From 5d47a35600270e7115061cb1320ee60ae9bcb6b8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 7 Feb 2008 17:24:07 -0500 Subject: NFS: Fix a potential file corruption issue when writing If the inode is flagged as having an invalid mapping, then we can't rely on the PageUptodate() flag. Ensure that we don't use the "anti-fragmentation" write optimisation in nfs_updatepage(), since that will cause NFS to write out areas of the page that are no longer guaranteed to be up to date. A potential corruption could occur in the following scenario: client 1 client 2 =============== =============== fd=open("f",O_CREAT|O_WRONLY,0644); write(fd,"fubar\n",6); // cache last page close(fd); fd=open("f",O_WRONLY|O_APPEND); write(fd,"foo\n",4); close(fd); fd=open("f",O_WRONLY|O_APPEND); write(fd,"bar\n",4); close(fd); ----- The bug may lead to the file "f" reading 'fubar\n\0\0\0\nbar\n' because client 2 does not update the cached page after re-opening the file for write. Instead it keeps it marked as PageUptodate() until someone calls invaldate_inode_pages2() (typically by calling read()). Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index b144b1957dd..f55c437124a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -696,6 +696,17 @@ int nfs_flush_incompatible(struct file *file, struct page *page) return status; } +/* + * If the page cache is marked as unsafe or invalid, then we can't rely on + * the PageUptodate() flag. In this case, we will need to turn off + * write optimisations that depend on the page contents being correct. + */ +static int nfs_write_pageuptodate(struct page *page, struct inode *inode) +{ + return PageUptodate(page) && + !(NFS_I(inode)->cache_validity & (NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA)); +} + /* * Update and possibly write a cached page of an NFS file. * @@ -717,10 +728,13 @@ int nfs_updatepage(struct file *file, struct page *page, (long long)(page_offset(page) +offset)); /* If we're not using byte range locks, and we know the page - * is entirely in cache, it may be more efficient to avoid - * fragmenting write requests. + * is up to date, it may be more efficient to extend the write + * to cover the entire page in order to avoid fragmentation + * inefficiencies. */ - if (PageUptodate(page) && inode->i_flock == NULL && !(file->f_mode & O_SYNC)) { + if (nfs_write_pageuptodate(page, inode) && + inode->i_flock == NULL && + !(file->f_mode & O_SYNC)) { count = max(count + offset, nfs_page_length(page)); offset = 0; } -- cgit v1.2.3