Error when creating names too long for tar format

The tar format (at least the version we are using), does not support
file names or symlink targets longer than 99 bytes.  Until now, the tar
creation code would silently truncate any names that are too long.  (Its
original application was pg_dump, where this never happens.)  This
creates problems when running base backups over the replication
protocol.

The most important problem is when a tablespace path is longer than 99
bytes, which will result in a truncated tablespace path being backed up.
Less importantly, the basebackup protocol also promises to back up any
other files it happens to find in the data directory, which would also
lead to file name truncation if someone put a file with a long name in
there.

Now both of these cases result in an error during the backup.

Add tests that fail when a too-long file name or symlink is attempted to
be backed up.

Reviewed-by: Robert Hass <robertmhaas@gmail.com>

src/backend/replication/basebackup.c

@@ -1258,11 +1258,30 @@ _tarWriteHeader(const char *filename, const char *linktarget,
 				struct stat * statbuf)
 {
 	char		h[512];
+	enum tarError rc;
 
-	tarCreateHeader(h, filename, linktarget, statbuf->st_size,
+	rc = tarCreateHeader(h, filename, linktarget, statbuf->st_size,
 					statbuf->st_mode, statbuf->st_uid, statbuf->st_gid,
 					statbuf->st_mtime);
 
+	switch (rc)
+	{
+		case TAR_OK:
+			break;
+		case TAR_NAME_TOO_LONG:
+			ereport(ERROR,
+					(errmsg("file name too long for tar format: \"%s\"",
+							filename)));
+			break;
+		case TAR_SYMLINK_TOO_LONG:
+			ereport(ERROR,
+					(errmsg("symbolic link target too long for tar format: file name \"%s\", target \"%s\"",
+							filename, linktarget)));
+			break;
+		default:
+			elog(ERROR, "unrecognized tar error: %d", rc);
+	}
+
 	pq_putmessage('d', h, 512);
 }
 

src/bin/pg_basebackup/t/010_pg_basebackup.pl

@@ -2,7 +2,7 @@ use strict;
 use warnings;
 use Cwd;
 use TestLib;
-use Test::More tests => 33;
+use Test::More tests => 35;
 
 program_help_ok('pg_basebackup');
 program_version_ok('pg_basebackup');
@@ -49,6 +49,13 @@ command_ok([ 'pg_basebackup', '-D', "$tempdir/tarbackup", '-Ft' ],
 	'tar format');
 ok(-f "$tempdir/tarbackup/base.tar", 'backup tar was created');
 
+my $superlongname = "superlongname_" . ("x"x100);
+
+system_or_bail 'touch', "$tempdir/pgdata/$superlongname";
+command_fails([ 'pg_basebackup', '-D', "$tempdir/tarbackup_l1", '-Ft' ],
+			  'pg_basebackup tar with long name fails');
+unlink "$tempdir/pgdata/$superlongname";
+
 # Create a temporary directory in the system location and symlink it
 # to our physical temp location.  That way we can use shorter names
 # for the tablespace directories, which hopefully won't run afoul of
@@ -117,3 +124,9 @@ command_fails(
 command_fails(
 	[ 'pg_basebackup', '-D', "$tempdir/backup_foo", '-Fp', "-Tfoo" ],
 	'-T with invalid format fails');
+
+mkdir "$tempdir/$superlongname";
+psql 'postgres', "CREATE TABLESPACE tblspc3 LOCATION '$tempdir/$superlongname';";
+command_fails([ 'pg_basebackup', '-D', "$tempdir/tarbackup_l3", '-Ft' ],
+			  'pg_basebackup tar with long symlink target fails');
+psql 'postgres', "DROP TABLESPACE tblspc3;";

src/include/pgtar.h

@@ -11,5 +11,13 @@
  *
  *-------------------------------------------------------------------------
  */
-extern void tarCreateHeader(char *h, const char *filename, const char *linktarget, size_t size, mode_t mode, uid_t uid, gid_t gid, time_t mtime);
+
+enum tarError
+{
+	TAR_OK = 0,
+	TAR_NAME_TOO_LONG,
+	TAR_SYMLINK_TOO_LONG
+};
+
+extern enum tarError tarCreateHeader(char *h, const char *filename, const char *linktarget, size_t size, mode_t mode, uid_t uid, gid_t gid, time_t mtime);
 extern int	tarChecksum(char *header);

src/port/tar.c

@@ -49,10 +49,16 @@ tarChecksum(char *header)
  * must always have space for 512 characters, which is a requirement by
  * the tar format.
  */
-void
+enum tarError
 tarCreateHeader(char *h, const char *filename, const char *linktarget,
 				size_t size, mode_t mode, uid_t uid, gid_t gid, time_t mtime)
 {
+	if (strlen(filename) > 99)
+		return TAR_NAME_TOO_LONG;
+
+	if (linktarget && strlen(linktarget) > 99)
+		return TAR_SYMLINK_TOO_LONG;
+
 	/*
 	 * Note: most of the fields in a tar header are not supposed to be
 	 * null-terminated.  We use sprintf, which will write a null after the
@@ -141,4 +147,6 @@ tarCreateHeader(char *h, const char *filename, const char *linktarget,
 	 * 6 digits, a space, and a null, which is legal per POSIX.
 	 */
 	sprintf(&h[148], "%06o ", tarChecksum(h));
+
+	return TAR_OK;
 }