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, 175 insertions, 0 deletions

diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
new file mode 100644
index 000000000..fcae1e432
--- /dev/null
+++ b/scripts/Makefile.vmlinux
@@ -0,0 +1,175 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+PHONY := __default
+__default: vmlinux
+
+include include/config/auto.conf
+include $(srctree)/scripts/Kbuild.include
+include $(srctree)/scripts/Makefile.lib
+
+targets :=
+
+%.o: %.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
+%.o: %.S FORCE
+	$(call if_changed_rule,as_o_S)
+
+# Built-in dtb
+# ---------------------------------------------------------------------------
+
+quiet_cmd_wrap_dtbs = WRAP    $@
+      cmd_wrap_dtbs = {							\
+	echo '\#include <asm-generic/vmlinux.lds.h>';			\
+	echo '.section .dtb.init.rodata,"a"';				\
+	while read dtb; do						\
+		symbase=__dtb_$$(basename -s .dtb "$${dtb}" | tr - _);	\
+		echo '.balign STRUCT_ALIGNMENT';			\
+		echo ".global $${symbase}_begin";			\
+		echo "$${symbase}_begin:";				\
+		echo '.incbin "'$$dtb'" ';				\
+		echo ".global $${symbase}_end";				\
+		echo "$${symbase}_end:";				\
+	done < $<;							\
+	} > $@
+
+.builtin-dtbs.S: .builtin-dtbs-list FORCE
+	$(call if_changed,wrap_dtbs)
+
+quiet_cmd_gen_dtbs_list = GEN     $@
+      cmd_gen_dtbs_list = \
+	$(if $(CONFIG_BUILTIN_DTB_NAME), echo "arch/$(SRCARCH)/boot/dts/$(CONFIG_BUILTIN_DTB_NAME).dtb",:) > $@
+
+.builtin-dtbs-list: arch/$(SRCARCH)/boot/dts/dtbs-list FORCE
+	$(call if_changed,$(if $(CONFIG_BUILTIN_DTB_ALL),copy,gen_dtbs_list))
+
+targets += .builtin-dtbs-list
+
+ifdef CONFIG_GENERIC_BUILTIN_DTB
+targets += .builtin-dtbs.S .builtin-dtbs.o
+vmlinux.unstripped: .builtin-dtbs.o
+endif
+
+# vmlinux.unstripped
+# ---------------------------------------------------------------------------
+
+ifdef CONFIG_ARCH_WANTS_PRE_LINK_VMLINUX
+vmlinux.unstripped: arch/$(SRCARCH)/tools/vmlinux.arch.o
+
+arch/$(SRCARCH)/tools/vmlinux.arch.o: vmlinux.o FORCE
+	$(Q)$(MAKE) $(build)=arch/$(SRCARCH)/tools $@
+endif
+
+ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
+
+# Final link of vmlinux with optional arch pass after final link
+cmd_link_vmlinux =							\
+	$< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)" "$@";	\
+	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
+
+targets += vmlinux.unstripped .vmlinux.export.o
+vmlinux.unstripped: scripts/link-vmlinux.sh vmlinux.o .vmlinux.export.o $(KBUILD_LDS) FORCE
+	+$(call if_changed_dep,link_vmlinux)
+ifdef CONFIG_DEBUG_INFO_BTF
+vmlinux.unstripped: $(RESOLVE_BTFIDS) $(srctree)/scripts/gen-btf.sh
+endif
+
+ifdef CONFIG_BUILDTIME_TABLE_SORT
+vmlinux.unstripped: scripts/sorttable
+endif
+
+# vmlinux
+# ---------------------------------------------------------------------------
+
+remove-section-y                                   := .modinfo
+remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel*' '!.rel*.dyn'
+# for compatibility with binutils < 2.32
+# https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=c12d9fa2afe7abcbe407a00e15719e1a1350c2a7
+remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel.*'
+
+remove-symbols := -w --strip-unneeded-symbol='__mod_device_table__*'
+
+# To avoid warnings: "empty loadable segment detected at ..." from GNU objcopy,
+# it is necessary to remove the PT_LOAD flag from the segment.
+quiet_cmd_strip_relocs = OBJCOPY $@
+      cmd_strip_relocs = $(OBJCOPY) $(patsubst %,--set-section-flags %=noload,$(remove-section-y)) $< $@; \
+                         $(OBJCOPY) $(addprefix --remove-section=,$(remove-section-y)) $(remove-symbols) $@
+
+targets += vmlinux
+vmlinux: vmlinux.unstripped FORCE
+	$(call if_changed,strip_relocs)
+
+# modules.builtin.modinfo
+# ---------------------------------------------------------------------------
+
+# .modinfo in vmlinux.unstripped is aligned to 8 bytes for compatibility with
+# tools that expect vmlinux to have sufficiently aligned sections but the
+# additional bytes used for padding .modinfo to satisfy this requirement break
+# certain versions of kmod with
+#
+#   depmod: ERROR: kmod_builtin_iter_next: unexpected string without modname prefix
+#
+# Strip the trailing padding bytes after extracting .modinfo to comply with
+# what kmod expects to parse.
+quiet_cmd_modules_builtin_modinfo = GEN     $@
+      cmd_modules_builtin_modinfo = $(cmd_objcopy); \
+                                    sed -i 's/\x00\+$$/\x00/g' $@; \
+                                    chmod -x $@
+
+OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary
+
+targets += modules.builtin.modinfo
+modules.builtin.modinfo: vmlinux.unstripped FORCE
+	$(call if_changed,modules_builtin_modinfo)
+
+# modules.builtin
+# ---------------------------------------------------------------------------
+
+__default: modules.builtin
+
+# The second line aids cases where multiple modules share the same object.
+
+quiet_cmd_modules_builtin = GEN     $@
+      cmd_modules_builtin = \
+	tr '\0' '\n' < $< | \
+	sed -n 's/^[[:alnum:]:_]*\.file=//p' | \
+	tr ' ' '\n' | uniq | sed -e 's:^:kernel/:' -e 's/$$/.ko/' > $@
+
+targets += modules.builtin
+modules.builtin: modules.builtin.modinfo FORCE
+	$(call if_changed,modules_builtin)
+
+# modules.builtin.ranges
+# ---------------------------------------------------------------------------
+ifdef CONFIG_BUILTIN_MODULE_RANGES
+__default: modules.builtin.ranges
+
+quiet_cmd_modules_builtin_ranges = GEN     $@
+      cmd_modules_builtin_ranges = gawk -f $(real-prereqs) > $@
+
+targets += modules.builtin.ranges
+modules.builtin.ranges: $(srctree)/scripts/generate_builtin_ranges.awk \
+			modules.builtin vmlinux.map vmlinux.o.map FORCE
+	$(call if_changed,modules_builtin_ranges)
+
+vmlinux.map: vmlinux.unstripped
+	@:
+
+endif
+
+# Add FORCE to the prerequisites of a target to force it to be always rebuilt.
+# ---------------------------------------------------------------------------
+
+PHONY += FORCE
+FORCE:
+
+# Read all saved command lines and dependencies for the $(targets) we
+# may be building above, using $(if_changed{,_dep}). As an
+# optimization, we don't need to read them if the target does not
+# exist, we will rebuild anyway in that case.
+
+existing-targets := $(wildcard $(sort $(targets)))
+
+-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd)
+
+.PHONY: $(PHONY)