x86 asm: Replace .align with .balign

The .align directive used to align storage locations is
ambiguous. On some platforms and assemblers it takes a byte count,
on others the argument is interpreted as a shift value. The current
usage expects the first interpretation.

Replace it with the unambiguous .balign directive which always
expects a byte count, regardless of platform and assembler.

Reviewed-by: Jorgen Lundman <lundman@lundman.net>
Reviewed-by: Tino Reichardt <milky-zfs@mcmilk.de>
Reviewed-by: Richard Yao <richard.yao@alumni.stonybrook.edu>
Signed-off-by: Attila Fülöp <attila@fueloep.org>
Closes #14422

module/icp/asm-x86_64/aes/aes_aesni.S

@@ -378,7 +378,7 @@ rijndael_key_setup_enc_intel_local:
 	FRAME_END
 	RET
 
-.align 4
+.balign 4
 .Lenc_key192:
 	cmp	$192, %KEYSIZE32
 	jnz	.Lenc_key128
@@ -415,7 +415,7 @@ rijndael_key_setup_enc_intel_local:
 	FRAME_END
 	RET
 
-.align 4
+.balign 4
 .Lenc_key128:
 	cmp $128, %KEYSIZE32
 	jnz .Lenc_key_invalid_key_bits
@@ -522,7 +522,7 @@ FRAME_BEGIN
 	add	%AESKEY, %ROUNDS64
 	mov	%ROUNDS64, %ENDAESKEY
 
-.align 4
+.balign 4
 .Ldec_key_reorder_loop:
 	movups	(%AESKEY), %xmm0
 	movups	(%ROUNDS64), %xmm1
@@ -533,7 +533,7 @@ FRAME_BEGIN
 	cmp	%AESKEY, %ROUNDS64
 	ja	.Ldec_key_reorder_loop
 
-.align 4
+.balign 4
 .Ldec_key_inv_loop:
 	movups	(%rcx), %xmm0
 	// Convert an encryption round key to a form usable for decryption
@@ -622,7 +622,7 @@ ENTRY_NP(aes_encrypt_intel)
 	movups	-0x50(%KEYP), %KEY
 	aesenc	%KEY, %STATE
 
-.align 4
+.balign 4
 .Lenc192:
 	// AES 192 and 256
 	movups	-0x40(%KEYP), %KEY
@@ -630,7 +630,7 @@ ENTRY_NP(aes_encrypt_intel)
 	movups	-0x30(%KEYP), %KEY
 	aesenc	%KEY, %STATE
 
-.align 4
+.balign 4
 .Lenc128:
 	// AES 128, 192, and 256
 	movups	-0x20(%KEYP), %KEY
@@ -705,7 +705,7 @@ ENTRY_NP(aes_decrypt_intel)
 	movups	-0x50(%KEYP), %KEY
 	aesdec	%KEY, %STATE
 
-.align 4
+.balign 4
 .Ldec192:
 	// AES 192 and 256
 	movups	-0x40(%KEYP), %KEY
@@ -713,7 +713,7 @@ ENTRY_NP(aes_decrypt_intel)
 	movups	-0x30(%KEYP), %KEY
 	aesdec	%KEY, %STATE
 
-.align 4
+.balign 4
 .Ldec128:
 	// AES 128, 192, and 256
 	movups	-0x20(%KEYP), %KEY

module/icp/asm-x86_64/aes/aes_amd64.S

@@ -694,7 +694,7 @@ aes_decrypt_amd64(const uint32_t rk[], int Nr, const uint32_t ct[4],
  *	unsigned char *out, const aes_encrypt_ctx cx[1])/
  */
 SECTION_STATIC
-.align	64
+.balign	64
 enc_tab:
 	enc_vals(u8)
 #ifdef	LAST_ROUND_TABLES
@@ -800,7 +800,7 @@ ENTRY_NP(aes_encrypt_amd64)
  *	unsigned char *out, const aes_encrypt_ctx cx[1])/
  */
 SECTION_STATIC
-.align	64
+.balign	64
 dec_tab:
 	dec_vals(v8)
 #ifdef	LAST_ROUND_TABLES

module/icp/asm-x86_64/modes/aesni-gcm-x86_64.S

@@ -58,7 +58,7 @@
 .text
 
 #ifdef HAVE_MOVBE
-.align 32
+.balign 32
 FUNCTION(_aesni_ctr32_ghash_6x)
 .cfi_startproc
 	ENDBR
@@ -75,7 +75,7 @@ FUNCTION(_aesni_ctr32_ghash_6x)
 	vmovdqu	%xmm4,16+8(%rsp)
 	jmp	.Loop6x
 
-.align	32
+.balign	32
 .Loop6x:
 	addl	$100663296,%ebx
 	jc	.Lhandle_ctr32
@@ -287,7 +287,7 @@ FUNCTION(_aesni_ctr32_ghash_6x)
 	vmovups	224-128(%rcx),%xmm1
 	jmp	.Lenc_tail
 
-.align	32
+.balign	32
 .Lhandle_ctr32:
 	vmovdqu	(%r11),%xmm0
 	vpshufb	%xmm0,%xmm1,%xmm6
@@ -309,7 +309,7 @@ FUNCTION(_aesni_ctr32_ghash_6x)
 	vpshufb	%xmm0,%xmm1,%xmm1
 	jmp	.Lresume_ctr32
 
-.align	32
+.balign	32
 .Lenc_tail:
 	vaesenc	%xmm15,%xmm9,%xmm9
 	vmovdqu	%xmm7,16+8(%rsp)
@@ -374,7 +374,7 @@ FUNCTION(_aesni_ctr32_ghash_6x)
 SET_SIZE(_aesni_ctr32_ghash_6x)
 #endif /* ifdef HAVE_MOVBE */
 
-.align 32
+.balign 32
 FUNCTION(_aesni_ctr32_ghash_no_movbe_6x)
 .cfi_startproc
 	ENDBR
@@ -391,7 +391,7 @@ FUNCTION(_aesni_ctr32_ghash_no_movbe_6x)
 	vmovdqu	%xmm4,16+8(%rsp)
 	jmp	.Loop6x_nmb
 
-.align	32
+.balign	32
 .Loop6x_nmb:
 	addl	$100663296,%ebx
 	jc	.Lhandle_ctr32_nmb
@@ -615,7 +615,7 @@ FUNCTION(_aesni_ctr32_ghash_no_movbe_6x)
 	vmovups	224-128(%rcx),%xmm1
 	jmp	.Lenc_tail_nmb
 
-.align	32
+.balign	32
 .Lhandle_ctr32_nmb:
 	vmovdqu	(%r11),%xmm0
 	vpshufb	%xmm0,%xmm1,%xmm6
@@ -637,7 +637,7 @@ FUNCTION(_aesni_ctr32_ghash_no_movbe_6x)
 	vpshufb	%xmm0,%xmm1,%xmm1
 	jmp	.Lresume_ctr32_nmb
 
-.align	32
+.balign	32
 .Lenc_tail_nmb:
 	vaesenc	%xmm15,%xmm9,%xmm9
 	vmovdqu	%xmm7,16+8(%rsp)
@@ -818,7 +818,7 @@ ENTRY_ALIGN(aesni_gcm_decrypt, 32)
 .cfi_endproc
 SET_SIZE(aesni_gcm_decrypt)
 
-.align 32
+.balign 32
 FUNCTION(_aesni_ctr32_6x)
 .cfi_startproc
 	ENDBR
@@ -843,7 +843,7 @@ FUNCTION(_aesni_ctr32_6x)
 	vpxor	%xmm4,%xmm14,%xmm14
 	jmp	.Loop_ctr32
 
-.align	16
+.balign	16
 .Loop_ctr32:
 	vaesenc	%xmm15,%xmm9,%xmm9
 	vaesenc	%xmm15,%xmm10,%xmm10
@@ -886,7 +886,7 @@ FUNCTION(_aesni_ctr32_6x)
 	leaq	96(%rsi),%rsi
 
 	RET
-.align	32
+.balign	32
 .Lhandle_ctr32_2:
 	vpshufb	%xmm0,%xmm1,%xmm6
 	vmovdqu	48(%r11),%xmm5
@@ -1237,7 +1237,7 @@ SET_SIZE(atomic_toggle_boolean_nv)
 
 SECTION_STATIC
 
-.align	64
+.balign	64
 .Lbswap_mask:
 .byte	15,14,13,12,11,10,9,8,7,6,5,4,3,2,1,0
 .Lpoly:
@@ -1249,7 +1249,7 @@ SECTION_STATIC
 .Lone_lsb:
 .byte	1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
 .byte	65,69,83,45,78,73,32,71,67,77,32,109,111,100,117,108,101,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
-.align	64
+.balign	64
 
 /* Mark the stack non-executable. */
 #if defined(__linux__) && defined(__ELF__)

module/icp/asm-x86_64/modes/gcm_pclmulqdq.S

@@ -102,7 +102,7 @@ gcm_mul_pclmulqdq(uint64_t *x_in, uint64_t *y, uint64_t *res) {
 // static uint8_t byte_swap16_mask[] = {
 //	 15, 14, 13, 12, 11, 10, 9, 8, 7, 6 ,5, 4, 3, 2, 1, 0 };
 .section .rodata
-.align XMM_ALIGN
+.balign XMM_ALIGN
 .Lbyte_swap16_mask:
 	.byte	15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
 

module/icp/asm-x86_64/modes/ghash-x86_64.S

@@ -188,7 +188,7 @@ ENTRY_ALIGN(gcm_init_htab_avx, 32)
 	vpxor	%xmm2,%xmm6,%xmm6
 	movq	$4,%r10
 	jmp	.Linit_start_avx
-.align	32
+.balign	32
 .Linit_loop_avx:
 	vpalignr	$8,%xmm3,%xmm4,%xmm5
 	vmovdqu	%xmm5,-16(%rdi)
@@ -386,7 +386,7 @@ ENTRY_ALIGN(gcm_ghash_avx, 32)
 	subq	$0x80,%rcx
 	jmp	.Loop8x_avx
 
-.align	32
+.balign	32
 .Loop8x_avx:
 	vpunpckhqdq	%xmm15,%xmm15,%xmm8
 	vmovdqu	112(%rdx),%xmm14
@@ -506,7 +506,7 @@ ENTRY_ALIGN(gcm_ghash_avx, 32)
 	addq	$0x80,%rcx
 	jmp	.Ltail_no_xor_avx
 
-.align	32
+.balign	32
 .Lshort_avx:
 	vmovdqu	-16(%rdx,%rcx,1),%xmm14
 	leaq	(%rdx,%rcx,1),%rdx
@@ -610,7 +610,7 @@ ENTRY_ALIGN(gcm_ghash_avx, 32)
 	subq	$0x10,%rcx
 	jmp	.Ltail_avx
 
-.align	32
+.balign	32
 .Ltail_avx:
 	vpxor	%xmm10,%xmm15,%xmm15
 .Ltail_no_xor_avx:
@@ -658,7 +658,7 @@ SET_SIZE(gcm_ghash_avx)
 #endif /* !_WIN32 || _KERNEL */
 
 SECTION_STATIC
-.align	64
+.balign	64
 .Lbswap_mask:
 .byte	15,14,13,12,11,10,9,8,7,6,5,4,3,2,1,0
 .L0x1c2_polynomial:
@@ -667,7 +667,7 @@ SECTION_STATIC
 .long	7,0,7,0
 .L7_mask_poly:
 .long	7,0,450,0
-.align	64
+.balign	64
 SET_OBJ(.Lrem_4bit)
 .Lrem_4bit:
 .long	0,0,0,471859200,0,943718400,0,610271232
@@ -710,7 +710,7 @@ SET_OBJ(.Lrem_8bit)
 .value	0xBBF0,0xBA32,0xB874,0xB9B6,0xBCF8,0xBD3A,0xBF7C,0xBEBE
 
 .byte	71,72,65,83,72,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
-.align	64
+.balign	64
 
 /* Mark the stack non-executable. */
 #if defined(__linux__) && defined(__ELF__)

module/icp/asm-x86_64/sha2/sha256_impl.S

@@ -133,7 +133,7 @@ ENTRY_NP(SHA256TransformBlocks)
 	mov	4*7(%rdi),%r11d
 	jmp	.Lloop
 
-.align	16
+.balign	16
 .Lloop:
 	xor	%rdi,%rdi
 	mov	4*0(%rsi),%r12d
@@ -873,7 +873,7 @@ ENTRY_NP(SHA256TransformBlocks)
 
 	add	%r14d,%eax			# h+=Maj(a,b,c)
 	jmp	.Lrounds_16_xx
-.align	16
+.balign	16
 .Lrounds_16_xx:
 	mov	4(%rsp),%r13d
 	mov	56(%rsp),%r12d
@@ -2064,7 +2064,7 @@ ENTRY_NP(SHA256TransformBlocks)
 SET_SIZE(SHA256TransformBlocks)
 
 .section .rodata
-.align	64
+.balign	64
 SET_OBJ(K256)
 K256:
 	.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5

module/icp/asm-x86_64/sha2/sha512_impl.S

@@ -134,7 +134,7 @@ ENTRY_NP(SHA512TransformBlocks)
 	mov	8*7(%rdi),%r11
 	jmp	.Lloop
 
-.align	16
+.balign	16
 .Lloop:
 	xor	%rdi,%rdi
 	mov	8*0(%rsi),%r12
@@ -874,7 +874,7 @@ ENTRY_NP(SHA512TransformBlocks)
 
 	add	%r14,%rax			# h+=Maj(a,b,c)
 	jmp	.Lrounds_16_xx
-.align	16
+.balign	16
 .Lrounds_16_xx:
 	mov	8(%rsp),%r13
 	mov	112(%rsp),%r12
@@ -2065,7 +2065,7 @@ ENTRY_NP(SHA512TransformBlocks)
 SET_SIZE(SHA512TransformBlocks)
 
 .section .rodata
-.align	64
+.balign	64
 SET_OBJ(K512)
 K512:
 	.quad	0x428a2f98d728ae22,0x7137449123ef65cd

module/lua/setjmp/setjmp_aarch64.S

@@ -35,7 +35,7 @@
 #define	ENTRY(sym) \
 	.text; \
 	.globl	sym; \
-	.align	2; \
+	.balign	2; \
 	.type	sym,#function; \
 sym:
 

module/lua/setjmp/setjmp_arm.S

@@ -40,7 +40,7 @@
 #define	ENTRY(x) \
 	.text; \
 	.syntax unified; \
-	.align 2; \
+	.balign 2; \
 	.global x; \
 	.type x,#function; \
 	_FUNC_MODE; \

module/lua/setjmp/setjmp_i386.S

@@ -25,7 +25,7 @@
 
 #define	ENTRY(x) \
 	.text; \
-	.align	8; \
+	.balign	8; \
 	.globl	x; \
 	.type	x, @function; \
 x:

module/lua/setjmp/setjmp_ppc.S

@@ -54,7 +54,7 @@
 #ifdef PPC64_ELF_ABI_v2
 
 #define	ENTRY(name) \
-	.align 2 ; \
+	.balign 2 ; \
 	.type name,@function; \
 	.weak name; \
 name:
@@ -64,7 +64,7 @@ name:
 #define	XGLUE(a,b) a##b
 #define	GLUE(a,b) XGLUE(a,b)
 #define	ENTRY(name) \
-	.align 2 ; \
+	.balign 2 ; \
 	.weak name; \
 	.weak GLUE(.,name); \
 	.pushsection ".opd","aw"; \

module/lua/setjmp/setjmp_sparc64.S

@@ -50,7 +50,7 @@
 
 #define	ENTRY(x)		\
 	.text ;			\
-	.align 32 ;		\
+	.balign 32 ;		\
 	.globl	x ;		\
 	.type	x,@function ;	\
 x: