[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAF8kJuPOTm8e-GLQ=SuQo_CWqjNy05CWFO0nG5OsMbhjjJfXqA@mail.gmail.com>
Date: Sat, 6 Sep 2025 00:09:44 -0700
From: Chris Li <chrisl@...nel.org>
To: Kairui Song <kasong@...cent.com>
Cc: linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>,
Matthew Wilcox <willy@...radead.org>, Hugh Dickins <hughd@...gle.com>, Barry Song <baohua@...nel.org>,
Baoquan He <bhe@...hat.com>, Nhat Pham <nphamcs@...il.com>,
Kemeng Shi <shikemeng@...weicloud.com>, Baolin Wang <baolin.wang@...ux.alibaba.com>,
Ying Huang <ying.huang@...ux.alibaba.com>, Johannes Weiner <hannes@...xchg.org>,
David Hildenbrand <david@...hat.com>, Yosry Ahmed <yosryahmed@...gle.com>,
Lorenzo Stoakes <lorenzo.stoakes@...cle.com>, Zi Yan <ziy@...dia.com>,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 10/15] mm, swap: wrap swap cache replacement with a helper
Acked-by: Chris Li <chrisl@...nel.org>
Chris
On Fri, Sep 5, 2025 at 12:15 PM Kairui Song <ryncsn@...il.com> wrote:
>
> From: Kairui Song <kasong@...cent.com>
>
> There are currently three swap cache users that are trying to replace an
> existing folio with a new one: huge memory splitting, migration, and
> shmem replacement. What they are doing is quite similar.
>
> Introduce a common helper for this. In later commits, they can be easily
> switched to use the swap table by updating this helper.
>
> The newly added helper also makes the swap cache API better defined, and
> debugging is easier.
>
> Signed-off-by: Kairui Song <kasong@...cent.com>
> ---
> mm/huge_memory.c | 5 ++---
> mm/migrate.c | 11 +++--------
> mm/shmem.c | 10 ++--------
> mm/swap.h | 3 +++
> mm/swap_state.c | 32 ++++++++++++++++++++++++++++++++
> 5 files changed, 42 insertions(+), 19 deletions(-)
>
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 26cedfcd7418..a4d192c8d794 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -3798,9 +3798,8 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
> * NOTE: shmem in swap cache is not supported yet.
> */
> if (swap_cache) {
> - __xa_store(&swap_cache->i_pages,
> - swap_cache_index(new_folio->swap),
> - new_folio, 0);
> + __swap_cache_replace_folio(swap_cache, new_folio->swap,
> + folio, new_folio);
> continue;
> }
>
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 8e435a078fc3..7e1d01aa8c85 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -566,7 +566,6 @@ static int __folio_migrate_mapping(struct address_space *mapping,
> struct zone *oldzone, *newzone;
> int dirty;
> long nr = folio_nr_pages(folio);
> - long entries, i;
>
> if (!mapping) {
> /* Take off deferred split queue while frozen and memcg set */
> @@ -615,9 +614,6 @@ static int __folio_migrate_mapping(struct address_space *mapping,
> if (folio_test_swapcache(folio)) {
> folio_set_swapcache(newfolio);
> newfolio->private = folio_get_private(folio);
> - entries = nr;
> - } else {
> - entries = 1;
> }
>
> /* Move dirty while folio refs frozen and newfolio not yet exposed */
> @@ -627,11 +623,10 @@ static int __folio_migrate_mapping(struct address_space *mapping,
> folio_set_dirty(newfolio);
> }
>
> - /* Swap cache still stores N entries instead of a high-order entry */
> - for (i = 0; i < entries; i++) {
> + if (folio_test_swapcache(folio))
> + __swap_cache_replace_folio(mapping, folio->swap, folio, newfolio);
> + else
> xas_store(&xas, newfolio);
> - xas_next(&xas);
> - }
>
> /*
> * Drop cache reference from old folio by unfreezing
> diff --git a/mm/shmem.c b/mm/shmem.c
> index cc6a0007c7a6..823ceae9dff8 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -2123,10 +2123,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
> struct folio *new, *old = *foliop;
> swp_entry_t entry = old->swap;
> struct address_space *swap_mapping = swap_address_space(entry);
> - pgoff_t swap_index = swap_cache_index(entry);
> - XA_STATE(xas, &swap_mapping->i_pages, swap_index);
> int nr_pages = folio_nr_pages(old);
> - int error = 0, i;
> + int error = 0;
>
> /*
> * We have arrived here because our zones are constrained, so don't
> @@ -2155,12 +2153,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
> new->swap = entry;
> folio_set_swapcache(new);
>
> - /* Swap cache still stores N entries instead of a high-order entry */
> xa_lock_irq(&swap_mapping->i_pages);
> - for (i = 0; i < nr_pages; i++) {
> - WARN_ON_ONCE(xas_store(&xas, new));
> - xas_next(&xas);
> - }
> + __swap_cache_replace_folio(swap_mapping, entry, old, new);
> xa_unlock_irq(&swap_mapping->i_pages);
>
> mem_cgroup_replace_folio(old, new);
> diff --git a/mm/swap.h b/mm/swap.h
> index 8b38577a4e04..a139c9131244 100644
> --- a/mm/swap.h
> +++ b/mm/swap.h
> @@ -182,6 +182,9 @@ int swap_cache_add_folio(struct folio *folio, swp_entry_t entry,
> void swap_cache_del_folio(struct folio *folio);
> void __swap_cache_del_folio(struct folio *folio,
> swp_entry_t entry, void *shadow);
> +void __swap_cache_replace_folio(struct address_space *address_space,
> + swp_entry_t entry,
> + struct folio *old, struct folio *new);
> void swap_cache_clear_shadow(int type, unsigned long begin,
> unsigned long end);
>
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index f3a32a06a950..38f5f4cf565d 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -234,6 +234,38 @@ void swap_cache_del_folio(struct folio *folio)
> folio_ref_sub(folio, folio_nr_pages(folio));
> }
>
> +/**
> + * __swap_cache_replace_folio - Replace a folio in the swap cache.
> + * @mapping: Swap mapping address space.
> + * @entry: The first swap entry that the new folio corresponds to.
> + * @old: The old folio to be replaced.
> + * @new: The new folio.
> + *
> + * Replace a existing folio in the swap cache with a new folio.
> + *
> + * Context: Caller must ensure both folios are locked, and lock the
> + * swap address_space that holds the entries to be replaced.
> + */
> +void __swap_cache_replace_folio(struct address_space *mapping,
> + swp_entry_t entry,
> + struct folio *old, struct folio *new)
> +{
> + unsigned long nr_pages = folio_nr_pages(new);
> + unsigned long offset = swap_cache_index(entry);
> + unsigned long end = offset + nr_pages;
> + XA_STATE(xas, &mapping->i_pages, offset);
> +
> + VM_WARN_ON_ONCE(entry.val != new->swap.val);
> + VM_WARN_ON_ONCE(!folio_test_locked(old) || !folio_test_locked(new));
> + VM_WARN_ON_ONCE(!folio_test_swapcache(old) || !folio_test_swapcache(new));
> +
> + /* Swap cache still stores N entries instead of a high-order entry */
> + do {
> + WARN_ON_ONCE(xas_store(&xas, new) != old);
> + xas_next(&xas);
> + } while (++offset < end);
> +}
> +
> /**
> * swap_cache_clear_shadow - Clears a set of shadows in the swap cache.
> * @type: Indicates the swap device.
> --
> 2.51.0
>
>
Powered by blists - more mailing lists