From: lizetao <[email protected]>
To: Pavel Begunkov <[email protected]>,
"[email protected]" <[email protected]>
Cc: Anuj Gupta <[email protected]>, Kanchan Joshi <[email protected]>
Subject: RE: [PATCH 2/4] io_uring: add registered request arguments
Date: Mon, 6 Jan 2025 11:33:42 +0000 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <cb3cc963ad684d5687b90f28ff9d928a20f80b76.1735301337.git.asml.silence@gmail.com>
Hi,
> -----Original Message-----
> From: Pavel Begunkov <[email protected]>
> Sent: Monday, December 30, 2024 9:30 PM
> To: [email protected]
> Cc: [email protected]; Anuj Gupta <[email protected]>; Kanchan
> Joshi <[email protected]>
> Subject: [PATCH 2/4] io_uring: add registered request arguments
>
> Similarly to registered wait arguments we want to have a pre-mapped space
> for various request arguments. Use the same parameter region, however as -
> >wait_args has different lifetime rules, add a new instance of struct
> io_reg_args.
>
> Signed-off-by: Pavel Begunkov <[email protected]>
> ---
> include/linux/io_uring_types.h | 2 ++
> io_uring/register.c | 3 +++
> 2 files changed, 5 insertions(+)
>
> diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
> index 49008f00d064..cd6642855533 100644
> --- a/include/linux/io_uring_types.h
> +++ b/include/linux/io_uring_types.h
> @@ -299,6 +299,8 @@ struct io_ring_ctx {
>
> struct io_submit_state submit_state;
>
> + struct io_reg_args sqe_args;
> +
> /*
> * Modifications are protected by ->uring_lock and -
> >mmap_lock.
> * The flags, buf_pages and buf_nr_pages fields should be
> stable diff --git a/io_uring/register.c b/io_uring/register.c index
> b926eb053408..d2232b90a81d 100644
> --- a/io_uring/register.c
> +++ b/io_uring/register.c
> @@ -607,6 +607,9 @@ static int io_register_mem_region(struct io_ring_ctx
> *ctx, void __user *uarg)
> ctx->wait_args.ptr = io_region_get_ptr(&ctx->param_region);
> ctx->wait_args.size = rd.size;
> }
> +
> + ctx->sqe_args.ptr = io_region_get_ptr(&ctx->param_region);
> + ctx->sqe_args.size = rd.size;
Why not add an enum value against sqe_args? Will mixing it with
IORING_MEM_REGION_REG_WAIT_ARG cause management confusion?
> return 0;
> }
>
> --
> 2.47.1
>
---
Li Zetao
next prev parent reply other threads:[~2025-01-06 11:33 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-30 13:30 [RFC 0/4] pre-mapped rw attributes Pavel Begunkov
2024-12-30 13:30 ` [PATCH 1/4] io_uring: add structure for registered arguments Pavel Begunkov
2024-12-30 13:30 ` [PATCH 2/4] io_uring: add registered request arguments Pavel Begunkov
2025-01-06 11:33 ` lizetao [this message]
2025-01-06 16:40 ` Pavel Begunkov
2024-12-30 13:30 ` [PATCH 3/4] io_uring/rw: use READ_ONCE with rw attributes Pavel Begunkov
2024-12-30 13:30 ` [PATCH 4/4] io_uring/rw: pre-mapped " Pavel Begunkov
2025-01-06 11:13 ` lizetao
2025-01-06 16:53 ` Pavel Begunkov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox