Fix comment syntax

Reviewed-by: Hugo Landau <hlandau@openssl.org>
Reviewed-by: Tom Cosgrove <tom.cosgrove@arm.com>
(Merged from https://github.com/openssl/openssl/pull/23072)

(cherry picked from commit 1fda942e8cd425263433094bf8714a80c05bcb2c)

1 files changed, 158 insertions, 158 deletions

diff --git a/crypto/ec/asm/ecp_sm2p256-armv8.pl b/crypto/ec/asm/ecp_sm2p256-armv8.pl
index 50950865e4..62fadc0454 100644
--- a/crypto/ec/asm/ecp_sm2p256-armv8.pl
+++ b/crypto/ec/asm/ecp_sm2p256-armv8.pl
@@ -28,44 +28,44 @@ my ($t4,$t5,$t6,$t7,$t8)=map("x$_",(15..19));
 sub bn_mod_add() {
 	my $mod = shift;
 $code.=<<___;
-	# Load inputs
+	// Load inputs
 	ldp $s0,$s1,[x1]
 	ldp $s2,$s3,[x1,#16]
 	ldp $s4,$s5,[x2]
 	ldp $s6,$s7,[x2,#16]
 
-	# Addition
+	// Addition
 	adds $s0,$s0,$s4
 	adcs $s1,$s1,$s5
 	adcs $s2,$s2,$s6
 	adcs $s3,$s3,$s7
 	adc $t4,xzr,xzr
 
-	# Load polynomial
+	// Load polynomial
 	adr x2,$mod
 	ldp $s4,$s5,[x2]
 	ldp $s6,$s7,[x2,#16]
 
-	# Backup Addition
+	// Backup Addition
 	mov $t0,$s0
 	mov $t1,$s1
 	mov $t2,$s2
 	mov $t3,$s3
 
-	# Sub polynomial
+	// Sub polynomial
 	subs $t0,$t0,$s4
 	sbcs $t1,$t1,$s5
 	sbcs $t2,$t2,$s6
 	sbcs $t3,$t3,$s7
 	sbcs $t4,$t4,xzr
 
-	# Select based on carry
+	// Select based on carry
 	csel $s0,$s0,$t0,cc
 	csel $s1,$s1,$t1,cc
 	csel $s2,$s2,$t2,cc
 	csel $s3,$s3,$t3,cc
 
-	# Store results
+	// Store results
 	stp $s0,$s1,[x0]
 	stp $s2,$s3,[x0,#16]
 ___
@@ -74,44 +74,44 @@ ___
 sub bn_mod_sub() {
 	my $mod = shift;
 $code.=<<___;
-	# Load inputs
+	// Load inputs
 	ldp $s0,$s1,[x1]
 	ldp $s2,$s3,[x1,#16]
 	ldp $s4,$s5,[x2]
 	ldp $s6,$s7,[x2,#16]
 
-	# Subtraction
+	// Subtraction
 	subs $s0,$s0,$s4
 	sbcs $s1,$s1,$s5
 	sbcs $s2,$s2,$s6
 	sbcs $s3,$s3,$s7
 	sbc $t4,xzr,xzr
 
-	# Load polynomial
+	// Load polynomial
 	adr x2,$mod
 	ldp $s4,$s5,[x2]
 	ldp $s6,$s7,[x2,#16]
 
-	# Backup subtraction
+	// Backup subtraction
 	mov $t0,$s0
 	mov $t1,$s1
 	mov $t2,$s2
 	mov $t3,$s3
 
-	# Add polynomial
+	// Add polynomial
 	adds $t0,$t0,$s4
 	adcs $t1,$t1,$s5
 	adcs $t2,$t2,$s6
 	adcs $t3,$t3,$s7
 	tst $t4,$t4
 
-	# Select based on carry
+	// Select based on carry
 	csel $s0,$s0,$t0,eq
 	csel $s1,$s1,$t1,eq
 	csel $s2,$s2,$t2,eq
 	csel $s3,$s3,$t3,eq
 
-	# Store results
+	// Store results
 	stp $s0,$s1,[x0]
 	stp $s2,$s3,[x0,#16]
 ___
@@ -120,38 +120,38 @@ ___
 sub bn_mod_div_by_2() {
 	my $mod = shift;
 $code.=<<___;
-	# Load inputs
+	// Load inputs
 	ldp $s0,$s1,[x1]
 	ldp $s2,$s3,[x1,#16]
 
-	# Save the least significant bit
+	// Save the least significant bit
 	mov $t0,$s0
 
-	# Right shift 1
+	// Right shift 1
 	extr $s0,$s1,$s0,#1
 	extr $s1,$s2,$s1,#1
 	extr $s2,$s3,$s2,#1
 	lsr $s3,$s3,#1
 
-	# Load mod
+	// Load mod
 	adr x2,$mod
 	ldp $s4,$s5,[x2]
 	ldp $s6,$s7,[x2,#16]
 
-	# Parity check
+	// Parity check
 	tst $t0,#1
 	csel $s4,xzr,$s4,eq
 	csel $s5,xzr,$s5,eq
 	csel $s6,xzr,$s6,eq
 	csel $s7,xzr,$s7,eq
 
-	# Add
+	// Add
 	adds $s0,$s0,$s4
 	adcs $s1,$s1,$s5
 	adcs $s2,$s2,$s6
 	adc $s3,$s3,$s7
 
-	# Store results
+	// Store results
 	stp $s0,$s1,[x0]
 	stp $s2,$s3,[x0,#16]
 ___
@@ -183,17 +183,17 @@ $code.=<<___;
 .align	5
 bn_rshift1:
 	AARCH64_VALID_CALL_TARGET
-	# Load inputs
+	// Load inputs
 	ldp $s0,$s1,[x0]
 	ldp $s2,$s3,[x0,#16]
 
-	# Right shift
+	// Right shift
 	extr $s0,$s1,$s0,#1
 	extr $s1,$s2,$s1,#1
 	extr $s2,$s3,$s2,#1
 	lsr $s3,$s3,#1
 
-	# Store results
+	// Store results
 	stp $s0,$s1,[x0]
 	stp $s2,$s3,[x0,#16]
 
@@ -206,19 +206,19 @@ bn_rshift1:
 .align	5
 bn_sub:
 	AARCH64_VALID_CALL_TARGET
-	# Load inputs
+	// Load inputs
 	ldp $s0,$s1,[x1]
 	ldp $s2,$s3,[x1,#16]
 	ldp $s4,$s5,[x2]
 	ldp $s6,$s7,[x2,#16]
 
-	# Subtraction
+	// Subtraction
 	subs $s0,$s0,$s4
 	sbcs $s1,$s1,$s5
 	sbcs $s2,$s2,$s6
 	sbc $s3,$s3,$s7
 
-	# Store results
+	// Store results
 	stp $s0,$s1,[x0]
 	stp $s2,$s3,[x0,#16]
 
@@ -255,11 +255,11 @@ $code.=<<___;
 .align	5
 ecp_sm2p256_mul_by_3:
 	AARCH64_VALID_CALL_TARGET
-	# Load inputs
+	// Load inputs
 	ldp $s0,$s1,[x1]
 	ldp $s2,$s3,[x1,#16]
 
-	# 2*a
+	// 2*a
 	adds $s0,$s0,$s0
 	adcs $s1,$s1,$s1
 	adcs $s2,$s2,$s2
@@ -271,7 +271,7 @@ ecp_sm2p256_mul_by_3:
 	mov $t2,$s2
 	mov $t3,$s3
 
-	# Sub polynomial
+	// Sub polynomial
 	adr x2,.Lpoly
 	ldp $s4,$s5,[x2]
 	ldp $s6,$s7,[x2,#16]
@@ -287,7 +287,7 @@ ecp_sm2p256_mul_by_3:
 	csel $s3,$s3,$t3,cs
 	eor $t4,$t4,$t4
 
-	# 3*a
+	// 3*a
 	ldp $s4,$s5,[x1]
 	ldp $s6,$s7,[x1,#16]
 	adds $s0,$s0,$s4
@@ -301,7 +301,7 @@ ecp_sm2p256_mul_by_3:
 	mov $t2,$s2
 	mov $t3,$s3
 
-	# Sub polynomial
+	// Sub polynomial
 	adr x2,.Lpoly
 	ldp $s4,$s5,[x2]
 	ldp $s6,$s7,[x2,#16]
@@ -316,7 +316,7 @@ ecp_sm2p256_mul_by_3:
 	csel $s2,$s2,$t2,cs
 	csel $s3,$s3,$t3,cs
 
-	# Store results
+	// Store results
 	stp $s0,$s1,[x0]
 	stp $s2,$s3,[x0,#16]
 
@@ -360,45 +360,45 @@ $code.=<<___;
 .size ecp_sm2p256_sub_mod_ord,.-ecp_sm2p256_sub_mod_ord
 
 .macro RDC
-	# a = |  s7   | ... | s0  |, where si are 64-bit quantities
-	#   = |a15|a14| ... |a1|a0|, where ai are 32-bit quantities
-	# |    s7     |    s6     |    s5     |    s4     |
-	# | a15 | a14 | a13 | a12 | a11 | a10 | a9  | a8  |
-	# |    s3     |    s2     |    s1     |    s0     |
-	# | a7  | a6  | a5  | a4  | a3  | a2  | a1  | a0  |
-	# =================================================
-	# | a8  | a11 | a10 | a9  | a8  |   0 |    s4     | (+)
-	# | a9  | a15 |    s6     | a11 |   0 | a10 | a9  | (+)
-	# | a10 |   0 | a14 | a13 | a12 |   0 |    s5     | (+)
-	# | a11 |   0 |    s7     | a13 |   0 | a12 | a11 | (+)
-	# | a12 |   0 |    s7     | a13 |   0 |    s6     | (+)
-	# | a12 |   0 |   0 | a15 | a14 |   0 | a14 | a13 | (+)
-	# | a13 |   0 |   0 |   0 | a15 |   0 | a14 | a13 | (+)
-	# | a13 |   0 |   0 |   0 |   0 |   0 |    s7     | (+)
-	# | a14 |   0 |   0 |   0 |   0 |   0 |    s7     | (+)
-	# | a14 |   0 |   0 |   0 |   0 |   0 |   0 | a15 | (+)
-	# | a15 |   0 |   0 |   0 |   0 |   0 |   0 | a15 | (+)
-	# | a15 |   0 |   0 |   0 |   0 |   0 |   0 |   0 | (+)
-	# |    s7     |   0 |   0 |   0 |   0 |   0 |   0 | (+)
-	# |   0 |   0 |   0 |   0 |   0 | a8  |   0 |   0 | (-)
-	# |   0 |   0 |   0 |   0 |   0 | a9  |   0 |   0 | (-)
-	# |   0 |   0 |   0 |   0 |   0 | a13 |   0 |   0 | (-)
-	# |   0 |   0 |   0 |   0 |   0 | a14 |   0 |   0 | (-)
-	# | U[7]| U[6]| U[5]| U[4]| U[3]| U[2]| U[1]| U[0]|
-	# |    V[3]   |    V[2]   |    V[1]   |    V[0]   |
-
-	# 1. 64-bit addition
-	# t2=s6+s7+s7
+	// a = |  s7   | ... | s0  |, where si are 64-bit quantities
+	//   = |a15|a14| ... |a1|a0|, where ai are 32-bit quantities
+	// |    s7     |    s6     |    s5     |    s4     |
+	// | a15 | a14 | a13 | a12 | a11 | a10 | a9  | a8  |
+	// |    s3     |    s2     |    s1     |    s0     |
+	// | a7  | a6  | a5  | a4  | a3  | a2  | a1  | a0  |
+	// =================================================
+	// | a8  | a11 | a10 | a9  | a8  |   0 |    s4     | (+)
+	// | a9  | a15 |    s6     | a11 |   0 | a10 | a9  | (+)
+	// | a10 |   0 | a14 | a13 | a12 |   0 |    s5     | (+)
+	// | a11 |   0 |    s7     | a13 |   0 | a12 | a11 | (+)
+	// | a12 |   0 |    s7     | a13 |   0 |    s6     | (+)
+	// | a12 |   0 |   0 | a15 | a14 |   0 | a14 | a13 | (+)
+	// | a13 |   0 |   0 |   0 | a15 |   0 | a14 | a13 | (+)
+	// | a13 |   0 |   0 |   0 |   0 |   0 |    s7     | (+)
+	// | a14 |   0 |   0 |   0 |   0 |   0 |    s7     | (+)
+	// | a14 |   0 |   0 |   0 |   0 |   0 |   0 | a15 | (+)
+	// | a15 |   0 |   0 |   0 |   0 |   0 |   0 | a15 | (+)
+	// | a15 |   0 |   0 |   0 |   0 |   0 |   0 |   0 | (+)
+	// |    s7     |   0 |   0 |   0 |   0 |   0 |   0 | (+)
+	// |   0 |   0 |   0 |   0 |   0 | a8  |   0 |   0 | (-)
+	// |   0 |   0 |   0 |   0 |   0 | a9  |   0 |   0 | (-)
+	// |   0 |   0 |   0 |   0 |   0 | a13 |   0 |   0 | (-)
+	// |   0 |   0 |   0 |   0 |   0 | a14 |   0 |   0 | (-)
+	// | U[7]| U[6]| U[5]| U[4]| U[3]| U[2]| U[1]| U[0]|
+	// |    V[3]   |    V[2]   |    V[1]   |    V[0]   |
+
+	// 1. 64-bit addition
+	// t2=s6+s7+s7
 	adds $t2,$s6,$s7
 	adcs $t1,xzr,xzr
 	adds $t2,$t2,$s7
 	adcs $t1,$t1,xzr
-	# t3=s4+s5+t2
+	// t3=s4+s5+t2
 	adds $t3,$s4,$t2
 	adcs $t4,$t1,xzr
 	adds $t3,$t3,$s5
 	adcs $t4,$t4,xzr
-	# sum
+	// sum
 	adds $s0,$s0,$t3
 	adcs $s1,$s1,$t4
 	adcs $s2,$s2,$t2
@@ -410,7 +410,7 @@ $code.=<<___;
 	stp $s0,$s1,[sp,#32]
 	stp $s2,$s3,[sp,#48]
 
-	# 2. 64-bit to 32-bit spread
+	// 2. 64-bit to 32-bit spread
 	mov $t1,#0xffffffff
 	mov $s0,$s4
 	mov $s1,$s5
@@ -425,7 +425,7 @@ $code.=<<___;
 	lsr $s6,$s6,#32 // a13
 	lsr $s7,$s7,#32 // a15
 
-	# 3. 32-bit addition
+	// 3. 32-bit addition
 	add $t1,$a14,$a12  // t1 <- a12 + a14
 	add $t2,$a15,$a13  // t2 <- a13 + a15
 	add $t3,$a8,$a9    // t3 <- a8 + a9
@@ -446,53 +446,53 @@ $code.=<<___;
 	add $a11,$a11,$t2  // a11 <- a9 + a11 + 2*(a13 + a15)
 	add $t1,$t1,$t4    // t1 <- a10 + a12 + 2*a14
 
-	# U[0]  s5	a9 + a11 + 2*(a13 + a15)
-	# U[1]  t1	a10 + a12 + 2*a14
-	# U[2] -t3	a8 + a9 + a13 + a14
-	# U[3]  s2	a8 + a11 + a12 + 2*a13 + a14 + a15
-	# U[4]  s4	a9 + a13 + a15
-	# U[5]  t4	a10 + a14
-	# U[6]  s7	a11 + a15
-	# U[7]  s1	a8 + a9 + a10 + a11 + 2*(a12 + a13 + a14 + a15)
+	// U[0]  s5	a9 + a11 + 2*(a13 + a15)
+	// U[1]  t1	a10 + a12 + 2*a14
+	// U[2] -t3	a8 + a9 + a13 + a14
+	// U[3]  s2	a8 + a11 + a12 + 2*a13 + a14 + a15
+	// U[4]  s4	a9 + a13 + a15
+	// U[5]  t4	a10 + a14
+	// U[6]  s7	a11 + a15
+	// U[7]  s1	a8 + a9 + a10 + a11 + 2*(a12 + a13 + a14 + a15)
 
-	# 4. 32-bit to 64-bit
+	// 4. 32-bit to 64-bit
 	lsl $s0,$t1,#32
 	extr $t1,$s2,$t1,#32
 	extr $s2,$t4,$s2,#32
 	extr $t4,$s1,$t4,#32
 	lsr $s1,$s1,#32
 
-	# 5. 64-bit addition
+	// 5. 64-bit addition
 	adds $s5,$s5,$s0
 	adcs $t1,$t1,xzr
 	adcs $s4,$s4,$s2
 	adcs $s7,$s7,$t4
 	adcs $t0,$t0,$s1
 
-	# V[0]	s5
-	# V[1]	t1
-	# V[2]	s4
-	# V[3]	s7
-	# carry	t0
-	# sub	t3
+	// V[0]	s5
+	// V[1]	t1
+	// V[2]	s4
+	// V[3]	s7
+	// carry	t0
+	// sub	t3
 
-	# 5. Process s0-s3
+	// 5. Process s0-s3
 	ldp $s0,$s1,[sp,#32]
 	ldp $s2,$s3,[sp,#48]
-	# add with V0-V3
+	// add with V0-V3
 	adds $s0,$s0,$s5
 	adcs $s1,$s1,$t1
 	adcs $s2,$s2,$s4
 	adcs $s3,$s3,$s7
 	adcs $t0,$t0,xzr
-	# sub with t3
+	// sub with t3
 	subs $s1,$s1,$t3
 	sbcs $s2,$s2,xzr
 	sbcs $s3,$s3,xzr
 	sbcs $t0,$t0,xzr
 
-	# 6. MOD
-	# First Mod
+	// 6. MOD
+	// First Mod
 	lsl $t1,$t0,#32
 	subs $t2,$t1,$t0
 
@@ -501,8 +501,8 @@ $code.=<<___;
 	adcs $s2,$s2,xzr
 	adcs $s3,$s3,$t1
 
-	# Last Mod
-	# return y - p if y > p else y
+	// Last Mod
+	// return y - p if y > p else y
 	mov $s4,$s0
 	mov $s5,$s1
 	mov $s6,$s2
@@ -533,44 +533,44 @@ $code.=<<___;
 .align	5
 ecp_sm2p256_mul:
 	AARCH64_SIGN_LINK_REGISTER
-	# Store scalar registers
+	// Store scalar registers
 	stp x29,x30,[sp,#-80]!
 	add x29,sp,#0
 	stp x16,x17,[sp,#16]
 	stp x18,x19,[sp,#64]
 
-	# Load inputs
+	// Load inputs
 	ldp $s0,$s1,[x1]
 	ldp $s2,$s3,[x1,#16]
 	ldp $s4,$s5,[x2]
 	ldp $s6,$s7,[x2,#16]
 
-### multiplication ###
-	# ========================
-	#             s3 s2 s1 s0
-	# *           s7 s6 s5 s4
-	# ------------------------
-	# +           s0 s0 s0 s0
-	#              *  *  *  *
-	#             s7 s6 s5 s4
-	#          s1 s1 s1 s1
-	#           *  *  *  *
-	#          s7 s6 s5 s4
-	#       s2 s2 s2 s2
-	#        *  *  *  *
-	#       s7 s6 s5 s4
-	#    s3 s3 s3 s3
-	#     *  *  *  *
-	#    s7 s6 s5 s4
-	# ------------------------
-	# s7 s6 s5 s4 s3 s2 s1 s0
-	# ========================
-
-### s0*s4 ###
+// ### multiplication ###
+	// ========================
+	//             s3 s2 s1 s0
+	// *           s7 s6 s5 s4
+	// ------------------------
+	// +           s0 s0 s0 s0
+	//              *  *  *  *
+	//             s7 s6 s5 s4
+	//          s1 s1 s1 s1
+	//           *  *  *  *
+	//          s7 s6 s5 s4
+	//       s2 s2 s2 s2
+	//        *  *  *  *
+	//       s7 s6 s5 s4
+	//    s3 s3 s3 s3
+	//     *  *  *  *
+	//    s7 s6 s5 s4
+	// ------------------------
+	// s7 s6 s5 s4 s3 s2 s1 s0
+	// ========================
+
+// ### s0*s4 ###
 	mul $t5,$s0,$s4
 	umulh $t2,$s0,$s4
 
-### s1*s4 + s0*s5 ###
+// ### s1*s4 + s0*s5 ###
 	mul $t0,$s1,$s4
 	umulh $t1,$s1,$s4
 	adds $t2,$t2,$t0
@@ -582,7 +582,7 @@ ecp_sm2p256_mul:
 	adcs $t3,$t3,$t1
 	adcs $t4,xzr,xzr
 
-### s2*s4 + s1*s5 + s0*s6 ###
+// ### s2*s4 + s1*s5 + s0*s6 ###
 	mul $t0,$s2,$s4
 	umulh $t1,$s2,$s4
 	adds $t3,$t3,$t0
@@ -600,7 +600,7 @@ ecp_sm2p256_mul:
 	adcs $t4,$t4,$t1
 	adcs $t6,$t6,xzr
 
-### s3*s4 + s2*s5 + s1*s6 + s0*s7 ###
+// ### s3*s4 + s2*s5 + s1*s6 + s0*s7 ###
 	mul $t0,$s3,$s4
 	umulh $t1,$s3,$s4
 	adds $t4,$t4,$t0
@@ -625,7 +625,7 @@ ecp_sm2p256_mul:
 	adcs $t6,$t6,$t1
 	adcs $t7,$t7,xzr
 
-### s3*s5 + s2*s6 + s1*s7 ###
+// ### s3*s5 + s2*s6 + s1*s7 ###
 	mul $t0,$s3,$s5
 	umulh $t1,$s3,$s5
 	adds $t6,$t6,$t0
@@ -644,7 +644,7 @@ ecp_sm2p256_mul:
 	adcs $t7,$t7,$t1
 	adcs $t8,$t8,xzr
 
-### s3*s6 + s2*s7 ###
+// ### s3*s6 + s2*s7 ###
 	mul $t0,$s3,$s6
 	umulh $t1,$s3,$s6
 	adds $t7,$t7,$t0
@@ -657,7 +657,7 @@ ecp_sm2p256_mul:
 	adcs $t8,$t8,$t1
 	adcs $t6,$t6,xzr
 
-### s3*s7 ###
+// ### s3*s7 ###
 	mul $t0,$s3,$s7
 	umulh $t1,$s3,$s7
 	adds $s6,$t8,$t0
@@ -668,15 +668,15 @@ ecp_sm2p256_mul:
 	mov $s2,$t3
 	mov $s3,$t4
 
-	# result of mul: s7 s6 s5 s4 s3 s2 s1 s0
+	// result of mul: s7 s6 s5 s4 s3 s2 s1 s0
 
-### Reduction ###
+// ### Reduction ###
 	RDC
 
 	stp $s0,$s1,[x0]
 	stp $s2,$s3,[x0,#16]
 
-	# Restore scalar registers
+	// Restore scalar registers
 	ldp x16,x17,[sp,#16]
 	ldp x18,x19,[sp,#64]
 	ldp x29,x30,[sp],#80
@@ -692,48 +692,48 @@ ecp_sm2p256_mul:
 
 ecp_sm2p256_sqr:
 	AARCH64_SIGN_LINK_REGISTER
-	# Store scalar registers
+	// Store scalar registers
 	stp x29,x30,[sp,#-80]!
 	add x29,sp,#0
 	stp x16,x17,[sp,#16]
 	stp x18,x19,[sp,#64]
 
-	# Load inputs
+	// Load inputs
 	ldp $s4,$s5,[x1]
 	ldp $s6,$s7,[x1,#16]
 
-### square ###
-	# ========================
-	#             s7 s6 s5 s4
-	# *           s7 s6 s5 s4
-	# ------------------------
-	# +           s4 s4 s4 s4
-	#              *  *  *  *
-	#             s7 s6 s5 s4
-	#          s5 s5 s5 s5
-	#           *  *  *  *
-	#          s7 s6 s5 s4
-	#       s6 s6 s6 s6
-	#        *  *  *  *
-	#       s7 s6 s5 s4
-	#    s7 s7 s7 s7
-	#     *  *  *  *
-	#    s7 s6 s5 s4
-	# ------------------------
-	# s7 s6 s5 s4 s3 s2 s1 s0
-	# ========================
-
-### s4*s5 ###
+// ### square ###
+	// ========================
+	//             s7 s6 s5 s4
+	// *           s7 s6 s5 s4
+	// ------------------------
+	// +           s4 s4 s4 s4
+	//              *  *  *  *
+	//             s7 s6 s5 s4
+	//          s5 s5 s5 s5
+	//           *  *  *  *
+	//          s7 s6 s5 s4
+	//       s6 s6 s6 s6
+	//        *  *  *  *
+	//       s7 s6 s5 s4
+	//    s7 s7 s7 s7
+	//     *  *  *  *
+	//    s7 s6 s5 s4
+	// ------------------------
+	// s7 s6 s5 s4 s3 s2 s1 s0
+	// ========================
+
+// ### s4*s5 ###
 	mul $s1,$s4,$s5
 	umulh $s2,$s4,$s5
 
-### s4*s6 ###
+// ### s4*s6 ###
 	mul $t0,$s6,$s4
 	umulh $s3,$s6,$s4
 	adds $s2,$s2,$t0
 	adcs $s3,$s3,xzr
 
-### s4*s7 + s5*s6 ###
+// ### s4*s7 + s5*s6 ###
 	mul $t0,$s7,$s4
 	umulh $t1,$s7,$s4
 	adds $s3,$s3,$t0
@@ -745,19 +745,19 @@ ecp_sm2p256_sqr:
 	adcs $s0,$s0,$t1
 	adcs $t2,xzr,xzr
 
-### s5*s7 ###
+// ### s5*s7 ###
 	mul $t0,$s7,$s5
 	umulh $t1,$s7,$s5
 	adds $s0,$s0,$t0
 	adcs $t2,$t2,$t1
 
-### s6*s7 ###
+// ### s6*s7 ###
 	mul $t0,$s7,$s6
 	umulh $t1,$s7,$s6
 	adds $t2,$t2,$t0
 	adcs $t3,$t1,xzr
 
-### 2*(t3,t2,s0,s3,s2,s1) ###
+// ### 2*(t3,t2,s0,s3,s2,s1) ###
 	adds $s1,$s1,$s1
 	adcs $s2,$s2,$s2
 	adcs $s3,$s3,$s3
@@ -766,19 +766,19 @@ ecp_sm2p256_sqr:
 	adcs $t3,$t3,$t3
 	adcs $t4,xzr,xzr
 
-### s4*s4 ###
+// ### s4*s4 ###
 	mul $t5,$s4,$s4
 	umulh $t6,$s4,$s4
 
-### s5*s5 ###
+// ### s5*s5 ###
 	mul $s4,$s5,$s5
 	umulh $s5,$s5,$s5
 
-### s6*s6 ###
+// ### s6*s6 ###
 	mul $t0,$s6,$s6
 	umulh $t1,$s6,$s6
 
-### s7*s7 ###
+// ### s7*s7 ###
 	mul $t7,$s7,$s7
 	umulh $t8,$s7,$s7
 
@@ -796,15 +796,15 @@ ecp_sm2p256_sqr:
 	mov $s6,$t3
 	mov $s7,$t4
 
-	# result of mul: s7 s6 s5 s4 s3 s2 s1 s0
+	// result of mul: s7 s6 s5 s4 s3 s2 s1 s0
 
-### Reduction ###
+// ### Reduction ###
 	RDC
 
 	stp $s0,$s1,[x0]
 	stp $s2,$s3,[x0,#16]
 
-	# Restore scalar registers
+	// Restore scalar registers
 	ldp x16,x17,[sp,#16]
 	ldp x18,x19,[sp,#64]
 	ldp x29,x30,[sp],#80