summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>2010-08-09 17:20:11 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-08-09 20:45:04 -0700
commitd2997b1042ec150616c1963b5e5e919ffd0b0ebf (patch)
treec970746ad3d5c3e0ccbd1695d07144dbe4534ec4 /mm
parent966cca029f739716fbcc8068b8c6dfe381f86fc3 (diff)
downloadblackbird-op-linux-d2997b1042ec150616c1963b5e5e919ffd0b0ebf.tar.gz
blackbird-op-linux-d2997b1042ec150616c1963b5e5e919ffd0b0ebf.zip
hibernation: freeze swap at hibernation
When taking a memory snapshot in hibernate_snapshot(), all (directly called) memory allocations use GFP_ATOMIC. Hence swap misusage during hibernation never occurs. But from a pessimistic point of view, there is no guarantee that no page allcation has __GFP_WAIT. It is better to have a global indication "we enter hibernation, don't use swap!". This patch tries to freeze new-swap-allocation during hibernation. (All user processes are frozenm so swapin is not a concern). This way, no updates will happen to swap_map[] between hibernate_snapshot() and save_image(). Swap is thawed when swsusp_free() is called. We can be assured that swap corruption will not occur. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Hugh Dickins <hughd@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ondrej Zary <linux@rainbow-software.org> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/swapfile.c94
1 files changed, 72 insertions, 22 deletions
diff --git a/mm/swapfile.c b/mm/swapfile.c
index f08d165871b3..1f3f9c59a73a 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -47,6 +47,8 @@ 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 ";
@@ -451,6 +453,8 @@ 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) {
@@ -483,28 +487,6 @@ 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;
@@ -764,6 +746,74 @@ 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).
*
OpenPOWER on IntegriCloud