Make type Datum be 8 bytes wide everywhere.

tglsfdc · tglsfdc · commit 2a600a93c7be · 2025-08-13T17:18:22.000-04:00
This patch makes sizeof(Datum) be 8 on all platforms including 32-bit ones. The objective is to allow USE_FLOAT8_BYVAL to be true everywhere, and in consequence to remove a lot of code that is specific to pass-by-reference handling of float8, int8, etc. The code for abbreviated sort keys can be simplified similarly. In this way we can reduce the maintenance effort involved in supporting 32-bit platforms, without going so far as to actually desupport them. Since Datum is strictly an in-memory concept, this has no impact on on-disk storage, though an initdb or pg_upgrade will be needed to fix affected catalog entries. We have required platforms to support [u]int64 for ages, so this breaks no supported platform. We can expect that this change will make 32-bit builds a bit slower and more memory-hungry, although being able to use pass-by-value handling of 8-byte types may buy back some of that. But we stopped optimizing for 32-bit cases a long time ago, and this seems like just another step on that path. This initial patch simply forces the correct type definition and USE_FLOAT8_BYVAL setting, and cleans up a couple of minor compiler complaints that ensued. This is sufficient for testing purposes. In the wake of a bunch of Datum-conversion cleanups by Peter Eisentraut, this now compiles cleanly with gcc on a 32-bit platform. (I'd only tested the previous version with clang, which it turns out is less picky than gcc about width-changing coercions.) There is a good deal of now-dead code that I'll remove in separate follow-up patches. A catversion bump is required because this affects initial catalog contents (on 32-bit machines) in two ways: pg_type.typbyval changes for some built-in types, and Const nodes in stored views/rules will now have 8 bytes not 4 for pass-by-value types. Author: Tom Lane <tgl@sss.pgh.pa.us> Reviewed-by: Peter Eisentraut <peter@eisentraut.org> Discussion: https://postgr.es/m/1749799.1752797397@sss.pgh.pa.us
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
@@ -399,7 +399,7 @@ cancel_before_shmem_exit(pg_on_exit_callback function, Datum arg)
 		before_shmem_exit_list[before_shmem_exit_index - 1].arg == arg)
 		--before_shmem_exit_index;
 	else
-		elog(ERROR, "before_shmem_exit callback (%p,0x%" PRIxPTR ") is not the latest entry",
+		elog(ERROR, "before_shmem_exit callback (%p,0x%" PRIx64 ") is not the latest entry",
 			 function, arg);
 }
 
diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
@@ -231,11 +231,8 @@ hash_resource_elem(Datum value, const ResourceOwnerDesc *kind)
 	 * 'kind' into the hash.  Just add it with hash_combine(), it perturbs the
 	 * result enough for our purposes.
 	 */
-#if SIZEOF_DATUM == 8
-	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
-#else
-	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
-#endif
+	return hash_combine64(murmurhash64((uint64) value),
+						  (uint64) (uintptr_t) kind);
 }
 
 /*
diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h
@@ -57,6 +57,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	202508051
+#define CATALOG_VERSION_NO	202508131
 
 #endif
diff --git a/src/include/nodes/nodes.h b/src/include/nodes/nodes.h
@@ -188,6 +188,8 @@ castNodeImpl(NodeTag type, void *ptr)
  * ----------------------------------------------------------------
  */
 
+#ifndef FRONTEND
+
 /*
  * nodes/{outfuncs.c,print.c}
  */
@@ -198,7 +200,7 @@ extern void outNode(struct StringInfoData *str, const void *obj);
 extern void outToken(struct StringInfoData *str, const char *s);
 extern void outBitmapset(struct StringInfoData *str,
 						 const struct Bitmapset *bms);
-extern void outDatum(struct StringInfoData *str, uintptr_t value,
+extern void outDatum(struct StringInfoData *str, Datum value,
 					 int typlen, bool typbyval);
 extern char *nodeToString(const void *obj);
 extern char *nodeToStringWithLocations(const void *obj);
@@ -212,7 +214,7 @@ extern void *stringToNode(const char *str);
 extern void *stringToNodeWithLocations(const char *str);
 #endif
 extern struct Bitmapset *readBitmapset(void);
-extern uintptr_t readDatum(bool typbyval);
+extern Datum readDatum(bool typbyval);
 extern bool *readBoolCols(int numCols);
 extern int *readIntCols(int numCols);
 extern Oid *readOidCols(int numCols);
@@ -235,6 +237,8 @@ extern void *copyObjectImpl(const void *from);
  */
 extern bool equal(const void *a, const void *b);
 
+#endif							/* !FRONTEND */
+
 
 /*
  * Typedef for parse location.  This is just an int, but this way
diff --git a/src/include/pg_config_manual.h b/src/include/pg_config_manual.h
@@ -74,17 +74,12 @@
 #define PARTITION_MAX_KEYS	32
 
 /*
- * Decide whether built-in 8-byte types, including float8, int8, and
- * timestamp, are passed by value.  This is on by default if sizeof(Datum) >=
- * 8 (that is, on 64-bit platforms).  If sizeof(Datum) < 8 (32-bit platforms),
- * this must be off.  We keep this here as an option so that it is easy to
- * test the pass-by-reference code paths on 64-bit platforms.
- *
- * Changing this requires an initdb.
+ * This symbol is now vestigial: built-in 8-byte types, including float8,
+ * int8, and timestamp, are always passed by value since we require Datum
+ * to be wide enough to permit that.  We continue to define the symbol here
+ * so as not to unnecessarily break extension code.
  */
-#if SIZEOF_VOID_P >= 8
 #define USE_FLOAT8_BYVAL 1
-#endif
 
 
 /*
diff --git a/src/include/postgres.h b/src/include/postgres.h
@@ -58,15 +58,22 @@
 
 /*
  * A Datum contains either a value of a pass-by-value type or a pointer to a
- * value of a pass-by-reference type.  Therefore, we require:
- *
- * sizeof(Datum) == sizeof(void *) == 4 or 8
+ * value of a pass-by-reference type.  Therefore, we must have
+ * sizeof(Datum) >= sizeof(void *).  No current or foreseeable Postgres
+ * platform has pointers wider than 8 bytes, and standardizing on Datum being
+ * exactly 8 bytes has advantages in reducing cross-platform differences.
  *
  * The functions below and the analogous functions for other types should be used to
  * convert between a Datum and the appropriate C type.
  */
 
-typedef uintptr_t Datum;
+typedef uint64_t Datum;
+
+/*
+ * This symbol is now vestigial, but we continue to define it so as not to
+ * unnecessarily break extension code.
+ */
+#define SIZEOF_DATUM 8
 
 /*
  * A NullableDatum is used in places where both a Datum and its nullness needs
@@ -83,8 +90,6 @@ typedef struct NullableDatum
 	/* due to alignment padding this could be used for flags for free */
 } NullableDatum;
 
-#define SIZEOF_DATUM SIZEOF_VOID_P
-
 /*
  * DatumGetBool
  *		Returns boolean value of a datum.
@@ -316,7 +321,7 @@ CommandIdGetDatum(CommandId X)
 static inline Pointer
 DatumGetPointer(Datum X)
 {
-	return (Pointer) X;
+	return (Pointer) (uintptr_t) X;
 }
 
 /*
@@ -326,7 +331,7 @@ DatumGetPointer(Datum X)
 static inline Datum
 PointerGetDatum(const void *X)
 {
-	return (Datum) X;
+	return (Datum) (uintptr_t) X;
 }
 
 /*

Original file line number	Diff line number	Diff line change
`@@ -399,7 +399,7 @@ cancel_before_shmem_exit(pg_on_exit_callback function, Datum arg)`
`399`	`399`	`before_shmem_exit_list[before_shmem_exit_index - 1].arg == arg)`
`400`	`400`	`--before_shmem_exit_index;`
`401`	`401`	`else`
`402`		`- elog(ERROR, "before_shmem_exit callback (%p,0x%" PRIxPTR ") is not the latest entry",`
	`402`	`+ elog(ERROR, "before_shmem_exit callback (%p,0x%" PRIx64 ") is not the latest entry",`
`403`	`403`	`function, arg);`
`404`	`404`	`}`
`405`	`405`