diff options
Diffstat (limited to 'mm/swapfile.c')
-rw-r--r-- | mm/swapfile.c | 1214 |
1 files changed, 552 insertions, 662 deletions
diff --git a/mm/swapfile.c b/mm/swapfile.c index b2a2e45c9a36..5fc1237a9f21 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -6,6 +6,7 @@ * 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> @@ -18,7 +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> @@ -39,18 +40,18 @@ #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> +#include <linux/completion.h> -#include <asm/pgtable.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.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 DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* @@ -62,6 +63,10 @@ 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 = -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 "; @@ -72,14 +77,14 @@ static const char Unused_offset[] = "Unused swap offset entry "; * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ -PLIST_HEAD(swap_active_head); +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 get_swap_page() instead of swap_active_head + * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, - * but get_swap_page() doesn't need to look at full ones. + * 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 @@ -101,11 +106,10 @@ atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { - if (type >= READ_ONCE(nr_swapfiles)) + if (type >= MAX_SWAPFILES) return NULL; - smp_rmb(); /* Pairs with smp_wmb in alloc_swap_info. */ - return READ_ONCE(swap_info[type]); + return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) @@ -128,27 +132,27 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); - struct page *page; + struct folio *folio; int ret = 0; - page = find_get_page(swap_address_space(entry), offset); - if (!page) + folio = filemap_get_folio(swap_address_space(entry), offset); + if (!folio) return 0; /* * When this function is called from scan_swap_map_slots() and it's - * called by vmscan.c at reclaiming pages. So, we hold a lock on a page, + * called by vmscan.c at reclaiming folios. So we hold a folio lock * 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() + * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ - if (trylock_page(page)) { + if (folio_trylock(folio)) { if ((flags & TTRS_ANYWAY) || - ((flags & TTRS_UNMAPPED) && !page_mapped(page)) || - ((flags & TTRS_FULL) && mem_cgroup_swap_full(page))) - ret = try_to_free_swap(page); - unlock_page(page); + ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || + ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))) + ret = folio_free_swap(folio); + folio_unlock(folio); } - put_page(page); + folio_put(folio); return ret; } @@ -181,7 +185,7 @@ static int discard_swap(struct swap_info_struct *si) 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(); @@ -192,7 +196,7 @@ static int discard_swap(struct swap_info_struct *si) 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; @@ -221,6 +225,19 @@ offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) BUG(); } +sector_t swap_page_sector(struct page *page) +{ + struct swap_info_struct *sis = page_swap_info(page); + struct swap_extent *se; + sector_t sector; + pgoff_t offset; + + offset = __page_file_index(page); + 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. @@ -243,7 +260,7 @@ static void discard_swap_cluster(struct swap_info_struct *si, start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_NOIO, 0)) + nr_blocks, GFP_NOIO)) break; se = next_se(se); @@ -441,10 +458,10 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* - * If scan_swap_map() can't find a free cluster, it will check + * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't - * taken by scan_swap_map(), mark the swap entries bad (occupied). It - * will be cleared after discard + * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). + * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); @@ -500,6 +517,14 @@ static void swap_discard_work(struct work_struct *work) spin_unlock(&si->lock); } +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); +} + static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; @@ -569,7 +594,7 @@ static void dec_cluster_info_page(struct swap_info_struct *p, } /* - * It's possible scan_swap_map() uses a free cluster in the middle of free + * It's possible scan_swap_map_slots() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ static bool @@ -601,7 +626,6 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, { struct percpu_cluster *cluster; struct swap_cluster_info *ci; - bool found_free; unsigned long tmp, max; new_cluster: @@ -614,17 +638,17 @@ new_cluster: } else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in - * discarding, do discard now and reclaim them + * discarding, do discard now and reclaim them, then + * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); - *scan_base = *offset = si->cluster_next; + *scan_base = this_cpu_read(*si->cluster_next_cpu); + *offset = *scan_base; goto new_cluster; } else return false; } - found_free = false; - /* * Other CPUs can use our cluster if they can't find a free cluster, * check if there is still free entry in the cluster @@ -632,27 +656,23 @@ new_cluster: tmp = cluster->next; max = min_t(unsigned long, si->max, (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); - if (tmp >= max) { - cluster_set_null(&cluster->index); - goto new_cluster; - } - ci = lock_cluster(si, tmp); - while (tmp < max) { - if (!si->swap_map[tmp]) { - found_free = true; - break; + if (tmp < max) { + ci = lock_cluster(si, tmp); + while (tmp < max) { + if (!si->swap_map[tmp]) + break; + tmp++; } - tmp++; + unlock_cluster(ci); } - unlock_cluster(ci); - if (!found_free) { + if (tmp >= max) { cluster_set_null(&cluster->index); goto new_cluster; } cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; - return found_free; + return true; } static void __del_from_avail_list(struct swap_info_struct *p) @@ -678,8 +698,8 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) - si->highest_bit -= nr_entries; - si->inuse_pages += nr_entries; + WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); + WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries); if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; @@ -702,6 +722,7 @@ static void add_to_avail_list(struct swap_info_struct *p) 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); @@ -710,23 +731,69 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset, if (end > si->highest_bit) { bool was_full = !si->highest_bit; - si->highest_bit = end; + WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } atomic_long_add(nr_entries, &nr_swap_pages); - si->inuse_pages -= nr_entries; + WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); 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); frontswap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } + clear_shadow_from_swap_cache(si->type, begin, end); +} + +static void set_cluster_next(struct swap_info_struct *si, unsigned long next) +{ + unsigned long prev; + + if (!(si->flags & SWP_SOLIDSTATE)) { + si->cluster_next = next; + return; + } + + prev = this_cpu_read(*si->cluster_next_cpu); + /* + * Cross the swap address space size aligned trunk, choose + * another trunk randomly to avoid lock contention on swap + * address space if possible. + */ + if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != + (next >> SWAP_ADDRESS_SPACE_SHIFT)) { + /* No free swap slots available */ + if (si->highest_bit <= si->lowest_bit) + return; + next = si->lowest_bit + + prandom_u32_max(si->highest_bit - si->lowest_bit + 1); + next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); + next = max_t(unsigned int, next, si->lowest_bit); + } + this_cpu_write(*si->cluster_next_cpu, next); +} + +static bool swap_offset_available_and_locked(struct swap_info_struct *si, + unsigned long offset) +{ + if (data_race(!si->swap_map[offset])) { + spin_lock(&si->lock); + return true; + } + + if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { + spin_lock(&si->lock); + return true; + } + + return false; } static int scan_swap_map_slots(struct swap_info_struct *si, @@ -739,9 +806,7 @@ static int scan_swap_map_slots(struct swap_info_struct *si, unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; int n_ret = 0; - - if (nr > SWAP_BATCH) - nr = SWAP_BATCH; + bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially @@ -755,17 +820,22 @@ static int scan_swap_map_slots(struct swap_info_struct *si, */ si->flags += SWP_SCANNING; - scan_base = offset = si->cluster_next; + /* + * Use percpu scan base for SSD to reduce lock contention on + * cluster and swap cache. For HDD, sequential access is more + * important. + */ + if (si->flags & SWP_SOLIDSTATE) + scan_base = this_cpu_read(*si->cluster_next_cpu); + else + scan_base = si->cluster_next; + offset = scan_base; /* SSD algorithm */ if (si->cluster_info) { - if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) - goto checks; - else + if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; - } - - if (unlikely(!si->cluster_nr--)) { + } else if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; @@ -843,12 +913,11 @@ checks: else goto done; } - si->swap_map[offset] = usage; + WRITE_ONCE(si->swap_map[offset], usage); inc_cluster_info_page(si, si->cluster_info, offset); unlock_cluster(ci); swap_range_alloc(si, offset, 1); - si->cluster_next = offset + 1; slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ @@ -871,51 +940,55 @@ checks: if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto checks; - else - goto done; - } - /* non-ssd case */ - ++offset; - - /* non-ssd case, still more slots in cluster? */ - if (si->cluster_nr && !si->swap_map[offset]) { + } else if (si->cluster_nr && !si->swap_map[++offset]) { + /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; goto checks; } + /* + * Even if there's no free clusters available (fragmented), + * try to scan a little more quickly with lock held unless we + * have scanned too many slots already. + */ + if (!scanned_many) { + unsigned long scan_limit; + + if (offset < scan_base) + scan_limit = scan_base; + else + scan_limit = si->highest_bit; + for (; offset <= scan_limit && --latency_ration > 0; + offset++) { + if (!si->swap_map[offset]) + goto checks; + } + } + done: + set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: spin_unlock(&si->lock); - while (++offset <= si->highest_bit) { - if (!si->swap_map[offset]) { - spin_lock(&si->lock); + while (++offset <= READ_ONCE(si->highest_bit)) { + if (swap_offset_available_and_locked(si, offset)) 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; + scanned_many = true; } } 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); + if (swap_offset_available_and_locked(si, offset)) goto checks; - } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; + scanned_many = true; } offset++; } @@ -930,8 +1003,7 @@ static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) { unsigned long idx; struct swap_cluster_info *ci; - unsigned long offset, i; - unsigned char *map; + unsigned long offset; /* * Should not even be attempting cluster allocations when huge @@ -951,9 +1023,7 @@ static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) alloc_cluster(si, idx); cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE); - map = si->swap_map + offset; - for (i = 0; i < SWAPFILE_CLUSTER; i++) - map[i] = SWAP_HAS_CACHE; + memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER); unlock_cluster(ci); swap_range_alloc(si, offset, SWAPFILE_CLUSTER); *slot = swp_entry(si->type, offset); @@ -974,21 +1044,6 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) swap_range_free(si, offset, SWAPFILE_CLUSTER); } -static unsigned long scan_swap_map(struct swap_info_struct *si, - unsigned char usage) -{ - swp_entry_t entry; - int n_ret; - - n_ret = scan_swap_map_slots(si, usage, 1, &entry); - - if (n_ret) - return swp_offset(entry); - else - return 0; - -} - int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) { unsigned long size = swap_entry_size(entry_size); @@ -1000,20 +1055,18 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER); + spin_lock(&swap_avail_lock); + avail_pgs = atomic_long_read(&nr_swap_pages) / size; - if (avail_pgs <= 0) + if (avail_pgs <= 0) { + spin_unlock(&swap_avail_lock); goto noswap; + } - if (n_goal > SWAP_BATCH) - n_goal = SWAP_BATCH; - - if (n_goal > avail_pgs) - n_goal = avail_pgs; + n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); - spin_lock(&swap_avail_lock); - start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { @@ -1038,7 +1091,7 @@ start_over: goto nextsi; } if (size == SWAPFILE_CLUSTER) { - if (!(si->flags & SWP_FS)) + if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, @@ -1053,14 +1106,14 @@ start_over: nextsi: /* * if we got here, it's likely that si was almost full before, - * and since scan_swap_map() can drop the si->lock, 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 and taking si->lock. - * Since we dropped the swap_avail_lock, the swap_avail_head - * 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. + * and since scan_swap_map_slots() can drop the si->lock, + * 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 and taking + * si->lock. Since we dropped the swap_avail_lock, the + * swap_avail_head 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_lists[node])) goto start_over; @@ -1076,32 +1129,7 @@ noswap: return n_ret; } -/* The only caller of this function is now suspend routine */ -swp_entry_t get_swap_page_of_type(int type) -{ - struct swap_info_struct *si = swap_type_to_swap_info(type); - pgoff_t offset; - - if (!si) - goto fail; - - spin_lock(&si->lock); - if (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); - } - atomic_long_inc(&nr_swap_pages); - } - spin_unlock(&si->lock); -fail: - return (swp_entry_t) {0}; -} - -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; @@ -1111,53 +1139,30 @@ static struct swap_info_struct *__swap_info_get(swp_entry_t entry) p = swp_swap_info(entry); if (!p) goto bad_nofile; - if (!(p->flags & SWP_USED)) + if (data_race(!(p->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; + if (data_race(!p->swap_map[swp_offset(entry)])) + goto bad_free; return p; +bad_free: + pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); + goto out; bad_offset: - pr_err("swap_info_get: %s%08lx\n", Bad_offset, entry.val); + pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: - pr_err("swap_info_get: %s%08lx\n", Unused_file, entry.val); + pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: - pr_err("swap_info_get: %s%08lx\n", Bad_file, entry.val); -out: - return NULL; -} - -static struct swap_info_struct *_swap_info_get(swp_entry_t entry) -{ - struct swap_info_struct *p; - - p = __swap_info_get(entry); - if (!p) - goto out; - if (!p->swap_map[swp_offset(entry)]) - goto bad_free; - return p; - -bad_free: - pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val); - goto out; + pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } -static struct swap_info_struct *swap_info_get(swp_entry_t entry) -{ - struct swap_info_struct *p; - - p = _swap_info_get(entry); - if (p) - spin_lock(&p->lock); - return p; -} - static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { @@ -1206,7 +1211,10 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, } usage = count | has_cache; - p->swap_map[offset] = usage ? : SWAP_HAS_CACHE; + if (usage) + WRITE_ONCE(p->swap_map[offset], usage); + else + WRITE_ONCE(p->swap_map[offset], SWAP_HAS_CACHE); return usage; } @@ -1217,18 +1225,12 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * - * The entirety of the RCU read critical section must come before the - * return from or after the call to synchronize_rcu() in - * enable_swap_info() or swapoff(). So if "si->flags & SWP_VALID" is - * true, the si->map, si->cluster_info, etc. must be valid in the - * critical section. - * * Notice that swapoff or swapoff+swapon can still happen before the - * rcu_read_lock() in get_swap_device() or after the rcu_read_unlock() - * in put_swap_device() if there isn't any other way to prevent - * swapoff, such as page lock, page table lock, etc. The caller must - * be prepared for that. For example, the following situation is - * possible. + * 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, such as page lock, page table lock, etc. The + * caller must be prepared for that. For example, the following + * situation is possible. * * CPU1 CPU2 * do_swap_page() @@ -1256,32 +1258,40 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry) si = swp_swap_info(entry); if (!si) goto bad_nofile; - - rcu_read_lock(); - if (!(si->flags & SWP_VALID)) - goto unlock_out; + if (!percpu_ref_tryget_live(&si->users)) + goto out; + /* + * Guarantee the si->users are checked before accessing other + * fields of swap_info_struct. + * + * Paired with the spin_unlock() after setup_swap_info() in + * enable_swap_info(). + */ + smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) - goto unlock_out; + goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; -unlock_out: - rcu_read_unlock(); +put_out: + pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); + percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *p, - swp_entry_t entry, unsigned char usage) + swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); + unsigned char usage; ci = lock_cluster_or_swap_info(p, offset); - usage = __swap_entry_free_locked(p, offset, usage); + usage = __swap_entry_free_locked(p, offset, 1); unlock_cluster_or_swap_info(p, ci); if (!usage) free_swap_slot(entry); @@ -1316,13 +1326,13 @@ void swap_free(swp_entry_t entry) p = _swap_info_get(entry); if (p) - __swap_entry_free(p, entry, 1); + __swap_entry_free(p, entry); } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ -void put_swap_page(struct page *page, swp_entry_t entry) +void put_swap_folio(struct folio *folio, swp_entry_t entry) { unsigned long offset = swp_offset(entry); unsigned long idx = offset / SWAPFILE_CLUSTER; @@ -1331,7 +1341,7 @@ void put_swap_page(struct page *page, swp_entry_t entry) unsigned char *map; unsigned int i, free_entries = 0; unsigned char val; - int size = swap_entry_size(hpage_nr_pages(page)); + int size = swap_entry_size(folio_nr_pages(folio)); si = _swap_info_get(entry); if (!si) @@ -1421,30 +1431,6 @@ void swapcache_free_entries(swp_entry_t *entries, int n) spin_unlock(&p->lock); } -/* - * How many references to page 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) -{ - int count = 0; - struct swap_info_struct *p; - struct swap_cluster_info *ci; - swp_entry_t entry; - unsigned long offset; - - entry.val = page_private(page); - p = _swap_info_get(entry); - if (p) { - offset = swp_offset(entry); - ci = lock_cluster_or_swap_info(p, offset); - count = swap_count(p->swap_map[offset]); - unlock_cluster_or_swap_info(p, ci); - } - return count; -} - int __swap_count(swp_entry_t entry) { struct swap_info_struct *si; @@ -1459,11 +1445,16 @@ int __swap_count(swp_entry_t entry) return count; } +/* + * 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. + */ static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { - int count = 0; pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; + int count; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); @@ -1562,167 +1553,61 @@ unlock_out: return ret; } -static bool page_swapped(struct page *page) +static bool folio_swapped(struct folio *folio) { - swp_entry_t entry; - struct swap_info_struct *si; - - if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) - return page_swapcount(page) != 0; - - page = compound_head(page); - entry.val = page_private(page); - si = _swap_info_get(entry); - if (si) - return swap_page_trans_huge_swapped(si, entry); - return false; -} - -static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount, - int *total_swapcount) -{ - int i, map_swapcount, _total_mapcount, _total_swapcount; - unsigned long offset = 0; - struct swap_info_struct *si; - struct swap_cluster_info *ci = NULL; - unsigned char *map = NULL; - int mapcount, swapcount = 0; + swp_entry_t entry = folio_swap_entry(folio); + struct swap_info_struct *si = _swap_info_get(entry); - /* hugetlbfs shouldn't call it */ - VM_BUG_ON_PAGE(PageHuge(page), page); - - if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) { - mapcount = page_trans_huge_mapcount(page, total_mapcount); - if (PageSwapCache(page)) - swapcount = page_swapcount(page); - if (total_swapcount) - *total_swapcount = swapcount; - return mapcount + swapcount; - } - - page = compound_head(page); - - _total_mapcount = _total_swapcount = map_swapcount = 0; - if (PageSwapCache(page)) { - swp_entry_t entry; + if (!si) + return false; - entry.val = page_private(page); - si = _swap_info_get(entry); - if (si) { - map = si->swap_map; - offset = swp_offset(entry); - } - } - if (map) - ci = lock_cluster(si, offset); - for (i = 0; i < HPAGE_PMD_NR; i++) { - mapcount = atomic_read(&page[i]._mapcount) + 1; - _total_mapcount += mapcount; - if (map) { - swapcount = swap_count(map[offset + i]); - _total_swapcount += swapcount; - } - map_swapcount = max(map_swapcount, mapcount + swapcount); - } - unlock_cluster(ci); - if (PageDoubleMap(page)) { - map_swapcount -= 1; - _total_mapcount -= HPAGE_PMD_NR; - } - mapcount = compound_mapcount(page); - map_swapcount += mapcount; - _total_mapcount += mapcount; - if (total_mapcount) - *total_mapcount = _total_mapcount; - if (total_swapcount) - *total_swapcount = _total_swapcount; + if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) + return swap_swapcount(si, entry) != 0; - return map_swapcount; + return swap_page_trans_huge_swapped(si, entry); } -/* - * 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. +/** + * 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. * - * NOTE: total_map_swapcount should not be relied upon by the caller if - * reuse_swap_page() returns false, but it may be always overwritten - * (see the other implementation for CONFIG_SWAP=n). + * Return: true if we were able to release the swap space. */ -bool reuse_swap_page(struct page *page, int *total_map_swapcount) +bool folio_free_swap(struct folio *folio) { - int count, total_mapcount, total_swapcount; + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - VM_BUG_ON_PAGE(!PageLocked(page), page); - if (unlikely(PageKsm(page))) + if (!folio_test_swapcache(folio)) + return false; + if (folio_test_writeback(folio)) + return false; + if (folio_swapped(folio)) return false; - count = page_trans_huge_map_swapcount(page, &total_mapcount, - &total_swapcount); - if (total_map_swapcount) - *total_map_swapcount = total_mapcount + total_swapcount; - if (count == 1 && PageSwapCache(page) && - (likely(!PageTransCompound(page)) || - /* The remaining swap count will be freed soon */ - total_swapcount == page_swapcount(page))) { - if (!PageWriteback(page)) { - page = compound_head(page); - delete_from_swap_cache(page); - SetPageDirty(page); - } else { - swp_entry_t entry; - struct swap_info_struct *p; - - entry.val = page_private(page); - p = swap_info_get(entry); - if (p->flags & SWP_STABLE_WRITES) { - spin_unlock(&p->lock); - return false; - } - spin_unlock(&p->lock); - } - } - - return count <= 1; -} - -/* - * 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) -{ - VM_BUG_ON_PAGE(!PageLocked(page), page); - - if (!PageSwapCache(page)) - return 0; - if (PageWriteback(page)) - return 0; - if (page_swapped(page)) - return 0; /* * 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. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) - return 0; + return false; - page = compound_head(page); - delete_from_swap_cache(page); - SetPageDirty(page); - return 1; + delete_from_swap_cache(folio); + folio_set_dirty(folio); + return true; } /* @@ -1739,7 +1624,7 @@ int free_swap_and_cache(swp_entry_t entry) p = _swap_info_get(entry); if (p) { - count = __swap_entry_free(p, entry, 1); + count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), @@ -1749,6 +1634,24 @@ int free_swap_and_cache(swp_entry_t entry) } #ifdef CONFIG_HIBERNATION + +swp_entry_t get_swap_page_of_type(int type) +{ + struct swap_info_struct *si = swap_type_to_swap_info(type); + swp_entry_t entry = {0}; + + if (!si) + goto fail; + + /* This is called for allocating swap entry, not cache */ + spin_lock(&si->lock); + if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry)) + atomic_long_dec(&nr_swap_pages); + spin_unlock(&si->lock); +fail: + return entry; +} + /* * Find the swap type that corresponds to given device (if any). * @@ -1757,13 +1660,12 @@ 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++) { @@ -1772,30 +1674,34 @@ 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) { + 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; } @@ -1805,12 +1711,13 @@ 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_swap_info(type); + struct swap_extent *se; 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); } /* @@ -1842,7 +1749,7 @@ unsigned int count_swap_pages(int type, int free) static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { - return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte); + return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* @@ -1851,12 +1758,12 @@ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) * 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 *page = folio_file_page(folio, swp_offset(entry)); struct page *swapcache; - struct mem_cgroup *memcg; spinlock_t *ptl; - pte_t *pte; + pte_t *pte, new_pte; int ret = 1; swapcache = page; @@ -1864,41 +1771,56 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (unlikely(!page)) return -ENOMEM; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, - &memcg, false)) { - ret = -ENOMEM; - goto out_nolock; - } - pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { - mem_cgroup_cancel_charge(page, memcg, false); ret = 0; goto out; } + if (unlikely(!PageUptodate(page))) { + pte_t pteval; + + dec_mm_counter(vma->vm_mm, MM_SWAPENTS); + pteval = swp_entry_to_pte(make_swapin_error_entry(page)); + set_pte_at(vma->vm_mm, addr, pte, pteval); + swap_free(entry); + ret = 0; + goto out; + } + + /* See do_swap_page() */ + BUG_ON(!PageAnon(page) && PageMappedToDisk(page)); + BUG_ON(PageAnon(page) && PageAnonExclusive(page)); + 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, false); - mem_cgroup_commit_charge(page, memcg, true, false); + rmap_t rmap_flags = RMAP_NONE; + + /* + * See do_swap_page(): PageWriteback() would be problematic. + * However, we do a wait_on_page_writeback() just before this + * call and have the page locked. + */ + VM_BUG_ON_PAGE(PageWriteback(page), page); + if (pte_swp_exclusive(*pte)) + rmap_flags |= RMAP_EXCLUSIVE; + + page_add_anon_rmap(page, vma, addr, rmap_flags); } else { /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); - lru_cache_add_active_or_unevictable(page, vma); - } + page_add_new_anon_rmap(page, vma, addr); + lru_cache_add_inactive_or_unevictable(page, vma); + } + new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); + if (pte_swp_soft_dirty(*pte)) + new_pte = pte_mksoft_dirty(new_pte); + if (pte_swp_uffd_wp(*pte)) + new_pte = pte_mkuffd_wp(new_pte); + 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); @@ -1908,21 +1830,19 @@ out_nolock: static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { - struct page *page; swp_entry_t entry; pte_t *pte; struct swap_info_struct *si; - unsigned long offset; int ret = 0; volatile unsigned char *swap_map; si = swap_info[type]; pte = pte_offset_map(pmd, addr); do { - struct vm_fault vmf; + struct folio *folio; + unsigned long offset; if (!is_swap_pte(*pte)) continue; @@ -1932,38 +1852,41 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, continue; offset = swp_offset(entry); - if (frontswap && !frontswap_test(si, offset)) - continue; - pte_unmap(pte); swap_map = &si->swap_map[offset]; - vmf.vma = vma; - vmf.address = addr; - vmf.pmd = pmd; - page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); - if (!page) { + folio = swap_cache_get_folio(entry, vma, addr); + if (!folio) { + struct page *page; + struct vm_fault vmf = { + .vma = vma, + .address = addr, + .real_address = addr, + .pmd = pmd, + }; + + page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, + &vmf); + if (page) + folio = page_folio(page); + } + if (!folio) { if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD) goto try_next; return -ENOMEM; } - lock_page(page); - wait_on_page_writeback(page); - ret = unuse_pte(vma, pmd, addr, entry, page); + folio_lock(folio); + folio_wait_writeback(folio); + ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); goto out; } - try_to_free_swap(page); - unlock_page(page); - put_page(page); - - if (*fs_pages_to_unuse && !--(*fs_pages_to_unuse)) { - ret = FRONTSWAP_PAGES_UNUSED; - goto out; - } + folio_free_swap(folio); + folio_unlock(folio); + folio_put(folio); try_next: pte = pte_offset_map(pmd, addr); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -1976,8 +1899,7 @@ out: static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { pmd_t *pmd; unsigned long next; @@ -1989,8 +1911,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, 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, type, - frontswap, fs_pages_to_unuse); + ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); @@ -1999,8 +1920,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { pud_t *pud; unsigned long next; @@ -2011,8 +1931,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - ret = unuse_pmd_range(vma, pud, addr, next, type, - frontswap, fs_pages_to_unuse); + ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); @@ -2021,8 +1940,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { p4d_t *p4d; unsigned long next; @@ -2033,16 +1951,14 @@ static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; - ret = unuse_pud_range(vma, p4d, addr, next, type, - frontswap, fs_pages_to_unuse); + 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, - bool frontswap, unsigned long *fs_pages_to_unuse) +static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; @@ -2056,41 +1972,40 @@ static int unuse_vma(struct vm_area_struct *vma, unsigned int type, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - ret = unuse_p4d_range(vma, pgd, addr, next, type, - frontswap, fs_pages_to_unuse); + 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, unsigned int type, - bool frontswap, unsigned long *fs_pages_to_unuse) +static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; + VMA_ITERATOR(vmi, mm, 0); - down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) { + mmap_read_lock(mm); + for_each_vma(vmi, vma) { if (vma->anon_vma) { - ret = unuse_vma(vma, type, frontswap, - fs_pages_to_unuse); + ret = unuse_vma(vma, type); if (ret) break; } + cond_resched(); } - up_read(&mm->mmap_sem); + 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. Return 0 - * if there are no inuse entries after prev till end of the map. + * 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 i; unsigned char count; @@ -2104,8 +2019,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) - if (!frontswap || frontswap_test(si, i)) - break; + break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } @@ -2116,39 +2030,31 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, return i; } -/* - * 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 page *page; + struct folio *folio; swp_entry_t entry; unsigned int i; - if (!si->inuse_pages) + if (!READ_ONCE(si->inuse_pages)) return 0; - if (!frontswap) - pages_to_unuse = 0; - retry: - retval = shmem_unuse(type, frontswap, &pages_to_unuse); + retval = shmem_unuse(type); if (retval) - goto out; + return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; - while (si->inuse_pages && + while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { @@ -2158,11 +2064,10 @@ retry: spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; - retval = unuse_mm(mm, type, frontswap, &pages_to_unuse); - + retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); - goto out; + return retval; } /* @@ -2177,34 +2082,26 @@ retry: mmput(prev_mm); i = 0; - while (si->inuse_pages && + while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && - (i = find_next_to_unuse(si, i, frontswap)) != 0) { + (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); - page = find_get_page(swap_address_space(entry), i); - if (!page) + folio = filemap_get_folio(swap_address_space(entry), i); + if (!folio) continue; /* - * It is conceivable that a racing task removed this page from - * swap cache just before we acquired the page lock. The page + * 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, try_to_free_swap() only removes stale pages. - */ - lock_page(page); - wait_on_page_writeback(page); - try_to_free_swap(page); - unlock_page(page); - put_page(page); - - /* - * For frontswap, we just need to unuse pages_to_unuse, if - * it was specified. Need not check frontswap again here as - * we already zeroed out pages_to_unuse if not frontswap. + * that is okay, folio_free_swap() only removes stale folios. */ - if (pages_to_unuse && --pages_to_unuse == 0) - goto out; + folio_lock(folio); + folio_wait_writeback(folio); + folio_free_swap(folio); + folio_unlock(folio); + folio_put(folio); } /* @@ -2213,19 +2110,20 @@ retry: * 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_writepage() could have - * been preempted after get_swap_page(), temporarily hiding that swap. - * It's easy and robust (though cpu-intensive) just to keep retrying. + * 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_writepage() 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 (si->inuse_pages) { + if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; - retval = -EINTR; + return -EINTR; } -out: - return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; + + return 0; } /* @@ -2249,36 +2147,6 @@ 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 *se; - pgoff_t offset; - - sis = swp_swap_info(entry); - *bdev = sis->bdev; - - offset = swp_offset(entry); - se = offset_to_swap_extent(sis, offset); - return se->start_block + (offset - se->start_page); -} - -/* - * 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) @@ -2350,8 +2218,8 @@ 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_readpage * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. @@ -2359,12 +2227,12 @@ EXPORT_SYMBOL_GPL(add_swap_extent); * 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. * @@ -2373,10 +2241,7 @@ EXPORT_SYMBOL_GPL(add_swap_extent); * * 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) { @@ -2393,12 +2258,13 @@ 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 >= 0) - sis->flags |= SWP_ACTIVATED; - if (!ret) { - sis->flags |= SWP_FS; - 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; } @@ -2449,7 +2315,7 @@ static void setup_swap_info(struct swap_info_struct *p, int prio, static void _enable_swap_info(struct swap_info_struct *p) { - p->flags |= SWP_WRITEOK | SWP_VALID; + p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; @@ -2460,7 +2326,7 @@ static void _enable_swap_info(struct swap_info_struct *p) * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. - * swap_avail_head needs to be priority ordered for get_swap_page(), + * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ @@ -2473,17 +2339,17 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { - frontswap_init(p->type, frontswap_map); + if (IS_ENABLED(CONFIG_FRONTSWAP)) + frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); /* - * Guarantee swap_map, cluster_info, etc. fields are valid - * between get/put_swap_device() if SWP_VALID bit is set + * Finished initializing swap device, now it's safe to reference it. */ - synchronize_rcu(); + percpu_ref_resurrect(&p->users); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p); @@ -2587,7 +2453,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) disable_swap_slots_cache_lock(); set_current_oom_origin(); - err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ + err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { @@ -2599,16 +2465,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) reenable_swap_slots_cache_unlock(); - spin_lock(&swap_lock); - spin_lock(&p->lock); - p->flags &= ~SWP_VALID; /* mark swap device as invalid */ - spin_unlock(&p->lock); - spin_unlock(&swap_lock); /* - * wait for swap operations protected by get/put_swap_device() - * to complete + * Wait for swap operations protected by get/put_swap_device() + * to complete. + * + * We need synchronize_rcu() here to protect the accessing to + * the swap cache data structure. */ + percpu_ref_kill(&p->users); synchronize_rcu(); + wait_for_completion(&p->comp); flush_work(&p->discard_work); @@ -2616,7 +2482,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); - if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev))) + if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); @@ -2624,7 +2490,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_lock(&p->lock); drain_mmlist(); - /* wait for anyone still in scan_swap_map */ + /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); @@ -2645,11 +2511,14 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); + arch_swap_invalidate_area(p->type); frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; + free_percpu(p->cluster_next_cpu); + p->cluster_next_cpu = NULL; vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); @@ -2757,20 +2626,24 @@ 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 = si->pages << (PAGE_SHIFT - 10); + inuse = READ_ONCE(si->inuse_pages) << (PAGE_SHIFT - 10); + file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); - seq_printf(swap, "%*s%s\t%u\t%u\t%d\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; } @@ -2797,6 +2670,7 @@ static int swaps_open(struct inode *inode, struct file *file) } 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, @@ -2824,6 +2698,7 @@ 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; int i; @@ -2831,6 +2706,12 @@ static struct swap_info_struct *alloc_swap_info(void) 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)) @@ -2838,21 +2719,20 @@ static struct swap_info_struct *alloc_swap_info(void) } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); + percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; - WRITE_ONCE(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(); - WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1); + smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ + nr_swapfiles++; } else { - kvfree(p); + defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() @@ -2865,8 +2745,13 @@ static struct swap_info_struct *alloc_swap_info(void) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); + if (defer) { + percpu_ref_exit(&defer->users); + kvfree(defer); + } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); + init_completion(&p->comp); return p; } @@ -2876,10 +2761,10 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) int error; if (S_ISBLK(inode->i_mode)) { - p->bdev = bdgrab(I_BDEV(inode)); - error = blkdev_get(p->bdev, + p->bdev = blkdev_get_by_dev(inode->i_rdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); - if (error < 0) { + if (IS_ERR(p->bdev)) { + error = PTR_ERR(p->bdev); p->bdev = NULL; return error; } @@ -2892,17 +2777,13 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ - if (blk_queue_is_zoned(p->bdev->bd_queue)) + if (bdev_is_zoned(p->bdev)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; } - inode_lock(inode); - if (IS_SWAPFILE(inode)) - return -EBUSY; - return 0; } @@ -2930,7 +2811,7 @@ unsigned long generic_max_swapfile_size(void) } /* Can be overridden by an architecture for additional checks. */ -__weak unsigned long max_swapfile_size(void) +__weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } @@ -2949,7 +2830,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, 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); @@ -2970,7 +2851,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, p->cluster_next = 1; p->cluster_nr = 0; - maxpages = max_swapfile_size(); + maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); @@ -3092,26 +2973,13 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, return nr_extents; } -/* - * Helper to sys_swapon determining if a given swap - * backing device queue supports DISCARD operations. - */ -static bool swap_discardable(struct swap_info_struct *si) -{ - struct request_queue *q = bdev_get_queue(si->bdev); - - if (!q || !blk_queue_discard(q)) - return false; - - return true; -} - SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; + struct dentry *dentry; int prio; int error; union swap_header *swap_header; @@ -3155,63 +3023,81 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) p->swap_file = swap_file; mapping = swap_file->f_mapping; + dentry = swap_file->f_path.dentry; inode = mapping->host; - /* will take i_rwsem; */ error = claim_swapfile(p, inode); if (unlikely(error)) 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; + } + /* * 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; + goto bad_swap_unlock_inode; } swap_header = kmap(page); maxpages = read_swap_header(p, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; - goto bad_swap; + goto bad_swap_unlock_inode; } /* 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; } - if (bdi_cap_stable_pages_required(inode_to_bdi(inode))) + if (p->bdev && bdev_stable_writes(p->bdev)) p->flags |= SWP_STABLE_WRITES; - if (bdi_cap_synchronous_io(inode_to_bdi(inode))) + if (p->bdev && p->bdev->bd_disk->fops->rw_page) p->flags |= SWP_SYNCHRONOUS_IO; - if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { + if (p->bdev && bdev_nonrot(p->bdev)) { int cpu; unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; + p->cluster_next_cpu = alloc_percpu(unsigned int); + if (!p->cluster_next_cpu) { + error = -ENOMEM; + goto bad_swap_unlock_inode; + } /* * select a random position to start with to help wear leveling * SSD */ - p->cluster_next = 1 + (prandom_u32() % p->highest_bit); + for_each_possible_cpu(cpu) { + per_cpu(*p->cluster_next_cpu, cpu) = + 1 + prandom_u32_max(p->highest_bit); + } nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) { error = -ENOMEM; - goto bad_swap; + goto bad_swap_unlock_inode; } for (ci = 0; ci < nr_cluster; ci++) @@ -3220,7 +3106,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) p->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!p->percpu_cluster) { error = -ENOMEM; - goto bad_swap; + goto bad_swap_unlock_inode; } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; @@ -3234,13 +3120,13 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = swap_cgroup_swapon(p->type, maxpages); if (error) - goto bad_swap; + goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; - goto bad_swap; + goto bad_swap_unlock_inode; } /* frontswap enabled? set up bit-per-page map for frontswap */ if (IS_ENABLED(CONFIG_FRONTSWAP)) @@ -3248,7 +3134,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sizeof(long), GFP_KERNEL); - if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { + if ((swap_flags & SWAP_FLAG_DISCARD) && + p->bdev && bdev_max_discard_sectors(p->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in @@ -3280,7 +3167,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = init_swap_address_space(p->type, maxpages); if (error) - goto bad_swap; + goto bad_swap_unlock_inode; /* * Flush any pending IO and dirty mappings before we start using this @@ -3290,7 +3177,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; - goto bad_swap; + goto free_swap_address_space; } mutex_lock(&swapon_mutex); @@ -3315,13 +3202,20 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = 0; goto out; +free_swap_address_space: + exit_swap_address_space(p->type); +bad_swap_unlock_inode: + inode_unlock(inode); bad_swap: free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; + free_percpu(p->cluster_next_cpu); + p->cluster_next_cpu = NULL; 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); } + inode = NULL; destroy_swap_extents(p); swap_cgroup_swapoff(p->type); spin_lock(&swap_lock); @@ -3333,13 +3227,8 @@ bad_swap: kvfree(frontswap_map); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); - if (swap_file) { - if (inode) { - inode_unlock(inode); - inode = NULL; - } + if (swap_file) filp_close(swap_file, NULL); - } out: if (page && !IS_ERR(page)) { kunmap(page); @@ -3364,7 +3253,7 @@ 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 += READ_ONCE(si->inuse_pages); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; @@ -3389,11 +3278,11 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) unsigned long offset; unsigned char count; unsigned char has_cache; - int err = -EINVAL; + int err; p = get_swap_device(entry); if (!p) - goto out; + return -EINVAL; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); @@ -3436,13 +3325,11 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) } else err = -ENOENT; /* unused swap entry */ - p->swap_map[offset] = count | has_cache; + WRITE_ONCE(p->swap_map[offset], count | has_cache); unlock_out: unlock_cluster_or_swap_info(p, ci); -out: - if (p) - put_swap_device(p); + put_swap_device(p); return err; } @@ -3476,7 +3363,7 @@ int swap_duplicate(swp_entry_t entry) * * Called when allocating swap cache for existing swap entry, * 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) @@ -3496,13 +3383,13 @@ struct swap_info_struct *page_swap_info(struct page *page) } /* - * out-of-line __page_file_ methods to avoid include hell. + * out-of-line methods to avoid include hell. */ -struct address_space *__page_file_mapping(struct page *page) +struct address_space *swapcache_mapping(struct folio *folio) { - return page_swap_info(page)->swap_file->f_mapping; + return page_swap_info(&folio->page)->swap_file->f_mapping; } -EXPORT_SYMBOL_GPL(__page_file_mapping); +EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __page_file_index(struct page *page) { @@ -3557,7 +3444,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) ci = lock_cluster(si, offset); - count = si->swap_map[offset] & ~SWAP_HAS_CACHE; + count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* @@ -3654,7 +3541,7 @@ static bool swap_count_continued(struct swap_info_struct *si, spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; - page = list_entry(head->lru.next, struct page, lru); + page = list_next_entry(head, lru); map = kmap_atomic(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ @@ -3666,13 +3553,13 @@ static bool swap_count_continued(struct swap_info_struct *si, */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_atomic(map); - page = list_entry(page->lru.next, struct page, lru); + page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_atomic(map); - page = list_entry(page->lru.next, struct page, lru); + page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; @@ -3682,12 +3569,10 @@ 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) { + while ((page = list_prev_entry(page, lru)) != head) { map = kmap_atomic(page) + offset; *map = COUNT_CONTINUED; kunmap_atomic(map); - page = list_entry(page->lru.prev, struct page, lru); } ret = true; /* incremented */ @@ -3698,7 +3583,7 @@ 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); + page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } @@ -3707,13 +3592,11 @@ init_map: *map = 0; /* we didn't zero the page */ if (*map == 0) count = 0; kunmap_atomic(map); - page = list_entry(page->lru.prev, struct page, lru); - while (page != head) { + while ((page = list_prev_entry(page, lru)) != head) { map = kmap_atomic(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_atomic(map); - page = list_entry(page->lru.prev, struct page, lru); } ret = count == COUNT_CONTINUED; } @@ -3745,11 +3628,12 @@ static void free_swap_count_continuations(struct swap_info_struct *si) } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, - gfp_t gfp_mask) +void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { struct swap_info_struct *si, *next; - if (!(gfp_mask & __GFP_IO) || !memcg) + int nid = page_to_nid(page); + + if (!(gfp_mask & __GFP_IO)) return; if (!blk_cgroup_congested()) @@ -3763,11 +3647,10 @@ void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, return; spin_lock(&swap_avail_lock); - plist_for_each_entry_safe(si, next, &swap_avail_heads[node], - avail_lists[node]) { + plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], + avail_lists[nid]) { if (si->bdev) { - blkcg_schedule_throttle(bdev_get_queue(si->bdev), - true); + blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } @@ -3789,6 +3672,13 @@ static int __init swapfile_init(void) for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); + swapfile_maximum_size = arch_max_swapfile_size(); + +#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); |