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, 82 insertions, 0 deletions

diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
new file mode 100644
index 000000000..ffb73b612
--- /dev/null
+++ b/include/asm-generic/bitops/lock.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_LOCK_H_
+#define _ASM_GENERIC_BITOPS_LOCK_H_
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+/**
+ * arch_test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics if
+ * the returned value is 0.
+ * It can be used to implement bit locks.
+ */
+static __always_inline int
+arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *addr)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	addr += BIT_WORD(nr);
+	if (READ_ONCE(*addr) & mask)
+		return 1;
+
+	old = raw_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)addr);
+	return !!(old & mask);
+}
+
+
+/**
+ * arch_clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+static __always_inline void
+arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *addr)
+{
+	addr += BIT_WORD(nr);
+	raw_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)addr);
+}
+
+/**
+ * arch___clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * A weaker form of clear_bit_unlock() as used by __bit_lock_unlock(). If all
+ * the bits in the word are protected by this lock some archs can use weaker
+ * ops to safely unlock.
+ *
+ * See for example x86's implementation.
+ */
+static inline void
+arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *addr)
+{
+	unsigned long old;
+
+	addr += BIT_WORD(nr);
+	old = READ_ONCE(*addr);
+	old &= ~BIT_MASK(nr);
+	raw_atomic_long_set_release((atomic_long_t *)addr, old);
+}
+
+#ifndef arch_xor_unlock_is_negative_byte
+static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
+{
+	long old;
+
+	old = raw_atomic_long_fetch_xor_release(mask, (atomic_long_t *)p);
+	return !!(old & BIT(7));
+}
+#endif
+
+#include <asm-generic/bitops/instrumented-lock.h>
+
+#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */