Virtualization - Jun 2009 - [Bridge] [PATCH][RFC] bridge-utils: add basic VEPA support

This patch adds basic Virtual Ethernet Port Aggregator (VEPA) 
capabilities to the Linux Ethernet bridging utilities.

The patch provides functionality that depends on the Linux kernel
patch 'net/bridge: add basic VEPA support'.

This patch relies on the patch 'bridge-utils: fix sysfs path for 
setting bridge configuration parameters'.

A Virtual Ethernet Port Aggregator (VEPA) is a capability within 
a physical end station that collaborates with an adjacent, external 
bridge to provide distributed bridging support between multiple 
virtual end stations and external networks. The VEPA collaborates 
by forwarding all station-originated frames to the adjacent bridge 
for frame processing and frame relay (including so-called 'hairpin' 
forwarding) and by steering and replicating frames received from 
the VEPA uplink to the appropriate destinations. A VEPA may be 
implemented in software or in conjunction with embedded hardware.

In particular, the patch extends the Linux Ethernet bridge utilities
to configure a bridge to act as
(1) a VEPA, or as
(2) a bridge supporting 'hairpin' forwarding.

You can find additional information on VEPA here:
http://tech.groups.yahoo.com/group/evb/
http://www.ieee802.org/1/files/public/docs2009/new-hudson-vepa_seminar-20090514d.pdf

Signed-off-by: Paul Congdon <paul.congdon at hp.com>
Signed-off-by: Anna Fischer <anna.fischer at hp.com>

---

 brctl/brctl_cmd.c           |  108 ++++++++++++++++++++++++++++++++++++++++---
 brctl/brctl_disp.c          |    6 ++
 libbridge/libbridge.h       |    7 +++
 libbridge/libbridge_devif.c |   90 ++++++++++++++++++++++++++++++++++-
 4 files changed, 201 insertions(+), 10 deletions(-)

diff --git a/brctl/brctl_cmd.c b/brctl/brctl_cmd.c
index c93dd55..77eaf1e 100644
--- a/brctl/brctl_cmd.c
+++ b/brctl/brctl_cmd.c
@@ -280,17 +280,26 @@ static int br_cmd_setportprio(int argc, char *const* argv)
 	return err != 0;
 }
 
+static int br_parse_param(const char *param, int *res)
+{
+	if (!strcmp(param, "on") || !strcmp(param, "yes")
+	    || !strcmp(param, "1"))
+		*res = 1;
+	else if (!strcmp(param, "off") || !strcmp(param, "no")
+		 || !strcmp(param, "0"))
+		*res = 0;
+	else {
+		return EINVAL;
+	}
+	return 0;
+}
+
 static int br_cmd_stp(int argc, char *const* argv)
 {
 	int stp, err;
 
-	if (!strcmp(argv[2], "on") || !strcmp(argv[2], "yes") 
-	    || !strcmp(argv[2], "1"))
-		stp = 1;
-	else if (!strcmp(argv[2], "off") || !strcmp(argv[2], "no")
-		 || !strcmp(argv[2], "0"))
-		stp = 0;
-	else {
+	err = br_parse_param(argv[2], &stp);
+	if (err) {
 		fprintf(stderr, "expect on/off for argument\n");
 		return 1;
 	}
@@ -316,6 +325,85 @@ static int br_cmd_showstp(int argc, char *const* argv)
 	return 0;
 }
 
+static int br_cmd_vepa(int argc, char *const* argv)
+{
+	int vepa, err;
+
+	err = br_parse_param(argv[2], &vepa);
+	if (err) {
+		fprintf(stderr, "expect on/off for argument\n");
+		return 1;
+	}
+
+	err = br_set_vepa_mode(argv[1], vepa);
+	if (err)
+		fprintf(stderr, "set vepa mode failed: %s\n",
+			strerror(errno));
+	return err != 0;
+}
+
+static int br_cmd_vepauplink(int argc, char *const* argv)
+{
+	const char *brname = *++argv;
+	const char *ifname = *++argv;
+	int err;
+
+	if (if_nametoindex(ifname) == 0) {
+		fprintf(stderr, "interface %s does not exist!\n",
+			ifname);
+		return 1;
+	} else if (if_nametoindex(brname) == 0) {
+		fprintf(stderr, "bridge %s does not exist!\n",
+			brname);
+		return 1;
+	}
+
+	err = br_set_vepa_uplink(brname, ifname);
+
+	if (err) {
+		fprintf(stderr, "cannot set %s as vepa uplink.\n%s has "
+			"to be valid port of bridge %s: %s\n", ifname,
+			ifname, brname, strerror(err));
+	}
+	return err != 0;
+}
+
+static int br_cmd_hairpin(int argc, char *const* argv)
+{
+	int hairpin, err;
+	const char *brname = *++argv;
+	const char *ifname = *++argv;
+	const char *hpmode = *++argv;
+
+	if (!strcmp(hpmode, "on") || !strcmp(hpmode, "yes")
+	    || !strcmp(hpmode, "1"))
+		hairpin = 1;
+	else if (!strcmp(hpmode, "off") || !strcmp(hpmode, "no")
+		 || !strcmp(hpmode, "0"))
+		hairpin = 0;
+	else {
+		fprintf(stderr, "expect on/off for argument\n");
+		return 1;
+	}
+	if (if_nametoindex(ifname) == 0) {
+		fprintf(stderr, "interface %s does not exist!\n",
+			ifname);
+		return 1;
+	} else if (if_nametoindex(brname) == 0) {
+		fprintf(stderr, "bridge %s does not exist!\n",
+			brname);
+		return 1;
+	}
+
+	err = br_set_hairpin_mode(brname, ifname, hairpin);
+
+	if (err) {
+		fprintf(stderr, "can't set %s to hairpin on bridge %s: %s\n",
+			ifname, brname, strerror(err));
+	}
+	return err != 0;
+}
+
 static int show_bridge(const char *name, void *arg)
 {
 	struct bridge_info info;
@@ -402,6 +490,8 @@ static const struct command commands[] = {
 	  "<bridge> <device>\tadd interface to bridge" },
 	{ 2, "delif", br_cmd_delif,
 	  "<bridge> <device>\tdelete interface from bridge" },
+	{ 3, "hairpin", br_cmd_hairpin,
+	  "<bridge> <port> {on|off}\tturn hairpin on/off" },
 	{ 2, "setageing", br_cmd_setageing,
 	  "<bridge> <time>\t\tset ageing time" },
 	{ 2, "setbridgeprio", br_cmd_setbridgeprio,
@@ -423,6 +513,10 @@ static const struct command commands[] = {
 	  "<bridge>\t\tshow bridge stp info"},
 	{ 2, "stp", br_cmd_stp,
 	  "<bridge> {on|off}\tturn stp on/off" },
+	{ 2, "vepa", br_cmd_vepa,
+	  "<bridge> {on|off}\tturn vepa on/off" },
+	{ 2, "vepauplink", br_cmd_vepauplink,
+	  "<bridge> <port>\t\tset uplink for vepa" },
 };
 
 const struct command *command_lookup(const char *cmd)
diff --git a/brctl/brctl_disp.c b/brctl/brctl_disp.c
index 27ce6d2..5bcf38b 100644
--- a/brctl/brctl_disp.c
+++ b/brctl/brctl_disp.c
@@ -93,6 +93,8 @@ static int dump_port_info(const char *br, const char *p,  void
*arg)
 		printf("CONFIG_PENDING ");
 	if (pinfo.top_change_ack)
 		printf("TOPOLOGY_CHANGE_ACK ");
+	if (pinfo.hairpin_mode)
+		printf("\n hairpin mode\t\t\%4i", pinfo.hairpin_mode);
 	printf("\n");
 	printf("\n");
 	return 0;
@@ -136,6 +138,10 @@ void br_dump_info(const char *br, const struct bridge_info
*bri)
 		printf("TOPOLOGY_CHANGE ");
 	if (bri->topology_change_detected)
 		printf("TOPOLOGY_CHANGE_DETECTED ");
+	if (bri->vepa_mode) {
+		printf("\n vepa mode\t\t%4i", bri->vepa_mode);
+		printf("\t\t\tuplink port\t\t%s", bri->uplink_port);
+	}
 	printf("\n");
 	printf("\n");
 	printf("\n");
diff --git a/libbridge/libbridge.h b/libbridge/libbridge.h
index 016acea..b232f45 100644
--- a/libbridge/libbridge.h
+++ b/libbridge/libbridge.h
@@ -54,6 +54,8 @@ struct bridge_info
 	struct timeval tcn_timer_value;
 	struct timeval topology_change_timer_value;
 	struct timeval gc_timer_value;
+	unsigned char vepa_mode;
+	char uplink_port[IFNAMSIZ];
 };
 
 struct fdb_entry
@@ -80,6 +82,7 @@ struct port_info
 	struct timeval message_age_timer_value;
 	struct timeval forward_delay_timer_value;
 	struct timeval hold_timer_value;
+	unsigned char hairpin_mode;
 };
 
 extern int br_init(void);
@@ -113,4 +116,8 @@ extern int br_set_path_cost(const char *br, const char *p,
 			    int path_cost);
 extern int br_read_fdb(const char *br, struct fdb_entry *fdbs, 
 		       unsigned long skip, int num);
+extern int br_set_vepa_uplink(const char *br, const char *uplink);
+extern int br_set_vepa_mode(const char *br, int vepa_mode);
+extern int br_set_hairpin_mode(const char *bridge, const char *dev,
+			       int hairpin_mode);
 #endif
diff --git a/libbridge/libbridge_devif.c b/libbridge/libbridge_devif.c
index 547bb86..cc4a9cb 100644
--- a/libbridge/libbridge_devif.c
+++ b/libbridge/libbridge_devif.c
@@ -36,6 +36,14 @@ static FILE *fpopen(const char *dir, const char *name)
 	return fopen(path, "r");
 }
 
+static int fpaccess(const char *dir, const char *name)
+{
+	char path[SYSFS_PATH_MAX];
+
+	snprintf(path, SYSFS_PATH_MAX, "%s/%s", dir, name);
+	return access(path, F_OK);
+}
+
 static void fetch_id(const char *dev, const char *name, struct bridge_id *id)
 {
 	FILE *f = fpopen(dev, name);
@@ -58,7 +66,8 @@ static int fetch_int(const char *dev, const char *name)
 	int value = -1;
 
 	if (!f) 
-		fprintf(stderr, "%s: %s\n", dev, strerror(errno));
+		fprintf(stderr, "%s/%s: %s\n", dev, name,
+			strerror(errno));
 	else {
 		fscanf(f, "%i", &value);
 		fclose(f);
@@ -73,6 +82,27 @@ static void fetch_tv(const char *dev, const char *name,
 	__jiffies_to_tv(tv, fetch_int(dev, name));
 }
 
+/* Fetch a string attribute out of sysfs. */
+static void fetch_string(const char *dev, const char *name, char *string)
+{
+	FILE *f = fpopen(dev, name);
+
+	if (!f) {
+		fprintf(stderr, "%s/%s: %s\n", dev, name,
+			strerror(errno));
+		sprintf(string, "-");
+	} else {
+		fscanf(f, "%s", string);
+		fclose(f);
+	}
+}
+
+/* Check if a feature is supported. */
+static int feature_supported(const char *dev, const char *feature)
+{
+	return !fpaccess(dev, feature);
+}
+
 /* Open sysfs path for writing bridge properties. */
 static FILE *br_sysfs_open(const char *bridge, const char *name)
 {
@@ -168,7 +198,8 @@ static int old_get_bridge_info(const char *bridge, struct
bridge_info *info)
 	__jiffies_to_tv(&info->topology_change_timer_value, 
 			i.topology_change_timer_value);
 	__jiffies_to_tv(&info->gc_timer_value, i.gc_timer_value);
-
+	info->vepa_mode = 0;
+	sprintf(info->uplink_port, "-");
 	return 0;
 }
 
@@ -209,7 +240,13 @@ int br_get_bridge_info(const char *bridge, struct
bridge_info *info)
 	info->stp_enabled = fetch_int(path, "stp_state");
 	info->topology_change = fetch_int(path, "topology_change");
 	info->topology_change_detected = fetch_int(path,
"topology_change_detected");
-
+	if (feature_supported(path, "vepa_mode")) {
+		info->vepa_mode = fetch_int(path, "vepa_mode");
+		fetch_string(path, "uplink_port", info->uplink_port);
+	} else {
+		info->vepa_mode = 0;
+		sprintf(info->uplink_port, "-");
+	}
 	closedir(dir);
 	return 0;
 
@@ -259,6 +296,7 @@ static int old_get_port_info(const char *brname, const char
*port,
 	__jiffies_to_tv(&info->forward_delay_timer_value, 
 			i.forward_delay_timer_value);
 	__jiffies_to_tv(&info->hold_timer_value, i.hold_timer_value);
+	info->hairpin_mode = 0;
 	return 0;
 }
 
@@ -291,6 +329,10 @@ int br_get_port_info(const char *brname, const char *port,
 	fetch_tv(path, "message_age_timer",
&info->message_age_timer_value);
 	fetch_tv(path, "forward_delay_timer",
&info->forward_delay_timer_value);
 	fetch_tv(path, "hold_timer", &info->hold_timer_value);
+	if (feature_supported(path, "hairpin_mode"))
+		info->hairpin_mode = fetch_int(path, "hairpin_mode");
+	else
+		info->hairpin_mode = 0;
 	closedir(d);
 
 	return 0;
@@ -322,6 +364,33 @@ static int br_set(const char *bridge, const char *name,
 	return ret < 0 ? errno : 0;
 }
 
+static int br_set_string(const char *bridge, const char *name,
+			 const char *string, int len)
+{
+	FILE *f;
+	char tmp[len];
+
+	f = br_sysfs_open(bridge, name);
+	if (f) {
+		if (fprintf(f, "%s", string) > 0) {
+			rewind(f);
+			len = fscanf(f, "%s", tmp);
+			if (strncmp(tmp, string, len) == 0) {
+				fclose(f);
+				return 0;
+			} else {
+				fclose(f);
+				return EINVAL;
+			}
+		}
+		return errno;
+	} else {
+		/* fallback to old ioctl */
+		/* not supported for new function */
+		return errno;
+	}
+}
+
 int br_set_bridge_forward_delay(const char *br, struct timeval *tv)
 {
 	return br_set(br, "forward_delay", __tv_to_jiffies(tv),
@@ -351,6 +420,16 @@ int br_set_stp_state(const char *br, int stp_state)
 	return br_set(br, "stp_state", stp_state,
BRCTL_SET_BRIDGE_STP_STATE);
 }
 
+int br_set_vepa_mode(const char *br, int vepa_mode)
+{
+	return br_set(br, "vepa_mode", vepa_mode, 0);
+}
+
+int br_set_vepa_uplink(const char *br, const char *uplink)
+{
+  return br_set_string(br, "uplink_port", uplink, IFNAMSIZ);
+}
+
 int br_set_bridge_priority(const char *br, int bridge_priority)
 {
 	return br_set(br, "priority", bridge_priority, 
@@ -398,6 +477,11 @@ int br_set_path_cost(const char *bridge, const char *port,
int cost)
 	return port_set(bridge, port, "path_cost", cost,
BRCTL_SET_PATH_COST);
 }
 
+int br_set_hairpin_mode(const char *bridge, const char *port, int hairpin_mode)
+{
+	return port_set(bridge, port, "hairpin_mode", hairpin_mode, 0);
+}
+
 static inline void __copy_fdb(struct fdb_entry *ent, 
 			      const struct __fdb_entry *f)
 {