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, 352 insertions, 0 deletions

diff --git a/lib/Makefile b/lib/Makefile
new file mode 100644
index 000000000..dfab95832
--- /dev/null
+++ b/lib/Makefile
@@ -0,0 +1,352 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for some libs needed in the kernel.
+#
+
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
+
+# Branch profiling isn't noinstr-safe
+ifdef CONFIG_TRACE_BRANCH_PROFILING
+CFLAGS_smp_processor_id.o += -DDISABLE_BRANCH_PROFILING
+endif
+
+# These files are disabled because they produce lots of non-interesting and/or
+# flaky coverage that is not a function of syscall inputs. For example,
+# rbtree can be global and individual rotations don't correlate with inputs.
+KCOV_INSTRUMENT_string.o := n
+KCOV_INSTRUMENT_rbtree.o := n
+KCOV_INSTRUMENT_list_debug.o := n
+KCOV_INSTRUMENT_debugobjects.o := n
+KCOV_INSTRUMENT_dynamic_debug.o := n
+KCOV_INSTRUMENT_fault-inject.o := n
+KCOV_INSTRUMENT_find_bit.o := n
+
+# string.o implements standard library functions like memset/memcpy etc.
+# Use -ffreestanding to ensure that the compiler does not try to "optimize"
+# them into calls to themselves.
+CFLAGS_string.o := -ffreestanding
+
+# Early boot use of cmdline, don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KASAN_SANITIZE_string.o := n
+
+CFLAGS_string.o += -fno-stack-protector
+endif
+
+lib-y := ctype.o string.o vsprintf.o cmdline.o \
+	 rbtree.o radix-tree.o timerqueue.o xarray.o \
+	 maple_tree.o idr.o extable.o irq_regs.o argv_split.o \
+	 flex_proportions.o ratelimit.o \
+	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
+	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
+	 nmi_backtrace.o win_minmax.o memcat_p.o \
+	 buildid.o objpool.o iomem_copy.o sys_info.o
+
+lib-$(CONFIG_UNION_FIND) += union_find.o
+lib-$(CONFIG_PRINTK) += dump_stack.o
+lib-$(CONFIG_SMP) += cpumask.o
+lib-$(CONFIG_MIN_HEAP) += min_heap.o
+
+lib-y	+= kobject.o klist.o
+obj-y	+= lockref.o
+
+CONTEXT_ANALYSIS_rhashtable.o := y
+
+obj-y += bcd.o sort.o parser.o debug_locks.o random32.o \
+	 bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
+	 list_sort.o uuid.o iov_iter.o clz_ctz.o \
+	 bsearch.o find_bit.o llist.o lwq.o memweight.o kfifo.o \
+	 percpu-refcount.o rhashtable.o base64.o \
+	 once.o refcount.o rcuref.o usercopy.o errseq.o bucket_locks.o \
+	 generic-radix-tree.o bitmap-str.o
+obj-y += string_helpers.o
+obj-y += hexdump.o
+obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o
+obj-y += kstrtox.o
+obj-$(CONFIG_FIND_BIT_BENCHMARK) += find_bit_benchmark.o
+obj-$(CONFIG_REGION_ALLOC_BENCHMARK) += region_alloc_benchmark.o
+obj-$(CONFIG_FIND_BIT_BENCHMARK_RUST) += find_bit_benchmark_rust.o
+obj-$(CONFIG_TEST_BPF) += test_bpf.o
+test_dhry-objs := dhry_1.o dhry_2.o dhry_run.o
+obj-$(CONFIG_TEST_DHRY) += test_dhry.o
+obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
+obj-$(CONFIG_TEST_BITOPS) += test_bitops.o
+CFLAGS_test_bitops.o += -Werror
+obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o
+obj-$(CONFIG_TEST_IDA) += test_ida.o
+obj-$(CONFIG_TEST_UBSAN) += test_ubsan.o
+CFLAGS_test_ubsan.o += $(call cc-disable-warning, unused-but-set-variable)
+UBSAN_SANITIZE_test_ubsan.o := y
+obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
+obj-$(CONFIG_TEST_LKM) += test_module.o
+obj-$(CONFIG_TEST_VMALLOC) += test_vmalloc.o
+obj-$(CONFIG_TEST_WORKQUEUE) += test_workqueue.o
+obj-$(CONFIG_TEST_RHASHTABLE) += test_rhashtable.o
+obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o
+obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o
+obj-$(CONFIG_TEST_DYNAMIC_DEBUG) += test_dynamic_debug.o
+
+obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
+ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_KASAN),yy)
+# FIXME: Clang breaks test_bitmap_const_eval when KASAN and GCOV are enabled
+GCOV_PROFILE_test_bitmap.o := n
+endif
+
+obj-$(CONFIG_TEST_XARRAY) += test_xarray.o
+obj-$(CONFIG_TEST_MAPLE_TREE) += test_maple_tree.o
+obj-$(CONFIG_TEST_PARMAN) += test_parman.o
+obj-$(CONFIG_TEST_KMOD) += test_kmod.o
+obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
+obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o
+obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o
+obj-$(CONFIG_TEST_MEMINIT) += test_meminit.o
+obj-$(CONFIG_TEST_LOCKUP) += test_lockup.o
+obj-$(CONFIG_TEST_HMM) += test_hmm.o
+obj-$(CONFIG_TEST_FREE_PAGES) += test_free_pages.o
+obj-$(CONFIG_TEST_REF_TRACKER) += test_ref_tracker.o
+obj-$(CONFIG_TEST_OBJPOOL) += test_objpool.o
+obj-$(CONFIG_TEST_KEXEC_HANDOVER) += test_kho.o
+
+obj-$(CONFIG_TEST_FPU) += test_fpu.o
+test_fpu-y := test_fpu_glue.o test_fpu_impl.o
+CFLAGS_test_fpu_impl.o += $(CC_FLAGS_FPU)
+CFLAGS_REMOVE_test_fpu_impl.o += $(CC_FLAGS_NO_FPU)
+
+obj-y += kunit/
+
+ifeq ($(CONFIG_DEBUG_KOBJECT),y)
+CFLAGS_kobject.o += -DDEBUG
+CFLAGS_kobject_uevent.o += -DDEBUG
+endif
+
+obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o
+CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any)
+
+obj-y += math/ crc/ crypto/ tests/ vdso/ raid/
+
+obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
+obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
+obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
+obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
+
+obj-$(CONFIG_GENERIC_CPU_CACHE_MAINTENANCE) += cache_maint.o
+
+lib-y += logic_pio.o
+
+lib-$(CONFIG_INDIRECT_IOMEM) += logic_iomem.o
+
+obj-$(CONFIG_TRACE_MMIO_ACCESS) += trace_readwrite.o
+
+obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
+
+obj-$(CONFIG_BTREE) += btree.o
+obj-$(CONFIG_INTERVAL_TREE) += interval_tree.o
+obj-$(CONFIG_ASSOCIATIVE_ARRAY) += assoc_array.o
+obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
+obj-$(CONFIG_LIST_HARDENED) += list_debug.o
+obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
+
+obj-$(CONFIG_GENERIC_BITREVERSE) += bitrev.o
+obj-$(CONFIG_LINEAR_RANGES) += linear_ranges.o
+obj-$(CONFIG_PACKING)	+= packing.o
+obj-$(CONFIG_PACKING_KUNIT_TEST) += packing_test.o
+obj-$(CONFIG_XXHASH)	+= xxhash.o
+obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
+
+obj-$(CONFIG_842_COMPRESS) += 842/
+obj-$(CONFIG_842_DECOMPRESS) += 842/
+obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
+obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
+obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc/
+obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
+obj-$(CONFIG_BCH) += bch.o
+obj-$(CONFIG_LZO_COMPRESS) += lzo/
+obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
+obj-$(CONFIG_LZ4_COMPRESS) += lz4/
+obj-$(CONFIG_LZ4HC_COMPRESS) += lz4/
+obj-$(CONFIG_LZ4_DECOMPRESS) += lz4/
+obj-$(CONFIG_ZSTD_COMPRESS) += zstd/
+obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd/
+obj-$(CONFIG_XZ_DEC) += xz/
+
+lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o
+lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o
+lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o
+lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o
+lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o
+lib-$(CONFIG_DECOMPRESS_LZ4) += decompress_unlz4.o
+lib-$(CONFIG_DECOMPRESS_ZSTD) += decompress_unzstd.o
+
+obj-$(CONFIG_TEXTSEARCH) += textsearch.o
+obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
+obj-$(CONFIG_TEXTSEARCH_BM) += ts_bm.o
+obj-$(CONFIG_TEXTSEARCH_FSM) += ts_fsm.o
+obj-$(CONFIG_SMP) += percpu_counter.o
+obj-$(CONFIG_AUDIT_GENERIC) += audit.o
+obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
+
+obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
+obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
+obj-$(CONFIG_FAULT_INJECTION_USERCOPY) += fault-inject-usercopy.o
+obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
+obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
+obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
+obj-$(CONFIG_MEMORY_NOTIFIER_ERROR_INJECT) += memory-notifier-error-inject.o
+obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \
+	of-reconfig-notifier-error-inject.o
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+
+obj-$(CONFIG_CODE_TAGGING) += codetag.o
+
+lib-$(CONFIG_GENERIC_BUG) += bug.o
+
+obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
+obj-$(CONFIG_ARCH_NEED_CMPXCHG_1_EMU) += cmpxchg-emu.o
+
+obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
+#ensure exported functions have prototypes
+CFLAGS_dynamic_debug.o := -DDYNAMIC_DEBUG_MODULE
+
+obj-$(CONFIG_SYMBOLIC_ERRNAME) += errname.o
+
+obj-$(CONFIG_NLATTR) += nlattr.o
+
+obj-$(CONFIG_LRU_CACHE) += lru_cache.o
+
+obj-$(CONFIG_GENERIC_CSUM) += checksum.o
+
+obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
+
+obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o
+
+obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
+
+obj-$(CONFIG_CLOSURES) += closure.o
+
+obj-$(CONFIG_DQL) += dynamic_queue_limits.o
+
+obj-$(CONFIG_GLOB) += glob.o
+
+obj-$(CONFIG_DIMLIB) += dim/
+obj-$(CONFIG_SIGNATURE) += digsig.o
+
+lib-$(CONFIG_CLZ_TAB) += clz_tab.o
+
+obj-$(CONFIG_GENERIC_STRNCPY_FROM_USER) += strncpy_from_user.o
+obj-$(CONFIG_GENERIC_STRNLEN_USER) += strnlen_user.o
+
+obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o
+
+obj-$(CONFIG_SG_SPLIT) += sg_split.o
+obj-$(CONFIG_SG_POOL) += sg_pool.o
+obj-$(CONFIG_MEMREGION) += memregion.o
+obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
+obj-$(CONFIG_IRQ_POLL) += irq_poll.o
+
+# stackdepot.c should not be instrumented or call instrumented functions.
+# Prevent the compiler from calling builtins like memcmp() or bcmp() from this
+# file.
+CFLAGS_stackdepot.o += -fno-builtin
+CONTEXT_ANALYSIS_stackdepot.o := y
+obj-$(CONFIG_STACKDEPOT) += stackdepot.o
+KASAN_SANITIZE_stackdepot.o := n
+# In particular, instrumenting stackdepot.c with KMSAN will result in infinite
+# recursion.
+KMSAN_SANITIZE_stackdepot.o := n
+KCOV_INSTRUMENT_stackdepot.o := n
+
+obj-$(CONFIG_REF_TRACKER) += ref_tracker.o
+
+libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \
+	       fdt_empty_tree.o fdt_addresses.o
+$(foreach file, $(libfdt_files), \
+	$(eval CFLAGS_$(file) = -I $(srctree)/scripts/dtc/libfdt))
+lib-$(CONFIG_LIBFDT) += $(libfdt_files)
+
+obj-$(CONFIG_BOOT_CONFIG) += bootconfig.o
+obj-$(CONFIG_BOOT_CONFIG_EMBED) += bootconfig-data.o
+
+$(obj)/bootconfig-data.o: $(obj)/default.bconf
+
+targets += default.bconf
+filechk_defbconf = cat $(or $(real-prereqs), /dev/null)
+$(obj)/default.bconf: $(CONFIG_BOOT_CONFIG_EMBED_FILE) FORCE
+	$(call filechk,defbconf)
+
+obj-$(CONFIG_CMDLINE_FROM_BOOTCONFIG) += embedded-cmdline.o
+$(obj)/embedded-cmdline.o: $(obj)/embedded_cmdline.bin
+
+# Render the bootconfig "kernel" subtree to a flat cmdline string using
+# the userspace tools/bootconfig parser (-C mode). The runtime prepend
+# helper enforces COMMAND_LINE_SIZE at boot, so no build-time size
+# check is performed here (COMMAND_LINE_SIZE is an arch header
+# constant, not a Kconfig value).
+quiet_cmd_render_cmdline = BCONF2C $@
+      cmd_render_cmdline = \
+	$(objtree)/tools/bootconfig/bootconfig -C $< > $@
+
+targets += embedded_cmdline.bin
+$(obj)/embedded_cmdline.bin: $(obj)/default.bconf $(objtree)/tools/bootconfig/bootconfig FORCE
+	$(call if_changed,render_cmdline)
+
+obj-$(CONFIG_RBTREE_TEST) += rbtree_test.o
+obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o
+
+obj-$(CONFIG_PERCPU_TEST) += percpu_test.o
+
+obj-$(CONFIG_ASN1) += asn1_decoder.o
+obj-$(CONFIG_ASN1_ENCODER) += asn1_encoder.o
+
+obj-$(CONFIG_FONT_SUPPORT) += fonts/
+
+#
+# Build a fast OID lookip registry from include/linux/oid_registry.h
+#
+obj-$(CONFIG_OID_REGISTRY) += oid_registry.o
+
+$(obj)/oid_registry.o: $(obj)/oid_registry_data.c
+
+$(obj)/oid_registry_data.c: $(srctree)/include/linux/oid_registry.h \
+			    $(src)/build_OID_registry
+	$(call cmd,build_OID_registry)
+
+quiet_cmd_build_OID_registry = GEN     $@
+      cmd_build_OID_registry = perl $(src)/build_OID_registry $< $@
+
+clean-files	+= oid_registry_data.c
+
+obj-$(CONFIG_UCS2_STRING) += ucs2_string.o
+obj-$(CONFIG_UBSAN) += ubsan.o
+
+UBSAN_SANITIZE_ubsan.o := n
+KASAN_SANITIZE_ubsan.o := n
+KCSAN_SANITIZE_ubsan.o := n
+KMSAN_SANITIZE_ubsan.o := n
+CFLAGS_ubsan.o := -fno-stack-protector $(DISABLE_KSTACK_ERASE)
+
+obj-$(CONFIG_SBITMAP) += sbitmap.o
+
+obj-$(CONFIG_PARMAN) += parman.o
+
+obj-y += group_cpus.o
+
+# GCC library routines
+obj-$(CONFIG_GENERIC_LIB_ASHLDI3) += ashldi3.o
+obj-$(CONFIG_GENERIC_LIB_ASHRDI3) += ashrdi3.o
+obj-$(CONFIG_GENERIC_LIB_LSHRDI3) += lshrdi3.o
+obj-$(CONFIG_GENERIC_LIB_MULDI3) += muldi3.o
+obj-$(CONFIG_GENERIC_LIB_CMPDI2) += cmpdi2.o
+obj-$(CONFIG_GENERIC_LIB_UCMPDI2) += ucmpdi2.o
+obj-$(CONFIG_OBJAGG) += objagg.o
+
+# pldmfw library
+obj-$(CONFIG_PLDMFW) += pldmfw/
+
+obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o
+
+obj-$(CONFIG_FIRMWARE_TABLE) += fw_table.o
+
+CONTEXT_ANALYSIS_test_context-analysis.o := y
+obj-$(CONFIG_CONTEXT_ANALYSIS_TEST) += test_context-analysis.o
+
+subdir-$(CONFIG_FORTIFY_SOURCE) += test_fortify