linux-kernel - Re: [PATCH] io_uring/wq: avoid indirect do_work/free

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <9d8f1460-6317-4e8a-ba90-53e35b41f235@kernel.dk>
Date: Sat, 29 Mar 2025 13:07:04 -0600
From: Jens Axboe <axboe@...nel.dk>
To: Caleb Sander Mateos <csander@...estorage.com>,
 Pavel Begunkov <asml.silence@...il.com>
Cc: io-uring@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] io_uring/wq: avoid indirect do_work/free_work calls

On 3/29/25 10:15 AM, Caleb Sander Mateos wrote:
> struct io_wq stores do_work and free_work function pointers which are
> called on each work item. But these function pointers are always set to
> io_wq_submit_work and io_wq_free_work, respectively. So remove these
> function pointers and just call the functions directly.

Was going to say that the indirect call here is not something
I'd be worried about in terms of performance, but it's also kind of
pointless to have them when we have just the single do_work/free_work
callback. And hence it'd reduce the struct footprint, which is always
useful. So yeah, I do think the change makes sense.

-- 
Jens Axboe