copy_user_template.S 3.2 KB
Newer Older
R
Richard Kuo 已提交
1
/*
R
Richard Kuo 已提交
2
 * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
R
Richard Kuo 已提交
3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 and
 * only version 2 as published by the Free Software Foundation.
 *
 * 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., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA.
 */

/* 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