userns: userns: check user namespace for task->file uid equivalence checks

Cheat for now and say all files belong to init_user_ns.  Next step will be
to let superblocks belong to a user_ns, and derive inode_userns(inode)
from inode->i_sb->s_user_ns.  Finally we'll introduce more flexible
arrangements.

Changelog:
	Feb 15: make is_owner_or_cap take const struct inode
	Feb 23: make is_owner_or_cap bool

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 40 insertions, 7 deletions

diff --git a/fs/inode.c b/fs/inode.c
index 16fefd373fc2..a21d5a938a17 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -25,6 +25,7 @@
 #include <linux/async.h>
 #include <linux/posix_acl.h>
 #include <linux/ima.h>
+#include <linux/cred.h>
 
 /*
  * This is needed for the following functions:
@@ -1733,3 +1734,19 @@ void inode_init_owner(struct inode *inode, const struct inode *dir,
         inode->i_mode = mode;
 }
 EXPORT_SYMBOL(inode_init_owner);
+
+/*
+ * return true if current either has CAP_FOWNER to the
+ * file, or owns the file.
+ */
+bool is_owner_or_cap(const struct inode *inode)
+{
+        struct user_namespace *ns = inode_userns(inode);
+
+        if (current_user_ns() == ns && current_fsuid() == inode->i_uid)
+                return true;
+        if (ns_capable(ns, CAP_FOWNER))
+                return true;
+        return false;
+}
+EXPORT_SYMBOL(is_owner_or_cap);
diff --git a/fs/namei.c b/fs/namei.c
index 5a9a6c3094da..dbb45a652ae3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -183,6 +183,9 @@ static int acl_permission_check(struct inode *inode, int mask, unsigned int flag
 
         mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 
+        if (current_user_ns() != inode_userns(inode))
+                goto other_perms;
+
         if (current_fsuid() == inode->i_uid)
                 mode >>= 6;
         else {
@@ -196,6 +199,7 @@ static int acl_permission_check(struct inode *inode, int mask, unsigned int flag
                         mode >>= 3;
         }
 
+other_perms:
         /*
          * If the DACs are ok we don't need any capability check.
          */
@@ -237,7 +241,7 @@ int generic_permission(struct inode *inode, int mask, unsigned int flags,
          * Executable DACs are overridable if at least one exec bit is set.
          */
         if (!(mask & MAY_EXEC) || execute_ok(inode))
-                if (capable(CAP_DAC_OVERRIDE))
+                if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE))
                         return 0;
 
         /*
@@ -245,7 +249,7 @@ int generic_permission(struct inode *inode, int mask, unsigned int flags,
          */
         mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
         if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
-                if (capable(CAP_DAC_READ_SEARCH))
+                if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH))
                         return 0;
 
         return -EACCES;
@@ -654,6 +658,7 @@ static inline int handle_reval_path(struct nameidata *nd)
 static inline int exec_permission(struct inode *inode, unsigned int flags)
 {
         int ret;
+        struct user_namespace *ns = inode_userns(inode);
 
         if (inode->i_op->permission) {
                 ret = inode->i_op->permission(inode, MAY_EXEC, flags);
@@ -666,7 +671,8 @@ static inline int exec_permission(struct inode *inode, unsigned int flags)
         if (ret == -ECHILD)
                 return ret;
 
-        if (capable(CAP_DAC_OVERRIDE) || capable(CAP_DAC_READ_SEARCH))
+        if (ns_capable(ns, CAP_DAC_OVERRIDE) ||
+                        ns_capable(ns, CAP_DAC_READ_SEARCH))
                 goto ok;
 
         return ret;
@@ -1842,11 +1848,15 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
 
         if (!(dir->i_mode & S_ISVTX))
                 return 0;
+        if (current_user_ns() != inode_userns(inode))
+                goto other_userns;
         if (inode->i_uid == fsuid)
                 return 0;
         if (dir->i_uid == fsuid)
                 return 0;
-        return !capable(CAP_FOWNER);
+
+other_userns:
+        return !ns_capable(inode_userns(inode), CAP_FOWNER);
 }
 
 /*
@@ -2440,7 +2450,8 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
         if (error)
                 return error;
 
-        if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
+        if ((S_ISCHR(mode) || S_ISBLK(mode)) &&
+            !ns_capable(inode_userns(dir), CAP_MKNOD))
                 return -EPERM;
 
         if (!dir->i_op->mknod)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 12529e966350..9eebc646d14a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1457,8 +1457,13 @@ enum {
 #define put_fs_excl() atomic_dec(&current->fs_excl)
 #define has_fs_excl() atomic_read(&current->fs_excl)
 
-#define is_owner_or_cap(inode)  \
-        ((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER))
+/*
+ * until VFS tracks user namespaces for inodes, just make all files
+ * belong to init_user_ns
+ */
+extern struct user_namespace init_user_ns;
+#define inode_userns(inode) (&init_user_ns)
+extern bool is_owner_or_cap(const struct inode *inode);
 
 /* not quite ready to be deprecated, but... */
 extern void lock_super(struct super_block *);