reboot: fix cad_pid use-after-free race

cad_pid is a single kernel-wide struct pid pointer. proc_do_cad_pid()
reads it and passes it to pid_vnr() without protecting the lifetime of
the referenced struct pid. A concurrent writer can replace cad_pid and
drop the final reference to the old struct pid after the reader has
loaded the pointer but before pid_vnr() has finished dereferencing it,
causing a use-after-free.

kill_cad_pid() has the same lifetime race when it passes cad_pid to
kill_pid().

At the time this issue was reported, an unprivileged user could reach the
sysctl through user and PID namespaces because cad_pid was registered in
pid_table[]. Moving cad_pid back to the global reboot sysctl table
corrected that namespace and permission mismatch, but did not fix the
underlying lifetime race.

Fix this by treating cad_pid as an RCU-protected pointer at both read
sites and by waiting for a grace period before dropping the old reference
on the write side.

call_rcu(&old_pid->rcu, ...) cannot be used here because free_pid()
also queues pid->rcu; queueing the same rcu_head twice can corrupt the
RCU callback list.

Original KASAN crash stack:
  kernel/pid.c:545 pid_nr_ns()        # reads freed pid->level
  kernel/pid.c:556 pid_vnr()          # calls pid_nr_ns()
  kernel/pid.c:775 proc_do_cad_pid()  # calls pid_vnr(cad_pid)

Fixes: 9ec52099e4b8 ("[PATCH] replace cad_pid by a struct pid")
Reported-by: AutonomousCodeSecurity@microsoft.com
Closes: https://lore.kernel.org/all/20260717210143.4734-1-blbllhy@gmail.com/
Link: https://lore.kernel.org/all/alz5ZYLE4kaq_v2P@redhat.com/
Link: https://lore.kernel.org/all/al4ICz9biJKtdZc4@redhat.com/
Suggested-by: Mateusz Guzik <mjguzik@gmail.com>
Suggested-by: Bradley Morgan <include@grrlz.net>
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Suggested-by: Eric W. Biederman <ebiederm@xmission.com>
Suggested-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Cc: stable@vger.kernel.org
Signed-off-by: Cen Zhang (Microsoft) <blbllhy@gmail.com>
Link: https://patch.msgid.link/20260814040944.16561-1-blbllhy@gmail.com
Reviewed-by: Bradley Morgan <include@grrlz.net>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

5 files changed, 30 insertions, 10 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3f100d69b053..fdafd164a42d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1778,7 +1778,7 @@ static inline bool is_lazy_mmu_mode_active(void)
 }
 #endif
 
-extern struct pid *cad_pid;
+extern struct pid __rcu *cad_pid;
 
 /*
  * Per process flags
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 584ae88b435e..d45a5476b97d 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -562,10 +562,7 @@ static inline sigset_t *sigmask_to_save(void)
 	return res;
 }
 
-static inline int kill_cad_pid(int sig, int priv)
-{
-	return kill_pid(cad_pid, sig, priv);
-}
+int kill_cad_pid(int sig, int priv);
 
 /* These can be the second arg to send_sig_info/send_group_sig_info.  */
 #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0)
diff --git a/init/main.c b/init/main.c
index 92d34e496a33..f46f3a8b3efd 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1644,7 +1644,7 @@ static noinline void __init kernel_init_freeable(void)
 	 */
 	set_mems_allowed(node_states[N_MEMORY]);
 
-	cad_pid = get_pid(task_pid(current));
+	rcu_assign_pointer(cad_pid, get_pid(task_pid(current)));
 
 	smp_prepare_cpus(setup_max_cpus);
 
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f070c5c1103a..d177d89fcc33 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -13,7 +13,9 @@
 #include <linux/kexec.h>
 #include <linux/kmod.h>
 #include <linux/kmsg_dump.h>
+#include <linux/rcupdate.h>
 #include <linux/reboot.h>
+#include <linux/sched/signal.h>
 #include <linux/suspend.h>
 #include <linux/syscalls.h>
 #include <linux/syscore_ops.h>
@@ -24,8 +26,7 @@
  */
 
 static int C_A_D = 1;
-struct pid *cad_pid;
-EXPORT_SYMBOL(cad_pid);
+struct pid __rcu *cad_pid;
 
 #if defined(CONFIG_ARM)
 #define DEFAULT_REBOOT_MODE		= REBOOT_HARD
@@ -1371,10 +1372,14 @@ static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffe
 {
 	struct ctl_table tmp_table = *table;
 	struct pid *new_pid;
+	struct pid *old_pid;
 	pid_t tmp_pid;
 	int r;
 
-	tmp_pid = pid_vnr(cad_pid);
+	rcu_read_lock();
+	tmp_pid = pid_vnr(rcu_dereference(cad_pid));
+	rcu_read_unlock();
+
 	tmp_table.data = &tmp_pid;
 
 	r = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
@@ -1385,7 +1390,13 @@ static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffe
 	if (!new_pid)
 		return -ESRCH;
 
-	put_pid(xchg(&cad_pid, new_pid));
+	old_pid = unrcu_pointer(xchg(&cad_pid, RCU_INITIALIZER(new_pid)));
+	/*
+	 * Wait for cad_pid readers before put_pid().  We cannot use
+	 * call_rcu() here because free_pid() already owns pid->rcu.
+	 */
+	synchronize_rcu();
+	put_pid(old_pid);
 	return 0;
 }
 
diff --git a/kernel/signal.c b/kernel/signal.c
index bbc0fd4cc4d7..2162fad7b940 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1899,6 +1899,18 @@ int kill_pid(struct pid *pid, int sig, int priv)
 }
 EXPORT_SYMBOL(kill_pid);
 
+int kill_cad_pid(int sig, int priv)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = kill_pid(rcu_dereference(cad_pid), sig, priv);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(kill_cad_pid);
+
 #ifdef CONFIG_POSIX_TIMERS
 /*
  * These functions handle POSIX timer signals. POSIX timers use