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, 157 insertions, 0 deletions

diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
new file mode 100644
index 000000000..d7d45067d
--- /dev/null
+++ b/scripts/Makefile.modpost
@@ -0,0 +1,157 @@
+# SPDX-License-Identifier: GPL-2.0
+# ===========================================================================
+# Module versions
+# ===========================================================================
+#
+# Stage one of module building created the following:
+# a) The individual .o files used for the module
+# b) A <module>.o file which is the .o files above linked together
+# c) A <module>.mod file, listing the name of the preliminary <module>.o file,
+#    plus all .o files
+# d) modules.order, which lists all the modules
+
+# Stage 2 is handled by this file and does the following
+# 1) Find all modules listed in modules.order
+# 2) modpost is then used to
+# 3)  create one <module>.mod.c file per module
+# 4)  create one Module.symvers file with CRC for all exported symbols
+
+# Step 3 is used to place certain information in the module's ELF
+# section, including information such as:
+#   Version magic (see include/linux/vermagic.h for full details)
+#     - Kernel release
+#     - SMP is CONFIG_SMP
+#     - PREEMPT is CONFIG_PREEMPT[_RT]
+#     - GCC Version
+#   Module info
+#     - Module version (MODULE_VERSION)
+#     - Module alias'es (MODULE_ALIAS)
+#     - Module license (MODULE_LICENSE)
+#     - See include/linux/module.h for more details
+
+# Step 4 is solely used to allow module versioning in external modules,
+# where the CRC of each module is retrieved from the Module.symvers file.
+
+PHONY := __modpost
+__modpost:
+
+include $(objtree)/include/config/auto.conf
+include $(srctree)/scripts/Kbuild.include
+
+MODPOST = $(objtree)/scripts/mod/modpost
+
+modpost-args =										\
+	$(if $(CONFIG_MODULES),-M)							\
+	$(if $(CONFIG_MODVERSIONS),-m)							\
+	$(if $(CONFIG_BASIC_MODVERSIONS),-b)						\
+	$(if $(CONFIG_EXTENDED_MODVERSIONS),-x)						\
+	$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a)					\
+	$(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E)					\
+	$(if $(KBUILD_MODPOST_WARN),-w)							\
+	$(if $(KBUILD_NSDEPS),-d modules.nsdeps)					\
+	$(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N)	\
+	$(if $(findstring 1, $(KBUILD_EXTRA_WARN)),-W)					\
+	-o $@
+
+modpost-deps := $(MODPOST)
+
+# 'make -i -k' ignores compile errors, and builds as many modules as possible.
+ifneq ($(findstring i,$(filter-out --%,$(MAKEFLAGS))),)
+modpost-args += -n
+endif
+
+# Read out modules.order to pass in modpost.
+# Otherwise, allmodconfig would fail with "Argument list too long".
+ifdef KBUILD_MODULES
+modpost-args += -T modules.order
+modpost-deps += modules.order
+endif
+
+ifeq ($(KBUILD_EXTMOD),)
+
+# Generate the list of in-tree objects in vmlinux
+# ---------------------------------------------------------------------------
+
+# This is used to retrieve symbol versions generated by genksyms.
+ifdef CONFIG_MODVERSIONS
+vmlinux.symvers Module.symvers: .vmlinux.objs
+endif
+
+# Ignore libgcc.a
+# Some architectures do '$(CC) --print-libgcc-file-name' to borrow libgcc.a
+# from the toolchain, but there is no EXPORT_SYMBOL in it.
+
+quiet_cmd_vmlinux_objs = GEN     $@
+      cmd_vmlinux_objs =		\
+	for f in $(real-prereqs); do	\
+		case $${f} in		\
+		*libgcc.a) ;;		\
+		*) $(AR) t $${f} ;;	\
+		esac			\
+	done > $@
+
+targets += .vmlinux.objs
+.vmlinux.objs: vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
+	$(call if_changed,vmlinux_objs)
+
+ifdef CONFIG_TRIM_UNUSED_KSYMS
+ksym-wl := $(CONFIG_UNUSED_KSYMS_WHITELIST)
+ksym-wl := $(if $(filter-out /%, $(ksym-wl)),$(if $(wildcard $(ksym-wl)),,$(srctree)/))$(ksym-wl)
+modpost-args += -t $(addprefix -u , $(ksym-wl))
+modpost-deps += $(ksym-wl)
+endif
+
+ifeq ($(wildcard vmlinux.o),)
+missing-input := vmlinux.o
+output-symdump := modules-only.symvers
+else
+modpost-args += vmlinux.o
+modpost-deps += vmlinux.o
+output-symdump := $(if $(KBUILD_MODULES), Module.symvers, vmlinux.symvers)
+endif
+
+else
+
+# set src + obj - they may be used in the modules's Makefile
+obj := .
+src := $(srcroot)
+
+# Include the module's Makefile to find KBUILD_EXTRA_SYMBOLS
+include $(kbuild-file)
+
+output-symdump := Module.symvers
+
+ifeq ($(wildcard $(objtree)/Module.symvers),)
+missing-input := $(objtree)/Module.symvers
+else
+modpost-args += -i $(objtree)/Module.symvers
+modpost-deps += $(objtree)/Module.symvers
+endif
+
+modpost-args += -e $(addprefix -i , $(KBUILD_EXTRA_SYMBOLS))
+
+endif # ($(KBUILD_EXTMOD),)
+
+quiet_cmd_modpost = MODPOST $@
+      cmd_modpost = \
+	$(if $(missing-input), \
+		echo >&2 "WARNING: $(missing-input) is missing."; \
+		echo >&2 "         Modules may not have dependencies or modversions."; \
+		echo >&2 "         You may get many unresolved symbol errors."; \
+		echo >&2 "         You can set KBUILD_MODPOST_WARN=1 to turn errors into warning"; \
+		echo >&2 "         if you want to proceed at your own risk.";) \
+	$(MODPOST) $(modpost-args)
+
+targets += $(output-symdump)
+$(output-symdump): $(modpost-deps) FORCE
+	$(call if_changed,modpost)
+
+__modpost: $(output-symdump)
+PHONY += FORCE
+FORCE:
+
+existing-targets := $(wildcard $(sort $(targets)))
+
+-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd)
+
+.PHONY: $(PHONY)