Clean up assorted failures under clang's -fsanitize=undefined checks.

Most of these are cases where we could call memcpy() or other libc
functions with a NULL pointer and a zero count, which is forbidden
by POSIX even though every production version of libc allows it.
We've fixed such things before in a piecemeal way, but apparently
never made an effort to try to get them all.  I don't claim that
this patch does so either, but it gets every failure I observe in
check-world, using clang 12.0.1 on current RHEL8.

numeric.c has a different issue that the sanitizer doesn't like:
"ln(-1.0)" will compute log10(0) and then try to assign the
resulting -Inf to an integer variable.  We don't actually use the
result in such a case, so there's no live bug.

Back-patch to all supported branches, with the idea that we might
start running a buildfarm member that tests this case.  This includes
back-patching c1132aae3 (Check the size in COPY_POINTER_FIELD),
which previously silenced some of these issues in copyfuncs.c.

Discussion: https://postgr.es/m/CALNJ-vT9r0DSsAOw9OXVJFxLENoVS_68kJ5x0p44atoYH+H4dg@mail.gmail.com

10 files changed, 52 insertions, 48 deletions

diff --git a/contrib/pgcrypto/px.c b/contrib/pgcrypto/px.c
index 4205e9c3eff..2099ce2a7a5 100644
--- a/contrib/pgcrypto/px.c
+++ b/contrib/pgcrypto/px.c
@@ -200,7 +200,7 @@ combo_init(PX_Combo *cx, const uint8 *key, unsigned klen,
 		ivbuf = palloc0(ivs);
 		if (ivlen > ivs)
 			memcpy(ivbuf, iv, ivs);
-		else
+		else if (ivlen > 0)
 			memcpy(ivbuf, iv, ivlen);
 	}
 
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index 9e258f918e5..763dc07361e 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -328,7 +328,7 @@ initscan(HeapScanDesc scan, ScanKey key, bool keep_startblock)
 	/*
 	 * copy the scan key, if appropriate
 	 */
-	if (key != NULL)
+	if (key != NULL && scan->rs_base.rs_nkeys > 0)
 		memcpy(scan->rs_base.rs_key, key, scan->rs_base.rs_nkeys * sizeof(ScanKeyData));
 
 	/*
diff --git a/src/backend/access/heap/heapam_visibility.c b/src/backend/access/heap/heapam_visibility.c
index d3c57cd16a8..20d82cad4b6 100644
--- a/src/backend/access/heap/heapam_visibility.c
+++ b/src/backend/access/heap/heapam_visibility.c
@@ -1564,8 +1564,8 @@ HeapTupleHeaderIsOnlyLocked(HeapTupleHeader tuple)
 static bool
 TransactionIdInArray(TransactionId xid, TransactionId *xip, Size num)
 {
-	return bsearch(&xid, xip, num,
-				   sizeof(TransactionId), xidComparator) != NULL;
+	return num > 0 &&
+		bsearch(&xid, xip, num, sizeof(TransactionId), xidComparator) != NULL;
 }
 
 /*
diff --git a/src/backend/access/transam/clog.c b/src/backend/access/transam/clog.c
index 3ea16a270a8..8575f1cb8e6 100644
--- a/src/backend/access/transam/clog.c
+++ b/src/backend/access/transam/clog.c
@@ -297,8 +297,9 @@ TransactionIdSetPageStatus(TransactionId xid, int nsubxids,
 	if (all_xact_same_page && xid == MyProc->xid &&
 		nsubxids <= THRESHOLD_SUBTRANS_CLOG_OPT &&
 		nsubxids == MyProc->subxidStatus.count &&
-		memcmp(subxids, MyProc->subxids.xids,
-			   nsubxids * sizeof(TransactionId)) == 0)
+		(nsubxids == 0 ||
+		 memcmp(subxids, MyProc->subxids.xids,
+				nsubxids * sizeof(TransactionId)) == 0))
 	{
 		/*
 		 * If we can immediately acquire XactSLRULock, we update the status of
diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index ca6f6d57d36..514044f3db7 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -5305,8 +5305,9 @@ SerializeTransactionState(Size maxsize, char *start_address)
 	{
 		if (FullTransactionIdIsValid(s->fullTransactionId))
 			workspace[i++] = XidFromFullTransactionId(s->fullTransactionId);
-		memcpy(&workspace[i], s->childXids,
-			   s->nChildXids * sizeof(TransactionId));
+		if (s->nChildXids > 0)
+			memcpy(&workspace[i], s->childXids,
+				   s->nChildXids * sizeof(TransactionId));
 		i += s->nChildXids;
 	}
 	Assert(i == nxids);
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index f0fa2e23375..a106a2cdf18 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -57,8 +57,11 @@
 #define COPY_POINTER_FIELD(fldname, sz) \
 	do { \
 		Size	_size = (sz); \
-		newnode->fldname = palloc(_size); \
-		memcpy(newnode->fldname, from->fldname, _size); \
+		if (_size > 0) \
+		{ \
+			newnode->fldname = palloc(_size); \
+			memcpy(newnode->fldname, from->fldname, _size); \
+		} \
 	} while (0)
 
 /* Copy a parse location field (for Copy, this is same as scalar case) */
@@ -296,12 +299,9 @@ _copyRecursiveUnion(const RecursiveUnion *from)
 	 */
 	COPY_SCALAR_FIELD(wtParam);
 	COPY_SCALAR_FIELD(numCols);
-	if (from->numCols > 0)
-	{
-		COPY_POINTER_FIELD(dupColIdx, from->numCols * sizeof(AttrNumber));
-		COPY_POINTER_FIELD(dupOperators, from->numCols * sizeof(Oid));
-		COPY_POINTER_FIELD(dupCollations, from->numCols * sizeof(Oid));
-	}
+	COPY_POINTER_FIELD(dupColIdx, from->numCols * sizeof(AttrNumber));
+	COPY_POINTER_FIELD(dupOperators, from->numCols * sizeof(Oid));
+	COPY_POINTER_FIELD(dupCollations, from->numCols * sizeof(Oid));
 	COPY_SCALAR_FIELD(numGroups);
 
 	return newnode;
@@ -897,13 +897,10 @@ _copyMergeJoin(const MergeJoin *from)
 	COPY_SCALAR_FIELD(skip_mark_restore);
 	COPY_NODE_FIELD(mergeclauses);
 	numCols = list_length(from->mergeclauses);
-	if (numCols > 0)
-	{
-		COPY_POINTER_FIELD(mergeFamilies, numCols * sizeof(Oid));
-		COPY_POINTER_FIELD(mergeCollations, numCols * sizeof(Oid));
-		COPY_POINTER_FIELD(mergeStrategies, numCols * sizeof(int));
-		COPY_POINTER_FIELD(mergeNullsFirst, numCols * sizeof(bool));
-	}
+	COPY_POINTER_FIELD(mergeFamilies, numCols * sizeof(Oid));
+	COPY_POINTER_FIELD(mergeCollations, numCols * sizeof(Oid));
+	COPY_POINTER_FIELD(mergeStrategies, numCols * sizeof(int));
+	COPY_POINTER_FIELD(mergeNullsFirst, numCols * sizeof(bool));
 
 	return newnode;
 }
@@ -1067,12 +1064,9 @@ _copyAgg(const Agg *from)
 	COPY_SCALAR_FIELD(aggstrategy);
 	COPY_SCALAR_FIELD(aggsplit);
 	COPY_SCALAR_FIELD(numCols);
-	if (from->numCols > 0)
-	{
-		COPY_POINTER_FIELD(grpColIdx, from->numCols * sizeof(AttrNumber));
-		COPY_POINTER_FIELD(grpOperators, from->numCols * sizeof(Oid));
-		COPY_POINTER_FIELD(grpCollations, from->numCols * sizeof(Oid));
-	}
+	COPY_POINTER_FIELD(grpColIdx, from->numCols * sizeof(AttrNumber));
+	COPY_POINTER_FIELD(grpOperators, from->numCols * sizeof(Oid));
+	COPY_POINTER_FIELD(grpCollations, from->numCols * sizeof(Oid));
 	COPY_SCALAR_FIELD(numGroups);
 	COPY_SCALAR_FIELD(transitionSpace);
 	COPY_BITMAPSET_FIELD(aggParams);
@@ -1094,19 +1088,13 @@ _copyWindowAgg(const WindowAgg *from)
 
 	COPY_SCALAR_FIELD(winref);
 	COPY_SCALAR_FIELD(partNumCols);
-	if (from->partNumCols > 0)
-	{
-		COPY_POINTER_FIELD(partColIdx, from->partNumCols * sizeof(AttrNumber));
-		COPY_POINTER_FIELD(partOperators, from->partNumCols * sizeof(Oid));
-		COPY_POINTER_FIELD(partCollations, from->partNumCols * sizeof(Oid));
-	}
+	COPY_POINTER_FIELD(partColIdx, from->partNumCols * sizeof(AttrNumber));
+	COPY_POINTER_FIELD(partOperators, from->partNumCols * sizeof(Oid));
+	COPY_POINTER_FIELD(partCollations, from->partNumCols * sizeof(Oid));
 	COPY_SCALAR_FIELD(ordNumCols);
-	if (from->ordNumCols > 0)
-	{
-		COPY_POINTER_FIELD(ordColIdx, from->ordNumCols * sizeof(AttrNumber));
-		COPY_POINTER_FIELD(ordOperators, from->ordNumCols * sizeof(Oid));
-		COPY_POINTER_FIELD(ordCollations, from->ordNumCols * sizeof(Oid));
-	}
+	COPY_POINTER_FIELD(ordColIdx, from->ordNumCols * sizeof(AttrNumber));
+	COPY_POINTER_FIELD(ordOperators, from->ordNumCols * sizeof(Oid));
+	COPY_POINTER_FIELD(ordCollations, from->ordNumCols * sizeof(Oid));
 	COPY_SCALAR_FIELD(frameOptions);
 	COPY_NODE_FIELD(startOffset);
 	COPY_NODE_FIELD(endOffset);
diff --git a/src/backend/storage/ipc/shm_mq.c b/src/backend/storage/ipc/shm_mq.c
index 8a46962f939..3240af4872a 100644
--- a/src/backend/storage/ipc/shm_mq.c
+++ b/src/backend/storage/ipc/shm_mq.c
@@ -748,8 +748,11 @@ shm_mq_receive(shm_mq_handle *mqh, Size *nbytesp, void **datap, bool nowait)
 
 		/* Copy as much as we can. */
 		Assert(mqh->mqh_partial_bytes + rb <= nbytes);
-		memcpy(&mqh->mqh_buffer[mqh->mqh_partial_bytes], rawdata, rb);
-		mqh->mqh_partial_bytes += rb;
+		if (rb > 0)
+		{
+			memcpy(&mqh->mqh_buffer[mqh->mqh_partial_bytes], rawdata, rb);
+			mqh->mqh_partial_bytes += rb;
+		}
 
 		/*
 		 * Update count of bytes that can be consumed, accounting for
diff --git a/src/backend/utils/adt/numeric.c b/src/backend/utils/adt/numeric.c
index 4ca13f4f477..e78e0b92479 100644
--- a/src/backend/utils/adt/numeric.c
+++ b/src/backend/utils/adt/numeric.c
@@ -9868,12 +9868,20 @@ exp_var(const NumericVar *arg, NumericVar *result, int rscale)
  *
  * Essentially, we're approximating log10(abs(ln(var))).  This is used to
  * determine the appropriate rscale when computing natural logarithms.
+ *
+ * Note: many callers call this before range-checking the input.  Therefore,
+ * we must be robust against values that are invalid to apply ln() to.
+ * We don't wish to throw an error here, so just return zero in such cases.
  */
 static int
 estimate_ln_dweight(const NumericVar *var)
 {
 	int			ln_dweight;
 
+	/* Caller should fail on ln(negative), but for the moment return zero */
+	if (var->sign != NUMERIC_POS)
+		return 0;
+
 	if (cmp_var(var, &const_zero_point_nine) >= 0 &&
 		cmp_var(var, &const_one_point_one) <= 0)
 	{
diff --git a/src/backend/utils/time/snapmgr.c b/src/backend/utils/time/snapmgr.c
index dca1bc8afca..3037cf478d1 100644
--- a/src/backend/utils/time/snapmgr.c
+++ b/src/backend/utils/time/snapmgr.c
@@ -536,12 +536,14 @@ SetTransactionSnapshot(Snapshot sourcesnap, VirtualTransactionId *sourcevxid,
 	CurrentSnapshot->xmax = sourcesnap->xmax;
 	CurrentSnapshot->xcnt = sourcesnap->xcnt;
 	Assert(sourcesnap->xcnt <= GetMaxSnapshotXidCount());
-	memcpy(CurrentSnapshot->xip, sourcesnap->xip,
-		   sourcesnap->xcnt * sizeof(TransactionId));
+	if (sourcesnap->xcnt > 0)
+		memcpy(CurrentSnapshot->xip, sourcesnap->xip,
+			   sourcesnap->xcnt * sizeof(TransactionId));
 	CurrentSnapshot->subxcnt = sourcesnap->subxcnt;
 	Assert(sourcesnap->subxcnt <= GetMaxSnapshotSubxidCount());
-	memcpy(CurrentSnapshot->subxip, sourcesnap->subxip,
-		   sourcesnap->subxcnt * sizeof(TransactionId));
+	if (sourcesnap->subxcnt > 0)
+		memcpy(CurrentSnapshot->subxip, sourcesnap->subxip,
+			   sourcesnap->subxcnt * sizeof(TransactionId));
 	CurrentSnapshot->suboverflowed = sourcesnap->suboverflowed;
 	CurrentSnapshot->takenDuringRecovery = sourcesnap->takenDuringRecovery;
 	/* NB: curcid should NOT be copied, it's a local matter */
diff --git a/src/fe_utils/print.c b/src/fe_utils/print.c
index d48fcc4a032..2d0f78b8a2d 100644
--- a/src/fe_utils/print.c
+++ b/src/fe_utils/print.c
@@ -896,7 +896,8 @@ print_aligned_text(const printTableContent *cont, FILE *fout, bool is_pager)
 
 			more_col_wrapping = col_count;
 			curr_nl_line = 0;
-			memset(header_done, false, col_count * sizeof(bool));
+			if (col_count > 0)
+				memset(header_done, false, col_count * sizeof(bool));
 			while (more_col_wrapping)
 			{
 				if (opt_border == 2)