[NET] core: add RFC2863 operstate

this patch adds a dormant flag to network devices, RFC2863 operstate derived
from these flags and possibility for userspace interaction. It allows drivers
to signal that a device is unusable for user traffic without disabling
queueing (and therefore the possibility for protocol establishment traffic to
flow) and a userspace supplicant (WPA, 802.1X) to mark a device unusable
without changes to the driver.

It is the result of our long discussion. However I must admit that it
represents what Jamal and I agreed on with compromises towards Krzysztof, but
Thomas and Krzysztof still disagree with some parts. Anyway I think it should
be applied.

Signed-off-by: Stefan Rompf <stefan@loplof.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/if.h

@@ -33,7 +33,7 @@
 #define	IFF_LOOPBACK	0x8		/* is a loopback net		*/
 #define	IFF_POINTOPOINT	0x10		/* interface is has p-p link	*/
 #define	IFF_NOTRAILERS	0x20		/* avoid use of trailers	*/
-#define	IFF_RUNNING	0x40		/* interface running and carrier ok */
+#define	IFF_RUNNING	0x40		/* interface RFC2863 OPER_UP	*/
 #define	IFF_NOARP	0x80		/* no ARP protocol		*/
 #define	IFF_PROMISC	0x100		/* receive all packets		*/
 #define	IFF_ALLMULTI	0x200		/* receive all multicast packets*/
@@ -43,12 +43,16 @@
 
 #define IFF_MULTICAST	0x1000		/* Supports multicast		*/
 
-#define IFF_VOLATILE	(IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_MASTER|IFF_SLAVE|IFF_RUNNING)
-
 #define IFF_PORTSEL	0x2000          /* can set media type		*/
 #define IFF_AUTOMEDIA	0x4000		/* auto media select active	*/
 #define IFF_DYNAMIC	0x8000		/* dialup device with changing addresses*/
 
+#define IFF_LOWER_UP	0x10000		/* driver signals L1 up		*/
+#define IFF_DORMANT	0x20000		/* driver signals dormant	*/
+
+#define IFF_VOLATILE	(IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|\
+		IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT)
+
 /* Private (from user) interface flags (netdevice->priv_flags). */
 #define IFF_802_1Q_VLAN 0x1             /* 802.1Q VLAN device.          */
 #define IFF_EBRIDGE	0x2		/* Ethernet bridging device.	*/
@@ -83,6 +87,22 @@
 #define IF_PROTO_FR_ETH_PVC 0x200B
 #define IF_PROTO_RAW    0x200C          /* RAW Socket                   */
 
+/* RFC 2863 operational status */
+enum {
+	IF_OPER_UNKNOWN,
+	IF_OPER_NOTPRESENT,
+	IF_OPER_DOWN,
+	IF_OPER_LOWERLAYERDOWN,
+	IF_OPER_TESTING,
+	IF_OPER_DORMANT,
+	IF_OPER_UP,
+};
+
+/* link modes */
+enum {
+	IF_LINK_MODE_DEFAULT,
+	IF_LINK_MODE_DORMANT,	/* limit upward transition to dormant */
+};
 
 /*
  *	Device mapping structure. I'd just gone off and designed a 

include/linux/netdevice.h

@@ -230,7 +230,8 @@ enum netdev_state_t
 	__LINK_STATE_SCHED,
 	__LINK_STATE_NOCARRIER,
 	__LINK_STATE_RX_SCHED,
-	__LINK_STATE_LINKWATCH_PENDING
+	__LINK_STATE_LINKWATCH_PENDING,
+	__LINK_STATE_DORMANT,
 };
 
 
@@ -335,11 +336,14 @@ struct net_device
 	 */
 
 
-	unsigned short		flags;	/* interface flags (a la BSD)	*/
+	unsigned int		flags;	/* interface flags (a la BSD)	*/
 	unsigned short		gflags;
         unsigned short          priv_flags; /* Like 'flags' but invisible to userspace. */
 	unsigned short		padded;	/* How much padding added by alloc_netdev() */
 
+	unsigned char		operstate; /* RFC2863 operstate */
+	unsigned char		link_mode; /* mapping policy to operstate */
+
 	unsigned		mtu;	/* interface MTU value		*/
 	unsigned short		type;	/* interface hardware type	*/
 	unsigned short		hard_header_len;	/* hardware hdr length	*/
@@ -714,6 +718,10 @@ static inline void dev_put(struct net_device *dev)
 /* Carrier loss detection, dial on demand. The functions netif_carrier_on
  * and _off may be called from IRQ context, but it is caller
  * who is responsible for serialization of these calls.
+ *
+ * The name carrier is inappropriate, these functions should really be
+ * called netif_lowerlayer_*() because they represent the state of any
+ * kind of lower layer not just hardware media.
  */
 
 extern void linkwatch_fire_event(struct net_device *dev);
@@ -729,6 +737,29 @@ extern void netif_carrier_on(struct net_device *dev);
 
 extern void netif_carrier_off(struct net_device *dev);
 
+static inline void netif_dormant_on(struct net_device *dev)
+{
+	if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state))
+		linkwatch_fire_event(dev);
+}
+
+static inline void netif_dormant_off(struct net_device *dev)
+{
+	if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state))
+		linkwatch_fire_event(dev);
+}
+
+static inline int netif_dormant(const struct net_device *dev)
+{
+	return test_bit(__LINK_STATE_DORMANT, &dev->state);
+}
+
+
+static inline int netif_oper_up(const struct net_device *dev) {
+	return (dev->operstate == IF_OPER_UP ||
+		dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
+}
+
 /* Hot-plugging. */
 static inline int netif_device_present(struct net_device *dev)
 {

include/linux/rtnetlink.h

@@ -733,6 +733,8 @@ enum
 #define IFLA_MAP IFLA_MAP
 	IFLA_WEIGHT,
 #define IFLA_WEIGHT IFLA_WEIGHT
+	IFLA_OPERSTATE,
+	IFLA_LINKMODE,
 	__IFLA_MAX
 };
 

net/core/dev.c

@@ -2174,12 +2174,20 @@ unsigned dev_get_flags(const struct net_device *dev)
 
 	flags = (dev->flags & ~(IFF_PROMISC |
 				IFF_ALLMULTI |
-				IFF_RUNNING)) | 
+				IFF_RUNNING |
+				IFF_LOWER_UP |
+				IFF_DORMANT)) |
 		(dev->gflags & (IFF_PROMISC |
 				IFF_ALLMULTI));
 
-	if (netif_running(dev) && netif_carrier_ok(dev))
-		flags |= IFF_RUNNING;
+	if (netif_running(dev)) {
+		if (netif_oper_up(dev))
+			flags |= IFF_RUNNING;
+		if (netif_carrier_ok(dev))
+			flags |= IFF_LOWER_UP;
+		if (netif_dormant(dev))
+			flags |= IFF_DORMANT;
+	}
 
 	return flags;
 }

net/core/link_watch.c

@@ -49,6 +49,45 @@ struct lw_event {
 /* Avoid kmalloc() for most systems */
 static struct lw_event singleevent;
 
+static unsigned char default_operstate(const struct net_device *dev)
+{
+	if (!netif_carrier_ok(dev))
+		return (dev->ifindex != dev->iflink ?
+			IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN);
+
+	if (netif_dormant(dev))
+		return IF_OPER_DORMANT;
+
+	return IF_OPER_UP;
+}
+
+
+static void rfc2863_policy(struct net_device *dev)
+{
+	unsigned char operstate = default_operstate(dev);
+
+	if (operstate == dev->operstate)
+		return;
+
+	write_lock_bh(&dev_base_lock);
+
+	switch(dev->link_mode) {
+	case IF_LINK_MODE_DORMANT:
+		if (operstate == IF_OPER_UP)
+			operstate = IF_OPER_DORMANT;
+		break;
+
+	case IF_LINK_MODE_DEFAULT:
+	default:
+		break;
+	};
+
+	dev->operstate = operstate;
+
+	write_unlock_bh(&dev_base_lock);
+}
+
+
 /* Must be called with the rtnl semaphore held */
 void linkwatch_run_queue(void)
 {
@@ -74,6 +113,7 @@ void linkwatch_run_queue(void)
 		 */
 		clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state);
 
+		rfc2863_policy(dev);
 		if (dev->flags & IFF_UP) {
 			if (netif_carrier_ok(dev)) {
 				WARN_ON(dev->qdisc_sleeping == &noop_qdisc);

net/core/net-sysfs.c

@@ -91,6 +91,7 @@ NETDEVICE_SHOW(iflink, fmt_dec);
 NETDEVICE_SHOW(ifindex, fmt_dec);
 NETDEVICE_SHOW(features, fmt_long_hex);
 NETDEVICE_SHOW(type, fmt_dec);
+NETDEVICE_SHOW(link_mode, fmt_dec);
 
 /* use same locking rules as GIFHWADDR ioctl's */
 static ssize_t format_addr(char *buf, const unsigned char *addr, int len)
@@ -133,6 +134,43 @@ static ssize_t show_carrier(struct class_device *dev, char *buf)
 	return -EINVAL;
 }
 
+static ssize_t show_dormant(struct class_device *dev, char *buf)
+{
+	struct net_device *netdev = to_net_dev(dev);
+
+	if (netif_running(netdev))
+		return sprintf(buf, fmt_dec, !!netif_dormant(netdev));
+
+	return -EINVAL;
+}
+
+static const char *operstates[] = {
+	"unknown",
+	"notpresent", /* currently unused */
+	"down",
+	"lowerlayerdown",
+	"testing", /* currently unused */
+	"dormant",
+	"up"
+};
+
+static ssize_t show_operstate(struct class_device *dev, char *buf)
+{
+	const struct net_device *netdev = to_net_dev(dev);
+	unsigned char operstate;
+
+	read_lock(&dev_base_lock);
+	operstate = netdev->operstate;
+	if (!netif_running(netdev))
+		operstate = IF_OPER_DOWN;
+	read_unlock(&dev_base_lock);
+
+	if (operstate >= sizeof(operstates))
+		return -EINVAL; /* should not happen */
+
+	return sprintf(buf, "%s\n", operstates[operstate]);
+}
+
 /* read-write attributes */
 NETDEVICE_SHOW(mtu, fmt_dec);
 
@@ -190,9 +228,12 @@ static struct class_device_attribute net_class_attributes[] = {
 	__ATTR(ifindex, S_IRUGO, show_ifindex, NULL),
 	__ATTR(features, S_IRUGO, show_features, NULL),
 	__ATTR(type, S_IRUGO, show_type, NULL),
+	__ATTR(link_mode, S_IRUGO, show_link_mode, NULL),
 	__ATTR(address, S_IRUGO, show_address, NULL),
 	__ATTR(broadcast, S_IRUGO, show_broadcast, NULL),
 	__ATTR(carrier, S_IRUGO, show_carrier, NULL),
+	__ATTR(dormant, S_IRUGO, show_dormant, NULL),
+	__ATTR(operstate, S_IRUGO, show_operstate, NULL),
 	__ATTR(mtu, S_IRUGO | S_IWUSR, show_mtu, store_mtu),
 	__ATTR(flags, S_IRUGO | S_IWUSR, show_flags, store_flags),
 	__ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len,

net/core/rtnetlink.c

@@ -179,6 +179,33 @@ rtattr_failure:
 }
 
 
+static void set_operstate(struct net_device *dev, unsigned char transition)
+{
+	unsigned char operstate = dev->operstate;
+
+	switch(transition) {
+	case IF_OPER_UP:
+		if ((operstate == IF_OPER_DORMANT ||
+		     operstate == IF_OPER_UNKNOWN) &&
+		    !netif_dormant(dev))
+			operstate = IF_OPER_UP;
+		break;
+
+	case IF_OPER_DORMANT:
+		if (operstate == IF_OPER_UP ||
+		    operstate == IF_OPER_UNKNOWN)
+			operstate = IF_OPER_DORMANT;
+		break;
+	};
+
+	if (dev->operstate != operstate) {
+		write_lock_bh(&dev_base_lock);
+		dev->operstate = operstate;
+		write_unlock_bh(&dev_base_lock);
+		netdev_state_change(dev);
+	}
+}
+
 static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				 int type, u32 pid, u32 seq, u32 change, 
 				 unsigned int flags)
@@ -208,6 +235,13 @@ static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 		RTA_PUT(skb, IFLA_WEIGHT, sizeof(weight), &weight);
 	}
 
+	if (1) {
+		u8 operstate = netif_running(dev)?dev->operstate:IF_OPER_DOWN;
+		u8 link_mode = dev->link_mode;
+		RTA_PUT(skb, IFLA_OPERSTATE, sizeof(operstate), &operstate);
+		RTA_PUT(skb, IFLA_LINKMODE, sizeof(link_mode), &link_mode);
+	}
+
 	if (1) {
 		struct rtnl_link_ifmap map = {
 			.mem_start   = dev->mem_start,
@@ -399,6 +433,22 @@ static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 		dev->weight = *((u32 *) RTA_DATA(ida[IFLA_WEIGHT - 1]));
 	}
 
+	if (ida[IFLA_OPERSTATE - 1]) {
+		if (ida[IFLA_OPERSTATE - 1]->rta_len != RTA_LENGTH(sizeof(u8)))
+			goto out;
+
+		set_operstate(dev, *((u8 *) RTA_DATA(ida[IFLA_OPERSTATE - 1])));
+	}
+
+	if (ida[IFLA_LINKMODE - 1]) {
+		if (ida[IFLA_LINKMODE - 1]->rta_len != RTA_LENGTH(sizeof(u8)))
+			goto out;
+
+		write_lock_bh(&dev_base_lock);
+		dev->link_mode = *((u8 *) RTA_DATA(ida[IFLA_LINKMODE - 1]));
+		write_unlock_bh(&dev_base_lock);
+	}
+
 	if (ifm->ifi_index >= 0 && ida[IFLA_IFNAME - 1]) {
 		char ifname[IFNAMSIZ];