From: Christoph Hellwig <hch@infradead.org>
To: Ming Lei <ming.lei@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org,
Mikulas Patocka <mpatocka@redhat.com>,
Zhaoyang Huang <zhaoyang.huang@unisoc.com>,
Dave Chinner <dchinner@redhat.com>,
linux-fsdevel@vger.kernel.org
Subject: calling into file systems directly from ->queue_rq, was Re: [PATCH V5 0/6] loop: improve loop aio perf by IOCB_NOWAIT
Date: Sun, 23 Nov 2025 22:12:24 -0800 [thread overview]
Message-ID: <aSP3SG_KaROJTBHx@infradead.org> (raw)
In-Reply-To: <20251015110735.1361261-1-ming.lei@redhat.com>
FYI, with this series I'm seeing somewhat frequent stack overflows when
using loop on top of XFS on top of stacked block devices.
This seems to be because this can now issue I/O directly from ->queue_rq
instead of breaking the stack chain, i.e. we can build much deeper call
stacks now.
Also this now means a file systems using current->journal_info can call
into another file system trying to use, making things blow up even worse.
In other words: I don't think issuing file system I/O from the
submission thread in loop can work, and we should drop this again.
next prev parent reply other threads:[~2025-11-24 6:12 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-15 11:07 [PATCH V5 0/6] loop: improve loop aio perf by IOCB_NOWAIT Ming Lei
2025-10-15 11:07 ` [PATCH V5 1/6] loop: add helper lo_cmd_nr_bvec() Ming Lei
2025-10-15 15:49 ` Bart Van Assche
2025-10-16 2:19 ` Ming Lei
2025-10-15 11:07 ` [PATCH V5 2/6] loop: add helper lo_rw_aio_prep() Ming Lei
2025-10-15 11:07 ` [PATCH V5 3/6] loop: add lo_submit_rw_aio() Ming Lei
2025-10-15 11:07 ` [PATCH V5 4/6] loop: move command blkcg/memcg initialization into loop_queue_work Ming Lei
2025-10-15 11:07 ` [PATCH V5 5/6] loop: try to handle loop aio command via NOWAIT IO first Ming Lei
2025-10-15 11:07 ` [PATCH V5 6/6] loop: add hint for handling aio via IOCB_NOWAIT Ming Lei
2025-11-18 12:55 ` [PATCH V5 0/6] loop: improve loop aio perf by IOCB_NOWAIT Ming Lei
2025-11-18 15:38 ` Jens Axboe
2025-11-24 6:12 ` Christoph Hellwig [this message]
2025-11-24 9:02 ` calling into file systems directly from ->queue_rq, was " Ming Lei
2025-11-24 9:05 ` Christoph Hellwig
2025-11-25 3:00 ` Ming Lei
2025-11-25 3:56 ` Jens Axboe
2025-11-25 7:26 ` Gao Xiang
2025-11-25 9:19 ` Ming Lei
2025-11-25 9:39 ` Gao Xiang
2025-11-25 10:13 ` Gao Xiang
2025-11-25 10:41 ` Ming Lei
2025-11-25 10:57 ` Gao Xiang
2025-11-25 11:10 ` Christoph Hellwig
2025-11-25 11:48 ` Ming Lei
2025-11-25 11:58 ` Gao Xiang
2025-11-25 12:18 ` Ming Lei
2025-11-25 15:16 ` Gao Xiang
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 \
--in-reply-to=aSP3SG_KaROJTBHx@infradead.org \
--to=hch@infradead.org \
--cc=axboe@kernel.dk \
--cc=dchinner@redhat.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=ming.lei@redhat.com \
--cc=mpatocka@redhat.com \
--cc=zhaoyang.huang@unisoc.com \
/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;
as well as URLs for NNTP newsgroup(s).