kselftest/arm64: Don't enable v8.5 for MTE selftest builds

Currently we set -march=armv8.5+memtag when building the MTE selftests,
allowing the compiler to emit v8.5 and MTE instructions for anything it
generates. This means that we may get code that will generate SIGILLs when
run on older systems rather than skipping on non-MTE systems as should be
the case. Most toolchains don't select any incompatible instructions but
I have seen some reports which suggest that some may be appearing which do
so. This is also potentially problematic in that if the compiler chooses to
emit any MTE instructions for the C code it may interfere with the MTE
usage we are trying to test.

Since the only reason we are specifying this option is to allow us to
assemble MTE instructions in mte_helper.S we can avoid these issues by
moving to using a .arch directive there and adding the -march explicitly to
the toolchain support check instead of the generic CFLAGS.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20220928154517.173108-1-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

tools/testing/selftests/arm64/mte/Makefile

@@ -11,11 +11,8 @@ LDFLAGS += -pthread
 SRCS := $(filter-out mte_common_util.c,$(wildcard *.c))
 PROGS := $(patsubst %.c,%,$(SRCS))
 
-#Add mte compiler option
-CFLAGS += -march=armv8.5-a+memtag
-
 #check if the compiler works well
-mte_cc_support := $(shell if ($(CC) $(CFLAGS) -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi)
+mte_cc_support := $(shell if ($(CC) $(CFLAGS) -march=armv8.5-a+memtag -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi)
 
 ifeq ($(mte_cc_support),1)
 # Generated binaries to be installed by top KSFT script

tools/testing/selftests/arm64/mte/mte_helper.S

@@ -3,6 +3,8 @@
 
 #include "mte_def.h"
 
+.arch	armv8.5-a+memtag
+
 #define ENTRY(name) \
 	.globl name ;\
 	.p2align 2;\