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, 56 insertions, 0 deletions

diff --git a/arch/alpha/lib/udelay.c b/arch/alpha/lib/udelay.c
new file mode 100644
index 000000000..873648263
--- /dev/null
+++ b/arch/alpha/lib/udelay.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 1993, 2000 Linus Torvalds
+ *
+ * Delay routines, using a pre-computed "loops_per_jiffy" value.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h> /* for udelay's use of smp_processor_id */
+#include <asm/param.h>
+#include <asm/smp.h>
+#include <linux/delay.h>
+
+/*
+ * Use only for very small delays (< 1 msec). 
+ *
+ * The active part of our cycle counter is only 32-bits wide, and
+ * we're treating the difference between two marks as signed.  On
+ * a 1GHz box, that's about 2 seconds.
+ */
+
+void
+__delay(int loops)
+{
+	int tmp;
+	__asm__ __volatile__(
+		"	rpcc %0\n"
+		"	addl %1,%0,%1\n"
+		"1:	rpcc %0\n"
+		"	subl %1,%0,%0\n"
+		"	bgt %0,1b"
+		: "=&r" (tmp), "=r" (loops) : "1"(loops));
+}
+EXPORT_SYMBOL(__delay);
+
+#ifdef CONFIG_SMP
+#define LPJ	 cpu_data[smp_processor_id()].loops_per_jiffy
+#else
+#define LPJ	 loops_per_jiffy
+#endif
+
+void
+udelay(unsigned long usecs)
+{
+	usecs *= (((unsigned long)HZ << 32) / 1000000) * LPJ;
+	__delay((long)usecs >> 32);
+}
+EXPORT_SYMBOL(udelay);
+
+void
+ndelay(unsigned long nsecs)
+{
+	nsecs *= (((unsigned long)HZ << 32) / 1000000000) * LPJ;
+	__delay((long)nsecs >> 32);
+}
+EXPORT_SYMBOL(ndelay);