linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Nhat Pham <nphamcs@gmail.com>
To: linux-mm@kvack.org
Cc: akpm@linux-foundation.org, hannes@cmpxchg.org, hughd@google.com,
	yosry.ahmed@linux.dev, mhocko@kernel.org,
	roman.gushchin@linux.dev, shakeel.butt@linux.dev,
	muchun.song@linux.dev, len.brown@intel.com,
	chengming.zhou@linux.dev, kasong@tencent.com, chrisl@kernel.org,
	huang.ying.caritas@gmail.com, ryan.roberts@arm.com,
	shikemeng@huaweicloud.com, viro@zeniv.linux.org.uk,
	baohua@kernel.org, bhe@redhat.com, osalvador@suse.de,
	lorenzo.stoakes@oracle.com, christophe.leroy@csgroup.eu,
	pavel@kernel.org, kernel-team@meta.com,
	linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
	linux-pm@vger.kernel.org, peterx@redhat.com, riel@surriel.com,
	joshua.hahnjy@gmail.com, npache@redhat.com, gourry@gourry.net,
	axelrasmussen@google.com, yuanchu@google.com, weixugc@google.com,
	rafael@kernel.org, jannh@google.com, pfalcato@suse.de,
	zhengqi.arch@bytedance.com
Subject: [PATCH v3 11/20] zswap: move zswap entry management to the virtual swap descriptor
Date: Sun,  8 Feb 2026 13:58:24 -0800	[thread overview]
Message-ID: <20260208215839.87595-12-nphamcs@gmail.com> (raw)
In-Reply-To: <20260208215839.87595-1-nphamcs@gmail.com>

Remove the zswap tree and manage zswap entries directly
through the virtual swap descriptor. This re-partitions the zswap pool
(by virtual swap cluster), which eliminates zswap tree lock contention.

Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
 include/linux/zswap.h |   6 +++
 mm/vswap.c            | 100 ++++++++++++++++++++++++++++++++++++++++++
 mm/zswap.c            |  40 -----------------
 3 files changed, 106 insertions(+), 40 deletions(-)

diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index 1a04caf283dc8..7eb3ce7e124fc 100644
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -6,6 +6,7 @@
 #include <linux/mm_types.h>
 
 struct lruvec;
+struct zswap_entry;
 
 extern atomic_long_t zswap_stored_pages;
 
@@ -33,6 +34,11 @@ void zswap_lruvec_state_init(struct lruvec *lruvec);
 void zswap_folio_swapin(struct folio *folio);
 bool zswap_is_enabled(void);
 bool zswap_never_enabled(void);
+void *zswap_entry_store(swp_entry_t swpentry, struct zswap_entry *entry);
+void *zswap_entry_load(swp_entry_t swpentry);
+void *zswap_entry_erase(swp_entry_t swpentry);
+bool zswap_empty(swp_entry_t swpentry);
+
 #else
 
 struct zswap_lruvec_state {};
diff --git a/mm/vswap.c b/mm/vswap.c
index d44199dc059a3..9bb733f00fd21 100644
--- a/mm/vswap.c
+++ b/mm/vswap.c
@@ -10,6 +10,7 @@
 #include <linux/swapops.h>
 #include <linux/swap_cgroup.h>
 #include <linux/cpuhotplug.h>
+#include <linux/zswap.h>
 #include "swap.h"
 #include "swap_table.h"
 
@@ -37,11 +38,13 @@
  * Swap descriptor - metadata of a swapped out page.
  *
  * @slot: The handle to the physical swap slot backing this page.
+ * @zswap_entry: The zswap entry associated with this swap slot.
  * @swap_cache: The folio in swap cache.
  * @shadow: The shadow entry.
  */
 struct swp_desc {
 	swp_slot_t slot;
+	struct zswap_entry *zswap_entry;
 	union {
 		struct folio *swap_cache;
 		void *shadow;
@@ -238,6 +241,7 @@ static void __vswap_alloc_from_cluster(struct vswap_cluster *cluster, int start)
 	for (i = 0; i < nr; i++) {
 		desc = &cluster->descriptors[start + i];
 		desc->slot.val = 0;
+		desc->zswap_entry = NULL;
 	}
 	cluster->count += nr;
 }
@@ -1009,6 +1013,102 @@ void __swap_cache_replace_folio(struct folio *old, struct folio *new)
 	rcu_read_unlock();
 }
 
+#ifdef CONFIG_ZSWAP
+/**
+ * zswap_entry_store - store a zswap entry for a swap entry
+ * @swpentry: the swap entry
+ * @entry: the zswap entry to store
+ *
+ * Stores a zswap entry in the swap descriptor for the given swap entry.
+ * The cluster is locked during the store operation.
+ *
+ * Return: the old zswap entry if one existed, NULL otherwise
+ */
+void *zswap_entry_store(swp_entry_t swpentry, struct zswap_entry *entry)
+{
+	struct vswap_cluster *cluster = NULL;
+	struct swp_desc *desc;
+	void *old;
+
+	rcu_read_lock();
+	desc = vswap_iter(&cluster, swpentry.val);
+	if (!desc) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	old = desc->zswap_entry;
+	desc->zswap_entry = entry;
+	spin_unlock(&cluster->lock);
+	rcu_read_unlock();
+
+	return old;
+}
+
+/**
+ * zswap_entry_load - load a zswap entry for a swap entry
+ * @swpentry: the swap entry
+ *
+ * Loads the zswap entry from the swap descriptor for the given swap entry.
+ *
+ * Return: the zswap entry if one exists, NULL otherwise
+ */
+void *zswap_entry_load(swp_entry_t swpentry)
+{
+	struct vswap_cluster *cluster = NULL;
+	struct swp_desc *desc;
+	void *zswap_entry;
+
+	rcu_read_lock();
+	desc = vswap_iter(&cluster, swpentry.val);
+	if (!desc) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	zswap_entry = desc->zswap_entry;
+	spin_unlock(&cluster->lock);
+	rcu_read_unlock();
+
+	return zswap_entry;
+}
+
+/**
+ * zswap_entry_erase - erase a zswap entry for a swap entry
+ * @swpentry: the swap entry
+ *
+ * Erases the zswap entry from the swap descriptor for the given swap entry.
+ * The cluster is locked during the erase operation.
+ *
+ * Return: the zswap entry that was erased, NULL if none existed
+ */
+void *zswap_entry_erase(swp_entry_t swpentry)
+{
+	struct vswap_cluster *cluster = NULL;
+	struct swp_desc *desc;
+	void *old;
+
+	rcu_read_lock();
+	desc = vswap_iter(&cluster, swpentry.val);
+	if (!desc) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	old = desc->zswap_entry;
+	desc->zswap_entry = NULL;
+	spin_unlock(&cluster->lock);
+	rcu_read_unlock();
+
+	return old;
+}
+
+bool zswap_empty(swp_entry_t swpentry)
+{
+	return xa_empty(&vswap_cluster_map);
+}
+#endif /* CONFIG_ZSWAP */
+
 int vswap_init(void)
 {
 	int i;
diff --git a/mm/zswap.c b/mm/zswap.c
index f7313261673ff..72441131f094e 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -223,37 +223,6 @@ static bool zswap_has_pool;
 * helpers and fwd declarations
 **********************************/
 
-static DEFINE_XARRAY(zswap_tree);
-
-#define zswap_tree_index(entry)	(entry.val)
-
-static inline void *zswap_entry_store(swp_entry_t swpentry,
-		struct zswap_entry *entry)
-{
-	pgoff_t offset = zswap_tree_index(swpentry);
-
-	return xa_store(&zswap_tree, offset, entry, GFP_KERNEL);
-}
-
-static inline void *zswap_entry_load(swp_entry_t swpentry)
-{
-	pgoff_t offset = zswap_tree_index(swpentry);
-
-	return xa_load(&zswap_tree, offset);
-}
-
-static inline void *zswap_entry_erase(swp_entry_t swpentry)
-{
-	pgoff_t offset = zswap_tree_index(swpentry);
-
-	return xa_erase(&zswap_tree, offset);
-}
-
-static inline bool zswap_empty(swp_entry_t swpentry)
-{
-	return xa_empty(&zswap_tree);
-}
-
 #define zswap_pool_debug(msg, p)			\
 	pr_debug("%s pool %s\n", msg, (p)->tfm_name)
 
@@ -1445,13 +1414,6 @@ static bool zswap_store_page(struct page *page,
 		goto compress_failed;
 
 	old = zswap_entry_store(page_swpentry, entry);
-	if (xa_is_err(old)) {
-		int err = xa_err(old);
-
-		WARN_ONCE(err != -ENOMEM, "unexpected xarray error: %d\n", err);
-		zswap_reject_alloc_fail++;
-		goto store_failed;
-	}
 
 	/*
 	 * We may have had an existing entry that became stale when
@@ -1498,8 +1460,6 @@ static bool zswap_store_page(struct page *page,
 
 	return true;
 
-store_failed:
-	zs_free(pool->zs_pool, entry->handle);
 compress_failed:
 	zswap_entry_cache_free(entry);
 	return false;
-- 
2.47.3



  parent reply	other threads:[~2026-02-08 21:59 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-08 21:58 [PATCH v3 00/20] Virtual Swap Space Nhat Pham
2026-02-08 21:58 ` [PATCH v3 01/20] mm/swap: decouple swap cache from physical swap infrastructure Nhat Pham
2026-02-08 22:26   ` [PATCH v3 00/20] Virtual Swap Space Nhat Pham
2026-02-10 17:59     ` Kairui Song
2026-02-10 18:52       ` Johannes Weiner
2026-02-10 19:11       ` Nhat Pham
2026-02-10 19:23         ` Nhat Pham
2026-02-12  5:07         ` Chris Li
2026-02-17 23:36         ` Nhat Pham
2026-02-10 21:58       ` Chris Li
2026-02-20 21:05       ` [PATCH] vswap: fix poor batching behavior of vswap free path Nhat Pham
2026-02-08 22:31   ` [PATCH v3 00/20] Virtual Swap Space Nhat Pham
2026-02-09 12:20     ` Chris Li
2026-02-10  2:36       ` Johannes Weiner
2026-02-10 21:24         ` Chris Li
2026-02-10 23:01           ` Johannes Weiner
2026-02-10 18:00       ` Nhat Pham
2026-02-10 23:17         ` Chris Li
2026-02-08 22:39   ` Nhat Pham
2026-02-09  2:22   ` [PATCH v3 01/20] mm/swap: decouple swap cache from physical swap infrastructure kernel test robot
2026-02-08 21:58 ` [PATCH v3 02/20] swap: rearrange the swap header file Nhat Pham
2026-02-08 21:58 ` [PATCH v3 03/20] mm: swap: add an abstract API for locking out swapoff Nhat Pham
2026-02-08 21:58 ` [PATCH v3 04/20] zswap: add new helpers for zswap entry operations Nhat Pham
2026-02-08 21:58 ` [PATCH v3 05/20] mm/swap: add a new function to check if a swap entry is in swap cached Nhat Pham
2026-02-08 21:58 ` [PATCH v3 06/20] mm: swap: add a separate type for physical swap slots Nhat Pham
2026-02-08 21:58 ` [PATCH v3 07/20] mm: create scaffolds for the new virtual swap implementation Nhat Pham
2026-02-08 21:58 ` [PATCH v3 08/20] zswap: prepare zswap for swap virtualization Nhat Pham
2026-02-08 21:58 ` [PATCH v3 09/20] mm: swap: allocate a virtual swap slot for each swapped out page Nhat Pham
2026-02-09 17:12   ` kernel test robot
2026-02-11 13:42   ` kernel test robot
2026-02-08 21:58 ` [PATCH v3 10/20] swap: move swap cache to virtual swap descriptor Nhat Pham
2026-02-08 21:58 ` Nhat Pham [this message]
2026-02-08 21:58 ` [PATCH v3 12/20] swap: implement the swap_cgroup API using virtual swap Nhat Pham
2026-02-08 21:58 ` [PATCH v3 13/20] swap: manage swap entry lifecycle at the virtual swap layer Nhat Pham
2026-02-08 21:58 ` [PATCH v3 14/20] mm: swap: decouple virtual swap slot from backing store Nhat Pham
2026-02-10  6:31   ` Dan Carpenter
2026-02-08 21:58 ` [PATCH v3 15/20] zswap: do not start zswap shrinker if there is no physical swap slots Nhat Pham
2026-02-08 21:58 ` [PATCH v3 16/20] swap: do not unnecesarily pin readahead swap entries Nhat Pham
2026-02-08 21:58 ` [PATCH v3 17/20] swapfile: remove zeromap bitmap Nhat Pham
2026-02-08 21:58 ` [PATCH v3 18/20] memcg: swap: only charge physical swap slots Nhat Pham
2026-02-09  2:01   ` kernel test robot
2026-02-09  2:12   ` kernel test robot
2026-02-08 21:58 ` [PATCH v3 19/20] swap: simplify swapoff using virtual swap Nhat Pham
2026-02-08 21:58 ` [PATCH v3 20/20] swapfile: replace the swap map with bitmaps Nhat Pham
2026-02-08 22:51 ` [PATCH v3 00/20] Virtual Swap Space Nhat Pham
2026-02-12 12:23   ` David Hildenbrand (Arm)
2026-02-12 17:29     ` Nhat Pham
2026-02-12 17:39       ` Nhat Pham
2026-02-12 20:11         ` David Hildenbrand (Arm)
2026-02-12 17:41       ` David Hildenbrand (Arm)
2026-02-12 17:45         ` Nhat Pham
2026-02-10 15:45 ` [syzbot ci] " syzbot ci

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=20260208215839.87595-12-nphamcs@gmail.com \
    --to=nphamcs@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=axelrasmussen@google.com \
    --cc=baohua@kernel.org \
    --cc=bhe@redhat.com \
    --cc=cgroups@vger.kernel.org \
    --cc=chengming.zhou@linux.dev \
    --cc=chrisl@kernel.org \
    --cc=christophe.leroy@csgroup.eu \
    --cc=gourry@gourry.net \
    --cc=hannes@cmpxchg.org \
    --cc=huang.ying.caritas@gmail.com \
    --cc=hughd@google.com \
    --cc=jannh@google.com \
    --cc=joshua.hahnjy@gmail.com \
    --cc=kasong@tencent.com \
    --cc=kernel-team@meta.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=mhocko@kernel.org \
    --cc=muchun.song@linux.dev \
    --cc=npache@redhat.com \
    --cc=osalvador@suse.de \
    --cc=pavel@kernel.org \
    --cc=peterx@redhat.com \
    --cc=pfalcato@suse.de \
    --cc=rafael@kernel.org \
    --cc=riel@surriel.com \
    --cc=roman.gushchin@linux.dev \
    --cc=ryan.roberts@arm.com \
    --cc=shakeel.butt@linux.dev \
    --cc=shikemeng@huaweicloud.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=weixugc@google.com \
    --cc=yosry.ahmed@linux.dev \
    --cc=yuanchu@google.com \
    --cc=zhengqi.arch@bytedance.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