1 /* SPDX-License-Identifier: GPL-2.0-or-later */ 2 /* 3 * INET An implementation of the TCP/IP protocol suite for the LINUX 4 * operating system. INET is implemented using the BSD Socket 5 * interface as the means of communication with the user level. 6 * 7 * IP/TCP/UDP checksumming routines 8 * 9 * Xtensa version: Copyright (C) 2001 Tensilica, Inc. by Kevin Chea 10 * Optimized by Joe Taylor 11 */ 12 13 #include <linux/errno.h> 14 #include <linux/linkage.h> 15 #include <asm/asmmacro.h> 16 #include <asm/core.h> 17 18 /* 19 * computes a partial checksum, e.g. for TCP/UDP fragments 20 */ 21 22 /* 23 * unsigned int csum_partial(const unsigned char *buf, int len, 24 * unsigned int sum); 25 * a2 = buf 26 * a3 = len 27 * a4 = sum 28 * 29 * This function assumes 2- or 4-byte alignment. Other alignments will fail! 30 */ 31 32 /* ONES_ADD converts twos-complement math to ones-complement. */ 33 #define ONES_ADD(sum, val) \ 34 add sum, sum, val ; \ 35 bgeu sum, val, 99f ; \ 36 addi sum, sum, 1 ; \ 37 99: ; 38 39 .text 40 ENTRY(csum_partial) 41 42 /* 43 * Experiments with Ethernet and SLIP connections show that buf 44 * is aligned on either a 2-byte or 4-byte boundary. 45 */ 46 abi_entry_default 47 extui a5, a2, 0, 2 48 bnez a5, 8f /* branch if 2-byte aligned */ 49 /* Fall-through on common case, 4-byte alignment */ 50 1: 51 srli a5, a3, 5 /* 32-byte chunks */ 52 #if XCHAL_HAVE_LOOPS 53 loopgtz a5, 2f 54 #else 55 beqz a5, 2f 56 slli a5, a5, 5 57 add a5, a5, a2 /* a5 = end of last 32-byte chunk */ 58 .Loop1: 59 #endif 60 l32i a6, a2, 0 61 l32i a7, a2, 4 62 ONES_ADD(a4, a6) 63 ONES_ADD(a4, a7) 64 l32i a6, a2, 8 65 l32i a7, a2, 12 66 ONES_ADD(a4, a6) 67 ONES_ADD(a4, a7) 68 l32i a6, a2, 16 69 l32i a7, a2, 20 70 ONES_ADD(a4, a6) 71 ONES_ADD(a4, a7) 72 l32i a6, a2, 24 73 l32i a7, a2, 28 74 ONES_ADD(a4, a6) 75 ONES_ADD(a4, a7) 76 addi a2, a2, 4*8 77 #if !XCHAL_HAVE_LOOPS 78 blt a2, a5, .Loop1 79 #endif 80 2: 81 extui a5, a3, 2, 3 /* remaining 4-byte chunks */ 82 #if XCHAL_HAVE_LOOPS 83 loopgtz a5, 3f 84 #else 85 beqz a5, 3f 86 slli a5, a5, 2 87 add a5, a5, a2 /* a5 = end of last 4-byte chunk */ 88 .Loop2: 89 #endif 90 l32i a6, a2, 0 91 ONES_ADD(a4, a6) 92 addi a2, a2, 4 93 #if !XCHAL_HAVE_LOOPS 94 blt a2, a5, .Loop2 95 #endif 96 3: 97 _bbci.l a3, 1, 5f /* remaining 2-byte chunk */ 98 l16ui a6, a2, 0 99 ONES_ADD(a4, a6) 100 addi a2, a2, 2 101 5: 102 _bbci.l a3, 0, 7f /* remaining 1-byte chunk */ 103 6: l8ui a6, a2, 0 104 #ifdef __XTENSA_EB__ 105 slli a6, a6, 8 /* load byte into bits 8..15 */ 106 #endif 107 ONES_ADD(a4, a6) 108 7: 109 mov a2, a4 110 abi_ret_default 111 112 /* uncommon case, buf is 2-byte aligned */ 113 8: 114 beqz a3, 7b /* branch if len == 0 */ 115 beqi a3, 1, 6b /* branch if len == 1 */ 116 117 extui a5, a2, 0, 1 118 bnez a5, 8f /* branch if 1-byte aligned */ 119 120 l16ui a6, a2, 0 /* common case, len >= 2 */ 121 ONES_ADD(a4, a6) 122 addi a2, a2, 2 /* adjust buf */ 123 addi a3, a3, -2 /* adjust len */ 124 j 1b /* now buf is 4-byte aligned */ 125 126 /* case: odd-byte aligned, len > 1 127 * This case is dog slow, so don't give us an odd address. 128 * (I don't think this ever happens, but just in case.) 129 */ 130 8: 131 srli a5, a3, 2 /* 4-byte chunks */ 132 #if XCHAL_HAVE_LOOPS 133 loopgtz a5, 2f 134 #else 135 beqz a5, 2f 136 slli a5, a5, 2 137 add a5, a5, a2 /* a5 = end of last 4-byte chunk */ 138 .Loop3: 139 #endif 140 l8ui a6, a2, 0 /* bits 24..31 */ 141 l16ui a7, a2, 1 /* bits 8..23 */ 142 l8ui a8, a2, 3 /* bits 0.. 8 */ 143 #ifdef __XTENSA_EB__ 144 slli a6, a6, 24 145 #else 146 slli a8, a8, 24 147 #endif 148 slli a7, a7, 8 149 or a7, a7, a6 150 or a7, a7, a8 151 ONES_ADD(a4, a7) 152 addi a2, a2, 4 153 #if !XCHAL_HAVE_LOOPS 154 blt a2, a5, .Loop3 155 #endif 156 2: 157 _bbci.l a3, 1, 3f /* remaining 2-byte chunk, still odd addr */ 158 l8ui a6, a2, 0 159 l8ui a7, a2, 1 160 #ifdef __XTENSA_EB__ 161 slli a6, a6, 8 162 #else 163 slli a7, a7, 8 164 #endif 165 or a7, a7, a6 166 ONES_ADD(a4, a7) 167 addi a2, a2, 2 168 3: 169 j 5b /* branch to handle the remaining byte */ 170 171 ENDPROC(csum_partial) 172 173 /* 174 * Copy from ds while checksumming, otherwise like csum_partial 175 */ 176 177 /* 178 unsigned int csum_partial_copy_generic (const char *src, char *dst, int len) 179 a2 = src 180 a3 = dst 181 a4 = len 182 a5 = sum 183 a8 = temp 184 a9 = temp 185 a10 = temp 186 187 This function is optimized for 4-byte aligned addresses. Other 188 alignments work, but not nearly as efficiently. 189 */ 190 191 ENTRY(csum_partial_copy_generic) 192 193 abi_entry_default 194 movi a5, -1 195 or a10, a2, a3 196 197 /* We optimize the following alignment tests for the 4-byte 198 aligned case. Two bbsi.l instructions might seem more optimal 199 (commented out below). However, both labels 5: and 3: are out 200 of the imm8 range, so the assembler relaxes them into 201 equivalent bbci.l, j combinations, which is actually 202 slower. */ 203 204 extui a9, a10, 0, 2 205 beqz a9, 1f /* branch if both are 4-byte aligned */ 206 bbsi.l a10, 0, 5f /* branch if one address is odd */ 207 j 3f /* one address is 2-byte aligned */ 208 209 /* _bbsi.l a10, 0, 5f */ /* branch if odd address */ 210 /* _bbsi.l a10, 1, 3f */ /* branch if 2-byte-aligned address */ 211 212 1: 213 /* src and dst are both 4-byte aligned */ 214 srli a10, a4, 5 /* 32-byte chunks */ 215 #if XCHAL_HAVE_LOOPS 216 loopgtz a10, 2f 217 #else 218 beqz a10, 2f 219 slli a10, a10, 5 220 add a10, a10, a2 /* a10 = end of last 32-byte src chunk */ 221 .Loop5: 222 #endif 223 EX(10f) l32i a9, a2, 0 224 EX(10f) l32i a8, a2, 4 225 EX(10f) s32i a9, a3, 0 226 EX(10f) s32i a8, a3, 4 227 ONES_ADD(a5, a9) 228 ONES_ADD(a5, a8) 229 EX(10f) l32i a9, a2, 8 230 EX(10f) l32i a8, a2, 12 231 EX(10f) s32i a9, a3, 8 232 EX(10f) s32i a8, a3, 12 233 ONES_ADD(a5, a9) 234 ONES_ADD(a5, a8) 235 EX(10f) l32i a9, a2, 16 236 EX(10f) l32i a8, a2, 20 237 EX(10f) s32i a9, a3, 16 238 EX(10f) s32i a8, a3, 20 239 ONES_ADD(a5, a9) 240 ONES_ADD(a5, a8) 241 EX(10f) l32i a9, a2, 24 242 EX(10f) l32i a8, a2, 28 243 EX(10f) s32i a9, a3, 24 244 EX(10f) s32i a8, a3, 28 245 ONES_ADD(a5, a9) 246 ONES_ADD(a5, a8) 247 addi a2, a2, 32 248 addi a3, a3, 32 249 #if !XCHAL_HAVE_LOOPS 250 blt a2, a10, .Loop5 251 #endif 252 2: 253 extui a10, a4, 2, 3 /* remaining 4-byte chunks */ 254 extui a4, a4, 0, 2 /* reset len for general-case, 2-byte chunks */ 255 #if XCHAL_HAVE_LOOPS 256 loopgtz a10, 3f 257 #else 258 beqz a10, 3f 259 slli a10, a10, 2 260 add a10, a10, a2 /* a10 = end of last 4-byte src chunk */ 261 .Loop6: 262 #endif 263 EX(10f) l32i a9, a2, 0 264 EX(10f) s32i a9, a3, 0 265 ONES_ADD(a5, a9) 266 addi a2, a2, 4 267 addi a3, a3, 4 268 #if !XCHAL_HAVE_LOOPS 269 blt a2, a10, .Loop6 270 #endif 271 3: 272 /* 273 Control comes to here in two cases: (1) It may fall through 274 to here from the 4-byte alignment case to process, at most, 275 one 2-byte chunk. (2) It branches to here from above if 276 either src or dst is 2-byte aligned, and we process all bytes 277 here, except for perhaps a trailing odd byte. It's 278 inefficient, so align your addresses to 4-byte boundaries. 279 280 a2 = src 281 a3 = dst 282 a4 = len 283 a5 = sum 284 */ 285 srli a10, a4, 1 /* 2-byte chunks */ 286 #if XCHAL_HAVE_LOOPS 287 loopgtz a10, 4f 288 #else 289 beqz a10, 4f 290 slli a10, a10, 1 291 add a10, a10, a2 /* a10 = end of last 2-byte src chunk */ 292 .Loop7: 293 #endif 294 EX(10f) l16ui a9, a2, 0 295 EX(10f) s16i a9, a3, 0 296 ONES_ADD(a5, a9) 297 addi a2, a2, 2 298 addi a3, a3, 2 299 #if !XCHAL_HAVE_LOOPS 300 blt a2, a10, .Loop7 301 #endif 302 4: 303 /* This section processes a possible trailing odd byte. */ 304 _bbci.l a4, 0, 8f /* 1-byte chunk */ 305 EX(10f) l8ui a9, a2, 0 306 EX(10f) s8i a9, a3, 0 307 #ifdef __XTENSA_EB__ 308 slli a9, a9, 8 /* shift byte to bits 8..15 */ 309 #endif 310 ONES_ADD(a5, a9) 311 8: 312 mov a2, a5 313 abi_ret_default 314 315 5: 316 /* Control branch to here when either src or dst is odd. We 317 process all bytes using 8-bit accesses. Grossly inefficient, 318 so don't feed us an odd address. */ 319 320 srli a10, a4, 1 /* handle in pairs for 16-bit csum */ 321 #if XCHAL_HAVE_LOOPS 322 loopgtz a10, 6f 323 #else 324 beqz a10, 6f 325 slli a10, a10, 1 326 add a10, a10, a2 /* a10 = end of last odd-aligned, 2-byte src chunk */ 327 .Loop8: 328 #endif 329 EX(10f) l8ui a9, a2, 0 330 EX(10f) l8ui a8, a2, 1 331 EX(10f) s8i a9, a3, 0 332 EX(10f) s8i a8, a3, 1 333 #ifdef __XTENSA_EB__ 334 slli a9, a9, 8 /* combine into a single 16-bit value */ 335 #else /* for checksum computation */ 336 slli a8, a8, 8 337 #endif 338 or a9, a9, a8 339 ONES_ADD(a5, a9) 340 addi a2, a2, 2 341 addi a3, a3, 2 342 #if !XCHAL_HAVE_LOOPS 343 blt a2, a10, .Loop8 344 #endif 345 6: 346 j 4b /* process the possible trailing odd byte */ 347 348 ENDPROC(csum_partial_copy_generic) 349 350 351 # Exception handler: 352 .section .fixup, "ax" 353 10: 354 movi a2, 0 355 abi_ret_default 356 357 .previous 358