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/clocksource/hyperv_timer.h | 111 +++++++++++++++++++++++++++++++++++++ 1 file changed, 111 insertions(+) create mode 100644 include/clocksource/hyperv_timer.h (limited to 'include/clocksource/hyperv_timer.h') diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h new file mode 100644 index 000000000..8d3befb7e --- /dev/null +++ b/include/clocksource/hyperv_timer.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Definitions for the clocksource provided by the Hyper-V + * hypervisor to guest VMs, as described in the Hyper-V Top + * Level Functional Spec (TLFS). + * + * Copyright (C) 2019, Microsoft, Inc. + * + * Author: Michael Kelley + */ + +#ifndef __CLKSOURCE_HYPERV_TIMER_H +#define __CLKSOURCE_HYPERV_TIMER_H + +#include +#include +#include + +#define HV_MAX_MAX_DELTA_TICKS 0xffffffff +#define HV_MIN_DELTA_TICKS 1 + +#ifdef CONFIG_HYPERV_TIMER + +#include + +/* Routines called by the VMbus driver */ +extern int hv_stimer_alloc(bool have_percpu_irqs); +extern int hv_stimer_cleanup(unsigned int cpu); +extern void hv_stimer_global_cleanup(void); + +extern void hv_init_clocksource(void); +extern void hv_remap_tsc_clocksource(void); + +extern unsigned long hv_get_tsc_pfn(void); +extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); + +extern void hv_adj_sched_clock_offset(u64 offset); + +static __always_inline bool +hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, + u64 *cur_tsc, u64 *time) +{ + u64 scale, offset; + u32 sequence; + + /* + * The protocol for reading Hyper-V TSC page is specified in Hypervisor + * Top-Level Functional Specification ver. 3.0 and above. To get the + * reference time we must do the following: + * - READ ReferenceTscSequence + * A special '0' value indicates the time source is unreliable and we + * need to use something else. The currently published specification + * versions (up to 4.0b) contain a mistake and wrongly claim '-1' + * instead of '0' as the special value, see commit c35b82ef0294. + * - ReferenceTime = + * ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset + * - READ ReferenceTscSequence again. In case its value has changed + * since our first reading we need to discard ReferenceTime and repeat + * the whole sequence as the hypervisor was updating the page in + * between. + */ + do { + sequence = READ_ONCE(tsc_pg->tsc_sequence); + if (!sequence) + return false; + /* + * Make sure we read sequence before we read other values from + * TSC page. + */ + smp_rmb(); + + scale = READ_ONCE(tsc_pg->tsc_scale); + offset = READ_ONCE(tsc_pg->tsc_offset); + *cur_tsc = hv_get_raw_timer(); + + /* + * Make sure we read sequence after we read all other values + * from TSC page. + */ + smp_rmb(); + + } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence); + + *time = mul_u64_u64_shr(*cur_tsc, scale, 64) + offset; + return true; +} + +#else /* CONFIG_HYPERV_TIMER */ +static inline unsigned long hv_get_tsc_pfn(void) +{ + return 0; +} + +static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void) +{ + return NULL; +} + +static __always_inline bool +hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time) +{ + return false; +} + +static inline int hv_stimer_cleanup(unsigned int cpu) { return 0; } +static inline void hv_stimer_global_cleanup(void) {} + +#endif /* CONFIG_HYPERV_TIMER */ + +#endif -- cgit v1.3.1