kbuild: re-implement CONFIG_TRIM_UNUSED_KSYMS to make it work in one-…

…pass

Commit a555bdd ("Kbuild: enable TRIM_UNUSED_KSYMS again, with some
guarding") re-enabled this feature, but Linus is still unhappy about
the build time.

The reason of the slowness is the recursion - this basically works in
two loops.

In the first loop, Kbuild builds the entire tree based on the temporary
autoksyms.h, which contains macro defines to control whether their
corresponding EXPORT_SYMBOL() is enabled or not, and also gathers all
symbols required by modules. After the tree traverse, Kbuild updates
autoksyms.h and triggers the second loop to rebuild source files whose
EXPORT_SYMBOL() needs flipping.

This commit re-implements CONFIG_TRIM_UNUSED_KSYMS to make it work in
one pass. In the new design, unneeded EXPORT_SYMBOL() instances are
trimmed by the linker instead of the preprocessor.

After the tree traverse, a linker script snippet <generated/keep-ksyms.h>
is generated. It feeds the list of necessary sections to vmlinus.lds.S
and modules.lds.S. The other sections fall into /DISCARD/.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>

Makefile

@@ -1162,29 +1162,23 @@ export KBUILD_LDS          := arch/$(SRCARCH)/kernel/vmlinux.lds
 # used by scripts/Makefile.package
 export KBUILD_ALLDIRS := $(sort $(filter-out arch/%,$(vmlinux-alldirs)) LICENSES arch include scripts tools)
 
-vmlinux-deps := $(KBUILD_LDS) $(KBUILD_VMLINUX_OBJS) $(KBUILD_VMLINUX_LIBS)
+targets :=
 
-# Recurse until adjust_autoksyms.sh is satisfied
-PHONY += autoksyms_recursive
 ifdef CONFIG_TRIM_UNUSED_KSYMS
 # For the kernel to actually contain only the needed exported symbols,
 # we have to build modules as well to determine what those symbols are.
 # (this can be evaluated only once include/config/auto.conf has been included)
 KBUILD_MODULES := 1
 
-autoksyms_recursive: descend modules.order
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/adjust_autoksyms.sh \
-	  "$(MAKE) -f $(srctree)/Makefile vmlinux"
-endif
-
-autoksyms_h := $(if $(CONFIG_TRIM_UNUSED_KSYMS), include/generated/autoksyms.h)
+quiet_cmd_gen_used_ksyms = GEN     $@
+      cmd_gen_used_ksyms = $(CONFIG_SHELL) $(srctree)/scripts/gen-keep-ksyms.sh $< > $@
 
-quiet_cmd_autoksyms_h = GEN     $@
-      cmd_autoksyms_h = mkdir -p $(dir $@); \
-			$(CONFIG_SHELL) $(srctree)/scripts/gen_autoksyms.sh $@
+include/generated/keep-ksyms.h: modules.order FORCE
+	$(call if_changed,gen_used_ksyms)
+targets += include/generated/keep-ksyms.h
 
-$(autoksyms_h):
-	$(call cmd,autoksyms_h)
+$(KBUILD_LDS) modules_prepare: include/generated/keep-ksyms.h
+endif
 
 $(KBUILD_LDS): prepare FORCE
 	$(Q)$(MAKE) $(build)=$(patsubst %/,%,$(dir $@)) $@
@@ -1196,11 +1190,11 @@ cmd_link-vmlinux =                                                 \
 	$(CONFIG_SHELL) $< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)";    \
 	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
 
-vmlinux: scripts/link-vmlinux.sh autoksyms_recursive $(KBUILD_LDS) \
+vmlinux: scripts/link-vmlinux.sh $(KBUILD_LDS) \
 			$(KBUILD_VMLINUX_OBJS) $(KBUILD_VMLINUX_LIBS) FORCE
 	+$(call if_changed,link-vmlinux)
 
-targets := vmlinux
+targets += vmlinux
 
 # The actual objects are generated when descending,
 # make sure no implicit rule kicks in
@@ -1229,7 +1223,7 @@ scripts: scripts_basic scripts_dtc
 PHONY += prepare archprepare
 
 archprepare: outputmakefile archheaders archscripts scripts include/config/kernel.release \
-	asm-generic $(version_h) $(autoksyms_h) include/generated/utsrelease.h \
+	asm-generic $(version_h) include/generated/utsrelease.h \
 	include/generated/autoconf.h
 
 prepare0: archprepare
@@ -1515,7 +1509,7 @@ endif # CONFIG_MODULES
 # make distclean Remove editor backup files, patch leftover files and the like
 
 # Directories & files removed with 'make clean'
-CLEAN_FILES += include/ksym vmlinux.symvers \
+CLEAN_FILES += vmlinux.symvers \
 	       modules.builtin modules.builtin.modinfo modules.nsdeps \
 	       compile_commands.json .thinlto-cache
 

arch/arm64/kvm/hyp/nvhe/hyp.lds.S

@@ -6,6 +6,7 @@
  * Linker script used for partial linking of nVHE EL2 object files.
  */
 
+#define NO_TRIM_KSYMS
 #include <asm/hyp_image.h>
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>

arch/powerpc/kernel/vdso32/vdso32.lds.S

@@ -3,6 +3,7 @@
  * This is the infamous ld script for the 32 bits vdso
  * library
  */
+#define NO_TRIM_KSYMS
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>

arch/powerpc/kernel/vdso64/vdso64.lds.S

@@ -3,6 +3,7 @@
  * This is the infamous ld script for the 64 bits vdso
  * library
  */
+#define NO_TRIM_KSYMS
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>

arch/s390/purgatory/purgatory.lds.S

@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
+#define NO_TRIM_KSYMS
 #include <asm-generic/vmlinux.lds.h>
 
 OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")

include/asm-generic/export.h

@@ -57,30 +57,7 @@ __kstrtab_\name:
 #endif
 .endm
 
-#if defined(CONFIG_TRIM_UNUSED_KSYMS)
-
-#include <linux/kconfig.h>
-#include <generated/autoksyms.h>
-
-.macro __ksym_marker sym
-	.section ".discard.ksym","a"
-__ksym_marker_\sym:
-	 .previous
-.endm
-
-#define __EXPORT_SYMBOL(sym, val, sec)				\
-	__ksym_marker sym;					\
-	__cond_export_sym(sym, val, sec, __is_defined(__KSYM_##sym))
-#define __cond_export_sym(sym, val, sec, conf)			\
-	___cond_export_sym(sym, val, sec, conf)
-#define ___cond_export_sym(sym, val, sec, enabled)		\
-	__cond_export_sym_##enabled(sym, val, sec)
-#define __cond_export_sym_1(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
-#define __cond_export_sym_0(sym, val, sec) /* nothing */
-
-#else
 #define __EXPORT_SYMBOL(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
-#endif
 
 #define EXPORT_SYMBOL(name)					\
 	__EXPORT_SYMBOL(name, KSYM_FUNC(name),)

include/asm-generic/vmlinux.lds.h

@@ -50,6 +50,8 @@
  *               [__nosave_begin, __nosave_end] for the nosave data
  */
 
+#include <linux/ksyms.lds.h>
+
 #ifndef LOAD_OFFSET
 #define LOAD_OFFSET 0
 #endif
@@ -486,34 +488,34 @@
 	/* Kernel symbol table: Normal symbols */			\
 	__ksymtab         : AT(ADDR(__ksymtab) - LOAD_OFFSET) {		\
 		__start___ksymtab = .;					\
-		KEEP(*(SORT(___ksymtab+*)))				\
+		KSYMTAB							\
 		__stop___ksymtab = .;					\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__ksymtab_gpl     : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) {	\
 		__start___ksymtab_gpl = .;				\
-		KEEP(*(SORT(___ksymtab_gpl+*)))				\
+		KSYMTAB_GPL						\
 		__stop___ksymtab_gpl = .;				\
 	}								\
 									\
 	/* Kernel symbol table: Normal symbols */			\
 	__kcrctab         : AT(ADDR(__kcrctab) - LOAD_OFFSET) {		\
 		__start___kcrctab = .;					\
-		KEEP(*(SORT(___kcrctab+*)))				\
+		KCRCTAB							\
 		__stop___kcrctab = .;					\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__kcrctab_gpl     : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) {	\
 		__start___kcrctab_gpl = .;				\
-		KEEP(*(SORT(___kcrctab_gpl+*)))				\
+		KCRCTAB_GPL						\
 		__stop___kcrctab_gpl = .;				\
 	}								\
 									\
 	/* Kernel symbol table: strings */				\
         __ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) {	\
-		*(__ksymtab_strings+*)					\
+		KSYMTAB_STRINGS						\
 	}								\
 									\
 	/* __*init sections */						\
@@ -999,6 +1001,7 @@
 	/DISCARD/ : {							\
 	EXIT_DISCARDS							\
 	EXIT_CALL							\
+	KSYM_DISCARDS							\
 	COMMON_DISCARDS							\
 	}
 

include/linux/export.h

@@ -76,9 +76,18 @@ struct kernel_symbol {
 };
 #endif
 
-#ifdef __GENKSYMS__
+#if !defined(CONFIG_MODULES) || defined(__DISABLE_EXPORTS)
+
+/*
+ * Allow symbol exports to be disabled completely so that C code may
+ * be reused in other execution contexts such as the UEFI stub or the
+ * decompressor.
+ */
+#define __EXPORT_SYMBOL(sym, sec, ns)
+
+#elif defined(__GENKSYMS__)
 
-#define ___EXPORT_SYMBOL(sym, sec, ns)	__GENKSYMS_EXPORT_SYMBOL(sym)
+#define __EXPORT_SYMBOL(sym, sec, ns)	__GENKSYMS_EXPORT_SYMBOL(sym)
 
 #else
 
@@ -94,7 +103,7 @@ struct kernel_symbol {
  * section flag requires it. Use '%progbits' instead of '@progbits' since the
  * former apparently works on all arches according to the binutils source.
  */
-#define ___EXPORT_SYMBOL(sym, sec, ns)						\
+#define __EXPORT_SYMBOL(sym, sec, ns)						\
 	extern typeof(sym) sym;							\
 	extern const char __kstrtab_##sym[];					\
 	extern const char __kstrtabns_##sym[];					\
@@ -107,45 +116,6 @@ struct kernel_symbol {
 	    "	.previous						\n");	\
 	__KSYMTAB_ENTRY(sym, sec)
 
-#endif
-
-#if !defined(CONFIG_MODULES) || defined(__DISABLE_EXPORTS)
-
-/*
- * Allow symbol exports to be disabled completely so that C code may
- * be reused in other execution contexts such as the UEFI stub or the
- * decompressor.
- */
-#define __EXPORT_SYMBOL(sym, sec, ns)
-
-#elif defined(CONFIG_TRIM_UNUSED_KSYMS)
-
-#include <generated/autoksyms.h>
-
-/*
- * For fine grained build dependencies, we want to tell the build system
- * about each possible exported symbol even if they're not actually exported.
- * We use a symbol pattern __ksym_marker_<symbol> that the build system filters
- * from the $(NM) output (see scripts/gen_ksymdeps.sh). These symbols are
- * discarded in the final link stage.
- */
-#define __ksym_marker(sym)	\
-	static int __ksym_marker_##sym[0] __section(".discard.ksym") __used
-
-#define __EXPORT_SYMBOL(sym, sec, ns)					\
-	__ksym_marker(sym);						\
-	__cond_export_sym(sym, sec, ns, __is_defined(__KSYM_##sym))
-#define __cond_export_sym(sym, sec, ns, conf)				\
-	___cond_export_sym(sym, sec, ns, conf)
-#define ___cond_export_sym(sym, sec, ns, enabled)			\
-	__cond_export_sym_##enabled(sym, sec, ns)
-#define __cond_export_sym_1(sym, sec, ns) ___EXPORT_SYMBOL(sym, sec, ns)
-#define __cond_export_sym_0(sym, sec, ns) /* nothing */
-
-#else
-
-#define __EXPORT_SYMBOL(sym, sec, ns)	___EXPORT_SYMBOL(sym, sec, ns)
-
 #endif /* CONFIG_MODULES */
 
 #ifdef DEFAULT_SYMBOL_NAMESPACE

include/linux/ksyms.lds.h

@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __KSYMS_LDS_H
+#define __KSYMS_LDS_H
+
+#if defined(CONFIG_TRIM_UNUSED_KSYMS) && !defined(NO_TRIM_KSYMS)
+#include <generated/keep-ksyms.h>
+
+#define KSYM_DISCARDS		*(___ksymtab+*) \
+				*(___ksymtab_gpl+*) \
+				*(___kcrctab+*) \
+				*(___kcrctab_gpl+*) \
+				*(__ksymtab_strings+*)
+#else
+#define KSYMTAB			KEEP(*(SORT(___ksymtab+*)))
+#define KSYMTAB_GPL		KEEP(*(SORT(___ksymtab_gpl+*)))
+#define KCRCTAB			KEEP(*(SORT(___kcrctab+*)))
+#define KCRCTAB_GPL		KEEP(*(SORT(___kcrctab_gpl+*)))
+#define KSYMTAB_STRINGS		*(__ksymtab_strings+*)
+#define KSYM_DISCARDS
+#endif
+
+#endif /* __KSYMS_LDS_H */

scripts/Makefile.build

@@ -244,16 +244,12 @@ objtool_dep = $(objtool_obj)					\
 			 include/config/stack/validation.h)
 
 ifdef CONFIG_TRIM_UNUSED_KSYMS
-cmd_gen_ksymdeps = \
-	$(CONFIG_SHELL) $(srctree)/scripts/gen_ksymdeps.sh $@ >> $(dot-target).cmd
-
 # List module undefined symbols
 undefined_syms = $(NM) $< | $(AWK) '$$1 == "U" { printf("%s%s", x++ ? " " : "", $$2) }';
 endif
 
 define rule_cc_o_c
 	$(call cmd_and_fixdep,cc_o_c)
-	$(call cmd,gen_ksymdeps)
 	$(call cmd,checksrc)
 	$(call cmd,checkdoc)
 	$(call cmd,objtool)
@@ -263,7 +259,6 @@ endef
 
 define rule_as_o_S
 	$(call cmd_and_fixdep,as_o_S)
-	$(call cmd,gen_ksymdeps)
 	$(call cmd,objtool)
 	$(call cmd,modversions_S)
 endef

scripts/Makefile.lib

@@ -311,6 +311,7 @@ DTC_FLAGS += $(DTC_FLAGS_$(basetarget))
 quiet_cmd_dt_S_dtb= DTB     $@
 cmd_dt_S_dtb=						\
 {							\
+	echo '\#define NO_TRIM_KSYMS';			\
 	echo '\#include <asm-generic/vmlinux.lds.h>'; 	\
 	echo '.section .dtb.init.rodata,"a"';		\
 	echo '.balign STRUCT_ALIGNMENT';		\