x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

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) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 217 insertions, 0 deletions

diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
new file mode 100644
index 000000000..44f5a4397
--- /dev/null
+++ b/arch/riscv/Makefile
@@ -0,0 +1,217 @@
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies.
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+
+LDFLAGS_vmlinux := -z norelro
+ifeq ($(CONFIG_RELOCATABLE),y)
+	LDFLAGS_vmlinux += -shared -Bsymbolic -z notext
+	KBUILD_CFLAGS += -fPIE
+endif
+ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
+	LDFLAGS_vmlinux += --no-relax
+	KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
+ifeq ($(CONFIG_RISCV_ISA_C),y)
+	CC_FLAGS_FTRACE := -fpatchable-function-entry=8,4
+else
+	CC_FLAGS_FTRACE := -fpatchable-function-entry=4,2
+endif
+endif
+
+ifeq ($(CONFIG_CMODEL_MEDLOW),y)
+KBUILD_CFLAGS_MODULE += -mcmodel=medany
+endif
+
+export BITS
+ifeq ($(CONFIG_ARCH_RV64I),y)
+	BITS := 64
+
+	KBUILD_CFLAGS += -mabi=lp64
+	KBUILD_AFLAGS += -mabi=lp64
+
+	KBUILD_LDFLAGS += -melf64lriscv
+
+	KBUILD_RUSTFLAGS += -Ctarget-cpu=generic-rv64 --target=riscv64imac-unknown-none-elf \
+			    -Cno-redzone
+else
+	BITS := 32
+
+	KBUILD_CFLAGS += -mabi=ilp32
+	KBUILD_AFLAGS += -mabi=ilp32
+	KBUILD_LDFLAGS += -melf32lriscv
+endif
+
+UTS_MACHINE := riscv$(BITS)
+
+# LLVM has an issue with target-features and LTO: https://github.com/llvm/llvm-project/issues/59350
+# Ensure it is aware of linker relaxation with LTO, otherwise relocations may
+# be incorrect: https://github.com/llvm/llvm-project/issues/65090
+ifeq ($(CONFIG_LTO_CLANG),y)
+	KBUILD_LDFLAGS += -mllvm -mattr=+c -mllvm -mattr=+relax
+endif
+
+ifeq ($(CONFIG_SHADOW_CALL_STACK),y)
+	KBUILD_LDFLAGS += --no-relax-gp
+endif
+
+# ISA string setting
+riscv-march-$(CONFIG_ARCH_RV32I)	:= rv32ima
+riscv-march-$(CONFIG_ARCH_RV64I)	:= rv64ima
+riscv-march-$(CONFIG_FPU)		:= $(riscv-march-y)fd
+riscv-march-$(CONFIG_RISCV_ISA_C)	:= $(riscv-march-y)c
+riscv-march-$(CONFIG_RISCV_ISA_V)	:= $(riscv-march-y)v
+
+ifneq ($(CONFIG_RISCV_ISA_C),y)
+	KBUILD_RUSTFLAGS += -Ctarget-feature=-c
+endif
+
+ifdef CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC
+KBUILD_CFLAGS += -Wa,-misa-spec=2.2
+KBUILD_AFLAGS += -Wa,-misa-spec=2.2
+else
+riscv-march-$(CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI) := $(riscv-march-y)_zicsr_zifencei
+endif
+
+KBUILD_BASE_ISA = -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/')
+export KBUILD_BASE_ISA
+
+# Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by
+# matching non-v and non-multi-letter extensions out with the filter ([^v_]*)
+KBUILD_CFLAGS += $(KBUILD_BASE_ISA)
+
+KBUILD_AFLAGS += -march=$(riscv-march-y)
+
+# For C code built with floating-point support, exclude V but keep F and D.
+CC_FLAGS_FPU  := -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)([^v_]*)v?/\1\2/')
+
+KBUILD_CFLAGS += -mno-save-restore
+
+ifeq ($(CONFIG_CMODEL_MEDLOW),y)
+	KBUILD_CFLAGS += -mcmodel=medlow
+endif
+ifeq ($(CONFIG_CMODEL_MEDANY),y)
+	KBUILD_CFLAGS += -mcmodel=medany
+endif
+
+# Avoid generating .eh_frame sections.
+KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
+
+# The RISC-V attributes frequently cause compatibility issues and provide no
+# information, so just turn them off.
+KBUILD_CFLAGS += $(call cc-option,-mno-riscv-attribute)
+KBUILD_AFLAGS += $(call cc-option,-mno-riscv-attribute)
+KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr)
+KBUILD_AFLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr)
+
+KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
+KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
+
+# GCC versions that support the "-mstrict-align" option default to allowing
+# unaligned accesses.  While unaligned accesses are explicitly allowed in the
+# RISC-V ISA, they're emulated by machine mode traps on all extant
+# architectures.  It's faster to have GCC emit only aligned accesses.
+ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS),y)
+KBUILD_CFLAGS += $(call cc-option,-mstrict-align)
+endif
+
+ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
+prepare: stack_protector_prepare
+stack_protector_prepare: prepare0
+	$(eval KBUILD_CFLAGS += -mstack-protector-guard=tls		  \
+				-mstack-protector-guard-reg=tp		  \
+				-mstack-protector-guard-offset=$(shell	  \
+			awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}' \
+				$(objtree)/include/generated/asm-offsets.h))
+endif
+
+# arch specific predefines for sparse
+CHECKFLAGS += -D__riscv -D__riscv_xlen=$(BITS)
+
+# Default target when executing plain make
+boot					:= arch/riscv/boot
+boot-image-y				:= Image
+boot-image-$(CONFIG_KERNEL_BZIP2)	:= Image.bz2
+boot-image-$(CONFIG_KERNEL_GZIP)	:= Image.gz
+boot-image-$(CONFIG_KERNEL_LZ4)		:= Image.lz4
+boot-image-$(CONFIG_KERNEL_LZMA)	:= Image.lzma
+boot-image-$(CONFIG_KERNEL_LZO)		:= Image.lzo
+boot-image-$(CONFIG_KERNEL_ZSTD)	:= Image.zst
+boot-image-$(CONFIG_KERNEL_XZ)		:= Image.xz
+ifdef CONFIG_RISCV_M_MODE
+boot-image-$(CONFIG_SOC_CANAAN_K210)	:= loader.bin
+endif
+boot-image-$(CONFIG_EFI_ZBOOT)		:= vmlinuz.efi
+KBUILD_IMAGE				:= $(boot)/$(boot-image-y)
+
+libs-y += arch/riscv/lib/
+libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+
+ifeq ($(KBUILD_EXTMOD),)
+ifeq ($(CONFIG_MMU),y)
+prepare: vdso_prepare
+vdso_prepare: prepare0
+	$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso include/generated/vdso-offsets.h
+	$(if $(CONFIG_RISCV_USER_CFI),$(Q)$(MAKE) \
+		$(build)=arch/riscv/kernel/vdso_cfi include/generated/vdso-cfi-offsets.h)
+	$(if $(CONFIG_COMPAT),$(Q)$(MAKE) \
+		$(build)=arch/riscv/kernel/compat_vdso include/generated/compat_vdso-offsets.h)
+
+endif
+endif
+
+vdso-install-$(CONFIG_MMU)		+= arch/riscv/kernel/vdso/vdso.so.dbg
+vdso-install-$(CONFIG_RISCV_USER_CFI)	+= arch/riscv/kernel/vdso_cfi/vdso-cfi.so.dbg
+vdso-install-$(CONFIG_COMPAT)	+= arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg
+
+BOOT_TARGETS := Image Image.gz Image.bz2 Image.lz4 Image.lzma Image.lzo Image.zst Image.xz loader loader.bin vmlinuz.efi
+
+all:	$(notdir $(KBUILD_IMAGE))
+
+loader.bin: loader
+Image.gz Image.bz2 Image.lz4 Image.lzma Image.lzo Image.zst Image.xz loader vmlinuz.efi: Image
+
+$(BOOT_TARGETS): vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+	@$(kecho) '  Kernel: $(boot)/$@ is ready'
+
+# the install target always installs KBUILD_IMAGE (which may be compressed)
+# but keep the zinstall target for compatibility with older releases
+install zinstall:
+	$(call cmd,install)
+
+PHONY += rv32_randconfig
+rv32_randconfig:
+	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/32-bit.config \
+		-f $(srctree)/Makefile randconfig
+
+PHONY += rv64_randconfig
+rv64_randconfig:
+	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/64-bit.config \
+		-f $(srctree)/Makefile randconfig
+
+PHONY += rv32_defconfig
+rv32_defconfig:
+	$(Q)$(MAKE) -f $(srctree)/Makefile defconfig 32-bit.config
+
+PHONY += rv32_nommu_virt_defconfig
+rv32_nommu_virt_defconfig:
+	$(Q)$(MAKE) -f $(srctree)/Makefile nommu_virt_defconfig 32-bit.config
+
+define archhelp
+  echo  '  Image		- Uncompressed kernel image (arch/riscv/boot/Image)'
+  echo  '  Image.gz	- Compressed kernel image (arch/riscv/boot/Image.gz)'
+  echo  '  Image.bz2	- Compressed kernel image (arch/riscv/boot/Image.bz2)'
+  echo  '  Image.lz4	- Compressed kernel image (arch/riscv/boot/Image.lz4)'
+  echo  '  Image.lzma	- Compressed kernel image (arch/riscv/boot/Image.lzma)'
+  echo  '  Image.lzo	- Compressed kernel image (arch/riscv/boot/Image.lzo)'
+  echo  '  Image.zst	- Compressed kernel image (arch/riscv/boot/Image.zst)'
+  echo  '  Image.xz	- Compressed kernel image (arch/riscv/boot/Image.xz)'
+  echo  '  vmlinuz.efi	- Compressed EFI kernel image (arch/riscv/boot/vmlinuz.efi)'
+  echo  '		  Default when CONFIG_EFI_ZBOOT=y'
+  echo  '  install	- Install kernel using (your) ~/bin/$(INSTALLKERNEL) or'
+  echo  '		  (distribution) /sbin/$(INSTALLKERNEL) or install to '
+  echo  '		  $$(INSTALL_PATH)'
+endef