ASR_BASE
Change-Id: Icf3719cc0afe3eeb3edc7fa80a2eb5199ca9dda1
diff --git a/marvell/linux/arch/powerpc/lib/copypage_power7.S b/marvell/linux/arch/powerpc/lib/copypage_power7.S
new file mode 100644
index 0000000..a9844c6
--- /dev/null
+++ b/marvell/linux/arch/powerpc/lib/copypage_power7.S
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/page.h>
+#include <asm/ppc_asm.h>
+
+_GLOBAL(copypage_power7)
+ /*
+ * We prefetch both the source and destination using enhanced touch
+ * instructions. We use a stream ID of 0 for the load side and
+ * 1 for the store side. Since source and destination are page
+ * aligned we don't need to clear the bottom 7 bits of either
+ * address.
+ */
+ ori r9,r3,1 /* stream=1 => to */
+
+#ifdef CONFIG_PPC_64K_PAGES
+ lis r7,0x0E01 /* depth=7
+ * units/cachelines=512 */
+#else
+ lis r7,0x0E00 /* depth=7 */
+ ori r7,r7,0x1000 /* units/cachelines=32 */
+#endif
+ ori r10,r7,1 /* stream=1 */
+
+ lis r8,0x8000 /* GO=1 */
+ clrldi r8,r8,32
+
+ /* setup read stream 0 */
+ dcbt 0,r4,0b01000 /* addr from */
+ dcbt 0,r7,0b01010 /* length and depth from */
+ /* setup write stream 1 */
+ dcbtst 0,r9,0b01000 /* addr to */
+ dcbtst 0,r10,0b01010 /* length and depth to */
+ eieio
+ dcbt 0,r8,0b01010 /* all streams GO */
+
+#ifdef CONFIG_ALTIVEC
+ mflr r0
+ std r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+ std r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+ std r0,16(r1)
+ stdu r1,-STACKFRAMESIZE(r1)
+ bl enter_vmx_ops
+ cmpwi r3,0
+ ld r0,STACKFRAMESIZE+16(r1)
+ ld r3,STK_REG(R31)(r1)
+ ld r4,STK_REG(R30)(r1)
+ mtlr r0
+
+ li r0,(PAGE_SIZE/128)
+ mtctr r0
+
+ beq .Lnonvmx_copy
+
+ addi r1,r1,STACKFRAMESIZE
+
+ li r6,16
+ li r7,32
+ li r8,48
+ li r9,64
+ li r10,80
+ li r11,96
+ li r12,112
+
+ .align 5
+1: lvx v7,0,r4
+ lvx v6,r4,r6
+ lvx v5,r4,r7
+ lvx v4,r4,r8
+ lvx v3,r4,r9
+ lvx v2,r4,r10
+ lvx v1,r4,r11
+ lvx v0,r4,r12
+ addi r4,r4,128
+ stvx v7,0,r3
+ stvx v6,r3,r6
+ stvx v5,r3,r7
+ stvx v4,r3,r8
+ stvx v3,r3,r9
+ stvx v2,r3,r10
+ stvx v1,r3,r11
+ stvx v0,r3,r12
+ addi r3,r3,128
+ bdnz 1b
+
+ b exit_vmx_ops /* tail call optimise */
+
+#else
+ li r0,(PAGE_SIZE/128)
+ mtctr r0
+
+ stdu r1,-STACKFRAMESIZE(r1)
+#endif
+
+.Lnonvmx_copy:
+ std r14,STK_REG(R14)(r1)
+ std r15,STK_REG(R15)(r1)
+ std r16,STK_REG(R16)(r1)
+ std r17,STK_REG(R17)(r1)
+ std r18,STK_REG(R18)(r1)
+ std r19,STK_REG(R19)(r1)
+ std r20,STK_REG(R20)(r1)
+
+1: ld r0,0(r4)
+ ld r5,8(r4)
+ ld r6,16(r4)
+ ld r7,24(r4)
+ ld r8,32(r4)
+ ld r9,40(r4)
+ ld r10,48(r4)
+ ld r11,56(r4)
+ ld r12,64(r4)
+ ld r14,72(r4)
+ ld r15,80(r4)
+ ld r16,88(r4)
+ ld r17,96(r4)
+ ld r18,104(r4)
+ ld r19,112(r4)
+ ld r20,120(r4)
+ addi r4,r4,128
+ std r0,0(r3)
+ std r5,8(r3)
+ std r6,16(r3)
+ std r7,24(r3)
+ std r8,32(r3)
+ std r9,40(r3)
+ std r10,48(r3)
+ std r11,56(r3)
+ std r12,64(r3)
+ std r14,72(r3)
+ std r15,80(r3)
+ std r16,88(r3)
+ std r17,96(r3)
+ std r18,104(r3)
+ std r19,112(r3)
+ std r20,120(r3)
+ addi r3,r3,128
+ bdnz 1b
+
+ ld r14,STK_REG(R14)(r1)
+ ld r15,STK_REG(R15)(r1)
+ ld r16,STK_REG(R16)(r1)
+ ld r17,STK_REG(R17)(r1)
+ ld r18,STK_REG(R18)(r1)
+ ld r19,STK_REG(R19)(r1)
+ ld r20,STK_REG(R20)(r1)
+ addi r1,r1,STACKFRAMESIZE
+ blr