From d80411dea6a43adc8fd92c9c39e367f44aba1be9 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 12 Dec 2016 08:21:51 -0700 Subject: block_dev: don't test bdev->bd_contains when it is not stable commit bcc7f5b4bee8e327689a4d994022765855c807ff upstream. bdev->bd_contains is not stable before calling __blkdev_get(). When __blkdev_get() is called on a parition with ->bd_openers == 0 it sets bdev->bd_contains = bdev; which is not correct for a partition. After a call to __blkdev_get() succeeds, ->bd_openers will be > 0 and then ->bd_contains is stable. When FMODE_EXCL is used, blkdev_get() calls bd_start_claiming() -> bd_prepare_to_claim() -> bd_may_claim() This call happens before __blkdev_get() is called, so ->bd_contains is not stable. So bd_may_claim() cannot safely use ->bd_contains. It currently tries to use it, and this can lead to a BUG_ON(). This happens when a whole device is already open with a bd_holder (in use by dm in my particular example) and two threads race to open a partition of that device for the first time, one opening with O_EXCL and one without. The thread that doesn't use O_EXCL gets through blkdev_get() to __blkdev_get(), gains the ->bd_mutex, and sets bdev->bd_contains = bdev; Immediately thereafter the other thread, using FMODE_EXCL, calls bd_start_claiming() from blkdev_get(). This should fail because the whole device has a holder, but because bdev->bd_contains == bdev bd_may_claim() incorrectly reports success. This thread continues and blocks on bd_mutex. The first thread then sets bdev->bd_contains correctly and drops the mutex. The thread using FMODE_EXCL then continues and when it calls bd_may_claim() again in: BUG_ON(!bd_may_claim(bdev, whole, holder)); The BUG_ON fires. Fix this by removing the dependency on ->bd_contains in bd_may_claim(). As bd_may_claim() has direct access to the whole device, it can simply test if the target bdev is the whole device. Fixes: 6b4517a7913a ("block: implement bd_claiming and claiming block") Signed-off-by: NeilBrown Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/block_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 44d4a1e9244e..f10dbac851a1 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -759,7 +759,7 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, return true; /* already a holder */ else if (bdev->bd_holder != NULL) return false; /* held by someone else */ - else if (bdev->bd_contains == bdev) + else if (whole == bdev) return true; /* is a whole device which isn't held */ else if (whole->bd_holder == bd_may_claim) -- cgit v1.2.3 From f4f02a856a92e1a2990a8d0f55d08a78a29c3cc0 Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Thu, 1 Dec 2016 09:18:28 +0100 Subject: block: protect iterate_bdevs() against concurrent close commit af309226db916e2c6e08d3eba3fa5c34225200c4 upstream. 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: [] 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:[] [] 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: [] __filemap_fdatawrite_range+0x85/0x90 [] filemap_fdatawrite+0x1f/0x30 [] fdatawrite_one_bdev+0x16/0x20 [] iterate_bdevs+0xf2/0x130 [] sys_sync+0x63/0x90 [] 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 [] blk_get_backing_dev_info+0x10/0x20 RSP 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. Fixes: 5c0d6b60a0ba ("vfs: Create function for iterating over block devices") Reported-and-tested-by: Wei Fang Signed-off-by: Rabin Vincent Signed-off-by: Jan Kara Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/block_dev.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index f10dbac851a1..198aea66fe71 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1806,6 +1806,7 @@ 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) || @@ -1826,8 +1827,12 @@ 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); } -- cgit v1.2.3