diff options
Diffstat (limited to 'mm/swapfile.c')
| -rw-r--r-- | mm/swapfile.c | 2625 |
1 files changed, 1860 insertions, 765 deletions
diff --git a/mm/swapfile.c b/mm/swapfile.c index 2da149cfc9a..4c524f7bd0b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -14,13 +14,14 @@ #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> -#include <linux/shm.h> +#include <linux/shmem_fs.h> #include <linux/blkdev.h> +#include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> @@ -28,69 +29,470 @@ #include <linux/capability.h> #include <linux/syscalls.h> #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 <asm/pgtable.h> #include <asm/tlbflush.h> #include <linux/swapops.h> +#include <linux/page_cgroup.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); -unsigned int nr_swapfiles; +static unsigned int nr_swapfiles; +atomic_long_t nr_swap_pages; +/* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; -static int swap_overflow; +static int least_priority; 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. + */ +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 + * because swap_active_head includes all swap_info_structs, + * but get_swap_page() 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); -static struct swap_info_struct swap_info[MAX_SWAPFILES]; +struct swap_info_struct *swap_info[MAX_SWAPFILES]; 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); + +static inline unsigned char swap_count(unsigned char ent) +{ + return ent & ~SWAP_HAS_CACHE; /* may include SWAP_HAS_CONT flag */ +} + +/* returns 1 if swap entry is freed */ +static int +__try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) +{ + swp_entry_t entry = swp_entry(si->type, offset); + struct page *page; + int ret = 0; + + page = find_get_page(swap_address_space(entry), entry.val); + if (!page) + return 0; + /* + * 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. + */ + if (trylock_page(page)) { + ret = try_to_free_swap(page); + unlock_page(page); + } + page_cache_release(page); + return ret; +} + /* - * We need this because the bdev->unplug_fn can sleep and we cannot - * hold swap_lock while calling the unplug_fn. And swap_lock - * cannot be turned into a mutex. + * swapon tell device that all the old swap contents can be discarded, + * to allow the swap device to optimize its wear-levelling. */ -static DECLARE_RWSEM(swap_unplug_sem); +static int discard_swap(struct swap_info_struct *si) +{ + struct swap_extent *se; + sector_t start_block; + sector_t nr_blocks; + int err = 0; + + /* Do not discard the swap header page! */ + se = &si->first_swap_extent; + 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); + if (err) + return err; + cond_resched(); + } + + list_for_each_entry(se, &si->first_swap_extent.list, list) { + 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); + if (err) + break; -void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) + cond_resched(); + } + return err; /* That will often be -EOPNOTSUPP */ +} + +/* + * swap allocation tell device that a cluster of swap can now be discarded, + * to allow the swap device to optimize its wear-levelling. + */ +static void discard_swap_cluster(struct swap_info_struct *si, + pgoff_t start_page, pgoff_t nr_pages) { - swp_entry_t entry; + struct swap_extent *se = si->curr_swap_extent; + int found_extent = 0; - down_read(&swap_unplug_sem); - entry.val = page_private(page); - if (PageSwapCache(page)) { - struct block_device *bdev = swap_info[swp_type(entry)].bdev; - struct backing_dev_info *bdi; + while (nr_pages) { + struct list_head *lh; - /* - * If the page is removed from swapcache from under us (with a - * racy try_to_unuse/swapoff) we need an additional reference - * count to avoid reading garbage from page_private(page) above. - * If the WARN_ON triggers during a swapoff it maybe the race - * condition and it's harmless. However if it triggers without - * swapoff it signals a problem. - */ - WARN_ON(page_count(page) <= 1); + 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; - bdi = bdev->bd_inode->i_mapping->backing_dev_info; - blk_run_backing_dev(bdi, page); + 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; + } + + lh = se->list.next; + se = list_entry(lh, struct swap_extent, list); } - up_read(&swap_unplug_sem); } #define SWAPFILE_CLUSTER 256 #define LATENCY_LIMIT 256 -static inline unsigned long scan_swap_map(struct swap_info_struct *si) +static inline void cluster_set_flag(struct swap_cluster_info *info, + unsigned int flag) +{ + info->flags = flag; +} + +static inline unsigned int cluster_count(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_count(struct swap_cluster_info *info, + unsigned int c) +{ + info->data = c; +} + +static inline void cluster_set_count_flag(struct swap_cluster_info *info, + unsigned int c, unsigned int f) +{ + info->flags = f; + info->data = c; +} + +static inline unsigned int cluster_next(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_next(struct swap_cluster_info *info, + unsigned int n) +{ + info->data = n; +} + +static inline void cluster_set_next_flag(struct swap_cluster_info *info, + unsigned int n, unsigned int f) +{ + info->flags = f; + info->data = n; +} + +static inline bool cluster_is_free(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_FREE; +} + +static inline bool cluster_is_null(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_NEXT_NULL; +} + +static inline void cluster_set_null(struct swap_cluster_info *info) +{ + info->flags = CLUSTER_FLAG_NEXT_NULL; + info->data = 0; +} + +/* Add a cluster to discard list and schedule it to do discard */ +static void swap_cluster_schedule_discard(struct swap_info_struct *si, + unsigned int idx) { - unsigned long offset, last_in_cluster; + /* + * If scan_swap_map() 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 + */ + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + SWAP_MAP_BAD, SWAPFILE_CLUSTER); + + if (cluster_is_null(&si->discard_cluster_head)) { + cluster_set_next_flag(&si->discard_cluster_head, + idx, 0); + cluster_set_next_flag(&si->discard_cluster_tail, + idx, 0); + } else { + unsigned int tail = cluster_next(&si->discard_cluster_tail); + cluster_set_next(&si->cluster_info[tail], idx); + cluster_set_next_flag(&si->discard_cluster_tail, + idx, 0); + } + + schedule_work(&si->discard_work); +} + +/* + * Doing discard actually. After a cluster discard is finished, the cluster + * will be added to free cluster list. caller should hold si->lock. +*/ +static void swap_do_scheduled_discard(struct swap_info_struct *si) +{ + struct swap_cluster_info *info; + unsigned int idx; + + info = si->cluster_info; + + while (!cluster_is_null(&si->discard_cluster_head)) { + idx = cluster_next(&si->discard_cluster_head); + + cluster_set_next_flag(&si->discard_cluster_head, + cluster_next(&info[idx]), 0); + if (cluster_next(&si->discard_cluster_tail) == idx) { + cluster_set_null(&si->discard_cluster_head); + cluster_set_null(&si->discard_cluster_tail); + } + spin_unlock(&si->lock); + + discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, + SWAPFILE_CLUSTER); + + spin_lock(&si->lock); + cluster_set_flag(&info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&si->free_cluster_head)) { + cluster_set_next_flag(&si->free_cluster_head, + idx, 0); + cluster_set_next_flag(&si->free_cluster_tail, + idx, 0); + } else { + unsigned int tail; + + tail = cluster_next(&si->free_cluster_tail); + cluster_set_next(&info[tail], idx); + cluster_set_next_flag(&si->free_cluster_tail, + idx, 0); + } + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + 0, SWAPFILE_CLUSTER); + } +} + +static void swap_discard_work(struct work_struct *work) +{ + struct swap_info_struct *si; + + si = container_of(work, struct swap_info_struct, discard_work); + + spin_lock(&si->lock); + swap_do_scheduled_discard(si); + spin_unlock(&si->lock); +} + +/* + * The cluster corresponding to page_nr will be used. The cluster will be + * removed from free cluster list and its usage counter will be increased. + */ +static void inc_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + if (cluster_is_free(&cluster_info[idx])) { + VM_BUG_ON(cluster_next(&p->free_cluster_head) != idx); + cluster_set_next_flag(&p->free_cluster_head, + cluster_next(&cluster_info[idx]), 0); + if (cluster_next(&p->free_cluster_tail) == idx) { + cluster_set_null(&p->free_cluster_tail); + cluster_set_null(&p->free_cluster_head); + } + cluster_set_count_flag(&cluster_info[idx], 0, 0); + } + + VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) + 1); +} + +/* + * The cluster corresponding to page_nr decreases one usage. If the usage + * counter becomes 0, which means no page in the cluster is in using, we can + * optionally discard the cluster and add it to free cluster list. + */ +static void dec_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + + VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) - 1); + + if (cluster_count(&cluster_info[idx]) == 0) { + /* + * If the swap is discardable, prepare discard the cluster + * instead of free it immediately. The cluster will be freed + * after discard. + */ + if ((p->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == + (SWP_WRITEOK | SWP_PAGE_DISCARD)) { + swap_cluster_schedule_discard(p, idx); + return; + } + + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&p->free_cluster_head)) { + cluster_set_next_flag(&p->free_cluster_head, idx, 0); + cluster_set_next_flag(&p->free_cluster_tail, idx, 0); + } else { + unsigned int tail = cluster_next(&p->free_cluster_tail); + cluster_set_next(&cluster_info[tail], idx); + cluster_set_next_flag(&p->free_cluster_tail, idx, 0); + } + } +} + +/* + * It's possible scan_swap_map() uses a free cluster in the middle of free + * cluster list. Avoiding such abuse to avoid list corruption. + */ +static bool +scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, + unsigned long offset) +{ + struct percpu_cluster *percpu_cluster; + bool conflict; + + offset /= SWAPFILE_CLUSTER; + conflict = !cluster_is_null(&si->free_cluster_head) && + offset != cluster_next(&si->free_cluster_head) && + cluster_is_free(&si->cluster_info[offset]); + + if (!conflict) + return false; + + percpu_cluster = this_cpu_ptr(si->percpu_cluster); + cluster_set_null(&percpu_cluster->index); + return true; +} + +/* + * Try to get a swap entry from current cpu's swap entry pool (a cluster). This + * might involve allocating a new cluster for current CPU too. + */ +static void scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, + unsigned long *offset, unsigned long *scan_base) +{ + struct percpu_cluster *cluster; + bool found_free; + unsigned long tmp; + +new_cluster: + cluster = this_cpu_ptr(si->percpu_cluster); + if (cluster_is_null(&cluster->index)) { + if (!cluster_is_null(&si->free_cluster_head)) { + cluster->index = si->free_cluster_head; + cluster->next = cluster_next(&cluster->index) * + SWAPFILE_CLUSTER; + } else if (!cluster_is_null(&si->discard_cluster_head)) { + /* + * we don't have free cluster but have some clusters in + * discarding, do discard now and reclaim them + */ + swap_do_scheduled_discard(si); + *scan_base = *offset = si->cluster_next; + goto new_cluster; + } else + return; + } + + 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 + */ + tmp = cluster->next; + while (tmp < si->max && tmp < (cluster_next(&cluster->index) + 1) * + SWAPFILE_CLUSTER) { + if (!si->swap_map[tmp]) { + found_free = true; + break; + } + tmp++; + } + if (!found_free) { + cluster_set_null(&cluster->index); + goto new_cluster; + } + cluster->next = tmp + 1; + *offset = tmp; + *scan_base = tmp; +} + +static unsigned long scan_swap_map(struct swap_info_struct *si, + unsigned char usage) +{ + unsigned long offset; + unsigned long scan_base; + unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; - /* + /* * 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 @@ -98,16 +500,33 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si) * 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 */ si->flags += SWP_SCANNING; - if (unlikely(!si->cluster_nr)) { - si->cluster_nr = SWAPFILE_CLUSTER - 1; - if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) - goto lowest; - spin_unlock(&swap_lock); + scan_base = offset = si->cluster_next; + + /* SSD algorithm */ + if (si->cluster_info) { + scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); + goto checks; + } + + if (unlikely(!si->cluster_nr--)) { + if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { + si->cluster_nr = SWAPFILE_CLUSTER - 1; + goto checks; + } + + spin_unlock(&si->lock); - offset = si->lowest_bit; + /* + * If seek is expensive, start searching for new cluster from + * start of partition, to minimize the span of allocated swap. + * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info + * case, just handled by scan_swap_map_try_ssd_cluster() above. + */ + scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ @@ -115,48 +534,78 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si) if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { - spin_lock(&swap_lock); - si->cluster_next = offset-SWAPFILE_CLUSTER+1; - goto cluster; + spin_lock(&si->lock); + offset -= SWAPFILE_CLUSTER - 1; + si->cluster_next = offset; + si->cluster_nr = SWAPFILE_CLUSTER - 1; + goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } - spin_lock(&swap_lock); - goto lowest; + + offset = scan_base; + spin_lock(&si->lock); + si->cluster_nr = SWAPFILE_CLUSTER - 1; } - si->cluster_nr--; -cluster: - offset = si->cluster_next; - if (offset > si->highest_bit) -lowest: offset = si->lowest_bit; -checks: if (!(si->flags & SWP_WRITEOK)) +checks: + if (si->cluster_info) { + while (scan_swap_map_ssd_cluster_conflict(si, offset)) + scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); + } + if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; - if (!si->swap_map[offset]) { - 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] = 1; - si->cluster_next = offset + 1; - si->flags -= SWP_SCANNING; - return offset; + 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 */ } - spin_unlock(&swap_lock); + if (si->swap_map[offset]) + goto scan; + + 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; + spin_lock(&swap_avail_lock); + plist_del(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); + } + si->swap_map[offset] = usage; + inc_cluster_info_page(si, si->cluster_info, offset); + si->cluster_next = offset + 1; + si->flags -= SWP_SCANNING; + + return offset; + +scan: + spin_unlock(&si->lock); while (++offset <= si->highest_bit) { if (!si->swap_map[offset]) { - spin_lock(&swap_lock); + 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)) { @@ -164,8 +613,23 @@ checks: if (!(si->flags & SWP_WRITEOK)) latency_ration = LATENCY_LIMIT; } } - spin_lock(&swap_lock); - goto lowest; + 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; + } + offset++; + } + spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; @@ -174,68 +638,93 @@ no_page: swp_entry_t get_swap_page(void) { - struct swap_info_struct *si; + struct swap_info_struct *si, *next; pgoff_t offset; - int type, next; - int wrapped = 0; - spin_lock(&swap_lock); - if (nr_swap_pages <= 0) + if (atomic_long_read(&nr_swap_pages) <= 0) goto noswap; - nr_swap_pages--; - - for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { - si = swap_info + type; - next = si->next; - if (next < 0 || - (!wrapped && si->prio != swap_info[next].prio)) { - next = swap_list.head; - wrapped++; + atomic_long_dec(&nr_swap_pages); + + spin_lock(&swap_avail_lock); + +start_over: + plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { + /* requeue si to after same-priority siblings */ + plist_requeue(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); + spin_lock(&si->lock); + if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + if (plist_node_empty(&si->avail_list)) { + spin_unlock(&si->lock); + goto nextsi; + } + WARN(!si->highest_bit, + "swap_info %d in list but !highest_bit\n", + si->type); + WARN(!(si->flags & SWP_WRITEOK), + "swap_info %d in list but !SWP_WRITEOK\n", + si->type); + plist_del(&si->avail_list, &swap_avail_head); + spin_unlock(&si->lock); + goto nextsi; } - if (!si->highest_bit) - continue; - if (!(si->flags & SWP_WRITEOK)) - continue; - - swap_list.next = next; - offset = scan_swap_map(si); - if (offset) { - spin_unlock(&swap_lock); - return swp_entry(type, offset); - } - next = swap_list.next; + /* 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(si->type, offset); + pr_debug("scan_swap_map of si %d failed to find offset\n", + si->type); + spin_lock(&swap_avail_lock); +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 (plist_node_empty(&next->avail_list)) + goto start_over; } - nr_swap_pages++; + spin_unlock(&swap_avail_lock); + + atomic_long_inc(&nr_swap_pages); noswap: - spin_unlock(&swap_lock); return (swp_entry_t) {0}; } +/* 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; pgoff_t offset; - spin_lock(&swap_lock); - si = swap_info + type; - if (si->flags & SWP_WRITEOK) { - nr_swap_pages--; - offset = scan_swap_map(si); + 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(&swap_lock); + spin_unlock(&si->lock); return swp_entry(type, offset); } - nr_swap_pages++; + atomic_long_inc(&nr_swap_pages); } - spin_unlock(&swap_lock); + spin_unlock(&si->lock); 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; + struct swap_info_struct *p; unsigned long offset, type; if (!entry.val) @@ -243,7 +732,7 @@ static struct swap_info_struct * swap_info_get(swp_entry_t entry) type = swp_type(entry); if (type >= nr_swapfiles) goto bad_nofile; - p = & swap_info[type]; + p = swap_info[type]; if (!(p->flags & SWP_USED)) goto bad_device; offset = swp_offset(entry); @@ -251,64 +740,129 @@ static struct swap_info_struct * swap_info_get(swp_entry_t entry) goto bad_offset; if (!p->swap_map[offset]) goto bad_free; - spin_lock(&swap_lock); + spin_lock(&p->lock); return p; bad_free: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val); + pr_err("swap_free: %s%08lx\n", Unused_offset, entry.val); goto out; bad_offset: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val); + pr_err("swap_free: %s%08lx\n", Bad_offset, entry.val); goto out; bad_device: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val); + pr_err("swap_free: %s%08lx\n", Unused_file, entry.val); goto out; bad_nofile: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val); + pr_err("swap_free: %s%08lx\n", Bad_file, entry.val); out: return NULL; -} - -static int swap_entry_free(struct swap_info_struct *p, unsigned long offset) -{ - int count = p->swap_map[offset]; - - if (count < SWAP_MAP_MAX) { - count--; - p->swap_map[offset] = count; - if (!count) { - if (offset < p->lowest_bit) - p->lowest_bit = offset; - if (offset > p->highest_bit) - p->highest_bit = offset; - if (p->prio > swap_info[swap_list.next].prio) - swap_list.next = p - swap_info; - nr_swap_pages++; - p->inuse_pages--; +} + +static unsigned char swap_entry_free(struct swap_info_struct *p, + 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]; + has_cache = count & SWAP_HAS_CACHE; + count &= ~SWAP_HAS_CACHE; + + if (usage == SWAP_HAS_CACHE) { + VM_BUG_ON(!has_cache); + has_cache = 0; + } else if (count == SWAP_MAP_SHMEM) { + /* + * Or we could insist on shmem.c using a special + * swap_shmem_free() and free_shmem_swap_and_cache()... + */ + count = 0; + } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { + if (count == COUNT_CONTINUED) { + if (swap_count_continued(p, offset, count)) + count = SWAP_MAP_MAX | COUNT_CONTINUED; + else + count = SWAP_MAP_MAX; + } else + count--; + } + + if (!count) + mem_cgroup_uncharge_swap(entry); + + usage = count | has_cache; + p->swap_map[offset] = usage; + + /* free if no reference */ + if (!usage) { + dec_cluster_info_page(p, p->cluster_info, offset); + if (offset < p->lowest_bit) + p->lowest_bit = offset; + if (offset > p->highest_bit) { + bool was_full = !p->highest_bit; + p->highest_bit = offset; + if (was_full && (p->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + WARN_ON(!plist_node_empty(&p->avail_list)); + if (plist_node_empty(&p->avail_list)) + plist_add(&p->avail_list, + &swap_avail_head); + spin_unlock(&swap_avail_lock); + } + } + 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); } } - return count; + + return usage; } /* - * Caller has made sure that the swapdevice corresponding to entry + * 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) { - struct swap_info_struct * p; + struct swap_info_struct *p; p = swap_info_get(entry); if (p) { - swap_entry_free(p, swp_offset(entry)); - spin_unlock(&swap_lock); + swap_entry_free(p, entry, 1); + spin_unlock(&p->lock); + } +} + +/* + * Called after dropping swapcache to decrease refcnt to swap entries. + */ +void swapcache_free(swp_entry_t entry, struct page *page) +{ + struct swap_info_struct *p; + unsigned char count; + + 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); } } /* * 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. */ -static inline int page_swapcount(struct page *page) +int page_swapcount(struct page *page) { int count = 0; struct swap_info_struct *p; @@ -317,113 +871,112 @@ static inline int page_swapcount(struct page *page) entry.val = page_private(page); p = swap_info_get(entry); if (p) { - /* Subtract the 1 for the swap cache itself */ - count = p->swap_map[swp_offset(entry)] - 1; - spin_unlock(&swap_lock); + count = swap_count(p->swap_map[swp_offset(entry)]); + spin_unlock(&p->lock); } return count; } /* - * We can use this swap cache entry directly - * if there are no other references to it. + * 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. */ -int can_share_swap_page(struct page *page) +int reuse_swap_page(struct page *page) { int count; - BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (unlikely(PageKsm(page))) + return 0; count = page_mapcount(page); - if (count <= 1 && PageSwapCache(page)) + if (count <= 1 && PageSwapCache(page)) { count += page_swapcount(page); - return count == 1; + if (count == 1 && !PageWriteback(page)) { + delete_from_swap_cache(page); + SetPageDirty(page); + } + } + return count <= 1; } /* - * Work out if there are any other processes sharing this - * swap cache page. Free it if you can. Return success. + * 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 remove_exclusive_swap_page(struct page *page) +int try_to_free_swap(struct page *page) { - int retval; - struct swap_info_struct * p; - swp_entry_t entry; - - BUG_ON(PagePrivate(page)); - BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(!PageLocked(page), page); if (!PageSwapCache(page)) return 0; if (PageWriteback(page)) return 0; - if (page_count(page) != 2) /* 2: us + cache */ + if (page_swapcount(page)) return 0; - entry.val = page_private(page); - p = swap_info_get(entry); - if (!p) + /* + * Once hibernation has begun to create its image of memory, + * there's a danger that one of the calls to try_to_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 + * another page of the image. On waking from hibernation, the + * original page 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; - /* Is the only swap cache user the cache itself? */ - retval = 0; - if (p->swap_map[swp_offset(entry)] == 1) { - /* Recheck the page count with the swapcache lock held.. */ - write_lock_irq(&swapper_space.tree_lock); - if ((page_count(page) == 2) && !PageWriteback(page)) { - __delete_from_swap_cache(page); - SetPageDirty(page); - retval = 1; - } - write_unlock_irq(&swapper_space.tree_lock); - } - spin_unlock(&swap_lock); - - if (retval) { - swap_free(entry); - page_cache_release(page); - } - - return retval; + delete_from_swap_cache(page); + SetPageDirty(page); + return 1; } /* * Free the swap entry like above, but also try to * free the page cache entry if it is the last user. */ -void free_swap_and_cache(swp_entry_t entry) +int free_swap_and_cache(swp_entry_t entry) { - struct swap_info_struct * p; + struct swap_info_struct *p; struct page *page = NULL; - if (is_migration_entry(entry)) - return; + if (non_swap_entry(entry)) + return 1; p = swap_info_get(entry); if (p) { - if (swap_entry_free(p, swp_offset(entry)) == 1) { - page = find_get_page(&swapper_space, entry.val); - if (page && unlikely(TestSetPageLocked(page))) { + 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; } } - spin_unlock(&swap_lock); + spin_unlock(&p->lock); } if (page) { - int one_user; - - BUG_ON(PagePrivate(page)); - one_user = (page_count(page) == 2); - /* Only cache user (+us), or swap space full? Free it! */ - /* Also recheck PageSwapCache after page is locked (above) */ + /* + * Not mapped elsewhere, or swap space full? Free it! + * Also recheck PageSwapCache now page is locked (above). + */ if (PageSwapCache(page) && !PageWriteback(page) && - (one_user || vm_swap_full())) { + (!page_mapped(page) || vm_swap_full())) { delete_from_swap_cache(page); SetPageDirty(page); } unlock_page(page); page_cache_release(page); } + return p != NULL; } #ifdef CONFIG_HIBERNATION @@ -438,37 +991,35 @@ void free_swap_and_cache(swp_entry_t entry) int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) { struct block_device *bdev = NULL; - int i; + int type; if (device) bdev = bdget(device); spin_lock(&swap_lock); - for (i = 0; i < nr_swapfiles; i++) { - struct swap_info_struct *sis = swap_info + i; + for (type = 0; type < nr_swapfiles; type++) { + struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (!bdev) { if (bdev_p) - *bdev_p = sis->bdev; + *bdev_p = bdgrab(sis->bdev); spin_unlock(&swap_lock); - return i; + return type; } if (bdev == sis->bdev) { - struct swap_extent *se; + struct swap_extent *se = &sis->first_swap_extent; - se = list_entry(sis->extent_list.next, - struct swap_extent, list); if (se->start_block == offset) { if (bdev_p) - *bdev_p = sis->bdev; + *bdev_p = bdgrab(sis->bdev); spin_unlock(&swap_lock); bdput(bdev); - return i; + return type; } } } @@ -480,6 +1031,21 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) } /* + * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev + * corresponding to given index in swap_info (swap type). + */ +sector_t swapdev_block(int type, pgoff_t offset) +{ + struct block_device *bdev; + + if ((unsigned int)type >= nr_swapfiles) + return 0; + if (!(swap_info[type]->flags & SWP_WRITEOK)) + return 0; + return map_swap_entry(swp_entry(type, offset), &bdev); +} + +/* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * @@ -489,18 +1055,37 @@ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; - if (type < nr_swapfiles) { - spin_lock(&swap_lock); - if (swap_info[type].flags & SWP_WRITEOK) { - n = swap_info[type].pages; + spin_lock(&swap_lock); + if ((unsigned int)type < nr_swapfiles) { + struct swap_info_struct *sis = swap_info[type]; + + spin_lock(&sis->lock); + if (sis->flags & SWP_WRITEOK) { + n = sis->pages; if (free) - n -= swap_info[type].inuse_pages; + n -= sis->inuse_pages; } - spin_unlock(&swap_lock); + spin_unlock(&sis->lock); } + spin_unlock(&swap_lock); return n; } +#endif /* CONFIG_HIBERNATION */ + +static inline int maybe_same_pte(pte_t pte, pte_t swp_pte) +{ +#ifdef CONFIG_MEM_SOFT_DIRTY + /* + * When pte keeps soft dirty bit the pte generated + * from swap entry does not has it, still it's same + * pte from logical point of view. + */ + pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte); + return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty); +#else + return pte_same(pte, swp_pte); #endif +} /* * No need to decide whether this PTE shares the swap entry with others, @@ -510,26 +1095,40 @@ unsigned int count_swap_pages(int type, int free) static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct page *page) { + struct page *swapcache; + struct mem_cgroup *memcg; spinlock_t *ptl; pte_t *pte; int ret = 1; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + swapcache = page; + page = ksm_might_need_to_copy(page, vma, addr); + if (unlikely(!page)) + return -ENOMEM; + + if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, + GFP_KERNEL, &memcg)) { ret = -ENOMEM; + goto out_nolock; + } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) { - if (ret > 0) - mem_cgroup_uncharge_page(page); + if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) { + mem_cgroup_cancel_charge_swapin(memcg); ret = 0; goto out; } - inc_mm_counter(vma->vm_mm, anon_rss); + 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))); - page_add_anon_rmap(page, vma, addr); + 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); swap_free(entry); /* * Move the page to the active list so it is not @@ -538,6 +1137,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, activate_page(page); out: pte_unmap_unlock(pte, ptl); +out_nolock: + if (page != swapcache) { + unlock_page(page); + put_page(page); + } return ret; } @@ -556,7 +1160,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * 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. + * preemptable whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE. */ pte = pte_offset_map(pmd, addr); do { @@ -564,7 +1168,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * swapoff spends a _lot_ of time in this loop! * Test inline before going to call unuse_pte. */ - if (unlikely(pte_same(*pte, swp_pte))) { + if (unlikely(maybe_same_pte(*pte, swp_pte))) { pte_unmap(pte); ret = unuse_pte(vma, pmd, addr, entry, page); if (ret) @@ -588,7 +1192,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_none_or_clear_bad(pmd)) + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, entry, page); if (ret) @@ -624,7 +1228,7 @@ static int unuse_vma(struct vm_area_struct *vma, unsigned long addr, end, next; int ret; - if (page->mapping) { + if (page_anon_vma(page)) { addr = page_address_in_vma(page, vma); if (addr == -EFAULT) return 0; @@ -655,8 +1259,8 @@ static int unuse_mm(struct mm_struct *mm, if (!down_read_trylock(&mm->mmap_sem)) { /* - * Activate page so shrink_cache is unlikely to unmap its - * ptes while lock is dropped, so swapoff can make progress. + * 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); @@ -672,15 +1276,16 @@ static int unuse_mm(struct mm_struct *mm, } /* - * Scan swap_map from current position to next entry still in use. + * 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. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, - unsigned int prev) + unsigned int prev, bool frontswap) { unsigned int max = si->max; unsigned int i = prev; - int count; + unsigned char count; /* * No need for swap_lock here: we're just looking @@ -702,8 +1307,14 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, prev = 0; i = 1; } - count = si->swap_map[i]; - if (count && count != SWAP_MAP_BAD) + if (frontswap) { + if (frontswap_test(si, i)) + break; + else + continue; + } + count = ACCESS_ONCE(si->swap_map[i]); + if (count && swap_count(count) != SWAP_MAP_BAD) break; } return i; @@ -713,19 +1324,25 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, * 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 */ -static int try_to_unuse(unsigned int type) +int try_to_unuse(unsigned int type, bool frontswap, + unsigned long pages_to_unuse) { - struct swap_info_struct * si = &swap_info[type]; + struct swap_info_struct *si = swap_info[type]; struct mm_struct *start_mm; - unsigned short *swap_map; - unsigned short swcount; + volatile unsigned char *swap_map; /* swap_map is accessed without + * locking. Mark it as volatile + * to prevent compiler doing + * something odd. + */ + unsigned char swcount; struct page *page; swp_entry_t entry; unsigned int i = 0; int retval = 0; - int reset_overflow = 0; - int shmem; /* * When searching mms for an entry, a good strategy is to @@ -739,8 +1356,7 @@ static int try_to_unuse(unsigned int type) * 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. Though it's only a serious concern when an overflowed - * swap count is reset from SWAP_MAP_MAX, preventing a rescan. + * that. */ start_mm = &init_mm; atomic_inc(&init_mm.mm_users); @@ -750,16 +1366,16 @@ static int try_to_unuse(unsigned int type) * 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)) != 0) { + while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { if (signal_pending(current)) { retval = -EINTR; break; } - /* + /* * 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. + * page and read the swap into it. */ swap_map = &si->swap_map[i]; entry = swp_entry(type, i); @@ -772,7 +1388,15 @@ static int try_to_unuse(unsigned int type) * reused since sys_swapoff() already disabled * allocation from here, or alloc_page() failed. */ - if (!*swap_map) + swcount = *swap_map; + /* + * We don't hold lock here, so the swap entry could be + * SWAP_MAP_BAD (when the cluster is discarding). + * Instead of fail out, We can just skip the swap + * entry because swapoff will wait for discarding + * finish anyway. + */ + if (!swcount || swcount == SWAP_MAP_BAD) continue; retval = -ENOMEM; break; @@ -802,18 +1426,19 @@ static int try_to_unuse(unsigned int type) /* * Remove all references to entry. - * Whenever we reach init_mm, there's no address space - * to search, but use it as a reminder to search shmem. */ - shmem = 0; swcount = *swap_map; - if (swcount > 1) { - if (start_mm == &init_mm) - shmem = shmem_unuse(entry, page); - else - retval = unuse_mm(start_mm, entry, page); + if (swap_count(swcount) == SWAP_MAP_SHMEM) { + retval = shmem_unuse(entry, page); + /* page has already been unlocked and released */ + if (retval < 0) + break; + continue; } - if (*swap_map > 1) { + 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; @@ -823,7 +1448,7 @@ static int try_to_unuse(unsigned int type) atomic_inc(&new_start_mm->mm_users); atomic_inc(&prev_mm->mm_users); spin_lock(&mmlist_lock); - while (*swap_map > 1 && !retval && !shmem && + 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)) @@ -835,13 +1460,13 @@ static int try_to_unuse(unsigned int type) cond_resched(); swcount = *swap_map; - if (swcount <= 1) + if (!swap_count(swcount)) /* any usage ? */ ; - else if (mm == &init_mm) { + else if (mm == &init_mm) set_start_mm = 1; - shmem = shmem_unuse(entry, page); - } else + else retval = unuse_mm(mm, entry, page); + if (set_start_mm && *swap_map < swcount) { mmput(new_start_mm); atomic_inc(&mm->mm_users); @@ -855,13 +1480,6 @@ static int try_to_unuse(unsigned int type) mmput(start_mm); start_mm = new_start_mm; } - if (shmem) { - /* page has already been unlocked and released */ - if (shmem > 0) - continue; - retval = shmem; - break; - } if (retval) { unlock_page(page); page_cache_release(page); @@ -869,26 +1487,6 @@ static int try_to_unuse(unsigned int type) } /* - * How could swap count reach 0x7fff when the maximum - * pid is 0x7fff, and there's no way to repeat a swap - * page within an mm (except in shmem, where it's the - * shared object which takes the reference count)? - * We believe SWAP_MAP_MAX cannot occur in Linux 2.4. - * - * If that's wrong, then we should worry more about - * exit_mmap() and do_munmap() cases described above: - * we might be resetting SWAP_MAP_MAX too early here. - * We know "Undead"s can happen, they're okay, so don't - * report them; but do report if we reset SWAP_MAP_MAX. - */ - if (*swap_map == SWAP_MAP_MAX) { - spin_lock(&swap_lock); - *swap_map = 1; - spin_unlock(&swap_lock); - reset_overflow = 1; - } - - /* * 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, @@ -900,8 +1498,15 @@ static int try_to_unuse(unsigned int type) * 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. */ - if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) { + if (swap_count(*swap_map) && + PageDirty(page) && PageSwapCache(page)) { struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, }; @@ -910,7 +1515,16 @@ static int try_to_unuse(unsigned int type) lock_page(page); wait_on_page_writeback(page); } - if (PageSwapCache(page)) + + /* + * 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); /* @@ -927,13 +1541,13 @@ static int try_to_unuse(unsigned int type) * interactive performance. */ cond_resched(); + if (frontswap && pages_to_unuse > 0) { + if (!--pages_to_unuse) + break; + } } mmput(start_mm); - if (reset_overflow) { - printk(KERN_WARNING "swapoff: cleared swap entry overflow\n"); - swap_overflow = 0; - } return retval; } @@ -946,10 +1560,10 @@ static int try_to_unuse(unsigned int type) static void drain_mmlist(void) { struct list_head *p, *next; - unsigned int i; + unsigned int type; - for (i = 0; i < nr_swapfiles; i++) - if (swap_info[i].inuse_pages) + for (type = 0; type < nr_swapfiles; type++) + if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) @@ -959,12 +1573,23 @@ static void drain_mmlist(void) /* * Use this swapdev's extent info to locate the (PAGE_SIZE) block which - * corresponds to page offset `offset'. + * 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. */ -sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset) +static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev) { - struct swap_extent *se = sis->curr_swap_extent; - struct swap_extent *start_se = se; + 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; @@ -974,44 +1599,43 @@ sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset) return se->start_block + (offset - se->start_page); } lh = se->list.next; - if (lh == &sis->extent_list) - lh = lh->next; se = list_entry(lh, struct swap_extent, list); sis->curr_swap_extent = se; BUG_ON(se == start_se); /* It *must* be present */ } } -#ifdef CONFIG_HIBERNATION /* - * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev - * corresponding to given index in swap_info (swap type). + * Returns the page offset into bdev for the specified page's swap entry. */ -sector_t swapdev_block(int swap_type, pgoff_t offset) +sector_t map_swap_page(struct page *page, struct block_device **bdev) { - struct swap_info_struct *sis; - - if (swap_type >= nr_swapfiles) - return 0; - - sis = swap_info + swap_type; - return (sis->flags & SWP_WRITEOK) ? map_swap_page(sis, offset) : 0; + swp_entry_t entry; + entry.val = page_private(page); + return map_swap_entry(entry, bdev); } -#endif /* CONFIG_HIBERNATION */ /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { - while (!list_empty(&sis->extent_list)) { + while (!list_empty(&sis->first_swap_extent.list)) { struct swap_extent *se; - se = list_entry(sis->extent_list.next, + se = list_entry(sis->first_swap_extent.list.next, struct swap_extent, list); list_del(&se->list); kfree(se); } + + if (sis->flags & SWP_FILE) { + 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); + } } /* @@ -1020,7 +1644,7 @@ static void destroy_swap_extents(struct swap_info_struct *sis) * * This function rather assumes that it is called in ascending page order. */ -static int +int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { @@ -1028,8 +1652,15 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, struct swap_extent *new_se; struct list_head *lh; - lh = sis->extent_list.prev; /* The highest page extent */ - if (lh != &sis->extent_list) { + 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); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { @@ -1049,7 +1680,7 @@ 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->extent_list); + list_add_tail(&new_se->list, &sis->first_swap_extent.list); return 1; } @@ -1086,258 +1717,264 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { - struct inode *inode; - unsigned blocks_per_page; - unsigned long page_no; - unsigned blkbits; - sector_t probe_block; - sector_t last_block; - sector_t lowest_block = -1; - sector_t highest_block = 0; - int nr_extents = 0; + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; int ret; - inode = sis->swap_file->f_mapping->host; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; - goto done; + return ret; } - blkbits = inode->i_blkbits; - blocks_per_page = PAGE_SIZE >> blkbits; - - /* - * Map all the blocks into the extent list. This code doesn't try - * to be very smart. - */ - probe_block = 0; - page_no = 0; - last_block = i_size_read(inode) >> blkbits; - while ((probe_block + blocks_per_page) <= last_block && - page_no < sis->max) { - unsigned block_in_page; - sector_t first_block; - - first_block = bmap(inode, probe_block); - if (first_block == 0) - goto bad_bmap; - - /* - * It must be PAGE_SIZE aligned on-disk - */ - if (first_block & (blocks_per_page - 1)) { - probe_block++; - goto reprobe; - } - - for (block_in_page = 1; block_in_page < blocks_per_page; - block_in_page++) { - sector_t block; - - block = bmap(inode, probe_block + block_in_page); - if (block == 0) - goto bad_bmap; - if (block != first_block + block_in_page) { - /* Discontiguity */ - probe_block++; - goto reprobe; - } - } - - first_block >>= (PAGE_SHIFT - blkbits); - if (page_no) { /* exclude the header page */ - if (first_block < lowest_block) - lowest_block = first_block; - if (first_block > highest_block) - highest_block = first_block; + 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; } + return ret; + } - /* - * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks - */ - ret = add_swap_extent(sis, page_no, 1, first_block); - if (ret < 0) - goto out; - nr_extents += ret; - page_no++; - probe_block += blocks_per_page; -reprobe: - continue; - } - ret = nr_extents; - *span = 1 + highest_block - lowest_block; - if (page_no == 0) - page_no = 1; /* force Empty message */ - sis->max = page_no; - sis->pages = page_no - 1; - sis->highest_bit = page_no - 1; -done: - sis->curr_swap_extent = list_entry(sis->extent_list.prev, - struct swap_extent, list); - goto out; -bad_bmap: - printk(KERN_ERR "swapon: swapfile has holes\n"); - ret = -EINVAL; -out: - return ret; + return generic_swapfile_activate(sis, swap_file, span); } -#if 0 /* We don't need this yet */ -#include <linux/backing-dev.h> -int page_queue_congested(struct page *page) +static void _enable_swap_info(struct swap_info_struct *p, int prio, + unsigned char *swap_map, + struct swap_cluster_info *cluster_info) { - struct backing_dev_info *bdi; - - BUG_ON(!PageLocked(page)); /* It pins the swap_info_struct */ + if (prio >= 0) + p->prio = prio; + else + p->prio = --least_priority; + /* + * the plist prio is negated because plist ordering is + * low-to-high, while swap ordering is high-to-low + */ + p->list.prio = -p->prio; + p->avail_list.prio = -p->prio; + p->swap_map = swap_map; + p->cluster_info = cluster_info; + p->flags |= SWP_WRITEOK; + atomic_long_add(p->pages, &nr_swap_pages); + total_swap_pages += p->pages; + + assert_spin_locked(&swap_lock); + /* + * both lists are plists, and thus priority ordered. + * swap_active_head needs to be priority ordered for swapoff(), + * 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(), + * which allocates swap pages from the highest available priority + * swap_info_struct. + */ + plist_add(&p->list, &swap_active_head); + spin_lock(&swap_avail_lock); + plist_add(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); +} - if (PageSwapCache(page)) { - swp_entry_t entry = { .val = page_private(page) }; - struct swap_info_struct *sis; +static void enable_swap_info(struct swap_info_struct *p, int prio, + unsigned char *swap_map, + struct swap_cluster_info *cluster_info, + unsigned long *frontswap_map) +{ + frontswap_init(p->type, frontswap_map); + spin_lock(&swap_lock); + spin_lock(&p->lock); + _enable_swap_info(p, prio, swap_map, cluster_info); + spin_unlock(&p->lock); + spin_unlock(&swap_lock); +} - sis = get_swap_info_struct(swp_type(entry)); - bdi = sis->bdev->bd_inode->i_mapping->backing_dev_info; - } else - bdi = page->mapping->backing_dev_info; - return bdi_write_congested(bdi); +static void reinsert_swap_info(struct swap_info_struct *p) +{ + spin_lock(&swap_lock); + spin_lock(&p->lock); + _enable_swap_info(p, p->prio, p->swap_map, p->cluster_info); + spin_unlock(&p->lock); + spin_unlock(&swap_lock); } -#endif -asmlinkage long sys_swapoff(const char __user * specialfile) +SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { - struct swap_info_struct * p = NULL; - unsigned short *swap_map; + struct swap_info_struct *p = NULL; + unsigned char *swap_map; + struct swap_cluster_info *cluster_info; + unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; - char * pathname; - int i, type, prev; - int err; - + struct filename *pathname; + int err, found = 0; + unsigned int old_block_size; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; + BUG_ON(!current->mm); + pathname = getname(specialfile); - err = PTR_ERR(pathname); if (IS_ERR(pathname)) - goto out; + return PTR_ERR(pathname); - victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0); - putname(pathname); + victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) 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; - if ((p->flags & SWP_ACTIVE) == SWP_ACTIVE) { - if (p->swap_file->f_mapping == mapping) + plist_for_each_entry(p, &swap_active_head, list) { + if (p->flags & SWP_WRITEOK) { + 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; } - if (!security_vm_enough_memory(p->pages)) + if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; 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(&swap_avail_lock); + plist_del(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); + spin_lock(&p->lock); + if (p->prio < 0) { + struct swap_info_struct *si = p; + + plist_for_each_entry_continue(si, &swap_active_head, list) { + si->prio++; + si->list.prio--; + si->avail_list.prio--; + } + least_priority++; } - nr_swap_pages -= p->pages; + 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); - current->flags |= PF_SWAPOFF; - err = try_to_unuse(type); - current->flags &= ~PF_SWAPOFF; + set_current_oom_origin(); + err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ + clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ - spin_lock(&swap_lock); - for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next) - if (p->prio >= swap_info[i].prio) - break; - p->next = i; - if (prev < 0) - swap_list.head = swap_list.next = p - swap_info; - else - swap_info[prev].next = p - swap_info; - nr_swap_pages += p->pages; - total_swap_pages += p->pages; - p->flags |= SWP_WRITEOK; - spin_unlock(&swap_lock); + reinsert_swap_info(p); goto out_dput; } - /* wait for any unplug function to finish */ - down_write(&swap_unplug_sem); - up_write(&swap_unplug_sem); + flush_work(&p->discard_work); destroy_swap_extents(p); + if (p->flags & SWP_CONTINUED) + free_swap_count_continuations(p); + 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; + old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; - p->flags = 0; + cluster_info = p->cluster_info; + p->cluster_info = NULL; + frontswap_map = frontswap_map_get(p); + spin_unlock(&p->lock); spin_unlock(&swap_lock); + frontswap_invalidate_area(p->type); + frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); + free_percpu(p->percpu_cluster); + p->percpu_cluster = NULL; vfree(swap_map); + vfree(cluster_info); + vfree(frontswap_map); + /* 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); - bd_release(bdev); + set_blocksize(bdev, 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); } 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); out_dput: filp_close(victim, NULL); out: + putname(pathname); return err; } #ifdef CONFIG_PROC_FS +static unsigned swaps_poll(struct file *file, poll_table *wait) +{ + struct seq_file *seq = file->private_data; + + poll_wait(file, &proc_poll_wait, wait); + + if (seq->poll_event != atomic_read(&proc_poll_event)) { + seq->poll_event = atomic_read(&proc_poll_event); + return POLLIN | POLLRDNORM | POLLERR | POLLPRI; + } + + return POLLIN | POLLRDNORM; +} + /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { - struct swap_info_struct *ptr = swap_info; - int i; + struct swap_info_struct *si; + int type; loff_t l = *pos; mutex_lock(&swapon_mutex); @@ -1345,11 +1982,13 @@ static void *swap_start(struct seq_file *swap, loff_t *pos) if (!l) return SEQ_START_TOKEN; - for (i = 0; i < nr_swapfiles; i++, ptr++) { - if (!(ptr->flags & SWP_USED) || !ptr->swap_map) + for (type = 0; type < nr_swapfiles; type++) { + smp_rmb(); /* read nr_swapfiles before swap_info[type] */ + si = swap_info[type]; + if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) - return ptr; + return si; } return NULL; @@ -1357,21 +1996,21 @@ static void *swap_start(struct seq_file *swap, loff_t *pos) static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { - struct swap_info_struct *ptr; - struct swap_info_struct *endptr = swap_info + nr_swapfiles; + struct swap_info_struct *si = v; + int type; if (v == SEQ_START_TOKEN) - ptr = swap_info; - else { - ptr = v; - ptr++; - } - - for (; ptr < endptr; ptr++) { - if (!(ptr->flags & SWP_USED) || !ptr->swap_map) + type = 0; + else + type = si->type + 1; + + for (; type < nr_swapfiles; type++) { + smp_rmb(); /* read nr_swapfiles before swap_info[type] */ + si = swap_info[type]; + if (!(si->flags & SWP_USED) || !si->swap_map) continue; ++*pos; - return ptr; + return si; } return NULL; @@ -1384,24 +2023,24 @@ static void swap_stop(struct seq_file *swap, void *v) static int swap_show(struct seq_file *swap, void *v) { - struct swap_info_struct *ptr = v; + struct swap_info_struct *si = v; struct file *file; int len; - if (ptr == SEQ_START_TOKEN) { + if (si == SEQ_START_TOKEN) { seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); return 0; } - file = ptr->swap_file; + 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 < 40 ? 40 - len : 1, " ", - S_ISBLK(file->f_path.dentry->d_inode->i_mode) ? + len < 40 ? 40 - len : 1, " ", + S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", - ptr->pages << (PAGE_SHIFT - 10), - ptr->inuse_pages << (PAGE_SHIFT - 10), - ptr->prio); + si->pages << (PAGE_SHIFT - 10), + si->inuse_pages << (PAGE_SHIFT - 10), + si->prio); return 0; } @@ -1414,7 +2053,16 @@ static const struct seq_operations swaps_op = { static int swaps_open(struct inode *inode, struct file *file) { - return seq_open(file, &swaps_op); + struct seq_file *seq; + int ret; + + ret = seq_open(file, &swaps_op); + if (ret) + return ret; + + seq = file->private_data; + seq->poll_event = atomic_read(&proc_poll_event); + return 0; } static const struct file_operations proc_swaps_operations = { @@ -1422,133 +2070,342 @@ static const struct file_operations proc_swaps_operations = { .read = seq_read, .llseek = seq_lseek, .release = seq_release, + .poll = swaps_poll, }; static int __init procswaps_init(void) { - struct proc_dir_entry *entry; - - entry = create_proc_entry("swaps", 0, NULL); - if (entry) - entry->proc_fops = &proc_swaps_operations; + proc_create("swaps", 0, NULL, &proc_swaps_operations); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ +#ifdef MAX_SWAPFILES_CHECK +static int __init max_swapfiles_check(void) +{ + MAX_SWAPFILES_CHECK(); + return 0; +} +late_initcall(max_swapfiles_check); +#endif + +static struct swap_info_struct *alloc_swap_info(void) +{ + struct swap_info_struct *p; + unsigned int type; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return ERR_PTR(-ENOMEM); + + spin_lock(&swap_lock); + for (type = 0; type < nr_swapfiles; type++) { + if (!(swap_info[type]->flags & SWP_USED)) + break; + } + if (type >= MAX_SWAPFILES) { + spin_unlock(&swap_lock); + kfree(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.) + */ + smp_wmb(); + nr_swapfiles++; + } else { + kfree(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); + plist_node_init(&p->list, 0); + plist_node_init(&p->avail_list, 0); + p->flags = SWP_USED; + spin_unlock(&swap_lock); + spin_lock_init(&p->lock); + + return p; +} + +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, + FMODE_READ | FMODE_WRITE | FMODE_EXCL, + sys_swapon); + if (error < 0) { + p->bdev = NULL; + 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; + } 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; + + return 0; +} + +static unsigned long read_swap_header(struct swap_info_struct *p, + 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)) { + pr_err("Unable to find swap-space signature\n"); + return 0; + } + + /* swap partition endianess 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); + 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) { + 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; + last_page = swap_header->info.last_page; + if (last_page > maxpages) { + pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", + maxpages << (PAGE_SHIFT - 10), + last_page << (PAGE_SHIFT - 10)); + } + 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) { + pr_warn("Swap area shorter than signature indicates\n"); + return 0; + } + if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) + return 0; + if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) + return 0; + + return maxpages; +} + +static int setup_swap_map_and_extents(struct swap_info_struct *p, + union swap_header *swap_header, + unsigned char *swap_map, + struct swap_cluster_info *cluster_info, + unsigned long maxpages, + sector_t *span) +{ + int i; + unsigned int nr_good_pages; + int nr_extents; + unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); + unsigned long idx = p->cluster_next / SWAPFILE_CLUSTER; + + nr_good_pages = maxpages - 1; /* omit header page */ + + cluster_set_null(&p->free_cluster_head); + cluster_set_null(&p->free_cluster_tail); + cluster_set_null(&p->discard_cluster_head); + cluster_set_null(&p->discard_cluster_tail); + + 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--; + /* + * Haven't marked the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, page_nr); + } + } + + /* Haven't marked the cluster free yet, no list operation involved */ + for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) + inc_cluster_info_page(p, cluster_info, i); + + if (nr_good_pages) { + swap_map[0] = SWAP_MAP_BAD; + /* + * Not mark the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, 0); + 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) { + pr_warn("Empty swap-file\n"); + return -EINVAL; + } + + if (!cluster_info) + return nr_extents; + + for (i = 0; i < nr_clusters; i++) { + if (!cluster_count(&cluster_info[idx])) { + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&p->free_cluster_head)) { + cluster_set_next_flag(&p->free_cluster_head, + idx, 0); + cluster_set_next_flag(&p->free_cluster_tail, + idx, 0); + } else { + unsigned int tail; + + tail = cluster_next(&p->free_cluster_tail); + cluster_set_next(&cluster_info[tail], idx); + cluster_set_next_flag(&p->free_cluster_tail, + idx, 0); + } + } + idx++; + if (idx == nr_clusters) + idx = 0; + } + return nr_extents; +} + /* - * Written 01/25/92 by Simmule Turner, heavily changed by Linus. - * - * The swapon system call + * Helper to sys_swapon determining if a given swap + * backing device queue supports DISCARD operations. */ -asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) +static bool swap_discardable(struct swap_info_struct *si) { - struct swap_info_struct * p; - char *name = NULL; - struct block_device *bdev = NULL; + 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; - unsigned int type; - int i, prev; + int i; + int prio; int error; - static int least_priority; - union swap_header *swap_header = NULL; - int swap_header_version; - unsigned int nr_good_pages = 0; - int nr_extents = 0; + union swap_header *swap_header; + int nr_extents; sector_t span; - unsigned long maxpages = 1; - int swapfilesize; - unsigned short *swap_map; + unsigned long maxpages; + unsigned char *swap_map = NULL; + struct swap_cluster_info *cluster_info = NULL; + unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; - int did_down = 0; + + if (swap_flags & ~SWAP_FLAGS_VALID) + return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - spin_lock(&swap_lock); - p = swap_info; - for (type = 0 ; type < nr_swapfiles ; type++,p++) - if (!(p->flags & SWP_USED)) - break; - error = -EPERM; - if (type >= MAX_SWAPFILES) { - spin_unlock(&swap_lock); - goto out; - } - if (type >= nr_swapfiles) - nr_swapfiles = type+1; - INIT_LIST_HEAD(&p->extent_list); - p->flags = SWP_USED; - p->swap_file = NULL; - p->old_block_size = 0; - p->swap_map = NULL; - p->lowest_bit = 0; - p->highest_bit = 0; - p->cluster_nr = 0; - p->inuse_pages = 0; - p->next = -1; - if (swap_flags & SWAP_FLAG_PREFER) { - p->prio = - (swap_flags & SWAP_FLAG_PRIO_MASK)>>SWAP_FLAG_PRIO_SHIFT; - } else { - p->prio = --least_priority; - } - spin_unlock(&swap_lock); + + p = alloc_swap_info(); + if (IS_ERR(p)) + return PTR_ERR(p); + + INIT_WORK(&p->discard_work, swap_discard_work); + name = getname(specialfile); - error = PTR_ERR(name); if (IS_ERR(name)) { + error = PTR_ERR(name); name = NULL; - goto bad_swap_2; + goto bad_swap; } - swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0); - error = PTR_ERR(swap_file); + swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(swap_file)) { + error = PTR_ERR(swap_file); swap_file = NULL; - goto bad_swap_2; + goto bad_swap; } p->swap_file = swap_file; mapping = swap_file->f_mapping; - inode = mapping->host; - error = -EBUSY; for (i = 0; i < nr_swapfiles; i++) { - struct swap_info_struct *q = &swap_info[i]; + struct swap_info_struct *q = swap_info[i]; - if (i == type || !q->swap_file) + if (q == p || !q->swap_file) continue; - if (mapping == q->swap_file->f_mapping) - goto bad_swap; - } - - error = -EINVAL; - if (S_ISBLK(inode->i_mode)) { - bdev = I_BDEV(inode); - error = bd_claim(bdev, sys_swapon); - if (error < 0) { - bdev = NULL; - error = -EINVAL; - goto bad_swap; - } - p->old_block_size = block_size(bdev); - error = set_blocksize(bdev, PAGE_SIZE); - if (error < 0) - goto bad_swap; - p->bdev = bdev; - } else if (S_ISREG(inode->i_mode)) { - p->bdev = inode->i_sb->s_bdev; - mutex_lock(&inode->i_mutex); - did_down = 1; - if (IS_SWAPFILE(inode)) { + if (mapping == q->swap_file->f_mapping) { error = -EBUSY; goto bad_swap; } - } else { - goto bad_swap; } - swapfilesize = i_size_read(inode) >> PAGE_SHIFT; + 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; /* * Read the swap header. @@ -1562,157 +2419,137 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) error = PTR_ERR(page); goto bad_swap; } - kmap(page); - swap_header = page_address(page); + swap_header = kmap(page); - if (!memcmp("SWAP-SPACE",swap_header->magic.magic,10)) - swap_header_version = 1; - else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10)) - swap_header_version = 2; - else { - printk(KERN_ERR "Unable to find swap-space signature\n"); + maxpages = read_swap_header(p, swap_header, inode); + if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap; } - - switch (swap_header_version) { - case 1: - printk(KERN_ERR "version 0 swap is no longer supported. " - "Use mkswap -v1 %s\n", name); - error = -EINVAL; - goto bad_swap; - case 2: - /* Check the swap header's sub-version and the size of - the swap file and bad block lists */ - if (swap_header->info.version != 1) { - printk(KERN_WARNING - "Unable to handle swap header version %d\n", - swap_header->info.version); - error = -EINVAL; - goto bad_swap; - } - - p->lowest_bit = 1; - p->cluster_next = 1; + /* OK, set up the swap map and apply the bad block list */ + swap_map = vzalloc(maxpages); + if (!swap_map) { + error = -ENOMEM; + goto bad_swap; + } + if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { + p->flags |= SWP_SOLIDSTATE; /* - * 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 a 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. + * select a random position to start with to help wear leveling + * SSD */ - 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; - p->highest_bit = maxpages - 1; + p->cluster_next = 1 + (prandom_u32() % p->highest_bit); - error = -EINVAL; - if (!maxpages) - goto bad_swap; - if (swapfilesize && maxpages > swapfilesize) { - printk(KERN_WARNING - "Swap area shorter than signature indicates\n"); + cluster_info = vzalloc(DIV_ROUND_UP(maxpages, + SWAPFILE_CLUSTER) * sizeof(*cluster_info)); + if (!cluster_info) { + error = -ENOMEM; goto bad_swap; } - if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) - goto bad_swap; - if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) - goto bad_swap; - - /* OK, set up the swap map and apply the bad block list */ - if (!(p->swap_map = vmalloc(maxpages * sizeof(short)))) { + p->percpu_cluster = alloc_percpu(struct percpu_cluster); + if (!p->percpu_cluster) { error = -ENOMEM; goto bad_swap; } - - error = 0; - memset(p->swap_map, 0, maxpages * sizeof(short)); - for (i = 0; i < swap_header->info.nr_badpages; i++) { - int page_nr = swap_header->info.badpages[i]; - if (page_nr <= 0 || page_nr >= swap_header->info.last_page) - error = -EINVAL; - else - p->swap_map[page_nr] = SWAP_MAP_BAD; + for_each_possible_cpu(i) { + struct percpu_cluster *cluster; + cluster = per_cpu_ptr(p->percpu_cluster, i); + cluster_set_null(&cluster->index); } - nr_good_pages = swap_header->info.last_page - - swap_header->info.nr_badpages - - 1 /* header page */; - if (error) - goto bad_swap; } - if (nr_good_pages) { - p->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) { - error = nr_extents; - goto bad_swap; - } - nr_good_pages = p->pages; - } - if (!nr_good_pages) { - printk(KERN_WARNING "Empty swap-file\n"); - error = -EINVAL; + error = swap_cgroup_swapon(p->type, maxpages); + if (error) + goto bad_swap; + + 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; } + /* frontswap enabled? set up bit-per-page map for frontswap */ + if (frontswap_enabled) + frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long)); - mutex_lock(&swapon_mutex); - spin_lock(&swap_lock); - p->flags = SWP_ACTIVE; - nr_swap_pages += nr_good_pages; - total_swap_pages += nr_good_pages; - - printk(KERN_INFO "Adding %uk swap on %s. " - "Priority:%d extents:%d across:%lluk\n", - nr_good_pages<<(PAGE_SHIFT-10), name, p->prio, - nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10)); - - /* 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; + if (p->bdev &&(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); + + /* + * 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)) + pr_err("swapon: discard_swap(%p): %d\n", + p, err); } - prev = i; - } - p->next = i; - if (prev < 0) { - swap_list.head = swap_list.next = p - swap_info; - } else { - swap_info[prev].next = p - swap_info; } - spin_unlock(&swap_lock); + + mutex_lock(&swapon_mutex); + prio = -1; + if (swap_flags & SWAP_FLAG_PREFER) + prio = + (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; + enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); + + pr_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" : ""); + 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; bad_swap: - if (bdev) { - set_blocksize(bdev, p->old_block_size); - bd_release(bdev); + free_percpu(p->percpu_cluster); + p->percpu_cluster = 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); } destroy_swap_extents(p); -bad_swap_2: + swap_cgroup_swapoff(p->type); spin_lock(&swap_lock); - swap_map = p->swap_map; p->swap_file = NULL; - p->swap_map = NULL; p->flags = 0; - if (!(swap_flags & SWAP_FLAG_PREFER)) - ++least_priority; spin_unlock(&swap_lock); vfree(swap_map); - if (swap_file) + vfree(cluster_info); + if (swap_file) { + if (inode && S_ISREG(inode->i_mode)) { + mutex_unlock(&inode->i_mutex); + inode = NULL; + } filp_close(swap_file, NULL); + } out: if (page && !IS_ERR(page)) { kunmap(page); @@ -1720,27 +2557,24 @@ out: } if (name) putname(name); - if (did_down) { - if (!error) - inode->i_flags |= S_SWAPFILE; + if (inode && S_ISREG(inode->i_mode)) mutex_unlock(&inode->i_mutex); - } return error; } void si_swapinfo(struct sysinfo *val) { - unsigned int i; + unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); - for (i = 0; i < nr_swapfiles; i++) { - if (!(swap_info[i].flags & SWP_USED) || - (swap_info[i].flags & SWP_WRITEOK)) - continue; - nr_to_be_unused += swap_info[i].inuse_pages; + for (type = 0; type < nr_swapfiles; type++) { + struct swap_info_struct *si = swap_info[type]; + + if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) + nr_to_be_unused += si->inuse_pages; } - val->freeswap = nr_swap_pages + nr_to_be_unused; + val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } @@ -1748,99 +2582,360 @@ void si_swapinfo(struct sysinfo *val) /* * Verify that a swap entry is valid and increment its swap map count. * - * Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as - * "permanent", but will be reclaimed by the next swapoff. + * 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 */ -int swap_duplicate(swp_entry_t entry) +static int __swap_duplicate(swp_entry_t entry, unsigned char usage) { - struct swap_info_struct * p; + struct swap_info_struct *p; unsigned long offset, type; - int result = 0; + unsigned char count; + unsigned char has_cache; + int err = -EINVAL; - if (is_migration_entry(entry)) - return 1; + if (non_swap_entry(entry)) + goto out; type = swp_type(entry); if (type >= nr_swapfiles) goto bad_file; - p = type + swap_info; + p = swap_info[type]; offset = swp_offset(entry); - spin_lock(&swap_lock); - if (offset < p->max && p->swap_map[offset]) { - if (p->swap_map[offset] < SWAP_MAP_MAX - 1) { - p->swap_map[offset]++; - result = 1; - } else if (p->swap_map[offset] <= SWAP_MAP_MAX) { - if (swap_overflow++ < 5) - printk(KERN_WARNING "swap_dup: swap entry overflow\n"); - p->swap_map[offset] = SWAP_MAP_MAX; - result = 1; - } + spin_lock(&p->lock); + if (unlikely(offset >= p->max)) + goto unlock_out; + + count = p->swap_map[offset]; + + /* + * 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; } - spin_unlock(&swap_lock); + + has_cache = count & SWAP_HAS_CACHE; + count &= ~SWAP_HAS_CACHE; + err = 0; + + if (usage == SWAP_HAS_CACHE) { + + /* 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 */ + err = -ENOENT; + + } else if (count || has_cache) { + + 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)) + count = COUNT_CONTINUED; + else + err = -ENOMEM; + } else + err = -ENOENT; /* unused swap entry */ + + p->swap_map[offset] = count | has_cache; + +unlock_out: + spin_unlock(&p->lock); out: - return result; + return err; bad_file: - printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val); + pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val); goto out; } -struct swap_info_struct * -get_swap_info_struct(unsigned type) +/* + * 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) +{ + __swap_duplicate(entry, SWAP_MAP_SHMEM); +} + +/* + * Increase reference count of swap entry by 1. + * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required + * but could not be atomically allocated. Returns 0, just as if it succeeded, + * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which + * might occur if a page table entry has got corrupted. + */ +int swap_duplicate(swp_entry_t entry) +{ + int err = 0; + + while (!err && __swap_duplicate(entry, 1) == -ENOMEM) + err = add_swap_count_continuation(entry, GFP_ATOMIC); + return err; +} + +/* + * @entry: swap entry for which we allocate swap cache. + * + * 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. + * Note: return code is different from swap_duplicate(). + */ +int swapcache_prepare(swp_entry_t entry) +{ + return __swap_duplicate(entry, SWAP_HAS_CACHE); +} + +struct swap_info_struct *page_swap_info(struct page *page) { - return &swap_info[type]; + swp_entry_t swap = { .val = page_private(page) }; + BUG_ON(!PageSwapCache(page)); + return swap_info[swp_type(swap)]; } /* - * swap_lock prevents swap_map being freed. Don't grab an extra - * reference on the swaphandle, it doesn't matter if it becomes unused. + * out-of-line __page_file_ methods to avoid include hell. */ -int valid_swaphandles(swp_entry_t entry, unsigned long *offset) +struct address_space *__page_file_mapping(struct page *page) +{ + VM_BUG_ON_PAGE(!PageSwapCache(page), page); + return page_swap_info(page)->swap_file->f_mapping; +} +EXPORT_SYMBOL_GPL(__page_file_mapping); + +pgoff_t __page_file_index(struct page *page) +{ + swp_entry_t swap = { .val = page_private(page) }; + VM_BUG_ON_PAGE(!PageSwapCache(page), page); + return swp_offset(swap); +} +EXPORT_SYMBOL_GPL(__page_file_index); + +/* + * add_swap_count_continuation - called when a swap count is duplicated + * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's + * page of the original vmalloc'ed swap_map, to hold the continuation count + * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called + * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. + * + * These continuation pages are seldom referenced: the common paths all work + * on the original swap_map, only referring to a continuation page when the + * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. + * + * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding + * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) + * can be called after dropping locks. + */ +int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; - int our_page_cluster = page_cluster; - pgoff_t target, toff; - pgoff_t base, end; - int nr_pages = 0; + struct page *head; + struct page *page; + struct page *list_page; + pgoff_t offset; + unsigned char count; - if (!our_page_cluster) /* no readahead */ - return 0; + /* + * When debugging, it's easier to use __GFP_ZERO here; but it's better + * for latency not to zero a page while GFP_ATOMIC and holding locks. + */ + page = alloc_page(gfp_mask | __GFP_HIGHMEM); - si = &swap_info[swp_type(entry)]; - target = swp_offset(entry); - base = (target >> our_page_cluster) << our_page_cluster; - end = base + (1 << our_page_cluster); - if (!base) /* first page is swap header */ - base++; + si = swap_info_get(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. + */ + goto outer; + } - spin_lock(&swap_lock); - if (end > si->max) /* don't go beyond end of map */ - end = si->max; + offset = swp_offset(entry); + count = si->swap_map[offset] & ~SWAP_HAS_CACHE; - /* Count contiguous allocated slots above our target */ - for (toff = target; ++toff < end; nr_pages++) { - /* Don't read in free or bad pages */ - if (!si->swap_map[toff]) - break; - if (si->swap_map[toff] == SWAP_MAP_BAD) - break; + if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { + /* + * The higher the swap count, the more likely it is that tasks + * will race to add swap count continuation: we need to avoid + * over-provisioning. + */ + goto out; } - /* Count contiguous allocated slots below our target */ - for (toff = target; --toff >= base; nr_pages++) { - /* Don't read in free or bad pages */ - if (!si->swap_map[toff]) - break; - if (si->swap_map[toff] == SWAP_MAP_BAD) - break; + + if (!page) { + spin_unlock(&si->lock); + return -ENOMEM; } - spin_unlock(&swap_lock); /* - * Indicate starting offset, and return number of pages to get: - * if only 1, say 0, since there's then no readahead to be done. + * We are fortunate that although vmalloc_to_page uses pte_offset_map, + * no architecture is using highmem pages for kernel page tables: so it + * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps. */ - *offset = ++toff; - return nr_pages? ++nr_pages: 0; + head = vmalloc_to_page(si->swap_map + offset); + offset &= ~PAGE_MASK; + + /* + * Page allocation does not initialize the page's lru field, + * but it does always reset its private field. + */ + if (!page_private(head)) { + BUG_ON(count & COUNT_CONTINUED); + INIT_LIST_HEAD(&head->lru); + set_page_private(head, SWP_CONTINUED); + si->flags |= SWP_CONTINUED; + } + + list_for_each_entry(list_page, &head->lru, lru) { + unsigned char *map; + + /* + * If the previous map said no continuation, but we've found + * a continuation page, free our allocation and use this one. + */ + if (!(count & COUNT_CONTINUED)) + goto out; + + map = kmap_atomic(list_page) + offset; + count = *map; + kunmap_atomic(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; + } + + list_add_tail(&page->lru, &head->lru); + page = NULL; /* now it's attached, don't free it */ +out: + spin_unlock(&si->lock); +outer: + if (page) + __free_page(page); + return 0; +} + +/* + * swap_count_continued - when the original swap_map count is incremented + * from SWAP_MAP_MAX, check if there is already a continuation page to carry + * 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. + */ +static bool swap_count_continued(struct swap_info_struct *si, + pgoff_t offset, unsigned char count) +{ + struct page *head; + struct page *page; + unsigned char *map; + + head = vmalloc_to_page(si->swap_map + offset); + if (page_private(head) != SWP_CONTINUED) { + BUG_ON(count & COUNT_CONTINUED); + return false; /* need to add count continuation */ + } + + offset &= ~PAGE_MASK; + page = list_entry(head->lru.next, struct page, lru); + map = kmap_atomic(page) + offset; + + if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ + goto init_map; /* jump over SWAP_CONT_MAX checks */ + + if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ + /* + * 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); + 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); + if (page == head) + return false; /* add count continuation */ + map = kmap_atomic(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; + *map = COUNT_CONTINUED; + kunmap_atomic(map); + page = list_entry(page->lru.prev, struct page, lru); + } + return true; /* incremented */ + + } else { /* decrementing */ + /* + * Think of how you subtract 1 from 1000 + */ + BUG_ON(count != COUNT_CONTINUED); + while (*map == COUNT_CONTINUED) { + kunmap_atomic(map); + page = list_entry(page->lru.next, struct page, lru); + BUG_ON(page == head); + map = kmap_atomic(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; + *map = SWAP_CONT_MAX | count; + count = COUNT_CONTINUED; + kunmap_atomic(map); + page = list_entry(page->lru.prev, struct page, lru); + } + return count == COUNT_CONTINUED; + } +} + +/* + * free_swap_count_continuations - swapoff free all the continuation pages + * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. + */ +static void free_swap_count_continuations(struct swap_info_struct *si) +{ + pgoff_t offset; + + for (offset = 0; offset < si->max; offset += PAGE_SIZE) { + 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); + __free_page(page); + } + } + } } |