| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | /* |
| 2 | * This file is subject to the terms and conditions of the GNU General Public |
| 3 | * License. See the file "COPYING" in the main directory of this archive |
| 4 | * for more details. |
| 5 | * |
| 6 | * Copyright (C) 1998 Ralf Baechle |
| 7 | */ |
| 8 | #include <asm/asm.h> |
| 9 | #include <asm/regdef.h> |
| 10 | |
| 11 | #define ADDC(sum,reg) \ |
| 12 | addu sum, reg; \ |
| 13 | sltu v1, sum, reg; \ |
| 14 | addu sum, v1 |
| 15 | |
| 16 | #define CSUM_BIGCHUNK(src, offset, sum, t0, t1, t2, t3) \ |
| 17 | lw t0, (offset + 0x00)(src); \ |
| 18 | lw t1, (offset + 0x04)(src); \ |
| 19 | lw t2, (offset + 0x08)(src); \ |
| 20 | lw t3, (offset + 0x0c)(src); \ |
| 21 | ADDC(sum, t0); \ |
| 22 | ADDC(sum, t1); \ |
| 23 | ADDC(sum, t2); \ |
| 24 | ADDC(sum, t3); \ |
| 25 | lw t0, (offset + 0x10)(src); \ |
| 26 | lw t1, (offset + 0x14)(src); \ |
| 27 | lw t2, (offset + 0x18)(src); \ |
| 28 | lw t3, (offset + 0x1c)(src); \ |
| 29 | ADDC(sum, t0); \ |
| 30 | ADDC(sum, t1); \ |
| 31 | ADDC(sum, t2); \ |
| 32 | ADDC(sum, t3); \ |
| 33 | |
| 34 | /* |
| 35 | * a0: source address |
| 36 | * a1: length of the area to checksum |
| 37 | * a2: partial checksum |
| 38 | */ |
| 39 | |
| 40 | #define src a0 |
| 41 | #define dest a1 |
| 42 | #define sum v0 |
| 43 | |
| 44 | .text |
| 45 | .set noreorder |
| 46 | |
| 47 | /* unknown src alignment and < 8 bytes to go */ |
| 48 | small_csumcpy: |
| 49 | move a1, t2 |
| 50 | |
| 51 | andi t0, a1, 4 |
| 52 | beqz t0, 1f |
| 53 | andi t0, a1, 2 |
| 54 | |
| 55 | /* Still a full word to go */ |
| 56 | ulw t1, (src) |
| 57 | addiu src, 4 |
| 58 | ADDC(sum, t1) |
| 59 | |
| 60 | 1: move t1, zero |
| 61 | beqz t0, 1f |
| 62 | andi t0, a1, 1 |
| 63 | |
| 64 | /* Still a halfword to go */ |
| 65 | ulhu t1, (src) |
| 66 | addiu src, 2 |
| 67 | |
| 68 | 1: beqz t0, 1f |
| 69 | sll t1, t1, 16 |
| 70 | |
| 71 | lbu t2, (src) |
| 72 | nop |
| 73 | |
| 74 | #ifdef __MIPSEB__ |
| 75 | sll t2, t2, 8 |
| 76 | #endif |
| 77 | or t1, t2 |
| 78 | |
| 79 | 1: ADDC(sum, t1) |
| 80 | |
| 81 | /* fold checksum */ |
| 82 | sll v1, sum, 16 |
| 83 | addu sum, v1 |
| 84 | sltu v1, sum, v1 |
| 85 | srl sum, sum, 16 |
| 86 | addu sum, v1 |
| 87 | |
| 88 | /* odd buffer alignment? */ |
| 89 | beqz t7, 1f |
| 90 | nop |
| 91 | sll v1, sum, 8 |
| 92 | srl sum, sum, 8 |
| 93 | or sum, v1 |
| 94 | andi sum, 0xffff |
| 95 | 1: |
| 96 | .set reorder |
| 97 | /* Add the passed partial csum. */ |
| 98 | ADDC(sum, a2) |
| 99 | jr ra |
| 100 | .set noreorder |
| 101 | |
| 102 | /* ------------------------------------------------------------------------- */ |
| 103 | |
| 104 | .align 5 |
| 105 | LEAF(csum_partial) |
| 106 | move sum, zero |
| 107 | move t7, zero |
| 108 | |
| 109 | sltiu t8, a1, 0x8 |
| 110 | bnez t8, small_csumcpy /* < 8 bytes to copy */ |
| 111 | move t2, a1 |
| 112 | |
| 113 | beqz a1, out |
| 114 | andi t7, src, 0x1 /* odd buffer? */ |
| 115 | |
| 116 | hword_align: |
| 117 | beqz t7, word_align |
| 118 | andi t8, src, 0x2 |
| 119 | |
| 120 | lbu t0, (src) |
| 121 | subu a1, a1, 0x1 |
| 122 | #ifdef __MIPSEL__ |
| 123 | sll t0, t0, 8 |
| 124 | #endif |
| 125 | ADDC(sum, t0) |
| 126 | addu src, src, 0x1 |
| 127 | andi t8, src, 0x2 |
| 128 | |
| 129 | word_align: |
| 130 | beqz t8, dword_align |
| 131 | sltiu t8, a1, 56 |
| 132 | |
| 133 | lhu t0, (src) |
| 134 | subu a1, a1, 0x2 |
| 135 | ADDC(sum, t0) |
| 136 | sltiu t8, a1, 56 |
| 137 | addu src, src, 0x2 |
| 138 | |
| 139 | dword_align: |
| 140 | bnez t8, do_end_words |
| 141 | move t8, a1 |
| 142 | |
| 143 | andi t8, src, 0x4 |
| 144 | beqz t8, qword_align |
| 145 | andi t8, src, 0x8 |
| 146 | |
| 147 | lw t0, 0x00(src) |
| 148 | subu a1, a1, 0x4 |
| 149 | ADDC(sum, t0) |
| 150 | addu src, src, 0x4 |
| 151 | andi t8, src, 0x8 |
| 152 | |
| 153 | qword_align: |
| 154 | beqz t8, oword_align |
| 155 | andi t8, src, 0x10 |
| 156 | |
| 157 | lw t0, 0x00(src) |
| 158 | lw t1, 0x04(src) |
| 159 | subu a1, a1, 0x8 |
| 160 | ADDC(sum, t0) |
| 161 | ADDC(sum, t1) |
| 162 | addu src, src, 0x8 |
| 163 | andi t8, src, 0x10 |
| 164 | |
| 165 | oword_align: |
| 166 | beqz t8, begin_movement |
| 167 | srl t8, a1, 0x7 |
| 168 | |
| 169 | lw t3, 0x08(src) |
| 170 | lw t4, 0x0c(src) |
| 171 | lw t0, 0x00(src) |
| 172 | lw t1, 0x04(src) |
| 173 | ADDC(sum, t3) |
| 174 | ADDC(sum, t4) |
| 175 | ADDC(sum, t0) |
| 176 | ADDC(sum, t1) |
| 177 | subu a1, a1, 0x10 |
| 178 | addu src, src, 0x10 |
| 179 | srl t8, a1, 0x7 |
| 180 | |
| 181 | begin_movement: |
| 182 | beqz t8, 1f |
| 183 | andi t2, a1, 0x40 |
| 184 | |
| 185 | move_128bytes: |
| 186 | CSUM_BIGCHUNK(src, 0x00, sum, t0, t1, t3, t4) |
| 187 | CSUM_BIGCHUNK(src, 0x20, sum, t0, t1, t3, t4) |
| 188 | CSUM_BIGCHUNK(src, 0x40, sum, t0, t1, t3, t4) |
| 189 | CSUM_BIGCHUNK(src, 0x60, sum, t0, t1, t3, t4) |
| 190 | subu t8, t8, 0x01 |
| 191 | bnez t8, move_128bytes |
| 192 | addu src, src, 0x80 |
| 193 | |
| 194 | 1: |
| 195 | beqz t2, 1f |
| 196 | andi t2, a1, 0x20 |
| 197 | |
| 198 | move_64bytes: |
| 199 | CSUM_BIGCHUNK(src, 0x00, sum, t0, t1, t3, t4) |
| 200 | CSUM_BIGCHUNK(src, 0x20, sum, t0, t1, t3, t4) |
| 201 | addu src, src, 0x40 |
| 202 | |
| 203 | 1: |
| 204 | beqz t2, do_end_words |
| 205 | andi t8, a1, 0x1c |
| 206 | |
| 207 | move_32bytes: |
| 208 | CSUM_BIGCHUNK(src, 0x00, sum, t0, t1, t3, t4) |
| 209 | andi t8, a1, 0x1c |
| 210 | addu src, src, 0x20 |
| 211 | |
| 212 | do_end_words: |
| 213 | beqz t8, maybe_end_cruft |
| 214 | srl t8, t8, 0x2 |
| 215 | |
| 216 | end_words: |
| 217 | lw t0, (src) |
| 218 | subu t8, t8, 0x1 |
| 219 | ADDC(sum, t0) |
| 220 | bnez t8, end_words |
| 221 | addu src, src, 0x4 |
| 222 | |
| 223 | maybe_end_cruft: |
| 224 | andi t2, a1, 0x3 |
| 225 | |
| 226 | small_memcpy: |
| 227 | j small_csumcpy; move a1, t2 |
| 228 | beqz t2, out |
| 229 | move a1, t2 |
| 230 | |
| 231 | end_bytes: |
| 232 | lb t0, (src) |
| 233 | subu a1, a1, 0x1 |
| 234 | bnez a2, end_bytes |
| 235 | addu src, src, 0x1 |
| 236 | |
| 237 | out: |
| 238 | jr ra |
| 239 | move v0, sum |
| 240 | END(csum_partial) |