Merge tag 'clang-lto-v5.12-rc1-part2' of git://git.kernel.org/pub/scm…

…/linux/kernel/git/kees/linux

Pull more clang LTO updates from Kees Cook:
 "Clang LTO x86 enablement.

  Full disclosure: while this has _not_ been in linux-next (since it
  initially looked like the objtool dependencies weren't going to make
  v5.12), it has been under daily build and runtime testing by Sami for
  quite some time. These x86 portions have been discussed on lkml, with
  Peter, Josh, and others helping nail things down.

  The bulk of the changes are to get objtool working happily. The rest
  of the x86 enablement is very small.

  Summary:

   - Generate __mcount_loc in objtool (Peter Zijlstra)

   - Support running objtool against vmlinux.o (Sami Tolvanen)

   - Clang LTO enablement for x86 (Sami Tolvanen)"

Link: https://lore.kernel.org/lkml/[email protected]/
Link: https://lore.kernel.org/lkml/[email protected]/

* tag 'clang-lto-v5.12-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  kbuild: lto: force rebuilds when switching CONFIG_LTO
  x86, build: allow LTO to be selected
  x86, cpu: disable LTO for cpu.c
  x86, vdso: disable LTO only for vDSO
  kbuild: lto: postpone objtool
  objtool: Split noinstr validation from --vmlinux
  x86, build: use objtool mcount
  tracing: add support for objtool mcount
  objtool: Don't autodetect vmlinux.o
  objtool: Fix __mcount_loc generation with Clang's assembler
  objtool: Add a pass for generating __mcount_loc

Makefile

@@ -862,6 +862,9 @@ ifdef CONFIG_FTRACE_MCOUNT_USE_CC
     endif
   endif
 endif
+ifdef CONFIG_FTRACE_MCOUNT_USE_OBJTOOL
+  CC_FLAGS_USING	+= -DCC_USING_NOP_MCOUNT
+endif
 ifdef CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
   ifdef CONFIG_HAVE_C_RECORDMCOUNT
     BUILD_C_RECORDMCOUNT := y
@@ -909,7 +912,8 @@ KBUILD_LDFLAGS += -mllvm -import-instr-limit=5
 endif
 
 ifdef CONFIG_LTO
-KBUILD_CFLAGS	+= $(CC_FLAGS_LTO)
+KBUILD_CFLAGS	+= -fno-lto $(CC_FLAGS_LTO)
+KBUILD_AFLAGS	+= -fno-lto
 export CC_FLAGS_LTO
 endif
 
@@ -1243,6 +1247,10 @@ uapi-asm-generic:
 PHONY += prepare-objtool prepare-resolve_btfids
 prepare-objtool: $(objtool_target)
 ifeq ($(SKIP_STACK_VALIDATION),1)
+ifdef CONFIG_FTRACE_MCOUNT_USE_OBJTOOL
+	@echo "error: Cannot generate __mcount_loc for CONFIG_DYNAMIC_FTRACE=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel" >&2
+	@false
+endif
 ifdef CONFIG_UNWINDER_ORC
 	@echo "error: Cannot generate ORC metadata for CONFIG_UNWINDER_ORC=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel" >&2
 	@false

arch/x86/Kconfig

@@ -97,6 +97,8 @@ config X86
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP	if NR_CPUS <= 4096
+	select ARCH_SUPPORTS_LTO_CLANG		if X86_64
+	select ARCH_SUPPORTS_LTO_CLANG_THIN	if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
@@ -169,6 +171,7 @@ config X86
 	select HAVE_CONTEXT_TRACKING		if X86_64
 	select HAVE_CONTEXT_TRACKING_OFFSTACK	if HAVE_CONTEXT_TRACKING
 	select HAVE_C_RECORDMCOUNT
+	select HAVE_OBJTOOL_MCOUNT		if STACK_VALIDATION
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE

arch/x86/Makefile

@@ -169,6 +169,11 @@ ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
 	KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,)
 endif
 
+ifdef CONFIG_LTO_CLANG
+KBUILD_LDFLAGS	+= -plugin-opt=-code-model=kernel \
+		   -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8)
+endif
+
 # Workaround for a gcc prelease that unfortunately was shipped in a suse release
 KBUILD_CFLAGS += -Wno-sign-compare
 #

arch/x86/entry/vdso/Makefile

@@ -91,7 +91,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),)
 endif
 endif
 
-$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
@@ -150,6 +150,7 @@ KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
 KBUILD_CFLAGS_32 += -fno-stack-protector
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)

arch/x86/power/Makefile

@@ -4,5 +4,9 @@
 # itself be stack-protected
 CFLAGS_cpu.o	:= -fno-stack-protector
 
+# Clang may incorrectly inline functions with stack protector enabled into
+# __restore_processor_state(): https://bugs.llvm.org/show_bug.cgi?id=47479
+CFLAGS_REMOVE_cpu.o := $(CC_FLAGS_LTO)
+
 obj-$(CONFIG_PM_SLEEP)		+= cpu.o
 obj-$(CONFIG_HIBERNATION)	+= hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o

kernel/trace/Kconfig

@@ -60,6 +60,11 @@ config HAVE_NOP_MCOUNT
 	help
 	  Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount
 
+config HAVE_OBJTOOL_MCOUNT
+	bool
+	help
+	  Arch supports objtool --mcount
+
 config HAVE_C_RECORDMCOUNT
 	bool
 	help
@@ -612,10 +617,18 @@ config FTRACE_MCOUNT_USE_CC
 	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
 	depends on FTRACE_MCOUNT_RECORD
 
+config FTRACE_MCOUNT_USE_OBJTOOL
+	def_bool y
+	depends on HAVE_OBJTOOL_MCOUNT
+	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
+	depends on !FTRACE_MCOUNT_USE_CC
+	depends on FTRACE_MCOUNT_RECORD
+
 config FTRACE_MCOUNT_USE_RECORDMCOUNT
 	def_bool y
 	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
 	depends on !FTRACE_MCOUNT_USE_CC
+	depends on !FTRACE_MCOUNT_USE_OBJTOOL
 	depends on FTRACE_MCOUNT_RECORD
 
 config TRACING_MAP

scripts/Makefile.build

@@ -218,27 +218,11 @@ cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)),
 endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
 
 ifdef CONFIG_STACK_VALIDATION
+ifndef CONFIG_LTO_CLANG
 ifneq ($(SKIP_STACK_VALIDATION),1)
 
 __objtool_obj := $(objtree)/tools/objtool/objtool
 
-objtool_args = $(if $(CONFIG_UNWINDER_ORC),orc generate,check)
-
-objtool_args += $(if $(part-of-module), --module,)
-
-ifndef CONFIG_FRAME_POINTER
-objtool_args += --no-fp
-endif
-ifdef CONFIG_GCOV_KERNEL
-objtool_args += --no-unreachable
-endif
-ifdef CONFIG_RETPOLINE
-  objtool_args += --retpoline
-endif
-ifdef CONFIG_X86_SMAP
-  objtool_args += --uaccess
-endif
-
 # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory
 # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file
 # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file
@@ -250,6 +234,7 @@ objtool_obj = $(if $(patsubst y%,, \
 	$(__objtool_obj))
 
 endif # SKIP_STACK_VALIDATION
+endif # CONFIG_LTO_CLANG
 endif # CONFIG_STACK_VALIDATION
 
 # Rebuild all objects when objtool changes, or is enabled/disabled.

scripts/Makefile.lib

@@ -222,6 +222,18 @@ dtc_cpp_flags  = -Wp,-MMD,$(depfile).pre.tmp -nostdinc                    \
 		 $(addprefix -I,$(DTC_INCLUDE))                          \
 		 -undef -D__DTS__
 
+# Objtool arguments are also needed for modfinal with LTO, so we define
+# then here to avoid duplication.
+objtool_args =								\
+	$(if $(CONFIG_UNWINDER_ORC),orc generate,check)			\
+	$(if $(part-of-module), --module,)				\
+	$(if $(CONFIG_FRAME_POINTER),, --no-fp)				\
+	$(if $(or $(CONFIG_GCOV_KERNEL),$(CONFIG_LTO_CLANG)), 		\
+		--no-unreachable,)					\
+	$(if $(CONFIG_RETPOLINE), --retpoline,)				\
+	$(if $(CONFIG_X86_SMAP), --uaccess,)				\
+	$(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount,)
+
 # Useful for describing the dependency of composite objects
 # Usage:
 #   $(call multi_depend, multi_used_targets, suffix_to_remove, suffix_to_add)

scripts/Makefile.modfinal

@@ -9,7 +9,7 @@ __modfinal:
 include include/config/auto.conf
 include $(srctree)/scripts/Kbuild.include
 
-# for c_flags
+# for c_flags and objtool_args
 include $(srctree)/scripts/Makefile.lib
 
 # find all modules listed in modules.order
@@ -34,10 +34,23 @@ 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
+
+# ELF processing was skipped earlier because we didn't have native code,
+# so let's now process the prelinked binary before we link the module.
+
+ifdef CONFIG_STACK_VALIDATION
+ifneq ($(SKIP_STACK_VALIDATION),1)
+cmd_ld_ko_o +=								\
+	$(objtree)/tools/objtool/objtool $(objtool_args)		\
+		$(@:.ko=$(prelink-ext).o);
+
+endif # SKIP_STACK_VALIDATION
+endif # CONFIG_STACK_VALIDATION
+
+endif # CONFIG_LTO_CLANG
 
 quiet_cmd_ld_ko_o = LD [M]  $@
-      cmd_ld_ko_o =                                                     \
+      cmd_ld_ko_o +=							\
 	$(LD) -r $(KBUILD_LDFLAGS)					\
 		$(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE)		\
 		-T scripts/module.lds -o $@ $(filter %.o, $^);		\

scripts/link-vmlinux.sh

@@ -103,14 +103,36 @@ modpost_link()
 
 objtool_link()
 {
+	local objtoolcmd;
 	local objtoolopt;
 
+	if [ "${CONFIG_LTO_CLANG} ${CONFIG_STACK_VALIDATION}" = "y y" ]; then
+		# Don't perform vmlinux validation unless explicitly requested,
+		# but run objtool on vmlinux.o now that we have an object file.
+		if [ -n "${CONFIG_UNWINDER_ORC}" ]; then
+			objtoolcmd="orc generate"
+		fi
+
+		objtoolopt="${objtoolopt} --duplicate"
+
+		if [ -n "${CONFIG_FTRACE_MCOUNT_USE_OBJTOOL}" ]; then
+			objtoolopt="${objtoolopt} --mcount"
+		fi
+	fi
+
 	if [ -n "${CONFIG_VMLINUX_VALIDATION}" ]; then
-		objtoolopt="check"
+		objtoolopt="${objtoolopt} --noinstr"
+	fi
+
+	if [ -n "${objtoolopt}" ]; then
+		if [ -z "${objtoolcmd}" ]; then
+			objtoolcmd="check"
+		fi
+		objtoolopt="${objtoolopt} --vmlinux"
 		if [ -z "${CONFIG_FRAME_POINTER}" ]; then
 			objtoolopt="${objtoolopt} --no-fp"
 		fi
-		if [ -n "${CONFIG_GCOV_KERNEL}" ]; then
+		if [ -n "${CONFIG_GCOV_KERNEL}" ] || [ -n "${CONFIG_LTO_CLANG}" ]; then
 			objtoolopt="${objtoolopt} --no-unreachable"
 		fi
 		if [ -n "${CONFIG_RETPOLINE}" ]; then
@@ -120,7 +142,7 @@ objtool_link()
 			objtoolopt="${objtoolopt} --uaccess"
 		fi
 		info OBJTOOL ${1}
-		tools/objtool/objtool ${objtoolopt} ${1}
+		tools/objtool/objtool ${objtoolcmd} ${objtoolopt} ${1}
 	fi
 }
 

tools/objtool/builtin-check.c

@@ -18,7 +18,7 @@
 #include <objtool/builtin.h>
 #include <objtool/objtool.h>
 
-bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux;
+bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux, mcount, noinstr;
 
 static const char * const check_usage[] = {
 	"objtool check [<options>] file.o",
@@ -34,13 +34,15 @@ const struct option check_options[] = {
 	OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"),
 	OPT_BOOLEAN('s', "stats", &stats, "print statistics"),
 	OPT_BOOLEAN('d', "duplicate", &validate_dup, "duplicate validation for vmlinux.o"),
+	OPT_BOOLEAN('n', "noinstr", &noinstr, "noinstr validation for vmlinux.o"),
 	OPT_BOOLEAN('l', "vmlinux", &vmlinux, "vmlinux.o validation"),
+	OPT_BOOLEAN('M', "mcount", &mcount, "generate __mcount_loc"),
 	OPT_END(),
 };
 
 int cmd_check(int argc, const char **argv)
 {
-	const char *objname, *s;
+	const char *objname;
 	struct objtool_file *file;
 	int ret;
 
@@ -51,10 +53,6 @@ int cmd_check(int argc, const char **argv)
 
 	objname = argv[0];
 
-	s = strstr(objname, "vmlinux.o");
-	if (s && !s[9])
-		vmlinux = true;
-
 	file = objtool_open_read(objname);
 	if (!file)
 		return 1;