diff --git a/include/libnetlink.h b/include/libnetlink.h
index 6bff6bae..9e4cc101 100644
--- a/include/libnetlink.h
+++ b/include/libnetlink.h
@@ -109,6 +109,27 @@ struct rtnl_ctrl_data {
 
 typedef int (*rtnl_filter_t)(struct nlmsghdr *n, void *);
 
+/**
+ * rtnl error handler called from
+ *      rtnl_dump_done()
+ *      rtnl_dump_error()
+ *
+ * Return value is a bitmask of the following values:
+ * RTNL_LET_NLERR
+ *      error handled as usual
+ * RTNL_SUPPRESS_NLMSG_DONE_NLERR
+ *      error in nlmsg_type == NLMSG_DONE will be suppressed
+ * RTNL_SUPPRESS_NLMSG_ERROR_NLERR
+ *      error in nlmsg_type == NLMSG_ERROR will be suppressed
+ *      and nlmsg will be skipped
+ * RTNL_SUPPRESS_NLERR - suppress error in both previous cases
+ */
+#define RTNL_LET_NLERR				0x01
+#define RTNL_SUPPRESS_NLMSG_DONE_NLERR		0x02
+#define RTNL_SUPPRESS_NLMSG_ERROR_NLERR		0x04
+#define RTNL_SUPPRESS_NLERR			0x06
+typedef int (*rtnl_err_hndlr_t)(struct nlmsghdr *n, void *);
+
 typedef int (*rtnl_listen_filter_t)(struct rtnl_ctrl_data *,
 				    struct nlmsghdr *n, void *);
 
@@ -118,6 +139,8 @@ typedef int (*nl_ext_ack_fn_t)(const char *errmsg, uint32_t off,
 struct rtnl_dump_filter_arg {
 	rtnl_filter_t filter;
 	void *arg1;
+	rtnl_err_hndlr_t errhndlr;
+	void *arg2;
 	__u16 nc_flags;
 };
 
@@ -126,6 +149,15 @@ int rtnl_dump_filter_nc(struct rtnl_handle *rth,
 			void *arg, __u16 nc_flags);
 #define rtnl_dump_filter(rth, filter, arg) \
 	rtnl_dump_filter_nc(rth, filter, arg, 0)
+int rtnl_dump_filter_errhndlr_nc(struct rtnl_handle *rth,
+				 rtnl_filter_t filter,
+				 void *arg1,
+				 rtnl_err_hndlr_t errhndlr,
+				 void *arg2,
+				 __u16 nc_flags);
+#define rtnl_dump_filter_errhndlr(rth, filter, farg, errhndlr, earg) \
+	rtnl_dump_filter_errhndlr_nc(rth, filter, farg, errhndlr, earg, 0)
+
 int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
 	      struct nlmsghdr **answer)
 	__attribute__((warn_unused_result));
diff --git a/ip/iproute.c b/ip/iproute.c
index 6b3ddc92..1e5e2002 100644
--- a/ip/iproute.c
+++ b/ip/iproute.c
@@ -1735,6 +1735,18 @@ static int iproute_flush(int family, rtnl_filter_t filter_fn)
 	}
 }
 
+static int save_route_errhndlr(struct nlmsghdr *n, void *arg)
+{
+	int err = -*(int *)NLMSG_DATA(n);
+
+	if (n->nlmsg_type == NLMSG_DONE &&
+	    filter.tb == RT_TABLE_MAIN &&
+	    err == ENOENT)
+		return RTNL_SUPPRESS_NLMSG_DONE_NLERR;
+
+	return RTNL_LET_NLERR;
+}
+
 static int iproute_list_flush_or_save(int argc, char **argv, int action)
 {
 	int dump_family = preferred_family;
@@ -1947,7 +1959,8 @@ static int iproute_list_flush_or_save(int argc, char **argv, int action)
 
 	new_json_obj(json);
 
-	if (rtnl_dump_filter(&rth, filter_fn, stdout) < 0) {
+	if (rtnl_dump_filter_errhndlr(&rth, filter_fn, stdout,
+				      save_route_errhndlr, NULL) < 0) {
 		fprintf(stderr, "Dump terminated\n");
 		return -2;
 	}
diff --git a/lib/bpf_libbpf.c b/lib/bpf_libbpf.c
index 864f8c35..dbec2cb5 100644
--- a/lib/bpf_libbpf.c
+++ b/lib/bpf_libbpf.c
@@ -268,10 +268,12 @@ static int load_bpf_object(struct bpf_cfg_in *cfg)
 	}
 
 	bpf_object__for_each_program(p, obj) {
+		bool prog_to_attach = !prog && cfg->section &&
+			!strcmp(get_bpf_program__section_name(p), cfg->section);
+
 		/* Only load the programs that will either be subsequently
 		 * attached or inserted into a tail call map */
-		if (find_legacy_tail_calls(p, obj) < 0 && cfg->section &&
-		    strcmp(get_bpf_program__section_name(p), cfg->section)) {
+		if (find_legacy_tail_calls(p, obj) < 0 && !prog_to_attach) {
 			ret = bpf_program__set_autoload(p, false);
 			if (ret)
 				return -EINVAL;
@@ -280,7 +282,8 @@ static int load_bpf_object(struct bpf_cfg_in *cfg)
 
 		bpf_program__set_type(p, cfg->type);
 		bpf_program__set_ifindex(p, cfg->ifindex);
-		if (!prog)
+
+		if (prog_to_attach)
 			prog = p;
 	}
 
diff --git a/lib/libnetlink.c b/lib/libnetlink.c
index 2f2cc1fe..7e977a67 100644
--- a/lib/libnetlink.c
+++ b/lib/libnetlink.c
@@ -718,7 +718,8 @@ int rtnl_dump_request_n(struct rtnl_handle *rth, struct nlmsghdr *n)
 	return sendmsg(rth->fd, &msg, 0);
 }
 
-static int rtnl_dump_done(struct nlmsghdr *h)
+static int rtnl_dump_done(struct nlmsghdr *h,
+			  const struct rtnl_dump_filter_arg *a)
 {
 	int len = *(int *)NLMSG_DATA(h);
 
@@ -728,11 +729,15 @@ static int rtnl_dump_done(struct nlmsghdr *h)
 	}
 
 	if (len < 0) {
+		errno = -len;
+
+		if (a->errhndlr && (a->errhndlr(h, a->arg2) & RTNL_SUPPRESS_NLMSG_DONE_NLERR))
+			return 0;
+
 		/* check for any messages returned from kernel */
 		if (nl_dump_ext_ack_done(h, len))
 			return len;
 
-		errno = -len;
 		switch (errno) {
 		case ENOENT:
 		case EOPNOTSUPP:
@@ -753,8 +758,9 @@ static int rtnl_dump_done(struct nlmsghdr *h)
 	return 0;
 }
 
-static void rtnl_dump_error(const struct rtnl_handle *rth,
-			    struct nlmsghdr *h)
+static int rtnl_dump_error(const struct rtnl_handle *rth,
+			    struct nlmsghdr *h,
+			    const struct rtnl_dump_filter_arg *a)
 {
 
 	if (h->nlmsg_len < NLMSG_LENGTH(sizeof(struct nlmsgerr))) {
@@ -766,11 +772,16 @@ static void rtnl_dump_error(const struct rtnl_handle *rth,
 		if (rth->proto == NETLINK_SOCK_DIAG &&
 		    (errno == ENOENT ||
 		     errno == EOPNOTSUPP))
-			return;
+			return -1;
+
+		if (a->errhndlr && (a->errhndlr(h, a->arg2) & RTNL_SUPPRESS_NLMSG_ERROR_NLERR))
+			return 0;
 
 		if (!(rth->flags & RTNL_HANDLE_F_SUPPRESS_NLERR))
 			perror("RTNETLINK answers");
 	}
+
+	return -1;
 }
 
 static int __rtnl_recvmsg(int fd, struct msghdr *msg, int flags)
@@ -879,7 +890,7 @@ static int rtnl_dump_filter_l(struct rtnl_handle *rth,
 					dump_intr = 1;
 
 				if (h->nlmsg_type == NLMSG_DONE) {
-					err = rtnl_dump_done(h);
+					err = rtnl_dump_done(h, a);
 					if (err < 0) {
 						free(buf);
 						return -1;
@@ -890,9 +901,13 @@ static int rtnl_dump_filter_l(struct rtnl_handle *rth,
 				}
 
 				if (h->nlmsg_type == NLMSG_ERROR) {
-					rtnl_dump_error(rth, h);
-					free(buf);
-					return -1;
+					err = rtnl_dump_error(rth, h, a);
+					if (err < 0) {
+						free(buf);
+						return -1;
+					}
+
+					goto skip_it;
 				}
 
 				if (!rth->dump_fp) {
@@ -928,12 +943,34 @@ skip_it:
 }
 
 int rtnl_dump_filter_nc(struct rtnl_handle *rth,
-		     rtnl_filter_t filter,
-		     void *arg1, __u16 nc_flags)
+			rtnl_filter_t filter,
+			void *arg1, __u16 nc_flags)
 {
-	const struct rtnl_dump_filter_arg a[2] = {
-		{ .filter = filter, .arg1 = arg1, .nc_flags = nc_flags, },
-		{ .filter = NULL,   .arg1 = NULL, .nc_flags = 0, },
+	const struct rtnl_dump_filter_arg a[] = {
+		{
+			.filter = filter, .arg1 = arg1,
+			.nc_flags = nc_flags,
+		},
+		{ },
+	};
+
+	return rtnl_dump_filter_l(rth, a);
+}
+
+int rtnl_dump_filter_errhndlr_nc(struct rtnl_handle *rth,
+		     rtnl_filter_t filter,
+		     void *arg1,
+		     rtnl_err_hndlr_t errhndlr,
+		     void *arg2,
+		     __u16 nc_flags)
+{
+	const struct rtnl_dump_filter_arg a[] = {
+		{
+			.filter = filter, .arg1 = arg1,
+			.errhndlr = errhndlr, .arg2 = arg2,
+			.nc_flags = nc_flags,
+		},
+		{ },
 	};
 
 	return rtnl_dump_filter_l(rth, a);
@@ -1138,16 +1175,16 @@ int rtnl_listen(struct rtnl_handle *rtnl,
 	char   buf[16384];
 	char   cmsgbuf[BUFSIZ];
 
-	if (rtnl->flags & RTNL_HANDLE_F_LISTEN_ALL_NSID) {
-		msg.msg_control = &cmsgbuf;
-		msg.msg_controllen = sizeof(cmsgbuf);
-	}
-
 	iov.iov_base = buf;
 	while (1) {
 		struct rtnl_ctrl_data ctrl;
 		struct cmsghdr *cmsg;
 
+		if (rtnl->flags & RTNL_HANDLE_F_LISTEN_ALL_NSID) {
+			msg.msg_control = &cmsgbuf;
+			msg.msg_controllen = sizeof(cmsgbuf);
+		}
+
 		iov.iov_len = sizeof(buf);
 		status = recvmsg(rtnl->fd, &msg, 0);
 
diff --git a/man/man8/ip-tunnel.8 b/man/man8/ip-tunnel.8
index 9a510af0..57e030dd 100644
--- a/man/man8/ip-tunnel.8
+++ b/man/man8/ip-tunnel.8
@@ -235,7 +235,7 @@ flag is equivalent to the combination
 .B It doesn't work. Don't use it.
 
 .TP
-.BI encaplim " ELIM"
+.BI encaplimit " ELIM"
 .RB ( " only IPv6 tunnels " )
 set a fixed encapsulation limit. Default is 4.
 
diff --git a/man/man8/tc-skbmod.8 b/man/man8/tc-skbmod.8
index eb3c38fa..76512311 100644
--- a/man/man8/tc-skbmod.8
+++ b/man/man8/tc-skbmod.8
@@ -5,12 +5,12 @@ skbmod - user-friendly packet editor action
 .SH SYNOPSIS
 .in +8
 .ti -8
-.BR tc " ... " "action skbmod " "{ [ " "set "
-.IR SETTABLE " ] [ "
+.BR tc " ... " "action skbmod " "{ " "set "
+.IR SETTABLE " | "
 .BI swap " SWAPPABLE"
-.RI " ] [ " CONTROL " ] [ "
+.RI " } [ " CONTROL " ] [ "
 .BI index " INDEX "
-] }
+]
 
 .ti -8
 .IR SETTABLE " := "
@@ -25,6 +25,7 @@ skbmod - user-friendly packet editor action
 .IR SWAPPABLE " := "
 .B mac
 .ti -8
+
 .IR CONTROL " := {"
 .BR reclassify " | " pipe " | " drop " | " shot " | " continue " | " pass " }"
 .SH DESCRIPTION
@@ -48,10 +49,7 @@ Change the source mac to the specified address.
 Change the ethertype to the specified value.
 .TP
 .BI mac
-Used to swap mac addresses. The
-.B swap mac
-directive is performed
-after any outstanding D/SMAC changes.
+Used to swap mac addresses.
 .TP
 .I CONTROL
 The following keywords allow to control how the tree of qdisc, classes,
@@ -128,9 +126,13 @@ tc filter add dev eth3 parent 1: protocol ip prio 10 \\
 .EE
 .RE
 
-As mentioned above, the swap action will occur after any
-.B " smac/dmac "
-substitutions are executed, if they are present.
+However, trying to
+.B set
+and
+.B swap
+in a single
+.B skbmod
+command will cause undefined behavior.
 
 .SH SEE ALSO
 .BR tc (8),
diff --git a/tc/m_police.c b/tc/m_police.c
index 2594c089..f38ab90a 100644
--- a/tc/m_police.c
+++ b/tc/m_police.c
@@ -278,7 +278,7 @@ static int print_police(struct action_util *a, FILE *f, struct rtattr *arg)
 	__u64 rate64, prate64;
 	__u64 pps64, ppsburst64;
 
-	print_string(PRINT_ANY, "kind", "%s", "police");
+	print_string(PRINT_JSON, "kind", "%s", "police");
 	if (arg == NULL)
 		return 0;
 
@@ -301,7 +301,8 @@ static int print_police(struct action_util *a, FILE *f, struct rtattr *arg)
 	    RTA_PAYLOAD(tb[TCA_POLICE_RATE64]) >= sizeof(rate64))
 		rate64 = rta_getattr_u64(tb[TCA_POLICE_RATE64]);
 
-	print_uint(PRINT_ANY, "index", "\t index %u ", p->index);
+	print_hex(PRINT_FP, NULL, " police 0x%x ", p->index);
+	print_uint(PRINT_JSON, "index", NULL, p->index);
 	tc_print_rate(PRINT_FP, NULL, "rate %s ", rate64);
 	buffer = tc_calc_xmitsize(rate64, p->burst);
 	print_size(PRINT_FP, NULL, "burst %s ", buffer);
@@ -342,12 +343,13 @@ static int print_police(struct action_util *a, FILE *f, struct rtattr *arg)
 		print_string(PRINT_FP, NULL, " ", NULL);
 	}
 
-	print_uint(PRINT_ANY, "overhead", "overhead %u ", p->rate.overhead);
+	print_size(PRINT_ANY, "overhead", "overhead %s ", p->rate.overhead);
 	linklayer = (p->rate.linklayer & TC_LINKLAYER_MASK);
 	if (linklayer > TC_LINKLAYER_ETHERNET || show_details)
 		print_string(PRINT_ANY, "linklayer", "linklayer %s ",
 			     sprint_linklayer(linklayer, b2));
-	print_int(PRINT_ANY, "ref", "ref %d ", p->refcnt);
+	print_nl();
+	print_int(PRINT_ANY, "ref", "\tref %d ", p->refcnt);
 	print_int(PRINT_ANY, "bind", "bind %d ", p->bindcnt);
 	if (show_stats) {
 		if (tb[TCA_POLICE_TM]) {
diff --git a/tc/m_skbmod.c b/tc/m_skbmod.c
index e13d3f16..3fe30651 100644
--- a/tc/m_skbmod.c
+++ b/tc/m_skbmod.c
@@ -28,10 +28,9 @@
 static void skbmod_explain(void)
 {
 	fprintf(stderr,
-		"Usage:... skbmod {[set <SETTABLE>] [swap <SWAPABLE>]} [CONTROL] [index INDEX]\n"
+		"Usage:... skbmod { set <SETTABLE> | swap <SWAPPABLE> } [CONTROL] [index INDEX]\n"
 		"where SETTABLE is: [dmac DMAC] [smac SMAC] [etype ETYPE]\n"
-		"where SWAPABLE is: \"mac\" to swap mac addresses\n"
-		"note: \"swap mac\" is done after any outstanding D/SMAC change\n"
+		"where SWAPPABLE is: \"mac\" to swap mac addresses\n"
 		"\tDMAC := 6 byte Destination MAC address\n"
 		"\tSMAC := optional 6 byte Source MAC address\n"
 		"\tETYPE := optional 16 bit ethertype\n"