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

Author: ctmarinas

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
 

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)

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

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

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)						\
 	({								\

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

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 */
 

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;