From: Kairui Song <ryncsn@gmail.com>
To: linux-mm@kvack.org
Cc: Andrew Morton <akpm@linux-foundation.org>,
Matthew Wilcox <willy@infradead.org>,
Hugh Dickins <hughd@google.com>, Chris Li <chrisl@kernel.org>,
Barry Song <baohua@kernel.org>, Baoquan He <bhe@redhat.com>,
Nhat Pham <nphamcs@gmail.com>,
Kemeng Shi <shikemeng@huaweicloud.com>,
Baolin Wang <baolin.wang@linux.alibaba.com>,
Ying Huang <ying.huang@linux.alibaba.com>,
Johannes Weiner <hannes@cmpxchg.org>,
David Hildenbrand <david@redhat.com>,
Yosry Ahmed <yosryahmed@google.com>,
Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
Zi Yan <ziy@nvidia.com>,
linux-kernel@vger.kernel.org, Kairui Song <kasong@tencent.com>
Subject: [PATCH 3/9] mm, swap: rename and move some swap cluster definition and helpers
Date: Sat, 23 Aug 2025 03:20:17 +0800 [thread overview]
Message-ID: <20250822192023.13477-4-ryncsn@gmail.com> (raw)
In-Reply-To: <20250822192023.13477-1-ryncsn@gmail.com>
From: Kairui Song <kasong@tencent.com>
No feature change, move cluster related definitions and helpers to
mm/swap.h, also tidy up and add a "swap_" prefix for cluster lock/unlock
helpers, so they can be used outside of swap files.
Signed-off-by: Kairui Song <kasong@tencent.com>
---
include/linux/swap.h | 34 ---------------
mm/swap.h | 63 ++++++++++++++++++++++++++++
mm/swapfile.c | 99 ++++++++++++++------------------------------
3 files changed, 93 insertions(+), 103 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c2da85cb7fe7..20efd9a34034 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -235,40 +235,6 @@ enum {
/* Special value in each swap_map continuation */
#define SWAP_CONT_MAX 0x7f /* Max count */
-/*
- * We use this to track usage of a cluster. A cluster is a block of swap disk
- * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All
- * free clusters are organized into a list. We fetch an entry from the list to
- * get a free cluster.
- *
- * The flags field determines if a cluster is free. This is
- * protected by cluster lock.
- */
-struct swap_cluster_info {
- spinlock_t lock; /*
- * Protect swap_cluster_info fields
- * other than list, and swap_info_struct->swap_map
- * elements corresponding to the swap cluster.
- */
- u16 count;
- u8 flags;
- u8 order;
- struct list_head list;
-};
-
-/* All on-list cluster must have a non-zero flag. */
-enum swap_cluster_flags {
- CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */
- CLUSTER_FLAG_FREE,
- CLUSTER_FLAG_NONFULL,
- CLUSTER_FLAG_FRAG,
- /* Clusters with flags above are allocatable */
- CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG,
- CLUSTER_FLAG_FULL,
- CLUSTER_FLAG_DISCARD,
- CLUSTER_FLAG_MAX,
-};
-
/*
* The first page in the swap file is the swap header, which is always marked
* bad to prevent it from being allocated as an entry. This also prevents the
diff --git a/mm/swap.h b/mm/swap.h
index bb2adbfd64a9..223b40f2d37e 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -7,10 +7,73 @@ struct swap_iocb;
extern int page_cluster;
+#ifdef CONFIG_THP_SWAP
+#define SWAPFILE_CLUSTER HPAGE_PMD_NR
+#define swap_entry_order(order) (order)
+#else
+#define SWAPFILE_CLUSTER 256
+#define swap_entry_order(order) 0
+#endif
+
+/*
+ * We use this to track usage of a cluster. A cluster is a block of swap disk
+ * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All
+ * free clusters are organized into a list. We fetch an entry from the list to
+ * get a free cluster.
+ *
+ * The flags field determines if a cluster is free. This is
+ * protected by cluster lock.
+ */
+struct swap_cluster_info {
+ spinlock_t lock; /*
+ * Protect swap_cluster_info fields
+ * other than list, and swap_info_struct->swap_map
+ * elements corresponding to the swap cluster.
+ */
+ u16 count;
+ u8 flags;
+ u8 order;
+ struct list_head list;
+};
+
+/* All on-list cluster must have a non-zero flag. */
+enum swap_cluster_flags {
+ CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */
+ CLUSTER_FLAG_FREE,
+ CLUSTER_FLAG_NONFULL,
+ CLUSTER_FLAG_FRAG,
+ /* Clusters with flags above are allocatable */
+ CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG,
+ CLUSTER_FLAG_FULL,
+ CLUSTER_FLAG_DISCARD,
+ CLUSTER_FLAG_MAX,
+};
+
#ifdef CONFIG_SWAP
#include <linux/swapops.h> /* for swp_offset */
#include <linux/blk_types.h> /* for bio_end_io_t */
+static inline struct swap_cluster_info *swp_offset_cluster(
+ struct swap_info_struct *si, pgoff_t offset)
+{
+ return &si->cluster_info[offset / SWAPFILE_CLUSTER];
+}
+
+static inline struct swap_cluster_info *swap_cluster_lock(
+ struct swap_info_struct *si,
+ unsigned long offset)
+{
+ struct swap_cluster_info *ci = swp_offset_cluster(si, offset);
+
+ spin_lock(&ci->lock);
+ return ci;
+}
+
+static inline void swap_cluster_unlock(struct swap_cluster_info *ci)
+{
+ spin_unlock(&ci->lock);
+}
+
/* linux/mm/page_io.c */
int sio_pool_init(void);
struct swap_iocb;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 12f2580ebe8d..618cf4333a3d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -58,9 +58,6 @@ static void swap_entries_free(struct swap_info_struct *si,
static void swap_range_alloc(struct swap_info_struct *si,
unsigned int nr_entries);
static bool folio_swapcache_freeable(struct folio *folio);
-static struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
- unsigned long offset);
-static inline void unlock_cluster(struct swap_cluster_info *ci);
static DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
@@ -259,9 +256,9 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
* swap_map is HAS_CACHE only, which means the slots have no page table
* reference or pending writeback, and can't be allocated to others.
*/
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
need_reclaim = swap_only_has_cache(si, offset, nr_pages);
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
if (!need_reclaim)
goto out_unlock;
@@ -386,20 +383,7 @@ static void discard_swap_cluster(struct swap_info_struct *si,
}
}
-#ifdef CONFIG_THP_SWAP
-#define SWAPFILE_CLUSTER HPAGE_PMD_NR
-
-#define swap_entry_order(order) (order)
-#else
-#define SWAPFILE_CLUSTER 256
-
-/*
- * Define swap_entry_order() as constant to let compiler to optimize
- * out some code if !CONFIG_THP_SWAP
- */
-#define swap_entry_order(order) 0
-#endif
-#define LATENCY_LIMIT 256
+#define LATENCY_LIMIT 256
static inline bool cluster_is_empty(struct swap_cluster_info *info)
{
@@ -426,34 +410,12 @@ static inline unsigned int cluster_index(struct swap_info_struct *si,
return ci - si->cluster_info;
}
-static inline struct swap_cluster_info *offset_to_cluster(struct swap_info_struct *si,
- unsigned long offset)
-{
- return &si->cluster_info[offset / SWAPFILE_CLUSTER];
-}
-
static inline unsigned int cluster_offset(struct swap_info_struct *si,
struct swap_cluster_info *ci)
{
return cluster_index(si, ci) * SWAPFILE_CLUSTER;
}
-static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
- unsigned long offset)
-{
- struct swap_cluster_info *ci;
-
- ci = offset_to_cluster(si, offset);
- spin_lock(&ci->lock);
-
- return ci;
-}
-
-static inline void unlock_cluster(struct swap_cluster_info *ci)
-{
- spin_unlock(&ci->lock);
-}
-
static void move_cluster(struct swap_info_struct *si,
struct swap_cluster_info *ci, struct list_head *list,
enum swap_cluster_flags new_flags)
@@ -809,7 +771,7 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
}
out:
relocate_cluster(si, ci);
- unlock_cluster(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);
@@ -876,7 +838,7 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
if (ci->flags == CLUSTER_FLAG_NONE)
relocate_cluster(si, ci);
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
if (to_scan <= 0)
break;
}
@@ -915,7 +877,7 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
if (offset == SWAP_ENTRY_INVALID)
goto new_cluster;
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
/* Cluster could have been used by another order */
if (cluster_is_usable(ci, order)) {
if (cluster_is_empty(ci))
@@ -923,7 +885,7 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
found = alloc_swap_scan_cluster(si, ci, offset,
order, usage);
} else {
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
}
if (found)
goto done;
@@ -1204,7 +1166,7 @@ static bool swap_alloc_fast(swp_entry_t *entry,
if (!si || !offset || !get_swap_device_info(si))
return false;
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
if (cluster_is_usable(ci, order)) {
if (cluster_is_empty(ci))
offset = cluster_offset(si, ci);
@@ -1212,7 +1174,7 @@ static bool swap_alloc_fast(swp_entry_t *entry,
if (found)
*entry = swp_entry(si->type, found);
} else {
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
}
put_swap_device(si);
@@ -1480,14 +1442,14 @@ static void swap_entries_put_cache(struct swap_info_struct *si,
unsigned long offset = swp_offset(entry);
struct swap_cluster_info *ci;
- ci = lock_cluster(si, offset);
- if (swap_only_has_cache(si, offset, nr))
+ ci = swap_cluster_lock(si, offset);
+ if (swap_only_has_cache(si, offset, nr)) {
swap_entries_free(si, ci, entry, nr);
- else {
+ } else {
for (int i = 0; i < nr; i++, entry.val++)
swap_entry_put_locked(si, ci, entry, SWAP_HAS_CACHE);
}
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
}
static bool swap_entries_put_map(struct swap_info_struct *si,
@@ -1505,7 +1467,7 @@ static bool swap_entries_put_map(struct swap_info_struct *si,
if (count != 1 && count != SWAP_MAP_SHMEM)
goto fallback;
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
if (!swap_is_last_map(si, offset, nr, &has_cache)) {
goto locked_fallback;
}
@@ -1514,21 +1476,20 @@ static bool swap_entries_put_map(struct swap_info_struct *si,
else
for (i = 0; i < nr; i++)
WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE);
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
return has_cache;
fallback:
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
locked_fallback:
for (i = 0; i < nr; i++, entry.val++) {
count = swap_entry_put_locked(si, ci, entry, 1);
if (count == SWAP_HAS_CACHE)
has_cache = true;
}
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
return has_cache;
-
}
/*
@@ -1578,7 +1539,7 @@ static void swap_entries_free(struct swap_info_struct *si,
unsigned char *map_end = map + nr_pages;
/* It should never free entries across different clusters */
- VM_BUG_ON(ci != offset_to_cluster(si, offset + nr_pages - 1));
+ VM_BUG_ON(ci != swp_offset_cluster(si, offset + nr_pages - 1));
VM_BUG_ON(cluster_is_empty(ci));
VM_BUG_ON(ci->count < nr_pages);
@@ -1653,9 +1614,9 @@ bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry)
struct swap_cluster_info *ci;
int count;
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
count = swap_count(si->swap_map[offset]);
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
return !!count;
}
@@ -1678,7 +1639,7 @@ int swp_swapcount(swp_entry_t entry)
offset = swp_offset(entry);
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
count = swap_count(si->swap_map[offset]);
if (!(count & COUNT_CONTINUED))
@@ -1701,7 +1662,7 @@ int swp_swapcount(swp_entry_t entry)
n *= (SWAP_CONT_MAX + 1);
} while (tmp_count & COUNT_CONTINUED);
out:
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
return count;
}
@@ -1716,7 +1677,7 @@ static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
int i;
bool ret = false;
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
if (nr_pages == 1) {
if (swap_count(map[roffset]))
ret = true;
@@ -1729,7 +1690,7 @@ static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
}
}
unlock_out:
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
return ret;
}
@@ -2662,8 +2623,8 @@ static void wait_for_allocation(struct swap_info_struct *si)
BUG_ON(si->flags & SWP_WRITEOK);
for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) {
- ci = lock_cluster(si, offset);
- unlock_cluster(ci);
+ ci = swap_cluster_lock(si, offset);
+ swap_cluster_unlock(ci);
}
}
@@ -3579,7 +3540,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
offset = swp_offset(entry);
VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);
VM_WARN_ON(usage == 1 && nr > 1);
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
err = 0;
for (i = 0; i < nr; i++) {
@@ -3634,7 +3595,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
}
unlock_out:
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
return err;
}
@@ -3733,7 +3694,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
offset = swp_offset(entry);
- ci = lock_cluster(si, offset);
+ ci = swap_cluster_lock(si, offset);
count = swap_count(si->swap_map[offset]);
@@ -3793,7 +3754,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
out_unlock_cont:
spin_unlock(&si->cont_lock);
out:
- unlock_cluster(ci);
+ swap_cluster_unlock(ci);
put_swap_device(si);
outer:
if (page)
--
2.51.0
next prev parent reply other threads:[~2025-08-22 19:21 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-22 19:20 [PATCH 0/9] mm, swap: introduce swap table as swap cache (phase I) Kairui Song
2025-08-22 19:20 ` [PATCH 1/9] mm, swap: use unified helper for swap cache look up Kairui Song
2025-08-27 2:47 ` Chris Li
2025-08-27 3:50 ` Chris Li
2025-08-27 13:45 ` Kairui Song
2025-08-27 3:52 ` Baoquan He
2025-08-27 13:46 ` Kairui Song
2025-08-28 3:20 ` Baolin Wang
2025-09-01 23:50 ` Barry Song
2025-09-02 6:12 ` Kairui Song
2025-09-02 6:52 ` Chris Li
2025-09-02 10:06 ` David Hildenbrand
2025-09-02 12:32 ` Chris Li
2025-09-02 13:18 ` David Hildenbrand
2025-09-02 16:38 ` Kairui Song
2025-09-02 10:10 ` David Hildenbrand
2025-09-02 17:13 ` Kairui Song
2025-09-03 8:00 ` David Hildenbrand
2025-09-03 17:41 ` Nhat Pham
2025-09-04 16:05 ` Kairui Song
2025-08-22 19:20 ` [PATCH 2/9] mm, swap: always lock and check the swap cache folio before use Kairui Song
2025-08-27 6:13 ` Chris Li
2025-08-27 13:44 ` Kairui Song
2025-08-30 1:42 ` Chris Li
2025-08-27 7:03 ` Chris Li
2025-08-27 14:35 ` Kairui Song
2025-08-28 3:41 ` Baolin Wang
2025-08-28 18:05 ` Kairui Song
2025-08-30 1:53 ` Chris Li
2025-08-30 15:15 ` Kairui Song
2025-08-30 17:17 ` Chris Li
2025-09-01 18:17 ` Kairui Song
2025-09-01 21:10 ` Chris Li
2025-09-02 5:40 ` Barry Song
2025-09-02 10:18 ` David Hildenbrand
2025-09-02 10:21 ` David Hildenbrand
2025-09-02 12:46 ` Chris Li
2025-09-02 13:27 ` Kairui Song
2025-08-22 19:20 ` Kairui Song [this message]
2025-08-30 2:31 ` [PATCH 3/9] mm, swap: rename and move some swap cluster definition and helpers Chris Li
2025-09-02 5:53 ` Barry Song
2025-09-02 10:20 ` David Hildenbrand
2025-09-02 12:50 ` Chris Li
2025-08-22 19:20 ` [PATCH 4/9] mm, swap: tidy up swap device and cluster info helpers Kairui Song
2025-08-27 3:47 ` Baoquan He
2025-08-27 17:44 ` Chris Li
2025-08-27 23:46 ` Baoquan He
2025-08-30 2:38 ` Chris Li
2025-09-02 6:01 ` Barry Song
2025-09-03 9:28 ` David Hildenbrand
2025-09-02 6:02 ` Barry Song
2025-09-02 13:33 ` David Hildenbrand
2025-09-02 15:03 ` Kairui Song
2025-09-03 8:11 ` David Hildenbrand
2025-08-22 19:20 ` [PATCH 5/9] mm/shmem, swap: remove redundant error handling for replacing folio Kairui Song
2025-08-25 3:02 ` Baolin Wang
2025-08-25 9:45 ` Kairui Song
2025-08-30 2:41 ` Chris Li
2025-09-03 8:25 ` David Hildenbrand
2025-08-22 19:20 ` [PATCH 6/9] mm, swap: use the swap table for the swap cache and switch API Kairui Song
2025-08-30 1:54 ` Baoquan He
2025-08-30 3:40 ` Chris Li
2025-08-30 3:34 ` Chris Li
2025-08-30 16:52 ` Kairui Song
2025-08-31 1:00 ` Chris Li
2025-09-02 11:51 ` Kairui Song
2025-09-02 9:55 ` Barry Song
2025-09-02 11:58 ` Kairui Song
2025-09-02 23:44 ` Barry Song
2025-09-03 2:12 ` Kairui Song
2025-09-03 2:31 ` Barry Song
2025-09-03 11:41 ` David Hildenbrand
2025-09-03 12:54 ` Kairui Song
2025-09-04 9:28 ` David Hildenbrand
2025-08-22 19:20 ` [PATCH 7/9] mm, swap: remove contention workaround for swap cache Kairui Song
2025-08-30 4:07 ` Chris Li
2025-08-30 15:24 ` Kairui Song
2025-08-31 15:54 ` Kairui Song
2025-08-31 20:06 ` Chris Li
2025-08-31 20:04 ` Chris Li
2025-09-02 10:06 ` Barry Song
2025-08-22 19:20 ` [PATCH 8/9] mm, swap: implement dynamic allocation of swap table Kairui Song
2025-08-30 4:17 ` Chris Li
2025-09-02 11:15 ` Barry Song
2025-09-02 13:17 ` Chris Li
2025-09-02 16:57 ` Kairui Song
2025-09-02 23:31 ` Barry Song
2025-09-03 2:13 ` Kairui Song
2025-09-03 12:35 ` Chris Li
2025-09-03 20:52 ` Barry Song
2025-09-04 6:50 ` Chris Li
2025-08-22 19:20 ` [PATCH 9/9] mm, swap: use a single page for swap table when the size fits Kairui Song
2025-08-30 4:23 ` Chris Li
2025-08-26 22:00 ` [PATCH 0/9] mm, swap: introduce swap table as swap cache (phase I) Chris Li
2025-08-30 5:44 ` Chris Li
2025-09-04 16:36 ` Kairui Song
2025-09-04 18:50 ` 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=20250822192023.13477-4-ryncsn@gmail.com \
--to=ryncsn@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=bhe@redhat.com \
--cc=chrisl@kernel.org \
--cc=david@redhat.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=kasong@tencent.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=nphamcs@gmail.com \
--cc=shikemeng@huaweicloud.com \
--cc=willy@infradead.org \
--cc=ying.huang@linux.alibaba.com \
--cc=yosryahmed@google.com \
--cc=ziy@nvidia.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