1 files changed, 46 insertions, 53 deletions

diff --git a/mm/swapfile.c b/mm/swapfile.c
index fafc26d1b1dc..71373d03fcee 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -31,6 +31,8 @@
 #include <linux/memcontrol.h>
 #include <linux/poll.h>
 #include <linux/oom.h>
+#include <linux/frontswap.h>
+#include <linux/swapfile.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -42,7 +44,7 @@ static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
 static void free_swap_count_continuations(struct swap_info_struct *);
 static sector_t map_swap_entry(swp_entry_t, struct block_device**);
 
-static DEFINE_SPINLOCK(swap_lock);
+DEFINE_SPINLOCK(swap_lock);
 static unsigned int nr_swapfiles;
 long nr_swap_pages;
 long total_swap_pages;
@@ -53,9 +55,9 @@ 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 ";
 
-static struct swap_list_t swap_list = {-1, -1};
+struct swap_list_t swap_list = {-1, -1};
 
-static struct swap_info_struct *swap_info[MAX_SWAPFILES];
+struct swap_info_struct *swap_info[MAX_SWAPFILES];
 
 static DEFINE_MUTEX(swapon_mutex);
 
@@ -556,6 +558,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
                         swap_list.next = p->type;
                 nr_swap_pages++;
                 p->inuse_pages--;
+                frontswap_invalidate_page(p->type, offset);
                 if ((p->flags & SWP_BLKDEV) &&
                                 disk->fops->swap_slot_free_notify)
                         disk->fops->swap_slot_free_notify(p->bdev, offset);
@@ -601,7 +604,7 @@ void swapcache_free(swp_entry_t entry, struct page *page)
  * This does not give an exact answer when swap count is continued,
  * but does include the high COUNT_CONTINUED flag to allow for that.
  */
-static inline int page_swapcount(struct page *page)
+int page_swapcount(struct page *page)
 {
         int count = 0;
         struct swap_info_struct *p;
@@ -717,37 +720,6 @@ int free_swap_and_cache(swp_entry_t entry)
         return p != NULL;
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-/**
- * mem_cgroup_count_swap_user - count the user of a swap entry
- * @ent: the swap entry to be checked
- * @pagep: the pointer for the swap cache page of the entry to be stored
- *
- * Returns the number of the user of the swap entry. The number is valid only
- * for swaps of anonymous pages.
- * If the entry is found on swap cache, the page is stored to pagep with
- * refcount of it being incremented.
- */
-int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep)
-{
-        struct page *page;
-        struct swap_info_struct *p;
-        int count = 0;
-
-        page = find_get_page(&swapper_space, ent.val);
-        if (page)
-                count += page_mapcount(page);
-        p = swap_info_get(ent);
-        if (p) {
-                count += swap_count(p->swap_map[swp_offset(ent)]);
-                spin_unlock(&swap_lock);
-        }
-
-        *pagep = page;
-        return count;
-}
-#endif
-
 #ifdef CONFIG_HIBERNATION
 /*
  * Find the swap type that corresponds to given device (if any).
@@ -1016,11 +988,12 @@ static int unuse_mm(struct mm_struct *mm,
 }
 
 /*
- * Scan swap_map from current position to next entry still in use.
+ * Scan swap_map (or frontswap_map if frontswap parameter is true)
+ * from current position to next entry still in use.
  * Recycle to start on reaching the end, returning 0 when empty.
  */
 static unsigned int find_next_to_unuse(struct swap_info_struct *si,
-                                        unsigned int prev)
+                                        unsigned int prev, bool frontswap)
 {
         unsigned int max = si->max;
         unsigned int i = prev;
@@ -1046,6 +1019,12 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si,
                         prev = 0;
                         i = 1;
                 }
+                if (frontswap) {
+                        if (frontswap_test(si, i))
+                                break;
+                        else
+                                continue;
+                }
                 count = si->swap_map[i];
                 if (count && swap_count(count) != SWAP_MAP_BAD)
                         break;
@@ -1057,8 +1036,12 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si,
  * We completely avoid races by reading each swap page in advance,
  * and then search for the process using it.  All the necessary
  * page table adjustments can then be made atomically.
+ *
+ * if the boolean frontswap is true, only unuse pages_to_unuse pages;
+ * pages_to_unuse==0 means all pages; ignored if frontswap is false
  */
-static int try_to_unuse(unsigned int type)
+int try_to_unuse(unsigned int type, bool frontswap,
+                 unsigned long pages_to_unuse)
 {
         struct swap_info_struct *si = swap_info[type];
         struct mm_struct *start_mm;
@@ -1091,7 +1074,7 @@ static int try_to_unuse(unsigned int type)
          * one pass through swap_map is enough, but not necessarily:
          * there are races when an instance of an entry might be missed.
          */
-        while ((i = find_next_to_unuse(si, i)) != 0) {
+        while ((i = find_next_to_unuse(si, i, frontswap)) != 0) {
                 if (signal_pending(current)) {
                         retval = -EINTR;
                         break;
@@ -1258,6 +1241,10 @@ static int try_to_unuse(unsigned int type)
                  * interactive performance.
                  */
                 cond_resched();
+                if (frontswap && pages_to_unuse > 0) {
+                        if (!--pages_to_unuse)
+                                break;
+                }
         }
 
         mmput(start_mm);
@@ -1517,7 +1504,8 @@ bad_bmap:
 }
 
 static void enable_swap_info(struct swap_info_struct *p, int prio,
-                                unsigned char *swap_map)
+                                unsigned char *swap_map,
+                                unsigned long *frontswap_map)
 {
         int i, prev;
 
@@ -1527,6 +1515,7 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
         else
                 p->prio = --least_priority;
         p->swap_map = swap_map;
+        frontswap_map_set(p, frontswap_map);
         p->flags |= SWP_WRITEOK;
         nr_swap_pages += p->pages;
         total_swap_pages += p->pages;
@@ -1543,6 +1532,7 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
                 swap_list.head = swap_list.next = p->type;
         else
                 swap_info[prev]->next = p->type;
+        frontswap_init(p->type);
         spin_unlock(&swap_lock);
 }
 
@@ -1616,7 +1606,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
         spin_unlock(&swap_lock);
 
         oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
-        err = try_to_unuse(type);
+        err = try_to_unuse(type, false, 0); /* force all pages to be unused */
         compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);
 
         if (err) {
@@ -1627,7 +1617,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
                  * sys_swapoff for this swap_info_struct at this point.
                  */
                 /* re-insert swap space back into swap_list */
-                enable_swap_info(p, p->prio, p->swap_map);
+                enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p));
                 goto out_dput;
         }
 
@@ -1653,9 +1643,11 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
         swap_map = p->swap_map;
         p->swap_map = NULL;
         p->flags = 0;
+        frontswap_invalidate_area(type);
         spin_unlock(&swap_lock);
         mutex_unlock(&swapon_mutex);
         vfree(swap_map);
+        vfree(frontswap_map_get(p));
         /* Destroy swap account informatin */
         swap_cgroup_swapoff(type);
 
@@ -1924,24 +1916,20 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 
         /*
          * Find out how many pages are allowed for a single swap
-         * device. There are three limiting factors: 1) the number
+         * 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
-         * the different architectures, and 3) the number of free bits
-         * in an exceptional radix_tree entry. In order to find 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.  Then the same is done for a radix_tree entry.
+         * swap pte.
          */
         maxpages = swp_offset(pte_to_swp_entry(
-                        swp_entry_to_pte(swp_entry(0, ~0UL))));
-        maxpages = swp_offset(radix_to_swp_entry(
-                        swp_to_radix_entry(swp_entry(0, maxpages)))) + 1;
-
+                        swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
         if (maxpages > swap_header->info.last_page) {
                 maxpages = swap_header->info.last_page + 1;
                 /* p->max is an unsigned int: don't overflow it */
@@ -2019,6 +2007,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
         sector_t span;
         unsigned long maxpages;
         unsigned char *swap_map = NULL;
+        unsigned long *frontswap_map = NULL;
         struct page *page = NULL;
         struct inode *inode = NULL;
 
@@ -2102,6 +2091,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
                 error = nr_extents;
                 goto bad_swap;
         }
+        /* frontswap enabled? set up bit-per-page map for frontswap */
+        if (frontswap_enabled)
+                frontswap_map = vzalloc(maxpages / sizeof(long));
 
         if (p->bdev) {
                 if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {
@@ -2117,14 +2109,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
         if (swap_flags & SWAP_FLAG_PREFER)
                 prio =
                   (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
-        enable_swap_info(p, prio, swap_map);
+        enable_swap_info(p, prio, swap_map, frontswap_map);
 
         printk(KERN_INFO "Adding %uk swap on %s.  "
-                        "Priority:%d extents:%d across:%lluk %s%s\n",
+                        "Priority:%d extents:%d across:%lluk %s%s%s\n",
                 p->pages<<(PAGE_SHIFT-10), name, p->prio,
                 nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
                 (p->flags & SWP_SOLIDSTATE) ? "SS" : "",
-                (p->flags & SWP_DISCARDABLE) ? "D" : "");
+                (p->flags & SWP_DISCARDABLE) ? "D" : "",
+                (frontswap_map) ? "FS" : "");
 
         mutex_unlock(&swapon_mutex);
         atomic_inc(&proc_poll_event);