isolation: Only configure UID/GID mappings in userns when spawning shell

When in passt mode, or pasta mode spawning a command, we create a userns
for ourselves.  This is used both to isolate the pasta/passt process itself
and to run the spawned command, if any.

Since eed17a47 "Handle userns isolation and dropping root at the same time"
we've handled both cases the same, configuring the UID and GID mappings in
the new userns to map whichever UID we're running as to root within the
userns.

This mapping is desirable when spawning a shell or other command, so that
the user gets a root shell with reasonably clear abilities within the
userns and netns.  It's not necessarily essential, though.  When not
spawning a shell, it doesn't really have any purpose: passt itself doesn't
need to be root and can operate fine with an unmapped user (using some of
the capabilities we get when entering the userns instead).

Configuring the uid_map can cause problems if passt is running with any
capabilities in the initial namespace, such as CAP_NET_BIND_SERVICE to
allow it to forward low ports.  In this case the kernel makes files in
/proc/pid owned by root rather than the starting user to prevent the user
from interfering with the operation of the capability-enhanced process.
This includes uid_map meaning we are not able to write to it.

Whether this behaviour is correct in the kernel is debatable, but in any
case we might as well avoid problems by only initializing the user mappings
when we really want them.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>

conf.c

@@ -1556,7 +1556,8 @@ void conf(struct ctx *c, int argc, char **argv)
 		if (*netns) {
 			pasta_open_ns(c, netns);
 		} else {
-			pasta_start_ns(c, argc - optind, argv + optind);
+			pasta_start_ns(c, uid, gid,
+				       argc - optind, argv + optind);
 		}
 	}
 

isolation.c

@@ -265,23 +265,10 @@ void isolate_user(uid_t uid, gid_t gid, bool use_userns, const char *userns,
 		close(ufd);
 
 	} else if (use_userns) { /* Create and join a new userns */
-		char uidmap[BUFSIZ];
-		char gidmap[BUFSIZ];
-
 		if (unshare(CLONE_NEWUSER) != 0) {
 			err("Couldn't create user namespace: %s", strerror(errno));
 			exit(EXIT_FAILURE);
 		}
-
-		/* Configure user and group mappings */
-		snprintf(uidmap, BUFSIZ, "0 %u 1", uid);
-		snprintf(gidmap, BUFSIZ, "0 %u 1", gid);
-
-		if (write_file("/proc/self/uid_map", uidmap) ||
-		    write_file("/proc/self/setgroups", "deny") ||
-		    write_file("/proc/self/gid_map", gidmap)) {
-			warn("Couldn't configure user namespace");
-		}
 	}
 
 	/* Joining a new userns gives us full capabilities; drop the

pasta.c

@@ -180,15 +180,19 @@ static int pasta_setup_ns(void *arg)
 /**
  * pasta_start_ns() - Fork command in new namespace if target ns is not given
  * @c:		Execution context
+ * @uid:	UID we're running as in the init namespace
+ * @gid:	GID we're running as in the init namespace
  * @argc:	Number of arguments for spawned command
  * @argv:	Command to spawn and arguments
  */
-void pasta_start_ns(struct ctx *c, int argc, char *argv[])
+void pasta_start_ns(struct ctx *c, uid_t uid, gid_t gid,
+		    int argc, char *argv[])
 {
 	struct pasta_setup_ns_arg arg = {
 		.exe = argv[0],
 		.argv = argv,
 	};
+	char uidmap[BUFSIZ], gidmap[BUFSIZ];
 	char ns_fn_stack[NS_FN_STACK_SIZE];
 	char *sh_argv[] = { NULL, NULL };
 	char sh_arg0[PATH_MAX + 1];
@@ -197,6 +201,15 @@ void pasta_start_ns(struct ctx *c, int argc, char *argv[])
 	if (!c->debug)
 		c->quiet = 1;
 
+	/* Configure user and group mappings */
+	snprintf(uidmap, BUFSIZ, "0 %u 1", uid);
+	snprintf(gidmap, BUFSIZ, "0 %u 1", gid);
+
+	if (write_file("/proc/self/uid_map", uidmap) ||
+	    write_file("/proc/self/setgroups", "deny") ||
+	    write_file("/proc/self/gid_map", gidmap)) {
+		warn("Couldn't configure user mappings");
+	}
 
 	if (argc == 0) {
 		arg.exe = getenv("SHELL");

pasta.h

@@ -7,7 +7,8 @@
 #define PASTA_H
 
 void pasta_open_ns(struct ctx *c, const char *netns);
-void pasta_start_ns(struct ctx *c, int argc, char *argv[]);
+void pasta_start_ns(struct ctx *c, uid_t uid, gid_t gid,
+		    int argc, char *argv[]);
 void pasta_ns_conf(struct ctx *c);
 void pasta_child_handler(int signal);
 int pasta_netns_quit_init(struct ctx *c);