Hi Nick, Thank you for the patch! Perhaps something to improve: [auto build test WARNING on cryptodev/master] [also build test WARNING on kdave/for-next f2fs/dev-test linus/master v5.10-rc3 next-20201113] [cannot apply to crypto/master squashfs/master] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in https://git-scm.com/docs/git-format-patch] url: https://github.com/0day-ci/linux/commits/Nick-Terrell/lib-zstd-Add-zstd-compatibility-wrapper/20201103-150617 base: https://git.kernel.org/pub/scm/linux/kernel/git/herbert/cryptodev-2.6.git master config: h8300-randconfig-r033-20201104 (attached as .config) compiler: h8300-linux-gcc (GCC) 9.3.0 reproduce (this is a W=1 build): wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross # https://github.com/0day-ci/linux/commit/667e96565ce79ec24e0ced9ec4093e92647e4163 git remote add linux-review https://github.com/0day-ci/linux git fetch --no-tags linux-review Nick-Terrell/lib-zstd-Add-zstd-compatibility-wrapper/20201103-150617 git checkout 667e96565ce79ec24e0ced9ec4093e92647e4163 # save the attached .config to linux build tree COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=h8300 If you fix the issue, kindly add following tag as appropriate Reported-by: kernel test robot <lkp@xxxxxxxxx> All warnings (new ones prefixed by >>): lib/zstd/compress/zstd_double_fast.c: In function 'ZSTD_compressBlock_doubleFast_extDict_generic': >> lib/zstd/compress/zstd_double_fast.c:501:1: warning: the frame size of 1256 bytes is larger than 1024 bytes [-Wframe-larger-than=] 501 | } | ^ lib/zstd/compress/zstd_double_fast.c: In function 'ZSTD_compressBlock_doubleFast': lib/zstd/compress/zstd_double_fast.c:336:1: warning: the frame size of 1224 bytes is larger than 1024 bytes [-Wframe-larger-than=] 336 | } | ^ lib/zstd/compress/zstd_double_fast.c: In function 'ZSTD_compressBlock_doubleFast_dictMatchState': lib/zstd/compress/zstd_double_fast.c:356:1: warning: the frame size of 1320 bytes is larger than 1024 bytes [-Wframe-larger-than=] 356 | } | ^ -- lib/zstd/compress/zstd_fast.c: In function 'ZSTD_compressBlock_fast_extDict_generic': >> lib/zstd/compress/zstd_fast.c:476:1: warning: the frame size of 1156 bytes is larger than 1024 bytes [-Wframe-larger-than=] 476 | } | ^ vim +501 lib/zstd/compress/zstd_double_fast.c 357 358 359 static size_t ZSTD_compressBlock_doubleFast_extDict_generic( 360 ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], 361 void const* src, size_t srcSize, 362 U32 const mls /* template */) 363 { 364 ZSTD_compressionParameters const* cParams = &ms->cParams; 365 U32* const hashLong = ms->hashTable; 366 U32 const hBitsL = cParams->hashLog; 367 U32* const hashSmall = ms->chainTable; 368 U32 const hBitsS = cParams->chainLog; 369 const BYTE* const istart = (const BYTE*)src; 370 const BYTE* ip = istart; 371 const BYTE* anchor = istart; 372 const BYTE* const iend = istart + srcSize; 373 const BYTE* const ilimit = iend - 8; 374 const BYTE* const base = ms->window.base; 375 const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); 376 const U32 lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog); 377 const U32 dictStartIndex = lowLimit; 378 const U32 dictLimit = ms->window.dictLimit; 379 const U32 prefixStartIndex = (dictLimit > lowLimit) ? dictLimit : lowLimit; 380 const BYTE* const prefixStart = base + prefixStartIndex; 381 const BYTE* const dictBase = ms->window.dictBase; 382 const BYTE* const dictStart = dictBase + dictStartIndex; 383 const BYTE* const dictEnd = dictBase + prefixStartIndex; 384 U32 offset_1=rep[0], offset_2=rep[1]; 385 386 DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_extDict_generic (srcSize=%zu)", srcSize); 387 388 /* if extDict is invalidated due to maxDistance, switch to "regular" variant */ 389 if (prefixStartIndex == dictStartIndex) 390 return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, mls, ZSTD_noDict); 391 392 /* Search Loop */ 393 while (ip < ilimit) { /* < instead of <=, because (ip+1) */ 394 const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls); 395 const U32 matchIndex = hashSmall[hSmall]; 396 const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base; 397 const BYTE* match = matchBase + matchIndex; 398 399 const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8); 400 const U32 matchLongIndex = hashLong[hLong]; 401 const BYTE* const matchLongBase = matchLongIndex < prefixStartIndex ? dictBase : base; 402 const BYTE* matchLong = matchLongBase + matchLongIndex; 403 404 const U32 curr = (U32)(ip-base); 405 const U32 repIndex = curr + 1 - offset_1; /* offset_1 expected <= curr +1 */ 406 const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base; 407 const BYTE* const repMatch = repBase + repIndex; 408 size_t mLength; 409 hashSmall[hSmall] = hashLong[hLong] = curr; /* update hash table */ 410 411 if ((((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex doesn't overlap dict + prefix */ 412 & (repIndex > dictStartIndex)) 413 && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { 414 const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; 415 mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4; 416 ip++; 417 ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH); 418 } else { 419 if ((matchLongIndex > dictStartIndex) && (MEM_read64(matchLong) == MEM_read64(ip))) { 420 const BYTE* const matchEnd = matchLongIndex < prefixStartIndex ? dictEnd : iend; 421 const BYTE* const lowMatchPtr = matchLongIndex < prefixStartIndex ? dictStart : prefixStart; 422 U32 offset; 423 mLength = ZSTD_count_2segments(ip+8, matchLong+8, iend, matchEnd, prefixStart) + 8; 424 offset = curr - matchLongIndex; 425 while (((ip>anchor) & (matchLong>lowMatchPtr)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */ 426 offset_2 = offset_1; 427 offset_1 = offset; 428 ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH); 429 430 } else if ((matchIndex > dictStartIndex) && (MEM_read32(match) == MEM_read32(ip))) { 431 size_t const h3 = ZSTD_hashPtr(ip+1, hBitsL, 8); 432 U32 const matchIndex3 = hashLong[h3]; 433 const BYTE* const match3Base = matchIndex3 < prefixStartIndex ? dictBase : base; 434 const BYTE* match3 = match3Base + matchIndex3; 435 U32 offset; 436 hashLong[h3] = curr + 1; 437 if ( (matchIndex3 > dictStartIndex) && (MEM_read64(match3) == MEM_read64(ip+1)) ) { 438 const BYTE* const matchEnd = matchIndex3 < prefixStartIndex ? dictEnd : iend; 439 const BYTE* const lowMatchPtr = matchIndex3 < prefixStartIndex ? dictStart : prefixStart; 440 mLength = ZSTD_count_2segments(ip+9, match3+8, iend, matchEnd, prefixStart) + 8; 441 ip++; 442 offset = curr+1 - matchIndex3; 443 while (((ip>anchor) & (match3>lowMatchPtr)) && (ip[-1] == match3[-1])) { ip--; match3--; mLength++; } /* catch up */ 444 } else { 445 const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend; 446 const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart; 447 mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4; 448 offset = curr - matchIndex; 449 while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ 450 } 451 offset_2 = offset_1; 452 offset_1 = offset; 453 ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH); 454 455 } else { 456 ip += ((ip-anchor) >> kSearchStrength) + 1; 457 continue; 458 } } 459 460 /* move to next sequence start */ 461 ip += mLength; 462 anchor = ip; 463 464 if (ip <= ilimit) { 465 /* Complementary insertion */ 466 /* done after iLimit test, as candidates could be > iend-8 */ 467 { U32 const indexToInsert = curr+2; 468 hashLong[ZSTD_hashPtr(base+indexToInsert, hBitsL, 8)] = indexToInsert; 469 hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] = (U32)(ip-2-base); 470 hashSmall[ZSTD_hashPtr(base+indexToInsert, hBitsS, mls)] = indexToInsert; 471 hashSmall[ZSTD_hashPtr(ip-1, hBitsS, mls)] = (U32)(ip-1-base); 472 } 473 474 /* check immediate repcode */ 475 while (ip <= ilimit) { 476 U32 const current2 = (U32)(ip-base); 477 U32 const repIndex2 = current2 - offset_2; 478 const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2; 479 if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) /* intentional overflow : ensure repIndex2 doesn't overlap dict + prefix */ 480 & (repIndex2 > dictStartIndex)) 481 && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { 482 const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend; 483 size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; 484 U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ 485 ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, repLength2-MINMATCH); 486 hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2; 487 hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2; 488 ip += repLength2; 489 anchor = ip; 490 continue; 491 } 492 break; 493 } } } 494 495 /* save reps for next block */ 496 rep[0] = offset_1; 497 rep[1] = offset_2; 498 499 /* Return the last literals size */ 500 return (size_t)(iend - anchor); > 501 } 502 --- 0-DAY CI Kernel Test Service, Intel Corporation https://lists.01.org/hyperkitty/list/kbuild-all@xxxxxxxxxxxx
Attachment:
.config.gz
Description: application/gzip
