linux-kernel - Re: [PATCH v2] f2fs: only fragment segment in the same section

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: <e1bc380d-be61-40ba-85ef-26b9cc6149dc@kernel.org>
Date: Tue, 25 Jun 2024 22:12:50 +0800
From: Chao Yu <chao@...nel.org>
To: Sheng Yong <shengyong@...o.com>, jaegeuk@...nel.org
Cc: linux-f2fs-devel@...ts.sourceforge.net, linux-kernel@...r.kernel.org,
 daehojeong@...gle.com
Subject: Re: [PATCH v2] f2fs: only fragment segment in the same section

On 2024/6/25 20:15, Sheng Yong wrote:
> When new_curseg() is allocating a new segment, if mode=fragment:xxx is
> switched on in large section scenario, __get_next_segno() will select
> the next segno randomly in the range of [0, maxsegno] in order to
> fragment segments.
> 
> If the candidate segno is free, get_new_segment() will use it directly
> as the new segment.
> 
> However, if the section of the candidate is not empty, and some other
> segments have already been used, and have a different type (e.g NODE)
> with the candidate (e.g DATA), GC will complain inconsistent segment
> type later.
> 
> This could be reproduced by the following steps:
> 
>    dd if=/dev/zero of=test.img bs=1M count=10240
>    mkfs.f2fs -s 128 test.img
>    mount -t f2fs test.img /mnt -o mode=fragment:block
>    echo 1 > /sys/fs/f2fs/loop0/max_fragment_chunk
>    echo 512 > /sys/fs/f2fs/loop0/max_fragment_hole
>    dd if=/dev/zero of=/mnt/testfile bs=4K count=100
>    umount /mnt
> 
>    F2FS-fs (loop0): Inconsistent segment (4377) type [0, 1] in SSA and SIT
> 
> In order to allow simulating segment fragmentation in large section
> scenario, this patch reduces the candidate range:
>   * if curseg is the last segment in the section, return curseg->segno
>     to make get_new_segment() itself find the next free segment.
>   * if curseg is in the middle of the secion, select candicate randomly in
>     the range of [curseg + 1, last_seg_in_the_same_section] to keep type
>     consistent.
> 
> Signed-off-by: Sheng Yong <shengyong@...o.com>

Reviewed-by: Chao Yu <chao@...nel.org>

Thanks,