Merge branch 'kernel-6.14.pid' into vfs.all

include/linux/pid.h

@@ -108,9 +108,6 @@ extern void exchange_tids(struct task_struct *task, struct task_struct *old);
 extern void transfer_pid(struct task_struct *old, struct task_struct *new,
 			 enum pid_type);
 
-extern int pid_max;
-extern int pid_max_min, pid_max_max;
-
 /*
  * look up a PID in the hash table. Must be called with the tasklist_lock
  * or rcu_read_lock() held.

include/linux/pid_namespace.h

@@ -30,6 +30,7 @@ struct pid_namespace {
 	struct task_struct *child_reaper;
 	struct kmem_cache *pid_cachep;
 	unsigned int level;
+	int pid_max;
 	struct pid_namespace *parent;
 #ifdef CONFIG_BSD_PROCESS_ACCT
 	struct fs_pin *bacct;
@@ -38,9 +39,14 @@ struct pid_namespace {
 	struct ucounts *ucounts;
 	int reboot;	/* group exit code if this pidns was rebooted */
 	struct ns_common ns;
-#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+	struct work_struct	work;
+#ifdef CONFIG_SYSCTL
+	struct ctl_table_set	set;
+	struct ctl_table_header *sysctls;
+#if defined(CONFIG_MEMFD_CREATE)
 	int memfd_noexec_scope;
 #endif
+#endif
 } __randomize_layout;
 
 extern struct pid_namespace init_pid_ns;
@@ -117,6 +123,8 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
 extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);
 void pidhash_init(void);
 void pid_idr_init(void);
+int register_pidns_sysctls(struct pid_namespace *pidns);
+void unregister_pidns_sysctls(struct pid_namespace *pidns);
 
 static inline bool task_is_in_init_pid_ns(struct task_struct *tsk)
 {

kernel/pid.c

@@ -61,10 +61,8 @@ struct pid init_struct_pid = {
 	}, }
 };
 
-int pid_max = PID_MAX_DEFAULT;
-
-int pid_max_min = RESERVED_PIDS + 1;
-int pid_max_max = PID_MAX_LIMIT;
+static int pid_max_min = RESERVED_PIDS + 1;
+static int pid_max_max = PID_MAX_LIMIT;
 
 /*
  * PID-map pages start out as NULL, they get allocated upon
@@ -83,6 +81,7 @@ struct pid_namespace init_pid_ns = {
 #ifdef CONFIG_PID_NS
 	.ns.ops = &pidns_operations,
 #endif
+	.pid_max = PID_MAX_DEFAULT,
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
 	.memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC,
 #endif
@@ -191,6 +190,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 
 	for (i = ns->level; i >= 0; i--) {
 		int tid = 0;
+		int pid_max = READ_ONCE(tmp->pid_max);
 
 		if (set_tid_size) {
 			tid = set_tid[ns->level - i];
@@ -644,17 +644,118 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 	return fd;
 }
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table_set *pid_table_root_lookup(struct ctl_table_root *root)
+{
+	return &task_active_pid_ns(current)->set;
+}
+
+static int set_is_seen(struct ctl_table_set *set)
+{
+	return &task_active_pid_ns(current)->set == set;
+}
+
+static int pid_table_root_permissions(struct ctl_table_header *head,
+				      const struct ctl_table *table)
+{
+	struct pid_namespace *pidns =
+		container_of(head->set, struct pid_namespace, set);
+	int mode = table->mode;
+
+	if (ns_capable(pidns->user_ns, CAP_SYS_ADMIN) ||
+	    uid_eq(current_euid(), make_kuid(pidns->user_ns, 0)))
+		mode = (mode & S_IRWXU) >> 6;
+	else if (in_egroup_p(make_kgid(pidns->user_ns, 0)))
+		mode = (mode & S_IRWXG) >> 3;
+	else
+		mode = mode & S_IROTH;
+	return (mode << 6) | (mode << 3) | mode;
+}
+
+static void pid_table_root_set_ownership(struct ctl_table_header *head,
+					 kuid_t *uid, kgid_t *gid)
+{
+	struct pid_namespace *pidns =
+		container_of(head->set, struct pid_namespace, set);
+	kuid_t ns_root_uid;
+	kgid_t ns_root_gid;
+
+	ns_root_uid = make_kuid(pidns->user_ns, 0);
+	if (uid_valid(ns_root_uid))
+		*uid = ns_root_uid;
+
+	ns_root_gid = make_kgid(pidns->user_ns, 0);
+	if (gid_valid(ns_root_gid))
+		*gid = ns_root_gid;
+}
+
+static struct ctl_table_root pid_table_root = {
+	.lookup		= pid_table_root_lookup,
+	.permissions	= pid_table_root_permissions,
+	.set_ownership	= pid_table_root_set_ownership,
+};
+
+static struct ctl_table pid_table[] = {
+	{
+		.procname	= "pid_max",
+		.data		= &init_pid_ns.pid_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &pid_max_min,
+		.extra2		= &pid_max_max,
+	},
+};
+#endif
+
+int register_pidns_sysctls(struct pid_namespace *pidns)
+{
+#ifdef CONFIG_SYSCTL
+	struct ctl_table *tbl;
+
+	setup_sysctl_set(&pidns->set, &pid_table_root, set_is_seen);
+
+	tbl = kmemdup(pid_table, sizeof(pid_table), GFP_KERNEL);
+	if (!tbl)
+		return -ENOMEM;
+	tbl->data = &pidns->pid_max;
+	pidns->pid_max = min(pid_max_max, max_t(int, pidns->pid_max,
+			     PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
+
+	pidns->sysctls = __register_sysctl_table(&pidns->set, "kernel", tbl,
+						 ARRAY_SIZE(pid_table));
+	if (!pidns->sysctls) {
+		kfree(tbl);
+		retire_sysctl_set(&pidns->set);
+		return -ENOMEM;
+	}
+#endif
+	return 0;
+}
+
+void unregister_pidns_sysctls(struct pid_namespace *pidns)
+{
+#ifdef CONFIG_SYSCTL
+	const struct ctl_table *tbl;
+
+	tbl = pidns->sysctls->ctl_table_arg;
+	unregister_sysctl_table(pidns->sysctls);
+	retire_sysctl_set(&pidns->set);
+	kfree(tbl);
+#endif
+}
+
 void __init pid_idr_init(void)
 {
 	/* Verify no one has done anything silly: */
 	BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING);
 
 	/* bump default and minimum pid_max based on number of cpus */
-	pid_max = min(pid_max_max, max_t(int, pid_max,
-				PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
+	init_pid_ns.pid_max = min(pid_max_max, max_t(int, init_pid_ns.pid_max,
+				  PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
 	pid_max_min = max_t(int, pid_max_min,
 				PIDS_PER_CPU_MIN * num_possible_cpus());
-	pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min);
+	pr_info("pid_max: default: %u minimum: %u\n", init_pid_ns.pid_max, pid_max_min);
 
 	idr_init(&init_pid_ns.idr);
 
@@ -665,6 +766,16 @@ void __init pid_idr_init(void)
 			NULL);
 }
 
+static __init int pid_namespace_sysctl_init(void)
+{
+#ifdef CONFIG_SYSCTL
+	/* "kernel" directory will have already been initialized. */
+	BUG_ON(register_pidns_sysctls(&init_pid_ns));
+#endif
+	return 0;
+}
+subsys_initcall(pid_namespace_sysctl_init);
+
 static struct file *__pidfd_fget(struct task_struct *task, int fd)
 {
 	struct file *file;

kernel/pid_namespace.c

@@ -70,6 +70,8 @@ static void dec_pid_namespaces(struct ucounts *ucounts)
 	dec_ucount(ucounts, UCOUNT_PID_NAMESPACES);
 }
 
+static void destroy_pid_namespace_work(struct work_struct *work);
+
 static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns,
 	struct pid_namespace *parent_pid_ns)
 {
@@ -105,17 +107,27 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 		goto out_free_idr;
 	ns->ns.ops = &pidns_operations;
 
+	ns->pid_max = parent_pid_ns->pid_max;
+	err = register_pidns_sysctls(ns);
+	if (err)
+		goto out_free_inum;
+
 	refcount_set(&ns->ns.count, 1);
 	ns->level = level;
 	ns->parent = get_pid_ns(parent_pid_ns);
 	ns->user_ns = get_user_ns(user_ns);
 	ns->ucounts = ucounts;
 	ns->pid_allocated = PIDNS_ADDING;
+	INIT_WORK(&ns->work, destroy_pid_namespace_work);
+
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
 	ns->memfd_noexec_scope = pidns_memfd_noexec_scope(parent_pid_ns);
 #endif
+
 	return ns;
 
+out_free_inum:
+	ns_free_inum(&ns->ns);
 out_free_idr:
 	idr_destroy(&ns->idr);
 	kmem_cache_free(pid_ns_cachep, ns);
@@ -137,12 +149,28 @@ static void delayed_free_pidns(struct rcu_head *p)
 
 static void destroy_pid_namespace(struct pid_namespace *ns)
 {
+	unregister_pidns_sysctls(ns);
+
 	ns_free_inum(&ns->ns);
 
 	idr_destroy(&ns->idr);
 	call_rcu(&ns->rcu, delayed_free_pidns);
 }
 
+static void destroy_pid_namespace_work(struct work_struct *work)
+{
+	struct pid_namespace *ns =
+		container_of(work, struct pid_namespace, work);
+
+	do {
+		struct pid_namespace *parent;
+
+		parent = ns->parent;
+		destroy_pid_namespace(ns);
+		ns = parent;
+	} while (ns != &init_pid_ns && refcount_dec_and_test(&ns->ns.count));
+}
+
 struct pid_namespace *copy_pid_ns(unsigned long flags,
 	struct user_namespace *user_ns, struct pid_namespace *old_ns)
 {
@@ -155,15 +183,8 @@ struct pid_namespace *copy_pid_ns(unsigned long flags,
 
 void put_pid_ns(struct pid_namespace *ns)
 {
-	struct pid_namespace *parent;
-
-	while (ns != &init_pid_ns) {
-		parent = ns->parent;
-		if (!refcount_dec_and_test(&ns->ns.count))
-			break;
-		destroy_pid_namespace(ns);
-		ns = parent;
-	}
+	if (ns && ns != &init_pid_ns && refcount_dec_and_test(&ns->ns.count))
+		schedule_work(&ns->work);
 }
 EXPORT_SYMBOL_GPL(put_pid_ns);
 
@@ -274,6 +295,7 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write,
 	next = idr_get_cursor(&pid_ns->idr) - 1;
 
 	tmp.data = &next;
+	tmp.extra2 = &pid_ns->pid_max;
 	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 	if (!ret && write)
 		idr_set_cursor(&pid_ns->idr, next + 1);
@@ -281,7 +303,6 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-extern int pid_max;
 static struct ctl_table pid_ns_ctl_table[] = {
 	{
 		.procname = "ns_last_pid",
@@ -289,7 +310,7 @@ static struct ctl_table pid_ns_ctl_table[] = {
 		.mode = 0666, /* permissions are checked in the handler */
 		.proc_handler = pid_ns_ctl_handler,
 		.extra1 = SYSCTL_ZERO,
-		.extra2 = &pid_max,
+		.extra2 = &init_pid_ns.pid_max,
 	},
 };
 #endif	/* CONFIG_CHECKPOINT_RESTORE */

kernel/sysctl.c

@@ -1803,15 +1803,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-	{
-		.procname	= "pid_max",
-		.data		= &pid_max,
-		.maxlen		= sizeof (int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &pid_max_min,
-		.extra2		= &pid_max_max,
-	},
 	{
 		.procname	= "panic_on_oops",
 		.data		= &panic_on_oops,

kernel/trace/pid_list.c

@@ -414,7 +414,7 @@ struct trace_pid_list *trace_pid_list_alloc(void)
 	int i;
 
 	/* According to linux/thread.h, pids can be no bigger that 30 bits */
-	WARN_ON_ONCE(pid_max > (1 << 30));
+	WARN_ON_ONCE(init_pid_ns.pid_max > (1 << 30));
 
 	pid_list = kzalloc(sizeof(*pid_list), GFP_KERNEL);
 	if (!pid_list)

kernel/trace/trace.h

@@ -718,8 +718,6 @@ extern unsigned long tracing_thresh;
 
 /* PID filtering */
 
-extern int pid_max;
-
 bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids,
 			     pid_t search_pid);
 bool trace_ignore_this_task(struct trace_pid_list *filtered_pids,

kernel/trace/trace_sched_switch.c

@@ -442,7 +442,7 @@ int trace_alloc_tgid_map(void)
 	if (tgid_map)
 		return 0;
 
-	tgid_map_max = pid_max;
+	tgid_map_max = init_pid_ns.pid_max;
 	map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map),
 		       GFP_KERNEL);
 	if (!map)

tools/testing/selftests/pid_namespace/.gitignore

@@ -1 +1,2 @@
+pid_max
 regression_enomem

tools/testing/selftests/pid_namespace/Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -g $(KHDR_INCLUDES)
 
-TEST_GEN_PROGS = regression_enomem
+TEST_GEN_PROGS = regression_enomem pid_max
 
 LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h
 

tools/testing/selftests/pid_namespace/pid_max.c

@@ -0,0 +1,358 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define _GNU_SOURCE
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/types.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/wait.h>
+
+#include "../kselftest_harness.h"
+#include "../pidfd/pidfd.h"
+
+#define __STACK_SIZE (8 * 1024 * 1024)
+static pid_t do_clone(int (*fn)(void *), void *arg, int flags)
+{
+	char *stack;
+	pid_t ret;
+
+	stack = malloc(__STACK_SIZE);
+	if (!stack)
+		return -ENOMEM;
+
+#ifdef __ia64__
+	ret = __clone2(fn, stack, __STACK_SIZE, flags | SIGCHLD, arg);
+#else
+	ret = clone(fn, stack + __STACK_SIZE, flags | SIGCHLD, arg);
+#endif
+	free(stack);
+	return ret;
+}
+
+static int pid_max_cb(void *data)
+{
+	int fd, ret;
+	pid_t pid;
+
+	ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+		return -1;
+	}
+
+	umount2("/proc", MNT_DETACH);
+
+	ret = mount("proc", "/proc", "proc", 0, NULL);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to mount proc\n");
+		return -1;
+	}
+
+	fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+	if (fd < 0) {
+		fprintf(stderr, "%m - Failed to open pid_max\n");
+		return -1;
+	}
+
+	ret = write(fd, "500", sizeof("500") - 1);
+	if (ret < 0) {
+		fprintf(stderr, "%m - Failed to write pid_max\n");
+		return -1;
+	}
+
+	for (int i = 0; i < 501; i++) {
+		pid = fork();
+		if (pid == 0)
+			exit(EXIT_SUCCESS);
+		wait_for_pid(pid);
+		if (pid > 500) {
+			fprintf(stderr, "Managed to create pid number beyond limit\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int pid_max_nested_inner(void *data)
+{
+	int fret = -1;
+	pid_t pids[2];
+	int fd, i, ret;
+
+	ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+		return fret;
+	}
+
+	umount2("/proc", MNT_DETACH);
+
+	ret = mount("proc", "/proc", "proc", 0, NULL);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to mount proc\n");
+		return fret;
+	}
+
+	fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+	if (fd < 0) {
+		fprintf(stderr, "%m - Failed to open pid_max\n");
+		return fret;
+	}
+
+	ret = write(fd, "500", sizeof("500") - 1);
+	close(fd);
+	if (ret < 0) {
+		fprintf(stderr, "%m - Failed to write pid_max\n");
+		return fret;
+	}
+
+	pids[0] = fork();
+	if (pids[0] < 0) {
+		fprintf(stderr, "Failed to create first new process\n");
+		return fret;
+	}
+
+	if (pids[0] == 0)
+		exit(EXIT_SUCCESS);
+
+	pids[1] = fork();
+	wait_for_pid(pids[0]);
+	if (pids[1] >= 0) {
+		if (pids[1] == 0)
+			exit(EXIT_SUCCESS);
+		wait_for_pid(pids[1]);
+
+		fprintf(stderr, "Managed to create process even though ancestor pid namespace had a limit\n");
+		return fret;
+	}
+
+	/* Now make sure that we wrap pids at 400. */
+	for (i = 0; i < 510; i++) {
+		pid_t pid;
+
+		pid = fork();
+		if (pid < 0)
+			return fret;
+
+		if (pid == 0)
+			exit(EXIT_SUCCESS);
+
+		wait_for_pid(pid);
+		if (pid >= 500) {
+			fprintf(stderr, "Managed to create process with pid %d beyond configured limit\n", pid);
+			return fret;
+		}
+	}
+
+	return 0;
+}
+
+static int pid_max_nested_outer(void *data)
+{
+	int fret = -1, nr_procs = 400;
+	pid_t pids[1000];
+	int fd, i, ret;
+	pid_t pid;
+
+	ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+		return fret;
+	}
+
+	umount2("/proc", MNT_DETACH);
+
+	ret = mount("proc", "/proc", "proc", 0, NULL);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to mount proc\n");
+		return fret;
+	}
+
+	fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+	if (fd < 0) {
+		fprintf(stderr, "%m - Failed to open pid_max\n");
+		return fret;
+	}
+
+	ret = write(fd, "400", sizeof("400") - 1);
+	close(fd);
+	if (ret < 0) {
+		fprintf(stderr, "%m - Failed to write pid_max\n");
+		return fret;
+	}
+
+	/*
+	 * Create 397 processes. This leaves room for do_clone() (398) and
+	 * one more 399. So creating another process needs to fail.
+	 */
+	for (nr_procs = 0; nr_procs < 396; nr_procs++) {
+		pid = fork();
+		if (pid < 0)
+			goto reap;
+
+		if (pid == 0)
+			exit(EXIT_SUCCESS);
+
+		pids[nr_procs] = pid;
+	}
+
+	pid = do_clone(pid_max_nested_inner, NULL, CLONE_NEWPID | CLONE_NEWNS);
+	if (pid < 0) {
+		fprintf(stderr, "%m - Failed to clone nested pidns\n");
+		goto reap;
+	}
+
+	if (wait_for_pid(pid)) {
+		fprintf(stderr, "%m - Nested pid_max failed\n");
+		goto reap;
+	}
+
+	fret = 0;
+
+reap:
+	for (int i = 0; i < nr_procs; i++)
+		wait_for_pid(pids[i]);
+
+	return fret;
+}
+
+static int pid_max_nested_limit_inner(void *data)
+{
+	int fret = -1, nr_procs = 400;
+	int fd, ret;
+	pid_t pid;
+	pid_t pids[1000];
+
+	ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+		return fret;
+	}
+
+	umount2("/proc", MNT_DETACH);
+
+	ret = mount("proc", "/proc", "proc", 0, NULL);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to mount proc\n");
+		return fret;
+	}
+
+	fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+	if (fd < 0) {
+		fprintf(stderr, "%m - Failed to open pid_max\n");
+		return fret;
+	}
+
+	ret = write(fd, "500", sizeof("500") - 1);
+	close(fd);
+	if (ret < 0) {
+		fprintf(stderr, "%m - Failed to write pid_max\n");
+		return fret;
+	}
+
+	for (nr_procs = 0; nr_procs < 500; nr_procs++) {
+		pid = fork();
+		if (pid < 0)
+			break;
+
+		if (pid == 0)
+			exit(EXIT_SUCCESS);
+
+		pids[nr_procs] = pid;
+	}
+
+	if (nr_procs >= 400) {
+		fprintf(stderr, "Managed to create processes beyond the configured outer limit\n");
+		goto reap;
+	}
+
+	fret = 0;
+
+reap:
+	for (int i = 0; i < nr_procs; i++)
+		wait_for_pid(pids[i]);
+
+	return fret;
+}
+
+static int pid_max_nested_limit_outer(void *data)
+{
+	int fd, ret;
+	pid_t pid;
+
+	ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+		return -1;
+	}
+
+	umount2("/proc", MNT_DETACH);
+
+	ret = mount("proc", "/proc", "proc", 0, NULL);
+	if (ret) {
+		fprintf(stderr, "%m - Failed to mount proc\n");
+		return -1;
+	}
+
+	fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+	if (fd < 0) {
+		fprintf(stderr, "%m - Failed to open pid_max\n");
+		return -1;
+	}
+
+	ret = write(fd, "400", sizeof("400") - 1);
+	close(fd);
+	if (ret < 0) {
+		fprintf(stderr, "%m - Failed to write pid_max\n");
+		return -1;
+	}
+
+	pid = do_clone(pid_max_nested_limit_inner, NULL, CLONE_NEWPID | CLONE_NEWNS);
+	if (pid < 0) {
+		fprintf(stderr, "%m - Failed to clone nested pidns\n");
+		return -1;
+	}
+
+	if (wait_for_pid(pid)) {
+		fprintf(stderr, "%m - Nested pid_max failed\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+TEST(pid_max_simple)
+{
+	pid_t pid;
+
+
+	pid = do_clone(pid_max_cb, NULL, CLONE_NEWPID | CLONE_NEWNS);
+	ASSERT_GT(pid, 0);
+	ASSERT_EQ(0, wait_for_pid(pid));
+}
+
+TEST(pid_max_nested_limit)
+{
+	pid_t pid;
+
+	pid = do_clone(pid_max_nested_limit_outer, NULL, CLONE_NEWPID | CLONE_NEWNS);
+	ASSERT_GT(pid, 0);
+	ASSERT_EQ(0, wait_for_pid(pid));
+}
+
+TEST(pid_max_nested)
+{
+	pid_t pid;
+
+	pid = do_clone(pid_max_nested_outer, NULL, CLONE_NEWPID | CLONE_NEWNS);
+	ASSERT_GT(pid, 0);
+	ASSERT_EQ(0, wait_for_pid(pid));
+}
+
+TEST_HARNESS_MAIN