From: "Kunwu Chan" <kunwu.chan@linux.dev>
To: "Lian Wang" <lianux.mm@gmail.com>, linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org,
"Andrew Morton" <akpm@linux-foundation.org>,
"Chris Li" <chrisl@kernel.org>, "Nhat Pham" <nphamcs@gmail.com>,
"Baoquan He" <baoquan.he@linux.dev>,
"Barry Song" <baohua@kernel.org>,
"Youngjun Park" <youngjun.park@lge.com>,
"Kemeng Shi" <shikemeng@huaweicloud.com>,
"Kairui Song" <kasong@tencent.com>,
"Jihan LIN" <linjh22s@gmail.com>, "Kees Cook" <kees@kernel.org>,
"Gustavo A. R. Silva" <gustavoars@kernel.org>,
"Thomas Gleixner" <tglx@kernel.org>,
linux-hardening@vger.kernel.org
Subject: Re: [RFC PATCH v4 09/18] mm/swap: avoid direct reclaim when populating swap cluster metadata
Date: Fri, 20 Nov 2026 04:31:33 +0000 [thread overview]
Message-ID: <b4a389b8d71b5e0fd9eb56af50f4bf6dce245532@linux.dev> (raw)
In-Reply-To: <88057ceeb0228fd33f42637a3c9647eea74d5d95.1794666741.git.lianux.mm@gmail.com>
Reviewed-by: Kunwu Chan <kunwu.chan@gmail.com>
Thanks,
Kunwu
>
> Swap cluster population is entered from swap allocation and may itself
> need memory for slot metadata. Its fallback drops the device and cluster
> locks before allocating with GFP_KERNEL, which can reenter swap
> allocation through direct reclaim.
>
> Make this allocation boundary explicitly non-reclaiming so callers can
> retain outer synchronization without a recursive swap allocation.
> Clear __GFP_DIRECT_RECLAIM from the fallback request while retaining
> __GFP_HIGH and __GFP_NOMEMALLOC. The retry can still wake kswapd, but
> fails without direct reclaim when memory is unavailable.
>
> This can make metadata allocation fail earlier under memory pressure.
> Keep the existing isolated-cluster rollback and restrict this request
> without adding a task-wide PF_MEMALLOC scope.
>
> Signed-off-by: Lian Wang <lianux.mm@gmail.com>
> ---
> mm/swapfile.c | 23 +++++++++++++----------
> 1 file changed, 13 insertions(+), 10 deletions(-)
>
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index c46b43414bf4..fae862fc873c 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -586,13 +586,14 @@ static void swap_cluster_assert_empty(struct swap_cluster_info *ci,
> }
>
> /*
> - * Allocate swap table for one cluster. Attempt an atomic allocation first,
> - * then fallback to sleeping allocation.
> + * Allocate swap table for one cluster. Attempt allocation under the locks
> + * first, then retry with the locks dropped without entering direct reclaim.
> */
> static struct swap_cluster_info *
> swap_cluster_populate(struct swap_info_struct *si,
> struct swap_cluster_info *ci)
> {
> + gfp_t gfp;
> int ret;
>
> /*
> @@ -610,9 +611,11 @@ swap_cluster_populate(struct swap_info_struct *si,
> return ci;
>
> /*
> - * Try a sleep allocation. Each isolated free cluster may cause
> - * a sleep allocation, but there is a limited number of them, so
> - * the potential recursive allocation is limited.
> + * Drop the device and cluster locks before retrying. Metadata allocation
> + * must not recurse into swap allocation through direct reclaim: callers
> + * can retain outer synchronization across cluster population. Restrict
> + * this request instead of granting the task PF_MEMALLOC, which could
> + * give allocator hooks and failure cleanup reserve access.
> */
> spin_unlock(&ci->lock);
> if (si->flags & SWP_SOLIDSTATE)
> @@ -620,8 +623,9 @@ swap_cluster_populate(struct swap_info_struct *si,
> else
> spin_unlock(&si->global_cluster->lock);
>
> - ret = swap_cluster_alloc_table(si, ci, __GFP_HIGH | __GFP_NOMEMALLOC |
> - GFP_KERNEL, false);
> + gfp = (GFP_KERNEL | __GFP_HIGH | __GFP_NOMEMALLOC) &
> + ~__GFP_DIRECT_RECLAIM;
> + ret = swap_cluster_alloc_table(si, ci, gfp, false);
>
> /*
> * Back to atomic context. We might have migrated to a new CPU with a
> @@ -3160,9 +3164,8 @@ static int swap_device_disable(struct address_space *mapping,
> return err;
>
> /*
> - * The swap allocator doesn't take swapon_rwsem. Looping through every
> - * cluster lock after clearing SWP_WRITEOK ensures that allocators see
> - * the updated flag and that no allocation remains in flight.
> + * Drain cluster-lock users after clearing SWP_WRITEOK, so swapoff
> + * does not race with operations that started before the transition.
> */
> for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) {
> ci = swap_cluster_lock(si, offset);
>
next prev parent reply other threads:[~2026-11-20 4:31 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-14 14:47 [RFC PATCH v4 00/18] mm/swap: introduce priority queues for swap device allocation Lian Wang
2026-11-14 14:48 ` [RFC PATCH v4 01/18] mm/swap: remove unused parameter for reading swap header Lian Wang
2026-11-19 15:56 ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 02/18] mm/swap: clean up hibernation error handling Lian Wang
2026-11-19 15:57 ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 03/18] mm/swap: cleanup and document swap device availability flag usage Lian Wang
2026-11-20 3:58 ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 04/18] mm/swap: introduce swap device iteration helper Lian Wang
2026-11-20 3:59 ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 05/18] mm/swap: change the swapon lock into a percpu rwsem Lian Wang
2026-11-20 4:12 ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 06/18] mm/swap: serialize swap publication before removing swapon mutex Lian Wang
2026-11-20 4:30 ` Kunwu Chan
2026-11-14 14:50 ` [RFC PATCH v4 07/18] mm/swap: consolidate swap inuse accounting helpers Lian Wang
2026-11-20 4:30 ` Kunwu Chan
2026-11-14 14:50 ` [RFC PATCH v4 08/18] mm/swap: change back to use each swap device's percpu cluster Lian Wang
2026-11-20 4:31 ` Kunwu Chan
2026-11-14 14:50 ` [RFC PATCH v4 09/18] mm/swap: avoid direct reclaim when populating swap cluster metadata Lian Wang
2026-11-20 4:31 ` Kunwu Chan [this message]
2026-11-14 14:50 ` [RFC PATCH v4 10/18] mm/swap: add priority queue for swap device allocation Lian Wang
2026-11-16 3:51 ` Kairui Song
2026-11-16 11:11 ` Lian Wang
2026-11-20 4:34 ` Kunwu Chan
2026-11-14 14:51 ` [RFC PATCH v4 11/18] mm/swap: remove available list Lian Wang
2026-11-20 4:36 ` Kunwu Chan
2026-11-14 14:51 ` [RFC PATCH v4 12/18] mm/swap: bound synchronous discard outside the allocation reader Lian Wang
2026-11-20 4:36 ` Kunwu Chan
2026-11-14 14:51 ` [RFC PATCH v4 13/18] mm/swap: drop swap active plist Lian Wang
2026-11-20 4:37 ` Kunwu Chan
2026-11-14 14:51 ` [RFC PATCH v4 14/18] lib/plist.c: remove requeue function Lian Wang
2026-11-14 14:52 ` [RFC PATCH v4 15/18] mm/swap: reuse per-CPU queue readers across priority changes Lian Wang
2026-11-14 14:52 ` [RFC PATCH v4 16/18] mm/swap: advance the global queue cursor directly between priority rings Lian Wang
2026-11-14 14:52 ` [RFC PATCH v4 17/18] mm/swap: skip reader rotation for single-device " Lian Wang
2026-11-14 14:52 ` [RFC PATCH v4 18/18] mm/swap: redistribute queue readers after membership changes Lian Wang
2026-11-16 3:29 ` Kairui Song
2026-11-16 3:52 ` [RFC PATCH v4 00/18] mm/swap: introduce priority queues for swap device allocation Kairui Song
2026-11-16 11:10 ` Lian Wang
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=b4a389b8d71b5e0fd9eb56af50f4bf6dce245532@linux.dev \
--to=kunwu.chan@linux.dev \
--cc=akpm@linux-foundation.org \
--cc=baohua@kernel.org \
--cc=baoquan.he@linux.dev \
--cc=chrisl@kernel.org \
--cc=gustavoars@kernel.org \
--cc=kasong@tencent.com \
--cc=kees@kernel.org \
--cc=lianux.mm@gmail.com \
--cc=linjh22s@gmail.com \
--cc=linux-hardening@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=nphamcs@gmail.com \
--cc=shikemeng@huaweicloud.com \
--cc=tglx@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