hashfn.c 17.5 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696
/*-------------------------------------------------------------------------
 *
 * hashfn.c
 *		Generic hashing functions, and hash functions for use in dynahash.c
 *		hashtables
 *
 *
 * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/utils/hash/hashfn.c
 *
 * NOTES
 *	  It is expected that every bit of a hash function's 32-bit result is
 *	  as random as every other; failure to ensure this is likely to lead
 *	  to poor performance of hash tables.  In most cases a hash
 *	  function should use hash_any() or its variant hash_uint32().
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "fmgr.h"
#include "utils/hashutils.h"
#include "utils/hsearch.h"


/*
 * This hash function was written by Bob Jenkins
 * (bob_jenkins@burtleburtle.net), and superficially adapted
 * for PostgreSQL by Neil Conway. For more information on this
 * hash function, see http://burtleburtle.net/bob/hash/doobs.html,
 * or Bob's article in Dr. Dobb's Journal, Sept. 1997.
 *
 * In the current code, we have adopted Bob's 2006 update of his hash
 * function to fetch the data a word at a time when it is suitably aligned.
 * This makes for a useful speedup, at the cost of having to maintain
 * four code paths (aligned vs unaligned, and little-endian vs big-endian).
 * It also uses two separate mixing functions mix() and final(), instead
 * of a slower multi-purpose function.
 */

/* Get a bit mask of the bits set in non-uint32 aligned addresses */
#define UINT32_ALIGN_MASK (sizeof(uint32) - 1)

/* Rotate a uint32 value left by k bits - note multiple evaluation! */
#define rot(x,k) (((x)<<(k)) | ((x)>>(32-(k))))

/*----------
 * mix -- mix 3 32-bit values reversibly.
 *
 * This is reversible, so any information in (a,b,c) before mix() is
 * still in (a,b,c) after mix().
 *
 * If four pairs of (a,b,c) inputs are run through mix(), or through
 * mix() in reverse, there are at least 32 bits of the output that
 * are sometimes the same for one pair and different for another pair.
 * This was tested for:
 * * pairs that differed by one bit, by two bits, in any combination
 *	 of top bits of (a,b,c), or in any combination of bottom bits of
 *	 (a,b,c).
 * * "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
 *	 the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
 *	 is commonly produced by subtraction) look like a single 1-bit
 *	 difference.
 * * the base values were pseudorandom, all zero but one bit set, or
 *	 all zero plus a counter that starts at zero.
 *
 * This does not achieve avalanche.  There are input bits of (a,b,c)
 * that fail to affect some output bits of (a,b,c), especially of a.  The
 * most thoroughly mixed value is c, but it doesn't really even achieve
 * avalanche in c.
 *
 * This allows some parallelism.  Read-after-writes are good at doubling
 * the number of bits affected, so the goal of mixing pulls in the opposite
 * direction from the goal of parallelism.  I did what I could.  Rotates
 * seem to cost as much as shifts on every machine I could lay my hands on,
 * and rotates are much kinder to the top and bottom bits, so I used rotates.
 *----------
 */
#define mix(a,b,c) \
{ \
  a -= c;  a ^= rot(c, 4);	c += b; \
  b -= a;  b ^= rot(a, 6);	a += c; \
  c -= b;  c ^= rot(b, 8);	b += a; \
  a -= c;  a ^= rot(c,16);	c += b; \
  b -= a;  b ^= rot(a,19);	a += c; \
  c -= b;  c ^= rot(b, 4);	b += a; \
}

/*----------
 * final -- final mixing of 3 32-bit values (a,b,c) into c
 *
 * Pairs of (a,b,c) values differing in only a few bits will usually
 * produce values of c that look totally different.  This was tested for
 * * pairs that differed by one bit, by two bits, in any combination
 *	 of top bits of (a,b,c), or in any combination of bottom bits of
 *	 (a,b,c).
 * * "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
 *	 the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
 *	 is commonly produced by subtraction) look like a single 1-bit
 *	 difference.
 * * the base values were pseudorandom, all zero but one bit set, or
 *	 all zero plus a counter that starts at zero.
 *
 * The use of separate functions for mix() and final() allow for a
 * substantial performance increase since final() does not need to
 * do well in reverse, but is does need to affect all output bits.
 * mix(), on the other hand, does not need to affect all output
 * bits (affecting 32 bits is enough).  The original hash function had
 * a single mixing operation that had to satisfy both sets of requirements
 * and was slower as a result.
 *----------
 */
#define final(a,b,c) \
{ \
  c ^= b; c -= rot(b,14); \
  a ^= c; a -= rot(c,11); \
  b ^= a; b -= rot(a,25); \
  c ^= b; c -= rot(b,16); \
  a ^= c; a -= rot(c, 4); \
  b ^= a; b -= rot(a,14); \
  c ^= b; c -= rot(b,24); \
}

/*
 * hash_any() -- hash a variable-length key into a 32-bit value
 *		k		: the key (the unaligned variable-length array of bytes)
 *		len		: the length of the key, counting by bytes
 *
 * Returns a uint32 value.  Every bit of the key affects every bit of
 * the return value.  Every 1-bit and 2-bit delta achieves avalanche.
 * About 6*len+35 instructions. The best hash table sizes are powers
 * of 2.  There is no need to do mod a prime (mod is sooo slow!).
 * If you need less than 32 bits, use a bitmask.
 *
 * This procedure must never throw elog(ERROR); the ResourceOwner code
 * relies on this not to fail.
 *
 * Note: we could easily change this function to return a 64-bit hash value
 * by using the final values of both b and c.  b is perhaps a little less
 * well mixed than c, however.
 */
Datum
hash_any(const unsigned char *k, int keylen)
{
	uint32		a,
				b,
				c,
				len;

	/* Set up the internal state */
	len = keylen;
	a = b = c = 0x9e3779b9 + len + 3923095;

	/* If the source pointer is word-aligned, we use word-wide fetches */
	if (((uintptr_t) k & UINT32_ALIGN_MASK) == 0)
	{
		/* Code path for aligned source data */
		const uint32 *ka = (const uint32 *) k;

		/* handle most of the key */
		while (len >= 12)
		{
			a += ka[0];
			b += ka[1];
			c += ka[2];
			mix(a, b, c);
			ka += 3;
			len -= 12;
		}

		/* handle the last 11 bytes */
		k = (const unsigned char *) ka;
#ifdef WORDS_BIGENDIAN
		switch (len)
		{
			case 11:
				c += ((uint32) k[10] << 8);
				/* fall through */
			case 10:
				c += ((uint32) k[9] << 16);
				/* fall through */
			case 9:
				c += ((uint32) k[8] << 24);
				/* fall through */
			case 8:
				/* the lowest byte of c is reserved for the length */
				b += ka[1];
				a += ka[0];
				break;
			case 7:
				b += ((uint32) k[6] << 8);
				/* fall through */
			case 6:
				b += ((uint32) k[5] << 16);
				/* fall through */
			case 5:
				b += ((uint32) k[4] << 24);
				/* fall through */
			case 4:
				a += ka[0];
				break;
			case 3:
				a += ((uint32) k[2] << 8);
				/* fall through */
			case 2:
				a += ((uint32) k[1] << 16);
				/* fall through */
			case 1:
				a += ((uint32) k[0] << 24);
				/* case 0: nothing left to add */
		}
#else							/* !WORDS_BIGENDIAN */
		switch (len)
		{
			case 11:
				c += ((uint32) k[10] << 24);
				/* fall through */
			case 10:
				c += ((uint32) k[9] << 16);
				/* fall through */
			case 9:
				c += ((uint32) k[8] << 8);
				/* fall through */
			case 8:
				/* the lowest byte of c is reserved for the length */
				b += ka[1];
				a += ka[0];
				break;
			case 7:
				b += ((uint32) k[6] << 16);
				/* fall through */
			case 6:
				b += ((uint32) k[5] << 8);
				/* fall through */
			case 5:
				b += k[4];
				/* fall through */
			case 4:
				a += ka[0];
				break;
			case 3:
				a += ((uint32) k[2] << 16);
				/* fall through */
			case 2:
				a += ((uint32) k[1] << 8);
				/* fall through */
			case 1:
				a += k[0];
				/* case 0: nothing left to add */
		}
#endif							/* WORDS_BIGENDIAN */
	}
	else
	{
		/* Code path for non-aligned source data */

		/* handle most of the key */
		while (len >= 12)
		{
#ifdef WORDS_BIGENDIAN
			a += (k[3] + ((uint32) k[2] << 8) + ((uint32) k[1] << 16) + ((uint32) k[0] << 24));
			b += (k[7] + ((uint32) k[6] << 8) + ((uint32) k[5] << 16) + ((uint32) k[4] << 24));
			c += (k[11] + ((uint32) k[10] << 8) + ((uint32) k[9] << 16) + ((uint32) k[8] << 24));
#else							/* !WORDS_BIGENDIAN */
			a += (k[0] + ((uint32) k[1] << 8) + ((uint32) k[2] << 16) + ((uint32) k[3] << 24));
			b += (k[4] + ((uint32) k[5] << 8) + ((uint32) k[6] << 16) + ((uint32) k[7] << 24));
			c += (k[8] + ((uint32) k[9] << 8) + ((uint32) k[10] << 16) + ((uint32) k[11] << 24));
#endif							/* WORDS_BIGENDIAN */
			mix(a, b, c);
			k += 12;
			len -= 12;
		}

		/* handle the last 11 bytes */
#ifdef WORDS_BIGENDIAN
		switch (len)
		{
			case 11:
				c += ((uint32) k[10] << 8);
				/* fall through */
			case 10:
				c += ((uint32) k[9] << 16);
				/* fall through */
			case 9:
				c += ((uint32) k[8] << 24);
				/* fall through */
			case 8:
				/* the lowest byte of c is reserved for the length */
				b += k[7];
				/* fall through */
			case 7:
				b += ((uint32) k[6] << 8);
				/* fall through */
			case 6:
				b += ((uint32) k[5] << 16);
				/* fall through */
			case 5:
				b += ((uint32) k[4] << 24);
				/* fall through */
			case 4:
				a += k[3];
				/* fall through */
			case 3:
				a += ((uint32) k[2] << 8);
				/* fall through */
			case 2:
				a += ((uint32) k[1] << 16);
				/* fall through */
			case 1:
				a += ((uint32) k[0] << 24);
				/* case 0: nothing left to add */
		}
#else							/* !WORDS_BIGENDIAN */
		switch (len)
		{
			case 11:
				c += ((uint32) k[10] << 24);
				/* fall through */
			case 10:
				c += ((uint32) k[9] << 16);
				/* fall through */
			case 9:
				c += ((uint32) k[8] << 8);
				/* fall through */
			case 8:
				/* the lowest byte of c is reserved for the length */
				b += ((uint32) k[7] << 24);
				/* fall through */
			case 7:
				b += ((uint32) k[6] << 16);
				/* fall through */
			case 6:
				b += ((uint32) k[5] << 8);
				/* fall through */
			case 5:
				b += k[4];
				/* fall through */
			case 4:
				a += ((uint32) k[3] << 24);
				/* fall through */
			case 3:
				a += ((uint32) k[2] << 16);
				/* fall through */
			case 2:
				a += ((uint32) k[1] << 8);
				/* fall through */
			case 1:
				a += k[0];
				/* case 0: nothing left to add */
		}
#endif							/* WORDS_BIGENDIAN */
	}

	final(a, b, c);

	/* report the result */
	return UInt32GetDatum(c);
}

/*
 * hash_any_extended() -- hash into a 64-bit value, using an optional seed
 *		k		: the key (the unaligned variable-length array of bytes)
 *		len		: the length of the key, counting by bytes
 *		seed	: a 64-bit seed (0 means no seed)
 *
 * Returns a uint64 value.  Otherwise similar to hash_any.
 */
Datum
hash_any_extended(const unsigned char *k, int keylen,
				  uint64 seed)
{
	uint32		a,
				b,
				c,
				len;

	/* Set up the internal state */
	len = keylen;
	a = b = c = 0x9e3779b9 + len + 3923095;

	/* If the seed is non-zero, use it to perturb the internal state. */
	if (seed != 0)
	{
		/*
		 * In essence, the seed is treated as part of the data being hashed,
		 * but for simplicity, we pretend that it's padded with four bytes of
		 * zeroes so that the seed constitutes a 12-byte chunk.
		 */
		a += (uint32) (seed >> 32);
		b += (uint32) seed;
		mix(a, b, c);
	}

	/* If the source pointer is word-aligned, we use word-wide fetches */
	if (((uintptr_t) k & UINT32_ALIGN_MASK) == 0)
	{
		/* Code path for aligned source data */
		const uint32 *ka = (const uint32 *) k;

		/* handle most of the key */
		while (len >= 12)
		{
			a += ka[0];
			b += ka[1];
			c += ka[2];
			mix(a, b, c);
			ka += 3;
			len -= 12;
		}

		/* handle the last 11 bytes */
		k = (const unsigned char *) ka;
#ifdef WORDS_BIGENDIAN
		switch (len)
		{
			case 11:
				c += ((uint32) k[10] << 8);
				/* fall through */
			case 10:
				c += ((uint32) k[9] << 16);
				/* fall through */
			case 9:
				c += ((uint32) k[8] << 24);
				/* fall through */
			case 8:
				/* the lowest byte of c is reserved for the length */
				b += ka[1];
				a += ka[0];
				break;
			case 7:
				b += ((uint32) k[6] << 8);
				/* fall through */
			case 6:
				b += ((uint32) k[5] << 16);
				/* fall through */
			case 5:
				b += ((uint32) k[4] << 24);
				/* fall through */
			case 4:
				a += ka[0];
				break;
			case 3:
				a += ((uint32) k[2] << 8);
				/* fall through */
			case 2:
				a += ((uint32) k[1] << 16);
				/* fall through */
			case 1:
				a += ((uint32) k[0] << 24);
				/* case 0: nothing left to add */
		}
#else							/* !WORDS_BIGENDIAN */
		switch (len)
		{
			case 11:
				c += ((uint32) k[10] << 24);
				/* fall through */
			case 10:
				c += ((uint32) k[9] << 16);
				/* fall through */
			case 9:
				c += ((uint32) k[8] << 8);
				/* fall through */
			case 8:
				/* the lowest byte of c is reserved for the length */
				b += ka[1];
				a += ka[0];
				break;
			case 7:
				b += ((uint32) k[6] << 16);
				/* fall through */
			case 6:
				b += ((uint32) k[5] << 8);
				/* fall through */
			case 5:
				b += k[4];
				/* fall through */
			case 4:
				a += ka[0];
				break;
			case 3:
				a += ((uint32) k[2] << 16);
				/* fall through */
			case 2:
				a += ((uint32) k[1] << 8);
				/* fall through */
			case 1:
				a += k[0];
				/* case 0: nothing left to add */
		}
#endif							/* WORDS_BIGENDIAN */
	}
	else
	{
		/* Code path for non-aligned source data */

		/* handle most of the key */
		while (len >= 12)
		{
#ifdef WORDS_BIGENDIAN
			a += (k[3] + ((uint32) k[2] << 8) + ((uint32) k[1] << 16) + ((uint32) k[0] << 24));
			b += (k[7] + ((uint32) k[6] << 8) + ((uint32) k[5] << 16) + ((uint32) k[4] << 24));
			c += (k[11] + ((uint32) k[10] << 8) + ((uint32) k[9] << 16) + ((uint32) k[8] << 24));
#else							/* !WORDS_BIGENDIAN */
			a += (k[0] + ((uint32) k[1] << 8) + ((uint32) k[2] << 16) + ((uint32) k[3] << 24));
			b += (k[4] + ((uint32) k[5] << 8) + ((uint32) k[6] << 16) + ((uint32) k[7] << 24));
			c += (k[8] + ((uint32) k[9] << 8) + ((uint32) k[10] << 16) + ((uint32) k[11] << 24));
#endif							/* WORDS_BIGENDIAN */
			mix(a, b, c);
			k += 12;
			len -= 12;
		}

		/* handle the last 11 bytes */
#ifdef WORDS_BIGENDIAN
		switch (len)
		{
			case 11:
				c += ((uint32) k[10] << 8);
				/* fall through */
			case 10:
				c += ((uint32) k[9] << 16);
				/* fall through */
			case 9:
				c += ((uint32) k[8] << 24);
				/* fall through */
			case 8:
				/* the lowest byte of c is reserved for the length */
				b += k[7];
				/* fall through */
			case 7:
				b += ((uint32) k[6] << 8);
				/* fall through */
			case 6:
				b += ((uint32) k[5] << 16);
				/* fall through */
			case 5:
				b += ((uint32) k[4] << 24);
				/* fall through */
			case 4:
				a += k[3];
				/* fall through */
			case 3:
				a += ((uint32) k[2] << 8);
				/* fall through */
			case 2:
				a += ((uint32) k[1] << 16);
				/* fall through */
			case 1:
				a += ((uint32) k[0] << 24);
				/* case 0: nothing left to add */
		}
#else							/* !WORDS_BIGENDIAN */
		switch (len)
		{
			case 11:
				c += ((uint32) k[10] << 24);
				/* fall through */
			case 10:
				c += ((uint32) k[9] << 16);
				/* fall through */
			case 9:
				c += ((uint32) k[8] << 8);
				/* fall through */
			case 8:
				/* the lowest byte of c is reserved for the length */
				b += ((uint32) k[7] << 24);
				/* fall through */
			case 7:
				b += ((uint32) k[6] << 16);
				/* fall through */
			case 6:
				b += ((uint32) k[5] << 8);
				/* fall through */
			case 5:
				b += k[4];
				/* fall through */
			case 4:
				a += ((uint32) k[3] << 24);
				/* fall through */
			case 3:
				a += ((uint32) k[2] << 16);
				/* fall through */
			case 2:
				a += ((uint32) k[1] << 8);
				/* fall through */
			case 1:
				a += k[0];
				/* case 0: nothing left to add */
		}
#endif							/* WORDS_BIGENDIAN */
	}

	final(a, b, c);

	/* report the result */
	PG_RETURN_UINT64(((uint64) b << 32) | c);
}

/*
 * hash_uint32() -- hash a 32-bit value to a 32-bit value
 *
 * This has the same result as
 *		hash_any(&k, sizeof(uint32))
 * but is faster and doesn't force the caller to store k into memory.
 */
Datum
hash_uint32(uint32 k)
{
	uint32		a,
				b,
				c;

	a = b = c = 0x9e3779b9 + (uint32) sizeof(uint32) + 3923095;
	a += k;

	final(a, b, c);

	/* report the result */
	return UInt32GetDatum(c);
}

/*
 * hash_uint32_extended() -- hash a 32-bit value to a 64-bit value, with a seed
 *
 * Like hash_uint32, this is a convenience function.
 */
Datum
hash_uint32_extended(uint32 k, uint64 seed)
{
	uint32		a,
				b,
				c;

	a = b = c = 0x9e3779b9 + (uint32) sizeof(uint32) + 3923095;

	if (seed != 0)
	{
		a += (uint32) (seed >> 32);
		b += (uint32) seed;
		mix(a, b, c);
	}

	a += k;

	final(a, b, c);

	/* report the result */
	PG_RETURN_UINT64(((uint64) b << 32) | c);
}

/*
 * string_hash: hash function for keys that are NUL-terminated strings.
 *
 * NOTE: this is the default hash function if none is specified.
 */
uint32
string_hash(const void *key, Size keysize)
{
	/*
	 * If the string exceeds keysize-1 bytes, we want to hash only that many,
	 * because when it is copied into the hash table it will be truncated at
	 * that length.
	 */
	Size		s_len = strlen((const char *) key);

	s_len = Min(s_len, keysize - 1);
	return DatumGetUInt32(hash_any((const unsigned char *) key,
								   (int) s_len));
}

/*
 * tag_hash: hash function for fixed-size tag values
 */
uint32
tag_hash(const void *key, Size keysize)
{
	return DatumGetUInt32(hash_any((const unsigned char *) key,
								   (int) keysize));
}

/*
 * uint32_hash: hash function for keys that are uint32 or int32
 *
 * (tag_hash works for this case too, but is slower)
 */
uint32
uint32_hash(const void *key, Size keysize)
{
	Assert(keysize == sizeof(uint32));
	return DatumGetUInt32(hash_uint32(*((const uint32 *) key)));
}