From: Baoquan He <baoquan.he@linux.dev>
To: linux-mm@kvack.org
Cc: akpm@linux-foundation.org, david@kernel.org, chrisl@kernel.org,
kasong@tencent.com, nphamcs@gmail.com, baohua@kernel.org,
youngjun.park@lge.com, corbet@lwn.net, hannes@cmpxchg.org,
chengming.zhou@linux.dev, kunwu.chan@gmail.com,
klarasmodin@gmail.com, linux-kernel@vger.kernel.org,
Baoquan He <hebaoquan@kylinos.cn>
Subject: [PATCH v5 18/19] mm, swap: do not give an xswap slot to a cgroup that cannot zswap
Date: Mon, 9 Nov 2026 13:54:54 +0800 [thread overview]
Message-ID: <20261109055455.536925-19-baoquan.he@linux.dev> (raw)
In-Reply-To: <20261109055455.536925-1-baoquan.he@linux.dev>
From: Baoquan He <hebaoquan@kylinos.cn>
At this point, an xswap slot holds only a zswap-backed page. It has no
storage of its own. If the folio's cgroup cannot take another zswap
page, giving it an xswap slot is wasted: zswap refuses the page and the
slot cannot hold it.
Skip xswap devices when the cgroup cannot zswap, and try a physical swap
device instead.
The check is obj_cgroup_may_zswap(). It is false when memory.zswap.max
is 0 anywhere in the hierarchy, or when the hierarchy has already
reached that limit. So the routing follows how much the cgroup has in
zswap, not only how it is configured. zswap_store() uses the same check,
but it first tries to shrink the memcg. The allocation-time check does
not try to shrink, so it is stricter.
Count active xswap devices, and do the cgroup lookup only when one
exists. Update the counter when the device is enabled, before a full
device can skip the avail-list insert, so a full device is still counted.
A device can appear between that read and the allocation. So if the
slot the allocator picked is on an xswap device, check the cgroup
again; when it cannot zswap, drop the slot and retry without xswap
devices.
Signed-off-by: Baoquan He <hebaoquan@kylinos.cn>
---
mm/swapfile.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 63 insertions(+), 6 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2e5383036fdc..efb48ef71611 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -326,6 +326,8 @@ static DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
atomic_long_t nr_swap_pages;
atomic_t nr_real_swapfiles;
+/* Active xswap devices, as in nr_real_swapfiles. */
+static atomic_t nr_xswap_files;
/*
* Some modules use swappable objects and may try to swap them out under
* memory pressure (via the shrinker). Before doing so, they may wish to
@@ -1519,7 +1521,9 @@ static void del_from_avail_list(struct swap_info_struct *si, bool swapoff)
lockdep_assert_held(&si->lock);
si->flags &= ~SWP_WRITEOK;
/* Count active devices, not merely those on the avail list. */
- if (!(si->flags & SWP_XSWAP))
+ if (si->flags & SWP_XSWAP)
+ atomic_sub(1, &nr_xswap_files);
+ else
atomic_sub(1, &nr_real_swapfiles);
atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages);
} else {
@@ -1558,7 +1562,9 @@ static void add_to_avail_list(struct swap_info_struct *si, bool swapon)
* Count the device here, not after adding it to the list: a
* full device is still active and skips the add below.
*/
- if (!(si->flags & SWP_XSWAP))
+ if (si->flags & SWP_XSWAP)
+ atomic_add(1, &nr_xswap_files);
+ else
atomic_add(1, &nr_real_swapfiles);
} else {
if (!(READ_ONCE(si->flags) & SWP_WRITEOK))
@@ -1682,7 +1688,7 @@ static bool get_swap_device_info(struct swap_info_struct *si)
* 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)
+static bool swap_alloc_fast(struct folio *folio, bool may_zswap)
{
unsigned int order = folio_order(folio);
struct swap_cluster_info *ci;
@@ -1722,6 +1728,11 @@ static bool swap_alloc_fast(struct folio *folio)
}
}
#endif
+ if (!may_zswap && (si->flags & SWP_XSWAP)) {
+ put_swap_device(si);
+ rcu_read_unlock();
+ return false;
+ }
ci = swap_cluster_lock(si, offset);
if (cluster_is_usable(ci, order)) {
@@ -1738,13 +1749,19 @@ static bool swap_alloc_fast(struct folio *folio)
}
/* Rotate the device and switch to a new cluster */
-static void swap_alloc_slow(struct folio *folio)
+static void swap_alloc_slow(struct folio *folio, bool may_zswap)
{
struct swap_info_struct *si, *next;
spin_lock(&swap_avail_lock);
start_over:
plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) {
+ /*
+ * Do not rotate a skipped device: the walk follows the
+ * rotation and would spin forever.
+ */
+ if (!may_zswap && (si->flags & SWP_XSWAP))
+ continue;
/* Rotate the device and switch to a new cluster */
plist_requeue(&si->avail_list, &swap_avail_head);
spin_unlock(&swap_avail_lock);
@@ -2067,6 +2084,17 @@ static int swap_dup_entries_cluster(struct swap_info_struct *si,
return err;
}
+/* Can the folio's cgroup take another zswap page? */
+static bool folio_may_zswap(struct folio *folio)
+{
+ struct obj_cgroup *objcg = get_obj_cgroup_from_folio(folio);
+ bool may_zswap = !objcg || obj_cgroup_may_zswap(objcg);
+
+ if (objcg)
+ obj_cgroup_put(objcg);
+ return may_zswap;
+}
+
/**
* folio_alloc_swap - allocate swap space for a folio
* @folio: folio we want to move to swap
@@ -2083,10 +2111,23 @@ int folio_alloc_swap(struct folio *folio)
{
unsigned int order = folio_order(folio);
unsigned int size = 1 << order;
+ /* True unless the gate below finds an xswap device to route away from. */
+ bool may_zswap = true;
+ bool zswap_checked = false;
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
+ /*
+ * A folio that zswap will not take must not get an xswap slot. With
+ * no xswap device to route away from, skip the lookup; a device that
+ * appears before we pick one is handled after the allocation.
+ */
+ if (atomic_read(&nr_xswap_files)) {
+ may_zswap = folio_may_zswap(folio);
+ zswap_checked = true;
+ }
+
if (order) {
/*
* Reject large allocation when THP_SWAP is disabled. Check below
@@ -2107,8 +2148,8 @@ int folio_alloc_swap(struct folio *folio)
again:
local_lock(&percpu_swap_cluster.lock);
- if (!swap_alloc_fast(folio))
- swap_alloc_slow(folio);
+ if (!swap_alloc_fast(folio, may_zswap))
+ swap_alloc_slow(folio, may_zswap);
local_unlock(&percpu_swap_cluster.lock);
if (!order && unlikely(!folio_test_swapcache(folio))) {
@@ -2116,6 +2157,22 @@ int folio_alloc_swap(struct folio *folio)
goto again;
}
+ /*
+ * The xswap gate was skipped because there was no device when we
+ * looked. One may have appeared since; check before keeping the
+ * xswap slot the allocator may have picked.
+ */
+ if (unlikely(!zswap_checked && atomic_read(&nr_xswap_files) &&
+ folio_test_swapcache(folio) &&
+ (__swap_entry_to_info(folio->swap)->flags & SWP_XSWAP))) {
+ zswap_checked = true;
+ may_zswap = folio_may_zswap(folio);
+ if (!may_zswap) {
+ swap_cache_del_folio(folio);
+ goto again;
+ }
+ }
+
/* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */
if (unlikely(mem_cgroup_try_charge_swap(folio))) {
swap_cache_del_folio(folio);
--
2.54.0
next prev parent reply other threads:[~2026-11-09 5:57 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-09 5:54 [PATCH v5 00/19] mm, swap: extendable swap devices (xswap phase I) Baoquan He
2026-11-09 5:54 ` [PATCH v5 01/19] mm: xswap support for zswap Baoquan He
2026-11-09 5:54 ` [PATCH v5 02/19] mm, swap: refactor free_swap_cluster_info to take swap_info_struct Baoquan He
2026-11-09 5:54 ` [PATCH v5 03/19] mm, swap: add VM_SPARSE cluster-array helpers for xswap Baoquan He
2026-11-09 5:54 ` [PATCH v5 04/19] mm, swap: use a VM_SPARSE cluster array for xswap devices Baoquan He
2026-11-09 5:54 ` [PATCH v5 05/19] mm, swap: widen swap_info_struct max/pages to unsigned long Baoquan He
2026-11-09 5:54 ` [PATCH v5 06/19] mm, swap: add a sysfs interface to create xswap devices Baoquan He
2026-11-09 5:54 ` [PATCH v5 07/19] mm, swap: refactor swapoff and add xswap_destroy Baoquan He
2026-11-09 5:54 ` [PATCH v5 08/19] mm, swap: require zswap for xswap devices Baoquan He
2026-11-09 5:54 ` [PATCH v5 09/19] mm, swap: use a stable id " Baoquan He
2026-11-09 5:54 ` [PATCH v5 10/19] mm, swap: let the command line set the xswap device size Baoquan He
2026-11-09 5:54 ` [PATCH v5 11/19] mm, swap: add CONFIG_XSWAP_DEFAULT_MAX Baoquan He
2026-11-09 5:54 ` [PATCH v5 12/19] mm, swap: let swapoff destroy xswap devices by name Baoquan He
2026-11-09 5:54 ` [PATCH v5 13/19] mm, swap: add xswap grow trigger on cluster allocation Baoquan He
2026-11-09 5:54 ` [PATCH v5 14/19] mm, swap: add debugfs counters for xswap Baoquan He
2026-11-09 5:54 ` [PATCH v5 15/19] mm, swap: make xswap cluster_info accesses RCU-safe Baoquan He
2026-11-09 5:54 ` [PATCH v5 16/19] mm, swap: prepare xswap_unmap_clusters for range shrinking Baoquan He
2026-11-09 5:54 ` [PATCH v5 17/19] mm, swap: add xswap shrink trigger and defer it to a workqueue Baoquan He
2026-11-09 5:54 ` Baoquan He [this message]
2026-11-09 5:54 ` [PATCH v5 19/19] mm, swap: skip the overcommit probe when removing xswap Baoquan He
2026-11-09 6:15 ` [PATCH v5 00/19] mm, swap: extendable swap devices (xswap phase I) 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=20261109055455.536925-19-baoquan.he@linux.dev \
--to=baoquan.he@linux.dev \
--cc=akpm@linux-foundation.org \
--cc=baohua@kernel.org \
--cc=chengming.zhou@linux.dev \
--cc=chrisl@kernel.org \
--cc=corbet@lwn.net \
--cc=david@kernel.org \
--cc=hannes@cmpxchg.org \
--cc=hebaoquan@kylinos.cn \
--cc=kasong@tencent.com \
--cc=klarasmodin@gmail.com \
--cc=kunwu.chan@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=nphamcs@gmail.com \
--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
all inboxes | Powered by JetHome®