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 08/18] mm/swap: change back to use each swap device's percpu cluster
Date: Fri, 20 Nov 2026 04:31:18 +0000 [thread overview]
Message-ID: <7cacd2a09ef50b1480dee84d8a2f160f60e113ab@linux.dev> (raw)
In-Reply-To: <f9cb4b2c57360c07bb1ff0d305e089635cb7e56e.1794666741.git.lianux.mm@gmail.com>
Reviewed-by: Kunwu Chan <kunwu.chan@gmail.com>
Thanks,
Kunwu
>
> From: Youngjun Park <youngjun.park@lge.com>
>
> This reverts commit 1b7e90020eb7 ("mm, swap: use percpu cluster as
> allocation fast path").
>
> The global percpu cluster causes several issues:
>
> 1) It prevents efficient swap allocation for users that do not want
> the default swap device policy. Because the cluster cache sits
> above device selection, users that need a different policy must
> bypass or replace the cache. This complicates incoming ideas like
> swap tiering.
>
> 2) It can bypass a caller's preferred device policy. Consider a future
> policy with per-memcg device restrictions: memcg1 can access devices
> A and B, where A has higher priority; memcg2 can only access B. Memcg2
> can write the global percpu cluster with device B, then memcg1 takes B
> in the fast path even though higher-priority device A is not exhausted.
>
> 3) The fast-path / slow-path design bundled with the global per-CPU
> cache is problematic: only the fast path uses the global cache,
> and the slow path is forced to rotate the allocation list. This
> complicates consumers like discard.
>
> Revert to per-device percpu clusters first. A later patch will
> introduce new infrastructure for a high-performance global
> allocation path.
>
> Suggested-by: Kairui Song <kasong@tencent.com>
> Co-developed-by: Baoquan He <bhe@redhat.com>
> Signed-off-by: Baoquan He <bhe@redhat.com>
> Signed-off-by: Youngjun Park <youngjun.park@lge.com>
> Signed-off-by: Kairui Song <kasong@tencent.com>
> Signed-off-by: Lian Wang <lianux.mm@gmail.com>
> ---
> include/linux/swap.h | 13 +++-
> mm/swapfile.c | 170 ++++++++++++++-----------------------------
> 2 files changed, 63 insertions(+), 120 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 717387e16a2d..c8a5684b2f4f 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -241,10 +241,17 @@ enum {
> #endif
>
> /*
> - * We keep using same cluster for rotational device so IO will be sequential.
> - * The purpose is to optimize SWAP throughput on these device.
> + * We assign a cluster to each CPU, so each CPU can allocate swap entry from
> + * its own cluster and swapout sequentially. The purpose is to optimize swapout
> + * throughput.
> */
> +struct percpu_cluster {
> + local_lock_t lock; /* Protect the percpu_cluster above */
> + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
> +};
> +
> struct swap_sequential_cluster {
> + spinlock_t lock; /* Serialize usage of global cluster */
> unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
> };
>
> @@ -267,8 +274,8 @@ struct swap_info_struct {
> /* list of cluster that are fragmented or contented */
> unsigned int pages; /* total of usable pages of swap */
> atomic_long_t inuse_pages; /* number of those currently in use */
> + struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
> struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */
> - spinlock_t global_cluster_lock; /* Serialize usage of global cluster */
> struct rb_root swap_extent_root;/* root of the swap extent rbtree */
> struct block_device *bdev; /* swap device or bdev of swap file */
> struct file *swap_file; /* seldom referenced */
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index aa020f2706b4..c46b43414bf4 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -145,18 +145,6 @@ static atomic_t proc_poll_event = ATOMIC_INIT(0);
>
> atomic_t nr_rotate_swap = ATOMIC_INIT(0);
>
> -struct percpu_swap_cluster {
> - struct swap_info_struct *si[SWAP_NR_ORDERS];
> - unsigned long offset[SWAP_NR_ORDERS];
> - local_lock_t lock;
> -};
> -
> -static DEFINE_PER_CPU(struct percpu_swap_cluster, percpu_swap_cluster) = {
> - .si = { NULL },
> - .offset = { SWAP_ENTRY_INVALID },
> - .lock = INIT_LOCAL_LOCK(),
> -};
> -
> /* May return NULL on invalid type, caller must check for NULL return */
> static struct swap_info_struct *swap_type_to_info(int type)
> {
> @@ -523,9 +511,10 @@ static int swap_cluster_alloc_table(struct swap_info_struct *si,
> lock:
> if (!locked) {
> if (si) {
> - local_lock(&percpu_swap_cluster.lock);
> - if (!(si->flags & SWP_SOLIDSTATE))
> - spin_lock(&si->global_cluster_lock);
> + if (si->flags & SWP_SOLIDSTATE)
> + local_lock(&si->percpu_cluster->lock);
> + else
> + spin_lock(&si->global_cluster->lock);
> }
> spin_lock(&ci->lock);
> }
> @@ -610,9 +599,10 @@ swap_cluster_populate(struct swap_info_struct *si,
> * Only cluster isolation from the allocator does table allocation.
> * Swap allocator uses percpu clusters and holds the local lock.
> */
> - lockdep_assert_held(&this_cpu_ptr(&percpu_swap_cluster)->lock);
> - if (!(si->flags & SWP_SOLIDSTATE))
> - lockdep_assert_held(&si->global_cluster_lock);
> + if (si->flags & SWP_SOLIDSTATE)
> + lockdep_assert_held(this_cpu_ptr(&si->percpu_cluster->lock));
> + else
> + lockdep_assert_held(&si->global_cluster->lock);
> lockdep_assert_held(&ci->lock);
>
> if (!swap_cluster_alloc_table(si, ci, __GFP_HIGH | __GFP_NOMEMALLOC |
> @@ -625,9 +615,10 @@ swap_cluster_populate(struct swap_info_struct *si,
> * the potential recursive allocation is limited.
> */
> spin_unlock(&ci->lock);
> - if (!(si->flags & SWP_SOLIDSTATE))
> - spin_unlock(&si->global_cluster_lock);
> - local_unlock(&percpu_swap_cluster.lock);
> + if (si->flags & SWP_SOLIDSTATE)
> + local_unlock(&si->percpu_cluster->lock);
> + else
> + spin_unlock(&si->global_cluster->lock);
>
> ret = swap_cluster_alloc_table(si, ci, __GFP_HIGH | __GFP_NOMEMALLOC |
> GFP_KERNEL, false);
> @@ -749,7 +740,7 @@ static bool swap_do_scheduled_discard(struct swap_info_struct *si)
> ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
> /*
> * Delete the cluster from list to prepare for discard, but keep
> - * the CLUSTER_FLAG_DISCARD flag, percpu_swap_cluster could be
> + * the CLUSTER_FLAG_DISCARD flag, there could be percpu_cluster
> * pointing to it, or ran into by relocate_cluster.
> */
> list_del(&ci->list);
> @@ -1104,12 +1095,10 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
> out:
> relocate_cluster(si, ci);
> swap_cluster_unlock(ci);
> - if (si->flags & SWP_SOLIDSTATE) {
> - this_cpu_write(percpu_swap_cluster.offset[order], next);
> - this_cpu_write(percpu_swap_cluster.si[order], si);
> - } else {
> + if (si->flags & SWP_SOLIDSTATE)
> + this_cpu_write(si->percpu_cluster->next[order], next);
> + else
> si->global_cluster->next[order] = next;
> - }
> return found;
> }
>
> @@ -1210,13 +1199,17 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si,
> if (order && !(si->flags & SWP_BLKDEV))
> return 0;
>
> - if (!(si->flags & SWP_SOLIDSTATE)) {
> + if (si->flags & SWP_SOLIDSTATE) {
> + /* Fast path using per CPU cluster */
> + local_lock(&si->percpu_cluster->lock);
> + offset = __this_cpu_read(si->percpu_cluster->next[order]);
> + } else {
> /* Serialize HDD SWAP allocation for each device. */
> - spin_lock(&si->global_cluster_lock);
> + spin_lock(&si->global_cluster->lock);
> offset = si->global_cluster->next[order];
> - if (offset == SWAP_ENTRY_INVALID)
> - goto new_cluster;
> + }
>
> + if (offset != SWAP_ENTRY_INVALID) {
> ci = swap_cluster_lock(si, offset);
> /* Cluster could have been used by another order */
> if (cluster_is_usable(ci, order)) {
> @@ -1230,7 +1223,6 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si,
> goto done;
> }
>
> -new_cluster:
> if (swap_prefer_free_cluster(si)) {
> found = alloc_swap_scan_list(si, &si->free_clusters, folio, false);
> if (found)
> @@ -1283,8 +1275,10 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si,
> goto done;
> }
> done:
> - if (!(si->flags & SWP_SOLIDSTATE))
> - spin_unlock(&si->global_cluster_lock);
> + if (si->flags & SWP_SOLIDSTATE)
> + local_unlock(&si->percpu_cluster->lock);
> + else
> + spin_unlock(&si->global_cluster->lock);
>
> return found;
> }
> @@ -1440,41 +1434,8 @@ static bool get_swap_device_info(struct swap_info_struct *si)
> return true;
> }
>
> -/*
> - * Fast path try to get swap entries with specified order from current
> - * CPU's swap entry pool (a cluster).
> - */
> -static bool swap_alloc_fast(struct folio *folio)
> -{
> - unsigned int order = folio_order(folio);
> - struct swap_cluster_info *ci;
> - struct swap_info_struct *si;
> - unsigned int offset;
> -
> - /*
> - * Once allocated, swap_info_struct will never be completely freed,
> - * so checking it's liveness by get_swap_device_info is enough.
> - */
> - si = this_cpu_read(percpu_swap_cluster.si[order]);
> - offset = this_cpu_read(percpu_swap_cluster.offset[order]);
> - if (!si || !offset || !get_swap_device_info(si))
> - return false;
> -
> - ci = swap_cluster_lock(si, offset);
> - if (cluster_is_usable(ci, order)) {
> - if (cluster_is_empty(ci))
> - offset = cluster_offset(si, ci);
> - alloc_swap_scan_cluster(si, ci, folio, offset);
> - } else {
> - swap_cluster_unlock(ci);
> - }
> -
> - put_swap_device(si);
> - return folio_test_swapcache(folio);
> -}
> -
> /* Rotate the device and switch to a new cluster */
> -static void swap_alloc_slow(struct folio *folio)
> +static void swap_alloc_entry(struct folio *folio)
> {
> struct swap_info_struct *si, *next;
>
> @@ -1842,10 +1803,7 @@ int folio_alloc_swap(struct folio *folio)
> }
>
> again:
> - local_lock(&percpu_swap_cluster.lock);
> - if (!swap_alloc_fast(folio))
> - swap_alloc_slow(folio);
> - local_unlock(&percpu_swap_cluster.lock);
> + swap_alloc_entry(folio);
>
> if (!order && unlikely(!folio_test_swapcache(folio))) {
> if (swap_sync_discard())
> @@ -2251,31 +2209,14 @@ void swap_put_entries_direct(swp_entry_t entry, int nr)
> */
> swp_entry_t swap_alloc_hibernation_slot(int type)
> {
> - struct swap_info_struct *pcp_si, *si = swap_type_to_info(type);
> - unsigned long pcp_offset, offset = SWAP_ENTRY_INVALID;
> - struct swap_cluster_info *ci;
> + struct swap_info_struct *si = swap_type_to_info(type);
> + unsigned long offset = SWAP_ENTRY_INVALID;
> swp_entry_t entry = {0};
>
> if (!si)
> goto fail;
>
> - /*
> - * Try the local cluster first if it matches the device. If
> - * not, try grab a new cluster and override local cluster.
> - */
> - local_lock(&percpu_swap_cluster.lock);
> - pcp_si = this_cpu_read(percpu_swap_cluster.si[0]);
> - pcp_offset = this_cpu_read(percpu_swap_cluster.offset[0]);
> - if (pcp_si == si && pcp_offset) {
> - ci = swap_cluster_lock(si, pcp_offset);
> - if (cluster_is_usable(ci, 0))
> - offset = alloc_swap_scan_cluster(si, ci, NULL, pcp_offset);
> - else
> - swap_cluster_unlock(ci);
> - }
> - if (!offset)
> - offset = cluster_alloc_swap_entry(si, NULL);
> - local_unlock(&percpu_swap_cluster.lock);
> + offset = cluster_alloc_swap_entry(si, NULL);
> if (offset)
> entry = swp_entry(si->type, offset);
>
> @@ -3253,27 +3194,6 @@ static void free_swap_cluster_info(struct swap_cluster_info *cluster_info,
> kvfree(cluster_info);
> }
>
> -/*
> - * Called after swap device's reference count is dead, so
> - * neither scan nor allocation will use it.
> - */
> -static void flush_percpu_swap_cluster(struct swap_info_struct *si)
> -{
> - int cpu, i;
> - struct swap_info_struct **pcp_si;
> -
> - for_each_possible_cpu(cpu) {
> - pcp_si = per_cpu_ptr(percpu_swap_cluster.si, cpu);
> - /*
> - * Invalidate the percpu swap cluster cache, si->users
> - * is dead, so no new user will point to it, just flush
> - * any existing user.
> - */
> - for (i = 0; i < SWAP_NR_ORDERS; i++)
> - cmpxchg(&pcp_si[i], si, NULL);
> - }
> -}
> -
> SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
> {
> struct swap_info_struct *p = NULL;
> @@ -3325,7 +3245,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
>
> flush_work(&p->discard_work);
> flush_work(&p->reclaim_work);
> - flush_percpu_swap_cluster(p);
>
> destroy_swap_extents(p, p->swap_file);
>
> @@ -3346,6 +3265,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
> percpu_up_write(&swapon_rwsem);
> arch_swap_invalidate_area(p->type);
> zswap_swapoff(p->type);
> + free_percpu(p->percpu_cluster);
> + p->percpu_cluster = NULL;
> kfree(p->global_cluster);
> p->global_cluster = NULL;
> free_swap_cluster_info(cluster_info, maxpages);
> @@ -3694,7 +3615,7 @@ static int setup_swap_clusters_info(struct swap_info_struct *si,
> {
> unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);
> struct swap_cluster_info *cluster_info;
> - int err = -ENOMEM;
> + int cpu, err = -ENOMEM;
> unsigned long i;
>
> cluster_info = kvzalloc_objs(*cluster_info, nr_clusters);
> @@ -3704,13 +3625,26 @@ static int setup_swap_clusters_info(struct swap_info_struct *si,
> for (i = 0; i < nr_clusters; i++)
> spin_lock_init(&cluster_info[i].lock);
>
> - if (!(si->flags & SWP_SOLIDSTATE)) {
> + if (si->flags & SWP_SOLIDSTATE) {
> + si->percpu_cluster = alloc_percpu(struct percpu_cluster);
> + if (!si->percpu_cluster)
> + goto err;
> +
> + for_each_possible_cpu(cpu) {
> + struct percpu_cluster *cluster;
> +
> + cluster = per_cpu_ptr(si->percpu_cluster, cpu);
> + for (i = 0; i < SWAP_NR_ORDERS; i++)
> + cluster->next[i] = SWAP_ENTRY_INVALID;
> + local_lock_init(&cluster->lock);
> + }
> + } else {
> si->global_cluster = kmalloc_obj(*si->global_cluster);
> if (!si->global_cluster)
> goto err;
> for (i = 0; i < SWAP_NR_ORDERS; i++)
> si->global_cluster->next[i] = SWAP_ENTRY_INVALID;
> - spin_lock_init(&si->global_cluster_lock);
> + spin_lock_init(&si->global_cluster->lock);
> }
>
> /*
> @@ -3984,6 +3918,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
> bad_swap_unlock_inode:
> inode_unlock(inode);
> bad_swap:
> + free_percpu(si->percpu_cluster);
> + si->percpu_cluster = NULL;
> kfree(si->global_cluster);
> si->global_cluster = NULL;
> inode = NULL;
>
next prev parent reply other threads:[~2026-11-20 4:31 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 [this message]
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
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=7cacd2a09ef50b1480dee84d8a2f160f60e113ab@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