From c0e473a0d226479e8e925d5ba93f751d8df628e9 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 23 Apr 2025 12:53:42 -0700 Subject: block: fix race between set_blocksize and read paths 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 Reviewed-by: Christoph Hellwig Reviewed-by: Luis Chamberlain Tested-by: Shin'ichiro Kawasaki Link: https://lore.kernel.org/r/174543795699.4139148.2086129139322431423.stgit@frogsfrogsfrogs Signed-off-by: Jens Axboe --- block/ioctl.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'block/ioctl.c') diff --git a/block/ioctl.c b/block/ioctl.c index faa40f383e27..e472cc1030c6 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -142,6 +142,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, if (err) return err; + inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) @@ -174,6 +175,7 @@ out_unplug: blk_finish_plug(&plug); fail: filemap_invalidate_unlock(bdev->bd_mapping); + inode_unlock(bdev->bd_mapping->host); return err; } @@ -199,12 +201,14 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode, end > bdev_nr_bytes(bdev)) return -EINVAL; + inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_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_mapping); + inode_unlock(bdev->bd_mapping->host); return err; } @@ -236,6 +240,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, return -EINVAL; /* Invalidate the page cache, including dirty pages */ + inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, end); if (err) @@ -246,6 +251,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, fail: filemap_invalidate_unlock(bdev->bd_mapping); + inode_unlock(bdev->bd_mapping->host); return err; } -- cgit v1.2.3