Address set of issues with errno handling

System calls mixed up in error code paths are causing two issues which
several code paths have not correctly handled:
1) For write() calls, sometimes the system may return less bytes than
what has been written without errno being set.  Some paths were careful
enough to consider that case, and assumed that errno should be set to
ENOSPC, other calls missed that.
2) errno generated by a system call is overwritten by other system calls
which may succeed once an error code path is taken, causing what is
reported to the user to be incorrect.

This patch uses the brute-force approach of correcting all those code
paths.  Some refactoring could happen in the future, but this is let as
future work, which is not targeted for back-branches anyway.

Author: Michael Paquier
Reviewed-by: Ashutosh Sharma
Discussion: https://postgr.es/m/[email protected]

9 files changed, 86 insertions, 4 deletions

diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c
index 8d3c861a330..ed7ba181c79 100644
--- a/src/backend/access/heap/rewriteheap.c
+++ b/src/backend/access/heap/rewriteheap.c
@@ -1168,9 +1168,14 @@ heap_xlog_logical_rewrite(XLogReaderState *r)
 	/* write out tail end of mapping file (again) */
 	pgstat_report_wait_start(WAIT_EVENT_LOGICAL_REWRITE_MAPPING_WRITE);
 	if (write(fd, data, len) != len)
+	{
+		/* if write didn't set errno, assume problem is no disk space */
+		if (errno == 0)
+			errno = ENOSPC;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not write to file \"%s\": %m", path)));
+	}
 	pgstat_report_wait_end();
 
 	/*
diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c
index 65194db70e3..a9ef1b3d73c 100644
--- a/src/backend/access/transam/twophase.c
+++ b/src/backend/access/transam/twophase.c
@@ -1241,12 +1241,17 @@ ReadTwoPhaseFile(TransactionId xid, bool give_warnings)
 	 */
 	if (fstat(fd, &stat))
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(fd);
 		if (give_warnings)
+		{
+			errno = save_errno;
 			ereport(WARNING,
 					(errcode_for_file_access(),
 					 errmsg("could not stat two-phase state file \"%s\": %m",
 							path)));
+		}
 		return NULL;
 	}
 
@@ -1274,13 +1279,18 @@ ReadTwoPhaseFile(TransactionId xid, bool give_warnings)
 	pgstat_report_wait_start(WAIT_EVENT_TWOPHASE_FILE_READ);
 	if (read(fd, buf, stat.st_size) != stat.st_size)
 	{
+		int			save_errno = errno;
+
 		pgstat_report_wait_end();
 		CloseTransientFile(fd);
 		if (give_warnings)
+		{
+			errno = save_errno;
 			ereport(WARNING,
 					(errcode_for_file_access(),
 					 errmsg("could not read two-phase state file \"%s\": %m",
 							path)));
+		}
 		pfree(buf);
 		return NULL;
 	}
@@ -1663,16 +1673,26 @@ RecreateTwoPhaseFile(TransactionId xid, void *content, int len)
 	pgstat_report_wait_start(WAIT_EVENT_TWOPHASE_FILE_WRITE);
 	if (write(fd, content, len) != len)
 	{
+		int			save_errno = errno;
+
 		pgstat_report_wait_end();
 		CloseTransientFile(fd);
+
+		/* if write didn't set errno, assume problem is no disk space */
+		errno = save_errno ? save_errno : ENOSPC;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not write two-phase state file: %m")));
 	}
 	if (write(fd, &statefile_crc, sizeof(pg_crc32c)) != sizeof(pg_crc32c))
 	{
+		int			save_errno = errno;
+
 		pgstat_report_wait_end();
 		CloseTransientFile(fd);
+
+		/* if write didn't set errno, assume problem is no disk space */
+		errno = save_errno ? save_errno : ENOSPC;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not write two-phase state file: %m")));
@@ -1686,7 +1706,10 @@ RecreateTwoPhaseFile(TransactionId xid, void *content, int len)
 	pgstat_report_wait_start(WAIT_EVENT_TWOPHASE_FILE_SYNC);
 	if (pg_fsync(fd) != 0)
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(fd);
+		errno = save_errno;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not fsync two-phase state file: %m")));
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index adbd6a21264..1a419aa49bf 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -3268,7 +3268,10 @@ XLogFileInit(XLogSegNo logsegno, bool *use_existent, bool use_lock)
 	pgstat_report_wait_start(WAIT_EVENT_WAL_INIT_SYNC);
 	if (pg_fsync(fd) != 0)
 	{
+		int			save_errno = errno;
+
 		close(fd);
+		errno = save_errno;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not fsync file \"%s\": %m", tmppath)));
@@ -11675,8 +11678,10 @@ retry:
 	if (lseek(readFile, (off_t) readOff, SEEK_SET) < 0)
 	{
 		char		fname[MAXFNAMELEN];
+		int			save_errno = errno;
 
 		XLogFileName(fname, curFileTLI, readSegNo, wal_segment_size);
+		errno = save_errno;
 		ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen),
 				(errcode_for_file_access(),
 				 errmsg("could not seek in log segment %s to offset %u: %m",
@@ -11688,9 +11693,11 @@ retry:
 	if (read(readFile, readBuf, XLOG_BLCKSZ) != XLOG_BLCKSZ)
 	{
 		char		fname[MAXFNAMELEN];
+		int			save_errno = errno;
 
 		pgstat_report_wait_end();
 		XLogFileName(fname, curFileTLI, readSegNo, wal_segment_size);
+		errno = save_errno;
 		ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen),
 				(errcode_for_file_access(),
 				 errmsg("could not read from log segment %s, offset %u: %m",
diff --git a/src/backend/access/transam/xlogutils.c b/src/backend/access/transam/xlogutils.c
index 52fe55e2afb..4ecdc9220f0 100644
--- a/src/backend/access/transam/xlogutils.c
+++ b/src/backend/access/transam/xlogutils.c
@@ -718,9 +718,10 @@ XLogRead(char *buf, int segsize, TimeLineID tli, XLogRecPtr startptr,
 			if (lseek(sendFile, (off_t) startoff, SEEK_SET) < 0)
 			{
 				char		path[MAXPGPATH];
+				int			save_errno = errno;
 
 				XLogFilePath(path, tli, sendSegNo, segsize);
-
+				errno = save_errno;
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not seek in log segment %s to offset %u: %m",
@@ -741,9 +742,10 @@ XLogRead(char *buf, int segsize, TimeLineID tli, XLogRecPtr startptr,
 		if (readbytes <= 0)
 		{
 			char		path[MAXPGPATH];
+			int			save_errno = errno;
 
 			XLogFilePath(path, tli, sendSegNo, segsize);
-
+			errno = save_errno;
 			ereport(ERROR,
 					(errcode_for_file_access(),
 					 errmsg("could not read from log segment %s, offset %u, length %lu: %m",
diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c
index 5688cbe2e9a..3f1eae38a92 100644
--- a/src/backend/replication/basebackup.c
+++ b/src/backend/replication/basebackup.c
@@ -495,6 +495,8 @@ perform_base_backup(basebackup_options *opt)
 			fp = AllocateFile(pathbuf, "rb");
 			if (fp == NULL)
 			{
+				int			save_errno = errno;
+
 				/*
 				 * Most likely reason for this is that the file was already
 				 * removed by a checkpoint, so check for that to get a better
@@ -502,6 +504,7 @@ perform_base_backup(basebackup_options *opt)
 				 */
 				CheckXLogRemoved(segno, tli);
 
+				errno = save_errno;
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not open file \"%s\": %m", pathbuf)));
diff --git a/src/backend/replication/logical/origin.c b/src/backend/replication/logical/origin.c
index 963878a5d87..3d3f6dff1b0 100644
--- a/src/backend/replication/logical/origin.c
+++ b/src/backend/replication/logical/origin.c
@@ -578,7 +578,12 @@ CheckPointReplicationOrigin(void)
 	/* write magic */
 	if ((write(tmpfd, &magic, sizeof(magic))) != sizeof(magic))
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(tmpfd);
+
+		/* if write didn't set errno, assume problem is no disk space */
+		errno = save_errno ? save_errno : ENOSPC;
 		ereport(PANIC,
 				(errcode_for_file_access(),
 				 errmsg("could not write to file \"%s\": %m",
@@ -617,7 +622,12 @@ CheckPointReplicationOrigin(void)
 		if ((write(tmpfd, &disk_state, sizeof(disk_state))) !=
 			sizeof(disk_state))
 		{
+			int			save_errno = errno;
+
 			CloseTransientFile(tmpfd);
+
+			/* if write didn't set errno, assume problem is no disk space */
+			errno = save_errno ? save_errno : ENOSPC;
 			ereport(PANIC,
 					(errcode_for_file_access(),
 					 errmsg("could not write to file \"%s\": %m",
@@ -633,7 +643,12 @@ CheckPointReplicationOrigin(void)
 	FIN_CRC32C(crc);
 	if ((write(tmpfd, &crc, sizeof(crc))) != sizeof(crc))
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(tmpfd);
+
+		/* if write didn't set errno, assume problem is no disk space */
+		errno = save_errno ? save_errno : ENOSPC;
 		ereport(PANIC,
 				(errcode_for_file_access(),
 				 errmsg("could not write to file \"%s\": %m",
diff --git a/src/backend/replication/logical/reorderbuffer.c b/src/backend/replication/logical/reorderbuffer.c
index e2f59bf5808..3799ad4011e 100644
--- a/src/backend/replication/logical/reorderbuffer.c
+++ b/src/backend/replication/logical/reorderbuffer.c
@@ -2304,7 +2304,9 @@ ReorderBufferSerializeChange(ReorderBuffer *rb, ReorderBufferTXN *txn,
 		int			save_errno = errno;
 
 		CloseTransientFile(fd);
-		errno = save_errno;
+
+		/* if write didn't set errno, assume problem is no disk space */
+		errno = save_errno ? save_errno : ENOSPC;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not write to data file for XID %u: %m",
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 4123cdebcfd..2c4a1bab4b4 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1605,7 +1605,12 @@ SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn)
 	pgstat_report_wait_start(WAIT_EVENT_SNAPBUILD_WRITE);
 	if ((write(fd, ondisk, needed_length)) != needed_length)
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(fd);
+
+		/* if write didn't set errno, assume problem is no disk space */
+		errno = save_errno ? save_errno : ENOSPC;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not write to file \"%s\": %m", tmppath)));
@@ -1623,7 +1628,10 @@ SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn)
 	pgstat_report_wait_start(WAIT_EVENT_SNAPBUILD_SYNC);
 	if (pg_fsync(fd) != 0)
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(fd);
+		errno = save_errno;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not fsync file \"%s\": %m", tmppath)));
@@ -1708,7 +1716,10 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	pgstat_report_wait_end();
 	if (readBytes != SnapBuildOnDiskConstantSize)
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(fd);
+		errno = save_errno;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not read file \"%s\", read %d of %d: %m",
@@ -1736,7 +1747,10 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	pgstat_report_wait_end();
 	if (readBytes != sizeof(SnapBuild))
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(fd);
+		errno = save_errno;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not read file \"%s\", read %d of %d: %m",
@@ -1753,7 +1767,10 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	pgstat_report_wait_end();
 	if (readBytes != sz)
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(fd);
+		errno = save_errno;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not read file \"%s\", read %d of %d: %m",
@@ -1769,7 +1786,10 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	pgstat_report_wait_end();
 	if (readBytes != sz)
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(fd);
+		errno = save_errno;
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not read file \"%s\", read %d of %d: %m",
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index e8b76b2f207..f5927b4d1d3 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1274,7 +1274,9 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 
 		pgstat_report_wait_end();
 		CloseTransientFile(fd);
-		errno = save_errno;
+
+		/* if write didn't set errno, assume problem is no disk space */
+		errno = save_errno ? save_errno : ENOSPC;
 		ereport(elevel,
 				(errcode_for_file_access(),
 				 errmsg("could not write to file \"%s\": %m",
@@ -1378,7 +1380,10 @@ RestoreSlotFromDisk(const char *name)
 	pgstat_report_wait_start(WAIT_EVENT_REPLICATION_SLOT_RESTORE_SYNC);
 	if (pg_fsync(fd) != 0)
 	{
+		int			save_errno = errno;
+
 		CloseTransientFile(fd);
+		errno = save_errno;
 		ereport(PANIC,
 				(errcode_for_file_access(),
 				 errmsg("could not fsync file \"%s\": %m",