mm/swap: fix race on swap_info reuse between swapoff and swapon

commit f893ab41e4dae2fe8991faf5d86d029068d1ef3a upstream.

swapoff clear swap_info's SWP_USED flag prematurely and free its
resources after that.  A concurrent swapon will reuse this swap_info
while its previous resources are not cleared completely.

These late freed resources are:
 - p->percpu_cluster
 - swap_cgroup_ctrl[type]
 - block_device setting
 - inode->i_flags &= ~S_SWAPFILE

This patch clears the SWP_USED flag after all its resources are freed,
so that swapon can reuse this swap_info by alloc_swap_info() safely.

[akpm@linux-foundation.org: tidy up code comment]
Signed-off-by: Weijie Yang <weijie.yang@samsung.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/mm/swapfile.c b/mm/swapfile.c
index fad1830..dbd2b67 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1649,7 +1649,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
        p->max = 0;
        swap_map = p->swap_map;
        p->swap_map = NULL;
-       p->flags = 0;
        spin_unlock(&swap_lock);
        mutex_unlock(&swapon_mutex);
        vfree(swap_map);
@@ -1667,6 +1666,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
                mutex_unlock(&inode->i_mutex);
        }
        filp_close(swap_file, NULL);
+
+       /*
+        * Clear the SWP_USED flag after all resources are freed so that swapon
+        * can reuse this swap_info in alloc_swap_info() safely.  It is ok to
+        * not hold p->lock after we cleared its SWP_WRITEOK.
+        */
+       spin_lock(&swap_lock);
+       p->flags = 0;
+       spin_unlock(&swap_lock);
+
        err = 0;
        atomic_inc(&proc_poll_event);
        wake_up_interruptible(&proc_poll_wait);