Commit 78524b05 authored by Kairui Song's avatar Kairui Song Committed by Andrew Morton
Browse files

mm, swap: avoid redundant swap device pinning 

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/20250313165935.63303-4-ryncsn@gmail.com


Signed-off-by: default avatarKairui Song <kasong@tencent.com>
Reviewed-by: default avatarBaoquan He <bhe@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 3123fb0a

mm/swap_state.c

+8 −6
Original line number Diff line number Diff line
@@ -426,17 +426,13 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, 
		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 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, 
	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_entry_t entry, gfp_t gfp_mask, 
		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_entry_t entry, gfp_t gfp_mask, 


	if (page_allocated)

		swap_read_folio(folio, plug);



	put_swap_device(si);

	return folio;

}

mm/zswap.c

+7 −1
Original line number Diff line number Diff line
@@ -1051,14 +1051,20 @@ static int zswap_writeback_entry(struct zswap_entry *entry, 
	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;