lh | 9ed821d | 2023-04-07 01:36:19 -0700 | [diff] [blame^] | 1 | ! Copyright 2005-2016 The OpenSSL Project Authors. All Rights Reserved. |
| 2 | ! |
| 3 | ! Licensed under the OpenSSL license (the "License"). You may not use |
| 4 | ! this file except in compliance with the License. You can obtain a copy |
| 5 | ! in the file LICENSE in the source distribution or at |
| 6 | ! https://www.openssl.org/source/license.html |
| 7 | |
| 8 | #if defined(__SUNPRO_C) && defined(__sparcv9) |
| 9 | # define ABI64 /* They've said -xarch=v9 at command line */ |
| 10 | #elif defined(__GNUC__) && defined(__arch64__) |
| 11 | # define ABI64 /* They've said -m64 at command line */ |
| 12 | #endif |
| 13 | |
| 14 | #ifdef ABI64 |
| 15 | .register %g2,#scratch |
| 16 | .register %g3,#scratch |
| 17 | # define FRAME -192 |
| 18 | # define BIAS 2047 |
| 19 | #else |
| 20 | # define FRAME -96 |
| 21 | # define BIAS 0 |
| 22 | #endif |
| 23 | |
| 24 | .text |
| 25 | .align 32 |
| 26 | .global OPENSSL_wipe_cpu |
| 27 | .type OPENSSL_wipe_cpu,#function |
| 28 | ! Keep in mind that this does not excuse us from wiping the stack! |
| 29 | ! This routine wipes registers, but not the backing store [which |
| 30 | ! resides on the stack, toward lower addresses]. To facilitate for |
| 31 | ! stack wiping I return pointer to the top of stack of the *caller*. |
| 32 | OPENSSL_wipe_cpu: |
| 33 | save %sp,FRAME,%sp |
| 34 | nop |
| 35 | #ifdef __sun |
| 36 | #include <sys/trap.h> |
| 37 | ta ST_CLEAN_WINDOWS |
| 38 | #else |
| 39 | call .walk.reg.wins |
| 40 | #endif |
| 41 | nop |
| 42 | call .PIC.zero.up |
| 43 | mov .zero-(.-4),%o0 |
| 44 | ld [%o0],%f0 |
| 45 | ld [%o0],%f1 |
| 46 | |
| 47 | subcc %g0,1,%o0 |
| 48 | ! Following is V9 "rd %ccr,%o0" instruction. However! V8 |
| 49 | ! specification says that it ("rd %asr2,%o0" in V8 terms) does |
| 50 | ! not cause illegal_instruction trap. It therefore can be used |
| 51 | ! to determine if the CPU the code is executing on is V8- or |
| 52 | ! V9-compliant, as V9 returns a distinct value of 0x99, |
| 53 | ! "negative" and "borrow" bits set in both %icc and %xcc. |
| 54 | .word 0x91408000 !rd %ccr,%o0 |
| 55 | cmp %o0,0x99 |
| 56 | bne .v8 |
| 57 | nop |
| 58 | ! Even though we do not use %fp register bank, |
| 59 | ! we wipe it as memcpy might have used it... |
| 60 | .word 0xbfa00040 !fmovd %f0,%f62 |
| 61 | .word 0xbba00040 !... |
| 62 | .word 0xb7a00040 |
| 63 | .word 0xb3a00040 |
| 64 | .word 0xafa00040 |
| 65 | .word 0xaba00040 |
| 66 | .word 0xa7a00040 |
| 67 | .word 0xa3a00040 |
| 68 | .word 0x9fa00040 |
| 69 | .word 0x9ba00040 |
| 70 | .word 0x97a00040 |
| 71 | .word 0x93a00040 |
| 72 | .word 0x8fa00040 |
| 73 | .word 0x8ba00040 |
| 74 | .word 0x87a00040 |
| 75 | .word 0x83a00040 !fmovd %f0,%f32 |
| 76 | .v8: fmovs %f1,%f31 |
| 77 | clr %o0 |
| 78 | fmovs %f0,%f30 |
| 79 | clr %o1 |
| 80 | fmovs %f1,%f29 |
| 81 | clr %o2 |
| 82 | fmovs %f0,%f28 |
| 83 | clr %o3 |
| 84 | fmovs %f1,%f27 |
| 85 | clr %o4 |
| 86 | fmovs %f0,%f26 |
| 87 | clr %o5 |
| 88 | fmovs %f1,%f25 |
| 89 | clr %o7 |
| 90 | fmovs %f0,%f24 |
| 91 | clr %l0 |
| 92 | fmovs %f1,%f23 |
| 93 | clr %l1 |
| 94 | fmovs %f0,%f22 |
| 95 | clr %l2 |
| 96 | fmovs %f1,%f21 |
| 97 | clr %l3 |
| 98 | fmovs %f0,%f20 |
| 99 | clr %l4 |
| 100 | fmovs %f1,%f19 |
| 101 | clr %l5 |
| 102 | fmovs %f0,%f18 |
| 103 | clr %l6 |
| 104 | fmovs %f1,%f17 |
| 105 | clr %l7 |
| 106 | fmovs %f0,%f16 |
| 107 | clr %i0 |
| 108 | fmovs %f1,%f15 |
| 109 | clr %i1 |
| 110 | fmovs %f0,%f14 |
| 111 | clr %i2 |
| 112 | fmovs %f1,%f13 |
| 113 | clr %i3 |
| 114 | fmovs %f0,%f12 |
| 115 | clr %i4 |
| 116 | fmovs %f1,%f11 |
| 117 | clr %i5 |
| 118 | fmovs %f0,%f10 |
| 119 | clr %g1 |
| 120 | fmovs %f1,%f9 |
| 121 | clr %g2 |
| 122 | fmovs %f0,%f8 |
| 123 | clr %g3 |
| 124 | fmovs %f1,%f7 |
| 125 | clr %g4 |
| 126 | fmovs %f0,%f6 |
| 127 | clr %g5 |
| 128 | fmovs %f1,%f5 |
| 129 | fmovs %f0,%f4 |
| 130 | fmovs %f1,%f3 |
| 131 | fmovs %f0,%f2 |
| 132 | |
| 133 | add %fp,BIAS,%i0 ! return pointer to caller“s top of stack |
| 134 | |
| 135 | ret |
| 136 | restore |
| 137 | |
| 138 | .zero: .long 0x0,0x0 |
| 139 | .PIC.zero.up: |
| 140 | retl |
| 141 | add %o0,%o7,%o0 |
| 142 | #ifdef DEBUG |
| 143 | .global walk_reg_wins |
| 144 | .type walk_reg_wins,#function |
| 145 | walk_reg_wins: |
| 146 | #endif |
| 147 | .walk.reg.wins: |
| 148 | save %sp,FRAME,%sp |
| 149 | cmp %i7,%o7 |
| 150 | be 2f |
| 151 | clr %o0 |
| 152 | cmp %o7,0 ! compiler never cleans %o7... |
| 153 | be 1f ! could have been a leaf function... |
| 154 | clr %o1 |
| 155 | call .walk.reg.wins |
| 156 | nop |
| 157 | 1: clr %o2 |
| 158 | clr %o3 |
| 159 | clr %o4 |
| 160 | clr %o5 |
| 161 | clr %o7 |
| 162 | clr %l0 |
| 163 | clr %l1 |
| 164 | clr %l2 |
| 165 | clr %l3 |
| 166 | clr %l4 |
| 167 | clr %l5 |
| 168 | clr %l6 |
| 169 | clr %l7 |
| 170 | add %o0,1,%i0 ! used for debugging |
| 171 | 2: ret |
| 172 | restore |
| 173 | .size OPENSSL_wipe_cpu,.-OPENSSL_wipe_cpu |
| 174 | |
| 175 | .global OPENSSL_atomic_add |
| 176 | .type OPENSSL_atomic_add,#function |
| 177 | .align 32 |
| 178 | OPENSSL_atomic_add: |
| 179 | #ifndef ABI64 |
| 180 | subcc %g0,1,%o2 |
| 181 | .word 0x95408000 !rd %ccr,%o2, see comment above |
| 182 | cmp %o2,0x99 |
| 183 | be .v9 |
| 184 | nop |
| 185 | save %sp,FRAME,%sp |
| 186 | ba .enter |
| 187 | nop |
| 188 | #ifdef __sun |
| 189 | ! Note that you do not have to link with libthread to call thr_yield, |
| 190 | ! as libc provides a stub, which is overloaded the moment you link |
| 191 | ! with *either* libpthread or libthread... |
| 192 | #define YIELD_CPU thr_yield |
| 193 | #else |
| 194 | ! applies at least to Linux and FreeBSD... Feedback expected... |
| 195 | #define YIELD_CPU sched_yield |
| 196 | #endif |
| 197 | .spin: call YIELD_CPU |
| 198 | nop |
| 199 | .enter: ld [%i0],%i2 |
| 200 | cmp %i2,-4096 |
| 201 | be .spin |
| 202 | mov -1,%i2 |
| 203 | swap [%i0],%i2 |
| 204 | cmp %i2,-1 |
| 205 | be .spin |
| 206 | add %i2,%i1,%i2 |
| 207 | stbar |
| 208 | st %i2,[%i0] |
| 209 | sra %i2,%g0,%i0 |
| 210 | ret |
| 211 | restore |
| 212 | .v9: |
| 213 | #endif |
| 214 | ld [%o0],%o2 |
| 215 | 1: add %o1,%o2,%o3 |
| 216 | .word 0xd7e2100a !cas [%o0],%o2,%o3, compare [%o0] with %o2 and swap %o3 |
| 217 | cmp %o2,%o3 |
| 218 | bne 1b |
| 219 | mov %o3,%o2 ! cas is always fetching to dest. register |
| 220 | add %o1,%o2,%o0 ! OpenSSL expects the new value |
| 221 | retl |
| 222 | sra %o0,%g0,%o0 ! we return signed int, remember? |
| 223 | .size OPENSSL_atomic_add,.-OPENSSL_atomic_add |
| 224 | |
| 225 | .global _sparcv9_rdtick |
| 226 | .align 32 |
| 227 | _sparcv9_rdtick: |
| 228 | subcc %g0,1,%o0 |
| 229 | .word 0x91408000 !rd %ccr,%o0 |
| 230 | cmp %o0,0x99 |
| 231 | bne .notick |
| 232 | xor %o0,%o0,%o0 |
| 233 | .word 0x91410000 !rd %tick,%o0 |
| 234 | retl |
| 235 | .word 0x93323020 !srlx %o0,32,%o1 |
| 236 | .notick: |
| 237 | retl |
| 238 | xor %o1,%o1,%o1 |
| 239 | .type _sparcv9_rdtick,#function |
| 240 | .size _sparcv9_rdtick,.-_sparcv9_rdtick |
| 241 | |
| 242 | .global _sparcv9_vis1_probe |
| 243 | .align 8 |
| 244 | _sparcv9_vis1_probe: |
| 245 | add %sp,BIAS+2,%o1 |
| 246 | .word 0xc19a5a40 !ldda [%o1]ASI_FP16_P,%f0 |
| 247 | retl |
| 248 | .word 0x81b00d80 !fxor %f0,%f0,%f0 |
| 249 | .type _sparcv9_vis1_probe,#function |
| 250 | .size _sparcv9_vis1_probe,.-_sparcv9_vis1_probe |
| 251 | |
| 252 | ! Probe and instrument VIS1 instruction. Output is number of cycles it |
| 253 | ! takes to execute rdtick and pair of VIS1 instructions. US-Tx VIS unit |
| 254 | ! is slow (documented to be 6 cycles on T2) and the core is in-order |
| 255 | ! single-issue, it should be possible to distinguish Tx reliably... |
| 256 | ! Observed return values are: |
| 257 | ! |
| 258 | ! UltraSPARC IIe 7 |
| 259 | ! UltraSPARC III 7 |
| 260 | ! UltraSPARC T1 24 |
| 261 | ! SPARC T4 65(*) |
| 262 | ! |
| 263 | ! (*) result has lesser to do with VIS instruction latencies, rdtick |
| 264 | ! appears that slow, but it does the trick in sense that FP and |
| 265 | ! VIS code paths are still slower than integer-only ones. |
| 266 | ! |
| 267 | ! Numbers for T2 and SPARC64 V-VII are more than welcomed. |
| 268 | ! |
| 269 | ! It would be possible to detect specifically US-T1 by instrumenting |
| 270 | ! fmul8ulx16, which is emulated on T1 and as such accounts for quite |
| 271 | ! a lot of %tick-s, couple of thousand on Linux... |
| 272 | .global _sparcv9_vis1_instrument |
| 273 | .align 8 |
| 274 | _sparcv9_vis1_instrument: |
| 275 | .word 0x81b00d80 !fxor %f0,%f0,%f0 |
| 276 | .word 0x85b08d82 !fxor %f2,%f2,%f2 |
| 277 | .word 0x91410000 !rd %tick,%o0 |
| 278 | .word 0x81b00d80 !fxor %f0,%f0,%f0 |
| 279 | .word 0x85b08d82 !fxor %f2,%f2,%f2 |
| 280 | .word 0x93410000 !rd %tick,%o1 |
| 281 | .word 0x81b00d80 !fxor %f0,%f0,%f0 |
| 282 | .word 0x85b08d82 !fxor %f2,%f2,%f2 |
| 283 | .word 0x95410000 !rd %tick,%o2 |
| 284 | .word 0x81b00d80 !fxor %f0,%f0,%f0 |
| 285 | .word 0x85b08d82 !fxor %f2,%f2,%f2 |
| 286 | .word 0x97410000 !rd %tick,%o3 |
| 287 | .word 0x81b00d80 !fxor %f0,%f0,%f0 |
| 288 | .word 0x85b08d82 !fxor %f2,%f2,%f2 |
| 289 | .word 0x99410000 !rd %tick,%o4 |
| 290 | |
| 291 | ! calculate intervals |
| 292 | sub %o1,%o0,%o0 |
| 293 | sub %o2,%o1,%o1 |
| 294 | sub %o3,%o2,%o2 |
| 295 | sub %o4,%o3,%o3 |
| 296 | |
| 297 | ! find minimum value |
| 298 | cmp %o0,%o1 |
| 299 | .word 0x38680002 !bgu,a %xcc,.+8 |
| 300 | mov %o1,%o0 |
| 301 | cmp %o0,%o2 |
| 302 | .word 0x38680002 !bgu,a %xcc,.+8 |
| 303 | mov %o2,%o0 |
| 304 | cmp %o0,%o3 |
| 305 | .word 0x38680002 !bgu,a %xcc,.+8 |
| 306 | mov %o3,%o0 |
| 307 | |
| 308 | retl |
| 309 | nop |
| 310 | .type _sparcv9_vis1_instrument,#function |
| 311 | .size _sparcv9_vis1_instrument,.-_sparcv9_vis1_instrument |
| 312 | |
| 313 | .global _sparcv9_vis2_probe |
| 314 | .align 8 |
| 315 | _sparcv9_vis2_probe: |
| 316 | retl |
| 317 | .word 0x81b00980 !bshuffle %f0,%f0,%f0 |
| 318 | .type _sparcv9_vis2_probe,#function |
| 319 | .size _sparcv9_vis2_probe,.-_sparcv9_vis2_probe |
| 320 | |
| 321 | .global _sparcv9_fmadd_probe |
| 322 | .align 8 |
| 323 | _sparcv9_fmadd_probe: |
| 324 | .word 0x81b00d80 !fxor %f0,%f0,%f0 |
| 325 | .word 0x85b08d82 !fxor %f2,%f2,%f2 |
| 326 | retl |
| 327 | .word 0x81b80440 !fmaddd %f0,%f0,%f2,%f0 |
| 328 | .type _sparcv9_fmadd_probe,#function |
| 329 | .size _sparcv9_fmadd_probe,.-_sparcv9_fmadd_probe |
| 330 | |
| 331 | .global _sparcv9_rdcfr |
| 332 | .align 8 |
| 333 | _sparcv9_rdcfr: |
| 334 | retl |
| 335 | .word 0x91468000 !rd %asr26,%o0 |
| 336 | .type _sparcv9_rdcfr,#function |
| 337 | .size _sparcv9_rdcfr,.-_sparcv9_rdcfr |
| 338 | |
| 339 | .global _sparcv9_vis3_probe |
| 340 | .align 8 |
| 341 | _sparcv9_vis3_probe: |
| 342 | retl |
| 343 | .word 0x81b022a0 !xmulx %g0,%g0,%g0 |
| 344 | .type _sparcv9_vis3_probe,#function |
| 345 | .size _sparcv9_vis3_probe,.-_sparcv9_vis3_probe |
| 346 | |
| 347 | .global _sparcv9_random |
| 348 | .align 8 |
| 349 | _sparcv9_random: |
| 350 | retl |
| 351 | .word 0x91b002a0 !random %o0 |
| 352 | .type _sparcv9_random,#function |
| 353 | .size _sparcv9_random,.-_sparcv9_vis3_probe |
| 354 | |
| 355 | .global _sparcv9_fjaesx_probe |
| 356 | .align 8 |
| 357 | _sparcv9_fjaesx_probe: |
| 358 | .word 0x81b09206 !faesencx %f2,%f6,%f0 |
| 359 | retl |
| 360 | nop |
| 361 | .size _sparcv9_fjaesx_probe,.-_sparcv9_fjaesx_probe |
| 362 | |
| 363 | .global OPENSSL_cleanse |
| 364 | .align 32 |
| 365 | OPENSSL_cleanse: |
| 366 | cmp %o1,14 |
| 367 | nop |
| 368 | #ifdef ABI64 |
| 369 | bgu %xcc,.Lot |
| 370 | #else |
| 371 | bgu .Lot |
| 372 | #endif |
| 373 | cmp %o1,0 |
| 374 | bne .Little |
| 375 | nop |
| 376 | retl |
| 377 | nop |
| 378 | |
| 379 | .Little: |
| 380 | stb %g0,[%o0] |
| 381 | subcc %o1,1,%o1 |
| 382 | bnz .Little |
| 383 | add %o0,1,%o0 |
| 384 | retl |
| 385 | nop |
| 386 | .align 32 |
| 387 | .Lot: |
| 388 | #ifndef ABI64 |
| 389 | subcc %g0,1,%g1 |
| 390 | ! see above for explanation |
| 391 | .word 0x83408000 !rd %ccr,%g1 |
| 392 | cmp %g1,0x99 |
| 393 | bne .v8lot |
| 394 | nop |
| 395 | #endif |
| 396 | |
| 397 | .v9lot: andcc %o0,7,%g0 |
| 398 | bz .v9aligned |
| 399 | nop |
| 400 | stb %g0,[%o0] |
| 401 | sub %o1,1,%o1 |
| 402 | ba .v9lot |
| 403 | add %o0,1,%o0 |
| 404 | .align 16,0x01000000 |
| 405 | .v9aligned: |
| 406 | .word 0xc0720000 !stx %g0,[%o0] |
| 407 | sub %o1,8,%o1 |
| 408 | andcc %o1,-8,%g0 |
| 409 | #ifdef ABI64 |
| 410 | .word 0x126ffffd !bnz %xcc,.v9aligned |
| 411 | #else |
| 412 | .word 0x124ffffd !bnz %icc,.v9aligned |
| 413 | #endif |
| 414 | add %o0,8,%o0 |
| 415 | |
| 416 | cmp %o1,0 |
| 417 | bne .Little |
| 418 | nop |
| 419 | retl |
| 420 | nop |
| 421 | #ifndef ABI64 |
| 422 | .v8lot: andcc %o0,3,%g0 |
| 423 | bz .v8aligned |
| 424 | nop |
| 425 | stb %g0,[%o0] |
| 426 | sub %o1,1,%o1 |
| 427 | ba .v8lot |
| 428 | add %o0,1,%o0 |
| 429 | nop |
| 430 | .v8aligned: |
| 431 | st %g0,[%o0] |
| 432 | sub %o1,4,%o1 |
| 433 | andcc %o1,-4,%g0 |
| 434 | bnz .v8aligned |
| 435 | add %o0,4,%o0 |
| 436 | |
| 437 | cmp %o1,0 |
| 438 | bne .Little |
| 439 | nop |
| 440 | retl |
| 441 | nop |
| 442 | #endif |
| 443 | .type OPENSSL_cleanse,#function |
| 444 | .size OPENSSL_cleanse,.-OPENSSL_cleanse |
| 445 | |
| 446 | .global CRYPTO_memcmp |
| 447 | .align 16 |
| 448 | CRYPTO_memcmp: |
| 449 | cmp %o2,0 |
| 450 | #ifdef ABI64 |
| 451 | beq,pn %xcc,.Lno_data |
| 452 | #else |
| 453 | beq .Lno_data |
| 454 | #endif |
| 455 | xor %g1,%g1,%g1 |
| 456 | nop |
| 457 | |
| 458 | .Loop_cmp: |
| 459 | ldub [%o0],%o3 |
| 460 | add %o0,1,%o0 |
| 461 | ldub [%o1],%o4 |
| 462 | add %o1,1,%o1 |
| 463 | subcc %o2,1,%o2 |
| 464 | xor %o3,%o4,%o4 |
| 465 | #ifdef ABI64 |
| 466 | bnz %xcc,.Loop_cmp |
| 467 | #else |
| 468 | bnz .Loop_cmp |
| 469 | #endif |
| 470 | or %o4,%g1,%g1 |
| 471 | |
| 472 | sub %g0,%g1,%g1 |
| 473 | srl %g1,31,%g1 |
| 474 | .Lno_data: |
| 475 | retl |
| 476 | mov %g1,%o0 |
| 477 | .type CRYPTO_memcmp,#function |
| 478 | .size CRYPTO_memcmp,.-CRYPTO_memcmp |
| 479 | |
| 480 | .global _sparcv9_vis1_instrument_bus |
| 481 | .align 8 |
| 482 | _sparcv9_vis1_instrument_bus: |
| 483 | mov %o1,%o3 ! save cnt |
| 484 | .word 0x99410000 !rd %tick,%o4 ! tick |
| 485 | mov %o4,%o5 ! lasttick = tick |
| 486 | set 0,%g4 ! diff |
| 487 | |
| 488 | andn %o0,63,%g1 |
| 489 | .word 0xc1985e00 !ldda [%g1]0xf0,%f0 ! block load |
| 490 | .word 0x8143e040 !membar #Sync |
| 491 | .word 0xc1b85c00 !stda %f0,[%g1]0xe0 ! block store and commit |
| 492 | .word 0x8143e040 !membar #Sync |
| 493 | ld [%o0],%o4 |
| 494 | add %o4,%g4,%g4 |
| 495 | .word 0xc9e2100c !cas [%o0],%o4,%g4 |
| 496 | |
| 497 | .Loop: .word 0x99410000 !rd %tick,%o4 |
| 498 | sub %o4,%o5,%g4 ! diff=tick-lasttick |
| 499 | mov %o4,%o5 ! lasttick=tick |
| 500 | |
| 501 | andn %o0,63,%g1 |
| 502 | .word 0xc1985e00 !ldda [%g1]0xf0,%f0 ! block load |
| 503 | .word 0x8143e040 !membar #Sync |
| 504 | .word 0xc1b85c00 !stda %f0,[%g1]0xe0 ! block store and commit |
| 505 | .word 0x8143e040 !membar #Sync |
| 506 | ld [%o0],%o4 |
| 507 | add %o4,%g4,%g4 |
| 508 | .word 0xc9e2100c !cas [%o0],%o4,%g4 |
| 509 | subcc %o1,1,%o1 ! --$cnt |
| 510 | bnz .Loop |
| 511 | add %o0,4,%o0 ! ++$out |
| 512 | |
| 513 | retl |
| 514 | mov %o3,%o0 |
| 515 | .type _sparcv9_vis1_instrument_bus,#function |
| 516 | .size _sparcv9_vis1_instrument_bus,.-_sparcv9_vis1_instrument_bus |
| 517 | |
| 518 | .global _sparcv9_vis1_instrument_bus2 |
| 519 | .align 8 |
| 520 | _sparcv9_vis1_instrument_bus2: |
| 521 | mov %o1,%o3 ! save cnt |
| 522 | sll %o1,2,%o1 ! cnt*=4 |
| 523 | |
| 524 | .word 0x99410000 !rd %tick,%o4 ! tick |
| 525 | mov %o4,%o5 ! lasttick = tick |
| 526 | set 0,%g4 ! diff |
| 527 | |
| 528 | andn %o0,63,%g1 |
| 529 | .word 0xc1985e00 !ldda [%g1]0xf0,%f0 ! block load |
| 530 | .word 0x8143e040 !membar #Sync |
| 531 | .word 0xc1b85c00 !stda %f0,[%g1]0xe0 ! block store and commit |
| 532 | .word 0x8143e040 !membar #Sync |
| 533 | ld [%o0],%o4 |
| 534 | add %o4,%g4,%g4 |
| 535 | .word 0xc9e2100c !cas [%o0],%o4,%g4 |
| 536 | |
| 537 | .word 0x99410000 !rd %tick,%o4 ! tick |
| 538 | sub %o4,%o5,%g4 ! diff=tick-lasttick |
| 539 | mov %o4,%o5 ! lasttick=tick |
| 540 | mov %g4,%g5 ! lastdiff=diff |
| 541 | .Loop2: |
| 542 | andn %o0,63,%g1 |
| 543 | .word 0xc1985e00 !ldda [%g1]0xf0,%f0 ! block load |
| 544 | .word 0x8143e040 !membar #Sync |
| 545 | .word 0xc1b85c00 !stda %f0,[%g1]0xe0 ! block store and commit |
| 546 | .word 0x8143e040 !membar #Sync |
| 547 | ld [%o0],%o4 |
| 548 | add %o4,%g4,%g4 |
| 549 | .word 0xc9e2100c !cas [%o0],%o4,%g4 |
| 550 | |
| 551 | subcc %o2,1,%o2 ! --max |
| 552 | bz .Ldone2 |
| 553 | nop |
| 554 | |
| 555 | .word 0x99410000 !rd %tick,%o4 ! tick |
| 556 | sub %o4,%o5,%g4 ! diff=tick-lasttick |
| 557 | mov %o4,%o5 ! lasttick=tick |
| 558 | cmp %g4,%g5 |
| 559 | mov %g4,%g5 ! lastdiff=diff |
| 560 | |
| 561 | .word 0x83408000 !rd %ccr,%g1 |
| 562 | and %g1,4,%g1 ! isolate zero flag |
| 563 | xor %g1,4,%g1 ! flip zero flag |
| 564 | |
| 565 | subcc %o1,%g1,%o1 ! conditional --$cnt |
| 566 | bnz .Loop2 |
| 567 | add %o0,%g1,%o0 ! conditional ++$out |
| 568 | |
| 569 | .Ldone2: |
| 570 | srl %o1,2,%o1 |
| 571 | retl |
| 572 | sub %o3,%o1,%o0 |
| 573 | .type _sparcv9_vis1_instrument_bus2,#function |
| 574 | .size _sparcv9_vis1_instrument_bus2,.-_sparcv9_vis1_instrument_bus2 |
| 575 | |
| 576 | .section ".init",#alloc,#execinstr |
| 577 | call OPENSSL_cpuid_setup |
| 578 | nop |