@@ -191,7 +191,5 @@ CFLAGS_font.o := -Dstatic=
 $(obj)/font.c: $(FONTC)
 	$(call cmd,shipped)
 
-AFLAGS_hyp-stub.o := -Wa,-march=armv7-a
-
 $(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S
 	$(call cmd,shipped)

@@ -14,7 +14,5 @@ obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_CPU_V7)		+= secure_cntvoff.o
 obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
 CFLAGS_REMOVE_mcpm_entry.o	= -pg
-AFLAGS_mcpm_head.o		:= -march=armv7-a
-AFLAGS_vlock.o			:= -march=armv7-a
 obj-$(CONFIG_BL_SWITCHER)	+= bL_switcher.o
 obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o

@@ -15,6 +15,8 @@
 
 #include "vlock.h"
 
+.arch armv7-a
+
 .if MCPM_SYNC_CLUSTER_CPUS
 .error "cpus must be the first member of struct mcpm_sync_struct"
 .endif

@@ -12,6 +12,8 @@
 #include <linux/linkage.h>
 #include "vlock.h"
 
+.arch armv7-a
+
 /* Select different code if voting flags  can fit in a single word. */
 #if VLOCK_VOTING_SIZE > 4
 #define FEW(x...)

@@ -70,7 +70,6 @@ obj-$(CONFIG_HAVE_TCM)		+= tcm.o
 obj-$(CONFIG_OF)		+= devtree.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_SWP_EMULATE)	+= swp_emulate.o
-CFLAGS_swp_emulate.o		:= -Wa,-march=armv7-a
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 
 obj-$(CONFIG_CPU_XSCALE)	+= xscale-cp0.o

@@ -99,7 +98,6 @@ CFLAGS_head-inflate-data.o := $(call cc-option,-Wframe-larger-than=10240)
 obj-$(CONFIG_XIP_DEFLATED_DATA) += head-inflate-data.o
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
-AFLAGS_hyp-stub.o		:=-Wa,-march=armv7-a
 ifeq ($(CONFIG_ARM_PSCI),y)
 obj-$(CONFIG_SMP)		+= psci_smp.o
 endif

@@ -9,6 +9,8 @@
 #include <asm/assembler.h>
 #include <asm/virt.h>
 
+.arch armv7-a
+
 #ifndef ZIMAGE
 /*
  * For the kernel proper, we need to find out the CPU boot mode long after

@@ -34,6 +34,7 @@
  */
 #define __user_swpX_asm(data, addr, res, temp, B)		\
 	__asm__ __volatile__(					\
+	".arch armv7-a\n"					\
 	"0:	ldrex"B"	%2, [%3]\n"			\
 	"1:	strex"B"	%0, %1, [%3]\n"			\
 	"	cmp		%0, #0\n"			\

@@ -36,10 +36,6 @@ else
   lib-y	+= io-readsw-armv4.o io-writesw-armv4.o
 endif
 
-ifeq ($(CONFIG_ARCH_RPC),y)
-  AFLAGS_delay-loop.o		+= -march=armv4
-endif
-
 $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
 

@@ -8,6 +8,10 @@
 #include <asm/assembler.h>
 #include <asm/delay.h>
 
+#ifdef CONFIG_ARCH_RPC
+		.arch	armv4
+#endif
+
 		.text
 
 .LC0:		.word	loops_per_jiffy

@@ -14,9 +14,6 @@ obj-$(CONFIG_SOC_SAMV7)		+= samv7.o
 # Power Management
 obj-$(CONFIG_ATMEL_PM)		+= pm.o pm_suspend.o
 
-ifeq ($(CONFIG_CPU_V7),y)
-AFLAGS_pm_suspend.o := -march=armv7-a
-endif
 ifeq ($(CONFIG_PM_DEBUG),y)
 CFLAGS_pm.o += -DDEBUG
 endif

@@ -12,6 +12,10 @@
 #include "pm.h"
 #include "pm_data-offsets.h"
 
+#ifdef CONFIG_CPU_V7
+.arch armv7-a
+#endif
+
 #define	SRAMC_SELF_FRESH_ACTIVE		0x01
 #define	SRAMC_SELF_FRESH_EXIT		0x00
 

@@ -36,7 +36,6 @@ obj-$(CONFIG_HAVE_IMX_GPC) += gpc.o
 obj-$(CONFIG_HAVE_IMX_MMDC) += mmdc.o
 obj-$(CONFIG_HAVE_IMX_SRC) += src.o
 ifneq ($(CONFIG_SOC_IMX6)$(CONFIG_SOC_IMX7D_CA7)$(CONFIG_SOC_LS1021A),)
-AFLAGS_headsmp.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SMP) += headsmp.o platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o
 endif

@@ -50,12 +49,10 @@ obj-$(CONFIG_SOC_IMX7D_CM4) += mach-imx7d-cm4.o
 obj-$(CONFIG_SOC_IMX7ULP) += mach-imx7ulp.o pm-imx7ulp.o
 
 ifeq ($(CONFIG_SUSPEND),y)
-AFLAGS_suspend-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o
 obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o
 endif
 ifeq ($(CONFIG_ARM_CPU_SUSPEND),y)
-AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += resume-imx6.o
 endif
 obj-$(CONFIG_SOC_IMX6) += pm-imx6.o

@@ -8,6 +8,8 @@
 #include <linux/init.h>
 #include <asm/assembler.h>
 
+.arch armv7-a
+
 diag_reg_offset:
 	.word	g_diag_reg - .
 

@@ -9,6 +9,8 @@
 #include <asm/hardware/cache-l2x0.h>
 #include "hardware.h"
 
+.arch armv7-a
+
 /*
  * The following code must assume it is running from physical address
  * where absolute virtual addresses to the data section have to be

@@ -9,6 +9,8 @@
 #include <asm/hardware/cache-l2x0.h>
 #include "hardware.h"
 
+.arch armv7-a
+
 /*
  * ==================== low level suspend ====================
  *

@@ -1,9 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-orion/include
 
-AFLAGS_coherency_ll.o		:= -Wa,-march=armv7-a
-CFLAGS_pmsu.o			:= -march=armv7-a
-
 obj-$(CONFIG_MACH_MVEBU_ANY)	 += system-controller.o mvebu-soc-id.o
 
 ifeq ($(CONFIG_MACH_MVEBU_V7),y)

@@ -23,6 +23,7 @@
 #include <asm/assembler.h>
 #include <asm/cp15.h>
 
+	.arch armv7-a
 	.text
 /*
  * Returns the coherency base address in r1 (r0 is untouched), or 0 if

@@ -294,6 +294,7 @@ int armada_370_xp_pmsu_idle_enter(unsigned long deepidle)
 
 	/* Test the CR_C bit and set it if it was cleared */
 	asm volatile(
+	".arch	armv7-a\n\t"
 	"mrc	p15, 0, r0, c1, c0, 0 \n\t"
 	"tst	r0, %0 \n\t"
 	"orreq	r0, r0, #(1 << 2) \n\t"

@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-AFLAGS_headsmp.o		+= -march=armv7-a
-
 obj-$(CONFIG_ARCH_WPCM450)	+= wpcm450.o
 obj-$(CONFIG_ARCH_NPCM7XX)	+= npcm7xx.o
 obj-$(CONFIG_SMP)		+= platsmp.o headsmp.o

@@ -6,6 +6,8 @@
 #include <linux/init.h>
 #include <asm/assembler.h>
 
+.arch armv7-a
+
 /*
  * The boot ROM does not start secondary CPUs in SVC mode, so we need to do that
  * here.

@@ -33,9 +33,6 @@ obj-$(CONFIG_CPU_ABRT_EV5TJ)	+= abort-ev5tj.o
 obj-$(CONFIG_CPU_ABRT_EV6)	+= abort-ev6.o
 obj-$(CONFIG_CPU_ABRT_EV7)	+= abort-ev7.o
 
-AFLAGS_abort-ev6.o	:=-Wa,-march=armv6k
-AFLAGS_abort-ev7.o	:=-Wa,-march=armv7-a
-
 obj-$(CONFIG_CPU_PABRT_LEGACY)	+= pabort-legacy.o
 obj-$(CONFIG_CPU_PABRT_V6)	+= pabort-v6.o
 obj-$(CONFIG_CPU_PABRT_V7)	+= pabort-v7.o

@@ -49,10 +46,6 @@ obj-$(CONFIG_CPU_CACHE_FA)	+= cache-fa.o
 obj-$(CONFIG_CPU_CACHE_NOP)	+= cache-nop.o
 obj-$(CONFIG_CPU_CACHE_V7M)	+= cache-v7m.o
 
-AFLAGS_cache-v6.o	:=-Wa,-march=armv6
-AFLAGS_cache-v7.o	:=-Wa,-march=armv7-a
-AFLAGS_cache-v7m.o	:=-Wa,-march=armv7-m
-
 obj-$(CONFIG_CPU_COPY_V4WT)	+= copypage-v4wt.o
 obj-$(CONFIG_CPU_COPY_V4WB)	+= copypage-v4wb.o
 obj-$(CONFIG_CPU_COPY_FEROCEON)	+= copypage-feroceon.o

@@ -62,8 +55,6 @@ obj-$(CONFIG_CPU_XSCALE)	+= copypage-xscale.o
 obj-$(CONFIG_CPU_XSC3)		+= copypage-xsc3.o
 obj-$(CONFIG_CPU_COPY_FA)	+= copypage-fa.o
 
-CFLAGS_copypage-feroceon.o := -march=armv5te
-
 obj-$(CONFIG_CPU_TLB_V4WT)	+= tlb-v4.o
 obj-$(CONFIG_CPU_TLB_V4WB)	+= tlb-v4wb.o
 obj-$(CONFIG_CPU_TLB_V4WBI)	+= tlb-v4wbi.o

@@ -72,9 +63,6 @@ obj-$(CONFIG_CPU_TLB_V6)	+= tlb-v6.o
 obj-$(CONFIG_CPU_TLB_V7)	+= tlb-v7.o
 obj-$(CONFIG_CPU_TLB_FA)	+= tlb-fa.o
 
-AFLAGS_tlb-v6.o		:=-Wa,-march=armv6
-AFLAGS_tlb-v7.o		:=-Wa,-march=armv7-a
-
 obj-$(CONFIG_CPU_ARM7TDMI)	+= proc-arm7tdmi.o
 obj-$(CONFIG_CPU_ARM720T)	+= proc-arm720.o
 obj-$(CONFIG_CPU_ARM740T)	+= proc-arm740.o

@@ -101,9 +89,6 @@ obj-$(CONFIG_CPU_V6K)		+= proc-v6.o
 obj-$(CONFIG_CPU_V7)		+= proc-v7.o proc-v7-bugs.o
 obj-$(CONFIG_CPU_V7M)		+= proc-v7m.o
 
-AFLAGS_proc-v6.o	:=-Wa,-march=armv6
-AFLAGS_proc-v7.o	:=-Wa,-march=armv7-a
-
 obj-$(CONFIG_OUTER_CACHE)	+= l2c-common.o
 obj-$(CONFIG_CACHE_B15_RAC)	+= cache-b15-rac.o
 obj-$(CONFIG_CACHE_FEROCEON_L2)	+= cache-feroceon-l2.o

@@ -16,6 +16,7 @@
  * abort here if the I-TLB and D-TLB aren't seeing the same
  * picture.  Unfortunately, this does happen.  We live with it.
  */
+	.arch	armv6k
 	.align	5
 ENTRY(v6_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR

@@ -12,6 +12,7 @@
  *
  * Purpose : obtain information about current aborted instruction.
  */
+	.arch	armv7-a
 	.align	5
 ENTRY(v7_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR

@@ -19,6 +19,8 @@
 #define D_CACHE_LINE_SIZE	32
 #define BTB_FLUSH_SIZE		8
 
+.arch armv6
+
 /*
  *	v6_flush_icache_all()
  *

@@ -16,6 +16,8 @@
 
 #include "proc-macros.S"
 
+.arch armv7-a
+
 #ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
 .globl icache_size
 	.data

@@ -18,6 +18,8 @@
 
 #include "proc-macros.S"
 
+.arch armv7-m
+
 /* Generic V7M read/write macros for memory mapped cache operations */
 .macro v7m_cache_read, rt, reg
 	movw	\rt, #:lower16:BASEADDR_V7M_SCB + \reg

@@ -15,6 +15,7 @@ static void feroceon_copy_user_page(void *kto, const void *kfrom)
 	int tmp;
 
 	asm volatile ("\
+.arch	armv5te					\n\
 1:	ldmia	%1!, {r2 - r7, ip, lr}		\n\
 	pld	[%1, #0]			\n\
 	pld	[%1, #32]			\n\

@@ -32,6 +32,8 @@
 #define TTB_FLAGS_SMP	TTB_RGN_WBWA|TTB_S
 #define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
 
+.arch armv6
+
 ENTRY(cpu_v6_proc_init)
 	ret	lr
 

@@ -24,6 +24,8 @@
 #define TTB_FLAGS_SMP	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
 #define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
 
+.arch armv7-a
+
 /*
  *	cpu_v7_switch_mm(pgd_phys, tsk)
  *

@@ -24,6 +24,8 @@
 #include "proc-v7-2level.S"
 #endif
 
+.arch armv7-a
+
 ENTRY(cpu_v7_proc_init)
 	ret	lr
 ENDPROC(cpu_v7_proc_init)

@@ -17,6 +17,8 @@
 
 #define HARVARD_TLB
 
+.arch armv6
+
 /*
  *	v6wbi_flush_user_tlb_range(start, end, vma)
  *

@@ -16,6 +16,8 @@
 #include <asm/tlbflush.h>
 #include "proc-macros.S"
 
+.arch armv7-a
+
 /*
  *	v7wbi_flush_user_tlb_range(start, end, vma)
  *

@@ -32,8 +32,6 @@ obj-$(CONFIG_FPGA_DFL_EMIF)	+= dfl-emif.o
 
 ti-emif-sram-objs		:= ti-emif-pm.o ti-emif-sram-pm.o
 
-AFLAGS_ti-emif-sram-pm.o	:=-Wa,-march=armv7-a
-
 $(obj)/ti-emif-sram-pm.o: $(obj)/ti-emif-asm-offsets.h
 
 $(obj)/ti-emif-asm-offsets.h: $(obj)/emif-asm-offsets.s FORCE

@@ -36,6 +36,7 @@
 
 	.arm
 	.align 3
+	.arch armv7-a
 
 ENTRY(ti_emif_sram)