kbuild: do not create *.prelink.o for Clang LTO or IBT

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)       |    (ELF)
                                                             |
                                                 foo.mod.o --/
                                                 (LLVM IR)

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

  One confusion is that 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)     |      (ELF)
                                                  |
                                      foo.mod.o --/
                                      (LLVM IR)

 [2] multi-object module

  Previously, $(AR) was used to combine LLVM IR files 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)     |      (ELF)
    foo2.c ---------> foo2.o ----/                |
                     (LLVM IR)        foo.mod.o --/
                                      (LLVM IR)

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)
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>

1 files changed, 20 insertions, 43 deletions

diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index f80196eef03a..cc7061258e42 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 +148,18 @@ $(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)
+
+# When a module consists of a single object, there is no reason to keep LLVM IR.
+# Make $(LD) covert LLVM IR to ELF here.
+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 +225,7 @@ 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 +234,15 @@ 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 +271,6 @@ $(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 +280,7 @@ $(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 +402,11 @@ $(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)