===
mounting stacked ecryptfs on ecryptfs has been shown to lead to bugs
in testing. For crypto info in xattr, there is no mechanism for handling
this at all, and for normal file headers, we run into other trouble:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
IP: [<ffffffffa015b0b3>] ecryptfs_d_revalidate+0x43/0xa0 [ecryptfs]
...
There doesn't seem to be any good usecase for this, so I'd suggest just
disallowing the configuration.
Based on a patch originally, I believe, from Mike Halcrow.
===
This is a backport of commit 4403158ba295c8e36f6736b1bb12d0f7e1923dac
https://bugs.launchpad.net/ubuntu/+bug/932987
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Colin Ian King <colin.king@canonical.com>
---
fs/ecryptfs/main.c | 8 ++++++++
1 files changed, 8 insertions(+), 0 deletions(-)
@@ -496,6 +496,7 @@ out:
}
struct kmem_cache *ecryptfs_sb_info_cache;
+static struct file_system_type ecryptfs_fs_type;
/**
* ecryptfs_fill_super
@@ -571,6 +572,13 @@ static int ecryptfs_read_super(struct super_block *sb, const char *dev_name,
ecryptfs_printk(KERN_WARNING, "path_lookup() failed\n");
goto out;
}
+ if (path.dentry->d_sb->s_type == &ecryptfs_fs_type) {
+ rc = -EINVAL;
+ printk(KERN_ERR "Mount on filesystem of type "
+ "eCryptfs explicitly disallowed due to "
+ "known incompatibilities\n");
+ goto out_free;
+ }
if (check_ruid && path.dentry->d_inode->i_uid != current_uid()) {
rc = -EPERM;
From: Colin Ian King <colin.king@canonical.com> This is a seriously simplified patch from Eric Sandeen; copy of rationale follows: