delete this hunk?
What do you think?

No need for v3 for that, I can just edit out that hunk with a note. I'll
run some testing today.

-- 
Jens Axboe

Re: [PATCH v3] io_uring/net: Allow to do vectorized send

[Norman Maurer]

> Am 29.07.2025 um 02:15 schrieb Jens Axboe <axboe@kernel.dk>:
> 
> On 7/29/25 12:59 AM, norman.maurer@googlemail.com wrote:
>> From: Norman Maurer <norman_maurer@apple.com>
>> 
>> At the moment you have to use sendmsg for vectorized send.
>> While this works it's suboptimal as it also means you need to
>> allocate a struct msghdr that needs to be kept alive until a
>> submission happens. We can remove this limitation by just
>> allowing to use send directly.
>> 
>> Signed-off-by: Norman Maurer <norman_maurer@apple.com>
>> ---
>> Changes since v1: Simplify flag check and fix line length of commit message
>> Changes since v2: Adjust SENDMSG_FLAGS  
>> 
>> ---
>> include/uapi/linux/io_uring.h | 4 ++++
>> io_uring/net.c                | 9 ++++++++-
>> 2 files changed, 12 insertions(+), 1 deletion(-)
>> 
>> diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
>> index b8a0e70ee2fd..6957dc539d83 100644
>> --- a/include/uapi/linux/io_uring.h
>> +++ b/include/uapi/linux/io_uring.h
>> @@ -392,12 +392,16 @@ enum io_uring_op {
>>  *                the starting buffer ID in cqe->flags as per
>>  *                usual for provided buffer usage. The buffers
>>  *                will be    contiguous from the starting buffer ID.
>> + *
>> + * IORING_SEND_VECTORIZED    If set, SEND[_ZC] will take a pointer to a io_vec
>> + *                to allow vectorized send operations.
>>  */
>> #define IORING_RECVSEND_POLL_FIRST    (1U << 0)
>> #define IORING_RECV_MULTISHOT        (1U << 1)
>> #define IORING_RECVSEND_FIXED_BUF    (1U << 2)
>> #define IORING_SEND_ZC_REPORT_USAGE    (1U << 3)
>> #define IORING_RECVSEND_BUNDLE        (1U << 4)
>> +#define IORING_SEND_VECTORIZED        (1U << 5)
>> 
>> /*
>>  * cqe.res for IORING_CQE_F_NOTIF if
>> diff --git a/io_uring/net.c b/io_uring/net.c
>> index ba2d0abea349..3ce5478438f0 100644
>> --- a/io_uring/net.c
>> +++ b/io_uring/net.c
>> @@ -382,6 +382,10 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>>    }
>>    if (req->flags & REQ_F_BUFFER_SELECT)
>>        return 0;
>> +
>> +    if (sr->flags & IORING_SEND_VECTORIZED)
>> +               return io_net_import_vec(req, kmsg, sr->buf, sr->len, ITER_SOURCE);
>> +
>>    return import_ubuf(ITER_SOURCE, sr->buf, sr->len, &kmsg->msg.msg_iter);
>> }
>> 
>> @@ -409,7 +413,7 @@ static int io_sendmsg_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe
>>    return io_net_import_vec(req, kmsg, msg.msg_iov, msg.msg_iovlen, ITER_SOURCE);
>> }
>> 
>> -#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE)
>> +#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE | IORING_SEND_VECTORIZED)
>> 
>> int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>> {
>> @@ -420,6 +424,9 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>>    sr->flags = READ_ONCE(sqe->ioprio);
>>    if (sr->flags & ~SENDMSG_FLAGS)
>>        return -EINVAL;
>> +    if (req->opcode == IORING_OP_SENDMSG && sr->flags & IORING_SEND_VECTORIZED)
>> +        return -EINVAL;
>> +
>>    sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
>>    if (sr->msg_flags & MSG_DONTWAIT)
>>        req->flags |= REQ_F_NOWAIT;
> 
> I think this looks simple enough, but after pondering this a bit, I also
> think we can just skip the check right above here. OP_SENDMSG is, by
> definition, working on IORING_SEND_VECTORIZED data. Hence returning
> -EINVAL from that seems a bit redundant. Maybe just delete this hunk?
> What do you think?

Works for me 

> 
> No need for v3 for that, I can just edit out that hunk with a note. I'll
> run some testing today.

Thanks! Looking forward to hear back on the results 

> 
> --
> Jens Axboe

Bye
Norman 

Re: [PATCH v3] io_uring/net: Allow to do vectorized send

[Jens Axboe]

On Mon, 28 Jul 2025 20:59:53 -1000, norman.maurer@googlemail.com wrote:
> At the moment you have to use sendmsg for vectorized send.
> While this works it's suboptimal as it also means you need to
> allocate a struct msghdr that needs to be kept alive until a
> submission happens. We can remove this limitation by just
> allowing to use send directly.
> 
> 
> [...]

Applied, thanks!

[1/1] io_uring/net: Allow to do vectorized send
      commit: 423a72545c7b59f304781bf38050d537b6a7ed5e

Best regards,
-- 
Jens Axboe