[PATCH v2] pid: Replace struct pid 1-element array with flex-array

[Kees Cook]

For pid namespaces, struct pid uses a dynamically sized array member,
"numbers". This was implemented using the ancient 1-element fake flexible
array, which has been deprecated for decades. Replace it with a C99
flexible array, refactor the array size calculations to use struct_size(),
and address elements via indexes. Note that the static initializer (which
defines a single element) works as-is, and requires no special handling.

Without this, CONFIG_UBSAN_BOUNDS (and potentially CONFIG_FORTIFY_SOURCE)
will trigger bounds checks when entering a pid namespace:
https://lore.kernel.org/lkml/20230517-bushaltestelle-super-e223978c1ba6@brauner

For example: unshare --fork --pid --mount-proc readlink /proc/self

Cc: Christian Brauner <brauner@xxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Andreas Gruenbacher <agruenba@xxxxxxxxxx>
Cc: Daniel Verkamp <dverkamp@xxxxxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
Cc: Jeff Xu <jeffxu@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: Luis Chamberlain <mcgrof@xxxxxxxxxx>
Cc: Frederic Weisbecker <frederic@xxxxxxxxxx>
Reported-by: syzbot+ac3b41786a2d0565b6d5@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://lore.kernel.org/lkml/000000000000c6de2a05fbdecbbb@xxxxxxxxxx/
Acked-by: Jeff Xu <jeffxu@xxxxxxxxxx>
Signed-off-by: Kees Cook <keescook@xxxxxxxxxxxx>
---
v2:
 - drop pointer math to array index conversions (torvalds)
 - use struct_size_t now that it exists (torvalds)
 - updated commit log with reproducer example
v1: https://lore.kernel.org/lkml/20230517225838.never.965-kees@xxxxxxxxxx/
---
 include/linux/pid.h    | 2 +-
 kernel/pid.c           | 7 +++++--
 kernel/pid_namespace.c | 2 +-
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/include/linux/pid.h b/include/linux/pid.h
index b75de288a8c2..653a527574c4 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -67,7 +67,7 @@ struct pid
 	/* wait queue for pidfd notifications */
 	wait_queue_head_t wait_pidfd;
 	struct rcu_head rcu;
-	struct upid numbers[1];
+	struct upid numbers[];
 };
 
 extern struct pid init_struct_pid;
diff --git a/kernel/pid.c b/kernel/pid.c
index f93954a0384d..6a1d23a11026 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -656,8 +656,11 @@ void __init pid_idr_init(void)
 
 	idr_init(&init_pid_ns.idr);
 
-	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
-			SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
+	init_pid_ns.pid_cachep = kmem_cache_create("pid",
+			struct_size_t(struct pid, numbers, 1),
+			__alignof__(struct pid),
+			SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT,
+			NULL);
 }
 
 static struct file *__pidfd_fget(struct task_struct *task, int fd)
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index b43eee07b00c..0bf44afe04dd 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -48,7 +48,7 @@ static struct kmem_cache *create_pid_cachep(unsigned int level)
 		return kc;
 
 	snprintf(name, sizeof(name), "pid_%u", level + 1);
-	len = sizeof(struct pid) + level * sizeof(struct upid);
+	len = struct_size_t(struct pid, numbers, level + 1);
 	mutex_lock(&pid_caches_mutex);
 	/* Name collision forces to do allocation under mutex. */
 	if (!*pkc)
-- 
2.34.1