swap: revert special hibernation allocation

Please revert 2.6.36-rc commit d2997b1042
"hibernation: freeze swap at hibernation".  It complicated matters by
adding a second swap allocation path, just for hibernation; without in any
way fixing the issue that it was intended to address - page reclaim after
fixing the hibernation image might free swap from a page already imaged as
swapcache, letting its swap be reallocated to store a different page of
the image: resulting in data corruption if the imaged page were freed as
clean then swapped back in.  Pages freed to si->swap_map were still in
danger of being reallocated by the alternative allocation path.

I guess it inadvertently fixed slow SSD swap allocation for hibernation,
as reported by Nigel Cunningham: by missing out the discards that occur on
the usual swap allocation path; but that was unintentional, and needs a
separate fix.

Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Ondrej Zary <linux@rainbow-software.org>
Cc: Andrea Gelmini <andrea.gelmini@gmail.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Nigel Cunningham <nigel@tuxonice.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/swapfile.c

@@ -47,8 +47,6 @@ long nr_swap_pages;
 long total_swap_pages;
 static int least_priority;
 
-static bool swap_for_hibernation;
-
 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 ";
@@ -453,8 +451,6 @@ swp_entry_t get_swap_page(void)
 	spin_lock(&swap_lock);
 	if (nr_swap_pages <= 0)
 		goto noswap;
-	if (swap_for_hibernation)
-		goto noswap;
 	nr_swap_pages--;
 
 	for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
@@ -487,6 +483,28 @@ noswap:
 	return (swp_entry_t) {0};
 }
 
+/* The only caller of this function is now susupend routine */
+swp_entry_t get_swap_page_of_type(int type)
+{
+	struct swap_info_struct *si;
+	pgoff_t offset;
+
+	spin_lock(&swap_lock);
+	si = swap_info[type];
+	if (si && (si->flags & SWP_WRITEOK)) {
+		nr_swap_pages--;
+		/* This is called for allocating swap entry, not cache */
+		offset = scan_swap_map(si, 1);
+		if (offset) {
+			spin_unlock(&swap_lock);
+			return swp_entry(type, offset);
+		}
+		nr_swap_pages++;
+	}
+	spin_unlock(&swap_lock);
+	return (swp_entry_t) {0};
+}
+
 static struct swap_info_struct *swap_info_get(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
@@ -746,74 +764,6 @@ int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep)
 #endif
 
 #ifdef CONFIG_HIBERNATION
-
-static pgoff_t hibernation_offset[MAX_SWAPFILES];
-/*
- * Once hibernation starts to use swap, we freeze swap_map[]. Otherwise,
- * saved swap_map[] image to the disk will be an incomplete because it's
- * changing without synchronization with hibernation snap shot.
- * At resume, we just make swap_for_hibernation=false. We can forget
- * used maps easily.
- */
-void hibernation_freeze_swap(void)
-{
-	int i;
-
-	spin_lock(&swap_lock);
-
-	printk(KERN_INFO "PM: Freeze Swap\n");
-	swap_for_hibernation = true;
-	for (i = 0; i < MAX_SWAPFILES; i++)
-		hibernation_offset[i] = 1;
-	spin_unlock(&swap_lock);
-}
-
-void hibernation_thaw_swap(void)
-{
-	spin_lock(&swap_lock);
-	if (swap_for_hibernation) {
-		printk(KERN_INFO "PM: Thaw Swap\n");
-		swap_for_hibernation = false;
-	}
-	spin_unlock(&swap_lock);
-}
-
-/*
- * Because updateing swap_map[] can make not-saved-status-change,
- * we use our own easy allocator.
- * Please see kernel/power/swap.c, Used swaps are recorded into
- * RB-tree.
- */
-swp_entry_t get_swap_for_hibernation(int type)
-{
-	pgoff_t off;
-	swp_entry_t val = {0};
-	struct swap_info_struct *si;
-
-	spin_lock(&swap_lock);
-
-	si = swap_info[type];
-	if (!si || !(si->flags & SWP_WRITEOK))
-		goto done;
-
-	for (off = hibernation_offset[type]; off < si->max; ++off) {
-		if (!si->swap_map[off])
-			break;
-	}
-	if (off < si->max) {
-		val = swp_entry(type, off);
-		hibernation_offset[type] = off + 1;
-	}
-done:
-	spin_unlock(&swap_lock);
-	return val;
-}
-
-void swap_free_for_hibernation(swp_entry_t ent)
-{
-	/* Nothing to do */
-}
-
 /*
  * Find the swap type that corresponds to given device (if any).
  *