pid: add pidfd_open()

This adds the pidfd_open() syscall. It allows a caller to retrieve pollable
pidfds for a process which did not get created via CLONE_PIDFD, i.e. for a
process that is created via traditional fork()/clone() calls that is only
referenced by a PID:

int pidfd = pidfd_open(1234, 0);
ret = pidfd_send_signal(pidfd, SIGSTOP, NULL, 0);

With the introduction of pidfds through CLONE_PIDFD it is possible to
created pidfds at process creation time.
However, a lot of processes get created with traditional PID-based calls
such as fork() or clone() (without CLONE_PIDFD). For these processes a
caller can currently not create a pollable pidfd. This is a problem for
Android's low memory killer (LMK) and service managers such as systemd.
Both are examples of tools that want to make use of pidfds to get reliable
notification of process exit for non-parents (pidfd polling) and race-free
signal sending (pidfd_send_signal()). They intend to switch to this API for
process supervision/management as soon as possible. Having no way to get
pollable pidfds from PID-only processes is one of the biggest blockers for
them in adopting this api. With pidfd_open() making it possible to retrieve
pidfds for PID-based processes we enable them to adopt this api.

In line with Arnd's recent changes to consolidate syscall numbers across
architectures, I have added the pidfd_open() syscall to all architectures
at the same time.

Signed-off-by: Christian Brauner <[email protected]>
Reviewed-by: David Howells <[email protected]>
Reviewed-by: Oleg Nesterov <[email protected]>
Acked-by: Arnd Bergmann <[email protected]>
Cc: "Eric W. Biederman" <[email protected]>
Cc: Kees Cook <[email protected]>
Cc: Joel Fernandes (Google) <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Jann Horn <[email protected]>
Cc: Andy Lutomirsky <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Aleksa Sarai <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Al Viro <[email protected]>
Cc: [email protected]

include/linux/syscalls.h

@@ -929,6 +929,7 @@ asmlinkage long sys_clock_adjtime32(clockid_t which_clock,
 				struct old_timex32 __user *tx);
 asmlinkage long sys_syncfs(int fd);
 asmlinkage long sys_setns(int fd, int nstype);
+asmlinkage long sys_pidfd_open(pid_t pid, unsigned int flags);
 asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg,
 			     unsigned int vlen, unsigned flags);
 asmlinkage long sys_process_vm_readv(pid_t pid,

kernel/pid.c

@@ -37,6 +37,8 @@
 #include <linux/syscalls.h>
 #include <linux/proc_ns.h>
 #include <linux/proc_fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/idr.h>
 
@@ -452,6 +454,73 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 	return idr_get_next(&ns->idr, &nr);
 }
 
+/**
+ * pidfd_create() - Create a new pid file descriptor.
+ *
+ * @pid:  struct pid that the pidfd will reference
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set.
+ *
+ * Note, that this function can only be called after the fd table has
+ * been unshared to avoid leaking the pidfd to the new process.
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ *         On error, a negative errno number will be returned.
+ */
+static int pidfd_create(struct pid *pid)
+{
+	int fd;
+
+	fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
+			      O_RDWR | O_CLOEXEC);
+	if (fd < 0)
+		put_pid(pid);
+
+	return fd;
+}
+
+/**
+ * pidfd_open() - Open new pid file descriptor.
+ *
+ * @pid:   pid for which to retrieve a pidfd
+ * @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).
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ *         On error, a negative errno number will be returned.
+ */
+SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
+{
+	int fd, ret;
+	struct pid *p;
+
+	if (flags)
+		return -EINVAL;
+
+	if (pid <= 0)
+		return -EINVAL;
+
+	p = find_get_pid(pid);
+	if (!p)
+		return -ESRCH;
+
+	ret = 0;
+	rcu_read_lock();
+	if (!pid_task(p, PIDTYPE_TGID))
+		ret = -EINVAL;
+	rcu_read_unlock();
+
+	fd = ret ?: pidfd_create(p);
+	put_pid(p);
+	return fd;
+}
+
 void __init pid_idr_init(void)
 {
 	/* Verify no one has done anything silly: */