--- /dev/null
+Link time optimization (LTO) for the Linux kernel
+
+This is an experimental feature.
+
+Link Time Optimization allows the compiler to optimize the complete program
+instead of just each file. LTO requires at least gcc 4.8 (but
+works more efficiently with 4.9+) LTO requires Linux binutils (the normal FSF
+releases used in many distributions do not work at the moment)
+
+The compiler can inline functions between files and do various other global
+optimizations, like specializing functions for common parameters,
+determing when global variables are clobbered, making functions pure/const,
+propagating constants globally, removing unneeded data and others.
+
+It will also drop unused functions which can make the kernel
+image smaller in some circumstances, in particular for small kernel
+configurations.
+
+For small monolithic kernels it can throw away unused code very effectively
+(especially when modules are disabled) and usually shrinks
+the code size.
+
+Build time and memory consumption at build time will increase, depending
+on the size of the largest binary. Modular kernels are less affected.
+With LTO incremental builds are less incremental, as always the whole
+binary needs to be re-optimized (but not re-parsed)
+
+Oops can be somewhat more difficult to read, due to the more aggressive
+inlining.
+
+Normal "reasonable" builds work with less than 4GB of RAM, but very large
+configurations like allyesconfig may need more memory. The actual
+memory needed depends on the available memory (gcc sizes its garbage
+collector pools based on that or on the ulimit -m limits) and
+the compiler version.
+
+gcc 4.9+ has much better build performance and less memory consumption
+
+- A few kernel features are currently incompatible with LTO, in particular
+function tracing, because they require special compiler flags for
+specific files, which is not supported in LTO right now.
+- Jobserver control for -j does not work correctly for the final
+LTO phase due to some problems with the kernel's pipe code.
+The makefiles hard codes -j<number of online cpus> for the final
+LTO phase to work around for this
+
+Configuration:
+- Enable CONFIG_LTO_MENU and then disable CONFIG_LTO_DISABLE.
+This is mainly to not have allyesconfig default to LTO.
+- FUNCTION_TRACER, STACK_TRACER, FUNCTION_GRAPH_TRACER, KALLSYMS_ALL, GCOV
+have to disabled because they are currently incompatible with LTO.
+- MODVERSIONS have to be disabled (may work with 4.9+)
+
+Requirements:
+- Enough memory: 4GB for a standard build, more for allyesconfig
+The peak memory usage happens single threaded (when lto-wpa merges types),
+so dialing back -j options will not help much.
+
+A 32bit compiler is unlikely to work due to the memory requirements.
+You can however build a kernel targeted at 32bit on a 64bit host.
+
+Example build procedure:
+
+Simplified procedure for distributions that have gcc 4.8, but not
+the Linux binutils (for example openSUSE 13.1 or FC20):
+
+The LTO builds requires gcc-nm/gcc-ar. Some distributions ship
+those in separate packages, which may need to be explicitely installed.
+
+- Get the latest Linux binutils from
+http://www.kernel.org/pub/linux/devel/binutils/
+and unpack it.
+
+We install it in a separate directory to not overwrite the system binutils.
+
+# replace VERSION with respective version numbers
+
+cd binutils*
+# don't forget the --enable-plugins!
+./configure --prefix=/opt/binutils-VERSION --enable-plugins
+make -j $(getconf _NPROCESSORS_ONLN) && sudo make install
+
+Fix up the kernel configuration to allow LTO:
+
+<start with a suitable kernel configuration>
+./source/scripts/config --disable function_tracer \
+ --disable function_graph_tracer \
+ --disable stack_tracer --enable lto_menu \
+ --disable lto_disable \
+ --disable gcov \
+ --disable kallsyms_all \
+ --disable modversions
+make oldconfig
+
+Then you can build with
+
+# The COMPILER_PATH is needed to let gcc use the new binutils
+# as the LTO plugin linker
+# if you installed gcc in a separate directory like below also
+# add it to the PATH line below before the regular $PATH
+# The COMPILER_PATH setting is only needed if the gcc was not built
+# with --with-plugin-ld pointing to the Linux binutils ld
+# The AR/NM setting works around a Makefile bug
+COMPILER_PATH=/opt/binutils-VERSION/bin PATH=$COMPILER_PATH:$PATH \
+make -j$(getconf _NPROCESSORS_ONLN) AR=gcc-ar NM=gcc-nm
+
+If you don't have gcc 4.8+ as system compiler you would also need
+to install that compiler. In this case I recommend getting
+a gcc 4.9+ snapshot from http://gcc.gnu.org (or release when available),
+as it builds much faster for LTO than 4.8.
+
+Here's an example build procedure:
+
+Assuming gcc is unpacked in gcc-VERSION
+
+cd gcc-VERSION
+./contrib/download_preqrequisites
+cd ..
+
+mkdir obj-gcc
+# please don't skip this cd. the build will not work correctly in the
+# source dir, you have to use the separate object dir
+cd obj-gcc
+../gcc-VERSION/configure --prefix=/opt/gcc-VERSION --enable-lto \
+--with-plugin-ld=/opt/binutils-VERSION/bin/ld
+--disable-nls --enable-languages=c,c++ \
+--disable-libstdcxx-pch
+make -j$(getconf _NPROCESSORS_ONLN)
+sudo make install-no-fixedincludes
+
+FAQs:
+
+Q: I get a section type attribute conflict
+A: Usually because of someone doing
+const __initdata (should be const __initconst) or const __read_mostly
+(should be just const). Check both symbols reported by gcc.
+
+Q: I see lots of undefined symbols for memcmp etc.
+A: Usually because NM=gcc-nm AR=gcc-ar are missing.
+The Makefile tries to set those automatically, but it doesn't always
+work. Better to set it manually on the make command line.
+
+Q: It's quite slow / uses too much memory.
+A: Consider a gcc 4.9 snapshot/release (not released yet)
+The main problem in 4.8 is the type merging in the single threaded WPA pass,
+which has been improved considerably in 4.9 by running it distributed.
+
+Q: It's still slow
+A: It'll always be somewhat slower than non LTO sorry.
+
+Q: What's up with .XXXXX numeric post fixes
+A: This is due LTO turning (near) all symbols to static
+Use gcc 4.9, it avoids them in most cases. They are also filtered out
+in kallsyms.
+
+References:
+
+Presentation on Kernel LTO
+(note, performance numbers/details outdated. In particular gcc 4.9 fixed
+most of the build time problems):
+http://halobates.de/kernel-lto.pdf
+
+Generic gcc LTO:
+http://www.ucw.cz/~hubicka/slides/labs2013.pdf
+http://www.hipeac.net/system/files/barcelona.pdf
+
+Somewhat outdated too:
+http://gcc.gnu.org/projects/lto/lto.pdf
+http://gcc.gnu.org/projects/lto/whopr.pdf
+
+Happy Link-Time-Optimizing!
+
+Andi Kleen
# Make variables (CC, etc...)
AS = $(CROSS_COMPILE)as
LD = $(CROSS_COMPILE)ld
+LDFINAL = $(LD)
CC = $(CROSS_COMPILE)gcc
CPP = $(CC) -E
+ifdef CONFIG_LTO
+AR = $(CROSS_COMPILE)gcc-ar
+else
AR = $(CROSS_COMPILE)ar
+endif
NM = $(CROSS_COMPILE)nm
STRIP = $(CROSS_COMPILE)strip
OBJCOPY = $(CROSS_COMPILE)objcopy
export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION
export ARCH SRCARCH CONFIG_SHELL HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP
+export CPP AR NM STRIP OBJCOPY OBJDUMP LDFINAL
export MAKE AWK GENKSYMS INSTALLKERNEL PERL UTS_MACHINE
export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL
export KBUILD_ARFLAGS
+ifdef CONFIG_LTO
+# LTO gcc creates a lot of files in TMPDIR, and with /tmp as tmpfs
+# it's easy to drive the machine OOM. Use the object directory
+# instead.
+ifndef TMPDIR
+TMPDIR ?= $(objtree)
+export TMPDIR
+$(info setting TMPDIR=$(objtree) for LTO build)
+endif
+endif
+
# When compiling out-of-tree modules, put MODVERDIR in the module
# tree rather than in the kernel tree. The kernel tree might
# even be read-only.
endif
include $(srctree)/scripts/Makefile.extrawarn
+include ${srctree}/scripts/Makefile.lto
# Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
KBUILD_CPPFLAGS += $(KCPPFLAGS)
config SCHED_OMIT_FRAME_POINTER
def_bool y
- prompt "Single-depth WCHAN output"
+ prompt "Single-depth WCHAN output" if !LTO && !FRAME_POINTER
depends on X86
---help---
Calculate simpler /proc/<PID>/wchan values. If this option
If unsure, say N.
+config LTO_MENU
+ bool "Enable gcc link time optimization (LTO)"
+ # Only tested on X86 for now. For other architectures you likely
+ # have to fix some things first, like adding asmlinkages etc.
+ depends on X86
+ # lto does not support excluding flags for specific files
+ # right now. Can be removed if that is fixed.
+ depends on !FUNCTION_TRACER
+ help
+ With this option gcc will do whole program optimizations for
+ the whole kernel and module. This increases compile time, but can
+ lead to better code. It allows gcc to inline functions between
+ different files and do other optimization. It might also trigger
+ bugs due to more aggressive optimization. It allows gcc to drop unused
+ code. On smaller monolithic kernel configurations
+ it usually leads to smaller kernels, especially when modules
+ are disabled.
+
+ With this option gcc will also do some global checking over
+ different source files. It also disables a number of kernel
+ features.
+
+ This option is recommended for release builds. With LTO
+ the kernel always has to be re-optimized (but not re-parsed)
+ on each build.
+
+ This requires a gcc 4.8 or later compiler and
+ Linux binutils 2.21.51.0.3 or later. gcc 4.9 builds significantly
+ faster than 4.8 It does not currently work with a FSF release of
+ binutils or with the gold linker.
+
+ On larger configurations this may need more than 4GB of RAM.
+ It will likely not work on those with a 32bit compiler.
+
+ When the toolchain support is not available this will (hopefully)
+ be automatically disabled.
+
+ For more information see Documentation/lto-build
+
+config LTO_DISABLE
+ bool "Disable LTO again"
+ depends on LTO_MENU
+ default n
+ help
+ This option is merely here so that allyesconfig or allmodconfig do
+ not enable LTO. If you want to actually use LTO do not enable.
+
+config LTO
+ bool
+ default y
+ depends on LTO_MENU && !LTO_DISABLE
+
+config LTO_DEBUG
+ bool "Enable LTO compile time debugging"
+ depends on LTO
+ help
+ Enable LTO debugging in the compiler. The compiler dumps
+ some log files that make it easier to figure out LTO
+ behavior. The log files also allow to reconstruct
+ the global inlining and a global callgraph.
+ They however add some (single threaded) cost to the
+ compilation. When in doubt do not enable.
+
+config LTO_CP_CLONE
+ bool "Allow aggressive cloning for function specialization"
+ depends on LTO
+ help
+ Allow the compiler to clone and specialize functions for specific
+ arguments when it determines these arguments are very commonly
+ called. Experimential. Will increase text size.
+
config SYSCTL
bool
config MODVERSIONS
bool "Module versioning support"
+ # LTO should work with gcc 4.9
+ depends on !LTO
help
Usually, you have to use modules compiled with your kernel.
Saying Y here makes it sometimes possible to use modules
config GCOV_KERNEL
bool "Enable gcov-based kernel profiling"
- depends on DEBUG_FS
+ depends on DEBUG_FS && !LTO
select CONSTRUCTORS if !UML
default n
---help---
config READABLE_ASM
bool "Generate readable assembler code"
- depends on DEBUG_KERNEL
+ depends on DEBUG_KERNEL && !LTO
help
Disable some compiler optimizations that tend to generate human unreadable
assembler output. This may make the kernel slightly slower, but it helps
--- /dev/null
+#
+# Support for gcc link time optimization
+#
+
+DISABLE_LTO :=
+LTO_CFLAGS :=
+
+export DISABLE_LTO
+export LTO_CFLAGS
+
+ifdef CONFIG_LTO
+# 4.7 works mostly, but it sometimes loses symbols on large builds
+# This can be worked around by marking those symbols visible,
+# but that is fairly ugly and the problem is gone with 4.8
+# So only allow it with 4.8 for now.
+ifeq ($(call cc-ifversion, -ge, 0408,y),y)
+ifneq ($(call cc-option,${LTO_CFLAGS},n),n)
+# We need HJ Lu's Linux binutils because mainline binutils does not
+# support mixing assembler and LTO code in the same ld -r object.
+# XXX check if the gcc plugin ld is the expected one too
+# XXX some Fedora binutils should also support it. How to check for that?
+ifeq ($(call ld-ifversion,-ge,22710001,y),y)
+ LTO_CFLAGS := -flto -fno-toplevel-reorder
+ LTO_FINAL_CFLAGS := -fuse-linker-plugin
+
+# the -fno-toplevel-reorder is to preserve the order of initcalls
+# everything else should tolerate reordering
+ LTO_FINAL_CFLAGS +=-fno-toplevel-reorder
+
+# enable LTO and set the jobs used by the LTO phase
+# this should be -flto=jobserver to coordinate with the
+# parent make, but work around
+# http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50639
+# use as many jobs as processors are online for now
+# this actually seems to be a kernel bug with the pipe code
+ LTO_FINAL_CFLAGS := -flto=$(shell getconf _NPROCESSORS_ONLN)
+ #LTO_FINAL_CFLAGS := -flto=jobserver
+
+ # requires plugin ar passed and very recent HJ binutils
+ LTO_CFLAGS += -fno-fat-lto-objects
+
+# Used to disable LTO for specific files (e.g. vdso)
+ DISABLE_LTO := -fno-lto
+
+ LTO_FINAL_CFLAGS += ${LTO_CFLAGS} -fwhole-program
+
+ifdef CONFIG_LTO_DEBUG
+ LTO_FINAL_CFLAGS += -dH -fdump-ipa-cgraph -fdump-ipa-inline-details
+ # -Wl,-plugin-save-temps -save-temps
+ LTO_CFLAGS +=
+endif
+ifdef CONFIG_LTO_CP_CLONE
+ LTO_FINAL_CFLAGS += -fipa-cp-clone
+ LTO_CFLAGS += -fipa-cp-clone
+endif
+
+ # In principle gcc should pass through options in the object files,
+ # but it doesn't always work. So do it here manually
+ # Note that special options for individual files does not
+ # work currently (except for some special cases that only
+ # affect the compiler frontend)
+ # The main offenders are FTRACE and GCOV -- we exclude
+ # those in the config.
+ LTO_FINAL_CFLAGS += $(filter -g%,${KBUILD_CFLAGS})
+ LTO_FINAL_CFLAGS += $(filter -O%,${KBUILD_CFLAGS})
+ LTO_FINAL_CFLAGS += $(filter -f%,${KBUILD_CFLAGS})
+ LTO_FINAL_CFLAGS += $(filter -m%,${KBUILD_CFLAGS})
+ LTO_FINAL_CFLAGS += $(filter -W%,${KBUILD_CFLAGS})
+
+ KBUILD_CFLAGS += ${LTO_CFLAGS}
+
+ LDFINAL := ${CONFIG_SHELL} ${srctree}/scripts/gcc-ld \
+ ${LTO_FINAL_CFLAGS}
+
+else
+ $(warning "WARNING: Too old linker version $(call ld-version) for kernel LTO. You need Linux binutils. CONFIG_LTO disabled.")
+endif
+else
+ $(warning "WARNING: Compiler/Linker does not support LTO/WHOPR with linker plugin. CONFIG_LTO disabled.")
+endif
+else
+ $(warning "WARNING: GCC $(call cc-version) too old for LTO/WHOPR. CONFIG_LTO disabled")
+endif
+endif
$(if $(KBUILD_EXTRA_SYMBOLS), $(patsubst %, -e %,$(KBUILD_EXTRA_SYMBOLS))) \
$(if $(KBUILD_EXTMOD),-o $(modulesymfile)) \
$(if $(CONFIG_DEBUG_SECTION_MISMATCH),,-S) \
- $(if $(KBUILD_EXTMOD)$(KBUILD_MODPOST_WARN),-w)
+ $(if $(KBUILD_EXTMOD)$(KBUILD_MODPOST_WARN),-w) \
+ $(if $(CONFIG_LTO),-w)
MODPOST_OPT=$(subst -i,-n,$(filter -i,$(MAKEFLAGS)))
targets += $(modules:.ko=.mod.o)
# Step 6), final link of the modules
-quiet_cmd_ld_ko_o = LD [M] $@
- cmd_ld_ko_o = $(LD) -r $(LDFLAGS) \
+quiet_cmd_ld_ko_o = LDFINAL [M] $@
+ cmd_ld_ko_o = $(LDFINAL) -r $(LDFLAGS) \
$(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
-o $@ $(filter-out FORCE,$^)
local lds="${objtree}/${KBUILD_LDS}"
if [ "${SRCARCH}" != "um" ]; then
- ${LD} ${LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \
+ ${LDFINAL} ${LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \
-T ${lds} ${KBUILD_VMLINUX_INIT} \
--start-group ${KBUILD_VMLINUX_MAIN} --end-group ${1}
else
projects / karo-tx-linux.git / commitdiff