proc: Usable inode numbers for the namespace file descriptors.

Assign a unique proc inode to each namespace, and use that
inode number to ensure we only allocate at most one proc
inode for every namespace in proc.

A single proc inode per namespace allows userspace to test
to see if two processes are in the same namespace.

This has been a long requested feature and only blocked because
a naive implementation would put the id in a global space and
would ultimately require having a namespace for the names of
namespaces, making migration and certain virtualization tricks
impossible.

We still don't have per superblock inode numbers for proc, which
appears necessary for application unaware checkpoint/restart and
migrations (if the application is using namespace file descriptors)
but that is now allowd by the design if it becomes important.

I have preallocated the ipc and uts initial proc inode numbers so
their structures can be statically initialized.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>

1 files changed, 15 insertions, 0 deletions

diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 89f6eaed067..f5975ccf934 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -58,6 +58,7 @@ int create_user_ns(struct cred *new)
         struct user_namespace *ns, *parent_ns = new->user_ns;
         kuid_t owner = new->euid;
         kgid_t group = new->egid;
+        int ret;
 
         /* The creator needs a mapping in the parent user namespace
          * or else we won't be able to reasonably tell userspace who
@@ -71,6 +72,12 @@ int create_user_ns(struct cred *new)
         if (!ns)
                 return -ENOMEM;
 
+        ret = proc_alloc_inum(&ns->proc_inum);
+        if (ret) {
+                kmem_cache_free(user_ns_cachep, ns);
+                return ret;
+        }
+
         kref_init(&ns->kref);
         /* Leave the new->user_ns reference with the new user namespace. */
         ns->parent = parent_ns;
@@ -103,6 +110,7 @@ void free_user_ns(struct kref *kref)
                 container_of(kref, struct user_namespace, kref);
 
         parent = ns->parent;
+        proc_free_inum(ns->proc_inum);
         kmem_cache_free(user_ns_cachep, ns);
         put_user_ns(parent);
 }
@@ -808,12 +816,19 @@ static int userns_install(struct nsproxy *nsproxy, void *ns)
         return commit_creds(cred);
 }
 
+static unsigned int userns_inum(void *ns)
+{
+        struct user_namespace *user_ns = ns;
+        return user_ns->proc_inum;
+}
+
 const struct proc_ns_operations userns_operations = {
         .name           = "user",
         .type           = CLONE_NEWUSER,
         .get            = userns_get,
         .put            = userns_put,
         .install        = userns_install,
+        .inum           = userns_inum,
 };
 
 static __init int user_namespaces_init(void)