summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2014-10-01 21:49:18 -0400
committerTheodore Ts'o <tytso@mit.edu>2014-10-01 21:49:18 -0400
commit90a8020278c1598fafd071736a0846b38510309c (patch)
tree2ab461b549a2b5f6b933895b1e61eb98627bba94
parentf6e63f90809946d410c42045577cb159fedabf8c (diff)
vfs: fix data corruption when blocksize < pagesize for mmaped data
->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> Cc: stable@vger.kernel.org
-rw-r--r--fs/buffer.c3
-rw-r--r--include/linux/mm.h1
-rw-r--r--mm/truncate.c57
3 files changed, 61 insertions, 0 deletions
diff --git a/fs/buffer.c b/fs/buffer.c
index 9a6029e0dd71..6dc1475dcb2d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2087,6 +2087,7 @@ int generic_write_end(struct file *file, struct address_space *mapping,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
+ loff_t old_size = inode->i_size;
int i_size_changed = 0;
copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
@@ -2106,6 +2107,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
unlock_page(page);
page_cache_release(page);
+ if (old_size < pos)
+ pagecache_isize_extended(inode, old_size, pos);
/*
* Don't mark the inode dirty under page lock. First, it unnecessarily
* makes the holding time of page lock longer. Second, it forces lock
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8981cc882ed2..5005464fe012 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1155,6 +1155,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
extern void truncate_pagecache(struct inode *inode, loff_t new);
extern void truncate_setsize(struct inode *inode, loff_t newsize);
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
int truncate_inode_page(struct address_space *mapping, struct page *page);
int generic_error_remove_page(struct address_space *mapping, struct page *page);
diff --git a/mm/truncate.c b/mm/truncate.c
index 96d167372d89..261eaf6e5a19 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"
static void clear_exceptional_entry(struct address_space *mapping,
@@ -719,12 +720,68 @@ EXPORT_SYMBOL(truncate_pagecache);
*/
void truncate_setsize(struct inode *inode, loff_t newsize)
{
+ loff_t oldsize = inode->i_size;
+
i_size_write(inode, newsize);
+ if (newsize > oldsize)
+ pagecache_isize_extended(inode, oldsize, newsize);
truncate_pagecache(inode, 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