internal/bytealg: share code for equal functions on arm

Move the shared code into byteal.memeqbody. This will allow to implement
optimizations (e.g. for #29001) in a single function.

Change-Id: Iaa34ddeb7068d92c35a8b4e581b7fd92da56535c
Reviewed-on: https://go-review.googlesource.com/c/go/+/166677
Run-TryBot: Tobias Klauser <tobias.klauser@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>

src/cmd/vet/all/whitelist/arm.txt

@@ -12,3 +12,4 @@ runtime/tls_arm.s: [arm] load_g: function load_g missing Go declaration
 runtime/tls_arm.s: [arm] _initcgo: function _initcgo missing Go declaration
 
 runtime/internal/atomic/asm_arm.s: [arm] cas: function cas missing Go declaration
+internal/bytealg/equal_arm.s: [arm] Equal: invalid MOVW of ret+24(FP); bool is 1-byte value

src/internal/bytealg/equal_arm.s

@@ -5,7 +5,6 @@
 #include "go_asm.h"
 #include "textflag.h"
 
-// TODO: share code with memequal?
 TEXT ·Equal(SB),NOSPLIT,$0-25
 	MOVW	a_len+4(FP), R1
 	MOVW	b_len+16(FP), R3
@@ -15,63 +14,60 @@ TEXT ·Equal(SB),NOSPLIT,$0-25
 
 	MOVW	a_base+0(FP), R0
 	MOVW	b_base+12(FP), R2
-	ADD	R0, R1		// end
-
-loop:
-	CMP	R0, R1
-	B.EQ	equal		// reached the end
-	MOVBU.P	1(R0), R4
-	MOVBU.P	1(R2), R5
-	CMP	R4, R5
-	B.EQ	loop
-
+	MOVW	$ret+24(FP), R7
+	B	memeqbody<>(SB)
 notequal:
 	MOVW	$0, R0
 	MOVBU	R0, ret+24(FP)
 	RET
 
-equal:
-	MOVW	$1, R0
-	MOVBU	R0, ret+24(FP)
-	RET
-
 // memequal(a, b unsafe.Pointer, size uintptr) bool
 TEXT runtime·memequal(SB),NOSPLIT|NOFRAME,$0-13
-	MOVW	a+0(FP), R1
+	MOVW	a+0(FP), R0
 	MOVW	b+4(FP), R2
-	MOVW	size+8(FP), R3
-	ADD	R1, R3, R6
+	CMP	R0, R2
+	B.EQ	eq
+	MOVW	size+8(FP), R1
+	MOVW	$ret+12(FP), R7
+	B	memeqbody<>(SB)
+eq:
 	MOVW	$1, R0
 	MOVB	R0, ret+12(FP)
-	CMP	R1, R2
-	RET.EQ
-loop:
-	CMP	R1, R6
-	RET.EQ
-	MOVBU.P	1(R1), R4
-	MOVBU.P	1(R2), R5
-	CMP	R4, R5
-	BEQ	loop
-
-	MOVW	$0, R0
-	MOVB	R0, ret+12(FP)
 	RET
 
 // memequal_varlen(a, b unsafe.Pointer) bool
-TEXT runtime·memequal_varlen(SB),NOSPLIT,$16-9
+TEXT runtime·memequal_varlen(SB),NOSPLIT|NOFRAME,$0-9
 	MOVW	a+0(FP), R0
-	MOVW	b+4(FP), R1
-	CMP	R0, R1
-	BEQ	eq
-	MOVW	4(R7), R2    // compiler stores size at offset 4 in the closure
-	MOVW	R0, 4(R13)
-	MOVW	R1, 8(R13)
-	MOVW	R2, 12(R13)
-	BL	runtime·memequal(SB)
-	MOVB	16(R13), R0
-	MOVB	R0, ret+8(FP)
-	RET
+	MOVW	b+4(FP), R2
+	CMP	R0, R2
+	B.EQ	eq
+	MOVW	4(R7), R1    // compiler stores size at offset 4 in the closure
+	MOVW	$ret+8(FP), R7
+	B	memeqbody<>(SB)
 eq:
 	MOVW	$1, R0
 	MOVB	R0, ret+8(FP)
 	RET
+
+// Input:
+// R0: data of a
+// R1: length
+// R2: data of b
+// R7: points to return value
+TEXT memeqbody<>(SB),NOSPLIT|NOFRAME,$0-0
+	ADD	R0, R1		// end
+loop:
+	CMP	R0, R1
+	B.EQ	equal		// reached the end
+	MOVBU.P	1(R0), R4
+	MOVBU.P	1(R2), R5
+	CMP	R4, R5
+	B.EQ	loop
+notequal:
+	MOVW	$0, R0
+	MOVB	R0, (R7)
+	RET
+equal:
+	MOVW	$1, R0
+	MOVB	R0, (R7)
+	RET