virtio_balloon: fix race between migration and ballooning

commit 21ea9fb69e7c4b1b1559c3e410943d3ff248ffcb upstream.

In balloon_page_dequeue, pages_lock should cover the loop
(ie, list_for_each_entry_safe). Otherwise, the cursor page could
be isolated by compaction and then list_del by isolation could
poison the page->lru.{prev,next} so the loop finally could
access wrong address like this. This patch fixes the bug.

general protection fault: 0000 [#1] SMP
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 2 PID: 82 Comm: vballoon Not tainted 4.4.0-rc5-mm1-access_bit+ #1906
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
task: ffff8800a7ff0000 ti: ffff8800a7fec000 task.ti: ffff8800a7fec000
RIP: 0010:[<ffffffff8115e754>]  [<ffffffff8115e754>] balloon_page_dequeue+0x54/0x130
RSP: 0018:ffff8800a7fefdc0  EFLAGS: 00010246
RAX: ffff88013fff9a70 RBX: ffffea000056fe00 RCX: 0000000000002b7d
RDX: ffff88013fff9a70 RSI: ffffea000056fe00 RDI: ffff88013fff9a68
RBP: ffff8800a7fefde8 R08: ffffea000056fda0 R09: 0000000000000000
R10: ffff8800a7fefd90 R11: 0000000000000001 R12: dead0000000000e0
R13: ffffea000056fe20 R14: ffff880138809070 R15: ffff880138809060
FS:  0000000000000000(0000) GS:ffff88013fc40000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00007f229c10e000 CR3: 00000000b8b53000 CR4: 00000000000006a0
Stack:
 0000000000000100 ffff880138809088 ffff880138809000 ffff880138809060
 0000000000000046 ffff8800a7fefe28 ffffffff812c86d3 ffff880138809020
 ffff880138809000 fffffffffff91900 0000000000000100 ffff880138809060
Call Trace:
 [<ffffffff812c86d3>] leak_balloon+0x93/0x1a0
 [<ffffffff812c8bc7>] balloon+0x217/0x2a0
 [<ffffffff8143739e>] ? __schedule+0x31e/0x8b0
 [<ffffffff81078160>] ? abort_exclusive_wait+0xb0/0xb0
 [<ffffffff812c89b0>] ? update_balloon_stats+0xf0/0xf0
 [<ffffffff8105b6e9>] kthread+0xc9/0xe0
 [<ffffffff8105b620>] ? kthread_park+0x60/0x60
 [<ffffffff8143b4af>] ret_from_fork+0x3f/0x70
 [<ffffffff8105b620>] ? kthread_park+0x60/0x60
Code: 8d 60 e0 0f 84 af 00 00 00 48 8b 43 20 a8 01 75 3b 48 89 d8 f0 0f ba 28 00 72 10 48 8b 03 f6 c4 08 75 2f 48 89 df e8 8c 83 f9 ff <49> 8b 44 24 20 4d 8d 6c 24 20 48 83 e8 20 4d 39 f5 74 7a 4c 89
RIP  [<ffffffff8115e754>] balloon_page_dequeue+0x54/0x130
 RSP <ffff8800a7fefdc0>
---[ end trace 43cf28060d708d5f ]---
Kernel panic - not syncing: Fatal exception
Dumping ftrace buffer:
   (ftrace buffer empty)
Kernel Offset: disabled

Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>

diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 6e45a5074bf023b85896b1feb01198a5f1c652ff..9b0f218af70ba26d4960c759cc390cce63e96dae 100644 (file)
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -86,6 +86,7 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
        bool dequeued_page;
 
        dequeued_page = false;
+       spin_lock_irqsave(&b_dev_info->pages_lock, flags);
        list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) {
                /*
                 * Block others from accessing the 'page' while we get around
@@ -93,7 +94,6 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
                 * to be released by the balloon driver.
                 */
                if (trylock_page(page)) {
-                       spin_lock_irqsave(&b_dev_info->pages_lock, flags);
                        /*
                         * Raise the page refcount here to prevent any wrong
                         * attempt to isolate this page, in case of coliding
@@ -105,12 +105,12 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
                         */
                        get_page(page);
                        balloon_page_delete(page);
-                       spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
                        unlock_page(page);
                        dequeued_page = true;
                        break;
                }
        }
+       spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 
        if (!dequeued_page) {
                /*