static DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
+long nr_swap_pages;
long total_swap_pages;
static int swap_overflow;
static int least_priority;
up_read(&swap_unplug_sem);
}
+/*
+ * swapon tell device that all the old swap contents can be discarded,
+ * to allow the swap device to optimize its wear-levelling.
+ */
+static int discard_swap(struct swap_info_struct *si)
+{
+ struct swap_extent *se;
+ int err = 0;
+
+ list_for_each_entry(se, &si->extent_list, list) {
+ sector_t start_block = se->start_block << (PAGE_SHIFT - 9);
+ pgoff_t nr_blocks = 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;
+ }
+
+ err = blkdev_issue_discard(si->bdev, start_block,
+ nr_blocks, GFP_KERNEL);
+ if (err)
+ break;
+
+ cond_resched();
+ }
+ return err; /* That will often be -EOPNOTSUPP */
+}
+
+/*
+ * swap allocation tell device that a cluster of swap can now be discarded,
+ * to allow the swap device to optimize its wear-levelling.
+ */
+static void discard_swap_cluster(struct swap_info_struct *si,
+ pgoff_t start_page, pgoff_t nr_pages)
+{
+ struct swap_extent *se = si->curr_swap_extent;
+ int found_extent = 0;
+
+ while (nr_pages) {
+ struct list_head *lh;
+
+ if (se->start_page <= start_page &&
+ start_page < se->start_page + se->nr_pages) {
+ pgoff_t offset = start_page - se->start_page;
+ sector_t start_block = se->start_block + offset;
+ pgoff_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, last_in_cluster;
+ unsigned long offset;
+ 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
*/
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;
+ offset = si->cluster_next;
+
+ if (unlikely(!si->cluster_nr--)) {
+ if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
+ si->cluster_nr = SWAPFILE_CLUSTER - 1;
+ goto checks;
+ }
+ if (si->flags & SWP_DISCARDABLE) {
+ /*
+ * Start range check on racing allocations, in case
+ * they overlap the cluster we eventually decide on
+ * (we scan without swap_lock to allow preemption).
+ * It's hardly conceivable that cluster_nr could be
+ * wrapped during our scan, but don't depend on it.
+ */
+ if (si->lowest_alloc)
+ goto checks;
+ si->lowest_alloc = si->max;
+ si->highest_alloc = 0;
+ }
spin_unlock(&swap_lock);
offset = si->lowest_bit;
last_in_cluster = offset + SWAPFILE_CLUSTER;
else if (offset == last_in_cluster) {
spin_lock(&swap_lock);
- si->cluster_next = offset-SWAPFILE_CLUSTER+1;
- goto cluster;
+ offset -= SWAPFILE_CLUSTER - 1;
+ si->cluster_next = offset;
+ si->cluster_nr = SWAPFILE_CLUSTER - 1;
+ found_free_cluster = 1;
+ goto checks;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
}
+
+ offset = si->lowest_bit;
spin_lock(&swap_lock);
- goto lowest;
+ si->cluster_nr = SWAPFILE_CLUSTER - 1;
+ si->lowest_alloc = 0;
}
- si->cluster_nr--;
-cluster:
- offset = si->cluster_next;
- if (offset > si->highest_bit)
-lowest: offset = si->lowest_bit;
-checks: if (!(si->flags & SWP_WRITEOK))
+checks:
+ if (!(si->flags & SWP_WRITEOK))
goto no_page;
if (!si->highest_bit)
goto no_page;
- if (!si->swap_map[offset]) {
- if (offset == si->lowest_bit)
- si->lowest_bit++;
- if (offset == si->highest_bit)
- si->highest_bit--;
- si->inuse_pages++;
- if (si->inuse_pages == si->pages) {
- si->lowest_bit = si->max;
- si->highest_bit = 0;
+ if (offset > si->highest_bit)
+ 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.
+ */
+ if (found_free_cluster) {
+ /*
+ * To optimize wear-levelling, discard the
+ * old data of the cluster, taking care not to
+ * discard any of its pages that have already
+ * been allocated by racing tasks (offset has
+ * already stepped over any at the beginning).
+ */
+ if (offset < si->highest_alloc &&
+ si->lowest_alloc <= last_in_cluster)
+ last_in_cluster = si->lowest_alloc - 1;
+ si->flags |= SWP_DISCARDING;
+ spin_unlock(&swap_lock);
+
+ if (offset < last_in_cluster)
+ discard_swap_cluster(si, offset,
+ last_in_cluster - offset + 1);
+
+ spin_lock(&swap_lock);
+ si->lowest_alloc = 0;
+ si->flags &= ~SWP_DISCARDING;
+
+ smp_mb(); /* wake_up_bit advises this */
+ wake_up_bit(&si->flags, ilog2(SWP_DISCARDING));
+
+ } else if (si->flags & SWP_DISCARDING) {
+ /*
+ * Delay using pages allocated by racing tasks
+ * until the whole discard has been issued. We
+ * could defer that delay until swap_writepage,
+ * but it's easier to keep this self-contained.
+ */
+ spin_unlock(&swap_lock);
+ wait_on_bit(&si->flags, ilog2(SWP_DISCARDING),
+ wait_for_discard, TASK_UNINTERRUPTIBLE);
+ spin_lock(&swap_lock);
+ } else {
+ /*
+ * Note pages allocated by racing tasks while
+ * scan for a free cluster is in progress, so
+ * that its final discard can exclude them.
+ */
+ if (offset < si->lowest_alloc)
+ si->lowest_alloc = offset;
+ if (offset > si->highest_alloc)
+ si->highest_alloc = offset;
}
- si->swap_map[offset] = 1;
- si->cluster_next = offset + 1;
- si->flags -= SWP_SCANNING;
- return offset;
}
+ return offset;
+scan:
spin_unlock(&swap_lock);
while (++offset <= si->highest_bit) {
if (!si->swap_map[offset]) {
}
}
spin_lock(&swap_lock);
- goto lowest;
+ goto checks;
no_page:
si->flags -= SWP_SCANNING;
printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
out:
return NULL;
-}
+}
static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
{
}
/*
- * 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.
*/
-static int remove_exclusive_swap_page_count(struct page *page, int count)
+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) != count) /* us + cache + ptes */
+ if (page_swapcount(page))
return 0;
- entry.val = page_private(page);
- 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.. */
- spin_lock_irq(&swapper_space.tree_lock);
- if ((page_count(page) == count) && !PageWriteback(page)) {
- __delete_from_swap_cache(page);
- SetPageDirty(page);
- retval = 1;
- }
- spin_unlock_irq(&swapper_space.tree_lock);
- }
- spin_unlock(&swap_lock);
-
- if (retval) {
- swap_free(entry);
- page_cache_release(page);
- }
-
- return retval;
-}
-
-/*
- * Most of the time the page should have two references: one for the
- * process and one for the swap cache.
- */
-int remove_exclusive_swap_page(struct page *page)
-{
- return remove_exclusive_swap_page_count(page, 2);
-}
-
-/*
- * The pageout code holds an extra reference to the page. That raises
- * the reference count to test for to 2 for a page that is only in the
- * swap cache plus 1 for each process that maps the page.
- */
-int remove_exclusive_swap_page_ref(struct page *page)
-{
- return remove_exclusive_swap_page_count(page, 2 + page_mapcount(page));
+ delete_from_swap_cache(page);
+ SetPageDirty(page);
+ return 1;
}
/*
spin_unlock(&swap_lock);
}
if (page) {
- int one_user;
-
- BUG_ON(PagePrivate(page));
- one_user = (page_count(page) == 2);
- /* Only cache user (+us), or swap space full? Free it! */
- /* Also recheck PageSwapCache after page is locked (above) */
+ /*
+ * Not mapped elsewhere, or swap space full? Free it!
+ * Also recheck PageSwapCache now page is locked (above).
+ */
if (PageSwapCache(page) && !PageWriteback(page) &&
- (one_user || vm_swap_full())) {
+ (!page_mapped(page) || vm_swap_full())) {
delete_from_swap_cache(page);
SetPageDirty(page);
}
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);
lock_page(page);
wait_on_page_writeback(page);
}
- if (PageSwapCache(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);
/*
{
struct backing_dev_info *bdi;
- BUG_ON(!PageLocked(page)); /* It pins the swap_info_struct */
+ VM_BUG_ON(!PageLocked(page)); /* It pins the swap_info_struct */
if (PageSwapCache(page)) {
swp_entry_t entry = { .val = page_private(page) };
char * pathname;
int i, type, prev;
int err;
-
+
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
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;
}
file = ptr->swap_file;
len = seq_path(swap, &file->f_path, " \t\n\\");
seq_printf(swap, "%*s%s\t%u\t%u\t%d\n",
- len < 40 ? 40 - len : 1, " ",
- S_ISBLK(file->f_path.dentry->d_inode->i_mode) ?
+ len < 40 ? 40 - len : 1, " ",
+ S_ISBLK(file->f_path.dentry->d_inode->i_mode) ?
"partition" : "file\t",
- ptr->pages << (PAGE_SHIFT - 10),
- ptr->inuse_pages << (PAGE_SHIFT - 10),
- ptr->prio);
+ ptr->pages << (PAGE_SHIFT - 10),
+ ptr->inuse_pages << (PAGE_SHIFT - 10),
+ ptr->prio);
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.
*
int i, prev;
int error;
union swap_header *swap_header = NULL;
- int swap_header_version;
unsigned int nr_good_pages = 0;
int nr_extents = 0;
sector_t span;
unsigned long maxpages = 1;
- int swapfilesize;
+ unsigned long swapfilepages;
unsigned short *swap_map = NULL;
struct page *page = NULL;
struct inode *inode = NULL;
goto bad_swap;
}
- swapfilesize = i_size_read(inode) >> PAGE_SHIFT;
+ swapfilepages = i_size_read(inode) >> PAGE_SHIFT;
/*
* Read the swap header.
error = PTR_ERR(page);
goto bad_swap;
}
- kmap(page);
- swap_header = page_address(page);
+ swap_header = kmap(page);
- if (!memcmp("SWAP-SPACE",swap_header->magic.magic,10))
- swap_header_version = 1;
- else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10))
- swap_header_version = 2;
- else {
+ if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) {
printk(KERN_ERR "Unable to find swap-space signature\n");
error = -EINVAL;
goto bad_swap;
}
-
- switch (swap_header_version) {
- case 1:
- printk(KERN_ERR "version 0 swap is no longer supported. "
- "Use mkswap -v1 %s\n", name);
+
+ /* swap partition endianess hack... */
+ if (swab32(swap_header->info.version) == 1) {
+ swab32s(&swap_header->info.version);
+ swab32s(&swap_header->info.last_page);
+ swab32s(&swap_header->info.nr_badpages);
+ for (i = 0; i < swap_header->info.nr_badpages; i++)
+ swab32s(&swap_header->info.badpages[i]);
+ }
+ /* Check the swap header's sub-version */
+ if (swap_header->info.version != 1) {
+ printk(KERN_WARNING
+ "Unable to handle swap header version %d\n",
+ swap_header->info.version);
error = -EINVAL;
goto bad_swap;
- case 2:
- /* 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) {
- printk(KERN_WARNING
- "Unable to handle swap header version %d\n",
- swap_header->info.version);
- error = -EINVAL;
- goto bad_swap;
- }
+ }
- p->lowest_bit = 1;
- p->cluster_next = 1;
+ p->lowest_bit = 1;
+ p->cluster_next = 1;
- /*
- * Find out how many pages are allowed for a single swap
- * device. There are two limiting factors: 1) the number of
- * bits for the swap offset in the swp_entry_t type and
- * 2) the number of bits in the a swap pte as defined by
- * the different architectures. In order to find the
- * largest possible bit mask a swap entry with swap type 0
- * and swap offset ~0UL is created, encoded to a swap pte,
- * decoded to a swp_entry_t again and finally the swap
- * offset is extracted. This will mask all the bits from
- * the initial ~0UL mask that can't be encoded in either
- * the swp_entry_t or the architecture definition of a
- * swap pte.
- */
- maxpages = swp_offset(pte_to_swp_entry(swp_entry_to_pte(swp_entry(0,~0UL)))) - 1;
- if (maxpages > swap_header->info.last_page)
- maxpages = swap_header->info.last_page;
- p->highest_bit = maxpages - 1;
+ /*
+ * Find out how many pages are allowed for a single swap
+ * device. There are two limiting factors: 1) the number of
+ * bits for the swap offset in the swp_entry_t type and
+ * 2) the number of bits in the a swap pte as defined by
+ * the different architectures. In order to find the
+ * largest possible bit mask a swap entry with swap type 0
+ * and swap offset ~0UL is created, encoded to a swap pte,
+ * decoded to a swp_entry_t again and finally the swap
+ * offset is extracted. This will mask all the bits from
+ * the initial ~0UL mask that can't be encoded in either
+ * the swp_entry_t or the architecture definition of a
+ * swap pte.
+ */
+ maxpages = swp_offset(pte_to_swp_entry(
+ swp_entry_to_pte(swp_entry(0, ~0UL)))) - 1;
+ if (maxpages > swap_header->info.last_page)
+ maxpages = swap_header->info.last_page;
+ p->highest_bit = maxpages - 1;
- error = -EINVAL;
- if (!maxpages)
- goto bad_swap;
- if (swapfilesize && maxpages > swapfilesize) {
- printk(KERN_WARNING
- "Swap area shorter than signature indicates\n");
- goto bad_swap;
- }
- if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
- goto bad_swap;
- if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
- goto bad_swap;
+ error = -EINVAL;
+ if (!maxpages)
+ goto bad_swap;
+ if (swapfilepages && maxpages > swapfilepages) {
+ printk(KERN_WARNING
+ "Swap area shorter than signature indicates\n");
+ goto bad_swap;
+ }
+ if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
+ goto bad_swap;
+ if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
+ goto bad_swap;
- /* OK, set up the swap map and apply the bad block list */
- swap_map = vmalloc(maxpages * sizeof(short));
- if (!swap_map) {
- error = -ENOMEM;
- goto bad_swap;
- }
+ /* OK, set up the swap map and apply the bad block list */
+ swap_map = vmalloc(maxpages * sizeof(short));
+ if (!swap_map) {
+ error = -ENOMEM;
+ goto bad_swap;
+ }
- error = 0;
- memset(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
- swap_map[page_nr] = SWAP_MAP_BAD;
- }
- nr_good_pages = swap_header->info.last_page -
- swap_header->info.nr_badpages -
- 1 /* header page */;
- if (error)
+ memset(swap_map, 0, maxpages * sizeof(short));
+ for (i = 0; i < swap_header->info.nr_badpages; i++) {
+ int page_nr = swap_header->info.badpages[i];
+ if (page_nr <= 0 || page_nr >= swap_header->info.last_page) {
+ error = -EINVAL;
goto bad_swap;
+ }
+ swap_map[page_nr] = SWAP_MAP_BAD;
}
+ nr_good_pages = swap_header->info.last_page -
+ swap_header->info.nr_badpages -
+ 1 /* header page */;
if (nr_good_pages) {
swap_map[0] = SWAP_MAP_BAD;
goto bad_swap;
}
+ if (discard_swap(p) == 0)
+ p->flags |= SWP_DISCARDABLE;
+
mutex_lock(&swapon_mutex);
spin_lock(&swap_lock);
if (swap_flags & SWAP_FLAG_PREFER)
else
p->prio = --least_priority;
p->swap_map = swap_map;
- p->flags = SWP_ACTIVE;
+ p->flags |= SWP_WRITEOK;
nr_swap_pages += nr_good_pages;
total_swap_pages += nr_good_pages;
printk(KERN_INFO "Adding %uk swap on %s. "
- "Priority:%d extents:%d across:%lluk\n",
+ "Priority:%d extents:%d across:%lluk%s\n",
nr_good_pages<<(PAGE_SHIFT-10), name, p->prio,
- nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10));
+ nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
+ (p->flags & SWP_DISCARDABLE) ? " D" : "");
/* insert swap space into swap_list: */
prev = -1;
git.openpandora.org / pandora-kernel.git / blobdiff