Merge master.kernel.org:/home/davem/BK/net-2.5

into penguin.transmeta.com:/home/penguin/torvalds/repositories/kernel/linux

10 files changed, 120 insertions, 148 deletions

diff --git a/include/linux/if_ec.h b/include/linux/if_ec.h
index 8e2e4a1fe424..b5ee8425325f 100644
--- a/include/linux/if_ec.h
+++ b/include/linux/if_ec.h
@@ -53,6 +53,7 @@ struct econet_opt
   unsigned char port;
   unsigned char station;
   unsigned char net;
+  unsigned short num;
 };
 
 #define ec_sk(__sk) ((struct econet_opt *)(__sk)->protinfo)
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index 64b16b277e3c..9d2206b1d06f 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -127,6 +127,7 @@ struct pppox_opt {
 	union {
 		struct pppoe_opt pppoe;
 	} proto;
+	unsigned short		num;
 };
 #define pppoe_dev	proto.pppoe.dev
 #define pppoe_pa	proto.pppoe.pa
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index d1d8425b181c..99d7f1663f30 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -52,70 +52,16 @@ struct vlan_hdr {
    unsigned short       h_vlan_encapsulated_proto; /* packet type ID field (or len) */
 };
 
-/*  Find a VLAN device by the MAC address of it's Ethernet device, and
- *  it's VLAN ID.  The default configuration is to have VLAN's scope
- *  to be box-wide, so the MAC will be ignored.  The mac will only be
- *  looked at if we are configured to have a seperate set of VLANs per
- *  each MAC addressable interface.  Note that this latter option does
- *  NOT follow the spec for VLANs, but may be useful for doing very
- *  large quantities of VLAN MUX/DEMUX onto FrameRelay or ATM PVCs.
- */
-struct net_device *find_802_1Q_vlan_dev(struct net_device* real_dev,
-                                        unsigned short VID); /* vlan.c */
+#define VLAN_VID_MASK	0xfff
 
 /* found in af_inet.c */
 extern int (*vlan_ioctl_hook)(unsigned long arg);
 
-/* found in vlan_dev.c */
-struct net_device_stats* vlan_dev_get_stats(struct net_device* dev);
-int vlan_dev_rebuild_header(struct sk_buff *skb);
-int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev,
-                  struct packet_type* ptype);
-int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
-                         unsigned short type, void *daddr, void *saddr,
-                         unsigned len);
-int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev);
-int vlan_dev_change_mtu(struct net_device *dev, int new_mtu);
-int vlan_dev_set_mac_address(struct net_device *dev, void* addr);
-int vlan_dev_open(struct net_device* dev);
-int vlan_dev_stop(struct net_device* dev);
-int vlan_dev_init(struct net_device* dev);
-void vlan_dev_destruct(struct net_device* dev);
-void vlan_dev_copy_and_sum(struct sk_buff *dest, unsigned char *src,
-                           int length, int base);
-int vlan_dev_set_ingress_priority(char* dev_name, __u32 skb_prio, short vlan_prio);
-int vlan_dev_set_egress_priority(char* dev_name, __u32 skb_prio, short vlan_prio);
-int vlan_dev_set_vlan_flag(char* dev_name, __u32 flag, short flag_val);
-
-/* VLAN multicast stuff */
-/* Delete all of the MC list entries from this vlan device.  Also deals
- * with the underlying device...
- */
-void vlan_flush_mc_list(struct net_device* dev);
-/* copy the mc_list into the vlan_info structure. */
-void vlan_copy_mc_list(struct dev_mc_list* mc_list, struct vlan_dev_info* vlan_info);
-/** dmi is a single entry into a dev_mc_list, a single node.  mc_list is
- *  an entire list, and we'll iterate through it.
- */
-int vlan_should_add_mc(struct dev_mc_list *dmi, struct dev_mc_list *mc_list);
-/** Taken from Gleb + Lennert's VLAN code, and modified... */
-void vlan_dev_set_multicast_list(struct net_device *vlan_dev);
-
-int vlan_collection_add_vlan(struct vlan_collection* vc, unsigned short vlan_id,
-                             unsigned short flags);
-int vlan_collection_remove_vlan(struct vlan_collection* vc,
-                                struct net_device* vlan_dev);
-int vlan_collection_remove_vlan_id(struct vlan_collection* vc, unsigned short vlan_id);
-
-/* found in vlan.c */
-/* Our listing of VLAN group(s) */
-extern struct vlan_group* p802_1Q_vlan_list;
-
 #define VLAN_NAME "vlan"
 
 /* if this changes, algorithm will have to be reworked because this
  * depends on completely exhausting the VLAN identifier space.  Thus
- * it gives constant time look-up, but it many cases it wastes memory.
+ * it gives constant time look-up, but in many cases it wastes memory.
  */
 #define VLAN_GROUP_ARRAY_LEN 4096
 
@@ -170,56 +116,73 @@ struct vlan_dev_info {
 
 /* inline functions */
 
-/* Used in vlan_skb_recv */
-static inline struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb)
+static inline struct net_device_stats *vlan_dev_get_stats(struct net_device *dev)
 {
-	if (VLAN_DEV_INFO(skb->dev)->flags & 1) {
-		skb = skb_share_check(skb, GFP_ATOMIC);
-		if (skb) {
-			/* Lifted from Gleb's VLAN code... */
-			memmove(skb->data - ETH_HLEN,
-				skb->data - VLAN_ETH_HLEN, 12);
-			skb->mac.raw += VLAN_HLEN;
-		}
-	}
-
-	return skb;
+	return &(VLAN_DEV_INFO(dev)->dev_stats);
 }
 
-static inline unsigned short vlan_dev_get_egress_qos_mask(struct net_device* dev,
-							  struct sk_buff* skb)
+static inline __u32 vlan_get_ingress_priority(struct net_device *dev,
+					      unsigned short vlan_tag)
 {
-	struct vlan_priority_tci_mapping *mp =
-		VLAN_DEV_INFO(dev)->egress_priority_map[(skb->priority & 0xF)];
-
-	while (mp) {
-		if (mp->priority == skb->priority) {
-			return mp->vlan_qos; /* This should already be shifted to mask
-					      * correctly with the VLAN's TCI
-					      */
-		}
-		mp = mp->next;
-	}
-	return 0;
-}
+	struct vlan_dev_info *vip = VLAN_DEV_INFO(dev);
 
-static inline int vlan_dmi_equals(struct dev_mc_list *dmi1,
-                                  struct dev_mc_list *dmi2)
-{
-	return ((dmi1->dmi_addrlen == dmi2->dmi_addrlen) &&
-		(memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0));
+	return vip->ingress_priority_map[(vlan_tag >> 13) & 0x7];
 }
 
-static inline void vlan_destroy_mc_list(struct dev_mc_list *mc_list)
+/* VLAN tx hw acceleration helpers. */
+struct vlan_skb_tx_cookie {
+	u32	magic;
+	u32	vlan_tag;
+};
+
+#define VLAN_TX_COOKIE_MAGIC	0x564c414e	/* "VLAN" in ascii. */
+#define VLAN_TX_SKB_CB(__skb)	((struct vlan_skb_tx_cookie *)&((__skb)->cb[0]))
+#define vlan_tx_tag_present(__skb) \
+	(VLAN_TX_SKB_CB(__skb)->magic == VLAN_TX_COOKIE_MAGIC)
+#define vlan_tx_tag_get(__skb)	(VLAN_TX_SKB_CB(__skb)->vlan_tag)
+
+/* VLAN rx hw acceleration helper.  This acts like netif_rx().  */
+static inline int vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
+				  unsigned short vlan_tag)
 {
-	struct dev_mc_list *dmi = mc_list;
-	struct dev_mc_list *next;
+	struct net_device_stats *stats;
 
-	while(dmi) {
-		next = dmi->next;
-		kfree(dmi);
-		dmi = next;
+	skb->dev = grp->vlan_devices[vlan_tag & VLAN_VID_MASK];
+	if (skb->dev == NULL) {
+		kfree_skb(skb);
+
+		/* Not NET_RX_DROP, this is not being dropped
+		 * due to congestion.
+		 */
+		return 0;
 	}
+
+	skb->dev->last_rx = jiffies;
+
+	stats = vlan_dev_get_stats(skb->dev);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+
+	skb->priority = vlan_get_ingress_priority(skb->dev, vlan_tag);
+	switch (skb->pkt_type) {
+	case PACKET_BROADCAST:
+		break;
+
+	case PACKET_MULTICAST:
+		stats->multicast++;
+		break;
+
+	case PACKET_OTHERHOST:
+		/* Our lower layer thinks this is not local, let's make sure.
+		 * This allows the VLAN to have a different MAC than the underlying
+		 * device, and still route correctly.
+		 */
+		if (!memcmp(skb->mac.ethernet->h_dest, skb->dev->dev_addr, ETH_ALEN))
+			skb->pkt_type = PACKET_HOST;
+		break;
+	};
+
+	return netif_rx(skb);
 }
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/ip.h b/include/linux/ip.h
index 97e388ade261..3ba8e804b0d8 100644
--- a/include/linux/ip.h
+++ b/include/linux/ip.h
@@ -116,17 +116,24 @@ struct ip_options {
 #define optlength(opt) (sizeof(struct ip_options) + opt->optlen)
 
 struct inet_opt {
+	/* Socket demultiplex comparisons on incoming packets. */
+	__u32			daddr;		/* Foreign IPv4 addr */
+	__u32			rcv_saddr;	/* Bound local IPv4 addr */
+	__u16			dport;		/* Destination port */
+	__u16			num;		/* Local port */
+	__u32			saddr;		/* Sending source */
 	int			ttl;		/* TTL setting */
 	int			tos;		/* TOS */
 	unsigned	   	cmsg_flags;
 	struct ip_options	*opt;
+	__u16			sport;		/* Source port */
 	unsigned char		hdrincl;	/* Include headers ? */
 	__u8			mc_ttl;		/* Multicasting TTL */
 	__u8			mc_loop;	/* Loopback */
+	__u8			pmtudisc;
+	__u16			id;		/* ID counter for DF pkts */
 	unsigned		recverr : 1,
 				freebind : 1;
-	__u16			id;		/* ID counter for DF pkts */
-	__u8			pmtudisc;
 	int			mc_index;	/* Multicast device index */
 	__u32			mc_addr;
 	struct ip_mc_socklist	*mc_list;	/* Group array */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8096e640c416..178f6a5a0fe6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -40,6 +40,7 @@
 #endif
 
 struct divert_blk;
+struct vlan_group;
 
 #define HAVE_ALLOC_NETDEV		/* feature macro: alloc_xxxdev
 					   functions are available. */
@@ -357,6 +358,10 @@ struct net_device
 #define NETIF_F_DYNALLOC	16	/* Self-dectructable device. */
 #define NETIF_F_HIGHDMA		32	/* Can DMA to high memory. */
 #define NETIF_F_FRAGLIST	64	/* Scatter/gather IO. */
+#define NETIF_F_HW_VLAN_TX	128	/* Transmit VLAN hw acceleration */
+#define NETIF_F_HW_VLAN_RX	256	/* Receive VLAN hw acceleration */
+#define NETIF_F_HW_VLAN_FILTER	512	/* Receive filtering on VLAN */
+#define NETIF_F_VLAN_CHALLENGED	1024	/* Device cannot handle VLAN packets */
 
 	/* Called after device is detached from network. */
 	void			(*uninit)(struct net_device *dev);
@@ -398,6 +403,13 @@ struct net_device
 #define HAVE_TX_TIMEOUT
 	void			(*tx_timeout) (struct net_device *dev);
 
+	void			(*vlan_rx_register)(struct net_device *dev,
+						    struct vlan_group *grp);
+	void			(*vlan_rx_add_vid)(struct net_device *dev,
+						   unsigned short vid);
+	void			(*vlan_rx_kill_vid)(struct net_device *dev,
+						    unsigned short vid);
+
 	int			(*hard_header_parse)(struct sk_buff *skb,
 						     unsigned char *haddr);
 	int			(*neigh_setup)(struct net_device *dev, struct neigh_parms *);
diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h
index f0e8b9927eab..107cce0c67a3 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack.h
@@ -82,10 +82,7 @@ struct ip_conntrack_expect
 #endif
 
 #include <linux/netfilter_ipv4/ip_conntrack_ftp.h>
-
-#if defined(CONFIG_IP_NF_IRC) || defined(CONFIG_IP_NF_IRC_MODULE)
 #include <linux/netfilter_ipv4/ip_conntrack_irc.h>
-#endif
 
 struct ip_conntrack
 {
@@ -125,9 +122,7 @@ struct ip_conntrack
 
 	union {
 		struct ip_ct_ftp ct_ftp_info;
-#if defined(CONFIG_IP_NF_IRC) || defined(CONFIG_IP_NF_IRC_MODULE)
 		struct ip_ct_irc ct_irc_info;
-#endif
 	} help;
 
 #ifdef CONFIG_IP_NF_NAT_NEEDED
diff --git a/include/net/ip.h b/include/net/ip.h
index 705fed205357..e2da92393da8 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -197,7 +197,8 @@ static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, str
 		 * does not change, they drop every other packet in
 		 * a TCP stream using header compression.
 		 */
-		iph->id = (sk && sk->daddr) ? htons(inet_sk(sk)->id++) : 0;
+		iph->id = (sk && inet_sk(sk)->daddr) ?
+					htons(inet_sk(sk)->id++) : 0;
 	} else
 		__ip_select_ident(iph, dst);
 }
diff --git a/include/net/sock.h b/include/net/sock.h
index 898193d61fc3..d50815f55ff3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -83,28 +83,22 @@ do {	spin_lock_init(&((__sk)->lock.slock)); \
 } while(0);
 
 struct sock {
-	/* Socket demultiplex comparisons on incoming packets. */
-	__u32			daddr;		/* Foreign IPv4 addr			*/
-	__u32			rcv_saddr;	/* Bound local IPv4 addr		*/
-	__u16			dport;		/* Destination port			*/
-	unsigned short		num;		/* Local port				*/
-	int			bound_dev_if;	/* Bound device index if != 0		*/
-
+	/* Begin of struct sock/struct tcp_tw_bucket shared layout */
+	volatile unsigned char	state,		/* Connection state */
+				zapped;		/* ax25 & ipx means !linked */
+	unsigned char		reuse;		/* SO_REUSEADDR setting */
+	unsigned char		shutdown;
+	int			bound_dev_if;	/* Bound device index if != 0 */
 	/* Main hash linkage for various protocol lookup tables. */
 	struct sock		*next;
 	struct sock		**pprev;
 	struct sock		*bind_next;
 	struct sock		**bind_pprev;
-
-	volatile unsigned char	state,		/* Connection state			*/
-				zapped;		/* In ax25 & ipx means not linked	*/
-	__u16			sport;		/* Source port				*/
-
-	unsigned short		family;		/* Address family			*/
-	unsigned char		reuse;		/* SO_REUSEADDR setting			*/
-	unsigned char		shutdown;
 	atomic_t		refcnt;		/* Reference count			*/
-
+	unsigned short		family;		/* Address family */
+	/* End of struct sock/struct tcp_tw_bucket shared layout */
+	unsigned char		use_write_queue;
+	unsigned char		userlocks;
 	socket_lock_t		lock;		/* Synchronizer...			*/
 	int			rcvbuf;		/* Size of receive buffer in bytes	*/
 
@@ -118,7 +112,6 @@ struct sock {
 	atomic_t		omem_alloc;	/* "o" is "option" or "other" */
 	int			wmem_queued;	/* Persistent queue size */
 	int			forward_alloc;	/* Space allocated forward. */
-	__u32			saddr;		/* Sending source			*/
 	unsigned int		allocation;	/* Allocation mode			*/
 	int			sndbuf;		/* Size of send buffer in bytes		*/
 	struct sock		*prev;
@@ -137,9 +130,7 @@ struct sock {
 				bsdism;
 	unsigned char		debug;
 	unsigned char		rcvtstamp;
-	unsigned char		use_write_queue;
-	unsigned char		userlocks;
-	/* Hole of 3 bytes. Try to pack. */
+	/* Hole of 1 byte. Try to pack. */
 	int			route_caps;
 	int			proc;
 	unsigned long	        lingertime;
@@ -759,16 +750,13 @@ static inline void sk_wake_async(struct sock *sk, int how, int band)
 
 #define SOCK_MIN_SNDBUF 2048
 #define SOCK_MIN_RCVBUF 256
-/* Must be less or equal SOCK_MIN_SNDBUF */
-#define SOCK_MIN_WRITE_SPACE	SOCK_MIN_SNDBUF
 
 /*
  *	Default write policy as shown to user space via poll/select/SIGIO
- *	Kernel internally doesn't use the MIN_WRITE_SPACE threshold.
  */
 static inline int sock_writeable(struct sock *sk) 
 {
-	return sock_wspace(sk) >= SOCK_MIN_WRITE_SPACE;
+	return atomic_read(&sk->wmem_alloc) < (sk->sndbuf / 2);
 }
 
 static inline int gfp_any(void)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index bccbac72b43e..c45fc3e12845 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -53,7 +53,7 @@ struct tcp_ehash_bucket {
  *	2) If all sockets have sk->reuse set, and none of them are in
  *	   TCP_LISTEN state, the port may be shared.
  *	   Failing that, goto test 3.
- *	3) If all sockets are bound to a specific sk->rcv_saddr local
+ *	3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local
  *	   address, and none of them are the same, the port may be
  *	   shared.
  *	   Failing this, the port cannot be shared.
@@ -162,23 +162,26 @@ struct tcp_tw_bucket {
 	 * XXX Yes I know this is gross, but I'd have to edit every single
 	 * XXX networking file if I created a "struct sock_header". -DaveM
 	 */
-	__u32			daddr;
-	__u32			rcv_saddr;
-	__u16			dport;
-	unsigned short		num;
+	volatile unsigned char	state,		/* Connection state	      */
+				substate;	/* "zapped" -> "substate"     */
+	unsigned char		reuse;		/* SO_REUSEADDR setting       */
+	unsigned char		rcv_wscale;	/* also TW bucket specific    */
 	int			bound_dev_if;
+	/* Main hash linkage for various protocol lookup tables. */
 	struct sock		*next;
 	struct sock		**pprev;
 	struct sock		*bind_next;
 	struct sock		**bind_pprev;
-	unsigned char		state,
-				substate; /* "zapped" is replaced with "substate" */
-	__u16			sport;
-	unsigned short		family;
-	unsigned char		reuse,
-				rcv_wscale; /* It is also TW bucket specific */
 	atomic_t		refcnt;
-
+	unsigned short		family;
+	/* End of struct sock/struct tcp_tw_bucket shared layout */
+	__u16			sport;
+	/* Socket demultiplex comparisons on incoming packets. */
+	/* these five are in inet_opt */
+	__u32			daddr;
+	__u32			rcv_saddr;
+	__u16			dport;
+	__u16			num;
 	/* And these are ours. */
 	int			hashent;
 	int			timeout;
@@ -236,20 +239,20 @@ extern void tcp_tw_deschedule(struct tcp_tw_bucket *tw);
 	__u64 __name = (((__u64)(__daddr))<<32)|((__u64)(__saddr));
 #endif /* __BIG_ENDIAN */
 #define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
-	(((*((__u64 *)&((__sk)->daddr)))== (__cookie))	&&		\
-	 ((*((__u32 *)&((__sk)->dport)))== (__ports))   &&		\
+	(((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie))	&&	\
+	 ((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports))   &&	\
 	 (!((__sk)->bound_dev_if) || ((__sk)->bound_dev_if == (__dif))))
 #else /* 32-bit arch */
 #define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr)
 #define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
-	(((__sk)->daddr			== (__saddr))	&&		\
-	 ((__sk)->rcv_saddr		== (__daddr))	&&		\
-	 ((*((__u32 *)&((__sk)->dport)))== (__ports))   &&		\
+	((inet_sk(__sk)->daddr			== (__saddr))	&&	\
+	 (inet_sk(__sk)->rcv_saddr		== (__daddr))	&&	\
+	 ((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports))	&&	\
 	 (!((__sk)->bound_dev_if) || ((__sk)->bound_dev_if == (__dif))))
 #endif /* 64-bit arch */
 
 #define TCP_IPV6_MATCH(__sk, __saddr, __daddr, __ports, __dif)	   \
-	(((*((__u32 *)&((__sk)->dport)))== (__ports))   	&& \
+	(((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports))   	&& \
 	 ((__sk)->family		== AF_INET6)		&& \
 	 !ipv6_addr_cmp(&inet6_sk(__sk)->daddr, (__saddr))	&& \
 	 !ipv6_addr_cmp(&inet6_sk(__sk)->rcv_saddr, (__daddr))	&& \
@@ -263,7 +266,7 @@ static __inline__ int tcp_lhashfn(unsigned short num)
 
 static __inline__ int tcp_sk_listen_hashfn(struct sock *sk)
 {
-	return tcp_lhashfn(sk->num);
+	return tcp_lhashfn(inet_sk(sk)->num);
 }
 
 #define MAX_TCP_HEADER	(128 + MAX_HEADER)
diff --git a/include/net/udp.h b/include/net/udp.h
index c7049c5b4bf8..15f7626f7dcd 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -23,6 +23,7 @@
 #define _UDP_H
 
 #include <linux/udp.h>
+#include <linux/ip.h>
 #include <net/sock.h>
 
 #define UDP_HTABLE_SIZE		128
@@ -41,7 +42,7 @@ static inline int udp_lport_inuse(u16 num)
 	struct sock *sk = udp_hash[num & (UDP_HTABLE_SIZE - 1)];
 
 	for(; sk != NULL; sk = sk->next) {
-		if(sk->num == num)
+		if (inet_sk(sk)->num == num)
 			return 1;
 	}
 	return 0;