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/20180622061535.GD5215@paquier.xyz

5 files changed, 47 insertions, 2 deletions

diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c
index b7d732a7d8f..8259ec5bd89 100644
--- a/src/backend/replication/basebackup.c
+++ b/src/backend/replication/basebackup.c
@@ -388,6 +388,8 @@ perform_base_backup(basebackup_options *opt, DIR *tblspcdir)
 			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
@@ -395,6 +397,7 @@ perform_base_backup(basebackup_options *opt, DIR *tblspcdir)
 				 */
 				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 ad99739971e..6fccdd86544 100644
--- a/src/backend/replication/logical/origin.c
+++ b/src/backend/replication/logical/origin.c
@@ -549,7 +549,12 @@ 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",
@@ -588,7 +593,12 @@ 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",
@@ -604,7 +614,12 @@ 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 71fa528bbb4..97c6721a7d5 100644
--- a/src/backend/replication/logical/reorderbuffer.c
+++ b/src/backend/replication/logical/reorderbuffer.c
@@ -2241,7 +2241,9 @@ 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 f4b1fea0f84..18dec24b352 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1566,7 +1566,12 @@ SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn)
 
 	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)));
@@ -1582,7 +1587,10 @@ SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn)
 	 */
 	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)));
@@ -1664,7 +1672,10 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	readBytes = read(fd, &ondisk, SnapBuildOnDiskConstantSize);
 	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",
@@ -1690,7 +1701,10 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	readBytes = read(fd, &ondisk.builder, sizeof(SnapBuild));
 	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",
@@ -1705,7 +1719,10 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	readBytes = read(fd, ondisk.builder.was_running.was_xip, sz);
 	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",
@@ -1719,7 +1736,10 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	readBytes = read(fd, ondisk.builder.committed.xip, sz);
 	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 e37098faffb..a5bc452d812 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1033,7 +1033,9 @@ SaveSlotToPath(ReplicationSlot *slot, const char *dir, int elevel)
 		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(elevel,
 				(errcode_for_file_access(),
 				 errmsg("could not write to file \"%s\": %m",
@@ -1136,7 +1138,10 @@ RestoreSlotFromDisk(const char *name)
 	 */
 	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",