X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fswapfile.c;h=fa5f10b9c28b0b6366f742c10c72b91f03374a71;hb=73c34b6accc8427584f5d7db4d5acb230ed8c912;hp=4d11f9d84666fbc0186f18729f52eb830496bcdb;hpb=f577eb30afdc68233f25d4d82b04102129262365;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/swapfile.c b/mm/swapfile.c index 4d11f9d..fa5f10b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -5,7 +5,6 @@ * Swap reorganised 29.12.95, Stephen Tweedie */ -#include #include #include #include @@ -17,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -28,27 +28,83 @@ #include #include #include +#include #include #include #include +#include -DEFINE_SPINLOCK(swap_lock); -unsigned int nr_swapfiles; +static DEFINE_SPINLOCK(swap_lock); +static unsigned int nr_swapfiles; +long nr_swap_pages; 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}; +static struct swap_list_t swap_list = {-1, -1}; -static struct swap_info_struct swap_info[MAX_SWAPFILES]; +static struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); +/* For reference count accounting in swap_map */ +/* enum for swap_map[] handling. internal use only */ +enum { + SWAP_MAP = 0, /* ops for reference from swap users */ + SWAP_CACHE, /* ops for reference from swap cache */ +}; + +static inline int swap_count(unsigned short ent) +{ + return ent & SWAP_COUNT_MASK; +} + +static inline bool swap_has_cache(unsigned short ent) +{ + return !!(ent & SWAP_HAS_CACHE); +} + +static inline unsigned short encode_swapmap(int count, bool has_cache) +{ + unsigned short ret = count; + + if (has_cache) + return SWAP_HAS_CACHE | ret; + return ret; +} + +/* 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(&swapper_space, 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 @@ -63,7 +119,7 @@ void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) down_read(&swap_unplug_sem); entry.val = page_private(page); if (PageSwapCache(page)) { - struct block_device *bdev = swap_info[swp_type(entry)].bdev; + struct block_device *bdev = swap_info[swp_type(entry)]->bdev; struct backing_dev_info *bdi; /* @@ -82,15 +138,101 @@ void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) up_read(&swap_unplug_sem); } +/* + * swapon tell device that all the old swap contents can be discarded, + * to allow the swap device to optimize its wear-levelling. + */ +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, DISCARD_FL_BARRIER); + 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, DISCARD_FL_BARRIER); + if (err) + break; + + 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) +{ + struct swap_extent *se = si->curr_swap_extent; + int found_extent = 0; + + while (nr_pages) { + struct list_head *lh; + + if (se->start_page <= start_page && + start_page < se->start_page + se->nr_pages) { + pgoff_t offset = start_page - se->start_page; + sector_t start_block = se->start_block + offset; + sector_t nr_blocks = se->nr_pages - offset; + + if (nr_blocks > nr_pages) + nr_blocks = nr_pages; + start_page += nr_blocks; + nr_pages -= nr_blocks; + + if (!found_extent++) + si->curr_swap_extent = se; + + start_block <<= PAGE_SHIFT - 9; + nr_blocks <<= PAGE_SHIFT - 9; + if (blkdev_issue_discard(si->bdev, start_block, + nr_blocks, GFP_NOIO, DISCARD_FL_BARRIER)) + break; + } + + lh = se->list.next; + se = list_entry(lh, struct swap_extent, list); + } +} + +static int wait_for_discard(void *word) +{ + schedule(); + return 0; +} + #define SWAPFILE_CLUSTER 256 #define LATENCY_LIMIT 256 -static inline unsigned long scan_swap_map(struct swap_info_struct *si) +static inline unsigned long scan_swap_map(struct swap_info_struct *si, + int cache) { - unsigned long offset, last_in_cluster; + unsigned long offset; + unsigned long scan_base; + unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; + int found_free_cluster = 0; - /* + /* * 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 +240,42 @@ 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; + scan_base = offset = si->cluster_next; + + if (unlikely(!si->cluster_nr--)) { + if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { + si->cluster_nr = SWAPFILE_CLUSTER - 1; + goto checks; + } + if (si->flags & SWP_DISCARDABLE) { + /* + * Start range check on racing allocations, in case + * they overlap the cluster we eventually decide on + * (we scan without swap_lock to allow preemption). + * It's hardly conceivable that cluster_nr could be + * wrapped during our scan, but don't depend on it. + */ + if (si->lowest_alloc) + goto checks; + si->lowest_alloc = si->max; + si->highest_alloc = 0; + } spin_unlock(&swap_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. + * But if seek is cheap, search from our current position, so + * that swap is allocated from all over the partition: if the + * Flash Translation Layer only remaps within limited zones, + * we don't want to wear out the first zone too quickly. + */ + if (!(si->flags & SWP_SOLIDSTATE)) + scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ @@ -116,56 +284,171 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si) 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; + offset -= SWAPFILE_CLUSTER - 1; + si->cluster_next = offset; + si->cluster_nr = SWAPFILE_CLUSTER - 1; + found_free_cluster = 1; + goto checks; + } + if (unlikely(--latency_ration < 0)) { + cond_resched(); + latency_ration = LATENCY_LIMIT; + } + } + + offset = si->lowest_bit; + last_in_cluster = offset + SWAPFILE_CLUSTER - 1; + + /* Locate the first empty (unaligned) cluster */ + for (; last_in_cluster < scan_base; offset++) { + if (si->swap_map[offset]) + last_in_cluster = offset + SWAPFILE_CLUSTER; + else if (offset == last_in_cluster) { + spin_lock(&swap_lock); + offset -= SWAPFILE_CLUSTER - 1; + si->cluster_next = offset; + si->cluster_nr = SWAPFILE_CLUSTER - 1; + found_free_cluster = 1; + goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } + + offset = scan_base; spin_lock(&swap_lock); - goto lowest; + si->cluster_nr = SWAPFILE_CLUSTER - 1; + si->lowest_alloc = 0; } - 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->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; + 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(&swap_lock); + swap_was_freed = __try_to_reclaim_swap(si, offset); + spin_lock(&swap_lock); + /* entry was freed successfully, try to use this again */ + if (swap_was_freed) + goto checks; + goto scan; /* check next one */ + } + + 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; + } + if (cache == SWAP_CACHE) /* at usual swap-out via vmscan.c */ + si->swap_map[offset] = encode_swapmap(0, true); + else /* at suspend */ + si->swap_map[offset] = encode_swapmap(1, false); + si->cluster_next = offset + 1; + si->flags -= SWP_SCANNING; + + if (si->lowest_alloc) { + /* + * Only set when SWP_DISCARDABLE, and there's a scan + * for a free cluster in progress or just completed. + */ + if (found_free_cluster) { + /* + * To optimize wear-levelling, discard the + * old data of the cluster, taking care not to + * discard any of its pages that have already + * been allocated by racing tasks (offset has + * already stepped over any at the beginning). + */ + if (offset < si->highest_alloc && + si->lowest_alloc <= last_in_cluster) + last_in_cluster = si->lowest_alloc - 1; + si->flags |= SWP_DISCARDING; + spin_unlock(&swap_lock); + + if (offset < last_in_cluster) + discard_swap_cluster(si, offset, + last_in_cluster - offset + 1); + + spin_lock(&swap_lock); + si->lowest_alloc = 0; + si->flags &= ~SWP_DISCARDING; + + smp_mb(); /* wake_up_bit advises this */ + wake_up_bit(&si->flags, ilog2(SWP_DISCARDING)); + + } else if (si->flags & SWP_DISCARDING) { + /* + * Delay using pages allocated by racing tasks + * until the whole discard has been issued. We + * could defer that delay until swap_writepage, + * but it's easier to keep this self-contained. + */ + spin_unlock(&swap_lock); + wait_on_bit(&si->flags, ilog2(SWP_DISCARDING), + wait_for_discard, TASK_UNINTERRUPTIBLE); + spin_lock(&swap_lock); + } else { + /* + * Note pages allocated by racing tasks while + * scan for a free cluster is in progress, so + * that its final discard can exclude them. + */ + if (offset < si->lowest_alloc) + si->lowest_alloc = offset; + if (offset > si->highest_alloc) + si->highest_alloc = offset; } - si->swap_map[offset] = 1; - si->cluster_next = offset + 1; - si->flags -= SWP_SCANNING; - return offset; } + return offset; +scan: spin_unlock(&swap_lock); while (++offset <= si->highest_bit) { if (!si->swap_map[offset]) { spin_lock(&swap_lock); goto checks; } + if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + spin_lock(&swap_lock); + goto checks; + } + if (unlikely(--latency_ration < 0)) { + cond_resched(); + latency_ration = LATENCY_LIMIT; + } + } + offset = si->lowest_bit; + while (++offset < scan_base) { + if (!si->swap_map[offset]) { + spin_lock(&swap_lock); + goto checks; + } + if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + spin_lock(&swap_lock); + goto checks; + } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } spin_lock(&swap_lock); - goto lowest; no_page: si->flags -= SWP_SCANNING; @@ -185,10 +468,10 @@ swp_entry_t get_swap_page(void) nr_swap_pages--; for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { - si = swap_info + type; + si = swap_info[type]; next = si->next; if (next < 0 || - (!wrapped && si->prio != swap_info[next].prio)) { + (!wrapped && si->prio != swap_info[next]->prio)) { next = swap_list.head; wrapped++; } @@ -199,7 +482,8 @@ swp_entry_t get_swap_page(void) continue; swap_list.next = next; - offset = scan_swap_map(si); + /* This is called for allocating swap entry for cache */ + offset = scan_swap_map(si, SWAP_CACHE); if (offset) { spin_unlock(&swap_lock); return swp_entry(type, offset); @@ -213,16 +497,18 @@ noswap: return (swp_entry_t) {0}; } +/* The only caller of this function is now susupend 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) { + si = swap_info[type]; + if (si && (si->flags & SWP_WRITEOK)) { nr_swap_pages--; - offset = scan_swap_map(si); + /* This is called for allocating swap entry, not cache */ + offset = scan_swap_map(si, SWAP_MAP); if (offset) { spin_unlock(&swap_lock); return swp_entry(type, offset); @@ -233,9 +519,9 @@ swp_entry_t get_swap_page_of_type(int type) 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 +529,7 @@ 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); @@ -267,26 +553,43 @@ bad_nofile: printk(KERN_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) +static int swap_entry_free(struct swap_info_struct *p, + swp_entry_t ent, int cache) { - 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--; + unsigned long offset = swp_offset(ent); + int count = swap_count(p->swap_map[offset]); + bool has_cache; + + has_cache = swap_has_cache(p->swap_map[offset]); + + if (cache == SWAP_MAP) { /* dropping usage count of swap */ + if (count < SWAP_MAP_MAX) { + count--; + p->swap_map[offset] = encode_swapmap(count, has_cache); } + } else { /* dropping swap cache flag */ + VM_BUG_ON(!has_cache); + p->swap_map[offset] = encode_swapmap(count, false); + } + /* return code. */ + count = p->swap_map[offset]; + /* free if no reference */ + if (!count) { + if (offset < p->lowest_bit) + p->lowest_bit = offset; + if (offset > p->highest_bit) + p->highest_bit = offset; + if (swap_list.next >= 0 && + p->prio > swap_info[swap_list.next]->prio) + swap_list.next = p->type; + nr_swap_pages++; + p->inuse_pages--; + } + if (!swap_count(count)) + mem_cgroup_uncharge_swap(ent); return count; } @@ -296,11 +599,34 @@ static int swap_entry_free(struct swap_info_struct *p, unsigned long offset) */ 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)); + swap_entry_free(p, entry, SWAP_MAP); + spin_unlock(&swap_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; + int ret; + + p = swap_info_get(entry); + if (p) { + ret = swap_entry_free(p, entry, SWAP_CACHE); + if (page) { + bool swapout; + if (ret) + swapout = true; /* the end of swap out */ + else + swapout = false; /* no more swap users! */ + mem_cgroup_uncharge_swapcache(page, entry, swapout); + } spin_unlock(&swap_lock); } } @@ -317,137 +643,160 @@ 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; + count = swap_count(p->swap_map[swp_offset(entry)]); spin_unlock(&swap_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(!PageLocked(page)); count = page_mapcount(page); - if (count <= 1 && PageSwapCache(page)) + if (count <= 1 && PageSwapCache(page)) { count += page_swapcount(page); + 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(!PageLocked(page)); if (!PageSwapCache(page)) return 0; if (PageWriteback(page)) return 0; - if (page_count(page) != 2) /* 2: us + cache */ - return 0; - - entry.val = page_private(page); - p = swap_info_get(entry); - if (!p) + if (page_swapcount(page)) 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 (non_swap_entry(entry)) + return 1; + p = swap_info_get(entry); if (p) { - if (swap_entry_free(p, swp_offset(entry)) == 1) - page = find_trylock_page(&swapper_space, entry.val); + if (swap_entry_free(p, entry, SWAP_MAP) == SWAP_HAS_CACHE) { + page = find_get_page(&swapper_space, entry.val); + if (page && !trylock_page(page)) { + page_cache_release(page); + page = NULL; + } + } spin_unlock(&swap_lock); } if (page) { - int one_user; - - BUG_ON(PagePrivate(page)); - page_cache_get(page); - one_user = (page_count(page) == 2); - /* Only cache user (+us), or swap space full? Free it! */ - if (!PageWriteback(page) && (one_user || vm_swap_full())) { + /* + * Not mapped elsewhere, or swap space full? Free it! + * Also recheck PageSwapCache now page is locked (above). + */ + if (PageSwapCache(page) && !PageWriteback(page) && + (!page_mapped(page) || vm_swap_full())) { delete_from_swap_cache(page); SetPageDirty(page); } unlock_page(page); page_cache_release(page); } + return p != NULL; } -#ifdef CONFIG_SOFTWARE_SUSPEND +#ifdef CONFIG_HIBERNATION /* - * Find the swap type that corresponds to given device (if any) + * Find the swap type that corresponds to given device (if any). + * + * @offset - number of the PAGE_SIZE-sized block of the device, starting + * from 0, in which the swap header is expected to be located. * - * This is needed for software suspend and is done in such a way that inode - * aliasing is allowed. + * This is needed for the suspend to disk (aka swsusp). */ -int swap_type_of(dev_t device) +int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) { - int i; + struct block_device *bdev = NULL; + int type; + + if (device) + bdev = bdget(device); - if (!device) - return -EINVAL; spin_lock(&swap_lock); - for (i = 0; i < nr_swapfiles; i++) { - struct inode *inode; + for (type = 0; type < nr_swapfiles; type++) { + struct swap_info_struct *sis = swap_info[type]; - if (!(swap_info[i].flags & SWP_WRITEOK)) + if (!(sis->flags & SWP_WRITEOK)) continue; - inode = swap_info->swap_file->f_dentry->d_inode; - if (S_ISBLK(inode->i_mode) && - device == MKDEV(imajor(inode), iminor(inode))) { + + if (!bdev) { + if (bdev_p) + *bdev_p = bdgrab(sis->bdev); + spin_unlock(&swap_lock); - return i; + return type; + } + if (bdev == sis->bdev) { + struct swap_extent *se = &sis->first_swap_extent; + + if (se->start_block == offset) { + if (bdev_p) + *bdev_p = bdgrab(sis->bdev); + + spin_unlock(&swap_lock); + bdput(bdev); + return type; + } } } spin_unlock(&swap_lock); + if (bdev) + bdput(bdev); + return -ENODEV; } /* + * 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_page(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) * @@ -457,38 +806,63 @@ 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]; + + 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(&swap_lock); return n; } -#endif +#endif /* CONFIG_HIBERNATION */ /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ -static void unuse_pte(struct vm_area_struct *vma, pte_t *pte, +static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct page *page) { + struct mem_cgroup *ptr = NULL; + spinlock_t *ptl; + pte_t *pte; + int ret = 1; + + if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, GFP_KERNEL, &ptr)) { + 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_cancel_charge_swapin(ptr); + ret = 0; + goto out; + } + inc_mm_counter(vma->vm_mm, anon_rss); 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); + mem_cgroup_commit_charge_swapin(page, ptr); swap_free(entry); /* * Move the page to the active list so it is not * immediately swapped out again after swapon. */ activate_page(page); +out: + pte_unmap_unlock(pte, ptl); +out_nolock: + return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, @@ -497,23 +871,34 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, { pte_t swp_pte = swp_entry_to_pte(entry); pte_t *pte; - spinlock_t *ptl; - int found = 0; + int ret = 0; - pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + /* + * We don't actually need pte lock while scanning for swp_pte: since + * we hold page lock and mmap_sem, swp_pte cannot be inserted into the + * page table while we're scanning; though it could get zapped, and on + * some architectures (e.g. x86_32 with PAE) we might catch a glimpse + * of unmatched parts which look like swp_pte, so unuse_pte must + * recheck under pte lock. Scanning without pte lock lets it be + * preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE. + */ + pte = pte_offset_map(pmd, addr); do { /* * swapoff spends a _lot_ of time in this loop! * Test inline before going to call unuse_pte. */ if (unlikely(pte_same(*pte, swp_pte))) { - unuse_pte(vma, pte++, addr, entry, page); - found = 1; - break; + pte_unmap(pte); + ret = unuse_pte(vma, pmd, addr, entry, page); + if (ret) + goto out; + pte = pte_offset_map(pmd, addr); } } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap_unlock(pte - 1, ptl); - return found; + pte_unmap(pte - 1); +out: + return ret; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, @@ -522,14 +907,16 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, { pmd_t *pmd; unsigned long next; + int ret; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; - if (unuse_pte_range(vma, pmd, addr, next, entry, page)) - return 1; + ret = unuse_pte_range(vma, pmd, addr, next, entry, page); + if (ret) + return ret; } while (pmd++, addr = next, addr != end); return 0; } @@ -540,14 +927,16 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, { pud_t *pud; unsigned long next; + int ret; pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - if (unuse_pmd_range(vma, pud, addr, next, entry, page)) - return 1; + ret = unuse_pmd_range(vma, pud, addr, next, entry, page); + if (ret) + return ret; } while (pud++, addr = next, addr != end); return 0; } @@ -557,6 +946,7 @@ static int unuse_vma(struct vm_area_struct *vma, { pgd_t *pgd; unsigned long addr, end, next; + int ret; if (page->mapping) { addr = page_address_in_vma(page, vma); @@ -574,8 +964,9 @@ static int unuse_vma(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - if (unuse_pud_range(vma, pgd, addr, next, entry, page)) - return 1; + ret = unuse_pud_range(vma, pgd, addr, next, entry, page); + if (ret) + return ret; } while (pgd++, addr = next, addr != end); return 0; } @@ -584,11 +975,12 @@ static int unuse_mm(struct mm_struct *mm, swp_entry_t entry, struct page *page) { struct vm_area_struct *vma; + int ret = 0; 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); @@ -596,26 +988,13 @@ static int unuse_mm(struct mm_struct *mm, lock_page(page); } for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (vma->anon_vma && unuse_vma(vma, entry, page)) + if (vma->anon_vma && (ret = unuse_vma(vma, entry, page))) break; } up_read(&mm->mmap_sem); - /* - * Currently unuse_mm cannot fail, but leave error handling - * at call sites for now, since we change it from time to time. - */ - return 0; + return (ret < 0)? ret: 0; } -#ifdef CONFIG_MIGRATION -int remove_vma_swap(struct vm_area_struct *vma, struct page *page) -{ - swp_entry_t entry = { .val = page_private(page) }; - - return unuse_vma(vma, entry, page); -} -#endif - /* * Scan swap_map from current position to next entry still in use. * Recycle to start on reaching the end, returning 0 when empty. @@ -648,7 +1027,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, i = 1; } count = si->swap_map[i]; - if (count && count != SWAP_MAP_BAD) + if (count && swap_count(count) != SWAP_MAP_BAD) break; } return i; @@ -661,7 +1040,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, */ static int try_to_unuse(unsigned int type) { - 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; @@ -701,15 +1080,15 @@ static int try_to_unuse(unsigned int type) 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); -again: - page = read_swap_cache_async(entry, NULL, 0); + page = read_swap_cache_async(entry, + GFP_HIGHUSER_MOVABLE, NULL, 0); if (!page) { /* * Either swap_duplicate() failed because entry @@ -743,12 +1122,6 @@ again: wait_on_page_locked(page); wait_on_page_writeback(page); lock_page(page); - if (!PageSwapCache(page)) { - /* Page migration has occured */ - unlock_page(page); - page_cache_release(page); - goto again; - } wait_on_page_writeback(page); /* @@ -758,13 +1131,13 @@ again: */ shmem = 0; swcount = *swap_map; - if (swcount > 1) { + if (swap_count(swcount)) { if (start_mm == &init_mm) shmem = shmem_unuse(entry, page); else retval = unuse_mm(start_mm, entry, page); } - if (*swap_map > 1) { + 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; @@ -774,13 +1147,11 @@ again: atomic_inc(&new_start_mm->mm_users); atomic_inc(&prev_mm->mm_users); spin_lock(&mmlist_lock); - while (*swap_map > 1 && !retval && + while (swap_count(*swap_map) && !retval && !shmem && (p = p->next) != &start_mm->mmlist) { mm = list_entry(p, struct mm_struct, mmlist); - if (atomic_inc_return(&mm->mm_users) == 1) { - atomic_dec(&mm->mm_users); + if (!atomic_inc_not_zero(&mm->mm_users)) continue; - } spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; @@ -788,13 +1159,14 @@ again: cond_resched(); swcount = *swap_map; - if (swcount <= 1) + if (!swap_count(swcount)) /* any usage ? */ ; else if (mm == &init_mm) { set_start_mm = 1; shmem = shmem_unuse(entry, page); } else retval = unuse_mm(mm, entry, page); + if (set_start_mm && *swap_map < swcount) { mmput(new_start_mm); atomic_inc(&mm->mm_users); @@ -808,6 +1180,13 @@ again: 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); @@ -815,21 +1194,25 @@ again: } /* - * 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. - * + * How could swap count reach 0x7ffe ? + * 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.(if occur, unsigned + * short is too small....) * 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) { + /* We might release the lock_page() in unuse_mm(). */ + if (!PageSwapCache(page) || page_private(page) != entry.val) + goto retry; + + if (swap_count(*swap_map) == SWAP_MAP_MAX) { spin_lock(&swap_lock); - *swap_map = 1; + *swap_map = encode_swapmap(0, true); spin_unlock(&swap_lock); reset_overflow = 1; } @@ -846,14 +1229,9 @@ again: * 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. - * - * Note shmem_unuse already deleted a swappage from - * the swap cache, unless the move to filepage failed: - * in which case it left swappage in cache, lowered its - * swap count to pass quickly through the loops above, - * and now we must reincrement count to try again later. */ - 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, }; @@ -862,19 +1240,25 @@ again: lock_page(page); wait_on_page_writeback(page); } - if (PageSwapCache(page)) { - if (shmem) - swap_duplicate(entry); - else - delete_from_swap_cache(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); /* * So we could skip searching mms once swap count went * to 1, we did not mark any present ptes as dirty: must - * mark page dirty so shrink_list will preserve it. + * mark page dirty so shrink_page_list will preserve it. */ SetPageDirty(page); +retry: unlock_page(page); page_cache_release(page); @@ -902,10 +1286,10 @@ again: 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) @@ -915,12 +1299,22 @@ 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 `offset'. 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) +sector_t map_swap_page(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; @@ -930,8 +1324,6 @@ 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 */ @@ -943,10 +1335,10 @@ sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset) */ 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); @@ -967,8 +1359,15 @@ 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) { @@ -988,7 +1387,7 @@ 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; } @@ -1040,7 +1439,7 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; - goto done; + goto out; } blkbits = inode->i_blkbits; @@ -1111,48 +1510,25 @@ reprobe: 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; +out: + return ret; bad_bmap: printk(KERN_ERR "swapon: swapfile has holes\n"); ret = -EINVAL; -out: - return ret; -} - -#if 0 /* We don't need this yet */ -#include -int page_queue_congested(struct page *page) -{ - struct backing_dev_info *bdi; - - BUG_ON(!PageLocked(page)); /* It pins the swap_info_struct */ - - if (PageSwapCache(page)) { - swp_entry_t entry = { .val = page_private(page) }; - struct swap_info_struct *sis; - - 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); + goto out; } -#endif -asmlinkage long sys_swapoff(const char __user * specialfile) +SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { - struct swap_info_struct * p = NULL; + struct swap_info_struct *p = NULL; unsigned short *swap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; - char * pathname; + char *pathname; int i, type, prev; int err; - + if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1170,9 +1546,9 @@ asmlinkage long sys_swapoff(const char __user * specialfile) 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) { + for (type = swap_list.head; type >= 0; type = swap_info[type]->next) { + p = swap_info[type]; + if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) break; } @@ -1190,35 +1566,44 @@ asmlinkage long sys_swapoff(const char __user * specialfile) spin_unlock(&swap_lock); goto out_dput; } - if (prev < 0) { + if (prev < 0) swap_list.head = p->next; - } else { - swap_info[prev].next = 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; } + if (p->prio < 0) { + for (i = p->next; i >= 0; i = swap_info[i]->next) + swap_info[i]->prio = p->prio--; + least_priority++; + } nr_swap_pages -= p->pages; total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&swap_lock); - current->flags |= PF_SWAPOFF; + current->flags |= PF_OOM_ORIGIN; err = try_to_unuse(type); - current->flags &= ~PF_SWAPOFF; + current->flags &= ~PF_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) + if (p->prio < 0) + p->prio = --least_priority; + prev = -1; + for (i = swap_list.head; i >= 0; i = swap_info[i]->next) { + if (p->prio >= swap_info[i]->prio) break; + prev = i; + } p->next = i; if (prev < 0) - swap_list.head = swap_list.next = p - swap_info; + swap_list.head = swap_list.next = type; else - swap_info[prev].next = p - swap_info; + swap_info[prev]->next = type; nr_swap_pages += p->pages; total_swap_pages += p->pages; p->flags |= SWP_WRITEOK; @@ -1252,6 +1637,9 @@ asmlinkage long sys_swapoff(const char __user * specialfile) spin_unlock(&swap_lock); mutex_unlock(&swapon_mutex); vfree(swap_map); + /* Destroy swap account informatin */ + swap_cgroup_swapoff(type); + inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); @@ -1275,17 +1663,22 @@ out: /* 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); - for (i = 0; i < nr_swapfiles; i++, ptr++) { - if (!(ptr->flags & SWP_USED) || !ptr->swap_map) + if (!l) + return SEQ_START_TOKEN; + + for (type = 0; type < nr_swapfiles; type++) { + smp_rmb(); /* read nr_swapfiles before swap_info[type] */ + si = swap_info[type]; + if (!(si->flags & SWP_USED) || !si->swap_map) continue; - if (!l--) - return ptr; + if (!--l) + return si; } return NULL; @@ -1293,14 +1686,21 @@ 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 = v; - struct swap_info_struct *endptr = swap_info + nr_swapfiles; - - for (++ptr; ptr < endptr; ptr++) { - if (!(ptr->flags & SWP_USED) || !ptr->swap_map) + struct swap_info_struct *si = v; + int type; + + if (v == SEQ_START_TOKEN) + 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; @@ -1313,26 +1713,28 @@ 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 (v == swap_info) - seq_puts(swap, "Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); + if (si == SEQ_START_TOKEN) { + seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); + return 0; + } - file = ptr->swap_file; - len = seq_path(swap, file->f_vfsmnt, file->f_dentry, " \t\n\\"); + 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_dentry->d_inode->i_mode) ? + len < 40 ? 40 - len : 1, " ", + S_ISBLK(file->f_path.dentry->d_inode->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; } -static struct seq_operations swaps_op = { +static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, @@ -1344,7 +1746,7 @@ static int swaps_open(struct inode *inode, struct file *file) return seq_open(file, &swaps_op); } -static struct file_operations proc_swaps_operations = { +static const struct file_operations proc_swaps_operations = { .open = swaps_open, .read = seq_read, .llseek = seq_lseek, @@ -1353,24 +1755,29 @@ static struct file_operations proc_swaps_operations = { 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 + /* * Written 01/25/92 by Simmule Turner, heavily changed by Linus. * * The swapon system call */ -asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) +SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { - struct swap_info_struct * p; + struct swap_info_struct *p; char *name = NULL; struct block_device *bdev = NULL; struct file *swap_file = NULL; @@ -1378,62 +1785,58 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) unsigned int type; int i, prev; 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; sector_t span; unsigned long maxpages = 1; - int swapfilesize; - unsigned short *swap_map; + unsigned long swapfilepages; + unsigned short *swap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; int did_down = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + spin_lock(&swap_lock); - p = swap_info; - for (type = 0 ; type < nr_swapfiles ; type++,p++) - if (!(p->flags & SWP_USED)) + for (type = 0; type < nr_swapfiles; type++) { + if (!(swap_info[type]->flags & SWP_USED)) break; + } error = -EPERM; - /* - * Test if adding another swap device is possible. There are - * two limiting factors: 1) the number of bits for the swap - * type swp_entry_t definition and 2) the number of bits for - * the swap type in the swap ptes as defined by the different - * architectures. To honor both limitations a swap entry - * with swap offset 0 and swap type ~0UL is created, encoded - * to a swap pte, decoded to a swp_entry_t again and finally - * the swap type part is extracted. This will mask all bits - * from the initial ~0UL that can't be encoded in either the - * swp_entry_t or the architecture definition of a swap pte. - */ - if (type > swp_type(pte_to_swp_entry(swp_entry_to_pte(swp_entry(~0UL,0))))) { + if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); + kfree(p); 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; + 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 { - p->prio = --least_priority; + 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); + p->flags = SWP_USED; + p->next = -1; spin_unlock(&swap_lock); + name = getname(specialfile); error = PTR_ERR(name); if (IS_ERR(name)) { @@ -1453,7 +1856,7 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) 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) continue; @@ -1487,7 +1890,7 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) goto bad_swap; } - swapfilesize = i_size_read(inode) >> PAGE_SHIFT; + swapfilepages = i_size_read(inode) >> PAGE_SHIFT; /* * Read the swap header. @@ -1496,105 +1899,100 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) error = -EINVAL; goto bad_swap; } - page = read_cache_page(mapping, 0, - (filler_t *)mapping->a_ops->readpage, swap_file); + page = read_mapping_page(mapping, 0, swap_file); if (IS_ERR(page)) { error = PTR_ERR(page); goto bad_swap; } - wait_on_page_locked(page); - if (!PageUptodate(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 { + if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { printk(KERN_ERR "Unable to find swap-space signature\n"); 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); + + /* 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) { + printk(KERN_WARNING + "Unable to handle swap header version %d\n", + swap_header->info.version); 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; + 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 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. - */ - 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; + /* + * 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. + */ + 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; - error = -EINVAL; - if (!maxpages) - 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; + error = -EINVAL; + if (!maxpages) + goto bad_swap; + if (swapfilepages && maxpages > swapfilepages) { + printk(KERN_WARNING + "Swap area shorter than signature indicates\n"); + 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)))) { - error = -ENOMEM; - goto bad_swap; - } + /* OK, set up the swap map and apply the bad block list */ + swap_map = vmalloc(maxpages * sizeof(short)); + if (!swap_map) { + 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; - } - nr_good_pages = swap_header->info.last_page - - swap_header->info.nr_badpages - - 1 /* header page */; - if (error) + memset(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; goto bad_swap; + } + swap_map[page_nr] = SWAP_MAP_BAD; } - if (swapfilesize && maxpages > swapfilesize) { - printk(KERN_WARNING - "Swap area shorter than signature indicates\n"); - error = -EINVAL; + error = swap_cgroup_swapon(type, maxpages); + if (error) goto bad_swap; - } + + nr_good_pages = swap_header->info.last_page - + swap_header->info.nr_badpages - + 1 /* header page */; + if (nr_good_pages) { - p->swap_map[0] = SWAP_MAP_BAD; + swap_map[0] = SWAP_MAP_BAD; p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, &span); @@ -1610,31 +2008,46 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) goto bad_swap; } + if (p->bdev) { + if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { + p->flags |= SWP_SOLIDSTATE; + p->cluster_next = 1 + (random32() % p->highest_bit); + } + if (discard_swap(p) == 0) + p->flags |= SWP_DISCARDABLE; + } + mutex_lock(&swapon_mutex); spin_lock(&swap_lock); - p->flags = SWP_ACTIVE; + if (swap_flags & SWAP_FLAG_PREFER) + p->prio = + (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; + else + p->prio = --least_priority; + p->swap_map = swap_map; + p->flags |= SWP_WRITEOK; 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", + "Priority:%d extents:%d across:%lluk %s%s\n", nr_good_pages<<(PAGE_SHIFT-10), name, p->prio, - nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10)); + nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), + (p->flags & SWP_SOLIDSTATE) ? "SS" : "", + (p->flags & SWP_DISCARDABLE) ? "D" : ""); /* 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) { + for (i = swap_list.head; i >= 0; i = swap_info[i]->next) { + if (p->prio >= swap_info[i]->prio) break; - } prev = i; } p->next = i; - if (prev < 0) { - swap_list.head = swap_list.next = p - swap_info; - } else { - swap_info[prev].next = p - swap_info; - } + if (prev < 0) + swap_list.head = swap_list.next = type; + else + swap_info[prev]->next = type; spin_unlock(&swap_lock); mutex_unlock(&swapon_mutex); error = 0; @@ -1645,14 +2058,11 @@ bad_swap: bd_release(bdev); } destroy_swap_extents(p); + swap_cgroup_swapoff(type); bad_swap_2: 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) @@ -1674,15 +2084,15 @@ out: 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->totalswap = total_swap_pages + nr_to_be_unused; @@ -1694,31 +2104,65 @@ void si_swapinfo(struct sysinfo *val) * * 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 */ -int swap_duplicate(swp_entry_t entry) +static int __swap_duplicate(swp_entry_t entry, bool cache) { - struct swap_info_struct * p; + struct swap_info_struct *p; unsigned long offset, type; - int result = 0; + int result = -EINVAL; + int count; + bool has_cache; + + if (non_swap_entry(entry)) + return -EINVAL; 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 (unlikely(offset >= p->max)) + goto unlock_out; + + count = swap_count(p->swap_map[offset]); + has_cache = swap_has_cache(p->swap_map[offset]); + + if (cache == SWAP_CACHE) { /* called for swapcache/swapin-readahead */ + + /* set SWAP_HAS_CACHE if there is no cache and entry is used */ + if (!has_cache && count) { + p->swap_map[offset] = encode_swapmap(count, true); + result = 0; + } else if (has_cache) /* someone added cache */ + result = -EEXIST; + else if (!count) /* no users */ + result = -ENOENT; + + } else if (count || has_cache) { + if (count < SWAP_MAP_MAX - 1) { + p->swap_map[offset] = encode_swapmap(count + 1, + has_cache); + result = 0; + } else if (count <= 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; + printk(KERN_WARNING + "swap_dup: swap entry overflow\n"); + p->swap_map[offset] = encode_swapmap(SWAP_MAP_MAX, + has_cache); + result = 0; } - } + } else + result = -ENOENT; /* unused swap entry */ +unlock_out: spin_unlock(&swap_lock); out: return result; @@ -1727,11 +2171,25 @@ bad_file: printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val); goto out; } +/* + * increase reference count of swap entry by 1. + */ +void swap_duplicate(swp_entry_t entry) +{ + __swap_duplicate(entry, SWAP_MAP); +} -struct swap_info_struct * -get_swap_info_struct(unsigned type) +/* + * @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_info[type]; + return __swap_duplicate(entry, SWAP_CACHE); } /* @@ -1740,30 +2198,48 @@ get_swap_info_struct(unsigned type) */ int valid_swaphandles(swp_entry_t entry, unsigned long *offset) { - int ret = 0, i = 1 << page_cluster; - unsigned long toff; - struct swap_info_struct *swapdev = swp_type(entry) + swap_info; + struct swap_info_struct *si; + int our_page_cluster = page_cluster; + pgoff_t target, toff; + pgoff_t base, end; + int nr_pages = 0; - if (!page_cluster) /* no readahead */ + if (!our_page_cluster) /* no readahead */ return 0; - toff = (swp_offset(entry) >> page_cluster) << page_cluster; - if (!toff) /* first page is swap header */ - toff++, i--; - *offset = toff; + + 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++; spin_lock(&swap_lock); - do { - /* Don't read-ahead past the end of the swap area */ - if (toff >= swapdev->max) + if (end > si->max) /* don't go beyond end of map */ + end = si->max; + + /* 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 (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD) break; + } + /* Count contiguous allocated slots below our target */ + for (toff = target; --toff >= base; nr_pages++) { /* Don't read in free or bad pages */ - if (!swapdev->swap_map[toff]) + if (!si->swap_map[toff]) break; - if (swapdev->swap_map[toff] == SWAP_MAP_BAD) + if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD) break; - toff++; - ret++; - } while (--i); + } spin_unlock(&swap_lock); - return ret; + + /* + * Indicate starting offset, and return number of pages to get: + * if only 1, say 0, since there's then no readahead to be done. + */ + *offset = ++toff; + return nr_pages? ++nr_pages: 0; }