Merge patch series "pidfd: improve uapi when task isn't found"

Christian Brauner <brauner@kernel.org> says:

We currently report EINVAL whenever a struct pid has no tasked attached
anymore thereby conflating two concepts:

(1) The task has already been reaped.
(2) The caller requested a pidfd for a thread-group leader but the pid
    actually references a struct pid that isn't used as a thread-group
    leader.

This is causing issues for non-threaded workloads as in [1] where they
expect ESRCH to be reported, not EINVAL. I think that's a very resonable
assumption.

This patch tries to allow userspace to distinguish between (1) and (2).
This is racy of course but that shouldn't matter.

* patches from https://lore.kernel.org/r/20250403-work-pidfd-fixes-v1-0-a123b6ed6716@kernel.org:
  selftest/pidfd: add test for thread-group leader pidfd open for thread
  pidfd: improve uapi when task isn't found
  pidfd: remove unneeded NULL check from pidfd_prepare()
  selftests/pidfd: adapt to recent changes

Link: https://lore.kernel.org/r/20250403-work-pidfd-fixes-v1-0-a123b6ed6716@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

2 files changed, 27 insertions, 9 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index c4b26cd8998b..4a2080b968c8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2108,10 +2108,27 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
  */
 int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
 {
-	bool thread = flags & PIDFD_THREAD;
+	int err = 0;
 
-	if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID))
-		return -EINVAL;
+	if (!(flags & PIDFD_THREAD)) {
+		/*
+		 * If this is struct pid isn't used as a thread-group
+		 * leader pid but the caller requested to create a
+		 * thread-group leader pidfd then report ENOENT to the
+		 * caller as a hint.
+		 */
+		if (!pid_has_task(pid, PIDTYPE_TGID))
+			err = -ENOENT;
+	}
+
+	/*
+	 * If this wasn't a thread-group leader struct pid or the task
+	 * got reaped in the meantime report -ESRCH to userspace.
+	 */
+	if (!pid_has_task(pid, PIDTYPE_PID))
+		err = -ESRCH;
+	if (err)
+		return err;
 
 	return __pidfd_prepare(pid, flags, ret);
 }
diff --git a/tools/testing/selftests/pidfd/pidfd_info_test.c b/tools/testing/selftests/pidfd/pidfd_info_test.c
index 1758a1b0457b..a0eb6e81eaa2 100644
--- a/tools/testing/selftests/pidfd/pidfd_info_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_info_test.c
@@ -299,6 +299,7 @@ TEST_F(pidfd_info, thread_group)
 	/* Opening a thread as a thread-group leader must fail. */
 	pidfd_thread = sys_pidfd_open(pid_thread, 0);
 	ASSERT_LT(pidfd_thread, 0);
+	ASSERT_EQ(errno, ENOENT);
 
 	/* Opening a thread as a PIDFD_THREAD must succeed. */
 	pidfd_thread = sys_pidfd_open(pid_thread, PIDFD_THREAD);
@@ -362,9 +363,9 @@ TEST_F(pidfd_info, thread_group)
 	ASSERT_EQ(ioctl(pidfd_leader, PIDFD_GET_INFO, &info), 0);
 	ASSERT_FALSE(!!(info.mask & PIDFD_INFO_CREDS));
 	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_EXIT));
-	/* The thread-group leader exited successfully. Only the specific thread was SIGKILLed. */
-	ASSERT_TRUE(WIFEXITED(info.exit_code));
-	ASSERT_EQ(WEXITSTATUS(info.exit_code), 0);
+	/* Even though the thread-group exited successfully it will still report the group exit code. */
+	ASSERT_TRUE(WIFSIGNALED(info.exit_code));
+	ASSERT_EQ(WTERMSIG(info.exit_code), SIGKILL);
 
 	/*
 	 * Retrieve exit information for the thread-group leader via the
@@ -375,9 +376,9 @@ TEST_F(pidfd_info, thread_group)
 	ASSERT_FALSE(!!(info2.mask & PIDFD_INFO_CREDS));
 	ASSERT_TRUE(!!(info2.mask & PIDFD_INFO_EXIT));
 
-	/* The thread-group leader exited successfully. Only the specific thread was SIGKILLed. */
-	ASSERT_TRUE(WIFEXITED(info2.exit_code));
-	ASSERT_EQ(WEXITSTATUS(info2.exit_code), 0);
+	/* Even though the thread-group exited successfully it will still report the group exit code. */
+	ASSERT_TRUE(WIFSIGNALED(info2.exit_code));
+	ASSERT_EQ(WTERMSIG(info2.exit_code), SIGKILL);
 
 	/* Retrieve exit information for the thread. */
 	info.mask = PIDFD_INFO_CGROUPID | PIDFD_INFO_EXIT;