1 /* SPDX-License-Identifier: GPL-2.0 */ 2 /* NG2memcpy.S: Niagara-2 optimized memcpy. 3 * 4 * Copyright (C) 2007 David S. Miller (davem@davemloft.net) 5 */ 6 7 #ifdef __KERNEL__ 8 #include <linux/linkage.h> 9 #include <asm/visasm.h> 10 #include <asm/asi.h> 11 #define GLOBAL_SPARE %g7 12 #else 13 #define ASI_PNF 0x82 14 #define ASI_BLK_P 0xf0 15 #define ASI_BLK_INIT_QUAD_LDD_P 0xe2 16 #define FPRS_FEF 0x04 17 #ifdef MEMCPY_DEBUG 18 #define VISEntryHalf rd %fprs, %o5; wr %g0, FPRS_FEF, %fprs; \ 19 clr %g1; clr %g2; clr %g3; clr %g5; subcc %g0, %g0, %g0; 20 #define VISExitHalf and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs 21 #else 22 #define VISEntryHalf rd %fprs, %o5; wr %g0, FPRS_FEF, %fprs 23 #define VISExitHalf and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs 24 #endif 25 #define GLOBAL_SPARE %g5 26 #endif 27 28 #ifndef STORE_ASI 29 #ifndef SIMULATE_NIAGARA_ON_NON_NIAGARA 30 #define STORE_ASI ASI_BLK_INIT_QUAD_LDD_P 31 #else 32 #define STORE_ASI 0x80 /* ASI_P */ 33 #endif 34 #endif 35 36 #ifndef EX_LD 37 #define EX_LD(x,y) x 38 #endif 39 #ifndef EX_LD_FP 40 #define EX_LD_FP(x,y) x 41 #endif 42 43 #ifndef EX_ST 44 #define EX_ST(x,y) x 45 #endif 46 #ifndef EX_ST_FP 47 #define EX_ST_FP(x,y) x 48 #endif 49 50 #ifndef LOAD 51 #define LOAD(type,addr,dest) type [addr], dest 52 #endif 53 54 #ifndef LOAD_BLK 55 #define LOAD_BLK(addr,dest) ldda [addr] ASI_BLK_P, dest 56 #endif 57 58 #ifndef STORE 59 #ifndef MEMCPY_DEBUG 60 #define STORE(type,src,addr) type src, [addr] 61 #else 62 #define STORE(type,src,addr) type##a src, [addr] 0x80 63 #endif 64 #endif 65 66 #ifndef STORE_BLK 67 #define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_P 68 #endif 69 70 #ifndef STORE_INIT 71 #define STORE_INIT(src,addr) stxa src, [addr] STORE_ASI 72 #endif 73 74 #ifndef FUNC_NAME 75 #define FUNC_NAME NG2memcpy 76 #endif 77 78 #ifndef PREAMBLE 79 #define PREAMBLE 80 #endif 81 82 #ifndef XCC 83 #define XCC xcc 84 #endif 85 86 #define FREG_FROB(x0, x1, x2, x3, x4, x5, x6, x7, x8) \ 87 faligndata %x0, %x1, %f0; \ 88 faligndata %x1, %x2, %f2; \ 89 faligndata %x2, %x3, %f4; \ 90 faligndata %x3, %x4, %f6; \ 91 faligndata %x4, %x5, %f8; \ 92 faligndata %x5, %x6, %f10; \ 93 faligndata %x6, %x7, %f12; \ 94 faligndata %x7, %x8, %f14; 95 96 #define FREG_MOVE_1(x0) \ 97 fsrc2 %x0, %f0; 98 #define FREG_MOVE_2(x0, x1) \ 99 fsrc2 %x0, %f0; \ 100 fsrc2 %x1, %f2; 101 #define FREG_MOVE_3(x0, x1, x2) \ 102 fsrc2 %x0, %f0; \ 103 fsrc2 %x1, %f2; \ 104 fsrc2 %x2, %f4; 105 #define FREG_MOVE_4(x0, x1, x2, x3) \ 106 fsrc2 %x0, %f0; \ 107 fsrc2 %x1, %f2; \ 108 fsrc2 %x2, %f4; \ 109 fsrc2 %x3, %f6; 110 #define FREG_MOVE_5(x0, x1, x2, x3, x4) \ 111 fsrc2 %x0, %f0; \ 112 fsrc2 %x1, %f2; \ 113 fsrc2 %x2, %f4; \ 114 fsrc2 %x3, %f6; \ 115 fsrc2 %x4, %f8; 116 #define FREG_MOVE_6(x0, x1, x2, x3, x4, x5) \ 117 fsrc2 %x0, %f0; \ 118 fsrc2 %x1, %f2; \ 119 fsrc2 %x2, %f4; \ 120 fsrc2 %x3, %f6; \ 121 fsrc2 %x4, %f8; \ 122 fsrc2 %x5, %f10; 123 #define FREG_MOVE_7(x0, x1, x2, x3, x4, x5, x6) \ 124 fsrc2 %x0, %f0; \ 125 fsrc2 %x1, %f2; \ 126 fsrc2 %x2, %f4; \ 127 fsrc2 %x3, %f6; \ 128 fsrc2 %x4, %f8; \ 129 fsrc2 %x5, %f10; \ 130 fsrc2 %x6, %f12; 131 #define FREG_MOVE_8(x0, x1, x2, x3, x4, x5, x6, x7) \ 132 fsrc2 %x0, %f0; \ 133 fsrc2 %x1, %f2; \ 134 fsrc2 %x2, %f4; \ 135 fsrc2 %x3, %f6; \ 136 fsrc2 %x4, %f8; \ 137 fsrc2 %x5, %f10; \ 138 fsrc2 %x6, %f12; \ 139 fsrc2 %x7, %f14; 140 #define FREG_LOAD_1(base, x0) \ 141 EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1) 142 #define FREG_LOAD_2(base, x0, x1) \ 143 EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ 144 EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); 145 #define FREG_LOAD_3(base, x0, x1, x2) \ 146 EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ 147 EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ 148 EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); 149 #define FREG_LOAD_4(base, x0, x1, x2, x3) \ 150 EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ 151 EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ 152 EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ 153 EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); 154 #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \ 155 EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ 156 EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ 157 EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ 158 EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \ 159 EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); 160 #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \ 161 EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ 162 EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ 163 EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ 164 EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \ 165 EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \ 166 EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); 167 #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \ 168 EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ 169 EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ 170 EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ 171 EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \ 172 EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \ 173 EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); \ 174 EX_LD_FP(LOAD(ldd, base + 0x30, %x6), NG2_retl_o2_plus_g1); 175 176 .register %g2,#scratch 177 .register %g3,#scratch 178 179 .text 180 #ifndef EX_RETVAL 181 #define EX_RETVAL(x) x 182 __restore_fp: 183 VISExitHalf 184 __restore_asi: 185 retl 186 wr %g0, ASI_AIUS, %asi 187 ENTRY(NG2_retl_o2) 188 ba,pt %xcc, __restore_asi 189 mov %o2, %o0 190 ENDPROC(NG2_retl_o2) 191 ENTRY(NG2_retl_o2_plus_1) 192 ba,pt %xcc, __restore_asi 193 add %o2, 1, %o0 194 ENDPROC(NG2_retl_o2_plus_1) 195 ENTRY(NG2_retl_o2_plus_4) 196 ba,pt %xcc, __restore_asi 197 add %o2, 4, %o0 198 ENDPROC(NG2_retl_o2_plus_4) 199 ENTRY(NG2_retl_o2_plus_8) 200 ba,pt %xcc, __restore_asi 201 add %o2, 8, %o0 202 ENDPROC(NG2_retl_o2_plus_8) 203 ENTRY(NG2_retl_o2_plus_o4_plus_1) 204 add %o4, 1, %o4 205 ba,pt %xcc, __restore_asi 206 add %o2, %o4, %o0 207 ENDPROC(NG2_retl_o2_plus_o4_plus_1) 208 ENTRY(NG2_retl_o2_plus_o4_plus_8) 209 add %o4, 8, %o4 210 ba,pt %xcc, __restore_asi 211 add %o2, %o4, %o0 212 ENDPROC(NG2_retl_o2_plus_o4_plus_8) 213 ENTRY(NG2_retl_o2_plus_o4_plus_16) 214 add %o4, 16, %o4 215 ba,pt %xcc, __restore_asi 216 add %o2, %o4, %o0 217 ENDPROC(NG2_retl_o2_plus_o4_plus_16) 218 ENTRY(NG2_retl_o2_plus_g1_fp) 219 ba,pt %xcc, __restore_fp 220 add %o2, %g1, %o0 221 ENDPROC(NG2_retl_o2_plus_g1_fp) 222 ENTRY(NG2_retl_o2_plus_g1_plus_64_fp) 223 add %g1, 64, %g1 224 ba,pt %xcc, __restore_fp 225 add %o2, %g1, %o0 226 ENDPROC(NG2_retl_o2_plus_g1_plus_64_fp) 227 ENTRY(NG2_retl_o2_plus_g1_plus_1) 228 add %g1, 1, %g1 229 ba,pt %xcc, __restore_asi 230 add %o2, %g1, %o0 231 ENDPROC(NG2_retl_o2_plus_g1_plus_1) 232 ENTRY(NG2_retl_o2_and_7_plus_o4) 233 and %o2, 7, %o2 234 ba,pt %xcc, __restore_asi 235 add %o2, %o4, %o0 236 ENDPROC(NG2_retl_o2_and_7_plus_o4) 237 ENTRY(NG2_retl_o2_and_7_plus_o4_plus_8) 238 and %o2, 7, %o2 239 add %o4, 8, %o4 240 ba,pt %xcc, __restore_asi 241 add %o2, %o4, %o0 242 ENDPROC(NG2_retl_o2_and_7_plus_o4_plus_8) 243 #endif 244 245 .align 64 246 247 .globl FUNC_NAME 248 .type FUNC_NAME,#function 249 FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 250 srlx %o2, 31, %g2 251 cmp %g2, 0 252 tne %xcc, 5 253 PREAMBLE 254 mov %o0, %o3 255 cmp %o2, 0 256 be,pn %XCC, 85f 257 or %o0, %o1, GLOBAL_SPARE 258 cmp %o2, 16 259 blu,a,pn %XCC, 80f 260 or GLOBAL_SPARE, %o2, GLOBAL_SPARE 261 262 /* 2 blocks (128 bytes) is the minimum we can do the block 263 * copy with. We need to ensure that we'll iterate at least 264 * once in the block copy loop. At worst we'll need to align 265 * the destination to a 64-byte boundary which can chew up 266 * to (64 - 1) bytes from the length before we perform the 267 * block copy loop. 268 * 269 * However, the cut-off point, performance wise, is around 270 * 4 64-byte blocks. 271 */ 272 cmp %o2, (4 * 64) 273 blu,pt %XCC, 75f 274 andcc GLOBAL_SPARE, 0x7, %g0 275 276 /* %o0: dst 277 * %o1: src 278 * %o2: len (known to be >= 128) 279 * 280 * The block copy loops can use %o4, %g2, %g3 as 281 * temporaries while copying the data. %o5 must 282 * be preserved between VISEntryHalf and VISExitHalf 283 */ 284 285 LOAD(prefetch, %o1 + 0x000, #one_read) 286 LOAD(prefetch, %o1 + 0x040, #one_read) 287 LOAD(prefetch, %o1 + 0x080, #one_read) 288 289 /* Align destination on 64-byte boundary. */ 290 andcc %o0, (64 - 1), %o4 291 be,pt %XCC, 2f 292 sub %o4, 64, %o4 293 sub %g0, %o4, %o4 ! bytes to align dst 294 sub %o2, %o4, %o2 295 1: subcc %o4, 1, %o4 296 EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_o4_plus_1) 297 EX_ST(STORE(stb, %g1, %o0), NG2_retl_o2_plus_o4_plus_1) 298 add %o1, 1, %o1 299 bne,pt %XCC, 1b 300 add %o0, 1, %o0 301 302 2: 303 /* Clobbers o5/g1/g2/g3/g7/icc/xcc. We must preserve 304 * o5 from here until we hit VISExitHalf. 305 */ 306 VISEntryHalf 307 308 membar #Sync 309 alignaddr %o1, %g0, %g0 310 311 add %o1, (64 - 1), %o4 312 andn %o4, (64 - 1), %o4 313 andn %o2, (64 - 1), %g1 314 sub %o2, %g1, %o2 315 316 and %o1, (64 - 1), %g2 317 add %o1, %g1, %o1 318 sub %o0, %o4, %g3 319 brz,pt %g2, 190f 320 cmp %g2, 32 321 blu,a 5f 322 cmp %g2, 16 323 cmp %g2, 48 324 blu,a 4f 325 cmp %g2, 40 326 cmp %g2, 56 327 blu 170f 328 nop 329 ba,a,pt %xcc, 180f 330 nop 331 332 4: /* 32 <= low bits < 48 */ 333 blu 150f 334 nop 335 ba,a,pt %xcc, 160f 336 nop 337 5: /* 0 < low bits < 32 */ 338 blu,a 6f 339 cmp %g2, 8 340 cmp %g2, 24 341 blu 130f 342 nop 343 ba,a,pt %xcc, 140f 344 nop 345 6: /* 0 < low bits < 16 */ 346 bgeu 120f 347 nop 348 /* fall through for 0 < low bits < 8 */ 349 110: sub %o4, 64, %g2 350 EX_LD_FP(LOAD_BLK(%g2, %f0), NG2_retl_o2_plus_g1) 351 1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) 352 EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) 353 FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16) 354 EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) 355 FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30) 356 subcc %g1, 64, %g1 357 add %o4, 64, %o4 358 bne,pt %xcc, 1b 359 LOAD(prefetch, %o4 + 64, #one_read) 360 ba,pt %xcc, 195f 361 nop 362 363 120: sub %o4, 56, %g2 364 FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12) 365 1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) 366 EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) 367 FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18) 368 EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) 369 FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30) 370 subcc %g1, 64, %g1 371 add %o4, 64, %o4 372 bne,pt %xcc, 1b 373 LOAD(prefetch, %o4 + 64, #one_read) 374 ba,pt %xcc, 195f 375 nop 376 377 130: sub %o4, 48, %g2 378 FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10) 379 1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) 380 EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) 381 FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20) 382 EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) 383 FREG_MOVE_6(f20, f22, f24, f26, f28, f30) 384 subcc %g1, 64, %g1 385 add %o4, 64, %o4 386 bne,pt %xcc, 1b 387 LOAD(prefetch, %o4 + 64, #one_read) 388 ba,pt %xcc, 195f 389 nop 390 391 140: sub %o4, 40, %g2 392 FREG_LOAD_5(%g2, f0, f2, f4, f6, f8) 393 1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) 394 EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) 395 FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22) 396 EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) 397 FREG_MOVE_5(f22, f24, f26, f28, f30) 398 subcc %g1, 64, %g1 399 add %o4, 64, %o4 400 bne,pt %xcc, 1b 401 LOAD(prefetch, %o4 + 64, #one_read) 402 ba,pt %xcc, 195f 403 nop 404 405 150: sub %o4, 32, %g2 406 FREG_LOAD_4(%g2, f0, f2, f4, f6) 407 1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) 408 EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) 409 FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24) 410 EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) 411 FREG_MOVE_4(f24, f26, f28, f30) 412 subcc %g1, 64, %g1 413 add %o4, 64, %o4 414 bne,pt %xcc, 1b 415 LOAD(prefetch, %o4 + 64, #one_read) 416 ba,pt %xcc, 195f 417 nop 418 419 160: sub %o4, 24, %g2 420 FREG_LOAD_3(%g2, f0, f2, f4) 421 1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) 422 EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) 423 FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26) 424 EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) 425 FREG_MOVE_3(f26, f28, f30) 426 subcc %g1, 64, %g1 427 add %o4, 64, %o4 428 bne,pt %xcc, 1b 429 LOAD(prefetch, %o4 + 64, #one_read) 430 ba,pt %xcc, 195f 431 nop 432 433 170: sub %o4, 16, %g2 434 FREG_LOAD_2(%g2, f0, f2) 435 1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) 436 EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) 437 FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28) 438 EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) 439 FREG_MOVE_2(f28, f30) 440 subcc %g1, 64, %g1 441 add %o4, 64, %o4 442 bne,pt %xcc, 1b 443 LOAD(prefetch, %o4 + 64, #one_read) 444 ba,pt %xcc, 195f 445 nop 446 447 180: sub %o4, 8, %g2 448 FREG_LOAD_1(%g2, f0) 449 1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) 450 EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) 451 FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30) 452 EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) 453 FREG_MOVE_1(f30) 454 subcc %g1, 64, %g1 455 add %o4, 64, %o4 456 bne,pt %xcc, 1b 457 LOAD(prefetch, %o4 + 64, #one_read) 458 ba,pt %xcc, 195f 459 nop 460 461 190: 462 1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) 463 subcc %g1, 64, %g1 464 EX_LD_FP(LOAD_BLK(%o4, %f0), NG2_retl_o2_plus_g1_plus_64) 465 EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1_plus_64) 466 add %o4, 64, %o4 467 bne,pt %xcc, 1b 468 LOAD(prefetch, %o4 + 64, #one_read) 469 470 195: 471 add %o4, %g3, %o0 472 membar #Sync 473 474 VISExitHalf 475 476 /* %o2 contains any final bytes still needed to be copied 477 * over. If anything is left, we copy it one byte at a time. 478 */ 479 brz,pt %o2, 85f 480 sub %o0, %o1, GLOBAL_SPARE 481 ba,a,pt %XCC, 90f 482 nop 483 484 .align 64 485 75: /* 16 < len <= 64 */ 486 bne,pn %XCC, 75f 487 sub %o0, %o1, GLOBAL_SPARE 488 489 72: 490 andn %o2, 0xf, %o4 491 and %o2, 0xf, %o2 492 1: subcc %o4, 0x10, %o4 493 EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_o4_plus_16) 494 add %o1, 0x08, %o1 495 EX_LD(LOAD(ldx, %o1, %g1), NG2_retl_o2_plus_o4_plus_16) 496 sub %o1, 0x08, %o1 497 EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_16) 498 add %o1, 0x8, %o1 499 EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_8) 500 bgu,pt %XCC, 1b 501 add %o1, 0x8, %o1 502 73: andcc %o2, 0x8, %g0 503 be,pt %XCC, 1f 504 nop 505 sub %o2, 0x8, %o2 506 EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_8) 507 EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_8) 508 add %o1, 0x8, %o1 509 1: andcc %o2, 0x4, %g0 510 be,pt %XCC, 1f 511 nop 512 sub %o2, 0x4, %o2 513 EX_LD(LOAD(lduw, %o1, %o5), NG2_retl_o2_plus_4) 514 EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4) 515 add %o1, 0x4, %o1 516 1: cmp %o2, 0 517 be,pt %XCC, 85f 518 nop 519 ba,pt %xcc, 90f 520 nop 521 522 75: 523 andcc %o0, 0x7, %g1 524 sub %g1, 0x8, %g1 525 be,pn %icc, 2f 526 sub %g0, %g1, %g1 527 sub %o2, %g1, %o2 528 529 1: subcc %g1, 1, %g1 530 EX_LD(LOAD(ldub, %o1, %o5), NG2_retl_o2_plus_g1_plus_1) 531 EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_g1_plus_1) 532 bgu,pt %icc, 1b 533 add %o1, 1, %o1 534 535 2: add %o1, GLOBAL_SPARE, %o0 536 andcc %o1, 0x7, %g1 537 bne,pt %icc, 8f 538 sll %g1, 3, %g1 539 540 cmp %o2, 16 541 bgeu,pt %icc, 72b 542 nop 543 ba,a,pt %xcc, 73b 544 545 8: mov 64, GLOBAL_SPARE 546 andn %o1, 0x7, %o1 547 EX_LD(LOAD(ldx, %o1, %g2), NG2_retl_o2) 548 sub GLOBAL_SPARE, %g1, GLOBAL_SPARE 549 andn %o2, 0x7, %o4 550 sllx %g2, %g1, %g2 551 1: add %o1, 0x8, %o1 552 EX_LD(LOAD(ldx, %o1, %g3), NG2_retl_o2_and_7_plus_o4) 553 subcc %o4, 0x8, %o4 554 srlx %g3, GLOBAL_SPARE, %o5 555 or %o5, %g2, %o5 556 EX_ST(STORE(stx, %o5, %o0), NG2_retl_o2_and_7_plus_o4_plus_8) 557 add %o0, 0x8, %o0 558 bgu,pt %icc, 1b 559 sllx %g3, %g1, %g2 560 561 srl %g1, 3, %g1 562 andcc %o2, 0x7, %o2 563 be,pn %icc, 85f 564 add %o1, %g1, %o1 565 ba,pt %xcc, 90f 566 sub %o0, %o1, GLOBAL_SPARE 567 568 .align 64 569 80: /* 0 < len <= 16 */ 570 andcc GLOBAL_SPARE, 0x3, %g0 571 bne,pn %XCC, 90f 572 sub %o0, %o1, GLOBAL_SPARE 573 574 1: 575 subcc %o2, 4, %o2 576 EX_LD(LOAD(lduw, %o1, %g1), NG2_retl_o2_plus_4) 577 EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4) 578 bgu,pt %XCC, 1b 579 add %o1, 4, %o1 580 581 85: retl 582 mov EX_RETVAL(%o3), %o0 583 584 .align 32 585 90: 586 subcc %o2, 1, %o2 587 EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_1) 588 EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_1) 589 bgu,pt %XCC, 90b 590 add %o1, 1, %o1 591 retl 592 mov EX_RETVAL(%o3), %o0 593 594 .size FUNC_NAME, .-FUNC_NAME 595