@@ -886,6 +886,21 @@ KBUILD_CFLAGS += $(CC_FLAGS_SCS)
export CC_FLAGS_SCS
endif
+ifdef CONFIG_LTO_CLANG
+ifdef CONFIG_THINLTO
+CC_FLAGS_LTO += -flto=thin -fsplit-lto-unit
+KBUILD_LDFLAGS += --thinlto-cache-dir=$(extmod-prefix).thinlto-cache
+else
+CC_FLAGS_LTO += -flto
+endif
+CC_FLAGS_LTO += -fvisibility=default
+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
@@ -1477,7 +1492,7 @@ 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
#
@@ -1714,7 +1729,8 @@ _emodinst_post: _emodinst_
$(call cmd,depmod)
clean-dirs := $(KBUILD_EXTMOD)
-clean: rm-files := $(KBUILD_EXTMOD)/Module.symvers $(KBUILD_EXTMOD)/modules.nsdeps
+clean: rm-files := $(KBUILD_EXTMOD)/Module.symvers $(KBUILD_EXTMOD)/modules.nsdeps \
+ $(KBUILD_EXTMOD)/.thinlto-cache
PHONY += help
help:
@@ -558,6 +558,81 @@ 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
+
+ If you say N here, the compiler will use full LTO, which may
+ produce faster code, but building the kernel will be significantly
+ slower as the linker won't efficiently utilize multiple threads.
+
+ If unsure, say Y.
+
+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"
+
+config LTO_CLANG
+ bool "Clang's Link Time Optimization (EXPERIMENTAL)"
+ # Clang >= 11: 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 !GCOV_KERNEL
+ 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
@@ -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
@@ -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)
@@ -425,8 +425,15 @@ $(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)
@@ -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) \
@@ -36,7 +43,7 @@ quiet_cmd_ld_ko_o = LD [M] $@
-T scripts/module.lds -o $@ $(filter %.o, $^); \
$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
-$(modules): %.ko: %.o %.mod.o scripts/module.lds FORCE
+$(modules): %.ko: %$(prelink-ext).o %.mod.o scripts/module.lds FORCE
+$(call if_changed,ld_ko_o)
targets += $(modules) $(modules:.ko=.mod.o)
@@ -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)
@@ -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