vfs: fix data corruption when blocksize < pagesize for mmaped data

commit 90a8020278c1598fafd071736a0846b38510309c upstream.

->page_mkwrite() is used by filesystems to allocate blocks under a page
which is becoming writeably mmapped in some process' address space. This
allows a filesystem to return a page fault if there is not enough space
available, user exceeds quota or similar problem happens, rather than
silently discarding data later when writepage is called.

However VFS fails to call ->page_mkwrite() in all the cases where
filesystems need it when blocksize < pagesize. For example when
blocksize = 1024, pagesize = 4096 the following is problematic:
  ftruncate(fd, 0);
  pwrite(fd, buf, 1024, 0);
  map = mmap(NULL, 1024, PROT_WRITE, MAP_SHARED, fd, 0);
  map[0] = 'a';       ----> page_mkwrite() for index 0 is called
  ftruncate(fd, 10000); /* or even pwrite(fd, buf, 1, 10000) */
  mremap(map, 1024, 10000, 0);
  map[4095] = 'a';    ----> no page_mkwrite() called

At the moment ->page_mkwrite() is called, filesystem can allocate only
one block for the page because i_size == 1024. Otherwise it would create
blocks beyond i_size which is generally undesirable. But later at
->writepage() time, we also need to store data at offset 4095 but we
don't have block allocated for it.

This patch introduces a helper function filesystems can use to have
->page_mkwrite() called at all the necessary moments.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
[lizf: Backported to 3.4:
 - adjust context
 - truncate_setsize() already has an oldsize variable]
Signed-off-by: Zefan Li <lizefan@huawei.com>

1 files changed, 59 insertions, 3 deletions

diff --git a/mm/truncate.c b/mm/truncate.c
index f38055cb8af6..708a499c49a8 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -20,6 +20,7 @@
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 
@@ -571,16 +572,71 @@ EXPORT_SYMBOL(truncate_pagecache);
  */
 void truncate_setsize(struct inode *inode, loff_t newsize)
 {
-	loff_t oldsize;
-
-	oldsize = inode->i_size;
+	loff_t oldsize = inode->i_size;
 	i_size_write(inode, newsize);
 
+	if (newsize > oldsize)
+		pagecache_isize_extended(inode, oldsize, newsize);
 	truncate_pagecache(inode, oldsize, newsize);
 }
 EXPORT_SYMBOL(truncate_setsize);
 
 /**
+ * pagecache_isize_extended - update pagecache after extension of i_size
+ * @inode:	inode for which i_size was extended
+ * @from:	original inode size
+ * @to:		new inode size
+ *
+ * Handle extension of inode size either caused by extending truncate or by
+ * write starting after current i_size. We mark the page straddling current
+ * i_size RO so that page_mkwrite() is called on the nearest write access to
+ * the page.  This way filesystem can be sure that page_mkwrite() is called on
+ * the page before user writes to the page via mmap after the i_size has been
+ * changed.
+ *
+ * The function must be called after i_size is updated so that page fault
+ * coming after we unlock the page will already see the new i_size.
+ * The function must be called while we still hold i_mutex - this not only
+ * makes sure i_size is stable but also that userspace cannot observe new
+ * i_size value before we are prepared to store mmap writes at new inode size.
+ */
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
+{
+	int bsize = 1 << inode->i_blkbits;
+	loff_t rounded_from;
+	struct page *page;
+	pgoff_t index;
+
+	WARN_ON(!mutex_is_locked(&inode->i_mutex));
+	WARN_ON(to > inode->i_size);
+
+	if (from >= to || bsize == PAGE_CACHE_SIZE)
+		return;
+	/* Page straddling @from will not have any hole block created? */
+	rounded_from = round_up(from, bsize);
+	if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
+		return;
+
+	index = from >> PAGE_CACHE_SHIFT;
+	page = find_lock_page(inode->i_mapping, index);
+	/* Page not cached? Nothing to do */
+	if (!page)
+		return;
+	/*
+	 * See clear_page_dirty_for_io() for details why set_page_dirty()
+	 * is needed.
+	 */
+	if (page_mkclean(page))
+		set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+}
+EXPORT_SYMBOL(pagecache_isize_extended);
+
+/**
+ * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
+ * @inode: inode
+ * @lstart: offset of beginning of hole
  * vmtruncate - unmap mappings "freed" by truncate() syscall
  * @inode: inode of the file used
  * @newsize: file offset to start truncating