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 13/18] mm/swap: drop swap active plist
Date: Fri, 20 Nov 2026 04:37:15 +0000 [thread overview]
Message-ID: <c766c294502b5df1cf14e5941f79080a61f17bcf@linux.dev> (raw)
In-Reply-To: <9ccd81f6f036eb1c3e50d396b44b5e43cff77d2a.1794666741.git.lianux.mm@gmail.com>
Reviewed-by: Kunwu Chan <kunwu.chan@gmail.com>
Thanks,
Kunwu
>
> From: Kairui Song <kasong@tencent.com>
>
> Remove swap_active_head and the associated plist_node. Device identity
> lookups can use the writable swap_info iterator without ordering.
>
> Keep priority ordering for the block-cgroup swap throttle target by
> walking the priority queue under the topology reader. Choose the first
> unmasked, writable, non-offlist device with a backing block device.
> Check OFFLIST as well as the pointer tag because full transitions can
> temporarily leave an unmasked entry, and keep the explicit WRITEOK
> check. The disable transition already publishes its mask before
> releasing the topology writer.
>
> This read-only lookup does not consume per-CPU allocation quotas or
> change retry cursors. It avoids making the throttle disk depend on
> swapon's swap-type assignment order when devices have different
> priorities.
>
> Signed-off-by: Kairui Song <kasong@tencent.com>
> Signed-off-by: Lian Wang <lianux.mm@gmail.com>
> ---
> include/linux/swap.h | 1 -
> mm/swapfile.c | 60 +++++++++++++++++++++++---------------------
> 2 files changed, 32 insertions(+), 29 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index d31f3f023d36..ce8a800751ca 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -263,7 +263,6 @@ struct swap_info_struct {
> struct percpu_ref users; /* indicate and keep swap device valid. */
> unsigned long flags; /* SWP_USED etc: see above */
> signed short prio; /* swap priority of this type */
> - struct plist_node list; /* entry in swap_active_head */
> signed char type; /* strange name for an index */
> unsigned int max; /* size of this swap device */
> struct swap_cluster_info *cluster_info; /* array, one entry per cluster */
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 6b2dbaf33cb6..bd098114ee4b 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -42,7 +42,6 @@
> #include <linux/completion.h>
> #include <linux/suspend.h>
> #include <linux/zswap.h>
> -#include <linux/plist.h>
>
> #include <asm/tlbflush.h>
> #include <linux/leafops.h>
> @@ -91,12 +90,6 @@ bool swap_migration_ad_supported;
> static const char Bad_file[] = "Bad swap file entry ";
> static const char Bad_offset[] = "Bad swap offset entry ";
>
> -/*
> - * all active swap_info_structs
> - * protected with swapon_rwsem, and ordered by priority.
> - */
> -static PLIST_HEAD(swap_active_head);
> -
> static inline struct swap_info_struct *__swap_iter(int *i, unsigned long flag)
> {
> lockdep_assert_held(&swapon_rwsem);
> @@ -3535,7 +3528,6 @@ static void __swap_device_enable(struct swap_info_struct *si)
> spin_unlock(&si->lock);
> atomic_long_add(si->pages, &nr_swap_pages);
> total_swap_pages += si->pages;
> - plist_add(&si->list, &swap_active_head);
> add_to_avail_list(si);
> }
>
> @@ -3555,9 +3547,8 @@ static int swap_device_disable(struct address_space *mapping,
> int err = -EINVAL;
>
> percpu_down_write(&swapon_rwsem);
> - plist_for_each_entry(si, &swap_active_head, list) {
> - if ((si->flags & SWP_WRITEOK) &&
> - si->swap_file->f_mapping == mapping) {
> + for_each_avail_swap(si) {
> + if (si->swap_file->f_mapping == mapping) {
> err = 0;
> break;
> }
> @@ -3583,8 +3574,6 @@ static int swap_device_disable(struct address_space *mapping,
> spin_lock(&si->lock);
> del_from_avail_list(si, true);
> spin_unlock(&si->lock);
> -
> - plist_del(&si->list, &swap_active_head);
> total_swap_pages -= si->pages;
> atomic_long_sub(si->pages, &nr_swap_pages);
>
> @@ -3913,7 +3902,6 @@ static struct swap_info_struct *alloc_swap_info(void)
> */
> }
> p->swap_extent_root = RB_ROOT;
> - plist_node_init(&p->list, 0);
> p->flags = SWP_USED;
> percpu_up_write(&swapon_rwsem);
> if (defer) {
> @@ -4323,12 +4311,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
> if (swap_flags & SWAP_FLAG_PREFER)
> prio = swap_flags & SWAP_FLAG_PRIO_MASK;
>
> - /*
> - * The plist prio is negated because plist ordering is
> - * low-to-high, while swap ordering is high-to-low
> - */
> si->prio = prio;
> - si->list.prio = -si->prio;
>
> /*
> * Publish swap_file before making the percpu ref live, then add the device
> @@ -4454,7 +4437,33 @@ int swap_dup_entry_direct(swp_entry_t entry)
> #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
> static bool __has_usable_swap(void)
> {
> - return !plist_head_empty(&swap_active_head);
> + return READ_ONCE(total_swap_pages) > 0;
> +}
> +
> +static struct swap_info_struct *swap_queue_first_usable_bdev(void)
> +{
> + struct swap_prio_ring *ring;
> + struct swap_info_struct *si;
> + unsigned int ring_idx, dev_idx;
> +
> + lockdep_assert_held(&swapon_rwsem);
> + for (ring_idx = 0; ring_idx < swap_queue_len; ring_idx++) {
> + ring = swap_queue[ring_idx];
> + for (dev_idx = 0; dev_idx < ring->size; dev_idx++) {
> + si = READ_ONCE(ring->dev[dev_idx]);
> + if (swap_device_masked(si))
> + continue;
> + si = swap_device_unmask_ptr(si);
> + if (!(READ_ONCE(si->flags) & SWP_WRITEOK))
> + continue;
> + if (atomic_long_read(&si->inuse_pages) &
> + SWAP_USAGE_OFFLIST_BIT)
> + continue;
> + if (si->bdev)
> + return si;
> + }
> + }
> + return NULL;
> }
>
> void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
> @@ -4478,14 +4487,9 @@ void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
> return;
>
> percpu_down_read(&swapon_rwsem);
> - plist_for_each_entry(si, &swap_active_head, list) {
> - if ((si->flags & SWP_WRITEOK) &&
> - !(atomic_long_read(&si->inuse_pages) &
> - SWAP_USAGE_OFFLIST_BIT) && si->bdev) {
> - blkcg_schedule_throttle(si->bdev->bd_disk, true);
> - break;
> - }
> - }
> + si = swap_queue_first_usable_bdev();
> + if (si)
> + blkcg_schedule_throttle(si->bdev->bd_disk, true);
> percpu_up_read(&swapon_rwsem);
> }
> #endif
>
next prev parent reply other threads:[~2026-11-20 4:37 UTC|newest]
Thread overview: 41+ 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
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 [this message]
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
2026-11-20 4:37 ` Kunwu Chan
2026-11-14 14:52 ` [RFC PATCH v4 16/18] mm/swap: advance the global queue cursor directly between priority rings Lian Wang
2026-11-20 4:38 ` Kunwu Chan
2026-11-14 14:52 ` [RFC PATCH v4 17/18] mm/swap: skip reader rotation for single-device " Lian Wang
2026-11-20 4:38 ` Kunwu Chan
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
2026-11-20 4:38 ` Kunwu Chan
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=c766c294502b5df1cf14e5941f79080a61f17bcf@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