Add amcheck verification of heap relations belonging to btree indexes.

Add a new, optional, capability to bt_index_check() and
bt_index_parent_check():  check that each heap tuple that should have an
index entry does in fact have one.  The extra checking is performed at
the end of the existing nbtree checks.

This is implemented by using a Bloom filter data structure.  The
implementation performs set membership tests within a callback (the same
type of callback that each index AM registers for CREATE INDEX).  The
Bloom filter is populated during the initial index verification scan.

Reusing the CREATE INDEX infrastructure allows the new verification
option to automatically benefit from the heap consistency checks that
CREATE INDEX already performs.  CREATE INDEX does thorough sanity
checking of HOT chains, so the new check actually manages to detect
problems in heap-only tuples.

Author: Peter Geoghegan
Reviewed-By: Pavan Deolasee, Andres Freund
Discussion: https://postgr.es/m/CAH2-Wzm5VmG7cu1N-H=nnS57wZThoSDQU+F5dewx3o84M+jY=g@mail.gmail.com

contrib/amcheck/Makefile

@@ -4,7 +4,7 @@ MODULE_big	= amcheck
 OBJS		= verify_nbtree.o $(WIN32RES)
 
 EXTENSION = amcheck
-DATA = amcheck--1.0.sql
+DATA = amcheck--1.0--1.1.sql amcheck--1.0.sql
 PGFILEDESC = "amcheck - function for verifying relation integrity"
 
 REGRESS = check check_btree

contrib/amcheck/amcheck--1.0--1.1.sql

@@ -0,0 +1,29 @@
+/* contrib/amcheck/amcheck--1.0--1.1.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "ALTER EXTENSION amcheck UPDATE TO '1.1'" to load this file. \quit
+
+-- In order to avoid issues with dependencies when updating amcheck to 1.1,
+-- create new, overloaded versions of the 1.0 functions
+
+--
+-- bt_index_check()
+--
+CREATE FUNCTION bt_index_check(index regclass,
+    heapallindexed boolean)
+RETURNS VOID
+AS 'MODULE_PATHNAME', 'bt_index_check'
+LANGUAGE C STRICT PARALLEL RESTRICTED;
+
+--
+-- bt_index_parent_check()
+--
+CREATE FUNCTION bt_index_parent_check(index regclass,
+    heapallindexed boolean)
+RETURNS VOID
+AS 'MODULE_PATHNAME', 'bt_index_parent_check'
+LANGUAGE C STRICT PARALLEL RESTRICTED;
+
+-- Don't want these to be available to public
+REVOKE ALL ON FUNCTION bt_index_check(regclass, boolean) FROM PUBLIC;
+REVOKE ALL ON FUNCTION bt_index_parent_check(regclass, boolean) FROM PUBLIC;

contrib/amcheck/amcheck.control

@@ -1,5 +1,5 @@
 # amcheck extension
 comment = 'functions for verifying relation integrity'
-default_version = '1.0'
+default_version = '1.1'
 module_pathname = '$libdir/amcheck'
 relocatable = true

contrib/amcheck/expected/check_btree.out

@@ -18,6 +18,8 @@ RESET ROLE;
 -- above explicit permission has to be granted for that.
 GRANT EXECUTE ON FUNCTION bt_index_check(regclass) TO bttest_role;
 GRANT EXECUTE ON FUNCTION bt_index_parent_check(regclass) TO bttest_role;
+GRANT EXECUTE ON FUNCTION bt_index_check(regclass, boolean) TO bttest_role;
+GRANT EXECUTE ON FUNCTION bt_index_parent_check(regclass, boolean) TO bttest_role;
 SET ROLE bttest_role;
 SELECT bt_index_check('bttest_a_idx');
  bt_index_check 
@@ -56,8 +58,14 @@ SELECT bt_index_check('bttest_a_idx');
  
 (1 row)
 
--- more expansive test
-SELECT bt_index_parent_check('bttest_b_idx');
+-- more expansive tests
+SELECT bt_index_check('bttest_a_idx', true);
+ bt_index_check 
+----------------
+ 
+(1 row)
+
+SELECT bt_index_parent_check('bttest_b_idx', true);
  bt_index_parent_check 
 -----------------------
  

contrib/amcheck/sql/check_btree.sql

@@ -21,6 +21,8 @@ RESET ROLE;
 -- above explicit permission has to be granted for that.
 GRANT EXECUTE ON FUNCTION bt_index_check(regclass) TO bttest_role;
 GRANT EXECUTE ON FUNCTION bt_index_parent_check(regclass) TO bttest_role;
+GRANT EXECUTE ON FUNCTION bt_index_check(regclass, boolean) TO bttest_role;
+GRANT EXECUTE ON FUNCTION bt_index_parent_check(regclass, boolean) TO bttest_role;
 SET ROLE bttest_role;
 SELECT bt_index_check('bttest_a_idx');
 SELECT bt_index_parent_check('bttest_a_idx');
@@ -42,8 +44,9 @@ ROLLBACK;
 
 -- normal check outside of xact
 SELECT bt_index_check('bttest_a_idx');
--- more expansive test
-SELECT bt_index_parent_check('bttest_b_idx');
+-- more expansive tests
+SELECT bt_index_check('bttest_a_idx', true);
+SELECT bt_index_parent_check('bttest_b_idx', true);
 
 BEGIN;
 SELECT bt_index_check('bttest_a_idx');

contrib/amcheck/verify_nbtree.c

@@ -8,6 +8,11 @@
  * (the insertion scankey sort-wise NULL semantics are needed for
  * verification).
  *
+ * When index-to-heap verification is requested, a Bloom filter is used to
+ * fingerprint all tuples in the target index, as the index is traversed to
+ * verify its structure.  A heap scan later uses Bloom filter probes to verify
+ * that every visible heap tuple has a matching index tuple.
+ *
  *
  * Copyright (c) 2017-2018, PostgreSQL Global Development Group
  *
@@ -18,11 +23,14 @@
  */
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/nbtree.h"
 #include "access/transam.h"
+#include "access/xact.h"
 #include "catalog/index.h"
 #include "catalog/pg_am.h"
 #include "commands/tablecmds.h"
+#include "lib/bloomfilter.h"
 #include "miscadmin.h"
 #include "storage/lmgr.h"
 #include "utils/memutils.h"
@@ -43,9 +51,10 @@ PG_MODULE_MAGIC;
  * target is the point of reference for a verification operation.
  *
  * Other B-Tree pages may be allocated, but those are always auxiliary (e.g.,
- * they are current target's child pages). Conceptually, problems are only
- * ever found in the current target page. Each page found by verification's
- * left/right, top/bottom scan becomes the target exactly once.
+ * they are current target's child pages).  Conceptually, problems are only
+ * ever found in the current target page (or for a particular heap tuple during
+ * heapallindexed verification).  Each page found by verification's left/right,
+ * top/bottom scan becomes the target exactly once.
  */
 typedef struct BtreeCheckState
 {
@@ -53,10 +62,13 @@ typedef struct BtreeCheckState
 	 * Unchanging state, established at start of verification:
 	 */
 
-	/* B-Tree Index Relation */
+	/* B-Tree Index Relation and associated heap relation */
 	Relation	rel;
+	Relation	heaprel;
 	/* ShareLock held on heap/index, rather than AccessShareLock? */
 	bool		readonly;
+	/* Also verifying heap has no unindexed tuples? */
+	bool		heapallindexed;
 	/* Per-page context */
 	MemoryContext targetcontext;
 	/* Buffer access strategy */
@@ -72,6 +84,15 @@ typedef struct BtreeCheckState
 	BlockNumber targetblock;
 	/* Target page's LSN */
 	XLogRecPtr	targetlsn;
+
+	/*
+	 * Mutable state, for optional heapallindexed verification:
+	 */
+
+	/* Bloom filter fingerprints B-Tree index */
+	bloom_filter *filter;
+	/* Debug counter */
+	int64		heaptuplespresent;
 } BtreeCheckState;
 
 /*
@@ -92,15 +113,20 @@ typedef struct BtreeLevel
 PG_FUNCTION_INFO_V1(bt_index_check);
 PG_FUNCTION_INFO_V1(bt_index_parent_check);
 
-static void bt_index_check_internal(Oid indrelid, bool parentcheck);
+static void bt_index_check_internal(Oid indrelid, bool parentcheck,
+						bool heapallindexed);
 static inline void btree_index_checkable(Relation rel);
-static void bt_check_every_level(Relation rel, bool readonly);
+static void bt_check_every_level(Relation rel, Relation heaprel,
+					 bool readonly, bool heapallindexed);
 static BtreeLevel bt_check_level_from_leftmost(BtreeCheckState *state,
 							 BtreeLevel level);
 static void bt_target_page_check(BtreeCheckState *state);
 static ScanKey bt_right_page_check_scankey(BtreeCheckState *state);
 static void bt_downlink_check(BtreeCheckState *state, BlockNumber childblock,
 				  ScanKey targetkey);
+static void bt_tuple_present_callback(Relation index, HeapTuple htup,
+						  Datum *values, bool *isnull,
+						  bool tupleIsAlive, void *checkstate);
 static inline bool offset_is_negative_infinity(BTPageOpaque opaque,
 							OffsetNumber offset);
 static inline bool invariant_leq_offset(BtreeCheckState *state,
@@ -116,37 +142,47 @@ static inline bool invariant_leq_nontarget_offset(BtreeCheckState *state,
 static Page palloc_btree_page(BtreeCheckState *state, BlockNumber blocknum);
 
 /*
- * bt_index_check(index regclass)
+ * bt_index_check(index regclass, heapallindexed boolean)
  *
  * Verify integrity of B-Tree index.
  *
  * Acquires AccessShareLock on heap & index relations.  Does not consider
- * invariants that exist between parent/child pages.
+ * invariants that exist between parent/child pages.  Optionally verifies
+ * that heap does not contain any unindexed or incorrectly indexed tuples.
  */
 Datum
 bt_index_check(PG_FUNCTION_ARGS)
 {
 	Oid			indrelid = PG_GETARG_OID(0);
+	bool		heapallindexed = false;
 
-	bt_index_check_internal(indrelid, false);
+	if (PG_NARGS() == 2)
+		heapallindexed = PG_GETARG_BOOL(1);
+
+	bt_index_check_internal(indrelid, false, heapallindexed);
 
 	PG_RETURN_VOID();
 }
 
 /*
- * bt_index_parent_check(index regclass)
+ * bt_index_parent_check(index regclass, heapallindexed boolean)
  *
  * Verify integrity of B-Tree index.
  *
  * Acquires ShareLock on heap & index relations.  Verifies that downlinks in
- * parent pages are valid lower bounds on child pages.
+ * parent pages are valid lower bounds on child pages.  Optionally verifies
+ * that heap does not contain any unindexed or incorrectly indexed tuples.
  */
 Datum
 bt_index_parent_check(PG_FUNCTION_ARGS)
 {
 	Oid			indrelid = PG_GETARG_OID(0);
+	bool		heapallindexed = false;
 
-	bt_index_check_internal(indrelid, true);
+	if (PG_NARGS() == 2)
+		heapallindexed = PG_GETARG_BOOL(1);
+
+	bt_index_check_internal(indrelid, true, heapallindexed);
 
 	PG_RETURN_VOID();
 }
@@ -155,7 +191,7 @@ bt_index_parent_check(PG_FUNCTION_ARGS)
  * Helper for bt_index_[parent_]check, coordinating the bulk of the work.
  */
 static void
-bt_index_check_internal(Oid indrelid, bool parentcheck)
+bt_index_check_internal(Oid indrelid, bool parentcheck, bool heapallindexed)
 {
 	Oid			heapid;
 	Relation	indrel;
@@ -185,15 +221,20 @@ bt_index_check_internal(Oid indrelid, bool parentcheck)
 	 * Open the target index relations separately (like relation_openrv(), but
 	 * with heap relation locked first to prevent deadlocking).  In hot
 	 * standby mode this will raise an error when parentcheck is true.
+	 *
+	 * There is no need for the usual indcheckxmin usability horizon test here,
+	 * even in the heapallindexed case, because index undergoing verification
+	 * only needs to have entries for a new transaction snapshot.  (If this is
+	 * a parentcheck verification, there is no question about committed or
+	 * recently dead heap tuples lacking index entries due to concurrent
+	 * activity.)
 	 */
 	indrel = index_open(indrelid, lockmode);
 
 	/*
 	 * Since we did the IndexGetRelation call above without any lock, it's
 	 * barely possible that a race against an index drop/recreation could have
-	 * netted us the wrong table.  Although the table itself won't actually be
-	 * examined during verification currently, a recheck still seems like a
-	 * good idea.
+	 * netted us the wrong table.
 	 */
 	if (heaprel == NULL || heapid != IndexGetRelation(indrelid, false))
 		ereport(ERROR,
@@ -204,8 +245,8 @@ bt_index_check_internal(Oid indrelid, bool parentcheck)
 	/* Relation suitable for checking as B-Tree? */
 	btree_index_checkable(indrel);
 
-	/* Check index */
-	bt_check_every_level(indrel, parentcheck);
+	/* Check index, possibly against table it is an index on */
+	bt_check_every_level(indrel, heaprel, parentcheck, heapallindexed);
 
 	/*
 	 * Release locks early. That's ok here because nothing in the called
@@ -253,11 +294,14 @@ btree_index_checkable(Relation rel)
 
 /*
  * Main entry point for B-Tree SQL-callable functions. Walks the B-Tree in
- * logical order, verifying invariants as it goes.
+ * logical order, verifying invariants as it goes.  Optionally, verification
+ * checks if the heap relation contains any tuples that are not represented in
+ * the index but should be.
  *
  * It is the caller's responsibility to acquire appropriate heavyweight lock on
  * the index relation, and advise us if extra checks are safe when a ShareLock
- * is held.
+ * is held.  (A lock of the same type must also have been acquired on the heap
+ * relation.)
  *
  * A ShareLock is generally assumed to prevent any kind of physical
  * modification to the index structure, including modifications that VACUUM may
@@ -272,13 +316,15 @@ btree_index_checkable(Relation rel)
  * parent/child check cannot be affected.)
  */
 static void
-bt_check_every_level(Relation rel, bool readonly)
+bt_check_every_level(Relation rel, Relation heaprel, bool readonly,
+					 bool heapallindexed)
 {
 	BtreeCheckState *state;
 	Page		metapage;
 	BTMetaPageData *metad;
 	uint32		previouslevel;
 	BtreeLevel	current;
+	Snapshot	snapshot = SnapshotAny;
 
 	/*
 	 * RecentGlobalXmin assertion matches index_getnext_tid().  See note on
@@ -291,7 +337,57 @@ bt_check_every_level(Relation rel, bool readonly)
 	 */
 	state = palloc(sizeof(BtreeCheckState));
 	state->rel = rel;
+	state->heaprel = heaprel;
 	state->readonly = readonly;
+	state->heapallindexed = heapallindexed;
+
+	if (state->heapallindexed)
+	{
+		int64		total_elems;
+		uint64		seed;
+
+		/* Size Bloom filter based on estimated number of tuples in index */
+		total_elems = (int64) state->rel->rd_rel->reltuples;
+		/* Random seed relies on backend srandom() call to avoid repetition */
+		seed = random();
+		/* Create Bloom filter to fingerprint index */
+		state->filter = bloom_create(total_elems, maintenance_work_mem, seed);
+		state->heaptuplespresent = 0;
+
+		/*
+		 * Register our own snapshot in !readonly case, rather than asking
+		 * IndexBuildHeapScan() to do this for us later.  This needs to happen
+		 * before index fingerprinting begins, so we can later be certain that
+		 * index fingerprinting should have reached all tuples returned by
+		 * IndexBuildHeapScan().
+		 */
+		if (!state->readonly)
+		{
+			snapshot = RegisterSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * GetTransactionSnapshot() always acquires a new MVCC snapshot in
+			 * READ COMMITTED mode.  A new snapshot is guaranteed to have all
+			 * the entries it requires in the index.
+			 *
+			 * We must defend against the possibility that an old xact snapshot
+			 * was returned at higher isolation levels when that snapshot is
+			 * not safe for index scans of the target index.  This is possible
+			 * when the snapshot sees tuples that are before the index's
+			 * indcheckxmin horizon.  Throwing an error here should be very
+			 * rare.  It doesn't seem worth using a secondary snapshot to avoid
+			 * this.
+			 */
+			if (IsolationUsesXactSnapshot() && rel->rd_index->indcheckxmin &&
+				!TransactionIdPrecedes(HeapTupleHeaderGetXmin(rel->rd_indextuple->t_data),
+									   snapshot->xmin))
+				ereport(ERROR,
+						(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+						 errmsg("index \"%s\" cannot be verified using transaction snapshot",
+								RelationGetRelationName(rel))));
+		}
+	}
+
 	/* Create context for page */
 	state->targetcontext = AllocSetContextCreate(CurrentMemoryContext,
 												 "amcheck context",
@@ -345,6 +441,69 @@ bt_check_every_level(Relation rel, bool readonly)
 		previouslevel = current.level;
 	}
 
+	/*
+	 * * Check whether heap contains unindexed/malformed tuples *
+	 */
+	if (state->heapallindexed)
+	{
+		IndexInfo  *indexinfo = BuildIndexInfo(state->rel);
+		HeapScanDesc scan;
+
+		/*
+		 * Create our own scan for IndexBuildHeapScan(), rather than getting it
+		 * to do so for us.  This is required so that we can actually use the
+		 * MVCC snapshot registered earlier in !readonly case.
+		 *
+		 * Note that IndexBuildHeapScan() calls heap_endscan() for us.
+		 */
+		scan = heap_beginscan_strat(state->heaprel, /* relation */
+									snapshot,	/* snapshot */
+									0,	/* number of keys */
+									NULL,	/* scan key */
+									true,	/* buffer access strategy OK */
+									true);	/* syncscan OK? */
+
+		/*
+		 * Scan will behave as the first scan of a CREATE INDEX CONCURRENTLY
+		 * behaves in !readonly case.
+		 *
+		 * It's okay that we don't actually use the same lock strength for the
+		 * heap relation as any other ii_Concurrent caller would in !readonly
+		 * case.  We have no reason to care about a concurrent VACUUM
+		 * operation, since there isn't going to be a second scan of the heap
+		 * that needs to be sure that there was no concurrent recycling of
+		 * TIDs.
+		 */
+		indexinfo->ii_Concurrent = !state->readonly;
+
+		/*
+		 * Don't wait for uncommitted tuple xact commit/abort when index is a
+		 * unique index on a catalog (or an index used by an exclusion
+		 * constraint).  This could otherwise happen in the readonly case.
+		 */
+		indexinfo->ii_Unique = false;
+		indexinfo->ii_ExclusionOps = NULL;
+		indexinfo->ii_ExclusionProcs = NULL;
+		indexinfo->ii_ExclusionStrats = NULL;
+
+		elog(DEBUG1, "verifying that tuples from index \"%s\" are present in \"%s\"",
+			 RelationGetRelationName(state->rel),
+			 RelationGetRelationName(state->heaprel));
+
+		IndexBuildHeapScan(state->heaprel, state->rel, indexinfo, true,
+						   bt_tuple_present_callback, (void *) state, scan);
+
+		ereport(DEBUG1,
+				(errmsg_internal("finished verifying presence of " INT64_FORMAT " tuples from table \"%s\" with bitset %.2f%% set",
+								 state->heaptuplespresent, RelationGetRelationName(heaprel),
+								 100.0 * bloom_prop_bits_set(state->filter))));
+
+		if (snapshot != SnapshotAny)
+			UnregisterSnapshot(snapshot);
+
+		bloom_free(state->filter);
+	}
+
 	/* Be tidy: */
 	MemoryContextDelete(state->targetcontext);
 }
@@ -497,7 +656,7 @@ bt_check_level_from_leftmost(BtreeCheckState *state, BtreeLevel level)
 					 errdetail_internal("Block pointed to=%u expected level=%u level in pointed to block=%u.",
 										current, level.level, opaque->btpo.level)));
 
-		/* Verify invariants for page -- all important checks occur here */
+		/* Verify invariants for page */
 		bt_target_page_check(state);
 
 nextpage:
@@ -544,6 +703,9 @@ nextpage:
  *
  * - That all child pages respect downlinks lower bound.
  *
+ * This is also where heapallindexed callers use their Bloom filter to
+ * fingerprint IndexTuples.
+ *
  * Note:  Memory allocated in this routine is expected to be released by caller
  * resetting state->targetcontext.
  */
@@ -572,21 +734,46 @@ bt_target_page_check(BtreeCheckState *state)
 		ItemId		itemid;
 		IndexTuple	itup;
 		ScanKey		skey;
+		size_t		tupsize;
 
 		CHECK_FOR_INTERRUPTS();
 
+		itemid = PageGetItemId(state->target, offset);
+		itup = (IndexTuple) PageGetItem(state->target, itemid);
+		tupsize = IndexTupleSize(itup);
+
+		/*
+		 * lp_len should match the IndexTuple reported length exactly, since
+		 * lp_len is completely redundant in indexes, and both sources of tuple
+		 * length are MAXALIGN()'d.  nbtree does not use lp_len all that
+		 * frequently, and is surprisingly tolerant of corrupt lp_len fields.
+		 */
+		if (tupsize != ItemIdGetLength(itemid))
+			ereport(ERROR,
+					(errcode(ERRCODE_INDEX_CORRUPTED),
+					 errmsg("index tuple size does not equal lp_len in index \"%s\"",
+							RelationGetRelationName(state->rel)),
+					 errdetail_internal("Index tid=(%u,%u) tuple size=%zu lp_len=%u page lsn=%X/%X.",
+										state->targetblock, offset,
+										tupsize, ItemIdGetLength(itemid),
+										(uint32) (state->targetlsn >> 32),
+										(uint32) state->targetlsn),
+					 errhint("This could be a torn page problem")));
+
 		/*
 		 * Don't try to generate scankey using "negative infinity" garbage
-		 * data
+		 * data on internal pages
 		 */
 		if (offset_is_negative_infinity(topaque, offset))
 			continue;
 
 		/* Build insertion scankey for current page offset */
-		itemid = PageGetItemId(state->target, offset);
-		itup = (IndexTuple) PageGetItem(state->target, itemid);
 		skey = _bt_mkscankey(state->rel, itup);
 
+		/* Fingerprint leaf page tuples (those that point to the heap) */
+		if (state->heapallindexed && P_ISLEAF(topaque) && !ItemIdIsDead(itemid))
+			bloom_add_element(state->filter, (unsigned char *) itup, tupsize);
+
 		/*
 		 * * High key check *
 		 *
@@ -680,8 +867,10 @@ bt_target_page_check(BtreeCheckState *state)
 		 * * Last item check *
 		 *
 		 * Check last item against next/right page's first data item's when
-		 * last item on page is reached.  This additional check can detect
-		 * transposed pages.
+		 * last item on page is reached.  This additional check will detect
+		 * transposed pages iff the supposed right sibling page happens to
+		 * belong before target in the key space.  (Otherwise, a subsequent
+		 * heap verification will probably detect the problem.)
 		 *
 		 * This check is similar to the item order check that will have
 		 * already been performed for every other "real" item on target page
@@ -1059,6 +1248,106 @@ bt_downlink_check(BtreeCheckState *state, BlockNumber childblock,
 	pfree(child);
 }
 
+/*
+ * Per-tuple callback from IndexBuildHeapScan, used to determine if index has
+ * all the entries that definitely should have been observed in leaf pages of
+ * the target index (that is, all IndexTuples that were fingerprinted by our
+ * Bloom filter).  All heapallindexed checks occur here.
+ *
+ * The redundancy between an index and the table it indexes provides a good
+ * opportunity to detect corruption, especially corruption within the table.
+ * The high level principle behind the verification performed here is that any
+ * IndexTuple that should be in an index following a fresh CREATE INDEX (based
+ * on the same index definition) should also have been in the original,
+ * existing index, which should have used exactly the same representation
+ *
+ * Since the overall structure of the index has already been verified, the most
+ * likely explanation for error here is a corrupt heap page (could be logical
+ * or physical corruption).  Index corruption may still be detected here,
+ * though.  Only readonly callers will have verified that left links and right
+ * links are in agreement, and so it's possible that a leaf page transposition
+ * within index is actually the source of corruption detected here (for
+ * !readonly callers).  The checks performed only for readonly callers might
+ * more accurately frame the problem as a cross-page invariant issue (this
+ * could even be due to recovery not replaying all WAL records).  The !readonly
+ * ERROR message raised here includes a HINT about retrying with readonly
+ * verification, just in case it's a cross-page invariant issue, though that
+ * isn't particularly likely.
+ *
+ * IndexBuildHeapScan() expects to be able to find the root tuple when a
+ * heap-only tuple (the live tuple at the end of some HOT chain) needs to be
+ * indexed, in order to replace the actual tuple's TID with the root tuple's
+ * TID (which is what we're actually passed back here).  The index build heap
+ * scan code will raise an error when a tuple that claims to be the root of the
+ * heap-only tuple's HOT chain cannot be located.  This catches cases where the
+ * original root item offset/root tuple for a HOT chain indicates (for whatever
+ * reason) that the entire HOT chain is dead, despite the fact that the latest
+ * heap-only tuple should be indexed.  When this happens, sequential scans may
+ * always give correct answers, and all indexes may be considered structurally
+ * consistent (i.e. the nbtree structural checks would not detect corruption).
+ * It may be the case that only index scans give wrong answers, and yet heap or
+ * SLRU corruption is the real culprit.  (While it's true that LP_DEAD bit
+ * setting will probably also leave the index in a corrupt state before too
+ * long, the problem is nonetheless that there is heap corruption.)
+ *
+ * Heap-only tuple handling within IndexBuildHeapScan() works in a way that
+ * helps us to detect index tuples that contain the wrong values (values that
+ * don't match the latest tuple in the HOT chain).  This can happen when there
+ * is no superseding index tuple due to a faulty assessment of HOT safety,
+ * perhaps during the original CREATE INDEX.  Because the latest tuple's
+ * contents are used with the root TID, an error will be raised when a tuple
+ * with the same TID but non-matching attribute values is passed back to us.
+ * Faulty assessment of HOT-safety was behind at least two distinct CREATE
+ * INDEX CONCURRENTLY bugs that made it into stable releases, one of which was
+ * undetected for many years.  In short, the same principle that allows a
+ * REINDEX to repair corruption when there was an (undetected) broken HOT chain
+ * also allows us to detect the corruption in many cases.
+ */
+static void
+bt_tuple_present_callback(Relation index, HeapTuple htup, Datum *values,
+						  bool *isnull, bool tupleIsAlive, void *checkstate)
+{
+	BtreeCheckState *state = (BtreeCheckState *) checkstate;
+	IndexTuple	itup;
+
+	Assert(state->heapallindexed);
+
+	/*
+	 * Generate an index tuple for fingerprinting.
+	 *
+	 * Index tuple formation is assumed to be deterministic, and IndexTuples
+	 * are assumed immutable.  While the LP_DEAD bit is mutable in leaf pages,
+	 * that's ItemId metadata, which was not fingerprinted.  (There will often
+	 * be some dead-to-everyone IndexTuples fingerprinted by the Bloom filter,
+	 * but we only try to detect the absence of needed tuples, so that's okay.)
+	 *
+	 * Note that we rely on deterministic index_form_tuple() TOAST compression.
+	 * If index_form_tuple() was ever enhanced to compress datums out-of-line,
+	 * or otherwise varied when or how compression was applied, our assumption
+	 * would break, leading to false positive reports of corruption.  For now,
+	 * we don't decompress/normalize toasted values as part of fingerprinting.
+	 */
+	itup = index_form_tuple(RelationGetDescr(index), values, isnull);
+	itup->t_tid = htup->t_self;
+
+	/* Probe Bloom filter -- tuple should be present */
+	if (bloom_lacks_element(state->filter, (unsigned char *) itup,
+							IndexTupleSize(itup)))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("heap tuple (%u,%u) from table \"%s\" lacks matching index tuple within index \"%s\"",
+						ItemPointerGetBlockNumber(&(itup->t_tid)),
+						ItemPointerGetOffsetNumber(&(itup->t_tid)),
+						RelationGetRelationName(state->heaprel),
+						RelationGetRelationName(state->rel)),
+				 !state->readonly
+				 ? errhint("Retrying verification using the function bt_index_parent_check() might provide a more specific error.")
+				 : 0));
+
+	state->heaptuplespresent++;
+	pfree(itup);
+}
+
 /*
  * Is particular offset within page (whose special state is passed by caller)
  * the page negative-infinity item?