[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAF8kJuPkipwbjiKNe_xSyDJwPxUvNuaqO94EqXyeUadUcPb06A@mail.gmail.com>
Date: Fri, 5 Sep 2025 22:45:12 -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 09/15] mm, swap: cleanup swap cache API and add kerneldoc
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>
>
> In preparation for replacing the swap cache backend with the swap table,
> clean up and add proper kernel doc for all swap cache APIs. Now all swap
> cache APIs are well-defined with consistent names.
>
> No feature change, only renaming and documenting.
>
> Signed-off-by: Kairui Song <kasong@...cent.com>
> ---
> mm/filemap.c | 2 +-
> mm/memory-failure.c | 2 +-
> mm/memory.c | 2 +-
> mm/swap.h | 48 ++++++++++++++-----------
> mm/swap_state.c | 86 ++++++++++++++++++++++++++++++++-------------
> mm/swapfile.c | 8 ++---
> mm/vmscan.c | 2 +-
> mm/zswap.c | 2 +-
> 8 files changed, 98 insertions(+), 54 deletions(-)
>
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 344ab106c21c..29ea56999a16 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -4517,7 +4517,7 @@ static void filemap_cachestat(struct address_space *mapping,
> * invalidation, so there might not be
> * a shadow in the swapcache (yet).
> */
> - shadow = get_shadow_from_swap_cache(swp);
> + shadow = swap_cache_get_shadow(swp);
> if (!shadow)
> goto resched;
> }
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index b93ab99ad3ef..922526533cd9 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1199,7 +1199,7 @@ static int me_swapcache_clean(struct page_state *ps, struct page *p)
> struct folio *folio = page_folio(p);
> int ret;
>
> - delete_from_swap_cache(folio);
> + swap_cache_del_folio(folio);
>
> ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_RECOVERED;
> folio_unlock(folio);
> diff --git a/mm/memory.c b/mm/memory.c
> index 5808c4ef21b3..41e641823558 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -4699,7 +4699,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
>
> memcg1_swapin(entry, nr_pages);
>
> - shadow = get_shadow_from_swap_cache(entry);
> + shadow = swap_cache_get_shadow(entry);
> if (shadow)
> workingset_refault(folio, shadow);
>
> diff --git a/mm/swap.h b/mm/swap.h
> index a65e72edb087..8b38577a4e04 100644
> --- a/mm/swap.h
> +++ b/mm/swap.h
> @@ -164,17 +164,29 @@ static inline bool folio_matches_swap_entry(const struct folio *folio,
> return folio->swap.val == round_down(entry.val, folio_nr_pages(folio));
> }
>
> +/*
> + * All swap cache helpers below require the caller to ensure the swap entries
> + * used are valid and stablize the device by any of the following ways:
> + * - Hold a reference by get_swap_device(): this ensures a single entry is
> + * valid and increases the swap device's refcount.
> + * - Locking a folio in the swap cache: this ensures the folio's swap entries
> + * are valid and pinned, also implies reference to the device.
> + * - Locking anything referencing the swap entry: e.g. PTL that protects
> + * swap entries in the page table, similar to locking swap cache folio.
> + * - See the comment of get_swap_device() for more complex usage.
> + */
> +struct folio *swap_cache_get_folio(swp_entry_t entry);
> +void *swap_cache_get_shadow(swp_entry_t entry);
> +int swap_cache_add_folio(struct folio *folio, swp_entry_t entry,
> + gfp_t gfp, void **shadow);
> +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_clear_shadow(int type, unsigned long begin,
> + unsigned long end);
> +
> void show_swap_cache_info(void);
> -void *get_shadow_from_swap_cache(swp_entry_t entry);
> -int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
> - gfp_t gfp, void **shadowp);
> -void __delete_from_swap_cache(struct folio *folio,
> - swp_entry_t entry, void *shadow);
> -void delete_from_swap_cache(struct folio *folio);
> -void clear_shadow_from_swap_cache(int type, unsigned long begin,
> - unsigned long end);
> void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr);
> -struct folio *swap_cache_get_folio(swp_entry_t entry);
> 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);
> @@ -302,28 +314,22 @@ static inline struct folio *swap_cache_get_folio(swp_entry_t entry)
> return NULL;
> }
>
> -static inline void *get_shadow_from_swap_cache(swp_entry_t entry)
> +static inline void *swap_cache_get_shadow(swp_entry_t entry)
> {
> return NULL;
> }
>
> -static inline int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
> - gfp_t gfp_mask, void **shadowp)
> -{
> - return -1;
> -}
> -
> -static inline void __delete_from_swap_cache(struct folio *folio,
> - swp_entry_t entry, void *shadow)
> +static inline int swap_cache_add_folio(swp_entry_t entry, struct folio *folio,
> + gfp_t gfp, void **shadow)
> {
> + return -EINVAL;
> }
>
> -static inline void delete_from_swap_cache(struct folio *folio)
> +static inline void swap_cache_del_folio(struct folio *folio)
> {
> }
>
> -static inline void clear_shadow_from_swap_cache(int type, unsigned long begin,
> - unsigned long end)
> +static inline void __swap_cache_del_folio(swp_entry_t entry, struct folio *folio, void *shadow)
> {
> }
>
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index 0ad4f3b41f1b..f3a32a06a950 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -78,8 +78,8 @@ void show_swap_cache_info(void)
> * Context: Caller must ensure @entry is valid and protect the swap device
> * with reference count or locks.
> * Return: Returns the found folio on success, NULL otherwise. The caller
> - * must lock and check if the folio still matches the swap entry before
> - * use (e.g. with folio_matches_swap_entry).
> + * must lock nd check if the folio still matches the swap entry before
> + * use (e.g., folio_matches_swap_entry).
> */
> struct folio *swap_cache_get_folio(swp_entry_t entry)
> {
> @@ -90,7 +90,15 @@ struct folio *swap_cache_get_folio(swp_entry_t entry)
> return folio;
> }
>
> -void *get_shadow_from_swap_cache(swp_entry_t entry)
> +/**
> + * swap_cache_get_shadow - Looks up a shadow in the swap cache.
> + * @entry: swap entry used for the lookup.
> + *
> + * Context: Caller must ensure @entry is valid and protect the swap device
> + * with reference count or locks.
> + * Return: Returns either NULL or an XA_VALUE (shadow).
> + */
> +void *swap_cache_get_shadow(swp_entry_t entry)
> {
> struct address_space *address_space = swap_address_space(entry);
> pgoff_t idx = swap_cache_index(entry);
> @@ -102,12 +110,21 @@ void *get_shadow_from_swap_cache(swp_entry_t entry)
> return NULL;
> }
>
> -/*
> - * add_to_swap_cache resembles filemap_add_folio on swapper_space,
> - * but sets SwapCache flag and 'swap' instead of mapping and index.
> +/**
> + * swap_cache_add_folio - Add a folio into the swap cache.
> + * @folio: The folio to be added.
> + * @entry: The swap entry corresponding to the folio.
> + * @gfp: gfp_mask for XArray node allocation.
> + * @shadowp: If a shadow is found, return the shadow.
> + *
> + * Context: Caller must ensure @entry is valid and protect the swap device
> + * with reference count or locks.
> + * The caller also needs to mark the corresponding swap_map slots with
> + * SWAP_HAS_CACHE to avoid race or conflict.
> + * Return: Returns 0 on success, error code otherwise.
> */
> -int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
> - gfp_t gfp, void **shadowp)
> +int swap_cache_add_folio(struct folio *folio, swp_entry_t entry,
> + gfp_t gfp, void **shadowp)
> {
> struct address_space *address_space = swap_address_space(entry);
> pgoff_t idx = swap_cache_index(entry);
> @@ -155,12 +172,20 @@ int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
> return xas_error(&xas);
> }
>
> -/*
> - * This must be called only on folios that have
> - * been verified to be in the swap cache.
> +/**
> + * __swap_cache_del_folio - Removes a folio from the swap cache.
> + * @folio: The folio.
> + * @entry: The first swap entry that the folio corresponds to.
> + * @shadow: shadow value to be filled in the swap cache.
> + *
> + * Removes a folio from the swap cache and fills a shadow in place.
> + * This won't put the folio's refcount. The caller has to do that.
> + *
> + * Context: Caller must hold the xa_lock, ensure the folio is
> + * locked and in the swap cache, using the index of @entry.
> */
> -void __delete_from_swap_cache(struct folio *folio,
> - swp_entry_t entry, void *shadow)
> +void __swap_cache_del_folio(struct folio *folio,
> + swp_entry_t entry, void *shadow)
> {
> struct address_space *address_space = swap_address_space(entry);
> int i;
> @@ -186,27 +211,40 @@ void __delete_from_swap_cache(struct folio *folio,
> __lruvec_stat_mod_folio(folio, NR_SWAPCACHE, -nr);
> }
>
> -/*
> - * This must be called only on folios that have
> - * been verified to be in the swap cache and locked.
> - * It will never put the folio into the free list,
> - * the caller has a reference on the folio.
> +/**
> + * swap_cache_del_folio - Removes a folio from the swap cache.
> + * @folio: The folio.
> + *
> + * Same as __swap_cache_del_folio, but handles lock and refcount. The
> + * caller must ensure the folio is either clean or has a swap count
> + * equal to zero, or it may cause data loss.
> + *
> + * Context: Caller must ensure the folio is locked and in the swap cache.
> */
> -void delete_from_swap_cache(struct folio *folio)
> +void swap_cache_del_folio(struct folio *folio)
> {
> swp_entry_t entry = folio->swap;
> struct address_space *address_space = swap_address_space(entry);
>
> xa_lock_irq(&address_space->i_pages);
> - __delete_from_swap_cache(folio, entry, NULL);
> + __swap_cache_del_folio(folio, entry, NULL);
> xa_unlock_irq(&address_space->i_pages);
>
> put_swap_folio(folio, entry);
> folio_ref_sub(folio, folio_nr_pages(folio));
> }
>
> -void clear_shadow_from_swap_cache(int type, unsigned long begin,
> - unsigned long end)
> +/**
> + * swap_cache_clear_shadow - Clears a set of shadows in the swap cache.
> + * @type: Indicates the swap device.
> + * @begin: Beginning offset of the range.
> + * @end: Ending offset of the range.
> + *
> + * Context: Caller must ensure the range is valid and hold a reference to
> + * the swap device.
> + */
> +void swap_cache_clear_shadow(int type, unsigned long begin,
> + unsigned long end)
> {
> unsigned long curr = begin;
> void *old;
> @@ -393,7 +431,7 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
> goto put_and_return;
>
> /*
> - * We might race against __delete_from_swap_cache(), and
> + * We might race against __swap_cache_del_folio(), and
> * stumble across a swap_map entry whose SWAP_HAS_CACHE
> * has not yet been cleared. Or race against another
> * __read_swap_cache_async(), which has set SWAP_HAS_CACHE
> @@ -412,7 +450,7 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
> goto fail_unlock;
>
> /* May fail (-ENOMEM) if XArray node allocation failed. */
> - if (add_to_swap_cache(new_folio, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow))
> + if (swap_cache_add_folio(new_folio, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow))
> goto fail_unlock;
>
> memcg1_swapin(entry, 1);
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 367481d319cd..731b541b1d33 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -266,7 +266,7 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
> if (!need_reclaim)
> goto out_unlock;
>
> - delete_from_swap_cache(folio);
> + swap_cache_del_folio(folio);
> folio_set_dirty(folio);
> ret = nr_pages;
> out_unlock:
> @@ -1123,7 +1123,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
> swap_slot_free_notify(si->bdev, offset);
> offset++;
> }
> - clear_shadow_from_swap_cache(si->type, begin, end);
> + swap_cache_clear_shadow(si->type, begin, end);
>
> /*
> * Make sure that try_to_unuse() observes si->inuse_pages reaching 0
> @@ -1288,7 +1288,7 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp)
> * TODO: this could cause a theoretical memory reclaim
> * deadlock in the swap out path.
> */
> - if (add_to_swap_cache(folio, entry, gfp | __GFP_NOMEMALLOC, NULL))
> + if (swap_cache_add_folio(folio, entry, gfp | __GFP_NOMEMALLOC, NULL))
> goto out_free;
>
> return 0;
> @@ -1758,7 +1758,7 @@ bool folio_free_swap(struct folio *folio)
> if (folio_swapped(folio))
> return false;
>
> - delete_from_swap_cache(folio);
> + swap_cache_del_folio(folio);
> folio_set_dirty(folio);
> return true;
> }
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index ca9e1cd3cd68..c79c6806560b 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -776,7 +776,7 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
>
> if (reclaimed && !mapping_exiting(mapping))
> shadow = workingset_eviction(folio, target_memcg);
> - __delete_from_swap_cache(folio, swap, shadow);
> + __swap_cache_del_folio(folio, swap, shadow);
> memcg1_swapout(folio, swap);
> xa_unlock_irq(&mapping->i_pages);
> put_swap_folio(folio, swap);
> diff --git a/mm/zswap.c b/mm/zswap.c
> index c88ad61b232c..3dda4310099e 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -1069,7 +1069,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
>
> out:
> if (ret && ret != -EEXIST) {
> - delete_from_swap_cache(folio);
> + swap_cache_del_folio(folio);
> folio_unlock(folio);
> }
> folio_put(folio);
> --
> 2.51.0
>
>
Powered by blists - more mailing lists