agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v3 2/7] Row pattern recognition patch (parse/analysis).
267+ messages / 2 participants
[nested] [flat]

* [PATCH v3 2/7] Row pattern recognition patch (parse/analysis).
@ 2023-07-26 10:49  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 267+ messages in thread

From: Tatsuo Ishii @ 2023-07-26 10:49 UTC (permalink / raw)

---
 src/backend/parser/parse_agg.c    |   7 ++
 src/backend/parser/parse_clause.c | 190 +++++++++++++++++++++++++++++-
 src/backend/parser/parse_expr.c   |   4 +
 src/backend/parser/parse_func.c   |   3 +
 4 files changed, 203 insertions(+), 1 deletion(-)

diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c
index 85cd47b7ae..aa7a1cee80 100644
--- a/src/backend/parser/parse_agg.c
+++ b/src/backend/parser/parse_agg.c
@@ -564,6 +564,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr)
 			errkind = true;
 			break;
 
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
+
 			/*
 			 * There is intentionally no default: case here, so that the
 			 * compiler will warn if we add a new ParseExprKind without
@@ -953,6 +957,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc,
 		case EXPR_KIND_CYCLE_MARK:
 			errkind = true;
 			break;
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
 
 			/*
 			 * There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c
index 334b9b42bd..ea2decc579 100644
--- a/src/backend/parser/parse_clause.c
+++ b/src/backend/parser/parse_clause.c
@@ -100,7 +100,10 @@ static WindowClause *findWindowClause(List *wclist, const char *name);
 static Node *transformFrameOffset(ParseState *pstate, int frameOptions,
 								  Oid rangeopfamily, Oid rangeopcintype, Oid *inRangeFunc,
 								  Node *clause);
-
+static void  transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef);
+static List *transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef);
+static void transformPatternClause(ParseState *pstate, WindowClause *wc, WindowDef *windef);
+static List *transformMeasureClause(ParseState *pstate, WindowClause *wc, WindowDef *windef);
 
 /*
  * transformFromClause -
@@ -2950,6 +2953,10 @@ transformWindowDefinitions(ParseState *pstate,
 											 rangeopfamily, rangeopcintype,
 											 &wc->endInRangeFunc,
 											 windef->endOffset);
+
+		/* Process Row Pattern Recognition related clauses */
+		transformRPR(pstate, wc, windef);
+
 		wc->runCondition = NIL;
 		wc->winref = winref;
 
@@ -3815,3 +3822,184 @@ transformFrameOffset(ParseState *pstate, int frameOptions,
 
 	return node;
 }
+
+/*
+ * transformRPR
+ *		Process Row Pattern Recognition related clauses
+ */
+static void
+transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef)
+{
+	/* Check Frame option. Frame must start at current row */
+
+	/*
+	 * Window definition exists?
+	 */
+	if (windef == NULL)
+		return;
+
+	/*
+	 * Row Pattern Common Syntax clause exists?
+	 */
+	if (windef->rpCommonSyntax == NULL)
+		return;
+
+	if ((wc->frameOptions & FRAMEOPTION_START_CURRENT_ROW) == 0)
+		ereport(ERROR,
+				(errcode(ERRCODE_SYNTAX_ERROR),
+				 errmsg("FRAME must start at current row when row patttern recognition is used")));
+
+	/* Transform AFTER MACH SKIP TO clause */
+	wc->rpSkipTo = windef->rpCommonSyntax->rpSkipTo;
+
+	/* Transform SEEK or INITIAL clause */
+	wc->initial = windef->rpCommonSyntax->initial;
+
+	/* Transform DEFINE clause into list of TargetEntry's */
+	wc->defineClause = transformDefineClause(pstate, wc, windef);
+
+	/* Check PATTERN clause and copy to patternClause */
+	transformPatternClause(pstate, wc, windef);
+
+	/* Transform MEASURE clause */
+	transformMeasureClause(pstate, wc, windef);
+}
+
+/*
+ * transformDefineClause Process DEFINE clause and transform ResTarget into
+ *		list of TargetEntry.
+ *
+ * XXX we only support column reference in row pattern definition search
+ * condition, e.g. "price". <row pattern definition variable name>.<column
+ * reference> is not supported, e.g. "A.price".
+ */
+static List *
+transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef)
+{
+	ListCell	*lc;
+	ResTarget	*restarget, *r;
+	List		*restargets;
+
+
+	/*
+	 * If Row Definition Common Syntax exists, DEFINE clause must exist.
+	 * (the raw parser should have already checked it.)
+	 */
+	Assert(windef->rpCommonSyntax->rpDefs != NULL);
+
+	/*
+	 * Check for duplicate row pattern definition variables.  The standard
+	 * requires that no two row pattern definition variable names shall be
+	 * equivalent.
+	 */
+	restargets = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpDefs)
+	{
+		char	*name;
+		ListCell	*l;
+
+		restarget = (ResTarget *)lfirst(lc);
+		name = restarget->name;
+
+		/*
+		 * Make sure that row pattern definition search condition is a boolean
+		 * expression.
+		 */
+		transformWhereClause(pstate, restarget->val,
+							 EXPR_KIND_RPR_DEFINE, "DEFINE");
+
+		foreach(l, restargets)
+		{
+			char		*n;
+
+			r = (ResTarget *) lfirst(l);
+			n = r->name;
+
+			if (!strcmp(n, name))
+				ereport(ERROR,
+						(errcode(ERRCODE_SYNTAX_ERROR),
+						 errmsg("row pattern definition variable name \"%s\" appears more than once in DEFINE clause",
+								name),
+						 parser_errposition(pstate, exprLocation((Node *)r))));
+		}
+		restargets = lappend(restargets, restarget);
+	}
+	list_free(restargets);
+
+	return transformTargetList(pstate, windef->rpCommonSyntax->rpDefs,
+							   EXPR_KIND_RPR_DEFINE);
+}
+
+/*
+ * transformPatternClause
+ *		Process PATTERN clause and return PATTERN clause in the raw parse tree
+ */
+static void
+transformPatternClause(ParseState *pstate, WindowClause *wc, WindowDef *windef)
+{
+	ListCell	*lc, *l;
+
+	/*
+	 * Row Pattern Common Syntax clause exists?
+	 */
+	if (windef->rpCommonSyntax == NULL)
+		return;
+
+	/*
+	 * Primary row pattern variable names in PATTERN clause must appear in
+	 * DEFINE clause as row pattern definition variable names.
+	 */
+	wc->patternVariable = NIL;
+	wc->patternRegexp = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpPatterns)
+	{
+		A_Expr	*a;
+		char	*name;
+		char	*regexp;
+		bool	found = false;
+
+		if (!IsA(lfirst(lc), A_Expr))
+			ereport(ERROR,
+					errmsg("node type is not A_Expr"));
+
+		a = (A_Expr *)lfirst(lc);
+		name = strVal(a->lexpr);
+
+		foreach(l, windef->rpCommonSyntax->rpDefs)
+		{
+			ResTarget	*restarget = (ResTarget *)lfirst(l);
+
+			if (!strcmp(restarget->name, name))
+			{
+				found = true;
+				break;
+			}
+		}
+
+		if (!found)
+			ereport(ERROR,
+					(errcode(ERRCODE_SYNTAX_ERROR),
+					 errmsg("primary row pattern variable name \"%s\" does not appear in DEFINE clause",
+							name),
+					 parser_errposition(pstate, exprLocation((Node *)a))));
+		wc->patternVariable = lappend(wc->patternVariable, makeString(pstrdup(name)));
+		regexp = strVal(lfirst(list_head(a->name)));
+		wc->patternRegexp = lappend(wc->patternRegexp, makeString(pstrdup(regexp)));
+	}
+}
+
+/*
+ * transformMeasureClause
+ *		Process MEASURE clause
+ */
+static List *
+transformMeasureClause(ParseState *pstate, WindowClause *wc, WindowDef *windef)
+{
+	if (windef->rowPatternMeasures == NIL)
+		return NIL;
+
+	ereport(ERROR,
+			(errcode(ERRCODE_SYNTAX_ERROR),
+			 errmsg("%s","MEASURE clause is not supported yet"),
+			 parser_errposition(pstate, exprLocation((Node *)windef->rowPatternMeasures))));
+}
diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c
index fed8e4d089..8921b7ae01 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -557,6 +557,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref)
 		case EXPR_KIND_COPY_WHERE:
 		case EXPR_KIND_GENERATED_COLUMN:
 		case EXPR_KIND_CYCLE_MARK:
+		case EXPR_KIND_RPR_DEFINE:
 			/* okay */
 			break;
 
@@ -1770,6 +1771,7 @@ transformSubLink(ParseState *pstate, SubLink *sublink)
 		case EXPR_KIND_VALUES:
 		case EXPR_KIND_VALUES_SINGLE:
 		case EXPR_KIND_CYCLE_MARK:
+		case EXPR_KIND_RPR_DEFINE:
 			/* okay */
 			break;
 		case EXPR_KIND_CHECK_CONSTRAINT:
@@ -3149,6 +3151,8 @@ ParseExprKindName(ParseExprKind exprKind)
 			return "GENERATED AS";
 		case EXPR_KIND_CYCLE_MARK:
 			return "CYCLE";
+		case EXPR_KIND_RPR_DEFINE:
+			return "DEFINE";
 
 			/*
 			 * There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_func.c b/src/backend/parser/parse_func.c
index b3f0b6a137..2ff3699538 100644
--- a/src/backend/parser/parse_func.c
+++ b/src/backend/parser/parse_func.c
@@ -2656,6 +2656,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location)
 		case EXPR_KIND_CYCLE_MARK:
 			errkind = true;
 			break;
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
 
 			/*
 			 * There is intentionally no default: case here, so that the
-- 
2.25.1


----Next_Part(Wed_Jul_26_21_21_34_2023_317)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v3-0003-Row-pattern-recognition-patch-planner.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

* [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