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

3 files changed, 96 insertions, 1 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 9fc4eb8bfdbc..207261f4879d 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -603,6 +603,96 @@ 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
+	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
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1b8cecdc028e..fd8abf9cb312 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -73,6 +73,8 @@ config ARM64
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_SHADOW_CALL_STACK if CC_HAVE_SHADOW_CALL_STACK
+	select ARCH_SUPPORTS_LTO_CLANG if CPU_LITTLE_ENDIAN
+	select ARCH_SUPPORTS_LTO_CLANG_THIN
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
 	select ARCH_SUPPORTS_NUMA_BALANCING
@@ -162,6 +164,8 @@ config ARM64
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS \
 		if $(cc-option,-fpatchable-function-entry=2)
+	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
+		if DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 76c0255ecc91..945e6bb326e3 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -29,7 +29,8 @@ ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv	\
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
 ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 
-CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS)
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) \
+				$(CC_FLAGS_LTO)
 KASAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
 OBJECT_FILES_NON_STANDARD	:= y