From e8a6f455578b17e04ad08f15b76486e06f812400 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 6 Mar 2020 14:14:03 -0800 Subject: [PATCH 04/24] kbuild: add support for Clang LTO 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 --- Makefile | 18 ++++++++- arch/Kconfig | 67 +++++++++++++++++++++++++++++++ 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, 153 insertions(+), 17 deletions(-) diff --git a/Makefile b/Makefile index 38acd65aa651..44615ea079e5 100644 --- a/Makefile +++ b/Makefile @@ -887,6 +887,22 @@ KBUILD_CFLAGS += $(CC_FLAGS_SCS) export CC_FLAGS_SCS endif +ifdef CONFIG_LTO_CLANG +ifdef CONFIG_THINLTO +CC_FLAGS_LTO_CLANG := -flto=thin -fsplit-lto-unit +KBUILD_LDFLAGS += --thinlto-cache-dir=.thinlto-cache +else +CC_FLAGS_LTO_CLANG := -flto +endif +CC_FLAGS_LTO_CLANG += -fvisibility=default +endif + +ifdef CONFIG_LTO +CC_FLAGS_LTO := $(CC_FLAGS_LTO_CLANG) +KBUILD_CFLAGS += $(CC_FLAGS_LTO) +export CC_FLAGS_LTO +endif + # arch Makefile may override CC so keep this after arch Makefile is included NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) @@ -1446,7 +1462,7 @@ MRPROPER_FILES += include/config include/generated \ *.spec # Directories & files removed with 'make distclean' -DISTCLEAN_FILES += tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS +DISTCLEAN_FILES += tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS .thinlto-cache # clean - Delete most, but leave enough to build external modules # diff --git a/arch/Kconfig b/arch/Kconfig index 8cc35dc556c7..df5a42854a51 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -552,6 +552,73 @@ config SHADOW_CALL_STACK reading and writing arbitrary memory may be able to locate them and hijack control flow by modifying the stacks. +config LTO + bool + +config ARCH_SUPPORTS_LTO_CLANG + bool + help + An architecture should select this option if it supports: + - compiling with Clang, + - compiling inline assembly with Clang's integrated assembler, + - and linking with LLD. + +config ARCH_SUPPORTS_THINLTO + bool + help + An architecture should select this option if it supports Clang's + ThinLTO. + +config THINLTO + bool "Clang ThinLTO" + depends on LTO_CLANG && ARCH_SUPPORTS_THINLTO + default y + help + This option enables Clang's ThinLTO, which allows for parallel + optimization and faster incremental compiles. More information + can be found from Clang's documentation: + + https://clang.llvm.org/docs/ThinLTO.html + +choice + prompt "Link Time Optimization (LTO)" + default LTO_NONE + help + This option enables Link Time Optimization (LTO), which allows the + compiler to optimize binaries globally. + + If unsure, select LTO_NONE. + +config LTO_NONE + bool "None" + +config LTO_CLANG + bool "Clang's Link Time Optimization (EXPERIMENTAL)" + # https://github.com/ClangBuiltLinux/linux/issues/510 + depends on CC_IS_CLANG && CLANG_VERSION >= 110000 && LD_IS_LLD + depends on $(success,$(NM) --help | head -n 1 | grep -qi llvm) + depends on $(success,$(AR) --help | head -n 1 | grep -qi llvm) + depends on ARCH_SUPPORTS_LTO_CLANG + depends on !FTRACE_MCOUNT_RECORD + depends on !KASAN + depends on !MODVERSIONS + select LTO + help + This option enables Clang's Link Time Optimization (LTO), which + allows the compiler to optimize the kernel globally. If you enable + this option, the compiler generates LLVM bitcode instead of ELF + object files, and the actual compilation from bitcode happens at + the LTO link step, which may take several minutes depending on the + kernel configuration. More information can be found from LLVM's + documentation: + + https://llvm.org/docs/LinkTimeOptimization.html + + To select this option, you also need to use LLVM tools to handle + the bitcode by passing LLVM=1 to make. + +endchoice + config HAVE_ARCH_WITHIN_STACK_FRAMES bool help diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 052e0f05a984..7f62f7eef94c 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -89,15 +89,18 @@ * .data. We don't want to pull in .data..other sections, which Linux * has defined. Same for text and bss. * + * With LTO_CLANG, the linker also splits sections by default, so we need + * these macros to combine the sections during the final link. + * * RODATA_MAIN is not used because existing code already defines .rodata.x * sections to be brought in with rodata. */ -#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION +#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* -#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..LPBX* +#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]* -#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* -#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* +#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L* +#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..compoundliteral* #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]* #else #define TEXT_MAIN .text diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 2e8810b7e5ed..f307e708a1b7 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -108,7 +108,7 @@ 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) @@ -424,8 +424,15 @@ $(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) $@ $(filter %.o,$^) +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, so we need to run +# LTO to compile them into native code before running modpost +prelink-ext = .lto + +quiet_cmd_cc_lto_link_modules = LTO [M] $@ +cmd_cc_lto_link_modules = \ + $(LD) $(ld_flags) -r -o $@ \ + --whole-archive $(filter-out FORCE,$^) + +%.lto.o: %.o FORCE + $(call if_changed,cc_lto_link_modules) + +PHONY += FORCE +FORCE: + +endif + +modules := $(sort $(shell cat $(MODORDER))) + # Read out modules.order to pass in modpost. # Otherwise, allmodconfig would fail with "Argument list too long". quiet_cmd_modpost = MODPOST $@ - cmd_modpost = sed 's/ko$$/o/' $< | $(MODPOST) -T - + cmd_modpost = sed 's/\.ko$$/$(prelink-ext)\.o/' $< | $(MODPOST) -T - -$(output-symdump): $(MODORDER) $(input-symdump) FORCE +$(output-symdump): $(MODORDER) $(input-symdump) $(modules:.ko=$(prelink-ext).o) FORCE $(call if_changed,modpost) targets += $(output-symdump) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 00c6e4f28a1a..4b9ae7751b63 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -52,6 +52,14 @@ modpost_link() ${KBUILD_VMLINUX_LIBS} \ --end-group" + if [ -n "${CONFIG_LTO_CLANG}" ]; then + # This might take a while, so indicate that we're doing + # an LTO link + info LTO ${1} + else + info LD ${1} + fi + ${LD} ${KBUILD_LDFLAGS} -r -o ${1} ${objects} } @@ -99,13 +107,22 @@ vmlinux_link() fi if [ "${SRCARCH}" != "um" ]; then - objects="--whole-archive \ - ${KBUILD_VMLINUX_OBJS} \ - --no-whole-archive \ - --start-group \ - ${KBUILD_VMLINUX_LIBS} \ - --end-group \ - ${@}" + if [ -n "${CONFIG_LTO_CLANG}" ]; then + # Use vmlinux.o instead of performing the slow LTO + # link again. + objects="--whole-archive \ + vmlinux.o \ + --no-whole-archive \ + ${@}" + else + objects="--whole-archive \ + ${KBUILD_VMLINUX_OBJS} \ + --no-whole-archive \ + --start-group \ + ${KBUILD_VMLINUX_LIBS} \ + --end-group \ + ${@}" + fi ${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} \ ${strip_debug#-Wl,} \ @@ -270,7 +287,6 @@ fi; ${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init need-builtin=1 #link vmlinux.o -info LD vmlinux.o modpost_link vmlinux.o objtool_link vmlinux.o -- 2.28.0