mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 11:37:47 +07:00
a9d57ef15c
Commit ce02ef06fc ("x86, retpolines: Raise limit for generating indirect
calls from switch-case") raised the limit under retpolines to 20 switch
cases where gcc would only then start to emit jump tables, and therefore
effectively disabling the emission of slow indirect calls in this area.
After this has been brought to attention to gcc folks [0], Martin Liska
has then fixed gcc to align with clang by avoiding to generate switch jump
tables entirely under retpolines. This is taking effect in gcc starting
from stable version 8.4.0. Given kernel supports compilation with older
versions of gcc where the fix is not being available or backported anymore,
we need to keep the extra KBUILD_CFLAGS around for some time and generally
set the -fno-jump-tables to align with what more recent gcc is doing
automatically today.
More than 20 switch cases are not expected to be fast-path critical, but
it would still be good to align with gcc behavior for versions < 8.4.0 in
order to have consistency across supported gcc versions. vmlinux size is
slightly growing by 0.27% for older gcc. This flag is only set to work
around affected gcc, no change for clang.
[0] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86952
Suggested-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Björn Töpel<bjorn.topel@intel.com>
Cc: Magnus Karlsson <magnus.karlsson@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: H.J. Lu <hjl.tools@gmail.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: David S. Miller <davem@davemloft.net>
Link: https://lkml.kernel.org/r/20190325135620.14882-1-daniel@iogearbox.net
332 lines
12 KiB
Makefile
332 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 -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))
|
|
|
|
# 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__
|
|
|
|
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
|
|
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
|
|
|
|
#
|
|
# 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
|
|
|
|
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,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=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)
|
|
|
|
KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE)
|
|
|
|
#
|
|
# The 64-bit kernel must be aligned to 2MB. Pass -z max-page-size=0x200000 to
|
|
# the linker to force 2MB page size regardless of the default page size used
|
|
# by the linker.
|
|
#
|
|
ifdef CONFIG_X86_64
|
|
KBUILD_LDFLAGS += $(call ld-option, -z max-page-size=0x200000)
|
|
endif
|
|
|
|
# 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
|
|
KBUILD_CFLAGS += $(RETPOLINE_CFLAGS)
|
|
# Additionally, avoid generating expensive indirect jumps which
|
|
# are subject to retpolines for small number of switch cases.
|
|
# clang turns off jump table generation by default when under
|
|
# retpoline builds, however, gcc does not for x86. This has
|
|
# only been fixed starting from gcc stable version 8.4.0 and
|
|
# onwards, but not for older ones. See gcc bug #86952.
|
|
ifndef CONFIG_CC_IS_CLANG
|
|
KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables)
|
|
endif
|
|
endif
|
|
|
|
archscripts: scripts_basic
|
|
$(Q)$(MAKE) $(build)=arch/x86/tools relocs
|
|
|
|
###
|
|
# Syscall table generation
|
|
|
|
archheaders:
|
|
$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
|
|
|
|
###
|
|
# 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 $@
|
|
|
|
archprepare: checkbin
|
|
checkbin:
|
|
ifndef CONFIG_CC_HAS_ASM_GOTO
|
|
@echo Compiler lacks asm-goto support.
|
|
@exit 1
|
|
endif
|
|
ifdef CONFIG_RETPOLINE
|
|
ifeq ($(RETPOLINE_CFLAGS),)
|
|
@echo "You are building kernel with non-retpoline compiler." >&2
|
|
@echo "Please update your compiler." >&2
|
|
@false
|
|
endif
|
|
endif
|
|
|
|
archclean:
|
|
$(Q)rm -rf $(objtree)/arch/i386
|
|
$(Q)rm -rf $(objtree)/arch/x86_64
|
|
$(Q)$(MAKE) $(clean)=$(boot)
|
|
$(Q)$(MAKE) $(clean)=arch/x86/tools
|
|
|
|
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
|