From dc5723b02e523b2c4a68667f7e28c65018f7202f Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Fri, 11 Dec 2020 10:46:19 -0800
Subject: 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
---
 arch/Kconfig | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 91 insertions(+)

(limited to 'arch/Kconfig')

diff --git a/arch/Kconfig b/arch/Kconfig
index 78c6f05b10f9..9494e3931f4b 100644
--- 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
-- 
cgit v1.2.3-58-ga151


From 38e89184900385b0dad1ee55c35ae8abcfee6ece Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Fri, 11 Dec 2020 10:46:20 -0800
Subject: kbuild: lto: fix module versioning

With CONFIG_MODVERSIONS, version information is linked into each
compilation unit that exports symbols. With LTO, we cannot use this
method as all C code is compiled into LLVM bitcode instead. This
change collects symbol versions into .symversions files and merges
them in link-vmlinux.sh where they are all linked into vmlinux.o at
the same time.

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/20201211184633.3213045-4-samitolvanen@google.com
---
 .gitignore               |  1 +
 Makefile                 |  3 ++-
 arch/Kconfig             |  1 -
 scripts/Makefile.build   | 33 +++++++++++++++++++++++++++++++--
 scripts/Makefile.modpost |  6 +++++-
 scripts/link-vmlinux.sh  | 23 ++++++++++++++++++++++-
 6 files changed, 61 insertions(+), 6 deletions(-)

(limited to 'arch/Kconfig')

diff --git a/.gitignore b/.gitignore
index d01cda8e1177..44e34991875e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -41,6 +41,7 @@
 *.so.dbg
 *.su
 *.symtypes
+*.symversions
 *.tab.[ch]
 *.tar
 *.xz
diff --git a/Makefile b/Makefile
index 2b9bcecd6ea1..173a7c9bd1fb 100644
--- a/Makefile
+++ b/Makefile
@@ -1837,7 +1837,8 @@ clean: $(clean-dirs)
 		-o -name '.tmp_*.o.*' \
 		-o -name '*.c.[012]*.*' \
 		-o -name '*.ll' \
-		-o -name '*.gcno' \) -type f -print | xargs rm -f
+		-o -name '*.gcno' \
+		-o -name '*.*.symversions' \) -type f -print | xargs rm -f
 
 # Generate tags for editors
 # ---------------------------------------------------------------------------
diff --git a/arch/Kconfig b/arch/Kconfig
index 9494e3931f4b..4f2f045d288e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -668,7 +668,6 @@ config HAS_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.
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 65d4bea937fa..d94fc9ab819d 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -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))	\
@@ -177,6 +186,7 @@ cmd_modversions_c =								\
 		rm -f $(@D)/.tmp_$(@F:.o=.ver);					\
 	fi
 endif
+endif
 
 ifdef CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
 # compiler will not generate __mcount_loc use recordmcount or recordmcount.pl
@@ -386,6 +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)
 #
@@ -393,8 +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
@@ -414,8 +439,11 @@ $(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
@@ -424,6 +452,7 @@ $(obj)/lib.a: $(lib-y) FORCE
 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
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 9ff8bfdb574d..066beffca09a 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -111,7 +111,11 @@ ifdef CONFIG_LTO_CLANG
 prelink-ext := .lto
 
 quiet_cmd_cc_lto_link_modules = LTO [M] $@
-cmd_cc_lto_link_modules = $(LD) $(ld_flags) -r -o $@ --whole-archive $^
+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)
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 596507573a48..78e55fe7210b 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -43,11 +43,26 @@ info()
 	fi
 }
 
+# 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}				\
@@ -57,6 +72,11 @@ modpost_link()
 		--end-group"
 
 	if [ -n "${CONFIG_LTO_CLANG}" ]; then
+		if [ -n "${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}
@@ -64,7 +84,7 @@ modpost_link()
 		info LD ${1}
 	fi
 
-	${LD} ${KBUILD_LDFLAGS} -r -o ${1} ${objects}
+	${LD} ${KBUILD_LDFLAGS} -r -o ${1} ${lds} ${objects}
 }
 
 objtool_link()
@@ -242,6 +262,7 @@ cleanup()
 {
 	rm -f .btf.*
 	rm -f .tmp_System.map
+	rm -f .tmp_symversions.lds
 	rm -f .tmp_vmlinux*
 	rm -f System.map
 	rm -f vmlinux
-- 
cgit v1.2.3-58-ga151