mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-12 22:56:48 +07:00
3f135e57a4
The GCC '-maccumulate-outgoing-args' flag is enabled for most configs,
mostly because of issues which are no longer relevant. For most
configs, and with most recent versions of GCC, it's no longer needed.
Clarify which cases need it, and only enable it for those cases. Also
produce a compile-time error for the ftrace graph + mcount + '-Os' case,
which will otherwise cause runtime failures.
The main benefit of '-maccumulate-outgoing-args' is that it prevents an
ugly prologue for functions which have aligned stacks. But removing the
option also has some benefits: more readable argument saves, smaller
text size, and (presumably) slightly improved performance.
Here are the object size savings for 32-bit and 64-bit defconfig
kernels:
text data bss dec hex filename
10006710 3543328 1773568 15323606 e9d1d6 vmlinux.x86-32.before
9706358 3547424 1773568 15027350 e54c96 vmlinux.x86-32.after
text data bss dec hex filename
10652105 4537576 843776 16033457 f4a6b1 vmlinux.x86-64.before
10639629 4537576 843776 16020981 f475f5 vmlinux.x86-64.after
That comes out to a 3% text size improvement on x86-32 and a 0.1% text
size improvement on x86-64.
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andrew Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170316193133.zrj6gug53766m6nn@treble
Signed-off-by: Ingo Molnar <mingo@kernel.org>
308 lines
10 KiB
Makefile
308 lines
10 KiB
Makefile
# 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 := $(ARCH)_defconfig
|
|
endif
|
|
|
|
# How to compile the 16-bit code. Note we always compile for -march=i386;
|
|
# that way we can complain to the user if the CPU is insufficient.
|
|
#
|
|
# The -m16 option is supported by GCC >= 4.9 and clang >= 3.5. For
|
|
# older versions of GCC, include an *assembly* header to make sure that
|
|
# gcc doesn't play any games behind our back.
|
|
CODE16GCC_CFLAGS := -m32 -Wa,$(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 \
|
|
$(call cc-option, -ffreestanding) \
|
|
$(call cc-option, -fno-stack-protector) \
|
|
$(call cc-option, -mpreferred-stack-boundary=2)
|
|
export REALMODE_CFLAGS
|
|
|
|
# BITS is used as extension for files which are available in a 32 bit
|
|
# and a 64 bit version to simplify shared Makefiles.
|
|
# e.g.: obj-y += foo_$(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
|
|
|
|
# prevent gcc from keeping the stack 16 byte aligned
|
|
KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
|
|
|
|
# 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 += -falign-jumps=1
|
|
|
|
# Pack loops tightly as well:
|
|
KBUILD_CFLAGS += -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)
|
|
|
|
# Use -mpreferred-stack-boundary=3 if supported.
|
|
KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
|
|
|
|
# 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
|
|
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)
|
|
KBUILD_CFLAGS += -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
|
|
|
|
KBUILD_CFLAGS += $(mflags-y)
|
|
KBUILD_AFLAGS += $(mflags-y)
|
|
|
|
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/
|
|
|
|
drivers-$(CONFIG_RAS) += arch/x86/ras/
|
|
|
|
####
|
|
# 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
|