--- zzzz-none-000/linux-3.10.107/arch/powerpc/lib/memcpy_power7.S	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/arch/powerpc/lib/memcpy_power7.S	2021-02-04 17:41:59.000000000 +0000
@@ -20,18 +20,27 @@
 #include <asm/ppc_asm.h>
 
 _GLOBAL(memcpy_power7)
+
+#ifdef __BIG_ENDIAN__
+#define LVS(VRT,RA,RB)		lvsl	VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRA,VRB,VRC
+#else
+#define LVS(VRT,RA,RB)		lvsr	VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRB,VRA,VRC
+#endif
+
 #ifdef CONFIG_ALTIVEC
 	cmpldi	r5,16
 	cmpldi	cr1,r5,4096
 
-	std	r3,48(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 
 	blt	.Lshort_copy
 	bgt	cr1,.Lvmx_copy
 #else
 	cmpldi	r5,16
 
-	std	r3,48(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 
 	blt	.Lshort_copy
 #endif
@@ -207,7 +216,7 @@
 	lbz	r0,0(r4)
 	stb	r0,0(r3)
 
-15:	ld	r3,48(r1)
+15:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 	blr
 
 .Lunwind_stack_nonvmx_copy:
@@ -217,16 +226,16 @@
 #ifdef CONFIG_ALTIVEC
 .Lvmx_copy:
 	mflr	r0
-	std	r4,56(r1)
-	std	r5,64(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	.enter_vmx_copy
+	bl	enter_vmx_copy
 	cmpwi	cr1,r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STACKFRAMESIZE+48(r1)
-	ld	r4,STACKFRAMESIZE+56(r1)
-	ld	r5,STACKFRAMESIZE+64(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
+	ld	r5,STK_REG(R29)(r1)
 	mtlr	r0
 
 	/*
@@ -312,29 +321,29 @@
 	li	r11,48
 
 	bf	cr7*4+3,5f
-	lvx	vr1,r0,r4
+	lvx	v1,r0,r4
 	addi	r4,r4,16
-	stvx	vr1,r0,r3
+	stvx	v1,r0,r3
 	addi	r3,r3,16
 
 5:	bf	cr7*4+2,6f
-	lvx	vr1,r0,r4
-	lvx	vr0,r4,r9
+	lvx	v1,r0,r4
+	lvx	v0,r4,r9
 	addi	r4,r4,32
-	stvx	vr1,r0,r3
-	stvx	vr0,r3,r9
+	stvx	v1,r0,r3
+	stvx	v0,r3,r9
 	addi	r3,r3,32
 
 6:	bf	cr7*4+1,7f
-	lvx	vr3,r0,r4
-	lvx	vr2,r4,r9
-	lvx	vr1,r4,r10
-	lvx	vr0,r4,r11
+	lvx	v3,r0,r4
+	lvx	v2,r4,r9
+	lvx	v1,r4,r10
+	lvx	v0,r4,r11
 	addi	r4,r4,64
-	stvx	vr3,r0,r3
-	stvx	vr2,r3,r9
-	stvx	vr1,r3,r10
-	stvx	vr0,r3,r11
+	stvx	v3,r0,r3
+	stvx	v2,r3,r9
+	stvx	v1,r3,r10
+	stvx	v0,r3,r11
 	addi	r3,r3,64
 
 7:	sub	r5,r5,r6
@@ -357,23 +366,23 @@
 	 */
 	.align	5
 8:
-	lvx	vr7,r0,r4
-	lvx	vr6,r4,r9
-	lvx	vr5,r4,r10
-	lvx	vr4,r4,r11
-	lvx	vr3,r4,r12
-	lvx	vr2,r4,r14
-	lvx	vr1,r4,r15
-	lvx	vr0,r4,r16
+	lvx	v7,r0,r4
+	lvx	v6,r4,r9
+	lvx	v5,r4,r10
+	lvx	v4,r4,r11
+	lvx	v3,r4,r12
+	lvx	v2,r4,r14
+	lvx	v1,r4,r15
+	lvx	v0,r4,r16
 	addi	r4,r4,128
-	stvx	vr7,r0,r3
-	stvx	vr6,r3,r9
-	stvx	vr5,r3,r10
-	stvx	vr4,r3,r11
-	stvx	vr3,r3,r12
-	stvx	vr2,r3,r14
-	stvx	vr1,r3,r15
-	stvx	vr0,r3,r16
+	stvx	v7,r0,r3
+	stvx	v6,r3,r9
+	stvx	v5,r3,r10
+	stvx	v4,r3,r11
+	stvx	v3,r3,r12
+	stvx	v2,r3,r14
+	stvx	v1,r3,r15
+	stvx	v0,r3,r16
 	addi	r3,r3,128
 	bdnz	8b
 
@@ -387,29 +396,29 @@
 	mtocrf	0x01,r6
 
 	bf	cr7*4+1,9f
-	lvx	vr3,r0,r4
-	lvx	vr2,r4,r9
-	lvx	vr1,r4,r10
-	lvx	vr0,r4,r11
+	lvx	v3,r0,r4
+	lvx	v2,r4,r9
+	lvx	v1,r4,r10
+	lvx	v0,r4,r11
 	addi	r4,r4,64
-	stvx	vr3,r0,r3
-	stvx	vr2,r3,r9
-	stvx	vr1,r3,r10
-	stvx	vr0,r3,r11
+	stvx	v3,r0,r3
+	stvx	v2,r3,r9
+	stvx	v1,r3,r10
+	stvx	v0,r3,r11
 	addi	r3,r3,64
 
 9:	bf	cr7*4+2,10f
-	lvx	vr1,r0,r4
-	lvx	vr0,r4,r9
+	lvx	v1,r0,r4
+	lvx	v0,r4,r9
 	addi	r4,r4,32
-	stvx	vr1,r0,r3
-	stvx	vr0,r3,r9
+	stvx	v1,r0,r3
+	stvx	v0,r3,r9
 	addi	r3,r3,32
 
 10:	bf	cr7*4+3,11f
-	lvx	vr1,r0,r4
+	lvx	v1,r0,r4
 	addi	r4,r4,16
-	stvx	vr1,r0,r3
+	stvx	v1,r0,r3
 	addi	r3,r3,16
 
 	/* Up to 15B to go */
@@ -438,8 +447,8 @@
 	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	ld	r3,48(r1)
-	b	.exit_vmx_copy		/* tail call optimise */
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	b	exit_vmx_copy		/* tail call optimise */
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -485,42 +494,42 @@
 	li	r10,32
 	li	r11,48
 
-	lvsl	vr16,0,r4	/* Setup permute control vector */
-	lvx	vr0,0,r4
+	LVS(v16,0,r4)		/* Setup permute control vector */
+	lvx	v0,0,r4
 	addi	r4,r4,16
 
 	bf	cr7*4+3,5f
-	lvx	vr1,r0,r4
-	vperm	vr8,vr0,vr1,vr16
+	lvx	v1,r0,r4
+	VPERM(v8,v0,v1,v16)
 	addi	r4,r4,16
-	stvx	vr8,r0,r3
+	stvx	v8,r0,r3
 	addi	r3,r3,16
-	vor	vr0,vr1,vr1
+	vor	v0,v1,v1
 
 5:	bf	cr7*4+2,6f
-	lvx	vr1,r0,r4
-	vperm	vr8,vr0,vr1,vr16
-	lvx	vr0,r4,r9
-	vperm	vr9,vr1,vr0,vr16
+	lvx	v1,r0,r4
+	VPERM(v8,v0,v1,v16)
+	lvx	v0,r4,r9
+	VPERM(v9,v1,v0,v16)
 	addi	r4,r4,32
-	stvx	vr8,r0,r3
-	stvx	vr9,r3,r9
+	stvx	v8,r0,r3
+	stvx	v9,r3,r9
 	addi	r3,r3,32
 
 6:	bf	cr7*4+1,7f
-	lvx	vr3,r0,r4
-	vperm	vr8,vr0,vr3,vr16
-	lvx	vr2,r4,r9
-	vperm	vr9,vr3,vr2,vr16
-	lvx	vr1,r4,r10
-	vperm	vr10,vr2,vr1,vr16
-	lvx	vr0,r4,r11
-	vperm	vr11,vr1,vr0,vr16
+	lvx	v3,r0,r4
+	VPERM(v8,v0,v3,v16)
+	lvx	v2,r4,r9
+	VPERM(v9,v3,v2,v16)
+	lvx	v1,r4,r10
+	VPERM(v10,v2,v1,v16)
+	lvx	v0,r4,r11
+	VPERM(v11,v1,v0,v16)
 	addi	r4,r4,64
-	stvx	vr8,r0,r3
-	stvx	vr9,r3,r9
-	stvx	vr10,r3,r10
-	stvx	vr11,r3,r11
+	stvx	v8,r0,r3
+	stvx	v9,r3,r9
+	stvx	v10,r3,r10
+	stvx	v11,r3,r11
 	addi	r3,r3,64
 
 7:	sub	r5,r5,r6
@@ -543,31 +552,31 @@
 	 */
 	.align	5
 8:
-	lvx	vr7,r0,r4
-	vperm	vr8,vr0,vr7,vr16
-	lvx	vr6,r4,r9
-	vperm	vr9,vr7,vr6,vr16
-	lvx	vr5,r4,r10
-	vperm	vr10,vr6,vr5,vr16
-	lvx	vr4,r4,r11
-	vperm	vr11,vr5,vr4,vr16
-	lvx	vr3,r4,r12
-	vperm	vr12,vr4,vr3,vr16
-	lvx	vr2,r4,r14
-	vperm	vr13,vr3,vr2,vr16
-	lvx	vr1,r4,r15
-	vperm	vr14,vr2,vr1,vr16
-	lvx	vr0,r4,r16
-	vperm	vr15,vr1,vr0,vr16
+	lvx	v7,r0,r4
+	VPERM(v8,v0,v7,v16)
+	lvx	v6,r4,r9
+	VPERM(v9,v7,v6,v16)
+	lvx	v5,r4,r10
+	VPERM(v10,v6,v5,v16)
+	lvx	v4,r4,r11
+	VPERM(v11,v5,v4,v16)
+	lvx	v3,r4,r12
+	VPERM(v12,v4,v3,v16)
+	lvx	v2,r4,r14
+	VPERM(v13,v3,v2,v16)
+	lvx	v1,r4,r15
+	VPERM(v14,v2,v1,v16)
+	lvx	v0,r4,r16
+	VPERM(v15,v1,v0,v16)
 	addi	r4,r4,128
-	stvx	vr8,r0,r3
-	stvx	vr9,r3,r9
-	stvx	vr10,r3,r10
-	stvx	vr11,r3,r11
-	stvx	vr12,r3,r12
-	stvx	vr13,r3,r14
-	stvx	vr14,r3,r15
-	stvx	vr15,r3,r16
+	stvx	v8,r0,r3
+	stvx	v9,r3,r9
+	stvx	v10,r3,r10
+	stvx	v11,r3,r11
+	stvx	v12,r3,r12
+	stvx	v13,r3,r14
+	stvx	v14,r3,r15
+	stvx	v15,r3,r16
 	addi	r3,r3,128
 	bdnz	8b
 
@@ -581,36 +590,36 @@
 	mtocrf	0x01,r6
 
 	bf	cr7*4+1,9f
-	lvx	vr3,r0,r4
-	vperm	vr8,vr0,vr3,vr16
-	lvx	vr2,r4,r9
-	vperm	vr9,vr3,vr2,vr16
-	lvx	vr1,r4,r10
-	vperm	vr10,vr2,vr1,vr16
-	lvx	vr0,r4,r11
-	vperm	vr11,vr1,vr0,vr16
+	lvx	v3,r0,r4
+	VPERM(v8,v0,v3,v16)
+	lvx	v2,r4,r9
+	VPERM(v9,v3,v2,v16)
+	lvx	v1,r4,r10
+	VPERM(v10,v2,v1,v16)
+	lvx	v0,r4,r11
+	VPERM(v11,v1,v0,v16)
 	addi	r4,r4,64
-	stvx	vr8,r0,r3
-	stvx	vr9,r3,r9
-	stvx	vr10,r3,r10
-	stvx	vr11,r3,r11
+	stvx	v8,r0,r3
+	stvx	v9,r3,r9
+	stvx	v10,r3,r10
+	stvx	v11,r3,r11
 	addi	r3,r3,64
 
 9:	bf	cr7*4+2,10f
-	lvx	vr1,r0,r4
-	vperm	vr8,vr0,vr1,vr16
-	lvx	vr0,r4,r9
-	vperm	vr9,vr1,vr0,vr16
+	lvx	v1,r0,r4
+	VPERM(v8,v0,v1,v16)
+	lvx	v0,r4,r9
+	VPERM(v9,v1,v0,v16)
 	addi	r4,r4,32
-	stvx	vr8,r0,r3
-	stvx	vr9,r3,r9
+	stvx	v8,r0,r3
+	stvx	v9,r3,r9
 	addi	r3,r3,32
 
 10:	bf	cr7*4+3,11f
-	lvx	vr1,r0,r4
-	vperm	vr8,vr0,vr1,vr16
+	lvx	v1,r0,r4
+	VPERM(v8,v0,v1,v16)
 	addi	r4,r4,16
-	stvx	vr8,r0,r3
+	stvx	v8,r0,r3
 	addi	r3,r3,16
 
 	/* Up to 15B to go */
@@ -642,6 +651,6 @@
 	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	ld	r3,48(r1)
-	b	.exit_vmx_copy		/* tail call optimise */
-#endif /* CONFiG_ALTIVEC */
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	b	exit_vmx_copy		/* tail call optimise */
+#endif /* CONFIG_ALTIVEC */