16 files changed, 195 insertions, 33 deletions

diff --git a/Makefile b/Makefile
index 441fe2b223ac..b18dbc634690 100644
--- a/Makefile
+++ b/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
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 595193bc2d31..792517c078c5 100644
--- a/arch/x86/Kconfig
+++ b/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
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index b797f1561943..2d6d5a28c3bf 100644
--- a/arch/x86/Makefile
+++ b/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 $(CONFIG_X86_32),4,8)
+endif
+
 # Workaround for a gcc prelease that unfortunately was shipped in a suse release
 KBUILD_CFLAGS += -Wno-sign-compare
 #
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 02e3e42f380b..05c4abc2fdfd 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -91,7 +91,7 @@ ifneq ($(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)
diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
index 3ff80156f21a..379777572bc9 100644
--- a/arch/x86/power/Makefile
+++ b/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
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61cefb157b59..9c266b93cbc0 100644
--- a/kernel/trace/Kconfig
+++ b/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
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index d94fc9ab819d..3f6bf0ea7c0e 100644
--- a/scripts/Makefile.build
+++ b/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.
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 2301babd3fbc..9f2531567c0e 100644
--- a/scripts/Makefile.lib
+++ b/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)
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index 6de2c35b64e8..735e11e9041b 100644
--- a/scripts/Makefile.modfinal
+++ b/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, $^);		\
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index c5919d5a0b4f..3b261b0f74f0 100755
--- a/scripts/link-vmlinux.sh
+++ b/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
 }
 
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index f47951e19c9d..c3a85d8f6c5c 100644
--- a/tools/objtool/builtin-check.c
+++ b/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;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 331a763d8775..080a3d6cbd75 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -249,7 +249,7 @@ static void init_insn_state(struct insn_state *state, struct section *sec)
 	 * not correctly determine insn->call_dest->sec (external symbols do
 	 * not have a section).
 	 */
-	if (vmlinux && sec)
+	if (vmlinux && noinstr && sec)
 		state->noinstr = sec->noinstr;
 }
 
@@ -548,6 +548,78 @@ static int create_static_call_sections(struct objtool_file *file)
 	return 0;
 }
 
+static int create_mcount_loc_sections(struct objtool_file *file)
+{
+	struct section *sec, *reloc_sec;
+	struct reloc *reloc;
+	unsigned long *loc;
+	struct instruction *insn;
+	int idx;
+
+	sec = find_section_by_name(file->elf, "__mcount_loc");
+	if (sec) {
+		INIT_LIST_HEAD(&file->mcount_loc_list);
+		WARN("file already has __mcount_loc section, skipping");
+		return 0;
+	}
+
+	if (list_empty(&file->mcount_loc_list))
+		return 0;
+
+	idx = 0;
+	list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node)
+		idx++;
+
+	sec = elf_create_section(file->elf, "__mcount_loc", 0, sizeof(unsigned long), idx);
+	if (!sec)
+		return -1;
+
+	reloc_sec = elf_create_reloc_section(file->elf, sec, SHT_RELA);
+	if (!reloc_sec)
+		return -1;
+
+	idx = 0;
+	list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) {
+
+		loc = (unsigned long *)sec->data->d_buf + idx;
+		memset(loc, 0, sizeof(unsigned long));
+
+		reloc = malloc(sizeof(*reloc));
+		if (!reloc) {
+			perror("malloc");
+			return -1;
+		}
+		memset(reloc, 0, sizeof(*reloc));
+
+		if (insn->sec->sym) {
+			reloc->sym = insn->sec->sym;
+			reloc->addend = insn->offset;
+		} else {
+			reloc->sym = find_symbol_containing(insn->sec, insn->offset);
+
+			if (!reloc->sym) {
+				WARN("missing symbol for insn at offset 0x%lx\n",
+				     insn->offset);
+				return -1;
+			}
+
+			reloc->addend = insn->offset - reloc->sym->offset;
+		}
+
+		reloc->type = R_X86_64_64;
+		reloc->offset = idx * sizeof(unsigned long);
+		reloc->sec = reloc_sec;
+		elf_add_reloc(file->elf, reloc);
+
+		idx++;
+	}
+
+	if (elf_rebuild_reloc_section(file->elf, reloc_sec))
+		return -1;
+
+	return 0;
+}
+
 /*
  * Warnings shouldn't be reported for ignored functions.
  */
@@ -975,6 +1047,22 @@ static int add_call_destinations(struct objtool_file *file)
 			insn->type = INSN_NOP;
 		}
 
+		if (mcount && !strcmp(insn->call_dest->name, "__fentry__")) {
+			if (reloc) {
+				reloc->type = R_NONE;
+				elf_write_reloc(file->elf, reloc);
+			}
+
+			elf_write_insn(file->elf, insn->sec,
+				       insn->offset, insn->len,
+				       arch_nop_insn(insn->len));
+
+			insn->type = INSN_NOP;
+
+			list_add_tail(&insn->mcount_loc_node,
+				      &file->mcount_loc_list);
+		}
+
 		/*
 		 * Whatever stack impact regular CALLs have, should be undone
 		 * by the RETURN of the called function.
@@ -3048,6 +3136,13 @@ int check(struct objtool_file *file)
 		goto out;
 	warnings += ret;
 
+	if (mcount) {
+		ret = create_mcount_loc_sections(file);
+		if (ret < 0)
+			goto out;
+		warnings += ret;
+	}
+
 out:
 	/*
 	 *  For now, don't fail the kernel build on fatal warnings.  These
diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h
index 85c979caa367..2502bb27de17 100644
--- a/tools/objtool/include/objtool/builtin.h
+++ b/tools/objtool/include/objtool/builtin.h
@@ -8,7 +8,7 @@
 #include <subcmd/parse-options.h>
 
 extern const struct option check_options[];
-extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux;
+extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux, mcount, noinstr;
 
 extern int cmd_check(int argc, const char **argv);
 extern int cmd_orc(int argc, const char **argv);
diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h
index 4891ead0e85f..f5be798107bc 100644
--- a/tools/objtool/include/objtool/check.h
+++ b/tools/objtool/include/objtool/check.h
@@ -40,6 +40,7 @@ struct instruction {
 	struct list_head list;
 	struct hlist_node hash;
 	struct list_head static_call_node;
+	struct list_head mcount_loc_node;
 	struct section *sec;
 	unsigned long offset;
 	unsigned int len;
diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h
index e114642efb65..e68e37476c15 100644
--- a/tools/objtool/include/objtool/objtool.h
+++ b/tools/objtool/include/objtool/objtool.h
@@ -19,6 +19,7 @@ struct objtool_file {
 	struct list_head insn_list;
 	DECLARE_HASHTABLE(insn_hash, 20);
 	struct list_head static_call_list;
+	struct list_head mcount_loc_list;
 	bool ignore_unreachables, c_file, hints, rodata;
 };
 
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index e848feb0a5fc..7b97ce499405 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -62,6 +62,7 @@ struct objtool_file *objtool_open_read(const char *_objname)
 	INIT_LIST_HEAD(&file.insn_list);
 	hash_init(file.insn_hash);
 	INIT_LIST_HEAD(&file.static_call_list);
+	INIT_LIST_HEAD(&file.mcount_loc_list);
 	file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment");
 	file.ignore_unreachables = no_unreachable;
 	file.hints = false;