linux-kernel - Re: [PATCH RFC 7/7] block: fix disordered IO in the case recursive split

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: <ac0ea34d-4572-43a6-c32d-11e0fba71f56@huaweicloud.com>
Date: Tue, 26 Aug 2025 09:20:34 +0800
From: Yu Kuai <yukuai1@...weicloud.com>
To: Christoph Hellwig <hch@...radead.org>, Yu Kuai <yukuai1@...weicloud.com>
Cc: colyli@...nel.org, hare@...e.de, tieren@...as.com, axboe@...nel.dk,
 tj@...nel.org, josef@...icpanda.com, song@...nel.org,
 akpm@...ux-foundation.org, neil@...wn.name, linux-block@...r.kernel.org,
 linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
 linux-raid@...r.kernel.org, yi.zhang@...wei.com, yangerkun@...wei.com,
 johnny.chenyi@...wei.com, "yukuai (C)" <yukuai3@...wei.com>
Subject: Re: [PATCH RFC 7/7] block: fix disordered IO in the case recursive
 split

Hi,

在 2025/08/25 19:07, Christoph Hellwig 写道:
> On Mon, Aug 25, 2025 at 05:37:00PM +0800, Yu Kuai wrote:
>> +void submit_bio_noacct(struct bio *bio)
> 
> Maybe just have version of submit_bio_noacct that takes the split
> argument, and make submit_bio_noacct a tiny wrapper around it?  That
> should create less churns than this version I think.  In fact I suspect
> we can actually bypass submit_bio_noacct entirely, all the checks and
> accounting in it were already done when submitting the origin bio, so
> the bio split helper could just call into submit_bio_noacct_nocheck
> directly.
> 

I can do this, I was trying to avoid touching submit_bio_noacct()
because there are many many callers, a tiny wrapper sounds good!

And for bypassing submit_bio_noacct(), I think it's ok, just
blk_throtl_bio() should be called seperately. Perhaps we can do
this later.

Thanks,
Kuai

> .
>