#include <linux/config.h>
#include <linux/mm.h>
+#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/backing-dev.h>
+#include <linux/mutex.h>
+#include <linux/capability.h>
+#include <linux/syscalls.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>
+#include <linux/vs_memory.h>
-spinlock_t swaplock = SPIN_LOCK_UNLOCKED;
+DEFINE_SPINLOCK(swap_lock);
unsigned int nr_swapfiles;
-int total_swap_pages;
+long total_swap_pages;
static int swap_overflow;
-EXPORT_SYMBOL(total_swap_pages);
-
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 ";
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);
/*
- * Array of backing blockdevs, for swap_unplug_fn. 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.
+ * We need this because the bdev->unplug_fn can sleep and we cannot
+ * hold swap_lock while calling the unplug_fn. And swap_lock
+ * cannot be turned into a mutex.
*/
-static DECLARE_MUTEX(swap_bdevs_sem);
-static struct block_device *swap_bdevs[MAX_SWAPFILES];
-
-#define SWAPFILE_CLUSTER 256
+static DECLARE_RWSEM(swap_unplug_sem);
-/*
- * Caller holds swap_bdevs_sem
- */
-static void install_swap_bdev(struct block_device *bdev)
-{
- int i;
-
- for (i = 0; i < MAX_SWAPFILES; i++) {
- if (swap_bdevs[i] == NULL) {
- swap_bdevs[i] = bdev;
- return;
- }
- }
- BUG();
-}
-
-static void remove_swap_bdev(struct block_device *bdev)
-{
- int i;
-
- for (i = 0; i < MAX_SWAPFILES; i++) {
- if (swap_bdevs[i] == bdev) {
- memcpy(&swap_bdevs[i], &swap_bdevs[i + 1],
- (MAX_SWAPFILES - i - 1) * sizeof(*swap_bdevs));
- swap_bdevs[MAX_SWAPFILES - 1] = NULL;
- return;
- }
- }
- BUG();
-}
-
-/*
- * Unlike a standard unplug_io_fn, swap_unplug_io_fn is never called
- * through swap's backing_dev_info (which is only used by shrink_list),
- * but directly from sync_page when PageSwapCache: and takes the page
- * as argument, so that it can find the right device from swp_entry_t.
- */
-void swap_unplug_io_fn(struct page *page)
+void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page)
{
swp_entry_t entry;
- down(&swap_bdevs_sem);
- entry.val = page->private;
+ down_read(&swap_unplug_sem);
+ entry.val = page_private(page);
if (PageSwapCache(page)) {
- struct block_device *bdev = swap_bdevs[swp_type(entry)];
+ struct block_device *bdev = swap_info[swp_type(entry)].bdev;
struct backing_dev_info *bdi;
- if (bdev) {
- bdi = bdev->bd_inode->i_mapping->backing_dev_info;
- (*bdi->unplug_io_fn)(bdi);
- }
+ /*
+ * If the page is removed from swapcache from under us (with a
+ * racy try_to_unuse/swapoff) we need an additional reference
+ * count to avoid reading garbage from page_private(page) above.
+ * If the WARN_ON triggers during a swapoff it maybe the race
+ * condition and it's harmless. However if it triggers without
+ * swapoff it signals a problem.
+ */
+ WARN_ON(page_count(page) <= 1);
+
+ bdi = bdev->bd_inode->i_mapping->backing_dev_info;
+ blk_run_backing_dev(bdi, page);
}
- up(&swap_bdevs_sem);
+ up_read(&swap_unplug_sem);
}
-static inline int scan_swap_map(struct swap_info_struct *si)
+#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 offset, last_in_cluster;
+ int latency_ration = LATENCY_LIMIT;
+
/*
- * We try to cluster swap pages by allocating them
- * sequentially in swap. Once we've allocated
- * SWAPFILE_CLUSTER pages this way, however, we resort to
- * first-free allocation, starting 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++;
+ * 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
+ */
+
+ si->flags += SWP_SCANNING;
+ if (unlikely(!si->cluster_nr)) {
+ si->cluster_nr = SWAPFILE_CLUSTER - 1;
+ if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER)
+ goto lowest;
+ spin_unlock(&swap_lock);
+
+ 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])
- continue;
- si->cluster_nr--;
- goto got_page;
- }
- }
- si->cluster_nr = SWAPFILE_CLUSTER;
-
- /* try to find an empty (even not aligned) cluster. */
- offset = si->lowest_bit;
- check_next_cluster:
- if (offset+SWAPFILE_CLUSTER-1 <= si->highest_bit)
- {
- int nr;
- for (nr = offset; nr < offset+SWAPFILE_CLUSTER; nr++)
- if (si->swap_map[nr])
- {
- offset = nr+1;
- goto check_next_cluster;
+ 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;
}
- /* We found a completly empty cluster, so start
- * using it.
- */
- goto got_page;
+ if (unlikely(--latency_ration < 0)) {
+ cond_resched();
+ latency_ration = LATENCY_LIMIT;
+ }
+ }
+ spin_lock(&swap_lock);
+ goto lowest;
}
- /* 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:
+
+ si->cluster_nr--;
+cluster:
+ offset = si->cluster_next;
+ if (offset > si->highest_bit)
+lowest: offset = si->lowest_bit;
+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--;
- if (si->lowest_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->inuse_pages++;
- nr_swap_pages--;
- si->cluster_next = offset+1;
+ si->cluster_next = offset + 1;
+ si->flags -= SWP_SCANNING;
return offset;
}
- si->lowest_bit = si->max;
- si->highest_bit = 0;
+
+ 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;
+ }
+ }
+ spin_lock(&swap_lock);
+ goto lowest;
+
+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)
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:
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)
{
int count = p->swap_map[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--;
}
p = swap_info_get(entry);
if (p) {
swap_entry_free(p, swp_offset(entry));
- swap_info_put(p);
+ spin_unlock(&swap_lock);
}
}
/*
- * Check if we're the only user of a swap page,
- * when the page is locked.
+ * How many references to page are currently swapped out?
*/
-static int exclusive_swap_page(struct page *page)
+static inline int page_swapcount(struct page *page)
{
- int retval = 0;
- struct swap_info_struct * p;
+ int count = 0;
+ 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) {
- /* Is the only swap cache user the cache itself? */
- if (p->swap_map[swp_offset(entry)] == 1) {
- /* Recheck the page count with the swapcache lock held.. */
- spin_lock(&swapper_space.tree_lock);
- if (page_count(page) == 2)
- retval = 1;
- spin_unlock(&swapper_space.tree_lock);
- }
- swap_info_put(p);
+ /* Subtract the 1 for the swap cache itself */
+ count = p->swap_map[swp_offset(entry)] - 1;
+ spin_unlock(&swap_lock);
}
- return retval;
+ return count;
}
/*
* We can use this swap cache entry directly
* if there are no other references to it.
- *
- * Here "exclusive_swap_page()" does the real
- * work, but we opportunistically check whether
- * we need to get all the locks first..
*/
int can_share_swap_page(struct page *page)
{
- int retval = 0;
+ int count;
- if (!PageLocked(page))
- BUG();
- switch (page_count(page)) {
- case 3:
- if (!PagePrivate(page))
- break;
- /* Fallthrough */
- case 2:
- if (!PageSwapCache(page))
- break;
- retval = exclusive_swap_page(page);
- break;
- case 1:
- if (PageReserved(page))
- break;
- retval = 1;
- }
- return retval;
+ BUG_ON(!PageLocked(page));
+ count = page_mapcount(page);
+ if (count <= 1 && PageSwapCache(page))
+ count += page_swapcount(page);
+ return count == 1;
}
/*
if (page_count(page) != 2) /* 2: us + cache */
return 0;
- entry.val = page->private;
+ entry.val = page_private(page);
p = swap_info_get(entry);
if (!p)
return 0;
retval = 0;
if (p->swap_map[swp_offset(entry)] == 1) {
/* Recheck the page count with the swapcache lock held.. */
- spin_lock(&swapper_space.tree_lock);
+ write_lock_irq(&swapper_space.tree_lock);
if ((page_count(page) == 2) && !PageWriteback(page)) {
__delete_from_swap_cache(page);
SetPageDirty(page);
retval = 1;
}
- spin_unlock(&swapper_space.tree_lock);
+ write_unlock_irq(&swapper_space.tree_lock);
}
- swap_info_put(p);
+ spin_unlock(&swap_lock);
if (retval) {
swap_free(entry);
p = swap_info_get(entry);
if (p) {
if (swap_entry_free(p, swp_offset(entry)) == 1) {
- spin_lock(&swapper_space.tree_lock);
- page = radix_tree_lookup(&swapper_space.page_tree,
- entry.val);
- if (page && TestSetPageLocked(page))
+ page = find_get_page(&swapper_space, entry.val);
+ if (page && unlikely(TestSetPageLocked(page))) {
+ page_cache_release(page);
page = NULL;
- spin_unlock(&swapper_space.tree_lock);
+ }
}
- swap_info_put(p);
+ 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())) {
+ /* Also recheck PageSwapCache after page is locked (above) */
+ if (PageSwapCache(page) && !PageWriteback(page) &&
+ (one_user || vm_swap_full())) {
delete_from_swap_cache(page);
SetPageDirty(page);
}
}
}
+#ifdef CONFIG_SOFTWARE_SUSPEND
+/*
+ * Find the swap type that corresponds to given device (if any)
+ *
+ * This is needed for software suspend and is done in such a way that inode
+ * aliasing is allowed.
+ */
+int swap_type_of(dev_t device)
+{
+ int i;
+
+ spin_lock(&swap_lock);
+ for (i = 0; i < nr_swapfiles; i++) {
+ struct inode *inode;
+
+ if (!(swap_info[i].flags & SWP_WRITEOK))
+ continue;
+ if (!device) {
+ spin_unlock(&swap_lock);
+ return i;
+ }
+ inode = swap_info->swap_file->f_dentry->d_inode;
+ if (S_ISBLK(inode->i_mode) &&
+ device == MKDEV(imajor(inode), iminor(inode))) {
+ spin_unlock(&swap_lock);
+ return i;
+ }
+ }
+ spin_unlock(&swap_lock);
+ return -ENODEV;
+}
+
/*
- * The swap entry has been read in advance, and we return 1 to indicate
- * that the page has been used or is no longer needed.
+ * Return either the total number of swap pages of given type, or the number
+ * of free pages of that type (depending on @free)
*
- * 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.
+ * This is needed for software suspend
*/
-/* vma->vm_mm->page_table_lock is held */
-static void
-unuse_pte(struct vm_area_struct *vma, unsigned long address, pte_t *dir,
- swp_entry_t entry, struct page *page, struct pte_chain **pte_chainp)
+unsigned int count_swap_pages(int type, int free)
{
- // vma->vm_mm->rss++;
- vx_rsspages_inc(vma->vm_mm);
+ 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,
+ unsigned long addr, swp_entry_t entry, struct page *page)
+{
+ inc_mm_counter(vma->vm_mm, anon_rss);
get_page(page);
- set_pte(dir, pte_mkold(mk_pte(page, vma->vm_page_prot)));
- *pte_chainp = page_add_rmap(page, dir, *pte_chainp);
+ set_pte_at(vma->vm_mm, addr, pte,
+ pte_mkold(mk_pte(page, vma->vm_page_prot)));
+ page_add_anon_rmap(page, vma, addr);
swap_free(entry);
+ /*
+ * Move the page to the active list so it is not
+ * immediately swapped out again after swapon.
+ */
+ activate_page(page);
}
-/* vma->vm_mm->page_table_lock is held */
-static int unuse_pmd(struct vm_area_struct * vma, pmd_t *dir,
- unsigned long address, unsigned long size, unsigned long offset,
- swp_entry_t entry, struct page *page, struct pte_chain **pte_chainp)
+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;
- unsigned long end;
pte_t swp_pte = swp_entry_to_pte(entry);
+ pte_t *pte;
+ spinlock_t *ptl;
+ int found = 0;
- if (pmd_none(*dir))
- return 0;
- if (pmd_bad(*dir)) {
- pmd_ERROR(*dir);
- pmd_clear(dir);
- return 0;
- }
- pte = pte_offset_map(dir, address);
- offset += address & PMD_MASK;
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
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, offset + address, pte,
- entry, page, pte_chainp);
- pte_unmap(pte);
- return 1;
+ unuse_pte(vma, pte++, addr, entry, page);
+ found = 1;
+ break;
}
- address += PAGE_SIZE;
- pte++;
- } while (address && (address < end));
- pte_unmap(pte - 1);
- return 0;
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+ pte_unmap_unlock(pte - 1, ptl);
+ return found;
}
-/* vma->vm_mm->page_table_lock is held */
-static int unuse_pgd(struct vm_area_struct * vma, pgd_t *dir,
- unsigned long address, unsigned long size,
- swp_entry_t entry, struct page *page, struct pte_chain **pte_chainp)
+static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
+ unsigned long addr, unsigned long end,
+ swp_entry_t entry, struct page *page)
{
- pmd_t * pmd;
- unsigned long offset, end;
+ pmd_t *pmd;
+ unsigned long next;
- if (pgd_none(*dir))
- return 0;
- if (pgd_bad(*dir)) {
- pgd_ERROR(*dir);
- pgd_clear(dir);
- return 0;
- }
- pmd = pmd_offset(dir, address);
- offset = address & PGDIR_MASK;
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- if (address >= end)
- BUG();
+ pmd = pmd_offset(pud, addr);
do {
- if (unuse_pmd(vma, pmd, address, end - address,
- offset, entry, page, pte_chainp))
+ 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;
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address && (address < end));
+ } while (pmd++, addr = next, addr != end);
return 0;
}
-/* vma->vm_mm->page_table_lock is held */
-static int unuse_vma(struct vm_area_struct * vma, pgd_t *pgdir,
- swp_entry_t entry, struct page *page, struct pte_chain **pte_chainp)
+static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ swp_entry_t entry, struct page *page)
{
- unsigned long start = vma->vm_start, end = vma->vm_end;
+ pud_t *pud;
+ unsigned long next;
- if (start >= end)
- BUG();
+ pud = pud_offset(pgd, addr);
do {
- if (unuse_pgd(vma, pgdir, start, end - start,
- entry, page, pte_chainp))
+ 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;
- start = (start + PGDIR_SIZE) & PGDIR_MASK;
- pgdir++;
- } while (start && (start < end));
+ } while (pud++, addr = next, addr != end);
return 0;
}
-static int unuse_process(struct mm_struct * mm,
- swp_entry_t entry, struct page* page)
+static int unuse_vma(struct vm_area_struct *vma,
+ swp_entry_t entry, struct page *page)
{
- struct vm_area_struct* vma;
- struct pte_chain *pte_chain;
+ pgd_t *pgd;
+ unsigned long addr, end, next;
- pte_chain = pte_chain_alloc(GFP_KERNEL);
- if (!pte_chain)
- return -ENOMEM;
+ if (page->mapping) {
+ addr = page_address_in_vma(page, vma);
+ if (addr == -EFAULT)
+ return 0;
+ else
+ end = addr + PAGE_SIZE;
+ } else {
+ addr = vma->vm_start;
+ end = vma->vm_end;
+ }
- /*
- * Go through process' page directory.
- */
- spin_lock(&mm->page_table_lock);
+ pgd = pgd_offset(vma->vm_mm, addr);
+ do {
+ 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;
+ } while (pgd++, addr = next, addr != end);
+ return 0;
+}
+
+static int unuse_mm(struct mm_struct *mm,
+ swp_entry_t entry, struct page *page)
+{
+ struct vm_area_struct *vma;
+
+ 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(page);
+ unlock_page(page);
+ down_read(&mm->mmap_sem);
+ lock_page(page);
+ }
for (vma = mm->mmap; vma; vma = vma->vm_next) {
- pgd_t * pgd = pgd_offset(mm, vma->vm_start);
- if (unuse_vma(vma, pgd, entry, page, &pte_chain))
+ if (vma->anon_vma && unuse_vma(vma, entry, page))
break;
}
- spin_unlock(&mm->page_table_lock);
- pte_chain_free(pte_chain);
+ 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;
}
+#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.
*/
-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) {
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;
*
* A simpler strategy would be to start at the last mm we
* freed the previous entry from; but that would take less
- * advantage of mmlist ordering (now preserved by swap_out()),
- * which clusters forked address spaces together, most recent
- * child immediately after parent. If we race with dup_mmap(),
- * we very much want to resolve parent before child, otherwise
- * we may miss some entries: using last mm would invert that.
+ * advantage of mmlist ordering, which clusters forked mms
+ * together, child after parent. If we race with dup_mmap(), we
+ * prefer to resolve parent before child, lest we miss entries
+ * duplicated after we scanned child: using last mm would invert
+ * that. Though it's only a serious concern when an overflowed
+ * swap count is reset from SWAP_MAP_MAX, preventing a rescan.
*/
start_mm = &init_mm;
atomic_inc(&init_mm.mm_users);
/*
* Keep on scanning until all entries have gone. Usually,
* one pass through swap_map is enough, but not necessarily:
- * mmput() removes mm from mmlist before exit_mmap() and its
- * zap_page_range(). That's not too bad, those entries are
- * on their way out, and handled faster there than here.
- * do_munmap() behaves similarly, taking the range out of mm's
- * vma list before zap_page_range(). But unfortunately, when
- * unmapping a part of a vma, it takes the whole out first,
- * then reinserts what's left after (might even reschedule if
- * open() method called) - so swap entries may be invisible
- * to swapoff for a while, then reappear - but that is rare.
+ * there are races when an instance of an entry might be missed.
*/
- while ((i = find_next_to_unuse(si, i))) {
+ while ((i = find_next_to_unuse(si, i)) != 0) {
if (signal_pending(current)) {
retval = -EINTR;
break;
*/
swap_map = &si->swap_map[i];
entry = swp_entry(type, i);
- page = read_swap_cache_async(entry);
+again:
+ page = read_swap_cache_async(entry, NULL, 0);
if (!page) {
/*
* Either swap_duplicate() failed because entry
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);
/*
- * Remove all references to entry, without blocking.
+ * Remove all references to entry.
* Whenever we reach init_mm, there's no address space
* to search, but use it as a reminder to search shmem.
*/
if (start_mm == &init_mm)
shmem = shmem_unuse(entry, page);
else
- retval = unuse_process(start_mm, entry, page);
+ retval = unuse_mm(start_mm, entry, page);
}
if (*swap_map > 1) {
int set_start_mm = (*swap_map >= swcount);
while (*swap_map > 1 && !retval &&
(p = p->next) != &start_mm->mmlist) {
mm = list_entry(p, struct mm_struct, mmlist);
- atomic_inc(&mm->mm_users);
+ if (atomic_inc_return(&mm->mm_users) == 1) {
+ atomic_dec(&mm->mm_users);
+ continue;
+ }
spin_unlock(&mmlist_lock);
mmput(prev_mm);
prev_mm = mm;
set_start_mm = 1;
shmem = shmem_unuse(entry, page);
} else
- retval = unuse_process(mm, entry, page);
+ retval = unuse_mm(mm, entry, page);
if (set_start_mm && *swap_map < swcount) {
mmput(new_start_mm);
atomic_inc(&mm->mm_users);
* 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;
}
return retval;
}
+/*
+ * 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)
+{
+ struct list_head *p, *next;
+ unsigned int i;
+
+ for (i = 0; i < nr_swapfiles; i++)
+ if (swap_info[i].inuse_pages)
+ return;
+ spin_lock(&mmlist_lock);
+ list_for_each_safe(p, next, &init_mm.mmlist)
+ list_del_init(p);
+ spin_unlock(&mmlist_lock);
+}
+
/*
* Use this swapdev's extent info to locate the (PAGE_SIZE) block which
* corresponds to page offset `offset'.
offset < (se->start_page + se->nr_pages)) {
return se->start_block + (offset - se->start_page);
}
- lh = se->list.prev;
+ lh = se->list.next;
if (lh == &sis->extent_list)
- lh = lh->prev;
+ 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 */
list_del(&se->list);
kfree(se);
}
- sis->nr_extents = 0;
}
/*
* Add a block range (and the corresponding page range) into this swapdev's
- * extent list. The extent list is kept sorted in block order.
+ * extent list. The extent list is kept sorted in page order.
*
- * This function rather assumes that it is called in ascending sector_t order.
- * It doesn't look for extent coalescing opportunities.
+ * This function rather assumes that it is called in ascending page order.
*/
static int
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.next; /* The highest-addressed block */
- while (lh != &sis->extent_list) {
+ lh = sis->extent_list.prev; /* The highest page extent */
+ if (lh != &sis->extent_list) {
se = list_entry(lh, struct swap_extent, list);
- if (se->start_block + se->nr_pages == start_block &&
- se->start_page + se->nr_pages == start_page) {
+ BUG_ON(se->start_page + se->nr_pages != start_page);
+ if (se->start_block + se->nr_pages == start_block) {
/* Merge it */
se->nr_pages += nr_pages;
return 0;
}
- lh = lh->next;
}
/*
new_se->nr_pages = nr_pages;
new_se->start_block = start_block;
- lh = sis->extent_list.prev; /* The lowest block */
- while (lh != &sis->extent_list) {
- se = list_entry(lh, struct swap_extent, list);
- if (se->start_block > start_block)
- break;
- lh = lh->prev;
- }
- list_add_tail(&new_se->list, lh);
- sis->nr_extents++;
- return 0;
+ list_add_tail(&new_se->list, &sis->extent_list);
+ return 1;
}
/*
* requirements, they are simply tossed out - we will never use those blocks
* for swapping.
*
- * For S_ISREG swapfiles we hold i_sem across the life of the swapon. This
+ * For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon. This
* prevents root from shooting her foot off by ftruncating an in-use swapfile,
* which will scribble on the fs.
*
* 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;
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;
}
}
}
+ 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)
- ret = -EINVAL;
+ page_no = 1; /* force Empty message */
sis->max = page_no;
+ sis->pages = page_no - 1;
sis->highest_bit = page_no - 1;
done:
sis->curr_swap_extent = list_entry(sis->extent_list.prev,
BUG_ON(!PageLocked(page)); /* It pins the swap_info_struct */
if (PageSwapCache(page)) {
- swp_entry_t entry = { .val = page->private };
+ swp_entry_t entry = { .val = page_private(page) };
struct swap_info_struct *sis;
sis = get_swap_info_struct(swp_type(entry));
unsigned short *swap_map;
struct file *swap_file, *victim;
struct address_space *mapping;
+ struct inode *inode;
char * pathname;
int i, type, prev;
int err;
if (IS_ERR(pathname))
goto out;
- victim = filp_open(pathname, O_RDWR, 0);
+ victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0);
putname(pathname);
err = PTR_ERR(victim);
if (IS_ERR(victim))
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 (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) {
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;
+
if (err) {
/* re-insert swap space back into swap_list */
- swap_list_lock();
+ spin_lock(&swap_lock);
for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next)
if (p->prio >= swap_info[i].prio)
break;
nr_swap_pages += p->pages;
total_swap_pages += p->pages;
p->flags |= SWP_WRITEOK;
- swap_list_unlock();
+ spin_unlock(&swap_lock);
goto out_dput;
}
- down(&swapon_sem);
- down(&swap_bdevs_sem);
- swap_list_lock();
- swap_device_lock(p);
+
+ /* wait for any unplug function to finish */
+ down_write(&swap_unplug_sem);
+ up_write(&swap_unplug_sem);
+
+ destroy_swap_extents(p);
+ mutex_lock(&swapon_mutex);
+ spin_lock(&swap_lock);
+ drain_mmlist();
+
+ /* wait for anyone still in scan_swap_map */
+ p->highest_bit = 0; /* cuts scans short */
+ while (p->flags >= SWP_SCANNING) {
+ spin_unlock(&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;
- destroy_swap_extents(p);
- swap_device_unlock(p);
- swap_list_unlock();
- remove_swap_bdev(p->bdev);
- up(&swap_bdevs_sem);
- up(&swapon_sem);
+ spin_unlock(&swap_lock);
+ mutex_unlock(&swapon_mutex);
vfree(swap_map);
- if (S_ISBLK(mapping->host->i_mode)) {
- struct block_device *bdev = I_BDEV(mapping->host);
+ 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 {
- up(&mapping->host->i_sem);
+ mutex_lock(&inode->i_mutex);
+ inode->i_flags &= ~S_SWAPFILE;
+ mutex_unlock(&inode->i_mutex);
}
filp_close(swap_file, NULL);
err = 0;
int i;
loff_t l = *pos;
- down(&swapon_sem);
+ mutex_lock(&swapon_mutex);
for (i = 0; i < nr_swapfiles; i++, ptr++) {
if (!(ptr->flags & SWP_USED) || !ptr->swap_map)
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)
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",
+ 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) ?
"partition" : "file\t",
int i, prev;
int error;
static int least_priority;
- union swap_header *swap_header = 0;
+ 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;
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))
* 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();
+ spin_unlock(&swap_lock);
goto out;
}
if (type >= nr_swapfiles)
nr_swapfiles = type+1;
INIT_LIST_HEAD(&p->extent_list);
p->flags = SWP_USED;
- p->nr_extents = 0;
p->swap_file = NULL;
p->old_block_size = 0;
p->swap_map = NULL;
p->highest_bit = 0;
p->cluster_nr = 0;
p->inuse_pages = 0;
- p->sdev_lock = SPIN_LOCK_UNLOCKED;
p->next = -1;
if (swap_flags & SWAP_FLAG_PREFER) {
p->prio =
} else {
p->prio = --least_priority;
}
- swap_list_unlock();
+ spin_unlock(&swap_lock);
name = getname(specialfile);
error = PTR_ERR(name);
if (IS_ERR(name)) {
name = NULL;
goto bad_swap_2;
}
- swap_file = filp_open(name, O_RDWR, 0);
+ swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0);
error = PTR_ERR(swap_file);
if (IS_ERR(swap_file)) {
swap_file = NULL;
error = bd_claim(bdev, sys_swapon);
if (error < 0) {
bdev = NULL;
+ error = -EINVAL;
goto bad_swap;
}
p->old_block_size = block_size(bdev);
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;
+ goto bad_swap;
+ }
} else {
goto bad_swap;
}
else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10))
swap_header_version = 2;
else {
- printk("Unable to find swap-space signature\n");
+ printk(KERN_ERR "Unable to find swap-space signature\n");
error = -EINVAL;
goto bad_swap;
}
}
p->lowest_bit = 1;
+ p->cluster_next = 1;
+
/*
* Find out how many pages are allowed for a single swap
* device. There are two limiting factors: 1) the number of
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;
error = 0;
memset(p->swap_map, 0, maxpages * sizeof(short));
- for (i=0; i<swap_header->info.nr_badpages; i++) {
- int page = swap_header->info.badpages[i];
- if (page <= 0 || page >= swap_header->info.last_page)
+ 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] = SWAP_MAP_BAD;
+ 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)
+ if (error)
goto bad_swap;
}
-
+
if (swapfilesize && maxpages > swapfilesize) {
printk(KERN_WARNING
"Swap area shorter than signature indicates\n");
error = -EINVAL;
goto bad_swap;
}
+ if (nr_good_pages) {
+ p->swap_map[0] = SWAP_MAP_BAD;
+ p->max = maxpages;
+ p->pages = nr_good_pages;
+ nr_extents = setup_swap_extents(p, &span);
+ if (nr_extents < 0) {
+ error = nr_extents;
+ goto bad_swap;
+ }
+ nr_good_pages = p->pages;
+ }
if (!nr_good_pages) {
printk(KERN_WARNING "Empty swap-file\n");
error = -EINVAL;
goto bad_swap;
}
- p->swap_map[0] = SWAP_MAP_BAD;
- p->max = maxpages;
- p->pages = nr_good_pages;
-
- error = setup_swap_extents(p);
- if (error)
- goto bad_swap;
- down(&swapon_sem);
- down(&swap_bdevs_sem);
- swap_list_lock();
- swap_device_lock(p);
+ mutex_lock(&swapon_mutex);
+ spin_lock(&swap_lock);
p->flags = SWP_ACTIVE;
nr_swap_pages += nr_good_pages;
total_swap_pages += nr_good_pages;
- printk(KERN_INFO "Adding %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\n",
+ nr_good_pages<<(PAGE_SHIFT-10), name, p->prio,
+ nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10));
/* insert swap space into swap_list: */
prev = -1;
} else {
swap_info[prev].next = p - swap_info;
}
- swap_device_unlock(p);
- swap_list_unlock();
- install_swap_bdev(p->bdev);
- up(&swap_bdevs_sem);
- up(&swapon_sem);
+ spin_unlock(&swap_lock);
+ mutex_unlock(&swapon_mutex);
error = 0;
goto out;
bad_swap:
set_blocksize(bdev, p->old_block_size);
bd_release(bdev);
}
+ destroy_swap_extents(p);
bad_swap_2:
- swap_list_lock();
+ 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;
- swap_list_unlock();
- destroy_swap_extents(p);
- if (swap_map)
- vfree(swap_map);
+ spin_unlock(&swap_lock);
+ vfree(swap_map);
if (swap_file)
filp_close(swap_file, NULL);
out:
}
if (name)
putname(name);
- if (error && did_down)
- up(&inode->i_sem);
+ if (did_down) {
+ if (!error)
+ inode->i_flags |= S_SWAPFILE;
+ mutex_unlock(&inode->i_mutex);
+ }
return error;
}
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))
}
val->freeswap = nr_swap_pages + nr_to_be_unused;
val->totalswap = total_swap_pages + nr_to_be_unused;
- swap_list_unlock();
- if (vx_flags(VXF_VIRT_MEM, 0))
- vx_vsi_swapinfo(val);
+ spin_unlock(&swap_lock);
+ if (vx_flags(VXF_VIRT_MEM, 0))
+ vx_vsi_swapinfo(val);
}
/*
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]++;
result = 1;
}
}
- swap_device_unlock(p);
+ spin_unlock(&swap_lock);
out:
return result;
}
/*
- * 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)
toff++, i--;
*offset = toff;
- swap_device_lock(swapdev);
+ spin_lock(&swap_lock);
do {
/* Don't read-ahead past the end of the swap area */
if (toff >= swapdev->max)
toff++;
ret++;
} while (--i);
- swap_device_unlock(swapdev);
+ spin_unlock(&swap_lock);
return ret;
}