block: protect iterate_bdevs() against concurrent close

If a block device is closed while iterate_bdevs() is handling it, the
following NULL pointer dereference occurs because bdev->b_disk is NULL
in bdev_get_queue(), which is called from blk_get_backing_dev_info() (in
turn called by the mapping_cap_writeback_dirty() call in
__filemap_fdatawrite_range()):

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000508
 IP: [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20
 PGD 9e62067 PUD 9ee8067 PMD 0
 Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
 Modules linked in:
 CPU: 1 PID: 2422 Comm: sync Not tainted 4.5.0-rc7+ #400
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
 task: ffff880009f4d700 ti: ffff880009f5c000 task.ti: ffff880009f5c000
 RIP: 0010:[<ffffffff81314790>]  [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20
 RSP: 0018:ffff880009f5fe68  EFLAGS: 00010246
 RAX: 0000000000000000 RBX: ffff88000ec17a38 RCX: ffffffff81a4e940
 RDX: 7fffffffffffffff RSI: 0000000000000000 RDI: ffff88000ec176c0
 RBP: ffff880009f5fe68 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000001 R11: 0000000000000000 R12: ffff88000ec17860
 R13: ffffffff811b25c0 R14: ffff88000ec178e0 R15: ffff88000ec17a38
 FS:  00007faee505d700(0000) GS:ffff88000fb00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
 CR2: 0000000000000508 CR3: 0000000009e8a000 CR4: 00000000000006e0
 Stack:
  ffff880009f5feb8 ffffffff8112e7f5 0000000000000000 7fffffffffffffff
  0000000000000000 0000000000000000 7fffffffffffffff 0000000000000001
  ffff88000ec178e0 ffff88000ec17860 ffff880009f5fec8 ffffffff8112e81f
 Call Trace:
  [<ffffffff8112e7f5>] __filemap_fdatawrite_range+0x85/0x90
  [<ffffffff8112e81f>] filemap_fdatawrite+0x1f/0x30
  [<ffffffff811b25d6>] fdatawrite_one_bdev+0x16/0x20
  [<ffffffff811bc402>] iterate_bdevs+0xf2/0x130
  [<ffffffff811b2763>] sys_sync+0x63/0x90
  [<ffffffff815d4272>] entry_SYSCALL_64_fastpath+0x12/0x76
 Code: 0f 1f 44 00 00 48 8b 87 f0 00 00 00 55 48 89 e5 <48> 8b 80 08 05 00 00 5d
 RIP  [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20
  RSP <ffff880009f5fe68>
 CR2: 0000000000000508
 ---[ end trace 2487336ceb3de62d ]---

The crash is easily reproducible by running the following command, if an
msleep(100) is inserted before the call to func() in iterate_devs():

 while :; do head -c1 /dev/nullb0; done > /dev/null & while :; do sync; done

Fix it by holding the bd_mutex across the func() call and only calling
func() if the bdev is opened.

Cc: stable@vger.kernel.org
Fixes: 5c0d6b60a0ba ("vfs: Create function for iterating over block devices")
Reported-and-tested-by: Wei Fang <fangwei1@huawei.com>
Signed-off-by: Rabin Vincent <rabinv@axis.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7022ddc..95acbd2 100644 (file)
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -2207,6 +2207,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
        spin_lock(&blockdev_superblock->s_inode_list_lock);
        list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
                struct address_space *mapping = inode->i_mapping;
+               struct block_device *bdev;
 
                spin_lock(&inode->i_lock);
                if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
@@ -2227,8 +2228,12 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
                 */
                iput(old_inode);
                old_inode = inode;
+               bdev = I_BDEV(inode);
 
-               func(I_BDEV(inode), arg);
+               mutex_lock(&bdev->bd_mutex);
+               if (bdev->bd_openers)
+                       func(bdev, arg);
+               mutex_unlock(&bdev->bd_mutex);
 
                spin_lock(&blockdev_superblock->s_inode_list_lock);
        }