pid: perform free_pid() calls outside of tasklist_lock

As the clone side already executes pid allocation with only pidmap_lock
held, issuing free_pid() while still holding tasklist_lock exacerbates
total hold time of the latter.

More things may show up later which require initial clean up with the
lock held and allow finishing without it. For that reason a struct to
collect such work is added instead of merely passing the pid array.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Link: https://lore.kernel.org/r/20250206164415.450051-5-mjguzik@gmail.com
Acked-by: "Liam R. Howlett" <Liam.Howlett@Oracle.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 9 insertions, 5 deletions

diff --git a/kernel/sys.c b/kernel/sys.c
index cb366ff8703a..4efca8a97d62 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1085,6 +1085,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 {
 	struct task_struct *p;
 	struct task_struct *group_leader = current->group_leader;
+	struct pid *pids[PIDTYPE_MAX] = { 0 };
 	struct pid *pgrp;
 	int err;
 
@@ -1142,13 +1143,14 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 		goto out;
 
 	if (task_pgrp(p) != pgrp)
-		change_pid(p, PIDTYPE_PGID, pgrp);
+		change_pid(pids, p, PIDTYPE_PGID, pgrp);
 
 	err = 0;
 out:
 	/* All paths lead to here, thus we are safe. -DaveM */
 	write_unlock_irq(&tasklist_lock);
 	rcu_read_unlock();
+	free_pids(pids);
 	return err;
 }
 
@@ -1222,21 +1224,22 @@ out:
 	return retval;
 }
 
-static void set_special_pids(struct pid *pid)
+static void set_special_pids(struct pid **pids, struct pid *pid)
 {
 	struct task_struct *curr = current->group_leader;
 
 	if (task_session(curr) != pid)
-		change_pid(curr, PIDTYPE_SID, pid);
+		change_pid(pids, curr, PIDTYPE_SID, pid);
 
 	if (task_pgrp(curr) != pid)
-		change_pid(curr, PIDTYPE_PGID, pid);
+		change_pid(pids, curr, PIDTYPE_PGID, pid);
 }
 
 int ksys_setsid(void)
 {
 	struct task_struct *group_leader = current->group_leader;
 	struct pid *sid = task_pid(group_leader);
+	struct pid *pids[PIDTYPE_MAX] = { 0 };
 	pid_t session = pid_vnr(sid);
 	int err = -EPERM;
 
@@ -1252,13 +1255,14 @@ int ksys_setsid(void)
 		goto out;
 
 	group_leader->signal->leader = 1;
-	set_special_pids(sid);
+	set_special_pids(pids, sid);
 
 	proc_clear_tty(group_leader);
 
 	err = session;
 out:
 	write_unlock_irq(&tasklist_lock);
+	free_pids(pids);
 	if (err > 0) {
 		proc_sid_connector(group_leader);
 		sched_autogroup_create_attach(group_leader);