[PATCH AUTOSEL 6.14 35/39] block: fix race between set_blocksize and read paths

[Sasha Levin <sashal@kernel.org>]

From: "Darrick J. Wong" <djwong@kernel.org>

[ Upstream commit c0e473a0d226479e8e925d5ba93f751d8df628e9 ]

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@frogsfrogsfrogs
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 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 9d73a8fbf7f99..06b8cab31d759 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -167,9 +167,26 @@ int set_blocksize(struct file *file, int size)
 
 	/* Don't change the size if it is same as current */
 	if (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(inode);
+		filemap_invalidate_lock(inode->i_mapping);
+
 		sync_blockdev(bdev);
+		kill_bdev(bdev);
+
 		inode->i_blkbits = blksize_bits(size);
 		kill_bdev(bdev);
+		filemap_invalidate_unlock(inode->i_mapping);
+		inode_unlock(inode);
 	}
 	return 0;
 }
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 0c77244a35c92..8f15d1aa6eb89 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -343,6 +343,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		op = REQ_OP_ZONE_RESET;
 
 		/* Invalidate the page cache, including dirty pages. */
+		inode_lock(bdev->bd_mapping->host);
 		filemap_invalidate_lock(bdev->bd_mapping);
 		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
 		if (ret)
@@ -364,8 +365,10 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
 
 fail:
-	if (cmd == BLKRESETZONE)
+	if (cmd == BLKRESETZONE) {
 		filemap_invalidate_unlock(bdev->bd_mapping);
+		inode_unlock(bdev->bd_mapping->host);
+	}
 
 	return ret;
 }
diff --git a/block/fops.c b/block/fops.c
index be9f1dbea9ce0..e221fdcaa8aaf 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -746,7 +746,14 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			ret = direct_write_fallback(iocb, from, ret,
 					blkdev_buffered_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 = blkdev_buffered_write(iocb, from);
+		inode_unlock_shared(bd_inode);
 	}
 
 	if (ret > 0)
@@ -757,6 +764,7 @@ 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 inode *bd_inode = bdev_file_inode(iocb->ki_filp);
 	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	loff_t size = bdev_nr_bytes(bdev);
 	loff_t pos = iocb->ki_pos;
@@ -793,7 +801,13 @@ 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))
@@ -836,6 +850,7 @@ 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);
 
 	/*
@@ -868,6 +883,7 @@ 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 6554b728bae6a..919066b4bb49c 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -141,6 +141,7 @@ 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)
@@ -173,6 +174,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 	blk_finish_plug(&plug);
 fail:
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 
@@ -198,12 +200,14 @@ 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;
 }
 
@@ -235,6 +239,7 @@ 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)
@@ -245,6 +250,7 @@ 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;
 }
 
-- 
2.39.5