return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */
}
+/* Reclaim the swap entry anyway if possible */
+#define TTRS_ANYWAY 0x1
+/*
+ * Reclaim the swap entry if there are no more mappings of the
+ * corresponding page
+ */
+#define TTRS_UNMAPPED 0x2
+/* Reclaim the swap entry if swap is getting full*/
+#define TTRS_FULL 0x4
+
/* returns 1 if swap entry is freed */
-static int
-__try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset)
+static int __try_to_reclaim_swap(struct swap_info_struct *si,
+ unsigned long offset, unsigned long flags)
{
swp_entry_t entry = swp_entry(si->type, offset);
struct page *page;
int ret = 0;
- page = find_get_page(swap_address_space(entry), swp_offset(entry));
+ page = find_get_page(swap_address_space(entry), offset);
if (!page)
return 0;
/*
- * This function is called from scan_swap_map() and it's called
- * by vmscan.c at reclaiming pages. So, we hold a lock on a page, here.
- * We have to use trylock for avoiding deadlock. This is a special
+ * When this function is called from scan_swap_map_slots() and it's
+ * called by vmscan.c at reclaiming pages. So, we hold a lock on a page,
+ * here. We have to use trylock for avoiding deadlock. This is a special
* case and you should use try_to_free_swap() with explicit lock_page()
* in usual operations.
*/
if (trylock_page(page)) {
- ret = try_to_free_swap(page);
+ if ((flags & TTRS_ANYWAY) ||
+ ((flags & TTRS_UNMAPPED) && !page_mapped(page)) ||
+ ((flags & TTRS_FULL) && mem_cgroup_swap_full(page)))
+ ret = try_to_free_swap(page);
unlock_page(page);
}
put_page(page);
#ifdef CONFIG_THP_SWAP
#define SWAPFILE_CLUSTER HPAGE_PMD_NR
+
+#define swap_entry_size(size) (size)
#else
#define SWAPFILE_CLUSTER 256
+
+/*
+ * Define swap_entry_size() as constant to let compiler to optimize
+ * out some code if !CONFIG_THP_SWAP
+ */
+#define swap_entry_size(size) 1
#endif
#define LATENCY_LIMIT 256
static inline bool cluster_is_huge(struct swap_cluster_info *info)
{
- return info->flags & CLUSTER_FLAG_HUGE;
+ if (IS_ENABLED(CONFIG_THP_SWAP))
+ return info->flags & CLUSTER_FLAG_HUGE;
+ return false;
}
static inline void cluster_clear_huge(struct swap_cluster_info *info)
spin_unlock(&ci->lock);
}
+/*
+ * Determine the locking method in use for this device. Return
+ * swap_cluster_info if SSD-style cluster-based locking is in place.
+ */
static inline struct swap_cluster_info *lock_cluster_or_swap_info(
- struct swap_info_struct *si,
- unsigned long offset)
+ struct swap_info_struct *si, unsigned long offset)
{
struct swap_cluster_info *ci;
+ /* Try to use fine-grained SSD-style locking if available: */
ci = lock_cluster(si, offset);
+ /* Otherwise, fall back to traditional, coarse locking: */
if (!ci)
spin_lock(&si->lock);
int swap_was_freed;
unlock_cluster(ci);
spin_unlock(&si->lock);
- swap_was_freed = __try_to_reclaim_swap(si, offset);
+ swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY);
spin_lock(&si->lock);
/* entry was freed successfully, try to use this again */
if (swap_was_freed)
return n_ret;
}
-#ifdef CONFIG_THP_SWAP
static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
{
unsigned long idx;
unsigned long offset, i;
unsigned char *map;
+ /*
+ * Should not even be attempting cluster allocations when huge
+ * page swap is disabled. Warn and fail the allocation.
+ */
+ if (!IS_ENABLED(CONFIG_THP_SWAP)) {
+ VM_WARN_ON_ONCE(1);
+ return 0;
+ }
+
if (cluster_list_empty(&si->free_clusters))
return 0;
struct swap_cluster_info *ci;
ci = lock_cluster(si, offset);
+ memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER);
cluster_set_count_flag(ci, 0, 0);
free_cluster(si, idx);
unlock_cluster(ci);
swap_range_free(si, offset, SWAPFILE_CLUSTER);
}
-#else
-static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
-{
- VM_WARN_ON_ONCE(1);
- return 0;
-}
-#endif /* CONFIG_THP_SWAP */
static unsigned long scan_swap_map(struct swap_info_struct *si,
unsigned char usage)
}
-int get_swap_pages(int n_goal, bool cluster, swp_entry_t swp_entries[])
+int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
{
- unsigned long nr_pages = cluster ? SWAPFILE_CLUSTER : 1;
+ unsigned long size = swap_entry_size(entry_size);
struct swap_info_struct *si, *next;
long avail_pgs;
int n_ret = 0;
int node;
/* Only single cluster request supported */
- WARN_ON_ONCE(n_goal > 1 && cluster);
+ WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
- avail_pgs = atomic_long_read(&nr_swap_pages) / nr_pages;
+ avail_pgs = atomic_long_read(&nr_swap_pages) / size;
if (avail_pgs <= 0)
goto noswap;
if (n_goal > avail_pgs)
n_goal = avail_pgs;
- atomic_long_sub(n_goal * nr_pages, &nr_swap_pages);
+ atomic_long_sub(n_goal * size, &nr_swap_pages);
spin_lock(&swap_avail_lock);
spin_unlock(&si->lock);
goto nextsi;
}
- if (cluster) {
- if (!(si->flags & SWP_FILE))
+ if (size == SWAPFILE_CLUSTER) {
+ if (!(si->flags & SWP_FS))
n_ret = swap_alloc_cluster(si, swp_entries);
} else
n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
n_goal, swp_entries);
spin_unlock(&si->lock);
- if (n_ret || cluster)
+ if (n_ret || size == SWAPFILE_CLUSTER)
goto check_out;
pr_debug("scan_swap_map of si %d failed to find offset\n",
si->type);
check_out:
if (n_ret < n_goal)
- atomic_long_add((long)(n_goal - n_ret) * nr_pages,
+ atomic_long_add((long)(n_goal - n_ret) * size,
&nr_swap_pages);
noswap:
return n_ret;
return p;
}
-static unsigned char __swap_entry_free(struct swap_info_struct *p,
- swp_entry_t entry, unsigned char usage)
+static unsigned char __swap_entry_free_locked(struct swap_info_struct *p,
+ unsigned long offset,
+ unsigned char usage)
{
- struct swap_cluster_info *ci;
- unsigned long offset = swp_offset(entry);
unsigned char count;
unsigned char has_cache;
- ci = lock_cluster_or_swap_info(p, offset);
-
count = p->swap_map[offset];
has_cache = count & SWAP_HAS_CACHE;
usage = count | has_cache;
p->swap_map[offset] = usage ? : SWAP_HAS_CACHE;
+ return usage;
+}
+
+static unsigned char __swap_entry_free(struct swap_info_struct *p,
+ swp_entry_t entry, unsigned char usage)
+{
+ struct swap_cluster_info *ci;
+ unsigned long offset = swp_offset(entry);
+
+ ci = lock_cluster_or_swap_info(p, offset);
+ usage = __swap_entry_free_locked(p, offset, usage);
unlock_cluster_or_swap_info(p, ci);
+ if (!usage)
+ free_swap_slot(entry);
return usage;
}
struct swap_info_struct *p;
p = _swap_info_get(entry);
- if (p) {
- if (!__swap_entry_free(p, entry, 1))
- free_swap_slot(entry);
- }
+ if (p)
+ __swap_entry_free(p, entry, 1);
}
/*
* Called after dropping swapcache to decrease refcnt to swap entries.
*/
-static void swapcache_free(swp_entry_t entry)
-{
- struct swap_info_struct *p;
-
- p = _swap_info_get(entry);
- if (p) {
- if (!__swap_entry_free(p, entry, SWAP_HAS_CACHE))
- free_swap_slot(entry);
- }
-}
-
-#ifdef CONFIG_THP_SWAP
-static void swapcache_free_cluster(swp_entry_t entry)
+void put_swap_page(struct page *page, swp_entry_t entry)
{
unsigned long offset = swp_offset(entry);
unsigned long idx = offset / SWAPFILE_CLUSTER;
unsigned char *map;
unsigned int i, free_entries = 0;
unsigned char val;
+ int size = swap_entry_size(hpage_nr_pages(page));
si = _swap_info_get(entry);
if (!si)
return;
- ci = lock_cluster(si, offset);
- VM_BUG_ON(!cluster_is_huge(ci));
- map = si->swap_map + offset;
- for (i = 0; i < SWAPFILE_CLUSTER; i++) {
- val = map[i];
- VM_BUG_ON(!(val & SWAP_HAS_CACHE));
- if (val == SWAP_HAS_CACHE)
- free_entries++;
- }
- if (!free_entries) {
- for (i = 0; i < SWAPFILE_CLUSTER; i++)
- map[i] &= ~SWAP_HAS_CACHE;
+ ci = lock_cluster_or_swap_info(si, offset);
+ if (size == SWAPFILE_CLUSTER) {
+ VM_BUG_ON(!cluster_is_huge(ci));
+ map = si->swap_map + offset;
+ for (i = 0; i < SWAPFILE_CLUSTER; i++) {
+ val = map[i];
+ VM_BUG_ON(!(val & SWAP_HAS_CACHE));
+ if (val == SWAP_HAS_CACHE)
+ free_entries++;
+ }
+ cluster_clear_huge(ci);
+ if (free_entries == SWAPFILE_CLUSTER) {
+ unlock_cluster_or_swap_info(si, ci);
+ spin_lock(&si->lock);
+ mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER);
+ swap_free_cluster(si, idx);
+ spin_unlock(&si->lock);
+ return;
+ }
}
- cluster_clear_huge(ci);
- unlock_cluster(ci);
- if (free_entries == SWAPFILE_CLUSTER) {
- spin_lock(&si->lock);
- ci = lock_cluster(si, offset);
- memset(map, 0, SWAPFILE_CLUSTER);
- unlock_cluster(ci);
- mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER);
- swap_free_cluster(si, idx);
- spin_unlock(&si->lock);
- } else if (free_entries) {
- for (i = 0; i < SWAPFILE_CLUSTER; i++, entry.val++) {
- if (!__swap_entry_free(si, entry, SWAP_HAS_CACHE))
- free_swap_slot(entry);
+ for (i = 0; i < size; i++, entry.val++) {
+ if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) {
+ unlock_cluster_or_swap_info(si, ci);
+ free_swap_slot(entry);
+ if (i == size - 1)
+ return;
+ lock_cluster_or_swap_info(si, offset);
}
}
+ unlock_cluster_or_swap_info(si, ci);
}
+#ifdef CONFIG_THP_SWAP
int split_swap_cluster(swp_entry_t entry)
{
struct swap_info_struct *si;
unlock_cluster(ci);
return 0;
}
-#else
-static inline void swapcache_free_cluster(swp_entry_t entry)
-{
-}
-#endif /* CONFIG_THP_SWAP */
-
-void put_swap_page(struct page *page, swp_entry_t entry)
-{
- if (!PageTransHuge(page))
- swapcache_free(entry);
- else
- swapcache_free_cluster(entry);
-}
+#endif
static int swp_entry_cmp(const void *ent1, const void *ent2)
{
return count;
}
-#ifdef CONFIG_THP_SWAP
static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
swp_entry_t entry)
{
ci = lock_cluster_or_swap_info(si, offset);
if (!ci || !cluster_is_huge(ci)) {
- if (map[roffset] != SWAP_HAS_CACHE)
+ if (swap_count(map[roffset]))
ret = true;
goto unlock_out;
}
for (i = 0; i < SWAPFILE_CLUSTER; i++) {
- if (map[offset + i] != SWAP_HAS_CACHE) {
+ if (swap_count(map[offset + i])) {
ret = true;
break;
}
swp_entry_t entry;
struct swap_info_struct *si;
- if (likely(!PageTransCompound(page)))
+ if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page)))
return page_swapcount(page) != 0;
page = compound_head(page);
/* hugetlbfs shouldn't call it */
VM_BUG_ON_PAGE(PageHuge(page), page);
- if (likely(!PageTransCompound(page))) {
- mapcount = atomic_read(&page->_mapcount) + 1;
- if (total_mapcount)
- *total_mapcount = mapcount;
+ if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) {
+ mapcount = page_trans_huge_mapcount(page, total_mapcount);
if (PageSwapCache(page))
swapcount = page_swapcount(page);
if (total_swapcount)
return map_swapcount;
}
-#else
-#define swap_page_trans_huge_swapped(si, entry) swap_swapcount(si, entry)
-#define page_swapped(page) (page_swapcount(page) != 0)
-
-static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount,
- int *total_swapcount)
-{
- int mapcount, swapcount = 0;
-
- /* hugetlbfs shouldn't call it */
- VM_BUG_ON_PAGE(PageHuge(page), page);
-
- mapcount = page_trans_huge_mapcount(page, total_mapcount);
- if (PageSwapCache(page))
- swapcount = page_swapcount(page);
- if (total_swapcount)
- *total_swapcount = swapcount;
- return mapcount + swapcount;
-}
-#endif
/*
* We can write to an anon page without COW if there are no other references
int free_swap_and_cache(swp_entry_t entry)
{
struct swap_info_struct *p;
- struct page *page = NULL;
unsigned char count;
if (non_swap_entry(entry))
if (p) {
count = __swap_entry_free(p, entry, 1);
if (count == SWAP_HAS_CACHE &&
- !swap_page_trans_huge_swapped(p, entry)) {
- page = find_get_page(swap_address_space(entry),
- swp_offset(entry));
- if (page && !trylock_page(page)) {
- put_page(page);
- page = NULL;
- }
- } else if (!count)
- free_swap_slot(entry);
- }
- if (page) {
- /*
- * Not mapped elsewhere, or swap space full? Free it!
- * Also recheck PageSwapCache now page is locked (above).
- */
- if (PageSwapCache(page) && !PageWriteback(page) &&
- (!page_mapped(page) || mem_cgroup_swap_full(page)) &&
- !swap_page_trans_huge_swapped(p, entry)) {
- page = compound_head(page);
- delete_from_swap_cache(page);
- SetPageDirty(page);
- }
- unlock_page(page);
- put_page(page);
+ !swap_page_trans_huge_swapped(p, entry))
+ __try_to_reclaim_swap(p, swp_offset(entry),
+ TTRS_UNMAPPED | TTRS_FULL);
}
return p != NULL;
}
kfree(se);
}
- if (sis->flags & SWP_FILE) {
+ if (sis->flags & SWP_ACTIVATED) {
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;
- sis->flags &= ~SWP_FILE;
- mapping->a_ops->swap_deactivate(swap_file);
+ sis->flags &= ~SWP_ACTIVATED;
+ if (mapping->a_ops->swap_deactivate)
+ mapping->a_ops->swap_deactivate(swap_file);
}
}
list_add_tail(&new_se->list, &sis->first_swap_extent.list);
return 1;
}
+EXPORT_SYMBOL_GPL(add_swap_extent);
/*
* A `swap extent' is a simple thing which maps a contiguous range of pages
if (mapping->a_ops->swap_activate) {
ret = mapping->a_ops->swap_activate(sis, swap_file, span);
+ if (ret >= 0)
+ sis->flags |= SWP_ACTIVATED;
if (!ret) {
- sis->flags |= SWP_FILE;
+ sis->flags |= SWP_FS;
ret = add_swap_extent(sis, 0, sis->max, 0);
*span = sis->pages;
}
return 0;
}
+
+/*
+ * 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 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.
+ */
+unsigned long generic_max_swapfile_size(void)
+{
+ return swp_offset(pte_to_swp_entry(
+ swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+}
+
+/* Can be overridden by an architecture for additional checks. */
+__weak unsigned long max_swapfile_size(void)
+{
+ return generic_max_swapfile_size();
+}
+
static unsigned long read_swap_header(struct swap_info_struct *p,
union swap_header *swap_header,
struct inode *inode)
p->cluster_next = 1;
p->cluster_nr = 0;
- /*
- * 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 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;
+ maxpages = max_swapfile_size();
last_page = swap_header->info.last_page;
if (!last_page) {
pr_warn("Empty swap-file\n");
}
}
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
+ gfp_t gfp_mask)
+{
+ struct swap_info_struct *si, *next;
+ if (!(gfp_mask & __GFP_IO) || !memcg)
+ return;
+
+ if (!blk_cgroup_congested())
+ return;
+
+ /*
+ * We've already scheduled a throttle, avoid taking the global swap
+ * lock.
+ */
+ if (current->throttle_queue)
+ return;
+
+ spin_lock(&swap_avail_lock);
+ plist_for_each_entry_safe(si, next, &swap_avail_heads[node],
+ avail_lists[node]) {
+ if (si->bdev) {
+ blkcg_schedule_throttle(bdev_get_queue(si->bdev),
+ true);
+ break;
+ }
+ }
+ spin_unlock(&swap_avail_lock);
+}
+#endif
+
static int __init swapfile_init(void)
{
int nid;
projects / linux.git / blobdiff