Makefile: Allow LTO to be disabled for a build

LTO (Link-Time Optimisation) is an very useful feature which can
significantly reduce the size of U-Boot binaries. So far it has been
made available for selected ARM boards and sandbox.

However, incremental builds are much slower when LTO is used. For example,
an incremental build of sandbox takes 2.1 seconds on my machine, but 6.7
seconds with LTO enabled.

Add a NO_LTO parameter to the build, similar to NO_SDL, so it can be
disabled during development if needed, for faster builds.

Add some documentation about LTO while we are here.

Signed-off-by: Simon Glass <sjg@chromium.org>

5 files changed, 33 insertions, 9 deletions

diff --git a/Makefile b/Makefile
index 541e942ed5..27375f033f 100644
--- a/Makefile
+++ b/Makefile
@@ -643,6 +643,13 @@ export CFLAGS_EFI	# Compiler flags to add when building EFI app
 export CFLAGS_NON_EFI	# Compiler flags to remove when building EFI app
 export EFI_TARGET	# binutils target if EFI is natively supported
 
+export LTO_ENABLE
+
+# This is y if LTO is enabled for this build. See NO_LTO=1 to disable LTO
+ifeq ($(NO_LTO),)
+LTO_ENABLE=$(if $(CONFIG_LTO),y)
+endif
+
 # If board code explicitly specified LDSCRIPT or CONFIG_SYS_LDSCRIPT, use
 # that (or fail if absent).  Otherwise, search for a linker script in a
 # standard location.
@@ -708,16 +715,16 @@ endif
 LTO_CFLAGS :=
 LTO_FINAL_LDFLAGS :=
 export LTO_CFLAGS LTO_FINAL_LDFLAGS
-ifdef CONFIG_LTO
+ifeq ($(LTO_ENABLE),y)
 	ifeq ($(cc-name),clang)
-		LTO_CFLAGS		+= -flto
+		LTO_CFLAGS		+= -DLTO_ENABLE -flto
 		LTO_FINAL_LDFLAGS	+= -flto
 
 		AR			= $(shell $(CC) -print-prog-name=llvm-ar)
 		NM			= $(shell $(CC) -print-prog-name=llvm-nm)
 	else
 		NPROC			:= $(shell nproc 2>/dev/null || echo 1)
-		LTO_CFLAGS		+= -flto=$(NPROC)
+		LTO_CFLAGS		+= -DLTO_ENABLE -flto=$(NPROC)
 		LTO_FINAL_LDFLAGS	+= -fuse-linker-plugin -flto=$(NPROC)
 
 		# use plugin aware tools
@@ -1765,7 +1772,7 @@ ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(ARCH)/Makefile.postlink)
 
 # Generate linker list symbols references to force compiler to not optimize
 # them away when compiling with LTO
-ifdef CONFIG_LTO
+ifeq ($(LTO_ENABLE),y)
 u-boot-keep-syms-lto := keep-syms-lto.o
 u-boot-keep-syms-lto_c := $(patsubst %.o,%.c,$(u-boot-keep-syms-lto))
 
@@ -1787,7 +1794,7 @@ endif
 
 # Rule to link u-boot
 # May be overridden by arch/$(ARCH)/config.mk
-ifdef CONFIG_LTO
+ifeq ($(LTO_ENABLE),y)
 quiet_cmd_u-boot__ ?= LTO     $@
       cmd_u-boot__ ?=								\
 		$(CC) -nostdlib -nostartfiles					\
diff --git a/arch/arm/config.mk b/arch/arm/config.mk
index b3548ce243..2065438d05 100644
--- a/arch/arm/config.mk
+++ b/arch/arm/config.mk
@@ -15,11 +15,11 @@ CFLAGS_NON_EFI := -fno-pic -ffixed-r9 -ffunction-sections -fdata-sections \
 		  -fstack-protector-strong
 CFLAGS_EFI := -fpic -fshort-wchar
 
-ifneq ($(CONFIG_LTO)$(CONFIG_USE_PRIVATE_LIBGCC),yy)
+ifneq ($(LTO_ENABLE)$(CONFIG_USE_PRIVATE_LIBGCC),yy)
 LDFLAGS_FINAL += --gc-sections
 endif
 
-ifndef CONFIG_LTO
+ifneq ($(LTO_ENABLE),y)
 PLATFORM_RELFLAGS += -ffunction-sections -fdata-sections
 endif
 
diff --git a/arch/arm/include/asm/global_data.h b/arch/arm/include/asm/global_data.h
index 6ee2a76761..cd6112dfcd 100644
--- a/arch/arm/include/asm/global_data.h
+++ b/arch/arm/include/asm/global_data.h
@@ -101,7 +101,7 @@ struct arch_global_data {
 
 #include <asm-generic/global_data.h>
 
-#if defined(__clang__) || defined(CONFIG_LTO)
+#if defined(__clang__) || defined(LTO_ENABLE)
 
 #define DECLARE_GLOBAL_DATA_PTR
 #define gd	get_gd()
diff --git a/doc/build/gcc.rst b/doc/build/gcc.rst
index ee544ad87e..a71f860a48 100644
--- a/doc/build/gcc.rst
+++ b/doc/build/gcc.rst
@@ -152,6 +152,23 @@ of dtc is new enough. It also makes sure that pylibfdt is present, if needed
 Note that the :doc:`tools` are always built with the included version of libfdt
 so it is not possible to build U-Boot tools with a system libfdt, at present.
 
+Link-time optimisation (LTO)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+U-Boot supports link-time optimisation which can reduce the size of the final
+U-Boot binaries, particularly with SPL.
+
+At present this can be enabled by ARM boards by adding `CONFIG_LTO=y` into the
+defconfig file. Other architectures are not supported. LTO is enabled by default
+for sandbox.
+
+This does incur a link-time penalty of several seconds. For faster incremental
+builds during development, you can disable it by setting `NO_LTO` to `1`.
+
+.. code-block:: bash
+
+    NO_LTO=1 make
+
 Other build targets
 ~~~~~~~~~~~~~~~~~~~
 
diff --git a/scripts/Makefile.spl b/scripts/Makefile.spl
index 3bafeb4fe9..0b3a51da13 100644
--- a/scripts/Makefile.spl
+++ b/scripts/Makefile.spl
@@ -489,7 +489,7 @@ endif
 
 # Rule to link u-boot-spl
 # May be overridden by arch/$(ARCH)/config.mk
-ifdef CONFIG_LTO
+ifeq ($(LTO_ENABLE),y)
 quiet_cmd_u-boot-spl ?= LTO     $@
       cmd_u-boot-spl ?= \
 	(									\