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 --- drivers/cpuidle/Kconfig | 93 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 93 insertions(+) create mode 100644 drivers/cpuidle/Kconfig (limited to 'drivers/cpuidle/Kconfig') diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig new file mode 100644 index 000000000..00e256204 --- /dev/null +++ b/drivers/cpuidle/Kconfig @@ -0,0 +1,93 @@ +# SPDX-License-Identifier: GPL-2.0-only +menu "CPU Idle" + +config CPU_IDLE + bool "CPU idle PM support" + default y if ACPI || PPC_PSERIES + select CPU_IDLE_GOV_LADDER if (!NO_HZ && !NO_HZ_IDLE) + select CPU_IDLE_GOV_MENU if (NO_HZ || NO_HZ_IDLE) && !CPU_IDLE_GOV_TEO + help + CPU idle is a generic framework for supporting software-controlled + idle processor power management. It includes modular cross-platform + governors that can be swapped during runtime. + + If you're using an ACPI-enabled platform, you should say Y here. + +if CPU_IDLE + +config CPU_IDLE_MULTIPLE_DRIVERS + bool + +config CPU_IDLE_GOV_LADDER + bool "Ladder governor (for periodic timer tick)" + +config CPU_IDLE_GOV_MENU + bool "Menu governor (for tickless system)" + +config CPU_IDLE_GOV_TEO + bool "Timer events oriented (TEO) governor (for tickless systems)" + help + This governor implements a simplified idle state selection method + focused on timer events and does not do any interactivity boosting. + + Some workloads benefit from using it and it generally should be safe + to use. Say Y here if you are not happy with the alternatives. + +config CPU_IDLE_GOV_HALTPOLL + bool "Haltpoll governor (for virtualized systems)" + depends on KVM_GUEST + help + This governor implements haltpoll idle state selection, to be + used in conjunction with the haltpoll cpuidle driver, allowing + for polling for a certain amount of time before entering idle + state. + + Some virtualized workloads benefit from using it. + +config DT_IDLE_STATES + bool + +config DT_IDLE_GENPD + depends on PM_GENERIC_DOMAINS_OF + bool + +menu "ARM CPU Idle Drivers" +depends on ARM || ARM64 +source "drivers/cpuidle/Kconfig.arm" +endmenu + +menu "MIPS CPU Idle Drivers" +depends on MIPS +source "drivers/cpuidle/Kconfig.mips" +endmenu + +menu "POWERPC CPU Idle Drivers" +depends on PPC +source "drivers/cpuidle/Kconfig.powerpc" +endmenu + +menu "RISC-V CPU Idle Drivers" +depends on RISCV +source "drivers/cpuidle/Kconfig.riscv" +endmenu + +menu "S390 CPU Idle Drivers" +depends on S390 +source "drivers/cpuidle/Kconfig.s390" +endmenu + +config HALTPOLL_CPUIDLE + tristate "Halt poll cpuidle driver" + depends on X86 && KVM_GUEST + select CPU_IDLE_GOV_HALTPOLL + default y + help + This option enables halt poll cpuidle driver, which allows to poll + before halting in the guest (more efficient than polling in the + host via halt_poll_ns for some scenarios). + +endif # CPU_IDLE + +config ARCH_NEEDS_CPU_IDLE_COUPLED + def_bool n +endmenu -- cgit v1.3.1