From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pf0-f194.google.com ([209.85.192.194]:33028 "EHLO mail-pf0-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751284AbcHKKQz (ORCPT ); Thu, 11 Aug 2016 06:16:55 -0400 From: Nicholas Piggin Subject: [PATCH 1/6] kbuild: allow architectures to use thin archives instead of ld -r Date: Thu, 11 Aug 2016 20:16:15 +1000 Message-Id: <1470910580-18458-2-git-send-email-npiggin@gmail.com> In-Reply-To: <1470910580-18458-1-git-send-email-npiggin@gmail.com> References: <1470910580-18458-1-git-send-email-npiggin@gmail.com> Sender: linux-kbuild-owner@vger.kernel.org List-ID: To: linux-kbuild@vger.kernel.org Cc: Nicholas Piggin , linux-arch@vger.kernel.org, Michal Marek , Sam Ravnborg , Stephen Rothwell , Arnd Bergmann , Nicolas Pitre , Segher Boessenkool , Alan Modra From: Stephen Rothwell ld -r is an incremental link used to create built-in.o files in build subdirectories. It produces relocatable object files containing all its input files, and these are are then pulled together and relocated in the final link. Aside from the bloat, this constrains the final link relocations, which has bitten large powerpc builds with unresolvable relocations in the final link. Alan Modra has recommended the kernel use thin archives for linking. This is an alternative and means that the linker has more information available to it when it links the kernel. This patch enables a config option architectures can select, which causes all built-in.o files to be built as thin archives. built-in.o files in subdirectories do not get symbol table or index attached, which improves speed and size. The final link pass creates a built-in.o archive in the root output directory which includes the symbol table and index. The linker then uses takes this file to link. The --whole-archive linker option is required, because the linker now has visibility to every individual object file, and it will otherwise just completely avoid including those without external references (consider a file with EXPORT_SYMBOL or initcall or hardware exceptions as its only entry points). The traditional built works "by luck" as built-in.o files are large enough that they're going to get external references. However this optimisation is unpredictable for the kernel (due to above external references), ineffective at culling unused, and costly because the .o files have to be searched for references. Superior alternatives for link-time culling should be used instead. Build characteristics for inclink vs thinarc, on a small powerpc64le pseries VM with a modest .config: inclink thinarc sizes vmlinux 15 618 680 15 625 028 sum of all built-in.o 56 091 808 1 054 334 sum excluding root built-in.o 151 430 find -name built-in.o | xargs rm ; time make vmlinux real 22.772s 21.143s user 13.280s 13.430s sys 4.310s 2.750s - Final kernel pulled in only about 6K more, which shows how ineffective the object file culling is. - Build performance looks improved due to less pagecache activity. On IO constrained systems it could be a bigger win. - Build size saving is significant. Side note, the toochain understands archives, so there's some tricks, $ ar t built-in.o # list all files you linked with $ size built-in.o # and their sizes $ objdump -d built-in.o # disassembly (unrelocated) with filenames Implementation by sfr, minor tweaks by npiggin. Signed-off-by: Stephen Rothwell Signed-off-by: Nicholas Piggin --- Changes since v1 - Fixed um build breakage - Fixed linking against lib.a archives (add symbol table) - Tested x86 builds - Tested arm64 defconfig thin archives cross compile inclinc - 385s 2.7GB; thinarc - 377s 1.8G arch/Kconfig | 6 +++++ scripts/Makefile.build | 23 +++++++++++++--- scripts/link-vmlinux.sh | 71 +++++++++++++++++++++++++++++++++++++++++-------- 3 files changed, 85 insertions(+), 15 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index e9c9334..02df9be 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -461,6 +461,12 @@ config CC_STACKPROTECTOR_STRONG endchoice +config THIN_ARCHIVES + bool + help + Select this if the architecture wants to use thin archives + instead of ld -r to create the built-in.o files. + config HAVE_ARCH_WITHIN_STACK_FRAMES bool help diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 11602e5..7ce183f 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -358,12 +358,22 @@ $(sort $(subdir-obj-y)): $(subdir-ym) ; # Rule to compile a set of .o files into one .o file # ifdef builtin-target -quiet_cmd_link_o_target = LD $@ + +ifdef CONFIG_THIN_ARCHIVES + cmd_make_builtin = rm -f $@; $(AR) rcST$(KBUILD_ARFLAGS) + cmd_make_empty_builtin = rm -f $@; $(AR) rcST$(KBUILD_ARFLAGS) + quiet_cmd_link_o_target = AR $@ +else + cmd_make_builtin = $(LD) $(ld_flags) -r -o + cmd_make_empty_builtin = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) + quiet_cmd_link_o_target = LD $@ +endif + # If the list of objects to link is empty, just create an empty built-in.o cmd_link_o_target = $(if $(strip $(obj-y)),\ - $(LD) $(ld_flags) -r -o $@ $(filter $(obj-y), $^) \ + $(cmd_make_builtin) $@ $(filter $(obj-y), $^) \ $(cmd_secanalysis),\ - rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@) + $(cmd_make_empty_builtin) $@) $(builtin-target): $(obj-y) FORCE $(call if_changed,link_o_target) @@ -389,7 +399,12 @@ $(modorder-target): $(subdir-ym) FORCE # ifdef lib-target quiet_cmd_link_l_target = AR $@ -cmd_link_l_target = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@ $(lib-y) + +ifdef CONFIG_THIN_ARCHIVES + cmd_link_l_target = rm -f $@; $(AR) rcT$(KBUILD_ARFLAGS) $@ $(lib-y) +else + cmd_link_l_target = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@ $(lib-y) +endif $(lib-target): $(lib-y) FORCE $(call if_changed,link_l_target) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 4f727eb..f742c65 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -37,12 +37,40 @@ info() fi } +# Thin archive build here makes a final archive with +# symbol table and indexes from vmlinux objects, which can be +# used as input to linker. +# +# Traditional incremental style of link does not require this step +# +# built-in.o output file +# +archive_builtin() +{ + if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then + info AR built-in.o + rm -f built-in.o; + ${AR} rcsT${KBUILD_ARFLAGS} built-in.o \ + ${KBUILD_VMLINUX_INIT} \ + ${KBUILD_VMLINUX_MAIN} + fi +} + # Link of vmlinux.o used for section mismatch analysis # ${1} output file modpost_link() { - ${LD} ${LDFLAGS} -r -o ${1} ${KBUILD_VMLINUX_INIT} \ - --start-group ${KBUILD_VMLINUX_MAIN} --end-group + local objects + + if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then + objects="--whole-archive built-in.o" + else + objects="${KBUILD_VMLINUX_INIT} \ + --start-group \ + ${KBUILD_VMLINUX_MAIN} \ + --end-group" + fi + ${LD} ${LDFLAGS} -r -o ${1} ${objects} } # Link of vmlinux @@ -51,18 +79,36 @@ modpost_link() vmlinux_link() { local lds="${objtree}/${KBUILD_LDS}" + local objects if [ "${SRCARCH}" != "um" ]; then - ${LD} ${LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \ - -T ${lds} ${KBUILD_VMLINUX_INIT} \ - --start-group ${KBUILD_VMLINUX_MAIN} --end-group ${1} + if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then + objects="--whole-archive built-in.o ${1}" + else + objects="${KBUILD_VMLINUX_INIT} \ + --start-group \ + ${KBUILD_VMLINUX_MAIN} \ + --end-group \ + ${1}" + fi + + ${LD} ${LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \ + -T ${lds} ${objects} else - ${CC} ${CFLAGS_vmlinux} -o ${2} \ - -Wl,-T,${lds} ${KBUILD_VMLINUX_INIT} \ - -Wl,--start-group \ - ${KBUILD_VMLINUX_MAIN} \ - -Wl,--end-group \ - -lutil -lrt -lpthread ${1} + if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then + objects="-Wl,--whole-archive built-in.o ${1}" + else + objects="${KBUILD_VMLINUX_INIT} \ + -Wl,--start-group \ + ${KBUILD_VMLINUX_MAIN} \ + -Wl,--end-group \ + ${1}" + fi + + ${CC} ${CFLAGS_vmlinux} -o ${2} \ + -Wl,-T,${lds} \ + ${objects} \ + -lutil -lrt -lpthread rm -f linux fi } @@ -119,6 +165,7 @@ cleanup() rm -f .tmp_kallsyms* rm -f .tmp_version rm -f .tmp_vmlinux* + rm -f built-in.o rm -f System.map rm -f vmlinux rm -f vmlinux.o @@ -162,6 +209,8 @@ case "${KCONFIG_CONFIG}" in . "./${KCONFIG_CONFIG}" esac +archive_builtin + #link vmlinux.o info LD vmlinux.o modpost_link vmlinux.o -- 2.8.1