arch: Introduce CONFIG_FUNCTION_ALIGNMENT

Generic function-alignment infrastructure.

Architectures can select FUNCTION_ALIGNMENT_xxB symbols; the
FUNCTION_ALIGNMENT symbol is then set to the largest such selected
size, 0 otherwise.

From this the -falign-functions compiler argument and __ALIGN macro
are set.

This incorporates the DEBUG_FORCE_FUNCTION_ALIGN_64B knob and future
alignment requirements for x86_64 (later in this series) into a single
place.

NOTE: also removes the 0x90 filler byte from the generic __ALIGN
primitive, that value makes no sense outside of x86.

NOTE: .balign 0 reverts to a no-op.

Requested-by: Linus Torvalds <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

Makefile

···
 export CC_FLAGS_CFI
 endif
 
-ifdef CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B
-KBUILD_CFLAGS += -falign-functions=64
+ifneq ($(CONFIG_FUNCTION_ALIGNMENT),0)
+KBUILD_CFLAGS += -falign-functions=$(CONFIG_FUNCTION_ALIGNMENT)
 endif
 
 # arch Makefile may override CC so keep this after arch Makefile is included

arch/Kconfig

···
 
 source "scripts/gcc-plugins/Kconfig"
 
+config FUNCTION_ALIGNMENT_4B
+	bool
+
+config FUNCTION_ALIGNMENT_8B
+	bool
+
+config FUNCTION_ALIGNMENT_16B
+	bool
+
+config FUNCTION_ALIGNMENT_32B
+	bool
+
+config FUNCTION_ALIGNMENT_64B
+	bool
+
+config FUNCTION_ALIGNMENT
+	int
+	default 64 if FUNCTION_ALIGNMENT_64B
+	default 32 if FUNCTION_ALIGNMENT_32B
+	default 16 if FUNCTION_ALIGNMENT_16B
+	default 8 if FUNCTION_ALIGNMENT_8B
+	default 4 if FUNCTION_ALIGNMENT_4B
+	default 0
+
 endmenu

arch/ia64/Kconfig

···
 	select NUMA if !FLATMEM
 	select PCI_MSI_ARCH_FALLBACKS if PCI_MSI
 	select ZONE_DMA32
+	select FUNCTION_ALIGNMENT_32B
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to

arch/ia64/Makefile

···
 EXTRA		:=
 
 cflags-y	:= -pipe $(EXTRA) -ffixed-r13 -mfixed-range=f12-f15,f32-f127 \
-		   -falign-functions=32 -frename-registers -fno-optimize-sibling-calls
+		   -frename-registers -fno-optimize-sibling-calls
 KBUILD_CFLAGS_KERNEL := -mconstant-gp
 
 GAS_STATUS	= $(shell $(srctree)/arch/ia64/scripts/check-gas "$(CC)" "$(OBJDUMP)")

arch/x86/Kconfig

···
 	select X86_FEATURE_NAMES		if PROC_FS
 	select PROC_PID_ARCH_STATUS		if PROC_FS
 	select HAVE_ARCH_NODE_DEV_GROUP		if X86_SGX
+	select FUNCTION_ALIGNMENT_16B		if X86_64 || X86_ALIGNMENT_16
+	select FUNCTION_ALIGNMENT_4B
 	imply IMA_SECURE_AND_OR_TRUSTED_BOOT    if EFI
 	select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
 

arch/x86/boot/compressed/head_64.S

···
 #include "pgtable.h"
 
 /*
+ * Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result
+ * in assembly errors due to trying to move .org backward due to the excessive
+ * alignment.
+ */
+#undef __ALIGN
+#define __ALIGN		.balign	16, 0x90
+
+/*
  * Locally defined symbols should be marked hidden:
  */
 	.hidden _bss

arch/x86/include/asm/linkage.h

···
 
 #ifdef __ASSEMBLY__
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16)
-#define __ALIGN		.p2align 4, 0x90
+#define __ALIGN		.balign CONFIG_FUNCTION_ALIGNMENT, 0x90;
 #define __ALIGN_STR	__stringify(__ALIGN)
-#endif
 
 #if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
 #define RET	jmp __x86_return_thunk

include/asm-generic/vmlinux.lds.h

···
 #define RO_EXCEPTION_TABLE
 #endif
 
-/* Align . to a 8 byte boundary equals to maximum function alignment. */
-#define ALIGN_FUNCTION()  . = ALIGN(8)
+/* Align . function alignment. */
+#define ALIGN_FUNCTION()  . = ALIGN(CONFIG_FUNCTION_ALIGNMENT)
 
 /*
  * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which

include/linux/linkage.h

···
 #endif
 
 #ifndef __ALIGN
-#define __ALIGN		.align 4,0x90
-#define __ALIGN_STR	".align 4,0x90"
+#define __ALIGN			.balign CONFIG_FUNCTION_ALIGNMENT
+#define __ALIGN_STR		__stringify(__ALIGN)
 #endif
 
 #ifdef __ASSEMBLY__

lib/Kconfig.debug

···
 config DEBUG_FORCE_FUNCTION_ALIGN_64B
 	bool "Force all function address 64B aligned"
 	depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC)
+	select FUNCTION_ALIGNMENT_64B
 	help
 	  There are cases that a commit from one domain changes the function
 	  address alignment of other domains, and cause magic performance