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, 134 insertions, 0 deletions

diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
new file mode 100644
index 000000000..0abcf994c
--- /dev/null
+++ b/arch/m68k/Makefile
@@ -0,0 +1,134 @@
+#
+# m68k/Makefile
+#
+# 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.
+#
+# Copyright (C) 1994 by Hamish Macdonald
+# Copyright (C) 2002,2011 Greg Ungerer <gerg@snapgear.com>
+#
+
+KBUILD_DEFCONFIG := multi_defconfig
+
+ifdef cross_compiling
+    ifeq ($(CROSS_COMPILE),)
+		CROSS_COMPILE := $(call cc-cross-prefix, \
+			m68k-linux-gnu- m68k-linux- m68k-unknown-linux-gnu-)
+    endif
+endif
+
+#
+#	Enable processor type. Ordering of these is important - we want to
+#	use the minimum processor type of the range we support. The logic
+#	for 680x0 will only allow use of the -m68060 or -m68040 if no other
+#	680x0 type is specified - and no option is specified for 68030 or
+#	68020. The other m68k/ColdFire types always specify some type of
+#	compiler cpu type flag.
+#
+ifndef CONFIG_M68040
+cpuflags-$(CONFIG_M68060)	= -m68060
+endif
+ifndef CONFIG_M68060
+cpuflags-$(CONFIG_M68040)	= -m68040
+endif
+cpuflags-$(CONFIG_M68030)	=
+cpuflags-$(CONFIG_M68020)	=
+cpuflags-$(CONFIG_M68000)	= -m68000
+cpuflags-$(CONFIG_M5441x)	= $(call cc-option,-mcpu=54455,-mcfv4e)
+cpuflags-$(CONFIG_M54xx)	= $(call cc-option,-mcpu=5475,-m5200)
+cpuflags-$(CONFIG_M5407)	= $(call cc-option,-mcpu=5407,-m5200)
+cpuflags-$(CONFIG_M532x)	= $(call cc-option,-mcpu=532x,-m5307)
+cpuflags-$(CONFIG_M537x)	= $(call cc-option,-mcpu=537x,-m5307)
+cpuflags-$(CONFIG_M5307)	= $(call cc-option,-mcpu=5307,-m5200)
+cpuflags-$(CONFIG_M528x)	= $(call cc-option,-mcpu=528x,-m5307)
+cpuflags-$(CONFIG_M5275)	= $(call cc-option,-mcpu=5275,-m5307)
+cpuflags-$(CONFIG_M5272)	= $(call cc-option,-mcpu=5272,-m5307)
+cpuflags-$(CONFIG_M5271)	= $(call cc-option,-mcpu=5271,-m5307)
+cpuflags-$(CONFIG_M523x)	= $(call cc-option,-mcpu=523x,-m5307)
+cpuflags-$(CONFIG_M525x)	= $(call cc-option,-mcpu=5253,-m5200)
+cpuflags-$(CONFIG_M5249)	= $(call cc-option,-mcpu=5249,-m5200)
+cpuflags-$(CONFIG_M520x)	= $(call cc-option,-mcpu=5208,-m5200)
+cpuflags-$(CONFIG_M5206e)	= $(call cc-option,-mcpu=5206e,-m5200)
+cpuflags-$(CONFIG_M5206)	= $(call cc-option,-mcpu=5206,-m5200)
+
+# Evaluate tune cc-option calls now
+cpuflags-y := $(cpuflags-y)
+
+KBUILD_AFLAGS += $(cpuflags-y)
+KBUILD_CFLAGS += $(cpuflags-y)
+
+KBUILD_CFLAGS += -pipe -ffreestanding
+
+ifdef CONFIG_MMU
+KBUILD_CFLAGS += -ffixed-a2
+else
+# we can use a m68k-linux-gcc toolchain with these in place
+KBUILD_CPPFLAGS += -DUTS_SYSNAME=\"uClinux\"
+KBUILD_CPPFLAGS += -D__uClinux__
+endif
+
+KBUILD_LDFLAGS := -m m68kelf
+
+ifdef CONFIG_SUN3
+LDFLAGS_vmlinux = -N
+endif
+
+CHECKFLAGS += -D__mc68000__
+
+
+ifdef CONFIG_KGDB
+# If configured for kgdb support, include debugging infos and keep the
+# frame pointer
+KBUILD_CFLAGS := $(subst -fomit-frame-pointer,,$(KBUILD_CFLAGS)) -g
+endif
+
+libs-y				+= arch/m68k/lib/
+
+
+all:	zImage
+
+lilo:	vmlinux
+	if [ -f $(INSTALL_PATH)/vmlinux ]; then mv -f $(INSTALL_PATH)/vmlinux $(INSTALL_PATH)/vmlinux.old; fi
+	if [ -f $(INSTALL_PATH)/System.map ]; then mv -f $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi
+	cat vmlinux > $(INSTALL_PATH)/vmlinux
+	cp System.map $(INSTALL_PATH)/System.map
+	if [ -x /sbin/lilo ]; then /sbin/lilo; else /etc/lilo/install; fi
+
+zImage compressed: vmlinux.gz
+
+vmlinux.gz: vmlinux
+
+ifndef CONFIG_KGDB
+	cp vmlinux vmlinux.tmp
+	$(STRIP) vmlinux.tmp
+	$(KGZIP) -9c vmlinux.tmp >vmlinux.gz
+	rm vmlinux.tmp
+else
+	$(KGZIP) -9c vmlinux >vmlinux.gz
+endif
+
+bzImage: vmlinux.bz2
+
+vmlinux.bz2: vmlinux
+
+ifndef CONFIG_KGDB
+	cp vmlinux vmlinux.tmp
+	$(STRIP) vmlinux.tmp
+	$(KBZIP2) -1c vmlinux.tmp >vmlinux.bz2
+	rm vmlinux.tmp
+else
+	$(KBZIP2) -1c vmlinux >vmlinux.bz2
+endif
+
+CLEAN_FILES += vmlinux.gz vmlinux.bz2
+
+archheaders:
+	$(Q)$(MAKE) $(build)=arch/m68k/kernel/syscalls all
+
+install: KBUILD_IMAGE := vmlinux.gz
+install:
+	$(call cmd,install)