agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH 3/7] Move XLOG stuff from heap_insert and heap_delete
267+ messages / 2 participants
[nested] [flat]

* [PATCH 3/7] Move XLOG stuff from heap_insert and heap_delete
@ 2019-03-25 04:29 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Kyotaro Horiguchi @ 2019-03-25 04:29 UTC (permalink / raw)

Succeeding commit makes heap_update emit insert and delete WAL
records. Move out XLOG stuff for insert and delete so that heap_update
can use the stuff.
---
 src/backend/access/heap/heapam.c | 277 ++++++++++++++++++++++-----------------
 1 file changed, 157 insertions(+), 120 deletions(-)

diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index 65536c7214..fe5d939c45 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -71,6 +71,11 @@
 
 static HeapTuple heap_prepare_insert(Relation relation, HeapTuple tup,
 					TransactionId xid, CommandId cid, int options);
+static XLogRecPtr log_heap_insert(Relation relation, Buffer buffer,
+				HeapTuple heaptup, int options, bool all_visible_cleared);
+static XLogRecPtr log_heap_delete(Relation relation, Buffer buffer,
+				HeapTuple tp, HeapTuple old_key_tuple, TransactionId new_xmax,
+				bool changingPart, bool all_visible_cleared);
 static XLogRecPtr log_heap_update(Relation reln, Buffer oldbuf,
 				Buffer newbuf, HeapTuple oldtup,
 				HeapTuple newtup, HeapTuple old_key_tup,
@@ -1889,6 +1894,7 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 	TransactionId xid = GetCurrentTransactionId();
 	HeapTuple	heaptup;
 	Buffer		buffer;
+	Page		page;
 	Buffer		vmbuffer = InvalidBuffer;
 	bool		all_visible_cleared = false;
 
@@ -1925,16 +1931,18 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 	 */
 	CheckForSerializableConflictIn(relation, NULL, InvalidBuffer);
 
+	page = BufferGetPage(buffer);
+
 	/* NO EREPORT(ERROR) from here till changes are logged */
 	START_CRIT_SECTION();
 
 	RelationPutHeapTuple(relation, buffer, heaptup,
 						 (options & HEAP_INSERT_SPECULATIVE) != 0);
 
-	if (PageIsAllVisible(BufferGetPage(buffer)))
+	if (PageIsAllVisible(page))
 	{
 		all_visible_cleared = true;
-		PageClearAllVisible(BufferGetPage(buffer));
+		PageClearAllVisible(page);
 		visibilitymap_clear(relation,
 							ItemPointerGetBlockNumber(&(heaptup->t_self)),
 							vmbuffer, VISIBILITYMAP_VALID_BITS);
@@ -1956,76 +1964,11 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 	/* XLOG stuff */
 	if (!(options & HEAP_INSERT_SKIP_WAL) && RelationNeedsWAL(relation))
 	{
-		xl_heap_insert xlrec;
-		xl_heap_header xlhdr;
 		XLogRecPtr	recptr;
-		Page		page = BufferGetPage(buffer);
-		uint8		info = XLOG_HEAP_INSERT;
-		int			bufflags = 0;
-
-		/*
-		 * If this is a catalog, we need to transmit combocids to properly
-		 * decode, so log that as well.
-		 */
-		if (RelationIsAccessibleInLogicalDecoding(relation))
-			log_heap_new_cid(relation, heaptup);
-
-		/*
-		 * If this is the single and first tuple on page, we can reinit the
-		 * page instead of restoring the whole thing.  Set flag, and hide
-		 * buffer references from XLogInsert.
-		 */
-		if (ItemPointerGetOffsetNumber(&(heaptup->t_self)) == FirstOffsetNumber &&
-			PageGetMaxOffsetNumber(page) == FirstOffsetNumber)
-		{
-			info |= XLOG_HEAP_INIT_PAGE;
-			bufflags |= REGBUF_WILL_INIT;
-		}
-
-		xlrec.offnum = ItemPointerGetOffsetNumber(&heaptup->t_self);
-		xlrec.flags = 0;
-		if (all_visible_cleared)
-			xlrec.flags |= XLH_INSERT_ALL_VISIBLE_CLEARED;
-		if (options & HEAP_INSERT_SPECULATIVE)
-			xlrec.flags |= XLH_INSERT_IS_SPECULATIVE;
-		Assert(ItemPointerGetBlockNumber(&heaptup->t_self) == BufferGetBlockNumber(buffer));
-
-		/*
-		 * For logical decoding, we need the tuple even if we're doing a full
-		 * page write, so make sure it's included even if we take a full-page
-		 * image. (XXX We could alternatively store a pointer into the FPW).
-		 */
-		if (RelationIsLogicallyLogged(relation) &&
-			!(options & HEAP_INSERT_NO_LOGICAL))
-		{
-			xlrec.flags |= XLH_INSERT_CONTAINS_NEW_TUPLE;
-			bufflags |= REGBUF_KEEP_DATA;
-		}
-
-		XLogBeginInsert();
-		XLogRegisterData((char *) &xlrec, SizeOfHeapInsert);
-
-		xlhdr.t_infomask2 = heaptup->t_data->t_infomask2;
-		xlhdr.t_infomask = heaptup->t_data->t_infomask;
-		xlhdr.t_hoff = heaptup->t_data->t_hoff;
-
-		/*
-		 * note we mark xlhdr as belonging to buffer; if XLogInsert decides to
-		 * write the whole page to the xlog, we don't need to store
-		 * xl_heap_header in the xlog.
-		 */
-		XLogRegisterBuffer(0, buffer, REGBUF_STANDARD | bufflags);
-		XLogRegisterBufData(0, (char *) &xlhdr, SizeOfHeapHeader);
-		/* PG73FORMAT: write bitmap [+ padding] [+ oid] + data */
-		XLogRegisterBufData(0,
-							(char *) heaptup->t_data + SizeofHeapTupleHeader,
-							heaptup->t_len - SizeofHeapTupleHeader);
-
-		/* filtering by origin on a row level is much more efficient */
-		XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);
-
-		recptr = XLogInsert(RM_HEAP_ID, info);
 
+		recptr = log_heap_insert(relation, buffer, heaptup,
+								 options, all_visible_cleared);
+			
 		PageSetLSN(page, recptr);
 	}
 
@@ -2744,58 +2687,10 @@ l1:
 	 */
 	if (RelationNeedsWAL(relation))
 	{
-		xl_heap_delete xlrec;
-		xl_heap_header xlhdr;
 		XLogRecPtr	recptr;
 
-		/* For logical decode we need combocids to properly decode the catalog */
-		if (RelationIsAccessibleInLogicalDecoding(relation))
-			log_heap_new_cid(relation, &tp);
-
-		xlrec.flags = 0;
-		if (all_visible_cleared)
-			xlrec.flags |= XLH_DELETE_ALL_VISIBLE_CLEARED;
-		if (changingPart)
-			xlrec.flags |= XLH_DELETE_IS_PARTITION_MOVE;
-		xlrec.infobits_set = compute_infobits(tp.t_data->t_infomask,
-											  tp.t_data->t_infomask2);
-		xlrec.offnum = ItemPointerGetOffsetNumber(&tp.t_self);
-		xlrec.xmax = new_xmax;
-
-		if (old_key_tuple != NULL)
-		{
-			if (relation->rd_rel->relreplident == REPLICA_IDENTITY_FULL)
-				xlrec.flags |= XLH_DELETE_CONTAINS_OLD_TUPLE;
-			else
-				xlrec.flags |= XLH_DELETE_CONTAINS_OLD_KEY;
-		}
-
-		XLogBeginInsert();
-		XLogRegisterData((char *) &xlrec, SizeOfHeapDelete);
-
-		XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
-
-		/*
-		 * Log replica identity of the deleted tuple if there is one
-		 */
-		if (old_key_tuple != NULL)
-		{
-			xlhdr.t_infomask2 = old_key_tuple->t_data->t_infomask2;
-			xlhdr.t_infomask = old_key_tuple->t_data->t_infomask;
-			xlhdr.t_hoff = old_key_tuple->t_data->t_hoff;
-
-			XLogRegisterData((char *) &xlhdr, SizeOfHeapHeader);
-			XLogRegisterData((char *) old_key_tuple->t_data
-							 + SizeofHeapTupleHeader,
-							 old_key_tuple->t_len
-							 - SizeofHeapTupleHeader);
-		}
-
-		/* filtering by origin on a row level is much more efficient */
-		XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);
-
-		recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE);
-
+		recptr = log_heap_delete(relation, buffer, &tp, old_key_tuple, new_xmax,
+								 changingPart, all_visible_cleared);
 		PageSetLSN(page, recptr);
 	}
 
@@ -7045,6 +6940,148 @@ log_heap_visible(RelFileNode rnode, Buffer heap_buffer, Buffer vm_buffer,
 	return recptr;
 }
 
+/*
+ * Perform XLogInsert for a heap-insert operation.  Caller must already
+ * have modified the buffer and marked it dirty.
+ */
+XLogRecPtr
+log_heap_insert(Relation relation, Buffer buffer,
+				HeapTuple heaptup, int options, bool all_visible_cleared)
+{
+	xl_heap_insert xlrec;
+	xl_heap_header xlhdr;
+	uint8		info = XLOG_HEAP_INSERT;
+	int			bufflags = 0;
+	Page		page = BufferGetPage(buffer);
+
+	/*
+	 * If this is a catalog, we need to transmit combocids to properly
+	 * decode, so log that as well.
+	 */
+	if (RelationIsAccessibleInLogicalDecoding(relation))
+		log_heap_new_cid(relation, heaptup);
+
+	/*
+	 * If this is the single and first tuple on page, we can reinit the
+	 * page instead of restoring the whole thing.  Set flag, and hide
+	 * buffer references from XLogInsert.
+	 */
+	if (ItemPointerGetOffsetNumber(&(heaptup->t_self)) == FirstOffsetNumber &&
+		PageGetMaxOffsetNumber(page) == FirstOffsetNumber)
+	{
+		info |= XLOG_HEAP_INIT_PAGE;
+		bufflags |= REGBUF_WILL_INIT;
+	}
+
+	xlrec.offnum = ItemPointerGetOffsetNumber(&heaptup->t_self);
+	xlrec.flags = 0;
+	if (all_visible_cleared)
+		xlrec.flags |= XLH_INSERT_ALL_VISIBLE_CLEARED;
+	if (options & HEAP_INSERT_SPECULATIVE)
+		xlrec.flags |= XLH_INSERT_IS_SPECULATIVE;
+	Assert(ItemPointerGetBlockNumber(&heaptup->t_self) == BufferGetBlockNumber(buffer));
+
+	/*
+	 * For logical decoding, we need the tuple even if we're doing a full
+	 * page write, so make sure it's included even if we take a full-page
+	 * image. (XXX We could alternatively store a pointer into the FPW).
+	 */
+	if (RelationIsLogicallyLogged(relation) &&
+		!(options & HEAP_INSERT_NO_LOGICAL))
+	{
+		xlrec.flags |= XLH_INSERT_CONTAINS_NEW_TUPLE;
+		bufflags |= REGBUF_KEEP_DATA;
+	}
+
+	XLogBeginInsert();
+	XLogRegisterData((char *) &xlrec, SizeOfHeapInsert);
+
+	xlhdr.t_infomask2 = heaptup->t_data->t_infomask2;
+	xlhdr.t_infomask = heaptup->t_data->t_infomask;
+	xlhdr.t_hoff = heaptup->t_data->t_hoff;
+
+	/*
+	 * note we mark xlhdr as belonging to buffer; if XLogInsert decides to
+	 * write the whole page to the xlog, we don't need to store
+	 * xl_heap_header in the xlog.
+	 */
+	XLogRegisterBuffer(0, buffer, REGBUF_STANDARD | bufflags);
+	XLogRegisterBufData(0, (char *) &xlhdr, SizeOfHeapHeader);
+	/* PG73FORMAT: write bitmap [+ padding] [+ oid] + data */
+	XLogRegisterBufData(0,
+						(char *) heaptup->t_data + SizeofHeapTupleHeader,
+						heaptup->t_len - SizeofHeapTupleHeader);
+
+	/* filtering by origin on a row level is much more efficient */
+	XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);
+
+	return XLogInsert(RM_HEAP_ID, info);
+}
+
+/*
+ * Perform XLogInsert for a heap-insert operation.  Caller must already
+ * have modified the buffer and marked it dirty.
+ *
+ * NB: heap_abort_speculative() uses the same xlog record and replay
+ * routines.
+ */
+static XLogRecPtr
+log_heap_delete(Relation relation, Buffer buffer,
+				HeapTuple tp, HeapTuple old_key_tuple, TransactionId new_xmax,
+				bool changingPart, bool all_visible_cleared)
+{
+	xl_heap_delete xlrec;
+	xl_heap_header xlhdr;
+
+	/* For logical decode we need combocids to properly decode the catalog */
+	if (RelationIsAccessibleInLogicalDecoding(relation))
+		log_heap_new_cid(relation, tp);
+
+	xlrec.flags = 0;
+	if (all_visible_cleared)
+		xlrec.flags |= XLH_DELETE_ALL_VISIBLE_CLEARED;
+	if (changingPart)
+		xlrec.flags |= XLH_DELETE_IS_PARTITION_MOVE;
+	xlrec.infobits_set = compute_infobits(tp->t_data->t_infomask,
+										  tp->t_data->t_infomask2);
+	xlrec.offnum = ItemPointerGetOffsetNumber(&tp->t_self);
+	xlrec.xmax = new_xmax;
+
+	if (old_key_tuple != NULL)
+	{
+		if (relation->rd_rel->relreplident == REPLICA_IDENTITY_FULL)
+			xlrec.flags |= XLH_DELETE_CONTAINS_OLD_TUPLE;
+		else
+			xlrec.flags |= XLH_DELETE_CONTAINS_OLD_KEY;
+	}
+
+	XLogBeginInsert();
+	XLogRegisterData((char *) &xlrec, SizeOfHeapDelete);
+
+	XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
+
+	/*
+	 * Log replica identity of the deleted tuple if there is one
+	 */
+	if (old_key_tuple != NULL)
+	{
+		xlhdr.t_infomask2 = old_key_tuple->t_data->t_infomask2;
+		xlhdr.t_infomask = old_key_tuple->t_data->t_infomask;
+		xlhdr.t_hoff = old_key_tuple->t_data->t_hoff;
+
+		XLogRegisterData((char *) &xlhdr, SizeOfHeapHeader);
+		XLogRegisterData((char *) old_key_tuple->t_data
+						 + SizeofHeapTupleHeader,
+						 old_key_tuple->t_len
+						 - SizeofHeapTupleHeader);
+	}
+
+	/* filtering by origin on a row level is much more efficient */
+	XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);
+
+	return XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE);
+}
+
 /*
  * Perform XLogInsert for a heap-update operation.  Caller must already
  * have modified the buffer(s) and marked them dirty.
-- 
2.16.3


----Next_Part(Mon_Mar_25_21_32_04_2019_838)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v8-0004-Add-infrastructure-to-WAL-logging-skip-feature.patch"



^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread

* [PATCH v2] Fix pg_control corruption in EXEC_BACKEND startup.
@ 2024-05-18 01:41 Thomas Munro <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Thomas Munro @ 2024-05-18 01:41 UTC (permalink / raw)

When backend processes were launched in EXEC_BACKEND builds, they would
run LocalProcessControlFile() to read in pg_control and extract several
important settings.

This happens too early to acquire ControlFileLock, and the postmaster is
also not allowed to acquire ControlFileLock, so it can't safely take a
copy to give to the child.

Instead, pass down the "proto-controlfile" that was read by the
postmaster in LocalProcessControlFile().  Introduce functions
ExportProtoControlFile() and ImportProtoControlFile() to allow that.
Subprocesses will extract information from that, and then later attach
to the current control file in shared memory.

Reported-by: Melanie Plageman <[email protected]> per Windows CI failure
Discussion: https://postgr.es/m/CAAKRu_YNGwEYrorQYza_W8tU%2B%3DtoXRHG8HpyHC-KDbZqA_ZVSA%40mail.gmail.com
---
 src/backend/access/transam/xlog.c       | 46 +++++++++++++++++++++++--
 src/backend/postmaster/launch_backend.c | 21 +++++++----
 src/include/access/xlog.h               |  5 +++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..e52517eb9c1 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -575,6 +575,10 @@ static WALInsertLockPadded *WALInsertLocks = NULL;
  */
 static ControlFileData *ControlFile = NULL;
 
+#ifdef EXEC_BACKEND
+static ControlFileData *ProtoControlFile = NULL;
+#endif
+
 /*
  * Calculate the amount of space left on the page after 'endptr'. Beware
  * multiple evaluation!
@@ -692,6 +696,7 @@ static bool PerformRecoveryXLogAction(void);
 static void InitControlFile(uint64 sysidentifier, uint32 data_checksum_version);
 static void WriteControlFile(void);
 static void ReadControlFile(void);
+static void ScanControlFile(void);
 static void UpdateControlFile(void);
 static char *str_time(pg_time_t tnow, char *buf, size_t bufsize);
 
@@ -4385,9 +4390,7 @@ WriteControlFile(void)
 static void
 ReadControlFile(void)
 {
-	pg_crc32c	crc;
 	int			fd;
-	char		wal_segsz_str[20];
 	int			r;
 
 	/*
@@ -4420,6 +4423,15 @@ ReadControlFile(void)
 
 	close(fd);
 
+	ScanControlFile();
+}
+
+static void
+ScanControlFile(void)
+{
+	static char wal_segsz_str[20];
+	pg_crc32c	crc;
+
 	/*
 	 * Check for expected pg_control format version.  If this is wrong, the
 	 * CRC check will likely fail because we'll be checking the wrong number
@@ -4941,8 +4953,33 @@ LocalProcessControlFile(bool reset)
 	Assert(reset || ControlFile == NULL);
 	ControlFile = palloc_object(ControlFileData);
 	ReadControlFile();
+
+#ifdef EXEC_BACKEND
+	/* We need to be able to give this to subprocesses. */
+	ProtoControlFile = ControlFile;
+#endif
 }
 
+#ifdef EXEC_BACKEND
+void
+ExportProtoControlFile(ControlFileData *copy)
+{
+	*copy = *ProtoControlFile;
+}
+
+/*
+ * Like LocalProcessControlFile(), but used early in EXEC_BACKEND children's
+ * startup.  This receives the same file that the postmaster first read.
+ */
+void
+ImportProtoControlFile(const ControlFileData *copy)
+{
+	ControlFile = palloc(sizeof(ControlFileData));
+	*ControlFile = *copy;
+	ScanControlFile();
+}
+#endif
+
 /*
  * Get the wal_level from the control file. For a standby, this value should be
  * considered as its active wal_level, because it may be different from what
@@ -5061,7 +5098,12 @@ XLOGShmemInit(void)
 	if (localControlFile)
 	{
 		memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
+#ifdef EXEC_BACKEND
+		/* We still hold a reference to give to subprocesses. */
+		Assert(ProtoControlFile == localControlFile);
+#else
 		pfree(localControlFile);
+#endif
 	}
 
 	/*
diff --git a/src/backend/postmaster/launch_backend.c b/src/backend/postmaster/launch_backend.c
index 45690b11c99..e08a405f949 100644
--- a/src/backend/postmaster/launch_backend.c
+++ b/src/backend/postmaster/launch_backend.c
@@ -33,6 +33,9 @@
 
 #include <unistd.h>
 
+#include "access/xlog.h"
+#include "catalog/pg_control.h"
+#include "common/file_utils.h"
 #include "libpq/libpq-be.h"
 #include "miscadmin.h"
 #include "postmaster/autovacuum.h"
@@ -133,6 +136,14 @@ typedef struct
 
 	int			MyPMChildSlot;
 
+	/*
+	 * A copy of the ControlFileData from early in Postmaster startup.  We
+	 * need to access its contents it at a phase of initialization before we
+	 * are allowed to acquire LWLocks, so we can't just use shared memory or
+	 * read the file from disk.
+	 */
+	ControlFileData proto_controlfile;
+
 	/*
 	 * These are only used by backend processes, but are here because passing
 	 * a socket needs some special handling on Windows. 'client_sock' is an
@@ -659,12 +670,6 @@ SubPostmasterMain(int argc, char *argv[])
 	 */
 	checkDataDir();
 
-	/*
-	 * (re-)read control file, as it contains config. The postmaster will
-	 * already have read this, but this process doesn't know about that.
-	 */
-	LocalProcessControlFile(false);
-
 	/*
 	 * Reload any libraries that were preloaded by the postmaster.  Since we
 	 * exec'd this process, those libraries didn't come along with us; but we
@@ -752,6 +757,8 @@ save_backend_variables(BackendParameters *param,
 	param->MaxBackends = MaxBackends;
 	param->num_pmchild_slots = num_pmchild_slots;
 
+	ExportProtoControlFile(&param->proto_controlfile);
+
 #ifdef WIN32
 	param->PostmasterHandle = PostmasterHandle;
 	if (!write_duplicated_handle(&param->initial_signal_pipe,
@@ -1026,6 +1033,8 @@ restore_backend_variables(BackendParameters *param)
 
 	strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
 
+	ImportProtoControlFile(&param->proto_controlfile);
+
 	/*
 	 * We need to restore fd.c's counts of externally-opened FDs; to avoid
 	 * confusion, be sure to do this after restoring max_safe_fds.  (Note:
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index fdfb572467b..f1f3ad4e96e 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -208,6 +208,7 @@ typedef enum WALAvailability
 
 struct XLogRecData;
 struct XLogReaderState;
+struct ControlFileData;
 
 extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
 								   XLogRecPtr fpw_lsn,
@@ -250,6 +251,10 @@ extern void XLOGShmemInit(void);
 extern void BootStrapXLOG(uint32 data_checksum_version);
 extern void InitializeWalConsistencyChecking(void);
 extern void LocalProcessControlFile(bool reset);
+#ifdef EXEC_BACKEND
+extern void ExportProtoControlFile(struct ControlFileData *copy);
+extern void ImportProtoControlFile(const struct ControlFileData *copy);
+#endif
 extern WalLevel GetActiveWalLevelOnStandby(void);
 extern void StartupXLOG(void);
 extern void ShutdownXLOG(int code, Datum arg);
-- 
2.47.3


--dhbc6bswyy6qufwn--





^ permalink  raw  reply  [nested|flat] 267+ messages in thread