From: Nhat Pham <nphamcs@gmail.com>
To: akpm@linux-foundation.org
Cc: chrisl@kernel.org, kasong@tencent.com, hannes@cmpxchg.org,
mhocko@kernel.org, roman.gushchin@linux.dev,
shakeel.butt@linux.dev, yosry@kernel.org, david@kernel.org,
muchun.song@linux.dev, shikemeng@huaweicloud.com,
baoquan.he@linux.dev, baohua@kernel.org, youngjun.park@lge.com,
chengming.zhou@linux.dev, ljs@kernel.org, liam@infradead.org,
vbabka@kernel.org, rppt@kernel.org, surenb@google.com,
qi.zheng@linux.dev, axelrasmussen@google.com, yuanchu@google.com,
weixugc@google.com, riel@surriel.com, gourry@gourry.net,
haowenchao22@gmail.com, corbet@lwn.net, kernel-team@meta.com,
nphamcs@gmail.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
cgroups@vger.kernel.org
Subject: [PATCH v3 10/11] mm, swap: defer memcg_table allocation for physical swap clusters
Date: Thu, 6 Aug 2026 11:42:53 -0700 [thread overview]
Message-ID: <20260806184254.3790858-11-nphamcs@gmail.com> (raw)
In-Reply-To: <20260806184254.3790858-1-nphamcs@gmail.com>
Stop allocating a memcg table for every physical swap cluster that only
ever holds vswap backings. The table costs SWAPFILE_CLUSTER *
sizeof(unsigned short) per cluster, 1 KB per 2 MB of swap on a 64-bit
kernel with 4 KB pages. On a vswap-heavy workload, where zswap writeback
is the only consumer of physical swap, that is the common case.
Such clusters never have their memcg_table read or written: vswap-layer
charging records on the vswap cluster's table, not the physical one.
Allocate eagerly only when the cluster is known to need a table: any
cluster in a !CONFIG_VSWAP build, or any vswap cluster. For physical
clusters in CONFIG_VSWAP builds, defer to alloc_swap_scan_cluster(),
which allocates on the first direct-use slot and skips entirely when the
cluster only holds pointer-tagged vswap backings.
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
mm/swapfile.c | 40 ++++++++++++++++++++++++++++++++--------
1 file changed, 32 insertions(+), 8 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b4d7af21ca1c..65559647eeb4 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -492,7 +492,8 @@ static void swap_cluster_free_table(struct swap_cluster_info *ci)
swap_cluster_free_table_folio_rcu_cb);
}
-static int swap_cluster_alloc_table(struct swap_cluster_info *ci, gfp_t gfp)
+static int swap_cluster_alloc_table(struct swap_info_struct *si,
+ struct swap_cluster_info *ci, gfp_t gfp)
{
struct swap_table *table = NULL;
struct folio *folio;
@@ -515,7 +516,16 @@ static int swap_cluster_alloc_table(struct swap_cluster_info *ci, gfp_t gfp)
rcu_assign_pointer(ci->table, table);
#ifdef CONFIG_MEMCG
- if (!mem_cgroup_disabled()) {
+ /*
+ * Allocate memcg_table eagerly only when we know it will be used:
+ * any cluster in a !CONFIG_VSWAP build (all slots are direct use),
+ * or any vswap cluster (every vswap alloc records memcg). Physical
+ * clusters in a CONFIG_VSWAP build defer to alloc_swap_scan_cluster,
+ * which allocates on the first direct-use slot and skips entirely
+ * when the cluster only holds Pointer-tagged vswap backings.
+ */
+ if ((!IS_ENABLED(CONFIG_VSWAP) || swap_is_vswap(si)) &&
+ !mem_cgroup_disabled()) {
VM_WARN_ON_ONCE(ci->memcg_table);
ci->memcg_table = kzalloc_obj(*ci->memcg_table, gfp);
if (!ci->memcg_table) {
@@ -589,8 +599,8 @@ swap_cluster_populate(struct swap_info_struct *si,
lockdep_assert_held(&si->global_cluster_lock);
lockdep_assert_held(&ci->lock);
- if (!swap_cluster_alloc_table(ci, __GFP_HIGH | __GFP_NOMEMALLOC |
- __GFP_NOWARN))
+ if (!swap_cluster_alloc_table(si, ci, __GFP_HIGH | __GFP_NOMEMALLOC |
+ __GFP_NOWARN))
return ci;
/*
@@ -608,8 +618,8 @@ swap_cluster_populate(struct swap_info_struct *si,
if (!swap_is_vswap(si))
local_unlock(&percpu_swap_cluster.lock);
- ret = swap_cluster_alloc_table(ci, __GFP_HIGH | __GFP_NOMEMALLOC |
- GFP_KERNEL);
+ ret = swap_cluster_alloc_table(si, ci, __GFP_HIGH | __GFP_NOMEMALLOC |
+ GFP_KERNEL);
/*
* Back to atomic context. We might have migrated to a new CPU with a
@@ -911,7 +921,7 @@ static int swap_cluster_setup_bad_slot(struct swap_info_struct *si,
ci = cluster_info + idx;
/* Need to allocate swap table first for initial bad slot marking. */
- if (!ci->count && swap_cluster_alloc_table(ci, GFP_KERNEL))
+ if (!ci->count && swap_cluster_alloc_table(si, ci, GFP_KERNEL))
return -ENOMEM;
spin_lock(&ci->lock);
/* Check for duplicated bad swap slots. */
@@ -1193,6 +1203,20 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
if (!ret)
continue;
}
+#ifdef CONFIG_MEMCG
+ /*
+ * Lazy-allocate memcg_table on the first direct-use slot of a
+ * physical cluster.
+ */
+ if (IS_ENABLED(CONFIG_VSWAP) && folio &&
+ !folio_test_swapcache(folio) && !mem_cgroup_disabled() &&
+ !ci->memcg_table) {
+ ci->memcg_table = kzalloc_obj(*ci->memcg_table,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (!ci->memcg_table)
+ goto out;
+ }
+#endif
if (!__swap_cluster_alloc_entries(si, ci, folio, offset % SWAPFILE_CLUSTER))
break;
found = offset;
@@ -1259,7 +1283,7 @@ static unsigned int alloc_swap_scan_dynamic(struct swap_info_struct *si,
spin_lock_init(&ci_dyn->ci.lock);
INIT_LIST_HEAD(&ci_dyn->ci.list);
- if (swap_cluster_alloc_table(&ci_dyn->ci, GFP_ATOMIC)) {
+ if (swap_cluster_alloc_table(si, &ci_dyn->ci, GFP_ATOMIC)) {
kfree(ci_dyn);
return SWAP_ENTRY_INVALID;
}
--
2.53.0-Meta
next prev parent reply other threads:[~2026-08-06 18:43 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-06 18:42 [PATCH v3 00/11] Virtual Swap Space (Swap Table Edition) Nhat Pham
2026-08-06 18:42 ` [PATCH v3 01/11] mm, swap: add virtual swap device infrastructure Nhat Pham
2026-08-06 18:42 ` [PATCH v3 02/11] mm, swap: support zswap and zeroswap as vswap backends Nhat Pham
2026-08-06 18:42 ` [PATCH v3 03/11] mm, swap: prepare the swap IO path for vswap Nhat Pham
2026-08-06 18:42 ` [PATCH v3 04/11] mm, swap: support physical swap as a vswap backend Nhat Pham
2026-08-06 18:42 ` [PATCH v3 05/11] mm, swap: enable THP swapin for vswap entries Nhat Pham
2026-08-06 18:42 ` [PATCH v3 06/11] mm, swap: write back vswap zswap entries to physical swap Nhat Pham
2026-08-06 18:42 ` [PATCH v3 07/11] mm, swap: reclaim physical slots backing cache-only vswap entries Nhat Pham
2026-08-06 18:42 ` [PATCH v3 08/11] mm, swap: only charge physical swap entries Nhat Pham
2026-08-06 18:42 ` [PATCH v3 09/11] mm, swap: add debugfs counters for vswap Nhat Pham
2026-08-06 18:42 ` Nhat Pham [this message]
2026-08-06 18:42 ` [PATCH v3 11/11] mm, swap: widen swap_info_struct max/pages to unsigned long Nhat Pham
2026-08-07 5:26 ` [syzbot ci] Re: Virtual Swap Space (Swap Table Edition) syzbot ci
2026-08-07 7:21 ` Chris Li
2026-08-07 9:07 ` [PATCH v3 00/11] " Chris Li
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=20260806184254.3790858-11-nphamcs@gmail.com \
--to=nphamcs@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=axelrasmussen@google.com \
--cc=baohua@kernel.org \
--cc=baoquan.he@linux.dev \
--cc=cgroups@vger.kernel.org \
--cc=chengming.zhou@linux.dev \
--cc=chrisl@kernel.org \
--cc=corbet@lwn.net \
--cc=david@kernel.org \
--cc=gourry@gourry.net \
--cc=hannes@cmpxchg.org \
--cc=haowenchao22@gmail.com \
--cc=kasong@tencent.com \
--cc=kernel-team@meta.com \
--cc=liam@infradead.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mhocko@kernel.org \
--cc=muchun.song@linux.dev \
--cc=qi.zheng@linux.dev \
--cc=riel@surriel.com \
--cc=roman.gushchin@linux.dev \
--cc=rppt@kernel.org \
--cc=shakeel.butt@linux.dev \
--cc=shikemeng@huaweicloud.com \
--cc=surenb@google.com \
--cc=vbabka@kernel.org \
--cc=weixugc@google.com \
--cc=yosry@kernel.org \
--cc=youngjun.park@lge.com \
--cc=yuanchu@google.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