From 6668ed271eaefaa63e686bdfbedaeb7b8e492722 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 10:43:19 +0200 Subject: selftests/bpf: Reject graph kptr use after RCU unlock 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 Link: https://lore.kernel.org/r/20260904084325.52250-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/vdso/futex.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 include/vdso/futex.h (limited to 'include/vdso/futex.h') diff --git a/include/vdso/futex.h b/include/vdso/futex.h new file mode 100644 index 000000000..3cd175eef --- /dev/null +++ b/include/vdso/futex.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _VDSO_FUTEX_H +#define _VDSO_FUTEX_H + +#include + +/** + * __vdso_futex_robust_list64_try_unlock - Try to unlock an uncontended robust futex + * with a 64-bit pending op pointer + * @lock: Pointer to the futex lock object + * @tid: The TID of the calling task + * @pop: Pointer to the task's robust_list_head::list_pending_op + * + * Return: The content of *@lock. On success this is the same as @tid. + * + * The function implements: + * if (atomic_try_cmpxchg(lock, &tid, 0)) + * *op = NULL; + * return tid; + * + * There is a race between a successful unlock and clearing the pending op + * pointer in the robust list head. If the calling task is interrupted in the + * race window and has to handle a (fatal) signal on return to user space then + * the kernel handles the clearing of @pending_op before attempting to deliver + * the signal. That ensures that a task cannot exit with a potentially invalid + * pending op pointer. + * + * User space uses it in the following way: + * + * if (__vdso_futex_robust_list64_try_unlock(lock, tid, &pending_op) != tid) + * err = sys_futex($OP | FUTEX_ROBUST_UNLOCK,....); + * + * If the unlock attempt fails due to the FUTEX_WAITERS bit set in the lock, + * then the syscall does the unlock, clears the pending op pointer and wakes the + * requested number of waiters. + */ +__u32 __vdso_futex_robust_list64_try_unlock(__u32 *lock, __u32 tid, __u64 *pop); + +/** + * __vdso_futex_robust_list32_try_unlock - Try to unlock an uncontended robust futex + * with a 32-bit pending op pointer + * @lock: Pointer to the futex lock object + * @tid: The TID of the calling task + * @pop: Pointer to the task's robust_list_head::list_pending_op + * + * Return: The content of *@lock. On success this is the same as @tid. + * + * Same as __vdso_futex_robust_list64_try_unlock() just with a 32-bit @pop pointer. + */ +__u32 __vdso_futex_robust_list32_try_unlock(__u32 *lock, __u32 tid, __u32 *pop); + +#endif -- cgit v1.3.1