diff options
Diffstat (limited to 'mm/swapfile.c')
| -rw-r--r-- | mm/swapfile.c | 158 |
1 files changed, 125 insertions, 33 deletions
diff --git a/mm/swapfile.c b/mm/swapfile.c index c7a33717d079..0b3674b1409a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -38,6 +38,7 @@ #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> +#include <linux/stop_machine.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -85,7 +86,7 @@ PLIST_HEAD(swap_active_head); * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ -struct plist_head *swap_avail_heads; +static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; @@ -1107,6 +1108,64 @@ static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, return p; } +/* + * Check whether swap entry is valid in the swap device. If so, + * return pointer to swap_info_struct, and keep the swap entry valid + * via preventing the swap device from being swapoff, until + * put_swap_device() is called. Otherwise return NULL. + * + * Notice that swapoff or swapoff+swapon can still happen before the + * preempt_disable() in get_swap_device() or after the + * preempt_enable() in put_swap_device() if there isn't any other way + * to prevent swapoff, such as page lock, page table lock, etc. The + * caller must be prepared for that. For example, the following + * situation is possible. + * + * CPU1 CPU2 + * do_swap_page() + * ... swapoff+swapon + * __read_swap_cache_async() + * swapcache_prepare() + * __swap_duplicate() + * // check swap_map + * // verify PTE not changed + * + * In __swap_duplicate(), the swap_map need to be checked before + * changing partly because the specified swap entry may be for another + * swap device which has been swapoff. And in do_swap_page(), after + * the page is read from the swap device, the PTE is verified not + * changed with the page table locked to check whether the swap device + * has been swapoff or swapoff+swapon. + */ +struct swap_info_struct *get_swap_device(swp_entry_t entry) +{ + struct swap_info_struct *si; + unsigned long type, offset; + + if (!entry.val) + goto out; + type = swp_type(entry); + if (type >= nr_swapfiles) + goto bad_nofile; + si = swap_info[type]; + + preempt_disable(); + if (!(si->flags & SWP_VALID)) + goto unlock_out; + offset = swp_offset(entry); + if (offset >= si->max) + goto unlock_out; + + return si; +bad_nofile: + pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); +out: + return NULL; +unlock_out: + preempt_enable(); + return NULL; +} + static unsigned char __swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { @@ -1328,11 +1387,18 @@ int page_swapcount(struct page *page) return count; } -int __swap_count(struct swap_info_struct *si, swp_entry_t entry) +int __swap_count(swp_entry_t entry) { + struct swap_info_struct *si; pgoff_t offset = swp_offset(entry); + int count = 0; - return swap_count(si->swap_map[offset]); + si = get_swap_device(entry); + if (si) { + count = swap_count(si->swap_map[offset]); + put_swap_device(si); + } + return count; } static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) @@ -1357,9 +1423,11 @@ int __swp_swapcount(swp_entry_t entry) int count = 0; struct swap_info_struct *si; - si = __swap_info_get(entry); - if (si) + si = get_swap_device(entry); + if (si) { count = swap_swapcount(si, entry); + put_swap_device(si); + } return count; } @@ -1800,8 +1868,6 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); - set_pte_at(vma->vm_mm, addr, pte, - pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { page_add_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, true, false); @@ -1810,6 +1876,8 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); } + set_pte_at(vma->vm_mm, addr, pte, + pte_mkold(mk_pte(page, vma->vm_page_prot))); swap_free(entry); /* * Move the page to the active list so it is not @@ -2451,9 +2519,9 @@ static int swap_node(struct swap_info_struct *p) return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } -static void _enable_swap_info(struct swap_info_struct *p, int prio, - unsigned char *swap_map, - struct swap_cluster_info *cluster_info) +static void setup_swap_info(struct swap_info_struct *p, int prio, + unsigned char *swap_map, + struct swap_cluster_info *cluster_info) { int i; @@ -2478,7 +2546,11 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, } p->swap_map = swap_map; p->cluster_info = cluster_info; - p->flags |= SWP_WRITEOK; +} + +static void _enable_swap_info(struct swap_info_struct *p) +{ + p->flags |= SWP_WRITEOK | SWP_VALID; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; @@ -2497,6 +2569,11 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, add_to_avail_list(p); } +static int swap_onoff_stop(void *arg) +{ + return 0; +} + static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, @@ -2505,7 +2582,17 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, prio, swap_map, cluster_info); + setup_swap_info(p, prio, swap_map, cluster_info); + spin_unlock(&p->lock); + spin_unlock(&swap_lock); + /* + * Guarantee swap_map, cluster_info, etc. fields are used + * between get/put_swap_device() only if SWP_VALID bit is set + */ + stop_machine(swap_onoff_stop, NULL, cpu_online_mask); + spin_lock(&swap_lock); + spin_lock(&p->lock); + _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -2514,7 +2601,8 @@ static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, p->prio, p->swap_map, p->cluster_info); + setup_swap_info(p, p->prio, p->swap_map, p->cluster_info); + _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -2617,6 +2705,17 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) reenable_swap_slots_cache_unlock(); + spin_lock(&swap_lock); + spin_lock(&p->lock); + p->flags &= ~SWP_VALID; /* mark swap device as invalid */ + spin_unlock(&p->lock); + spin_unlock(&swap_lock); + /* + * wait for swap operations protected by get/put_swap_device() + * to complete + */ + stop_machine(swap_onoff_stop, NULL, cpu_online_mask); + flush_work(&p->discard_work); destroy_swap_extents(p); @@ -3356,22 +3455,16 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) { struct swap_info_struct *p; struct swap_cluster_info *ci; - unsigned long offset, type; + unsigned long offset; unsigned char count; unsigned char has_cache; int err = -EINVAL; - if (non_swap_entry(entry)) + p = get_swap_device(entry); + if (!p) goto out; - type = swp_type(entry); - if (type >= nr_swapfiles) - goto bad_file; - p = swap_info[type]; offset = swp_offset(entry); - if (unlikely(offset >= p->max)) - goto out; - ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; @@ -3417,11 +3510,9 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) unlock_out: unlock_cluster_or_swap_info(p, ci); out: + if (p) + put_swap_device(p); return err; - -bad_file: - pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val); - goto out; } /* @@ -3513,6 +3604,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) struct page *list_page; pgoff_t offset; unsigned char count; + int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better @@ -3520,15 +3612,15 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); - si = swap_info_get(entry); + si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing - * __swap_duplicate(): the swap entry has been freed, - * perhaps even the whole swap_map cleared for swapoff. + * __swap_duplicate(): the swap device may be swapoff */ goto outer; } + spin_lock(&si->lock); offset = swp_offset(entry); @@ -3546,9 +3638,8 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) } if (!page) { - unlock_cluster(ci); - spin_unlock(&si->lock); - return -ENOMEM; + ret = -ENOMEM; + goto out; } /* @@ -3600,10 +3691,11 @@ out_unlock_cont: out: unlock_cluster(ci); spin_unlock(&si->lock); + put_swap_device(si); outer: if (page) __free_page(page); - return 0; + return ret; } /* |