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

13 files changed, 78 insertions, 49 deletions

diff --git a/fs/coredump.c b/fs/coredump.c
index 9f4aae202109..1e7c7c66a8f5 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -354,7 +354,7 @@ static int zap_process(struct task_struct *start, int exit_code)
 	struct task_struct *t;
 	int nr = 0;
 
-	/* ignore all signals except SIGKILL, see prepare_signal() */
+	/* Allow SIGKILL, see prepare_signal() */
 	start->signal->flags = SIGNAL_GROUP_EXIT;
 	start->signal->group_exit_code = exit_code;
 	start->signal->group_stop_count = 0;
diff --git a/fs/exec.c b/fs/exec.c
index 5fd73915c62c..45914e57c0d5 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1885,7 +1885,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 	 * whether NPROC limit is still exceeded.
 	 */
 	if ((current->flags & PF_NPROC_EXCEEDED) &&
-	    is_ucounts_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
+	    is_rlimit_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
 		retval = -EAGAIN;
 		goto out_ret;
 	}
diff --git a/fs/proc/array.c b/fs/proc/array.c
index eb815759842c..7d1c3114d496 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -276,7 +276,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p)
 		collect_sigign_sigcatch(p, &ignored, &caught);
 		num_threads = get_nr_threads(p);
 		rcu_read_lock();  /* FIXME: is this correct? */
-		qsize = get_ucounts_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING);
+		qsize = get_rlimit_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING);
 		rcu_read_unlock();
 		qlim = task_rlimit(p, RLIMIT_SIGPENDING);
 		unlock_task_sighand(p, &flags);
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index cafbe03eed01..20099268fa25 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -94,6 +94,7 @@ struct signal_struct {
 	refcount_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
+	int			quick_threads;
 	struct list_head	thread_head;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 33a4240e6a6f..45f09bec02c4 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -54,15 +54,17 @@ enum ucount_type {
 	UCOUNT_FANOTIFY_GROUPS,
 	UCOUNT_FANOTIFY_MARKS,
 #endif
+	UCOUNT_COUNTS,
+};
+
+enum rlimit_type {
 	UCOUNT_RLIMIT_NPROC,
 	UCOUNT_RLIMIT_MSGQUEUE,
 	UCOUNT_RLIMIT_SIGPENDING,
 	UCOUNT_RLIMIT_MEMLOCK,
-	UCOUNT_COUNTS,
+	UCOUNT_RLIMIT_COUNTS,
 };
 
-#define MAX_PER_NAMESPACE_UCOUNTS UCOUNT_RLIMIT_NPROC
-
 struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
@@ -99,6 +101,7 @@ struct user_namespace {
 #endif
 	struct ucounts		*ucounts;
 	long ucount_max[UCOUNT_COUNTS];
+	long rlimit_max[UCOUNT_RLIMIT_COUNTS];
 } __randomize_layout;
 
 struct ucounts {
@@ -107,6 +110,7 @@ struct ucounts {
 	kuid_t uid;
 	atomic_t count;
 	atomic_long_t ucount[UCOUNT_COUNTS];
+	atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS];
 };
 
 extern struct user_namespace init_user_ns;
@@ -120,21 +124,26 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid);
 struct ucounts * __must_check get_ucounts(struct ucounts *ucounts);
 void put_ucounts(struct ucounts *ucounts);
 
-static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type type)
+static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type type)
 {
-	return atomic_long_read(&ucounts->ucount[type]);
+	return atomic_long_read(&ucounts->rlimit[type]);
 }
 
-long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
-bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
-long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type);
-void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type);
-bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max);
+long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
+bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type);
+void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type);
+bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max);
+
+static inline long get_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type)
+{
+	return READ_ONCE(ns->rlimit_max[type]);
+}
 
-static inline void set_rlimit_ucount_max(struct user_namespace *ns,
-		enum ucount_type type, unsigned long max)
+static inline void set_userns_rlimit_max(struct user_namespace *ns,
+		enum rlimit_type type, unsigned long max)
 {
-	ns->ucount_max[type] = max <= LONG_MAX ? max : LONG_MAX;
+	ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX;
 }
 
 #ifdef CONFIG_USER_NS
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 12ad7860bb88..83370fef8879 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -1746,6 +1746,7 @@ out_filesystem:
 	unregister_filesystem(&mqueue_fs_type);
 out_sysctl:
 	kmem_cache_destroy(mqueue_inode_cachep);
+	retire_mq_sysctls(&init_ipc_ns);
 	return error;
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 84021b24f79e..4f7424523bac 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -733,11 +733,29 @@ static void check_stack_usage(void)
 static inline void check_stack_usage(void) {}
 #endif
 
+static void synchronize_group_exit(struct task_struct *tsk, long code)
+{
+	struct sighand_struct *sighand = tsk->sighand;
+	struct signal_struct *signal = tsk->signal;
+
+	spin_lock_irq(&sighand->siglock);
+	signal->quick_threads--;
+	if ((signal->quick_threads == 0) &&
+	    !(signal->flags & SIGNAL_GROUP_EXIT)) {
+		signal->flags = SIGNAL_GROUP_EXIT;
+		signal->group_exit_code = code;
+		signal->group_stop_count = 0;
+	}
+	spin_unlock_irq(&sighand->siglock);
+}
+
 void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
 
+	synchronize_group_exit(tsk, code);
+
 	WARN_ON(tsk->plug);
 
 	kcov_task_exit(tsk);
@@ -905,7 +923,7 @@ do_group_exit(int exit_code)
 		exit_code = sig->group_exit_code;
 	else if (sig->group_exec_task)
 		exit_code = 0;
-	else if (!thread_group_empty(current)) {
+	else {
 		struct sighand_struct *const sighand = current->sighand;
 
 		spin_lock_irq(&sighand->siglock);
diff --git a/kernel/fork.c b/kernel/fork.c
index 90c85b17bf69..296ebf26b70f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -925,13 +925,13 @@ void __init fork_init(void)
 	init_task.signal->rlim[RLIMIT_SIGPENDING] =
 		init_task.signal->rlim[RLIMIT_NPROC];
 
-	for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++)
+	for (i = 0; i < UCOUNT_COUNTS; i++)
 		init_user_ns.ucount_max[i] = max_threads/2;
 
-	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC,      RLIM_INFINITY);
-	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE,   RLIM_INFINITY);
-	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY);
-	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK,    RLIM_INFINITY);
+	set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC,      RLIM_INFINITY);
+	set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE,   RLIM_INFINITY);
+	set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY);
+	set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK,    RLIM_INFINITY);
 
 #ifdef CONFIG_VMAP_STACK
 	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
@@ -1692,6 +1692,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 		return -ENOMEM;
 
 	sig->nr_threads = 1;
+	sig->quick_threads = 1;
 	atomic_set(&sig->live, 1);
 	refcount_set(&sig->sigcnt, 1);
 
@@ -2118,7 +2119,7 @@ static __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_free;
 
 	retval = -EAGAIN;
-	if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
+	if (is_rlimit_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_cleanup_count;
@@ -2462,6 +2463,7 @@ static __latent_entropy struct task_struct *copy_process(
 			__this_cpu_inc(process_counts);
 		} else {
 			current->signal->nr_threads++;
+			current->signal->quick_threads++;
 			atomic_inc(&current->signal->live);
 			refcount_inc(&current->signal->sigcnt);
 			task_join_group_stop(p);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 3c677918d8f2..7243a010f433 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -704,6 +704,7 @@ int kthread_stop(struct task_struct *k)
 	kthread = to_kthread(k);
 	set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
 	kthread_unpark(k);
+	set_tsk_thread_flag(k, TIF_NOTIFY_SIGNAL);
 	wake_up_process(k);
 	wait_for_completion(&kthread->exited);
 	ret = kthread->result;
diff --git a/kernel/signal.c b/kernel/signal.c
index 6f86fda5e432..8a0f114d00e0 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -913,8 +913,9 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
 		if (signal->core_state)
 			return sig == SIGKILL;
 		/*
-		 * The process is in the middle of dying, nothing to do.
+		 * The process is in the middle of dying, drop the signal.
 		 */
+		return false;
 	} else if (sig_kernel_stop(sig)) {
 		/*
 		 * This is a stop signal.  Remove SIGCONT from all queues.
diff --git a/kernel/sys.c b/kernel/sys.c
index b911fa6d81ab..8a6432465dc5 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -496,7 +496,7 @@ static void flag_nproc_exceeded(struct cred *new)
 	 * for programs doing set*uid()+execve() by harmlessly deferring the
 	 * failure to the execve() stage.
 	 */
-	if (is_ucounts_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) &&
+	if (is_rlimit_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) &&
 			new->user != INIT_USER)
 		current->flags |= PF_NPROC_EXCEEDED;
 	else
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 06ea04d44685..ee8e57fd6f90 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -87,10 +87,6 @@ static struct ctl_table user_table[] = {
 	UCOUNT_ENTRY("max_fanotify_groups"),
 	UCOUNT_ENTRY("max_fanotify_marks"),
 #endif
-	{ },
-	{ },
-	{ },
-	{ },
 	{ }
 };
 #endif /* CONFIG_SYSCTL */
@@ -263,29 +259,29 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
 	put_ucounts(ucounts);
 }
 
-long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
+long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v)
 {
 	struct ucounts *iter;
 	long max = LONG_MAX;
 	long ret = 0;
 
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		long new = atomic_long_add_return(v, &iter->ucount[type]);
+		long new = atomic_long_add_return(v, &iter->rlimit[type]);
 		if (new < 0 || new > max)
 			ret = LONG_MAX;
 		else if (iter == ucounts)
 			ret = new;
-		max = READ_ONCE(iter->ns->ucount_max[type]);
+		max = get_userns_rlimit_max(iter->ns, type);
 	}
 	return ret;
 }
 
-bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
+bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_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_sub_return(v, &iter->ucount[type]);
+		long dec = atomic_long_sub_return(v, &iter->rlimit[type]);
 		WARN_ON_ONCE(dec < 0);
 		if (iter == ucounts)
 			new = dec;
@@ -294,11 +290,11 @@ bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
 }
 
 static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
-				struct ucounts *last, enum ucount_type type)
+				struct ucounts *last, enum rlimit_type type)
 {
 	struct ucounts *iter, *next;
 	for (iter = ucounts; iter != last; iter = next) {
-		long dec = atomic_long_sub_return(1, &iter->ucount[type]);
+		long dec = atomic_long_sub_return(1, &iter->rlimit[type]);
 		WARN_ON_ONCE(dec < 0);
 		next = iter->ns->ucounts;
 		if (dec == 0)
@@ -306,12 +302,12 @@ static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
 	}
 }
 
-void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type)
+void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type)
 {
 	do_dec_rlimit_put_ucounts(ucounts, NULL, type);
 }
 
-long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type)
 {
 	/* Caller must hold a reference to ucounts */
 	struct ucounts *iter;
@@ -319,12 +315,12 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
 	long dec, ret = 0;
 
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		long new = atomic_long_add_return(1, &iter->ucount[type]);
+		long new = atomic_long_add_return(1, &iter->rlimit[type]);
 		if (new < 0 || new > max)
 			goto unwind;
 		if (iter == ucounts)
 			ret = new;
-		max = READ_ONCE(iter->ns->ucount_max[type]);
+		max = get_userns_rlimit_max(iter->ns, type);
 		/*
 		 * Grab an extra ucount reference for the caller when
 		 * the rlimit count was previously 0.
@@ -336,24 +332,24 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
 	}
 	return ret;
 dec_unwind:
-	dec = atomic_long_sub_return(1, &iter->ucount[type]);
+	dec = atomic_long_sub_return(1, &iter->rlimit[type]);
 	WARN_ON_ONCE(dec < 0);
 unwind:
 	do_dec_rlimit_put_ucounts(ucounts, iter, type);
 	return 0;
 }
 
-bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long rlimit)
+bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long rlimit)
 {
 	struct ucounts *iter;
 	long max = rlimit;
 	if (rlimit > LONG_MAX)
 		max = LONG_MAX;
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		long val = get_ucounts_value(iter, type);
+		long val = get_rlimit_value(iter, type);
 		if (val < 0 || val > max)
 			return true;
-		max = READ_ONCE(iter->ns->ucount_max[type]);
+		max = get_userns_rlimit_max(iter->ns, type);
 	}
 	return false;
 }
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 5481ba44a8d6..981bb2d10d83 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -131,13 +131,13 @@ int create_user_ns(struct cred *new)
 	ns->owner = owner;
 	ns->group = group;
 	INIT_WORK(&ns->work, free_user_ns);
-	for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) {
+	for (i = 0; i < UCOUNT_COUNTS; i++) {
 		ns->ucount_max[i] = INT_MAX;
 	}
-	set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit());
-	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));
+	set_userns_rlimit_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit());
+	set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE));
+	set_userns_rlimit_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING));
+	set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK));
 	ns->ucounts = ucounts;
 
 	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */