Merge tag 'clang-lto-v5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull clang LTO updates from Kees Cook:
 "Clang Link Time Optimization.

  This is built on the work done preparing for LTO by arm64 folks,
  tracing folks, etc. This includes the core changes as well as the
  remaining pieces for arm64 (LTO has been the default build method on
  Android for about 3 years now, as it is the prerequisite for the
  Control Flow Integrity protections).

  While x86 LTO enablement is done, it depends on some pending objtool
  clean-ups. It's possible that I'll send a "part 2" pull request for
  LTO that includes x86 support.

  For merge log posterity, and as detailed in commit dc5723b02e52
  ("kbuild: add support for Clang LTO"), here is the lt;dr to do an LTO
  build:

        make LLVM=1 LLVM_IAS=1 defconfig
        scripts/config -e LTO_CLANG_THIN
        make LLVM=1 LLVM_IAS=1

  (To do a cross-compile of arm64, add "CROSS_COMPILE=aarch64-linux-gnu-"
  and "ARCH=arm64" to the "make" command lines.)

  Summary:

   - Clang LTO build infrastructure and arm64-specific enablement (Sami
     Tolvanen)

   - Recursive build CC_FLAGS_LTO fix (Alexander Lobakin)"

* tag 'clang-lto-v5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  kbuild: prevent CC_FLAGS_LTO self-bloating on recursive rebuilds
  arm64: allow LTO to be selected
  arm64: disable recordmcount with DYNAMIC_FTRACE_WITH_REGS
  arm64: vdso: disable LTO
  drivers/misc/lkdtm: disable LTO for rodata.o
  efi/libstub: disable LTO
  scripts/mod: disable LTO for empty.c
  modpost: lto: strip .lto from module names
  PCI: Fix PREL32 relocations for LTO
  init: lto: fix PREL32 relocations
  init: lto: ensure initcall ordering
  kbuild: lto: add a default list of used symbols
  kbuild: lto: merge module sections
  kbuild: lto: limit inlining
  kbuild: lto: fix module versioning
  kbuild: add support for Clang LTO
  tracing: move function tracer options to Kconfig

12 files changed, 458 insertions, 31 deletions

diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 4c058f12dd73..d94fc9ab819d 100644
--- 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)
@@ -166,6 +166,15 @@ ifdef CONFIG_MODVERSIONS
 #   the actual value of the checksum generated by genksyms
 # o remove .tmp_<file>.o to <file>.o
 
+ifdef CONFIG_LTO_CLANG
+# Generate .o.symversions files for each .o with exported symbols, and link these
+# to the kernel and/or modules at the end.
+cmd_modversions_c =								\
+	if $(NM) $@ 2>/dev/null | grep -q __ksymtab; then			\
+		$(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes))	\
+		    > $@.symversions;						\
+	fi;
+else
 cmd_modversions_c =								\
 	if $(OBJDUMP) -h $@ | grep -q __ksymtab; then				\
 		$(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes))	\
@@ -177,9 +186,9 @@ cmd_modversions_c =								\
 		rm -f $(@D)/.tmp_$(@F:.o=.ver);					\
 	fi
 endif
+endif
 
-ifdef CONFIG_FTRACE_MCOUNT_RECORD
-ifndef CC_USING_RECORD_MCOUNT
+ifdef CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
 # compiler will not generate __mcount_loc use recordmcount or recordmcount.pl
 ifdef BUILD_C_RECORDMCOUNT
 ifeq ("$(origin RECORDMCOUNT_WARN)", "command line")
@@ -206,8 +215,7 @@ recordmcount_source := $(srctree)/scripts/recordmcount.pl
 endif # BUILD_C_RECORDMCOUNT
 cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)),	\
 	$(sub_cmd_record_mcount))
-endif # CC_USING_RECORD_MCOUNT
-endif # CONFIG_FTRACE_MCOUNT_RECORD
+endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
 
 ifdef CONFIG_STACK_VALIDATION
 ifneq ($(SKIP_STACK_VALIDATION),1)
@@ -388,6 +396,18 @@ $(obj)/%.asn1.c $(obj)/%.asn1.h: $(src)/%.asn1 $(objtree)/scripts/asn1_compiler
 $(subdir-builtin): $(obj)/%/built-in.a: $(obj)/% ;
 $(subdir-modorder): $(obj)/%/modules.order: $(obj)/% ;
 
+# combine symversions for later processing
+quiet_cmd_update_lto_symversions = SYMVER  $@
+ifeq ($(CONFIG_LTO_CLANG) $(CONFIG_MODVERSIONS),y y)
+      cmd_update_lto_symversions =					\
+	rm -f $@.symversions						\
+	$(foreach n, $(filter-out FORCE,$^),				\
+		$(if $(wildcard $(n).symversions),			\
+			; cat $(n).symversions >> $@.symversions))
+else
+      cmd_update_lto_symversions = echo >/dev/null
+endif
+
 #
 # Rule to compile a set of .o files into one .a file (without symbol table)
 #
@@ -395,8 +415,11 @@ $(subdir-modorder): $(obj)/%/modules.order: $(obj)/% ;
 quiet_cmd_ar_builtin = AR      $@
       cmd_ar_builtin = rm -f $@; $(AR) cDPrST $@ $(real-prereqs)
 
+quiet_cmd_ar_and_symver = AR      $@
+      cmd_ar_and_symver = $(cmd_update_lto_symversions); $(cmd_ar_builtin)
+
 $(obj)/built-in.a: $(real-obj-y) FORCE
-	$(call if_changed,ar_builtin)
+	$(call if_changed,ar_and_symver)
 
 #
 # Rule to create modules.order file
@@ -416,15 +439,26 @@ $(obj)/modules.order: $(obj-m) FORCE
 #
 # Rule to compile a set of .o files into one .a file (with symbol table)
 #
+quiet_cmd_ar_lib = AR      $@
+      cmd_ar_lib = $(cmd_update_lto_symversions); $(cmd_ar)
+
 $(obj)/lib.a: $(lib-y) FORCE
-	$(call if_changed,ar)
+	$(call if_changed,ar_lib)
 
 # NOTE:
 # 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 =						\
+	$(cmd_update_lto_symversions);				\
+	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)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index b00855b247e0..2301babd3fbc 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -119,9 +119,11 @@ target-stem = $(basename $(patsubst $(obj)/%,%,$@))
 # These flags are needed for modversions and compiling, so we define them here
 # $(modname_flags) defines KBUILD_MODNAME as the name of the module it will
 # end up in (or would, if it gets compiled in)
-name-fix = $(call stringify,$(subst $(comma),_,$(subst -,_,$1)))
+name-fix-token = $(subst $(comma),_,$(subst -,_,$1))
+name-fix = $(call stringify,$(call name-fix-token,$1))
 basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget))
-modname_flags  = -DKBUILD_MODNAME=$(call name-fix,$(modname))
+modname_flags  = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \
+		 -D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname))
 modfile_flags  = -DKBUILD_MODFILE=$(call stringify,$(modfile))
 
 _c_flags       = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index d49ec001825d..6de2c35b64e8 100644
--- 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))
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index f54b6ac37ac2..066beffca09a 100644
--- 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 +105,30 @@ $(input-symdump):
 	@echo >&2 'WARNING: Symbol version dump "$@" 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 $@					\
+		$(shell [ -s $(@:.lto.o=.o.symversions) ] &&		\
+			echo -T $(@:.lto.o=.o.symversions))		\
+		--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)
diff --git a/scripts/generate_initcall_order.pl b/scripts/generate_initcall_order.pl
new file mode 100755
index 000000000000..1a88d3f1b913
--- /dev/null
+++ b/scripts/generate_initcall_order.pl
@@ -0,0 +1,270 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generates a linker script that specifies the correct initcall order.
+#
+# Copyright (C) 2019 Google LLC
+
+use strict;
+use warnings;
+use IO::Handle;
+use IO::Select;
+use POSIX ":sys_wait_h";
+
+my $nm = $ENV{'NM'} || die "$0: ERROR: NM not set?";
+my $objtree = $ENV{'objtree'} || '.';
+
+## currently active child processes
+my $jobs = {};		# child process pid -> file handle
+## results from child processes
+my $results = {};	# object index -> [ { level, secname }, ... ]
+
+## reads _NPROCESSORS_ONLN to determine the maximum number of processes to
+## start
+sub get_online_processors {
+	open(my $fh, "getconf _NPROCESSORS_ONLN 2>/dev/null |")
+		or die "$0: ERROR: failed to execute getconf: $!";
+	my $procs = <$fh>;
+	close($fh);
+
+	if (!($procs =~ /^\d+$/)) {
+		return 1;
+	}
+
+	return int($procs);
+}
+
+## writes results to the parent process
+## format: <file index> <initcall level> <base initcall section name>
+sub write_results {
+	my ($index, $initcalls) = @_;
+
+	# sort by the counter value to ensure the order of initcalls within
+	# each object file is correct
+	foreach my $counter (sort { $a <=> $b } keys(%{$initcalls})) {
+		my $level = $initcalls->{$counter}->{'level'};
+
+		# section name for the initcall function
+		my $secname = $initcalls->{$counter}->{'module'} . '__' .
+			      $counter . '_' .
+			      $initcalls->{$counter}->{'line'} . '_' .
+			      $initcalls->{$counter}->{'function'};
+
+		print "$index $level $secname\n";
+	}
+}
+
+## reads a result line from a child process and adds it to the $results array
+sub read_results{
+	my ($fh) = @_;
+
+	# each child prints out a full line w/ autoflush and exits after the
+	# last line, so even if buffered I/O blocks here, it shouldn't block
+	# very long
+	my $data = <$fh>;
+
+	if (!defined($data)) {
+		return 0;
+	}
+
+	chomp($data);
+
+	my ($index, $level, $secname) = $data =~
+		/^(\d+)\ ([^\ ]+)\ (.*)$/;
+
+	if (!defined($index) ||
+		!defined($level) ||
+		!defined($secname)) {
+		die "$0: ERROR: child process returned invalid data: $data\n";
+	}
+
+	$index = int($index);
+
+	if (!exists($results->{$index})) {
+		$results->{$index} = [];
+	}
+
+	push (@{$results->{$index}}, {
+		'level'   => $level,
+		'secname' => $secname
+	});
+
+	return 1;
+}
+
+## finds initcalls from an object file or all object files in an archive, and
+## writes results back to the parent process
+sub find_initcalls {
+	my ($index, $file) = @_;
+
+	die "$0: ERROR: file $file doesn't exist?" if (! -f $file);
+
+	open(my $fh, "\"$nm\" --defined-only \"$file\" 2>/dev/null |")
+		or die "$0: ERROR: failed to execute \"$nm\": $!";
+
+	my $initcalls = {};
+
+	while (<$fh>) {
+		chomp;
+
+		# check for the start of a new object file (if processing an
+		# archive)
+		my ($path)= $_ =~ /^(.+)\:$/;
+
+		if (defined($path)) {
+			write_results($index, $initcalls);
+			$initcalls = {};
+			next;
+		}
+
+		# look for an initcall
+		my ($module, $counter, $line, $symbol) = $_ =~
+			/[a-z]\s+__initcall__(\S*)__(\d+)_(\d+)_(.*)$/;
+
+		if (!defined($module)) {
+			$module = ''
+		}
+
+		if (!defined($counter) ||
+			!defined($line) ||
+			!defined($symbol)) {
+			next;
+		}
+
+		# parse initcall level
+		my ($function, $level) = $symbol =~
+			/^(.*)((early|rootfs|con|[0-9])s?)$/;
+
+		die "$0: ERROR: invalid initcall name $symbol in $file($path)"
+			if (!defined($function) || !defined($level));
+
+		$initcalls->{$counter} = {
+			'module'   => $module,
+			'line'     => $line,
+			'function' => $function,
+			'level'    => $level,
+		};
+	}
+
+	close($fh);
+	write_results($index, $initcalls);
+}
+
+## waits for any child process to complete, reads the results, and adds them to
+## the $results array for later processing
+sub wait_for_results {
+	my ($select) = @_;
+
+	my $pid = 0;
+	do {
+		# unblock children that may have a full write buffer
+		foreach my $fh ($select->can_read(0)) {
+			read_results($fh);
+		}
+
+		# check for children that have exited, read the remaining data
+		# from them, and clean up
+		$pid = waitpid(-1, WNOHANG);
+		if ($pid > 0) {
+			if (!exists($jobs->{$pid})) {
+				next;
+			}
+
+			my $fh = $jobs->{$pid};
+			$select->remove($fh);
+
+			while (read_results($fh)) {
+				# until eof
+			}
+
+			close($fh);
+			delete($jobs->{$pid});
+		}
+	} while ($pid > 0);
+}
+
+## forks a child to process each file passed in the command line and collects
+## the results
+sub process_files {
+	my $index = 0;
+	my $njobs = $ENV{'PARALLELISM'} || get_online_processors();
+	my $select = IO::Select->new();
+
+	while (my $file = shift(@ARGV)) {
+		# fork a child process and read it's stdout
+		my $pid = open(my $fh, '-|');
+
+		if (!defined($pid)) {
+			die "$0: ERROR: failed to fork: $!";
+		} elsif ($pid) {
+			# save the child process pid and the file handle
+			$select->add($fh);
+			$jobs->{$pid} = $fh;
+		} else {
+			# in the child process
+			STDOUT->autoflush(1);
+			find_initcalls($index, "$objtree/$file");
+			exit;
+		}
+
+		$index++;
+
+		# limit the number of children to $njobs
+		if (scalar(keys(%{$jobs})) >= $njobs) {
+			wait_for_results($select);
+		}
+	}
+
+	# wait for the remaining children to complete
+	while (scalar(keys(%{$jobs})) > 0) {
+		wait_for_results($select);
+	}
+}
+
+sub generate_initcall_lds() {
+	process_files();
+
+	my $sections = {};	# level -> [ secname, ...]
+
+	# sort results to retain link order and split to sections per
+	# initcall level
+	foreach my $index (sort { $a <=> $b } keys(%{$results})) {
+		foreach my $result (@{$results->{$index}}) {
+			my $level = $result->{'level'};
+
+			if (!exists($sections->{$level})) {
+				$sections->{$level} = [];
+			}
+
+			push(@{$sections->{$level}}, $result->{'secname'});
+		}
+	}
+
+	die "$0: ERROR: no initcalls?" if (!keys(%{$sections}));
+
+	# print out a linker script that defines the order of initcalls for
+	# each level
+	print "SECTIONS {\n";
+
+	foreach my $level (sort(keys(%{$sections}))) {
+		my $section;
+
+		if ($level eq 'con') {
+			$section = '.con_initcall.init';
+		} else {
+			$section = ".initcall${level}.init";
+		}
+
+		print "\t${section} : {\n";
+
+		foreach my $secname (@{$sections->{$level}}) {
+			print "\t\t*(${section}..${secname}) ;\n";
+		}
+
+		print "\t}\n";
+	}
+
+	print "}\n";
+}
+
+generate_initcall_lds();
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 6eded325c837..c5919d5a0b4f 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -43,11 +43,37 @@ info()
 	fi
 }
 
+# Generate a linker script to ensure correct ordering of initcalls.
+gen_initcalls()
+{
+	info GEN .tmp_initcalls.lds
+
+	${PYTHON} ${srctree}/scripts/jobserver-exec		\
+	${PERL} ${srctree}/scripts/generate_initcall_order.pl	\
+		${KBUILD_VMLINUX_OBJS} ${KBUILD_VMLINUX_LIBS}	\
+		> .tmp_initcalls.lds
+}
+
+# If CONFIG_LTO_CLANG is selected, collect generated symbol versions into
+# .tmp_symversions.lds
+gen_symversions()
+{
+	info GEN .tmp_symversions.lds
+	rm -f .tmp_symversions.lds
+
+	for o in ${KBUILD_VMLINUX_OBJS} ${KBUILD_VMLINUX_LIBS}; do
+		if [ -f ${o}.symversions ]; then
+			cat ${o}.symversions >> .tmp_symversions.lds
+		fi
+	done
+}
+
 # Link of vmlinux.o used for section mismatch analysis
 # ${1} output file
 modpost_link()
 {
 	local objects
+	local lds=""
 
 	objects="--whole-archive				\
 		${KBUILD_VMLINUX_OBJS}				\
@@ -56,7 +82,23 @@ modpost_link()
 		${KBUILD_VMLINUX_LIBS}				\
 		--end-group"
 
-	${LD} ${KBUILD_LDFLAGS} -r -o ${1} ${objects}
+	if [ -n "${CONFIG_LTO_CLANG}" ]; then
+		gen_initcalls
+		lds="-T .tmp_initcalls.lds"
+
+		if [ -n "${CONFIG_MODVERSIONS}" ]; then
+			gen_symversions
+			lds="${lds} -T .tmp_symversions.lds"
+		fi
+
+		# 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} ${lds} ${objects}
 }
 
 objtool_link()
@@ -103,13 +145,22 @@ 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,}			\
@@ -225,6 +276,8 @@ cleanup()
 {
 	rm -f .btf.*
 	rm -f .tmp_System.map
+	rm -f .tmp_initcalls.lds
+	rm -f .tmp_symversions.lds
 	rm -f .tmp_vmlinux*
 	rm -f System.map
 	rm -f vmlinux
@@ -274,7 +327,6 @@ 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
 
diff --git a/scripts/lto-used-symbollist.txt b/scripts/lto-used-symbollist.txt
new file mode 100644
index 000000000000..38e7bb9ebaae
--- /dev/null
+++ b/scripts/lto-used-symbollist.txt
@@ -0,0 +1,5 @@
+memcpy
+memmove
+memset
+__stack_chk_fail
+__stack_chk_guard
diff --git a/scripts/mod/Makefile b/scripts/mod/Makefile
index 78071681d924..c9e38ad937fd 100644
--- a/scripts/mod/Makefile
+++ b/scripts/mod/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 OBJECT_FILES_NON_STANDARD := y
+CFLAGS_REMOVE_empty.o += $(CC_FLAGS_LTO)
 
 hostprogs-always-y	+= modpost mk_elfconfig
 always-y		+= empty.o
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index d6c81657d695..be0642126f53 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -17,7 +17,6 @@
 #include <ctype.h>
 #include <string.h>
 #include <limits.h>
-#include <stdbool.h>
 #include <errno.h>
 #include "modpost.h"
 #include "../../include/linux/license.h"
@@ -84,14 +83,6 @@ modpost_log(enum loglevel loglevel, const char *fmt, ...)
 		error_occurred = true;
 }
 
-static inline bool strends(const char *str, const char *postfix)
-{
-	if (strlen(str) < strlen(postfix))
-		return false;
-
-	return strcmp(str + strlen(str) - strlen(postfix), postfix) == 0;
-}
-
 void *do_nofail(void *ptr, const char *expr)
 {
 	if (!ptr)
@@ -1988,6 +1979,10 @@ static char *remove_dot(char *s)
 		size_t m = strspn(s + n + 1, "0123456789");
 		if (m && (s[n + m] == '.' || s[n + m] == 0))
 			s[n] = 0;
+
+		/* strip trailing .lto */
+		if (strends(s, ".lto"))
+			s[strlen(s) - 4] = '\0';
 	}
 	return s;
 }
@@ -2011,6 +2006,9 @@ static void read_symbols(const char *modname)
 		/* strip trailing .o */
 		tmp = NOFAIL(strdup(modname));
 		tmp[strlen(tmp) - 2] = '\0';
+		/* strip trailing .lto */
+		if (strends(tmp, ".lto"))
+			tmp[strlen(tmp) - 4] = '\0';
 		mod = new_module(tmp);
 		free(tmp);
 	}
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index e6f46eee0af0..1f76eea7cfde 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -2,6 +2,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <stdarg.h>
+#include <stdbool.h>
 #include <string.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -180,6 +181,14 @@ static inline unsigned int get_secindex(const struct elf_info *info,
 	return info->symtab_shndx_start[sym - info->symtab_start];
 }
 
+static inline bool strends(const char *str, const char *postfix)
+{
+	if (strlen(str) < strlen(postfix))
+		return false;
+
+	return strcmp(str + strlen(str) - strlen(postfix), postfix) == 0;
+}
+
 /* file2alias.c */
 extern unsigned int cross_build;
 void handle_moddevtable(struct module *mod, struct elf_info *info,
diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c
index d587f40f1117..760e6baa7eda 100644
--- a/scripts/mod/sumversion.c
+++ b/scripts/mod/sumversion.c
@@ -391,10 +391,14 @@ void get_src_version(const char *modname, char sum[], unsigned sumlen)
 	struct md4_ctx md;
 	char *fname;
 	char filelist[PATH_MAX + 1];
+	int postfix_len = 1;
+
+	if (strends(modname, ".lto.o"))
+		postfix_len = 5;
 
 	/* objects for a module are listed in the first line of *.mod file. */
 	snprintf(filelist, sizeof(filelist), "%.*smod",
-		 (int)strlen(modname) - 1, modname);
+		 (int)strlen(modname) - postfix_len, modname);
 
 	buf = read_text_file(filelist);
 
diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index 69b9b71a6a47..18d5b8423635 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -23,6 +23,30 @@ SECTIONS {
 	.init_array		0 : ALIGN(8) { *(SORT(.init_array.*)) *(.init_array) }
 
 	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
+
+	__patchable_function_entries : { *(__patchable_function_entries) }
+
+	/*
+	 * With CONFIG_LTO_CLANG, LLD always enables -fdata-sections and
+	 * -ffunction-sections, which increases the size of the final module.
+	 * Merge the split sections in the final binary.
+	 */
+	.bss : {
+		*(.bss .bss.[0-9a-zA-Z_]*)
+		*(.bss..L*)
+	}
+
+	.data : {
+		*(.data .data.[0-9a-zA-Z_]*)
+		*(.data..L*)
+	}
+
+	.rodata : {
+		*(.rodata .rodata.[0-9a-zA-Z_]*)
+		*(.rodata..L*)
+	}
+
+	.text : { *(.text .text.[0-9a-zA-Z_]*) }
 }
 
 /* bring in arch-specific sections */