From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions When using eBPF to probe CS CALL instructions within a function, a crash can be triggered. The eBPF tool probes offset 257 of the __hrtimer_run_queues() function: <__hrtimer_run_queues+249>: nopl 0x0(%rax,%rax,1) <__hrtimer_run_queues+254>: mov %r14,%rdi <__hrtimer_run_queues+257>: cs call <__x86_indirect_thunk_r12> <__hrtimer_run_queues+263>: mov %eax,%r12d <__hrtimer_run_queues+266>: xchg %ax,%ax <__hrtimer_run_queues+268>: mov %r13,%rdi Which triggers this crash: BUG: unable to handle page fault for address: 00000000000f41c9 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P RIP: 0010:__hrtimer_run_queues+0x106/0x230 Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is at the 6th byte of the above CS CALL instruction. Since the CS CALL instruction occupies 6 bytes, the exception occurred in the middle of that call instruction. The root cause is that when using eBPF tools to probe in the middle of a function, a kprobe with INT3 is used as the underlying implementation. During single-step emulation of the original CALL instruction, int3_emulate_call() assumes that the probed CALL instruction is 5 bytes long. However, the actual CS-prefixed CALL instruction occupies 6 bytes, so it constructs an incorrect exception return address. When the CPU returns from the kprobe handler, the next instruction to be executed is at the address of the last byte of that CS CALL instruction. Coincidentally, starting from that address, the CPU fetches and decodes a completely different instruction, which ultimately triggers a kernel crash. Fix the issue by using the actual instruction length obtained from the instruction decoder when constructing the exception return address, rather than relying on the hardcoded CALL_INSN_SIZE macro. [ mingo: Refined the changelog ] Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step") Suggested-by: Masami Hiramatsu (Google) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- include/asm-generic/bitops/instrumented-atomic.h | 103 +++++++++++++++++++++++ 1 file changed, 103 insertions(+) create mode 100644 include/asm-generic/bitops/instrumented-atomic.h (limited to 'include/asm-generic/bitops/instrumented-atomic.h') diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h new file mode 100644 index 000000000..c010d5427 --- /dev/null +++ b/include/asm-generic/bitops/instrumented-atomic.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This file provides wrappers with sanitizer instrumentation for atomic bit + * operations. + * + * To use this functionality, an arch's bitops.h file needs to define each of + * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), + * arch___set_bit(), etc.). + */ +#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H +#define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H + +#include + +/** + * set_bit - Atomically set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * This is a relaxed atomic operation (no implied memory barriers). + * + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static __always_inline void set_bit(long nr, volatile unsigned long *addr) +{ + instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); + arch_set_bit(nr, addr); +} + +/** + * clear_bit - Clears a bit in memory + * @nr: Bit to clear + * @addr: Address to start counting from + * + * This is a relaxed atomic operation (no implied memory barriers). + */ +static __always_inline void clear_bit(long nr, volatile unsigned long *addr) +{ + instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); + arch_clear_bit(nr, addr); +} + +/** + * change_bit - Toggle a bit in memory + * @nr: Bit to change + * @addr: Address to start counting from + * + * This is a relaxed atomic operation (no implied memory barriers). + * + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static __always_inline void change_bit(long nr, volatile unsigned long *addr) +{ + instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); + arch_change_bit(nr, addr); +} + +/** + * test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) +{ + kcsan_mb(); + instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_set_bit(nr, addr); +} + +/** + * test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) +{ + kcsan_mb(); + instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_clear_bit(nr, addr); +} + +/** + * test_and_change_bit - Change a bit and return its old value + * @nr: Bit to change + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) +{ + kcsan_mb(); + instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_change_bit(nr, addr); +} + +#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H */ -- cgit v1.3.1