kbuild: allow archs to select link dead code/data elimination

Introduce LD_DEAD_CODE_DATA_ELIMINATION option for architectures to
select to build with -ffunction-sections, -fdata-sections, and link
with --gc-sections. It requires some work (documented) to ensure all
unreferenced entrypoints are live, and requires toolchain and build
verification, so it is made a per-arch option for now.

On a random powerpc64le build, this yelds a significant size saving,
it boots and runs fine, but there is a lot I haven't tested as yet, so
these savings may be reduced if there are bugs in the link.

    text      data        bss        dec   filename
11169741   1180744    1923176	14273661   vmlinux
10445269   1004127    1919707	13369103   vmlinux.dce

~700K text, ~170K data, 6% removed from kernel image size.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michal Marek <mmarek@suse.com>

Makefile

@@ -622,6 +622,11 @@ include arch/$(SRCARCH)/Makefile
 KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
 KBUILD_CFLAGS	+= $(call cc-disable-warning,maybe-uninitialized,)
 
+ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
+KBUILD_CFLAGS	+= $(call cc-option,-ffunction-sections,)
+KBUILD_CFLAGS	+= $(call cc-option,-fdata-sections,)
+endif
+
 ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 KBUILD_CFLAGS	+= -Os
 else
@@ -809,6 +814,10 @@ LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\
 KBUILD_LDFLAGS_MODULE += $(LDFLAGS_BUILD_ID)
 LDFLAGS_vmlinux += $(LDFLAGS_BUILD_ID)
 
+ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
+LDFLAGS_vmlinux	+= $(call ld-option, --gc-sections,)
+endif
+
 ifeq ($(CONFIG_STRIP_ASM_SYMS),y)
 LDFLAGS_vmlinux	+= $(call ld-option, -X,)
 endif

arch/Kconfig

@@ -467,6 +467,19 @@ config THIN_ARCHIVES
 	  Select this if the architecture wants to use thin archives
 	  instead of ld -r to create the built-in.o files.
 
+config LD_DEAD_CODE_DATA_ELIMINATION
+	bool
+	help
+	  Select this if the architecture wants to do dead code and
+	  data elimination with the linker by compiling with
+	  -ffunction-sections -fdata-sections and linking with
+	  --gc-sections.
+
+	  This requires that the arch annotates or otherwise protects
+	  its external entry points from being discarded. Linker scripts
+	  must also merge .text.*, .data.*, and .bss.* correctly into
+	  output sections.
+
 config HAVE_CONTEXT_TRACKING
 	bool
 	help

include/asm-generic/vmlinux.lds.h

@@ -196,9 +196,14 @@
 	*(.dtb.init.rodata)						\
 	VMLINUX_SYMBOL(__dtb_end) = .;
 
-/* .data section */
+/*
+ * .data section
+ * -fdata-sections generates .data.identifier which needs to be pulled in
+ * with .data, but don't want to pull in .data..stuff which has its own
+ * requirements. Same for bss.
+ */
 #define DATA_DATA							\
-	*(.data)							\
+	*(.data .data.[0-9a-zA-Z_]*)					\
 	*(.ref.data)							\
 	*(.data..shared_aligned) /* percpu related */			\
 	MEM_KEEP(init.data)						\
@@ -320,76 +325,76 @@
 	/* Kernel symbol table: Normal symbols */			\
 	__ksymtab         : AT(ADDR(__ksymtab) - LOAD_OFFSET) {		\
 		VMLINUX_SYMBOL(__start___ksymtab) = .;			\
-		*(SORT(___ksymtab+*))					\
+		KEEP(*(SORT(___ksymtab+*)))				\
 		VMLINUX_SYMBOL(__stop___ksymtab) = .;			\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__ksymtab_gpl     : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___ksymtab_gpl) = .;		\
-		*(SORT(___ksymtab_gpl+*))				\
+		KEEP(*(SORT(___ksymtab_gpl+*)))				\
 		VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: Normal unused symbols */		\
 	__ksymtab_unused  : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___ksymtab_unused) = .;		\
-		*(SORT(___ksymtab_unused+*))				\
+		KEEP(*(SORT(___ksymtab_unused+*)))			\
 		VMLINUX_SYMBOL(__stop___ksymtab_unused) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only unused symbols */		\
 	__ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .;	\
-		*(SORT(___ksymtab_unused_gpl+*))			\
+		KEEP(*(SORT(___ksymtab_unused_gpl+*)))			\
 		VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: GPL-future-only symbols */		\
 	__ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .;	\
-		*(SORT(___ksymtab_gpl_future+*))			\
+		KEEP(*(SORT(___ksymtab_gpl_future+*)))			\
 		VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: Normal symbols */			\
 	__kcrctab         : AT(ADDR(__kcrctab) - LOAD_OFFSET) {		\
 		VMLINUX_SYMBOL(__start___kcrctab) = .;			\
-		*(SORT(___kcrctab+*))					\
+		KEEP(*(SORT(___kcrctab+*)))				\
 		VMLINUX_SYMBOL(__stop___kcrctab) = .;			\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only symbols */			\
 	__kcrctab_gpl     : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___kcrctab_gpl) = .;		\
-		*(SORT(___kcrctab_gpl+*))				\
+		KEEP(*(SORT(___kcrctab_gpl+*)))				\
 		VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: Normal unused symbols */		\
 	__kcrctab_unused  : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start___kcrctab_unused) = .;		\
-		*(SORT(___kcrctab_unused+*))				\
+		KEEP(*(SORT(___kcrctab_unused+*)))			\
 		VMLINUX_SYMBOL(__stop___kcrctab_unused) = .;		\
 	}								\
 									\
 	/* Kernel symbol table: GPL-only unused symbols */		\
 	__kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .;	\
-		*(SORT(___kcrctab_unused_gpl+*))			\
+		KEEP(*(SORT(___kcrctab_unused_gpl+*)))			\
 		VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: GPL-future-only symbols */		\
 	__kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .;	\
-		*(SORT(___kcrctab_gpl_future+*))			\
+		KEEP(*(SORT(___kcrctab_gpl_future+*)))			\
 		VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .;	\
 	}								\
 									\
 	/* Kernel symbol table: strings */				\
         __ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) {	\
-		*(__ksymtab_strings)					\
+		KEEP(*(__ksymtab_strings))				\
 	}								\
 									\
 	/* __*init sections */						\
@@ -424,7 +429,7 @@
 #define SECURITY_INIT							\
 	.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
-		*(.security_initcall.init) 				\
+		KEEP(*(.security_initcall.init))			\
 		VMLINUX_SYMBOL(__security_initcall_end) = .;		\
 	}
 
@@ -432,7 +437,7 @@
  * during second ld run in second ld pass when generating System.map */
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
-		*(.text.hot .text .text.fixup .text.unlikely)		\
+		*(.text.hot .text .text.fixup .text.unlikely .text.*)	\
 		*(.ref.text)						\
 	MEM_KEEP(init.text)						\
 	MEM_KEEP(exit.text)						\
@@ -527,6 +532,7 @@
 
 /* init and exit section handling */
 #define INIT_DATA							\
+	KEEP(*(SORT(___kentry+*)))					\
 	*(.init.data)							\
 	MEM_DISCARD(init.data)						\
 	KERNEL_CTORS()							\
@@ -593,7 +599,7 @@
 		BSS_FIRST_SECTIONS					\
 		*(.bss..page_aligned)					\
 		*(.dynbss)						\
-		*(.bss)							\
+		*(.bss .bss.[0-9a-zA-Z_]*)				\
 		*(COMMON)						\
 	}
 
@@ -676,12 +682,12 @@
 
 #define INIT_CALLS_LEVEL(level)						\
 		VMLINUX_SYMBOL(__initcall##level##_start) = .;		\
-		*(.initcall##level##.init)				\
-		*(.initcall##level##s.init)				\
+		KEEP(*(.initcall##level##.init))			\
+		KEEP(*(.initcall##level##s.init))			\
 
 #define INIT_CALLS							\
 		VMLINUX_SYMBOL(__initcall_start) = .;			\
-		*(.initcallearly.init)					\
+		KEEP(*(.initcallearly.init))				\
 		INIT_CALLS_LEVEL(0)					\
 		INIT_CALLS_LEVEL(1)					\
 		INIT_CALLS_LEVEL(2)					\
@@ -695,21 +701,21 @@
 
 #define CON_INITCALL							\
 		VMLINUX_SYMBOL(__con_initcall_start) = .;		\
-		*(.con_initcall.init)					\
+		KEEP(*(.con_initcall.init))				\
 		VMLINUX_SYMBOL(__con_initcall_end) = .;
 
 #define SECURITY_INITCALL						\
 		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
-		*(.security_initcall.init)				\
+		KEEP(*(.security_initcall.init))			\
 		VMLINUX_SYMBOL(__security_initcall_end) = .;
 
 #ifdef CONFIG_BLK_DEV_INITRD
 #define INIT_RAM_FS							\
 	. = ALIGN(4);							\
 	VMLINUX_SYMBOL(__initramfs_start) = .;				\
-	*(.init.ramfs)							\
+	KEEP(*(.init.ramfs))						\
 	. = ALIGN(8);							\
-	*(.init.ramfs.info)
+	KEEP(*(.init.ramfs.info))
 #else
 #define INIT_RAM_FS
 #endif

include/linux/compiler.h

@@ -182,6 +182,29 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 # define unreachable() do { } while (1)
 #endif
 
+/*
+ * KENTRY - kernel entry point
+ * This can be used to annotate symbols (functions or data) that are used
+ * without their linker symbol being referenced explicitly. For example,
+ * interrupt vector handlers, or functions in the kernel image that are found
+ * programatically.
+ *
+ * Not required for symbols exported with EXPORT_SYMBOL, or initcalls. Those
+ * are handled in their own way (with KEEP() in linker scripts).
+ *
+ * KENTRY can be avoided if the symbols in question are marked as KEEP() in the
+ * linker script. For example an architecture could KEEP() its entire
+ * boot/exception vector code rather than annotate each function and data.
+ */
+#ifndef KENTRY
+# define KENTRY(sym)						\
+	extern typeof(sym) sym;					\
+	static const unsigned long __kentry_##sym		\
+	__used							\
+	__attribute__((section("___kentry" "+" #sym ), used))	\
+	= (unsigned long)&sym;
+#endif
+
 #ifndef RELOC_HIDE
 # define RELOC_HIDE(ptr, off)					\
   ({ unsigned long __ptr;					\

include/linux/export.h

 #ifndef _LINUX_EXPORT_H
 #define _LINUX_EXPORT_H
+
 /*
  * Export symbols from the kernel to modules.  Forked from module.h
  * to reduce the amount of pointless cruft we feed to gcc when only
@@ -46,7 +47,7 @@ extern struct module __this_module;
 	extern __visible void *__crc_##sym __attribute__((weak));	\
 	static const unsigned long __kcrctab_##sym			\
 	__used								\
-	__attribute__((section("___kcrctab" sec "+" #sym), unused))	\
+	__attribute__((section("___kcrctab" sec "+" #sym), used))	\
 	= (unsigned long) &__crc_##sym;
 #else
 #define __CRC_SYMBOL(sym, sec)
@@ -59,10 +60,9 @@ extern struct module __this_module;
 	static const char __kstrtab_##sym[]				\
 	__attribute__((section("__ksymtab_strings"), aligned(1)))	\
 	= VMLINUX_SYMBOL_STR(sym);					\
-	extern const struct kernel_symbol __ksymtab_##sym;	\
-	__visible const struct kernel_symbol __ksymtab_##sym	\
+	static const struct kernel_symbol __ksymtab_##sym		\
 	__used								\
-	__attribute__((section("___ksymtab" sec "+" #sym), unused))	\
+	__attribute__((section("___ksymtab" sec "+" #sym), used))	\
 	= { (unsigned long)&sym, __kstrtab_##sym }
 
 #if defined(__KSYM_DEPS__)

include/linux/init.h

@@ -150,24 +150,8 @@ extern bool initcall_debug;
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_LTO
-/* Work around a LTO gcc problem: when there is no reference to a variable
- * in a module it will be moved to the end of the program. This causes
- * reordering of initcalls which the kernel does not like.
- * Add a dummy reference function to avoid this. The function is
- * deleted by the linker.
- */
-#define LTO_REFERENCE_INITCALL(x) \
-	; /* yes this is needed */			\
-	static __used __exit void *reference_##x(void)	\
-	{						\
-		return &x;				\
-	}
-#else
-#define LTO_REFERENCE_INITCALL(x)
-#endif
-
-/* initcalls are now grouped by functionality into separate 
+/*
+ * initcalls are now grouped by functionality into separate
  * subsections. Ordering inside the subsections is determined
  * by link order. 
  * For backwards compatibility, initcall() puts the call in 
@@ -175,12 +159,16 @@ extern bool initcall_debug;
  *
  * The `id' arg to __define_initcall() is needed so that multiple initcalls
  * can point at the same handler without causing duplicate-symbol build errors.
+ *
+ * Initcalls are run by placing pointers in initcall sections that the
+ * kernel iterates at runtime. The linker can do dead code / data elimination
+ * and remove that completely, so the initcall sections have to be marked
+ * as KEEP() in the linker script.
  */
 
 #define __define_initcall(fn, id) \
 	static initcall_t __initcall_##fn##id __used \
-	__attribute__((__section__(".initcall" #id ".init"))) = fn; \
-	LTO_REFERENCE_INITCALL(__initcall_##fn##id)
+	__attribute__((__section__(".initcall" #id ".init"))) = fn;
 
 /*
  * Early initcalls run before initializing SMP.

init/Makefile

@@ -2,6 +2,8 @@
 # Makefile for the linux kernel.
 #
 
+ccflags-y := -fno-function-sections -fno-data-sections
+
 obj-y                          := main.o version.o mounts.o
 ifneq ($(CONFIG_BLK_DEV_INITRD),y)
 obj-y                          += noinitramfs.o