x86: Add straight-line-speculation mitigation

[ Upstream commit e463a09af2f0677b9485a7e8e4e70b396b2ffb6f ]

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: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211204134908.140103474@infradead.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 819f8c2..d02b04d 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -468,6 +468,18 @@ 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)

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 7488cfb..3002278 100644 (file)
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -179,6 +179,10 @@ ifdef CONFIG_RETPOLINE
   endif
 endif
 
+ifdef CONFIG_SLS
+  KBUILD_CFLAGS += -mharden-sls=all
+endif
+
 KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE)
 
 ifdef CONFIG_LTO_CLANG

diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index ebddec2..0309079 100644 (file)
--- a/arch/x86/include/asm/linkage.h
+++ b/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__ */
 

diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index cbb67b6..3432345 100644 (file)
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -35,7 +35,7 @@
        __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)                                       \

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1b3ce3b..847776c 100644 (file)
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -308,7 +308,7 @@ 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)

diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 3d68dfb..3ec2cb8 100644 (file)
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -16,6 +16,8 @@ enum insn_type {
  */
 static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 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;
@@ -41,8 +43,7 @@ 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;
        }
 

diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index e84d649..50ea390 100644 (file)
--- a/arch/x86/lib/memmove_64.S
+++ b/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

diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index d7455ee..9556ff5 100644 (file)
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -34,7 +34,7 @@ SYM_FUNC_START(__x86_indirect_thunk_\reg)
 
        ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
                      __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
-                     __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE
+                     __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE
 
 SYM_FUNC_END(__x86_indirect_thunk_\reg)
 

diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 17508c0..2b988b6 100644 (file)
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -232,7 +232,8 @@ 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)
 
 ifndef CONFIG_LTO_CLANG
 

diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index d74cee5..59a3df8 100755 (executable)
--- a/scripts/link-vmlinux.sh
+++ b/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