@@ -2587,7 +2587,8 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
if ((iocb->ki_flags & IOCB_WAITQ) && already_read)
iocb->ki_flags |= IOCB_NOWAIT;
- if (unlikely(iocb->ki_pos >= i_size_read(inode)))
+ isize = i_size_read(inode);
+ if (unlikely(iocb->ki_pos >= isize))
break;
error = filemap_get_pages(iocb, iter->count, &fbatch, false);
@@ -2602,7 +2603,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
* part of the page is not copied back to userspace (unless
* another truncate extends the file - this is desired though).
*/
- isize = i_size_read(inode);
+ isize = min_t(loff_t, isize, i_size_read(inode));
if (unlikely(iocb->ki_pos >= isize))
goto put_folios;
end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
When DIO write and buffered read are performed on the same file on two CPUs, the following race may occur: cpu1 cpu2 Direct write 1024 from 4096 | Buffered read 8192 from 0 -----------------------------|---------------------------- ... ... ext4_file_write_iter ext4_dio_write_iter iomap_dio_rw ... ext4_file_read_iter generic_file_read_iter filemap_read filemap_get_pages ... ext4_mpage_readpages ext4_readpage_limit(inode) i_size_read(inode) // 4096 ext4_dio_write_end_io i_size_write(inode, 5120) i_size_read(inode) // 5120 1. read alloc 8192 0 8192 |-------------------|-------------------| 2. read form disk (i_size 4096) 0 filled data 4096 filled zero 8192 |-------------------|-------------------| 3. copyout (i_size 5120) 0 copyout to uset buffer 5120 8192 |------------------------|--------------| |~~~~| Inconsistent data In the above race, because of the change of inode_size, the actual data read from the disk is only 4096 bytes, but copied to the user's buffer 5120 bytes, including 1024 bytes of zero-filled tail page, which results in the data read by the user is not consistent with the data on the disk. To solve this problem completely, we should take the lesser of the number of bytes actually read or the inode_size and use that as the final read size. The problem here is that we don't know how many bytes of valid data filemap_get_pages() reads, or how many bytes of valid data are in a page, so we have to rely on inode_size to determine the range of valid data. So we read the inode_size before and after filemap_get_pages(), and take the smaller of the two as the size of the copyout to reduce the probability of the above issue being triggered. Signed-off-by: Baokun Li <libaokun1@huawei.com> --- mm/filemap.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)