No code changes, just documenting what's happening a little better. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
		
			
				
	
	
		
			168 lines
		
	
	
	
		
			3.4 KiB
			
		
	
	
	
		
			ArmAsm
		
	
	
	
	
	
			
		
		
	
	
			168 lines
		
	
	
	
		
			3.4 KiB
			
		
	
	
	
		
			ArmAsm
		
	
	
	
	
	
/*
 | 
						|
 * This program is free software; you can redistribute it and/or modify
 | 
						|
 * it under the terms of the GNU General Public License as published by
 | 
						|
 * the Free Software Foundation; either version 2 of the License, or
 | 
						|
 * (at your option) any later version.
 | 
						|
 *
 | 
						|
 * This program is distributed in the hope that it will be useful,
 | 
						|
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 | 
						|
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 | 
						|
 * GNU General Public License for more details.
 | 
						|
 *
 | 
						|
 * You should have received a copy of the GNU General Public License
 | 
						|
 * along with this program; if not, write to the Free Software
 | 
						|
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 | 
						|
 *
 | 
						|
 * 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
 | 
						|
 | 
						|
.machine push
 | 
						|
.machine "power4"
 | 
						|
	/* setup read stream 0  */
 | 
						|
	dcbt	r0,r4,0b01000  	/* addr from */
 | 
						|
	dcbt	r0,r7,0b01010   /* length and depth from */
 | 
						|
	/* setup write stream 1 */
 | 
						|
	dcbtst	r0,r9,0b01000   /* addr to */
 | 
						|
	dcbtst	r0,r10,0b01010  /* length and depth to */
 | 
						|
	eieio
 | 
						|
	dcbt	r0,r8,0b01010	/* all streams GO */
 | 
						|
.machine pop
 | 
						|
 | 
						|
#ifdef CONFIG_ALTIVEC
 | 
						|
	mflr	r0
 | 
						|
	std	r3,48(r1)
 | 
						|
	std	r4,56(r1)
 | 
						|
	std	r0,16(r1)
 | 
						|
	stdu	r1,-STACKFRAMESIZE(r1)
 | 
						|
	bl	.enter_vmx_copy
 | 
						|
	cmpwi	r3,0
 | 
						|
	ld	r0,STACKFRAMESIZE+16(r1)
 | 
						|
	ld	r3,STACKFRAMESIZE+48(r1)
 | 
						|
	ld	r4,STACKFRAMESIZE+56(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	vr7,r0,r4
 | 
						|
	lvx	vr6,r4,r6
 | 
						|
	lvx	vr5,r4,r7
 | 
						|
	lvx	vr4,r4,r8
 | 
						|
	lvx	vr3,r4,r9
 | 
						|
	lvx	vr2,r4,r10
 | 
						|
	lvx	vr1,r4,r11
 | 
						|
	lvx	vr0,r4,r12
 | 
						|
	addi	r4,r4,128
 | 
						|
	stvx	vr7,r0,r3
 | 
						|
	stvx	vr6,r3,r6
 | 
						|
	stvx	vr5,r3,r7
 | 
						|
	stvx	vr4,r3,r8
 | 
						|
	stvx	vr3,r3,r9
 | 
						|
	stvx	vr2,r3,r10
 | 
						|
	stvx	vr1,r3,r11
 | 
						|
	stvx	vr0,r3,r12
 | 
						|
	addi	r3,r3,128
 | 
						|
	bdnz	1b
 | 
						|
 | 
						|
	b	.exit_vmx_copy		/* 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
 |