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

3 files changed, 38 insertions, 1 deletions

diff --git a/src/backend/replication/logical/origin.c b/src/backend/replication/logical/origin.c
index 4bd754df945..c281734fd59 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 93f373c9efd..6ed5fc405bd 100644
--- a/src/backend/replication/logical/reorderbuffer.c
+++ b/src/backend/replication/logical/reorderbuffer.c
@@ -2352,7 +2352,9 @@ 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 901e95ede4f..a2668765984 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1583,7 +1583,12 @@ 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)));
@@ -1599,7 +1604,10 @@ 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)));
@@ -1681,7 +1689,10 @@ 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",
@@ -1707,7 +1718,10 @@ 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",
@@ -1722,7 +1736,10 @@ 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",
@@ -1736,7 +1753,10 @@ 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",