Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (21 commits)
  [IPV4] SNMP: Support OutMcastPkts and OutBcastPkts
  [IPV4] SNMP: Support InMcastPkts and InBcastPkts
  [IPV4] SNMP: Support InTruncatedPkts
  [IPV4] SNMP: Support InNoRoutes
  [SNMP]: Add definitions for {In,Out}BcastPkts
  [TCP] FRTO: RFC4138 allows Nagle override when new data must be sent
  [TCP] FRTO: Delay skb available check until it's mandatory
  [XFRM]: Restrict upper layer information by bundle.
  [TCP]: Catch skb with S+L bugs earlier
  [PATCH] INET : IPV4 UDP lookups converted to a 2 pass algo
  [L2TP]: Add the ability to autoload a pppox protocol module.
  [SKB]: Introduce skb_queue_walk_safe()
  [AF_IUCV/IUCV]: smp_call_function deadlock
  [IPV6]: Fix slab corruption running ip6sic
  [TCP]: Update references in two old comments
  [XFRM]: Export SPD info
  [IPV6]: Track device renames in snmp6.
  [SCTP]: Fix sctp_getsockopt_local_addrs_old() to use local storage.
  [NET]: Remove NETIF_F_INTERNAL_STATS, default to internal stats.
  [NETPOLL]: Remove CONFIG_NETPOLL_RX
  ...

arch/s390/appldata/appldata_net_sum.c

@@ -109,9 +109,6 @@ static void appldata_get_net_sum_data(void *data)
 	read_lock(&dev_base_lock);
 	for (dev = dev_base; dev != NULL; dev = dev->next) {
 		stats = dev->get_stats(dev);
-		if (stats == NULL) {
-			continue;
-		}
 		rx_packets += stats->rx_packets;
 		tx_packets += stats->tx_packets;
 		rx_bytes   += stats->rx_bytes;

drivers/net/Kconfig

@@ -2927,11 +2927,6 @@ endif #NETDEVICES
 config NETPOLL
 	def_bool NETCONSOLE
 
-config NETPOLL_RX
-	bool "Netpoll support for trapping incoming packets"
-	default n
-	depends on NETPOLL
-
 config NETPOLL_TRAP
 	bool "Netpoll traffic trapping"
 	default n

drivers/net/bonding/bond_main.c

@@ -1360,13 +1360,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		goto err_undo_flags;
 	}
 
-	if (slave_dev->get_stats == NULL) {
-		printk(KERN_NOTICE DRV_NAME
-			": %s: the driver for slave device %s does not provide "
-			"get_stats function, network statistics will be "
-			"inaccurate.\n", bond_dev->name, slave_dev->name);
-	}
-
 	new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
 	if (!new_slave) {
 		res = -ENOMEM;
@@ -3641,33 +3634,31 @@ static struct net_device_stats *bond_get_stats(struct net_device *bond_dev)
 
 	bond_for_each_slave(bond, slave, i) {
 		sstats = slave->dev->get_stats(slave->dev);
-		if (sstats) {
-			stats->rx_packets += sstats->rx_packets;
-			stats->rx_bytes += sstats->rx_bytes;
-			stats->rx_errors += sstats->rx_errors;
-			stats->rx_dropped += sstats->rx_dropped;
-
-			stats->tx_packets += sstats->tx_packets;
-			stats->tx_bytes += sstats->tx_bytes;
-			stats->tx_errors += sstats->tx_errors;
-			stats->tx_dropped += sstats->tx_dropped;
-
-			stats->multicast += sstats->multicast;
-			stats->collisions += sstats->collisions;
-
-			stats->rx_length_errors += sstats->rx_length_errors;
-			stats->rx_over_errors += sstats->rx_over_errors;
-			stats->rx_crc_errors += sstats->rx_crc_errors;
-			stats->rx_frame_errors += sstats->rx_frame_errors;
-			stats->rx_fifo_errors += sstats->rx_fifo_errors;
-			stats->rx_missed_errors += sstats->rx_missed_errors;
-
-			stats->tx_aborted_errors += sstats->tx_aborted_errors;
-			stats->tx_carrier_errors += sstats->tx_carrier_errors;
-			stats->tx_fifo_errors += sstats->tx_fifo_errors;
-			stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors;
-			stats->tx_window_errors += sstats->tx_window_errors;
-		}
+		stats->rx_packets += sstats->rx_packets;
+		stats->rx_bytes += sstats->rx_bytes;
+		stats->rx_errors += sstats->rx_errors;
+		stats->rx_dropped += sstats->rx_dropped;
+
+		stats->tx_packets += sstats->tx_packets;
+		stats->tx_bytes += sstats->tx_bytes;
+		stats->tx_errors += sstats->tx_errors;
+		stats->tx_dropped += sstats->tx_dropped;
+
+		stats->multicast += sstats->multicast;
+		stats->collisions += sstats->collisions;
+
+		stats->rx_length_errors += sstats->rx_length_errors;
+		stats->rx_over_errors += sstats->rx_over_errors;
+		stats->rx_crc_errors += sstats->rx_crc_errors;
+		stats->rx_frame_errors += sstats->rx_frame_errors;
+		stats->rx_fifo_errors += sstats->rx_fifo_errors;
+		stats->rx_missed_errors += sstats->rx_missed_errors;
+
+		stats->tx_aborted_errors += sstats->tx_aborted_errors;
+		stats->tx_carrier_errors += sstats->tx_carrier_errors;
+		stats->tx_fifo_errors += sstats->tx_fifo_errors;
+		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors;
+		stats->tx_window_errors += sstats->tx_window_errors;
 	}
 
 	read_unlock_bh(&bond->lock);

drivers/net/pppox.c

@@ -31,6 +31,7 @@
 #include <linux/ppp_defs.h>
 #include <linux/if_ppp.h>
 #include <linux/ppp_channel.h>
+#include <linux/kmod.h>
 
 #include <net/sock.h>
 
@@ -114,6 +115,13 @@ static int pppox_create(struct socket *sock, int protocol)
 		goto out;
 
 	rc = -EPROTONOSUPPORT;
+#ifdef CONFIG_KMOD
+	if (!pppox_protos[protocol]) {
+		char buffer[32];
+		sprintf(buffer, "pppox-proto-%d", protocol);
+		request_module(buffer);
+	}
+#endif
 	if (!pppox_protos[protocol] ||
 	    !try_module_get(pppox_protos[protocol]->owner))
 		goto out;

drivers/parisc/led.c

@@ -373,8 +373,6 @@ static __inline__ int led_get_net_activity(void)
 	    if (LOOPBACK(in_dev->ifa_list->ifa_local))
 		continue;
 	    stats = dev->get_stats(dev);
-	    if (!stats)
-		continue;
 	    rx_total += stats->rx_packets;
 	    tx_total += stats->tx_packets;
 	}

include/linux/netdevice.h

@@ -325,7 +325,6 @@ struct net_device
 #define NETIF_F_VLAN_CHALLENGED	1024	/* Device cannot handle VLAN packets */
 #define NETIF_F_GSO		2048	/* Enable software GSO. */
 #define NETIF_F_LLTX		4096	/* LockLess TX */
-#define NETIF_F_INTERNAL_STATS	8192	/* Use stats structure in net_device */
 
 	/* Segmentation offload features */
 #define NETIF_F_GSO_SHIFT	16
@@ -654,8 +653,10 @@ static inline void netif_start_queue(struct net_device *dev)
 static inline void netif_wake_queue(struct net_device *dev)
 {
 #ifdef CONFIG_NETPOLL_TRAP
-	if (netpoll_trap())
+	if (netpoll_trap()) {
+		clear_bit(__LINK_STATE_XOFF, &dev->state);
 		return;
+	}
 #endif
 	if (test_and_clear_bit(__LINK_STATE_XOFF, &dev->state))
 		__netif_schedule(dev);
@@ -663,10 +664,6 @@ static inline void netif_wake_queue(struct net_device *dev)
 
 static inline void netif_stop_queue(struct net_device *dev)
 {
-#ifdef CONFIG_NETPOLL_TRAP
-	if (netpoll_trap())
-		return;
-#endif
 	set_bit(__LINK_STATE_XOFF, &dev->state);
 }
 

include/linux/skbuff.h

@@ -1471,6 +1471,11 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
 		     prefetch(skb->next), (skb != (struct sk_buff *)(queue));	\
 		     skb = skb->next)
 
+#define skb_queue_walk_safe(queue, skb, tmp)					\
+		for (skb = (queue)->next, tmp = skb->next;			\
+		     skb != (struct sk_buff *)(queue);				\
+		     skb = tmp, tmp = skb->next)
+
 #define skb_queue_reverse_walk(queue, skb) \
 		for (skb = (queue)->prev;					\
 		     prefetch(skb->prev), (skb != (struct sk_buff *)(queue));	\

include/linux/snmp.h

@@ -40,6 +40,8 @@ enum
 	IPSTATS_MIB_FRAGCREATES,		/* FragCreates */
 	IPSTATS_MIB_INMCASTPKTS,		/* InMcastPkts */
 	IPSTATS_MIB_OUTMCASTPKTS,		/* OutMcastPkts */
+	IPSTATS_MIB_INBCASTPKTS,		/* InBcastPkts */
+	IPSTATS_MIB_OUTBCASTPKTS,		/* OutBcastPkts */
 	__IPSTATS_MIB_MAX
 };
 

include/linux/xfrm.h

@@ -185,6 +185,11 @@ enum {
 #define XFRM_MSG_NEWSADINFO XFRM_MSG_NEWSADINFO
 	XFRM_MSG_GETSADINFO,
 #define XFRM_MSG_GETSADINFO XFRM_MSG_GETSADINFO
+
+	XFRM_MSG_NEWSPDINFO,
+#define XFRM_MSG_NEWSPDINFO XFRM_MSG_NEWSPDINFO
+	XFRM_MSG_GETSPDINFO,
+#define XFRM_MSG_GETSPDINFO XFRM_MSG_GETSPDINFO
 	__XFRM_MSG_MAX
 };
 #define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1)
@@ -290,6 +295,36 @@ enum xfrm_sadattr_type_t {
 #define XFRMA_SAD_MAX (__XFRMA_SAD_MAX - 1)
 };
 
+/* SPD Table filter flags  */
+enum xfrm_spd_ftype_t {
+	XFRM_SPD_UNSPEC,
+	XFRM_SPD_HMASK=1,
+	XFRM_SPD_HMAX=2,
+	XFRM_SPD_ICNT=4,
+	XFRM_SPD_OCNT=8,
+	XFRM_SPD_FCNT=16,
+	XFRM_SPD_ISCNT=32,
+	XFRM_SPD_OSCNT=64,
+	XFRM_SPD_FSCNT=128,
+	__XFRM_SPD_MAX
+
+#define XFRM_SPD_MAX (__XFRM_SPD_MAX - 1)
+};
+enum xfrm_spdattr_type_t {
+	XFRMA_SPD_UNSPEC,
+	XFRMA_SPDHMASK,
+	XFRMA_SPDHMAX,
+	XFRMA_SPDICNT,
+	XFRMA_SPDOCNT,
+	XFRMA_SPDFCNT,
+	XFRMA_SPDISCNT,
+	XFRMA_SPDOSCNT,
+	XFRMA_SPDFSCNT,
+	__XFRMA_SPD_MAX
+
+#define XFRMA_SPD_MAX (__XFRMA_SPD_MAX - 1)
+};
+
 struct xfrm_usersa_info {
 	struct xfrm_selector		sel;
 	struct xfrm_id			id;

include/net/flow.h

@@ -97,4 +97,10 @@ extern void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir,
 extern void flow_cache_flush(void);
 extern atomic_t flow_cache_genid;
 
+static inline int flow_cache_uli_match(struct flowi *fl1, struct flowi *fl2)
+{
+	return (fl1->proto == fl2->proto &&
+		!memcmp(&fl1->uli_u, &fl2->uli_u, sizeof(fl1->uli_u)));
+}
+
 #endif

include/net/iucv/iucv.h

@@ -16,7 +16,7 @@
  * completed a register, it can exploit the other functions.
  * For furthur reference on all IUCV functionality, refer to the
  * CP Programming Services book, also available on the web thru
- * www.ibm.com/s390/vm/pubs, manual # SC24-5760
+ * www.vm.ibm.com/pubs, manual # SC24-6084
  *
  * Definition of Return Codes
  * - All positive return codes including zero are reflected back

include/net/tcp.h

@@ -736,9 +736,7 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk)
 
 static inline void tcp_sync_left_out(struct tcp_sock *tp)
 {
-	if (tp->rx_opt.sack_ok &&
-	    (tp->sacked_out >= tp->packets_out - tp->lost_out))
-		tp->sacked_out = tp->packets_out - tp->lost_out;
+	BUG_ON(tp->sacked_out + tp->lost_out > tp->packets_out);
 	tp->left_out = tp->sacked_out + tp->lost_out;
 }
 
@@ -1201,9 +1199,14 @@ static inline struct sk_buff *tcp_send_head(struct sock *sk)
 
 static inline void tcp_advance_send_head(struct sock *sk, struct sk_buff *skb)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
 	sk->sk_send_head = skb->next;
 	if (sk->sk_send_head == (struct sk_buff *)&sk->sk_write_queue)
 		sk->sk_send_head = NULL;
+	/* Don't override Nagle indefinately with F-RTO */
+	if (tp->frto_counter == 2)
+		tp->frto_counter = 3;
 }
 
 static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)

include/net/xfrm.h

@@ -423,6 +423,18 @@ struct xfrm_sadinfo
 	u32 sadhmcnt; /* max allowed hash bkts */
 	u32 sadcnt; /* current running count */
 };
+
+struct xfrm_spdinfo
+{
+	u32 incnt;
+	u32 outcnt;
+	u32 fwdcnt;
+	u32 inscnt;
+	u32 outscnt;
+	u32 fwdscnt;
+	u32 spdhcnt;
+	u32 spdhmcnt;
+};
 #ifdef CONFIG_AUDITSYSCALL
 extern void xfrm_audit_log(uid_t auid, u32 secid, int type, int result,
 		    struct xfrm_policy *xp, struct xfrm_state *x);
@@ -591,6 +603,10 @@ struct xfrm_dst
 		struct rt6_info		rt6;
 	} u;
 	struct dst_entry *route;
+#ifdef CONFIG_XFRM_SUB_POLICY
+	struct flowi *origin;
+	struct xfrm_selector *partner;
+#endif
 	u32 genid;
 	u32 route_mtu_cached;
 	u32 child_mtu_cached;
@@ -603,6 +619,12 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst)
 	dst_release(xdst->route);
 	if (likely(xdst->u.dst.xfrm))
 		xfrm_state_put(xdst->u.dst.xfrm);
+#ifdef CONFIG_XFRM_SUB_POLICY
+	kfree(xdst->origin);
+	xdst->origin = NULL;
+	kfree(xdst->partner);
+	xdst->partner = NULL;
+#endif
 }
 
 extern void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev);
@@ -946,6 +968,7 @@ extern struct xfrm_state *xfrm_find_acq_byseq(u32 seq);
 extern int xfrm_state_delete(struct xfrm_state *x);
 extern void xfrm_state_flush(u8 proto, struct xfrm_audit *audit_info);
 extern void xfrm_sad_getinfo(struct xfrm_sadinfo *si);
+extern void xfrm_spd_getinfo(struct xfrm_spdinfo *si);
 extern int xfrm_replay_check(struct xfrm_state *x, __be32 seq);
 extern void xfrm_replay_advance(struct xfrm_state *x, __be32 seq);
 extern void xfrm_replay_notify(struct xfrm_state *x, int event);

net/core/dev.c

@@ -2101,26 +2101,23 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
 {
 	struct net_device_stats *stats = dev->get_stats(dev);
 
-	if (stats) {
-		seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
-				"%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
-			   dev->name, stats->rx_bytes, stats->rx_packets,
-			   stats->rx_errors,
-			   stats->rx_dropped + stats->rx_missed_errors,
-			   stats->rx_fifo_errors,
-			   stats->rx_length_errors + stats->rx_over_errors +
-			     stats->rx_crc_errors + stats->rx_frame_errors,
-			   stats->rx_compressed, stats->multicast,
-			   stats->tx_bytes, stats->tx_packets,
-			   stats->tx_errors, stats->tx_dropped,
-			   stats->tx_fifo_errors, stats->collisions,
-			   stats->tx_carrier_errors +
-			     stats->tx_aborted_errors +
-			     stats->tx_window_errors +
-			     stats->tx_heartbeat_errors,
-			   stats->tx_compressed);
-	} else
-		seq_printf(seq, "%6s: No statistics available.\n", dev->name);
+	seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
+		   "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
+		   dev->name, stats->rx_bytes, stats->rx_packets,
+		   stats->rx_errors,
+		   stats->rx_dropped + stats->rx_missed_errors,
+		   stats->rx_fifo_errors,
+		   stats->rx_length_errors + stats->rx_over_errors +
+		    stats->rx_crc_errors + stats->rx_frame_errors,
+		   stats->rx_compressed, stats->multicast,
+		   stats->tx_bytes, stats->tx_packets,
+		   stats->tx_errors, stats->tx_dropped,
+		   stats->tx_fifo_errors, stats->collisions,
+		   stats->tx_carrier_errors +
+		    stats->tx_aborted_errors +
+		    stats->tx_window_errors +
+		    stats->tx_heartbeat_errors,
+		   stats->tx_compressed);
 }
 
 /*
@@ -3257,11 +3254,9 @@ void netdev_run_todo(void)
 	mutex_unlock(&net_todo_run_mutex);
 }
 
-static struct net_device_stats *maybe_internal_stats(struct net_device *dev)
+static struct net_device_stats *internal_stats(struct net_device *dev)
 {
-	if (dev->features & NETIF_F_INTERNAL_STATS)
-		return &dev->stats;
-	return NULL;
+	return &dev->stats;
 }
 
 /**
@@ -3299,7 +3294,7 @@ struct net_device *alloc_netdev(int sizeof_priv, const char *name,
 	if (sizeof_priv)
 		dev->priv = netdev_priv(dev);
 
-	dev->get_stats = maybe_internal_stats;
+	dev->get_stats = internal_stats;
 	setup(dev);
 	strcpy(dev->name, name);
 	return dev;

net/ipv4/ip_input.c

@@ -329,6 +329,7 @@ static inline int ip_rcv_options(struct sk_buff *skb)
 static inline int ip_rcv_finish(struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
+	struct rtable *rt;
 
 	/*
 	 *	Initialise the virtual path cache for the packet. It describes
@@ -340,6 +341,8 @@ static inline int ip_rcv_finish(struct sk_buff *skb)
 		if (unlikely(err)) {
 			if (err == -EHOSTUNREACH)
 				IP_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
+			else if (err == -ENETUNREACH)
+				IP_INC_STATS_BH(IPSTATS_MIB_INNOROUTES);
 			goto drop;
 		}
 	}
@@ -358,6 +361,12 @@ static inline int ip_rcv_finish(struct sk_buff *skb)
 	if (iph->ihl > 5 && ip_rcv_options(skb))
 		goto drop;
 
+	rt = (struct rtable*)skb->dst;
+	if (rt->rt_type == RTN_MULTICAST)
+		IP_INC_STATS_BH(IPSTATS_MIB_INMCASTPKTS);
+	else if (rt->rt_type == RTN_BROADCAST)
+		IP_INC_STATS_BH(IPSTATS_MIB_INBCASTPKTS);
+
 	return dst_input(skb);
 
 drop:
@@ -414,7 +423,10 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 		goto inhdr_error;
 
 	len = ntohs(iph->tot_len);
-	if (skb->len < len || len < (iph->ihl*4))
+	if (skb->len < len) {
+		IP_INC_STATS_BH(IPSTATS_MIB_INTRUNCATEDPKTS);
+		goto drop;
+	} else if (len < (iph->ihl*4))
 		goto inhdr_error;
 
 	/* Our transport medium may have padded the buffer out. Now we know it

net/ipv4/ip_output.c

@@ -160,9 +160,15 @@ EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
 static inline int ip_finish_output2(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb->dst;
+	struct rtable *rt = (struct rtable *)dst;
 	struct net_device *dev = dst->dev;
 	int hh_len = LL_RESERVED_SPACE(dev);
 
+	if (rt->rt_type == RTN_MULTICAST)
+		IP_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS);
+	else if (rt->rt_type == RTN_BROADCAST)
+		IP_INC_STATS(IPSTATS_MIB_OUTBCASTPKTS);
+
 	/* Be paranoid, rather than too clever. */
 	if (unlikely(skb_headroom(skb) < hh_len && dev->hard_header)) {
 		struct sk_buff *skb2;

net/ipv4/tcp.c

@@ -1573,14 +1573,12 @@ void tcp_close(struct sock *sk, long timeout)
 
 	sk_stream_mem_reclaim(sk);
 
-	/* As outlined in draft-ietf-tcpimpl-prob-03.txt, section
-	 * 3.10, we send a RST here because data was lost.  To
-	 * witness the awful effects of the old behavior of always
-	 * doing a FIN, run an older 2.1.x kernel or 2.0.x, start
-	 * a bulk GET in an FTP client, suspend the process, wait
-	 * for the client to advertise a zero window, then kill -9
-	 * the FTP client, wheee...  Note: timeout is always zero
-	 * in such a case.
+	/* As outlined in RFC 2525, section 2.17, we send a RST here because
+	 * data was lost. To witness the awful effects of the old behavior of
+	 * always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk
+	 * GET in an FTP client, suspend the process, wait for the client to
+	 * advertise a zero window, then kill -9 the FTP client, wheee...
+	 * Note: timeout is always zero in such a case.
 	 */
 	if (data_was_unread) {
 		/* Unread data was tossed, zap the connection. */

net/ipv4/tcp_input.c

@@ -1265,20 +1265,15 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
 	return flag;
 }
 
-/* F-RTO can only be used if these conditions are satisfied:
- *  - there must be some unsent new data
- *  - the advertised window should allow sending it
- *  - TCP has never retransmitted anything other than head (SACK enhanced
- *    variant from Appendix B of RFC4138 is more robust here)
+/* F-RTO can only be used if TCP has never retransmitted anything other than
+ * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here)
  */
 int tcp_use_frto(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 
-	if (!sysctl_tcp_frto || !tcp_send_head(sk) ||
-		after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
-		      tp->snd_una + tp->snd_wnd))
+	if (!sysctl_tcp_frto)
 		return 0;
 
 	if (IsSackFrto())
@@ -2642,7 +2637,9 @@ static void tcp_undo_spur_to_response(struct sock *sk, int flag)
  *                  algorithm is not part of the F-RTO detection algorithm
  *                  given in RFC4138 but can be selected separately).
  * Otherwise (basically on duplicate ACK), RTO was (likely) caused by a loss
- * and TCP falls back to conventional RTO recovery.
+ * and TCP falls back to conventional RTO recovery. F-RTO allows overriding
+ * of Nagle, this is done using frto_counter states 2 and 3, when a new data
+ * segment of any size sent during F-RTO, state 2 is upgraded to 3.
  *
  * Rationale: if the RTO was spurious, new ACKs should arrive from the
  * original window even after we transmit two new data segments.
@@ -2671,7 +2668,7 @@ static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
 		inet_csk(sk)->icsk_retransmits = 0;
 
 	if (!before(tp->snd_una, tp->frto_highmark)) {
-		tcp_enter_frto_loss(sk, tp->frto_counter + 1, flag);
+		tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag);
 		return 1;
 	}
 
@@ -2697,7 +2694,7 @@ static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
 			return 1;
 		}
 
-		if ((tp->frto_counter == 2) &&
+		if ((tp->frto_counter >= 2) &&
 		    (!(flag&FLAG_FORWARD_PROGRESS) ||
 		     ((flag&FLAG_DATA_SACKED) && !(flag&FLAG_ONLY_ORIG_SACKED)))) {
 			/* RFC4138 shortcoming (see comment above) */
@@ -2710,10 +2707,19 @@ static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
 	}
 
 	if (tp->frto_counter == 1) {
+		/* Sending of the next skb must be allowed or no FRTO */
+		if (!tcp_send_head(sk) ||
+		    after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
+				     tp->snd_una + tp->snd_wnd)) {
+			tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3),
+					    flag);
+			return 1;
+		}
+
 		tp->snd_cwnd = tcp_packets_in_flight(tp) + 2;
 		tp->frto_counter = 2;
 		return 1;
-	} else /* frto_counter == 2 */ {
+	} else {
 		switch (sysctl_tcp_frto_response) {
 		case 2:
 			tcp_undo_spur_to_response(sk, flag);

net/ipv4/tcp_output.c

@@ -1035,8 +1035,10 @@ static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb,
 	if (nonagle & TCP_NAGLE_PUSH)
 		return 1;
 
-	/* Don't use the nagle rule for urgent data (or for the final FIN).  */
-	if (tp->urg_mode ||
+	/* Don't use the nagle rule for urgent data (or for the final FIN).
+	 * Nagle can be ignored during F-RTO too (see RFC4138).
+	 */
+	if (tp->urg_mode || (tp->frto_counter == 2) ||
 	    (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
 		return 1;
 
@@ -2035,7 +2037,7 @@ void tcp_send_fin(struct sock *sk)
 /* We get here when a process closes a file descriptor (either due to
  * an explicit close() or as a byproduct of exit()'ing) and there
  * was unread data in the receive queue.  This behavior is recommended
- * by draft-ietf-tcpimpl-prob-03.txt section 3.10.  -DaveM
+ * by RFC 2525, section 2.17.  -DaveM
  */
 void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 {

net/ipv4/udp.c

@@ -114,14 +114,33 @@ DEFINE_RWLOCK(udp_hash_lock);
 
 static int udp_port_rover;
 
-static inline int __udp_lib_lport_inuse(__u16 num, struct hlist_head udptable[])
+/*
+ * Note about this hash function :
+ * Typical use is probably daddr = 0, only dport is going to vary hash
+ */
+static inline unsigned int hash_port_and_addr(__u16 port, __be32 addr)
+{
+	addr ^= addr >> 16;
+	addr ^= addr >> 8;
+	return port ^ addr;
+}
+
+static inline int __udp_lib_port_inuse(unsigned int hash, int port,
+	__be32 daddr, struct hlist_head udptable[])
 {
 	struct sock *sk;
 	struct hlist_node *node;
+	struct inet_sock *inet;
 
-	sk_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)])
-		if (sk->sk_hash == num)
+	sk_for_each(sk, node, &udptable[hash & (UDP_HTABLE_SIZE - 1)]) {
+		if (sk->sk_hash != hash)
+			continue;
+		inet = inet_sk(sk);
+		if (inet->num != port)
+			continue;
+		if (inet->rcv_saddr == daddr)
 			return 1;
+	}
 	return 0;
 }
 
@@ -142,6 +161,7 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 	struct hlist_node *node;
 	struct hlist_head *head;
 	struct sock *sk2;
+	unsigned int hash;
 	int    error = 1;
 
 	write_lock_bh(&udp_hash_lock);
@@ -156,7 +176,9 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 		for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
 			int size;
 
-			head = &udptable[result & (UDP_HTABLE_SIZE - 1)];
+			hash = hash_port_and_addr(result,
+					inet_sk(sk)->rcv_saddr);
+			head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
 			if (hlist_empty(head)) {
 				if (result > sysctl_local_port_range[1])
 					result = sysctl_local_port_range[0] +
@@ -181,7 +203,10 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 				result = sysctl_local_port_range[0]
 					+ ((result - sysctl_local_port_range[0]) &
 					   (UDP_HTABLE_SIZE - 1));
-			if (! __udp_lib_lport_inuse(result, udptable))
+			hash = hash_port_and_addr(result,
+					inet_sk(sk)->rcv_saddr);
+			if (! __udp_lib_port_inuse(hash, result,
+				inet_sk(sk)->rcv_saddr, udptable))
 				break;
 		}
 		if (i >= (1 << 16) / UDP_HTABLE_SIZE)
@@ -189,11 +214,13 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 gotit:
 		*port_rover = snum = result;
 	} else {
-		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
+		hash = hash_port_and_addr(snum, inet_sk(sk)->rcv_saddr);
+		head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
 
 		sk_for_each(sk2, node, head)
-			if (sk2->sk_hash == snum                             &&
+			if (sk2->sk_hash == hash                             &&
 			    sk2 != sk                                        &&
+			    inet_sk(sk2)->num == snum	                     &&
 			    (!sk2->sk_reuse        || !sk->sk_reuse)         &&
 			    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
 			     || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
@@ -201,9 +228,9 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 				goto fail;
 	}
 	inet_sk(sk)->num = snum;
-	sk->sk_hash = snum;
+	sk->sk_hash = hash;
 	if (sk_unhashed(sk)) {
-		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
+		head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
 		sk_add_node(sk, head);
 		sock_prot_inc_use(sk->sk_prot);
 	}
@@ -242,63 +269,78 @@ static struct sock *__udp4_lib_lookup(__be32 saddr, __be16 sport,
 {
 	struct sock *sk, *result = NULL;
 	struct hlist_node *node;
-	unsigned short hnum = ntohs(dport);
-	int badness = -1;
+	unsigned int hash, hashwild;
+	int score, best = -1;
+
+	hash = hash_port_and_addr(ntohs(dport), daddr);
+	hashwild = hash_port_and_addr(ntohs(dport), 0);
 
 	read_lock(&udp_hash_lock);
-	sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
+
+lookup:
+
+	sk_for_each(sk, node, &udptable[hash & (UDP_HTABLE_SIZE - 1)]) {
 		struct inet_sock *inet = inet_sk(sk);
 
-		if (sk->sk_hash == hnum && !ipv6_only_sock(sk)) {
-			int score = (sk->sk_family == PF_INET ? 1 : 0);
-			if (inet->rcv_saddr) {
-				if (inet->rcv_saddr != daddr)
-					continue;
-				score+=2;
-			}
-			if (inet->daddr) {
-				if (inet->daddr != saddr)
-					continue;
-				score+=2;
-			}
-			if (inet->dport) {
-				if (inet->dport != sport)
-					continue;
-				score+=2;
-			}
-			if (sk->sk_bound_dev_if) {
-				if (sk->sk_bound_dev_if != dif)
-					continue;
-				score+=2;
-			}
-			if (score == 9) {
-				result = sk;
-				break;
-			} else if (score > badness) {
-				result = sk;
-				badness = score;
-			}
+		if (sk->sk_hash != hash || ipv6_only_sock(sk) ||
+			inet->num != dport)
+			continue;
+
+		score = (sk->sk_family == PF_INET ? 1 : 0);
+		if (inet->rcv_saddr) {
+			if (inet->rcv_saddr != daddr)
+				continue;
+			score+=2;
+		}
+		if (inet->daddr) {
+			if (inet->daddr != saddr)
+				continue;
+			score+=2;
+		}
+		if (inet->dport) {
+			if (inet->dport != sport)
+				continue;
+			score+=2;
+		}
+		if (sk->sk_bound_dev_if) {
+			if (sk->sk_bound_dev_if != dif)
+				continue;
+			score+=2;
+		}
+		if (score == 9) {
+			result = sk;
+			goto found;
+		} else if (score > best) {
+			result = sk;
+			best = score;
 		}
 	}
+
+	if (hash != hashwild) {
+		hash = hashwild;
+		goto lookup;
+	}
+found:
 	if (result)
 		sock_hold(result);
 	read_unlock(&udp_hash_lock);
 	return result;
 }
 
-static inline struct sock *udp_v4_mcast_next(struct sock *sk,
-					     __be16 loc_port, __be32 loc_addr,
-					     __be16 rmt_port, __be32 rmt_addr,
-					     int dif)
+static inline struct sock *udp_v4_mcast_next(
+			struct sock *sk,
+			unsigned int hnum, __be16 loc_port, __be32 loc_addr,
+			__be16 rmt_port, __be32 rmt_addr,
+			int dif)
 {
 	struct hlist_node *node;
 	struct sock *s = sk;
-	unsigned short hnum = ntohs(loc_port);
 
 	sk_for_each_from(s, node) {
 		struct inet_sock *inet = inet_sk(s);
 
 		if (s->sk_hash != hnum					||
+		    inet->num != loc_port				||
 		    (inet->daddr && inet->daddr != rmt_addr)		||
 		    (inet->dport != rmt_port && inet->dport)		||
 		    (inet->rcv_saddr && inet->rcv_saddr != loc_addr)	||
@@ -1129,29 +1171,44 @@ static int __udp4_lib_mcast_deliver(struct sk_buff *skb,
 				    __be32 saddr, __be32 daddr,
 				    struct hlist_head udptable[])
 {
-	struct sock *sk;
+	struct sock *sk, *skw, *sknext;
 	int dif;
+	unsigned int hash = hash_port_and_addr(ntohs(uh->dest), daddr);
+	unsigned int hashwild = hash_port_and_addr(ntohs(uh->dest), 0);
 
-	read_lock(&udp_hash_lock);
-	sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
 	dif = skb->dev->ifindex;
-	sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
-	if (sk) {
-		struct sock *sknext = NULL;
 
+	read_lock(&udp_hash_lock);
+
+	sk = sk_head(&udptable[hash & (UDP_HTABLE_SIZE - 1)]);
+	skw = sk_head(&udptable[hashwild & (UDP_HTABLE_SIZE - 1)]);
+
+	sk = udp_v4_mcast_next(sk, hash, uh->dest, daddr, uh->source, saddr, dif);
+	if (!sk) {
+		hash = hashwild;
+		sk = udp_v4_mcast_next(skw, hash, uh->dest, daddr, uh->source,
+			saddr, dif);
+	}
+	if (sk) {
 		do {
 			struct sk_buff *skb1 = skb;
-
-			sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
-						   uh->source, saddr, dif);
+			sknext = udp_v4_mcast_next(sk_next(sk), hash, uh->dest,
+				daddr, uh->source, saddr, dif);
+			if (!sknext && hash != hashwild) {
+				hash = hashwild;
+				sknext = udp_v4_mcast_next(skw, hash, uh->dest,
+					daddr, uh->source, saddr, dif);
+			}
 			if (sknext)
 				skb1 = skb_clone(skb, GFP_ATOMIC);
 
 			if (skb1) {
 				int ret = udp_queue_rcv_skb(sk, skb1);
 				if (ret > 0)
-					/* we should probably re-process instead
-					 * of dropping packets here. */
+					/*
+					 * we should probably re-process
+					 * instead of dropping packets here.
+					 */
 					kfree_skb(skb1);
 			}
 			sk = sknext;