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, 14 insertions, 4 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 4820c2aaeb5a..b4386ff6a641 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -825,9 +825,14 @@ void __init fork_init(void)
 	init_task.signal->rlim[RLIMIT_SIGPENDING] =
 		init_task.signal->rlim[RLIMIT_NPROC];
 
-	for (i = 0; i < UCOUNT_COUNTS; i++)
+	for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++)
 		init_user_ns.ucount_max[i] = max_threads/2;
 
+	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, task_rlimit(&init_task, RLIMIT_NPROC));
+	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, task_rlimit(&init_task, RLIMIT_MSGQUEUE));
+	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, task_rlimit(&init_task, RLIMIT_SIGPENDING));
+	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, task_rlimit(&init_task, RLIMIT_MEMLOCK));
+
 #ifdef CONFIG_VMAP_STACK
 	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
 			  NULL, free_vm_stack_cache);
@@ -1978,8 +1983,7 @@ static __latent_entropy struct task_struct *copy_process(
 	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
 	retval = -EAGAIN;
-	if (atomic_read(&p->real_cred->user->processes) >=
-			task_rlimit(p, RLIMIT_NPROC)) {
+	if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
 		if (p->real_cred->user != INIT_USER &&
 		    !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
 			goto bad_fork_free;
@@ -2388,7 +2392,7 @@ bad_fork_cleanup_threadgroup_lock:
 #endif
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
-	atomic_dec(&p->cred->user->processes);
+	dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 	exit_creds(p);
 bad_fork_free:
 	WRITE_ONCE(p->__state, TASK_DEAD);
@@ -3001,6 +3005,12 @@ int ksys_unshare(unsigned long unshare_flags)
 	if (err)
 		goto bad_unshare_cleanup_cred;
 
+	if (new_cred) {
+		err = set_cred_ucounts(new_cred);
+		if (err)
+			goto bad_unshare_cleanup_cred;
+	}
+
 	if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
 		if (do_sysvsem) {
 			/*