NFS: Fix a write request leak in nfs_invalidate_page()

Ryusuke Konishi says:

The recent truncate_complete_page() clears the dirty flag from a page
before calling a_ops->invalidatepage(),
^^^^^^
static void
truncate_complete_page(struct address_space *mapping, struct page *page)
{
        ...
        cancel_dirty_page(page, PAGE_CACHE_SIZE);  <--- Inserted here at
kernel 2.6.20

        if (PagePrivate(page))
                do_invalidatepage(page, 0);   ---> will call
a_ops->invalidatepage()
        ...
}

and this is disturbing nfs_wb_page_priority() from calling 
nfs_writepage_locked() that is expected to handle the pending
request (=nfs_page) associated with the page.

int nfs_wb_page_priority(struct inode *inode, struct page *page, int how)
{
        ...
        if (clear_page_dirty_for_io(page)) {
                ret = nfs_writepage_locked(page, &wbc);
                if (ret < 0)
                        goto out;
        }
        ...
}

Since truncate_complete_page() will get rid of the page after
a_ops->invalidatepage() returns, the request (=nfs_page) associated
with the page becomes a garbage in nfs_inode->nfs_page_tree.
------------------------

Fix this by ensuring that nfs_wb_page_priority() recognises that it may
also need to clear out non-dirty pages that have an nfs_page associated
with them.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

fs/nfs/file.c

@@ -316,7 +316,7 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 	if (offset != 0)
 		return;
 	/* Cancel any unstarted writes on this page */
-	nfs_wb_page_priority(page->mapping->host, page, FLUSH_INVALIDATE);
+	nfs_wb_page_cancel(page->mapping->host, page);
 }
 
 static int nfs_release_page(struct page *page, gfp_t gfp)

fs/nfs/write.c

@@ -1396,6 +1396,50 @@ int nfs_sync_mapping_range(struct address_space *mapping, loff_t range_start, lo
 	return ret;
 }
 
+int nfs_wb_page_cancel(struct inode *inode, struct page *page)
+{
+	struct nfs_page *req;
+	loff_t range_start = page_offset(page);
+	loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
+	struct writeback_control wbc = {
+		.bdi = page->mapping->backing_dev_info,
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = LONG_MAX,
+		.range_start = range_start,
+		.range_end = range_end,
+	};
+	int ret = 0;
+
+	BUG_ON(!PageLocked(page));
+	for (;;) {
+		req = nfs_page_find_request(page);
+		if (req == NULL)
+			goto out;
+		if (test_bit(PG_NEED_COMMIT, &req->wb_flags)) {
+			nfs_release_request(req);
+			break;
+		}
+		if (nfs_lock_request_dontget(req)) {
+			nfs_inode_remove_request(req);
+			/*
+			 * In case nfs_inode_remove_request has marked the
+			 * page as being dirty
+			 */
+			cancel_dirty_page(page, PAGE_CACHE_SIZE);
+			nfs_unlock_request(req);
+			break;
+		}
+		ret = nfs_wait_on_request(req);
+		if (ret < 0)
+			goto out;
+	}
+	if (!PagePrivate(page))
+		return 0;
+	ret = nfs_sync_mapping_wait(page->mapping, &wbc, FLUSH_INVALIDATE);
+out:
+	return ret;
+}
+
 int nfs_wb_page_priority(struct inode *inode, struct page *page, int how)
 {
 	loff_t range_start = page_offset(page);

include/linux/nfs_fs.h

@@ -431,6 +431,7 @@ extern int nfs_sync_mapping_range(struct address_space *, loff_t, loff_t, int);
 extern int nfs_wb_all(struct inode *inode);
 extern int nfs_wb_page(struct inode *inode, struct page* page);
 extern int nfs_wb_page_priority(struct inode *inode, struct page* page, int how);
+extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 extern int  nfs_commit_inode(struct inode *, int);
 extern struct nfs_write_data *nfs_commit_alloc(void);