| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1244488987-32564-49-git-send-email-tytso@mit.edu>
Date: Mon, 8 Jun 2009 15:23:06 -0400
From: Theodore Ts'o <tytso@....edu>
To: Linux Kernel Developers List <linux-kernel@...r.kernel.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>,
Jan Kara <jack@...e.cz>, "Theodore Ts'o" <tytso@....edu>
Subject: [PATCH 48/49] ext4: truncate the file properly if we fail to copy data from userspace
From: Aneesh Kumar K.V <aneesh.kumar@...ux.vnet.ibm.com>
In generic_perform_write if we fail to copy the user data we don't
update the inode->i_size. We should truncate the file in the above
case so that we don't have blocks allocated outside inode->i_size. Add
the inode to orphan list in the same transaction as block allocation
This ensures that if we crash in between the recovery would do the
truncate.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@...ux.vnet.ibm.com>
CC: Jan Kara <jack@...e.cz>
Signed-off-by: "Theodore Ts'o" <tytso@....edu>
---
fs/ext4/inode.c | 128 +++++++++++++++++++++++++++++++++++++++++++-----------
1 files changed, 102 insertions(+), 26 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 036552a..5dc6c3d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1552,6 +1552,52 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh)
return ext4_handle_dirty_metadata(handle, NULL, bh);
}
+static int ext4_generic_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ int i_size_changed = 0;
+ struct inode *inode = mapping->host;
+ handle_t *handle = ext4_journal_current_handle();
+
+ copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+ /*
+ * No need to use i_size_read() here, the i_size
+ * cannot change under us because we hold i_mutex.
+ *
+ * But it's important to update i_size while still holding page lock:
+ * page writeout could otherwise come in and zero beyond i_size.
+ */
+ if (pos + copied > inode->i_size) {
+ i_size_write(inode, pos + copied);
+ i_size_changed = 1;
+ }
+
+ if (pos + copied > EXT4_I(inode)->i_disksize) {
+ /* We need to mark inode dirty even if
+ * new_i_size is less that inode->i_size
+ * bu greater than i_disksize.(hint delalloc)
+ */
+ ext4_update_i_disksize(inode, (pos + copied));
+ i_size_changed = 1;
+ }
+ unlock_page(page);
+ page_cache_release(page);
+
+ /*
+ * Don't mark the inode dirty under page lock. First, it unnecessarily
+ * makes the holding time of page lock longer. Second, it forces lock
+ * ordering of page lock and transaction start for journaling
+ * filesystems.
+ */
+ if (i_size_changed)
+ ext4_mark_inode_dirty(handle, inode);
+
+ return copied;
+}
+
/*
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
@@ -1575,21 +1621,15 @@ static int ext4_ordered_write_end(struct file *file,
ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
- loff_t new_i_size;
-
- new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize) {
- ext4_update_i_disksize(inode, new_i_size);
- /* We need to mark inode dirty even if
- * new_i_size is less that inode->i_size
- * bu greater than i_disksize.(hint delalloc)
- */
- ext4_mark_inode_dirty(handle, inode);
- }
-
- ret2 = generic_write_end(file, mapping, pos, len, copied,
+ ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = ret2;
+ if (pos + len > inode->i_size)
+ /* if we have allocated more blocks and copied
+ * less. We will have blocks allocated outside
+ * inode->i_size. So truncate them
+ */
+ ext4_orphan_add(handle, inode);
if (ret2 < 0)
ret = ret2;
}
@@ -1597,6 +1637,18 @@ static int ext4_ordered_write_end(struct file *file,
if (!ret)
ret = ret2;
+ if (pos + len > inode->i_size) {
+ vmtruncate(inode, inode->i_size);
+ /*
+ * If vmtruncate failed early the inode might still be
+ * on the orphan list; we need to make sure the inode
+ * is removed from the orphan list in that case.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+ }
+
+
return ret ? ret : copied;
}
@@ -1608,25 +1660,21 @@ static int ext4_writeback_write_end(struct file *file,
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
int ret = 0, ret2;
- loff_t new_i_size;
trace_mark(ext4_writeback_write_end,
"dev %s ino %lu pos %llu len %u copied %u",
inode->i_sb->s_id, inode->i_ino,
(unsigned long long) pos, len, copied);
- new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize) {
- ext4_update_i_disksize(inode, new_i_size);
- /* We need to mark inode dirty even if
- * new_i_size is less that inode->i_size
- * bu greater than i_disksize.(hint delalloc)
- */
- ext4_mark_inode_dirty(handle, inode);
- }
-
- ret2 = generic_write_end(file, mapping, pos, len, copied,
+ ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = ret2;
+ if (pos + len > inode->i_size)
+ /* if we have allocated more blocks and copied
+ * less. We will have blocks allocated outside
+ * inode->i_size. So truncate them
+ */
+ ext4_orphan_add(handle, inode);
+
if (ret2 < 0)
ret = ret2;
@@ -1634,6 +1682,17 @@ static int ext4_writeback_write_end(struct file *file,
if (!ret)
ret = ret2;
+ if (pos + len > inode->i_size) {
+ vmtruncate(inode, inode->i_size);
+ /*
+ * If vmtruncate failed early the inode might still be
+ * on the orphan list; we need to make sure the inode
+ * is removed from the orphan list in that case.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+ }
+
return ret ? ret : copied;
}
@@ -1678,10 +1737,27 @@ static int ext4_journalled_write_end(struct file *file,
}
unlock_page(page);
+ page_cache_release(page);
+ if (pos + len > inode->i_size)
+ /* if we have allocated more blocks and copied
+ * less. We will have blocks allocated outside
+ * inode->i_size. So truncate them
+ */
+ ext4_orphan_add(handle, inode);
+
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
- page_cache_release(page);
+ if (pos + len > inode->i_size) {
+ vmtruncate(inode, inode->i_size);
+ /*
+ * If vmtruncate failed early the inode might still be
+ * on the orphan list; we need to make sure the inode
+ * is removed from the orphan list in that case.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+ }
return ret ? ret : copied;
}
--
1.6.3.2.1.gb9f7d.dirty
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists