/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
 */

/* Numerology:
 * WXYZ
 * W: width in bytes
 * X: Load=0, Store=1
 * Y: Location 0=preamble,8=loop,9=epilog
 * Z: Location=0,handler=9
 */
        .text
        .global FUNCNAME
        .type FUNCNAME, @function
        .p2align 5
FUNCNAME:
        {
                p0 = cmp.gtu(bytes,#0)
                if (!p0.new) jump:nt .Ldone
                r3 = or(dst,src)
                r4 = xor(dst,src)
        }
        {
                p1 = cmp.gtu(bytes,#15)
                p0 = bitsclr(r3,#7)
                if (!p0.new) jump:nt .Loop_not_aligned_8
                src_dst_sav = combine(src,dst)
        }

        {
                loopcount = lsr(bytes,#3)
                if (!p1) jump .Lsmall
        }
        p3=sp1loop0(.Loop8,loopcount)
.Loop8:
8080:
8180:
        {
                if (p3) memd(dst++#8) = d_dbuf
                d_dbuf = memd(src++#8)
        }:endloop0
8190:
        {
                memd(dst++#8) = d_dbuf
                bytes -= asl(loopcount,#3)
                jump .Lsmall
        }

.Loop_not_aligned_8:
        {
                p0 = bitsclr(r4,#7)
                if (p0.new) jump:nt .Lalign
        }
        {
                p0 = bitsclr(r3,#3)
                if (!p0.new) jump:nt .Loop_not_aligned_4
                p1 = cmp.gtu(bytes,#7)
        }

        {
                if (!p1) jump .Lsmall
                loopcount = lsr(bytes,#2)
        }
        p3=sp1loop0(.Loop4,loopcount)
.Loop4:
4080:
4180:
        {
                if (p3) memw(dst++#4) = w_dbuf
                w_dbuf = memw(src++#4)
        }:endloop0
4190:
        {
                memw(dst++#4) = w_dbuf
                bytes -= asl(loopcount,#2)
                jump .Lsmall
        }

.Loop_not_aligned_4:
        {
                p0 = bitsclr(r3,#1)
                if (!p0.new) jump:nt .Loop_not_aligned
                p1 = cmp.gtu(bytes,#3)
        }

        {
                if (!p1) jump .Lsmall
                loopcount = lsr(bytes,#1)
        }
        p3=sp1loop0(.Loop2,loopcount)
.Loop2:
2080:
2180:
        {
                if (p3) memh(dst++#2) = w_dbuf
                w_dbuf = memuh(src++#2)
        }:endloop0
2190:
        {
                memh(dst++#2) = w_dbuf
                bytes -= asl(loopcount,#1)
                jump .Lsmall
        }

.Loop_not_aligned: /* Works for as small as one byte */
        p3=sp1loop0(.Loop1,bytes)
.Loop1:
1080:
1180:
        {
                if (p3) memb(dst++#1) = w_dbuf
                w_dbuf = memub(src++#1)
        }:endloop0
        /* Done */
1190:
        {
                memb(dst) = w_dbuf
                jumpr r31
                r0 = #0
        }

.Lsmall:
        {
                p0 = cmp.gtu(bytes,#0)
                if (p0.new) jump:nt .Loop_not_aligned
        }
.Ldone:
        {
                r0 = #0
                jumpr r31
        }
        .falign
.Lalign:
1000:
        {
                if (p0.new) w_dbuf = memub(src)
                p0 = tstbit(src,#0)
                if (!p1) jump .Lsmall
        }
1100:
        {
                if (p0) memb(dst++#1) = w_dbuf
                if (p0) bytes = add(bytes,#-1)
                if (p0) src = add(src,#1)
        }
2000:
        {
                if (p0.new) w_dbuf = memuh(src)
                p0 = tstbit(src,#1)
                if (!p1) jump .Lsmall
        }
2100:
        {
                if (p0) memh(dst++#2) = w_dbuf
                if (p0) bytes = add(bytes,#-2)
                if (p0) src = add(src,#2)
        }
4000:
        {
                if (p0.new) w_dbuf = memw(src)
                p0 = tstbit(src,#2)
                if (!p1) jump .Lsmall
        }
4100:
        {
                if (p0) memw(dst++#4) = w_dbuf
                if (p0) bytes = add(bytes,#-4)
                if (p0) src = add(src,#4)
                jump FUNCNAME
        }
        .size FUNCNAME,.-FUNCNAME