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: (170 commits)
  commit 3d9dd756
  Author: Zach Brown <zach.brown@oracle.com>
  Date:   Fri Apr 14 16:04:18 2006 -0700
  
      [PATCH] ip_output: account for fraggap when checking to add trailer_len
      
      During other work I noticed that ip_append_data() seemed to be forgetting to
      include the frag gap in its calculation of a fragment that consumes the rest of
      the payload.  Herbert confirmed that this was a bug that snuck in during a
      previous rework.
Signed-off-by: Zach Brown <zach.brown@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
  
  commit 08d09997
  Author: Linus Walleij <triad@df.lth.se>
  Date:   Fri Apr 14 16:03:33 2006 -0700
  
      [IRDA]: smsc-ircc2, smcinit support for ALi ISA bridges
      
  ...

Documentation/networking/xfrm_sync.txt

+
+The sync patches work is based on initial patches from
+Krisztian <hidden@balabit.hu> and others and additional patches
+from Jamal <hadi@cyberus.ca>.
+
+The end goal for syncing is to be able to insert attributes + generate
+events so that the an SA can be safely moved from one machine to another
+for HA purposes.
+The idea is to synchronize the SA so that the takeover machine can do
+the processing of the SA as accurate as possible if it has access to it.
+
+We already have the ability to generate SA add/del/upd events.
+These patches add ability to sync and have accurate lifetime byte (to
+ensure proper decay of SAs) and replay counters to avoid replay attacks
+with as minimal loss at failover time.
+This way a backup stays as closely uptodate as an active member.
+
+Because the above items change for every packet the SA receives,
+it is possible for a lot of the events to be generated.
+For this reason, we also add a nagle-like algorithm to restrict
+the events. i.e we are going to set thresholds to say "let me
+know if the replay sequence threshold is reached or 10 secs have passed"
+These thresholds are set system-wide via sysctls or can be updated
+per SA.
+
+The identified items that need to be synchronized are:
+- the lifetime byte counter
+note that: lifetime time limit is not important if you assume the failover
+machine is known ahead of time since the decay of the time countdown
+is not driven by packet arrival.
+- the replay sequence for both inbound and outbound
+
+1) Message Structure
+----------------------
+
+nlmsghdr:aevent_id:optional-TLVs.
+
+The netlink message types are:
+
+XFRM_MSG_NEWAE and XFRM_MSG_GETAE.
+
+A XFRM_MSG_GETAE does not have TLVs.
+A XFRM_MSG_NEWAE will have at least two TLVs (as is
+discussed further below).
+
+aevent_id structure looks like:
+
+   struct xfrm_aevent_id {
+             struct xfrm_usersa_id           sa_id;
+             __u32                           flags;
+   };
+
+xfrm_usersa_id in this message layout identifies the SA.
+
+flags are used to indicate different things. The possible
+flags are:
+        XFRM_AE_RTHR=1, /* replay threshold*/
+        XFRM_AE_RVAL=2, /* replay value */
+        XFRM_AE_LVAL=4, /* lifetime value */
+        XFRM_AE_ETHR=8, /* expiry timer threshold */
+        XFRM_AE_CR=16, /* Event cause is replay update */
+        XFRM_AE_CE=32, /* Event cause is timer expiry */
+        XFRM_AE_CU=64, /* Event cause is policy update */
+
+How these flags are used is dependent on the direction of the
+message (kernel<->user) as well the cause (config, query or event).
+This is described below in the different messages.
+
+The pid will be set appropriately in netlink to recognize direction
+(0 to the kernel and pid = processid that created the event
+when going from kernel to user space)
+
+A program needs to subscribe to multicast group XFRMNLGRP_AEVENTS
+to get notified of these events.
+
+2) TLVS reflect the different parameters:
+-----------------------------------------
+
+a) byte value (XFRMA_LTIME_VAL)
+This TLV carries the running/current counter for byte lifetime since
+last event.
+
+b)replay value (XFRMA_REPLAY_VAL)
+This TLV carries the running/current counter for replay sequence since
+last event.
+
+c)replay threshold (XFRMA_REPLAY_THRESH)
+This TLV carries the threshold being used by the kernel to trigger events
+when the replay sequence is exceeded.
+
+d) expiry timer (XFRMA_ETIMER_THRESH)
+This is a timer value in milliseconds which is used as the nagle
+value to rate limit the events.
+
+3) Default configurations for the parameters:
+----------------------------------------------
+
+By default these events should be turned off unless there is
+at least one listener registered to listen to the multicast
+group XFRMNLGRP_AEVENTS.
+
+Programs installing SAs will need to specify the two thresholds, however,
+in order to not change existing applications such as racoon
+we also provide default threshold values for these different parameters
+in case they are not specified.
+
+the two sysctls/proc entries are:
+a) /proc/sys/net/core/sysctl_xfrm_aevent_etime
+used to provide default values for the XFRMA_ETIMER_THRESH in incremental
+units of time of 100ms. The default is 10 (1 second)
+
+b) /proc/sys/net/core/sysctl_xfrm_aevent_rseqth
+used to provide default values for XFRMA_REPLAY_THRESH parameter
+in incremental packet count. The default is two packets.
+
+4) Message types
+----------------
+
+a) XFRM_MSG_GETAE issued by user-->kernel.
+XFRM_MSG_GETAE does not carry any TLVs.
+The response is a XFRM_MSG_NEWAE which is formatted based on what
+XFRM_MSG_GETAE queried for.
+The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs.
+*if XFRM_AE_RTHR flag is set, then XFRMA_REPLAY_THRESH is also retrieved
+*if XFRM_AE_ETHR flag is set, then XFRMA_ETIMER_THRESH is also retrieved
+
+b) XFRM_MSG_NEWAE is issued by either user space to configure
+or kernel to announce events or respond to a XFRM_MSG_GETAE.
+
+i) user --> kernel to configure a specific SA.
+any of the values or threshold parameters can be updated by passing the
+appropriate TLV.
+A response is issued back to the sender in user space to indicate success
+or failure.
+In the case of success, additionally an event with
+XFRM_MSG_NEWAE is also issued to any listeners as described in iii).
+
+ii) kernel->user direction as a response to XFRM_MSG_GETAE
+The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs.
+The threshold TLVs will be included if explicitly requested in
+the XFRM_MSG_GETAE message.
+
+iii) kernel->user to report as event if someone sets any values or
+thresholds for an SA using XFRM_MSG_NEWAE (as described in #i above).
+In such a case XFRM_AE_CU flag is set to inform the user that
+the change happened as a result of an update.
+The message will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs.
+
+iv) kernel->user to report event when replay threshold or a timeout
+is exceeded.
+In such a case either XFRM_AE_CR (replay exceeded) or XFRM_AE_CE (timeout
+happened) is set to inform the user what happened.
+Note the two flags are mutually exclusive.
+The message will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs.
+
+Exceptions to threshold settings
+--------------------------------
+
+If you have an SA that is getting hit by traffic in bursts such that
+there is a period where the timer threshold expires with no packets
+seen, then an odd behavior is seen as follows:
+The first packet arrival after a timer expiry will trigger a timeout
+aevent; i.e we dont wait for a timeout period or a packet threshold
+to be reached. This is done for simplicity and efficiency reasons.
+
+-JHS

drivers/net/irda/irda-usb.c

@@ -1815,14 +1815,14 @@ static int irda_usb_probe(struct usb_interface *intf,
 		self->needspatch = (ret < 0);
 		if (ret < 0) {
 			printk("patch_device failed\n");
-			goto err_out_4;
+			goto err_out_5;
 		}
 
 		/* replace IrDA class descriptor with what patched device is now reporting */
 		irda_desc = irda_usb_find_class_desc (self->usbintf);
 		if (irda_desc == NULL) {
 			ret = -ENODEV;
-			goto err_out_4;
+			goto err_out_5;
 		}
 		if (self->irda_desc)
 			kfree (self->irda_desc);
@@ -1832,6 +1832,8 @@ static int irda_usb_probe(struct usb_interface *intf,
 
 	return 0;
 
+err_out_5:
+	unregister_netdev(self->netdev);
 err_out_4:
 	kfree(self->speed_buff);
 err_out_3:

include/net/arp.h

@@ -10,8 +10,6 @@
 extern struct neigh_table arp_tbl;
 
 extern void	arp_init(void);
-extern int	arp_rcv(struct sk_buff *skb, struct net_device *dev,
-			struct packet_type *pt, struct net_device *orig_dev);
 extern int	arp_find(unsigned char *haddr, struct sk_buff *skb);
 extern int	arp_ioctl(unsigned int cmd, void __user *arg);
 extern void     arp_send(int type, int ptype, u32 dest_ip, 

include/net/xfrm.h

@@ -143,6 +143,11 @@ struct xfrm_state
 	/* Replay detection state at the time we sent the last notification */
 	struct xfrm_replay_state preplay;
 
+	/* internal flag that only holds state for delayed aevent at the
+	 * moment
+	*/
+	u32			xflags;
+
 	/* Replay detection notification settings */
 	u32			replay_maxage;
 	u32			replay_maxdiff;
@@ -168,6 +173,9 @@ struct xfrm_state
 	void			*data;
 };
 
+/* xflags - make enum if more show up */
+#define XFRM_TIME_DEFER	1
+
 enum {
 	XFRM_STATE_VOID,
 	XFRM_STATE_ACQ,

net/ipv4/arp.c

@@ -928,7 +928,8 @@ static void parp_redo(struct sk_buff *skb)
  *	Receive an arp request from the device layer.
  */
 
-int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
+		   struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct arphdr *arp;
 
@@ -1417,7 +1418,6 @@ 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);

net/ipv4/devinet.c

@@ -1556,7 +1556,6 @@ void __init devinet_init(void)
 #endif
 }
 
-EXPORT_SYMBOL(devinet_ioctl);
 EXPORT_SYMBOL(in_dev_finish_destroy);
 EXPORT_SYMBOL(inet_select_addr);
 EXPORT_SYMBOL(inetdev_by_index);

net/ipv4/fib_frontend.c

@@ -666,4 +666,3 @@ void __init ip_fib_init(void)
 }
 
 EXPORT_SYMBOL(inet_addr_type);
-EXPORT_SYMBOL(ip_rt_ioctl);

net/ipv4/inet_hashtables.c

@@ -43,8 +43,6 @@ struct inet_bind_bucket *inet_bind_bucket_create(kmem_cache_t *cachep,
 	return tb;
 }
 
-EXPORT_SYMBOL(inet_bind_bucket_create);
-
 /*
  * Caller must hold hashbucket lock for this tb with local BH disabled
  */
@@ -64,8 +62,6 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
 	inet_csk(sk)->icsk_bind_hash = tb;
 }
 
-EXPORT_SYMBOL(inet_bind_hash);
-
 /*
  * Get rid of any references to a local port held by the given sock.
  */

net/ipv4/ip_output.c

@@ -904,7 +904,7 @@ int ip_append_data(struct sock *sk,
 			 * because we have no idea what fragment will be
 			 * the last.
 			 */
-			if (datalen == length)
+			if (datalen == length + fraggap)
 				alloclen += rt->u.dst.trailer_len;
 
 			if (transhdrlen) {

net/ipv4/tcp_input.c

@@ -4559,7 +4559,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 
 EXPORT_SYMBOL(sysctl_tcp_ecn);
 EXPORT_SYMBOL(sysctl_tcp_reordering);
-EXPORT_SYMBOL(sysctl_tcp_abc);
 EXPORT_SYMBOL(tcp_parse_options);
 EXPORT_SYMBOL(tcp_rcv_established);
 EXPORT_SYMBOL(tcp_rcv_state_process);

net/ipv4/tcp_ipv4.c

@@ -1859,5 +1859,4 @@ EXPORT_SYMBOL(tcp_proc_unregister);
 #endif
 EXPORT_SYMBOL(sysctl_local_port_range);
 EXPORT_SYMBOL(sysctl_tcp_low_latency);
-EXPORT_SYMBOL(sysctl_tcp_tw_reuse);
 

net/ipv4/tcp_output.c

@@ -59,9 +59,6 @@ int sysctl_tcp_tso_win_divisor = 3;
 int sysctl_tcp_mtu_probing = 0;
 int sysctl_tcp_base_mss = 512;
 
-EXPORT_SYMBOL(sysctl_tcp_mtu_probing);
-EXPORT_SYMBOL(sysctl_tcp_base_mss);
-
 static void update_send_head(struct sock *sk, struct tcp_sock *tp,
 			     struct sk_buff *skb)
 {

net/xfrm/xfrm_state.c

@@ -805,16 +805,22 @@ void xfrm_replay_notify(struct xfrm_state *x, int event)
 	case XFRM_REPLAY_UPDATE:
 		if (x->replay_maxdiff &&
 		    (x->replay.seq - x->preplay.seq < x->replay_maxdiff) &&
-		    (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff))
-			return;
+		    (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff)) {
+			if (x->xflags & XFRM_TIME_DEFER)
+				event = XFRM_REPLAY_TIMEOUT;
+			else
+				return;
+		}
 
 		break;
 
 	case XFRM_REPLAY_TIMEOUT:
 		if ((x->replay.seq == x->preplay.seq) &&
 		    (x->replay.bitmap == x->preplay.bitmap) &&
-		    (x->replay.oseq == x->preplay.oseq))
+		    (x->replay.oseq == x->preplay.oseq)) {
+			x->xflags |= XFRM_TIME_DEFER;
 			return;
+		}
 
 		break;
 	}
@@ -825,8 +831,10 @@ void xfrm_replay_notify(struct xfrm_state *x, int event)
 	km_state_notify(x, &c);
 
 	if (x->replay_maxage &&
-	    !mod_timer(&x->rtimer, jiffies + x->replay_maxage))
+	    !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) {
 		xfrm_state_hold(x);
+		x->xflags &= ~XFRM_TIME_DEFER;
+	}
 }
 EXPORT_SYMBOL(xfrm_replay_notify);
 
@@ -836,10 +844,15 @@ static void xfrm_replay_timer_handler(unsigned long data)
 
 	spin_lock(&x->lock);
 
-	if (xfrm_aevent_is_on() && x->km.state == XFRM_STATE_VALID)
-		xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT);
+	if (x->km.state == XFRM_STATE_VALID) {
+		if (xfrm_aevent_is_on())
+			xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT);
+		else
+			x->xflags |= XFRM_TIME_DEFER;
+	}
 
 	spin_unlock(&x->lock);
+	xfrm_state_put(x);
 }
 
 int xfrm_replay_check(struct xfrm_state *x, u32 seq)