1
0
Fork 0

Smack: fix d_instantiate logic for sockfs and pipefs

Since 4b936885a (v2.6.32) all inodes on sockfs and pipefs are disconnected.
It caused filesystem specific code in smack_d_instantiate to be skipped,
because all inodes on those pseudo filesystems were treated as root inodes.
As a result all sockfs inodes had the Smack label set to floor.

In most cases access checks for sockets use socket_smack data so the inode
label is not important. But there are special cases that were broken.
One example would be calling fcntl with F_SETOWN command on a socket fd.

Now smack_d_instantiate expects all pipefs and sockfs inodes to be
disconnected and has the logic in appropriate place.

Signed-off-by: Rafal Krypa <r.krypa@samsung.com>
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
zero-colors
Rafal Krypa 2016-12-09 14:03:04 +01:00 committed by Casey Schaufler
parent c9d238a18b
commit 805b65a80b
1 changed files with 7 additions and 7 deletions

View File

@ -3486,6 +3486,13 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
case PIPEFS_MAGIC:
isp->smk_inode = smk_of_current();
break;
case SOCKFS_MAGIC:
/*
* Socket access is controlled by the socket
* structures associated with the task involved.
*/
isp->smk_inode = &smack_known_star;
break;
default:
isp->smk_inode = sbsp->smk_root;
break;
@ -3502,19 +3509,12 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
*/
switch (sbp->s_magic) {
case SMACK_MAGIC:
case PIPEFS_MAGIC:
case SOCKFS_MAGIC:
case CGROUP_SUPER_MAGIC:
/*
* Casey says that it's a little embarrassing
* that the smack file system doesn't do
* extended attributes.
*
* Casey says pipes are easy (?)
*
* Socket access is controlled by the socket
* structures associated with the task involved.
*
* Cgroupfs is special
*/
final = &smack_known_star;