Hole puching currently evicts pages from page cache and then goes on to remove blocks from the inode. This happens under both i_mmap_sem and i_rwsem held exclusively which provides appropriate serialization with racing page faults. However there is currently nothing that prevents ordinary read(2) from racing with the hole punch and instantiating page cache page after hole punching has evicted page cache but before it has removed blocks from the inode. This page cache page will be mapping soon to be freed block and that can lead to returning stale data to userspace or even filesystem corruption.
Fix the problem by protecting reads as well as readahead requests with i_mmap_sem.
CC: stable@vger.kernel.org Reported-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Jan Kara jack@suse.cz --- fs/ext4/file.c | 35 +++++++++++++++++++++++++++++++---- 1 file changed, 31 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 2c5baa5e8291..a21fa9f8fb5d 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -34,6 +34,17 @@ #include "xattr.h" #include "acl.h"
+static ssize_t ext4_file_buffered_read(struct kiocb *iocb, struct iov_iter *to) +{ + ssize_t ret; + struct inode *inode = file_inode(iocb->ki_filp); + + down_read(&EXT4_I(inode)->i_mmap_sem); + ret = generic_file_read_iter(iocb, to); + up_read(&EXT4_I(inode)->i_mmap_sem); + return ret; +} + #ifdef CONFIG_FS_DAX static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) { @@ -52,7 +63,7 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) if (!IS_DAX(inode)) { inode_unlock_shared(inode); /* Fallback to buffered IO in case we cannot support DAX */ - return generic_file_read_iter(iocb, to); + return ext4_file_buffered_read(iocb, to); } ret = dax_iomap_rw(iocb, to, &ext4_iomap_ops); inode_unlock_shared(inode); @@ -64,17 +75,32 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { - if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb)))) + struct inode *inode = file_inode(iocb->ki_filp); + + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO;
if (!iov_iter_count(to)) return 0; /* skip atime */
#ifdef CONFIG_FS_DAX - if (IS_DAX(file_inode(iocb->ki_filp))) + if (IS_DAX(inode)) return ext4_dax_read_iter(iocb, to); #endif - return generic_file_read_iter(iocb, to); + if (iocb->ki_flags & IOCB_DIRECT) + return generic_file_read_iter(iocb, to); + return ext4_file_buffered_read(iocb, to); +} + +static int ext4_readahead(struct file *filp, loff_t start, loff_t end) +{ + struct inode *inode = file_inode(filp); + int ret; + + down_read(&EXT4_I(inode)->i_mmap_sem); + ret = generic_readahead(filp, start, end); + up_read(&EXT4_I(inode)->i_mmap_sem); + return ret; }
/* @@ -518,6 +544,7 @@ const struct file_operations ext4_file_operations = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ext4_fallocate, + .readahead = ext4_readahead, };
const struct inode_operations ext4_file_inode_operations = {