Fix dynahash.c to suppress hash bucket splits while a hash_seq_search() scan

is in progress on the same hashtable.  This seems the least invasive way to
fix the recently-recognized problem that a split could cause the scan to
visit entries twice or (with much lower probability) miss them entirely.
The only field-reported problem caused by this is the "failed to re-find
shared lock object" PANIC in COMMIT PREPARED reported by Michel Dorochevsky,
which was caused by multiply visited entries.  However, it seems certain
that mdsync() is vulnerable to missing required fsync's due to missed
entries, and I am fearful that RelationCacheInitializePhase2() might be at
risk as well.  Because of that and the generalized hazard presented by this
bug, back-patch all the supported branches.

Along the way, fix pg_prepared_statement() and pg_cursor() to not assume
that the hashtables they are examining will stay static between calls.
This is risky regardless of the newly noted dynahash problem, because
hash_seq_search() has never promised to cope with deletion of table entries
other than the just-returned one.  There may be no bug here because the only
supported way to call these functions is via ExecMakeTableFunctionResult()
which will cycle them to completion before doing anything very interesting,
but it seems best to get rid of the assumption.  This affects 8.2 and HEAD
only, since those functions weren't there earlier.

2 files changed, 21 insertions, 3 deletions

diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 2c53f12ce5a..f873f93cc52 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/nodes/execnodes.h,v 1.139.2.3 2005/11/28 23:46:25 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/nodes/execnodes.h,v 1.139.2.4 2007/04/26 23:25:09 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -382,8 +382,20 @@ typedef struct TupleHashTableData
 
 typedef HASH_SEQ_STATUS TupleHashIterator;
 
-#define ResetTupleHashIterator(htable, iter) \
+/*
+ * Use InitTupleHashIterator/TermTupleHashIterator for a read/write scan.
+ * Use ResetTupleHashIterator if the table can be frozen (in this case no
+ * explicit scan termination is needed).
+ */
+#define InitTupleHashIterator(htable, iter) \
 	hash_seq_init(iter, (htable)->hashtab)
+#define TermTupleHashIterator(iter) \
+	hash_seq_term(iter)
+#define ResetTupleHashIterator(htable, iter) \
+	do { \
+		hash_freeze((htable)->hashtab); \
+		hash_seq_init(iter, (htable)->hashtab); \
+	} while (0)
 #define ScanTupleHashTable(iter) \
 	((TupleHashEntry) hash_seq_search(iter))
 
diff --git a/src/include/utils/hsearch.h b/src/include/utils/hsearch.h
index 24b43e892c6..cdc70a77d82 100644
--- a/src/include/utils/hsearch.h
+++ b/src/include/utils/hsearch.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/utils/hsearch.h,v 1.41.2.1 2006/06/25 18:29:56 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/utils/hsearch.h,v 1.41.2.2 2007/04/26 23:25:09 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -119,6 +119,8 @@ typedef struct HTAB
 	MemoryContext hcxt;			/* memory context if default allocator used */
 	char	   *tabname;		/* table name (for error messages) */
 	bool		isshared;		/* true if table is in shared memory */
+	/* freezing a shared table isn't allowed, so we can keep state here */
+	bool		frozen;			/* true = no more inserts allowed */
 } HTAB;
 
 /* Parameter data structure for hash_create */
@@ -185,8 +187,12 @@ extern void *hash_search(HTAB *hashp, const void *keyPtr, HASHACTION action,
 			bool *foundPtr);
 extern void hash_seq_init(HASH_SEQ_STATUS *status, HTAB *hashp);
 extern void *hash_seq_search(HASH_SEQ_STATUS *status);
+extern void hash_seq_term(HASH_SEQ_STATUS *status);
+extern void hash_freeze(HTAB *hashp);
 extern Size hash_estimate_size(long num_entries, Size entrysize);
 extern long hash_select_dirsize(long num_entries);
+extern void AtEOXact_HashTables(bool isCommit);
+extern void AtEOSubXact_HashTables(bool isCommit, int nestDepth);
 
 /*
  * prototypes for functions in hashfn.c