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, 126 insertions, 0 deletions

diff --git a/arch/hexagon/mm/cache.c b/arch/hexagon/mm/cache.c
new file mode 100644
index 000000000..7e46f40c8
--- /dev/null
+++ b/arch/hexagon/mm/cache.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Cache management functions for Hexagon
+ *
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/mm.h>
+#include <asm/cacheflush.h>
+#include <asm/hexagon_vm.h>
+
+#define spanlines(start, end) \
+	(((end - (start & ~(LINESIZE - 1))) >> LINEBITS) + 1)
+
+void flush_dcache_range(unsigned long start, unsigned long end)
+{
+	unsigned long lines = spanlines(start, end-1);
+	unsigned long i, flags;
+
+	start &= ~(LINESIZE - 1);
+
+	local_irq_save(flags);
+
+	for (i = 0; i < lines; i++) {
+		__asm__ __volatile__ (
+		"	dccleaninva(%0);	"
+		:
+		: "r" (start)
+		);
+		start += LINESIZE;
+	}
+	local_irq_restore(flags);
+}
+
+void flush_icache_range(unsigned long start, unsigned long end)
+{
+	unsigned long lines = spanlines(start, end-1);
+	unsigned long i, flags;
+
+	start &= ~(LINESIZE - 1);
+
+	local_irq_save(flags);
+
+	for (i = 0; i < lines; i++) {
+		__asm__ __volatile__ (
+			"	dccleana(%0); "
+			"	icinva(%0);	"
+			:
+			: "r" (start)
+		);
+		start += LINESIZE;
+	}
+	__asm__ __volatile__ (
+		"isync"
+	);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_range);
+
+void hexagon_clean_dcache_range(unsigned long start, unsigned long end)
+{
+	unsigned long lines = spanlines(start, end-1);
+	unsigned long i, flags;
+
+	start &= ~(LINESIZE - 1);
+
+	local_irq_save(flags);
+
+	for (i = 0; i < lines; i++) {
+		__asm__ __volatile__ (
+		"	dccleana(%0);	"
+		:
+		: "r" (start)
+		);
+		start += LINESIZE;
+	}
+	local_irq_restore(flags);
+}
+
+void hexagon_inv_dcache_range(unsigned long start, unsigned long end)
+{
+	unsigned long lines = spanlines(start, end-1);
+	unsigned long i, flags;
+
+	start &= ~(LINESIZE - 1);
+
+	local_irq_save(flags);
+
+	for (i = 0; i < lines; i++) {
+		__asm__ __volatile__ (
+		"	dcinva(%0);	"
+		:
+		: "r" (start)
+		);
+		start += LINESIZE;
+	}
+	local_irq_restore(flags);
+}
+
+
+
+
+/*
+ * This is just really brutal and shouldn't be used anyways,
+ * especially on V2.  Left here just in case.
+ */
+void flush_cache_all_hexagon(void)
+{
+	unsigned long flags;
+	local_irq_save(flags);
+	__vmcache_ickill();
+	__vmcache_dckill();
+	__vmcache_l2kill();
+	local_irq_restore(flags);
+	mb();
+}
+
+void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
+		       unsigned long vaddr, void *dst, void *src, int len)
+{
+	memcpy(dst, src, len);
+	if (vma->vm_flags & VM_EXEC) {
+		flush_icache_range((unsigned long) dst,
+		(unsigned long) dst + len);
+	}
+}