fix-segment-reread-after-tli-switch-1.patch

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 8614907..045d21d 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -572,6 +572,7 @@ static uint32 readRecordBufSize = 0;
 static XLogRecPtr ReadRecPtr;	/* start of last record read */
 static XLogRecPtr EndRecPtr;	/* end+1 of last record read */
 static TimeLineID lastPageTLI = 0;
+static TimeLineID lastSegmentTLI = 0;
 
 static XLogRecPtr minRecoveryPoint;		/* local copy of
 										 * ControlFile->minRecoveryPoint */
@@ -655,7 +656,7 @@ static void CleanupBackupHistory(void);
 static void UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force);
 static XLogRecord *ReadRecord(XLogRecPtr *RecPtr, int emode, bool fetching_ckpt);
 static void CheckRecoveryConsistency(void);
-static bool ValidXLOGHeader(XLogPageHeader hdr, int emode);
+static bool ValidXLOGHeader(XLogPageHeader hdr, int emode, bool segmentonly);
 static XLogRecord *ReadCheckpointRecord(XLogRecPtr RecPtr, int whichChkpt);
 static List *readTimeLineHistory(TimeLineID targetTLI);
 static bool existsTimeLineHistory(TimeLineID probeTLI);
@@ -3927,7 +3928,7 @@ ReadRecord(XLogRecPtr *RecPtr, int emode, bool fetching_ckpt)
 		 * to go backwards (but we can't reset that variable right here, since
 		 * we might not change files at all).
 		 */
-		lastPageTLI = 0;		/* see comment in ValidXLOGHeader */
+		lastPageTLI = lastSegmentTLI = 0;	/* see comment in ValidXLOGHeader */
 		randAccess = true;		/* allow curFileTLI to go backwards too */
 	}
 
@@ -4190,7 +4191,7 @@ next_record_is_invalid:
  * ReadRecord.	It's not intended for use from anywhere else.
  */
 static bool
-ValidXLOGHeader(XLogPageHeader hdr, int emode)
+ValidXLOGHeader(XLogPageHeader hdr, int emode, bool segmentonly)
 {
 	XLogRecPtr	recaddr;
 
@@ -4285,18 +4286,31 @@ ValidXLOGHeader(XLogPageHeader hdr, int emode)
 	 * successive pages of a consistent WAL sequence.
 	 *
 	 * Of course this check should only be applied when advancing sequentially
-	 * across pages; therefore ReadRecord resets lastPageTLI to zero when
-	 * going to a random page.
+	 * across pages; therefore ReadRecord resets lastPageTLI and
+	 * lastSegmentTLI to zero when going to a random page.
+	 *
+	 * Sometimes we re-open a segment that's already been partially replayed.
+	 * In that case we cannot perform the normal TLI check: if there is a
+	 * timeline switch within the segment, the first page has a smaller TLI
+	 * than later pages following the timeline switch, and we might've read
+	 * them already. As a weaker test, we still check that it's not smaller
+	 * than the TLI we last saw at the beginning of a segment. Pass
+	 * segmentonly = true when re-validating the first page like that, and the
+	 * page you're actually interested in comes later.
 	 */
-	if (hdr->xlp_tli < lastPageTLI)
+	if (hdr->xlp_tli < (segmentonly ? lastSegmentTLI : lastPageTLI))
 	{
 		ereport(emode_for_corrupt_record(emode, recaddr),
 				(errmsg("out-of-sequence timeline ID %u (after %u) in log file %u, segment %u, offset %u",
-						hdr->xlp_tli, lastPageTLI,
+						hdr->xlp_tli,
+						segmentonly ? lastSegmentTLI : lastPageTLI,
 						readId, readSeg, readOff)));
 		return false;
 	}
 	lastPageTLI = hdr->xlp_tli;
+	if (readOff == 0)
+		lastSegmentTLI = hdr->xlp_tli;
+
 	return true;
 }
 
@@ -10440,7 +10454,7 @@ retry:
 							readId, readSeg, readOff)));
 			goto next_record_is_invalid;
 		}
-		if (!ValidXLOGHeader((XLogPageHeader) readBuf, emode))
+		if (!ValidXLOGHeader((XLogPageHeader) readBuf, emode, true))
 			goto next_record_is_invalid;
 	}
 
@@ -10462,7 +10476,7 @@ retry:
 				readId, readSeg, readOff)));
 		goto next_record_is_invalid;
 	}
-	if (!ValidXLOGHeader((XLogPageHeader) readBuf, emode))
+	if (!ValidXLOGHeader((XLogPageHeader) readBuf, emode, false))
 		goto next_record_is_invalid;
 
 	Assert(targetId == readId);