The SWAP_MAP_SHMEM state was originally introduced in the commit aaa468653b4a ("swap_info: note SWAP_MAP_SHMEM"), to quickly determine if a swap entry belongs to shmem during swapoff. However, swapoff has since been rewritten drastically in the commit b56a2d8af914 ("mm: rid swapoff of quadratic complexity"). Now having swap count == SWAP_MAP_SHMEM value is basically the same as having swap count == 1, and swap_shmem_alloc() behaves analogously to swap_duplicate() This RFC proposes the removal of this state and the associated helper to simplify the state machine (both mentally and code-wise). We will also have an extra state/special value that can be repurposed (for swap entries that never gets re-duplicated). Another motivation (albeit a bit premature at the moment) is the new swap abstraction I am currently working on, that would allow for swap/zswap decoupling, swapoff optimization, etc. The fewer states and swap API functions there are, the simpler the conversion will be. I am sending this series first as an RFC, just in case I missed something or misunderstood this state, or if someone has a swap optimization in mind for shmem that would require this special state. Swap experts, let me know if I'm mistaken :) Otherwise if there is no objection I will resend this patch series again for merging. Nhat Pham (2): swapfile: add a batched variant for swap_duplicate() swap: shmem: remove SWAP_MAP_SHMEM include/linux/swap.h | 16 ++++++++-------- mm/shmem.c | 2 +- mm/swapfile.c | 28 +++++++++------------------- 3 files changed, 18 insertions(+), 28 deletions(-) base-commit: acfabf7e197f7a5bedf4749dac1f39551417b049 -- 2.43.5 Add swap_duplicate_nr(), the batched variant of swap_duplicate(), that operates on multiple contiguous swap entries. This will be used in the following patch to remove SWAP_MAP_SHMEM. Signed-off-by: Nhat Pham <nphamcs@gmail.com> --- include/linux/swap.h | 10 ++++++++-- mm/swapfile.c | 13 +++++++++---- 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index XXXXXXX..XXXXXXX 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -XXX,XX +XXX,XX @@ extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t, int); -extern int swap_duplicate(swp_entry_t); +extern int swap_duplicate_nr(swp_entry_t, int); extern int swapcache_prepare(swp_entry_t entry, int nr); extern void swap_free_nr(swp_entry_t entry, int nr_pages); extern void swapcache_free_entries(swp_entry_t *entries, int n); @@ -XXX,XX +XXX,XX @@ static inline void swap_shmem_alloc(swp_entry_t swp, int nr) { } -static inline int swap_duplicate(swp_entry_t swp) +static inline int swap_duplicate_nr(swp_entry_t swp, int nr) { return 0; } @@ -XXX,XX +XXX,XX @@ static inline int add_swap_extent(struct swap_info_struct *sis, } #endif /* CONFIG_SWAP */ +static inline int swap_duplicate(swp_entry_t entry) +{ + return swap_duplicate_nr(entry, 1); +} + + static inline void free_swap_and_cache(swp_entry_t entry) { free_swap_and_cache_nr(entry, 1); diff --git a/mm/swapfile.c b/mm/swapfile.c index XXXXXXX..XXXXXXX 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -XXX,XX +XXX,XX @@ void swap_shmem_alloc(swp_entry_t entry, int nr) __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } -/* - * Increase reference count of swap entry by 1. +/** + * swap_duplicate_nr() - Increase reference count of nr contiguous swap entries + * by 1. + * + * @entry: first swap entry from which we want to increase the refcount. + * @nr: Number of entries in range. + * * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ -int swap_duplicate(swp_entry_t entry) +int swap_duplicate_nr(swp_entry_t entry, int nr) { int err = 0; - while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) + while (!err && __swap_duplicate(entry, 1, nr) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } -- 2.43.5 The SWAP_MAP_SHMEM state was introduced in the commit aaa468653b4a ("swap_info: note SWAP_MAP_SHMEM"), to quickly determine if a swap entry belongs to shmem during swapoff. However, swapoff has since been rewritten in the commit b56a2d8af914 ("mm: rid swapoff of quadratic complexity"). Now having swap count == SWAP_MAP_SHMEM value is basically the same as having swap count == 1, and swap_shmem_alloc() behaves analogously to swap_duplicate(). Remove this state and the associated helper to simplify the state machine (both mentally and in terms of actual code). We will also have an extra state/special value that can be repurposed (for swap entries that never gets re-duplicated). Signed-off-by: Nhat Pham <nphamcs@gmail.com> --- include/linux/swap.h | 6 ------ mm/shmem.c | 2 +- mm/swapfile.c | 15 --------------- 3 files changed, 1 insertion(+), 22 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index XXXXXXX..XXXXXXX 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -XXX,XX +XXX,XX @@ enum { /* Special value in first swap_map */ #define SWAP_MAP_MAX 0x3e /* Max count */ #define SWAP_MAP_BAD 0x3f /* Note page is bad */ -#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ /* Special value in each swap_map continuation */ #define SWAP_CONT_MAX 0x7f /* Max count */ @@ -XXX,XX +XXX,XX @@ void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); -extern void swap_shmem_alloc(swp_entry_t, int); extern int swap_duplicate_nr(swp_entry_t, int); extern int swapcache_prepare(swp_entry_t entry, int nr); extern void swap_free_nr(swp_entry_t entry, int nr_pages); @@ -XXX,XX +XXX,XX @@ static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) return 0; } -static inline void swap_shmem_alloc(swp_entry_t swp, int nr) -{ -} - static inline int swap_duplicate_nr(swp_entry_t swp, int nr) { return 0; diff --git a/mm/shmem.c b/mm/shmem.c index XXXXXXX..XXXXXXX 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -XXX,XX +XXX,XX @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN, NULL) == 0) { shmem_recalc_inode(inode, 0, nr_pages); - swap_shmem_alloc(swap, nr_pages); + swap_duplicate_nr(swap, nr_pages); shmem_delete_from_page_cache(folio, swp_to_radix_entry(swap)); mutex_unlock(&shmem_swaplist_mutex); diff --git a/mm/swapfile.c b/mm/swapfile.c index XXXXXXX..XXXXXXX 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -XXX,XX +XXX,XX @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *si, if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; - } else if (count == SWAP_MAP_SHMEM) { - /* - * Or we could insist on shmem.c using a special - * swap_shmem_free() and free_shmem_swap_and_cache()... - */ - count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(si, offset, count)) @@ -XXX,XX +XXX,XX @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) return err; } -/* - * Help swapoff by noting that swap entry belongs to shmem/tmpfs - * (in which case its reference count is never incremented). - */ -void swap_shmem_alloc(swp_entry_t entry, int nr) -{ - __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); -} - /** * swap_duplicate_nr() - Increase reference count of nr contiguous swap entries * by 1. -- 2.43.5 Changelog: v2: * Fix a WARN in the shmem THP swap path. Thanks Baolin, Yosry, and Barry for the report and the discussion on how to solve it. * Squash the two patches into one. RFC v1: https://lore.kernel.org/all/20240923231142.4155415-1-nphamcs@gmail.com/ The SWAP_MAP_SHMEM state was originally introduced in the commit aaa468653b4a ("swap_info: note SWAP_MAP_SHMEM"), to quickly determine if a swap entry belongs to shmem during swapoff. However, swapoff has since been rewritten drastically in the commit b56a2d8af914 ("mm: rid swapoff of quadratic complexity"). Now having swap count == SWAP_MAP_SHMEM value is basically the same as having swap count == 1, and swap_shmem_alloc() behaves analogously to swap_duplicate() This RFC proposes the removal of this state and the associated helper to simplify the state machine (both mentally and code-wise). We will also have an extra state/special value that can be repurposed (for swap entries that never gets re-duplicated). Another motivation is the new swap abstraction I am currently working on, that would allow for swap/zswap decoupling, swapoff optimization, etc. The fewer states and swap API functions there are, the simpler the conversion will be. Nhat Pham (1): swap: shmem: remove SWAP_MAP_SHMEM include/linux/swap.h | 16 ++++++++-------- mm/shmem.c | 2 +- mm/swapfile.c | 41 +++++++++++++++++++++-------------------- 3 files changed, 30 insertions(+), 29 deletions(-) base-commit: 391cad4424af8bb563e1504c5adaef0155b4abb6 -- 2.43.5 The SWAP_MAP_SHMEM state was introduced in the commit aaa468653b4a ("swap_info: note SWAP_MAP_SHMEM"), to quickly determine if a swap entry belongs to shmem during swapoff. However, swapoff has since been rewritten in the commit b56a2d8af914 ("mm: rid swapoff of quadratic complexity"). Now having swap count == SWAP_MAP_SHMEM value is basically the same as having swap count == 1, and swap_shmem_alloc() behaves analogously to swap_duplicate(). The only difference of note is that swap_shmem_alloc() does not check for -ENOMEM returned from __swap_duplicate(), but it is OK because shmem never re-duplicates any swap entry it owns. This will stil be safe if we use (batched) swap_duplicate() instead. This commit adds swap_duplicate_nr(), the batched variant of swap_duplicate(), and removes the SWAP_MAP_SHMEM state and the associated swap_shmem_alloc() helper to simplify the state machine (both mentally and in terms of actual code). We will also have an extra state/special value that can be repurposed (for swap entries that never gets re-duplicated). Signed-off-by: Nhat Pham <nphamcs@gmail.com> --- include/linux/swap.h | 16 ++++++++-------- mm/shmem.c | 2 +- mm/swapfile.c | 41 +++++++++++++++++++++-------------------- 3 files changed, 30 insertions(+), 29 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index XXXXXXX..XXXXXXX 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -XXX,XX +XXX,XX @@ enum { /* Special value in first swap_map */ #define SWAP_MAP_MAX 0x3e /* Max count */ #define SWAP_MAP_BAD 0x3f /* Note page is bad */ -#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ /* Special value in each swap_map continuation */ #define SWAP_CONT_MAX 0x7f /* Max count */ @@ -XXX,XX +XXX,XX @@ void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); -extern void swap_shmem_alloc(swp_entry_t, int); -extern int swap_duplicate(swp_entry_t); +extern int swap_duplicate_nr(swp_entry_t, int); extern int swapcache_prepare(swp_entry_t entry, int nr); extern void swap_free_nr(swp_entry_t entry, int nr_pages); extern void swapcache_free_entries(swp_entry_t *entries, int n); @@ -XXX,XX +XXX,XX @@ static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) return 0; } -static inline void swap_shmem_alloc(swp_entry_t swp, int nr) -{ -} - -static inline int swap_duplicate(swp_entry_t swp) +static inline int swap_duplicate_nr(swp_entry_t swp, int nr) { return 0; } @@ -XXX,XX +XXX,XX @@ static inline int add_swap_extent(struct swap_info_struct *sis, } #endif /* CONFIG_SWAP */ +static inline int swap_duplicate(swp_entry_t entry) +{ + return swap_duplicate_nr(entry, 1); +} + + static inline void free_swap_and_cache(swp_entry_t entry) { free_swap_and_cache_nr(entry, 1); diff --git a/mm/shmem.c b/mm/shmem.c index XXXXXXX..XXXXXXX 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -XXX,XX +XXX,XX @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN, NULL) == 0) { shmem_recalc_inode(inode, 0, nr_pages); - swap_shmem_alloc(swap, nr_pages); + swap_duplicate_nr(swap, nr_pages); shmem_delete_from_page_cache(folio, swp_to_radix_entry(swap)); mutex_unlock(&shmem_swaplist_mutex); diff --git a/mm/swapfile.c b/mm/swapfile.c index XXXXXXX..XXXXXXX 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -XXX,XX +XXX,XX @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *si, if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; - } else if (count == SWAP_MAP_SHMEM) { - /* - * Or we could insist on shmem.c using a special - * swap_shmem_free() and free_shmem_swap_and_cache()... - */ - count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(si, offset, count)) @@ -XXX,XX +XXX,XX @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); - VM_WARN_ON(usage == 1 && nr > 1); ci = lock_cluster_or_swap_info(si, offset); err = 0; @@ -XXX,XX +XXX,XX @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) err = -EEXIST; } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { err = -EINVAL; + } else { + /* + * The only swap_duplicate_nr() caller that passes nr > 1 is shmem, + * who never re-duplicates any swap entry it owns. So this should + * not happen. + */ + VM_WARN_ON(nr > 1 && (count & ~COUNT_CONTINUED) == SWAP_MAP_MAX); } if (err) @@ -XXX,XX +XXX,XX @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) return err; } -/* - * Help swapoff by noting that swap entry belongs to shmem/tmpfs - * (in which case its reference count is never incremented). - */ -void swap_shmem_alloc(swp_entry_t entry, int nr) -{ - __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); -} - -/* - * Increase reference count of swap entry by 1. +/** + * swap_duplicate_nr() - Increase reference count of nr contiguous swap entries + * by 1. + * + * @entry: first swap entry from which we want to increase the refcount. + * @nr: Number of entries in range. + * * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. + * + * Note that we are currently not handling the case where nr > 1 and we need to + * add swap count continuation. This is OK, because no such user exists - shmem + * is the only user that can pass nr > 1, and it never re-duplicates any swap + * entry it owns. */ -int swap_duplicate(swp_entry_t entry) +int swap_duplicate_nr(swp_entry_t entry, int nr) { int err = 0; - while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) + while (!err && __swap_duplicate(entry, 1, nr) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } -- 2.43.5