[PATCH 28/46] scripts, lto: re-add gcc-ld

[PATCH 28/46] scripts, lto: re-add gcc-ld

[Jiri Slaby (SUSE)]

From: Andi Kleen <ak@linux.intel.com>

The primary goal of the script is to mangle linker command line arguments
into something which gcc understands. Such as converting "-z now" into
"-Wl,-z,now".

The script was removed by commit 86879fd277e8 (scripts: remove obsolete
gcc-ld script) as there was no use in the kernel. It had been added long
time ago to support exactly these lto patches, so we need to add it back
now.

Since the removed version, it is improved a bit:
* some missing linker and gcc command line arguments were added, and
* when V=1 is specified, it prints the final gcc command line

[js] rebase + commit message massage

Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-kbuild@vger.kernel.org
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 scripts/gcc-ld | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)
 create mode 100755 scripts/gcc-ld

diff --git a/scripts/gcc-ld b/scripts/gcc-ld
new file mode 100755
index 000000000000..13e85ece8d04
--- /dev/null
+++ b/scripts/gcc-ld
@@ -0,0 +1,40 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# run gcc with ld options
+# used as a wrapper to execute link time optimizations
+# yes virginia, this is not pretty
+
+ARGS="-nostdlib"
+
+for j in "$@" ; do
+	if [ "$j" = -v ] ; then
+		exec `$CC -print-prog-name=ld` -v
+	fi
+done
+
+while [ "$1" != "" ] ; do
+	case "$1" in
+	-save-temps*|-m32|-m64) N="$1" ;;
+	-r) N="$1" ;;
+	-flinker-output*) N="$1" ;;
+	-[Wg]*) N="$1" ;;
+	-[olv]|-[Ofd]*|-nostdlib) N="$1" ;;
+	--end-group|--start-group|--whole-archive|--no-whole-archive|\
+--no-undefined|--hash-style*|--build-id*|--eh-frame-hdr|-Bsymbolic)
+		 N="-Wl,$1" ;;
+	-[RTFGhIezcbyYu]*|\
+--script|--defsym|-init|-Map|--oformat|-rpath|\
+-rpath-link|--sort-section|--section-start|-Tbss|-Tdata|-Ttext|-soname|\
+--version-script|--dynamic-list|--version-exports-symbol|--wrap|-m|-z)
+		A="$1" ; shift ; N="-Wl,$A,$1" ;;
+	-[m]*) N="$1" ;;
+	-*) N="-Wl,$1" ;;
+	*)  N="$1" ;;
+	esac
+	ARGS="$ARGS $N"
+	shift
+done
+
+[ -n "$V" ] && echo >&2 $CC $ARGS
+
+exec $CC $ARGS
-- 
2.38.1

[PATCH 29/46] scripts, lto: use CONFIG_LTO for many LTO specific actions

[Jiri Slaby (SUSE)]

From: Andi Kleen <ak@linux.intel.com>

The clang LTO and the gcc LTO share some changes in Makefiles and build
scripts. Change the common ones to use CONFIG_LTO instead of
CONFIG_LTO_CLANG so that they can be used by gcc too.

[js] fix scripts/link-vmlinux.sh too

Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-kbuild@vger.kernel.org
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 Makefile                          | 2 +-
 include/asm-generic/vmlinux.lds.h | 2 +-
 kernel/kallsyms.c                 | 2 +-
 scripts/Makefile.build            | 2 +-
 scripts/Makefile.lib              | 2 +-
 scripts/link-vmlinux.sh           | 2 +-
 scripts/module.lds.S              | 2 +-
 7 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/Makefile b/Makefile
index 58cd4f5e1c3a..0b723c903819 100644
--- a/Makefile
+++ b/Makefile
@@ -992,7 +992,7 @@ endif
 endif
 endif
 
-ifdef CONFIG_LTO
+ifdef CONFIG_LTO_CLANG
 KBUILD_CFLAGS	+= -fno-lto $(CC_FLAGS_LTO)
 KBUILD_AFLAGS	+= -fno-lto
 export CC_FLAGS_LTO
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 3dc5824141cd..5e2179dd41d5 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -96,7 +96,7 @@
  * RODATA_MAIN is not used because existing code already defines .rodata.x
  * sections to be brought in with rodata.
  */
-#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG)
+#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO)
 #define TEXT_MAIN .text .text.[0-9a-zA-Z_]*
 #define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L*
 #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]*
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 60c20f301a6b..1d4557ae090f 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -167,7 +167,7 @@ static bool cleanup_symbol_name(char *s)
 {
 	char *res;
 
-	if (!IS_ENABLED(CONFIG_LTO_CLANG))
+	if (!IS_ENABLED(CONFIG_LTO))
 		return false;
 
 	/*
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 564a20ce2667..0a28e3884efe 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -153,7 +153,7 @@ is-single-obj-m = $(and $(part-of-module),$(filter $@, $(obj-m)),y)
 
 # When a module consists of a single object, there is no reason to keep LLVM IR.
 # Make $(LD) covert LLVM IR to ELF here.
-ifdef CONFIG_LTO_CLANG
+ifdef CONFIG_LTO
 cmd_ld_single_m = $(if $(is-single-obj-m), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@)
 endif
 
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 3aa384cec76b..ac918fd84d96 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -269,7 +269,7 @@ objtool-args = $(objtool-args-y)					\
 	$(if $(delay-objtool), --link)					\
 	$(if $(part-of-module), --module)
 
-delay-objtool := $(or $(CONFIG_LTO_CLANG),$(CONFIG_X86_KERNEL_IBT))
+delay-objtool := $(or $(CONFIG_LTO),$(CONFIG_X86_KERNEL_IBT))
 
 cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool-args) $@)
 cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd)
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 918470d768e9..652f33be9549 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -60,7 +60,7 @@ vmlinux_link()
 	# skip output file argument
 	shift
 
-	if is_enabled CONFIG_LTO_CLANG || is_enabled CONFIG_X86_KERNEL_IBT; then
+	if is_enabled CONFIG_LTO || is_enabled CONFIG_X86_KERNEL_IBT; then
 		# Use vmlinux.o instead of performing the slow LTO link again.
 		objs=vmlinux.o
 		libs=
diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index da4bddd26171..b36b0527b0a8 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -27,7 +27,7 @@ SECTIONS {
 	__kcfi_traps 		: { KEEP(*(.kcfi_traps)) }
 #endif
 
-#ifdef CONFIG_LTO_CLANG
+#ifdef CONFIG_LTO
 	/*
 	 * With CONFIG_LTO_CLANG, LLD always enables -fdata-sections and
 	 * -ffunction-sections, which increases the size of the final module.
-- 
2.38.1

[PATCH 30/46] Kbuild, lto: Add Link Time Optimization support

[Jiri Slaby (SUSE)]

From: Andi Kleen <ak@linux.intel.com>

This patch adds gcc LTO support. It leverages some of the existing
support for clang LTO.

With LTO, gcc will do whole program optimizations for the whole kernel
and each module. This increases compile time, but can generate faster
and smaller code and allows the compiler to do global checking. For
example the compiler can complain now about type mismatches for symbols
between different files.

LTO allows gcc to inline functions between different files and do
various other optimization across the whole binary.

The LTO patches have been used for many years by various users, mostly
to make their kernel smaller. The original versions date back to 2012.

This version has a lot of outdated cruft dropped and doesn't need any
special tool chain (except for new enough) anymore.

This adds the basic Kbuild plumbing for LTO:
* Add a new LDFINAL variable that controls the final link for vmlinux or
  module. In this case we call gcc-ld instead of ld, to run the LTO
  step.

* Add Makefile support to enable LTO

For more information see Documentation/kbuild/lto-build.rst

Thanks to H.J. Lu, Joe Mario, Honza Hubicka, Richard Biener, Don Zickus,
Changlong Xie, Gleb Schukin, Martin Liska, various github contributors,
who helped with this project (and probably some more who I forgot,
sorry).

[js] pass -flto only once (the one with jobserver)
[ml] "-m: command not found" and whitespace fix
[bs] fixed Documentation issues:
  * blank line padding before single requirement list
  * use bullet list for FAQ
  * use bullet lists for external link references list
  * add LTO documentation to toc index

Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-kbuild@vger.kernel.org
Cc: Richard Biener <RGuenther@suse.com>
Cc: Jan Hubicka <jh@suse.de>
Cc: H.J. Lu <hjl.tools@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 Documentation/kbuild/index.rst     |  2 +
 Documentation/kbuild/lto-build.rst | 76 ++++++++++++++++++++++++++++++
 Makefile                           |  4 +-
 arch/Kconfig                       | 52 ++++++++++++++++++++
 scripts/Makefile.build             |  9 ++--
 scripts/Makefile.lto               | 43 +++++++++++++++++
 scripts/Makefile.modfinal          |  2 +-
 scripts/Makefile.vmlinux           |  3 +-
 scripts/Makefile.vmlinux_o         |  4 +-
 scripts/link-vmlinux.sh            |  7 +--
 10 files changed, 190 insertions(+), 12 deletions(-)
 create mode 100644 Documentation/kbuild/lto-build.rst
 create mode 100644 scripts/Makefile.lto

diff --git a/Documentation/kbuild/index.rst b/Documentation/kbuild/index.rst
index cee2f99f734b..1937eee7c437 100644
--- a/Documentation/kbuild/index.rst
+++ b/Documentation/kbuild/index.rst
@@ -22,6 +22,8 @@ Kernel Build System
     gcc-plugins
     llvm
 
+    lto-build
+
 .. only::  subproject and html
 
    Indices
diff --git a/Documentation/kbuild/lto-build.rst b/Documentation/kbuild/lto-build.rst
new file mode 100644
index 000000000000..3fb17342e72f
--- /dev/null
+++ b/Documentation/kbuild/lto-build.rst
@@ -0,0 +1,76 @@
+=====================================================
+gcc link time optimization (LTO) for the Linux kernel
+=====================================================
+
+Link Time Optimization allows the compiler to optimize the complete program
+instead of just each file.
+
+The compiler can inline functions between files and do various other global
+optimizations, like specializing functions for common parameters,
+determing when global variables are clobbered, making functions pure/const,
+propagating constants globally, removing unneeded data and others.
+
+It will also drop unused functions which can make the kernel
+image smaller in some circumstances, in particular for small kernel
+configurations.
+
+For small monolithic kernels it can throw away unused code very effectively
+(especially when modules are disabled) and usually shrinks
+the code size.
+
+Build time and memory consumption at build time will increase, depending
+on the size of the largest binary. Modular kernels are less affected.
+With LTO incremental builds are less incremental, as always the whole
+binary needs to be re-optimized (but not re-parsed)
+
+Oopses can be somewhat more difficult to read, due to the more aggressive
+inlining: it helps to use scripts/faddr2line.
+
+It is currently incompatible with live patching.
+
+Normal "reasonable" builds work with less than 4GB of RAM, but very large
+configurations like allyesconfig typically need more memory. The actual
+memory needed depends on the available memory (gcc sizes its garbage
+collector pools based on that or on the ulimit -m limits) and
+the compiler version.
+
+Requirements:
+-------------
+
+- Enough memory: 4GB for a standard build, more for allyesconfig
+  The peak memory usage happens single threaded (when lto-wpa merges types),
+  so dialing back -j options will not help much.
+
+A 32bit hosted compiler is unlikely to work due to the memory requirements.
+You can however build a kernel targeted at 32bit on a 64bit host.
+
+FAQs:
+-----
+
+* I get a section type attribute conflict
+
+  Usually because of someone doing const __initdata (should be
+  const __initconst) or const __read_mostly (should be just const). Check
+  both symbols reported by gcc.
+
+References:
+-----------
+
+* Presentation on Kernel LTO
+  (note, performance numbers/details totally outdated.)
+
+  http://halobates.de/kernel-lto.pdf
+
+* Generic gcc LTO:
+
+  * http://www.ucw.cz/~hubicka/slides/labs2013.pdf
+  * http://www.hipeac.net/system/files/barcelona.pdf
+
+* Somewhat outdated too (from GCC site):
+
+  * http://gcc.gnu.org/projects/lto/lto.pdf
+  * http://gcc.gnu.org/projects/lto/whopr.pdf
+
+Happy Link-Time-Optimizing!
+
+Andi Kleen
diff --git a/Makefile b/Makefile
index 0b723c903819..d0dfb5ca2b21 100644
--- a/Makefile
+++ b/Makefile
@@ -482,6 +482,7 @@ KBUILD_HOSTLDLIBS   := $(HOST_LFS_LIBS) $(HOSTLDLIBS)
 
 # Make variables (CC, etc...)
 CPP		= $(CC) -E
+LDFINAL		= $(LD)
 ifneq ($(LLVM),)
 CC		= $(LLVM_PREFIX)clang$(LLVM_SUFFIX)
 LD		= $(LLVM_PREFIX)ld.lld$(LLVM_SUFFIX)
@@ -604,7 +605,7 @@ export RUSTC RUSTDOC RUSTFMT RUSTC_OR_CLIPPY_QUIET RUSTC_OR_CLIPPY BINDGEN CARGO
 export HOSTRUSTC KBUILD_HOSTRUSTFLAGS
 export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL
 export PERL PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
-export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD
+export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD LDFINAL
 export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE
 export KBUILD_USERCFLAGS KBUILD_USERLDFLAGS
 
@@ -1085,6 +1086,7 @@ include-$(CONFIG_KMSAN)		+= scripts/Makefile.kmsan
 include-$(CONFIG_UBSAN)		+= scripts/Makefile.ubsan
 include-$(CONFIG_KCOV)		+= scripts/Makefile.kcov
 include-$(CONFIG_RANDSTRUCT)	+= scripts/Makefile.randstruct
+include-$(CONFIG_LTO_GCC)	+= scripts/Makefile.lto
 include-$(CONFIG_GCC_PLUGINS)	+= scripts/Makefile.gcc-plugins
 
 include $(addprefix $(srctree)/, $(include-y))
diff --git a/arch/Kconfig b/arch/Kconfig
index 8f138e580d1a..ad52c8fddfb4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -689,6 +689,21 @@ config HAS_LTO_CLANG
 	  The compiler and Kconfig options support building with Clang's
 	  LTO.
 
+config ARCH_SUPPORTS_LTO_GCC
+	bool
+
+# Some ar versions leak file descriptors when using the LTO
+# plugin and cause strange errors when ulimit -n is too low.
+# Pick an arbitrary threshold, which should be enough for most
+# kernel configs. This was a regression that is only
+# in some transient binutils version, so either older or
+# new enough is ok.
+# This might not be the exact range with this bug.
+config BAD_AR
+	depends on LD_VERSION = 23000
+	depends on $(shell,ulimit -n) < 4000
+	def_bool y
+
 choice
 	prompt "Link Time Optimization (LTO)"
 	default LTO_NONE
@@ -736,8 +751,45 @@ config LTO_CLANG_THIN
 	    https://clang.llvm.org/docs/ThinLTO.html
 
 	  If unsure, say Y.
+
+config LTO_GCC
+	bool "gcc LTO"
+	depends on ARCH_SUPPORTS_LTO_GCC && CC_IS_GCC
+	depends on GCC_VERSION >= 100300
+	depends on LD_VERSION >= 22700
+	depends on !BAD_AR
+	select LTO
+	help
+	  Enable whole program (link time) optimizations (LTO) for the whole
+	  kernel and each module. This usually increases compile time,
+	  especially for incremential builds, but tends to generate better code
+	  as well as some global checks.
+
+	  It allows the compiler to inline functions between different files
+	  and do other global optimization, like propagating constants between
+	  functions, determine side effects of functions, avoid unnecessary
+	  register saving around functions, or optimize unused function
+	  arguments. It also allows the compiler to drop unused functions.
+
+	  With this option the compiler will also do some global checking over
+	  different source files.
+
+	  This requires a gcc 10.3 or later compiler and binutils >= 2.27.
+
+	  On larger non modular configurations this may need more than 4GB of
+	  RAM for the link phase, as well as a 64bit host compiler.
+
+	  For more information see Documentation/kbuild/lto-build.rst
 endchoice
 
+config LTO_CP_CLONE
+	bool "Allow aggressive cloning for function specialization"
+	depends on LTO_GCC
+	help
+	  Allow the compiler to clone and specialize functions for specific
+	  arguments when it determines these arguments are commonly
+	  called.  Experimential. Will increase text size.
+
 config ARCH_SUPPORTS_CFI_CLANG
 	bool
 	help
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 0a28e3884efe..9b522c9efcb6 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -154,7 +154,7 @@ is-single-obj-m = $(and $(part-of-module),$(filter $@, $(obj-m)),y)
 # When a module consists of a single object, there is no reason to keep LLVM IR.
 # Make $(LD) covert LLVM IR to ELF here.
 ifdef CONFIG_LTO
-cmd_ld_single_m = $(if $(is-single-obj-m), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@)
+cmd_ld_single_m = $(if $(is-single-obj-m), ; $(LDFINAL) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@)
 endif
 
 quiet_cmd_cc_o_c = CC $(quiet_modtag)  $@
@@ -265,7 +265,8 @@ $(obj)/%.usyms: $(obj)/%.o FORCE
 	$(call if_changed,undefined_syms)
 
 quiet_cmd_cc_lst_c = MKLST   $@
-      cmd_cc_lst_c = $(CC) $(c_flags) -g -c -o $*.o $< && \
+      cmd_cc_lst_c = $(if $(CONFIG_LTO),$(warning Listing in LTO mode does not match final binary)) \
+		     $(CC) $(c_flags) -g -c -o $*.o $< && \
 		     $(CONFIG_SHELL) $(srctree)/scripts/makelst $*.o \
 				     System.map $(OBJDUMP) > $@
 
@@ -446,8 +447,8 @@ $(obj)/modules.order: $(obj-m) FORCE
 $(obj)/lib.a: $(lib-y) FORCE
 	$(call if_changed,ar)
 
-quiet_cmd_ld_multi_m = LD [M]  $@
-      cmd_ld_multi_m = $(LD) $(ld_flags) -r -o $@ @$(patsubst %.o,%.mod,$@) $(cmd_objtool)
+quiet_cmd_ld_multi_m = LDFINAL [M] $@
+      cmd_ld_multi_m = $(LDFINAL) $(ld_flags) -r -o $@ @$(patsubst %.o,%.mod,$@) $(cmd_objtool)
 
 define rule_ld_multi_m
 	$(call cmd_and_savecmd,ld_multi_m)
diff --git a/scripts/Makefile.lto b/scripts/Makefile.lto
new file mode 100644
index 000000000000..33ac0da2bb47
--- /dev/null
+++ b/scripts/Makefile.lto
@@ -0,0 +1,43 @@
+#
+# Support for gcc link time optimization
+#
+
+DISABLE_LTO_GCC :=
+export DISABLE_LTO_GCC
+
+ifdef CONFIG_LTO_GCC
+	CC_FLAGS_LTO_GCC := -flto
+	DISABLE_LTO_GCC := -fno-lto
+
+	KBUILD_CFLAGS += ${CC_FLAGS_LTO_GCC}
+
+	CC_FLAGS_LTO := -flto
+	export CC_FLAGS_LTO
+
+	lto-flags-y := -flinker-output=nolto-rel -flto=jobserver
+	lto-flags-y += -fwhole-program
+
+	lto-flags-$(CONFIG_LTO_CP_CLONE) += -fipa-cp-clone
+
+	# allow extra flags from command line
+	lto-flags-y += ${LTO_EXTRA_CFLAGS}
+
+	# For LTO we need to use gcc to do the linking, not ld
+	# directly. Use a wrapper to convert the ld command line
+	# to gcc
+	LDFINAL := ${CONFIG_SHELL} ${srctree}/scripts/gcc-ld \
+                  ${lto-flags-y}
+
+	# LTO gcc creates a lot of files in TMPDIR, and with /tmp as tmpfs
+	# it's easy to drive the machine OOM. Use the object directory
+	# instead for temporaries.
+	# This has the drawback that there might be some junk more visible
+	# after interrupted compilations, but you would have that junk
+	# there anyways in /tmp.
+	TMPDIR ?= $(objtree)
+	export TMPDIR
+
+	# use plugin aware tools
+	AR = $(CROSS_COMPILE)gcc-ar
+	NM = $(CROSS_COMPILE)gcc-nm
+endif # CONFIG_LTO_GCC
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index 25bedd83644b..c52536c91c8c 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -32,7 +32,7 @@ ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
 
 quiet_cmd_ld_ko_o = LD [M]  $@
       cmd_ld_ko_o +=							\
-	$(LD) -r $(KBUILD_LDFLAGS)					\
+	$(LDFINAL) -r $(KBUILD_LDFLAGS)					\
 		$(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE)		\
 		-T scripts/module.lds -o $@ $(filter %.o, $^);		\
 	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
index 49946cb96844..8871e55f881b 100644
--- a/scripts/Makefile.vmlinux
+++ b/scripts/Makefile.vmlinux
@@ -26,7 +26,8 @@ ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
 
 # Final link of vmlinux with optional arch pass after final link
 cmd_link_vmlinux =							\
-	$< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)";		\
+	$< "$(LD)" "$(LDFINAL)" "$(KBUILD_LDFLAGS)"			\
+	"$(LDFLAGS_vmlinux)";						\
 	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
 
 targets += vmlinux
diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
index 1c86895cfcf8..1f646b16aa70 100644
--- a/scripts/Makefile.vmlinux_o
+++ b/scripts/Makefile.vmlinux_o
@@ -44,9 +44,9 @@ objtool-args = $(vmlinux-objtool-args-y) --link
 # Link of vmlinux.o used for section mismatch analysis
 # ---------------------------------------------------------------------------
 
-quiet_cmd_ld_vmlinux.o = LD      $@
+quiet_cmd_ld_vmlinux.o = LDFINAL $@
       cmd_ld_vmlinux.o = \
-	$(LD) ${KBUILD_LDFLAGS} -r -o $@ \
+	$(LDFINAL) ${KBUILD_LDFLAGS} -r -o $@ \
 	$(addprefix -T , $(initcalls-lds)) \
 	--whole-archive vmlinux.a --no-whole-archive \
 	--start-group $(KBUILD_VMLINUX_LIBS) --end-group \
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 652f33be9549..c89258bcf818 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -29,8 +29,9 @@
 set -e
 
 LD="$1"
-KBUILD_LDFLAGS="$2"
-LDFLAGS_vmlinux="$3"
+LDFINAL="$2"
+KBUILD_LDFLAGS="$3"
+LDFLAGS_vmlinux="$4"
 
 is_enabled() {
 	grep -q "^$1=y" include/config/auto.conf
@@ -82,7 +83,7 @@ vmlinux_link()
 		ldlibs="-lutil -lrt -lpthread"
 	else
 		wl=
-		ld="${LD}"
+		ld="${LDFINAL}"
 		ldflags="${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux}"
 		ldlibs=
 	fi
-- 
2.38.1

Re: [PATCH 30/46] Kbuild, lto: Add Link Time Optimization support

[Josh Poimboeuf]

On Mon, Nov 14, 2022 at 12:43:28PM +0100, Jiri Slaby (SUSE) wrote:
> +++ b/Documentation/kbuild/lto-build.rst
> @@ -0,0 +1,76 @@
> +=====================================================
> +gcc link time optimization (LTO) for the Linux kernel
> +=====================================================
> +
> +Link Time Optimization allows the compiler to optimize the complete program
> +instead of just each file.
> +
> +The compiler can inline functions between files and do various other global
> +optimizations, like specializing functions for common parameters,
> +determing when global variables are clobbered, making functions pure/const,
> +propagating constants globally, removing unneeded data and others.
> +
> +It will also drop unused functions which can make the kernel
> +image smaller in some circumstances, in particular for small kernel
> +configurations.
> +
> +For small monolithic kernels it can throw away unused code very effectively
> +(especially when modules are disabled) and usually shrinks
> +the code size.
> +
> +Build time and memory consumption at build time will increase, depending
> +on the size of the largest binary. Modular kernels are less affected.
> +With LTO incremental builds are less incremental, as always the whole
> +binary needs to be re-optimized (but not re-parsed)
> +
> +Oopses can be somewhat more difficult to read, due to the more aggressive
> +inlining: it helps to use scripts/faddr2line.
> +
> +It is currently incompatible with live patching.

... because ?

-- 
Josh

Re: [PATCH 30/46] Kbuild, lto: Add Link Time Optimization support

[Martin Liška]

On 11/14/22 19:55, Josh Poimboeuf wrote:
> On Mon, Nov 14, 2022 at 12:43:28PM +0100, Jiri Slaby (SUSE) wrote:
>> +++ b/Documentation/kbuild/lto-build.rst
>> @@ -0,0 +1,76 @@
>> +=====================================================
>> +gcc link time optimization (LTO) for the Linux kernel
>> +=====================================================
>> +
>> +Link Time Optimization allows the compiler to optimize the complete program
>> +instead of just each file.
>> +
>> +The compiler can inline functions between files and do various other global
>> +optimizations, like specializing functions for common parameters,
>> +determing when global variables are clobbered, making functions pure/const,
>> +propagating constants globally, removing unneeded data and others.
>> +
>> +It will also drop unused functions which can make the kernel
>> +image smaller in some circumstances, in particular for small kernel
>> +configurations.
>> +
>> +For small monolithic kernels it can throw away unused code very effectively
>> +(especially when modules are disabled) and usually shrinks
>> +the code size.
>> +
>> +Build time and memory consumption at build time will increase, depending
>> +on the size of the largest binary. Modular kernels are less affected.
>> +With LTO incremental builds are less incremental, as always the whole
>> +binary needs to be re-optimized (but not re-parsed)
>> +
>> +Oopses can be somewhat more difficult to read, due to the more aggressive
>> +inlining: it helps to use scripts/faddr2line.
>> +
>> +It is currently incompatible with live patching.
> 
> ... because ?

There's no fundamental reason why live patching can't coexist with -flto.

We removed the sorry message for GCC 13.1 release:
https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=1a308905c1baf64d0ea4d09d7d92b55e79a2a339
when it comes to -flive-patching=inline-clone option.

But it seems Linux does not utilize the option (based on git grep):
https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html#index-flive-patching

That said, I would remove this limitation as LTO can make creation of live patches
more complicated, but fundamentally there's no barrier.

Thanks,
Martin

[PATCH 34/46] scripts, lto: disable gcc LTO for some mod sources

[Jiri Slaby (SUSE)]

From: Andi Kleen <andi@firstfloor.org>

The mod tools scan assembler (devicetable-offsets.s) to generate symbols
into devicetable-offsets.h and binary (empty.o) to find out ELF setup.
That doesn't work with LTO. So just disable LTO for empty.o and
devicetable-offsets.s.

Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-kbuild@vger.kernel.org
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 scripts/mod/Makefile | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/scripts/mod/Makefile b/scripts/mod/Makefile
index c9e38ad937fd..aa3465d6bc4a 100644
--- a/scripts/mod/Makefile
+++ b/scripts/mod/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 OBJECT_FILES_NON_STANDARD := y
 CFLAGS_REMOVE_empty.o += $(CC_FLAGS_LTO)
+CFLAGS_REMOVE_empty.o += $(CC_FLAGS_LTO_GCC)
 
 hostprogs-always-y	+= modpost mk_elfconfig
 always-y		+= empty.o
@@ -9,6 +10,8 @@ modpost-objs	:= modpost.o file2alias.o sumversion.o
 
 devicetable-offsets-file := devicetable-offsets.h
 
+$(obj)/devicetable-offsets.s: KBUILD_CFLAGS += $(DISABLE_LTO_GCC)
+
 $(obj)/$(devicetable-offsets-file): $(obj)/devicetable-offsets.s FORCE
 	$(call filechk,offsets,__DEVICETABLE_OFFSETS_H__)
 
-- 
2.38.1

[PATCH 35/46] Kbuild, lto: disable gcc LTO for bounds+asm-offsets

[Jiri Slaby (SUSE)]

From: Andi Kleen <andi@firstfloor.org>

Disable LTO when generating the bounds+asm-offsets.s files which are
scanned for C constants. With a LTO build, the file would contain the
gcc IR in assembler form, which breaks the scanning scripts.

Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-kbuild@vger.kernel.org
Signed-off-by: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 Kbuild | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Kbuild b/Kbuild
index 464b34a08f51..40744d76d416 100644
--- a/Kbuild
+++ b/Kbuild
@@ -11,6 +11,8 @@ bounds-file := include/generated/bounds.h
 
 targets := kernel/bounds.s
 
+kernel/bounds.s: KBUILD_CFLAGS += $(DISABLE_LTO_GCC)
+
 $(bounds-file): kernel/bounds.s FORCE
 	$(call filechk,offsets,__LINUX_BOUNDS_H__)
 
@@ -30,6 +32,7 @@ offsets-file := include/generated/asm-offsets.h
 targets += arch/$(SRCARCH)/kernel/asm-offsets.s
 
 arch/$(SRCARCH)/kernel/asm-offsets.s: $(timeconst-file) $(bounds-file)
+arch/$(SRCARCH)/kernel/asm-offsets.s: KBUILD_CFLAGS += $(DISABLE_LTO_GCC)
 
 $(offsets-file): arch/$(SRCARCH)/kernel/asm-offsets.s FORCE
 	$(call filechk,offsets,__ASM_OFFSETS_H__)
-- 
2.38.1

[PATCH 38/46] Kbuild, lto: don't include weak source file symbols in System.map

[Jiri Slaby (SUSE)]

From: Andi Kleen <andi@firstfloor.org>

The gcc LTO build can generate some extra weak source code file name
symbols on the second kallsyms link like:
  0000000002fdf20a W head64.c.552cf5a6

This causes the "Inconsistent kallsyms data" error due to mismatches in
the stage1 vs stage2 kallsyms link. Filter those out when generating
the System.map.

Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-kbuild@vger.kernel.org
Signed-off-by: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 scripts/mksysmap | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/mksysmap b/scripts/mksysmap
index 16a08b8ef2f8..0f19a44ab136 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -34,6 +34,7 @@
 #   U - undefined global symbols
 #   N - debugging symbols
 #   w - local weak symbols
+#   W - weak symbols if they contain .c.
 
 # readprofile starts reading symbols when _stext is found, and
 # continue until it finds a symbol which is not either of 'T', 't',
@@ -57,4 +58,5 @@ $NM -n $1 | grep -v		\
 	-e ' __kstrtab_'	\
 	-e ' __kstrtabns_'	\
 	-e ' L0$'		\
+	-e ' W .*\.c\.'		\
 > $2
-- 
2.38.1

[PATCH 43/46] scripts, lto: check C symbols for modversions

[Jiri Slaby (SUSE)]

From: Andi Kleen <ak@linux.intel.com>

The gcc LTO nm doesn't output assembler symbols, which makes the
symversions check fail because ksymtab is defined in assembler. Instead,
check for a C symbol that is generated too.

Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-kbuild@vger.kernel.org
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 scripts/Makefile.build | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 9b522c9efcb6..dafa8aeed9c2 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -173,7 +173,7 @@ ifdef CONFIG_MODVERSIONS
 #   be compiled and linked to the kernel and/or modules.
 
 gen_symversions =								\
-	if $(NM) $@ 2>/dev/null | grep -q __ksymtab; then			\
+	if $(NM) $@ 2>/dev/null | grep -q __kstrtab; then			\
 		$(call cmd_gensymtypes_$(1),$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \
 			>> $(dot-target).cmd;					\
 	fi
-- 
2.38.1

[PATCH 44/46] scripts/bloat-o-meter, lto: handle gcc LTO

[Jiri Slaby (SUSE)]

From: Andi Kleen <ak@linux.intel.com>

gcc LTO can add .lto_priv postfixes to symbols. Ignore those in
bloat-o-meter to allow comparison of non-LTO with LTO kernels.

Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: linux-kbuild@vger.kernel.org
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 scripts/bloat-o-meter | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter
index f9553f60a14a..ab994b3bf6e2 100755
--- a/scripts/bloat-o-meter
+++ b/scripts/bloat-o-meter
@@ -45,7 +45,7 @@ def getsizes(file, format):
                 if name == "linux_banner": continue
                 if name == "vermagic": continue
                 # statics and some other optimizations adds random .NUMBER
-                name = re_NUMBER.sub('', name)
+                name = re_NUMBER.sub('', name).replace(".lto_priv", "")
                 sym[name] = sym.get(name, 0) + int(size, 16)
     return sym
 
-- 
2.38.1