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 --- drivers/md/dm-vdo/cpu.h | 59 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 drivers/md/dm-vdo/cpu.h (limited to 'drivers/md/dm-vdo/cpu.h') diff --git a/drivers/md/dm-vdo/cpu.h b/drivers/md/dm-vdo/cpu.h new file mode 100644 index 000000000..d6a2615ba --- /dev/null +++ b/drivers/md/dm-vdo/cpu.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2023 Red Hat + */ + +#ifndef UDS_CPU_H +#define UDS_CPU_H + +#include + +/** + * uds_prefetch_address() - Minimize cache-miss latency by attempting to move data into a CPU cache + * before it is accessed. + * + * @address: the address to fetch (may be invalid) + * @for_write: must be constant at compile time--false if for reading, true if for writing + */ +static inline void uds_prefetch_address(const void *address, bool for_write) +{ + /* + * for_write won't be a constant if we are compiled with optimization turned off, in which + * case prefetching really doesn't matter. clang can't figure out that if for_write is a + * constant, it can be passed as the second, mandatorily constant argument to prefetch(), + * at least currently on llvm 12. + */ + if (__builtin_constant_p(for_write)) { + if (for_write) + __builtin_prefetch(address, true); + else + __builtin_prefetch(address, false); + } +} + +/** + * uds_prefetch_range() - Minimize cache-miss latency by attempting to move a range of addresses + * into a CPU cache before they are accessed. + * + * @start: the starting address to fetch (may be invalid) + * @size: the number of bytes in the address range + * @for_write: must be constant at compile time--false if for reading, true if for writing + */ +static inline void uds_prefetch_range(const void *start, unsigned int size, + bool for_write) +{ + /* + * Count the number of cache lines to fetch, allowing for the address range to span an + * extra cache line boundary due to address alignment. + */ + const char *address = (const char *) start; + unsigned int offset = ((uintptr_t) address % L1_CACHE_BYTES); + unsigned int cache_lines = (1 + ((size + offset) / L1_CACHE_BYTES)); + + while (cache_lines-- > 0) { + uds_prefetch_address(address, for_write); + address += L1_CACHE_BYTES; + } +} + +#endif /* UDS_CPU_H */ -- cgit v1.3.1