MDEV-17958 Make bug-endian innodb_checksum_algorithm=crc32 optional

In MySQL 5.7, it was noticed that files are not portable between
big-endian and little-endian processor architectures
(such as SPARC and x86), because the original implementation of
innodb_checksum_algorithm=crc32 was not byte order agnostic.

A byte order agnostic implementation of innodb_checksum_algorithm=crc32
was only added to MySQL 5.7, not backported to 5.6. Consequently,
MariaDB Server versions 10.0 and 10.1 only contain the CRC-32C
implementation that works incorrectly on big-endian architectures,
and MariaDB Server 10.2.2 got the byte-order agnostic CRC-32C
implementation from MySQL 5.7.

MySQL 5.7 introduced a "legacy crc32" variant that is functionally
equivalent to the big-endian version of the original crc32 implementation.
Thanks to this variant, old data files can be transferred from big-endian
systems to newer versions.

Introducing new variants of checksum algorithms (without introducing
new names for them, or something on the pages themselves to identify
the algorithm) generally is a bad idea, because each checksum algorithm
is like a lottery ticket. The more algorithms you try, the more likely
it will be for the checksum to match on a corrupted page.

So, essentially MySQL 5.7 weakened innodb_checksum_algorithm=crc32,
and MariaDB 10.2.2 inherited this weakening.

We introduce a build option that together with MDEV-17957
makes innodb_checksum_algorithm=strict_crc32 strict again
by only allowing one variant of the checksum to match.

WITH_INNODB_BUG_ENDIAN_CRC32: A new cmake option for enabling the
bug-compatible "legacy crc32" checksum. This is only enabled on
big-endian systems by default, to facilitate an upgrade from
MariaDB 10.0 or 10.1. Checked by #ifdef INNODB_BUG_ENDIAN_CRC32.

ut_crc32_byte_by_byte: Remove (unused function).

legacy_big_endian_checksum: Remove. This variable seems to have
unnecessarily complicated the logic. When the weakening is enabled,
we must always fall back to the buggy checksum.

buf_page_check_crc32(): A helper function to compute one or
two CRC-32C variants.

storage/innobase/buf/buf0buf.cc

@@ -756,17 +756,14 @@ buf_page_is_zeroes(
 @param[in]	read_buf		database page
 @param[in]	checksum_field1		new checksum field
 @param[in]	checksum_field2		old checksum field
-@param[in]	use_legacy_big_endian   use legacy big endian algorithm
 @return true if the page is in crc32 checksum format. */
 bool
 buf_page_is_checksum_valid_crc32(
 	const byte*			read_buf,
 	ulint				checksum_field1,
-	ulint				checksum_field2,
-	bool				use_legacy_big_endian)
+	ulint				checksum_field2)
 {
-	const uint32_t	crc32 = buf_calc_page_crc32(read_buf,
-						    use_legacy_big_endian);
+	const uint32_t	crc32 = buf_calc_page_crc32(read_buf);
 
 #ifdef UNIV_INNOCHECKSUM
 	if (log_file
@@ -783,17 +780,11 @@ buf_page_is_checksum_valid_crc32(
 		return false;
 	}
 
-	if (checksum_field1 == crc32) {
-		return(true);
-	} else {
-		const uint32_t	crc32_legacy = buf_calc_page_crc32(read_buf, true);
-
-		if (checksum_field1 == crc32_legacy) {
-			return(true);
-		}
-	}
-
-	return(false);
+	return checksum_field1 == crc32
+#ifdef INNODB_BUG_ENDIAN_CRC32
+		|| checksum_field1 == buf_calc_page_crc32(read_buf, true)
+#endif
+		;
 }
 
 /** Checks if the page is in innodb checksum format.
@@ -922,6 +913,29 @@ buf_page_is_checksum_valid_none(
 	       && checksum_field1 == BUF_NO_CHECKSUM_MAGIC);
 }
 
+#ifdef INNODB_BUG_ENDIAN_CRC32
+/** Validate the CRC-32C checksum of a page.
+@param[in]	page		buffer page (srv_page_size bytes)
+@param[in]	checksum	CRC-32C checksum stored on page
+@return	computed checksum */
+static uint32_t buf_page_check_crc32(const byte* page, uint32_t checksum)
+{
+	uint32_t crc32 = buf_calc_page_crc32(page);
+
+	if (checksum != crc32) {
+		crc32 = buf_calc_page_crc32(page, true);
+	}
+
+	return crc32;
+}
+#else /* INNODB_BUG_ENDIAN_CRC32 */
+/** Validate the CRC-32C checksum of a page.
+@param[in]	page		buffer page (srv_page_size bytes)
+@param[in]	checksum	CRC-32C checksum stored on page
+@return	computed checksum */
+# define buf_page_check_crc32(page, checksum) buf_calc_page_crc32(page)
+#endif /* INNODB_BUG_ENDIAN_CRC32 */
+
 /** Check if a page is corrupt.
 @param[in]	check_lsn	whether the LSN should be checked
 @param[in]	read_buf	database page
@@ -1037,26 +1051,20 @@ buf_page_is_corrupted(
 	    && *reinterpret_cast<const ib_uint64_t*>(
 		    read_buf + FIL_PAGE_LSN) == 0) {
 
-		ulint i;
-
 		/* make sure that the page is really empty */
-		for (ulint i = 0; i < UNIV_PAGE_SIZE; i++) {
+		for (ulint i = 0; i < page_size.logical(); i++) {
 			if (read_buf[i] != 0) {
 				return(true);
 			}
 		}
 #ifdef UNIV_INNOCHECKSUM
-		if (i >= page_size.logical()) {
-			if (log_file) {
-				fprintf(log_file, "Page::%llu"
-					" is empty and uncorrupted\n",
-					cur_page_num);
-			}
-			return(false);
+		if (log_file) {
+			fprintf(log_file, "Page::%llu"
+				" is empty and uncorrupted\n",
+				cur_page_num);
 		}
-#else
-		return(i < page_size.logical());
 #endif /* UNIV_INNOCHECKSUM */
+		return(false);
 	}
 
 	const srv_checksum_algorithm_t	curr_algo =
@@ -1065,10 +1073,7 @@ buf_page_is_corrupted(
 	switch (curr_algo) {
 	case SRV_CHECKSUM_ALGORITHM_STRICT_CRC32:
 		return !buf_page_is_checksum_valid_crc32(
-			read_buf, checksum_field1, checksum_field2, false)
-			&& !buf_page_is_checksum_valid_crc32(
-				read_buf, checksum_field1, checksum_field2,
-				true);
+			read_buf, checksum_field1, checksum_field2);
 	case SRV_CHECKSUM_ALGORITHM_STRICT_INNODB:
 		return !buf_page_is_checksum_valid_innodb(
 			read_buf, checksum_field1, checksum_field2);
@@ -1111,19 +1116,10 @@ buf_page_is_corrupted(
 
 			if (srv_checksum_algorithm
 			    == SRV_CHECKSUM_ALGORITHM_CRC32) {
-
-				crc32 = buf_calc_page_crc32(
-					read_buf, legacy_big_endian_checksum);
+				crc32 = buf_page_check_crc32(read_buf,
+							     checksum_field2);
 				crc32_inited = true;
 
-				if (!legacy_big_endian_checksum
-				    && checksum_field2 != crc32) {
-					crc32 = buf_calc_page_crc32(read_buf,
-								    true);
-					legacy_big_endian_checksum =
-						checksum_field2 == crc32;
-				}
-
 				if (checksum_field2 != crc32
 				    && checksum_field2
 				       != buf_calc_page_old_checksum(read_buf)) {
@@ -1135,19 +1131,10 @@ buf_page_is_corrupted(
 
 				if (checksum_field2
 				    != buf_calc_page_old_checksum(read_buf)) {
-					crc32 = buf_calc_page_crc32(
-						read_buf,
-						legacy_big_endian_checksum);
+					crc32 = buf_page_check_crc32(
+						read_buf, checksum_field2);
 					crc32_inited = true;
 
-					if (!legacy_big_endian_checksum
-					    && checksum_field2 != crc32) {
-						crc32 = buf_calc_page_crc32(
-							read_buf, true);
-						legacy_big_endian_checksum =
-							checksum_field2 == crc32;
-					}
-
 					if (checksum_field2 != crc32) {
 						return true;
 					}
@@ -1161,18 +1148,9 @@ buf_page_is_corrupted(
 			   == SRV_CHECKSUM_ALGORITHM_CRC32) {
 
 			if (!crc32_inited) {
-				crc32 = buf_calc_page_crc32(
-					read_buf,
-					legacy_big_endian_checksum);
+				crc32 = buf_page_check_crc32(
+					read_buf, checksum_field2);
 				crc32_inited = true;
-
-				if (!legacy_big_endian_checksum
-				    && checksum_field2 != crc32) {
-					crc32 = buf_calc_page_crc32(
-						read_buf, true);
-					legacy_big_endian_checksum =
-						checksum_field2 == crc32;
-				}
 			}
 
 			if (checksum_field1 != crc32
@@ -1188,18 +1166,9 @@ buf_page_is_corrupted(
 			    != buf_calc_page_new_checksum(read_buf)) {
 
 				if (!crc32_inited) {
-					crc32 = buf_calc_page_crc32(
-						read_buf,
-						legacy_big_endian_checksum);
+					crc32 = buf_page_check_crc32(
+						read_buf, checksum_field2);
 					crc32_inited = true;
-
-					if (!legacy_big_endian_checksum
-					    && checksum_field2 != crc32) {
-						crc32 = buf_calc_page_crc32(
-							read_buf, true);
-						legacy_big_endian_checksum =
-							checksum_field2 == crc32;
-					}
 				}
 
 				if (checksum_field1 != crc32) {
@@ -1255,10 +1224,12 @@ buf_page_print(const byte* read_buf, const page_size_t& page_size)
 			<< page_zip_calc_checksum(
 				read_buf, page_size.physical(),
 				SRV_CHECKSUM_ALGORITHM_CRC32)
+#ifdef INNODB_BUG_ENDIAN_CRC32
 			<< "/"
 			<< page_zip_calc_checksum(
 				read_buf, page_size.physical(),
 				SRV_CHECKSUM_ALGORITHM_CRC32, true)
+#endif
 			<< ", "
 			<< buf_checksum_algorithm_name(
 				SRV_CHECKSUM_ALGORITHM_INNODB)
@@ -1284,9 +1255,10 @@ buf_page_print(const byte* read_buf, const page_size_t& page_size)
 
 	} else {
 		const uint32_t	crc32 = buf_calc_page_crc32(read_buf);
-
+#ifdef INNODB_BUG_ENDIAN_CRC32
 		const uint32_t	crc32_legacy = buf_calc_page_crc32(read_buf,
 								   true);
+#endif /* INNODB_BUG_ENDIAN_CRC32 */
 		ulint page_type = fil_page_get_type(read_buf);
 
 		ib::info() << "Uncompressed page, stored checksum in field1 "
@@ -1295,7 +1267,10 @@ buf_page_print(const byte* read_buf, const page_size_t& page_size)
 			<< ", calculated checksums for field1: "
 			<< buf_checksum_algorithm_name(
 				SRV_CHECKSUM_ALGORITHM_CRC32) << " "
-			<< crc32 << "/" << crc32_legacy
+			<< crc32
+#ifdef INNODB_BUG_ENDIAN_CRC32
+			<< "/" << crc32_legacy
+#endif
 			<< ", "
 			<< buf_checksum_algorithm_name(
 				SRV_CHECKSUM_ALGORITHM_INNODB) << " "
@@ -1312,7 +1287,10 @@ buf_page_print(const byte* read_buf, const page_size_t& page_size)
 			<< ", calculated checksums for field2: "
 			<< buf_checksum_algorithm_name(
 				SRV_CHECKSUM_ALGORITHM_CRC32) << " "
-			<< crc32 << "/" << crc32_legacy
+			<< crc32
+#ifdef INNODB_BUG_ENDIAN_CRC32
+			<< "/" << crc32_legacy
+#endif
 			<< ", "
 			<< buf_checksum_algorithm_name(
 				SRV_CHECKSUM_ALGORITHM_INNODB) << " "
@@ -3950,10 +3928,12 @@ buf_zip_decompress(
 			<< ", crc32: "
 			<< page_zip_calc_checksum(
 				frame, size, SRV_CHECKSUM_ALGORITHM_CRC32)
+#ifdef INNODB_BUG_ENDIAN_CRC32
 			<< "/"
 			<< page_zip_calc_checksum(
 				frame, size, SRV_CHECKSUM_ALGORITHM_CRC32,
 				true)
+#endif
 			<< " innodb: "
 			<< page_zip_calc_checksum(
 				frame, size, SRV_CHECKSUM_ALGORITHM_INNODB)

storage/innobase/buf/buf0checksum.cc

@@ -39,44 +39,56 @@ ha_innodb.cc:12251: error: cannot convert 'srv_checksum_algorithm_t*' to
   'long unsigned int*' in initialization */
 ulong	srv_checksum_algorithm = SRV_CHECKSUM_ALGORITHM_INNODB;
 
-/** set if we have found pages matching legacy big endian checksum */
-bool	legacy_big_endian_checksum = false;
-/** Calculates the CRC32 checksum of a page. The value is stored to the page
+#ifdef INNODB_BUG_ENDIAN_CRC32
+/** Calculate the CRC32 checksum of a page. The value is stored to the page
 when it is written to a file and also checked for a match when reading from
-the file. When reading we allow both normal CRC32 and CRC-legacy-big-endian
-variants. Note that we must be careful to calculate the same value on 32-bit
-and 64-bit architectures.
-@param[in]	page			buffer page (UNIV_PAGE_SIZE bytes)
-@param[in]	use_legacy_big_endian	if true then use big endian
-byteorder when converting byte strings to integers
-@return checksum */
-uint32_t
-buf_calc_page_crc32(
-	const byte*	page,
-	bool		use_legacy_big_endian /* = false */)
+the file. Note that we must be careful to calculate the same value on all
+architectures.
+@param[in]	page		buffer page (srv_page_size bytes)
+@param[in]	bug_endian	whether to use big endian byteorder
+when converting byte strings to integers, for bug-compatibility with
+big-endian architecture running MySQL 5.6, MariaDB 10.0 or MariaDB 10.1
+@return	CRC-32C */
+uint32_t buf_calc_page_crc32(const byte* page, bool bug_endian)
 {
-	/* Since the field FIL_PAGE_FILE_FLUSH_LSN, and in versions <= 4.1.x
-	FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID, are written outside the buffer pool
-	to the first pages of data files, we have to skip them in the page
-	checksum calculation.
-	We must also skip the field FIL_PAGE_SPACE_OR_CHKSUM where the
-	checksum is stored, and also the last 8 bytes of page because
-	there we store the old formula checksum. */
-
-	ut_crc32_func_t	crc32_func = use_legacy_big_endian
-		? ut_crc32_legacy_big_endian
-		: ut_crc32;
-
-	const uint32_t	c1 = crc32_func(
-		page + FIL_PAGE_OFFSET,
-		FIL_PAGE_FILE_FLUSH_LSN_OR_KEY_VERSION - FIL_PAGE_OFFSET);
-
-	const uint32_t	c2 = crc32_func(
-		page + FIL_PAGE_DATA,
-		UNIV_PAGE_SIZE - FIL_PAGE_DATA - FIL_PAGE_END_LSN_OLD_CHKSUM);
-
-	return(c1 ^ c2);
+	return bug_endian
+		? ut_crc32_legacy_big_endian(
+			page + FIL_PAGE_OFFSET,
+			FIL_PAGE_FILE_FLUSH_LSN_OR_KEY_VERSION
+			- FIL_PAGE_OFFSET)
+		^ ut_crc32_legacy_big_endian(page + FIL_PAGE_DATA,
+					     srv_page_size
+					     - (FIL_PAGE_DATA
+						+ FIL_PAGE_END_LSN_OLD_CHKSUM))
+		: ut_crc32(page + FIL_PAGE_OFFSET,
+			   FIL_PAGE_FILE_FLUSH_LSN_OR_KEY_VERSION
+			   - FIL_PAGE_OFFSET)
+		^ ut_crc32(page + FIL_PAGE_DATA,
+			   srv_page_size
+			   - (FIL_PAGE_DATA + FIL_PAGE_END_LSN_OLD_CHKSUM));
+}
+#else
+/** Calculate the CRC32 checksum of a page. The value is stored to the page
+when it is written to a file and also checked for a match when reading from
+the file. Note that we must be careful to calculate the same value on all
+architectures.
+@param[in]	page			buffer page (srv_page_size bytes)
+@return	CRC-32C */
+uint32_t buf_calc_page_crc32(const byte* page)
+{
+	/* Note: innodb_checksum_algorithm=crc32 could and should have
+	included the entire page in the checksum, and CRC-32 values
+	should be combined with the CRC-32 function, not with
+	exclusive OR. We stick to the current algorithm in order to
+	remain compatible with old data files. */
+	return ut_crc32(page + FIL_PAGE_OFFSET,
+			FIL_PAGE_FILE_FLUSH_LSN_OR_KEY_VERSION
+			- FIL_PAGE_OFFSET)
+		^ ut_crc32(page + FIL_PAGE_DATA,
+			   srv_page_size
+			   - (FIL_PAGE_DATA + FIL_PAGE_END_LSN_OLD_CHKSUM));
 }
+#endif
 
 /** Calculate a checksum which is stored to the page when it is written
 to a file. Note that we must be careful to calculate the same value on

storage/innobase/fil/fil0crypt.cc

@@ -2636,10 +2636,8 @@ fil_space_verify_crypt_checksum(
 					srv_checksum_algorithm);
 		switch (algorithm) {
 		case SRV_CHECKSUM_ALGORITHM_STRICT_CRC32:
-			/* We never supported upgrade from the "legacy crc32"
-			on big endian systems from MariaDB 10.1 to later. */
 			valid = buf_page_is_checksum_valid_crc32(
-				page, checksum1, checksum2, false);
+				page, checksum1, checksum2);
 			break;
 		case SRV_CHECKSUM_ALGORITHM_STRICT_INNODB:
 			valid = buf_page_is_checksum_valid_innodb(
@@ -2649,13 +2647,11 @@ fil_space_verify_crypt_checksum(
 		case SRV_CHECKSUM_ALGORITHM_CRC32:
 		case SRV_CHECKSUM_ALGORITHM_INNODB:
 		case SRV_CHECKSUM_ALGORITHM_NONE:
-			/* We never supported upgrade from the "legacy crc32"
-			on big endian systems from MariaDB 10.1 to later.
-			We also never supported
+			/* never supported
 			innodb_checksum_algorithm=none or strict_none
 			for encrypted pages. */
 			valid = buf_page_is_checksum_valid_crc32(
-				page, checksum1, checksum2, false)
+				page, checksum1, checksum2)
 				|| buf_page_is_checksum_valid_innodb(
 					page, checksum1, checksum2);
 			break;
@@ -2684,8 +2680,11 @@ fil_space_verify_crypt_checksum(
 		ib::info()
 			<< "If unencrypted: stored checksum [" << checksum1
 			<< ":" << checksum2 << "] calculated crc32 ["
-			<< buf_calc_page_crc32(page, false) << ":"
-			<< buf_calc_page_crc32(page, true) << "] innodb ["
+			<< buf_calc_page_crc32(page)
+# ifdef INNODB_BUG_ENDIAN_CRC32
+			<< ":" << buf_calc_page_crc32(page, true)
+# endif /* INNODB_BUG_ENDIAN_CRC32 */
+			<< "] innodb ["
 			<< buf_calc_page_old_checksum(page) << ":"
 			<< buf_calc_page_new_checksum(page) << "] LSN "
 			<< mach_read_from_4(page + FIL_PAGE_LSN);

storage/innobase/include/buf0buf.h

@@ -716,14 +716,12 @@ buf_block_unfix(
 @param[in]	read_buf		database page
 @param[in]	checksum_field1		new checksum field
 @param[in]	checksum_field2		old checksum field
-@param[in]	use_legacy_big_endian   use legacy big endian algorithm
 @return true if the page is in crc32 checksum format. */
 bool
 buf_page_is_checksum_valid_crc32(
 	const byte*			read_buf,
 	ulint				checksum_field1,
-	ulint				checksum_field2,
-	bool				use_legacy_big_endian)
+	ulint				checksum_field2)
 	MY_ATTRIBUTE((nonnull(1), warn_unused_result));
 
 /** Checks if the page is in innodb checksum format.

storage/innobase/include/buf0checksum.h

 /*****************************************************************************
 
 Copyright (c) 1995, 2016, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2017, MariaDB Corporation.
+Copyright (c) 2017, 2018, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -29,19 +29,26 @@ Created Aug 11, 2011 Vasil Dimov
 
 #include "buf0types.h"
 
+#ifdef INNODB_BUG_ENDIAN_CRC32
 /** Calculate the CRC32 checksum of a page. The value is stored to the page
 when it is written to a file and also checked for a match when reading from
-the file. When reading we allow both normal CRC32 and CRC-legacy-big-endian
-variants. Note that we must be careful to calculate the same value on 32-bit
-and 64-bit architectures.
-@param[in]	page			buffer page (UNIV_PAGE_SIZE bytes)
-@param[in]	use_legacy_big_endian	if true then use big endian
-byteorder when converting byte strings to integers
-@return checksum */
-uint32_t
-buf_calc_page_crc32(
-	const byte*	page,
-	bool		use_legacy_big_endian = false);
+the file. Note that we must be careful to calculate the same value on all
+architectures.
+@param[in]	page		buffer page (srv_page_size bytes)
+@param[in]	bug_endian	whether to use big endian byteorder
+when converting byte strings to integers, for bug-compatibility with
+big-endian architecture running MySQL 5.6, MariaDB 10.0 or MariaDB 10.1
+@return	CRC-32C */
+uint32_t buf_calc_page_crc32(const byte* page, bool bug_endian = false);
+#else
+/** Calculate the CRC32 checksum of a page. The value is stored to the page
+when it is written to a file and also checked for a match when reading from
+the file. Note that we must be careful to calculate the same value on all
+architectures.
+@param[in]	page			buffer page (srv_page_size bytes)
+@return	CRC-32C */
+uint32_t buf_calc_page_crc32(const byte* page);
+#endif
 
 /** Calculate a checksum which is stored to the page when it is written
 to a file. Note that we must be careful to calculate the same value on
@@ -69,6 +76,5 @@ const char*
 buf_checksum_algorithm_name(srv_checksum_algorithm_t algo);
 
 extern ulong	srv_checksum_algorithm;
-extern bool	legacy_big_endian_checksum;
 
 #endif /* buf0checksum_h */

storage/innobase/include/page0zip.h

@@ -492,16 +492,17 @@ page_zip_parse_compress(
 @param[in]	data			compressed page
 @param[in]	size			size of compressed page
 @param[in]	algo			algorithm to use
-@param[in]	use_legacy_big_endian	only used if algo is
-SRV_CHECKSUM_ALGORITHM_CRC32 or SRV_CHECKSUM_ALGORITHM_STRICT_CRC32 - if true
-then use big endian byteorder when converting byte strings to integers.
 @return page checksum */
 uint32_t
 page_zip_calc_checksum(
 	const void*			data,
 	ulint				size,
-	srv_checksum_algorithm_t	algo,
-	bool				use_legacy_big_endian = false);
+	srv_checksum_algorithm_t	algo
+#ifdef INNODB_BUG_ENDIAN_CRC32
+	/** for crc32, use the big-endian bug-compatible crc32 variant */
+	, bool				use_legacy_big_endian = false
+#endif
+);
 
 /**********************************************************************//**
 Verify a compressed page's checksum.

storage/innobase/include/ut0crc32.h

 /*****************************************************************************
 
 Copyright (c) 2011, 2015, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2016, MariaDB Corporation.
+Copyright (c) 2016, 2018, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -47,13 +47,11 @@ typedef uint32_t	(*ut_crc32_func_t)(const byte* ptr, ulint len);
 /** Pointer to CRC32 calculation function. */
 extern ut_crc32_func_t	ut_crc32;
 
+#ifdef INNODB_BUG_ENDIAN_CRC32
 /** Pointer to CRC32 calculation function, which uses big-endian byte order
 when converting byte strings to integers internally. */
 extern ut_crc32_func_t	ut_crc32_legacy_big_endian;
-
-/** Pointer to CRC32-byte-by-byte calculation function (byte order agnostic,
-but very slow). */
-extern ut_crc32_func_t	ut_crc32_byte_by_byte;
+#endif /* INNODB_BUG_ENDIAN_CRC32 */
 
 extern const char*	ut_crc32_implementation;
 

storage/innobase/innodb.cmake

@@ -25,6 +25,7 @@ INCLUDE(lzma.cmake)
 INCLUDE(bzip2.cmake)
 INCLUDE(snappy.cmake)
 INCLUDE(numa)
+INCLUDE(TestBigEndian)
 
 MYSQL_CHECK_LZ4()
 MYSQL_CHECK_LZO()
@@ -32,6 +33,7 @@ MYSQL_CHECK_LZMA()
 MYSQL_CHECK_BZIP2()
 MYSQL_CHECK_SNAPPY()
 MYSQL_CHECK_NUMA()
+TEST_BIG_ENDIAN(IS_BIG_ENDIAN)
 
 IF(CMAKE_CROSSCOMPILING)
   # Use CHECK_C_SOURCE_COMPILES instead of CHECK_C_SOURCE_RUNS when
@@ -123,6 +125,11 @@ ELSEIF(WITH_INNODB_ROOT_GUESS)
   ADD_DEFINITIONS(-DBTR_CUR_ADAPT)
 ENDIF()
 
+OPTION(WITH_INNODB_BUG_ENDIAN_CRC32 "Weaken innodb_checksum_algorithm=crc32 by supporting upgrade from big-endian systems running 5.6/10.0/10.1" ${IS_BIG_ENDIAN})
+IF(WITH_INNODB_BUG_ENDIAN_CRC32)
+  ADD_DEFINITIONS(-DINNODB_BUG_ENDIAN_CRC32)
+ENDIF()
+
 OPTION(WITH_INNODB_EXTRA_DEBUG "Enable extra InnoDB debug checks" OFF)
 IF(WITH_INNODB_EXTRA_DEBUG)
   IF(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")

storage/innobase/page/page0zip.cc

@@ -4909,18 +4909,17 @@ page_zip_parse_compress(
 @param[in]	data			compressed page
 @param[in]	size			size of compressed page
 @param[in]	algo			algorithm to use
-@param[in]	use_legacy_big_endian	only used if algo is
-SRV_CHECKSUM_ALGORITHM_CRC32 or SRV_CHECKSUM_ALGORITHM_STRICT_CRC32 - if true
-then use big endian byteorder when converting byte strings to integers.
-SRV_CHECKSUM_ALGORITHM_CRC32 or SRV_CHECKSUM_ALGORITHM_STRICT_CRC32 - if true
-then use big endian byteorder when converting byte strings to integers.
 @return page checksum */
 uint32_t
 page_zip_calc_checksum(
 	const void*			data,
 	ulint				size,
-	srv_checksum_algorithm_t	algo,
-	bool				use_legacy_big_endian /* = false */)
+	srv_checksum_algorithm_t	algo
+#ifdef INNODB_BUG_ENDIAN_CRC32
+	/** for crc32, use the big-endian bug-compatible crc32 variant */
+	, bool				use_legacy_big_endian
+#endif
+)
 {
 	uLong		adler;
 	const Bytef*	s = static_cast<const byte*>(data);
@@ -4931,25 +4930,25 @@ page_zip_calc_checksum(
 	switch (algo) {
 	case SRV_CHECKSUM_ALGORITHM_CRC32:
 	case SRV_CHECKSUM_ALGORITHM_STRICT_CRC32:
-		{
-			ut_ad(size > FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);
-
-			ut_crc32_func_t	crc32_func = use_legacy_big_endian
-				? ut_crc32_legacy_big_endian
-				: ut_crc32;
-
-			const uint32_t	crc32
-				= crc32_func(
-					s + FIL_PAGE_OFFSET,
-					FIL_PAGE_LSN - FIL_PAGE_OFFSET)
-				^ crc32_func(
+		ut_ad(size > FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);
+#ifdef INNODB_BUG_ENDIAN_CRC32
+		if (use_legacy_big_endian) {
+			return ut_crc32_legacy_big_endian(s + FIL_PAGE_OFFSET,
+							  FIL_PAGE_LSN
+							  - FIL_PAGE_OFFSET)
+				^ ut_crc32_legacy_big_endian(
 					s + FIL_PAGE_TYPE, 2)
-				^ crc32_func(
+				^ ut_crc32_legacy_big_endian(
 					s + FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID,
-					size - FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);
-
-			return(crc32);
+					size
+					- FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);
 		}
+#endif
+		return ut_crc32(s + FIL_PAGE_OFFSET,
+				FIL_PAGE_LSN - FIL_PAGE_OFFSET)
+			^ ut_crc32(s + FIL_PAGE_TYPE, 2)
+			^ ut_crc32(s + FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID,
+				   size - FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);
 	case SRV_CHECKSUM_ALGORITHM_INNODB:
 	case SRV_CHECKSUM_ALGORITHM_STRICT_INNODB:
 		ut_ad(size > FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);
@@ -4984,13 +4983,8 @@ page_zip_verify_checksum(
 	const void*	data,		/*!< in: compressed page */
 	ulint		size)		/*!< in: size of compressed page */
 {
-	ib_uint32_t	stored;
-	ib_uint32_t	calc;
-	ib_uint32_t	crc32 = 0;
-	ib_uint32_t	innodb = 0;
-
-	stored = static_cast<ib_uint32_t>(mach_read_from_4(
-		static_cast<const unsigned char*>(data) + FIL_PAGE_SPACE_OR_CHKSUM));
+	const uint32_t stored = mach_read_from_4(
+		static_cast<const byte*>(data) + FIL_PAGE_SPACE_OR_CHKSUM);
 
 #if FIL_PAGE_LSN % 8
 #error "FIL_PAGE_LSN must be 64 bit aligned"
@@ -5034,8 +5028,7 @@ page_zip_verify_checksum(
 		return(TRUE);
 	}
 
-	calc = static_cast<ib_uint32_t>(page_zip_calc_checksum(
-		data, size, curr_algo));
+	uint32_t calc = page_zip_calc_checksum(data, size, curr_algo);
 
 #ifdef UNIV_INNOCHECKSUM
 	if (log_file) {
@@ -5070,13 +5063,11 @@ page_zip_verify_checksum(
 
 	switch (curr_algo) {
 	case SRV_CHECKSUM_ALGORITHM_STRICT_CRC32:
-		calc = page_zip_calc_checksum(data, size, curr_algo, true);
-		if (calc == stored) {
-			legacy_big_endian_checksum = true;
-			return TRUE;
-		}
-
-		return FALSE;
+#ifdef INNODB_BUG_ENDIAN_CRC32
+		return stored == page_zip_calc_checksum(data, size, curr_algo,
+							true);
+#endif
+		/* fall through */
 	case SRV_CHECKSUM_ALGORITHM_STRICT_INNODB:
 	case SRV_CHECKSUM_ALGORITHM_STRICT_NONE:
 		return FALSE;
@@ -5085,29 +5076,29 @@ page_zip_verify_checksum(
 			return(TRUE);
 		}
 
-		calc = page_zip_calc_checksum(data, size, curr_algo, true);
-		crc32 = calc;
-
-		if (crc32 == stored) {
-			legacy_big_endian_checksum = true;
-			return TRUE;
-		}
-
-		innodb = static_cast<ib_uint32_t>(page_zip_calc_checksum(
-			data, size, SRV_CHECKSUM_ALGORITHM_INNODB));
-		break;
+		return
+#ifdef INNODB_BUG_ENDIAN_CRC32
+			stored == page_zip_calc_checksum(data, size, curr_algo,
+							 true) ||
+#endif
+			stored == page_zip_calc_checksum(
+				data, size, SRV_CHECKSUM_ALGORITHM_INNODB);
 	case SRV_CHECKSUM_ALGORITHM_INNODB:
 		if (stored == BUF_NO_CHECKSUM_MAGIC) {
 			return TRUE;
 		}
 
-		crc32 = static_cast<ib_uint32_t>(page_zip_calc_checksum(
-			data, size, SRV_CHECKSUM_ALGORITHM_CRC32));
-		innodb = calc;
-		break;
+		return stored == page_zip_calc_checksum(
+			data, size, SRV_CHECKSUM_ALGORITHM_CRC32)
+#ifdef INNODB_BUG_ENDIAN_CRC32
+			|| stored == page_zip_calc_checksum(
+				data, size,
+				SRV_CHECKSUM_ALGORITHM_CRC32, true)
+#endif
+			;
 	case SRV_CHECKSUM_ALGORITHM_NONE:
 		return TRUE;
 	}
 
-	return (stored == crc32 || stored == innodb);
+	return FALSE;
 }

storage/innobase/ut/ut0crc32.cc

@@ -2,7 +2,7 @@
 
 Copyright (c) 2009, 2010 Facebook, Inc. All Rights Reserved.
 Copyright (c) 2011, 2015, Oracle and/or its affiliates. All Rights Reserved.
-Copyright (c) 2016, MariaDB Corporation.
+Copyright (c) 2016, 2018, MariaDB Corporation.
 
 This program is free software; you can redistribute it and/or modify it under
 the terms of the GNU General Public License as published by the Free Software
@@ -92,13 +92,11 @@ mysys/my_perf.c, contributed by Facebook under the following license.
 /** Pointer to CRC32 calculation function. */
 ut_crc32_func_t	ut_crc32;
 
+#ifdef INNODB_BUG_ENDIAN_CRC32
 /** Pointer to CRC32 calculation function, which uses big-endian byte order
 when converting byte strings to integers internally. */
 ut_crc32_func_t	ut_crc32_legacy_big_endian;
-
-/** Pointer to CRC32-byte-by-byte calculation function (byte order agnostic,
-but very slow). */
-ut_crc32_func_t	ut_crc32_byte_by_byte;
+#endif /* INNODB_BUG_ENDIAN_CRC32 */
 
 /** Text description of CRC32 implementation */
 const char*	ut_crc32_implementation;
@@ -278,6 +276,7 @@ ut_crc32_64_hw(
 	*len -= 8;
 }
 
+#ifdef INNODB_BUG_ENDIAN_CRC32
 /** Calculate CRC32 over 64-bit byte string using a hardware/CPU instruction.
 The byte string is converted to a 64-bit integer using big endian byte order.
 @param[in,out]	crc	crc32 checksum so far when this function is called,
@@ -308,6 +307,7 @@ ut_crc32_64_legacy_big_endian_hw(
 	*data += 8;
 	*len -= 8;
 }
+#endif /* INNODB_BUG_ENDIAN_CRC32 */
 
 /** Calculates CRC32 using hardware/CPU instructions.
 @param[in]	buf	data over which to calculate CRC32
@@ -396,6 +396,7 @@ ut_crc32_hw(
 	return(~crc);
 }
 
+# ifdef INNODB_BUG_ENDIAN_CRC32
 /** Calculates CRC32 using hardware/CPU instructions.
 This function uses big endian byte ordering when converting byte sequence to
 integers.
@@ -445,26 +446,7 @@ ut_crc32_legacy_big_endian_hw(
 
 	return(~crc);
 }
-
-/** Calculates CRC32 using hardware/CPU instructions.
-This function processes one byte at a time (very slow) and thus it does
-not depend on the byte order of the machine.
-@param[in]	buf	data over which to calculate CRC32
-@param[in]	len	data length
-@return CRC-32C (polynomial 0x11EDC6F41) */
-uint32_t
-ut_crc32_byte_by_byte_hw(
-	const byte*	buf,
-	ulint		len)
-{
-	uint32_t	crc = 0xFFFFFFFFU;
-
-	while (len > 0) {
-		ut_crc32_8_hw(&crc, &buf, &len);
-	}
-
-	return(~crc);
-}
+# endif /* INNODB_BUG_ENDIAN_CRC32 */
 #endif /* defined(__GNUC__) && defined(__x86_64__) || (_WIN64) */
 
 /* CRC32 software implementation. */
@@ -577,6 +559,7 @@ ut_crc32_64_sw(
 	*len -= 8;
 }
 
+#ifdef INNODB_BUG_ENDIAN_CRC32
 /** Calculate CRC32 over 64-bit byte string using a software implementation.
 The byte string is converted to a 64-bit integer using big endian byte order.
 @param[in,out]	crc	crc32 checksum so far when this function is called,
@@ -602,6 +585,7 @@ ut_crc32_64_legacy_big_endian_sw(
 	*data += 8;
 	*len -= 8;
 }
+#endif /* INNODB_BUG_ENDIAN_CRC32 */
 
 /** Calculates CRC32 in software, without using CPU instructions.
 @param[in]	buf	data over which to calculate CRC32
@@ -653,6 +637,7 @@ ut_crc32_sw(
 	return(~crc);
 }
 
+#ifdef INNODB_BUG_ENDIAN_CRC32
 /** Calculates CRC32 in software, without using CPU instructions.
 This function uses big endian byte ordering when converting byte sequence to
 integers.
@@ -704,28 +689,7 @@ ut_crc32_legacy_big_endian_sw(
 
 	return(~crc);
 }
-
-/** Calculates CRC32 in software, without using CPU instructions.
-This function processes one byte at a time (very slow) and thus it does
-not depend on the byte order of the machine.
-@param[in]	buf	data over which to calculate CRC32
-@param[in]	len	data length
-@return CRC-32C (polynomial 0x11EDC6F41) */
-uint32_t
-ut_crc32_byte_by_byte_sw(
-	const byte*	buf,
-	ulint		len)
-{
-	uint32_t	crc = 0xFFFFFFFFU;
-
-	ut_a(ut_crc32_slice8_table_initialized);
-
-	while (len > 0) {
-		ut_crc32_8_sw(&crc, &buf, &len);
-	}
-
-	return(~crc);
-}
+#endif /* INNODB_BUG_ENDIAN_CRC32 */
 
 /********************************************************************//**
 Initializes the data structures used by ut_crc32*(). Does not do any
@@ -736,8 +700,9 @@ ut_crc32_init()
 {
 	ut_crc32_slice8_table_init();
 	ut_crc32 = ut_crc32_sw;
+#ifdef INNODB_BUG_ENDIAN_CRC32
 	ut_crc32_legacy_big_endian = ut_crc32_legacy_big_endian_sw;
-	ut_crc32_byte_by_byte = ut_crc32_byte_by_byte_sw;
+#endif /* INNODB_BUG_ENDIAN_CRC32 */
 	ut_crc32_implementation = "Using generic crc32 instructions";
 
 #if (defined(__GNUC__) && defined(__x86_64__)) || defined(_MSC_VER)
@@ -770,8 +735,9 @@ ut_crc32_init()
 
 	if (features_ecx & 1 << 20) {
 		ut_crc32 = ut_crc32_hw;
+#ifdef INNODB_BUG_ENDIAN_CRC32
 		ut_crc32_legacy_big_endian = ut_crc32_legacy_big_endian_hw;
-		ut_crc32_byte_by_byte = ut_crc32_byte_by_byte_hw;
+#endif /* INNODB_BUG_ENDIAN_CRC32 */
 		ut_crc32_implementation = "Using SSE2 crc32 instructions";
 	}