1 files changed, 165 insertions, 41 deletions

diff --git a/kernel/pid.c b/kernel/pid.c
index b52b10865454..924084713be8 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -42,6 +42,8 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/idr.h>
+#include <linux/pidfs.h>
+#include <linux/seqlock.h>
 #include <net/sock.h>
 #include <uapi/linux/pidfd.h>
 
@@ -59,12 +61,8 @@ struct pid init_struct_pid = {
 	}, }
 };
 
-int pid_max = PID_MAX_DEFAULT;
-
-#define RESERVED_PIDS		300
-
-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
@@ -104,6 +103,7 @@ EXPORT_SYMBOL_GPL(init_pid_ns);
  */
 
 static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
+seqcount_spinlock_t pidmap_lock_seq = SEQCNT_SPINLOCK_ZERO(pidmap_lock_seq, &pidmap_lock);
 
 void put_pid(struct pid *pid)
 {
@@ -154,6 +154,7 @@ void free_pid(struct pid *pid)
 
 		idr_remove(&ns->idr, upid->nr);
 	}
+	pidfs_remove_pid(pid);
 	spin_unlock_irqrestore(&pidmap_lock, flags);
 
 	call_rcu(&pid->rcu, delayed_put_pid);
@@ -189,6 +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];
@@ -269,20 +271,24 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	INIT_HLIST_HEAD(&pid->inodes);
 
 	upid = pid->numbers + ns->level;
+	idr_preload(GFP_KERNEL);
 	spin_lock_irq(&pidmap_lock);
 	if (!(ns->pid_allocated & PIDNS_ADDING))
 		goto out_unlock;
+	pidfs_add_pid(pid);
 	for ( ; upid >= pid->numbers; --upid) {
 		/* Make the PID visible to find_pid_ns. */
 		idr_replace(&upid->ns->idr, pid, upid->nr);
 		upid->ns->pid_allocated++;
 	}
 	spin_unlock_irq(&pidmap_lock);
+	idr_preload_end();
 
 	return pid;
 
 out_unlock:
 	spin_unlock_irq(&pidmap_lock);
+	idr_preload_end();
 	put_pid_ns(ns);
 
 out_free:
@@ -349,6 +355,11 @@ static void __change_pid(struct task_struct *task, enum pid_type type,
 	hlist_del_rcu(&task->pid_links[type]);
 	*pid_ptr = new;
 
+	if (type == PIDTYPE_PID) {
+		WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID));
+		wake_up_all(&pid->wait_pidfd);
+	}
+
 	for (tmp = PIDTYPE_MAX; --tmp >= 0; )
 		if (pid_has_task(pid, tmp))
 			return;
@@ -391,8 +402,7 @@ void exchange_tids(struct task_struct *left, struct task_struct *right)
 void transfer_pid(struct task_struct *old, struct task_struct *new,
 			   enum pid_type type)
 {
-	if (type == PIDTYPE_PID)
-		new->thread_pid = old->thread_pid;
+	WARN_ON_ONCE(type == PIDTYPE_PID);
 	hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]);
 }
 
@@ -526,20 +536,17 @@ EXPORT_SYMBOL_GPL(find_ge_pid);
 
 struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
 {
-	struct fd f;
+	CLASS(fd, f)(fd);
 	struct pid *pid;
 
-	f = fdget(fd);
-	if (!f.file)
+	if (fd_empty(f))
 		return ERR_PTR(-EBADF);
 
-	pid = pidfd_pid(f.file);
+	pid = pidfd_pid(fd_file(f));
 	if (!IS_ERR(pid)) {
 		get_pid(pid);
-		*flags = f.file->f_flags;
+		*flags = fd_file(f)->f_flags;
 	}
-
-	fdput(f);
 	return pid;
 }
 
@@ -552,11 +559,6 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
  * Return the task associated with @pidfd. The function takes a reference on
  * the returned task. The caller is responsible for releasing that reference.
  *
- * Currently, the process identified by @pidfd is always a thread-group leader.
- * This restriction currently exists for all aspects of pidfds including pidfd
- * creation (CLONE_PIDFD cannot be used with CLONE_THREAD) and pidfd polling
- * (only supports thread group leaders).
- *
  * Return: On success, the task_struct associated with the pidfd.
  *	   On error, a negative errno number will be returned.
  */
@@ -595,7 +597,7 @@ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags)
  * Return: On success, a cloexec pidfd is returned.
  *         On error, a negative errno number will be returned.
  */
-int pidfd_create(struct pid *pid, unsigned int flags)
+static int pidfd_create(struct pid *pid, unsigned int flags)
 {
 	int pidfd;
 	struct file *pidfd_file;
@@ -615,11 +617,8 @@ int pidfd_create(struct pid *pid, unsigned int flags)
  * @flags: flags to pass
  *
  * This creates a new pid file descriptor with the O_CLOEXEC flag set for
- * the process identified by @pid. Currently, the process identified by
- * @pid must be a thread-group leader. This restriction currently exists
- * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot
- * be used with CLONE_THREAD) and pidfd polling (only supports thread group
- * leaders).
+ * the task identified by @pid. Without PIDFD_THREAD flag the target task
+ * must be a thread-group leader.
  *
  * Return: On success, a cloexec pidfd is returned.
  *         On error, a negative errno number will be returned.
@@ -629,7 +628,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 	int fd;
 	struct pid *p;
 
-	if (flags & ~PIDFD_NONBLOCK)
+	if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD))
 		return -EINVAL;
 
 	if (pid <= 0)
@@ -645,17 +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 const 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);
 
@@ -666,6 +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;
@@ -682,7 +792,26 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 
 	up_read(&task->signal->exec_update_lock);
 
-	return file ?: ERR_PTR(-EBADF);
+	if (!file) {
+		/*
+		 * It is possible that the target thread is exiting; it can be
+		 * either:
+		 * 1. before exit_signals(), which gives a real fd
+		 * 2. before exit_files() takes the task_lock() gives a real fd
+		 * 3. after exit_files() releases task_lock(), ->files is NULL;
+		 *    this has PF_EXITING, since it was set in exit_signals(),
+		 *    __pidfd_fget() returns EBADF.
+		 * In case 3 we get EBADF, but that really means ESRCH, since
+		 * the task is currently exiting and has freed its files
+		 * struct, so we fix it up.
+		 */
+		if (task->flags & PF_EXITING)
+			file = ERR_PTR(-ESRCH);
+		else
+			file = ERR_PTR(-EBADF);
+	}
+
+	return file;
 }
 
 static int pidfd_getfd(struct pid *pid, int fd)
@@ -726,23 +855,18 @@ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd,
 		unsigned int, flags)
 {
 	struct pid *pid;
-	struct fd f;
-	int ret;
 
 	/* flags is currently unused - make sure it's unset */
 	if (flags)
 		return -EINVAL;
 
-	f = fdget(pidfd);
-	if (!f.file)
+	CLASS(fd, f)(pidfd);
+	if (fd_empty(f))
 		return -EBADF;
 
-	pid = pidfd_pid(f.file);
+	pid = pidfd_pid(fd_file(f));
 	if (IS_ERR(pid))
-		ret = PTR_ERR(pid);
-	else
-		ret = pidfd_getfd(pid, fd);
+		return PTR_ERR(pid);
 
-	fdput(f);
-	return ret;
+	return pidfd_getfd(pid, fd);
 }