diff options
Diffstat (limited to 'mm/swapfile.c')
| -rw-r--r-- | mm/swapfile.c | 4181 |
1 files changed, 2831 insertions, 1350 deletions
diff --git a/mm/swapfile.c b/mm/swapfile.c index 36af6eeaa67e..46d2008e4b99 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * @@ -5,7 +6,10 @@ * Swap reorganised 29.12.95, Stephen Tweedie */ +#include <linux/blkdev.h> #include <linux/mm.h> +#include <linux/sched/mm.h> +#include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> @@ -15,7 +19,7 @@ #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> -#include <linux/blkdev.h> +#include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> @@ -31,74 +35,265 @@ #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> -#include <linux/frontswap.h> #include <linux/swapfile.h> #include <linux/export.h> +#include <linux/sort.h> +#include <linux/completion.h> +#include <linux/suspend.h> +#include <linux/zswap.h> +#include <linux/plist.h> -#include <asm/pgtable.h> #include <asm/tlbflush.h> -#include <linux/swapops.h> -#include <linux/page_cgroup.h> +#include <linux/leafops.h> +#include <linux/swap_cgroup.h> +#include "swap_table.h" +#include "internal.h" +#include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); -static sector_t map_swap_entry(swp_entry_t, struct block_device**); - -DEFINE_SPINLOCK(swap_lock); +static void swap_entries_free(struct swap_info_struct *si, + struct swap_cluster_info *ci, + swp_entry_t entry, unsigned int nr_pages); +static void swap_range_alloc(struct swap_info_struct *si, + unsigned int nr_entries); +static bool folio_swapcache_freeable(struct folio *folio); +static void move_cluster(struct swap_info_struct *si, + struct swap_cluster_info *ci, struct list_head *list, + enum swap_cluster_flags new_flags); + +static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; +/* + * Some modules use swappable objects and may try to swap them out under + * memory pressure (via the shrinker). Before doing so, they may wish to + * check to see if any swap space is available. + */ +EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; -static int least_priority; -static atomic_t highest_priority_index = ATOMIC_INIT(-1); +#define DEF_SWAP_PRIO -1 +unsigned long swapfile_maximum_size; +#ifdef CONFIG_MIGRATION +bool swap_migration_ad_supported; +#endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; -struct swap_list_t swap_list = {-1, -1}; +/* + * all active swap_info_structs + * protected with swap_lock, and ordered by priority. + */ +static PLIST_HEAD(swap_active_head); + +/* + * all available (active, not full) swap_info_structs + * protected with swap_avail_lock, ordered by priority. + * This is used by folio_alloc_swap() instead of swap_active_head + * because swap_active_head includes all swap_info_structs, + * but folio_alloc_swap() doesn't need to look at full ones. + * This uses its own lock instead of swap_lock because when a + * swap_info_struct changes between not-full/full, it needs to + * add/remove itself to/from this list, but the swap_info_struct->lock + * is held and the locking order requires swap_lock to be taken + * before any swap_info_struct->lock. + */ +static PLIST_HEAD(swap_avail_head); +static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; +static struct kmem_cache *swap_table_cachep; + static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); +atomic_t nr_rotate_swap = ATOMIC_INIT(0); + +struct percpu_swap_cluster { + struct swap_info_struct *si[SWAP_NR_ORDERS]; + unsigned long offset[SWAP_NR_ORDERS]; + local_lock_t lock; +}; + +static DEFINE_PER_CPU(struct percpu_swap_cluster, percpu_swap_cluster) = { + .si = { NULL }, + .offset = { SWAP_ENTRY_INVALID }, + .lock = INIT_LOCAL_LOCK(), +}; + +/* May return NULL on invalid type, caller must check for NULL return */ +static struct swap_info_struct *swap_type_to_info(int type) +{ + if (type >= MAX_SWAPFILES) + return NULL; + return READ_ONCE(swap_info[type]); /* rcu_dereference() */ +} + +/* May return NULL on invalid entry, caller must check for NULL return */ +static struct swap_info_struct *swap_entry_to_info(swp_entry_t entry) +{ + return swap_type_to_info(swp_type(entry)); +} + static inline unsigned char swap_count(unsigned char ent) { - return ent & ~SWAP_HAS_CACHE; /* may include SWAP_HAS_CONT flag */ + return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } -/* returns 1 if swap entry is freed */ -static int -__try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) +/* + * Use the second highest bit of inuse_pages counter as the indicator + * if one swap device is on the available plist, so the atomic can + * still be updated arithmetically while having special data embedded. + * + * inuse_pages counter is the only thing indicating if a device should + * be on avail_lists or not (except swapon / swapoff). By embedding the + * off-list bit in the atomic counter, updates no longer need any lock + * to check the list status. + * + * This bit will be set if the device is not on the plist and not + * usable, will be cleared if the device is on the plist. + */ +#define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2)) +#define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT) +static long swap_usage_in_pages(struct swap_info_struct *si) { - swp_entry_t entry = swp_entry(si->type, offset); - struct page *page; - int ret = 0; + return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK; +} - page = find_get_page(swap_address_space(entry), entry.val); - if (!page) +/* Reclaim the swap entry anyway if possible */ +#define TTRS_ANYWAY 0x1 +/* + * Reclaim the swap entry if there are no more mappings of the + * corresponding page + */ +#define TTRS_UNMAPPED 0x2 +/* Reclaim the swap entry if swap is getting full */ +#define TTRS_FULL 0x4 + +static bool swap_only_has_cache(struct swap_info_struct *si, + unsigned long offset, int nr_pages) +{ + unsigned char *map = si->swap_map + offset; + unsigned char *map_end = map + nr_pages; + + do { + VM_BUG_ON(!(*map & SWAP_HAS_CACHE)); + if (*map != SWAP_HAS_CACHE) + return false; + } while (++map < map_end); + + return true; +} + +static bool swap_is_last_map(struct swap_info_struct *si, + unsigned long offset, int nr_pages, bool *has_cache) +{ + unsigned char *map = si->swap_map + offset; + unsigned char *map_end = map + nr_pages; + unsigned char count = *map; + + if (swap_count(count) != 1 && swap_count(count) != SWAP_MAP_SHMEM) + return false; + + while (++map < map_end) { + if (*map != count) + return false; + } + + *has_cache = !!(count & SWAP_HAS_CACHE); + return true; +} + +/* + * returns number of pages in the folio that backs the swap entry. If positive, + * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no + * folio was associated with the swap entry. + */ +static int __try_to_reclaim_swap(struct swap_info_struct *si, + unsigned long offset, unsigned long flags) +{ + const swp_entry_t entry = swp_entry(si->type, offset); + struct swap_cluster_info *ci; + struct folio *folio; + int ret, nr_pages; + bool need_reclaim; + +again: + folio = swap_cache_get_folio(entry); + if (!folio) return 0; + + nr_pages = folio_nr_pages(folio); + ret = -nr_pages; + + /* + * We hold a folio lock here. We have to use trylock for + * avoiding deadlock. This is a special case and you should + * use folio_free_swap() with explicit folio_lock() in usual + * operations. + */ + if (!folio_trylock(folio)) + goto out; + /* - * This function is called from scan_swap_map() and it's called - * by vmscan.c at reclaiming pages. So, we hold a lock on a page, here. - * We have to use trylock for avoiding deadlock. This is a special - * case and you should use try_to_free_swap() with explicit lock_page() - * in usual operations. + * Offset could point to the middle of a large folio, or folio + * may no longer point to the expected offset before it's locked. */ - if (trylock_page(page)) { - ret = try_to_free_swap(page); - unlock_page(page); + if (!folio_matches_swap_entry(folio, entry)) { + folio_unlock(folio); + folio_put(folio); + goto again; } - page_cache_release(page); + offset = swp_offset(folio->swap); + + need_reclaim = ((flags & TTRS_ANYWAY) || + ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || + ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); + if (!need_reclaim || !folio_swapcache_freeable(folio)) + goto out_unlock; + + /* + * It's safe to delete the folio from swap cache only if the folio's + * swap_map is HAS_CACHE only, which means the slots have no page table + * reference or pending writeback, and can't be allocated to others. + */ + ci = swap_cluster_lock(si, offset); + need_reclaim = swap_only_has_cache(si, offset, nr_pages); + swap_cluster_unlock(ci); + if (!need_reclaim) + goto out_unlock; + + swap_cache_del_folio(folio); + folio_set_dirty(folio); + ret = nr_pages; +out_unlock: + folio_unlock(folio); +out: + folio_put(folio); return ret; } +static inline struct swap_extent *first_se(struct swap_info_struct *sis) +{ + struct rb_node *rb = rb_first(&sis->swap_extent_root); + return rb_entry(rb, struct swap_extent, rb_node); +} + +static inline struct swap_extent *next_se(struct swap_extent *se) +{ + struct rb_node *rb = rb_next(&se->rb_node); + return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; +} + /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. @@ -111,23 +306,23 @@ static int discard_swap(struct swap_info_struct *si) int err = 0; /* Do not discard the swap header page! */ - se = &si->first_swap_extent; + se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, 0); + nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } - list_for_each_entry(se, &si->first_swap_extent.list, list) { + for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, 0); + nr_blocks, GFP_KERNEL); if (err) break; @@ -136,6 +331,39 @@ static int discard_swap(struct swap_info_struct *si) return err; /* That will often be -EOPNOTSUPP */ } +static struct swap_extent * +offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) +{ + struct swap_extent *se; + struct rb_node *rb; + + rb = sis->swap_extent_root.rb_node; + while (rb) { + se = rb_entry(rb, struct swap_extent, rb_node); + if (offset < se->start_page) + rb = rb->rb_left; + else if (offset >= se->start_page + se->nr_pages) + rb = rb->rb_right; + else + return se; + } + /* It *must* be present */ + BUG(); +} + +sector_t swap_folio_sector(struct folio *folio) +{ + struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); + struct swap_extent *se; + sector_t sector; + pgoff_t offset; + + offset = swp_offset(folio->swap); + se = offset_to_swap_extent(sis, offset); + sector = se->start_block + (offset - se->start_page); + return sector << (PAGE_SHIFT - 9); +} + /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. @@ -143,433 +371,1152 @@ static int discard_swap(struct swap_info_struct *si) static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { - struct swap_extent *se = si->curr_swap_extent; - int found_extent = 0; + struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { - struct list_head *lh; - - if (se->start_page <= start_page && - start_page < se->start_page + se->nr_pages) { - pgoff_t offset = start_page - se->start_page; - sector_t start_block = se->start_block + offset; - sector_t nr_blocks = se->nr_pages - offset; - - if (nr_blocks > nr_pages) - nr_blocks = nr_pages; - start_page += nr_blocks; - nr_pages -= nr_blocks; - - if (!found_extent++) - si->curr_swap_extent = se; - - start_block <<= PAGE_SHIFT - 9; - nr_blocks <<= PAGE_SHIFT - 9; - if (blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_NOIO, 0)) - break; - } + pgoff_t offset = start_page - se->start_page; + sector_t start_block = se->start_block + offset; + sector_t nr_blocks = se->nr_pages - offset; + + if (nr_blocks > nr_pages) + nr_blocks = nr_pages; + start_page += nr_blocks; + nr_pages -= nr_blocks; + + start_block <<= PAGE_SHIFT - 9; + nr_blocks <<= PAGE_SHIFT - 9; + if (blkdev_issue_discard(si->bdev, start_block, + nr_blocks, GFP_NOIO)) + break; - lh = se->list.next; - se = list_entry(lh, struct swap_extent, list); + se = next_se(se); } } -static int wait_for_discard(void *word) +#define LATENCY_LIMIT 256 + +static inline bool cluster_is_empty(struct swap_cluster_info *info) { - schedule(); - return 0; + return info->count == 0; } -#define SWAPFILE_CLUSTER 256 -#define LATENCY_LIMIT 256 +static inline bool cluster_is_discard(struct swap_cluster_info *info) +{ + return info->flags == CLUSTER_FLAG_DISCARD; +} -static unsigned long scan_swap_map(struct swap_info_struct *si, - unsigned char usage) +static inline bool cluster_table_is_alloced(struct swap_cluster_info *ci) { - unsigned long offset; - unsigned long scan_base; - unsigned long last_in_cluster = 0; - int latency_ration = LATENCY_LIMIT; - int found_free_cluster = 0; + return rcu_dereference_protected(ci->table, lockdep_is_held(&ci->lock)); +} + +static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order) +{ + if (unlikely(ci->flags > CLUSTER_FLAG_USABLE)) + return false; + if (!cluster_table_is_alloced(ci)) + return false; + if (!order) + return true; + return cluster_is_empty(ci) || order == ci->order; +} + +static inline unsigned int cluster_index(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + return ci - si->cluster_info; +} + +static inline unsigned int cluster_offset(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + return cluster_index(si, ci) * SWAPFILE_CLUSTER; +} + +static struct swap_table *swap_table_alloc(gfp_t gfp) +{ + struct folio *folio; + + if (!SWP_TABLE_USE_PAGE) + return kmem_cache_zalloc(swap_table_cachep, gfp); + + folio = folio_alloc(gfp | __GFP_ZERO, 0); + if (folio) + return folio_address(folio); + return NULL; +} + +static void swap_table_free_folio_rcu_cb(struct rcu_head *head) +{ + struct folio *folio; + + folio = page_folio(container_of(head, struct page, rcu_head)); + folio_put(folio); +} + +static void swap_table_free(struct swap_table *table) +{ + if (!SWP_TABLE_USE_PAGE) { + kmem_cache_free(swap_table_cachep, table); + return; + } + + call_rcu(&(folio_page(virt_to_folio(table), 0)->rcu_head), + swap_table_free_folio_rcu_cb); +} + +static void swap_cluster_free_table(struct swap_cluster_info *ci) +{ + unsigned int ci_off; + struct swap_table *table; + + /* Only empty cluster's table is allow to be freed */ + lockdep_assert_held(&ci->lock); + VM_WARN_ON_ONCE(!cluster_is_empty(ci)); + for (ci_off = 0; ci_off < SWAPFILE_CLUSTER; ci_off++) + VM_WARN_ON_ONCE(!swp_tb_is_null(__swap_table_get(ci, ci_off))); + table = (void *)rcu_dereference_protected(ci->table, true); + rcu_assign_pointer(ci->table, NULL); + + swap_table_free(table); +} + +/* + * Allocate swap table for one cluster. Attempt an atomic allocation first, + * then fallback to sleeping allocation. + */ +static struct swap_cluster_info * +swap_cluster_alloc_table(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + struct swap_table *table; /* - * We try to cluster swap pages by allocating them sequentially - * in swap. Once we've allocated SWAPFILE_CLUSTER pages this - * way, however, we resort to first-free allocation, starting - * a new cluster. This prevents us from scattering swap pages - * all over the entire swap partition, so that we reduce - * overall disk seek times between swap pages. -- sct - * But we do now try to find an empty cluster. -Andrea - * And we let swap pages go all over an SSD partition. Hugh + * Only cluster isolation from the allocator does table allocation. + * Swap allocator uses percpu clusters and holds the local lock. */ + lockdep_assert_held(&ci->lock); + lockdep_assert_held(&this_cpu_ptr(&percpu_swap_cluster)->lock); - si->flags += SWP_SCANNING; - scan_base = offset = si->cluster_next; + /* The cluster must be free and was just isolated from the free list. */ + VM_WARN_ON_ONCE(ci->flags || !cluster_is_empty(ci)); - if (unlikely(!si->cluster_nr--)) { - if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { - si->cluster_nr = SWAPFILE_CLUSTER - 1; - goto checks; - } - if (si->flags & SWP_PAGE_DISCARD) { - /* - * Start range check on racing allocations, in case - * they overlap the cluster we eventually decide on - * (we scan without swap_lock to allow preemption). - * It's hardly conceivable that cluster_nr could be - * wrapped during our scan, but don't depend on it. - */ - if (si->lowest_alloc) - goto checks; - si->lowest_alloc = si->max; - si->highest_alloc = 0; - } + table = swap_table_alloc(__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (table) { + rcu_assign_pointer(ci->table, table); + return ci; + } + + /* + * Try a sleep allocation. Each isolated free cluster may cause + * a sleep allocation, but there is a limited number of them, so + * the potential recursive allocation is limited. + */ + spin_unlock(&ci->lock); + if (!(si->flags & SWP_SOLIDSTATE)) + spin_unlock(&si->global_cluster_lock); + local_unlock(&percpu_swap_cluster.lock); + + table = swap_table_alloc(__GFP_HIGH | __GFP_NOMEMALLOC | GFP_KERNEL); + + /* + * Back to atomic context. We might have migrated to a new CPU with a + * usable percpu cluster. But just keep using the isolated cluster to + * make things easier. Migration indicates a slight change of workload + * so using a new free cluster might not be a bad idea, and the worst + * could happen with ignoring the percpu cluster is fragmentation, + * which is acceptable since this fallback and race is rare. + */ + local_lock(&percpu_swap_cluster.lock); + if (!(si->flags & SWP_SOLIDSTATE)) + spin_lock(&si->global_cluster_lock); + spin_lock(&ci->lock); + + /* Nothing except this helper should touch a dangling empty cluster. */ + if (WARN_ON_ONCE(cluster_table_is_alloced(ci))) { + if (table) + swap_table_free(table); + return ci; + } + + if (!table) { + move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); + spin_unlock(&ci->lock); + return NULL; + } + + rcu_assign_pointer(ci->table, table); + return ci; +} + +static void move_cluster(struct swap_info_struct *si, + struct swap_cluster_info *ci, struct list_head *list, + enum swap_cluster_flags new_flags) +{ + VM_WARN_ON(ci->flags == new_flags); + + BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX); + lockdep_assert_held(&ci->lock); + + spin_lock(&si->lock); + if (ci->flags == CLUSTER_FLAG_NONE) + list_add_tail(&ci->list, list); + else + list_move_tail(&ci->list, list); + spin_unlock(&si->lock); + ci->flags = new_flags; +} + +/* Add a cluster to discard list and schedule it to do discard */ +static void swap_cluster_schedule_discard(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); + move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD); + schedule_work(&si->discard_work); +} + +static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) +{ + swap_cluster_free_table(ci); + move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); + ci->order = 0; +} + +/* + * Isolate and lock the first cluster that is not contented on a list, + * clean its flag before taken off-list. Cluster flag must be in sync + * with list status, so cluster updaters can always know the cluster + * list status without touching si lock. + * + * Note it's possible that all clusters on a list are contented so + * this returns NULL for an non-empty list. + */ +static struct swap_cluster_info *isolate_lock_cluster( + struct swap_info_struct *si, struct list_head *list) +{ + struct swap_cluster_info *ci, *found = NULL; + + spin_lock(&si->lock); + list_for_each_entry(ci, list, list) { + if (!spin_trylock(&ci->lock)) + continue; + + /* We may only isolate and clear flags of following lists */ + VM_BUG_ON(!ci->flags); + VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE && + ci->flags != CLUSTER_FLAG_FULL); + + list_del(&ci->list); + ci->flags = CLUSTER_FLAG_NONE; + found = ci; + break; + } + spin_unlock(&si->lock); + + if (found && !cluster_table_is_alloced(found)) { + /* Only an empty free cluster's swap table can be freed. */ + VM_WARN_ON_ONCE(list != &si->free_clusters); + VM_WARN_ON_ONCE(!cluster_is_empty(found)); + return swap_cluster_alloc_table(si, found); + } + + return found; +} + +/* + * Doing discard actually. After a cluster discard is finished, the cluster + * will be added to free cluster list. Discard cluster is a bit special as + * they don't participate in allocation or reclaim, so clusters marked as + * CLUSTER_FLAG_DISCARD must remain off-list or on discard list. + */ +static bool swap_do_scheduled_discard(struct swap_info_struct *si) +{ + struct swap_cluster_info *ci; + bool ret = false; + unsigned int idx; + + spin_lock(&si->lock); + while (!list_empty(&si->discard_clusters)) { + ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); + /* + * Delete the cluster from list to prepare for discard, but keep + * the CLUSTER_FLAG_DISCARD flag, percpu_swap_cluster could be + * pointing to it, or ran into by relocate_cluster. + */ + list_del(&ci->list); + idx = cluster_index(si, ci); spin_unlock(&si->lock); + discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, + SWAPFILE_CLUSTER); + spin_lock(&ci->lock); /* - * If seek is expensive, start searching for new cluster from - * start of partition, to minimize the span of allocated swap. - * But if seek is cheap, search from our current position, so - * that swap is allocated from all over the partition: if the - * Flash Translation Layer only remaps within limited zones, - * we don't want to wear out the first zone too quickly. + * Discard is done, clear its flags as it's off-list, then + * return the cluster to allocation list. */ - if (!(si->flags & SWP_SOLIDSTATE)) - scan_base = offset = si->lowest_bit; - last_in_cluster = offset + SWAPFILE_CLUSTER - 1; - - /* Locate the first empty (unaligned) cluster */ - for (; last_in_cluster <= si->highest_bit; offset++) { - if (si->swap_map[offset]) - last_in_cluster = offset + SWAPFILE_CLUSTER; - else if (offset == last_in_cluster) { - spin_lock(&si->lock); - offset -= SWAPFILE_CLUSTER - 1; - si->cluster_next = offset; - si->cluster_nr = SWAPFILE_CLUSTER - 1; - found_free_cluster = 1; - goto checks; - } - if (unlikely(--latency_ration < 0)) { - cond_resched(); - latency_ration = LATENCY_LIMIT; - } + ci->flags = CLUSTER_FLAG_NONE; + __free_cluster(si, ci); + spin_unlock(&ci->lock); + ret = true; + spin_lock(&si->lock); + } + spin_unlock(&si->lock); + return ret; +} + +static void swap_discard_work(struct work_struct *work) +{ + struct swap_info_struct *si; + + si = container_of(work, struct swap_info_struct, discard_work); + + swap_do_scheduled_discard(si); +} + +static void swap_users_ref_free(struct percpu_ref *ref) +{ + struct swap_info_struct *si; + + si = container_of(ref, struct swap_info_struct, users); + complete(&si->comp); +} + +/* + * Must be called after freeing if ci->count == 0, moves the cluster to free + * or discard list. + */ +static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) +{ + VM_BUG_ON(ci->count != 0); + VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); + lockdep_assert_held(&ci->lock); + + /* + * If the swap is discardable, prepare discard the cluster + * instead of free it immediately. The cluster will be freed + * after discard. + */ + if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == + (SWP_WRITEOK | SWP_PAGE_DISCARD)) { + swap_cluster_schedule_discard(si, ci); + return; + } + + __free_cluster(si, ci); +} + +/* + * Must be called after freeing if ci->count != 0, moves the cluster to + * nonfull list. + */ +static void partial_free_cluster(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER); + lockdep_assert_held(&ci->lock); + + if (ci->flags != CLUSTER_FLAG_NONFULL) + move_cluster(si, ci, &si->nonfull_clusters[ci->order], + CLUSTER_FLAG_NONFULL); +} + +/* + * Must be called after allocation, moves the cluster to full or frag list. + * Note: allocation doesn't acquire si lock, and may drop the ci lock for + * reclaim, so the cluster could be any where when called. + */ +static void relocate_cluster(struct swap_info_struct *si, + struct swap_cluster_info *ci) +{ + lockdep_assert_held(&ci->lock); + + /* Discard cluster must remain off-list or on discard list */ + if (cluster_is_discard(ci)) + return; + + if (!ci->count) { + if (ci->flags != CLUSTER_FLAG_FREE) + free_cluster(si, ci); + } else if (ci->count != SWAPFILE_CLUSTER) { + if (ci->flags != CLUSTER_FLAG_FRAG) + move_cluster(si, ci, &si->frag_clusters[ci->order], + CLUSTER_FLAG_FRAG); + } else { + if (ci->flags != CLUSTER_FLAG_FULL) + move_cluster(si, ci, &si->full_clusters, + CLUSTER_FLAG_FULL); + } +} + +/* + * The cluster corresponding to @offset will be accounted as having one bad + * slot. The cluster will not be added to the free cluster list, and its + * usage counter will be increased by 1. Only used for initialization. + */ +static int swap_cluster_setup_bad_slot(struct swap_cluster_info *cluster_info, + unsigned long offset) +{ + unsigned long idx = offset / SWAPFILE_CLUSTER; + struct swap_table *table; + struct swap_cluster_info *ci; + + ci = cluster_info + idx; + if (!ci->table) { + table = swap_table_alloc(GFP_KERNEL); + if (!table) + return -ENOMEM; + rcu_assign_pointer(ci->table, table); + } + + ci->count++; + + WARN_ON(ci->count > SWAPFILE_CLUSTER); + WARN_ON(ci->flags); + + return 0; +} + +static bool cluster_reclaim_range(struct swap_info_struct *si, + struct swap_cluster_info *ci, + unsigned long start, unsigned long end) +{ + unsigned char *map = si->swap_map; + unsigned long offset = start; + int nr_reclaim; + + spin_unlock(&ci->lock); + do { + switch (READ_ONCE(map[offset])) { + case 0: + offset++; + break; + case SWAP_HAS_CACHE: + nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); + if (nr_reclaim > 0) + offset += nr_reclaim; + else + goto out; + break; + default: + goto out; } + } while (offset < end); +out: + spin_lock(&ci->lock); + /* + * Recheck the range no matter reclaim succeeded or not, the slot + * could have been be freed while we are not holding the lock. + */ + for (offset = start; offset < end; offset++) + if (READ_ONCE(map[offset])) + return false; - offset = si->lowest_bit; - last_in_cluster = offset + SWAPFILE_CLUSTER - 1; - - /* Locate the first empty (unaligned) cluster */ - for (; last_in_cluster < scan_base; offset++) { - if (si->swap_map[offset]) - last_in_cluster = offset + SWAPFILE_CLUSTER; - else if (offset == last_in_cluster) { - spin_lock(&si->lock); - offset -= SWAPFILE_CLUSTER - 1; - si->cluster_next = offset; - si->cluster_nr = SWAPFILE_CLUSTER - 1; - found_free_cluster = 1; - goto checks; - } - if (unlikely(--latency_ration < 0)) { - cond_resched(); - latency_ration = LATENCY_LIMIT; - } + return true; +} + +static bool cluster_scan_range(struct swap_info_struct *si, + struct swap_cluster_info *ci, + unsigned long start, unsigned int nr_pages, + bool *need_reclaim) +{ + unsigned long offset, end = start + nr_pages; + unsigned char *map = si->swap_map; + + if (cluster_is_empty(ci)) + return true; + + for (offset = start; offset < end; offset++) { + switch (READ_ONCE(map[offset])) { + case 0: + continue; + case SWAP_HAS_CACHE: + if (!vm_swap_full()) + return false; + *need_reclaim = true; + continue; + default: + return false; } + } - offset = scan_base; - spin_lock(&si->lock); - si->cluster_nr = SWAPFILE_CLUSTER - 1; - si->lowest_alloc = 0; + return true; +} + +/* + * Currently, the swap table is not used for count tracking, just + * do a sanity check here to ensure nothing leaked, so the swap + * table should be empty upon freeing. + */ +static void swap_cluster_assert_table_empty(struct swap_cluster_info *ci, + unsigned int start, unsigned int nr) +{ + unsigned int ci_off = start % SWAPFILE_CLUSTER; + unsigned int ci_end = ci_off + nr; + unsigned long swp_tb; + + if (IS_ENABLED(CONFIG_DEBUG_VM)) { + do { + swp_tb = __swap_table_get(ci, ci_off); + VM_WARN_ON_ONCE(!swp_tb_is_null(swp_tb)); + } while (++ci_off < ci_end); } +} + +static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, + unsigned int start, unsigned char usage, + unsigned int order) +{ + unsigned int nr_pages = 1 << order; + + lockdep_assert_held(&ci->lock); -checks: if (!(si->flags & SWP_WRITEOK)) - goto no_page; - if (!si->highest_bit) - goto no_page; - if (offset > si->highest_bit) - scan_base = offset = si->lowest_bit; - - /* reuse swap entry of cache-only swap if not busy. */ - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { - int swap_was_freed; - spin_unlock(&si->lock); - swap_was_freed = __try_to_reclaim_swap(si, offset); - spin_lock(&si->lock); - /* entry was freed successfully, try to use this again */ - if (swap_was_freed) - goto checks; - goto scan; /* check next one */ - } + return false; - if (si->swap_map[offset]) - goto scan; + /* + * The first allocation in a cluster makes the + * cluster exclusive to this order + */ + if (cluster_is_empty(ci)) + ci->order = order; - if (offset == si->lowest_bit) - si->lowest_bit++; - if (offset == si->highest_bit) - si->highest_bit--; - si->inuse_pages++; - if (si->inuse_pages == si->pages) { - si->lowest_bit = si->max; - si->highest_bit = 0; - } - si->swap_map[offset] = usage; - si->cluster_next = offset + 1; - si->flags -= SWP_SCANNING; + memset(si->swap_map + start, usage, nr_pages); + swap_cluster_assert_table_empty(ci, start, nr_pages); + swap_range_alloc(si, nr_pages); + ci->count += nr_pages; - if (si->lowest_alloc) { - /* - * Only set when SWP_PAGE_DISCARD, and there's a scan - * for a free cluster in progress or just completed. - */ - if (found_free_cluster) { - /* - * To optimize wear-levelling, discard the - * old data of the cluster, taking care not to - * discard any of its pages that have already - * been allocated by racing tasks (offset has - * already stepped over any at the beginning). - */ - if (offset < si->highest_alloc && - si->lowest_alloc <= last_in_cluster) - last_in_cluster = si->lowest_alloc - 1; - si->flags |= SWP_DISCARDING; - spin_unlock(&si->lock); + return true; +} - if (offset < last_in_cluster) - discard_swap_cluster(si, offset, - last_in_cluster - offset + 1); +/* Try use a new cluster for current CPU and allocate from it. */ +static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, + struct swap_cluster_info *ci, + unsigned long offset, + unsigned int order, + unsigned char usage) +{ + unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; + unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER); + unsigned long end = min(start + SWAPFILE_CLUSTER, si->max); + unsigned int nr_pages = 1 << order; + bool need_reclaim, ret; - spin_lock(&si->lock); - si->lowest_alloc = 0; - si->flags &= ~SWP_DISCARDING; + lockdep_assert_held(&ci->lock); - smp_mb(); /* wake_up_bit advises this */ - wake_up_bit(&si->flags, ilog2(SWP_DISCARDING)); + if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER) + goto out; - } else if (si->flags & SWP_DISCARDING) { - /* - * Delay using pages allocated by racing tasks - * until the whole discard has been issued. We - * could defer that delay until swap_writepage, - * but it's easier to keep this self-contained. - */ - spin_unlock(&si->lock); - wait_on_bit(&si->flags, ilog2(SWP_DISCARDING), - wait_for_discard, TASK_UNINTERRUPTIBLE); - spin_lock(&si->lock); - } else { + for (end -= nr_pages; offset <= end; offset += nr_pages) { + need_reclaim = false; + if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim)) + continue; + if (need_reclaim) { + ret = cluster_reclaim_range(si, ci, offset, offset + nr_pages); /* - * Note pages allocated by racing tasks while - * scan for a free cluster is in progress, so - * that its final discard can exclude them. + * Reclaim drops ci->lock and cluster could be used + * by another order. Not checking flag as off-list + * cluster has no flag set, and change of list + * won't cause fragmentation. */ - if (offset < si->lowest_alloc) - si->lowest_alloc = offset; - if (offset > si->highest_alloc) - si->highest_alloc = offset; + if (!cluster_is_usable(ci, order)) + goto out; + if (cluster_is_empty(ci)) + offset = start; + /* Reclaim failed but cluster is usable, try next */ + if (!ret) + continue; } + if (!cluster_alloc_range(si, ci, offset, usage, order)) + break; + found = offset; + offset += nr_pages; + if (ci->count < SWAPFILE_CLUSTER && offset <= end) + next = offset; + break; + } +out: + relocate_cluster(si, ci); + swap_cluster_unlock(ci); + if (si->flags & SWP_SOLIDSTATE) { + this_cpu_write(percpu_swap_cluster.offset[order], next); + this_cpu_write(percpu_swap_cluster.si[order], si); + } else { + si->global_cluster->next[order] = next; } - return offset; + return found; +} -scan: - spin_unlock(&si->lock); - while (++offset <= si->highest_bit) { - if (!si->swap_map[offset]) { - spin_lock(&si->lock); - goto checks; - } - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { - spin_lock(&si->lock); - goto checks; - } - if (unlikely(--latency_ration < 0)) { - cond_resched(); - latency_ration = LATENCY_LIMIT; +static unsigned int alloc_swap_scan_list(struct swap_info_struct *si, + struct list_head *list, + unsigned int order, + unsigned char usage, + bool scan_all) +{ + unsigned int found = SWAP_ENTRY_INVALID; + + do { + struct swap_cluster_info *ci = isolate_lock_cluster(si, list); + unsigned long offset; + + if (!ci) + break; + offset = cluster_offset(si, ci); + found = alloc_swap_scan_cluster(si, ci, offset, order, usage); + if (found) + break; + } while (scan_all); + + return found; +} + +static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) +{ + long to_scan = 1; + unsigned long offset, end; + struct swap_cluster_info *ci; + unsigned char *map = si->swap_map; + int nr_reclaim; + + if (force) + to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER; + + while ((ci = isolate_lock_cluster(si, &si->full_clusters))) { + offset = cluster_offset(si, ci); + end = min(si->max, offset + SWAPFILE_CLUSTER); + to_scan--; + + while (offset < end) { + if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { + spin_unlock(&ci->lock); + nr_reclaim = __try_to_reclaim_swap(si, offset, + TTRS_ANYWAY); + spin_lock(&ci->lock); + if (nr_reclaim) { + offset += abs(nr_reclaim); + continue; + } + } + offset++; } + + /* in case no swap cache is reclaimed */ + if (ci->flags == CLUSTER_FLAG_NONE) + relocate_cluster(si, ci); + + swap_cluster_unlock(ci); + if (to_scan <= 0) + break; } - offset = si->lowest_bit; - while (++offset < scan_base) { - if (!si->swap_map[offset]) { - spin_lock(&si->lock); - goto checks; - } - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { - spin_lock(&si->lock); - goto checks; - } - if (unlikely(--latency_ration < 0)) { - cond_resched(); - latency_ration = LATENCY_LIMIT; +} + +static void swap_reclaim_work(struct work_struct *work) +{ + struct swap_info_struct *si; + + si = container_of(work, struct swap_info_struct, reclaim_work); + + swap_reclaim_full_clusters(si, true); +} + +/* + * Try to allocate swap entries with specified order and try set a new + * cluster for current CPU too. + */ +static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order, + unsigned char usage) +{ + struct swap_cluster_info *ci; + unsigned int offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; + + /* + * Swapfile is not block device so unable + * to allocate large entries. + */ + if (order && !(si->flags & SWP_BLKDEV)) + return 0; + + if (!(si->flags & SWP_SOLIDSTATE)) { + /* Serialize HDD SWAP allocation for each device. */ + spin_lock(&si->global_cluster_lock); + offset = si->global_cluster->next[order]; + if (offset == SWAP_ENTRY_INVALID) + goto new_cluster; + + ci = swap_cluster_lock(si, offset); + /* Cluster could have been used by another order */ + if (cluster_is_usable(ci, order)) { + if (cluster_is_empty(ci)) + offset = cluster_offset(si, ci); + found = alloc_swap_scan_cluster(si, ci, offset, + order, usage); + } else { + swap_cluster_unlock(ci); } + if (found) + goto done; } - spin_lock(&si->lock); -no_page: - si->flags -= SWP_SCANNING; - return 0; +new_cluster: + /* + * If the device need discard, prefer new cluster over nonfull + * to spread out the writes. + */ + if (si->flags & SWP_PAGE_DISCARD) { + found = alloc_swap_scan_list(si, &si->free_clusters, order, usage, + false); + if (found) + goto done; + } + + if (order < PMD_ORDER) { + found = alloc_swap_scan_list(si, &si->nonfull_clusters[order], + order, usage, true); + if (found) + goto done; + } + + if (!(si->flags & SWP_PAGE_DISCARD)) { + found = alloc_swap_scan_list(si, &si->free_clusters, order, usage, + false); + if (found) + goto done; + } + + /* Try reclaim full clusters if free and nonfull lists are drained */ + if (vm_swap_full()) + swap_reclaim_full_clusters(si, false); + + if (order < PMD_ORDER) { + /* + * Scan only one fragment cluster is good enough. Order 0 + * allocation will surely success, and large allocation + * failure is not critical. Scanning one cluster still + * keeps the list rotated and reclaimed (for HAS_CACHE). + */ + found = alloc_swap_scan_list(si, &si->frag_clusters[order], order, + usage, false); + if (found) + goto done; + } + + if (order) + goto done; + + /* Order 0 stealing from higher order */ + for (int o = 1; o < SWAP_NR_ORDERS; o++) { + /* + * Clusters here have at least one usable slots and can't fail order 0 + * allocation, but reclaim may drop si->lock and race with another user. + */ + found = alloc_swap_scan_list(si, &si->frag_clusters[o], + 0, usage, true); + if (found) + goto done; + + found = alloc_swap_scan_list(si, &si->nonfull_clusters[o], + 0, usage, true); + if (found) + goto done; + } +done: + if (!(si->flags & SWP_SOLIDSTATE)) + spin_unlock(&si->global_cluster_lock); + + return found; } -swp_entry_t get_swap_page(void) +/* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */ +static void del_from_avail_list(struct swap_info_struct *si, bool swapoff) { - struct swap_info_struct *si; - pgoff_t offset; - int type, next; - int wrapped = 0; - int hp_index; + unsigned long pages; - spin_lock(&swap_lock); - if (atomic_long_read(&nr_swap_pages) <= 0) - goto noswap; - atomic_long_dec(&nr_swap_pages); + spin_lock(&swap_avail_lock); - for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { - hp_index = atomic_xchg(&highest_priority_index, -1); + if (swapoff) { /* - * highest_priority_index records current highest priority swap - * type which just frees swap entries. If its priority is - * higher than that of swap_list.next swap type, we use it. It - * isn't protected by swap_lock, so it can be an invalid value - * if the corresponding swap type is swapoff. We double check - * the flags here. It's even possible the swap type is swapoff - * and swapon again and its priority is changed. In such rare - * case, low prority swap type might be used, but eventually - * high priority swap will be used after several rounds of - * swap. + * Forcefully remove it. Clear the SWP_WRITEOK flags for + * swapoff here so it's synchronized by both si->lock and + * swap_avail_lock, to ensure the result can be seen by + * add_to_avail_list. */ - if (hp_index != -1 && hp_index != type && - swap_info[type]->prio < swap_info[hp_index]->prio && - (swap_info[hp_index]->flags & SWP_WRITEOK)) { - type = hp_index; - swap_list.next = type; - } + lockdep_assert_held(&si->lock); + si->flags &= ~SWP_WRITEOK; + atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); + } else { + /* + * If not called by swapoff, take it off-list only if it's + * full and SWAP_USAGE_OFFLIST_BIT is not set (strictly + * si->inuse_pages == pages), any concurrent slot freeing, + * or device already removed from plist by someone else + * will make this return false. + */ + pages = si->pages; + if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages, + pages | SWAP_USAGE_OFFLIST_BIT)) + goto skip; + } - si = swap_info[type]; - next = si->next; - if (next < 0 || - (!wrapped && si->prio != swap_info[next]->prio)) { - next = swap_list.head; - wrapped++; - } + plist_del(&si->avail_list, &swap_avail_head); - spin_lock(&si->lock); - if (!si->highest_bit) { - spin_unlock(&si->lock); - continue; - } - if (!(si->flags & SWP_WRITEOK)) { - spin_unlock(&si->lock); - continue; +skip: + spin_unlock(&swap_avail_lock); +} + +/* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */ +static void add_to_avail_list(struct swap_info_struct *si, bool swapon) +{ + long val; + unsigned long pages; + + spin_lock(&swap_avail_lock); + + /* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */ + if (swapon) { + lockdep_assert_held(&si->lock); + si->flags |= SWP_WRITEOK; + } else { + if (!(READ_ONCE(si->flags) & SWP_WRITEOK)) + goto skip; + } + + if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT)) + goto skip; + + val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); + + /* + * When device is full and device is on the plist, only one updater will + * see (inuse_pages == si->pages) and will call del_from_avail_list. If + * that updater happen to be here, just skip adding. + */ + pages = si->pages; + if (val == pages) { + /* Just like the cmpxchg in del_from_avail_list */ + if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages, + pages | SWAP_USAGE_OFFLIST_BIT)) + goto skip; + } + + plist_add(&si->avail_list, &swap_avail_head); + +skip: + spin_unlock(&swap_avail_lock); +} + +/* + * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock + * within each cluster, so the total contribution to the global counter should + * always be positive and cannot exceed the total number of usable slots. + */ +static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries) +{ + long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages); + + /* + * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set, + * remove it from the plist. + */ + if (unlikely(val == si->pages)) { + del_from_avail_list(si, false); + return true; + } + + return false; +} + +static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries) +{ + long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages); + + /* + * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set, + * add it to the plist. + */ + if (unlikely(val & SWAP_USAGE_OFFLIST_BIT)) + add_to_avail_list(si, false); +} + +static void swap_range_alloc(struct swap_info_struct *si, + unsigned int nr_entries) +{ + if (swap_usage_add(si, nr_entries)) { + if (vm_swap_full()) + schedule_work(&si->reclaim_work); + } + atomic_long_sub(nr_entries, &nr_swap_pages); +} + +static void swap_range_free(struct swap_info_struct *si, unsigned long offset, + unsigned int nr_entries) +{ + unsigned long begin = offset; + unsigned long end = offset + nr_entries - 1; + void (*swap_slot_free_notify)(struct block_device *, unsigned long); + unsigned int i; + + /* + * Use atomic clear_bit operations only on zeromap instead of non-atomic + * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. + */ + for (i = 0; i < nr_entries; i++) { + clear_bit(offset + i, si->zeromap); + zswap_invalidate(swp_entry(si->type, offset + i)); + } + + if (si->flags & SWP_BLKDEV) + swap_slot_free_notify = + si->bdev->bd_disk->fops->swap_slot_free_notify; + else + swap_slot_free_notify = NULL; + while (offset <= end) { + arch_swap_invalidate_page(si->type, offset); + if (swap_slot_free_notify) + swap_slot_free_notify(si->bdev, offset); + offset++; + } + __swap_cache_clear_shadow(swp_entry(si->type, begin), nr_entries); + + /* + * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 + * only after the above cleanups are done. + */ + smp_wmb(); + atomic_long_add(nr_entries, &nr_swap_pages); + swap_usage_sub(si, nr_entries); +} + +static bool get_swap_device_info(struct swap_info_struct *si) +{ + if (!percpu_ref_tryget_live(&si->users)) + return false; + /* + * Guarantee the si->users are checked before accessing other + * fields of swap_info_struct, and si->flags (SWP_WRITEOK) is + * up to dated. + * + * Paired with the spin_unlock() after setup_swap_info() in + * enable_swap_info(), and smp_wmb() in swapoff. + */ + smp_rmb(); + return true; +} + +/* + * Fast path try to get swap entries with specified order from current + * CPU's swap entry pool (a cluster). + */ +static bool swap_alloc_fast(swp_entry_t *entry, + int order) +{ + struct swap_cluster_info *ci; + struct swap_info_struct *si; + unsigned int offset, found = SWAP_ENTRY_INVALID; + + /* + * Once allocated, swap_info_struct will never be completely freed, + * so checking it's liveness by get_swap_device_info is enough. + */ + si = this_cpu_read(percpu_swap_cluster.si[order]); + offset = this_cpu_read(percpu_swap_cluster.offset[order]); + if (!si || !offset || !get_swap_device_info(si)) + return false; + + ci = swap_cluster_lock(si, offset); + if (cluster_is_usable(ci, order)) { + if (cluster_is_empty(ci)) + offset = cluster_offset(si, ci); + found = alloc_swap_scan_cluster(si, ci, offset, order, SWAP_HAS_CACHE); + if (found) + *entry = swp_entry(si->type, found); + } else { + swap_cluster_unlock(ci); + } + + put_swap_device(si); + return !!found; +} + +/* Rotate the device and switch to a new cluster */ +static void swap_alloc_slow(swp_entry_t *entry, + int order) +{ + unsigned long offset; + struct swap_info_struct *si, *next; + + spin_lock(&swap_avail_lock); +start_over: + plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { + /* Rotate the device and switch to a new cluster */ + plist_requeue(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); + if (get_swap_device_info(si)) { + offset = cluster_alloc_swap_entry(si, order, SWAP_HAS_CACHE); + put_swap_device(si); + if (offset) { + *entry = swp_entry(si->type, offset); + return; + } + if (order) + return; } - swap_list.next = next; + spin_lock(&swap_avail_lock); + /* + * if we got here, it's likely that si was almost full before, + * multiple callers probably all tried to get a page from the + * same si and it filled up before we could get one; or, the si + * filled up between us dropping swap_avail_lock. + * Since we dropped the swap_avail_lock, the swap_avail_list + * may have been modified; so if next is still in the + * swap_avail_head list then try it, otherwise start over if we + * have not gotten any slots. + */ + if (plist_node_empty(&next->avail_list)) + goto start_over; + } + spin_unlock(&swap_avail_lock); +} + +/* + * Discard pending clusters in a synchronized way when under high pressure. + * Return: true if any cluster is discarded. + */ +static bool swap_sync_discard(void) +{ + bool ret = false; + struct swap_info_struct *si, *next; + spin_lock(&swap_lock); +start_over: + plist_for_each_entry_safe(si, next, &swap_active_head, list) { spin_unlock(&swap_lock); - /* This is called for allocating swap entry for cache */ - offset = scan_swap_map(si, SWAP_HAS_CACHE); - spin_unlock(&si->lock); - if (offset) - return swp_entry(type, offset); + if (get_swap_device_info(si)) { + if (si->flags & SWP_PAGE_DISCARD) + ret = swap_do_scheduled_discard(si); + put_swap_device(si); + } + if (ret) + return true; + spin_lock(&swap_lock); - next = swap_list.next; + if (plist_node_empty(&next->list)) + goto start_over; } - - atomic_long_inc(&nr_swap_pages); -noswap: spin_unlock(&swap_lock); - return (swp_entry_t) {0}; + + return false; } -/* The only caller of this function is now susupend routine */ -swp_entry_t get_swap_page_of_type(int type) +/** + * folio_alloc_swap - allocate swap space for a folio + * @folio: folio we want to move to swap + * + * Allocate swap space for the folio and add the folio to the + * swap cache. + * + * Context: Caller needs to hold the folio lock. + * Return: Whether the folio was added to the swap cache. + */ +int folio_alloc_swap(struct folio *folio) { - struct swap_info_struct *si; - pgoff_t offset; + unsigned int order = folio_order(folio); + unsigned int size = 1 << order; + swp_entry_t entry = {}; - si = swap_info[type]; - spin_lock(&si->lock); - if (si && (si->flags & SWP_WRITEOK)) { - atomic_long_dec(&nr_swap_pages); - /* This is called for allocating swap entry, not cache */ - offset = scan_swap_map(si, 1); - if (offset) { - spin_unlock(&si->lock); - return swp_entry(type, offset); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); + + if (order) { + /* + * Reject large allocation when THP_SWAP is disabled, + * the caller should split the folio and try again. + */ + if (!IS_ENABLED(CONFIG_THP_SWAP)) + return -EAGAIN; + + /* + * Allocation size should never exceed cluster size + * (HPAGE_PMD_SIZE). + */ + if (size > SWAPFILE_CLUSTER) { + VM_WARN_ON_ONCE(1); + return -EINVAL; } - atomic_long_inc(&nr_swap_pages); } - spin_unlock(&si->lock); - return (swp_entry_t) {0}; + +again: + local_lock(&percpu_swap_cluster.lock); + if (!swap_alloc_fast(&entry, order)) + swap_alloc_slow(&entry, order); + local_unlock(&percpu_swap_cluster.lock); + + if (unlikely(!order && !entry.val)) { + if (swap_sync_discard()) + goto again; + } + + /* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */ + if (mem_cgroup_try_charge_swap(folio, entry)) + goto out_free; + + if (!entry.val) + return -ENOMEM; + + swap_cache_add_folio(folio, entry, NULL); + + return 0; + +out_free: + put_swap_folio(folio, entry); + return -ENOMEM; } -static struct swap_info_struct *swap_info_get(swp_entry_t entry) +static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { - struct swap_info_struct *p; - unsigned long offset, type; + struct swap_info_struct *si; + unsigned long offset; if (!entry.val) goto out; - type = swp_type(entry); - if (type >= nr_swapfiles) + si = swap_entry_to_info(entry); + if (!si) goto bad_nofile; - p = swap_info[type]; - if (!(p->flags & SWP_USED)) + if (data_race(!(si->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); - if (offset >= p->max) + if (offset >= si->max) goto bad_offset; - if (!p->swap_map[offset]) + if (data_race(!si->swap_map[swp_offset(entry)])) goto bad_free; - spin_lock(&p->lock); - return p; + return si; bad_free: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val); + pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val); + pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val); + pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val); + pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } -/* - * This swap type frees swap entry, check if it is the highest priority swap - * type which just frees swap entry. get_swap_page() uses - * highest_priority_index to search highest priority swap type. The - * swap_info_struct.lock can't protect us if there are multiple swap types - * active, so we use atomic_cmpxchg. - */ -static void set_highest_priority_index(int type) -{ - int old_hp_index, new_hp_index; - - do { - old_hp_index = atomic_read(&highest_priority_index); - if (old_hp_index != -1 && - swap_info[old_hp_index]->prio >= swap_info[type]->prio) - break; - new_hp_index = type; - } while (atomic_cmpxchg(&highest_priority_index, - old_hp_index, new_hp_index) != old_hp_index); -} - -static unsigned char swap_entry_free(struct swap_info_struct *p, - swp_entry_t entry, unsigned char usage) +static unsigned char swap_entry_put_locked(struct swap_info_struct *si, + struct swap_cluster_info *ci, + swp_entry_t entry, + unsigned char usage) { unsigned long offset = swp_offset(entry); unsigned char count; unsigned char has_cache; - count = p->swap_map[offset]; + count = si->swap_map[offset]; + has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; @@ -584,7 +1531,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { - if (swap_count_continued(p, offset, count)) + if (swap_count_continued(si, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; @@ -592,188 +1539,500 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, count--; } - if (!count) - mem_cgroup_uncharge_swap(entry); - usage = count | has_cache; - p->swap_map[offset] = usage; - - /* free if no reference */ - if (!usage) { - if (offset < p->lowest_bit) - p->lowest_bit = offset; - if (offset > p->highest_bit) - p->highest_bit = offset; - set_highest_priority_index(p->type); - atomic_long_inc(&nr_swap_pages); - p->inuse_pages--; - frontswap_invalidate_page(p->type, offset); - if (p->flags & SWP_BLKDEV) { - struct gendisk *disk = p->bdev->bd_disk; - if (disk->fops->swap_slot_free_notify) - disk->fops->swap_slot_free_notify(p->bdev, - offset); - } - } + if (usage) + WRITE_ONCE(si->swap_map[offset], usage); + else + swap_entries_free(si, ci, entry, 1); return usage; } /* - * Caller has made sure that the swapdevice corresponding to entry + * When we get a swap entry, if there aren't some other ways to + * prevent swapoff, such as the folio in swap cache is locked, RCU + * reader side is locked, etc., the swap entry may become invalid + * because of swapoff. Then, we need to enclose all swap related + * functions with get_swap_device() and put_swap_device(), unless the + * swap functions call get/put_swap_device() by themselves. + * + * RCU reader side lock (including any spinlock) is sufficient to + * prevent swapoff, because synchronize_rcu() is called in swapoff() + * before freeing data structures. + * + * Check whether swap entry is valid in the swap device. If so, + * return pointer to swap_info_struct, and keep the swap entry valid + * via preventing the swap device from being swapoff, until + * put_swap_device() is called. Otherwise return NULL. + * + * Notice that swapoff or swapoff+swapon can still happen before the + * percpu_ref_tryget_live() in get_swap_device() or after the + * percpu_ref_put() in put_swap_device() if there isn't any other way + * to prevent swapoff. The caller must be prepared for that. For + * example, the following situation is possible. + * + * CPU1 CPU2 + * do_swap_page() + * ... swapoff+swapon + * __read_swap_cache_async() + * swapcache_prepare() + * __swap_duplicate() + * // check swap_map + * // verify PTE not changed + * + * In __swap_duplicate(), the swap_map need to be checked before + * changing partly because the specified swap entry may be for another + * swap device which has been swapoff. And in do_swap_page(), after + * the page is read from the swap device, the PTE is verified not + * changed with the page table locked to check whether the swap device + * has been swapoff or swapoff+swapon. + */ +struct swap_info_struct *get_swap_device(swp_entry_t entry) +{ + struct swap_info_struct *si; + unsigned long offset; + + if (!entry.val) + goto out; + si = swap_entry_to_info(entry); + if (!si) + goto bad_nofile; + if (!get_swap_device_info(si)) + goto out; + offset = swp_offset(entry); + if (offset >= si->max) + goto put_out; + + return si; +bad_nofile: + pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); +out: + return NULL; +put_out: + pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); + percpu_ref_put(&si->users); + return NULL; +} + +static void swap_entries_put_cache(struct swap_info_struct *si, + swp_entry_t entry, int nr) +{ + unsigned long offset = swp_offset(entry); + struct swap_cluster_info *ci; + + ci = swap_cluster_lock(si, offset); + if (swap_only_has_cache(si, offset, nr)) { + swap_entries_free(si, ci, entry, nr); + } else { + for (int i = 0; i < nr; i++, entry.val++) + swap_entry_put_locked(si, ci, entry, SWAP_HAS_CACHE); + } + swap_cluster_unlock(ci); +} + +static bool swap_entries_put_map(struct swap_info_struct *si, + swp_entry_t entry, int nr) +{ + unsigned long offset = swp_offset(entry); + struct swap_cluster_info *ci; + bool has_cache = false; + unsigned char count; + int i; + + if (nr <= 1) + goto fallback; + count = swap_count(data_race(si->swap_map[offset])); + if (count != 1 && count != SWAP_MAP_SHMEM) + goto fallback; + + ci = swap_cluster_lock(si, offset); + if (!swap_is_last_map(si, offset, nr, &has_cache)) { + goto locked_fallback; + } + if (!has_cache) + swap_entries_free(si, ci, entry, nr); + else + for (i = 0; i < nr; i++) + WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE); + swap_cluster_unlock(ci); + + return has_cache; + +fallback: + ci = swap_cluster_lock(si, offset); +locked_fallback: + for (i = 0; i < nr; i++, entry.val++) { + count = swap_entry_put_locked(si, ci, entry, 1); + if (count == SWAP_HAS_CACHE) + has_cache = true; + } + swap_cluster_unlock(ci); + return has_cache; +} + +/* + * Only functions with "_nr" suffix are able to free entries spanning + * cross multi clusters, so ensure the range is within a single cluster + * when freeing entries with functions without "_nr" suffix. + */ +static bool swap_entries_put_map_nr(struct swap_info_struct *si, + swp_entry_t entry, int nr) +{ + int cluster_nr, cluster_rest; + unsigned long offset = swp_offset(entry); + bool has_cache = false; + + cluster_rest = SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER; + while (nr) { + cluster_nr = min(nr, cluster_rest); + has_cache |= swap_entries_put_map(si, entry, cluster_nr); + cluster_rest = SWAPFILE_CLUSTER; + nr -= cluster_nr; + entry.val += cluster_nr; + } + + return has_cache; +} + +/* + * Check if it's the last ref of swap entry in the freeing path. + * Qualified value includes 1, SWAP_HAS_CACHE or SWAP_MAP_SHMEM. + */ +static inline bool __maybe_unused swap_is_last_ref(unsigned char count) +{ + return (count == SWAP_HAS_CACHE) || (count == 1) || + (count == SWAP_MAP_SHMEM); +} + +/* + * Drop the last ref of swap entries, caller have to ensure all entries + * belong to the same cgroup and cluster. + */ +static void swap_entries_free(struct swap_info_struct *si, + struct swap_cluster_info *ci, + swp_entry_t entry, unsigned int nr_pages) +{ + unsigned long offset = swp_offset(entry); + unsigned char *map = si->swap_map + offset; + unsigned char *map_end = map + nr_pages; + + /* It should never free entries across different clusters */ + VM_BUG_ON(ci != __swap_offset_to_cluster(si, offset + nr_pages - 1)); + VM_BUG_ON(cluster_is_empty(ci)); + VM_BUG_ON(ci->count < nr_pages); + + ci->count -= nr_pages; + do { + VM_BUG_ON(!swap_is_last_ref(*map)); + *map = 0; + } while (++map < map_end); + + mem_cgroup_uncharge_swap(entry, nr_pages); + swap_range_free(si, offset, nr_pages); + swap_cluster_assert_table_empty(ci, offset, nr_pages); + + if (!ci->count) + free_cluster(si, ci); + else + partial_free_cluster(si, ci); +} + +/* + * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ -void swap_free(swp_entry_t entry) +void swap_free_nr(swp_entry_t entry, int nr_pages) { - struct swap_info_struct *p; + int nr; + struct swap_info_struct *sis; + unsigned long offset = swp_offset(entry); + + sis = _swap_info_get(entry); + if (!sis) + return; - p = swap_info_get(entry); - if (p) { - swap_entry_free(p, entry, 1); - spin_unlock(&p->lock); + while (nr_pages) { + nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); + swap_entries_put_map(sis, swp_entry(sis->type, offset), nr); + offset += nr; + nr_pages -= nr; } } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ -void swapcache_free(swp_entry_t entry, struct page *page) +void put_swap_folio(struct folio *folio, swp_entry_t entry) { - struct swap_info_struct *p; - unsigned char count; + struct swap_info_struct *si; + int size = 1 << swap_entry_order(folio_order(folio)); - p = swap_info_get(entry); - if (p) { - count = swap_entry_free(p, entry, SWAP_HAS_CACHE); - if (page) - mem_cgroup_uncharge_swapcache(page, entry, count != 0); - spin_unlock(&p->lock); - } + si = _swap_info_get(entry); + if (!si) + return; + + swap_entries_put_cache(si, entry, size); +} + +int __swap_count(swp_entry_t entry) +{ + struct swap_info_struct *si = __swap_entry_to_info(entry); + pgoff_t offset = swp_offset(entry); + + return swap_count(si->swap_map[offset]); } /* - * How many references to page are currently swapped out? + * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ -int page_swapcount(struct page *page) +bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry) { - int count = 0; - struct swap_info_struct *p; - swp_entry_t entry; + pgoff_t offset = swp_offset(entry); + struct swap_cluster_info *ci; + int count; - entry.val = page_private(page); - p = swap_info_get(entry); - if (p) { - count = swap_count(p->swap_map[swp_offset(entry)]); - spin_unlock(&p->lock); - } - return count; + ci = swap_cluster_lock(si, offset); + count = swap_count(si->swap_map[offset]); + swap_cluster_unlock(ci); + return !!count; } /* - * We can write to an anon page without COW if there are no other references - * to it. And as a side-effect, free up its swap: because the old content - * on disk will never be read, and seeking back there to write new content - * later would only waste time away from clustering. + * How many references to @entry are currently swapped out? + * This considers COUNT_CONTINUED so it returns exact answer. */ -int reuse_swap_page(struct page *page) +int swp_swapcount(swp_entry_t entry) { - int count; + int count, tmp_count, n; + struct swap_info_struct *si; + struct swap_cluster_info *ci; + struct page *page; + pgoff_t offset; + unsigned char *map; - VM_BUG_ON(!PageLocked(page)); - if (unlikely(PageKsm(page))) + si = _swap_info_get(entry); + if (!si) return 0; - count = page_mapcount(page); - if (count <= 1 && PageSwapCache(page)) { - count += page_swapcount(page); - if (count == 1 && !PageWriteback(page)) { - delete_from_swap_cache(page); - SetPageDirty(page); + + offset = swp_offset(entry); + + ci = swap_cluster_lock(si, offset); + + count = swap_count(si->swap_map[offset]); + if (!(count & COUNT_CONTINUED)) + goto out; + + count &= ~COUNT_CONTINUED; + n = SWAP_MAP_MAX + 1; + + page = vmalloc_to_page(si->swap_map + offset); + offset &= ~PAGE_MASK; + VM_BUG_ON(page_private(page) != SWP_CONTINUED); + + do { + page = list_next_entry(page, lru); + map = kmap_local_page(page); + tmp_count = map[offset]; + kunmap_local(map); + + count += (tmp_count & ~COUNT_CONTINUED) * n; + n *= (SWAP_CONT_MAX + 1); + } while (tmp_count & COUNT_CONTINUED); +out: + swap_cluster_unlock(ci); + return count; +} + +static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, + swp_entry_t entry, int order) +{ + struct swap_cluster_info *ci; + unsigned char *map = si->swap_map; + unsigned int nr_pages = 1 << order; + unsigned long roffset = swp_offset(entry); + unsigned long offset = round_down(roffset, nr_pages); + int i; + bool ret = false; + + ci = swap_cluster_lock(si, offset); + if (nr_pages == 1) { + if (swap_count(map[roffset])) + ret = true; + goto unlock_out; + } + for (i = 0; i < nr_pages; i++) { + if (swap_count(map[offset + i])) { + ret = true; + break; } } - return count <= 1; +unlock_out: + swap_cluster_unlock(ci); + return ret; } -/* - * If swap is getting full, or if there are no more mappings of this page, - * then try_to_free_swap is called to free its swap space. - */ -int try_to_free_swap(struct page *page) +static bool folio_swapped(struct folio *folio) { - VM_BUG_ON(!PageLocked(page)); + swp_entry_t entry = folio->swap; + struct swap_info_struct *si = _swap_info_get(entry); - if (!PageSwapCache(page)) - return 0; - if (PageWriteback(page)) - return 0; - if (page_swapcount(page)) - return 0; + if (!si) + return false; + + if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) + return swap_entry_swapped(si, entry); + + return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); +} + +static bool folio_swapcache_freeable(struct folio *folio) +{ + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + + if (!folio_test_swapcache(folio)) + return false; + if (folio_test_writeback(folio)) + return false; /* * Once hibernation has begun to create its image of memory, - * there's a danger that one of the calls to try_to_free_swap() + * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free - * the swap from a page which has already been recorded in the - * image as a clean swapcache page, and then reuse its swap for + * the swap from a folio which has already been recorded in the + * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the - * original page might be freed under memory pressure, then + * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * - * Hibration suspends storage while it is writing the image + * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) - return 0; + return false; - delete_from_swap_cache(page); - SetPageDirty(page); - return 1; + return true; } -/* - * Free the swap entry like above, but also try to - * free the page cache entry if it is the last user. +/** + * folio_free_swap() - Free the swap space used for this folio. + * @folio: The folio to remove. + * + * If swap is getting full, or if there are no more mappings of this folio, + * then call folio_free_swap to free its swap space. + * + * Return: true if we were able to release the swap space. */ -int free_swap_and_cache(swp_entry_t entry) +bool folio_free_swap(struct folio *folio) { - struct swap_info_struct *p; - struct page *page = NULL; - - if (non_swap_entry(entry)) - return 1; - - p = swap_info_get(entry); - if (p) { - if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) { - page = find_get_page(swap_address_space(entry), - entry.val); - if (page && !trylock_page(page)) { - page_cache_release(page); - page = NULL; - } + if (!folio_swapcache_freeable(folio)) + return false; + if (folio_swapped(folio)) + return false; + + swap_cache_del_folio(folio); + folio_set_dirty(folio); + return true; +} + +/** + * free_swap_and_cache_nr() - Release reference on range of swap entries and + * reclaim their cache if no more references remain. + * @entry: First entry of range. + * @nr: Number of entries in range. + * + * For each swap entry in the contiguous range, release a reference. If any swap + * entries become free, try to reclaim their underlying folios, if present. The + * offset range is defined by [entry.offset, entry.offset + nr). + */ +void free_swap_and_cache_nr(swp_entry_t entry, int nr) +{ + const unsigned long start_offset = swp_offset(entry); + const unsigned long end_offset = start_offset + nr; + struct swap_info_struct *si; + bool any_only_cache = false; + unsigned long offset; + + si = get_swap_device(entry); + if (!si) + return; + + if (WARN_ON(end_offset > si->max)) + goto out; + + /* + * First free all entries in the range. + */ + any_only_cache = swap_entries_put_map_nr(si, entry, nr); + + /* + * Short-circuit the below loop if none of the entries had their + * reference drop to zero. + */ + if (!any_only_cache) + goto out; + + /* + * Now go back over the range trying to reclaim the swap cache. + */ + for (offset = start_offset; offset < end_offset; offset += nr) { + nr = 1; + if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { + /* + * Folios are always naturally aligned in swap so + * advance forward to the next boundary. Zero means no + * folio was found for the swap entry, so advance by 1 + * in this case. Negative value means folio was found + * but could not be reclaimed. Here we can still advance + * to the next boundary. + */ + nr = __try_to_reclaim_swap(si, offset, + TTRS_UNMAPPED | TTRS_FULL); + if (nr == 0) + nr = 1; + else if (nr < 0) + nr = -nr; + nr = ALIGN(offset + 1, nr) - offset; } - spin_unlock(&p->lock); } - if (page) { - /* - * Not mapped elsewhere, or swap space full? Free it! - * Also recheck PageSwapCache now page is locked (above). - */ - if (PageSwapCache(page) && !PageWriteback(page) && - (!page_mapped(page) || vm_swap_full())) { - delete_from_swap_cache(page); - SetPageDirty(page); + +out: + put_swap_device(si); +} + +#ifdef CONFIG_HIBERNATION + +swp_entry_t get_swap_page_of_type(int type) +{ + struct swap_info_struct *si = swap_type_to_info(type); + unsigned long offset; + swp_entry_t entry = {0}; + + if (!si) + goto fail; + + /* This is called for allocating swap entry, not cache */ + if (get_swap_device_info(si)) { + if (si->flags & SWP_WRITEOK) { + /* + * Grab the local lock to be complaint + * with swap table allocation. + */ + local_lock(&percpu_swap_cluster.lock); + offset = cluster_alloc_swap_entry(si, 0, 1); + local_unlock(&percpu_swap_cluster.lock); + if (offset) + entry = swp_entry(si->type, offset); } - unlock_page(page); - page_cache_release(page); + put_swap_device(si); } - return p != NULL; +fail: + return entry; } -#ifdef CONFIG_HIBERNATION /* * Find the swap type that corresponds to given device (if any). * @@ -782,13 +2041,12 @@ int free_swap_and_cache(swp_entry_t entry) * * This is needed for the suspend to disk (aka swsusp). */ -int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) +int swap_type_of(dev_t device, sector_t offset) { - struct block_device *bdev = NULL; int type; - if (device) - bdev = bdget(device); + if (!device) + return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { @@ -797,30 +2055,34 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) if (!(sis->flags & SWP_WRITEOK)) continue; - if (!bdev) { - if (bdev_p) - *bdev_p = bdgrab(sis->bdev); - - spin_unlock(&swap_lock); - return type; - } - if (bdev == sis->bdev) { - struct swap_extent *se = &sis->first_swap_extent; + if (device == sis->bdev->bd_dev) { + struct swap_extent *se = first_se(sis); if (se->start_block == offset) { - if (bdev_p) - *bdev_p = bdgrab(sis->bdev); - spin_unlock(&swap_lock); - bdput(bdev); return type; } } } spin_unlock(&swap_lock); - if (bdev) - bdput(bdev); + return -ENODEV; +} + +int find_first_swap(dev_t *device) +{ + int type; + + spin_lock(&swap_lock); + for (type = 0; type < nr_swapfiles; type++) { + struct swap_info_struct *sis = swap_info[type]; + if (!(sis->flags & SWP_WRITEOK)) + continue; + *device = sis->bdev->bd_dev; + spin_unlock(&swap_lock); + return type; + } + spin_unlock(&swap_lock); return -ENODEV; } @@ -830,13 +2092,13 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) */ sector_t swapdev_block(int type, pgoff_t offset) { - struct block_device *bdev; + struct swap_info_struct *si = swap_type_to_info(type); + struct swap_extent *se; - if ((unsigned int)type >= nr_swapfiles) - return 0; - if (!(swap_info[type]->flags & SWP_WRITEOK)) + if (!si || !(si->flags & SWP_WRITEOK)) return 0; - return map_swap_entry(swp_entry(type, offset), &bdev); + se = offset_to_swap_extent(si, offset); + return se->start_block + (offset - se->start_page); } /* @@ -857,7 +2119,7 @@ unsigned int count_swap_pages(int type, int free) if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) - n -= sis->inuse_pages; + n -= swap_usage_in_pages(sis); } spin_unlock(&sis->lock); } @@ -866,103 +2128,199 @@ unsigned int count_swap_pages(int type, int free) } #endif /* CONFIG_HIBERNATION */ +static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) +{ + return pte_same(pte_swp_clear_flags(pte), swp_pte); +} + /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, swp_entry_t entry, struct page *page) + unsigned long addr, swp_entry_t entry, struct folio *folio) { - struct page *swapcache; - struct mem_cgroup *memcg; + struct page *page; + struct folio *swapcache; spinlock_t *ptl; - pte_t *pte; + pte_t *pte, new_pte, old_pte; + bool hwpoisoned = false; int ret = 1; - swapcache = page; - page = ksm_might_need_to_copy(page, vma, addr); - if (unlikely(!page)) - return -ENOMEM; + /* + * If the folio is removed from swap cache by others, continue to + * unuse other PTEs. try_to_unuse may try again if we missed this one. + */ + if (!folio_matches_swap_entry(folio, entry)) + return 0; - if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, - GFP_KERNEL, &memcg)) { - ret = -ENOMEM; - goto out_nolock; + swapcache = folio; + folio = ksm_might_need_to_copy(folio, vma, addr); + if (unlikely(!folio)) + return -ENOMEM; + else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { + hwpoisoned = true; + folio = swapcache; } + page = folio_file_page(folio, swp_offset(entry)); + if (PageHWPoison(page)) + hwpoisoned = true; + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) { - mem_cgroup_cancel_charge_swapin(memcg); + if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), + swp_entry_to_pte(entry)))) { ret = 0; goto out; } + old_pte = ptep_get(pte); + + if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { + swp_entry_t swp_entry; + + dec_mm_counter(vma->vm_mm, MM_SWAPENTS); + if (hwpoisoned) { + swp_entry = make_hwpoison_entry(page); + } else { + swp_entry = make_poisoned_swp_entry(); + } + new_pte = swp_entry_to_pte(swp_entry); + ret = 0; + goto setpte; + } + + /* + * Some architectures may have to restore extra metadata to the page + * when reading from swap. This metadata may be indexed by swap entry + * so this must be called before swap_free(). + */ + arch_swap_restore(folio_swap(entry, folio), folio); + dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); - get_page(page); - set_pte_at(vma->vm_mm, addr, pte, - pte_mkold(mk_pte(page, vma->vm_page_prot))); - if (page == swapcache) - page_add_anon_rmap(page, vma, addr); - else /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, addr); - mem_cgroup_commit_charge_swapin(page, memcg); + folio_get(folio); + if (folio == swapcache) { + rmap_t rmap_flags = RMAP_NONE; + + /* + * See do_swap_page(): writeback would be problematic. + * However, we do a folio_wait_writeback() just before this + * call and have the folio locked. + */ + VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); + if (pte_swp_exclusive(old_pte)) + rmap_flags |= RMAP_EXCLUSIVE; + /* + * We currently only expect small !anon folios, which are either + * fully exclusive or fully shared. If we ever get large folios + * here, we have to be careful. + */ + if (!folio_test_anon(folio)) { + VM_WARN_ON_ONCE(folio_test_large(folio)); + VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); + folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); + } else { + folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); + } + } else { /* ksm created a completely new copy */ + folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); + folio_add_lru_vma(folio, vma); + } + new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); + if (pte_swp_soft_dirty(old_pte)) + new_pte = pte_mksoft_dirty(new_pte); + if (pte_swp_uffd_wp(old_pte)) + new_pte = pte_mkuffd_wp(new_pte); +setpte: + set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); - /* - * Move the page to the active list so it is not - * immediately swapped out again after swapon. - */ - activate_page(page); out: - pte_unmap_unlock(pte, ptl); -out_nolock: - if (page != swapcache) { - unlock_page(page); - put_page(page); + if (pte) + pte_unmap_unlock(pte, ptl); + if (folio != swapcache) { + folio_unlock(folio); + folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - swp_entry_t entry, struct page *page) + unsigned long addr, unsigned long end, + unsigned int type) { - pte_t swp_pte = swp_entry_to_pte(entry); - pte_t *pte; - int ret = 0; + pte_t *pte = NULL; + struct swap_info_struct *si; - /* - * We don't actually need pte lock while scanning for swp_pte: since - * we hold page lock and mmap_sem, swp_pte cannot be inserted into the - * page table while we're scanning; though it could get zapped, and on - * some architectures (e.g. x86_32 with PAE) we might catch a glimpse - * of unmatched parts which look like swp_pte, so unuse_pte must - * recheck under pte lock. Scanning without pte lock lets it be - * preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE. - */ - pte = pte_offset_map(pmd, addr); + si = swap_info[type]; do { - /* - * swapoff spends a _lot_ of time in this loop! - * Test inline before going to call unuse_pte. - */ - if (unlikely(pte_same(*pte, swp_pte))) { - pte_unmap(pte); - ret = unuse_pte(vma, pmd, addr, entry, page); - if (ret) - goto out; + struct folio *folio; + unsigned long offset; + unsigned char swp_count; + softleaf_t entry; + int ret; + pte_t ptent; + + if (!pte++) { pte = pte_offset_map(pmd, addr); + if (!pte) + break; } - } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap(pte - 1); -out: - return ret; + + ptent = ptep_get_lockless(pte); + entry = softleaf_from_pte(ptent); + + if (!softleaf_is_swap(entry)) + continue; + if (swp_type(entry) != type) + continue; + + offset = swp_offset(entry); + pte_unmap(pte); + pte = NULL; + + folio = swap_cache_get_folio(entry); + if (!folio) { + struct vm_fault vmf = { + .vma = vma, + .address = addr, + .real_address = addr, + .pmd = pmd, + }; + + folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, + &vmf); + } + if (!folio) { + swp_count = READ_ONCE(si->swap_map[offset]); + if (swp_count == 0 || swp_count == SWAP_MAP_BAD) + continue; + return -ENOMEM; + } + + folio_lock(folio); + folio_wait_writeback(folio); + ret = unuse_pte(vma, pmd, addr, entry, folio); + if (ret < 0) { + folio_unlock(folio); + folio_put(folio); + return ret; + } + + folio_free_swap(folio); + folio_unlock(folio); + folio_put(folio); + } while (addr += PAGE_SIZE, addr != end); + + if (pte) + pte_unmap(pte); + return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, - swp_entry_t entry, struct page *page) + unsigned int type) { pmd_t *pmd; unsigned long next; @@ -970,100 +2328,108 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { + cond_resched(); next = pmd_addr_end(addr, end); - if (pmd_none_or_trans_huge_or_clear_bad(pmd)) - continue; - ret = unuse_pte_range(vma, pmd, addr, next, entry, page); + ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } -static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, +static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, - swp_entry_t entry, struct page *page) + unsigned int type) { pud_t *pud; unsigned long next; int ret; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - ret = unuse_pmd_range(vma, pud, addr, next, entry, page); + ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } -static int unuse_vma(struct vm_area_struct *vma, - swp_entry_t entry, struct page *page) +static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned int type) +{ + p4d_t *p4d; + unsigned long next; + int ret; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + ret = unuse_pud_range(vma, p4d, addr, next, type); + if (ret) + return ret; + } while (p4d++, addr = next, addr != end); + return 0; +} + +static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; - if (page_anon_vma(page)) { - addr = page_address_in_vma(page, vma); - if (addr == -EFAULT) - return 0; - else - end = addr + PAGE_SIZE; - } else { - addr = vma->vm_start; - end = vma->vm_end; - } + addr = vma->vm_start; + end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - ret = unuse_pud_range(vma, pgd, addr, next, entry, page); + ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } -static int unuse_mm(struct mm_struct *mm, - swp_entry_t entry, struct page *page) +static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; + VMA_ITERATOR(vmi, mm, 0); + + mmap_read_lock(mm); + if (check_stable_address_space(mm)) + goto unlock; + for_each_vma(vmi, vma) { + if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { + ret = unuse_vma(vma, type); + if (ret) + break; + } - if (!down_read_trylock(&mm->mmap_sem)) { - /* - * Activate page so shrink_inactive_list is unlikely to unmap - * its ptes while lock is dropped, so swapoff can make progress. - */ - activate_page(page); - unlock_page(page); - down_read(&mm->mmap_sem); - lock_page(page); - } - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (vma->anon_vma && (ret = unuse_vma(vma, entry, page))) - break; + cond_resched(); } - up_read(&mm->mmap_sem); - return (ret < 0)? ret: 0; +unlock: + mmap_read_unlock(mm); + return ret; } /* - * Scan swap_map (or frontswap_map if frontswap parameter is true) - * from current position to next entry still in use. - * Recycle to start on reaching the end, returning 0 when empty. + * Scan swap_map from current position to next entry still in use. + * Return 0 if there are no inuse entries after prev till end of + * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, - unsigned int prev, bool frontswap) + unsigned int prev) { - unsigned int max = si->max; - unsigned int i = prev; + unsigned int i; unsigned char count; /* @@ -1072,250 +2438,120 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ - for (;;) { - if (++i >= max) { - if (!prev) { - i = 0; - break; - } - /* - * No entries in use at top of swap_map, - * loop back to start and recheck there. - */ - max = prev + 1; - prev = 0; - i = 1; - } - if (frontswap) { - if (frontswap_test(si, i)) - break; - else - continue; - } - count = si->swap_map[i]; + for (i = prev + 1; i < si->max; i++) { + count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; + if ((i % LATENCY_LIMIT) == 0) + cond_resched(); } + + if (i == si->max) + i = 0; + return i; } -/* - * We completely avoid races by reading each swap page in advance, - * and then search for the process using it. All the necessary - * page table adjustments can then be made atomically. - * - * if the boolean frontswap is true, only unuse pages_to_unuse pages; - * pages_to_unuse==0 means all pages; ignored if frontswap is false - */ -int try_to_unuse(unsigned int type, bool frontswap, - unsigned long pages_to_unuse) +static int try_to_unuse(unsigned int type) { + struct mm_struct *prev_mm; + struct mm_struct *mm; + struct list_head *p; + int retval = 0; struct swap_info_struct *si = swap_info[type]; - struct mm_struct *start_mm; - unsigned char *swap_map; - unsigned char swcount; - struct page *page; + struct folio *folio; swp_entry_t entry; - unsigned int i = 0; - int retval = 0; + unsigned int i; - /* - * When searching mms for an entry, a good strategy is to - * start at the first mm we freed the previous entry from - * (though actually we don't notice whether we or coincidence - * freed the entry). Initialize this start_mm with a hold. - * - * A simpler strategy would be to start at the last mm we - * freed the previous entry from; but that would take less - * advantage of mmlist ordering, which clusters forked mms - * together, child after parent. If we race with dup_mmap(), we - * prefer to resolve parent before child, lest we miss entries - * duplicated after we scanned child: using last mm would invert - * that. - */ - start_mm = &init_mm; - atomic_inc(&init_mm.mm_users); + if (!swap_usage_in_pages(si)) + goto success; - /* - * Keep on scanning until all entries have gone. Usually, - * one pass through swap_map is enough, but not necessarily: - * there are races when an instance of an entry might be missed. - */ - while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { - if (signal_pending(current)) { - retval = -EINTR; - break; - } +retry: + retval = shmem_unuse(type); + if (retval) + return retval; - /* - * Get a page for the entry, using the existing swap - * cache page if there is one. Otherwise, get a clean - * page and read the swap into it. - */ - swap_map = &si->swap_map[i]; - entry = swp_entry(type, i); - page = read_swap_cache_async(entry, - GFP_HIGHUSER_MOVABLE, NULL, 0); - if (!page) { - /* - * Either swap_duplicate() failed because entry - * has been freed independently, and will not be - * reused since sys_swapoff() already disabled - * allocation from here, or alloc_page() failed. - */ - if (!*swap_map) - continue; - retval = -ENOMEM; - break; - } + prev_mm = &init_mm; + mmget(prev_mm); - /* - * Don't hold on to start_mm if it looks like exiting. - */ - if (atomic_read(&start_mm->mm_users) == 1) { - mmput(start_mm); - start_mm = &init_mm; - atomic_inc(&init_mm.mm_users); - } - - /* - * Wait for and lock page. When do_swap_page races with - * try_to_unuse, do_swap_page can handle the fault much - * faster than try_to_unuse can locate the entry. This - * apparently redundant "wait_on_page_locked" lets try_to_unuse - * defer to do_swap_page in such a case - in some tests, - * do_swap_page and try_to_unuse repeatedly compete. - */ - wait_on_page_locked(page); - wait_on_page_writeback(page); - lock_page(page); - wait_on_page_writeback(page); + spin_lock(&mmlist_lock); + p = &init_mm.mmlist; + while (swap_usage_in_pages(si) && + !signal_pending(current) && + (p = p->next) != &init_mm.mmlist) { - /* - * Remove all references to entry. - */ - swcount = *swap_map; - if (swap_count(swcount) == SWAP_MAP_SHMEM) { - retval = shmem_unuse(entry, page); - /* page has already been unlocked and released */ - if (retval < 0) - break; + mm = list_entry(p, struct mm_struct, mmlist); + if (!mmget_not_zero(mm)) continue; - } - if (swap_count(swcount) && start_mm != &init_mm) - retval = unuse_mm(start_mm, entry, page); - - if (swap_count(*swap_map)) { - int set_start_mm = (*swap_map >= swcount); - struct list_head *p = &start_mm->mmlist; - struct mm_struct *new_start_mm = start_mm; - struct mm_struct *prev_mm = start_mm; - struct mm_struct *mm; - - atomic_inc(&new_start_mm->mm_users); - atomic_inc(&prev_mm->mm_users); - spin_lock(&mmlist_lock); - while (swap_count(*swap_map) && !retval && - (p = p->next) != &start_mm->mmlist) { - mm = list_entry(p, struct mm_struct, mmlist); - if (!atomic_inc_not_zero(&mm->mm_users)) - continue; - spin_unlock(&mmlist_lock); - mmput(prev_mm); - prev_mm = mm; - - cond_resched(); - - swcount = *swap_map; - if (!swap_count(swcount)) /* any usage ? */ - ; - else if (mm == &init_mm) - set_start_mm = 1; - else - retval = unuse_mm(mm, entry, page); - - if (set_start_mm && *swap_map < swcount) { - mmput(new_start_mm); - atomic_inc(&mm->mm_users); - new_start_mm = mm; - set_start_mm = 0; - } - spin_lock(&mmlist_lock); - } - spin_unlock(&mmlist_lock); - mmput(prev_mm); - mmput(start_mm); - start_mm = new_start_mm; - } + spin_unlock(&mmlist_lock); + mmput(prev_mm); + prev_mm = mm; + retval = unuse_mm(mm, type); if (retval) { - unlock_page(page); - page_cache_release(page); - break; + mmput(prev_mm); + return retval; } /* - * If a reference remains (rare), we would like to leave - * the page in the swap cache; but try_to_unmap could - * then re-duplicate the entry once we drop page lock, - * so we might loop indefinitely; also, that page could - * not be swapped out to other storage meanwhile. So: - * delete from cache even if there's another reference, - * after ensuring that the data has been saved to disk - - * since if the reference remains (rarer), it will be - * read from disk into another page. Splitting into two - * pages would be incorrect if swap supported "shared - * private" pages, but they are handled by tmpfs files. - * - * Given how unuse_vma() targets one particular offset - * in an anon_vma, once the anon_vma has been determined, - * this splitting happens to be just what is needed to - * handle where KSM pages have been swapped out: re-reading - * is unnecessarily slow, but we can fix that later on. + * Make sure that we aren't completely killing + * interactive performance. */ - if (swap_count(*swap_map) && - PageDirty(page) && PageSwapCache(page)) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - }; + cond_resched(); + spin_lock(&mmlist_lock); + } + spin_unlock(&mmlist_lock); - swap_writepage(page, &wbc); - lock_page(page); - wait_on_page_writeback(page); - } + mmput(prev_mm); - /* - * It is conceivable that a racing task removed this page from - * swap cache just before we acquired the page lock at the top, - * or while we dropped it in unuse_mm(). The page might even - * be back in swap cache on another swap area: that we must not - * delete, since it may not have been written out to swap yet. - */ - if (PageSwapCache(page) && - likely(page_private(page) == entry.val)) - delete_from_swap_cache(page); + i = 0; + while (swap_usage_in_pages(si) && + !signal_pending(current) && + (i = find_next_to_unuse(si, i)) != 0) { - /* - * So we could skip searching mms once swap count went - * to 1, we did not mark any present ptes as dirty: must - * mark page dirty so shrink_page_list will preserve it. - */ - SetPageDirty(page); - unlock_page(page); - page_cache_release(page); + entry = swp_entry(type, i); + folio = swap_cache_get_folio(entry); + if (!folio) + continue; /* - * Make sure that we aren't completely killing - * interactive performance. + * It is conceivable that a racing task removed this folio from + * swap cache just before we acquired the page lock. The folio + * might even be back in swap cache on another swap area. But + * that is okay, folio_free_swap() only removes stale folios. */ - cond_resched(); - if (frontswap && pages_to_unuse > 0) { - if (!--pages_to_unuse) - break; - } + folio_lock(folio); + folio_wait_writeback(folio); + folio_free_swap(folio); + folio_unlock(folio); + folio_put(folio); + } + + /* + * Lets check again to see if there are still swap entries in the map. + * If yes, we would need to do retry the unuse logic again. + * Under global memory pressure, swap entries can be reinserted back + * into process space after the mmlist loop above passes over them. + * + * Limit the number of retries? No: when mmget_not_zero() + * above fails, that mm is likely to be freeing swap from + * exit_mmap(), which proceeds at its own independent pace; + * and even shmem_writeout() could have been preempted after + * folio_alloc_swap(), temporarily hiding that swap. It's easy + * and robust (though cpu-intensive) just to keep retrying. + */ + if (swap_usage_in_pages(si)) { + if (!signal_pending(current)) + goto retry; + return -EINTR; } - mmput(start_mm); - return retval; +success: + /* + * Make sure that further cleanups after try_to_unuse() returns happen + * after swap_range_free() reduces si->inuse_pages to 0. + */ + smp_mb(); + return 0; } /* @@ -1330,7 +2566,7 @@ static void drain_mmlist(void) unsigned int type; for (type = 0; type < nr_swapfiles; type++) - if (swap_info[type]->inuse_pages) + if (swap_usage_in_pages(swap_info[type])) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) @@ -1339,75 +2575,31 @@ static void drain_mmlist(void) } /* - * Use this swapdev's extent info to locate the (PAGE_SIZE) block which - * corresponds to page offset for the specified swap entry. - * Note that the type of this function is sector_t, but it returns page offset - * into the bdev, not sector offset. - */ -static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev) -{ - struct swap_info_struct *sis; - struct swap_extent *start_se; - struct swap_extent *se; - pgoff_t offset; - - sis = swap_info[swp_type(entry)]; - *bdev = sis->bdev; - - offset = swp_offset(entry); - start_se = sis->curr_swap_extent; - se = start_se; - - for ( ; ; ) { - struct list_head *lh; - - if (se->start_page <= offset && - offset < (se->start_page + se->nr_pages)) { - return se->start_block + (offset - se->start_page); - } - lh = se->list.next; - se = list_entry(lh, struct swap_extent, list); - sis->curr_swap_extent = se; - BUG_ON(se == start_se); /* It *must* be present */ - } -} - -/* - * Returns the page offset into bdev for the specified page's swap entry. - */ -sector_t map_swap_page(struct page *page, struct block_device **bdev) -{ - swp_entry_t entry; - entry.val = page_private(page); - return map_swap_entry(entry, bdev); -} - -/* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { - while (!list_empty(&sis->first_swap_extent.list)) { - struct swap_extent *se; + while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { + struct rb_node *rb = sis->swap_extent_root.rb_node; + struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); - se = list_entry(sis->first_swap_extent.list.next, - struct swap_extent, list); - list_del(&se->list); + rb_erase(rb, &sis->swap_extent_root); kfree(se); } - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; - sis->flags &= ~SWP_FILE; - mapping->a_ops->swap_deactivate(swap_file); + sis->flags &= ~SWP_ACTIVATED; + if (mapping->a_ops->swap_deactivate) + mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's - * extent list. The extent list is kept sorted in page order. + * extent tree. * * This function rather assumes that it is called in ascending page order. */ @@ -1415,20 +2607,21 @@ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { + struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; - struct list_head *lh; - - if (start_page == 0) { - se = &sis->first_swap_extent; - sis->curr_swap_extent = se; - se->start_page = 0; - se->nr_pages = nr_pages; - se->start_block = start_block; - return 1; - } else { - lh = sis->first_swap_extent.list.prev; /* Highest extent */ - se = list_entry(lh, struct swap_extent, list); + + /* + * place the new node at the right most since the + * function is called in ascending page order. + */ + while (*link) { + parent = *link; + link = &parent->rb_right; + } + + if (parent) { + se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ @@ -1437,9 +2630,7 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, } } - /* - * No merge. Insert a new extent, preserving ordering. - */ + /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; @@ -1447,14 +2638,16 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, new_se->nr_pages = nr_pages; new_se->start_block = start_block; - list_add_tail(&new_se->list, &sis->first_swap_extent.list); + rb_link_node(&new_se->rb_node, parent, link); + rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } +EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages - * onto a contiguous range of disk blocks. An ordered list of swap extents - * is built at swapon time and is then used at swap_writepage/swap_readpage + * onto a contiguous range of disk blocks. A rbtree of swap extents is + * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. @@ -1462,25 +2655,21 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap - * extent list operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK + * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks - * and will parse them into an ordered extent list, in PAGE_SIZE chunks. If - * some stray blocks are found which do not fall within the PAGE_SIZE alignment + * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray + * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * - * For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon. This - * prevents root from shooting her foot off by ftruncating an in-use swapfile, - * which will scribble on the fs. + * For all swap devices we set S_SWAPFILE across the life of the swapon. This + * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of - * extents in the list. To avoid much list walking, we cache the previous - * search location in `curr_swap_extent', and start new searches from there. - * This is extremely effective. The average number of iterations in - * map_swap_page() has been measured at about 0.3 per page. - akpm. + * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { @@ -1497,10 +2686,13 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); - if (!ret) { - sis->flags |= SWP_FILE; - ret = add_swap_extent(sis, 0, sis->max, 0); - *span = sis->pages; + if (ret < 0) + return ret; + sis->flags |= SWP_ACTIVATED; + if ((sis->flags & SWP_FS_OPS) && + sio_pool_init() != 0) { + destroy_swap_extents(sis); + return -ENOMEM; } return ret; } @@ -1508,66 +2700,140 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) return generic_swapfile_activate(sis, swap_file, span); } -static void _enable_swap_info(struct swap_info_struct *p, int prio, - unsigned char *swap_map) +static void setup_swap_info(struct swap_info_struct *si, int prio, + unsigned char *swap_map, + struct swap_cluster_info *cluster_info, + unsigned long *zeromap) +{ + si->prio = prio; + /* + * the plist prio is negated because plist ordering is + * low-to-high, while swap ordering is high-to-low + */ + si->list.prio = -si->prio; + si->avail_list.prio = -si->prio; + si->swap_map = swap_map; + si->cluster_info = cluster_info; + si->zeromap = zeromap; +} + +static void _enable_swap_info(struct swap_info_struct *si) { - int i, prev; + atomic_long_add(si->pages, &nr_swap_pages); + total_swap_pages += si->pages; - if (prio >= 0) - p->prio = prio; - else - p->prio = --least_priority; - p->swap_map = swap_map; - p->flags |= SWP_WRITEOK; - atomic_long_add(p->pages, &nr_swap_pages); - total_swap_pages += p->pages; - - /* insert swap space into swap_list: */ - prev = -1; - for (i = swap_list.head; i >= 0; i = swap_info[i]->next) { - if (p->prio >= swap_info[i]->prio) - break; - prev = i; - } - p->next = i; - if (prev < 0) - swap_list.head = swap_list.next = p->type; - else - swap_info[prev]->next = p->type; + assert_spin_locked(&swap_lock); + + plist_add(&si->list, &swap_active_head); + + /* Add back to available list */ + add_to_avail_list(si, true); } -static void enable_swap_info(struct swap_info_struct *p, int prio, +static void enable_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, - unsigned long *frontswap_map) + struct swap_cluster_info *cluster_info, + unsigned long *zeromap) { - frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); - spin_lock(&p->lock); - _enable_swap_info(p, prio, swap_map); - spin_unlock(&p->lock); + spin_lock(&si->lock); + setup_swap_info(si, prio, swap_map, cluster_info, zeromap); + spin_unlock(&si->lock); + spin_unlock(&swap_lock); + /* + * Finished initializing swap device, now it's safe to reference it. + */ + percpu_ref_resurrect(&si->users); + spin_lock(&swap_lock); + spin_lock(&si->lock); + _enable_swap_info(si); + spin_unlock(&si->lock); spin_unlock(&swap_lock); } -static void reinsert_swap_info(struct swap_info_struct *p) +static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); - spin_lock(&p->lock); - _enable_swap_info(p, p->prio, p->swap_map); - spin_unlock(&p->lock); + spin_lock(&si->lock); + setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap); + _enable_swap_info(si); + spin_unlock(&si->lock); spin_unlock(&swap_lock); } +/* + * Called after clearing SWP_WRITEOK, ensures cluster_alloc_range + * see the updated flags, so there will be no more allocations. + */ +static void wait_for_allocation(struct swap_info_struct *si) +{ + unsigned long offset; + unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER); + struct swap_cluster_info *ci; + + BUG_ON(si->flags & SWP_WRITEOK); + + for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) { + ci = swap_cluster_lock(si, offset); + swap_cluster_unlock(ci); + } +} + +static void free_cluster_info(struct swap_cluster_info *cluster_info, + unsigned long maxpages) +{ + struct swap_cluster_info *ci; + int i, nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); + + if (!cluster_info) + return; + for (i = 0; i < nr_clusters; i++) { + ci = cluster_info + i; + /* Cluster with bad marks count will have a remaining table */ + spin_lock(&ci->lock); + if (rcu_dereference_protected(ci->table, true)) { + ci->count = 0; + swap_cluster_free_table(ci); + } + spin_unlock(&ci->lock); + } + kvfree(cluster_info); +} + +/* + * Called after swap device's reference count is dead, so + * neither scan nor allocation will use it. + */ +static void flush_percpu_swap_cluster(struct swap_info_struct *si) +{ + int cpu, i; + struct swap_info_struct **pcp_si; + + for_each_possible_cpu(cpu) { + pcp_si = per_cpu_ptr(percpu_swap_cluster.si, cpu); + /* + * Invalidate the percpu swap cluster cache, si->users + * is dead, so no new user will point to it, just flush + * any existing user. + */ + for (i = 0; i < SWAP_NR_ORDERS; i++) + cmpxchg(&pcp_si[i], si, NULL); + } +} + + SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; - unsigned long *frontswap_map; + unsigned long *zeromap; + struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; - int i, type, prev; - int err; + unsigned int maxpages; + int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1584,17 +2850,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out; mapping = victim->f_mapping; - prev = -1; spin_lock(&swap_lock); - for (type = swap_list.head; type >= 0; type = swap_info[type]->next) { - p = swap_info[type]; + plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { - if (p->swap_file->f_mapping == mapping) + if (p->swap_file->f_mapping == mapping) { + found = 1; break; + } } - prev = type; } - if (type < 0) { + if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; @@ -1606,28 +2871,18 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - if (prev < 0) - swap_list.head = p->next; - else - swap_info[prev]->next = p->next; - if (type == swap_list.next) { - /* just pick something that's safe... */ - swap_list.next = swap_list.head; - } spin_lock(&p->lock); - if (p->prio < 0) { - for (i = p->next; i >= 0; i = swap_info[i]->next) - swap_info[i]->prio = p->prio--; - least_priority++; - } + del_from_avail_list(p, true); + plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; - p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); + wait_for_allocation(p); + set_current_oom_origin(); - err = try_to_unuse(type, false, 0); /* force all pages to be unused */ + err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { @@ -1636,53 +2891,73 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out_dput; } + /* + * Wait for swap operations protected by get/put_swap_device() + * to complete. Because of synchronize_rcu() here, all swap + * operations protected by RCU reader side lock (including any + * spinlock) will be waited too. This makes it easy to + * prevent folio_test_swapcache() and the following swap cache + * operations from racing with swapoff. + */ + percpu_ref_kill(&p->users); + synchronize_rcu(); + wait_for_completion(&p->comp); + + flush_work(&p->discard_work); + flush_work(&p->reclaim_work); + flush_percpu_swap_cluster(p); + destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); + if (!(p->flags & SWP_SOLIDSTATE)) + atomic_dec(&nr_rotate_swap); + mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); - /* wait for anyone still in scan_swap_map */ - p->highest_bit = 0; /* cuts scans short */ - while (p->flags >= SWP_SCANNING) { - spin_unlock(&p->lock); - spin_unlock(&swap_lock); - schedule_timeout_uninterruptible(1); - spin_lock(&swap_lock); - spin_lock(&p->lock); - } - swap_file = p->swap_file; p->swap_file = NULL; - p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; - p->flags = 0; - frontswap_map = frontswap_map_get(p); - frontswap_map_set(p, NULL); + zeromap = p->zeromap; + p->zeromap = NULL; + maxpages = p->max; + cluster_info = p->cluster_info; + p->max = 0; + p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); - frontswap_invalidate_area(type); + arch_swap_invalidate_area(p->type); + zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); + kfree(p->global_cluster); + p->global_cluster = NULL; vfree(swap_map); - vfree(frontswap_map); - /* Destroy swap account informatin */ - swap_cgroup_swapoff(type); + kvfree(zeromap); + free_cluster_info(cluster_info, maxpages); + /* Destroy swap account information */ + swap_cgroup_swapoff(p->type); inode = mapping->host; - if (S_ISBLK(inode->i_mode)) { - struct block_device *bdev = I_BDEV(inode); - set_blocksize(bdev, p->old_block_size); - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); - } else { - mutex_lock(&inode->i_mutex); - inode->i_flags &= ~S_SWAPFILE; - mutex_unlock(&inode->i_mutex); - } + + inode_lock(inode); + inode->i_flags &= ~S_SWAPFILE; + inode_unlock(inode); filp_close(swap_file, NULL); + + /* + * Clear the SWP_USED flag after all resources are freed so that swapon + * can reuse this swap_info in alloc_swap_info() safely. It is ok to + * not hold p->lock after we cleared its SWP_WRITEOK. + */ + spin_lock(&swap_lock); + p->flags = 0; + spin_unlock(&swap_lock); + err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); @@ -1695,7 +2970,7 @@ out: } #ifdef CONFIG_PROC_FS -static unsigned swaps_poll(struct file *file, poll_table *wait) +static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; @@ -1703,10 +2978,10 @@ static unsigned swaps_poll(struct file *file, poll_table *wait) if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); - return POLLIN | POLLRDNORM | POLLERR | POLLPRI; + return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } /* iterator */ @@ -1721,9 +2996,7 @@ static void *swap_start(struct seq_file *swap, loff_t *pos) if (!l) return SEQ_START_TOKEN; - for (type = 0; type < nr_swapfiles; type++) { - smp_rmb(); /* read nr_swapfiles before swap_info[type] */ - si = swap_info[type]; + for (type = 0; (si = swap_type_to_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) @@ -1743,12 +3016,10 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) else type = si->type + 1; - for (; type < nr_swapfiles; type++) { - smp_rmb(); /* read nr_swapfiles before swap_info[type] */ - si = swap_info[type]; + ++(*pos); + for (; (si = swap_type_to_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; - ++*pos; return si; } @@ -1765,20 +3036,24 @@ static int swap_show(struct seq_file *swap, void *v) struct swap_info_struct *si = v; struct file *file; int len; + unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { - seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); + seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } + bytes = K(si->pages); + inuse = K(swap_usage_in_pages(si)); + file = si->swap_file; - len = seq_path(swap, &file->f_path, " \t\n\\"); - seq_printf(swap, "%*s%s\t%u\t%u\t%d\n", + len = seq_file_path(swap, file, " \t\n\\"); + seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", - si->pages << (PAGE_SHIFT - 10), - si->inuse_pages << (PAGE_SHIFT - 10), + bytes, bytes < 10000000 ? "\t" : "", + inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } @@ -1804,17 +3079,18 @@ static int swaps_open(struct inode *inode, struct file *file) return 0; } -static const struct file_operations proc_swaps_operations = { - .open = swaps_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, - .poll = swaps_poll, +static const struct proc_ops swaps_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, + .proc_open = swaps_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, + .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { - proc_create("swaps", 0, NULL, &proc_swaps_operations); + proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); @@ -1832,12 +3108,19 @@ late_initcall(max_swapfiles_check); static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; + struct swap_info_struct *defer = NULL; unsigned int type; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kvzalloc(sizeof(struct swap_info_struct), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); + if (percpu_ref_init(&p->users, swap_users_ref_free, + PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { + kvfree(p); + return ERR_PTR(-ENOMEM); + } + spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) @@ -1845,128 +3128,153 @@ static struct swap_info_struct *alloc_swap_info(void) } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); - kfree(p); + percpu_ref_exit(&p->users); + kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; - swap_info[type] = p; /* - * Write swap_info[type] before nr_swapfiles, in case a - * racing procfs swap_start() or swap_next() is reading them. - * (We never shrink nr_swapfiles, we never free this entry.) + * Publish the swap_info_struct after initializing it. + * Note that kvzalloc() above zeroes all its fields. */ - smp_wmb(); + smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { - kfree(p); + defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } - INIT_LIST_HEAD(&p->first_swap_extent.list); + p->swap_extent_root = RB_ROOT; + plist_node_init(&p->list, 0); + plist_node_init(&p->avail_list, 0); p->flags = SWP_USED; - p->next = -1; spin_unlock(&swap_lock); + if (defer) { + percpu_ref_exit(&defer->users); + kvfree(defer); + } spin_lock_init(&p->lock); + spin_lock_init(&p->cont_lock); + atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT); + init_completion(&p->comp); return p; } -static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) +static int claim_swapfile(struct swap_info_struct *si, struct inode *inode) { - int error; - if (S_ISBLK(inode->i_mode)) { - p->bdev = bdgrab(I_BDEV(inode)); - error = blkdev_get(p->bdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, - sys_swapon); - if (error < 0) { - p->bdev = NULL; + si->bdev = I_BDEV(inode); + /* + * Zoned block devices contain zones that have a sequential + * write only restriction. Hence zoned block devices are not + * suitable for swapping. Disallow them here. + */ + if (bdev_is_zoned(si->bdev)) return -EINVAL; - } - p->old_block_size = block_size(p->bdev); - error = set_blocksize(p->bdev, PAGE_SIZE); - if (error < 0) - return error; - p->flags |= SWP_BLKDEV; + si->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { - p->bdev = inode->i_sb->s_bdev; - mutex_lock(&inode->i_mutex); - if (IS_SWAPFILE(inode)) - return -EBUSY; - } else - return -EINVAL; + si->bdev = inode->i_sb->s_bdev; + } return 0; } -static unsigned long read_swap_header(struct swap_info_struct *p, + +/* + * Find out how many pages are allowed for a single swap device. There + * are two limiting factors: + * 1) the number of bits for the swap offset in the swp_entry_t type, and + * 2) the number of bits in the swap pte, as defined by the different + * architectures. + * + * In order to find the largest possible bit mask, a swap entry with + * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, + * decoded to a swp_entry_t again, and finally the swap offset is + * extracted. + * + * This will mask all the bits from the initial ~0UL mask that can't + * be encoded in either the swp_entry_t or the architecture definition + * of a swap pte. + */ +unsigned long generic_max_swapfile_size(void) +{ + swp_entry_t entry = swp_entry(0, ~0UL); + const pte_t pte = softleaf_to_pte(entry); + + /* + * Since the PTE can be an invalid softleaf entry (e.g. the none PTE), + * we need to do this manually. + */ + entry = __pte_to_swp_entry(pte); + entry = swp_entry(__swp_type(entry), __swp_offset(entry)); + + return swp_offset(entry) + 1; +} + +/* Can be overridden by an architecture for additional checks. */ +__weak unsigned long arch_max_swapfile_size(void) +{ + return generic_max_swapfile_size(); +} + +static unsigned long read_swap_header(struct swap_info_struct *si, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; + unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { - printk(KERN_ERR "Unable to find swap-space signature\n"); + pr_err("Unable to find swap-space signature\n"); return 0; } - /* swap partition endianess hack... */ + /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); + if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) + return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { - printk(KERN_WARNING - "Unable to handle swap header version %d\n", - swap_header->info.version); + pr_warn("Unable to handle swap header version %d\n", + swap_header->info.version); return 0; } - p->lowest_bit = 1; - p->cluster_next = 1; - p->cluster_nr = 0; - - /* - * Find out how many pages are allowed for a single swap - * device. There are two limiting factors: 1) the number - * of bits for the swap offset in the swp_entry_t type, and - * 2) the number of bits in the swap pte as defined by the - * different architectures. In order to find the - * largest possible bit mask, a swap entry with swap type 0 - * and swap offset ~0UL is created, encoded to a swap pte, - * decoded to a swp_entry_t again, and finally the swap - * offset is extracted. This will mask all the bits from - * the initial ~0UL mask that can't be encoded in either - * the swp_entry_t or the architecture definition of a - * swap pte. - */ - maxpages = swp_offset(pte_to_swp_entry( - swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; - if (maxpages > swap_header->info.last_page) { - maxpages = swap_header->info.last_page + 1; + maxpages = swapfile_maximum_size; + last_page = swap_header->info.last_page; + if (!last_page) { + pr_warn("Empty swap-file\n"); + return 0; + } + if (last_page > maxpages) { + pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", + K(maxpages), K(last_page)); + } + if (maxpages > last_page) { + maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } - p->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { - printk(KERN_WARNING - "Swap area shorter than signature indicates\n"); + pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) @@ -1977,66 +3285,117 @@ static unsigned long read_swap_header(struct swap_info_struct *p, return maxpages; } -static int setup_swap_map_and_extents(struct swap_info_struct *p, - union swap_header *swap_header, - unsigned char *swap_map, - unsigned long maxpages, - sector_t *span) +static int setup_swap_map(struct swap_info_struct *si, + union swap_header *swap_header, + unsigned char *swap_map, + unsigned long maxpages) { - int i; - unsigned int nr_good_pages; - int nr_extents; - - nr_good_pages = maxpages - 1; /* omit header page */ + unsigned long i; + swap_map[0] = SWAP_MAP_BAD; /* omit header page */ for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; - nr_good_pages--; + si->pages--; } } - if (nr_good_pages) { - swap_map[0] = SWAP_MAP_BAD; - p->max = maxpages; - p->pages = nr_good_pages; - nr_extents = setup_swap_extents(p, span); - if (nr_extents < 0) - return nr_extents; - nr_good_pages = p->pages; - } - if (!nr_good_pages) { - printk(KERN_WARNING "Empty swap-file\n"); + if (!si->pages) { + pr_warn("Empty swap-file\n"); return -EINVAL; } - return nr_extents; + return 0; } -/* - * Helper to sys_swapon determining if a given swap - * backing device queue supports DISCARD operations. - */ -static bool swap_discardable(struct swap_info_struct *si) +static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, + union swap_header *swap_header, + unsigned long maxpages) { - struct request_queue *q = bdev_get_queue(si->bdev); + unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); + struct swap_cluster_info *cluster_info; + int err = -ENOMEM; + unsigned long i; - if (!q || !blk_queue_discard(q)) - return false; + cluster_info = kvcalloc(nr_clusters, sizeof(*cluster_info), GFP_KERNEL); + if (!cluster_info) + goto err; - return true; + for (i = 0; i < nr_clusters; i++) + spin_lock_init(&cluster_info[i].lock); + + if (!(si->flags & SWP_SOLIDSTATE)) { + si->global_cluster = kmalloc(sizeof(*si->global_cluster), + GFP_KERNEL); + if (!si->global_cluster) + goto err; + for (i = 0; i < SWAP_NR_ORDERS; i++) + si->global_cluster->next[i] = SWAP_ENTRY_INVALID; + spin_lock_init(&si->global_cluster_lock); + } + + /* + * Mark unusable pages as unavailable. The clusters aren't + * marked free yet, so no list operations are involved yet. + * + * See setup_swap_map(): header page, bad pages, + * and the EOF part of the last cluster. + */ + err = swap_cluster_setup_bad_slot(cluster_info, 0); + if (err) + goto err; + for (i = 0; i < swap_header->info.nr_badpages; i++) { + unsigned int page_nr = swap_header->info.badpages[i]; + + if (page_nr >= maxpages) + continue; + err = swap_cluster_setup_bad_slot(cluster_info, page_nr); + if (err) + goto err; + } + for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) { + err = swap_cluster_setup_bad_slot(cluster_info, i); + if (err) + goto err; + } + + INIT_LIST_HEAD(&si->free_clusters); + INIT_LIST_HEAD(&si->full_clusters); + INIT_LIST_HEAD(&si->discard_clusters); + + for (i = 0; i < SWAP_NR_ORDERS; i++) { + INIT_LIST_HEAD(&si->nonfull_clusters[i]); + INIT_LIST_HEAD(&si->frag_clusters[i]); + } + + for (i = 0; i < nr_clusters; i++) { + struct swap_cluster_info *ci = &cluster_info[i]; + + if (ci->count) { + ci->flags = CLUSTER_FLAG_NONFULL; + list_add_tail(&ci->list, &si->nonfull_clusters[0]); + } else { + ci->flags = CLUSTER_FLAG_FREE; + list_add_tail(&ci->list, &si->free_clusters); + } + } + + return cluster_info; +err: + free_cluster_info(cluster_info, maxpages); + return ERR_PTR(err); } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { - struct swap_info_struct *p; + struct swap_info_struct *si; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; - int i; + struct dentry *dentry; int prio; int error; union swap_header *swap_header; @@ -2044,9 +3403,11 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; - unsigned long *frontswap_map = NULL; - struct page *page = NULL; + unsigned long *zeromap = NULL; + struct swap_cluster_info *cluster_info = NULL; + struct folio *folio = NULL; struct inode *inode = NULL; + bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; @@ -2054,9 +3415,12 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - p = alloc_swap_info(); - if (IS_ERR(p)) - return PTR_ERR(p); + si = alloc_swap_info(); + if (IS_ERR(si)) + return PTR_ERR(si); + + INIT_WORK(&si->discard_work, swap_discard_work); + INIT_WORK(&si->reclaim_work, swap_reclaim_work); name = getname(specialfile); if (IS_ERR(name)) { @@ -2064,165 +3428,217 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) name = NULL; goto bad_swap; } - swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); + swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } - p->swap_file = swap_file; + si->swap_file = swap_file; mapping = swap_file->f_mapping; + dentry = swap_file->f_path.dentry; + inode = mapping->host; - for (i = 0; i < nr_swapfiles; i++) { - struct swap_info_struct *q = swap_info[i]; + error = claim_swapfile(si, inode); + if (unlikely(error)) + goto bad_swap; - if (q == p || !q->swap_file) - continue; - if (mapping == q->swap_file->f_mapping) { - error = -EBUSY; - goto bad_swap; - } + inode_lock(inode); + if (d_unlinked(dentry) || cant_mount(dentry)) { + error = -ENOENT; + goto bad_swap_unlock_inode; + } + if (IS_SWAPFILE(inode)) { + error = -EBUSY; + goto bad_swap_unlock_inode; } - inode = mapping->host; - /* If S_ISREG(inode->i_mode) will do mutex_lock(&inode->i_mutex); */ - error = claim_swapfile(p, inode); - if (unlikely(error)) - goto bad_swap; + /* + * The swap subsystem needs a major overhaul to support this. + * It doesn't work yet so just disable it for now. + */ + if (mapping_min_folio_order(mapping) > 0) { + error = -EINVAL; + goto bad_swap_unlock_inode; + } /* * Read the swap header. */ - if (!mapping->a_ops->readpage) { + if (!mapping->a_ops->read_folio) { error = -EINVAL; - goto bad_swap; + goto bad_swap_unlock_inode; } - page = read_mapping_page(mapping, 0, swap_file); - if (IS_ERR(page)) { - error = PTR_ERR(page); - goto bad_swap; + folio = read_mapping_folio(mapping, 0, swap_file); + if (IS_ERR(folio)) { + error = PTR_ERR(folio); + goto bad_swap_unlock_inode; } - swap_header = kmap(page); + swap_header = kmap_local_folio(folio, 0); - maxpages = read_swap_header(p, swap_header, inode); + maxpages = read_swap_header(si, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; - goto bad_swap; + goto bad_swap_unlock_inode; + } + + si->max = maxpages; + si->pages = maxpages - 1; + nr_extents = setup_swap_extents(si, &span); + if (nr_extents < 0) { + error = nr_extents; + goto bad_swap_unlock_inode; } + if (si->pages != si->max - 1) { + pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max); + error = -EINVAL; + goto bad_swap_unlock_inode; + } + + maxpages = si->max; /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; - goto bad_swap; + goto bad_swap_unlock_inode; } - error = swap_cgroup_swapon(p->type, maxpages); + error = swap_cgroup_swapon(si->type, maxpages); if (error) - goto bad_swap; + goto bad_swap_unlock_inode; - nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, - maxpages, &span); - if (unlikely(nr_extents < 0)) { - error = nr_extents; - goto bad_swap; + error = setup_swap_map(si, swap_header, swap_map, maxpages); + if (error) + goto bad_swap_unlock_inode; + + /* + * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might + * be above MAX_PAGE_ORDER incase of a large swap file. + */ + zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), + GFP_KERNEL | __GFP_ZERO); + if (!zeromap) { + error = -ENOMEM; + goto bad_swap_unlock_inode; } - /* frontswap enabled? set up bit-per-page map for frontswap */ - if (frontswap_enabled) - frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long)); - if (p->bdev) { - if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { - p->flags |= SWP_SOLIDSTATE; - p->cluster_next = 1 + (prandom_u32() % p->highest_bit); - } + if (si->bdev && bdev_stable_writes(si->bdev)) + si->flags |= SWP_STABLE_WRITES; - if ((swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { - /* - * When discard is enabled for swap with no particular - * policy flagged, we set all swap discard flags here in - * order to sustain backward compatibility with older - * swapon(8) releases. - */ - p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | - SWP_PAGE_DISCARD); + if (si->bdev && bdev_synchronous(si->bdev)) + si->flags |= SWP_SYNCHRONOUS_IO; - /* - * By flagging sys_swapon, a sysadmin can tell us to - * either do single-time area discards only, or to just - * perform discards for released swap page-clusters. - * Now it's time to adjust the p->flags accordingly. - */ - if (swap_flags & SWAP_FLAG_DISCARD_ONCE) - p->flags &= ~SWP_PAGE_DISCARD; - else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) - p->flags &= ~SWP_AREA_DISCARD; - - /* issue a swapon-time discard if it's still required */ - if (p->flags & SWP_AREA_DISCARD) { - int err = discard_swap(p); - if (unlikely(err)) - printk(KERN_ERR - "swapon: discard_swap(%p): %d\n", - p, err); - } + if (si->bdev && bdev_nonrot(si->bdev)) { + si->flags |= SWP_SOLIDSTATE; + } else { + atomic_inc(&nr_rotate_swap); + inced_nr_rotate_swap = true; + } + + cluster_info = setup_clusters(si, swap_header, maxpages); + if (IS_ERR(cluster_info)) { + error = PTR_ERR(cluster_info); + cluster_info = NULL; + goto bad_swap_unlock_inode; + } + + if ((swap_flags & SWAP_FLAG_DISCARD) && + si->bdev && bdev_max_discard_sectors(si->bdev)) { + /* + * When discard is enabled for swap with no particular + * policy flagged, we set all swap discard flags here in + * order to sustain backward compatibility with older + * swapon(8) releases. + */ + si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | + SWP_PAGE_DISCARD); + + /* + * By flagging sys_swapon, a sysadmin can tell us to + * either do single-time area discards only, or to just + * perform discards for released swap page-clusters. + * Now it's time to adjust the p->flags accordingly. + */ + if (swap_flags & SWAP_FLAG_DISCARD_ONCE) + si->flags &= ~SWP_PAGE_DISCARD; + else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) + si->flags &= ~SWP_AREA_DISCARD; + + /* issue a swapon-time discard if it's still required */ + if (si->flags & SWP_AREA_DISCARD) { + int err = discard_swap(si); + if (unlikely(err)) + pr_err("swapon: discard_swap(%p): %d\n", + si, err); } } + error = zswap_swapon(si->type, maxpages); + if (error) + goto bad_swap_unlock_inode; + + /* + * Flush any pending IO and dirty mappings before we start using this + * swap device. + */ + inode->i_flags |= S_SWAPFILE; + error = inode_drain_writes(inode); + if (error) { + inode->i_flags &= ~S_SWAPFILE; + goto free_swap_zswap; + } + mutex_lock(&swapon_mutex); - prio = -1; + prio = DEF_SWAP_PRIO; if (swap_flags & SWAP_FLAG_PREFER) - prio = - (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; - enable_swap_info(p, prio, swap_map, frontswap_map); - - printk(KERN_INFO "Adding %uk swap on %s. " - "Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", - p->pages<<(PAGE_SHIFT-10), name->name, p->prio, - nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), - (p->flags & SWP_SOLIDSTATE) ? "SS" : "", - (p->flags & SWP_DISCARDABLE) ? "D" : "", - (p->flags & SWP_AREA_DISCARD) ? "s" : "", - (p->flags & SWP_PAGE_DISCARD) ? "c" : "", - (frontswap_map) ? "FS" : ""); + prio = swap_flags & SWAP_FLAG_PRIO_MASK; + enable_swap_info(si, prio, swap_map, cluster_info, zeromap); + + pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", + K(si->pages), name->name, si->prio, nr_extents, + K((unsigned long long)span), + (si->flags & SWP_SOLIDSTATE) ? "SS" : "", + (si->flags & SWP_DISCARDABLE) ? "D" : "", + (si->flags & SWP_AREA_DISCARD) ? "s" : "", + (si->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); - if (S_ISREG(inode->i_mode)) - inode->i_flags |= S_SWAPFILE; error = 0; goto out; +free_swap_zswap: + zswap_swapoff(si->type); +bad_swap_unlock_inode: + inode_unlock(inode); bad_swap: - if (inode && S_ISBLK(inode->i_mode) && p->bdev) { - set_blocksize(p->bdev, p->old_block_size); - blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); - } - destroy_swap_extents(p); - swap_cgroup_swapoff(p->type); + kfree(si->global_cluster); + si->global_cluster = NULL; + inode = NULL; + destroy_swap_extents(si); + swap_cgroup_swapoff(si->type); spin_lock(&swap_lock); - p->swap_file = NULL; - p->flags = 0; + si->swap_file = NULL; + si->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); - if (swap_file) { - if (inode && S_ISREG(inode->i_mode)) { - mutex_unlock(&inode->i_mutex); - inode = NULL; - } + kvfree(zeromap); + if (cluster_info) + free_cluster_info(cluster_info, maxpages); + if (inced_nr_rotate_swap) + atomic_dec(&nr_rotate_swap); + if (swap_file) filp_close(swap_file, NULL); - } out: - if (page && !IS_ERR(page)) { - kunmap(page); - page_cache_release(page); - } + if (!IS_ERR_OR_NULL(folio)) + folio_release_kmap(folio, swap_header); if (name) putname(name); - if (inode && S_ISREG(inode->i_mode)) - mutex_unlock(&inode->i_mutex); + if (inode) + inode_unlock(inode); return error; } @@ -2236,7 +3652,7 @@ void si_swapinfo(struct sysinfo *val) struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) - nr_to_be_unused += si->inuse_pages; + nr_to_be_unused += swap_usage_in_pages(si); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; @@ -2244,84 +3660,99 @@ void si_swapinfo(struct sysinfo *val) } /* - * Verify that a swap entry is valid and increment its swap map count. + * Verify that nr swap entries are valid and increment their swap map counts. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL - * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ -static int __swap_duplicate(swp_entry_t entry, unsigned char usage) +static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) { - struct swap_info_struct *p; - unsigned long offset, type; + struct swap_info_struct *si; + struct swap_cluster_info *ci; + unsigned long offset; unsigned char count; unsigned char has_cache; - int err = -EINVAL; + int err, i; - if (non_swap_entry(entry)) - goto out; + si = swap_entry_to_info(entry); + if (WARN_ON_ONCE(!si)) { + pr_err("%s%08lx\n", Bad_file, entry.val); + return -EINVAL; + } - type = swp_type(entry); - if (type >= nr_swapfiles) - goto bad_file; - p = swap_info[type]; offset = swp_offset(entry); + VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); + VM_WARN_ON(usage == 1 && nr > 1); + ci = swap_cluster_lock(si, offset); - spin_lock(&p->lock); - if (unlikely(offset >= p->max)) - goto unlock_out; - - count = p->swap_map[offset]; - has_cache = count & SWAP_HAS_CACHE; - count &= ~SWAP_HAS_CACHE; err = 0; + for (i = 0; i < nr; i++) { + count = si->swap_map[offset + i]; - if (usage == SWAP_HAS_CACHE) { + /* + * swapin_readahead() doesn't check if a swap entry is valid, so the + * swap entry could be SWAP_MAP_BAD. Check here with lock held. + */ + if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { + err = -ENOENT; + goto unlock_out; + } - /* set SWAP_HAS_CACHE if there is no cache and entry is used */ - if (!has_cache && count) - has_cache = SWAP_HAS_CACHE; - else if (has_cache) /* someone else added cache */ - err = -EEXIST; - else /* no users remaining */ + has_cache = count & SWAP_HAS_CACHE; + count &= ~SWAP_HAS_CACHE; + + if (!count && !has_cache) { err = -ENOENT; + } else if (usage == SWAP_HAS_CACHE) { + if (has_cache) + err = -EEXIST; + } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { + err = -EINVAL; + } - } else if (count || has_cache) { + if (err) + goto unlock_out; + } - if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) + for (i = 0; i < nr; i++) { + count = si->swap_map[offset + i]; + has_cache = count & SWAP_HAS_CACHE; + count &= ~SWAP_HAS_CACHE; + + if (usage == SWAP_HAS_CACHE) + has_cache = SWAP_HAS_CACHE; + else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; - else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) - err = -EINVAL; - else if (swap_count_continued(p, offset, count)) + else if (swap_count_continued(si, offset + i, count)) count = COUNT_CONTINUED; - else + else { + /* + * Don't need to rollback changes, because if + * usage == 1, there must be nr == 1. + */ err = -ENOMEM; - } else - err = -ENOENT; /* unused swap entry */ + goto unlock_out; + } - p->swap_map[offset] = count | has_cache; + WRITE_ONCE(si->swap_map[offset + i], count | has_cache); + } unlock_out: - spin_unlock(&p->lock); -out: + swap_cluster_unlock(ci); return err; - -bad_file: - printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val); - goto out; } /* * 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) +void swap_shmem_alloc(swp_entry_t entry, int nr) { - __swap_duplicate(entry, SWAP_MAP_SHMEM); + __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } /* @@ -2335,48 +3766,32 @@ int swap_duplicate(swp_entry_t entry) { int err = 0; - while (!err && __swap_duplicate(entry, 1) == -ENOMEM) + while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* - * @entry: swap entry for which we allocate swap cache. + * @entry: first swap entry from which we allocate nr swap cache. * - * Called when allocating swap cache for existing swap entry, + * Called when allocating swap cache for existing swap entries, * This can return error codes. Returns 0 at success. - * -EBUSY means there is a swap cache. + * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ -int swapcache_prepare(swp_entry_t entry) +int swapcache_prepare(swp_entry_t entry, int nr) { - return __swap_duplicate(entry, SWAP_HAS_CACHE); -} - -struct swap_info_struct *page_swap_info(struct page *page) -{ - swp_entry_t swap = { .val = page_private(page) }; - BUG_ON(!PageSwapCache(page)); - return swap_info[swp_type(swap)]; + return __swap_duplicate(entry, SWAP_HAS_CACHE, nr); } /* - * out-of-line __page_file_ methods to avoid include hell. + * Caller should ensure entries belong to the same folio so + * the entries won't span cross cluster boundary. */ -struct address_space *__page_file_mapping(struct page *page) -{ - VM_BUG_ON(!PageSwapCache(page)); - return page_swap_info(page)->swap_file->f_mapping; -} -EXPORT_SYMBOL_GPL(__page_file_mapping); - -pgoff_t __page_file_index(struct page *page) +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { - swp_entry_t swap = { .val = page_private(page) }; - VM_BUG_ON(!PageSwapCache(page)); - return swp_offset(swap); + swap_entries_put_cache(si, entry, nr); } -EXPORT_SYMBOL_GPL(__page_file_index); /* * add_swap_count_continuation - called when a swap count is duplicated @@ -2396,11 +3811,13 @@ EXPORT_SYMBOL_GPL(__page_file_index); int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; + struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; + int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better @@ -2408,18 +3825,20 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); - si = swap_info_get(entry); + si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing - * __swap_duplicate(): the swap entry has been freed, - * perhaps even the whole swap_map cleared for swapoff. + * __swap_duplicate(): the swap device may be swapoff */ goto outer; } offset = swp_offset(entry); - count = si->swap_map[offset] & ~SWAP_HAS_CACHE; + + ci = swap_cluster_lock(si, offset); + + count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* @@ -2431,18 +3850,14 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) } if (!page) { - spin_unlock(&si->lock); - return -ENOMEM; + ret = -ENOMEM; + goto out; } - /* - * We are fortunate that although vmalloc_to_page uses pte_offset_map, - * no architecture is using highmem pages for kernel pagetables: so it - * will not corrupt the GFP_ATOMIC caller's atomic pagetable kmaps. - */ head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; + spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. @@ -2462,28 +3877,31 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) - goto out; + goto out_unlock_cont; - map = kmap_atomic(list_page) + offset; + map = kmap_local_page(list_page) + offset; count = *map; - kunmap_atomic(map); + kunmap_local(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) - goto out; + goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ +out_unlock_cont: + spin_unlock(&si->cont_lock); out: - spin_unlock(&si->lock); + swap_cluster_unlock(ci); + put_swap_device(si); outer: if (page) __free_page(page); - return 0; + return ret; } /* @@ -2492,7 +3910,8 @@ outer: * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. - * Called while __swap_duplicate() or swap_entry_free() holds swap_lock. + * Called while __swap_duplicate() or caller of swap_entry_put_locked() + * holds cluster lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) @@ -2500,6 +3919,7 @@ static bool swap_count_continued(struct swap_info_struct *si, struct page *head; struct page *page; unsigned char *map; + bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { @@ -2507,9 +3927,10 @@ static bool swap_count_continued(struct swap_info_struct *si, return false; /* need to add count continuation */ } + spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; - page = list_entry(head->lru.next, struct page, lru); - map = kmap_atomic(page) + offset; + page = list_next_entry(head, lru); + map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ @@ -2519,29 +3940,29 @@ static bool swap_count_continued(struct swap_info_struct *si, * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { - kunmap_atomic(map); - page = list_entry(page->lru.next, struct page, lru); + kunmap_local(map); + page = list_next_entry(page, lru); BUG_ON(page == head); - map = kmap_atomic(page) + offset; + map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { - kunmap_atomic(map); - page = list_entry(page->lru.next, struct page, lru); - if (page == head) - return false; /* add count continuation */ - map = kmap_atomic(page) + offset; + kunmap_local(map); + page = list_next_entry(page, lru); + if (page == head) { + ret = false; /* add count continuation */ + goto out; + } + map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; - kunmap_atomic(map); - page = list_entry(page->lru.prev, struct page, lru); - while (page != head) { - map = kmap_atomic(page) + offset; + kunmap_local(map); + while ((page = list_prev_entry(page, lru)) != head) { + map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; - kunmap_atomic(map); - page = list_entry(page->lru.prev, struct page, lru); + kunmap_local(map); } - return true; /* incremented */ + ret = true; /* incremented */ } else { /* decrementing */ /* @@ -2549,26 +3970,27 @@ init_map: *map = 0; /* we didn't zero the page */ */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { - kunmap_atomic(map); - page = list_entry(page->lru.next, struct page, lru); + kunmap_local(map); + page = list_next_entry(page, lru); BUG_ON(page == head); - map = kmap_atomic(page) + offset; + map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; - kunmap_atomic(map); - page = list_entry(page->lru.prev, struct page, lru); - while (page != head) { - map = kmap_atomic(page) + offset; + kunmap_local(map); + while ((page = list_prev_entry(page, lru)) != head) { + map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; - kunmap_atomic(map); - page = list_entry(page->lru.prev, struct page, lru); + kunmap_local(map); } - return count == COUNT_CONTINUED; + ret = count == COUNT_CONTINUED; } +out: + spin_unlock(&si->cont_lock); + return ret; } /* @@ -2583,13 +4005,72 @@ static void free_swap_count_continuations(struct swap_info_struct *si) struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { - struct list_head *this, *next; - list_for_each_safe(this, next, &head->lru) { - struct page *page; - page = list_entry(this, struct page, lru); - list_del(this); + struct page *page, *next; + + list_for_each_entry_safe(page, next, &head->lru, lru) { + list_del(&page->lru); __free_page(page); } } } } + +#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +static bool __has_usable_swap(void) +{ + return !plist_head_empty(&swap_active_head); +} + +void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) +{ + struct swap_info_struct *si; + + if (!(gfp & __GFP_IO)) + return; + + if (!__has_usable_swap()) + return; + + if (!blk_cgroup_congested()) + return; + + /* + * We've already scheduled a throttle, avoid taking the global swap + * lock. + */ + if (current->throttle_disk) + return; + + spin_lock(&swap_avail_lock); + plist_for_each_entry(si, &swap_avail_head, avail_list) { + if (si->bdev) { + blkcg_schedule_throttle(si->bdev->bd_disk, true); + break; + } + } + spin_unlock(&swap_avail_lock); +} +#endif + +static int __init swapfile_init(void) +{ + swapfile_maximum_size = arch_max_swapfile_size(); + + /* + * Once a cluster is freed, it's swap table content is read + * only, and all swap cache readers (swap_cache_*) verifies + * the content before use. So it's safe to use RCU slab here. + */ + if (!SWP_TABLE_USE_PAGE) + swap_table_cachep = kmem_cache_create("swap_table", + sizeof(struct swap_table), + 0, SLAB_PANIC | SLAB_TYPESAFE_BY_RCU, NULL); + +#ifdef CONFIG_MIGRATION + if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) + swap_migration_ad_supported = true; +#endif /* CONFIG_MIGRATION */ + + return 0; +} +subsys_initcall(swapfile_init); |