x86: Add straight-line-speculation mitigation

Make use of an upcoming GCC feature to mitigate
straight-line-speculation for x86:

  https://gcc.gnu.org/g:53a643f8568067d7700a9f2facc8ba39974973d3
  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102952
  https://bugs.llvm.org/show_bug.cgi?id=52323

It's built tested on x86_64-allyesconfig using GCC-12 and GCC-11.

Maintenance overhead of this should be fairly low due to objtool
validation.

Size overhead of all these additional int3 instructions comes to:

     text	   data	    bss	    dec	    hex	filename
  22267751	6933356	2011368	31212475	1dc43bb	defconfig-build/vmlinux
  22804126	6933356	1470696	31208178	1dc32f2	defconfig-build/vmlinux.sls

Or roughly 2.4% additional text.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NBorislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211204134908.140103474@infradead.org

arch/x86/Kconfig

@@ -472,6 +472,18 @@ config RETPOLINE
 	  branches. Requires a compiler with -mindirect-branch=thunk-extern
 	  support for full protection. The kernel may run slower.
 
+config CC_HAS_SLS
+	def_bool $(cc-option,-mharden-sls=all)
+
+config SLS
+	bool "Mitigate Straight-Line-Speculation"
+	depends on CC_HAS_SLS && X86_64
+	default n
+	help
+	  Compile the kernel with straight-line-speculation options to guard
+	  against straight line speculation. The kernel image might be slightly
+	  larger.
+
 config X86_CPU_RESCTRL
 	bool "x86 CPU resource control support"
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)

arch/x86/Makefile

@@ -191,6 +191,10 @@ ifdef CONFIG_RETPOLINE
   endif
 endif
 
+ifdef CONFIG_SLS
+  KBUILD_CFLAGS += -mharden-sls=all
+endif
+
 KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE)
 
 ifdef CONFIG_LTO_CLANG

arch/x86/include/asm/linkage.h

@@ -18,9 +18,19 @@
 #define __ALIGN_STR	__stringify(__ALIGN)
 #endif
 
+#ifdef CONFIG_SLS
+#define RET	ret; int3
+#else
+#define RET	ret
+#endif
+
 #else /* __ASSEMBLY__ */
 
+#ifdef CONFIG_SLS
+#define ASM_RET	"ret; int3\n\t"
+#else
 #define ASM_RET	"ret\n\t"
+#endif
 
 #endif /* __ASSEMBLY__ */
 

arch/x86/include/asm/static_call.h

@@ -36,7 +36,7 @@
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
 
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
-	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop")
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop")
 
 
 #define ARCH_ADD_TRAMP_KEY(name)					\

arch/x86/kernel/ftrace.c

@@ -303,7 +303,7 @@ union ftrace_op_code_union {
 	} __attribute__((packed));
 };
 
-#define RET_SIZE		1
+#define RET_SIZE		1 + IS_ENABLED(CONFIG_SLS)
 
 static unsigned long
 create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)

arch/x86/kernel/static_call.c

@@ -17,6 +17,8 @@ enum insn_type {
  */
 static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 };
 
+static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
+
 static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
 {
 	const void *emulate = NULL;
@@ -42,8 +44,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
 		break;
 
 	case RET:
-		code = text_gen_insn(RET_INSN_OPCODE, insn, func);
-		size = RET_INSN_SIZE;
+		code = &retinsn;
 		break;
 	}
 

arch/x86/lib/memmove_64.S

@@ -40,7 +40,7 @@ SYM_FUNC_START(__memmove)
 	/* FSRM implies ERMS => no length checks, do the copy directly */
 .Lmemmove_begin_forward:
 	ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM
-	ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; RET", X86_FEATURE_ERMS
+	ALTERNATIVE "", __stringify(movq %rdx, %rcx; rep movsb; RET), X86_FEATURE_ERMS
 
 	/*
 	 * movsq instruction have many startup latency

arch/x86/lib/retpoline.S

@@ -34,7 +34,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
 
 	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
 		      __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
-		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
+		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_AMD
 
 .endm
 

scripts/Makefile.build

@@ -234,7 +234,8 @@ objtool_args =								\
 	$(if $(CONFIG_GCOV_KERNEL)$(CONFIG_LTO_CLANG), --no-unreachable)\
 	$(if $(CONFIG_RETPOLINE), --retpoline)				\
 	$(if $(CONFIG_X86_SMAP), --uaccess)				\
-	$(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount)
+	$(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount)		\
+	$(if $(CONFIG_SLS), --sls)
 
 cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool_args) $@)
 cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd)

scripts/link-vmlinux.sh

@@ -139,6 +139,9 @@ objtool_link()
 		if [ -n "${CONFIG_X86_SMAP}" ]; then
 			objtoolopt="${objtoolopt} --uaccess"
 		fi
+		if [ -n "${CONFIG_SLS}" ]; then
+			objtoolopt="${objtoolopt} --sls"
+		fi
 		info OBJTOOL ${1}
 		tools/objtool/objtool ${objtoolcmd} ${objtoolopt} ${1}
 	fi