Merge branch 'for-next/asm-annotations' into for-next/core

* for-next/asm-annotations:
  : Modernise arm64 assembly annotations
  arm64: head: Convert install_el2_stub to SYM_INNER_LABEL
  arm64: Mark call_smc_arch_workaround_1 as __maybe_unused
  arm64: entry-ftrace.S: Fix missing argument for CONFIG_FUNCTION_GRAPH_TRACER=y
  arm64: vdso32: Convert to modern assembler annotations
  arm64: vdso: Convert to modern assembler annotations
  arm64: sdei: Annotate SDEI entry points using new style annotations
  arm64: kvm: Modernize __smccc_workaround_1_smc_start annotations
  arm64: kvm: Modernize annotation for __bp_harden_hyp_vecs
  arm64: kvm: Annotate assembly using modern annoations
  arm64: kernel: Convert to modern annotations for assembly data
  arm64: head: Annotate stext and preserve_boot_args as code
  arm64: head.S: Convert to modern annotations for assembly functions
  arm64: ftrace: Modernise annotation of return_to_handler
  arm64: ftrace: Correct annotation of ftrace_caller assembly
  arm64: entry-ftrace.S: Convert to modern annotations for assembly functions
  arm64: entry: Additional annotation conversions for entry.S
  arm64: entry: Annotate ret_from_fork as code
  arm64: entry: Annotate vector table and handlers as code
  arm64: crypto: Modernize names for AES function macros
  arm64: crypto: Modernize some extra assembly annotations

17 files changed, 212 insertions, 207 deletions

diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index 45062553467f..1dc5bbbfeed2 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -9,8 +9,8 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-#define AES_ENTRY(func)		SYM_FUNC_START(ce_ ## func)
-#define AES_ENDPROC(func)	SYM_FUNC_END(ce_ ## func)
+#define AES_FUNC_START(func)		SYM_FUNC_START(ce_ ## func)
+#define AES_FUNC_END(func)		SYM_FUNC_END(ce_ ## func)
 
 	.arch		armv8-a+crypto
 
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index 8a2faa42b57e..cf618d8f6cec 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -51,7 +51,7 @@ SYM_FUNC_END(aes_decrypt_block5x)
 	 *		   int blocks)
 	 */
 
-AES_ENTRY(aes_ecb_encrypt)
+AES_FUNC_START(aes_ecb_encrypt)
 	stp		x29, x30, [sp, #-16]!
 	mov		x29, sp
 
@@ -79,10 +79,10 @@ ST5(	st1		{v4.16b}, [x0], #16		)
 .Lecbencout:
 	ldp		x29, x30, [sp], #16
 	ret
-AES_ENDPROC(aes_ecb_encrypt)
+AES_FUNC_END(aes_ecb_encrypt)
 
 
-AES_ENTRY(aes_ecb_decrypt)
+AES_FUNC_START(aes_ecb_decrypt)
 	stp		x29, x30, [sp, #-16]!
 	mov		x29, sp
 
@@ -110,7 +110,7 @@ ST5(	st1		{v4.16b}, [x0], #16		)
 .Lecbdecout:
 	ldp		x29, x30, [sp], #16
 	ret
-AES_ENDPROC(aes_ecb_decrypt)
+AES_FUNC_END(aes_ecb_decrypt)
 
 
 	/*
@@ -126,7 +126,7 @@ AES_ENDPROC(aes_ecb_decrypt)
 	 *			 u32 const rk2[]);
 	 */
 
-AES_ENTRY(aes_essiv_cbc_encrypt)
+AES_FUNC_START(aes_essiv_cbc_encrypt)
 	ld1		{v4.16b}, [x5]			/* get iv */
 
 	mov		w8, #14				/* AES-256: 14 rounds */
@@ -135,7 +135,7 @@ AES_ENTRY(aes_essiv_cbc_encrypt)
 	enc_switch_key	w3, x2, x6
 	b		.Lcbcencloop4x
 
-AES_ENTRY(aes_cbc_encrypt)
+AES_FUNC_START(aes_cbc_encrypt)
 	ld1		{v4.16b}, [x5]			/* get iv */
 	enc_prepare	w3, x2, x6
 
@@ -167,10 +167,10 @@ AES_ENTRY(aes_cbc_encrypt)
 .Lcbcencout:
 	st1		{v4.16b}, [x5]			/* return iv */
 	ret
-AES_ENDPROC(aes_cbc_encrypt)
-AES_ENDPROC(aes_essiv_cbc_encrypt)
+AES_FUNC_END(aes_cbc_encrypt)
+AES_FUNC_END(aes_essiv_cbc_encrypt)
 
-AES_ENTRY(aes_essiv_cbc_decrypt)
+AES_FUNC_START(aes_essiv_cbc_decrypt)
 	stp		x29, x30, [sp, #-16]!
 	mov		x29, sp
 
@@ -181,7 +181,7 @@ AES_ENTRY(aes_essiv_cbc_decrypt)
 	encrypt_block	cbciv, w8, x6, x7, w9
 	b		.Lessivcbcdecstart
 
-AES_ENTRY(aes_cbc_decrypt)
+AES_FUNC_START(aes_cbc_decrypt)
 	stp		x29, x30, [sp, #-16]!
 	mov		x29, sp
 
@@ -238,8 +238,8 @@ ST5(	st1		{v4.16b}, [x0], #16		)
 	st1		{cbciv.16b}, [x5]		/* return iv */
 	ldp		x29, x30, [sp], #16
 	ret
-AES_ENDPROC(aes_cbc_decrypt)
-AES_ENDPROC(aes_essiv_cbc_decrypt)
+AES_FUNC_END(aes_cbc_decrypt)
+AES_FUNC_END(aes_essiv_cbc_decrypt)
 
 
 	/*
@@ -249,7 +249,7 @@ AES_ENDPROC(aes_essiv_cbc_decrypt)
 	 *		       int rounds, int bytes, u8 const iv[])
 	 */
 
-AES_ENTRY(aes_cbc_cts_encrypt)
+AES_FUNC_START(aes_cbc_cts_encrypt)
 	adr_l		x8, .Lcts_permute_table
 	sub		x4, x4, #16
 	add		x9, x8, #32
@@ -276,9 +276,9 @@ AES_ENTRY(aes_cbc_cts_encrypt)
 	st1		{v0.16b}, [x4]			/* overlapping stores */
 	st1		{v1.16b}, [x0]
 	ret
-AES_ENDPROC(aes_cbc_cts_encrypt)
+AES_FUNC_END(aes_cbc_cts_encrypt)
 
-AES_ENTRY(aes_cbc_cts_decrypt)
+AES_FUNC_START(aes_cbc_cts_decrypt)
 	adr_l		x8, .Lcts_permute_table
 	sub		x4, x4, #16
 	add		x9, x8, #32
@@ -305,7 +305,7 @@ AES_ENTRY(aes_cbc_cts_decrypt)
 	st1		{v2.16b}, [x4]			/* overlapping stores */
 	st1		{v0.16b}, [x0]
 	ret
-AES_ENDPROC(aes_cbc_cts_decrypt)
+AES_FUNC_END(aes_cbc_cts_decrypt)
 
 	.section	".rodata", "a"
 	.align		6
@@ -324,7 +324,7 @@ AES_ENDPROC(aes_cbc_cts_decrypt)
 	 *		   int blocks, u8 ctr[])
 	 */
 
-AES_ENTRY(aes_ctr_encrypt)
+AES_FUNC_START(aes_ctr_encrypt)
 	stp		x29, x30, [sp, #-16]!
 	mov		x29, sp
 
@@ -409,7 +409,7 @@ ST5(	st1		{v4.16b}, [x0], #16		)
 	rev		x7, x7
 	ins		vctr.d[0], x7
 	b		.Lctrcarrydone
-AES_ENDPROC(aes_ctr_encrypt)
+AES_FUNC_END(aes_ctr_encrypt)
 
 
 	/*
@@ -433,7 +433,7 @@ AES_ENDPROC(aes_ctr_encrypt)
 	uzp1		xtsmask.4s, xtsmask.4s, \tmp\().4s
 	.endm
 
-AES_ENTRY(aes_xts_encrypt)
+AES_FUNC_START(aes_xts_encrypt)
 	stp		x29, x30, [sp, #-16]!
 	mov		x29, sp
 
@@ -518,9 +518,9 @@ AES_ENTRY(aes_xts_encrypt)
 	st1		{v2.16b}, [x4]			/* overlapping stores */
 	mov		w4, wzr
 	b		.Lxtsencctsout
-AES_ENDPROC(aes_xts_encrypt)
+AES_FUNC_END(aes_xts_encrypt)
 
-AES_ENTRY(aes_xts_decrypt)
+AES_FUNC_START(aes_xts_decrypt)
 	stp		x29, x30, [sp, #-16]!
 	mov		x29, sp
 
@@ -612,13 +612,13 @@ AES_ENTRY(aes_xts_decrypt)
 	st1		{v2.16b}, [x4]			/* overlapping stores */
 	mov		w4, wzr
 	b		.Lxtsdecctsout
-AES_ENDPROC(aes_xts_decrypt)
+AES_FUNC_END(aes_xts_decrypt)
 
 	/*
 	 * aes_mac_update(u8 const in[], u32 const rk[], int rounds,
 	 *		  int blocks, u8 dg[], int enc_before, int enc_after)
 	 */
-AES_ENTRY(aes_mac_update)
+AES_FUNC_START(aes_mac_update)
 	frame_push	6
 
 	mov		x19, x0
@@ -676,4 +676,4 @@ AES_ENTRY(aes_mac_update)
 	ld1		{v0.16b}, [x23]			/* get dg */
 	enc_prepare	w21, x20, x0
 	b		.Lmacloop4x
-AES_ENDPROC(aes_mac_update)
+AES_FUNC_END(aes_mac_update)
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
index 247d34ddaab0..e47d3ec2cfb4 100644
--- a/arch/arm64/crypto/aes-neon.S
+++ b/arch/arm64/crypto/aes-neon.S
@@ -8,8 +8,8 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-#define AES_ENTRY(func)		SYM_FUNC_START(neon_ ## func)
-#define AES_ENDPROC(func)	SYM_FUNC_END(neon_ ## func)
+#define AES_FUNC_START(func)		SYM_FUNC_START(neon_ ## func)
+#define AES_FUNC_END(func)		SYM_FUNC_END(neon_ ## func)
 
 	xtsmask		.req	v7
 	cbciv		.req	v7
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index 084c6a30b03a..6b958dcdf136 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -587,20 +587,20 @@ CPU_LE(	rev		w8, w8		)
 	 *			  struct ghash_key const *k, u64 dg[], u8 ctr[],
 	 *			  int rounds, u8 tag)
 	 */
-ENTRY(pmull_gcm_encrypt)
+SYM_FUNC_START(pmull_gcm_encrypt)
 	pmull_gcm_do_crypt	1
-ENDPROC(pmull_gcm_encrypt)
+SYM_FUNC_END(pmull_gcm_encrypt)
 
 	/*
 	 * void pmull_gcm_decrypt(int blocks, u8 dst[], const u8 src[],
 	 *			  struct ghash_key const *k, u64 dg[], u8 ctr[],
 	 *			  int rounds, u8 tag)
 	 */
-ENTRY(pmull_gcm_decrypt)
+SYM_FUNC_START(pmull_gcm_decrypt)
 	pmull_gcm_do_crypt	0
-ENDPROC(pmull_gcm_decrypt)
+SYM_FUNC_END(pmull_gcm_decrypt)
 
-pmull_gcm_ghash_4x:
+SYM_FUNC_START_LOCAL(pmull_gcm_ghash_4x)
 	movi		MASK.16b, #0xe1
 	shl		MASK.2d, MASK.2d, #57
 
@@ -681,9 +681,9 @@ pmull_gcm_ghash_4x:
 	eor		XL.16b, XL.16b, T2.16b
 
 	ret
-ENDPROC(pmull_gcm_ghash_4x)
+SYM_FUNC_END(pmull_gcm_ghash_4x)
 
-pmull_gcm_enc_4x:
+SYM_FUNC_START_LOCAL(pmull_gcm_enc_4x)
 	ld1		{KS0.16b}, [x5]			// load upper counter
 	sub		w10, w8, #4
 	sub		w11, w8, #3
@@ -746,7 +746,7 @@ pmull_gcm_enc_4x:
 	eor		INP3.16b, INP3.16b, KS3.16b
 
 	ret
-ENDPROC(pmull_gcm_enc_4x)
+SYM_FUNC_END(pmull_gcm_enc_4x)
 
 	.section	".rodata", "a"
 	.align		6
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 44a243754c1b..7c7eeeaab9fa 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -36,6 +36,8 @@
  */
 #define KVM_VECTOR_PREAMBLE	(2 * AARCH64_INSN_SIZE)
 
+#define __SMCCC_WORKAROUND_1_SMC_SZ 36
+
 #ifndef __ASSEMBLY__
 
 #include <linux/mm.h>
@@ -75,6 +77,8 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
+extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
+
 /* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */
 #define __hyp_this_cpu_ptr(sym)						\
 	({								\
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 53d846f1bfe7..b5f723cf9599 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -480,7 +480,7 @@ static inline void *kvm_get_hyp_vector(void)
 	int slot = -1;
 
 	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) {
-		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs_start));
+		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
 		slot = data->hyp_vectors_slot;
 	}
 
@@ -509,14 +509,13 @@ static inline int kvm_map_vectors(void)
 	 *  HBP +  HEL2 -> use hardened vertors and use exec mapping
 	 */
 	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) {
-		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs_start);
+		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs);
 		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
 	}
 
 	if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
-		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs_start);
-		unsigned long size = (__bp_harden_hyp_vecs_end -
-				      __bp_harden_hyp_vecs_start);
+		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs);
+		unsigned long size = __BP_HARDEN_HYP_VECS_SZ;
 
 		/*
 		 * Always allocate a spare vector slot, as we don't
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 21a4bcfdb378..3c9533322558 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -13,6 +13,7 @@
 #define TTBR_ASID_MASK	(UL(0xffff) << 48)
 
 #define BP_HARDEN_EL2_SLOTS 4
+#define __BP_HARDEN_HYP_VECS_SZ (BP_HARDEN_EL2_SLOTS * SZ_2K)
 
 #ifndef __ASSEMBLY__
 
@@ -45,7 +46,8 @@ struct bp_hardening_data {
 
 #if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\
      defined(CONFIG_HARDEN_EL2_VECTORS))
-extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[];
+
+extern char __bp_harden_hyp_vecs[];
 extern atomic_t arm64_el2_vector_last_slot;
 #endif  /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
 
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 703ad0a84f99..df56d2295d16 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -11,6 +11,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/kvm_asm.h>
 #include <asm/smp_plat.h>
 
 static bool __maybe_unused
@@ -113,13 +114,10 @@ atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
 DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
-extern char __smccc_workaround_1_smc_start[];
-extern char __smccc_workaround_1_smc_end[];
-
 static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 				const char *hyp_vecs_end)
 {
-	void *dst = lm_alias(__bp_harden_hyp_vecs_start + slot * SZ_2K);
+	void *dst = lm_alias(__bp_harden_hyp_vecs + slot * SZ_2K);
 	int i;
 
 	for (i = 0; i < SZ_2K; i += 0x80)
@@ -163,9 +161,6 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 	raw_spin_unlock(&bp_lock);
 }
 #else
-#define __smccc_workaround_1_smc_start		NULL
-#define __smccc_workaround_1_smc_end		NULL
-
 static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
 				      const char *hyp_vecs_end)
@@ -176,7 +171,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 
 #include <linux/arm-smccc.h>
 
-static void call_smc_arch_workaround_1(void)
+static void __maybe_unused call_smc_arch_workaround_1(void)
 {
 	arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
 }
@@ -239,11 +234,14 @@ static int detect_harden_bp_fw(void)
 		smccc_end = NULL;
 		break;
 
+#if IS_ENABLED(CONFIG_KVM_ARM_HOST)
 	case SMCCC_CONDUIT_SMC:
 		cb = call_smc_arch_workaround_1;
-		smccc_start = __smccc_workaround_1_smc_start;
-		smccc_end = __smccc_workaround_1_smc_end;
+		smccc_start = __smccc_workaround_1_smc;
+		smccc_end = __smccc_workaround_1_smc +
+			__SMCCC_WORKAROUND_1_SMC_SZ;
 		break;
+#endif
 
 	default:
 		return -1;
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 7d02f9966d34..833d48c9acb5 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -75,27 +75,27 @@
 	add	x29, sp, #S_STACKFRAME
 	.endm
 
-ENTRY(ftrace_regs_caller)
+SYM_CODE_START(ftrace_regs_caller)
 	ftrace_regs_entry	1
 	b	ftrace_common
-ENDPROC(ftrace_regs_caller)
+SYM_CODE_END(ftrace_regs_caller)
 
-ENTRY(ftrace_caller)
+SYM_CODE_START(ftrace_caller)
 	ftrace_regs_entry	0
 	b	ftrace_common
-ENDPROC(ftrace_caller)
+SYM_CODE_END(ftrace_caller)
 
-ENTRY(ftrace_common)
+SYM_CODE_START(ftrace_common)
 	sub	x0, x30, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
 	mov	x1, x9				// parent_ip (callsite's LR)
 	ldr_l	x2, function_trace_op		// op
 	mov	x3, sp				// regs
 
-GLOBAL(ftrace_call)
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	bl	ftrace_stub
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
+SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
 	nop				// If enabled, this will be replaced
 					// "b ftrace_graph_caller"
 #endif
@@ -122,17 +122,17 @@ ftrace_common_return:
 	add	sp, sp, #S_FRAME_SIZE + 16
 
 	ret	x9
-ENDPROC(ftrace_common)
+SYM_CODE_END(ftrace_common)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
+SYM_CODE_START(ftrace_graph_caller)
 	ldr	x0, [sp, #S_PC]
 	sub	x0, x0, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
 	add	x1, sp, #S_LR			// parent_ip (callsite's LR)
 	ldr	x2, [sp, #S_FRAME_SIZE]	   	// parent fp (callsite's FP)
 	bl	prepare_ftrace_return
 	b	ftrace_common_return
-ENDPROC(ftrace_graph_caller)
+SYM_CODE_END(ftrace_graph_caller)
 #endif
 
 #else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
@@ -218,7 +218,7 @@ ENDPROC(ftrace_graph_caller)
  *     - tracer function to probe instrumented function's entry,
  *     - ftrace_graph_caller to set up an exit hook
  */
-ENTRY(_mcount)
+SYM_FUNC_START(_mcount)
 	mcount_enter
 
 	ldr_l	x2, ftrace_trace_function
@@ -242,7 +242,7 @@ skip_ftrace_call:			// }
 	b.ne	ftrace_graph_caller	//     ftrace_graph_caller();
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 	mcount_exit
-ENDPROC(_mcount)
+SYM_FUNC_END(_mcount)
 EXPORT_SYMBOL(_mcount)
 NOKPROBE(_mcount)
 
@@ -253,9 +253,9 @@ NOKPROBE(_mcount)
  * and later on, NOP to branch to ftrace_caller() when enabled or branch to
  * NOP when disabled per-function base.
  */
-ENTRY(_mcount)
+SYM_FUNC_START(_mcount)
 	ret
-ENDPROC(_mcount)
+SYM_FUNC_END(_mcount)
 EXPORT_SYMBOL(_mcount)
 NOKPROBE(_mcount)
 
@@ -268,24 +268,24 @@ NOKPROBE(_mcount)
  *     - tracer function to probe instrumented function's entry,
  *     - ftrace_graph_caller to set up an exit hook
  */
-ENTRY(ftrace_caller)
+SYM_FUNC_START(ftrace_caller)
 	mcount_enter
 
 	mcount_get_pc0	x0		//     function's pc
 	mcount_get_lr	x1		//     function's lr
 
-GLOBAL(ftrace_call)			// tracer(pc, lr);
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)	// tracer(pc, lr);
 	nop				// This will be replaced with "bl xxx"
 					// where xxx can be any kind of tracer.
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
+SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
 	nop				// If enabled, this will be replaced
 					// "b ftrace_graph_caller"
 #endif
 
 	mcount_exit
-ENDPROC(ftrace_caller)
+SYM_FUNC_END(ftrace_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -298,20 +298,20 @@ ENDPROC(ftrace_caller)
  * the call stack in order to intercept instrumented function's return path
  * and run return_to_handler() later on its exit.
  */
-ENTRY(ftrace_graph_caller)
+SYM_FUNC_START(ftrace_graph_caller)
 	mcount_get_pc		  x0	//     function's pc
 	mcount_get_lr_addr	  x1	//     pointer to function's saved lr
 	mcount_get_parent_fp	  x2	//     parent's fp
 	bl	prepare_ftrace_return	// prepare_ftrace_return(pc, &lr, fp)
 
 	mcount_exit
-ENDPROC(ftrace_graph_caller)
+SYM_FUNC_END(ftrace_graph_caller)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
-ENTRY(ftrace_stub)
+SYM_FUNC_START(ftrace_stub)
 	ret
-ENDPROC(ftrace_stub)
+SYM_FUNC_END(ftrace_stub)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
@@ -320,7 +320,7 @@ ENDPROC(ftrace_stub)
  * Run ftrace_return_to_handler() before going back to parent.
  * @fp is checked against the value passed by ftrace_graph_caller().
  */
-ENTRY(return_to_handler)
+SYM_CODE_START(return_to_handler)
 	/* save return value regs */
 	sub sp, sp, #64
 	stp x0, x1, [sp]
@@ -340,5 +340,5 @@ ENTRY(return_to_handler)
 	add sp, sp, #64
 
 	ret
-END(return_to_handler)
+SYM_CODE_END(return_to_handler)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 9461d812ae27..e5d4e30ee242 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -465,7 +465,7 @@ alternative_endif
 	.pushsection ".entry.text", "ax"
 
 	.align	11
-ENTRY(vectors)
+SYM_CODE_START(vectors)
 	kernel_ventry	1, sync_invalid			// Synchronous EL1t
 	kernel_ventry	1, irq_invalid			// IRQ EL1t
 	kernel_ventry	1, fiq_invalid			// FIQ EL1t
@@ -492,7 +492,7 @@ ENTRY(vectors)
 	kernel_ventry	0, fiq_invalid, 32		// FIQ 32-bit EL0
 	kernel_ventry	0, error_invalid, 32		// Error 32-bit EL0
 #endif
-END(vectors)
+SYM_CODE_END(vectors)
 
 #ifdef CONFIG_VMAP_STACK
 	/*
@@ -534,57 +534,57 @@ __bad_stack:
 	ASM_BUG()
 	.endm
 
-el0_sync_invalid:
+SYM_CODE_START_LOCAL(el0_sync_invalid)
 	inv_entry 0, BAD_SYNC
-ENDPROC(el0_sync_invalid)
+SYM_CODE_END(el0_sync_invalid)
 
-el0_irq_invalid:
+SYM_CODE_START_LOCAL(el0_irq_invalid)
 	inv_entry 0, BAD_IRQ
-ENDPROC(el0_irq_invalid)
+SYM_CODE_END(el0_irq_invalid)
 
-el0_fiq_invalid:
+SYM_CODE_START_LOCAL(el0_fiq_invalid)
 	inv_entry 0, BAD_FIQ
-ENDPROC(el0_fiq_invalid)
+SYM_CODE_END(el0_fiq_invalid)
 
-el0_error_invalid:
+SYM_CODE_START_LOCAL(el0_error_invalid)
 	inv_entry 0, BAD_ERROR
-ENDPROC(el0_error_invalid)
+SYM_CODE_END(el0_error_invalid)
 
 #ifdef CONFIG_COMPAT
-el0_fiq_invalid_compat:
+SYM_CODE_START_LOCAL(el0_fiq_invalid_compat)
 	inv_entry 0, BAD_FIQ, 32
-ENDPROC(el0_fiq_invalid_compat)
+SYM_CODE_END(el0_fiq_invalid_compat)
 #endif
 
-el1_sync_invalid:
+SYM_CODE_START_LOCAL(el1_sync_invalid)
 	inv_entry 1, BAD_SYNC
-ENDPROC(el1_sync_invalid)
+SYM_CODE_END(el1_sync_invalid)
 
-el1_irq_invalid:
+SYM_CODE_START_LOCAL(el1_irq_invalid)
 	inv_entry 1, BAD_IRQ
-ENDPROC(el1_irq_invalid)
+SYM_CODE_END(el1_irq_invalid)
 
-el1_fiq_invalid:
+SYM_CODE_START_LOCAL(el1_fiq_invalid)
 	inv_entry 1, BAD_FIQ
-ENDPROC(el1_fiq_invalid)
+SYM_CODE_END(el1_fiq_invalid)
 
-el1_error_invalid:
+SYM_CODE_START_LOCAL(el1_error_invalid)
 	inv_entry 1, BAD_ERROR
-ENDPROC(el1_error_invalid)
+SYM_CODE_END(el1_error_invalid)
 
 /*
  * EL1 mode handlers.
  */
 	.align	6
-el1_sync:
+SYM_CODE_START_LOCAL_NOALIGN(el1_sync)
 	kernel_entry 1
 	mov	x0, sp
 	bl	el1_sync_handler
 	kernel_exit 1
-ENDPROC(el1_sync)
+SYM_CODE_END(el1_sync)
 
 	.align	6
-el1_irq:
+SYM_CODE_START_LOCAL_NOALIGN(el1_irq)
 	kernel_entry 1
 	gic_prio_irq_setup pmr=x20, tmp=x1
 	enable_da_f
@@ -639,42 +639,42 @@ alternative_else_nop_endif
 #endif
 
 	kernel_exit 1
-ENDPROC(el1_irq)
+SYM_CODE_END(el1_irq)
 
 /*
  * EL0 mode handlers.
  */
 	.align	6
-el0_sync:
+SYM_CODE_START_LOCAL_NOALIGN(el0_sync)
 	kernel_entry 0
 	mov	x0, sp
 	bl	el0_sync_handler
 	b	ret_to_user
-ENDPROC(el0_sync)
+SYM_CODE_END(el0_sync)
 
 #ifdef CONFIG_COMPAT
 	.align	6
-el0_sync_compat:
+SYM_CODE_START_LOCAL_NOALIGN(el0_sync_compat)
 	kernel_entry 0, 32
 	mov	x0, sp
 	bl	el0_sync_compat_handler
 	b	ret_to_user
-ENDPROC(el0_sync_compat)
+SYM_CODE_END(el0_sync_compat)
 
 	.align	6
-el0_irq_compat:
+SYM_CODE_START_LOCAL_NOALIGN(el0_irq_compat)
 	kernel_entry 0, 32
 	b	el0_irq_naked
-ENDPROC(el0_irq_compat)
+SYM_CODE_END(el0_irq_compat)
 
-el0_error_compat:
+SYM_CODE_START_LOCAL_NOALIGN(el0_error_compat)
 	kernel_entry 0, 32
 	b	el0_error_naked
-ENDPROC(el0_error_compat)
+SYM_CODE_END(el0_error_compat)
 #endif
 
 	.align	6
-el0_irq:
+SYM_CODE_START_LOCAL_NOALIGN(el0_irq)
 	kernel_entry 0
 el0_irq_naked:
 	gic_prio_irq_setup pmr=x20, tmp=x0
@@ -696,9 +696,9 @@ el0_irq_naked:
 	bl	trace_hardirqs_on
 #endif
 	b	ret_to_user
-ENDPROC(el0_irq)
+SYM_CODE_END(el0_irq)
 
-el1_error:
+SYM_CODE_START_LOCAL(el1_error)
 	kernel_entry 1
 	mrs	x1, esr_el1
 	gic_prio_kentry_setup tmp=x2
@@ -706,9 +706,9 @@ el1_error:
 	mov	x0, sp
 	bl	do_serror
 	kernel_exit 1
-ENDPROC(el1_error)
+SYM_CODE_END(el1_error)
 
-el0_error:
+SYM_CODE_START_LOCAL(el0_error)
 	kernel_entry 0
 el0_error_naked:
 	mrs	x25, esr_el1
@@ -720,7 +720,7 @@ el0_error_naked:
 	bl	do_serror
 	enable_da_f
 	b	ret_to_user
-ENDPROC(el0_error)
+SYM_CODE_END(el0_error)
 
 /*
  * Ok, we need to do extra processing, enter the slow path.
@@ -832,7 +832,7 @@ alternative_else_nop_endif
 	.endm
 
 	.align	11
-ENTRY(tramp_vectors)
+SYM_CODE_START_NOALIGN(tramp_vectors)
 	.space	0x400
 
 	tramp_ventry
@@ -844,24 +844,24 @@ ENTRY(tramp_vectors)
 	tramp_ventry	32
 	tramp_ventry	32
 	tramp_ventry	32
-END(tramp_vectors)
+SYM_CODE_END(tramp_vectors)
 
-ENTRY(tramp_exit_native)
+SYM_CODE_START(tramp_exit_native)
 	tramp_exit
-END(tramp_exit_native)
+SYM_CODE_END(tramp_exit_native)
 
-ENTRY(tramp_exit_compat)
+SYM_CODE_START(tramp_exit_compat)
 	tramp_exit	32
-END(tramp_exit_compat)
+SYM_CODE_END(tramp_exit_compat)
 
 	.ltorg
 	.popsection				// .entry.tramp.text
 #ifdef CONFIG_RANDOMIZE_BASE
 	.pushsection ".rodata", "a"
 	.align PAGE_SHIFT
-	.globl	__entry_tramp_data_start
-__entry_tramp_data_start:
+SYM_DATA_START(__entry_tramp_data_start)
 	.quad	vectors
+SYM_DATA_END(__entry_tramp_data_start)
 	.popsection				// .rodata
 #endif /* CONFIG_RANDOMIZE_BASE */
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
@@ -874,7 +874,7 @@ __entry_tramp_data_start:
  * Previous and next are guaranteed not to be the same.
  *
  */
-ENTRY(cpu_switch_to)
+SYM_FUNC_START(cpu_switch_to)
 	mov	x10, #THREAD_CPU_CONTEXT
 	add	x8, x0, x10
 	mov	x9, sp
@@ -896,20 +896,20 @@ ENTRY(cpu_switch_to)
 	mov	sp, x9
 	msr	sp_el0, x1
 	ret
-ENDPROC(cpu_switch_to)
+SYM_FUNC_END(cpu_switch_to)
 NOKPROBE(cpu_switch_to)
 
 /*
  * This is how we return from a fork.
  */
-ENTRY(ret_from_fork)
+SYM_CODE_START(ret_from_fork)
 	bl	schedule_tail
 	cbz	x19, 1f				// not a kernel thread
 	mov	x0, x20
 	blr	x19
 1:	get_current_task tsk
 	b	ret_to_user
-ENDPROC(ret_from_fork)
+SYM_CODE_END(ret_from_fork)
 NOKPROBE(ret_from_fork)
 
 #ifdef CONFIG_ARM_SDE_INTERFACE
@@ -938,7 +938,7 @@ NOKPROBE(ret_from_fork)
  */
 .ltorg
 .pushsection ".entry.tramp.text", "ax"
-ENTRY(__sdei_asm_entry_trampoline)
+SYM_CODE_START(__sdei_asm_entry_trampoline)
 	mrs	x4, ttbr1_el1
 	tbz	x4, #USER_ASID_BIT, 1f
 
@@ -960,7 +960,7 @@ ENTRY(__sdei_asm_entry_trampoline)
 	ldr	x4, =__sdei_asm_handler
 #endif
 	br	x4
-ENDPROC(__sdei_asm_entry_trampoline)
+SYM_CODE_END(__sdei_asm_entry_trampoline)
 NOKPROBE(__sdei_asm_entry_trampoline)
 
 /*
@@ -970,21 +970,22 @@ NOKPROBE(__sdei_asm_entry_trampoline)
  * x2: exit_mode
  * x4: struct sdei_registered_event argument from registration time.
  */
-ENTRY(__sdei_asm_exit_trampoline)
+SYM_CODE_START(__sdei_asm_exit_trampoline)
 	ldr	x4, [x4, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]
 	cbnz	x4, 1f
 
 	tramp_unmap_kernel	tmp=x4
 
 1:	sdei_handler_exit exit_mode=x2
-ENDPROC(__sdei_asm_exit_trampoline)
+SYM_CODE_END(__sdei_asm_exit_trampoline)
 NOKPROBE(__sdei_asm_exit_trampoline)
 	.ltorg
 .popsection		// .entry.tramp.text
 #ifdef CONFIG_RANDOMIZE_BASE
 .pushsection ".rodata", "a"
-__sdei_asm_trampoline_next_handler:
+SYM_DATA_START(__sdei_asm_trampoline_next_handler)
 	.quad	__sdei_asm_handler
+SYM_DATA_END(__sdei_asm_trampoline_next_handler)
 .popsection		// .rodata
 #endif /* CONFIG_RANDOMIZE_BASE */
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
@@ -1002,7 +1003,7 @@ __sdei_asm_trampoline_next_handler:
  * follow SMC-CC. We save (or retrieve) all the registers as the handler may
  * want them.
  */
-ENTRY(__sdei_asm_handler)
+SYM_CODE_START(__sdei_asm_handler)
 	stp     x2, x3, [x1, #SDEI_EVENT_INTREGS + S_PC]
 	stp     x4, x5, [x1, #SDEI_EVENT_INTREGS + 16 * 2]
 	stp     x6, x7, [x1, #SDEI_EVENT_INTREGS + 16 * 3]
@@ -1085,6 +1086,6 @@ alternative_else_nop_endif
 	tramp_alias	dst=x5, sym=__sdei_asm_exit_trampoline
 	br	x5
 #endif
-ENDPROC(__sdei_asm_handler)
+SYM_CODE_END(__sdei_asm_handler)
 NOKPROBE(__sdei_asm_handler)
 #endif /* CONFIG_ARM_SDE_INTERFACE */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index f79023c9b374..5fa9daa1d227 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -105,7 +105,7 @@ pe_header:
 	 *  x24        __primary_switch() .. relocate_kernel()
 	 *                                        current RELR displacement
 	 */
-ENTRY(stext)
+SYM_CODE_START(stext)
 	bl	preserve_boot_args
 	bl	el2_setup			// Drop to EL1, w0=cpu_boot_mode
 	adrp	x23, __PHYS_OFFSET
@@ -120,12 +120,12 @@ ENTRY(stext)
 	 */
 	bl	__cpu_setup			// initialise processor
 	b	__primary_switch
-ENDPROC(stext)
+SYM_CODE_END(stext)
 
 /*
  * Preserve the arguments passed by the bootloader in x0 .. x3
  */
-preserve_boot_args:
+SYM_CODE_START_LOCAL(preserve_boot_args)
 	mov	x21, x0				// x21=FDT
 
 	adr_l	x0, boot_args			// record the contents of
@@ -137,7 +137,7 @@ preserve_boot_args:
 
 	mov	x1, #0x20			// 4 x 8 bytes
 	b	__inval_dcache_area		// tail call
-ENDPROC(preserve_boot_args)
+SYM_CODE_END(preserve_boot_args)
 
 /*
  * Macro to create a table entry to the next page.
@@ -275,7 +275,7 @@ ENDPROC(preserve_boot_args)
  *   - first few MB of the kernel linear mapping to jump to once the MMU has
  *     been enabled
  */
-__create_page_tables:
+SYM_FUNC_START_LOCAL(__create_page_tables)
 	mov	x28, lr
 
 	/*
@@ -403,14 +403,14 @@ __create_page_tables:
 	bl	__inval_dcache_area
 
 	ret	x28
-ENDPROC(__create_page_tables)
+SYM_FUNC_END(__create_page_tables)
 
 /*
  * The following fragment of code is executed with the MMU enabled.
  *
  *   x0 = __PHYS_OFFSET
  */
-__primary_switched:
+SYM_FUNC_START_LOCAL(__primary_switched)
 	adrp	x4, init_thread_union
 	add	sp, x4, #THREAD_SIZE
 	adr_l	x5, init_task
@@ -455,7 +455,7 @@ __primary_switched:
 	mov	x29, #0
 	mov	x30, #0
 	b	start_kernel
-ENDPROC(__primary_switched)
+SYM_FUNC_END(__primary_switched)
 
 /*
  * end early head section, begin head code that is also used for
@@ -463,8 +463,9 @@ ENDPROC(__primary_switched)
  */
 	.section ".idmap.text","awx"
 
-ENTRY(kimage_vaddr)
+SYM_DATA_START(kimage_vaddr)
 	.quad		_text - TEXT_OFFSET
+SYM_DATA_END(kimage_vaddr)
 EXPORT_SYMBOL(kimage_vaddr)
 
 /*
@@ -474,7 +475,7 @@ EXPORT_SYMBOL(kimage_vaddr)
  * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in w0 if
  * booted in EL1 or EL2 respectively.
  */
-ENTRY(el2_setup)
+SYM_FUNC_START(el2_setup)
 	msr	SPsel, #1			// We want to use SP_EL{1,2}
 	mrs	x0, CurrentEL
 	cmp	x0, #CurrentEL_EL2
@@ -598,7 +599,7 @@ set_hcr:
 	isb
 	ret
 
-install_el2_stub:
+SYM_INNER_LABEL(install_el2_stub, SYM_L_LOCAL)
 	/*
 	 * When VHE is not in use, early init of EL2 and EL1 needs to be
 	 * done here.
@@ -635,13 +636,13 @@ install_el2_stub:
 	msr	elr_el2, lr
 	mov	w0, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
 	eret
-ENDPROC(el2_setup)
+SYM_FUNC_END(el2_setup)
 
 /*
  * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
  * in w0. See arch/arm64/include/asm/virt.h for more info.
  */
-set_cpu_boot_mode_flag:
+SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag)
 	adr_l	x1, __boot_cpu_mode
 	cmp	w0, #BOOT_CPU_MODE_EL2
 	b.ne	1f
@@ -650,7 +651,7 @@ set_cpu_boot_mode_flag:
 	dmb	sy
 	dc	ivac, x1			// Invalidate potentially stale cache line
 	ret
-ENDPROC(set_cpu_boot_mode_flag)
+SYM_FUNC_END(set_cpu_boot_mode_flag)
 
 /*
  * These values are written with the MMU off, but read with the MMU on.
@@ -666,15 +667,17 @@ ENDPROC(set_cpu_boot_mode_flag)
  * This is not in .bss, because we set it sufficiently early that the boot-time
  * zeroing of .bss would clobber it.
  */
-ENTRY(__boot_cpu_mode)
+SYM_DATA_START(__boot_cpu_mode)
 	.long	BOOT_CPU_MODE_EL2
 	.long	BOOT_CPU_MODE_EL1
+SYM_DATA_END(__boot_cpu_mode)
 /*
  * The booting CPU updates the failed status @__early_cpu_boot_status,
  * with MMU turned off.
  */
-ENTRY(__early_cpu_boot_status)
+SYM_DATA_START(__early_cpu_boot_status)
 	.quad 	0
+SYM_DATA_END(__early_cpu_boot_status)
 
 	.popsection
 
@@ -682,7 +685,7 @@ ENTRY(__early_cpu_boot_status)
 	 * This provides a "holding pen" for platforms to hold all secondary
 	 * cores are held until we're ready for them to initialise.
 	 */
-ENTRY(secondary_holding_pen)
+SYM_FUNC_START(secondary_holding_pen)
 	bl	el2_setup			// Drop to EL1, w0=cpu_boot_mode
 	bl	set_cpu_boot_mode_flag
 	mrs	x0, mpidr_el1
@@ -694,19 +697,19 @@ pen:	ldr	x4, [x3]
 	b.eq	secondary_startup
 	wfe
 	b	pen
-ENDPROC(secondary_holding_pen)
+SYM_FUNC_END(secondary_holding_pen)
 
 	/*
 	 * Secondary entry point that jumps straight into the kernel. Only to
 	 * be used where CPUs are brought online dynamically by the kernel.
 	 */
-ENTRY(secondary_entry)
+SYM_FUNC_START(secondary_entry)
 	bl	el2_setup			// Drop to EL1
 	bl	set_cpu_boot_mode_flag
 	b	secondary_startup
-ENDPROC(secondary_entry)
+SYM_FUNC_END(secondary_entry)
 
-secondary_startup:
+SYM_FUNC_START_LOCAL(secondary_startup)
 	/*
 	 * Common entry point for secondary CPUs.
 	 */
@@ -716,9 +719,9 @@ secondary_startup:
 	bl	__enable_mmu
 	ldr	x8, =__secondary_switched
 	br	x8
-ENDPROC(secondary_startup)
+SYM_FUNC_END(secondary_startup)
 
-__secondary_switched:
+SYM_FUNC_START_LOCAL(__secondary_switched)
 	adr_l	x5, vectors
 	msr	vbar_el1, x5
 	isb
@@ -733,13 +736,13 @@ __secondary_switched:
 	mov	x29, #0
 	mov	x30, #0
 	b	secondary_start_kernel
-ENDPROC(__secondary_switched)
+SYM_FUNC_END(__secondary_switched)
 
-__secondary_too_slow:
+SYM_FUNC_START_LOCAL(__secondary_too_slow)
 	wfe
 	wfi
 	b	__secondary_too_slow
-ENDPROC(__secondary_too_slow)
+SYM_FUNC_END(__secondary_too_slow)
 
 /*
  * The booting CPU updates the failed status @__early_cpu_boot_status,
@@ -771,7 +774,7 @@ ENDPROC(__secondary_too_slow)
  * Checks if the selected granule size is supported by the CPU.
  * If it isn't, park the CPU
  */
-ENTRY(__enable_mmu)
+SYM_FUNC_START(__enable_mmu)
 	mrs	x2, ID_AA64MMFR0_EL1
 	ubfx	x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4
 	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
@@ -795,9 +798,9 @@ ENTRY(__enable_mmu)
 	dsb	nsh
 	isb
 	ret
-ENDPROC(__enable_mmu)
+SYM_FUNC_END(__enable_mmu)
 
-ENTRY(__cpu_secondary_check52bitva)
+SYM_FUNC_START(__cpu_secondary_check52bitva)
 #ifdef CONFIG_ARM64_VA_BITS_52
 	ldr_l	x0, vabits_actual
 	cmp	x0, #52
@@ -815,9 +818,9 @@ ENTRY(__cpu_secondary_check52bitva)
 
 #endif
 2:	ret
-ENDPROC(__cpu_secondary_check52bitva)
+SYM_FUNC_END(__cpu_secondary_check52bitva)
 
-__no_granule_support:
+SYM_FUNC_START_LOCAL(__no_granule_support)
 	/* Indicate that this CPU can't boot and is stuck in the kernel */
 	update_early_cpu_boot_status \
 		CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_NO_GRAN, x1, x2
@@ -825,10 +828,10 @@ __no_granule_support:
 	wfe
 	wfi
 	b	1b
-ENDPROC(__no_granule_support)
+SYM_FUNC_END(__no_granule_support)
 
 #ifdef CONFIG_RELOCATABLE
-__relocate_kernel:
+SYM_FUNC_START_LOCAL(__relocate_kernel)
 	/*
 	 * Iterate over each entry in the relocation table, and apply the
 	 * relocations in place.
@@ -930,10 +933,10 @@ __relocate_kernel:
 #endif
 	ret
 
-ENDPROC(__relocate_kernel)
+SYM_FUNC_END(__relocate_kernel)
 #endif
 
-__primary_switch:
+SYM_FUNC_START_LOCAL(__primary_switch)
 #ifdef CONFIG_RANDOMIZE_BASE
 	mov	x19, x0				// preserve new SCTLR_EL1 value
 	mrs	x20, sctlr_el1			// preserve old SCTLR_EL1 value
@@ -976,4 +979,4 @@ __primary_switch:
 	ldr	x8, =__primary_switched
 	adrp	x0, __PHYS_OFFSET
 	br	x8
-ENDPROC(__primary_switch)
+SYM_FUNC_END(__primary_switch)
diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S
index 0723aa398d6e..12324863d5c2 100644
--- a/arch/arm64/kernel/vdso/sigreturn.S
+++ b/arch/arm64/kernel/vdso/sigreturn.S
@@ -14,7 +14,7 @@
 	.text
 
 	nop
-ENTRY(__kernel_rt_sigreturn)
+SYM_FUNC_START(__kernel_rt_sigreturn)
 	.cfi_startproc
 	.cfi_signal_frame
 	.cfi_def_cfa	x29, 0
@@ -23,4 +23,4 @@ ENTRY(__kernel_rt_sigreturn)
 	mov	x8, #__NR_rt_sigreturn
 	svc	#0
 	.cfi_endproc
-ENDPROC(__kernel_rt_sigreturn)
+SYM_FUNC_END(__kernel_rt_sigreturn)
diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S
index 1a81277c2d09..620524969696 100644
--- a/arch/arm64/kernel/vdso32/sigreturn.S
+++ b/arch/arm64/kernel/vdso32/sigreturn.S
@@ -10,13 +10,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 
-#define ARM_ENTRY(name)		\
-	ENTRY(name)
-
-#define ARM_ENDPROC(name)	\
-	.type name, %function;	\
-	END(name)
-
 	.text
 
 	.arm
@@ -24,39 +17,39 @@
 	.save {r0-r15}
 	.pad #COMPAT_SIGFRAME_REGS_OFFSET
 	nop
-ARM_ENTRY(__kernel_sigreturn_arm)
+SYM_FUNC_START(__kernel_sigreturn_arm)
 	mov r7, #__NR_compat_sigreturn
 	svc #0
 	.fnend
-ARM_ENDPROC(__kernel_sigreturn_arm)
+SYM_FUNC_END(__kernel_sigreturn_arm)
 
 	.fnstart
 	.save {r0-r15}
 	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
 	nop
-ARM_ENTRY(__kernel_rt_sigreturn_arm)
+SYM_FUNC_START(__kernel_rt_sigreturn_arm)
 	mov r7, #__NR_compat_rt_sigreturn
 	svc #0
 	.fnend
-ARM_ENDPROC(__kernel_rt_sigreturn_arm)
+SYM_FUNC_END(__kernel_rt_sigreturn_arm)
 
 	.thumb
 	.fnstart
 	.save {r0-r15}
 	.pad #COMPAT_SIGFRAME_REGS_OFFSET
 	nop
-ARM_ENTRY(__kernel_sigreturn_thumb)
+SYM_FUNC_START(__kernel_sigreturn_thumb)
 	mov r7, #__NR_compat_sigreturn
 	svc #0
 	.fnend
-ARM_ENDPROC(__kernel_sigreturn_thumb)
+SYM_FUNC_END(__kernel_sigreturn_thumb)
 
 	.fnstart
 	.save {r0-r15}
 	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
 	nop
-ARM_ENTRY(__kernel_rt_sigreturn_thumb)
+SYM_FUNC_START(__kernel_rt_sigreturn_thumb)
 	mov r7, #__NR_compat_rt_sigreturn
 	svc #0
 	.fnend
-ARM_ENDPROC(__kernel_rt_sigreturn_thumb)
+SYM_FUNC_END(__kernel_rt_sigreturn_thumb)
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 160be2b4696d..84f32cf5abc7 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -18,7 +18,7 @@
 
 	.align	11
 
-ENTRY(__kvm_hyp_init)
+SYM_CODE_START(__kvm_hyp_init)
 	ventry	__invalid		// Synchronous EL2t
 	ventry	__invalid		// IRQ EL2t
 	ventry	__invalid		// FIQ EL2t
@@ -117,9 +117,9 @@ CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 
 	/* Hello, World! */
 	eret
-ENDPROC(__kvm_hyp_init)
+SYM_CODE_END(__kvm_hyp_init)
 
-ENTRY(__kvm_handle_stub_hvc)
+SYM_CODE_START(__kvm_handle_stub_hvc)
 	cmp	x0, #HVC_SOFT_RESTART
 	b.ne	1f
 
@@ -158,7 +158,7 @@ reset:
 	ldr	x0, =HVC_STUB_ERR
 	eret
 
-ENDPROC(__kvm_handle_stub_hvc)
+SYM_CODE_END(__kvm_handle_stub_hvc)
 
 	.ltorg
 
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index c0094d520dff..3c79a1124af2 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -28,7 +28,7 @@
  * and is used to implement hyp stubs in the same way as in
  * arch/arm64/kernel/hyp_stub.S.
  */
-ENTRY(__kvm_call_hyp)
+SYM_FUNC_START(__kvm_call_hyp)
 	hvc	#0
 	ret
-ENDPROC(__kvm_call_hyp)
+SYM_FUNC_END(__kvm_call_hyp)
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
index 78ff53225691..5b8ff517ff10 100644
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -11,12 +11,12 @@
 	.text
 	.pushsection	.hyp.text, "ax"
 
-ENTRY(__fpsimd_save_state)
+SYM_FUNC_START(__fpsimd_save_state)
 	fpsimd_save	x0, 1
 	ret
-ENDPROC(__fpsimd_save_state)
+SYM_FUNC_END(__fpsimd_save_state)
 
-ENTRY(__fpsimd_restore_state)
+SYM_FUNC_START(__fpsimd_restore_state)
 	fpsimd_restore	x0, 1
 	ret
-ENDPROC(__fpsimd_restore_state)
+SYM_FUNC_END(__fpsimd_restore_state)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index ffa68d5713f1..c2a13ab3c471 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -180,7 +180,7 @@ el2_error:
 	eret
 	sb
 
-ENTRY(__hyp_do_panic)
+SYM_FUNC_START(__hyp_do_panic)
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
 		      PSR_MODE_EL1h)
 	msr	spsr_el2, lr
@@ -188,18 +188,19 @@ ENTRY(__hyp_do_panic)
 	msr	elr_el2, lr
 	eret
 	sb
-ENDPROC(__hyp_do_panic)
+SYM_FUNC_END(__hyp_do_panic)
 
-ENTRY(__hyp_panic)
+SYM_CODE_START(__hyp_panic)
 	get_host_ctxt x0, x1
 	b	hyp_panic
-ENDPROC(__hyp_panic)
+SYM_CODE_END(__hyp_panic)
 
 .macro invalid_vector	label, target = __hyp_panic
 	.align	2
+SYM_CODE_START(\label)
 \label:
 	b \target
-ENDPROC(\label)
+SYM_CODE_END(\label)
 .endm
 
 	/* None of these should ever happen */
@@ -246,7 +247,7 @@ check_preamble_length 661b, 662b
 check_preamble_length 661b, 662b
 .endm
 
-ENTRY(__kvm_hyp_vector)
+SYM_CODE_START(__kvm_hyp_vector)
 	invalid_vect	el2t_sync_invalid	// Synchronous EL2t
 	invalid_vect	el2t_irq_invalid	// IRQ EL2t
 	invalid_vect	el2t_fiq_invalid	// FIQ EL2t
@@ -266,7 +267,7 @@ ENTRY(__kvm_hyp_vector)
 	valid_vect	el1_irq			// IRQ 32-bit EL1
 	invalid_vect	el1_fiq_invalid		// FIQ 32-bit EL1
 	valid_vect	el1_error		// Error 32-bit EL1
-ENDPROC(__kvm_hyp_vector)
+SYM_CODE_END(__kvm_hyp_vector)
 
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
 .macro hyp_ventry
@@ -311,15 +312,17 @@ alternative_cb_end
 .endm
 
 	.align	11
-ENTRY(__bp_harden_hyp_vecs_start)
+SYM_CODE_START(__bp_harden_hyp_vecs)
 	.rept BP_HARDEN_EL2_SLOTS
 	generate_vectors
 	.endr
-ENTRY(__bp_harden_hyp_vecs_end)
+1:	.org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
+	.org 1b
+SYM_CODE_END(__bp_harden_hyp_vecs)
 
 	.popsection
 
-ENTRY(__smccc_workaround_1_smc_start)
+SYM_CODE_START(__smccc_workaround_1_smc)
 	esb
 	sub	sp, sp, #(8 * 4)
 	stp	x2, x3, [sp, #(8 * 0)]
@@ -329,5 +332,7 @@ ENTRY(__smccc_workaround_1_smc_start)
 	ldp	x2, x3, [sp, #(8 * 0)]
 	ldp	x0, x1, [sp, #(8 * 2)]
 	add	sp, sp, #(8 * 4)
-ENTRY(__smccc_workaround_1_smc_end)
+1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
+	.org 1b
+SYM_CODE_END(__smccc_workaround_1_smc)
 #endif