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 all assembly code with Clang's integrated assembler, - and linking with LLD. While using CONFIG_LTO_CLANG_FULL results in the best runtime performance, the compilation is not scalable in time or memory. CONFIG_LTO_CLANG_THIN enables ThinLTO, which allows parallel optimization and faster incremental builds. ThinLTO is used by default if the architecture also selects ARCH_SUPPORTS_LTO_CLANG_THIN: https://clang.llvm.org/docs/ThinLTO.html To enable LTO, LLVM tools must be used to handle bitcode files, by passing LLVM=1 and LLVM_IAS=1 options to make: $ make LLVM=1 LLVM_IAS=1 defconfig $ scripts/config -e LTO_CLANG_THIN $ make LLVM=1 LLVM_IAS=1 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. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201211184633.3213045-3-samitolvanen@google.com
2020-12-11 10:46:19 -08:00 · 2020-12-11 10:46:19 -08:00 · dc5723b02e
commit dc5723b02e
parent 3b15cdc159
7 changed files with 174 additions and 18 deletions
--- a/19
+++ b/19
@ -893,6 +893,21 @@ KBUILD_CFLAGS	+= $(CC_FLAGS_SCS)
 export CC_FLAGS_SCS
 endif

+ifdef CONFIG_LTO_CLANG
+ifdef CONFIG_LTO_CLANG_THIN
+CC_FLAGS_LTO	+= -flto=thin -fsplit-lto-unit
+KBUILD_LDFLAGS	+= --thinlto-cache-dir=$(extmod-prefix).thinlto-cache
+else
+CC_FLAGS_LTO	+= -flto
+endif
+CC_FLAGS_LTO	+= -fvisibility=hidden
+endif
+
+ifdef CONFIG_LTO
+KBUILD_CFLAGS	+= $(CC_FLAGS_LTO)
+export CC_FLAGS_LTO
+endif
+
 ifdef CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_32B
 KBUILD_CFLAGS += -falign-functions=32
 endif
@ -1479,7 +1494,7 @@ 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
 #
@ -1725,7 +1740,7 @@ PHONY += compile_commands.json

 clean-dirs := $(KBUILD_EXTMOD)
 clean: rm-files := $(KBUILD_EXTMOD)/Module.symvers $(KBUILD_EXTMOD)/modules.nsdeps \
-	$(KBUILD_EXTMOD)/compile_commands.json
+	$(KBUILD_EXTMOD)/compile_commands.json $(KBUILD_EXTMOD)/.thinlto-cache

 PHONY += help
 help:
--- a/arch/Kconfig
+++ b/arch/Kconfig
@ -631,6 +631,97 @@ 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
+	help
+	  Selected if the kernel will be built using the compiler's LTO feature.
+
+config LTO_CLANG
+	bool
+	select LTO
+	help
+	  Selected if the kernel will be built using Clang's LTO feature.
+
+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_LTO_CLANG_THIN
+	bool
+	help
+	  An architecture should select this option if it can support Clang's
+	  ThinLTO mode.
+
+config HAS_LTO_CLANG
+	def_bool y
+	# Clang >= 11: https://github.com/ClangBuiltLinux/linux/issues/510
+	depends on CC_IS_CLANG && CLANG_VERSION >= 110000 && LD_IS_LLD
+	depends on $(success,test $(LLVM) -eq 1)
+	depends on $(success,test $(LLVM_IAS) -eq 1)
+	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_USE_RECORDMCOUNT
+	depends on !KASAN
+	depends on !GCOV_KERNEL
+	depends on !MODVERSIONS
+	help
+	  The compiler and Kconfig options support building with Clang's
+	  LTO.
+
+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. Note that LTO is very resource-intensive
+	  so it's disabled by default.
+
+config LTO_NONE
+	bool "None"
+	help
+	  Build the kernel normally, without Link Time Optimization (LTO).
+
+config LTO_CLANG_FULL
+	bool "Clang Full LTO (EXPERIMENTAL)"
+	depends on HAS_LTO_CLANG
+	depends on !COMPILE_TEST
+	select LTO_CLANG
+	help
+          This option enables Clang's full 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
+
+	  During link time, this option can use a large amount of RAM, and
+	  may take much longer than the ThinLTO option.
+
+config LTO_CLANG_THIN
+	bool "Clang ThinLTO (EXPERIMENTAL)"
+	depends on HAS_LTO_CLANG && ARCH_SUPPORTS_LTO_CLANG_THIN
+	select LTO_CLANG
+	help
+	  This option enables Clang's ThinLTO, which allows for parallel
+	  optimization and faster incremental compiles compared to the
+	  CONFIG_LTO_CLANG_FULL option. More information can be found
+	  from Clang's documentation:
+
+	    https://clang.llvm.org/docs/ThinLTO.html
+
+	  If unsure, say Y.
+endchoice
+
 config HAVE_ARCH_WITHIN_STACK_FRAMES
 	bool
 	help
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@ -90,15 +90,18 @@
 * .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
--- 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)) -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)
@ -421,8 +421,15 @@ $(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) cDPrsT $@ $(filter %.o,$^)
+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)
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@ -30,6 +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)					\
@ -53,8 +59,9 @@ if_changed_except = $(if $(call newer_prereqs_except,$(2))$(cmd-check),      \
 	$(cmd);                                                              \
 	printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd, @:)

+
 # Re-generate module BTFs if either module's .ko or vmlinux changed
-$(modules): %.ko: %.o %.mod.o scripts/module.lds $(if $(KBUILD_BUILTIN),vmlinux) FORCE
+$(modules): %.ko: %$(prelink-ext).o %.mod.o scripts/module.lds $(if $(KBUILD_BUILTIN),vmlinux) FORCE
 	+$(call if_changed_except,ld_ko_o,vmlinux)
 ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 	+$(if $(newer-prereqs),$(call cmd,btf_ko))
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@ -43,6 +43,9 @@ __modpost:
 include include/config/auto.conf
 include scripts/Kbuild.include

+# for ld_flags
+include scripts/Makefile.lib
+
 MODPOST = scripts/mod/modpost								\
 	$(if $(CONFIG_MODVERSIONS),-m)							\
 	$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a)					\
@ -102,12 +105,26 @@ $(input-symdump):
 	@echo >&2 'WARNING: Symbol version dump "$@" 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 $^
+
+%.lto.o: %.o
+	$(call if_changed,cc_lto_link_modules)
+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)
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@ -56,6 +56,14 @@ 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}
 }

@ -103,13 +111,22 @@ 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,}			\
@ -274,7 +291,6 @@ 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