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 --- scripts/xz_wrap.sh | 162 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 162 insertions(+) create mode 100755 scripts/xz_wrap.sh (limited to 'scripts/xz_wrap.sh') diff --git a/scripts/xz_wrap.sh b/scripts/xz_wrap.sh new file mode 100755 index 000000000..f19369687 --- /dev/null +++ b/scripts/xz_wrap.sh @@ -0,0 +1,162 @@ +#!/bin/sh +# SPDX-License-Identifier: 0BSD +# +# This is a wrapper for xz to compress the kernel image using appropriate +# compression options depending on the architecture. +# +# Author: Lasse Collin + +# This has specialized settings for the following archs. However, +# XZ-compressed kernel isn't currently supported on every listed arch. +# +# Arch Align Notes +# arm 2/4 ARM and ARM-Thumb2 +# arm64 4 +# csky 2 +# loongarch 4 +# mips 2/4 MicroMIPS is 2-byte aligned +# parisc 4 +# powerpc 4 Uses its own wrapper for compressors instead of this. +# riscv 2/4 +# s390 2 +# sh 2 +# sparc 4 +# x86 1 + +# A few archs use 2-byte or 4-byte aligned instructions depending on +# the kernel config. This function is used to check if the relevant +# config option is set to "y". +is_enabled() +{ + grep -q "^$1=y$" include/config/auto.conf +} + +# XZ_VERSION is needed to disable features that aren't available in +# old XZ Utils versions. +XZ_VERSION=$($XZ --robot --version) || exit +XZ_VERSION=$(printf '%s\n' "$XZ_VERSION" | sed -n 's/^XZ_VERSION=//p') + +# Assume that no BCJ filter is available. +BCJ= + +# Set the instruction alignment to 1, 2, or 4 bytes. +# +# Set the BCJ filter if one is available. +# It must match the #ifdef usage in lib/decompress_unxz.c. +case $SRCARCH in + arm) + if is_enabled CONFIG_THUMB2_KERNEL; then + ALIGN=2 + BCJ=--armthumb + else + ALIGN=4 + BCJ=--arm + fi + ;; + + arm64) + ALIGN=4 + + # ARM64 filter was added in XZ Utils 5.4.0. + if [ "$XZ_VERSION" -ge 50040002 ]; then + BCJ=--arm64 + else + echo "$0: Upgrading to xz >= 5.4.0" \ + "would enable the ARM64 filter" \ + "for better compression" >&2 + fi + ;; + + csky) + ALIGN=2 + ;; + + loongarch) + ALIGN=4 + ;; + + mips) + if is_enabled CONFIG_CPU_MICROMIPS; then + ALIGN=2 + else + ALIGN=4 + fi + ;; + + parisc) + ALIGN=4 + ;; + + powerpc) + ALIGN=4 + + # The filter is only for big endian instruction encoding. + if is_enabled CONFIG_CPU_BIG_ENDIAN; then + BCJ=--powerpc + fi + ;; + + riscv) + if is_enabled CONFIG_RISCV_ISA_C; then + ALIGN=2 + else + ALIGN=4 + fi + + # RISC-V filter was added in XZ Utils 5.6.0. + if [ "$XZ_VERSION" -ge 50060002 ]; then + BCJ=--riscv + else + echo "$0: Upgrading to xz >= 5.6.0" \ + "would enable the RISC-V filter" \ + "for better compression" >&2 + fi + ;; + + s390) + ALIGN=2 + ;; + + sh) + ALIGN=2 + ;; + + sparc) + ALIGN=4 + BCJ=--sparc + ;; + + x86) + ALIGN=1 + BCJ=--x86 + ;; + + *) + echo "$0: Arch-specific tuning is missing for '$SRCARCH'" >&2 + + # Guess 2-byte-aligned instructions. Guessing too low + # should hurt less than guessing too high. + ALIGN=2 + ;; +esac + +# Select the LZMA2 options matching the instruction alignment. +case $ALIGN in + 1) LZMA2OPTS= ;; + 2) LZMA2OPTS=lp=1 ;; + 4) LZMA2OPTS=lp=2,lc=2 ;; + *) echo "$0: ALIGN wrong or missing" >&2; exit 1 ;; +esac + +# Use single-threaded mode because it compresses a little better +# (and uses less RAM) than multithreaded mode. +# +# For the best compression, the dictionary size shouldn't be +# smaller than the uncompressed kernel. 128 MiB dictionary +# needs less than 1400 MiB of RAM in single-threaded mode. +# +# On the archs that use this script to compress the kernel, +# decompression in the preboot code is done in single-call mode. +# Thus the dictionary size doesn't affect the memory requirements +# of the preboot decompressor at all. +exec $XZ --check=crc32 --threads=1 $BCJ --lzma2=$LZMA2OPTS,dict=128MiB -- cgit v1.3.1