On Fri, Sep 4, 2020 at 5:31 AM Sami Tolvanen <samitolva...@google.com> wrote: > > This change adds build system support for Clang's Link Time > Optimization (LTO). With -flto, instead of ELF object files, Clang > produces LLVM bitcode, which is compiled into native code at link > time, allowing the final binary to be optimized globally. For more > details, see: > > https://llvm.org/docs/LinkTimeOptimization.html > > The Kconfig option CONFIG_LTO_CLANG is implemented as a choice, > which defaults to LTO being disabled. To use LTO, the architecture > must select ARCH_SUPPORTS_LTO_CLANG and support: > > - compiling with Clang, > - compiling inline assembly with Clang's integrated assembler, > - and linking with LLD. > > While using full LTO results in the best runtime performance, the > compilation is not scalable in time or memory. CONFIG_THINLTO > enables ThinLTO, which allows parallel optimization and faster > incremental builds. ThinLTO is used by default if the architecture > also selects ARCH_SUPPORTS_THINLTO: > > https://clang.llvm.org/docs/ThinLTO.html > > To enable LTO, LLVM tools must be used to handle bitcode files. The > easiest way is to pass the LLVM=1 option to make: > > $ make LLVM=1 defconfig > $ scripts/config -e LTO_CLANG > $ make LLVM=1 > > Alternatively, at least the following LLVM tools must be used: > > CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm > > To prepare for LTO support with other compilers, common parts are > gated behind the CONFIG_LTO option, and LTO can be disabled for > specific files by filtering out CC_FLAGS_LTO. > > Note that support for DYNAMIC_FTRACE and MODVERSIONS are added in > follow-up patches. > > Signed-off-by: Sami Tolvanen <samitolva...@google.com> > --- > Makefile | 18 +++++++- > arch/Kconfig | 68 +++++++++++++++++++++++++++++++ > include/asm-generic/vmlinux.lds.h | 11 +++-- > scripts/Makefile.build | 9 +++- > scripts/Makefile.modfinal | 9 +++- > scripts/Makefile.modpost | 24 ++++++++++- > scripts/link-vmlinux.sh | 32 +++++++++++---- > 7 files changed, 154 insertions(+), 17 deletions(-)
> #define TEXT_MAIN .text > diff --git a/scripts/Makefile.build b/scripts/Makefile.build > index 6ecf30c70ced..a5f4b5d407e6 100644 > --- a/scripts/Makefile.build > +++ b/scripts/Makefile.build > @@ -111,7 +111,7 @@ endif > # --------------------------------------------------------------------------- > > quiet_cmd_cc_s_c = CC $(quiet_modtag) $@ > - cmd_cc_s_c = $(CC) $(filter-out $(DEBUG_CFLAGS), $(c_flags)) > $(DISABLE_LTO) -fverbose-asm -S -o $@ $< > + cmd_cc_s_c = $(CC) $(filter-out $(DEBUG_CFLAGS) $(CC_FLAGS_LTO), > $(c_flags)) -fverbose-asm -S -o $@ $< > > $(obj)/%.s: $(src)/%.c FORCE > $(call if_changed_dep,cc_s_c) > @@ -428,8 +428,15 @@ $(obj)/lib.a: $(lib-y) FORCE > # Do not replace $(filter %.o,^) with $(real-prereqs). When a single object > # module is turned into a multi object module, $^ will contain header file > # dependencies recorded in the .*.cmd file. > +ifdef CONFIG_LTO_CLANG > +quiet_cmd_link_multi-m = AR [M] $@ > +cmd_link_multi-m = \ > + rm -f $@; \ > + $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(filter %.o,$^) KBUILD_ARFLAGS no longer exists in the mainline. (commit 13dc8c029cabf52ba95f60c56eb104d4d95d5889) > +else > quiet_cmd_link_multi-m = LD [M] $@ > cmd_link_multi-m = $(LD) $(ld_flags) -r -o $@ $(filter %.o,$^) > +endif > > $(multi-used-m): FORCE > $(call if_changed,link_multi-m) > diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal > index 411c1e600e7d..1005b147abd0 100644 > --- a/scripts/Makefile.modfinal > +++ b/scripts/Makefile.modfinal > @@ -6,6 +6,7 @@ > PHONY := __modfinal > __modfinal: > > +include $(objtree)/include/config/auto.conf > include $(srctree)/scripts/Kbuild.include > > # for c_flags > @@ -29,6 +30,12 @@ quiet_cmd_cc_o_c = CC [M] $@ > > ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink) > > +ifdef CONFIG_LTO_CLANG > +# With CONFIG_LTO_CLANG, reuse the object file we compiled for modpost to > +# avoid a second slow LTO link > +prelink-ext := .lto > +endif > + > quiet_cmd_ld_ko_o = LD [M] $@ > cmd_ld_ko_o = \ > $(LD) -r $(KBUILD_LDFLAGS) \ > @@ -37,7 +44,7 @@ quiet_cmd_ld_ko_o = LD [M] $@ > -o $@ $(filter %.o, $^); \ > $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true) > > -$(modules): %.ko: %.o %.mod.o $(KBUILD_LDS_MODULE) FORCE > +$(modules): %.ko: %$(prelink-ext).o %.mod.o $(KBUILD_LDS_MODULE) FORCE > +$(call if_changed,ld_ko_o) > > targets += $(modules) $(modules:.ko=.mod.o) > diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost > index f54b6ac37ac2..a70f1f7da6aa 100644 > --- a/scripts/Makefile.modpost > +++ b/scripts/Makefile.modpost > @@ -102,12 +102,32 @@ $(input-symdump): > @echo >&2 'WARNING: Symbol version dump "$@" is missing.' > @echo >&2 ' Modules may not have dependencies or modversions.' > > +ifdef CONFIG_LTO_CLANG > +# With CONFIG_LTO_CLANG, .o files might be LLVM bitcode, or, .o files might be even thin archives. For example, $ file net/ipv6/netfilter/nf_defrag_ipv6.o net/ipv6/netfilter/nf_defrag_ipv6.o: thin archive with 6 symbol entries Now we have 3 possibilities for .o files: - ELF (real .o) - LLVM bitcode (.bc) - Thin archive (.a) Let me discuss how to proceed with this... -- Best Regards Masahiro Yamada
