X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fswapfile.c;h=312fafe0ab6ed4815ac02da3f712aca18bacbbad;hb=03fb3d2af96c2783c3a5bc03f3d984cf422f0e69;hp=73521d39e9850f93fc1248651cd9ca66fae827b0;hpb=11d31886dbcb61039ed3789e583d21c6e70960fd;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/swapfile.c b/mm/swapfile.c index 73521d3..312fafe 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 @@ -25,45 +25,47 @@ #include #include #include +#include +#include #include +#include #include #include #include +#include -DEFINE_SPINLOCK(swaplock); -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; - -EXPORT_SYMBOL(total_swap_pages); +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}; -struct swap_info_struct swap_info[MAX_SWAPFILES]; +static struct swap_info_struct swap_info[MAX_SWAPFILES]; -static DECLARE_MUTEX(swapon_sem); +static DEFINE_MUTEX(swapon_mutex); /* * We need this because the bdev->unplug_fn can sleep and we cannot - * hold swap_list_lock while calling the unplug_fn. And swap_list_lock - * cannot be turned into a semaphore. + * hold swap_lock while calling the unplug_fn. And swap_lock + * cannot be turned into a mutex. */ static DECLARE_RWSEM(swap_unplug_sem); -#define SWAPFILE_CLUSTER 256 - void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) { swp_entry_t entry; down_read(&swap_unplug_sem); - entry.val = page->private; + entry.val = page_private(page); if (PageSwapCache(page)) { struct block_device *bdev = swap_info[swp_type(entry)].bdev; struct backing_dev_info *bdi; @@ -71,8 +73,8 @@ void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) /* * 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 above. If - * the WARN_ON triggers during a swapoff it maybe the race + * 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. */ @@ -84,116 +86,353 @@ void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) up_read(&swap_unplug_sem); } -static inline int scan_swap_map(struct swap_info_struct *si) +/* + * 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) { - unsigned long offset; - /* - * We try to cluster swap pages by allocating them - * sequentially in swap. Once we've allocated - * SWAPFILE_CLUSTER pages this way, however, we resort to - * first-free allocation, starting a new cluster. This - * prevents us from scattering swap pages all over the entire - * swap partition, so that we reduce overall disk seek times - * between swap pages. -- sct */ - if (si->cluster_nr) { - while (si->cluster_next <= si->highest_bit) { - offset = si->cluster_next++; - if (si->swap_map[offset]) + struct swap_extent *se; + int err = 0; + + list_for_each_entry(se, &si->extent_list, list) { + sector_t start_block = se->start_block << (PAGE_SHIFT - 9); + sector_t nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); + + if (se->start_page == 0) { + /* Do not discard the swap header page! */ + start_block += 1 << (PAGE_SHIFT - 9); + nr_blocks -= 1 << (PAGE_SHIFT - 9); + if (!nr_blocks) continue; - si->cluster_nr--; - goto got_page; } + + err = blkdev_issue_discard(si->bdev, start_block, + nr_blocks, GFP_KERNEL); + if (err) + break; + + cond_resched(); } - si->cluster_nr = SWAPFILE_CLUSTER; + return err; /* That will often be -EOPNOTSUPP */ +} - /* try to find an empty (even not aligned) cluster. */ - offset = si->lowest_bit; - check_next_cluster: - if (offset+SWAPFILE_CLUSTER-1 <= si->highest_bit) - { - unsigned long nr; - for (nr = offset; nr < offset+SWAPFILE_CLUSTER; nr++) - if (si->swap_map[nr]) - { - offset = nr+1; - goto check_next_cluster; +/* + * 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)) + break; + } + + lh = se->list.next; + if (lh == &si->extent_list) + lh = lh->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) +{ + 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 + * a new cluster. This prevents us from scattering swap pages + * all over the entire swap partition, so that we reduce + * overall disk seek times between swap pages. -- sct + * But we do now try to find an empty cluster. -Andrea + * And we let swap pages go all over an SSD partition. Hugh + */ + + si->flags += SWP_SCANNING; + 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); + + /* + * 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 */ + for (; last_in_cluster <= si->highest_bit; offset++) { + if (si->swap_map[offset]) + last_in_cluster = offset + SWAPFILE_CLUSTER; + else if (offset == last_in_cluster) { + spin_lock(&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 = 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; } - /* We found a completly empty cluster, so start - * using it. + } + + offset = scan_base; + spin_lock(&swap_lock); + si->cluster_nr = SWAPFILE_CLUSTER - 1; + si->lowest_alloc = 0; + } + +checks: + if (!(si->flags & SWP_WRITEOK)) + goto no_page; + if (!si->highest_bit) + goto no_page; + if (offset > si->highest_bit) + scan_base = offset = si->lowest_bit; + 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; + } + si->swap_map[offset] = 1; + 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. */ - goto got_page; + 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; + } } - /* No luck, so now go finegrined as usual. -Andrea */ - for (offset = si->lowest_bit; offset <= si->highest_bit ; offset++) { - if (si->swap_map[offset]) - continue; - si->lowest_bit = offset+1; - got_page: - if (offset == si->lowest_bit) - si->lowest_bit++; - if (offset == si->highest_bit) - si->highest_bit--; - if (si->lowest_bit > si->highest_bit) { - si->lowest_bit = si->max; - si->highest_bit = 0; + return offset; + +scan: + spin_unlock(&swap_lock); + while (++offset <= si->highest_bit) { + if (!si->swap_map[offset]) { + 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 (unlikely(--latency_ration < 0)) { + cond_resched(); + latency_ration = LATENCY_LIMIT; } - si->swap_map[offset] = 1; - si->inuse_pages++; - nr_swap_pages--; - si->cluster_next = offset+1; - return offset; } - si->lowest_bit = si->max; - si->highest_bit = 0; + spin_lock(&swap_lock); + +no_page: + si->flags -= SWP_SCANNING; return 0; } swp_entry_t get_swap_page(void) { - struct swap_info_struct * p; - unsigned long offset; - swp_entry_t entry; - int type, wrapped = 0; + struct swap_info_struct *si; + pgoff_t offset; + int type, next; + int wrapped = 0; - entry.val = 0; /* Out of memory */ - swap_list_lock(); - type = swap_list.next; - if (type < 0) - goto out; + spin_lock(&swap_lock); if (nr_swap_pages <= 0) - goto out; + 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++; + } - while (1) { - p = &swap_info[type]; - if ((p->flags & SWP_ACTIVE) == SWP_ACTIVE) { - swap_device_lock(p); - offset = scan_swap_map(p); - swap_device_unlock(p); - if (offset) { - entry = swp_entry(type,offset); - type = swap_info[type].next; - if (type < 0 || - p->prio != swap_info[type].prio) { - swap_list.next = swap_list.head; - } else { - swap_list.next = type; - } - goto out; - } + 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); } - type = p->next; - if (!wrapped) { - if (type < 0 || p->prio != swap_info[type].prio) { - type = swap_list.head; - wrapped = 1; - } - } else - if (type < 0) - goto out; /* out of swap space */ + next = swap_list.next; } -out: - swap_list_unlock(); - return entry; + + nr_swap_pages++; +noswap: + spin_unlock(&swap_lock); + return (swp_entry_t) {0}; +} + +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); + if (offset) { + spin_unlock(&swap_lock); + return swp_entry(type, offset); + } + nr_swap_pages++; + } + spin_unlock(&swap_lock); + return (swp_entry_t) {0}; } static struct swap_info_struct * swap_info_get(swp_entry_t entry) @@ -214,10 +453,7 @@ static struct swap_info_struct * swap_info_get(swp_entry_t entry) goto bad_offset; if (!p->swap_map[offset]) goto bad_free; - swap_list_lock(); - if (p->prio > swap_info[swap_list.next].prio) - swap_list.next = type; - swap_device_lock(p); + spin_lock(&swap_lock); return p; bad_free: @@ -233,16 +469,11 @@ bad_nofile: printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val); out: return NULL; -} - -static void swap_info_put(struct swap_info_struct * p) -{ - swap_device_unlock(p); - swap_list_unlock(); } -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) { + unsigned long offset = swp_offset(ent); int count = p->swap_map[offset]; if (count < SWAP_MAP_MAX) { @@ -253,8 +484,11 @@ static int swap_entry_free(struct swap_info_struct *p, unsigned long offset) 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--; + mem_cgroup_uncharge_swap(ent); } } return count; @@ -270,8 +504,8 @@ void swap_free(swp_entry_t entry) p = swap_info_get(entry); if (p) { - swap_entry_free(p, swp_offset(entry)); - swap_info_put(p); + swap_entry_free(p, entry); + spin_unlock(&swap_lock); } } @@ -284,140 +518,234 @@ static inline int page_swapcount(struct page *page) struct swap_info_struct *p; swp_entry_t entry; - entry.val = page->private; + 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; - swap_info_put(p); + 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 */ + if (page_swapcount(page)) return 0; - entry.val = page->private; - p = swap_info_get(entry); - if (!p) - 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); - } - swap_info_put(p); - - 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 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); - swap_info_put(p); + if (swap_entry_free(p, entry) == 1) { + 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_HIBERNATION /* - * Always set the resulting pte to be nowrite (the same as COW pages - * after one process has exited). We don't know just how many PTEs will - * share this swap entry, so be cautious and let do_wp_page work out - * what to do if a write is requested later. + * 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. * - * vma->vm_mm->page_table_lock is held. + * This is needed for the suspend to disk (aka swsusp). + */ +int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) +{ + struct block_device *bdev = NULL; + int i; + + if (device) + bdev = bdget(device); + + spin_lock(&swap_lock); + for (i = 0; i < nr_swapfiles; i++) { + struct swap_info_struct *sis = swap_info + i; + + if (!(sis->flags & SWP_WRITEOK)) + continue; + + if (!bdev) { + if (bdev_p) + *bdev_p = bdget(sis->bdev->bd_dev); + + spin_unlock(&swap_lock); + return i; + } + if (bdev == sis->bdev) { + struct swap_extent *se; + + se = list_entry(sis->extent_list.next, + struct swap_extent, list); + if (se->start_block == offset) { + if (bdev_p) + *bdev_p = bdget(sis->bdev->bd_dev); + + spin_unlock(&swap_lock); + bdput(bdev); + return i; + } + } + } + spin_unlock(&swap_lock); + if (bdev) + bdput(bdev); + + return -ENODEV; +} + +/* + * Return either the total number of swap pages of given type, or the number + * of free pages of that type (depending on @free) + * + * This is needed for software suspend + */ +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; + if (free) + n -= swap_info[type].inuse_pages; + } + spin_unlock(&swap_lock); + } + return n; +} +#endif + +/* + * 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) { - inc_mm_counter(vma->vm_mm, rss); + 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, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { - pte_t *pte; pte_t swp_pte = swp_entry_to_pte(entry); + pte_t *pte; + int ret = 0; + /* + * 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 { /* @@ -425,13 +753,16 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * Test inline before going to call unuse_pte. */ if (unlikely(pte_same(*pte, swp_pte))) { - unuse_pte(vma, pte, addr, entry, page); pte_unmap(pte); - return 1; + 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(pte - 1); - return 0; +out: + return ret; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, @@ -440,14 +771,16 @@ 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; } @@ -458,14 +791,16 @@ 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; } @@ -475,6 +810,7 @@ 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); @@ -492,8 +828,9 @@ 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; } @@ -502,46 +839,42 @@ 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); down_read(&mm->mmap_sem); lock_page(page); } - spin_lock(&mm->page_table_lock); 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; } - spin_unlock(&mm->page_table_lock); 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; } /* * Scan swap_map from current position to next entry still in use. * Recycle to start on reaching the end, returning 0 when empty. */ -static int find_next_to_unuse(struct swap_info_struct *si, int prev) +static unsigned int find_next_to_unuse(struct swap_info_struct *si, + unsigned int prev) { - int max = si->max; - int i = prev; + unsigned int max = si->max; + unsigned int i = prev; int count; /* - * No need for swap_device_lock(si) here: we're just looking + * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new - * allocations from this area (while holding swap_list_lock()). + * allocations from this area (while holding swap_lock). */ for (;;) { if (++i >= max) { @@ -577,7 +910,7 @@ static int try_to_unuse(unsigned int type) unsigned short swcount; struct page *page; swp_entry_t entry; - int i = 0; + unsigned int i = 0; int retval = 0; int reset_overflow = 0; int shmem; @@ -611,14 +944,15 @@ 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); - 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 @@ -677,13 +1011,11 @@ 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 && + while (*swap_map > 1 && !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; @@ -711,6 +1043,13 @@ 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); @@ -731,9 +1070,9 @@ static int try_to_unuse(unsigned int type) * report them; but do report if we reset SWAP_MAP_MAX. */ if (*swap_map == SWAP_MAP_MAX) { - swap_device_lock(si); + spin_lock(&swap_lock); *swap_map = 1; - swap_device_unlock(si); + spin_unlock(&swap_lock); reset_overflow = 1; } @@ -749,12 +1088,6 @@ 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. - * - * 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)) { struct writeback_control wbc = { @@ -765,17 +1098,22 @@ static int try_to_unuse(unsigned int type) 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); unlock_page(page); @@ -797,9 +1135,9 @@ static int try_to_unuse(unsigned int type) } /* - * After a successful try_to_unuse, if no swap is now in use, we know we - * can empty the mmlist. swap_list_lock must be held on entry and exit. - * Note that mmlist_lock nests inside swap_list_lock, and an mm must be + * After a successful try_to_unuse, if no swap is now in use, we know + * we can empty the mmlist. swap_lock must be held on entry and exit. + * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) @@ -841,6 +1179,23 @@ sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset) } } +#ifdef CONFIG_HIBERNATION +/* + * 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 swap_type, pgoff_t offset) +{ + 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; +} +#endif /* CONFIG_HIBERNATION */ + /* * Free all of a swapdev's extent information */ @@ -854,7 +1209,6 @@ static void destroy_swap_extents(struct swap_info_struct *sis) list_del(&se->list); kfree(se); } - sis->nr_extents = 0; } /* @@ -893,8 +1247,7 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, new_se->start_block = start_block; list_add_tail(&new_se->list, &sis->extent_list); - sis->nr_extents++; - return 0; + return 1; } /* @@ -928,7 +1281,7 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, * This is extremely effective. The average number of iterations in * map_swap_page() has been measured at about 0.3 per page. - akpm. */ -static int setup_swap_extents(struct swap_info_struct *sis) +static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct inode *inode; unsigned blocks_per_page; @@ -936,11 +1289,15 @@ static int setup_swap_extents(struct swap_info_struct *sis) unsigned blkbits; sector_t probe_block; sector_t last_block; + sector_t lowest_block = -1; + sector_t highest_block = 0; + int nr_extents = 0; 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; } @@ -985,19 +1342,28 @@ static int setup_swap_extents(struct swap_info_struct *sis) } } + 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; + } + /* * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks */ - ret = add_swap_extent(sis, page_no, 1, - first_block >> (PAGE_SHIFT - blkbits)); - if (ret) + 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 = 0; + ret = nr_extents; + *span = 1 + highest_block - lowest_block; if (page_no == 0) page_no = 1; /* force Empty message */ sis->max = page_no; @@ -1014,27 +1380,7 @@ 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 }; - 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); -} -#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; @@ -1044,7 +1390,7 @@ asmlinkage long sys_swapoff(const char __user * specialfile) char * pathname; int i, type, prev; int err; - + if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1061,10 +1407,10 @@ asmlinkage long sys_swapoff(const char __user * specialfile) mapping = victim->f_mapping; prev = -1; - swap_list_lock(); + 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->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) break; } @@ -1072,14 +1418,14 @@ asmlinkage long sys_swapoff(const char __user * specialfile) } if (type < 0) { err = -EINVAL; - swap_list_unlock(); + spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory(p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; - swap_list_unlock(); + spin_unlock(&swap_lock); goto out_dput; } if (prev < 0) { @@ -1091,24 +1437,31 @@ asmlinkage long sys_swapoff(const char __user * specialfile) /* 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; - swap_list_unlock(); + spin_unlock(&swap_lock); + current->flags |= PF_SWAPOFF; err = try_to_unuse(type); current->flags &= ~PF_SWAPOFF; - /* wait for any unplug function to finish */ - down_write(&swap_unplug_sem); - up_write(&swap_unplug_sem); - if (err) { /* re-insert swap space back into swap_list */ - swap_list_lock(); - for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next) + spin_lock(&swap_lock); + 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; @@ -1117,33 +1470,48 @@ asmlinkage long sys_swapoff(const char __user * specialfile) nr_swap_pages += p->pages; total_swap_pages += p->pages; p->flags |= SWP_WRITEOK; - swap_list_unlock(); + spin_unlock(&swap_lock); goto out_dput; } + + /* wait for any unplug function to finish */ + down_write(&swap_unplug_sem); + up_write(&swap_unplug_sem); + destroy_swap_extents(p); - down(&swapon_sem); - swap_list_lock(); + mutex_lock(&swapon_mutex); + spin_lock(&swap_lock); drain_mmlist(); - swap_device_lock(p); + + /* wait for anyone still in scan_swap_map */ + p->highest_bit = 0; /* cuts scans short */ + while (p->flags >= SWP_SCANNING) { + spin_unlock(&swap_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&swap_lock); + } + swap_file = p->swap_file; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; p->flags = 0; - swap_device_unlock(p); - swap_list_unlock(); - up(&swapon_sem); + 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); set_blocksize(bdev, p->old_block_size); bd_release(bdev); } else { - down(&inode->i_sem); + mutex_lock(&inode->i_mutex); inode->i_flags &= ~S_SWAPFILE; - up(&inode->i_sem); + mutex_unlock(&inode->i_mutex); } filp_close(swap_file, NULL); err = 0; @@ -1162,12 +1530,15 @@ static void *swap_start(struct seq_file *swap, loff_t *pos) int i; loff_t l = *pos; - down(&swapon_sem); + mutex_lock(&swapon_mutex); + + if (!l) + return SEQ_START_TOKEN; for (i = 0; i < nr_swapfiles; i++, ptr++) { if (!(ptr->flags & SWP_USED) || !ptr->swap_map) continue; - if (!l--) + if (!--l) return ptr; } @@ -1176,10 +1547,17 @@ 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 *ptr; struct swap_info_struct *endptr = swap_info + nr_swapfiles; - for (++ptr; ptr < endptr; ptr++) { + if (v == SEQ_START_TOKEN) + ptr = swap_info; + else { + ptr = v; + ptr++; + } + + for (; ptr < endptr; ptr++) { if (!(ptr->flags & SWP_USED) || !ptr->swap_map) continue; ++*pos; @@ -1191,7 +1569,7 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) static void swap_stop(struct seq_file *swap, void *v) { - up(&swapon_sem); + mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) @@ -1200,22 +1578,24 @@ static int swap_show(struct seq_file *swap, void *v) struct file *file; int len; - if (v == swap_info) - seq_puts(swap, "Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); + if (ptr == 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\\"); - seq_printf(swap, "%*s%s\t%d\t%ld\t%d\n", - len < 40 ? 40 - len : 1, " ", - S_ISBLK(file->f_dentry->d_inode->i_mode) ? + 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) ? "partition" : "file\t", - ptr->pages << (PAGE_SHIFT - 10), - ptr->inuse_pages << (PAGE_SHIFT - 10), - ptr->prio); + ptr->pages << (PAGE_SHIFT - 10), + ptr->inuse_pages << (PAGE_SHIFT - 10), + ptr->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, @@ -1227,7 +1607,7 @@ 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, @@ -1236,22 +1616,27 @@ 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; char *name = NULL; @@ -1261,62 +1646,36 @@ 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; - int nr_good_pages = 0; + 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; - swap_list_lock(); + spin_lock(&swap_lock); p = swap_info; for (type = 0 ; type < nr_swapfiles ; type++,p++) if (!(p->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))))) { - swap_list_unlock(); + if (type >= MAX_SWAPFILES) { + spin_unlock(&swap_lock); goto out; } if (type >= nr_swapfiles) nr_swapfiles = type+1; + memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->extent_list); p->flags = SWP_USED; - p->nr_extents = 0; - 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; - spin_lock_init(&p->sdev_lock); 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; - } - swap_list_unlock(); + spin_unlock(&swap_lock); name = getname(specialfile); error = PTR_ERR(name); if (IS_ERR(name)) { @@ -1350,6 +1709,7 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) error = bd_claim(bdev, sys_swapon); if (error < 0) { bdev = NULL; + error = -EINVAL; goto bad_swap; } p->old_block_size = block_size(bdev); @@ -1359,7 +1719,7 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) p->bdev = bdev; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; - down(&inode->i_sem); + mutex_lock(&inode->i_mutex); did_down = 1; if (IS_SWAPFILE(inode)) { error = -EBUSY; @@ -1369,7 +1729,7 @@ 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. @@ -1378,108 +1738,106 @@ 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 { - printk("Unable to find swap-space signature\n"); + 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; - /* - * 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; - - /* 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; - } + p->lowest_bit = 1; + p->cluster_next = 1; - error = 0; - memset(p->swap_map, 0, maxpages * sizeof(short)); - for (i=0; iinfo.nr_badpages; i++) { - int page = swap_header->info.badpages[i]; - if (page <= 0 || page >= swap_header->info.last_page) - error = -EINVAL; - else - p->swap_map[page] = SWAP_MAP_BAD; - } - nr_good_pages = swap_header->info.last_page - - swap_header->info.nr_badpages - - 1 /* header page */; - if (error) - goto bad_swap; - } + /* + * 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; - if (swapfilesize && maxpages > swapfilesize) { + error = -EINVAL; + if (!maxpages) + goto bad_swap; + if (swapfilepages && maxpages > swapfilepages) { printk(KERN_WARNING "Swap area shorter than signature indicates\n"); - error = -EINVAL; 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 */ + swap_map = vmalloc(maxpages * sizeof(short)); + if (!swap_map) { + error = -ENOMEM; + goto bad_swap; + } + + 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; + } + + 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; - error = setup_swap_extents(p); - if (error) + 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) { @@ -1488,15 +1846,31 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) goto bad_swap; } - down(&swapon_sem); - swap_list_lock(); - swap_device_lock(p); - p->flags = SWP_ACTIVE; + 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); + 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 %dk swap on %s. Priority:%d extents:%d\n", - nr_good_pages<<(PAGE_SHIFT-10), name, - p->prio, p->nr_extents); + + printk(KERN_INFO "Adding %uk swap on %s. " + "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), + (p->flags & SWP_SOLIDSTATE) ? "SS" : "", + (p->flags & SWP_DISCARDABLE) ? "D" : ""); /* insert swap space into swap_list: */ prev = -1; @@ -1512,9 +1886,8 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) } else { swap_info[prev].next = p - swap_info; } - swap_device_unlock(p); - swap_list_unlock(); - up(&swapon_sem); + spin_unlock(&swap_lock); + mutex_unlock(&swapon_mutex); error = 0; goto out; bad_swap: @@ -1523,15 +1896,12 @@ bad_swap: bd_release(bdev); } destroy_swap_extents(p); + swap_cgroup_swapoff(type); bad_swap_2: - swap_list_lock(); - swap_map = p->swap_map; + spin_lock(&swap_lock); p->swap_file = NULL; - p->swap_map = NULL; p->flags = 0; - if (!(swap_flags & SWAP_FLAG_PREFER)) - ++least_priority; - swap_list_unlock(); + spin_unlock(&swap_lock); vfree(swap_map); if (swap_file) filp_close(swap_file, NULL); @@ -1545,7 +1915,7 @@ out: if (did_down) { if (!error) inode->i_flags |= S_SWAPFILE; - up(&inode->i_sem); + mutex_unlock(&inode->i_mutex); } return error; } @@ -1555,7 +1925,7 @@ void si_swapinfo(struct sysinfo *val) unsigned int i; unsigned long nr_to_be_unused = 0; - swap_list_lock(); + spin_lock(&swap_lock); for (i = 0; i < nr_swapfiles; i++) { if (!(swap_info[i].flags & SWP_USED) || (swap_info[i].flags & SWP_WRITEOK)) @@ -1564,7 +1934,7 @@ void si_swapinfo(struct sysinfo *val) } val->freeswap = nr_swap_pages + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; - swap_list_unlock(); + spin_unlock(&swap_lock); } /* @@ -1579,13 +1949,16 @@ int swap_duplicate(swp_entry_t entry) unsigned long offset, type; int result = 0; + if (is_migration_entry(entry)) + return 1; + type = swp_type(entry); if (type >= nr_swapfiles) goto bad_file; p = type + swap_info; offset = swp_offset(entry); - swap_device_lock(p); + 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]++; @@ -1597,7 +1970,7 @@ int swap_duplicate(swp_entry_t entry) result = 1; } } - swap_device_unlock(p); + spin_unlock(&swap_lock); out: return result; @@ -1613,35 +1986,53 @@ get_swap_info_struct(unsigned type) } /* - * swap_device_lock prevents swap_map being freed. Don't grab an extra + * swap_lock prevents swap_map being freed. Don't grab an extra * reference on the swaphandle, it doesn't matter if it becomes unused. */ 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; - swap_device_lock(swapdev); - do { - /* Don't read-ahead past the end of the swap area */ - if (toff >= swapdev->max) + 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); + 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 (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 (si->swap_map[toff] == SWAP_MAP_BAD) break; - toff++; - ret++; - } while (--i); - swap_device_unlock(swapdev); - return ret; + } + 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. + */ + *offset = ++toff; + return nr_pages? ++nr_pages: 0; }