linux/arch/x86/Makefile
David Woodhouse 76b043848f x86/retpoline: Add initial retpoline support
Enable the use of -mindirect-branch=thunk-extern in newer GCC, and provide
the corresponding thunks. Provide assembler macros for invoking the thunks
in the same way that GCC does, from native and inline assembler.

This adds X86_FEATURE_RETPOLINE and sets it by default on all CPUs. In
some circumstances, IBRS microcode features may be used instead, and the
retpoline can be disabled.

On AMD CPUs if lfence is serialising, the retpoline can be dramatically
simplified to a simple "lfence; jmp *\reg". A future patch, after it has
been verified that lfence really is serialising in all circumstances, can
enable this by setting the X86_FEATURE_RETPOLINE_AMD feature bit in addition
to X86_FEATURE_RETPOLINE.

Do not align the retpoline in the altinstr section, because there is no
guarantee that it stays aligned when it's copied over the oldinstr during
alternative patching.

[ Andi Kleen: Rename the macros, add CONFIG_RETPOLINE option, export thunks]
[ tglx: Put actual function CALL/JMP in front of the macros, convert to
  	symbolic labels ]
[ dwmw2: Convert back to numeric labels, merge objtool fixes ]

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: thomas.lendacky@amd.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515707194-20531-4-git-send-email-dwmw@amazon.co.uk
2018-01-12 00:14:28 +01:00

342 lines
12 KiB
Makefile

# SPDX-License-Identifier: GPL-2.0
# Unified Makefile for i386 and x86_64
# select defconfig based on actual architecture
ifeq ($(ARCH),x86)
ifeq ($(shell uname -m),x86_64)
KBUILD_DEFCONFIG := x86_64_defconfig
else
KBUILD_DEFCONFIG := i386_defconfig
endif
else
KBUILD_DEFCONFIG := $(ARCH)_defconfig
endif
# For gcc stack alignment is specified with -mpreferred-stack-boundary,
# clang has the option -mstack-alignment for that purpose.
ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
cc_stack_align4 := -mpreferred-stack-boundary=2
cc_stack_align8 := -mpreferred-stack-boundary=3
else ifneq ($(call cc-option, -mstack-alignment=16),)
cc_stack_align4 := -mstack-alignment=4
cc_stack_align8 := -mstack-alignment=8
endif
# How to compile the 16-bit code. Note we always compile for -march=i386;
# that way we can complain to the user if the CPU is insufficient.
#
# The -m16 option is supported by GCC >= 4.9 and clang >= 3.5. For
# older versions of GCC, include an *assembly* header to make sure that
# gcc doesn't play any games behind our back.
CODE16GCC_CFLAGS := -m32 -Wa,$(srctree)/arch/x86/boot/code16gcc.h
M16_CFLAGS := $(call cc-option, -m16, $(CODE16GCC_CFLAGS))
REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -D__KERNEL__ \
-DDISABLE_BRANCH_PROFILING \
-Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
-fno-strict-aliasing -fomit-frame-pointer -fno-pic \
-mno-mmx -mno-sse
REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding)
REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector)
REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4))
export REALMODE_CFLAGS
# BITS is used as extension for files which are available in a 32 bit
# and a 64 bit version to simplify shared Makefiles.
# e.g.: obj-y += foo_$(BITS).o
export BITS
ifdef CONFIG_X86_NEED_RELOCS
LDFLAGS_vmlinux := --emit-relocs
endif
#
# Prevent GCC from generating any FP code by mistake.
#
# This must happen before we try the -mpreferred-stack-boundary, see:
#
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
#
KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
ifeq ($(CONFIG_X86_32),y)
BITS := 32
UTS_MACHINE := i386
CHECKFLAGS += -D__i386__
biarch := $(call cc-option,-m32)
KBUILD_AFLAGS += $(biarch)
KBUILD_CFLAGS += $(biarch)
KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
# Never want PIC in a 32-bit kernel, prevent breakage with GCC built
# with nonstandard options
KBUILD_CFLAGS += -fno-pic
# Align the stack to the register width instead of using the default
# alignment of 16 bytes. This reduces stack usage and the number of
# alignment instructions.
KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4))
# Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
# a lot more stack due to the lack of sharing of stacklots:
KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0400, \
$(call cc-option,-fno-unit-at-a-time))
# CPU-specific tuning. Anything which can be shared with UML should go here.
include arch/x86/Makefile_32.cpu
KBUILD_CFLAGS += $(cflags-y)
# temporary until string.h is fixed
KBUILD_CFLAGS += -ffreestanding
else
BITS := 64
UTS_MACHINE := x86_64
CHECKFLAGS += -D__x86_64__ -m64
biarch := -m64
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
# Align jump targets to 1 byte, not the default 16 bytes:
KBUILD_CFLAGS += $(call cc-option,-falign-jumps=1)
# Pack loops tightly as well:
KBUILD_CFLAGS += $(call cc-option,-falign-loops=1)
# Don't autogenerate traditional x87 instructions
KBUILD_CFLAGS += $(call cc-option,-mno-80387)
KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
# By default gcc and clang use a stack alignment of 16 bytes for x86.
# However the standard kernel entry on x86-64 leaves the stack on an
# 8-byte boundary. If the compiler isn't informed about the actual
# alignment it will generate extra alignment instructions for the
# default alignment which keep the stack *mis*aligned.
# Furthermore an alignment to the register width reduces stack usage
# and the number of alignment instructions.
KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align8))
# Use -mskip-rax-setup if supported.
KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
cflags-$(CONFIG_MCORE2) += \
$(call cc-option,-march=core2,$(call cc-option,-mtune=generic))
cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \
$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
KBUILD_CFLAGS += $(cflags-y)
KBUILD_CFLAGS += -mno-red-zone
KBUILD_CFLAGS += -mcmodel=kernel
# -funit-at-a-time shrinks the kernel .text considerably
# unfortunately it makes reading oopses harder.
KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
endif
ifdef CONFIG_X86_X32
x32_ld_ok := $(call try-run,\
/bin/echo -e '1: .quad 1b' | \
$(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" - && \
$(OBJCOPY) -O elf32-x86-64 "$$TMP" "$$TMPO" && \
$(LD) -m elf32_x86_64 "$$TMPO" -o "$$TMP",y,n)
ifeq ($(x32_ld_ok),y)
CONFIG_X86_X32_ABI := y
KBUILD_AFLAGS += -DCONFIG_X86_X32_ABI
KBUILD_CFLAGS += -DCONFIG_X86_X32_ABI
else
$(warning CONFIG_X86_X32 enabled but no binutils support)
endif
endif
export CONFIG_X86_X32_ABI
# Don't unroll struct assignments with kmemcheck enabled
ifeq ($(CONFIG_KMEMCHECK),y)
KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
endif
#
# If the function graph tracer is used with mcount instead of fentry,
# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109)
#
ifdef CONFIG_FUNCTION_GRAPH_TRACER
ifndef CONFIG_HAVE_FENTRY
ACCUMULATE_OUTGOING_ARGS := 1
else
ifeq ($(call cc-option-yn, -mfentry), n)
ACCUMULATE_OUTGOING_ARGS := 1
# GCC ignores '-maccumulate-outgoing-args' when used with '-Os'.
# If '-Os' is enabled, disable it and print a warning.
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
undefine CONFIG_CC_OPTIMIZE_FOR_SIZE
$(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
endif
endif
endif
endif
#
# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a
# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226). There's no way
# to test for this bug at compile-time because the test case needs to execute,
# which is a no-go for cross compilers. So check the GCC version instead.
#
ifdef CONFIG_JUMP_LABEL
ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1)
ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1)
endif
endif
ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
# This compiler flag is not supported by Clang:
KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,)
endif
# Stackpointer is addressed different for 32 bit and 64 bit x86
sp-$(CONFIG_X86_32) := esp
sp-$(CONFIG_X86_64) := rsp
# do binutils support CFI?
cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1)
# is .cfi_signal_frame supported too?
cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
# does binutils support specific instructions?
asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1)
sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1)
sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1)
KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr)
KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr)
LDFLAGS := -m elf_$(UTS_MACHINE)
# Speed up the build
KBUILD_CFLAGS += -pipe
# Workaround for a gcc prelease that unfortunately was shipped in a suse release
KBUILD_CFLAGS += -Wno-sign-compare
#
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
# Avoid indirect branches in kernel to deal with Spectre
ifdef CONFIG_RETPOLINE
RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
ifneq ($(RETPOLINE_CFLAGS),)
KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
else
$(warning CONFIG_RETPOLINE=y, but not supported by the compiler. Toolchain update recommended.)
endif
endif
archscripts: scripts_basic
$(Q)$(MAKE) $(build)=arch/x86/tools relocs
###
# Syscall table generation
archheaders:
$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
archprepare:
ifeq ($(CONFIG_KEXEC_FILE),y)
$(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c
endif
###
# Kernel objects
head-y := arch/x86/kernel/head_$(BITS).o
head-y += arch/x86/kernel/head$(BITS).o
head-y += arch/x86/kernel/ebda.o
head-y += arch/x86/kernel/platform-quirks.o
libs-y += arch/x86/lib/
# See arch/x86/Kbuild for content of core part of the kernel
core-y += arch/x86/
# drivers-y are linked after core-y
drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
drivers-$(CONFIG_PCI) += arch/x86/pci/
# must be linked after kernel/
drivers-$(CONFIG_OPROFILE) += arch/x86/oprofile/
# suspend and hibernation support
drivers-$(CONFIG_PM) += arch/x86/power/
drivers-$(CONFIG_FB) += arch/x86/video/
####
# boot loader support. Several targets are kept for legacy purposes
boot := arch/x86/boot
BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage
PHONY += bzImage $(BOOT_TARGETS)
# Default kernel to build
all: bzImage
# KBUILD_IMAGE specify target image being built
KBUILD_IMAGE := $(boot)/bzImage
bzImage: vmlinux
ifeq ($(CONFIG_X86_DECODER_SELFTEST),y)
$(Q)$(MAKE) $(build)=arch/x86/tools posttest
endif
$(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE)
$(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot
$(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@
$(BOOT_TARGETS): vmlinux
$(Q)$(MAKE) $(build)=$(boot) $@
PHONY += install
install:
$(Q)$(MAKE) $(build)=$(boot) $@
PHONY += vdso_install
vdso_install:
$(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@
archclean:
$(Q)rm -rf $(objtree)/arch/i386
$(Q)rm -rf $(objtree)/arch/x86_64
$(Q)$(MAKE) $(clean)=$(boot)
$(Q)$(MAKE) $(clean)=arch/x86/tools
$(Q)$(MAKE) $(clean)=arch/x86/purgatory
define archhelp
echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)'
echo ' install - Install kernel using'
echo ' (your) ~/bin/$(INSTALLKERNEL) or'
echo ' (distribution) /sbin/$(INSTALLKERNEL) or'
echo ' install to $$(INSTALL_PATH) and run lilo'
echo ' fdimage - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)'
echo ' fdimage144 - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)'
echo ' fdimage288 - Create 2.8MB boot floppy image (arch/x86/boot/fdimage)'
echo ' isoimage - Create a boot CD-ROM image (arch/x86/boot/image.iso)'
echo ' bzdisk/fdimage*/isoimage also accept:'
echo ' FDARGS="..." arguments for the booted kernel'
echo ' FDINITRD=file initrd for the booted kernel'
endef