compressed-datum-slicing-20190103a.patch

diff --git a/src/backend/access/heap/tuptoaster.c b/src/backend/access/heap/tuptoaster.c
index fdbaf38126..ff47c07f02 100644
--- a/src/backend/access/heap/tuptoaster.c
+++ b/src/backend/access/heap/tuptoaster.c
@@ -76,6 +76,7 @@ static struct varlena *toast_fetch_datum(struct varlena *attr);
 static struct varlena *toast_fetch_datum_slice(struct varlena *attr,
 						int32 sliceoffset, int32 length);
 static struct varlena *toast_decompress_datum(struct varlena *attr);
+static struct varlena *toast_decompress_datum_slice(struct varlena *attr, int32 slicelength);
 static int toast_open_indexes(Relation toastrel,
 				   LOCKMODE lock,
 				   Relation **toastidxs,
@@ -302,7 +303,11 @@ heap_tuple_untoast_attr_slice(struct varlena *attr,
 	{
 		struct varlena *tmp = preslice;
 
-		preslice = toast_decompress_datum(tmp);
+		/* Decompress enough to encompass the slice and the offset */
+		if (slicelength > 0 && sliceoffset >= 0)
+			preslice = toast_decompress_datum_slice(tmp, slicelength + sliceoffset);
+		else
+			preslice = toast_decompress_datum(tmp);
 
 		if (tmp != attr)
 			pfree(tmp);
@@ -2274,9 +2279,39 @@ toast_decompress_datum(struct varlena *attr)
 	if (pglz_decompress(TOAST_COMPRESS_RAWDATA(attr),
 						VARSIZE(attr) - TOAST_COMPRESS_HDRSZ,
 						VARDATA(result),
-						TOAST_COMPRESS_RAWSIZE(attr)) < 0)
+						TOAST_COMPRESS_RAWSIZE(attr), false) < 0)
+		elog(ERROR, "compressed data is corrupted");
+
+	return result;
+}
+
+
+/* ----------
+ * toast_decompress_datum_slice -
+ *
+ * Decompress the front of a compressed version of a varlena datum.
+ * offset handling happens in heap_tuple_untoast_attr_slice.
+ * Here we just decompress a slice from the front.
+ */
+static struct varlena *
+toast_decompress_datum_slice(struct varlena *attr, int32 slicelength)
+{
+	struct varlena *result;
+	int32 rawsize;
+
+	Assert(VARATT_IS_COMPRESSED(attr));
+
+	result = (struct varlena *) palloc(slicelength + VARHDRSZ);
+	SET_VARSIZE(result, slicelength + VARHDRSZ);
+
+	rawsize = pglz_decompress(TOAST_COMPRESS_RAWDATA(attr),
+						VARSIZE(attr) - TOAST_COMPRESS_HDRSZ,
+						VARDATA(result),
+						slicelength, true);
+	if (rawsize < 0)
 		elog(ERROR, "compressed data is corrupted");
 
+	SET_VARSIZE(result, rawsize + VARHDRSZ);
 	return result;
 }
 
diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c
index c5e019bf77..859b3ec4fd 100644
--- a/src/backend/access/transam/xlogreader.c
+++ b/src/backend/access/transam/xlogreader.c
@@ -1425,7 +1425,7 @@ RestoreBlockImage(XLogReaderState *record, uint8 block_id, char *page)
 	{
 		/* If a backup block image is compressed, decompress it */
 		if (pglz_decompress(ptr, bkpb->bimg_len, tmp.data,
-							BLCKSZ - bkpb->hole_length) < 0)
+							BLCKSZ - bkpb->hole_length, false) < 0)
 		{
 			report_invalid_record(record, "invalid compressed image at %X/%X, block %d",
 								  (uint32) (record->ReadRecPtr >> 32),
diff --git a/src/common/pg_lzcompress.c b/src/common/pg_lzcompress.c
index 2d25da3a23..4a46b9376b 100644
--- a/src/common/pg_lzcompress.c
+++ b/src/common/pg_lzcompress.c
@@ -680,7 +680,7 @@ pglz_compress(const char *source, int32 slen, char *dest,
  */
 int32
 pglz_decompress(const char *source, int32 slen, char *dest,
-				int32 rawsize)
+				int32 rawsize, bool is_slice)
 {
 	const unsigned char *sp;
 	const unsigned char *srcend;
@@ -703,6 +703,10 @@ pglz_decompress(const char *source, int32 slen, char *dest,
 
 		for (ctrlc = 0; ctrlc < 8 && sp < srcend; ctrlc++)
 		{
+
+			if (dp >= destend)	/* check for buffer overrun */
+				break;		/* do not clobber memory */
+
 			if (ctrl & 1)
 			{
 				/*
@@ -721,19 +725,6 @@ pglz_decompress(const char *source, int32 slen, char *dest,
 				if (len == 18)
 					len += *sp++;
 
-				/*
-				 * Check for output buffer overrun, to ensure we don't clobber
-				 * memory in case of corrupt input.  Note: we must advance dp
-				 * here to ensure the error is detected below the loop.  We
-				 * don't simply put the elog inside the loop since that will
-				 * probably interfere with optimization.
-				 */
-				if (dp + len > destend)
-				{
-					dp += len;
-					break;
-				}
-
 				/*
 				 * Now we copy the bytes specified by the tag from OUTPUT to
 				 * OUTPUT. It is dangerous and platform dependent to use
@@ -744,6 +735,8 @@ pglz_decompress(const char *source, int32 slen, char *dest,
 				{
 					*dp = dp[-off];
 					dp++;
+					if (dp >= destend)	/* check for buffer overrun */
+						break;		/* do not clobber memory */
 				}
 			}
 			else
@@ -752,9 +745,6 @@ pglz_decompress(const char *source, int32 slen, char *dest,
 				 * An unset control bit means LITERAL BYTE. So we just copy
 				 * one from INPUT to OUTPUT.
 				 */
-				if (dp >= destend)	/* check for buffer overrun */
-					break;		/* do not clobber memory */
-
 				*dp++ = *sp++;
 			}
 
@@ -767,12 +757,15 @@ pglz_decompress(const char *source, int32 slen, char *dest,
 
 	/*
 	 * Check we decompressed the right amount.
+	 * If we are slicing, then we won't necessarily
+	 * be at the end of the source or dest buffers
+	 * when we hit a stop, so we don't test then.
 	 */
-	if (dp != destend || sp != srcend)
+	if (!is_slice && (dp != destend || sp != srcend))
 		return -1;
 
 	/*
 	 * That's it.
 	 */
-	return rawsize;
+	return (char*)dp - dest;
 }
diff --git a/src/include/common/pg_lzcompress.h b/src/include/common/pg_lzcompress.h
index d4b2e8a53c..d8364cd34a 100644
--- a/src/include/common/pg_lzcompress.h
+++ b/src/include/common/pg_lzcompress.h
@@ -86,6 +86,6 @@ extern const PGLZ_Strategy *const PGLZ_strategy_always;
 extern int32 pglz_compress(const char *source, int32 slen, char *dest,
 			  const PGLZ_Strategy *strategy);
 extern int32 pglz_decompress(const char *source, int32 slen, char *dest,
-				int32 rawsize);
+				int32 rawsize, bool is_slice);
 
 #endif							/* _PG_LZCOMPRESS_H_ */