Switch to CRC-32C in WAL and other places.

The old algorithm was found to not be the usual CRC-32 algorithm, used by
Ethernet et al. We were using a non-reflected lookup table with code meant
for a reflected lookup table. That's a strange combination that AFAICS does
not correspond to any bit-wise CRC calculation, which makes it difficult to
reason about its properties. Although it has worked well in practice, seems
safer to use a well-known algorithm.

Since we're changing the algorithm anyway, we might as well choose a
different polynomial. The Castagnoli polynomial has better error-correcting
properties than the traditional CRC-32 polynomial, even if we had
implemented it correctly. Another reason for picking that is that some new
CPUs have hardware support for calculating CRC-32C, but not CRC-32, let
alone our strange variant of it. This patch doesn't add any support for such
hardware, but a future patch could now do that.

The old algorithm is kept around for tsquery and pg_trgm, which use the
values in indexes that need to remain compatible so that pg_upgrade works.
While we're at it, share the old lookup table for CRC-32 calculation
between hstore, ltree and core. They all use the same table, so might as
well.

Author: hlinnaka

contrib/hstore/Makefile

@@ -2,7 +2,7 @@
 
 MODULE_big = hstore
 OBJS = hstore_io.o hstore_op.o hstore_gist.o hstore_gin.o hstore_compat.o \
-	crc32.o $(WIN32RES)
+	$(WIN32RES)
 
 EXTENSION = hstore
 DATA = hstore--1.3.sql hstore--1.2--1.3.sql \

contrib/hstore/crc32.c

@@ -6,8 +6,8 @@
 #include "access/gist.h"
 #include "access/skey.h"
 #include "catalog/pg_type.h"
+#include "utils/pg_crc.h"
 
-#include "crc32.h"
 #include "hstore.h"
 
 /* bigint defines */
@@ -68,6 +68,20 @@ typedef struct
 
 #define WISH_F(a,b,c) (double)( -(double)(((a)-(b))*((a)-(b))*((a)-(b)))*(c) )
 
+/* shorthand for calculating CRC-32 of a single chunk of data. */
+static pg_crc32
+crc32_sz(char *buf, int size)
+{
+	pg_crc32 crc;
+
+	INIT_TRADITIONAL_CRC32(crc);
+	COMP_TRADITIONAL_CRC32(crc, buf, size);
+	FIN_TRADITIONAL_CRC32(crc);
+
+	return crc;
+}
+
+
 PG_FUNCTION_INFO_V1(ghstore_in);
 PG_FUNCTION_INFO_V1(ghstore_out);
 

contrib/hstore/crc32.h

@@ -1,7 +1,12 @@
-/* Both POSIX and CRC32 checksums */
-
 /* contrib/ltree/crc32.c */
 
+/*
+ * Implements CRC-32, as used in ltree.
+ *
+ * Note that the CRC is used in the on-disk format of GiST indexes, so we
+ * must stay backwards-compatible!
+ */
+
 #include "postgres.h"
 
 #include <sys/types.h>
@@ -15,100 +20,23 @@
 #define TOLOWER(x)	(x)
 #endif
 
+#include "utils/pg_crc.h"
 #include "crc32.h"
 
-/*
- * This code implements the AUTODIN II polynomial
- * The variable corresponding to the macro argument "crc" should
- * be an unsigned long.
- * Oroginal code  by Spencer Garrett <srg@quick.com>
- */
-
-#define _CRC32_(crc, ch)	 ((crc) = ((crc) >> 8) ^ crc32tab[((crc) ^ (ch)) & 0xff])
-
-/* generated using the AUTODIN II polynomial
- *	x^32 + x^26 + x^23 + x^22 + x^16 +
- *	x^12 + x^11 + x^10 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + 1
- */
-
-static const unsigned int crc32tab[256] = {
-	0x00000000, 0x77073096, 0xee0e612c, 0x990951ba,
-	0x076dc419, 0x706af48f, 0xe963a535, 0x9e6495a3,
-	0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988,
-	0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91,
-	0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de,
-	0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7,
-	0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec,
-	0x14015c4f, 0x63066cd9, 0xfa0f3d63, 0x8d080df5,
-	0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172,
-	0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b,
-	0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940,
-	0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59,
-	0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116,
-	0x21b4f4b5, 0x56b3c423, 0xcfba9599, 0xb8bda50f,
-	0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
-	0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d,
-	0x76dc4190, 0x01db7106, 0x98d220bc, 0xefd5102a,
-	0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433,
-	0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818,
-	0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01,
-	0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e,
-	0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457,
-	0x65b0d9c6, 0x12b7e950, 0x8bbeb8ea, 0xfcb9887c,
-	0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65,
-	0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2,
-	0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb,
-	0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0,
-	0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9,
-	0x5005713c, 0x270241aa, 0xbe0b1010, 0xc90c2086,
-	0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
-	0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4,
-	0x59b33d17, 0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad,
-	0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a,
-	0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683,
-	0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8,
-	0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1,
-	0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe,
-	0xf762575d, 0x806567cb, 0x196c3671, 0x6e6b06e7,
-	0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc,
-	0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5,
-	0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252,
-	0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b,
-	0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60,
-	0xdf60efc3, 0xa867df55, 0x316e8eef, 0x4669be79,
-	0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
-	0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f,
-	0xc5ba3bbe, 0xb2bd0b28, 0x2bb45a92, 0x5cb36a04,
-	0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d,
-	0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a,
-	0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713,
-	0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38,
-	0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21,
-	0x86d3d2d4, 0xf1d4e242, 0x68ddb3f8, 0x1fda836e,
-	0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777,
-	0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c,
-	0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45,
-	0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2,
-	0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db,
-	0xaed16a4a, 0xd9d65adc, 0x40df0b66, 0x37d83bf0,
-	0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
-	0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6,
-	0xbad03605, 0xcdd70693, 0x54de5729, 0x23d967bf,
-	0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94,
-	0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d,
-};
-
 unsigned int
 ltree_crc32_sz(char *buf, int size)
 {
-	unsigned int crc = ~((unsigned int) 0);
-	char	   *p;
-	int			len,
-				nr;
-
-	len = 0;
-	nr = size;
-	for (len += nr, p = buf; nr--; ++p)
-		_CRC32_(crc, TOLOWER((unsigned int) *p));
-	return ~crc;
+	pg_crc32 crc;
+	char	   *p = buf;
+
+	INIT_TRADITIONAL_CRC32(crc);
+	while (size > 0)
+	{
+		char c = (char) TOLOWER(*p);
+		COMP_TRADITIONAL_CRC32(crc, &c, 1);
+		size--;
+		p++;
+	}
+	FIN_TRADITIONAL_CRC32(crc);
+	return (unsigned int) crc;
 }

contrib/hstore/hstore_gist.c

@@ -108,9 +108,9 @@ compact_trigram(trgm *tptr, char *str, int bytelen)
 	{
 		pg_crc32	crc;
 
-		INIT_CRC32(crc);
-		COMP_CRC32(crc, str, bytelen);
-		FIN_CRC32(crc);
+		INIT_LEGACY_CRC32(crc);
+		COMP_LEGACY_CRC32(crc, str, bytelen);
+		FIN_LEGACY_CRC32(crc);
 
 		/*
 		 * use only 3 upper bytes from crc, hope, it's good enough hashing

contrib/ltree/crc32.c

@@ -847,9 +847,9 @@ TwoPhaseGetDummyProc(TransactionId xid)
  *	6. TwoPhaseRecordOnDisk
  *	7. ...
  *	8. TwoPhaseRecordOnDisk (end sentinel, rmid == TWOPHASE_RM_END_ID)
- *	9. CRC32
+ *	9. checksum (CRC-32C)
  *
- * Each segment except the final CRC32 is MAXALIGN'd.
+ * Each segment except the final checksum is MAXALIGN'd.
  */
 
 /*
@@ -1056,11 +1056,11 @@ EndPrepare(GlobalTransaction gxact)
 						path)));
 
 	/* Write data to file, and calculate CRC as we pass over it */
-	INIT_CRC32(statefile_crc);
+	INIT_CRC32C(statefile_crc);
 
 	for (record = records.head; record != NULL; record = record->next)
 	{
-		COMP_CRC32(statefile_crc, record->data, record->len);
+		COMP_CRC32C(statefile_crc, record->data, record->len);
 		if ((write(fd, record->data, record->len)) != record->len)
 		{
 			CloseTransientFile(fd);
@@ -1070,7 +1070,7 @@ EndPrepare(GlobalTransaction gxact)
 		}
 	}
 
-	FIN_CRC32(statefile_crc);
+	FIN_CRC32C(statefile_crc);
 
 	/*
 	 * Write a deliberately bogus CRC to the state file; this is just paranoia
@@ -1289,13 +1289,13 @@ ReadTwoPhaseFile(TransactionId xid, bool give_warnings)
 		return NULL;
 	}
 
-	INIT_CRC32(calc_crc);
-	COMP_CRC32(calc_crc, buf, crc_offset);
-	FIN_CRC32(calc_crc);
+	INIT_CRC32C(calc_crc);
+	COMP_CRC32C(calc_crc, buf, crc_offset);
+	FIN_CRC32C(calc_crc);
 
 	file_crc = *((pg_crc32 *) (buf + crc_offset));
 
-	if (!EQ_CRC32(calc_crc, file_crc))
+	if (!EQ_CRC32C(calc_crc, file_crc))
 	{
 		pfree(buf);
 		return NULL;
@@ -1540,9 +1540,9 @@ RecreateTwoPhaseFile(TransactionId xid, void *content, int len)
 	int			fd;
 
 	/* Recompute CRC */
-	INIT_CRC32(statefile_crc);
-	COMP_CRC32(statefile_crc, content, len);
-	FIN_CRC32(statefile_crc);
+	INIT_CRC32C(statefile_crc);
+	COMP_CRC32C(statefile_crc, content, len);
+	FIN_CRC32C(statefile_crc);
 
 	TwoPhaseFilePath(path, xid);