Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Masahiro Yamada <masahiroy@kernel.org>
To:     linux-kbuild@vger.kernel.org
Cc:     linux-kernel@vger.kernel.org,
        Peter Zijlstra <peterz@infradead.org>,
        Josh Poimboeuf <jpoimboe@redhat.com>, llvm@lists.linux.dev,
        Helge Deller <deller@gmx.de>, linux-parisc@vger.kernel.org,
        Masahiro Yamada <masahiroy@kernel.org>,
        Nicolas Schier <nicolas@fjasle.eu>,
        Nathan Chancellor <nathan@kernel.org>,
        Sami Tolvanen <samitolvanen@google.com>,
        Sedat Dilek <sedat.dilek@gmail.com>,
        Michal Marek <michal.lkml@markovi.net>,
        Nick Desaulniers <ndesaulniers@google.com>,
        Tom Rix <trix@redhat.com>
Subject: [PATCH v7 2/8] kbuild: do not create *.prelink.o for Clang LTO or IBT
Date:   Fri, 27 May 2022 19:01:49 +0900
Message-Id: <20220527100155.1996314-3-masahiroy@kernel.org>
In-Reply-To: <20220527100155.1996314-1-masahiroy@kernel.org>
References: <20220527100155.1996314-1-masahiroy@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

When CONFIG_LTO_CLANG=y, additional intermediate *.prelink.o is created
for each module. Also, objtool is postponed until LLVM IR is converted
to ELF.

CONFIG_X86_KERNEL_IBT works in a similar way to postpone objtool until
objects are merged together.

This commit stops generating *.prelink.o, so the build flow will look
similar with/without LTO.

The following figures show how the LTO build currently works, and
how this commit is changing it.

Current build flow
==================

 [1] single-object module

                                      $(LD)
           $(CC)                     +objtool              $(LD)
    foo.c --------------------> foo.o -----> foo.prelink.o -----> foo.ko
                              (LLVM IR)          (ELF)       |
                                                             |
                                                 foo.mod.o --/

 [2] multi-object module
                                      $(LD)
           $(CC)         $(AR)       +objtool               $(LD)
    foo1.c -----> foo1.o -----> foo.o -----> foo.prelink.o -----> foo.ko
                           |  (archive)          (ELF)       |
    foo2.c -----> foo2.o --/                                 |
                 (LLVM IR)                       foo.mod.o --/

  One confusion is foo.o in multi-object module is an archive despite of
  its suffix.

New build flow
==============

 [1] single-object module

  Since there is only one object, there is no need to keep the LLVM IR.
  Use $(CC)+$(LD) to generate an ELF object in one build rule. When LTO
  is disabled, $(LD) is unneeded because $(CC) produces an ELF object.

               $(CC)+$(LD)+objtool              $(LD)
    foo.c ----------------------------> foo.o ---------> foo.ko
                                        (ELF)     |
                                                  |
                                      foo.mod.o --/

 [2] multi-object module

  Previously, $(AR) was used to combine LLVM bitcode into an archive,
  but there was no technical reason to do so. Use $(LD) to merge them
  into a single ELF object.

                               $(LD)
             $(CC)            +objtool          $(LD)
    foo1.c ---------> foo1.o ---------> foo.o ---------> foo.ko
                                 |      (ELF)     |
    foo2.c ---------> foo2.o ----/                |
                     (LLVM IR)        foo.mod.o --/

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com> # LLVM-14 (x86-64)
---

(no changes since v2)

Changes in v2:
 - replace the chain of $(if ...) with $(and )

 scripts/Kbuild.include    |  4 +++
 scripts/Makefile.build    | 60 ++++++++++++---------------------------
 scripts/Makefile.lib      |  7 -----
 scripts/Makefile.modfinal |  5 ++--
 scripts/Makefile.modpost  |  9 ++----
 scripts/mod/modpost.c     |  7 -----
 6 files changed, 26 insertions(+), 66 deletions(-)

diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 3514c2149e9d..455a0a6ce12d 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -15,6 +15,10 @@ pound := \#
 # Name of target with a '.' as filename prefix. foo/bar.o => foo/.bar.o
 dot-target = $(dir $@).$(notdir $@)
 
+###
+# Name of target with a '.tmp_' as filename prefix. foo/bar.o => foo/.tmp_bar.o
+tmp-target = $(dir $@).tmp_$(notdir $@)
+
 ###
 # The temporary file to save gcc -MMD generated dependencies must not
 # contain a comma
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index f80196eef03a..23e1fb19f9ad 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -88,10 +88,6 @@ endif
 targets-for-modules := $(foreach x, o mod $(if $(CONFIG_TRIM_UNUSED_KSYMS), usyms), \
 				$(patsubst %.o, %.$x, $(filter %.o, $(obj-m))))
 
-ifneq ($(CONFIG_LTO_CLANG)$(CONFIG_X86_KERNEL_IBT),)
-targets-for-modules += $(patsubst %.o, %.prelink.o, $(filter %.o, $(obj-m)))
-endif
-
 ifdef need-modorder
 targets-for-modules += $(obj)/modules.order
 endif
@@ -152,8 +148,16 @@ $(obj)/%.ll: $(src)/%.c FORCE
 # The C file is compiled and updated dependency information is generated.
 # (See cmd_cc_o_c + relevant part of rule_cc_o_c)
 
+is-single-obj-m = $(and $(part-of-module),$(filter $@, $(obj-m)),y)
+
+ifdef CONFIG_LTO_CLANG
+cmd_ld_single_m = $(if $(is-single-obj-m), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@)
+endif
+
 quiet_cmd_cc_o_c = CC $(quiet_modtag)  $@
-      cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $< $(cmd_objtool)
+      cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $< \
+		$(cmd_ld_single_m) \
+		$(cmd_objtool)
 
 ifdef CONFIG_MODVERSIONS
 # When module versioning is enabled the following steps are executed:
@@ -219,7 +223,7 @@ objtool_args =								\
 	$(if $(CONFIG_STACK_VALIDATION), --stackval)			\
 	$(if $(CONFIG_HAVE_STATIC_CALL_INLINE), --static-call)		\
 	--uaccess							\
-	$(if $($(CONFIG_LTO_CLANG)$(CONFIG_X86_KERNEL_IBT)), --link)	\
+	$(if $(delay-objtool), --link)					\
 	$(if $(part-of-module), --module)				\
 	$(if $(CONFIG_GCOV_KERNEL), --no-unreachable)
 
@@ -228,21 +232,16 @@ cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(o
 
 endif # CONFIG_OBJTOOL
 
-ifneq ($(CONFIG_LTO_CLANG)$(CONFIG_X86_KERNEL_IBT),)
-
-# Skip objtool for LLVM bitcode
-$(obj)/%.o: objtool-enabled :=
-
-else
 
 # '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
 
-$(obj)/%.o: objtool-enabled = $(if $(filter-out y%, \
-	$(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n),y)
+is-standard-object = $(if $(filter-out y%, $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n),y)
 
-endif
+delay-objtool := $(or $(CONFIG_LTO_CLANG),$(CONFIG_X86_KERNEL_IBT))
+
+$(obj)/%.o: objtool-enabled = $(if $(is-standard-object),$(if $(delay-objtool),$(is-single-obj-m),y))
 
 ifdef CONFIG_TRIM_UNUSED_KSYMS
 cmd_gen_ksymdeps = \
@@ -271,24 +270,6 @@ $(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE
 	$(call if_changed_rule,cc_o_c)
 	$(call cmd,force_checksrc)
 
-ifneq ($(CONFIG_LTO_CLANG)$(CONFIG_X86_KERNEL_IBT),)
-# Module .o files may contain LLVM bitcode, compile them into native code
-# before ELF processing
-quiet_cmd_cc_prelink_modules = LD [M]  $@
-      cmd_cc_prelink_modules =						\
-	$(LD) $(ld_flags) -r -o $@					\
-		--whole-archive $(filter-out FORCE,$^)			\
-		$(cmd_objtool)
-
-# objtool was skipped for LLVM bitcode, run it now that we have compiled
-# modules into native code
-$(obj)/%.prelink.o: objtool-enabled = y
-$(obj)/%.prelink.o: part-of-module := y
-
-$(obj)/%.prelink.o: $(obj)/%.o FORCE
-	$(call if_changed,cc_prelink_modules)
-endif
-
 cmd_mod = echo $(addprefix $(obj)/, $(call real-search, $*.o, .o, -objs -y -m)) | \
 	$(AWK) -v RS='( |\n)' '!x[$$0]++' > $@
 
@@ -298,7 +279,7 @@ $(obj)/%.mod: FORCE
 # List module undefined symbols
 cmd_undefined_syms = $(NM) $< | sed -n 's/^  *U //p' > $@
 
-$(obj)/%.usyms: $(obj)/%$(mod-prelink-ext).o FORCE
+$(obj)/%.usyms: $(obj)/%.o FORCE
 	$(call if_changed,undefined_syms)
 
 quiet_cmd_cc_lst_c = MKLST   $@
@@ -420,16 +401,11 @@ $(obj)/modules.order: $(obj-m) FORCE
 $(obj)/lib.a: $(lib-y) FORCE
 	$(call if_changed,ar)
 
-ifneq ($(CONFIG_LTO_CLANG)$(CONFIG_X86_KERNEL_IBT),)
-quiet_cmd_link_multi-m = AR [M]  $@
-cmd_link_multi-m =						\
-	rm -f $@; 						\
-	$(AR) cDPrsT $@ @$(patsubst %.o,%.mod,$@)
-else
 quiet_cmd_link_multi-m = LD [M]  $@
-      cmd_link_multi-m = $(LD) $(ld_flags) -r -o $@ @$(patsubst %.o,%.mod,$@)
-endif
+      cmd_link_multi-m = $(LD) $(ld_flags) -r -o $@ @$(patsubst %.o,%.mod,$@) $(cmd_objtool)
 
+$(multi-obj-m): objtool-enabled := $(delay-objtool)
+$(multi-obj-m): part-of-module := y
 $(multi-obj-m): %.o: %.mod FORCE
 	$(call if_changed,link_multi-m)
 $(call multi_depend, $(multi-obj-m), .o, -objs -y -m)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 0453a1904646..f75138385449 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -225,13 +225,6 @@ dtc_cpp_flags  = -Wp,-MMD,$(depfile).pre.tmp -nostdinc                    \
 		 $(addprefix -I,$(DTC_INCLUDE))                          \
 		 -undef -D__DTS__
 
-ifneq ($(CONFIG_LTO_CLANG)$(CONFIG_X86_KERNEL_IBT),)
-# With CONFIG_LTO_CLANG, .o files in modules might be LLVM bitcode, so we
-# need to run LTO to compile them into native code (.lto.o) before further
-# processing.
-mod-prelink-ext := .prelink
-endif
-
 # 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 7f39599e9fae..35100e981f4a 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 and mod-prelink-ext
+# for c_flags
 include $(srctree)/scripts/Makefile.lib
 
 # find all modules listed in modules.order
@@ -54,9 +54,8 @@ 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
-$(modules): %.ko: %$(mod-prelink-ext).o %.mod.o scripts/module.lds $(if $(KBUILD_BUILTIN),vmlinux) FORCE
+$(modules): %.ko: %.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 8b343480813d..911606496341 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -41,9 +41,6 @@ __modpost:
 include include/config/auto.conf
 include $(srctree)/scripts/Kbuild.include
 
-# for mod-prelink-ext
-include $(srctree)/scripts/Makefile.lib
-
 MODPOST = scripts/mod/modpost								\
 	$(if $(CONFIG_MODVERSIONS),-m)							\
 	$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a)					\
@@ -117,8 +114,6 @@ $(input-symdump):
 	@echo >&2 '         Modules may not have dependencies or modversions.'
 	@echo >&2 '         You may get many unresolved symbol warnings.'
 
-modules := $(sort $(shell cat $(MODORDER)))
-
 # KBUILD_MODPOST_WARN can be set to avoid error out in case of undefined symbols
 ifneq ($(KBUILD_MODPOST_WARN)$(filter-out $(existing-input-symdump), $(input-symdump)),)
 MODPOST += -w
@@ -127,9 +122,9 @@ endif
 # 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$$/$(mod-prelink-ext)\.o/' $< | $(MODPOST) -T -
+      cmd_modpost = sed 's/ko$$/o/' $< | $(MODPOST) -T -
 
-$(output-symdump): $(MODORDER) $(input-symdump) $(modules:.ko=$(mod-prelink-ext).o) FORCE
+$(output-symdump): $(MODORDER) $(input-symdump) FORCE
 	$(call if_changed,modpost)
 
 targets += $(output-symdump)
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index b70a31b4245a..e74224a6a8e8 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1903,10 +1903,6 @@ static char *remove_dot(char *s)
 		size_t m = strspn(s + n + 1, "0123456789");
 		if (m && (s[n + m + 1] == '.' || s[n + m + 1] == 0))
 			s[n] = 0;
-
-		/* strip trailing .prelink */
-		if (strends(s, ".prelink"))
-			s[strlen(s) - 8] = '\0';
 	}
 	return s;
 }
@@ -2028,9 +2024,6 @@ static void read_symbols(const char *modname)
 		/* strip trailing .o */
 		tmp = NOFAIL(strdup(modname));
 		tmp[strlen(tmp) - 2] = '\0';
-		/* strip trailing .prelink */
-		if (strends(tmp, ".prelink"))
-			tmp[strlen(tmp) - 8] = '\0';
 		mod = new_module(tmp);
 		free(tmp);
 	}
-- 
2.32.0