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, 163 insertions, 0 deletions

diff --git a/lib/ubsan.h b/lib/ubsan.h
new file mode 100644
index 000000000..b37e22374
--- /dev/null
+++ b/lib/ubsan.h
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LIB_UBSAN_H
+#define _LIB_UBSAN_H
+
+/*
+ * ABI defined by Clang's UBSAN enum SanitizerHandler:
+ * https://github.com/llvm/llvm-project/blob/release/16.x/clang/lib/CodeGen/CodeGenFunction.h#L113
+ */
+enum ubsan_checks {
+	ubsan_add_overflow,
+	ubsan_builtin_unreachable,
+	ubsan_cfi_check_fail,
+	ubsan_divrem_overflow,
+	ubsan_dynamic_type_cache_miss,
+	ubsan_float_cast_overflow,
+	ubsan_function_type_mismatch,
+	ubsan_implicit_conversion,
+	ubsan_invalid_builtin,
+	ubsan_invalid_objc_cast,
+	ubsan_load_invalid_value,
+	ubsan_missing_return,
+	ubsan_mul_overflow,
+	ubsan_negate_overflow,
+	ubsan_nullability_arg,
+	ubsan_nullability_return,
+	ubsan_nonnull_arg,
+	ubsan_nonnull_return,
+	ubsan_out_of_bounds,
+	ubsan_pointer_overflow,
+	ubsan_shift_out_of_bounds,
+	ubsan_sub_overflow,
+	ubsan_type_mismatch,
+	ubsan_alignment_assumption,
+	ubsan_vla_bound_not_positive,
+};
+
+enum {
+	type_kind_int = 0,
+	type_kind_float = 1,
+	type_unknown = 0xffff
+};
+
+struct type_descriptor {
+	u16 type_kind;
+	u16 type_info;
+	char type_name[];
+};
+
+struct source_location {
+	const char *file_name;
+	union {
+		unsigned long reported;
+		struct {
+			u32 line;
+			u32 column;
+		};
+	};
+};
+
+struct overflow_data {
+	struct source_location location;
+	struct type_descriptor *type;
+};
+
+struct implicit_conversion_data {
+	struct source_location location;
+	struct type_descriptor *from_type;
+	struct type_descriptor *to_type;
+	unsigned char type_check_kind;
+};
+
+struct type_mismatch_data {
+	struct source_location location;
+	struct type_descriptor *type;
+	unsigned long alignment;
+	unsigned char type_check_kind;
+};
+
+struct type_mismatch_data_v1 {
+	struct source_location location;
+	struct type_descriptor *type;
+	unsigned char log_alignment;
+	unsigned char type_check_kind;
+};
+
+struct type_mismatch_data_common {
+	struct source_location *location;
+	struct type_descriptor *type;
+	unsigned long alignment;
+	unsigned char type_check_kind;
+};
+
+struct nonnull_arg_data {
+	struct source_location location;
+	struct source_location attr_location;
+	int arg_index;
+};
+
+struct out_of_bounds_data {
+	struct source_location location;
+	struct type_descriptor *array_type;
+	struct type_descriptor *index_type;
+};
+
+struct shift_out_of_bounds_data {
+	struct source_location location;
+	struct type_descriptor *lhs_type;
+	struct type_descriptor *rhs_type;
+};
+
+struct unreachable_data {
+	struct source_location location;
+};
+
+struct invalid_value_data {
+	struct source_location location;
+	struct type_descriptor *type;
+};
+
+struct alignment_assumption_data {
+	struct source_location location;
+	struct source_location assumption_location;
+	struct type_descriptor *type;
+};
+
+#if defined(CONFIG_ARCH_SUPPORTS_INT128)
+typedef __int128 s_max;
+typedef unsigned __int128 u_max;
+#else
+typedef s64 s_max;
+typedef u64 u_max;
+#endif
+
+/*
+ * When generating Runtime Calls, Clang doesn't respect the -mregparm=3
+ * option used on i386: https://github.com/llvm/llvm-project/issues/89670
+ * Fix this for earlier Clang versions by forcing the calling convention
+ * to use non-register arguments.
+ */
+#if defined(CONFIG_X86_32) && \
+    defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 190000
+# define ubsan_linkage asmlinkage
+#else
+# define ubsan_linkage
+#endif
+
+void ubsan_linkage __ubsan_handle_add_overflow(void *data, void *lhs, void *rhs);
+void ubsan_linkage __ubsan_handle_sub_overflow(void *data, void *lhs, void *rhs);
+void ubsan_linkage __ubsan_handle_mul_overflow(void *data, void *lhs, void *rhs);
+void ubsan_linkage __ubsan_handle_negate_overflow(void *_data, void *old_val);
+void ubsan_linkage __ubsan_handle_divrem_overflow(void *_data, void *lhs, void *rhs);
+void ubsan_linkage __ubsan_handle_implicit_conversion(void *_data, void *lhs, void *rhs);
+void ubsan_linkage __ubsan_handle_type_mismatch(struct type_mismatch_data *data, void *ptr);
+void ubsan_linkage __ubsan_handle_type_mismatch_v1(void *_data, void *ptr);
+void ubsan_linkage __ubsan_handle_out_of_bounds(void *_data, void *index);
+void ubsan_linkage __ubsan_handle_shift_out_of_bounds(void *_data, void *lhs, void *rhs);
+void ubsan_linkage __ubsan_handle_builtin_unreachable(void *_data);
+void ubsan_linkage __ubsan_handle_load_invalid_value(void *_data, void *val);
+void ubsan_linkage __ubsan_handle_alignment_assumption(void *_data, unsigned long ptr,
+						       unsigned long align,
+						       unsigned long offset);
+
+#endif