[PATCH 3/3] crypto: arm/chacha-scalar - switch to common rev_32 macro

[Ard Biesheuvel]

Drop the local definition of a byte swapping macro and use the common
one instead.

Signed-off-by: Ard Biesheuvel <ardb at kernel.org>
---
 arch/arm/crypto/chacha-scalar-core.S | 43 ++++++--------------
 1 file changed, 13 insertions(+), 30 deletions(-)

diff --git a/arch/arm/crypto/chacha-scalar-core.S b/arch/arm/crypto/chacha-scalar-core.S
index 2985b80a45b5..5d06153e8b05 100644
--- a/arch/arm/crypto/chacha-scalar-core.S
+++ b/arch/arm/crypto/chacha-scalar-core.S
@@ -41,32 +41,15 @@
 	X14	.req	r12
 	X15	.req	r14
 
-.macro __rev		out, in,  t0, t1, t2
-.if __LINUX_ARM_ARCH__ >= 6
-	rev		\out, \in
-.else
-	lsl		\t0, \in, #24
-	and		\t1, \in, #0xff00
-	and		\t2, \in, #0xff0000
-	orr		\out, \t0, \in, lsr #24
-	orr		\out, \out, \t1, lsl #8
-	orr		\out, \out, \t2, lsr #8
-.endif
-.endm
-
-.macro _le32_bswap	x,  t0, t1, t2
+.macro _le32_bswap_4x	a, b, c, d,  tmp
 #ifdef __ARMEB__
-	__rev		\x, \x,  \t0, \t1, \t2
+	rev_32		\a,  \tmp
+	rev_32		\b,  \tmp
+	rev_32		\c,  \tmp
+	rev_32		\d,  \tmp
 #endif
 .endm
 
-.macro _le32_bswap_4x	a, b, c, d,  t0, t1, t2
-	_le32_bswap	\a,  \t0, \t1, \t2
-	_le32_bswap	\b,  \t0, \t1, \t2
-	_le32_bswap	\c,  \t0, \t1, \t2
-	_le32_bswap	\d,  \t0, \t1, \t2
-.endm
-
 .macro __ldrd		a, b, src, offset
 #if __LINUX_ARM_ARCH__ >= 6
 	ldrd		\a, \b, [\src, #\offset]
@@ -200,7 +183,7 @@
 	add		X1, X1, r9
 	add		X2, X2, r10
 	add		X3, X3, r11
-	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	_le32_bswap_4x	X0, X1, X2, X3,  r8
 	ldmia		r12!, {r8-r11}
 	eor		X0, X0, r8
 	eor		X1, X1, r9
@@ -216,7 +199,7 @@
 	ldmia		r12!, {X0-X3}
 	add		X6, r10, X6, ror #brot
 	add		X7, r11, X7, ror #brot
-	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	_le32_bswap_4x	X4, X5, X6, X7,  r8
 	eor		X4, X4, X0
 	eor		X5, X5, X1
 	eor		X6, X6, X2
@@ -231,7 +214,7 @@
 	add		r1, r1, r9		// x9
 	add		r6, r6, r10		// x10
 	add		r7, r7, r11		// x11
-	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	_le32_bswap_4x	r0, r1, r6, r7,  r8
 	ldmia		r12!, {r8-r11}
 	eor		r0, r0, r8		// x8
 	eor		r1, r1, r9		// x9
@@ -245,7 +228,7 @@
 	add		r3, r9, r3, ror #drot	// x13
 	add		r4, r10, r4, ror #drot	// x14
 	add		r5, r11, r5, ror #drot	// x15
-	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	_le32_bswap_4x	r2, r3, r4, r5,  r9
 	  ldr		r9, [sp, #72]		// load LEN
 	eor		r2, r2, r0		// x12
 	eor		r3, r3, r1		// x13
@@ -301,7 +284,7 @@
 	add		X1, X1, r9
 	add		X2, X2, r10
 	add		X3, X3, r11
-	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	_le32_bswap_4x	X0, X1, X2, X3,  r8
 	stmia		r14!, {X0-X3}
 
 	// Save keystream for x4-x7
@@ -311,7 +294,7 @@
 	add		X5, r9, X5, ror #brot
 	add		X6, r10, X6, ror #brot
 	add		X7, r11, X7, ror #brot
-	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	_le32_bswap_4x	X4, X5, X6, X7,  r8
 	  add		r8, sp, #64
 	stmia		r14!, {X4-X7}
 
@@ -323,7 +306,7 @@
 	add		r1, r1, r9		// x9
 	add		r6, r6, r10		// x10
 	add		r7, r7, r11		// x11
-	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	_le32_bswap_4x	r0, r1, r6, r7,  r8
 	stmia		r14!, {r0,r1,r6,r7}
 	__ldrd		r8, r9, sp, 144
 	__ldrd		r10, r11, sp, 152
@@ -331,7 +314,7 @@
 	add		r3, r9, r3, ror #drot	// x13
 	add		r4, r10, r4, ror #drot	// x14
 	add		r5, r11, r5, ror #drot	// x15
-	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	_le32_bswap_4x	r2, r3, r4, r5,  r9
 	stmia		r14, {r2-r5}
 
 	// Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
-- 
2.17.1