Merge tag 'pidfd-v5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull pidfd updates from Christian Brauner:
 "This patchset makes it possible to retrieve pidfds at process creation
  time by introducing the new flag CLONE_PIDFD to the clone() system
  call. Linus originally suggested to implement this as a new flag to
  clone() instead of making it a separate system call.

  After a thorough review from Oleg CLONE_PIDFD returns pidfds in the
  parent_tidptr argument. This means we can give back the associated pid
  and the pidfd at the same time. Access to process metadata information
  thus becomes rather trivial.

  As has been agreed, CLONE_PIDFD creates file descriptors based on
  anonymous inodes similar to the new mount api. They are made
  unconditional by this patchset as they are now needed by core kernel
  code (vfs, pidfd) even more than they already were before (timerfd,
  signalfd, io_uring, epoll etc.). The core patchset is rather small.
  The bulky looking changelist is caused by David's very simple changes
  to Kconfig to make anon inodes unconditional.

  A pidfd comes with additional information in fdinfo if the kernel
  supports procfs. The fdinfo file contains the pid of the process in
  the callers pid namespace in the same format as the procfs status
  file, i.e. "Pid:\t%d".

  To remove worries about missing metadata access this patchset comes
  with a sample/test program that illustrates how a combination of
  CLONE_PIDFD and pidfd_send_signal() can be used to gain race-free
  access to process metadata through /proc/<pid>.

  Further work based on this patchset has been done by Joel. His work
  makes pidfds pollable. It finished too late for this merge window. I
  would prefer to have it sitting in linux-next for a while and send it
  for inclusion during the 5.3 merge window"

* tag 'pidfd-v5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  samples: show race-free pidfd metadata access
  signal: support CLONE_PIDFD with pidfd_send_signal
  clone: add CLONE_PIDFD
  Make anon_inodes unconditional

3 files changed, 112 insertions, 10 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index fbe9dfcd8680..8b03d93ba068 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -11,6 +11,7 @@
  * management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
  */
 
+#include <linux/anon_inodes.h>
 #include <linux/slab.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/mm.h>
@@ -21,6 +22,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/seq_file.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
@@ -1670,6 +1672,58 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif /* #ifdef CONFIG_TASKS_RCU */
 }
 
+static int pidfd_release(struct inode *inode, struct file *file)
+{
+	struct pid *pid = file->private_data;
+
+	file->private_data = NULL;
+	put_pid(pid);
+	return 0;
+}
+
+#ifdef CONFIG_PROC_FS
+static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct pid_namespace *ns = proc_pid_ns(file_inode(m->file));
+	struct pid *pid = f->private_data;
+
+	seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
+	seq_putc(m, '\n');
+}
+#endif
+
+const struct file_operations pidfd_fops = {
+	.release = pidfd_release,
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo = pidfd_show_fdinfo,
+#endif
+};
+
+/**
+ * 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;
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -1682,13 +1736,14 @@ static __latent_entropy struct task_struct *copy_process(
 					unsigned long clone_flags,
 					unsigned long stack_start,
 					unsigned long stack_size,
+					int __user *parent_tidptr,
 					int __user *child_tidptr,
 					struct pid *pid,
 					int trace,
 					unsigned long tls,
 					int node)
 {
-	int retval;
+	int pidfd = -1, retval;
 	struct task_struct *p;
 	struct multiprocess_signals delayed;
 
@@ -1738,6 +1793,31 @@ static __latent_entropy struct task_struct *copy_process(
 			return ERR_PTR(-EINVAL);
 	}
 
+	if (clone_flags & CLONE_PIDFD) {
+		int reserved;
+
+		/*
+		 * - CLONE_PARENT_SETTID is useless for pidfds and also
+		 *   parent_tidptr is used to return pidfds.
+		 * - CLONE_DETACHED is blocked so that we can potentially
+		 *   reuse it later for CLONE_PIDFD.
+		 * - CLONE_THREAD is blocked until someone really needs it.
+		 */
+		if (clone_flags &
+		    (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD))
+			return ERR_PTR(-EINVAL);
+
+		/*
+		 * Verify that parent_tidptr is sane so we can potentially
+		 * reuse it later.
+		 */
+		if (get_user(reserved, parent_tidptr))
+			return ERR_PTR(-EFAULT);
+
+		if (reserved != 0)
+			return ERR_PTR(-EINVAL);
+	}
+
 	/*
 	 * Force any signals received before this point to be delivered
 	 * before the fork happens.  Collect up signals sent to multiple
@@ -1944,6 +2024,22 @@ static __latent_entropy struct task_struct *copy_process(
 		}
 	}
 
+	/*
+	 * This has to happen after we've potentially unshared the file
+	 * descriptor table (so that the pidfd doesn't leak into the child
+	 * if the fd table isn't shared).
+	 */
+	if (clone_flags & CLONE_PIDFD) {
+		retval = pidfd_create(pid);
+		if (retval < 0)
+			goto bad_fork_free_pid;
+
+		pidfd = retval;
+		retval = put_user(pidfd, parent_tidptr);
+		if (retval)
+			goto bad_fork_put_pidfd;
+	}
+
 #ifdef CONFIG_BLOCK
 	p->plug = NULL;
 #endif
@@ -2004,7 +2100,7 @@ static __latent_entropy struct task_struct *copy_process(
 	 */
 	retval = cgroup_can_fork(p);
 	if (retval)
-		goto bad_fork_free_pid;
+		goto bad_fork_put_pidfd;
 
 	/*
 	 * From this point on we must avoid any synchronous user-space
@@ -2119,6 +2215,9 @@ bad_fork_cancel_cgroup:
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
 	cgroup_cancel_fork(p);
+bad_fork_put_pidfd:
+	if (clone_flags & CLONE_PIDFD)
+		ksys_close(pidfd);
 bad_fork_free_pid:
 	cgroup_threadgroup_change_end(current);
 	if (pid != &init_struct_pid)
@@ -2184,7 +2283,7 @@ static inline void init_idle_pids(struct task_struct *idle)
 struct task_struct *fork_idle(int cpu)
 {
 	struct task_struct *task;
-	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+	task = copy_process(CLONE_VM, 0, 0, NULL, NULL, &init_struct_pid, 0, 0,
 			    cpu_to_node(cpu));
 	if (!IS_ERR(task)) {
 		init_idle_pids(task);
@@ -2236,7 +2335,7 @@ long _do_fork(unsigned long clone_flags,
 			trace = 0;
 	}
 
-	p = copy_process(clone_flags, stack_start, stack_size,
+	p = copy_process(clone_flags, stack_start, stack_size, parent_tidptr,
 			 child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
 	add_latent_entropy();
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 227ba170298e..cd83cc376767 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3513,7 +3513,6 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
 	return kill_something_info(sig, &info, pid);
 }
 
-#ifdef CONFIG_PROC_FS
 /*
  * Verify that the signaler and signalee either are in the same pid namespace
  * or that the signaler's pid namespace is an ancestor of the signalee's pid
@@ -3550,6 +3549,14 @@ static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t *info)
 	return copy_siginfo_from_user(kinfo, info);
 }
 
+static struct pid *pidfd_to_pid(const struct file *file)
+{
+	if (file->f_op == &pidfd_fops)
+		return file->private_data;
+
+	return tgid_pidfd_to_pid(file);
+}
+
 /**
  * sys_pidfd_send_signal - send a signal to a process through a task file
  *                          descriptor
@@ -3586,7 +3593,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 		return -EBADF;
 
 	/* Is this a pidfd? */
-	pid = tgid_pidfd_to_pid(f.file);
+	pid = pidfd_to_pid(f.file);
 	if (IS_ERR(pid)) {
 		ret = PTR_ERR(pid);
 		goto err;
@@ -3620,7 +3627,6 @@ err:
 	fdput(f);
 	return ret;
 }
-#endif /* CONFIG_PROC_FS */
 
 static int
 do_send_specific(pid_t tgid, pid_t pid, int sig, struct kernel_siginfo *info)
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index d21f4befaea4..4d9ae5ea6caf 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -167,9 +167,6 @@ COND_SYSCALL(syslog);
 
 /* kernel/sched/core.c */
 
-/* kernel/signal.c */
-COND_SYSCALL(pidfd_send_signal);
-
 /* kernel/sys.c */
 COND_SYSCALL(setregid);
 COND_SYSCALL(setgid);