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

8 files changed, 186 insertions, 52 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;
diff --git a/kernel/exit.c b/kernel/exit.c
index 65809fac3038..9a89e7f36acb 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -188,7 +188,7 @@ repeat:
 	/* don't need to get the RCU readlock here - the process is dead and
 	 * can't be modifying its own credentials. But shut RCU-lockdep up */
 	rcu_read_lock();
-	atomic_dec(&__task_cred(p)->user->processes);
+	dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 	rcu_read_unlock();
 
 	cgroup_release(p);
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) {
 			/*
diff --git a/kernel/signal.c b/kernel/signal.c
index 20d1d896d5b0..de0920353d30 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -412,8 +412,8 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
 		 int override_rlimit, const unsigned int sigqueue_flags)
 {
 	struct sigqueue *q = NULL;
-	struct user_struct *user;
-	int sigpending;
+	struct ucounts *ucounts = NULL;
+	long sigpending;
 
 	/*
 	 * Protect access to @t credentials. This can go away when all
@@ -424,27 +424,26 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
 	 * changes from/to zero.
 	 */
 	rcu_read_lock();
-	user = __task_cred(t)->user;
-	sigpending = atomic_inc_return(&user->sigpending);
+	ucounts = task_ucounts(t);
+	sigpending = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1);
 	if (sigpending == 1)
-		get_uid(user);
+		ucounts = get_ucounts(ucounts);
 	rcu_read_unlock();
 
-	if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
+	if (override_rlimit || (sigpending < LONG_MAX && sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
 		q = kmem_cache_alloc(sigqueue_cachep, gfp_flags);
 	} else {
 		print_dropped_signal(sig);
 	}
 
 	if (unlikely(q == NULL)) {
-		if (atomic_dec_and_test(&user->sigpending))
-			free_uid(user);
+		if (ucounts && dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1))
+			put_ucounts(ucounts);
 	} else {
 		INIT_LIST_HEAD(&q->list);
 		q->flags = sigqueue_flags;
-		q->user = user;
+		q->ucounts = ucounts;
 	}
-
 	return q;
 }
 
@@ -452,8 +451,10 @@ static void __sigqueue_free(struct sigqueue *q)
 {
 	if (q->flags & SIGQUEUE_PREALLOC)
 		return;
-	if (atomic_dec_and_test(&q->user->sigpending))
-		free_uid(q->user);
+	if (q->ucounts && dec_rlimit_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING, 1)) {
+		put_ucounts(q->ucounts);
+		q->ucounts = NULL;
+	}
 	kmem_cache_free(sigqueue_cachep, q);
 }
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 9de46a4bf492..ef1a78f5d71c 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -479,7 +479,7 @@ static int set_user(struct cred *new)
 	 * for programs doing set*uid()+execve() by harmlessly deferring the
 	 * failure to the execve() stage.
 	 */
-	if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) &&
+	if (is_ucounts_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) &&
 			new_user != INIT_USER)
 		current->flags |= PF_NPROC_EXCEEDED;
 	else
@@ -558,6 +558,10 @@ long __sys_setreuid(uid_t ruid, uid_t euid)
 	if (retval < 0)
 		goto error;
 
+	retval = set_cred_ucounts(new);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -616,6 +620,10 @@ long __sys_setuid(uid_t uid)
 	if (retval < 0)
 		goto error;
 
+	retval = set_cred_ucounts(new);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -691,6 +699,10 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 	if (retval < 0)
 		goto error;
 
+	retval = set_cred_ucounts(new);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 8d8874f1c35e..87799e2379bd 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -8,6 +8,12 @@
 #include <linux/kmemleak.h>
 #include <linux/user_namespace.h>
 
+struct ucounts init_ucounts = {
+	.ns    = &init_user_ns,
+	.uid   = GLOBAL_ROOT_UID,
+	.count = ATOMIC_INIT(1),
+};
+
 #define UCOUNTS_HASHTABLE_BITS 10
 static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)];
 static DEFINE_SPINLOCK(ucounts_lock);
@@ -78,6 +84,10 @@ static struct ctl_table user_table[] = {
 	UCOUNT_ENTRY("max_fanotify_groups"),
 	UCOUNT_ENTRY("max_fanotify_marks"),
 #endif
+	{ },
+	{ },
+	{ },
+	{ },
 	{ }
 };
 #endif /* CONFIG_SYSCTL */
@@ -129,7 +139,24 @@ static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struc
 	return NULL;
 }
 
-static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
+static void hlist_add_ucounts(struct ucounts *ucounts)
+{
+	struct hlist_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid);
+	spin_lock_irq(&ucounts_lock);
+	hlist_add_head(&ucounts->node, hashent);
+	spin_unlock_irq(&ucounts_lock);
+}
+
+struct ucounts *get_ucounts(struct ucounts *ucounts)
+{
+	if (ucounts && atomic_add_negative(1, &ucounts->count)) {
+		put_ucounts(ucounts);
+		ucounts = NULL;
+	}
+	return ucounts;
+}
+
+struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid)
 {
 	struct hlist_head *hashent = ucounts_hashentry(ns, uid);
 	struct ucounts *ucounts, *new;
@@ -145,7 +172,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 
 		new->ns = ns;
 		new->uid = uid;
-		new->count = 0;
+		atomic_set(&new->count, 1);
 
 		spin_lock_irq(&ucounts_lock);
 		ucounts = find_ucounts(ns, uid, hashent);
@@ -153,40 +180,35 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 			kfree(new);
 		} else {
 			hlist_add_head(&new->node, hashent);
-			ucounts = new;
+			spin_unlock_irq(&ucounts_lock);
+			return new;
 		}
 	}
-	if (ucounts->count == INT_MAX)
-		ucounts = NULL;
-	else
-		ucounts->count += 1;
 	spin_unlock_irq(&ucounts_lock);
+	ucounts = get_ucounts(ucounts);
 	return ucounts;
 }
 
-static void put_ucounts(struct ucounts *ucounts)
+void put_ucounts(struct ucounts *ucounts)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&ucounts_lock, flags);
-	ucounts->count -= 1;
-	if (!ucounts->count)
+	if (atomic_dec_and_test(&ucounts->count)) {
+		spin_lock_irqsave(&ucounts_lock, flags);
 		hlist_del_init(&ucounts->node);
-	else
-		ucounts = NULL;
-	spin_unlock_irqrestore(&ucounts_lock, flags);
-
-	kfree(ucounts);
+		spin_unlock_irqrestore(&ucounts_lock, flags);
+		kfree(ucounts);
+	}
 }
 
-static inline bool atomic_inc_below(atomic_t *v, int u)
+static inline bool atomic_long_inc_below(atomic_long_t *v, int u)
 {
-	int c, old;
-	c = atomic_read(v);
+	long c, old;
+	c = atomic_long_read(v);
 	for (;;) {
 		if (unlikely(c >= u))
 			return false;
-		old = atomic_cmpxchg(v, c, c+1);
+		old = atomic_long_cmpxchg(v, c, c+1);
 		if (likely(old == c))
 			return true;
 		c = old;
@@ -198,19 +220,19 @@ struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid,
 {
 	struct ucounts *ucounts, *iter, *bad;
 	struct user_namespace *tns;
-	ucounts = get_ucounts(ns, uid);
+	ucounts = alloc_ucounts(ns, uid);
 	for (iter = ucounts; iter; iter = tns->ucounts) {
-		int max;
+		long max;
 		tns = iter->ns;
 		max = READ_ONCE(tns->ucount_max[type]);
-		if (!atomic_inc_below(&iter->ucount[type], max))
+		if (!atomic_long_inc_below(&iter->ucount[type], max))
 			goto fail;
 	}
 	return ucounts;
 fail:
 	bad = iter;
 	for (iter = ucounts; iter != bad; iter = iter->ns->ucounts)
-		atomic_dec(&iter->ucount[type]);
+		atomic_long_dec(&iter->ucount[type]);
 
 	put_ucounts(ucounts);
 	return NULL;
@@ -220,12 +242,54 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
 {
 	struct ucounts *iter;
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		int dec = atomic_dec_if_positive(&iter->ucount[type]);
+		long dec = atomic_long_dec_if_positive(&iter->ucount[type]);
 		WARN_ON_ONCE(dec < 0);
 	}
 	put_ucounts(ucounts);
 }
 
+long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
+{
+	struct ucounts *iter;
+	long ret = 0;
+
+	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
+		long max = READ_ONCE(iter->ns->ucount_max[type]);
+		long new = atomic_long_add_return(v, &iter->ucount[type]);
+		if (new < 0 || new > max)
+			ret = LONG_MAX;
+		else if (iter == ucounts)
+			ret = new;
+	}
+	return ret;
+}
+
+bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
+{
+	struct ucounts *iter;
+	long new = -1; /* Silence compiler warning */
+	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
+		long dec = atomic_long_add_return(-v, &iter->ucount[type]);
+		WARN_ON_ONCE(dec < 0);
+		if (iter == ucounts)
+			new = dec;
+	}
+	return (new == 0);
+}
+
+bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max)
+{
+	struct ucounts *iter;
+	if (get_ucounts_value(ucounts, type) > max)
+		return true;
+	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
+		max = READ_ONCE(iter->ns->ucount_max[type]);
+		if (get_ucounts_value(iter, type) > max)
+			return true;
+	}
+	return false;
+}
+
 static __init int user_namespace_sysctl_init(void)
 {
 #ifdef CONFIG_SYSCTL
@@ -241,6 +305,8 @@ static __init int user_namespace_sysctl_init(void)
 	BUG_ON(!user_header);
 	BUG_ON(!setup_userns_sysctls(&init_user_ns));
 #endif
+	hlist_add_ucounts(&init_ucounts);
+	inc_rlimit_ucounts(&init_ucounts, UCOUNT_RLIMIT_NPROC, 1);
 	return 0;
 }
 subsys_initcall(user_namespace_sysctl_init);
diff --git a/kernel/user.c b/kernel/user.c
index a2478cddf536..c82399c1618a 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -98,9 +98,6 @@ static DEFINE_SPINLOCK(uidhash_lock);
 /* root_user.__count is 1, for init task cred */
 struct user_struct root_user = {
 	.__count	= REFCOUNT_INIT(1),
-	.processes	= ATOMIC_INIT(1),
-	.sigpending	= ATOMIC_INIT(0),
-	.locked_shm     = 0,
 	.uid		= GLOBAL_ROOT_UID,
 	.ratelimit	= RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0),
 };
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 8d62863721b0..ef82d401dde8 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -119,9 +119,13 @@ int create_user_ns(struct cred *new)
 	ns->owner = owner;
 	ns->group = group;
 	INIT_WORK(&ns->work, free_user_ns);
-	for (i = 0; i < UCOUNT_COUNTS; i++) {
+	for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) {
 		ns->ucount_max[i] = INT_MAX;
 	}
+	set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC));
+	set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE));
+	set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING));
+	set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK));
 	ns->ucounts = ucounts;
 
 	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
@@ -1340,6 +1344,9 @@ static int userns_install(struct nsset *nsset, struct ns_common *ns)
 	put_user_ns(cred->user_ns);
 	set_cred_user_ns(cred, get_user_ns(user_ns));
 
+	if (set_cred_ucounts(cred) < 0)
+		return -EINVAL;
+
 	return 0;
 }