v24-0001-Design-to-extend-the-varattrib_4b-varatt_externa.patch

From efb7ec44fe72817ad005341fb8be816bfc0c20ea Mon Sep 17 00:00:00 2001
From: Nikhil Kumar Veldanda <veldanda.nikhilkumar17@gmail.com>
Date: Tue, 20 May 2025 05:43:29 +0000
Subject: [PATCH v24 1/2] Design to extend the varattrib_4b/varatt_external
 format for support of multiple TOAST compression algorithms.

---
 contrib/amcheck/verify_heapam.c               |   2 +-
 src/backend/access/brin/brin_tuple.c          |   4 +-
 src/backend/access/common/detoast.c           |   6 +-
 src/backend/access/common/indextuple.c        |   5 +-
 src/backend/access/common/toast_compression.c |  26 ++++
 src/backend/access/common/toast_internals.c   |  29 +++--
 src/backend/access/table/toast_helper.c       |   8 +-
 src/include/access/detoast.h                  |   7 +-
 src/include/access/toast_compression.h        |  22 ++--
 src/include/access/toast_internals.h          |  42 +++----
 src/include/varatt.h                          | 114 +++++++++++++++---
 src/tools/pgindent/typedefs.list              |   2 +-
 12 files changed, 189 insertions(+), 78 deletions(-)

diff --git a/contrib/amcheck/verify_heapam.c b/contrib/amcheck/verify_heapam.c
index aa9cccd1da4..2161d129502 100644
--- a/contrib/amcheck/verify_heapam.c
+++ b/contrib/amcheck/verify_heapam.c
@@ -1786,7 +1786,7 @@ check_tuple_attribute(HeapCheckContext *ctx)
 		bool		valid = false;
 
 		/* Compressed attributes should have a valid compression method */
-		cmid = TOAST_COMPRESS_METHOD(&toast_pointer);
+		cmid = VARATT_EXTERNAL_GET_COMPRESS_METHOD(toast_pointer);
 		switch (cmid)
 		{
 				/* List of all valid compression method IDs */
diff --git a/src/backend/access/brin/brin_tuple.c b/src/backend/access/brin/brin_tuple.c
index 861f397e6db..eb19739da03 100644
--- a/src/backend/access/brin/brin_tuple.c
+++ b/src/backend/access/brin/brin_tuple.c
@@ -223,6 +223,7 @@ brin_form_tuple(BrinDesc *brdesc, BlockNumber blkno, BrinMemTuple *tuple,
 			{
 				Datum		cvalue;
 				char		compression;
+				CompressionInfo cmp;
 				Form_pg_attribute att = TupleDescAttr(brdesc->bd_tupdesc,
 													  keyno);
 
@@ -237,7 +238,8 @@ brin_form_tuple(BrinDesc *brdesc, BlockNumber blkno, BrinMemTuple *tuple,
 				else
 					compression = InvalidCompressionMethod;
 
-				cvalue = toast_compress_datum(value, compression);
+				cmp = setup_cmp_info(compression, att);
+				cvalue = toast_compress_datum(value, cmp);
 
 				if (DatumGetPointer(cvalue) != NULL)
 				{
diff --git a/src/backend/access/common/detoast.c b/src/backend/access/common/detoast.c
index 62651787742..01419d1c65f 100644
--- a/src/backend/access/common/detoast.c
+++ b/src/backend/access/common/detoast.c
@@ -478,7 +478,7 @@ toast_decompress_datum(struct varlena *attr)
 	 * Fetch the compression method id stored in the compression header and
 	 * decompress the data using the appropriate decompression routine.
 	 */
-	cmid = TOAST_COMPRESS_METHOD(attr);
+	cmid = VARDATA_COMPRESSED_GET_COMPRESS_METHOD(attr);
 	switch (cmid)
 	{
 		case TOAST_PGLZ_COMPRESSION_ID:
@@ -514,14 +514,14 @@ toast_decompress_datum_slice(struct varlena *attr, int32 slicelength)
 	 * have been seen to give wrong results if passed an output size that is
 	 * more than the data's true decompressed size.
 	 */
-	if ((uint32) slicelength >= TOAST_COMPRESS_EXTSIZE(attr))
+	if ((uint32) slicelength >= VARDATA_COMPRESSED_GET_EXTSIZE(attr))
 		return toast_decompress_datum(attr);
 
 	/*
 	 * Fetch the compression method id stored in the compression header and
 	 * decompress the data slice using the appropriate decompression routine.
 	 */
-	cmid = TOAST_COMPRESS_METHOD(attr);
+	cmid = VARDATA_COMPRESSED_GET_COMPRESS_METHOD(attr);
 	switch (cmid)
 	{
 		case TOAST_PGLZ_COMPRESSION_ID:
diff --git a/src/backend/access/common/indextuple.c b/src/backend/access/common/indextuple.c
index 1986b943a28..1fe0e4288cc 100644
--- a/src/backend/access/common/indextuple.c
+++ b/src/backend/access/common/indextuple.c
@@ -123,9 +123,10 @@ index_form_tuple_context(TupleDesc tupleDescriptor,
 			 att->attstorage == TYPSTORAGE_MAIN))
 		{
 			Datum		cvalue;
+			CompressionInfo cmp;
 
-			cvalue = toast_compress_datum(untoasted_values[i],
-										  att->attcompression);
+			cmp = setup_cmp_info(att->attcompression, att);
+			cvalue = toast_compress_datum(untoasted_values[i], cmp);
 
 			if (DatumGetPointer(cvalue) != NULL)
 			{
diff --git a/src/backend/access/common/toast_compression.c b/src/backend/access/common/toast_compression.c
index 21f2f4af97e..422a387b06f 100644
--- a/src/backend/access/common/toast_compression.c
+++ b/src/backend/access/common/toast_compression.c
@@ -21,6 +21,7 @@
 #include "access/toast_compression.h"
 #include "common/pg_lzcompress.h"
 #include "varatt.h"
+#include "utils/attoptcache.h"
 
 /* GUC */
 int			default_toast_compression = TOAST_PGLZ_COMPRESSION;
@@ -314,3 +315,28 @@ GetCompressionMethodName(char method)
 			return NULL;		/* keep compiler quiet */
 	}
 }
+
+CompressionInfo
+setup_cmp_info(char cmethod, Form_pg_attribute att)
+{
+	CompressionInfo info;
+
+	/* initialize from the attribute’s default settings */
+	info.cmethod = cmethod;
+	info.meta = false;
+
+	/* If the compression method is not valid, use the current default */
+	if (!CompressionMethodIsValid(cmethod))
+		info.cmethod = default_toast_compression;
+
+	switch (info.cmethod)
+	{
+		case TOAST_PGLZ_COMPRESSION:
+		case TOAST_LZ4_COMPRESSION:
+			break;
+		default:
+			elog(ERROR, "invalid compression method %c", info.cmethod);
+	}
+
+	return info;
+}
diff --git a/src/backend/access/common/toast_internals.c b/src/backend/access/common/toast_internals.c
index 7d8be8346ce..7ba28744e90 100644
--- a/src/backend/access/common/toast_internals.c
+++ b/src/backend/access/common/toast_internals.c
@@ -43,7 +43,7 @@ static bool toastid_valueid_exists(Oid toastrelid, Oid valueid);
  * ----------
  */
 Datum
-toast_compress_datum(Datum value, char cmethod)
+toast_compress_datum(Datum value, CompressionInfo cmp)
 {
 	struct varlena *tmp = NULL;
 	int32		valsize;
@@ -54,14 +54,10 @@ toast_compress_datum(Datum value, char cmethod)
 
 	valsize = VARSIZE_ANY_EXHDR(DatumGetPointer(value));
 
-	/* If the compression method is not valid, use the current default */
-	if (!CompressionMethodIsValid(cmethod))
-		cmethod = default_toast_compression;
-
 	/*
 	 * Call appropriate compression routine for the compression method.
 	 */
-	switch (cmethod)
+	switch (cmp.cmethod)
 	{
 		case TOAST_PGLZ_COMPRESSION:
 			tmp = pglz_compress_datum((const struct varlena *) value);
@@ -72,7 +68,7 @@ toast_compress_datum(Datum value, char cmethod)
 			cmid = TOAST_LZ4_COMPRESSION_ID;
 			break;
 		default:
-			elog(ERROR, "invalid compression method %c", cmethod);
+			elog(ERROR, "invalid compression method %c", cmp.cmethod);
 	}
 
 	if (tmp == NULL)
@@ -90,9 +86,11 @@ toast_compress_datum(Datum value, char cmethod)
 	 */
 	if (VARSIZE(tmp) < valsize - 2)
 	{
+		bool		meta = cmp.meta;
+
 		/* successful compression */
 		Assert(cmid != TOAST_INVALID_COMPRESSION_ID);
-		TOAST_COMPRESS_SET_SIZE_AND_COMPRESS_METHOD(tmp, valsize, cmid);
+		TOAST_COMPRESS_SET_SIZE_AND_COMPRESS_METHOD(tmp, valsize, cmid, meta);
 		return PointerGetDatum(tmp);
 	}
 	else
@@ -143,6 +141,7 @@ toast_save_datum(Relation rel, Datum value,
 	Pointer		dval = DatumGetPointer(value);
 	int			num_indexes;
 	int			validIndex;
+	ToastCompressionId cm = TOAST_INVALID_COMPRESSION_ID;
 
 	Assert(!VARATT_IS_EXTERNAL(value));
 
@@ -179,14 +178,18 @@ toast_save_datum(Relation rel, Datum value,
 	}
 	else if (VARATT_IS_COMPRESSED(dval))
 	{
+		bool		meta;
+
 		data_p = VARDATA(dval);
 		data_todo = VARSIZE(dval) - VARHDRSZ;
 		/* rawsize in a compressed datum is just the size of the payload */
 		toast_pointer.va_rawsize = VARDATA_COMPRESSED_GET_EXTSIZE(dval) + VARHDRSZ;
-
+		cm = VARDATA_COMPRESSED_GET_COMPRESS_METHOD(dval);
+		meta = TOAST_CMPID_EXTENDED(cm) ?
+			VARATT_4BCE_HAS_META(((varattrib_4b *) (dval))->va_compressed_ext.va_ecinfo) :
+			false;
 		/* set external size and compression method */
-		VARATT_EXTERNAL_SET_SIZE_AND_COMPRESS_METHOD(toast_pointer, data_todo,
-													 VARDATA_COMPRESSED_GET_COMPRESS_METHOD(dval));
+		VARATT_EXTERNAL_SET_SIZE_AND_COMPRESS_METHOD(toast_pointer, data_todo, cm, meta);
 		/* Assert that the numbers look like it's compressed */
 		Assert(VARATT_EXTERNAL_IS_COMPRESSED(toast_pointer));
 	}
@@ -368,9 +371,9 @@ toast_save_datum(Relation rel, Datum value,
 	/*
 	 * Create the TOAST pointer value that we'll return
 	 */
-	result = (struct varlena *) palloc(TOAST_POINTER_SIZE);
+	result = (struct varlena *) palloc(TOAST_CMPID_EXTENDED(cm) ? TOAST_POINTER_EXT_SIZE : TOAST_POINTER_NOEXT_SIZE);
 	SET_VARTAG_EXTERNAL(result, VARTAG_ONDISK);
-	memcpy(VARDATA_EXTERNAL(result), &toast_pointer, sizeof(toast_pointer));
+	memcpy(VARDATA_EXTERNAL(result), &toast_pointer, TOAST_CMPID_EXTENDED(cm) ? TOAST_POINTER_EXT_SIZE - VARHDRSZ_EXTERNAL : TOAST_POINTER_NOEXT_SIZE - VARHDRSZ_EXTERNAL);
 
 	return PointerGetDatum(result);
 }
diff --git a/src/backend/access/table/toast_helper.c b/src/backend/access/table/toast_helper.c
index b60fab0a4d2..1edd07634db 100644
--- a/src/backend/access/table/toast_helper.c
+++ b/src/backend/access/table/toast_helper.c
@@ -171,7 +171,7 @@ toast_tuple_init(ToastTupleContext *ttc)
  * The column must have attstorage EXTERNAL or EXTENDED if check_main is
  * false, and must have attstorage MAIN if check_main is true.
  *
- * The column must have a minimum size of MAXALIGN(TOAST_POINTER_SIZE);
+ * The column must have a minimum size of MAXALIGN(TOAST_POINTER_NOEXT_SIZE);
  * if not, no benefit is to be expected by compressing it.
  *
  * The return value is the index of the biggest suitable column, or
@@ -184,7 +184,7 @@ toast_tuple_find_biggest_attribute(ToastTupleContext *ttc,
 	TupleDesc	tupleDesc = ttc->ttc_rel->rd_att;
 	int			numAttrs = tupleDesc->natts;
 	int			biggest_attno = -1;
-	int32		biggest_size = MAXALIGN(TOAST_POINTER_SIZE);
+	int32		biggest_size = MAXALIGN(TOAST_POINTER_NOEXT_SIZE);
 	int32		skip_colflags = TOASTCOL_IGNORE;
 	int			i;
 
@@ -229,8 +229,10 @@ toast_tuple_try_compression(ToastTupleContext *ttc, int attribute)
 	Datum	   *value = &ttc->ttc_values[attribute];
 	Datum		new_value;
 	ToastAttrInfo *attr = &ttc->ttc_attr[attribute];
+	Form_pg_attribute att = TupleDescAttr(ttc->ttc_rel->rd_att, attribute);
+	CompressionInfo cmp = setup_cmp_info(attr->tai_compression, att);
 
-	new_value = toast_compress_datum(*value, attr->tai_compression);
+	new_value = toast_compress_datum(*value, cmp);
 
 	if (DatumGetPointer(new_value) != NULL)
 	{
diff --git a/src/include/access/detoast.h b/src/include/access/detoast.h
index e603a2276c3..8dbbe4d8192 100644
--- a/src/include/access/detoast.h
+++ b/src/include/access/detoast.h
@@ -23,12 +23,13 @@
 do { \
 	varattrib_1b_e *attre = (varattrib_1b_e *) (attr); \
 	Assert(VARATT_IS_EXTERNAL(attre)); \
-	Assert(VARSIZE_EXTERNAL(attre) == sizeof(toast_pointer) + VARHDRSZ_EXTERNAL); \
-	memcpy(&(toast_pointer), VARDATA_EXTERNAL(attre), sizeof(toast_pointer)); \
+	memset(&(toast_pointer), 0, sizeof(toast_pointer)); \
+	memcpy(&(toast_pointer), VARDATA_EXTERNAL(attre), VARSIZE_EXTERNAL(attre) - VARHDRSZ_EXTERNAL); \
 } while (0)
 
 /* Size of an EXTERNAL datum that contains a standard TOAST pointer */
-#define TOAST_POINTER_SIZE (VARHDRSZ_EXTERNAL + sizeof(varatt_external))
+#define TOAST_POINTER_NOEXT_SIZE (VARHDRSZ_EXTERNAL + offsetof(varatt_external, extended))
+#define TOAST_POINTER_EXT_SIZE (TOAST_POINTER_NOEXT_SIZE + MEMBER_SIZE(varatt_external, extended.cmp))
 
 /* Size of an EXTERNAL datum that contains an indirection pointer */
 #define INDIRECT_POINTER_SIZE (VARHDRSZ_EXTERNAL + sizeof(varatt_indirect))
diff --git a/src/include/access/toast_compression.h b/src/include/access/toast_compression.h
index 13c4612ceed..3812fe89fe4 100644
--- a/src/include/access/toast_compression.h
+++ b/src/include/access/toast_compression.h
@@ -13,6 +13,8 @@
 #ifndef TOAST_COMPRESSION_H
 #define TOAST_COMPRESSION_H
 
+#include "catalog/pg_attribute.h"
+
 /*
  * GUC support.
  *
@@ -22,18 +24,6 @@
  */
 extern PGDLLIMPORT int default_toast_compression;
 
-/*
- * Built-in compression method ID.  The toast compression header will store
- * this in the first 2 bits of the raw length.  These built-in compression
- * method IDs are directly mapped to the built-in compression methods.
- *
- * Don't use these values for anything other than understanding the meaning
- * of the raw bits from a varlena; in particular, if the goal is to identify
- * a compression method, use the constants TOAST_PGLZ_COMPRESSION, etc.
- * below. We might someday support more than 4 compression methods, but
- * we can never have more than 4 values in this enum, because there are
- * only 2 bits available in the places where this is stored.
- */
 typedef enum ToastCompressionId
 {
 	TOAST_PGLZ_COMPRESSION_ID = 0,
@@ -41,6 +31,12 @@ typedef enum ToastCompressionId
 	TOAST_INVALID_COMPRESSION_ID = 2,
 } ToastCompressionId;
 
+typedef struct CompressionInfo
+{
+	char		cmethod;
+	bool		meta;
+} CompressionInfo;
+
 /*
  * Built-in compression methods.  pg_attribute will store these in the
  * attcompression column.  In attcompression, InvalidCompressionMethod
@@ -51,6 +47,7 @@ typedef enum ToastCompressionId
 #define InvalidCompressionMethod		'\0'
 
 #define CompressionMethodIsValid(cm)  ((cm) != InvalidCompressionMethod)
+#define TOAST_CMPID_EXTENDED(cmpid)	(!(cmpid == TOAST_PGLZ_COMPRESSION_ID || cmpid == TOAST_LZ4_COMPRESSION_ID ||cmpid == TOAST_INVALID_COMPRESSION_ID))
 
 
 /* pglz compression/decompression routines */
@@ -69,5 +66,6 @@ extern struct varlena *lz4_decompress_datum_slice(const struct varlena *value,
 extern ToastCompressionId toast_get_compression_id(struct varlena *attr);
 extern char CompressionNameToMethod(const char *compression);
 extern const char *GetCompressionMethodName(char method);
+extern CompressionInfo setup_cmp_info(char cmethod, Form_pg_attribute att);
 
 #endif							/* TOAST_COMPRESSION_H */
diff --git a/src/include/access/toast_internals.h b/src/include/access/toast_internals.h
index 06ae8583c1e..966317f2399 100644
--- a/src/include/access/toast_internals.h
+++ b/src/include/access/toast_internals.h
@@ -17,35 +17,31 @@
 #include "utils/relcache.h"
 #include "utils/snapshot.h"
 
-/*
- *	The information at the start of the compressed toast data.
- */
-typedef struct toast_compress_header
-{
-	int32		vl_len_;		/* varlena header (do not touch directly!) */
-	uint32		tcinfo;			/* 2 bits for compression method and 30 bits
-								 * external size; see va_extinfo */
-} toast_compress_header;
-
 /*
  * Utilities for manipulation of header information for compressed
  * toast entries.
  */
-#define TOAST_COMPRESS_EXTSIZE(ptr) \
-	(((toast_compress_header *) (ptr))->tcinfo & VARLENA_EXTSIZE_MASK)
-#define TOAST_COMPRESS_METHOD(ptr) \
-	(((toast_compress_header *) (ptr))->tcinfo >> VARLENA_EXTSIZE_BITS)
-
-#define TOAST_COMPRESS_SET_SIZE_AND_COMPRESS_METHOD(ptr, len, cm_method) \
-	do { \
-		Assert((len) > 0 && (len) <= VARLENA_EXTSIZE_MASK); \
-		Assert((cm_method) == TOAST_PGLZ_COMPRESSION_ID || \
-			   (cm_method) == TOAST_LZ4_COMPRESSION_ID); \
-		((toast_compress_header *) (ptr))->tcinfo = \
-			(len) | ((uint32) (cm_method) << VARLENA_EXTSIZE_BITS); \
+#define TOAST_COMPRESS_SET_SIZE_AND_COMPRESS_METHOD(ptr, len, cm_method, meta)			\
+	do {																				\
+		Assert((len) > 0 && (len) <= VARLENA_EXTSIZE_MASK);								\
+		Assert((cm_method) == TOAST_PGLZ_COMPRESSION_ID ||								\
+				(cm_method) == TOAST_LZ4_COMPRESSION_ID);								\
+		if (!TOAST_CMPID_EXTENDED((cm_method)))											\
+		{																				\
+			((varattrib_4b *)(ptr))->va_compressed.va_tcinfo =							\
+				((uint32)(len)) | ((uint32)(cm_method) << VARLENA_EXTSIZE_BITS);		\
+		}																				\
+		else																			\
+		{																				\
+			/* extended path: mark EXT flag in tcinfo */								\
+			((varattrib_4b *)(ptr))->va_compressed_ext.va_tcinfo =						\
+				((uint32)(len)) | ((uint32)(VARATT_4BCE_EXTFLAG) << VARLENA_EXTSIZE_BITS);	\
+			((varattrib_4b *)(ptr))->va_compressed_ext.va_ecinfo = 						\
+				VARATT_4BCE_ENCODE((meta), (cm_method));							\
+		}																				\
 	} while (0)
 
-extern Datum toast_compress_datum(Datum value, char cmethod);
+extern Datum toast_compress_datum(Datum value, CompressionInfo cmp);
 extern Oid	toast_get_valid_index(Oid toastoid, LOCKMODE lock);
 
 extern void toast_delete_datum(Relation rel, Datum value, bool is_speculative);
diff --git a/src/include/varatt.h b/src/include/varatt.h
index 2e8564d4998..bb4496d81d6 100644
--- a/src/include/varatt.h
+++ b/src/include/varatt.h
@@ -28,6 +28,9 @@
  * you need to memcpy from the tuple into a local struct variable before
  * you can look at these fields!  (The reason we use memcmp is to avoid
  * having to do that just to detect equality of two TOAST pointers...)
+ *
+ * When the top two bits of va_extinfo (as checked by VARATT_4BCE_EXTFLAG) are set,
+ * It means it holds additional information.
  */
 typedef struct varatt_external
 {
@@ -36,6 +39,14 @@ typedef struct varatt_external
 								 * compression method */
 	Oid			va_valueid;		/* Unique ID of value within TOAST table */
 	Oid			va_toastrelid;	/* RelID of TOAST table containing it */
+	/* -------- optional trailer -------- */
+	union
+	{
+		struct					/* compression-method trailer */
+		{
+			uint8		va_ecinfo;	/* Extended compression methods info */
+		}			cmp;
+	}			extended;		/* "extended" = optional bytes */
 }			varatt_external;
 
 /*
@@ -93,11 +104,24 @@ typedef enum vartag_external
 #define VARTAG_IS_EXPANDED(tag) \
 	(((tag) & ~1) == VARTAG_EXPANDED_RO)
 
-#define VARTAG_SIZE(tag) \
-	((tag) == VARTAG_INDIRECT ? sizeof(varatt_indirect) : \
-	 VARTAG_IS_EXPANDED(tag) ? sizeof(varatt_expanded) : \
-	 (tag) == VARTAG_ONDISK ? sizeof(varatt_external) : \
-	 (AssertMacro(false), 0))
+#define MEMBER_SIZE(type, member)  sizeof( ((type *)0)->member )
+
+#define VARTAG_SIZE(PTR)														\
+(																				\
+	VARTAG_EXTERNAL(PTR) == VARTAG_INDIRECT ?									\
+		sizeof(varatt_indirect) :												\
+	VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR)) ?									\
+		sizeof(varatt_expanded) :												\
+	VARTAG_EXTERNAL(PTR) == VARTAG_ONDISK ?										\
+		(offsetof(varatt_external, extended) +									\
+			((UNALIGNED_U32((const uint8 *)(PTR) + VARHDRSZ_EXTERNAL +			\
+							offsetof(varatt_external, va_extinfo))				\
+			>> VARLENA_EXTSIZE_BITS) == VARATT_4BCE_EXTFLAG						\
+				? MEMBER_SIZE(varatt_external, extended.cmp)					\
+				: 0))															\
+		:																		\
+	(AssertMacro(false), 0)														\
+)
 
 /*
  * These structs describe the header of a varlena object that may have been
@@ -122,6 +146,14 @@ typedef union
 								 * compression method; see va_extinfo */
 		char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Compressed data */
 	}			va_compressed;
+	struct
+	{
+		uint32		va_header;
+		uint32		va_tcinfo;	/* Original data size (excludes header) and
+								 * compression method; see va_extinfo */
+		uint8		va_ecinfo;	/* algorithm id (0–255) */
+		char		va_data[FLEXIBLE_ARRAY_MEMBER];
+	}			va_compressed_ext;
 } varattrib_4b;
 
 typedef struct
@@ -206,6 +238,12 @@ typedef struct
 	(((varattrib_1b_e *) (PTR))->va_header = 0x80, \
 	 ((varattrib_1b_e *) (PTR))->va_tag = (tag))
 
+#define UNALIGNED_U32(ptr)							\
+	( (uint32) (((const uint8 *)(ptr))[3])			\
+	| ((uint32)(((const uint8 *)(ptr))[2]) <<  8)	\
+	| ((uint32)(((const uint8 *)(ptr))[1]) << 16)	\
+	| ((uint32)(((const uint8 *)(ptr))[0]) << 24) )
+
 #else							/* !WORDS_BIGENDIAN */
 
 #define VARATT_IS_4B(PTR) \
@@ -239,6 +277,12 @@ typedef struct
 	(((varattrib_1b_e *) (PTR))->va_header = 0x01, \
 	 ((varattrib_1b_e *) (PTR))->va_tag = (tag))
 
+#define UNALIGNED_U32(ptr)							\
+	( (uint32) (((const uint8 *)(ptr))[0])			\
+	| ((uint32)(((const uint8 *)(ptr))[1]) <<  8)	\
+	| ((uint32)(((const uint8 *)(ptr))[2]) << 16)	\
+	| ((uint32)(((const uint8 *)(ptr))[3]) << 24) )
+
 #endif							/* WORDS_BIGENDIAN */
 
 #define VARDATA_4B(PTR)		(((varattrib_4b *) (PTR))->va_4byte.va_data)
@@ -282,7 +326,7 @@ typedef struct
 #define VARDATA_SHORT(PTR)					VARDATA_1B(PTR)
 
 #define VARTAG_EXTERNAL(PTR)				VARTAG_1B_E(PTR)
-#define VARSIZE_EXTERNAL(PTR)				(VARHDRSZ_EXTERNAL + VARTAG_SIZE(VARTAG_EXTERNAL(PTR)))
+#define VARSIZE_EXTERNAL(PTR)				(VARHDRSZ_EXTERNAL + VARTAG_SIZE(PTR))
 #define VARDATA_EXTERNAL(PTR)				VARDATA_1B_E(PTR)
 
 #define VARATT_IS_COMPRESSED(PTR)			VARATT_IS_4B_C(PTR)
@@ -328,20 +372,33 @@ typedef struct
 #define VARDATA_COMPRESSED_GET_EXTSIZE(PTR) \
 	(((varattrib_4b *) (PTR))->va_compressed.va_tcinfo & VARLENA_EXTSIZE_MASK)
 #define VARDATA_COMPRESSED_GET_COMPRESS_METHOD(PTR) \
-	(((varattrib_4b *) (PTR))->va_compressed.va_tcinfo >> VARLENA_EXTSIZE_BITS)
+	( (VARATT_IS_4BCE(PTR)) ? VARATT_4BCE_GET_CMID(((varattrib_4b *) (PTR))->va_compressed_ext.va_ecinfo) \
+	: (((varattrib_4b *) (PTR))->va_compressed.va_tcinfo >> VARLENA_EXTSIZE_BITS))
 
 /* Same for external Datums; but note argument is a struct varatt_external */
 #define VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) \
 	((toast_pointer).va_extinfo & VARLENA_EXTSIZE_MASK)
-#define VARATT_EXTERNAL_GET_COMPRESS_METHOD(toast_pointer) \
-	((toast_pointer).va_extinfo >> VARLENA_EXTSIZE_BITS)
-
-#define VARATT_EXTERNAL_SET_SIZE_AND_COMPRESS_METHOD(toast_pointer, len, cm) \
-	do { \
-		Assert((cm) == TOAST_PGLZ_COMPRESSION_ID || \
-			   (cm) == TOAST_LZ4_COMPRESSION_ID); \
-		((toast_pointer).va_extinfo = \
-			(len) | ((uint32) (cm) << VARLENA_EXTSIZE_BITS)); \
+#define VARATT_EXTERNAL_GET_COMPRESS_METHOD(toast_pointer)							\
+	( ((toast_pointer).va_extinfo >> VARLENA_EXTSIZE_BITS) == VARATT_4BCE_EXTFLAG	\
+		? VARATT_4BCE_GET_CMID((toast_pointer).extended.cmp.va_ecinfo)				\
+			: (toast_pointer).va_extinfo >> VARLENA_EXTSIZE_BITS )
+
+#define VARATT_EXTERNAL_SET_SIZE_AND_COMPRESS_METHOD(toast_pointer, len, cm, meta)				\
+	do {																						\
+		Assert((cm) == TOAST_PGLZ_COMPRESSION_ID ||												\
+				(cm) == TOAST_LZ4_COMPRESSION_ID);												\
+		if (!TOAST_CMPID_EXTENDED(cm))															\
+		{																						\
+			/* method fits in the low bits of va_extinfo */										\
+			(toast_pointer).va_extinfo = (uint32)(len) | ((uint32)(cm) << VARLENA_EXTSIZE_BITS);\
+		}																						\
+		else																					\
+		{																						\
+			/* set “extended” flag and store the extra byte */									\
+			(toast_pointer).va_extinfo = (uint32)(len) |										\
+				(VARATT_4BCE_EXTFLAG << VARLENA_EXTSIZE_BITS);									\
+			(toast_pointer).extended.cmp.va_ecinfo = VARATT_4BCE_ENCODE(meta, cm);		\
+		}																						\
 	} while (0)
 
 /*
@@ -355,4 +412,29 @@ typedef struct
 	(VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer) < \
 	 (toast_pointer).va_rawsize - VARHDRSZ)
 
+/* Upper-two-bit pattern 0b11 marks “extended compression info present”. */
+#define VARATT_4BCE_EXTFLAG             0x3
+
+/* Helper: pack <flag, cmid> into a single byte:  flag (b0), cmid-2 (b1..7) */
+#define VARATT_4BCE_ENCODE(flag, cmid) \
+    ((uint8)((((cmid) - 2) << 1) | ((flag) & 0x01)))
+
+#define VARATT_4BCE_HAS_META(raw)       ((raw) & 0x01u)
+#define VARATT_4BCE_GET_CMID(raw)       ((((raw) >> 1) & 0x7Fu) + 2)
+
+/* Pointer-level helpers */
+#define VARATT_4BCE_PTR_HAS_META(ptr) \
+    VARATT_4BCE_HAS_META(((varattrib_4b *)(ptr))->va_compressed_ext.va_ecinfo)
+
+/* Does this varattrib use the “compressed-extended” format? */
+#define VARATT_IS_4BCE(ptr) \
+    ((((varattrib_4b *)(ptr))->va_compressed_ext.va_tcinfo >> VARLENA_EXTSIZE_BITS) \
+        == VARATT_4BCE_EXTFLAG)
+
+/* Access the start of the compressed payload */
+#define VARDATA_4BCE(ptr) \
+    (((varattrib_4b *)(ptr))->va_compressed_ext.va_data)
+
+#define VARHDRSZ_4BCE	(offsetof(varattrib_4b, va_compressed_ext.va_data))
+
 #endif
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 9ea573fae21..27adbebed3f 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -483,6 +483,7 @@ CompositeIOData
 CompositeTypeStmt
 CompoundAffixFlag
 CompressFileHandle
+CompressionInfo
 CompressionLocation
 CompressorState
 ComputeXidHorizonsResult
@@ -4101,7 +4102,6 @@ timeout_handler_proc
 timeout_params
 timerCA
 tlist_vinfo
-toast_compress_header
 tokenize_error_callback_arg
 transferMode
 transfer_thread_arg

base-commit: 54675d89863378b092c838a4e110551203d89b54
-- 
2.47.1