#include <linux/namei.h>
#include <linux/shm.h>
#include <linux/blkdev.h>
+#include <linux/random.h>
#include <linux/writeback.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>
+#include <linux/page_cgroup.h>
static DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
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);
+ 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;
+ }
+
+ 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;
+ 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 last_in_cluster;
+ 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
* 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;
- offset = si->cluster_next;
+ 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);
- offset = si->lowest_bit;
+ /*
+ * 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 */
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)) {
}
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;
+ }
+ }
+
+ offset = scan_base;
spin_lock(&swap_lock);
si->cluster_nr = SWAPFILE_CLUSTER - 1;
+ si->lowest_alloc = 0;
}
checks:
if (!si->highest_bit)
goto no_page;
if (offset > si->highest_bit)
- offset = si->lowest_bit;
+ scan_base = offset = si->lowest_bit;
if (si->swap_map[offset])
goto scan;
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;
+ }
+ }
return offset;
scan:
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;
+ }
+ }
spin_lock(&swap_lock);
- goto checks;
no_page:
si->flags -= SWP_SCANNING;
return NULL;
}
-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) {
swap_list.next = p - swap_info;
nr_swap_pages++;
p->inuse_pages--;
+ mem_cgroup_uncharge_swap(ent);
}
}
return count;
p = swap_info_get(entry);
if (p) {
- swap_entry_free(p, swp_offset(entry));
+ swap_entry_free(p, entry);
spin_unlock(&swap_lock);
}
}
* 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;
+ return 1;
p = swap_info_get(entry);
if (p) {
- if (swap_entry_free(p, swp_offset(entry)) == 1) {
+ if (swap_entry_free(p, entry) == 1) {
page = find_get_page(&swapper_space, entry.val);
if (page && !trylock_page(page)) {
page_cache_release(page);
unlock_page(page);
page_cache_release(page);
}
+ return p != NULL;
}
#ifdef CONFIG_HIBERNATION
if (!bdev) {
if (bdev_p)
- *bdev_p = sis->bdev;
+ *bdev_p = bdget(sis->bdev->bd_dev);
spin_unlock(&swap_lock);
return i;
struct swap_extent, list);
if (se->start_block == offset) {
if (bdev_p)
- *bdev_p = sis->bdev;
+ *bdev_p = bdget(sis->bdev->bd_dev);
spin_unlock(&swap_lock);
bdput(bdev);
static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, swp_entry_t entry, struct page *page)
{
+ struct mem_cgroup *ptr = NULL;
spinlock_t *ptl;
pte_t *pte;
int ret = 1;
- if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
+ 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_uncharge_page(page);
+ mem_cgroup_cancel_charge_swapin(ptr);
ret = 0;
goto out;
}
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
activate_page(page);
out:
pte_unmap_unlock(pte, ptl);
+out_nolock:
return ret;
}
return ret;
}
-#if 0 /* We don't need this yet */
-#include <linux/backing-dev.h>
-int page_queue_congested(struct page *page)
-{
- struct backing_dev_info *bdi;
-
- VM_BUG_ON(!PageLocked(page)); /* It pins the swap_info_struct */
-
- if (PageSwapCache(page)) {
- swp_entry_t entry = { .val = page_private(page) };
- 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;
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);
*
* 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;
}
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 */;
goto bad_swap;
}
+ 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)
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%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_SOLIDSTATE) ? "SS" : "",
+ (p->flags & SWP_DISCARDABLE) ? "D" : "");
/* insert swap space into swap_list: */
prev = -1;
bd_release(bdev);
}
destroy_swap_extents(p);
+ swap_cgroup_swapoff(type);
bad_swap_2:
spin_lock(&swap_lock);
p->swap_file = NULL;