ARM: 9263/1: use .arch directives instead of assembler command line flags

Similar to commit a6c30873ee4a ("ARM: 8989/1: use .fpu assembler
directives instead of assembler arguments").

GCC and GNU binutils support setting the "sub arch" via -march=,
-Wa,-march, target function attribute, and .arch assembler directive.

Clang was missing support for -Wa,-march=, but this was implemented in
clang-13.

The behavior of both GCC and Clang is to
prefer -Wa,-march= over -march= for assembler and assembler-with-cpp
sources, but Clang will warn about the -march= being unused.

clang: warning: argument unused during compilation: '-march=armv6k'
[-Wunused-command-line-argument]

Since most assembler is non-conditionally assembled with one sub arch
(modulo arch/arm/delay-loop.S which conditionally is assembled as armv4
based on CONFIG_ARCH_RPC, and arch/arm/mach-at91/pm-suspend.S which is
conditionally assembled as armv7-a based on CONFIG_CPU_V7), prefer the
.arch assembler directive.

Add a few more instances found in compile testing as found by Arnd and
Nathan.

Link: https://github.com/llvm/llvm-project/commit/1d51c699b9e2ebc5bcfdbe85c74cc871426333d4
Link: https://bugs.llvm.org/show_bug.cgi?id=48894
Link: https://github.com/ClangBuiltLinux/linux/issues/1195
Link: https://github.com/ClangBuiltLinux/linux/issues/1315

Suggested-by: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>

12 files changed, 19 insertions, 15 deletions

diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 3510503bc5e6..71b858c9b10c 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -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
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index c58bf8b43fea..836dc1299243 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -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
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index f81bceacc660..53fb41c24774 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -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
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index f0f65eb073e4..250c83bf7158 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -19,6 +19,8 @@
 #define D_CACHE_LINE_SIZE	32
 #define BTB_FLUSH_SIZE		8
 
+.arch armv6
+
 /*
  *	v6_flush_icache_all()
  *
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 7c9499b728c4..127afe2096ba 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -16,6 +16,8 @@
 
 #include "proc-macros.S"
 
+.arch armv7-a
+
 #ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
 .globl icache_size
 	.data
diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S
index 1bc3a0a50753..eb60b5e5e2ad 100644
--- a/arch/arm/mm/cache-v7m.S
+++ b/arch/arm/mm/cache-v7m.S
@@ -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
diff --git a/arch/arm/mm/copypage-feroceon.c b/arch/arm/mm/copypage-feroceon.c
index 064b19e63571..5fc8ef1e665f 100644
--- a/arch/arm/mm/copypage-feroceon.c
+++ b/arch/arm/mm/copypage-feroceon.c
@@ -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\
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index a0618f3e6836..203dff89ab1a 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -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
 
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index 5db029c8f987..0a3083ad19c2 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -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)
  *
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 26d726a08a34..6b4ef9539b68 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -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)
diff --git a/arch/arm/mm/tlb-v6.S b/arch/arm/mm/tlb-v6.S
index 74f4b383afe3..1d91e49b2c2d 100644
--- a/arch/arm/mm/tlb-v6.S
+++ b/arch/arm/mm/tlb-v6.S
@@ -17,6 +17,8 @@
 
 #define HARVARD_TLB
 
+.arch armv6
+
 /*
  *	v6wbi_flush_user_tlb_range(start, end, vma)
  *
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index 87bf4ab17721..35fd6d4f0d03 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -16,6 +16,8 @@
 #include <asm/tlbflush.h>
 #include "proc-macros.S"
 
+.arch armv7-a
+
 /*
  *	v7wbi_flush_user_tlb_range(start, end, vma)
  *