Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull user namespace rlimit handling update from Eric Biederman:
 "This is the work mainly by Alexey Gladkov to limit rlimits to the
  rlimits of the user that created a user namespace, and to allow users
  to have stricter limits on the resources created within a user
  namespace."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  cred: add missing return error code when set_cred_ucounts() failed
  ucounts: Silence warning in dec_rlimit_ucounts
  ucounts: Set ucount_max to the largest positive value the type can hold
  kselftests: Add test to check for rlimit changes in different user namespaces
  Reimplement RLIMIT_MEMLOCK on top of ucounts
  Reimplement RLIMIT_SIGPENDING on top of ucounts
  Reimplement RLIMIT_MSGQUEUE on top of ucounts
  Reimplement RLIMIT_NPROC on top of ucounts
  Use atomic_t for ucounts reference counting
  Add a reference to ucounts for each cred
  Increase size of ucounts to atomic_long_t

1 files changed, 46 insertions, 5 deletions

diff --git a/kernel/cred.c b/kernel/cred.c
index e1d274cd741b..e6fd2b3fc31f 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -60,6 +60,7 @@ struct cred init_cred = {
 	.user			= INIT_USER,
 	.user_ns		= &init_user_ns,
 	.group_info		= &init_groups,
+	.ucounts		= &init_ucounts,
 };
 
 static inline void set_cred_subscribers(struct cred *cred, int n)
@@ -119,6 +120,8 @@ static void put_cred_rcu(struct rcu_head *rcu)
 	if (cred->group_info)
 		put_group_info(cred->group_info);
 	free_uid(cred->user);
+	if (cred->ucounts)
+		put_ucounts(cred->ucounts);
 	put_user_ns(cred->user_ns);
 	kmem_cache_free(cred_jar, cred);
 }
@@ -222,6 +225,7 @@ struct cred *cred_alloc_blank(void)
 #ifdef CONFIG_DEBUG_CREDENTIALS
 	new->magic = CRED_MAGIC;
 #endif
+	new->ucounts = get_ucounts(&init_ucounts);
 
 	if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
@@ -284,6 +288,11 @@ struct cred *prepare_creds(void)
 
 	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
+
+	new->ucounts = get_ucounts(new->ucounts);
+	if (!new->ucounts)
+		goto error;
+
 	validate_creds(new);
 	return new;
 
@@ -351,7 +360,7 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 		kdebug("share_creds(%p{%d,%d})",
 		       p->cred, atomic_read(&p->cred->usage),
 		       read_cred_subscribers(p->cred));
-		atomic_inc(&p->cred->user->processes);
+		inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 		return 0;
 	}
 
@@ -363,6 +372,9 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 		ret = create_user_ns(new);
 		if (ret < 0)
 			goto error_put;
+		ret = set_cred_ucounts(new);
+		if (ret < 0)
+			goto error_put;
 	}
 
 #ifdef CONFIG_KEYS
@@ -384,8 +396,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	}
 #endif
 
-	atomic_inc(&new->user->processes);
 	p->cred = p->real_cred = get_cred(new);
+	inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 	alter_cred_subscribers(new, 2);
 	validate_creds(new);
 	return 0;
@@ -485,12 +497,12 @@ int commit_creds(struct cred *new)
 	 * in set_user().
 	 */
 	alter_cred_subscribers(new, 2);
-	if (new->user != old->user)
-		atomic_inc(&new->user->processes);
+	if (new->user != old->user || new->user_ns != old->user_ns)
+		inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
 	rcu_assign_pointer(task->real_cred, new);
 	rcu_assign_pointer(task->cred, new);
 	if (new->user != old->user)
-		atomic_dec(&old->user->processes);
+		dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
 	alter_cred_subscribers(old, -2);
 
 	/* send notifications */
@@ -653,6 +665,31 @@ int cred_fscmp(const struct cred *a, const struct cred *b)
 }
 EXPORT_SYMBOL(cred_fscmp);
 
+int set_cred_ucounts(struct cred *new)
+{
+	struct task_struct *task = current;
+	const struct cred *old = task->real_cred;
+	struct ucounts *old_ucounts = new->ucounts;
+
+	if (new->user == old->user && new->user_ns == old->user_ns)
+		return 0;
+
+	/*
+	 * This optimization is needed because alloc_ucounts() uses locks
+	 * for table lookups.
+	 */
+	if (old_ucounts && old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->euid))
+		return 0;
+
+	if (!(new->ucounts = alloc_ucounts(new->user_ns, new->euid)))
+		return -EAGAIN;
+
+	if (old_ucounts)
+		put_ucounts(old_ucounts);
+
+	return 0;
+}
+
 /*
  * initialise the credentials stuff
  */
@@ -719,6 +756,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
+	new->ucounts = get_ucounts(new->ucounts);
+	if (!new->ucounts)
+		goto error;
+
 	put_cred(old);
 	validate_creds(new);
 	return new;