[PATCH] NFS: Fix races in nfs_revalidate_mapping()

Prevent the call to invalidate_inode_pages2() from racing with file writes
by taking the inode->i_mutex across the page cache flush and invalidate.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/nfs/dir.c

@@ -532,7 +532,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 
 	lock_kernel();
 
-	res = nfs_revalidate_mapping(inode, filp->f_mapping);
+	res = nfs_revalidate_mapping_nolock(inode, filp->f_mapping);
 	if (res < 0) {
 		unlock_kernel();
 		return res;

fs/nfs/inode.c

@@ -665,34 +665,14 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 	return __nfs_revalidate_inode(server, inode);
 }
 
-/**
- * nfs_revalidate_mapping - Revalidate the pagecache
- * @inode - pointer to host inode
- * @mapping - pointer to mapping
- */
-int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
-	int ret = 0;
 	
-	if (NFS_STALE(inode))
-		ret = -ESTALE;
-	if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
-			|| nfs_attribute_timeout(inode))
-		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
-	if (ret < 0)
-		goto out;
-
-	if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
 	if (mapping->nrpages != 0) {
-			if (S_ISREG(inode->i_mode)) {
-				ret = nfs_sync_mapping(mapping);
-				if (ret < 0)
-					goto out;
-			}
-			ret = invalidate_inode_pages2(mapping);
+		int ret = invalidate_inode_pages2(mapping);
 		if (ret < 0)
-				goto out;
+			return ret;
 	}
 	spin_lock(&inode->i_lock);
 	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
@@ -702,12 +682,69 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 		nfsi->cache_change_attribute = jiffies;
 	}
 	spin_unlock(&inode->i_lock);
-
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
 	dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
-				inode->i_sb->s_id,
-				(long long)NFS_FILEID(inode));
+			inode->i_sb->s_id, (long long)NFS_FILEID(inode));
+	return 0;
+}
+
+static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
+{
+	int ret = 0;
+
+	mutex_lock(&inode->i_mutex);
+	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_DATA) {
+		ret = nfs_sync_mapping(mapping);
+		if (ret == 0)
+			ret = nfs_invalidate_mapping_nolock(inode, mapping);
+	}
+	mutex_unlock(&inode->i_mutex);
+	return ret;
+}
+
+/**
+ * nfs_revalidate_mapping_nolock - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
+ */
+int nfs_revalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	int ret = 0;
+
+	if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
+			|| nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
+		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+		if (ret < 0)
+			goto out;
+	}
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+		ret = nfs_invalidate_mapping_nolock(inode, mapping);
+out:
+	return ret;
+}
+
+/**
+ * nfs_revalidate_mapping - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
+ *
+ * This version of the function will take the inode->i_mutex and attempt to
+ * flush out all dirty data if it needs to invalidate the page cache.
+ */
+int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	int ret = 0;
+
+	if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
+			|| nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
+		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+		if (ret < 0)
+			goto out;
 	}
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+		ret = nfs_invalidate_mapping(inode, mapping);
 out:
 	return ret;
 }

fs/nfs/symlink.c

@@ -50,7 +50,9 @@ static void *nfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
 	struct inode *inode = dentry->d_inode;
 	struct page *page;
-	void *err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
+	void *err;
+
+	err = ERR_PTR(nfs_revalidate_mapping_nolock(inode, inode->i_mapping));
 	if (err)
 		goto read_failed;
 	page = read_cache_page(&inode->i_data, 0,

include/linux/nfs_fs.h

@@ -308,6 +308,7 @@ extern int nfs_attribute_timeout(struct inode *inode);
 extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
 extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
+extern int nfs_revalidate_mapping_nolock(struct inode *inode, struct address_space *mapping);
 extern int nfs_setattr(struct dentry *, struct iattr *);
 extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr);
 extern void nfs_begin_attr_update(struct inode *);