/*
 * Copyright (c) 2013-2014, ARM Limited and Contributors. All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * Redistributions of source code must retain the above copyright notice, this
 * list of conditions and the following disclaimer.
 *
 * Redistributions in binary form must reproduce the above copyright notice,
 * this list of conditions and the following disclaimer in the documentation
 * and/or other materials provided with the distribution.
 *
 * Neither the name of ARM nor the names of its contributors may be used
 * to endorse or promote products derived from this software without specific
 * prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include <arch.h>
#include <asm_macros.S>

	.globl	dcisw
	.globl	dccisw
	.globl	dccsw
	.globl	dccvac
	.globl	dcivac
	.globl	dccivac
	.globl	dccvau
	.globl	dczva
	.globl	flush_dcache_range
	.globl	inv_dcache_range
	.globl	dcsw_op_louis
	.globl	dcsw_op_all

func dcisw
	dc	isw, x0
	ret


func dccisw
	dc	cisw, x0
	ret


func dccsw
	dc	csw, x0
	ret


func dccvac
	dc	cvac, x0
	ret


func dcivac
	dc	ivac, x0
	ret


func dccivac
	dc	civac, x0
	ret


func dccvau
	dc	cvau, x0
	ret


func dczva
	dc	zva, x0
	ret


	/* ------------------------------------------
	 * Clean+Invalidate from base address till
	 * size. 'x0' = addr, 'x1' = size
	 * ------------------------------------------
	 */
func flush_dcache_range
	dcache_line_size x2, x3
	add	x1, x0, x1
	sub	x3, x2, #1
	bic	x0, x0, x3
flush_loop:
	dc	civac, x0
	add	x0, x0, x2
	cmp	x0, x1
	b.lo    flush_loop
	dsb	sy
	ret


	/* ------------------------------------------
	 * Invalidate from base address till
	 * size. 'x0' = addr, 'x1' = size
	 * ------------------------------------------
	 */
func inv_dcache_range
	dcache_line_size x2, x3
	add	x1, x0, x1
	sub	x3, x2, #1
	bic	x0, x0, x3
inv_loop:
	dc	ivac, x0
	add	x0, x0, x2
	cmp	x0, x1
	b.lo    inv_loop
	dsb	sy
	ret


	/* ---------------------------------------------------------------
	 * Data cache operations by set/way to the level specified
	 *
	 * The main function, do_dcsw_op requires:
	 * x0: The operation type (0-2), as defined in arch.h
	 * x3: The last cache level to operate on
	 * x9: clidr_el1
	 * and will carry out the operation on each data cache from level 0
	 * to the level in x3 in sequence
	 *
	 * The dcsw_op macro sets up the x3 and x9 parameters based on
	 * clidr_el1 cache information before invoking the main function
	 * ---------------------------------------------------------------
	 */

	.macro	dcsw_op shift, fw, ls
	mrs	x9, clidr_el1
	ubfx	x3, x9, \shift, \fw
	lsl	x3, x3, \ls
	b	do_dcsw_op
	.endm

func do_dcsw_op
	cbz	x3, exit
	mov	x10, xzr
	adr	x14, dcsw_loop_table	// compute inner loop address
	add	x14, x14, x0, lsl #5	// inner loop is 8x32-bit instructions
	mov	x0, x9
	mov	w8, #1
loop1:
	add	x2, x10, x10, lsr #1	// work out 3x current cache level
	lsr	x1, x0, x2		// extract cache type bits from clidr
	and	x1, x1, #7		// mask the bits for current cache only
	cmp	x1, #2			// see what cache we have at this level
	b.lt	level_done		// nothing to do if no cache or icache

	msr	csselr_el1, x10		// select current cache level in csselr
	isb				// isb to sych the new cssr&csidr
	mrs	x1, ccsidr_el1		// read the new ccsidr
	and	x2, x1, #7		// extract the length of the cache lines
	add	x2, x2, #4		// add 4 (line length offset)
	ubfx	x4, x1, #3, #10		// maximum way number
	clz	w5, w4			// bit position of way size increment
	lsl	w9, w4, w5		// w9 = aligned max way number
	lsl	w16, w8, w5		// w16 = way number loop decrement
	orr	w9, w10, w9		// w9 = combine way and cache number
	ubfx	w6, w1, #13, #15	// w6 = max set number
	lsl	w17, w8, w2		// w17 = set number loop decrement
	dsb	sy			// barrier before we start this level
	br	x14			// jump to DC operation specific loop

	.macro	dcsw_loop _op
loop2_\_op:
	lsl	w7, w6, w2		// w7 = aligned max set number

loop3_\_op:
	orr	w11, w9, w7		// combine cache, way and set number
	dc	\_op, x11
	subs	w7, w7, w17		// decrement set number
	b.ge	loop3_\_op

	subs	x9, x9, x16		// decrement way number
	b.ge	loop2_\_op

	b	level_done
	.endm

level_done:
	add	x10, x10, #2		// increment cache number
	cmp	x3, x10
	b.gt    loop1
	msr	csselr_el1, xzr		// select cache level 0 in csselr
	dsb	sy			// barrier to complete final cache operation
	isb
exit:
	ret

dcsw_loop_table:
	dcsw_loop isw
	dcsw_loop cisw
	dcsw_loop csw


func dcsw_op_louis
	dcsw_op #LOUIS_SHIFT, #CLIDR_FIELD_WIDTH, #LEVEL_SHIFT


func dcsw_op_all
	dcsw_op #LOC_SHIFT, #CLIDR_FIELD_WIDTH, #LEVEL_SHIFT