#include <asm/tlbflush.h>
#include <linux/swapops.h>
-DEFINE_SPINLOCK(swap_lock);
-unsigned int nr_swapfiles;
+static DEFINE_SPINLOCK(swap_lock);
+static unsigned int nr_swapfiles;
long total_swap_pages;
static int swap_overflow;
+static int least_priority;
static const char Bad_file[] = "Bad swap file entry ";
static const char Unused_file[] = "Unused swap file entry ";
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";
-struct swap_list_t swap_list = {-1, -1};
+static struct swap_list_t swap_list = {-1, -1};
static struct swap_info_struct swap_info[MAX_SWAPFILES];
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);
+ spin_lock_irq(&swapper_space.tree_lock);
if ((page_count(page) == 2) && !PageWriteback(page)) {
__delete_from_swap_cache(page);
SetPageDirty(page);
retval = 1;
}
- write_unlock_irq(&swapper_space.tree_lock);
+ spin_unlock_irq(&swapper_space.tree_lock);
}
spin_unlock(&swap_lock);
if (p) {
if (swap_entry_free(p, swp_offset(entry)) == 1) {
page = find_get_page(&swapper_space, entry.val);
- if (page && unlikely(TestSetPageLocked(page))) {
+ if (page && unlikely(!trylock_page(page))) {
page_cache_release(page);
page = NULL;
}
* 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 int 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)
{
+ spinlock_t *ptl;
+ pte_t *pte;
+ int ret = 1;
+
if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
- return -ENOMEM;
+ ret = -ENOMEM;
+
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
+ if (ret > 0)
+ mem_cgroup_uncharge_page(page);
+ ret = 0;
+ goto out;
+ }
inc_mm_counter(vma->vm_mm, anon_rss);
get_page(page);
* immediately swapped out again after swapon.
*/
activate_page(page);
- return 1;
+out:
+ pte_unmap_unlock(pte, ptl);
+ return ret;
}
static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
{
pte_t swp_pte = swp_entry_to_pte(entry);
pte_t *pte;
- spinlock_t *ptl;
int ret = 0;
- pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ /*
+ * We don't actually need pte lock while scanning for swp_pte: since
+ * we hold page lock and mmap_sem, swp_pte cannot be inserted into the
+ * page table while we're scanning; though it could get zapped, and on
+ * some architectures (e.g. x86_32 with PAE) we might catch a glimpse
+ * of unmatched parts which look like swp_pte, so unuse_pte must
+ * recheck under pte lock. Scanning without pte lock lets it be
+ * preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE.
+ */
+ pte = pte_offset_map(pmd, addr);
do {
/*
* swapoff spends a _lot_ of time in this loop!
* Test inline before going to call unuse_pte.
*/
if (unlikely(pte_same(*pte, swp_pte))) {
- ret = unuse_pte(vma, pte++, addr, entry, page);
- break;
+ pte_unmap(pte);
+ ret = unuse_pte(vma, pmd, addr, entry, page);
+ if (ret)
+ goto out;
+ pte = pte_offset_map(pmd, addr);
}
} while (pte++, addr += PAGE_SIZE, addr != end);
- pte_unmap_unlock(pte - 1, ptl);
+ pte_unmap(pte - 1);
+out:
return ret;
}
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);
/* 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;
if (err) {
/* re-insert swap space back into swap_list */
spin_lock(&swap_lock);
- for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next)
+ if (p->prio < 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;
}
file = ptr->swap_file;
- len = seq_path(swap, file->f_path.mnt, file->f_path.dentry, " \t\n\\");
+ 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) ?
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);
unsigned int type;
int i, prev;
int error;
- static int least_priority;
union swap_header *swap_header = NULL;
int swap_header_version;
unsigned int nr_good_pages = 0;
sector_t span;
unsigned long maxpages = 1;
int swapfilesize;
- unsigned short *swap_map;
+ unsigned short *swap_map = NULL;
struct page *page = NULL;
struct inode *inode = NULL;
int did_down = 0;
}
if (type >= nr_swapfiles)
nr_swapfiles = type+1;
+ memset(p, 0, sizeof(*p));
INIT_LIST_HEAD(&p->extent_list);
p->flags = SWP_USED;
- p->swap_file = NULL;
- p->old_block_size = 0;
- p->swap_map = NULL;
- p->lowest_bit = 0;
- p->highest_bit = 0;
- p->cluster_nr = 0;
- p->inuse_pages = 0;
p->next = -1;
- if (swap_flags & SWAP_FLAG_PREFER) {
- p->prio =
- (swap_flags & SWAP_FLAG_PRIO_MASK)>>SWAP_FLAG_PRIO_SHIFT;
- } else {
- p->prio = --least_priority;
- }
spin_unlock(&swap_lock);
name = getname(specialfile);
error = PTR_ERR(name);
error = -EINVAL;
goto bad_swap;
case 2:
+ /* 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 and the size of
the swap file and bad block lists */
if (swap_header->info.version != 1) {
goto bad_swap;
/* OK, set up the swap map and apply the bad block list */
- if (!(p->swap_map = vmalloc(maxpages * sizeof(short)))) {
+ swap_map = vmalloc(maxpages * sizeof(short));
+ if (!swap_map) {
error = -ENOMEM;
goto bad_swap;
}
error = 0;
- memset(p->swap_map, 0, maxpages * sizeof(short));
+ 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;
else
- p->swap_map[page_nr] = SWAP_MAP_BAD;
+ swap_map[page_nr] = SWAP_MAP_BAD;
}
nr_good_pages = swap_header->info.last_page -
swap_header->info.nr_badpages -
}
if (nr_good_pages) {
- p->swap_map[0] = SWAP_MAP_BAD;
+ swap_map[0] = SWAP_MAP_BAD;
p->max = maxpages;
p->pages = nr_good_pages;
nr_extents = setup_swap_extents(p, &span);
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_ACTIVE;
nr_swap_pages += nr_good_pages;
total_swap_pages += nr_good_pages;
destroy_swap_extents(p);
bad_swap_2:
spin_lock(&swap_lock);
- swap_map = p->swap_map;
p->swap_file = NULL;
- p->swap_map = NULL;
p->flags = 0;
- if (!(swap_flags & SWAP_FLAG_PREFER))
- ++least_priority;
spin_unlock(&swap_lock);
vfree(swap_map);
if (swap_file)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff