From: Kairui Song <ryncsn@gmail.com>
To: linux-mm@kvack.org
Cc: Andrew Morton <akpm@linux-foundation.org>,
Kemeng Shi <shikemeng@huaweicloud.com>,
Nhat Pham <nphamcs@gmail.com>, Baoquan He <bhe@redhat.com>,
Barry Song <baohua@kernel.org>,
Johannes Weiner <hannes@cmpxchg.org>,
David Hildenbrand <david@kernel.org>,
Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
Youngjun Park <youngjun.park@lge.com>,
linux-kernel@vger.kernel.org, Chris Li <chrisl@kernel.org>,
Kairui Song <kasong@tencent.com>
Subject: [PATCH v2 03/12] mm, swap: remove redundant arguments and locking for enabling a device
Date: Wed, 28 Jan 2026 17:28:27 +0800 [thread overview]
Message-ID: <20260128-swap-table-p3-v2-3-fe0b67ef0215@tencent.com> (raw)
In-Reply-To: <20260128-swap-table-p3-v2-0-fe0b67ef0215@tencent.com>
From: Kairui Song <kasong@tencent.com>
There is no need to repeatedly pass zero map and priority values.
zeromap is similar to cluster info and swap_map, which are only used
once the swap device is exposed. And the prio values are currently
read only once set, and only used for the list insertion upon expose
or swap info display.
Signed-off-by: Kairui Song <kasong@tencent.com>
---
mm/swapfile.c | 48 ++++++++++++++++++------------------------------
1 file changed, 18 insertions(+), 30 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 53ce222c3aba..80bf0ea098f6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2652,19 +2652,6 @@ static int setup_swap_extents(struct swap_info_struct *sis,
return generic_swapfile_activate(sis, swap_file, span);
}
-static void setup_swap_info(struct swap_info_struct *si, int prio,
- unsigned long *zeromap)
-{
- si->prio = prio;
- /*
- * the plist prio is negated because plist ordering is
- * low-to-high, while swap ordering is high-to-low
- */
- si->list.prio = -si->prio;
- si->avail_list.prio = -si->prio;
- si->zeromap = zeromap;
-}
-
static void _enable_swap_info(struct swap_info_struct *si)
{
atomic_long_add(si->pages, &nr_swap_pages);
@@ -2678,17 +2665,12 @@ static void _enable_swap_info(struct swap_info_struct *si)
add_to_avail_list(si, true);
}
-static void enable_swap_info(struct swap_info_struct *si, int prio,
- unsigned long *zeromap)
+/*
+ * Called after the swap device is ready, resurrect its percpu ref, it's now
+ * safe to reference it. Add it to the list to expose it to the allocator.
+ */
+static void enable_swap_info(struct swap_info_struct *si)
{
- spin_lock(&swap_lock);
- spin_lock(&si->lock);
- setup_swap_info(si, prio, zeromap);
- spin_unlock(&si->lock);
- spin_unlock(&swap_lock);
- /*
- * Finished initializing swap device, now it's safe to reference it.
- */
percpu_ref_resurrect(&si->users);
spin_lock(&swap_lock);
spin_lock(&si->lock);
@@ -2701,7 +2683,6 @@ static void reinsert_swap_info(struct swap_info_struct *si)
{
spin_lock(&swap_lock);
spin_lock(&si->lock);
- setup_swap_info(si, si->prio, si->zeromap);
_enable_swap_info(si);
spin_unlock(&si->lock);
spin_unlock(&swap_lock);
@@ -3354,7 +3335,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
int nr_extents;
sector_t span;
unsigned long maxpages;
- unsigned long *zeromap = NULL;
struct folio *folio = NULL;
struct inode *inode = NULL;
bool inced_nr_rotate_swap = false;
@@ -3470,9 +3450,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
* Use kvmalloc_array instead of bitmap_zalloc as the allocation order might
* be above MAX_PAGE_ORDER incase of a large swap file.
*/
- zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long),
- GFP_KERNEL | __GFP_ZERO);
- if (!zeromap) {
+ si->zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!si->zeromap) {
error = -ENOMEM;
goto bad_swap_unlock_inode;
}
@@ -3541,10 +3521,17 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
if (swap_flags & SWAP_FLAG_PREFER)
prio = swap_flags & SWAP_FLAG_PRIO_MASK;
+ /*
+ * The plist prio is negated because plist ordering is
+ * low-to-high, while swap ordering is high-to-low
+ */
+ si->prio = prio;
+ si->list.prio = -si->prio;
+ si->avail_list.prio = -si->prio;
si->swap_file = swap_file;
/* Sets SWP_WRITEOK, resurrect the percpu ref, expose the swap device */
- enable_swap_info(si, prio, zeromap);
+ enable_swap_info(si);
pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n",
K(si->pages), name->name, si->prio, nr_extents,
@@ -3574,6 +3561,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
si->swap_map = NULL;
free_swap_cluster_info(si->cluster_info, si->max);
si->cluster_info = NULL;
+ kvfree(si->zeromap);
+ si->zeromap = NULL;
/*
* Clear the SWP_USED flag after all resources are freed so
* alloc_swap_info can reuse this si safely.
@@ -3581,7 +3570,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
spin_lock(&swap_lock);
si->flags = 0;
spin_unlock(&swap_lock);
- kvfree(zeromap);
if (inced_nr_rotate_swap)
atomic_dec(&nr_rotate_swap);
if (swap_file)
--
2.52.0
next prev parent reply other threads:[~2026-01-28 9:30 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-28 9:28 [PATCH v2 00/12] mm, swap: swap table phase III: remove swap_map Kairui Song
2026-01-28 9:28 ` [PATCH v2 01/12] mm, swap: protect si->swap_file properly and use as a mount indicator Kairui Song
2026-01-28 9:28 ` [PATCH v2 02/12] mm, swap: clean up swapon process and locking Kairui Song
2026-01-29 8:35 ` YoungJun Park
2026-02-02 2:31 ` Kairui Song
2026-01-28 9:28 ` Kairui Song [this message]
2026-01-28 9:28 ` [PATCH v2 04/12] mm, swap: consolidate bad slots setup and make it more robust Kairui Song
2026-01-28 9:28 ` [PATCH v2 05/12] mm/workingset: leave highest bits empty for anon shadow Kairui Song
2026-01-28 9:28 ` [PATCH v2 06/12] mm, swap: implement helpers for reserving data in the swap table Kairui Song
2026-01-29 7:28 ` YoungJun Park
2026-02-02 2:30 ` Kairui Song
2026-01-28 9:28 ` [PATCH v2 07/12] mm, swap: mark bad slots in swap table directly Kairui Song
2026-01-28 9:28 ` [PATCH v2 08/12] mm, swap: simplify swap table sanity range check Kairui Song
2026-01-28 9:28 ` [PATCH v2 09/12] mm, swap: use the swap table to track the swap count Kairui Song
2026-01-29 7:05 ` YoungJun Park
2026-01-29 8:28 ` YoungJun Park
2026-02-02 3:27 ` Kairui Song
2026-01-28 9:28 ` [PATCH v2 10/12] mm, swap: no need to truncate the scan border Kairui Song
2026-01-28 9:28 ` [PATCH v2 11/12] mm, swap: simplify checking if a folio is swapped Kairui Song
2026-01-28 9:28 ` [PATCH v2 12/12] mm, swap: no need to clear the shadow explicitly Kairui Song
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=20260128-swap-table-p3-v2-3-fe0b67ef0215@tencent.com \
--to=ryncsn@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=baohua@kernel.org \
--cc=bhe@redhat.com \
--cc=chrisl@kernel.org \
--cc=david@kernel.org \
--cc=hannes@cmpxchg.org \
--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=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