[PATCH v2 2/2] pid: fix cad_pid use-after-free race

[Cen Zhang (Microsoft)]

proc_do_cad_pid() reads the global cad_pid pointer 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.

The sysctl is mode 0600, but access is checked against the owning user
namespace, so an unprivileged user can reach it via userns, pidns, and a
proc mount.

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.

KASAN crash stack:
  kernel/pid.c:545 pid_nr_ns()        # reads freed pid->level
  kernel/pid.c:556 pid_vnr()
  kernel/pid.c:775 proc_do_cad_pid()
  fs/proc/proc_sysctl.c proc_sys_call_handler()
  fs/read_write.c vfs_read()
  fs/read_write.c __x64_sys_pread64()

Fixes: 9ec52099e4b8 ("[PATCH] replace cad_pid by a struct pid")
Reported-by: AutonomousCodeSecurity@xxxxxxxxxxxxx
Closes: https://lore.kernel.org/all/20260717210143.4734-1-blbllhy@xxxxxxxxx/
Suggested-by: Mateusz Guzik <mjguzik@xxxxxxxxx>
Reviewed-by: Bradley Morgan <include@xxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Cen Zhang (Microsoft) <blbllhy@xxxxxxxxx>
---
v2:
  - Split out kill_cad_pid() deinline into a preparatory patch.
  - Annotate cad_pid as __rcu and use rcu_dereference().
  - Protect kill_cad_pid() by taking a pid reference under RCU.
  - Add a comment explaining why synchronize_rcu() is used instead of
    call_rcu().

 include/linux/sched.h |  2 +-
 init/main.c           |  2 +-
 kernel/pid.c          | 26 +++++++++++++++++++++++---
 kernel/reboot.c       |  2 +-
 4 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 373bcc0598d1..31ce72b1233c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1767,7 +1767,7 @@ 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/init/main.c b/init/main.c
index e363232b428b..19a10d0c2760 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1636,7 +1636,7 @@ 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/pid.c b/kernel/pid.c
index 234ebee29375..bffc5f765080 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -559,7 +559,17 @@ EXPORT_SYMBOL_GPL(pid_vnr);
 
 int kill_cad_pid(int sig, int priv)
 {
-	return kill_pid(cad_pid, sig, priv);
+	struct pid *pid;
+	int ret;
+
+	rcu_read_lock();
+	pid = get_pid(rcu_dereference(cad_pid));
+	rcu_read_unlock();
+
+	ret = kill_pid(pid, sig, priv);
+	put_pid(pid);
+
+	return ret;
 }
 
 pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
@@ -773,11 +783,15 @@ static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffe
 		size_t *lenp, loff_t *ppos)
 {
 	struct pid *new_pid;
+	struct pid *old_pid;
 	pid_t tmp_pid;
 	int r;
 	struct ctl_table tmp_table = *table;
 
-	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);
@@ -788,7 +802,13 @@ 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/reboot.c b/kernel/reboot.c
index 695c33e75efd..fc191a48c0e9 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -24,7 +24,7 @@
  */
 
 static int C_A_D = 1;
-struct pid *cad_pid;
+struct pid __rcu *cad_pid;
 EXPORT_SYMBOL(cad_pid);
 
 #if defined(CONFIG_ARM)
-- 
2.53.0