Fix #71890: Add support for crc32c Castagnoli's polynomial.

This variant of crc32 is heavily used by storage systems, such as iSCSI, SCTP, Btrfs, ext4, and is increasingly being used in API (such as Google Cloud Storage, and Apache Kafka).
php · Mar 5, 2019 · 09757eb · 09757eb
1 parent 95aa6ba
commit 09757eb
Show file tree

Hide file tree

Showing 9 changed files with 201 additions and 9 deletions.
diff --git a/ext/hash/hash.c b/ext/hash/hash.c
@@ -40,10 +40,10 @@ struct mhash_bc_entry {
 	int value;
 };
 
-#define MHASH_NUM_ALGOS 34
+#define MHASH_NUM_ALGOS 35
 
 static struct mhash_bc_entry mhash_to_hash[MHASH_NUM_ALGOS] = {
-	{"CRC32", "crc32", 0},
+	{"CRC32", "crc32", 0}, /* used by bzip */
 	{"MD5", "md5", 1},
 	{"SHA1", "sha1", 2},
 	{"HAVAL256", "haval256,3", 3},
@@ -52,7 +52,7 @@ static struct mhash_bc_entry mhash_to_hash[MHASH_NUM_ALGOS] = {
 	{NULL, NULL, 6},
 	{"TIGER", "tiger192,3", 7},
 	{"GOST", "gost", 8},
-	{"CRC32B", "crc32b", 9},
+	{"CRC32B", "crc32b", 9}, /* used by ethernet (IEEE 802.3), gzip, zip, png, etc */
 	{"HAVAL224", "haval224,3", 10},
 	{"HAVAL192", "haval192,3", 11},
 	{"HAVAL160", "haval160,3", 12},
@@ -77,6 +77,7 @@ static struct mhash_bc_entry mhash_to_hash[MHASH_NUM_ALGOS] = {
 	{"FNV164", "fnv164", 31},
 	{"FNV1A64", "fnv1a64", 32},
 	{"JOAAT", "joaat", 33},
+	{"CRC32C", "crc32c", 34}, /* Castagnoli's CRC, used by iSCSI, SCTP, Btrfs, ext4, etc */
 };
 #endif
 
@@ -1204,6 +1205,7 @@ PHP_MINIT_FUNCTION(hash)
 	php_hash_register_algo("adler32",		&php_hash_adler32_ops);
 	php_hash_register_algo("crc32",			&php_hash_crc32_ops);
 	php_hash_register_algo("crc32b",		&php_hash_crc32b_ops);
+	php_hash_register_algo("crc32c",		&php_hash_crc32c_ops);
 	php_hash_register_algo("fnv132",		&php_hash_fnv132_ops);
 	php_hash_register_algo("fnv1a32",		&php_hash_fnv1a32_ops);
 	php_hash_register_algo("fnv164",		&php_hash_fnv164_ops);

diff --git a/ext/hash/hash_crc32.c b/ext/hash/hash_crc32.c
@@ -44,7 +44,16 @@ PHP_HASH_API void PHP_CRC32BUpdate(PHP_CRC32_CTX *context, const unsigned char *
 	}
 }
 
-PHP_HASH_API void PHP_CRC32Final(unsigned char digest[4], PHP_CRC32_CTX *context)
+PHP_HASH_API void PHP_CRC32CUpdate(PHP_CRC32_CTX *context, const unsigned char *input, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; ++i) {
+		context->state = (context->state >> 8) ^ crc32c_table[(context->state ^ input[i]) & 0xff];
+	}
+}
+
+PHP_HASH_API void PHP_CRC32LEFinal(unsigned char digest[4], PHP_CRC32_CTX *context)
 {
 	context->state=~context->state;
 	digest[3] = (unsigned char) ((context->state >> 24) & 0xff);
@@ -54,7 +63,7 @@ PHP_HASH_API void PHP_CRC32Final(unsigned char digest[4], PHP_CRC32_CTX *context
 	context->state = 0;
 }
 
-PHP_HASH_API void PHP_CRC32BFinal(unsigned char digest[4], PHP_CRC32_CTX *context)
+PHP_HASH_API void PHP_CRC32BEFinal(unsigned char digest[4], PHP_CRC32_CTX *context)
 {
 	context->state=~context->state;
 	digest[0] = (unsigned char) ((context->state >> 24) & 0xff);
@@ -73,7 +82,7 @@ PHP_HASH_API int PHP_CRC32Copy(const php_hash_ops *ops, PHP_CRC32_CTX *orig_cont
 const php_hash_ops php_hash_crc32_ops = {
 	(php_hash_init_func_t) PHP_CRC32Init,
 	(php_hash_update_func_t) PHP_CRC32Update,
-	(php_hash_final_func_t) PHP_CRC32Final,
+	(php_hash_final_func_t) PHP_CRC32LEFinal,
 	(php_hash_copy_func_t) PHP_CRC32Copy,
 	4, /* what to say here? */
 	4,
@@ -84,7 +93,18 @@ const php_hash_ops php_hash_crc32_ops = {
 const php_hash_ops php_hash_crc32b_ops = {
 	(php_hash_init_func_t) PHP_CRC32Init,
 	(php_hash_update_func_t) PHP_CRC32BUpdate,
-	(php_hash_final_func_t) PHP_CRC32BFinal,
+	(php_hash_final_func_t) PHP_CRC32BEFinal,
+	(php_hash_copy_func_t) PHP_CRC32Copy,
+	4, /* what to say here? */
+	4,
+	sizeof(PHP_CRC32_CTX),
+	0
+};
+
+const php_hash_ops php_hash_crc32c_ops = {
+	(php_hash_init_func_t) PHP_CRC32Init,
+	(php_hash_update_func_t) PHP_CRC32CUpdate,
+	(php_hash_final_func_t) PHP_CRC32BEFinal,
 	(php_hash_copy_func_t) PHP_CRC32Copy,
 	4, /* what to say here? */
 	4,

diff --git a/ext/hash/php_hash.h b/ext/hash/php_hash.h
@@ -91,6 +91,7 @@ extern const php_hash_ops php_hash_gost_crypto_ops;
 extern const php_hash_ops php_hash_adler32_ops;
 extern const php_hash_ops php_hash_crc32_ops;
 extern const php_hash_ops php_hash_crc32b_ops;
+extern const php_hash_ops php_hash_crc32c_ops;
 extern const php_hash_ops php_hash_fnv132_ops;
 extern const php_hash_ops php_hash_fnv1a32_ops;
 extern const php_hash_ops php_hash_fnv164_ops;

diff --git a/ext/hash/php_hash_crc32.h b/ext/hash/php_hash_crc32.h
@@ -28,7 +28,9 @@ typedef struct {
 PHP_HASH_API void PHP_CRC32Init(PHP_CRC32_CTX *context);
 PHP_HASH_API void PHP_CRC32Update(PHP_CRC32_CTX *context, const unsigned char *input, size_t len);
 PHP_HASH_API void PHP_CRC32BUpdate(PHP_CRC32_CTX *context, const unsigned char *input, size_t len);
-PHP_HASH_API void PHP_CRC32Final(unsigned char digest[4], PHP_CRC32_CTX *context);
+PHP_HASH_API void PHP_CRC32CUpdate(PHP_CRC32_CTX *context, const unsigned char *input, size_t len);
+PHP_HASH_API void PHP_CRC32LEFinal(unsigned char digest[4], PHP_CRC32_CTX *context);
+PHP_HASH_API void PHP_CRC32BEFinal(unsigned char digest[4], PHP_CRC32_CTX *context);
 PHP_HASH_API int PHP_CRC32Copy(const php_hash_ops *ops, PHP_CRC32_CTX *orig_context, PHP_CRC32_CTX *copy_context);
 
 #endif
diff --git a/ext/hash/php_hash_crc32_tables.h b/ext/hash/php_hash_crc32_tables.h
@@ -136,3 +136,71 @@ static const uint32_t crc32b_table[] = {
 	0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94,
 	0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d,
 };
+
+static const uint32_t crc32c_table[] = {
+	0x00000000, 0xf26b8303, 0xe13b70f7, 0x1350f3f4,
+	0xc79a971f, 0x35f1141c, 0x26a1e7e8, 0xd4ca64eb,
+	0x8ad958cf, 0x78b2dbcc, 0x6be22838, 0x9989ab3b,
+	0x4d43cfd0, 0xbf284cd3, 0xac78bf27, 0x5e133c24,
+	0x105ec76f, 0xe235446c, 0xf165b798, 0x030e349b,
+	0xd7c45070, 0x25afd373, 0x36ff2087, 0xc494a384,
+	0x9a879fa0, 0x68ec1ca3, 0x7bbcef57, 0x89d76c54,
+	0x5d1d08bf, 0xaf768bbc, 0xbc267848, 0x4e4dfb4b,
+	0x20bd8ede, 0xd2d60ddd, 0xc186fe29, 0x33ed7d2a,
+	0xe72719c1, 0x154c9ac2, 0x061c6936, 0xf477ea35,
+	0xaa64d611, 0x580f5512, 0x4b5fa6e6, 0xb93425e5,
+	0x6dfe410e, 0x9f95c20d, 0x8cc531f9, 0x7eaeb2fa,
+	0x30e349b1, 0xc288cab2, 0xd1d83946, 0x23b3ba45,
+	0xf779deae, 0x05125dad, 0x1642ae59, 0xe4292d5a,
+	0xba3a117e, 0x4851927d, 0x5b016189, 0xa96ae28a,
+	0x7da08661, 0x8fcb0562, 0x9c9bf696, 0x6ef07595,
+	0x417b1dbc, 0xb3109ebf, 0xa0406d4b, 0x522bee48,
+	0x86e18aa3, 0x748a09a0, 0x67dafa54, 0x95b17957,
+	0xcba24573, 0x39c9c670, 0x2a993584, 0xd8f2b687,
+	0x0c38d26c, 0xfe53516f, 0xed03a29b, 0x1f682198,
+	0x5125dad3, 0xa34e59d0, 0xb01eaa24, 0x42752927,
+	0x96bf4dcc, 0x64d4cecf, 0x77843d3b, 0x85efbe38,
+	0xdbfc821c, 0x2997011f, 0x3ac7f2eb, 0xc8ac71e8,
+	0x1c661503, 0xee0d9600, 0xfd5d65f4, 0x0f36e6f7,
+	0x61c69362, 0x93ad1061, 0x80fde395, 0x72966096,
+	0xa65c047d, 0x5437877e, 0x4767748a, 0xb50cf789,
+	0xeb1fcbad, 0x197448ae, 0x0a24bb5a, 0xf84f3859,
+	0x2c855cb2, 0xdeeedfb1, 0xcdbe2c45, 0x3fd5af46,
+	0x7198540d, 0x83f3d70e, 0x90a324fa, 0x62c8a7f9,
+	0xb602c312, 0x44694011, 0x5739b3e5, 0xa55230e6,
+	0xfb410cc2, 0x092a8fc1, 0x1a7a7c35, 0xe811ff36,
+	0x3cdb9bdd, 0xceb018de, 0xdde0eb2a, 0x2f8b6829,
+	0x82f63b78, 0x709db87b, 0x63cd4b8f, 0x91a6c88c,
+	0x456cac67, 0xb7072f64, 0xa457dc90, 0x563c5f93,
+	0x082f63b7, 0xfa44e0b4, 0xe9141340, 0x1b7f9043,
+	0xcfb5f4a8, 0x3dde77ab, 0x2e8e845f, 0xdce5075c,
+	0x92a8fc17, 0x60c37f14, 0x73938ce0, 0x81f80fe3,
+	0x55326b08, 0xa759e80b, 0xb4091bff, 0x466298fc,
+	0x1871a4d8, 0xea1a27db, 0xf94ad42f, 0x0b21572c,
+	0xdfeb33c7, 0x2d80b0c4, 0x3ed04330, 0xccbbc033,
+	0xa24bb5a6, 0x502036a5, 0x4370c551, 0xb11b4652,
+	0x65d122b9, 0x97baa1ba, 0x84ea524e, 0x7681d14d,
+	0x2892ed69, 0xdaf96e6a, 0xc9a99d9e, 0x3bc21e9d,
+	0xef087a76, 0x1d63f975, 0x0e330a81, 0xfc588982,
+	0xb21572c9, 0x407ef1ca, 0x532e023e, 0xa145813d,
+	0x758fe5d6, 0x87e466d5, 0x94b49521, 0x66df1622,
+	0x38cc2a06, 0xcaa7a905, 0xd9f75af1, 0x2b9cd9f2,
+	0xff56bd19, 0x0d3d3e1a, 0x1e6dcdee, 0xec064eed,
+	0xc38d26c4, 0x31e6a5c7, 0x22b65633, 0xd0ddd530,
+	0x0417b1db, 0xf67c32d8, 0xe52cc12c, 0x1747422f,
+	0x49547e0b, 0xbb3ffd08, 0xa86f0efc, 0x5a048dff,
+	0x8ecee914, 0x7ca56a17, 0x6ff599e3, 0x9d9e1ae0,
+	0xd3d3e1ab, 0x21b862a8, 0x32e8915c, 0xc083125f,
+	0x144976b4, 0xe622f5b7, 0xf5720643, 0x07198540,
+	0x590ab964, 0xab613a67, 0xb831c993, 0x4a5a4a90,
+	0x9e902e7b, 0x6cfbad78, 0x7fab5e8c, 0x8dc0dd8f,
+	0xe330a81a, 0x115b2b19, 0x020bd8ed, 0xf0605bee,
+	0x24aa3f05, 0xd6c1bc06, 0xc5914ff2, 0x37faccf1,
+	0x69e9f0d5, 0x9b8273d6, 0x88d28022, 0x7ab90321,
+	0xae7367ca, 0x5c18e4c9, 0x4f48173d, 0xbd23943e,
+	0xf36e6f75, 0x0105ec76, 0x12551f82, 0xe03e9c81,
+	0x34f4f86a, 0xc69f7b69, 0xd5cf889d, 0x27a40b9e,
+	0x79b737ba, 0x8bdcb4b9, 0x988c474d, 0x6ae7c44e,
+	0xbe2da0a5, 0x4c4623a6, 0x5f16d052, 0xad7d5351,
+};
+
diff --git a/ext/hash/tests/crc32.phpt b/ext/hash/tests/crc32.phpt
@@ -2,33 +2,118 @@
 Hash: CRC32 algorithm
 --FILE--
 <?php
+echo "crc32\n";
 echo hash('crc32', ''), "\n";
 echo hash('crc32', 'a'), "\n";
 echo hash('crc32', 'abc'), "\n";
 echo hash('crc32', 'message digest'), "\n";
 echo hash('crc32', 'abcdefghijklmnopqrstuvwxyz'), "\n";
 echo hash('crc32', 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'), "\n";
 echo hash('crc32', '12345678901234567890123456789012345678901234567890123456789012345678901234567890'), "\n";
+
+echo "crc32b\n";
 echo hash('crc32b', ''), "\n";
 echo hash('crc32b', 'a'), "\n";
 echo hash('crc32b', 'abc'), "\n";
 echo hash('crc32b', 'message digest'), "\n";
 echo hash('crc32b', 'abcdefghijklmnopqrstuvwxyz'), "\n";
 echo hash('crc32b', 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'), "\n";
 echo hash('crc32b', '12345678901234567890123456789012345678901234567890123456789012345678901234567890'), "\n";
+
+echo "crc32c\n";
+echo hash('crc32c', ''), "\n";
+echo hash('crc32c', 'a'), "\n";
+echo hash('crc32c', 'ab'), "\n";
+echo hash('crc32c', 'abc'), "\n";
+echo hash('crc32c', 'abcd'), "\n";
+echo hash('crc32c', 'abcde'), "\n";
+echo hash('crc32c', 'abcdef'), "\n";
+echo hash('crc32c', 'abcdefg'), "\n";
+echo hash('crc32c', 'abcdefgh'), "\n";
+echo hash('crc32c', 'abcdefghi'), "\n";
+echo hash('crc32c', 'abcdefghij'), "\n";
+echo hash('crc32c', 'abcdefghijklmnopqrstuvwxyz'), "\n";
+echo hash('crc32c', 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'), "\n";
+echo hash('crc32c', '12345678901234567890123456789012345678901234567890123456789012345678901234567890'), "\n";
+echo hash('crc32c', 'message digest'), "\n";
+echo hash('crc32c', "I can't remember anything"), "\n";
+echo hash('crc32c', "I can't remember anything" . "Can’t tell if this is true or dream"), "\n";
+echo hash('crc32c', 'Discard medicine more than two years old.'), "\n";
+echo hash('crc32c', 'He who has a shady past knows that nice guys finish last.'), "\n";
+echo hash('crc32c', "I wouldn't marry him with a ten foot pole."), "\n";
+echo hash('crc32c', "Free! Free!/A trip/to Mars/for 900/empty jars/Burma Shave"), "\n";
+echo hash('crc32c', "The days of the digital watch are numbered.  -Tom Stoppard"), "\n";
+echo hash('crc32c', "Nepal premier won't resign."), "\n";
+echo hash('crc32c', "For every action there is an equal and opposite government program."), "\n";
+echo hash('crc32c', "His money is twice tainted: 'taint yours and 'taint mine."), "\n";
+echo hash('crc32c', "There is no reason for any individual to have a computer in their home. -Ken Olsen, 1977"), "\n";
+echo hash('crc32c', "It's a tiny change to the code and not completely disgusting. - Bob Manchek"), "\n";
+echo hash('crc32c', "size:  a.out:  bad magic"), "\n";
+echo hash('crc32c', "The major problem is with sendmail.  -Mark Horton"), "\n";
+echo hash('crc32c', "Give me a rock, paper and scissors and I will move the world.  CCFestoon"), "\n";
+echo hash('crc32c', "If the enemy is within range, then so are you."), "\n";
+echo hash('crc32c', "It's well we cannot hear the screams/That we create in others' dreams."), "\n";
+echo hash('crc32c', "You remind me of a TV show, but that's all right: I watch it anyway."), "\n";
+echo hash('crc32c', "C is as portable as Stonehedge!!"), "\n";
+echo hash('crc32c', "Even if I could be Shakespeare, I think I should still choose to be Faraday. - A. Huxley"), "\n";
+echo hash('crc32c', "The fugacity of a constituent in a mixture of gases at a given temperature is proportional to its mole fraction.  Lewis-Randall Rule"), "\n";
+echo hash('crc32c', "How can you write a big system without C++?  -Paul Glick"), "\n";
+echo hash('crc32c', "\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\v\f\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#\$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"), "\n";
+
 ?>
 --EXPECT--
+crc32
 00000000
 6b9b9319
 73bb8c64
 5703c9bf
 9693bf77
 882174a0
 96790816
+crc32b
 00000000
 e8b7be43
 352441c2
 20159d7f
 4c2750bd
 1fc2e6d2
 7ca94a72
+crc32c
+00000000
+c1d04330
+e2a22936
+364b3fb7
+92c80a31
+c450d697
+53bceff1
+e627f441
+0a9421b7
+2ddc99fc
+e6599437
+9ee6ef25
+a245d57d
+477a6781
+02bd79d0
+5e405e93
+516ad412
+b2cc01fe
+0e28207f
+be93f964
+9e3be0c3
+f505ef04
+85d3dc82
+c5142380
+75eb77dd
+91ebe9f7
+f0b1168e
+572b74e2
+8a58a6d5
+9c426c50
+735400a4
+bec49c95
+a95a2079
+de2e65c5
+297a88ed
+66ed1d8b
+dcded527
+9c44184b
diff --git a/ext/hash/tests/hash-clone.phpt b/ext/hash/tests/hash-clone.phpt
@@ -125,6 +125,9 @@ string(8) "e5cfc160"
 string(6) "crc32b"
 string(8) "69147a4e"
 string(8) "69147a4e"
+string(6) "crc32c"
+string(8) "5e405e93"
+string(8) "5e405e93"
 string(6) "fnv132"
 string(8) "98139504"
 string(8) "98139504"
@@ -281,6 +284,9 @@ string(8) "59f8d3d2"
 string(6) "crc32b"
 string(8) "69147a4e"
 string(8) "3ee63999"
+string(6) "crc32c"
+string(8) "5e405e93"
+string(8) "516ad412"
 string(6) "fnv132"
 string(8) "98139504"
 string(8) "59ad036f"

diff --git a/ext/hash/tests/hash_algos.phpt b/ext/hash/tests/hash_algos.phpt
@@ -16,7 +16,7 @@ var_dump(hash_algos());
 ===Done===
 --EXPECTF--
 *** Testing hash_algos() : basic functionality ***
-array(52) {
+array(53) {
   [%d]=>
   string(3) "md2"
   [%d]=>
@@ -82,6 +82,8 @@ array(52) {
   [%d]=>
   string(6) "crc32b"
   [%d]=>
+  string(6) "crc32c"
+  [%d]=>
   string(6) "fnv132"
   [%d]=>
   string(7) "fnv1a32"

diff --git a/ext/hash/tests/hash_copy_001.phpt b/ext/hash/tests/hash_copy_001.phpt
@@ -125,6 +125,9 @@ string(8) "e5cfc160"
 string(6) "crc32b"
 string(8) "69147a4e"
 string(8) "69147a4e"
+string(6) "crc32c"
+string(8) "5e405e93"
+string(8) "5e405e93"
 string(6) "fnv132"
 string(8) "98139504"
 string(8) "98139504"
@@ -281,6 +284,9 @@ string(8) "59f8d3d2"
 string(6) "crc32b"
 string(8) "69147a4e"
 string(8) "3ee63999"
+string(6) "crc32c"
+string(8) "5e405e93"
+string(8) "516ad412"
 string(6) "fnv132"
 string(8) "98139504"
 string(8) "59ad036f"