diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 3e4e5cc1636f4dc1743f90d4bbbf24098a31d86c..1d754357e842fccc912346bb56c06e0b05a66d0c 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -64,13 +64,21 @@ branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pa
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
 # integrated assemblers.
-branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a
-KBUILD_CFLAGS += $(branch-prot-flags-y)
+ifeq ($(CONFIG_AS_HAS_PAC), y)
+asm-arch := armv8.3-a
+endif
 endif
 
+KBUILD_CFLAGS += $(branch-prot-flags-y)
+
 ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
 # make sure to pass the newest target architecture to -march.
-KBUILD_CFLAGS	+= -Wa,-march=armv8.4-a
+asm-arch := armv8.4-a
+endif
+
+ifdef asm-arch
+KBUILD_CFLAGS	+= -Wa,-march=$(asm-arch) \
+		   -DARM64_ASM_ARCH='"$(asm-arch)"'
 endif
 
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
index b9c630287012b4f234894c2c9dcf1d7cc90631da..fc0fd6d4c0f376728ad2a1f179d9e35716b72ab4 100644
--- a/arch/arm64/include/asm/compiler.h
+++ b/arch/arm64/include/asm/compiler.h
@@ -18,6 +18,12 @@
 #ifndef __ASM_COMPILER_H
 #define __ASM_COMPILER_H
 
+#ifdef ARM64_ASM_ARCH
+#define ARM64_ASM_PREAMBLE ".arch " ARM64_ASM_ARCH "\n"
+#else
+#define ARM64_ASM_PREAMBLE
+#endif
+
 /*
  * This is used to ensure the compiler did actually allocate the register we
  * asked it for some inline assembly sequences.  Apparently we can't trust the
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index a3e27a1cd2607f784bcb3481d5b71e384fadf380..2e4a9046ead7845bfb8409712fbad50039193f7e 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -39,14 +39,16 @@
  * not. The macros handles invoking the asm with or without the
  * register argument as appropriate.
  */
-#define __TLBI_0(op, arg) asm ("tlbi " #op "\n"				       \
+#define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
+			       "tlbi " #op "\n"				       \
 		   ALTERNATIVE("nop\n			nop",		       \
 			       "dsb ish\n		tlbi " #op,	       \
 			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
 			       CONFIG_QCOM_FALKOR_ERRATUM_1009)		       \
 			    : : )
 
-#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0\n"			       \
+#define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
+			       "tlbi " #op ", %0\n"			       \
 		   ALTERNATIVE("nop\n			nop",		       \
 			       "dsb ish\n		tlbi " #op ", %0",     \
 			       ARM64_WORKAROUND_REPEAT_TLBI,		       \