Merge davem@nuts.davemloft.net:/disk1/BK/net-2.6

into kernel.bkbits.net:/home/davem/net-2.6

Documentation/Changes

@@ -407,7 +407,7 @@ o  <http://www.iptables.org/downloads.html>
 
 Ip-route2
 ---------
-o  <ftp://ftp.inr.ac.ru/ip-routing/iproute2-2.2.4-now-ss991023.tar.gz>
+o  <ftp://ftp.tux.org/pub/net/ip-routing/iproute2-2.2.4-now-ss991023.tar.gz>
 
 OProfile
 --------

Documentation/networking/ethertap.txt

@@ -47,7 +47,7 @@ This allows the kernel to exchange data with userspace applications. There
 are two ways of doing this, the new way works with netlink sockets and I
 have no experience with that yet. ANK uses it in his excellent iproute2
 package, see for example rtmon.c. iproute2 can be found on
-ftp://ftp.inr.ac.ru/ip-routing/iproute2*
+ftp://ftp.tux.org/pub/net/ip-routing/iproute2*
 
 The new way is described, partly in netlink(7), available on 
 http://www.europe.redhat.com/documentation/man-pages/man7/netlink.7.php3

drivers/net/Space.c

@@ -430,28 +430,3 @@ static int __init net_olddevs_init(void)
 }
 
 device_initcall(net_olddevs_init);
-
-/*
- * The @dev_base list is protected by @dev_base_lock and the rtln
- * semaphore.
- *
- * Pure readers hold dev_base_lock for reading.
- *
- * Writers must hold the rtnl semaphore while they loop through the
- * dev_base list, and hold dev_base_lock for writing when they do the
- * actual updates.  This allows pure readers to access the list even
- * while a writer is preparing to update it.
- *
- * To put it another way, dev_base_lock is held for writing only to
- * protect against pure readers; the rtnl semaphore provides the
- * protection against other writers.
- *
- * See, for example usages, register_netdevice() and
- * unregister_netdevice(), which must be called with the rtnl
- * semaphore held.
- */
-struct net_device *dev_base;
-rwlock_t dev_base_lock = RW_LOCK_UNLOCKED;
-
-EXPORT_SYMBOL(dev_base);
-EXPORT_SYMBOL(dev_base_lock);

drivers/net/pppoe.c

@@ -517,7 +517,7 @@ static int pppoe_create(struct socket *sock)
 	sk->sk_protocol	   = PX_PROTO_OE;
 	sk->sk_destruct	   = pppoe_sk_free;
 
-	po = pppox_sk(sk) = kmalloc(sizeof(*po), GFP_KERNEL);
+	po = sk->sk_protinfo = kmalloc(sizeof(*po), GFP_KERNEL);
 	if (!po)
 		goto frees;
 	memset(po, 0, sizeof(*po));

include/linux/if_vlan.h

@@ -200,6 +200,152 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb,
 {
 	return __vlan_hwaccel_rx(skb, grp, vlan_tag, 1);
 }
+
+/**
+ * __vlan_put_tag - regular VLAN tag inserting
+ * @skb: skbuff to tag
+ * @tag: VLAN tag to insert
+ *
+ * Inserts the VLAN tag into @skb as part of the payload
+ * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ * 
+ * Following the skb_unshare() example, in case of error, the calling function
+ * doesn't have to worry about freeing the original skb.
+ */
+static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, unsigned short tag)
+{
+	struct vlan_ethhdr *veth;
+
+	if (skb_headroom(skb) < VLAN_HLEN) {
+		struct sk_buff *sk_tmp = skb;
+		skb = skb_realloc_headroom(sk_tmp, VLAN_HLEN);
+		kfree_skb(sk_tmp);
+		if (!skb) {
+			printk(KERN_ERR "vlan: failed to realloc headroom\n");
+			return NULL;
+		}
+	} else {
+		skb = skb_unshare(skb, GFP_ATOMIC);
+		if (!skb) {
+			printk(KERN_ERR "vlan: failed to unshare skbuff\n");
+			return NULL;
+		}
+	}
+
+	veth = (struct vlan_ethhdr *)skb_push(skb, VLAN_HLEN);
+
+	/* Move the mac addresses to the beginning of the new header. */
+	memmove(skb->data, skb->data + VLAN_HLEN, 2 * VLAN_ETH_ALEN);
+
+	/* first, the ethernet type */
+	veth->h_vlan_proto = __constant_htons(ETH_P_8021Q);
+
+	/* now, the tag */
+	veth->h_vlan_TCI = htons(tag);
+
+	skb->protocol = __constant_htons(ETH_P_8021Q);
+	skb->mac.raw -= VLAN_HLEN;
+	skb->nh.raw -= VLAN_HLEN;
+
+	return skb;
+}
+
+/**
+ * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting
+ * @skb: skbuff to tag
+ * @tag: VLAN tag to insert
+ *
+ * Puts the VLAN tag in @skb->cb[] and lets the device do the rest
+ */
+static inline struct sk_buff *__vlan_hwaccel_put_tag(struct sk_buff *skb, unsigned short tag)
+{
+	struct vlan_skb_tx_cookie *cookie;
+
+	cookie = VLAN_TX_SKB_CB(skb);
+	cookie->magic = VLAN_TX_COOKIE_MAGIC;
+	cookie->vlan_tag = tag;
+
+	return skb;
+}
+
+#define HAVE_VLAN_PUT_TAG
+
+/**
+ * vlan_put_tag - inserts VLAN tag according to device features
+ * @skb: skbuff to tag
+ * @tag: VLAN tag to insert
+ *
+ * Assumes skb->dev is the target that will xmit this frame.
+ * Returns a VLAN tagged skb.
+ */
+static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb, unsigned short tag)
+{
+	if (skb->dev->features & NETIF_F_HW_VLAN_TX) {
+		return __vlan_hwaccel_put_tag(skb, tag);
+	} else {
+		return __vlan_put_tag(skb, tag);
+	}
+}
+
+/**
+ * __vlan_get_tag - get the VLAN ID that is part of the payload
+ * @skb: skbuff to query
+ * @tag: buffer to store vlaue
+ * 
+ * Returns error if the skb is not of VLAN type
+ */
+static inline int __vlan_get_tag(struct sk_buff *skb, unsigned short *tag)
+{
+	struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb->data;
+
+	if (veth->h_vlan_proto != __constant_htons(ETH_P_8021Q)) {
+		return -EINVAL;
+	}
+
+	*tag = ntohs(veth->h_vlan_TCI);
+
+	return 0;
+}
+
+/**
+ * __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[]
+ * @skb: skbuff to query
+ * @tag: buffer to store vlaue
+ * 
+ * Returns error if @skb->cb[] is not set correctly
+ */
+static inline int __vlan_hwaccel_get_tag(struct sk_buff *skb, unsigned short *tag)
+{
+	struct vlan_skb_tx_cookie *cookie;
+
+	cookie = VLAN_TX_SKB_CB(skb);
+	if (cookie->magic == VLAN_TX_COOKIE_MAGIC) {
+		*tag = cookie->vlan_tag;
+		return 0;
+	} else {
+		*tag = 0;
+		return -EINVAL;
+	}
+}
+
+#define HAVE_VLAN_GET_TAG
+
+/**
+ * vlan_get_tag - get the VLAN ID from the skb
+ * @skb: skbuff to query
+ * @tag: buffer to store vlaue
+ * 
+ * Returns error if the skb is not VLAN tagged
+ */
+static inline int vlan_get_tag(struct sk_buff *skb, unsigned short *tag)
+{
+	if (skb->dev->features & NETIF_F_HW_VLAN_TX) {
+		return __vlan_hwaccel_get_tag(skb, tag);
+	} else {
+		return __vlan_get_tag(skb, tag);
+	}
+}
+
 #endif /* __KERNEL__ */
 
 /* VLAN IOCTLs are found in sockios.h */

include/linux/kernel.h

@@ -90,6 +90,7 @@ asmlinkage int printk(const char * fmt, ...)
 unsigned long int_sqrt(unsigned long);
 
 extern int printk_ratelimit(void);
+extern int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst);
 
 static inline void console_silent(void)
 {

include/linux/netdevice.h

@@ -375,6 +375,10 @@ struct net_device
 	atomic_t		refcnt;
 	/* delayed register/unregister */
 	struct list_head	todo_list;
+	/* device name hash chain */
+	struct hlist_node	name_hlist;
+	/* device index hash chain */
+	struct hlist_node	index_hlist;
 
 	/* register/unregister state machine */
 	enum { NETREG_UNINITIALIZED=0,

include/linux/string.h

@@ -52,6 +52,9 @@ extern int strnicmp(const char *, const char *, __kernel_size_t);
 #ifndef __HAVE_ARCH_STRCHR
 extern char * strchr(const char *,int);
 #endif
+#ifndef __HAVE_ARCH_STRNCHR
+extern char * strnchr(const char *, size_t, int);
+#endif
 #ifndef __HAVE_ARCH_STRRCHR
 extern char * strrchr(const char *,int);
 #endif

include/net/arp.h

@@ -5,6 +5,8 @@
 #include <linux/if_arp.h>
 #include <net/neighbour.h>
 
+#define HAVE_ARP_CREATE
+
 extern struct neigh_table arp_tbl;
 
 extern void	arp_init(void);
@@ -19,6 +21,12 @@ extern int	arp_bind_neighbour(struct dst_entry *dst);
 extern int	arp_mc_map(u32 addr, u8 *haddr, struct net_device *dev, int dir);
 extern void	arp_ifdown(struct net_device *dev);
 
+extern struct sk_buff *arp_create(int type, int ptype, u32 dest_ip,
+				  struct net_device *dev, u32 src_ip,
+				  unsigned char *dest_hw, unsigned char *src_hw,
+				  unsigned char *target_hw);
+extern void arp_xmit(struct sk_buff *skb);
+
 extern struct neigh_ops arp_broken_ops;
 
 #endif	/* _ARP_H */

kernel/printk.c

@@ -784,12 +784,6 @@ void tty_write_message(struct tty_struct *tty, char *msg)
 	return;
 }
 
-/* minimum time in jiffies between messages */
-int printk_ratelimit_jiffies = 5*HZ;
-
-/* number of messages we send before ratelimiting */
-int printk_ratelimit_burst = 10;
-
 /*
  * printk rate limiting, lifted from the networking subsystem.
  *
@@ -797,7 +791,7 @@ int printk_ratelimit_burst = 10;
  * every printk_ratelimit_jiffies to make a denial-of-service
  * attack impossible.
  */
-int printk_ratelimit(void)
+int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst)
 {
 	static spinlock_t ratelimit_lock = SPIN_LOCK_UNLOCKED;
 	static unsigned long toks = 10*5*HZ;
@@ -809,12 +803,12 @@ int printk_ratelimit(void)
 	spin_lock_irqsave(&ratelimit_lock, flags);
 	toks += now - last_msg;
 	last_msg = now;
-	if (toks > (printk_ratelimit_burst * printk_ratelimit_jiffies))
-		toks = printk_ratelimit_burst * printk_ratelimit_jiffies;
-	if (toks >= printk_ratelimit_jiffies) {
+	if (toks > (ratelimit_burst * ratelimit_jiffies))
+		toks = ratelimit_burst * ratelimit_jiffies;
+	if (toks >= ratelimit_jiffies) {
 		int lost = missed;
 		missed = 0;
-		toks -= printk_ratelimit_jiffies;
+		toks -= ratelimit_jiffies;
 		spin_unlock_irqrestore(&ratelimit_lock, flags);
 		if (lost)
 			printk(KERN_WARNING "printk: %d messages suppressed.\n", lost);
@@ -824,4 +818,17 @@ int printk_ratelimit(void)
 	spin_unlock_irqrestore(&ratelimit_lock, flags);
 	return 0;
 }
+EXPORT_SYMBOL(__printk_ratelimit);
+
+/* minimum time in jiffies between messages */
+int printk_ratelimit_jiffies = 5*HZ;
+
+/* number of messages we send before ratelimiting */
+int printk_ratelimit_burst = 10;
+
+int printk_ratelimit(void)
+{
+	return __printk_ratelimit(printk_ratelimit_jiffies,
+				printk_ratelimit_burst);
+}
 EXPORT_SYMBOL(printk_ratelimit);

lib/string.c

@@ -273,6 +273,22 @@ char * strrchr(const char * s, int c)
 }
 #endif
 
+#ifndef __HAVE_ARCH_STRNCHR
+/**
+ * strnchr - Find a character in a length limited string
+ * @s: The string to be searched
+ * @count: The number of characters to be searched
+ * @c: The character to search for
+ */
+char *strnchr(const char *s, size_t count, int c)
+{
+	for (; count-- && *s != '\0'; ++s)
+		if (*s == (char) c)
+			return (char *) s;
+	return NULL;
+}
+#endif
+
 #ifndef __HAVE_ARCH_STRLEN
 /**
  * strlen - Find the length of a string

net/8021q/vlan_dev.c

@@ -445,6 +445,7 @@ int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 
 	if (veth->h_vlan_proto != __constant_htons(ETH_P_8021Q)) {
+		int orig_headroom = skb_headroom(skb);
 		unsigned short veth_TCI;
 
 		/* This is not a VLAN frame...but we can fix that! */
@@ -454,33 +455,7 @@ int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		printk(VLAN_DBG "%s: proto to encap: 0x%hx (hbo)\n",
 			__FUNCTION__, htons(veth->h_vlan_proto));
 #endif
-
-		if (skb_headroom(skb) < VLAN_HLEN) {
-			struct sk_buff *sk_tmp = skb;
-			skb = skb_realloc_headroom(sk_tmp, VLAN_HLEN);
-			kfree_skb(sk_tmp);
-			if (skb == NULL) {
-				stats->tx_dropped++;
-				return 0;
-			}
-			VLAN_DEV_INFO(dev)->cnt_inc_headroom_on_tx++;
-		} else {
-			if (!(skb = skb_unshare(skb, GFP_ATOMIC))) {
-				printk(KERN_ERR "vlan: failed to unshare skbuff\n");
-				stats->tx_dropped++;
-				return 0;
-			}
-		}
-		veth = (struct vlan_ethhdr *)skb_push(skb, VLAN_HLEN);
-
-		/* Move the mac addresses to the beginning of the new header. */
-		memmove(skb->data, skb->data + VLAN_HLEN, 12);
-
-		/* first, the ethernet type */
-		/* put_unaligned(__constant_htons(ETH_P_8021Q), &veth->h_vlan_proto); */
-		veth->h_vlan_proto = __constant_htons(ETH_P_8021Q);
-
-		/* Now, construct the second two bytes. This field looks something
+		/* Construct the second two bytes. This field looks something
 		 * like:
 		 * usr_priority: 3 bits	 (high bits)
 		 * CFI		 1 bit
@@ -489,10 +464,16 @@ int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		veth_TCI = VLAN_DEV_INFO(dev)->vlan_id;
 		veth_TCI |= vlan_dev_get_egress_qos_mask(dev, skb);
 
-		veth->h_vlan_TCI = htons(veth_TCI);
+		skb = __vlan_put_tag(skb, veth_TCI);
+		if (!skb) {
+			stats->tx_dropped++;
+			return 0;
 		}
 
-	skb->dev = VLAN_DEV_INFO(dev)->real_dev;
+		if (orig_headroom < VLAN_HLEN) {
+			VLAN_DEV_INFO(dev)->cnt_inc_headroom_on_tx++;
+		}
+	}
 
 #ifdef VLAN_DEBUG
 	printk(VLAN_DBG "%s: about to send skb: %p to dev: %s\n",
@@ -506,10 +487,7 @@ int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	stats->tx_packets++; /* for statics only */
 	stats->tx_bytes += skb->len;
 
-	skb->protocol = __constant_htons(ETH_P_8021Q);
-	skb->mac.raw -= VLAN_HLEN;
-	skb->nh.raw -= VLAN_HLEN;
-
+	skb->dev = VLAN_DEV_INFO(dev)->real_dev;
 	dev_queue_xmit(skb);
 
 	return 0;
@@ -518,17 +496,22 @@ int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 int vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct net_device_stats *stats = vlan_dev_get_stats(dev);
-	struct vlan_skb_tx_cookie *cookie;
+	unsigned short veth_TCI;
+
+	/* Construct the second two bytes. This field looks something
+	 * like:
+	 * usr_priority: 3 bits	 (high bits)
+	 * CFI		 1 bit
+	 * VLAN ID	 12 bits (low bits)
+	 */
+	veth_TCI = VLAN_DEV_INFO(dev)->vlan_id;
+	veth_TCI |= vlan_dev_get_egress_qos_mask(dev, skb);
+	skb = __vlan_hwaccel_put_tag(skb, veth_TCI);
 
 	stats->tx_packets++;
 	stats->tx_bytes += skb->len;
 
 	skb->dev = VLAN_DEV_INFO(dev)->real_dev;
-	cookie = VLAN_TX_SKB_CB(skb);
-	cookie->magic = VLAN_TX_COOKIE_MAGIC;
-	cookie->vlan_tag = (VLAN_DEV_INFO(dev)->vlan_id |
-			    vlan_dev_get_egress_qos_mask(dev, skb));
-
 	dev_queue_xmit(skb);
 
 	return 0;

net/Kconfig

@@ -145,7 +145,7 @@ config DECNET
 
 	  To find some tools to use with the kernel layer support, please
 	  look at Patrick Caulfield's web site:
-	  <http://linux.dreamtime.org/decnet/>.
+	  <http://linux-decnet.sourceforge.net/>.
 
 	  More detailed documentation is available in
 	  <file:Documentation/networking/decnet.txt>.
@@ -436,7 +436,7 @@ config X25
 	  (say Y to "LAPB Data Link Driver" below if you want that).
 
 	  You can read more about X.25 at <http://www.sangoma.com/x25.htm> and
-	  <http://www.cisco.com/univercd/data/doc/software/11_0/rpcg/cx25.htm>.
+	  <http://www.cisco.com/univercd/cc/td/doc/product/software/ios11/cbook/cx25.htm>.
 	  Information about X.25 for Linux is contained in the files
 	  <file:Documentation/networking/x25.txt> and
 	  <file:Documentation/networking/x25-iface.txt>.
@@ -571,7 +571,7 @@ config NET_FASTROUTE
 
 	  At the moment, few devices support fast switching (tulip is one of
 	  them, a modified 8390 driver can be found at
-	  <ftp://ftp.inr.ac.ru/ip-routing/fastroute/fastroute-8390.tar.gz>).
+	  <ftp://ftp.tux.org/pub/net/ip-routing/fastroute/fastroute-8390.tar.gz>).
 
 	  If unsure, say N.
 
@@ -583,7 +583,7 @@ config NET_HW_FLOWCONTROL
 	  during periods of extreme congestion. At the moment only a couple
 	  of device drivers support it (really only one -- tulip, a modified
 	  8390 driver can be found at
-	  <ftp://ftp.inr.ac.ru/ip-routing/fastroute/fastroute-8390.tar.gz>).
+	  <ftp://ftp.tux.org/pub/net/ip-routing/fastroute/fastroute-8390.tar.gz>).
 
 	  Really, this option is applicable to any machine attached to a fast
 	  enough network, and even a 10 Mb NIC is able to kill a not very slow
@@ -614,7 +614,7 @@ config NET_SCHED
 	  This code is considered to be experimental.
 
 	  To administer these schedulers, you'll need the user-level utilities
-	  from the package iproute2+tc at <ftp://ftp.inr.ac.ru/ip-routing/>.
+	  from the package iproute2+tc at <ftp://ftp.tux.org/pub/net/ip-routing/>.
 	  That package also contains some documentation; for more, check out
 	  <http://snafu.freedom.org/linux2.2/iproute-notes.html>.
 

net/core/dev.c

@@ -160,6 +160,47 @@ static void sample_queue(unsigned long dummy);
 static struct timer_list samp_timer = TIMER_INITIALIZER(sample_queue, 0, 0);
 #endif
 
+/*
+ * The @dev_base list is protected by @dev_base_lock and the rtln
+ * semaphore.
+ *
+ * Pure readers hold dev_base_lock for reading.
+ *
+ * Writers must hold the rtnl semaphore while they loop through the
+ * dev_base list, and hold dev_base_lock for writing when they do the
+ * actual updates.  This allows pure readers to access the list even
+ * while a writer is preparing to update it.
+ *
+ * To put it another way, dev_base_lock is held for writing only to
+ * protect against pure readers; the rtnl semaphore provides the
+ * protection against other writers.
+ *
+ * See, for example usages, register_netdevice() and
+ * unregister_netdevice(), which must be called with the rtnl
+ * semaphore held.
+ */
+struct net_device *dev_base;
+struct net_device **dev_tail = &dev_base;
+rwlock_t dev_base_lock = RW_LOCK_UNLOCKED;
+
+EXPORT_SYMBOL(dev_base);
+EXPORT_SYMBOL(dev_base_lock);
+
+#define NETDEV_HASHBITS	8
+static struct hlist_head dev_name_head[1<<NETDEV_HASHBITS];
+static struct hlist_head dev_index_head[1<<NETDEV_HASHBITS];
+
+static inline struct hlist_head *dev_name_hash(const char *name)
+{
+	unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
+	return &dev_name_head[hash & ((1<<NETDEV_HASHBITS)-1)];
+}
+
+static inline struct hlist_head *dev_index_hash(int ifindex)
+{
+	return &dev_index_head[ifindex & ((1<<NETDEV_HASHBITS)-1)];
+}
+
 /*
  *	Our notifier list
  */
@@ -443,12 +484,15 @@ __setup("netdev=", netdev_boot_setup);
 
 struct net_device *__dev_get_by_name(const char *name)
 {
-	struct net_device *dev;
+	struct hlist_node *p;
 
-	for (dev = dev_base; dev; dev = dev->next)
+	hlist_for_each(p, dev_name_hash(name)) {
+		struct net_device *dev
+			= hlist_entry(p, struct net_device, name_hlist);
 		if (!strncmp(dev->name, name, IFNAMSIZ))
-			break;
 			return dev;
+	}
+	return NULL;
 }
 
 /**
@@ -516,12 +560,15 @@ int __dev_get(const char *name)
 
 struct net_device *__dev_get_by_index(int ifindex)
 {
-	struct net_device *dev;
+	struct hlist_node *p;
 
-	for (dev = dev_base; dev; dev = dev->next)
+	hlist_for_each(p, dev_index_hash(ifindex)) {
+		struct net_device *dev
+			= hlist_entry(p, struct net_device, index_hlist);
 		if (dev->ifindex == ifindex)
-			break;
 			return dev;
+	}
+	return NULL;
 }
 
 
@@ -673,30 +720,55 @@ int dev_valid_name(const char *name)
 
 int dev_alloc_name(struct net_device *dev, const char *name)
 {
-	int i;
-	char buf[32];
-	char *p;
+	int i = 0;
+	char buf[IFNAMSIZ];
+	const char *p;
+	const int max_netdevices = 8*PAGE_SIZE;
+	long *inuse;
+	struct net_device *d;
 
+	p = strnchr(name, IFNAMSIZ-1, '%');
+	if (p) {
 		/*
 		 * Verify the string as this thing may have come from
 		 * the user.  There must be either one "%d" and no other "%"
-	 * characters, or no "%" characters at all.
+		 * characters.
 		 */
-	p = strchr(name, '%');
-	if (p && (p[1] != 'd' || strchr(p + 2, '%')))
+		if (p[1] != 'd' || strchr(p + 2, '%'))
 			return -EINVAL;
 
-	/*
-	 * If you need over 100 please also fix the algorithm...
-	 */
-	for (i = 0; i < 100; i++) {
+		/* Use one page as a bit array of possible slots */
+		inuse = (long *) get_zeroed_page(GFP_ATOMIC);
+		if (!inuse)
+			return -ENOMEM;
+
+		for (d = dev_base; d; d = d->next) {
+			if (!sscanf(d->name, name, &i))
+				continue;
+			if (i < 0 || i >= max_netdevices)
+				continue;
+
+			/*  avoid cases where sscanf is not exact inverse of printf */
+			snprintf(buf, sizeof(buf), name, i);
+			if (!strncmp(buf, d->name, IFNAMSIZ))
+				set_bit(i, inuse);
+		}
+
+		i = find_first_zero_bit(inuse, max_netdevices);
+		free_page((unsigned long) inuse);
+	}
+
 	snprintf(buf, sizeof(buf), name, i);
 	if (!__dev_get_by_name(buf)) {
-			strcpy(dev->name, buf);
+		strlcpy(dev->name, buf, IFNAMSIZ);
 		return i;
 	}
-	}
-	return -ENFILE;	/* Over 100 of the things .. bail out! */
+
+	/* It is possible to run out of possible slots
+	 * when the name is long and there isn't enough space left
+	 * for the digits, or if all bits are used.
+	 */
+	return -ENFILE;
 }
 
 
@@ -729,6 +801,9 @@ int dev_change_name(struct net_device *dev, char *newname)
 	else
 		strlcpy(dev->name, newname, IFNAMSIZ);
 
+	hlist_del(&dev->name_hlist);
+	hlist_add_head(&dev->name_hlist, dev_name_hash(dev->name));
+
 	class_device_rename(&dev->class_dev, dev->name);
 	notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev);
 	return 0;
@@ -2717,7 +2792,8 @@ static inline void net_set_todo(struct net_device *dev)
 
 int register_netdevice(struct net_device *dev)
 {
-	struct net_device *d, **dp;
+	struct hlist_head *head;
+	struct hlist_node *p;
 	int ret;
 
 	BUG_ON(dev_boot_phase);
@@ -2758,12 +2834,16 @@ int register_netdevice(struct net_device *dev)
 	if (dev->iflink == -1)
 		dev->iflink = dev->ifindex;
 
-	/* Check for existence, and append to tail of chain */
+	/* Check for existence of name */
+	head = dev_name_hash(dev->name);
+	hlist_for_each(p, head) {
+		struct net_device *d
+			= hlist_entry(p, struct net_device, name_hlist);
+		if (!strncmp(d->name, dev->name, IFNAMSIZ)) {
 			ret = -EEXIST;
-	for (dp = &dev_base; (d = *dp) != NULL; dp = &d->next) {
-		if (d == dev || !strcmp(d->name, dev->name))
  			goto out_err;
 		}
+ 	}
 
 	/* Fix illegal SG+CSUM combinations. */
 	if ((dev->features & NETIF_F_SG) &&
@@ -2793,7 +2873,10 @@ int register_netdevice(struct net_device *dev)
 	dev->next = NULL;
 	dev_init_scheduler(dev);
 	write_lock_bh(&dev_base_lock);
-	*dp = dev;
+	*dev_tail = dev;
+	dev_tail = &dev->next;
+	hlist_add_head(&dev->name_hlist, head);
+	hlist_add_head(&dev->index_hlist, dev_index_hash(dev->ifindex));
 	dev_hold(dev);
 	dev->reg_state = NETREG_REGISTERING;
 	write_unlock_bh(&dev_base_lock);
@@ -3015,6 +3098,10 @@ int unregister_netdevice(struct net_device *dev)
 	for (dp = &dev_base; (d = *dp) != NULL; dp = &d->next) {
 		if (d == dev) {
 			write_lock_bh(&dev_base_lock);
+			hlist_del(&dev->name_hlist);
+			hlist_del(&dev->index_hlist);
+			if (dev_tail == &dev->next)
+				dev_tail = dp;
 			*dp = d->next;
 			write_unlock_bh(&dev_base_lock);
 			break;
@@ -3091,6 +3178,12 @@ static int __init net_dev_init(void)
 	for (i = 0; i < 16; i++) 
 		INIT_LIST_HEAD(&ptype_base[i]);
 
+	for (i = 0; i < ARRAY_SIZE(dev_name_head); i++)
+		INIT_HLIST_HEAD(&dev_name_head[i]);
+
+	for (i = 0; i < ARRAY_SIZE(dev_index_head); i++)
+		INIT_HLIST_HEAD(&dev_index_head[i]);
+
 	/*
 	 *	Initialise the packet receive queues.
 	 */

net/core/utils.c

@@ -41,37 +41,11 @@ int net_msg_cost = 5*HZ;
 int net_msg_burst = 10;
 
 /* 
- * This enforces a rate limit: not more than one kernel message
- * every 5secs to make a denial-of-service attack impossible.
- *
- * All warning printk()s should be guarded by this function. 
+ * All net warning printk()s should be guarded by this function.
  */ 
 int net_ratelimit(void)
 {
-	static spinlock_t ratelimit_lock = SPIN_LOCK_UNLOCKED;
-	static unsigned long toks = 10*5*HZ;
-	static unsigned long last_msg; 
-	static int missed;
-	unsigned long flags;
-	unsigned long now = jiffies;
-
-	spin_lock_irqsave(&ratelimit_lock, flags);
-	toks += now - last_msg;
-	last_msg = now;
-	if (toks > net_msg_burst)
-		toks = net_msg_burst;
-	if (toks >= net_msg_cost) {
-		int lost = missed;
-		missed = 0;
-		toks -= net_msg_cost;
-		spin_unlock_irqrestore(&ratelimit_lock, flags);
-		if (lost)
-			printk(KERN_WARNING "NET: %d messages suppressed.\n", lost);
-		return 1;
-	}
-	missed++;
-	spin_unlock_irqrestore(&ratelimit_lock, flags);
-	return 0;
+	return __printk_ratelimit(net_msg_cost, net_msg_burst);
 }
 
 EXPORT_SYMBOL(net_random);

net/decnet/Kconfig

@@ -22,8 +22,9 @@ config DECNET_ROUTER
 	  network link driver", "Routing messages" and "Network packet
 	  filtering".  The first two are required to allow configuration via
 	  rtnetlink (you will need Alexey Kuznetsov's iproute2 package
-	  from <ftp://ftp.inr.ac.ru/>). The "Network packet filtering" option
-	  will be required for the forthcoming routing daemon to work.
+	  from <ftp://ftp.tux.org/pub/net/ip-routing/>). The "Network packet
+	  filtering" option will be required for the forthcoming routing daemon
+	  to work.
 
 	  See <file:Documentation/networking/decnet.txt> for more information.
 

net/ipv4/Kconfig

@@ -71,7 +71,7 @@ config IP_MULTIPLE_TABLES
 	  documentation at <http://www.compendium.com.ar/policy-routing.txt>
 	  and <ftp://post.tepkom.ru/pub/vol2/Linux/docs/advanced-routing.tex>.
 	  You will need supporting software from
-	  <ftp://ftp.inr.ac.ru/ip-routing/>.
+	  <ftp://ftp.tux.org/pub/net/ip-routing/>.
 
 	  If unsure, say N.
 

net/ipv4/arp.c

@@ -67,6 +67,10 @@
  *					now it is in net/core/neighbour.c.
  *		Krzysztof Halasa:	Added Frame Relay ARP support.
  *		Arnaldo C. Melo :	convert /proc/net/arp to seq_file
+ *		Shmulik Hen:		Split arp_send to arp_create and
+ *					arp_xmit so intermediate drivers like
+ *					bonding can change the skb before
+ *					sending (e.g. insert 8021q tag).
  */
 
 #include <linux/module.h>
@@ -487,11 +491,10 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt)
  */
 
 /*
- *	Create and send an arp packet. If (dest_hw == NULL), we create a broadcast
+ *	Create an arp packet. If (dest_hw == NULL), we create a broadcast
  *	message.
  */
-
-void arp_send(int type, int ptype, u32 dest_ip, 
+struct sk_buff *arp_create(int type, int ptype, u32 dest_ip,
 			   struct net_device *dev, u32 src_ip,
 			   unsigned char *dest_hw, unsigned char *src_hw,
 			   unsigned char *target_hw)
@@ -500,13 +503,6 @@ void arp_send(int type, int ptype, u32 dest_ip,
 	struct arphdr *arp;
 	unsigned char *arp_ptr;
 
-	/*
-	 *	No arp on this interface.
-	 */
-	
-	if (dev->flags&IFF_NOARP)
-		return;
-
 	/*
 	 *	Allocate a buffer
 	 */
@@ -514,7 +510,7 @@ void arp_send(int type, int ptype, u32 dest_ip,
 	skb = alloc_skb(sizeof(struct arphdr)+ 2*(dev->addr_len+4)
 				+ LL_RESERVED_SPACE(dev), GFP_ATOMIC);
 	if (skb == NULL)
-		return;
+		return NULL;
 
 	skb_reserve(skb, LL_RESERVED_SPACE(dev));
 	skb->nh.raw = skb->data;
@@ -594,12 +590,46 @@ void arp_send(int type, int ptype, u32 dest_ip,
 	arp_ptr+=dev->addr_len;
 	memcpy(arp_ptr, &dest_ip, 4);
 
-	/* Send it off, maybe filter it using firewalling first.  */
-	NF_HOOK(NF_ARP, NF_ARP_OUT, skb, NULL, dev, dev_queue_xmit);
-	return;
+	return skb;
 
 out:
 	kfree_skb(skb);
+	return NULL;
+}
+
+/*
+ *	Send an arp packet.
+ */
+void arp_xmit(struct sk_buff *skb)
+{
+	/* Send it off, maybe filter it using firewalling first.  */
+	NF_HOOK(NF_ARP, NF_ARP_OUT, skb, NULL, skb->dev, dev_queue_xmit);
+}
+
+/*
+ *	Create and send an arp packet.
+ */
+void arp_send(int type, int ptype, u32 dest_ip, 
+	      struct net_device *dev, u32 src_ip, 
+	      unsigned char *dest_hw, unsigned char *src_hw,
+	      unsigned char *target_hw)
+{
+	struct sk_buff *skb;
+
+	/*
+	 *	No arp on this interface.
+	 */
+	
+	if (dev->flags&IFF_NOARP)
+		return;
+
+	skb = arp_create(type, ptype, dest_ip, dev, src_ip,
+			 dest_hw, src_hw, target_hw);
+	if (skb == NULL) {
+		return;
+	}
+
+	arp_xmit(skb);
 }
 
 static void parp_redo(struct sk_buff *skb)
@@ -1437,6 +1467,8 @@ static int __init arp_proc_init(void)
 EXPORT_SYMBOL(arp_broken_ops);
 EXPORT_SYMBOL(arp_find);
 EXPORT_SYMBOL(arp_rcv);
+EXPORT_SYMBOL(arp_create);
+EXPORT_SYMBOL(arp_xmit);
 EXPORT_SYMBOL(arp_send);
 EXPORT_SYMBOL(arp_tbl);
 

net/ipv6/ndisc.c

@@ -707,8 +707,10 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 	struct ndisc_options ndopts;
 	struct net_device *dev = skb->dev;
 	struct inet6_ifaddr *ifp;
+	struct inet6_dev *idev = NULL;
 	struct neighbour *neigh;
-	int addr_type = ipv6_addr_type(saddr);
+	int dad = ipv6_addr_any(saddr);
+	int inc;
 
 	if (ipv6_addr_is_multicast(&msg->target)) {
 		if (net_ratelimit())
@@ -720,7 +722,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 	 * RFC2461 7.1.1:
 	 * DAD has to be destined for solicited node multicast address.
 	 */
-	if (addr_type == IPV6_ADDR_ANY &&
+	if (dad &&
 	    !(daddr->s6_addr32[0] == htonl(0xff020000) &&
 	      daddr->s6_addr32[1] == htonl(0x00000000) &&
 	      daddr->s6_addr32[2] == htonl(0x00000001) &&
@@ -750,13 +752,15 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 		 *	there MUST NOT be source link-layer address option 
 		 *	in the message.
 		 */
-		if (addr_type == IPV6_ADDR_ANY) {
+		if (dad) {
 			if (net_ratelimit())
 				printk(KERN_WARNING "ICMP6 NS: bad DAD packet (link-layer address option)\n");
 			return;
 		}
 	}
 
+	inc = ipv6_addr_is_multicast(daddr);
+
 	if ((ifp = ipv6_get_ifaddr(&msg->target, dev, 1)) != NULL) {
 		if (ifp->flags & IFA_F_TENTATIVE) {
 			/* Address is tentative. If the source
@@ -764,81 +768,64 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 			   does DAD, otherwise we ignore solicitations
 			   until DAD timer expires.
 			 */
-			if (addr_type == IPV6_ADDR_ANY) {
+			if (!dad)
+				goto out;
 			if (dev->type == ARPHRD_IEEE802_TR) {
-					unsigned char *sadr = skb->mac.raw ;
-					if (((sadr[8] &0x7f) != (dev->dev_addr[0] & 0x7f)) ||
-					(sadr[9] != dev->dev_addr[1]) ||
-					(sadr[10] != dev->dev_addr[2]) ||
-					(sadr[11] != dev->dev_addr[3]) ||
-					(sadr[12] != dev->dev_addr[4]) ||
-					(sadr[13] != dev->dev_addr[5])) 
-					{
-						addrconf_dad_failure(ifp) ; 
+				unsigned char *sadr = skb->mac.raw;
+				if (((sadr[8] ^ dev->dev_addr[0]) & 0x7f) == 0 &&
+				    sadr[9] == dev->dev_addr[1] &&
+				    sadr[10] == dev->dev_addr[2] &&
+				    sadr[11] == dev->dev_addr[3] &&
+				    sadr[12] == dev->dev_addr[4] &&
+				    sadr[13] == dev->dev_addr[5]) {
+					/* looped-back to us */
+					goto out;
 				}
-				} else {
-					addrconf_dad_failure(ifp);
 			}
-			} else
-				in6_ifa_put(ifp);
+			addrconf_dad_failure(ifp); 
 			return;
 		}
 
-		if (addr_type == IPV6_ADDR_ANY) {
-			struct in6_addr maddr;
-
-			ipv6_addr_all_nodes(&maddr);
-			ndisc_send_na(dev, NULL, &maddr, &ifp->addr, 
-				      ifp->idev->cnf.forwarding, 0, 
-				      1, 1);
-			in6_ifa_put(ifp);
+		idev = ifp->idev;
+	} else {
+		idev = in6_dev_get(dev);
+		if (!idev) {
+			/* XXX: count this drop? */
 			return;
 		}
 
-		if (addr_type & IPV6_ADDR_UNICAST) {
-			if (ipv6_addr_is_multicast(daddr))
-				nd_tbl.stats.rcv_probes_mcast++;
-			else
-				nd_tbl.stats.rcv_probes_ucast++;
-
+		if (ipv6_chk_acast_addr(dev, &msg->target) ||
+		    (idev->cnf.forwarding && 
+		     pneigh_lookup(&nd_tbl, &msg->target, dev, 0))) {
+			if (skb->stamp.tv_sec != 0 &&
+			    skb->pkt_type != PACKET_HOST &&
+			    inc != 0 &&
+			    idev->nd_parms->proxy_delay != 0) {
 				/*
-			 *	update / create cache entry
-			 *	for the source address
+				 * for anycast or proxy,
+				 * sender should delay its response 
+				 * by a random time between 0 and 
+				 * MAX_ANYCAST_DELAY_TIME seconds.
+				 * (RFC2461) -- yoshfuji
 				 */
-
-			neigh = neigh_event_ns(&nd_tbl, lladdr, saddr, dev);
-
-			if (neigh || !dev->hard_header) {
-				ndisc_send_na(dev, neigh, saddr, &ifp->addr, 
-					      ifp->idev->cnf.forwarding, 1, 
-					      1, 1);
-				if (neigh)
-					neigh_release(neigh);
-			}
+				struct sk_buff *n = skb_clone(skb, GFP_ATOMIC);
+				if (n)
+					pneigh_enqueue(&nd_tbl, idev->nd_parms, n);
+				goto out;
 			}
-		in6_ifa_put(ifp);
-	} else if (ipv6_chk_acast_addr(dev, &msg->target)) {
-		struct inet6_dev *idev = in6_dev_get(dev);
-	
-		/* anycast */
-	
-		if (!idev) {
-			/* XXX: count this drop? */
-			return;
+		} else
+			goto out;
 	}
 
-		if (addr_type == IPV6_ADDR_ANY) {
+	if (dad) {
 		struct in6_addr maddr;
 
 		ipv6_addr_all_nodes(&maddr);
 		ndisc_send_na(dev, NULL, &maddr, &msg->target,
-				      idev->cnf.forwarding, 0, 0, 1);
-			in6_dev_put(idev);
-			return;
+			      idev->cnf.forwarding, 0, (ifp != NULL), 1);
+		goto out;
 	}
 
-		if (addr_type & IPV6_ADDR_UNICAST) {
-			int inc = ipv6_addr_is_multicast(daddr);
 	if (inc)
 		nd_tbl.stats.rcv_probes_mcast++;
 	else
@@ -848,62 +835,22 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 	 *	update / create cache entry
 	 *	for the source address
 	 */
-
-			neigh = neigh_event_ns(&nd_tbl, lladdr, saddr, skb->dev);
+	neigh = neigh_event_ns(&nd_tbl, lladdr, saddr, dev);
 
 	if (neigh || !dev->hard_header) {
-				ndisc_send_na(dev, neigh, saddr,
-					      &msg->target, 
-					      idev->cnf.forwarding, 1, 0, inc);
+		ndisc_send_na(dev, neigh, saddr, &msg->target,
+			      idev->cnf.forwarding, 
+			      1, (ifp != NULL && inc), inc);
 		if (neigh)
 			neigh_release(neigh);
 	}
-		}
-		in6_dev_put(idev);
-	} else {
-		struct inet6_dev *in6_dev = in6_dev_get(dev);
-
-		if (in6_dev && in6_dev->cnf.forwarding &&
-		    (addr_type & IPV6_ADDR_UNICAST ||
-		     addr_type == IPV6_ADDR_ANY) &&
-		    pneigh_lookup(&nd_tbl, &msg->target, dev, 0)) {
-			int inc = ipv6_addr_is_multicast(daddr);
 
-			if (skb->stamp.tv_sec == 0 ||
-			    skb->pkt_type == PACKET_HOST ||
-			    inc == 0 ||
-			    in6_dev->nd_parms->proxy_delay == 0) {
-				if (inc)
-					nd_tbl.stats.rcv_probes_mcast++;
+out:
+	if (ifp)
+		in6_ifa_put(ifp);
 	else
-					nd_tbl.stats.rcv_probes_ucast++;
-					
-				if (addr_type & IPV6_ADDR_UNICAST) {
-					neigh = neigh_event_ns(&nd_tbl, lladdr, saddr, dev);
+		in6_dev_put(idev);
 
-					if (neigh) {
-						ndisc_send_na(dev, neigh, saddr, &msg->target,
-							      0, 1, 0, 1);
-						neigh_release(neigh);
-					}
-				} else {
-					/* proxy should also protect against DAD */
-					struct in6_addr maddr;
-					ipv6_addr_all_nodes(&maddr);
-					ndisc_send_na(dev, NULL, &maddr, &msg->target, 
-						      0, 0, 0, 1);
-				}
-			} else {
-				struct sk_buff *n = skb_clone(skb, GFP_ATOMIC);
-				if (n)
-					pneigh_enqueue(&nd_tbl, in6_dev->nd_parms, n);
-				in6_dev_put(in6_dev);
-				return;
-			}
-		}
-		if (in6_dev)
-			in6_dev_put(in6_dev);
-	}
 	return;
 }
 

net/netlink/af_netlink.c

@@ -230,7 +230,7 @@ static int netlink_create(struct socket *sock, int protocol)
 	sock_init_data(sock,sk);
 	sk_set_owner(sk, THIS_MODULE);
 
-	nlk = nlk_sk(sk) = kmalloc(sizeof(*nlk), GFP_KERNEL);
+	nlk = sk->sk_protinfo = kmalloc(sizeof(*nlk), GFP_KERNEL);
 	if (!nlk) {
 		sk_free(sk);
 		return -ENOMEM;

net/packet/af_packet.c

@@ -961,7 +961,7 @@ static int packet_create(struct socket *sock, int protocol)
 	sock_init_data(sock,sk);
 	sk_set_owner(sk, THIS_MODULE);
 
-	po = pkt_sk(sk) = kmalloc(sizeof(*po), GFP_KERNEL);
+	po = sk->sk_protinfo = kmalloc(sizeof(*po), GFP_KERNEL);
 	if (!po)
 		goto out_free;
 	memset(po, 0, sizeof(*po));