arm64: Support Clang UBSAN trap codes for better reporting

When building with CONFIG_UBSAN_TRAP=y on arm64, Clang encodes the UBSAN
check (handler) type in the esr. Extract this and actually report these
traps as coming from the specific UBSAN check that tripped.

Before:

  Internal error: BRK handler: 00000000f20003e8 [#1] PREEMPT SMP

After:

  Internal error: UBSAN: shift out of bounds: 00000000f2005514 [#1] PREEMPT SMP

Acked-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Mukesh Ojha <quic_mojha@quicinc.com>
Reviewed-by: Fangrui Song <maskray@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: John Stultz <jstultz@google.com>
Cc: Yongqin Liu <yongqin.liu@linaro.org>
Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: Yury Norov <yury.norov@gmail.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Marco Elver <elver@google.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: llvm@lists.linux.dev
Signed-off-by: Kees Cook <keescook@chromium.org>

arch/arm64/include/asm/brk-imm.h

@@ -17,6 +17,7 @@
  * 0x401: for compile time BRK instruction
  * 0x800: kernel-mode BUG() and WARN() traps
  * 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff)
+ * 0x55xx: Undefined Behavior Sanitizer traps ('U' << 8)
  * 0x8xxx: Control-Flow Integrity traps
  */
 #define KPROBES_BRK_IMM			0x004
@@ -28,6 +29,8 @@
 #define BUG_BRK_IMM			0x800
 #define KASAN_BRK_IMM			0x900
 #define KASAN_BRK_MASK			0x0ff
+#define UBSAN_BRK_IMM			0x5500
+#define UBSAN_BRK_MASK			0x00ff
 
 #define CFI_BRK_IMM_TARGET		GENMASK(4, 0)
 #define CFI_BRK_IMM_TYPE		GENMASK(9, 5)

arch/arm64/kernel/traps.c

@@ -26,6 +26,7 @@
 #include <linux/syscalls.h>
 #include <linux/mm_types.h>
 #include <linux/kasan.h>
+#include <linux/ubsan.h>
 #include <linux/cfi.h>
 
 #include <asm/atomic.h>
@@ -1074,6 +1075,19 @@ static struct break_hook kasan_break_hook = {
 };
 #endif
 
+#ifdef CONFIG_UBSAN_TRAP
+static int ubsan_handler(struct pt_regs *regs, unsigned long esr)
+{
+	die(report_ubsan_failure(regs, esr & UBSAN_BRK_MASK), regs, esr);
+	return DBG_HOOK_HANDLED;
+}
+
+static struct break_hook ubsan_break_hook = {
+	.fn	= ubsan_handler,
+	.imm	= UBSAN_BRK_IMM,
+	.mask	= UBSAN_BRK_MASK,
+};
+#endif
 
 #define esr_comment(esr) ((esr) & ESR_ELx_BRK64_ISS_COMMENT_MASK)
 
@@ -1091,6 +1105,10 @@ int __init early_brk64(unsigned long addr, unsigned long esr,
 #ifdef CONFIG_KASAN_SW_TAGS
 	if ((esr_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
 		return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
+#endif
+#ifdef CONFIG_UBSAN_TRAP
+	if ((esr_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM)
+		return ubsan_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
 }
@@ -1104,6 +1122,9 @@ void __init trap_init(void)
 	register_kernel_break_hook(&fault_break_hook);
 #ifdef CONFIG_KASAN_SW_TAGS
 	register_kernel_break_hook(&kasan_break_hook);
+#endif
+#ifdef CONFIG_UBSAN_TRAP
+	register_kernel_break_hook(&ubsan_break_hook);
 #endif
 	debug_traps_init();
 }

include/linux/ubsan.h

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UBSAN_H
+#define _LINUX_UBSAN_H
+
+#ifdef CONFIG_UBSAN_TRAP
+const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type);
+#endif
+
+#endif

lib/Makefile

@@ -340,9 +340,7 @@ quiet_cmd_build_OID_registry = GEN     $@
 clean-files	+= oid_registry_data.c
 
 obj-$(CONFIG_UCS2_STRING) += ucs2_string.o
-ifneq ($(CONFIG_UBSAN_TRAP),y)
 obj-$(CONFIG_UBSAN) += ubsan.o
-endif
 
 UBSAN_SANITIZE_ubsan.o := n
 KASAN_SANITIZE_ubsan.o := n

lib/ubsan.c

@@ -14,10 +14,76 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
+#include <linux/ubsan.h>
 #include <kunit/test-bug.h>
 
 #include "ubsan.h"
 
+#ifdef CONFIG_UBSAN_TRAP
+/*
+ * Only include matches for UBSAN checks that are actually compiled in.
+ * The mappings of struct SanitizerKind (the -fsanitize=xxx args) to
+ * enum SanitizerHandler (the traps) in Clang is in clang/lib/CodeGen/.
+ */
+const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type)
+{
+	switch (check_type) {
+#ifdef CONFIG_UBSAN_BOUNDS
+	/*
+	 * SanitizerKind::ArrayBounds and SanitizerKind::LocalBounds
+	 * emit SanitizerHandler::OutOfBounds.
+	 */
+	case ubsan_out_of_bounds:
+		return "UBSAN: array index out of bounds";
+#endif
+#ifdef CONFIG_UBSAN_SHIFT
+	/*
+	 * SanitizerKind::ShiftBase and SanitizerKind::ShiftExponent
+	 * emit SanitizerHandler::ShiftOutOfBounds.
+	 */
+	case ubsan_shift_out_of_bounds:
+		return "UBSAN: shift out of bounds";
+#endif
+#ifdef CONFIG_UBSAN_DIV_ZERO
+	/*
+	 * SanitizerKind::IntegerDivideByZero emits
+	 * SanitizerHandler::DivremOverflow.
+	 */
+	case ubsan_divrem_overflow:
+		return "UBSAN: divide/remainder overflow";
+#endif
+#ifdef CONFIG_UBSAN_UNREACHABLE
+	/*
+	 * SanitizerKind::Unreachable emits
+	 * SanitizerHandler::BuiltinUnreachable.
+	 */
+	case ubsan_builtin_unreachable:
+		return "UBSAN: unreachable code";
+#endif
+#if defined(CONFIG_UBSAN_BOOL) || defined(CONFIG_UBSAN_ENUM)
+	/*
+	 * SanitizerKind::Bool and SanitizerKind::Enum emit
+	 * SanitizerHandler::LoadInvalidValue.
+	 */
+	case ubsan_load_invalid_value:
+		return "UBSAN: loading invalid value";
+#endif
+#ifdef CONFIG_UBSAN_ALIGNMENT
+	/*
+	 * SanitizerKind::Alignment emits SanitizerHandler::TypeMismatch
+	 * or SanitizerHandler::AlignmentAssumption.
+	 */
+	case ubsan_alignment_assumption:
+		return "UBSAN: alignment assumption";
+	case ubsan_type_mismatch:
+		return "UBSAN: type mismatch";
+#endif
+	default:
+		return "UBSAN: unrecognized failure code";
+	}
+}
+
+#else
 static const char * const type_check_kinds[] = {
 	"load of",
 	"store to",
@@ -384,3 +450,5 @@ void __ubsan_handle_alignment_assumption(void *_data, unsigned long ptr,
 	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_alignment_assumption);
+
+#endif /* !CONFIG_UBSAN_TRAP */

lib/ubsan.h

@@ -2,6 +2,38 @@
 #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,