pid_namespace: avoid optimization of accesses to ->child_reaper

To avoid potential problems related to cpu/compiler optimizations around
->child_reaper, let's use WRITE_ONCE (additional to task_list lock)
everywhere we write it and use READ_ONCE where we read it without
explicit lock. Note: It also pairs with existing READ_ONCE with no lock
in nsfs_fh_to_dentry().

Also let's add ASSERT_EXCLUSIVE_WRITER before write to identify to KCSAN
that we don't expect any concurrent ->child_reaper modifications, and
those must be detected.

--

Suggested-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://patch.msgid.link/20260318122157.280595-2-ptikhomirov@virtuozzo.com
v3: Split from main commit. Add ASSERT_EXCLUSIVE_WRITER.
v5: Add one more READ_ONCE for access without lock in free_pid().
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/kernel/exit.c b/kernel/exit.c
index ede3117fa7d413a40105af85be6da21583cbaa88..31b714c3a7914ba23004657068c38a0d021298ab 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -608,7 +608,8 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
 
        reaper = find_alive_thread(father);
        if (reaper) {
-               pid_ns->child_reaper = reaper;
+               ASSERT_EXCLUSIVE_WRITER(pid_ns->child_reaper);
+               WRITE_ONCE(pid_ns->child_reaper, reaper);
                return reaper;
        }
 

diff --git a/kernel/fork.c b/kernel/fork.c
index 65113a304518ae73590704034513ba06e708928a..874670450996d2e66a286534b842e8ddae7235ed 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2423,7 +2423,10 @@ __latent_entropy struct task_struct *copy_process(
                        init_task_pid(p, PIDTYPE_SID, task_session(current));
 
                        if (is_child_reaper(pid)) {
-                               ns_of_pid(pid)->child_reaper = p;
+                               struct pid_namespace *ns = ns_of_pid(pid);
+
+                               ASSERT_EXCLUSIVE_WRITER(ns->child_reaper);
+                               WRITE_ONCE(ns->child_reaper, p);
                                p->signal->flags |= SIGNAL_UNKILLABLE;
                        }
                        p->signal->shared_pending.signal = delayed.signal;

diff --git a/kernel/pid.c b/kernel/pid.c
index 3b96571d0fe652bbcc22fc80895c4e21df89f16c..386e51fcebb3ec2dc802aa2aac3a4c057b0f2df7 100644 (file)
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -128,7 +128,7 @@ void free_pid(struct pid *pid)
                         * is the reaper wake up the reaper.  The reaper
                         * may be sleeping in zap_pid_ns_processes().
                         */
-                       wake_up_process(ns->child_reaper);
+                       wake_up_process(READ_ONCE(ns->child_reaper));
                        break;
                case PIDNS_ADDING:
                        /* Handle a fork failure of the first process */
@@ -219,7 +219,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid,
                         * Also fail if a PID != 1 is requested and
                         * no PID 1 exists.
                         */
-                       if (tid != 1 && !tmp->child_reaper)
+                       if (tid != 1 && !READ_ONCE(tmp->child_reaper))
                                goto out_abort;
                        retval = -EPERM;
                        if (!checkpoint_restore_ns_capable(tmp->user_ns))