The patch titled
Subject: mm, swap: avoid redundant swap device pinning
has been added to the -mm mm-unstable branch. Its filename is
mm-swap-avoid-redundant-swap-device-pinning.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-swap-avoid-redundant-swap-device-pinning.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Kairui Song <kasong@xxxxxxxxxxx>
Subject: mm, swap: avoid redundant swap device pinning
Date: Tue, 25 Feb 2025 02:02:08 +0800
Currently __read_swap_cache_async() has get/put_swap_device() calls to
increase/decrease a swap device reference to prevent swapoff. While some
of its callers have already held the swap device reference, e.g in
do_swap_page() and shmem_swapin_folio() where __read_swap_cache_async()
will finally called. Now there are only two callers not holding a swap
device reference, so make them hold a reference instead. And drop the
get/put_swap_device calls in __read_swap_cache_async. This should reduce
the overhead for swap in during page fault slightly.
Link: https://lkml.kernel.org/r/20250224180212.22802-4-ryncsn@xxxxxxxxx
Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
Reviewed-by: Baoquan He <bhe@xxxxxxxxxx>
Cc: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Cc: Barry Song <v-songbaohua@xxxxxxxx>
Cc: Chris Li <chrisl@xxxxxxxxxx>
Cc: "Huang, Ying" <ying.huang@xxxxxxxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Kalesh Singh <kaleshsingh@xxxxxxxxxx>
Cc: Matthew Wilcow (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Nhat Pham <nphamcs@xxxxxxxxx>
Cc: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/swap_state.c | 14 ++++++++------
mm/zswap.c | 6 ++++++
2 files changed, 14 insertions(+), 6 deletions(-)
--- a/mm/swap_state.c~mm-swap-avoid-redundant-swap-device-pinning
+++ a/mm/swap_state.c
@@ -426,17 +426,13 @@ struct folio *__read_swap_cache_async(sw
struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated,
bool skip_if_exists)
{
- struct swap_info_struct *si;
+ struct swap_info_struct *si = swp_swap_info(entry);
struct folio *folio;
struct folio *new_folio = NULL;
struct folio *result = NULL;
void *shadow = NULL;
*new_page_allocated = false;
- si = get_swap_device(entry);
- if (!si)
- return NULL;
-
for (;;) {
int err;
/*
@@ -532,7 +528,6 @@ fail_unlock:
put_swap_folio(new_folio, entry);
folio_unlock(new_folio);
put_and_return:
- put_swap_device(si);
if (!(*new_page_allocated) && new_folio)
folio_put(new_folio);
return result;
@@ -552,11 +547,16 @@ struct folio *read_swap_cache_async(swp_
struct vm_area_struct *vma, unsigned long addr,
struct swap_iocb **plug)
{
+ struct swap_info_struct *si;
bool page_allocated;
struct mempolicy *mpol;
pgoff_t ilx;
struct folio *folio;
+ si = get_swap_device(entry);
+ if (!si)
+ return NULL;
+
mpol = get_vma_policy(vma, addr, 0, &ilx);
folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
&page_allocated, false);
@@ -564,6 +564,8 @@ struct folio *read_swap_cache_async(swp_
if (page_allocated)
swap_read_folio(folio, plug);
+
+ put_swap_device(si);
return folio;
}
--- a/mm/zswap.c~mm-swap-avoid-redundant-swap-device-pinning
+++ a/mm/zswap.c
@@ -1051,14 +1051,20 @@ static int zswap_writeback_entry(struct
struct folio *folio;
struct mempolicy *mpol;
bool folio_was_allocated;
+ struct swap_info_struct *si;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
};
/* try to allocate swap cache folio */
+ si = get_swap_device(swpentry);
+ if (!si)
+ return -EEXIST;
+
mpol = get_task_policy(current);
folio = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
NO_INTERLEAVE_INDEX, &folio_was_allocated, true);
+ put_swap_device(si);
if (!folio)
return -ENOMEM;
_
Patches currently in -mm which might be from kasong@xxxxxxxxxxx are
mm-swap-avoid-reclaiming-irrelevant-swap-cache.patch
mm-swap-drop-the-flag-ttrs_direct.patch
mm-swap-avoid-redundant-swap-device-pinning.patch
mm-swap-dont-update-the-counter-up-front.patch
mm-swap-use-percpu-cluster-as-allocation-fast-path.patch
mm-swap-remove-swap-slot-cache.patch
mm-swap-simplify-folio-swap-allocation.patch
