yb_ddl_parser 0.1.0

data/ext/yb_ddl_parser/vendor/yugabyte-postgres/src/include/storage/bufpage.h

@@ -0,0 +1,457 @@
+/*-------------------------------------------------------------------------
+ *
+ * bufpage.h
+ *	  Standard POSTGRES buffer page definitions.
+ *
+ *
+ * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/storage/bufpage.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef BUFPAGE_H
+#define BUFPAGE_H
+
+#include "access/xlogdefs.h"
+#include "storage/block.h"
+#include "storage/item.h"
+#include "storage/off.h"
+
+/*
+ * A postgres disk page is an abstraction layered on top of a postgres
+ * disk block (which is simply a unit of i/o, see block.h).
+ *
+ * specifically, while a disk block can be unformatted, a postgres
+ * disk page is always a slotted page of the form:
+ *
+ * +----------------+---------------------------------+
+ * | PageHeaderData | linp1 linp2 linp3 ...           |
+ * +-----------+----+---------------------------------+
+ * | ... linpN |									  |
+ * +-----------+--------------------------------------+
+ * |		   ^ pd_lower							  |
+ * |												  |
+ * |			 v pd_upper							  |
+ * +-------------+------------------------------------+
+ * |			 | tupleN ...                         |
+ * +-------------+------------------+-----------------+
+ * |	   ... tuple3 tuple2 tuple1 | "special space" |
+ * +--------------------------------+-----------------+
+ *									^ pd_special
+ *
+ * a page is full when nothing can be added between pd_lower and
+ * pd_upper.
+ *
+ * all blocks written out by an access method must be disk pages.
+ *
+ * EXCEPTIONS:
+ *
+ * obviously, a page is not formatted before it is initialized by
+ * a call to PageInit.
+ *
+ * NOTES:
+ *
+ * linp1..N form an ItemId (line pointer) array.  ItemPointers point
+ * to a physical block number and a logical offset (line pointer
+ * number) within that block/page.  Note that OffsetNumbers
+ * conventionally start at 1, not 0.
+ *
+ * tuple1..N are added "backwards" on the page.  Since an ItemPointer
+ * offset is used to access an ItemId entry rather than an actual
+ * byte-offset position, tuples can be physically shuffled on a page
+ * whenever the need arises.  This indirection also keeps crash recovery
+ * relatively simple, because the low-level details of page space
+ * management can be controlled by standard buffer page code during
+ * logging, and during recovery.
+ *
+ * AM-generic per-page information is kept in PageHeaderData.
+ *
+ * AM-specific per-page data (if any) is kept in the area marked "special
+ * space"; each AM has an "opaque" structure defined somewhere that is
+ * stored as the page trailer.  an access method should always
+ * initialize its pages with PageInit and then set its own opaque
+ * fields.
+ */
+
+typedef Pointer Page;
+
+
+/*
+ * location (byte offset) within a page.
+ *
+ * note that this is actually limited to 2^15 because we have limited
+ * ItemIdData.lp_off and ItemIdData.lp_len to 15 bits (see itemid.h).
+ */
+typedef uint16 LocationIndex;
+
+
+/*
+ * For historical reasons, the 64-bit LSN value is stored as two 32-bit
+ * values.
+ */
+typedef struct
+{
+	uint32		xlogid;			/* high bits */
+	uint32		xrecoff;		/* low bits */
+} PageXLogRecPtr;
+
+#define PageXLogRecPtrGet(val) \
+	((uint64) (val).xlogid << 32 | (val).xrecoff)
+#define PageXLogRecPtrSet(ptr, lsn) \
+	((ptr).xlogid = (uint32) ((lsn) >> 32), (ptr).xrecoff = (uint32) (lsn))
+
+/*
+ * disk page organization
+ *
+ * space management information generic to any page
+ *
+ *		pd_lsn		- identifies xlog record for last change to this page.
+ *		pd_checksum - page checksum, if set.
+ *		pd_flags	- flag bits.
+ *		pd_lower	- offset to start of free space.
+ *		pd_upper	- offset to end of free space.
+ *		pd_special	- offset to start of special space.
+ *		pd_pagesize_version - size in bytes and page layout version number.
+ *		pd_prune_xid - oldest XID among potentially prunable tuples on page.
+ *
+ * The LSN is used by the buffer manager to enforce the basic rule of WAL:
+ * "thou shalt write xlog before data".  A dirty buffer cannot be dumped
+ * to disk until xlog has been flushed at least as far as the page's LSN.
+ *
+ * pd_checksum stores the page checksum, if it has been set for this page;
+ * zero is a valid value for a checksum. If a checksum is not in use then
+ * we leave the field unset. This will typically mean the field is zero
+ * though non-zero values may also be present if databases have been
+ * pg_upgraded from releases prior to 9.3, when the same byte offset was
+ * used to store the current timelineid when the page was last updated.
+ * Note that there is no indication on a page as to whether the checksum
+ * is valid or not, a deliberate design choice which avoids the problem
+ * of relying on the page contents to decide whether to verify it. Hence
+ * there are no flag bits relating to checksums.
+ *
+ * pd_prune_xid is a hint field that helps determine whether pruning will be
+ * useful.  It is currently unused in index pages.
+ *
+ * The page version number and page size are packed together into a single
+ * uint16 field.  This is for historical reasons: before PostgreSQL 7.3,
+ * there was no concept of a page version number, and doing it this way
+ * lets us pretend that pre-7.3 databases have page version number zero.
+ * We constrain page sizes to be multiples of 256, leaving the low eight
+ * bits available for a version number.
+ *
+ * Minimum possible page size is perhaps 64B to fit page header, opaque space
+ * and a minimal tuple; of course, in reality you want it much bigger, so
+ * the constraint on pagesize mod 256 is not an important restriction.
+ * On the high end, we can only support pages up to 32KB because lp_off/lp_len
+ * are 15 bits.
+ */
+
+typedef struct PageHeaderData
+{
+	/* XXX LSN is member of *any* block, not only page-organized ones */
+	PageXLogRecPtr pd_lsn;		/* LSN: next byte after last byte of xlog
+								 * record for last change to this page */
+	uint16		pd_checksum;	/* checksum */
+	uint16		pd_flags;		/* flag bits, see below */
+	LocationIndex pd_lower;		/* offset to start of free space */
+	LocationIndex pd_upper;		/* offset to end of free space */
+	LocationIndex pd_special;	/* offset to start of special space */
+	uint16		pd_pagesize_version;
+	TransactionId pd_prune_xid; /* oldest prunable XID, or zero if none */
+	ItemIdData	pd_linp[FLEXIBLE_ARRAY_MEMBER]; /* line pointer array */
+} PageHeaderData;
+
+typedef PageHeaderData *PageHeader;
+
+/*
+ * pd_flags contains the following flag bits.  Undefined bits are initialized
+ * to zero and may be used in the future.
+ *
+ * PD_HAS_FREE_LINES is set if there are any LP_UNUSED line pointers before
+ * pd_lower.  This should be considered a hint rather than the truth, since
+ * changes to it are not WAL-logged.
+ *
+ * PD_PAGE_FULL is set if an UPDATE doesn't find enough free space in the
+ * page for its new tuple version; this suggests that a prune is needed.
+ * Again, this is just a hint.
+ */
+#define PD_HAS_FREE_LINES	0x0001	/* are there any unused line pointers? */
+#define PD_PAGE_FULL		0x0002	/* not enough free space for new tuple? */
+#define PD_ALL_VISIBLE		0x0004	/* all tuples on page are visible to
+									 * everyone */
+
+#define PD_VALID_FLAG_BITS	0x0007	/* OR of all valid pd_flags bits */
+
+/*
+ * Page layout version number 0 is for pre-7.3 Postgres releases.
+ * Releases 7.3 and 7.4 use 1, denoting a new HeapTupleHeader layout.
+ * Release 8.0 uses 2; it changed the HeapTupleHeader layout again.
+ * Release 8.1 uses 3; it redefined HeapTupleHeader infomask bits.
+ * Release 8.3 uses 4; it changed the HeapTupleHeader layout again, and
+ *		added the pd_flags field (by stealing some bits from pd_tli),
+ *		as well as adding the pd_prune_xid field (which enlarges the header).
+ *
+ * As of Release 9.3, the checksum version must also be considered when
+ * handling pages.
+ */
+#define PG_PAGE_LAYOUT_VERSION		4
+#define PG_DATA_CHECKSUM_VERSION	1
+
+/* ----------------------------------------------------------------
+ *						page support macros
+ * ----------------------------------------------------------------
+ */
+
+/*
+ * PageIsValid
+ *		True iff page is valid.
+ */
+#define PageIsValid(page) PointerIsValid(page)
+
+/*
+ * line pointer(s) do not count as part of header
+ */
+#define SizeOfPageHeaderData (offsetof(PageHeaderData, pd_linp))
+
+/*
+ * PageIsEmpty
+ *		returns true iff no itemid has been allocated on the page
+ */
+#define PageIsEmpty(page) \
+	(((PageHeader) (page))->pd_lower <= SizeOfPageHeaderData)
+
+/*
+ * PageIsNew
+ *		returns true iff page has not been initialized (by PageInit)
+ */
+#define PageIsNew(page) (((PageHeader) (page))->pd_upper == 0)
+
+/*
+ * PageGetItemId
+ *		Returns an item identifier of a page.
+ */
+#define PageGetItemId(page, offsetNumber) \
+	((ItemId) (&((PageHeader) (page))->pd_linp[(offsetNumber) - 1]))
+
+/*
+ * PageGetContents
+ *		To be used in cases where the page does not contain line pointers.
+ *
+ * Note: prior to 8.3 this was not guaranteed to yield a MAXALIGN'd result.
+ * Now it is.  Beware of old code that might think the offset to the contents
+ * is just SizeOfPageHeaderData rather than MAXALIGN(SizeOfPageHeaderData).
+ */
+#define PageGetContents(page) \
+	((char *) (page) + MAXALIGN(SizeOfPageHeaderData))
+
+/* ----------------
+ *		macros to access page size info
+ * ----------------
+ */
+
+/*
+ * PageSizeIsValid
+ *		True iff the page size is valid.
+ */
+#define PageSizeIsValid(pageSize) ((pageSize) == BLCKSZ)
+
+/*
+ * PageGetPageSize
+ *		Returns the page size of a page.
+ *
+ * this can only be called on a formatted page (unlike
+ * BufferGetPageSize, which can be called on an unformatted page).
+ * however, it can be called on a page that is not stored in a buffer.
+ */
+#define PageGetPageSize(page) \
+	((Size) (((PageHeader) (page))->pd_pagesize_version & (uint16) 0xFF00))
+
+/*
+ * PageGetPageLayoutVersion
+ *		Returns the page layout version of a page.
+ */
+#define PageGetPageLayoutVersion(page) \
+	(((PageHeader) (page))->pd_pagesize_version & 0x00FF)
+
+/*
+ * PageSetPageSizeAndVersion
+ *		Sets the page size and page layout version number of a page.
+ *
+ * We could support setting these two values separately, but there's
+ * no real need for it at the moment.
+ */
+#define PageSetPageSizeAndVersion(page, size, version) \
+( \
+	AssertMacro(((size) & 0xFF00) == (size)), \
+	AssertMacro(((version) & 0x00FF) == (version)), \
+	((PageHeader) (page))->pd_pagesize_version = (size) | (version) \
+)
+
+/* ----------------
+ *		page special data macros
+ * ----------------
+ */
+/*
+ * PageGetSpecialSize
+ *		Returns size of special space on a page.
+ */
+#define PageGetSpecialSize(page) \
+	((uint16) (PageGetPageSize(page) - ((PageHeader)(page))->pd_special))
+
+/*
+ * Using assertions, validate that the page special pointer is OK.
+ *
+ * This is intended to catch use of the pointer before page initialization.
+ * It is implemented as a function due to the limitations of the MSVC
+ * compiler, which choked on doing all these tests within another macro.  We
+ * return true so that AssertMacro() can be used while still getting the
+ * specifics from the macro failure within this function.
+ */
+static inline bool
+PageValidateSpecialPointer(Page page)
+{
+	Assert(PageIsValid(page));
+	Assert(((PageHeader) (page))->pd_special <= BLCKSZ);
+	Assert(((PageHeader) (page))->pd_special >= SizeOfPageHeaderData);
+
+	return true;
+}
+
+/*
+ * PageGetSpecialPointer
+ *		Returns pointer to special space on a page.
+ */
+#define PageGetSpecialPointer(page) \
+( \
+	AssertMacro(PageValidateSpecialPointer(page)), \
+	(char *) ((char *) (page) + ((PageHeader) (page))->pd_special) \
+)
+
+/*
+ * PageGetItem
+ *		Retrieves an item on the given page.
+ *
+ * Note:
+ *		This does not change the status of any of the resources passed.
+ *		The semantics may change in the future.
+ */
+#define PageGetItem(page, itemId) \
+( \
+	AssertMacro(PageIsValid(page)), \
+	AssertMacro(ItemIdHasStorage(itemId)), \
+	(Item)(((char *)(page)) + ItemIdGetOffset(itemId)) \
+)
+
+/*
+ * PageGetMaxOffsetNumber
+ *		Returns the maximum offset number used by the given page.
+ *		Since offset numbers are 1-based, this is also the number
+ *		of items on the page.
+ *
+ *		NOTE: if the page is not initialized (pd_lower == 0), we must
+ *		return zero to ensure sane behavior.  Accept double evaluation
+ *		of the argument so that we can ensure this.
+ */
+#define PageGetMaxOffsetNumber(page) \
+	(((PageHeader) (page))->pd_lower <= SizeOfPageHeaderData ? 0 : \
+	 ((((PageHeader) (page))->pd_lower - SizeOfPageHeaderData) \
+	  / sizeof(ItemIdData)))
+
+/*
+ * Additional macros for access to page headers. (Beware multiple evaluation
+ * of the arguments!)
+ */
+#define PageGetLSN(page) \
+	PageXLogRecPtrGet(((PageHeader) (page))->pd_lsn)
+#define PageSetLSN(page, lsn) \
+	PageXLogRecPtrSet(((PageHeader) (page))->pd_lsn, lsn)
+
+#define PageHasFreeLinePointers(page) \
+	(((PageHeader) (page))->pd_flags & PD_HAS_FREE_LINES)
+#define PageSetHasFreeLinePointers(page) \
+	(((PageHeader) (page))->pd_flags |= PD_HAS_FREE_LINES)
+#define PageClearHasFreeLinePointers(page) \
+	(((PageHeader) (page))->pd_flags &= ~PD_HAS_FREE_LINES)
+
+#define PageIsFull(page) \
+	(((PageHeader) (page))->pd_flags & PD_PAGE_FULL)
+#define PageSetFull(page) \
+	(((PageHeader) (page))->pd_flags |= PD_PAGE_FULL)
+#define PageClearFull(page) \
+	(((PageHeader) (page))->pd_flags &= ~PD_PAGE_FULL)
+
+#define PageIsAllVisible(page) \
+	(((PageHeader) (page))->pd_flags & PD_ALL_VISIBLE)
+#define PageSetAllVisible(page) \
+	(((PageHeader) (page))->pd_flags |= PD_ALL_VISIBLE)
+#define PageClearAllVisible(page) \
+	(((PageHeader) (page))->pd_flags &= ~PD_ALL_VISIBLE)
+
+#define PageSetPrunable(page, xid) \
+do { \
+	Assert(TransactionIdIsNormal(xid)); \
+	if (!TransactionIdIsValid(((PageHeader) (page))->pd_prune_xid) || \
+		TransactionIdPrecedes(xid, ((PageHeader) (page))->pd_prune_xid)) \
+		((PageHeader) (page))->pd_prune_xid = (xid); \
+} while (0)
+#define PageClearPrunable(page) \
+	(((PageHeader) (page))->pd_prune_xid = InvalidTransactionId)
+
+
+/* ----------------------------------------------------------------
+ *		extern declarations
+ * ----------------------------------------------------------------
+ */
+
+/* flags for PageAddItemExtended() */
+#define PAI_OVERWRITE			(1 << 0)
+#define PAI_IS_HEAP				(1 << 1)
+
+/* flags for PageIsVerifiedExtended() */
+#define PIV_LOG_WARNING			(1 << 0)
+#define PIV_REPORT_STAT			(1 << 1)
+
+#define PageAddItem(page, item, size, offsetNumber, overwrite, is_heap) \
+	PageAddItemExtended(page, item, size, offsetNumber, \
+						((overwrite) ? PAI_OVERWRITE : 0) | \
+						((is_heap) ? PAI_IS_HEAP : 0))
+
+#define PageIsVerified(page, blkno) \
+	PageIsVerifiedExtended(page, blkno, \
+						   PIV_LOG_WARNING | PIV_REPORT_STAT)
+
+/*
+ * Check that BLCKSZ is a multiple of sizeof(size_t).  In
+ * PageIsVerifiedExtended(), it is much faster to check if a page is
+ * full of zeroes using the native word size.  Note that this assertion
+ * is kept within a header to make sure that StaticAssertDecl() works
+ * across various combinations of platforms and compilers.
+ */
+StaticAssertDecl(BLCKSZ == ((BLCKSZ / sizeof(size_t)) * sizeof(size_t)),
+				 "BLCKSZ has to be a multiple of sizeof(size_t)");
+
+extern void PageInit(Page page, Size pageSize, Size specialSize);
+extern bool PageIsVerifiedExtended(Page page, BlockNumber blkno, int flags);
+extern OffsetNumber PageAddItemExtended(Page page, Item item, Size size,
+										OffsetNumber offsetNumber, int flags);
+extern Page PageGetTempPage(Page page);
+extern Page PageGetTempPageCopy(Page page);
+extern Page PageGetTempPageCopySpecial(Page page);
+extern void PageRestoreTempPage(Page tempPage, Page oldPage);
+extern void PageRepairFragmentation(Page page);
+extern void PageTruncateLinePointerArray(Page page);
+extern Size PageGetFreeSpace(Page page);
+extern Size PageGetFreeSpaceForMultipleTuples(Page page, int ntups);
+extern Size PageGetExactFreeSpace(Page page);
+extern Size PageGetHeapFreeSpace(Page page);
+extern void PageIndexTupleDelete(Page page, OffsetNumber offset);
+extern void PageIndexMultiDelete(Page page, OffsetNumber *itemnos, int nitems);
+extern void PageIndexTupleDeleteNoCompact(Page page, OffsetNumber offset);
+extern bool PageIndexTupleOverwrite(Page page, OffsetNumber offnum,
+									Item newtup, Size newsize);
+extern char *PageSetChecksumCopy(Page page, BlockNumber blkno);
+extern void PageSetChecksumInplace(Page page, BlockNumber blkno);
+
+#endif							/* BUFPAGE_H */

data/ext/yb_ddl_parser/vendor/yugabyte-postgres/src/include/storage/checksum.h

@@ -0,0 +1,24 @@
+/*-------------------------------------------------------------------------
+ *
+ * checksum.h
+ *	  Checksum implementation for data pages.
+ *
+ * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/storage/checksum.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef CHECKSUM_H
+#define CHECKSUM_H
+
+#include "storage/block.h"
+
+/*
+ * Compute the checksum for a Postgres page.  The page must be aligned on a
+ * 4-byte boundary.
+ */
+extern uint16 pg_checksum_page(char *page, BlockNumber blkno);
+
+#endif							/* CHECKSUM_H */

data/ext/yb_ddl_parser/vendor/yugabyte-postgres/src/include/storage/checksum_impl.h

@@ -0,0 +1,215 @@
+/*-------------------------------------------------------------------------
+ *
+ * checksum_impl.h
+ *	  Checksum implementation for data pages.
+ *
+ * This file exists for the benefit of external programs that may wish to
+ * check Postgres page checksums.  They can #include this to get the code
+ * referenced by storage/checksum.h.  (Note: you may need to redefine
+ * Assert() as empty to compile this successfully externally.)
+ *
+ * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/storage/checksum_impl.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+/*
+ * The algorithm used to checksum pages is chosen for very fast calculation.
+ * Workloads where the database working set fits into OS file cache but not
+ * into shared buffers can read in pages at a very fast pace and the checksum
+ * algorithm itself can become the largest bottleneck.
+ *
+ * The checksum algorithm itself is based on the FNV-1a hash (FNV is shorthand
+ * for Fowler/Noll/Vo).  The primitive of a plain FNV-1a hash folds in data 1
+ * byte at a time according to the formula:
+ *
+ *	   hash = (hash ^ value) * FNV_PRIME
+ *
+ * FNV-1a algorithm is described at http://www.isthe.com/chongo/tech/comp/fnv/
+ *
+ * PostgreSQL doesn't use FNV-1a hash directly because it has bad mixing of
+ * high bits - high order bits in input data only affect high order bits in
+ * output data. To resolve this we xor in the value prior to multiplication
+ * shifted right by 17 bits. The number 17 was chosen because it doesn't
+ * have common denominator with set bit positions in FNV_PRIME and empirically
+ * provides the fastest mixing for high order bits of final iterations quickly
+ * avalanche into lower positions. For performance reasons we choose to combine
+ * 4 bytes at a time. The actual hash formula used as the basis is:
+ *
+ *	   hash = (hash ^ value) * FNV_PRIME ^ ((hash ^ value) >> 17)
+ *
+ * The main bottleneck in this calculation is the multiplication latency. To
+ * hide the latency and to make use of SIMD parallelism multiple hash values
+ * are calculated in parallel. The page is treated as a 32 column two
+ * dimensional array of 32 bit values. Each column is aggregated separately
+ * into a partial checksum. Each partial checksum uses a different initial
+ * value (offset basis in FNV terminology). The initial values actually used
+ * were chosen randomly, as the values themselves don't matter as much as that
+ * they are different and don't match anything in real data. After initializing
+ * partial checksums each value in the column is aggregated according to the
+ * above formula. Finally two more iterations of the formula are performed with
+ * value 0 to mix the bits of the last value added.
+ *
+ * The partial checksums are then folded together using xor to form a single
+ * 32-bit checksum. The caller can safely reduce the value to 16 bits
+ * using modulo 2^16-1. That will cause a very slight bias towards lower
+ * values but this is not significant for the performance of the
+ * checksum.
+ *
+ * The algorithm choice was based on what instructions are available in SIMD
+ * instruction sets. This meant that a fast and good algorithm needed to use
+ * multiplication as the main mixing operator. The simplest multiplication
+ * based checksum primitive is the one used by FNV. The prime used is chosen
+ * for good dispersion of values. It has no known simple patterns that result
+ * in collisions. Test of 5-bit differentials of the primitive over 64bit keys
+ * reveals no differentials with 3 or more values out of 100000 random keys
+ * colliding. Avalanche test shows that only high order bits of the last word
+ * have a bias. Tests of 1-4 uncorrelated bit errors, stray 0 and 0xFF bytes,
+ * overwriting page from random position to end with 0 bytes, and overwriting
+ * random segments of page with 0x00, 0xFF and random data all show optimal
+ * 2e-16 false positive rate within margin of error.
+ *
+ * Vectorization of the algorithm requires 32bit x 32bit -> 32bit integer
+ * multiplication instruction. As of 2013 the corresponding instruction is
+ * available on x86 SSE4.1 extensions (pmulld) and ARM NEON (vmul.i32).
+ * Vectorization requires a compiler to do the vectorization for us. For recent
+ * GCC versions the flags -msse4.1 -funroll-loops -ftree-vectorize are enough
+ * to achieve vectorization.
+ *
+ * The optimal amount of parallelism to use depends on CPU specific instruction
+ * latency, SIMD instruction width, throughput and the amount of registers
+ * available to hold intermediate state. Generally, more parallelism is better
+ * up to the point that state doesn't fit in registers and extra load-store
+ * instructions are needed to swap values in/out. The number chosen is a fixed
+ * part of the algorithm because changing the parallelism changes the checksum
+ * result.
+ *
+ * The parallelism number 32 was chosen based on the fact that it is the
+ * largest state that fits into architecturally visible x86 SSE registers while
+ * leaving some free registers for intermediate values. For future processors
+ * with 256bit vector registers this will leave some performance on the table.
+ * When vectorization is not available it might be beneficial to restructure
+ * the computation to calculate a subset of the columns at a time and perform
+ * multiple passes to avoid register spilling. This optimization opportunity
+ * is not used. Current coding also assumes that the compiler has the ability
+ * to unroll the inner loop to avoid loop overhead and minimize register
+ * spilling. For less sophisticated compilers it might be beneficial to
+ * manually unroll the inner loop.
+ */
+
+#include "storage/bufpage.h"
+
+/* number of checksums to calculate in parallel */
+#define N_SUMS 32
+/* prime multiplier of FNV-1a hash */
+#define FNV_PRIME 16777619
+
+/* Use a union so that this code is valid under strict aliasing */
+typedef union
+{
+	PageHeaderData phdr;
+	uint32		data[BLCKSZ / (sizeof(uint32) * N_SUMS)][N_SUMS];
+} PGChecksummablePage;
+
+/*
+ * Base offsets to initialize each of the parallel FNV hashes into a
+ * different initial state.
+ */
+static const uint32 checksumBaseOffsets[N_SUMS] = {
+	0x5B1F36E9, 0xB8525960, 0x02AB50AA, 0x1DE66D2A,
+	0x79FF467A, 0x9BB9F8A3, 0x217E7CD2, 0x83E13D2C,
+	0xF8D4474F, 0xE39EB970, 0x42C6AE16, 0x993216FA,
+	0x7B093B5D, 0x98DAFF3C, 0xF718902A, 0x0B1C9CDB,
+	0xE58F764B, 0x187636BC, 0x5D7B3BB1, 0xE73DE7DE,
+	0x92BEC979, 0xCCA6C0B2, 0x304A0979, 0x85AA43D4,
+	0x783125BB, 0x6CA8EAA2, 0xE407EAC6, 0x4B5CFC3E,
+	0x9FBF8C76, 0x15CA20BE, 0xF2CA9FD3, 0x959BD756
+};
+
+/*
+ * Calculate one round of the checksum.
+ */
+#define CHECKSUM_COMP(checksum, value) \
+do { \
+	uint32 __tmp = (checksum) ^ (value); \
+	(checksum) = __tmp * FNV_PRIME ^ (__tmp >> 17); \
+} while (0)
+
+/*
+ * Block checksum algorithm.  The page must be adequately aligned
+ * (at least on 4-byte boundary).
+ */
+static uint32
+pg_checksum_block(const PGChecksummablePage *page)
+{
+	uint32		sums[N_SUMS];
+	uint32		result = 0;
+	uint32		i,
+				j;
+
+	/* ensure that the size is compatible with the algorithm */
+	Assert(sizeof(PGChecksummablePage) == BLCKSZ);
+
+	/* initialize partial checksums to their corresponding offsets */
+	memcpy(sums, checksumBaseOffsets, sizeof(checksumBaseOffsets));
+
+	/* main checksum calculation */
+	for (i = 0; i < (uint32) (BLCKSZ / (sizeof(uint32) * N_SUMS)); i++)
+		for (j = 0; j < N_SUMS; j++)
+			CHECKSUM_COMP(sums[j], page->data[i][j]);
+
+	/* finally add in two rounds of zeroes for additional mixing */
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < N_SUMS; j++)
+			CHECKSUM_COMP(sums[j], 0);
+
+	/* xor fold partial checksums together */
+	for (i = 0; i < N_SUMS; i++)
+		result ^= sums[i];
+
+	return result;
+}
+
+/*
+ * Compute the checksum for a Postgres page.
+ *
+ * The page must be adequately aligned (at least on a 4-byte boundary).
+ * Beware also that the checksum field of the page is transiently zeroed.
+ *
+ * The checksum includes the block number (to detect the case where a page is
+ * somehow moved to a different location), the page header (excluding the
+ * checksum itself), and the page data.
+ */
+uint16
+pg_checksum_page(char *page, BlockNumber blkno)
+{
+	PGChecksummablePage *cpage = (PGChecksummablePage *) page;
+	uint16		save_checksum;
+	uint32		checksum;
+
+	/* We only calculate the checksum for properly-initialized pages */
+	Assert(!PageIsNew(&cpage->phdr));
+
+	/*
+	 * Save pd_checksum and temporarily set it to zero, so that the checksum
+	 * calculation isn't affected by the old checksum stored on the page.
+	 * Restore it after, because actually updating the checksum is NOT part of
+	 * the API of this function.
+	 */
+	save_checksum = cpage->phdr.pd_checksum;
+	cpage->phdr.pd_checksum = 0;
+	checksum = pg_checksum_block(cpage);
+	cpage->phdr.pd_checksum = save_checksum;
+
+	/* Mix in the block number to detect transposed pages */
+	checksum ^= blkno;
+
+	/*
+	 * Reduce to a uint16 (to fit in the pd_checksum field) with an offset of
+	 * one. That avoids checksums of zero, which seems like a good idea.
+	 */
+	return (uint16) ((checksum % 65535) + 1);
+}