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 --- arch/arm/mach-versatile/hotplug.c | 102 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 102 insertions(+) create mode 100644 arch/arm/mach-versatile/hotplug.c (limited to 'arch/arm/mach-versatile/hotplug.c') diff --git a/arch/arm/mach-versatile/hotplug.c b/arch/arm/mach-versatile/hotplug.c new file mode 100644 index 000000000..5a1521755 --- /dev/null +++ b/arch/arm/mach-versatile/hotplug.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2002 ARM Ltd. + * All Rights Reserved + * + * This hotplug implementation is _specific_ to the situation found on + * ARM development platforms where there is _no_ possibility of actually + * taking a CPU offline, resetting it, or otherwise. Real platforms must + * NOT copy this code. + */ +#include +#include +#include + +#include +#include + +#include "platsmp.h" + +static inline void versatile_immitation_enter_lowpower(unsigned int actrl_mask) +{ + unsigned int v; + + asm volatile( + "mcr p15, 0, %1, c7, c5, 0\n" + " mcr p15, 0, %1, c7, c10, 4\n" + /* + * Turn off coherency + */ + " mrc p15, 0, %0, c1, c0, 1\n" + " bic %0, %0, %3\n" + " mcr p15, 0, %0, c1, c0, 1\n" + " mrc p15, 0, %0, c1, c0, 0\n" + " bic %0, %0, %2\n" + " mcr p15, 0, %0, c1, c0, 0\n" + : "=&r" (v) + : "r" (0), "Ir" (CR_C), "Ir" (actrl_mask) + : "cc"); +} + +static inline void versatile_immitation_leave_lowpower(unsigned int actrl_mask) +{ + unsigned int v; + + asm volatile( + "mrc p15, 0, %0, c1, c0, 0\n" + " orr %0, %0, %1\n" + " mcr p15, 0, %0, c1, c0, 0\n" + " mrc p15, 0, %0, c1, c0, 1\n" + " orr %0, %0, %2\n" + " mcr p15, 0, %0, c1, c0, 1\n" + : "=&r" (v) + : "Ir" (CR_C), "Ir" (actrl_mask) + : "cc"); +} + +static inline void versatile_immitation_do_lowpower(unsigned int cpu, int *spurious) +{ + /* + * there is no power-control hardware on this platform, so all + * we can do is put the core into WFI; this is safe as the calling + * code will have already disabled interrupts. + * + * This code should not be used outside Versatile platforms. + */ + for (;;) { + wfi(); + + if (versatile_cpu_release == cpu_logical_map(cpu)) { + /* + * OK, proper wakeup, we're done + */ + break; + } + + /* + * Getting here, means that we have come out of WFI without + * having been woken up - this shouldn't happen + * + * Just note it happening - when we're woken, we can report + * its occurrence. + */ + (*spurious)++; + } +} + +/* + * platform-specific code to shutdown a CPU. + * This code supports immitation-style CPU hotplug for Versatile/Realview/ + * Versatile Express platforms that are unable to do real CPU hotplug. + */ +void versatile_immitation_cpu_die(unsigned int cpu, unsigned int actrl_mask) +{ + int spurious = 0; + + versatile_immitation_enter_lowpower(actrl_mask); + versatile_immitation_do_lowpower(cpu, &spurious); + versatile_immitation_leave_lowpower(actrl_mask); + + if (spurious) + pr_warn("CPU%u: %u spurious wakeup calls\n", cpu, spurious); +} -- cgit v1.3.1