linux-kernel - Re: mm: sleeping function called from invalid context shmem_undo

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 31 Jan 2017 12:31:41 +0300
From:   "Kirill A. Shutemov" <kirill@...temov.name>
To:     Dmitry Vyukov <dvyukov@...gle.com>
Cc:     Hugh Dickins <hughd@...gle.com>,
        "linux-mm@...ck.org" <linux-mm@...ck.org>,
        LKML <linux-kernel@...r.kernel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Johannes Weiner <hannes@...xchg.org>,
        Vlastimil Babka <vbabka@...e.cz>,
        Andrey Ryabinin <aryabinin@...tuozzo.com>,
        syzkaller <syzkaller@...glegroups.com>
Subject: Re: mm: sleeping function called from invalid context
 shmem_undo_range

On Tue, Jan 31, 2017 at 09:27:41AM +0100, Dmitry Vyukov wrote:
> Hello,
> 
> I've got the following report while running syzkaller fuzzer on
> fd694aaa46c7ed811b72eb47d5eb11ce7ab3f7f1:

This should help:

>From fb85b3fe273decb11c558d56257193424b8f071a Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Date: Tue, 31 Jan 2017 12:22:26 +0300
Subject: [PATCH] shmem: fix sleeping from atomic context

Syzkaller fuzzer managed to trigger this:

BUG: sleeping function called from invalid context at mm/shmem.c:852
in_atomic(): 1, irqs_disabled(): 0, pid: 529, name: khugepaged
3 locks held by khugepaged/529:
 #0:  (shrinker_rwsem){++++..}, at: [<ffffffff818d7ef1>]
shrink_slab.part.59+0x121/0xd30 mm/vmscan.c:451
 #1:  (&type->s_umount_key#29){++++..}, at: [<ffffffff81a63630>]
trylock_super+0x20/0x100 fs/super.c:392
 #2:  (&(&sbinfo->shrinklist_lock)->rlock){+.+.-.}, at:
[<ffffffff818fd83e>] spin_lock include/linux/spinlock.h:302 [inline]
 #2:  (&(&sbinfo->shrinklist_lock)->rlock){+.+.-.}, at:
[<ffffffff818fd83e>] shmem_unused_huge_shrink+0x28e/0x1490
mm/shmem.c:427
CPU: 2 PID: 529 Comm: khugepaged Not tainted 4.10.0-rc5+ #201
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
 ___might_sleep+0x47e/0x650 kernel/sched/core.c:7780
 shmem_undo_range+0xb20/0x2710 mm/shmem.c:852
 shmem_truncate_range+0x27/0xa0 mm/shmem.c:939
 shmem_evict_inode+0x35f/0xca0 mm/shmem.c:1030
 evict+0x46e/0x980 fs/inode.c:553
 iput_final fs/inode.c:1515 [inline]
 iput+0x589/0xb20 fs/inode.c:1542
 shmem_unused_huge_shrink+0xbad/0x1490 mm/shmem.c:446
 shmem_unused_huge_scan+0x10c/0x170 mm/shmem.c:512
 super_cache_scan+0x376/0x450 fs/super.c:106
 do_shrink_slab mm/vmscan.c:378 [inline]
 shrink_slab.part.59+0x543/0xd30 mm/vmscan.c:481
 shrink_slab mm/vmscan.c:2592 [inline]
 shrink_node+0x2c7/0x870 mm/vmscan.c:2592
 shrink_zones mm/vmscan.c:2734 [inline]
 do_try_to_free_pages+0x369/0xc80 mm/vmscan.c:2776
 try_to_free_pages+0x3c6/0x900 mm/vmscan.c:2982
 __perform_reclaim mm/page_alloc.c:3301 [inline]
 __alloc_pages_direct_reclaim mm/page_alloc.c:3322 [inline]
 __alloc_pages_slowpath+0xa24/0x1c30 mm/page_alloc.c:3683
 __alloc_pages_nodemask+0x544/0xae0 mm/page_alloc.c:3848
 __alloc_pages include/linux/gfp.h:426 [inline]
 __alloc_pages_node include/linux/gfp.h:439 [inline]
 khugepaged_alloc_page+0xc2/0x1b0 mm/khugepaged.c:750
 collapse_huge_page+0x182/0x1fe0 mm/khugepaged.c:955
 khugepaged_scan_pmd+0xfdf/0x12a0 mm/khugepaged.c:1208
 khugepaged_scan_mm_slot mm/khugepaged.c:1727 [inline]
 khugepaged_do_scan mm/khugepaged.c:1808 [inline]
 khugepaged+0xe9b/0x1590 mm/khugepaged.c:1853
 kthread+0x326/0x3f0 kernel/kthread.c:227
 ret_from_fork+0x31/0x40 arch/x86/entry/entry_64.S:430

The iput() from atomic context was a bad idea: if after igrab() somebody
else calls iput() and we left with the last inode reference, our iput()
would lead to inode eviction and therefore sleeping.

This patch should fix the situation.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
Reported-by: Dmitry Vyukov <dvyukov@...gle.com>
---
 mm/shmem.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 3c9be716083f..54d1ebfb577d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -415,6 +415,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 		struct shrink_control *sc, unsigned long nr_to_split)
 {
 	LIST_HEAD(list), *pos, *next;
+	LIST_HEAD(to_remove);
 	struct inode *inode;
 	struct shmem_inode_info *info;
 	struct page *page;
@@ -441,9 +442,8 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 		/* Check if there's anything to gain */
 		if (round_up(inode->i_size, PAGE_SIZE) ==
 				round_up(inode->i_size, HPAGE_PMD_SIZE)) {
-			list_del_init(&info->shrinklist);
+			list_move(&info->shrinklist, &to_remove);
 			removed++;
-			iput(inode);
 			goto next;
 		}
 
@@ -454,6 +454,13 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 	}
 	spin_unlock(&sbinfo->shrinklist_lock);
 
+	list_for_each_safe(pos, next, &to_remove) {
+		info = list_entry(pos, struct shmem_inode_info, shrinklist);
+		inode = &info->vfs_inode;
+		list_del_init(&info->shrinklist);
+		iput(inode);
+	}
+
 	list_for_each_safe(pos, next, &list) {
 		int ret;
 
-- 
 Kirill A. Shutemov