Add support for not crossing filesystem boundaries (-x) to rsync. Option

and behaviour is the same as GPL rsync.

Initial diff received feedback from benno@, schwarze@, deraadt@ and
florian@. Thanks!

OK deraadt@

5 files changed, 95 insertions, 12 deletions

diff --git a/usr.bin/rsync/extern.h b/usr.bin/rsync/extern.h
index 9ae08e7515e..305821be579 100644
--- a/usr.bin/rsync/extern.h
+++ b/usr.bin/rsync/extern.h
@@ -1,4 +1,4 @@
-/*	$Id: extern.h,v 1.27 2019/04/02 05:32:08 deraadt Exp $ */
+/*	$Id: extern.h,v 1.28 2019/04/04 04:19:54 bket Exp $ */
 /*
  * Copyright (c) 2019 Kristaps Dzonsons <kristaps@bsd.lv>
  *
@@ -117,6 +117,7 @@ struct	opts {
 	int		 devices;		/* --devices */
 	int		 specials;		/* --specials */
 	int		 numeric_ids;		/* --numeric-ids */
+	int		 one_file_system;	/* -x */
 	char		*rsync_path;		/* --rsync-path */
 	char		*ssh_prog;		/* --rsh or -e */
 	char		*port;			/* --port */
diff --git a/usr.bin/rsync/fargs.c b/usr.bin/rsync/fargs.c
index 55bf1b4b8af..59dadc856c7 100644
--- a/usr.bin/rsync/fargs.c
+++ b/usr.bin/rsync/fargs.c
@@ -1,4 +1,4 @@
-/*	$Id: fargs.c,v 1.15 2019/04/02 05:32:08 deraadt Exp $ */
+/*	$Id: fargs.c,v 1.16 2019/04/04 04:19:54 bket Exp $ */
 /*
  * Copyright (c) 2019 Kristaps Dzonsons <kristaps@bsd.lv>
  *
@@ -106,6 +106,10 @@ fargs_cmdline(struct sess *sess, const struct fargs *f, size_t *skip)
 		addargs(&args, "-v");
 	if (sess->opts->verbose > 0)
 		addargs(&args, "-v");
+	if (sess->opts->one_file_system > 1)
+		addargs(&args, "-x");
+	if (sess->opts->one_file_system > 0)
+		addargs(&args, "-x");
 	if (sess->opts->specials && !sess->opts->devices)
 		addargs(&args, "--specials");
 	if (!sess->opts->specials && sess->opts->devices)
diff --git a/usr.bin/rsync/flist.c b/usr.bin/rsync/flist.c
index b39599583e3..ac29ad47098 100644
--- a/usr.bin/rsync/flist.c
+++ b/usr.bin/rsync/flist.c
@@ -1,4 +1,4 @@
-/*	$Id: flist.c,v 1.23 2019/03/31 09:26:05 deraadt Exp $ */
+/*	$Id: flist.c,v 1.24 2019/04/04 04:19:54 bket Exp $ */
 /*
  * Copyright (c) 2019 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2019 Florian Obser <florian@openbsd.org>
@@ -804,11 +804,12 @@ flist_gen_dirent(struct sess *sess, char *root, struct flist **fl, size_t *sz,
     size_t *max)
 {
 	char		*cargv[2], *cp;
-	int		 rc = 0;
+	int		 rc = 0, nxdev = 0, flag, i;
 	FTS		*fts;
 	FTSENT		*ent;
 	struct flist	*f;
 	size_t		 flsz = 0, stripdir;
+	dev_t		*xdev;
 	struct stat	 st;
 
 	cargv[0] = root;
@@ -913,6 +914,48 @@ flist_gen_dirent(struct sess *sess, char *root, struct flist **fl, size_t *sz,
 			continue;
 		}
 
+		/*
+		 * If rsync is told to avoid crossing a filesystem
+		 * boundary when recursing, then replace all mount point
+		 * directories with empty directories.  The latter is
+		 * prevented by telling rsync multiple times to avoid
+		 * crossing a filesystem boundary when recursing.
+		 * Replacing mount point directories is tricky. We need
+		 * to sort out which directories to include.  As such,
+		 * keep track of unique device inodes, and use these for
+		 * comparison.
+		 */
+
+		if (sess->opts->one_file_system &&
+		    ent->fts_statp->st_dev != st.st_dev) {
+			if (sess->opts->one_file_system > 1 ||
+			    !S_ISDIR(ent->fts_statp->st_mode))
+				continue;
+
+			if ((xdev = malloc(sizeof(dev_t))) == NULL) {
+				ERRX1(sess, "malloc");
+				goto out;
+			}
+
+			flag = 0;
+			for (i = 0; i < nxdev; i++)
+				if (xdev[i] == ent->fts_statp->st_dev) {
+					flag = 1;
+					break;
+				}
+			if (flag)
+				continue;
+
+			if (nxdev)
+				if ((xdev = realloc(xdev, sizeof(dev_t))) ==
+				    NULL) {
+					ERRX1(sess, "realloc");
+					goto out;
+				}
+			xdev[nxdev] = ent->fts_statp->st_dev;
+			nxdev++;
+		}
+
 		/* Allocate a new file entry. */
 
 		if (!flist_realloc(sess, fl, sz, max)) {
@@ -966,6 +1009,8 @@ flist_gen_dirent(struct sess *sess, char *root, struct flist **fl, size_t *sz,
 	rc = 1;
 out:
 	fts_close(fts);
+	if (sess->opts->one_file_system)
+		free(xdev);
 	return rc;
 }
 
@@ -1129,10 +1174,11 @@ flist_gen_dels(struct sess *sess, const char *root, struct flist **fl,
     size_t *sz,	const struct flist *wfl, size_t wflsz)
 {
 	char		**cargv = NULL;
-	int		  rc = 0, c;
+	int		  rc = 0, c, flag;
 	FTS		 *fts = NULL;
 	FTSENT		 *ent;
 	struct flist	 *f;
+	struct stat	  st;
 	size_t		  cargvs = 0, i, j, max = 0, stripdir;
 	ENTRY		  hent;
 	ENTRY		 *hentp;
@@ -1253,6 +1299,31 @@ flist_gen_dels(struct sess *sess, const char *root, struct flist **fl,
 		} else if (stripdir >= ent->fts_pathlen)
 			continue;
 
+		assert(ent->fts_statp != NULL);
+
+		/*
+		 * If rsync is told to avoid crossing a filesystem
+		 * boundary when recursing, then exclude all entries
+		 * from the list with a device inode, which does not
+		 * match that of one of the top-level directories.
+		 */
+
+		if (sess->opts->one_file_system) {
+			flag = 0;
+			for (i = 0; i < wflsz; i++) {
+				if (stat(wfl[i].path, &st) == -1) {
+					ERR(sess, "%s: stat", wfl[i].path);
+					goto out;
+				}
+				if (ent->fts_statp->st_dev == st.st_dev) {
+					flag = 1;
+					break;
+				}
+			}
+			if (!flag)
+				continue;
+		}
+
 		/* Look up in hashtable. */
 
 		memset(&hent, 0, sizeof(ENTRY));
@@ -1273,7 +1344,6 @@ flist_gen_dels(struct sess *sess, const char *root, struct flist **fl,
 			goto out;
 		}
 		f->wpath = f->path + stripdir;
-		assert(ent->fts_statp != NULL);
 		flist_copy_stat(f, ent->fts_statp);
 		errno = 0;
 	}
diff --git a/usr.bin/rsync/main.c b/usr.bin/rsync/main.c
index dd598d93eb2..4f0b386e0bf 100644
--- a/usr.bin/rsync/main.c
+++ b/usr.bin/rsync/main.c
@@ -1,4 +1,4 @@
-/*	$Id: main.c,v 1.43 2019/04/01 13:04:51 schwarze Exp $ */
+/*	$Id: main.c,v 1.44 2019/04/04 04:19:54 bket Exp $ */
 /*
  * Copyright (c) 2019 Kristaps Dzonsons <kristaps@bsd.lv>
  *
@@ -315,7 +315,7 @@ main(int argc, char *argv[])
 
 	memset(&opts, 0, sizeof(struct opts));
 
-	while ((c = getopt_long(argc, argv, "Dae:ghlnoprtvz", lopts, NULL))
+	while ((c = getopt_long(argc, argv, "Dae:ghlnoprtvxz", lopts, NULL))
 	    != -1) {
 		switch (c) {
 		case 'D':
@@ -359,6 +359,9 @@ main(int argc, char *argv[])
 		case 'v':
 			opts.verbose++;
 			break;
+		case 'x':
+			opts.one_file_system++;
+			break;
 		case 'z':
 			fprintf(stderr, "%s: -z not supported yet\n", getprogname());
 			break;
@@ -505,7 +508,7 @@ main(int argc, char *argv[])
 	exit(rc);
 usage:
 	fprintf(stderr, "usage: %s"
-	    " [-aDglnoprtv] [-e program] [--del] [--numeric-ids]\n"
+	    " [-aDglnoprtvx] [-e program] [--del] [--numeric-ids]\n"
 	    "\t[--port=portnumber] [--rsync-path=program] [--version]\n"
 	    "\tsource ... directory\n",
 	    getprogname());
diff --git a/usr.bin/rsync/rsync.1 b/usr.bin/rsync/rsync.1
index c16168fff8f..3747a3fe70e 100644
--- a/usr.bin/rsync/rsync.1
+++ b/usr.bin/rsync/rsync.1
@@ -1,4 +1,4 @@
-.\"	$OpenBSD: rsync.1,v 1.16 2019/04/01 13:04:51 schwarze Exp $
+.\"	$OpenBSD: rsync.1,v 1.17 2019/04/04 04:19:54 bket Exp $
 .\"
 .\" Copyright (c) 2019 Kristaps Dzonsons <kristaps@bsd.lv>
 .\"
@@ -14,7 +14,7 @@
 .\" ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 .\" OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 .\"
-.Dd $Mdocdate: April 1 2019 $
+.Dd $Mdocdate: April 4 2019 $
 .Dt OPENRSYNC 1
 .Os
 .Sh NAME
@@ -22,7 +22,7 @@
 .Nd synchronise local and remote files
 .Sh SYNOPSIS
 .Nm openrsync
-.Op Fl aDglnoprtv
+.Op Fl aDglnoprtvx
 .Op Fl e Ar program
 .Op Fl -del
 .Op Fl -numeric-ids
@@ -141,6 +141,11 @@ Increase verbosity.
 Specify once for files being transferred, twice for specific status,
 thrice for per-file transfer information, and four times for per-file
 breakdowns.
+.It Fl x
+Do not cross filesystem boundaries.
+If this option is repeated, all mount point directories from the copy are
+omitted.
+Otherwise, it includes an empty directory at each mount point it encounters.
 .It Fl -version
 Print version and exit.
 .El