From: Baoquan He <baoquan.he@linux.dev>
To: Nhat Pham <nphamcs@gmail.com>
Cc: Baoquan He <hebaoquan@kylinos.cn>,
linux-mm@kvack.org, akpm@linux-foundation.org, chrisl@kernel.org,
kasong@tencent.com, baohua@kernel.org, youngjun.park@lge.com,
hannes@cmpxchg.org, yosry@kernel.org, shikemeng@huaweicloud.com,
chengming.zhou@linux.dev, david@kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 07/16] mm, swap: add xswap grow trigger on cluster allocation
Date: Thu, 3 Sep 2026 16:24:06 +0800 [thread overview]
Message-ID: <apkupjBofpvnxyOG@fedora> (raw)
In-Reply-To: <CAKEwX=P53GAmyPeBQ29XaHnGw5qpKkiKiBEwuhdRKdkMPT0GSg@mail.gmail.com>
On 09/02/26 at 10:15am, Nhat Pham wrote:
> On Thu, Aug 27, 2026 at 5:45 AM Baoquan He <hebaoquan@kylinos.cn> wrote:
> >
> > When cluster_alloc_swap_entry() fails to find a free cluster and
> > the xswap device still has room to grow, expand the mapped range
> > by XSWAP_GROW_CLUSTERS clusters.
> >
> > Since xswap is always SWP_SOLIDSTATE, no locks need to be dropped
> > before calling xswap_map_clusters(), global_cluster_lock is never
> > held on this path.
>
> What about local_lock()? I believe we're still holding
> percpu_swap_cluster's local lock as we invoke xswap_map_clusters()?
> Would this lead to issues :/
Good question. Kashiko also reported this , have fixed it by moving
swap_alloc_slow()() out of the lock scope as swap_alloc_slow() does not
touch the per-cpu swap cluster cache.
next prev parent reply other threads:[~2026-09-03 8:24 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-27 9:44 [PATCH 00/16] xswap: extendable swap device backed by zswap Baoquan He
2026-08-27 9:44 ` [PATCH 01/16] mm: zswap: return -ENOENT when the swap device is gone Baoquan He
2026-09-02 14:53 ` Nhat Pham
2026-09-03 7:54 ` Baoquan He
2026-08-27 9:44 ` [PATCH 02/16] mm: xswap support for zswap Baoquan He
2026-08-27 9:44 ` [PATCH 03/16] mm, swap: add CONFIG_XSWAP and xswap fields to swap_info_struct Baoquan He
2026-08-27 9:44 ` [PATCH 04/16] mm, swap: refactor free_swap_cluster_info to take swap_info_struct Baoquan He
2026-08-27 9:44 ` [PATCH 05/16] mm, swap: add xswap cluster grow via VM_SPARSE vmalloc Baoquan He
2026-08-27 9:44 ` [PATCH 06/16] mm, swap: add sysfs create interface for xswap Baoquan He
2026-08-27 9:44 ` [PATCH 07/16] mm, swap: add xswap grow trigger on cluster allocation Baoquan He
2026-09-02 14:15 ` Nhat Pham
2026-09-03 8:24 ` Baoquan He [this message]
2026-08-27 9:44 ` [PATCH 08/16] mm, swap: add xswap_try_shrink and shrink trigger on cluster free Baoquan He
2026-08-27 9:44 ` [PATCH 09/16] mm, swap: free backing pages in xswap_unmap_clusters Baoquan He
2026-08-27 9:45 ` [PATCH 10/16] mm, swap: add nr_free_tail for O(1) xswap shrink detection Baoquan He
2026-08-27 9:45 ` [PATCH 11/16] mm, swap: add adjustable runtime ceiling (nr_clusters) for xswap Baoquan He
2026-08-27 9:45 ` [PATCH 12/16] mm, swap: add debugfs knob for xswap per-device cluster limit Baoquan He
2026-08-27 9:45 ` [PATCH 13/16] mm, swap: defer xswap shrink to workqueue to avoid lock recursion Baoquan He
2026-09-02 14:50 ` Nhat Pham
2026-09-03 9:17 ` Baoquan He
2026-08-27 9:45 ` [PATCH 14/16] mm, swap: refactor swapoff + add xswap_destroy Baoquan He
2026-09-03 6:59 ` Youngjun Park
2026-09-04 5:33 ` Baoquan He
2026-08-27 9:45 ` [PATCH 15/16] mm, swap: require zswap for xswap devices Baoquan He
2026-09-03 6:52 ` Youngjun Park
2026-09-04 7:57 ` Baoquan He
2026-08-27 9:45 ` [PATCH 16/16] mm, swap: allow setting xswap device priority at creation Baoquan He
2026-08-27 13:59 ` [syzbot ci] Re: xswap: extendable swap device backed by zswap syzbot ci
2026-08-31 8:35 ` Baoquan He
2026-08-31 17:54 ` [PATCH 00/16] " Kairui Song
2026-09-01 11:03 ` Baoquan He
2026-09-02 14:10 ` Nhat Pham
2026-09-04 9:42 ` Baoquan He
2026-09-02 14:33 ` Nhat Pham
2026-09-03 7:35 ` Youngjun Park
2026-09-04 3:33 ` Baoquan He
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=apkupjBofpvnxyOG@fedora \
--to=baoquan.he@linux.dev \
--cc=akpm@linux-foundation.org \
--cc=baohua@kernel.org \
--cc=chengming.zhou@linux.dev \
--cc=chrisl@kernel.org \
--cc=david@kernel.org \
--cc=hannes@cmpxchg.org \
--cc=hebaoquan@kylinos.cn \
--cc=kasong@tencent.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=nphamcs@gmail.com \
--cc=shikemeng@huaweicloud.com \
--cc=yosry@kernel.org \
--cc=youngjun.park@lge.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