From: "Darrick J. Wong" djwong@kernel.org
commit c0e473a0d226479e8e925d5ba93f751d8df628e9 upstream.
With the new large sector size support, it's now the case that set_blocksize can change i_blksize and the folio order in a manner that conflicts with a concurrent reader and causes a kernel crash.
Specifically, let's say that udev-worker calls libblkid to detect the labels on a block device. The read call can create an order-0 folio to read the first 4096 bytes from the disk. But then udev is preempted.
Next, someone tries to mount an 8k-sectorsize filesystem from the same block device. The filesystem calls set_blksize, which sets i_blksize to 8192 and the minimum folio order to 1.
Now udev resumes, still holding the order-0 folio it allocated. It then tries to schedule a read bio and do_mpage_readahead tries to create bufferheads for the folio. Unfortunately, blocks_per_folio == 0 because the page size is 4096 but the blocksize is 8192 so no bufferheads are attached and the bh walk never sets bdev. We then submit the bio with a NULL block device and crash.
Therefore, truncate the page cache after flushing but before updating i_blksize. However, that's not enough -- we also need to lock out file IO and page faults during the update. Take both the i_rwsem and the invalidate_lock in exclusive mode for invalidations, and in shared mode for read/write operations.
I don't know if this is the correct fix, but xfs/259 found it.
Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Luis Chamberlain mcgrof@kernel.org Tested-by: Shin'ichiro Kawasaki shinichiro.kawasaki@wdc.com Link: https://lore.kernel.org/r/174543795699.4139148.2086129139322431423.stgit@fro... Signed-off-by: Jens Axboe axboe@kernel.dk [use bdev->bd_inode instead & fix small contextual changes] Signed-off-by: Mahmoud Adam mngyadam@amazon.de --- block/bdev.c | 17 +++++++++++++++++ block/blk-zoned.c | 5 ++++- block/fops.c | 16 ++++++++++++++++ block/ioctl.c | 6 ++++++ 4 files changed, 43 insertions(+), 1 deletion(-)
diff --git a/block/bdev.c b/block/bdev.c index b61502ec8da06c..5a631a0ca46a81 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -147,9 +147,26 @@ int set_blocksize(struct block_device *bdev, int size)
/* Don't change the size if it is same as current */ if (bdev->bd_inode->i_blkbits != blksize_bits(size)) { + /* + * Flush and truncate the pagecache before we reconfigure the + * mapping geometry because folio sizes are variable now. If a + * reader has already allocated a folio whose size is smaller + * than the new min_order but invokes readahead after the new + * min_order becomes visible, readahead will think there are + * "zero" blocks per folio and crash. Take the inode and + * invalidation locks to avoid racing with + * read/write/fallocate. + */ + inode_lock(bdev->bd_inode); + filemap_invalidate_lock(bdev->bd_inode->i_mapping); + sync_blockdev(bdev); + kill_bdev(bdev); + bdev->bd_inode->i_blkbits = blksize_bits(size); kill_bdev(bdev); + filemap_invalidate_unlock(bdev->bd_inode->i_mapping); + inode_unlock(bdev->bd_inode); } return 0; } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index db829401d8d0ca..ef72612ca4645f 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -417,6 +417,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, op = REQ_OP_ZONE_RESET;
/* Invalidate the page cache, including dirty pages. */ + inode_lock(bdev->bd_inode); filemap_invalidate_lock(bdev->bd_inode->i_mapping); ret = blkdev_truncate_zone_range(bdev, mode, &zrange); if (ret) @@ -439,8 +440,10 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, GFP_KERNEL);
fail: - if (cmd == BLKRESETZONE) + if (cmd == BLKRESETZONE) { filemap_invalidate_unlock(bdev->bd_inode->i_mapping); + inode_unlock(bdev->bd_inode); + }
return ret; } diff --git a/block/fops.c b/block/fops.c index fb7a57ed42d995..2fc6ac6679ee63 100644 --- a/block/fops.c +++ b/block/fops.c @@ -592,7 +592,14 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = direct_write_fallback(iocb, from, ret, generic_perform_write(iocb, from)); } else { + /* + * Take i_rwsem and invalidate_lock to avoid racing with + * set_blocksize changing i_blkbits/folio order and punching + * out the pagecache. + */ + inode_lock_shared(bd_inode); ret = generic_perform_write(iocb, from); + inode_unlock_shared(bd_inode); }
if (ret > 0) @@ -605,6 +612,7 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct block_device *bdev = iocb->ki_filp->private_data; + struct inode *bd_inode = bdev->bd_inode; loff_t size = bdev_nr_bytes(bdev); loff_t pos = iocb->ki_pos; size_t shorted = 0; @@ -652,7 +660,13 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) goto reexpand; }
+ /* + * Take i_rwsem and invalidate_lock to avoid racing with set_blocksize + * changing i_blkbits/folio order and punching out the pagecache. + */ + inode_lock_shared(bd_inode); ret = filemap_read(iocb, to, ret); + inode_unlock_shared(bd_inode);
reexpand: if (unlikely(shorted)) @@ -695,6 +709,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, if ((start | len) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL;
+ inode_lock(inode); filemap_invalidate_lock(inode->i_mapping);
/* @@ -735,6 +750,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
fail: filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); return error; }
diff --git a/block/ioctl.c b/block/ioctl.c index 552da0ccbec09e..b37bbe9b3487d8 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -114,6 +114,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, end > bdev_nr_bytes(bdev)) return -EINVAL;
+ inode_lock(inode); filemap_invalidate_lock(inode->i_mapping); err = truncate_bdev_range(bdev, mode, start, end - 1); if (err) @@ -121,6 +122,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, err = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL); fail: filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); return err; }
@@ -146,12 +148,14 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode, end > bdev_nr_bytes(bdev)) return -EINVAL;
+ inode_lock(bdev->bd_inode); filemap_invalidate_lock(bdev->bd_inode->i_mapping); err = truncate_bdev_range(bdev, mode, start, end - 1); if (!err) err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9, GFP_KERNEL); filemap_invalidate_unlock(bdev->bd_inode->i_mapping); + inode_unlock(bdev->bd_inode); return err; }
@@ -184,6 +188,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, return -EINVAL;
/* Invalidate the page cache, including dirty pages */ + inode_lock(inode); filemap_invalidate_lock(inode->i_mapping); err = truncate_bdev_range(bdev, mode, start, end); if (err) @@ -194,6 +199,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
fail: filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); return err; }