selftests/bpf: Reject graph kptr use after RCU unlockgrafted

Add a sleepable verifier test that loads a graph-node local kptr in an
explicit RCU read-side critical section, then passes its node to
bpf_rbtree_remove() after the section ends.

Before the verifier fix, the stale NON_OWN_REF flag makes the node look like
a live borrowed reference and the program is accepted. After the fix, the
pointer is demoted without NON_OWN_REF and the graph kfunc argument is
rejected.

Also exercise a graph kptr loaded while a spin lock provides implicit RCU
protection. The pointer must be invalidated when the lock is released, which
guards the required ordering between non-owning-reference invalidation and
RCU demotion.

Update the existing fault-protected load test state description. The
post-unlock pointer no longer carries NON_OWN_REF, but remains readable
because the load is rewritten to use BPF_PROBE_MEM.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260904084325.52250-7-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 97 insertions, 0 deletions

diff --git a/fs/fs_pin.c b/fs/fs_pin.c
new file mode 100644
index 000000000..47ef3c71c
--- /dev/null
+++ b/fs/fs_pin.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include "internal.h"
+#include "mount.h"
+
+static DEFINE_SPINLOCK(pin_lock);
+
+void pin_remove(struct fs_pin *pin)
+{
+	spin_lock(&pin_lock);
+	hlist_del_init(&pin->m_list);
+	hlist_del_init(&pin->s_list);
+	spin_unlock(&pin_lock);
+	spin_lock_irq(&pin->wait.lock);
+	pin->done = 1;
+	wake_up_locked(&pin->wait);
+	spin_unlock_irq(&pin->wait.lock);
+}
+
+void pin_insert(struct fs_pin *pin, struct vfsmount *m)
+{
+	spin_lock(&pin_lock);
+	hlist_add_head(&pin->s_list, &m->mnt_sb->s_pins);
+	hlist_add_head(&pin->m_list, &real_mount(m)->mnt_pins);
+	spin_unlock(&pin_lock);
+}
+
+void pin_kill(struct fs_pin *p)
+{
+	wait_queue_entry_t wait;
+
+	if (!p) {
+		rcu_read_unlock();
+		return;
+	}
+	init_wait(&wait);
+	spin_lock_irq(&p->wait.lock);
+	if (likely(!p->done)) {
+		p->done = -1;
+		spin_unlock_irq(&p->wait.lock);
+		rcu_read_unlock();
+		p->kill(p);
+		return;
+	}
+	if (p->done > 0) {
+		spin_unlock_irq(&p->wait.lock);
+		rcu_read_unlock();
+		return;
+	}
+	__add_wait_queue(&p->wait, &wait);
+	while (1) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		spin_unlock_irq(&p->wait.lock);
+		rcu_read_unlock();
+		schedule();
+		rcu_read_lock();
+		if (likely(list_empty(&wait.entry)))
+			break;
+		/* OK, we know p couldn't have been freed yet */
+		spin_lock_irq(&p->wait.lock);
+		if (p->done > 0) {
+			spin_unlock_irq(&p->wait.lock);
+			break;
+		}
+	}
+	rcu_read_unlock();
+}
+
+void mnt_pin_kill(struct mount *m)
+{
+	while (1) {
+		struct hlist_node *p;
+		rcu_read_lock();
+		p = READ_ONCE(m->mnt_pins.first);
+		if (!p) {
+			rcu_read_unlock();
+			break;
+		}
+		pin_kill(hlist_entry(p, struct fs_pin, m_list));
+	}
+}
+
+void group_pin_kill(struct hlist_head *p)
+{
+	while (1) {
+		struct hlist_node *q;
+		rcu_read_lock();
+		q = READ_ONCE(p->first);
+		if (!q) {
+			rcu_read_unlock();
+			break;
+		}
+		pin_kill(hlist_entry(q, struct fs_pin, s_list));
+	}
+}