postgres/src/backend/utils/cache/partcache.c

/*-------------------------------------------------------------------------
 *
 * partcache.c
 *		Support routines for manipulating partition information cached in
 *		relcache
 *
 * Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * IDENTIFICATION
 *		  src/backend/utils/cache/partcache.c
 *
 *-------------------------------------------------------------------------
*/
#include "postgres.h"

#include "access/hash.h"
#include "access/heapam.h"
#include "access/htup_details.h"
#include "access/nbtree.h"
#include "catalog/partition.h"
#include "catalog/pg_inherits.h"
#include "catalog/pg_opclass.h"
#include "catalog/pg_partitioned_table.h"
#include "miscadmin.h"
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#include "optimizer/clauses.h"
#include "optimizer/planner.h"
#include "partitioning/partbounds.h"
#include "utils/builtins.h"
#include "utils/datum.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/partcache.h"
#include "utils/rel.h"
#include "utils/syscache.h"


static List *generate_partition_qual(Relation rel);
static int32 qsort_partition_hbound_cmp(const void *a, const void *b);
static int32 qsort_partition_list_value_cmp(const void *a, const void *b,
							   void *arg);
static int32 qsort_partition_rbound_cmp(const void *a, const void *b,
						   void *arg);


/*
 * RelationBuildPartitionKey
 *		Build and attach to relcache partition key data of relation
 *
 * Partitioning key data is a complex structure; to avoid complicated logic to
 * free individual elements whenever the relcache entry is flushed, we give it
 * its own memory context, child of CacheMemoryContext, which can easily be
 * deleted on its own.  To avoid leaking memory in that context in case of an
 * error partway through this function, the context is initially created as a
 * child of CurTransactionContext and only re-parented to CacheMemoryContext
 * at the end, when no further errors are possible.  Also, we don't make this
 * context the current context except in very brief code sections, out of fear
 * that some of our callees allocate memory on their own which would be leaked
 * permanently.
 */
void
RelationBuildPartitionKey(Relation relation)
{
	Form_pg_partitioned_table form;
	HeapTuple	tuple;
	bool		isnull;
	int			i;
	PartitionKey key;
	AttrNumber *attrs;
	oidvector  *opclass;
	oidvector  *collation;
	ListCell   *partexprs_item;
	Datum		datum;
	MemoryContext partkeycxt,
				oldcxt;
	int16		procnum;

	tuple = SearchSysCache1(PARTRELID,
							ObjectIdGetDatum(RelationGetRelid(relation)));

	/*
	 * The following happens when we have created our pg_class entry but not
	 * the pg_partitioned_table entry yet.
	 */
	if (!HeapTupleIsValid(tuple))
		return;

	partkeycxt = AllocSetContextCreate(CurTransactionContext,
									   "partition key",
									   ALLOCSET_SMALL_SIZES);
	MemoryContextCopyAndSetIdentifier(partkeycxt,
									  RelationGetRelationName(relation));

	key = (PartitionKey) MemoryContextAllocZero(partkeycxt,
												sizeof(PartitionKeyData));

	/* Fixed-length attributes */
	form = (Form_pg_partitioned_table) GETSTRUCT(tuple);
	key->strategy = form->partstrat;
	key->partnatts = form->partnatts;

	/*
	 * We can rely on the first variable-length attribute being mapped to the
	 * relevant field of the catalog's C struct, because all previous
	 * attributes are non-nullable and fixed-length.
	 */
	attrs = form->partattrs.values;

	/* But use the hard way to retrieve further variable-length attributes */
	/* Operator class */
	datum = SysCacheGetAttr(PARTRELID, tuple,
							Anum_pg_partitioned_table_partclass, &isnull);
	Assert(!isnull);
	opclass = (oidvector *) DatumGetPointer(datum);

	/* Collation */
	datum = SysCacheGetAttr(PARTRELID, tuple,
							Anum_pg_partitioned_table_partcollation, &isnull);
	Assert(!isnull);
	collation = (oidvector *) DatumGetPointer(datum);

	/* Expressions */
	datum = SysCacheGetAttr(PARTRELID, tuple,
							Anum_pg_partitioned_table_partexprs, &isnull);
	if (!isnull)
	{
		char	   *exprString;
		Node	   *expr;

		exprString = TextDatumGetCString(datum);
		expr = stringToNode(exprString);
		pfree(exprString);

		/*
		 * Run the expressions through const-simplification since the planner
		 * will be comparing them to similarly-processed qual clause operands,
		 * and may fail to detect valid matches without this step; fix
		 * opfuncids while at it.  We don't need to bother with
		 * canonicalize_qual() though, because partition expressions should be
		 * in canonical form already (ie, no need for OR-merging or constant
		 * elimination).
		 */
		expr = eval_const_expressions(NULL, expr);
		fix_opfuncids(expr);

		oldcxt = MemoryContextSwitchTo(partkeycxt);
		key->partexprs = (List *) copyObject(expr);
		MemoryContextSwitchTo(oldcxt);
	}

	oldcxt = MemoryContextSwitchTo(partkeycxt);
	key->partattrs = (AttrNumber *) palloc0(key->partnatts * sizeof(AttrNumber));
	key->partopfamily = (Oid *) palloc0(key->partnatts * sizeof(Oid));
	key->partopcintype = (Oid *) palloc0(key->partnatts * sizeof(Oid));
	key->partsupfunc = (FmgrInfo *) palloc0(key->partnatts * sizeof(FmgrInfo));

	key->partcollation = (Oid *) palloc0(key->partnatts * sizeof(Oid));

	/* Gather type and collation info as well */
	key->parttypid = (Oid *) palloc0(key->partnatts * sizeof(Oid));
	key->parttypmod = (int32 *) palloc0(key->partnatts * sizeof(int32));
	key->parttyplen = (int16 *) palloc0(key->partnatts * sizeof(int16));
	key->parttypbyval = (bool *) palloc0(key->partnatts * sizeof(bool));
	key->parttypalign = (char *) palloc0(key->partnatts * sizeof(char));
	key->parttypcoll = (Oid *) palloc0(key->partnatts * sizeof(Oid));
	MemoryContextSwitchTo(oldcxt);

	/* determine support function number to search for */
	procnum = (key->strategy == PARTITION_STRATEGY_HASH) ?
		HASHEXTENDED_PROC : BTORDER_PROC;

	/* Copy partattrs and fill other per-attribute info */
	memcpy(key->partattrs, attrs, key->partnatts * sizeof(int16));
	partexprs_item = list_head(key->partexprs);
	for (i = 0; i < key->partnatts; i++)
	{
		AttrNumber	attno = key->partattrs[i];
		HeapTuple	opclasstup;
		Form_pg_opclass opclassform;
		Oid			funcid;

		/* Collect opfamily information */
		opclasstup = SearchSysCache1(CLAOID,
									 ObjectIdGetDatum(opclass->values[i]));
		if (!HeapTupleIsValid(opclasstup))
			elog(ERROR, "cache lookup failed for opclass %u", opclass->values[i]);

		opclassform = (Form_pg_opclass) GETSTRUCT(opclasstup);
		key->partopfamily[i] = opclassform->opcfamily;
		key->partopcintype[i] = opclassform->opcintype;

		/* Get a support function for the specified opfamily and datatypes */
		funcid = get_opfamily_proc(opclassform->opcfamily,
								   opclassform->opcintype,
								   opclassform->opcintype,
								   procnum);
		if (!OidIsValid(funcid))
			ereport(ERROR,
					(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
					 errmsg("operator class \"%s\" of access method %s is missing support function %d for type %s",
							NameStr(opclassform->opcname),
							(key->strategy == PARTITION_STRATEGY_HASH) ?
							"hash" : "btree",
							procnum,
							format_type_be(opclassform->opcintype))));

		fmgr_info_cxt(funcid, &key->partsupfunc[i], partkeycxt);

		/* Collation */
		key->partcollation[i] = collation->values[i];

		/* Collect type information */
		if (attno != 0)
		{
			Form_pg_attribute att = TupleDescAttr(relation->rd_att, attno - 1);

			key->parttypid[i] = att->atttypid;
			key->parttypmod[i] = att->atttypmod;
			key->parttypcoll[i] = att->attcollation;
		}
		else
		{
			if (partexprs_item == NULL)
				elog(ERROR, "wrong number of partition key expressions");

			key->parttypid[i] = exprType(lfirst(partexprs_item));
			key->parttypmod[i] = exprTypmod(lfirst(partexprs_item));
			key->parttypcoll[i] = exprCollation(lfirst(partexprs_item));

			partexprs_item = lnext(partexprs_item);
		}
		get_typlenbyvalalign(key->parttypid[i],
							 &key->parttyplen[i],
							 &key->parttypbyval[i],
							 &key->parttypalign[i]);

		ReleaseSysCache(opclasstup);
	}

	ReleaseSysCache(tuple);

	/*
	 * Success --- reparent our context and make the relcache point to the
	 * newly constructed key
	 */
	MemoryContextSetParent(partkeycxt, CacheMemoryContext);
	relation->rd_partkeycxt = partkeycxt;
	relation->rd_partkey = key;
}

/*
 * RelationBuildPartitionDesc
 *		Form rel's partition descriptor
 *
 * Not flushed from the cache by RelationClearRelation() unless changed because
 * of addition or removal of partition.
 */
void
RelationBuildPartitionDesc(Relation rel)
{
	List	   *inhoids,
			   *partoids;
	Oid		   *oids = NULL;
	List	   *boundspecs = NIL;
	ListCell   *cell;
	int			i,
				nparts;
	PartitionKey key = RelationGetPartitionKey(rel);
	PartitionDesc result;
	MemoryContext oldcxt;

	int			ndatums = 0;
	int			default_index = -1;

	/* Hash partitioning specific */
	PartitionHashBound **hbounds = NULL;

	/* List partitioning specific */
	PartitionListValue **all_values = NULL;
	int			null_index = -1;

	/* Range partitioning specific */
	PartitionRangeBound **rbounds = NULL;

	/* Get partition oids from pg_inherits */
	inhoids = find_inheritance_children(RelationGetRelid(rel), NoLock);

	/* Collect bound spec nodes in a list */
	i = 0;
	partoids = NIL;
	foreach(cell, inhoids)
	{
		Oid			inhrelid = lfirst_oid(cell);
		HeapTuple	tuple;
		Datum		datum;
		bool		isnull;
		Node	   *boundspec;

		tuple = SearchSysCache1(RELOID, inhrelid);
		if (!HeapTupleIsValid(tuple))
			elog(ERROR, "cache lookup failed for relation %u", inhrelid);

		/*
		 * It is possible that the pg_class tuple of a partition has not been
		 * updated yet to set its relpartbound field.  The only case where
		 * this happens is when we open the parent relation to check using its
		 * partition descriptor that a new partition's bound does not overlap
		 * some existing partition.
		 */
		if (!((Form_pg_class) GETSTRUCT(tuple))->relispartition)
		{
			ReleaseSysCache(tuple);
			continue;
		}

		datum = SysCacheGetAttr(RELOID, tuple,
								Anum_pg_class_relpartbound,
								&isnull);
		Assert(!isnull);
		boundspec = (Node *) stringToNode(TextDatumGetCString(datum));

		/*
		 * Sanity check: If the PartitionBoundSpec says this is the default
		 * partition, its OID should correspond to whatever's stored in
		 * pg_partitioned_table.partdefid; if not, the catalog is corrupt.
		 */
		if (castNode(PartitionBoundSpec, boundspec)->is_default)
		{
			Oid			partdefid;

			partdefid = get_default_partition_oid(RelationGetRelid(rel));
			if (partdefid != inhrelid)
				elog(ERROR, "expected partdefid %u, but got %u",
					 inhrelid, partdefid);
		}

		boundspecs = lappend(boundspecs, boundspec);
		partoids = lappend_oid(partoids, inhrelid);
		ReleaseSysCache(tuple);
	}

	nparts = list_length(partoids);

	if (nparts > 0)
	{
		oids = (Oid *) palloc(nparts * sizeof(Oid));
		i = 0;
		foreach(cell, partoids)
			oids[i++] = lfirst_oid(cell);

		/* Convert from node to the internal representation */
		if (key->strategy == PARTITION_STRATEGY_HASH)
		{
			ndatums = nparts;
			hbounds = (PartitionHashBound **)
				palloc(nparts * sizeof(PartitionHashBound *));

			i = 0;
			foreach(cell, boundspecs)
			{
				PartitionBoundSpec *spec = castNode(PartitionBoundSpec,
													lfirst(cell));

				if (spec->strategy != PARTITION_STRATEGY_HASH)
					elog(ERROR, "invalid strategy in partition bound spec");

				hbounds[i] = (PartitionHashBound *)
					palloc(sizeof(PartitionHashBound));

				hbounds[i]->modulus = spec->modulus;
				hbounds[i]->remainder = spec->remainder;
				hbounds[i]->index = i;
				i++;
			}

			/* Sort all the bounds in ascending order */
			qsort(hbounds, nparts, sizeof(PartitionHashBound *),
				  qsort_partition_hbound_cmp);
		}
		else if (key->strategy == PARTITION_STRATEGY_LIST)
		{
			List	   *non_null_values = NIL;

			/*
			 * Create a unified list of non-null values across all partitions.
			 */
			i = 0;
			null_index = -1;
			foreach(cell, boundspecs)
			{
				PartitionBoundSpec *spec = castNode(PartitionBoundSpec,
													lfirst(cell));
				ListCell   *c;

				if (spec->strategy != PARTITION_STRATEGY_LIST)
					elog(ERROR, "invalid strategy in partition bound spec");

				/*
				 * Note the index of the partition bound spec for the default
				 * partition. There's no datum to add to the list of non-null
				 * datums for this partition.
				 */
				if (spec->is_default)
				{
					default_index = i;
					i++;
					continue;
				}

				foreach(c, spec->listdatums)
				{
					Const	   *val = castNode(Const, lfirst(c));
					PartitionListValue *list_value = NULL;

					if (!val->constisnull)
					{
						list_value = (PartitionListValue *)
							palloc0(sizeof(PartitionListValue));
						list_value->index = i;
						list_value->value = val->constvalue;
					}
					else
					{
						/*
						 * Never put a null into the values array, flag
						 * instead for the code further down below where we
						 * construct the actual relcache struct.
						 */
						if (null_index != -1)
							elog(ERROR, "found null more than once");
						null_index = i;
					}

					if (list_value)
						non_null_values = lappend(non_null_values,
												  list_value);
				}

				i++;
			}

			ndatums = list_length(non_null_values);

			/*
			 * Collect all list values in one array. Alongside the value, we
			 * also save the index of partition the value comes from.
			 */
			all_values = (PartitionListValue **) palloc(ndatums *
														sizeof(PartitionListValue *));
			i = 0;
			foreach(cell, non_null_values)
			{
				PartitionListValue *src = lfirst(cell);

				all_values[i] = (PartitionListValue *)
					palloc(sizeof(PartitionListValue));
				all_values[i]->value = src->value;
				all_values[i]->index = src->index;
				i++;
			}

			qsort_arg(all_values, ndatums, sizeof(PartitionListValue *),
					  qsort_partition_list_value_cmp, (void *) key);
		}
		else if (key->strategy == PARTITION_STRATEGY_RANGE)
		{
			int			k;
			PartitionRangeBound **all_bounds,
					   *prev;

			all_bounds = (PartitionRangeBound **) palloc0(2 * nparts *
														  sizeof(PartitionRangeBound *));

			/*
			 * Create a unified list of range bounds across all the
			 * partitions.
			 */
			i = ndatums = 0;
			foreach(cell, boundspecs)
			{
				PartitionBoundSpec *spec = castNode(PartitionBoundSpec,
													lfirst(cell));
				PartitionRangeBound *lower,
						   *upper;

				if (spec->strategy != PARTITION_STRATEGY_RANGE)
					elog(ERROR, "invalid strategy in partition bound spec");

				/*
				 * Note the index of the partition bound spec for the default
				 * partition. There's no datum to add to the allbounds array
				 * for this partition.
				 */
				if (spec->is_default)
				{
					default_index = i++;
					continue;
				}

				lower = make_one_range_bound(key, i, spec->lowerdatums,
											 true);
				upper = make_one_range_bound(key, i, spec->upperdatums,
											 false);
				all_bounds[ndatums++] = lower;
				all_bounds[ndatums++] = upper;
				i++;
			}

			Assert(ndatums == nparts * 2 ||
				   (default_index != -1 && ndatums == (nparts - 1) * 2));

			/* Sort all the bounds in ascending order */
			qsort_arg(all_bounds, ndatums,
					  sizeof(PartitionRangeBound *),
					  qsort_partition_rbound_cmp,
					  (void *) key);

			/* Save distinct bounds from all_bounds into rbounds. */
			rbounds = (PartitionRangeBound **)
				palloc(ndatums * sizeof(PartitionRangeBound *));
			k = 0;
			prev = NULL;
			for (i = 0; i < ndatums; i++)
			{
				PartitionRangeBound *cur = all_bounds[i];
				bool		is_distinct = false;
				int			j;

				/* Is the current bound distinct from the previous one? */
				for (j = 0; j < key->partnatts; j++)
				{
					Datum		cmpval;

					if (prev == NULL || cur->kind[j] != prev->kind[j])
					{
						is_distinct = true;
						break;
					}

					/*
					 * If the bounds are both MINVALUE or MAXVALUE, stop now
					 * and treat them as equal, since any values after this
					 * point must be ignored.
					 */
					if (cur->kind[j] != PARTITION_RANGE_DATUM_VALUE)
						break;

					cmpval = FunctionCall2Coll(&key->partsupfunc[j],
											   key->partcollation[j],
											   cur->datums[j],
											   prev->datums[j]);
					if (DatumGetInt32(cmpval) != 0)
					{
						is_distinct = true;
						break;
					}
				}

				/*
				 * Only if the bound is distinct save it into a temporary
				 * array i.e. rbounds which is later copied into boundinfo
				 * datums array.
				 */
				if (is_distinct)
					rbounds[k++] = all_bounds[i];

				prev = cur;
			}

			/* Update ndatums to hold the count of distinct datums. */
			ndatums = k;
		}
		else
			elog(ERROR, "unexpected partition strategy: %d",
				 (int) key->strategy);
	}

	/* Now build the actual relcache partition descriptor */
	rel->rd_pdcxt = AllocSetContextCreate(CacheMemoryContext,
										  "partition descriptor",
										  ALLOCSET_DEFAULT_SIZES);
	MemoryContextCopyAndSetIdentifier(rel->rd_pdcxt, RelationGetRelationName(rel));

	oldcxt = MemoryContextSwitchTo(rel->rd_pdcxt);

	result = (PartitionDescData *) palloc0(sizeof(PartitionDescData));
	result->nparts = nparts;
	if (nparts > 0)
	{
		PartitionBoundInfo boundinfo;
		int		   *mapping;
		int			next_index = 0;

		result->oids = (Oid *) palloc0(nparts * sizeof(Oid));

		boundinfo = (PartitionBoundInfoData *)
			palloc0(sizeof(PartitionBoundInfoData));
		boundinfo->strategy = key->strategy;
		boundinfo->default_index = -1;
		boundinfo->ndatums = ndatums;
		boundinfo->null_index = -1;
		boundinfo->datums = (Datum **) palloc0(ndatums * sizeof(Datum *));

		/* Initialize mapping array with invalid values */
		mapping = (int *) palloc(sizeof(int) * nparts);
		for (i = 0; i < nparts; i++)
			mapping[i] = -1;

		switch (key->strategy)
		{
			case PARTITION_STRATEGY_HASH:
				{
					/* Modulus are stored in ascending order */
					int			greatest_modulus = hbounds[ndatums - 1]->modulus;

					boundinfo->indexes = (int *) palloc(greatest_modulus *
														sizeof(int));

					for (i = 0; i < greatest_modulus; i++)
						boundinfo->indexes[i] = -1;

					for (i = 0; i < nparts; i++)
					{
						int			modulus = hbounds[i]->modulus;
						int			remainder = hbounds[i]->remainder;

						boundinfo->datums[i] = (Datum *) palloc(2 *
																sizeof(Datum));
						boundinfo->datums[i][0] = Int32GetDatum(modulus);
						boundinfo->datums[i][1] = Int32GetDatum(remainder);

						while (remainder < greatest_modulus)
						{
							/* overlap? */
							Assert(boundinfo->indexes[remainder] == -1);
							boundinfo->indexes[remainder] = i;
							remainder += modulus;
						}

						mapping[hbounds[i]->index] = i;
						pfree(hbounds[i]);
					}
					pfree(hbounds);
					break;
				}

			case PARTITION_STRATEGY_LIST:
				{
					boundinfo->indexes = (int *) palloc(ndatums * sizeof(int));

					/*
					 * Copy values.  Indexes of individual values are mapped
					 * to canonical values so that they match for any two list
					 * partitioned tables with same number of partitions and
					 * same lists per partition.  One way to canonicalize is
					 * to assign the index in all_values[] of the smallest
					 * value of each partition, as the index of all of the
					 * partition's values.
					 */
					for (i = 0; i < ndatums; i++)
					{
						boundinfo->datums[i] = (Datum *) palloc(sizeof(Datum));
						boundinfo->datums[i][0] = datumCopy(all_values[i]->value,
															key->parttypbyval[0],
															key->parttyplen[0]);

						/* If the old index has no mapping, assign one */
						if (mapping[all_values[i]->index] == -1)
							mapping[all_values[i]->index] = next_index++;

						boundinfo->indexes[i] = mapping[all_values[i]->index];
					}

					/*
					 * If null-accepting partition has no mapped index yet,
					 * assign one.  This could happen if such partition
					 * accepts only null and hence not covered in the above
					 * loop which only handled non-null values.
					 */
					if (null_index != -1)
					{
						Assert(null_index >= 0);
						if (mapping[null_index] == -1)
							mapping[null_index] = next_index++;
						boundinfo->null_index = mapping[null_index];
					}

					/* Assign mapped index for the default partition. */
					if (default_index != -1)
					{
						/*
						 * The default partition accepts any value not
						 * specified in the lists of other partitions, hence
						 * it should not get mapped index while assigning
						 * those for non-null datums.
						 */
						Assert(default_index >= 0 &&
							   mapping[default_index] == -1);
						mapping[default_index] = next_index++;
						boundinfo->default_index = mapping[default_index];
					}

					/* All partition must now have a valid mapping */
					Assert(next_index == nparts);
					break;
				}

			case PARTITION_STRATEGY_RANGE:
				{
					boundinfo->kind = (PartitionRangeDatumKind **)
						palloc(ndatums *
							   sizeof(PartitionRangeDatumKind *));
					boundinfo->indexes = (int *) palloc((ndatums + 1) *
														sizeof(int));

					for (i = 0; i < ndatums; i++)
					{
						int			j;

						boundinfo->datums[i] = (Datum *) palloc(key->partnatts *
																sizeof(Datum));
						boundinfo->kind[i] = (PartitionRangeDatumKind *)
							palloc(key->partnatts *
								   sizeof(PartitionRangeDatumKind));
						for (j = 0; j < key->partnatts; j++)
						{
							if (rbounds[i]->kind[j] == PARTITION_RANGE_DATUM_VALUE)
								boundinfo->datums[i][j] =
									datumCopy(rbounds[i]->datums[j],
											  key->parttypbyval[j],
											  key->parttyplen[j]);
							boundinfo->kind[i][j] = rbounds[i]->kind[j];
						}

						/*
						 * There is no mapping for invalid indexes.
						 *
						 * Any lower bounds in the rbounds array have invalid
						 * indexes assigned, because the values between the
						 * previous bound (if there is one) and this (lower)
						 * bound are not part of the range of any existing
						 * partition.
						 */
						if (rbounds[i]->lower)
							boundinfo->indexes[i] = -1;
						else
						{
							int			orig_index = rbounds[i]->index;

							/* If the old index has no mapping, assign one */
							if (mapping[orig_index] == -1)
								mapping[orig_index] = next_index++;

							boundinfo->indexes[i] = mapping[orig_index];
						}
					}

					/* Assign mapped index for the default partition. */
					if (default_index != -1)
					{
						Assert(default_index >= 0 && mapping[default_index] == -1);
						mapping[default_index] = next_index++;
						boundinfo->default_index = mapping[default_index];
					}
					boundinfo->indexes[i] = -1;
					break;
				}

			default:
				elog(ERROR, "unexpected partition strategy: %d",
					 (int) key->strategy);
		}

		result->boundinfo = boundinfo;

		/*
		 * Now assign OIDs from the original array into mapped indexes of the
		 * result array.  Order of OIDs in the former is defined by the
		 * catalog scan that retrieved them, whereas that in the latter is
		 * defined by canonicalized representation of the partition bounds.
		 */
		for (i = 0; i < nparts; i++)
			result->oids[mapping[i]] = oids[i];
		pfree(mapping);
	}

	MemoryContextSwitchTo(oldcxt);
	rel->rd_partdesc = result;
}

/*
 * RelationGetPartitionQual
 *
 * Returns a list of partition quals
 */
List *
RelationGetPartitionQual(Relation rel)
{
	/* Quick exit */
	if (!rel->rd_rel->relispartition)
		return NIL;

	return generate_partition_qual(rel);
}

/*
 * get_partition_qual_relid
 *
 * Returns an expression tree describing the passed-in relation's partition
 * constraint. If there is no partition constraint returns NULL; this can
 * happen if the default partition is the only partition.
 */
Expr *
get_partition_qual_relid(Oid relid)
{
	Relation	rel = heap_open(relid, AccessShareLock);
	Expr	   *result = NULL;
	List	   *and_args;

	/* Do the work only if this relation is a partition. */
	if (rel->rd_rel->relispartition)
	{
		and_args = generate_partition_qual(rel);

		if (and_args == NIL)
			result = NULL;
		else if (list_length(and_args) > 1)
			result = makeBoolExpr(AND_EXPR, and_args, -1);
		else
			result = linitial(and_args);
	}

	/* Keep the lock. */
	heap_close(rel, NoLock);

	return result;
}

/*
 * generate_partition_qual
 *
 * Generate partition predicate from rel's partition bound expression. The
 * function returns a NIL list if there is no predicate.
 *
 * Result expression tree is stored CacheMemoryContext to ensure it survives
 * as long as the relcache entry. But we should be running in a less long-lived
 * working context. To avoid leaking cache memory if this routine fails partway
 * through, we build in working memory and then copy the completed structure
 * into cache memory.
 */
static List *
generate_partition_qual(Relation rel)
{
	HeapTuple	tuple;
	MemoryContext oldcxt;
	Datum		boundDatum;
	bool		isnull;
	PartitionBoundSpec *bound;
	List	   *my_qual = NIL,
			   *result = NIL;
	Relation	parent;
	bool		found_whole_row;

	/* Guard against stack overflow due to overly deep partition tree */
	check_stack_depth();

	/* Quick copy */
	if (rel->rd_partcheck != NIL)
		return copyObject(rel->rd_partcheck);

	/* Grab at least an AccessShareLock on the parent table */
	parent = heap_open(get_partition_parent(RelationGetRelid(rel)),
					   AccessShareLock);

	/* Get pg_class.relpartbound */
	tuple = SearchSysCache1(RELOID, RelationGetRelid(rel));
	if (!HeapTupleIsValid(tuple))
		elog(ERROR, "cache lookup failed for relation %u",
			 RelationGetRelid(rel));

	boundDatum = SysCacheGetAttr(RELOID, tuple,
								 Anum_pg_class_relpartbound,
								 &isnull);
	if (isnull)					/* should not happen */
		elog(ERROR, "relation \"%s\" has relpartbound = null",
			 RelationGetRelationName(rel));
	bound = castNode(PartitionBoundSpec,
					 stringToNode(TextDatumGetCString(boundDatum)));
	ReleaseSysCache(tuple);

	my_qual = get_qual_from_partbound(rel, parent, bound);

	/* Add the parent's quals to the list (if any) */
	if (parent->rd_rel->relispartition)
		result = list_concat(generate_partition_qual(parent), my_qual);
	else
		result = my_qual;

	/*
	 * Change Vars to have partition's attnos instead of the parent's. We do
	 * this after we concatenate the parent's quals, because we want every Var
	 * in it to bear this relation's attnos. It's safe to assume varno = 1
	 * here.
	 */
	result = map_partition_varattnos(result, 1, rel, parent,
									 &found_whole_row);
	/* There can never be a whole-row reference here */
	if (found_whole_row)
		elog(ERROR, "unexpected whole-row reference found in partition key");

	/* Save a copy in the relcache */
	oldcxt = MemoryContextSwitchTo(CacheMemoryContext);
	rel->rd_partcheck = copyObject(result);
	MemoryContextSwitchTo(oldcxt);

	/* Keep the parent locked until commit */
	heap_close(parent, NoLock);

	return result;
}

/*
 * qsort_partition_hbound_cmp
 *
 * We sort hash bounds by modulus, then by remainder.
 */
static int32
qsort_partition_hbound_cmp(const void *a, const void *b)
{
	PartitionHashBound *h1 = (*(PartitionHashBound *const *) a);
	PartitionHashBound *h2 = (*(PartitionHashBound *const *) b);

	return partition_hbound_cmp(h1->modulus, h1->remainder,
								h2->modulus, h2->remainder);
}

/*
 * qsort_partition_list_value_cmp
 *
 * Compare two list partition bound datums
 */
static int32
qsort_partition_list_value_cmp(const void *a, const void *b, void *arg)
{
	Datum		val1 = (*(const PartitionListValue **) a)->value,
				val2 = (*(const PartitionListValue **) b)->value;
	PartitionKey key = (PartitionKey) arg;

	return DatumGetInt32(FunctionCall2Coll(&key->partsupfunc[0],
										   key->partcollation[0],
										   val1, val2));
}

/* Used when sorting range bounds across all range partitions */
static int32
qsort_partition_rbound_cmp(const void *a, const void *b, void *arg)
{
	PartitionRangeBound *b1 = (*(PartitionRangeBound *const *) a);
	PartitionRangeBound *b2 = (*(PartitionRangeBound *const *) b);
	PartitionKey key = (PartitionKey) arg;

	return partition_rbound_cmp(key->partnatts, key->partsupfunc,
								key->partcollation, b1->datums, b1->kind,
								b1->lower, b2);
}