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:
  [ATM] CLIP: Do not refer freed skbuff in clip_mkip().
  [NET]: Drop tx lock in dev_watchdog_up
  [PACKET]: Don't truncate non-linear skbs with mmaped IO
  [NET]: Mark frame diverter for future removal.
  [NETFILTER]: Add secmark headers to header-y
  [ATM]: linux-atm-general mailing list is subscribers only
  [ATM]: [he] when transmit fails, unmap the dma regions
  [TCP] tcp-lp: update information to MAINTAINERS
  [TCP] tcp-lp: bug fix for oops in 2.6.18-rc6
  [BRIDGE]: random extra bytes on STP TCN packet
  [IPV6]: Accept -1 for IPV6_TCLASS
  [IPV6]: Fix tclass setting for raw sockets.
  [IPVS]: remove the debug option go ip_vs_ftp
  [IPVS]: Make sure ip_vs_ftp ports are valid
  [IPVS]: auto-help for ip_vs_ftp
  [IPVS]: Document the ports option to ip_vs_ftp in kernel-parameters.txt
  [TCP]: Turn ABC off.
  [NEIGH]: neigh_table_clear() doesn't free stats

Documentation/feature-removal-schedule.txt

@@ -281,3 +281,16 @@ Why:	The deferred output hooks are a layering violation causing unusual
 Who:	Patrick McHardy <kaber@trash.net>
 
 ---------------------------
+
+What:	frame diverter
+When:	November 2006
+Why:	The frame diverter is included in most distribution kernels, but is
+	broken. It does not correctly handle many things:
+	- IPV6
+	- non-linear skb's
+	- network device RCU on removal
+	- input frames not correctly checked for protocol errors
+	It also adds allocation overhead even if not enabled.
+	It is not clear if anyone is still using it.
+Who:	Stephen Hemminger <shemminger@osdl.org>
+

Documentation/kernel-parameters.txt

@@ -697,6 +697,12 @@ running once the system is up.
 	ips=		[HW,SCSI] Adaptec / IBM ServeRAID controller
 			See header of drivers/scsi/ips.c.
 
+	ports=		[IP_VS_FTP] IPVS ftp helper module
+			Default is 21.
+			Up to 8 (IP_VS_APP_MAX_PORTS) ports
+			may be specified.
+			Format: <port>,<port>....
+
 	irqfixup	[HW]
 			When an interrupt is not handled search all handlers
 			for it. Intended to get systems with badly broken

Documentation/networking/ip-sysctl.txt

@@ -102,9 +102,15 @@ inet_peer_gc_maxtime - INTEGER
 TCP variables: 
 
 tcp_abc - INTEGER
-	Controls Appropriate Byte Count defined in RFC3465. If set to
+	Controls Appropriate Byte Count (ABC) defined in RFC3465.
-	0 then does congestion avoid once per ack. 1 is conservative
+	ABC is a way of increasing congestion window (cwnd) more slowly
-	value, and 2 is more agressive.
+	in response to partial acknowledgments.
+	Possible values are:
+		0 increase cwnd once per acknowledgment (no ABC)
+		1 increase cwnd once per acknowledgment of full sized segment
+		2 allow increase cwnd by two if acknowledgment is
+		  of two segments to compensate for delayed acknowledgments.
+	Default: 0 (off)
 
 tcp_syn_retries - INTEGER
 	Number of times initial SYNs for an active TCP connection attempt

MAINTAINERS

@@ -416,7 +416,7 @@ S:	Supported
 ATM
 P:	Chas Williams
 M:	chas@cmf.nrl.navy.mil
-L:	linux-atm-general@lists.sourceforge.net
+L:	linux-atm-general@lists.sourceforge.net (subscribers-only)
 W:	http://linux-atm.sourceforge.net
 S:	Maintained
 
@@ -2810,6 +2810,14 @@ M:	hadi@cyberus.ca
 L:	netdev@vger.kernel.org
 S:	Maintained
 
+TCP LOW PRIORITY MODULE
+P:	Wong Hoi Sing, Edison
+M:	hswong3i@gmail.com
+P:	Hung Hing Lun, Mike
+M:	hlhung3i@gmail.com
+W:	http://tcp-lp-mod.sourceforge.net/
+S:	Maintained
+
 TI OMAP RANDOM NUMBER GENERATOR SUPPORT
 P:	Deepak Saxena
 M:	dsaxena@plexity.net

drivers/atm/he.c

@@ -2282,6 +2282,8 @@ __enqueue_tpd(struct he_dev *he_dev, struct he_tpd *tpd, unsigned cid)
 				TPDRQ_MASK(he_readl(he_dev, TPDRQ_B_H)));
 
 		if (new_tail == he_dev->tpdrq_head) {
+			int slot;
+
 			hprintk("tpdrq full (cid 0x%x)\n", cid);
 			/*
 			 * FIXME
@@ -2289,6 +2291,13 @@ __enqueue_tpd(struct he_dev *he_dev, struct he_tpd *tpd, unsigned cid)
 			 * after service_tbrq, service the backlog
 			 * for now, we just drop the pdu
 			 */
+			for (slot = 0; slot < TPD_MAXIOV; ++slot) {
+				if (tpd->iovec[slot].addr)
+					pci_unmap_single(he_dev->pci_dev,
+						tpd->iovec[slot].addr,
+						tpd->iovec[slot].len & TPD_LEN_MASK,
+								PCI_DMA_TODEVICE);
+			}
 			if (tpd->skb) {
 				if (tpd->vcc->pop)
 					tpd->vcc->pop(tpd->vcc, tpd->skb);

include/linux/netfilter/Kbuild

@@ -5,7 +5,7 @@ header-y := nf_conntrack_sctp.h nf_conntrack_tuple_common.h		\
 	    xt_helper.h xt_length.h xt_limit.h xt_mac.h xt_mark.h	\
 	    xt_MARK.h xt_multiport.h xt_NFQUEUE.h xt_pkttype.h		\
 	    xt_policy.h xt_realm.h xt_sctp.h xt_state.h xt_string.h	\
-	    xt_tcpmss.h xt_tcpudp.h
+	    xt_tcpmss.h xt_tcpudp.h xt_SECMARK.h xt_CONNSECMARK.h
 
 unifdef-y := nf_conntrack_common.h nf_conntrack_ftp.h		\
 	nf_conntrack_tcp.h nfnetlink.h x_tables.h xt_physdev.h

net/Kconfig

@@ -177,7 +177,7 @@ source "net/lapb/Kconfig"
 
 config NET_DIVERT
 	bool "Frame Diverter (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on EXPERIMENTAL && BROKEN
 	---help---
 	  The Frame Diverter allows you to divert packets from the
 	  network, that are not aimed at the interface receiving it (in

net/atm/clip.c

@@ -500,9 +500,11 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout)
 		} else {
 			unsigned int len = skb->len;
 
+			skb_get(skb);
 			clip_push(vcc, skb);
 			PRIV(skb->dev)->stats.rx_packets--;
 			PRIV(skb->dev)->stats.rx_bytes -= len;
+			kfree_skb(skb);
 		}
 	return 0;
 }

net/bridge/br_stp_bpdu.c

@@ -121,7 +121,7 @@ void br_send_tcn_bpdu(struct net_bridge_port *p)
 	buf[1] = 0;
 	buf[2] = 0;
 	buf[3] = BPDU_TYPE_TCN;
-	br_send_bpdu(p, buf, 7);
+	br_send_bpdu(p, buf, 4);
 }
 
 /*

net/core/neighbour.c

@@ -1432,6 +1432,9 @@ int neigh_table_clear(struct neigh_table *tbl)
 	kfree(tbl->phash_buckets);
 	tbl->phash_buckets = NULL;
 
+	free_percpu(tbl->stats);
+	tbl->stats = NULL;
+
 	return 0;
 }
 

net/ipv4/ipvs/ip_vs_ftp.c

@@ -46,14 +46,7 @@
  */
 static int ports[IP_VS_APP_MAX_PORTS] = {21, 0};
 module_param_array(ports, int, NULL, 0);
-
+MODULE_PARM_DESC(ports, "Ports to monitor for FTP control commands");
-/*
- *	Debug level
- */
-#ifdef CONFIG_IP_VS_DEBUG
-static int debug=0;
-module_param(debug, int, 0);
-#endif
 
 
 /*	Dummy variable */
@@ -177,7 +170,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 					   &start, &end) != 1)
 			return 1;
 
-		IP_VS_DBG(1-debug, "PASV response (%u.%u.%u.%u:%d) -> "
+		IP_VS_DBG(7, "PASV response (%u.%u.%u.%u:%d) -> "
 			  "%u.%u.%u.%u:%d detected\n",
 			  NIPQUAD(from), ntohs(port), NIPQUAD(cp->caddr), 0);
 
@@ -280,7 +273,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	while (data <= data_limit - 6) {
 		if (strnicmp(data, "PASV\r\n", 6) == 0) {
 			/* Passive mode on */
-			IP_VS_DBG(1-debug, "got PASV at %zd of %zd\n",
+			IP_VS_DBG(7, "got PASV at %zd of %zd\n",
 				  data - data_start,
 				  data_limit - data_start);
 			cp->app_data = &ip_vs_ftp_pasv;
@@ -302,7 +295,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 				   &start, &end) != 1)
 		return 1;
 
-	IP_VS_DBG(1-debug, "PORT %u.%u.%u.%u:%d detected\n",
+	IP_VS_DBG(7, "PORT %u.%u.%u.%u:%d detected\n",
 		  NIPQUAD(to), ntohs(port));
 
 	/* Passive mode off */
@@ -311,7 +304,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	/*
 	 * Now update or create a connection entry for it
 	 */
-	IP_VS_DBG(1-debug, "protocol %s %u.%u.%u.%u:%d %u.%u.%u.%u:%d\n",
+	IP_VS_DBG(7, "protocol %s %u.%u.%u.%u:%d %u.%u.%u.%u:%d\n",
 		  ip_vs_proto_name(iph->protocol),
 		  NIPQUAD(to), ntohs(port), NIPQUAD(cp->vaddr), 0);
 
@@ -372,10 +365,16 @@ static int __init ip_vs_ftp_init(void)
 	for (i=0; i<IP_VS_APP_MAX_PORTS; i++) {
 		if (!ports[i])
 			continue;
+		if (ports[i] < 0 || ports[i] > 0xffff) {
+			IP_VS_WARNING("ip_vs_ftp: Ignoring invalid "
+				      "configuration port[%d] = %d\n",
+				      i, ports[i]);
+			continue;
+		}
 		ret = register_ip_vs_app_inc(app, app->protocol, ports[i]);
 		if (ret)
 			break;
-		IP_VS_DBG(1-debug, "%s: loaded support on port[%d] = %d\n",
+		IP_VS_INFO("%s: loaded support on port[%d] = %d\n",
 		 	   app->name, i, ports[i]);
 	}
 

net/ipv4/tcp_input.c

@@ -89,7 +89,7 @@ int sysctl_tcp_frto;
 int sysctl_tcp_nometrics_save;
 
 int sysctl_tcp_moderate_rcvbuf = 1;
-int sysctl_tcp_abc = 1;
+int sysctl_tcp_abc;
 
 #define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
 #define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/

net/ipv4/tcp_lp.c

@@ -3,13 +3,8 @@
  *
  * TCP Low Priority is a distributed algorithm whose goal is to utilize only
  *   the excess network bandwidth as compared to the ``fair share`` of
- *   bandwidth as targeted by TCP. Available from:
+ *   bandwidth as targeted by TCP.
- *     http://www.ece.rice.edu/~akuzma/Doc/akuzma/TCP-LP.pdf
  *
- * Original Author:
- *   Aleksandar Kuzmanovic <akuzma@northwestern.edu>
- *
- * See http://www-ece.rice.edu/networks/TCP-LP/ for their implementation.
  * As of 2.6.13, Linux supports pluggable congestion control algorithms.
  * Due to the limitation of the API, we take the following changes from
  * the original TCP-LP implementation:
@@ -24,11 +19,20 @@
  *   o OWD is handled in relative format, where local time stamp will in
  *     tcp_time_stamp format.
  *
- * Port from 2.4.19 to 2.6.16 as module by:
+ * Original Author:
- *   Wong Hoi Sing Edison <hswong3i@gmail.com>
+ *   Aleksandar Kuzmanovic <akuzma@northwestern.edu>
- *   Hung Hing Lun <hlhung3i@gmail.com>
+ * Available from:
+ *   http://www.ece.rice.edu/~akuzma/Doc/akuzma/TCP-LP.pdf
+ * Original implementation for 2.4.19:
+ *   http://www-ece.rice.edu/networks/TCP-LP/
  *
- * Version: $Id: tcp_lp.c,v 1.22 2006-05-02 18:18:19 hswong3i Exp $
+ * 2.6.x module Authors:
+ *   Wong Hoi Sing, Edison <hswong3i@gmail.com>
+ *   Hung Hing Lun, Mike <hlhung3i@gmail.com>
+ * SourceForge project page:
+ *   http://tcp-lp-mod.sourceforge.net/
+ *
+ * Version: $Id: tcp_lp.c,v 1.24 2006/09/05 20:22:53 hswong3i Exp $
  */
 
 #include <linux/config.h>
@@ -153,16 +157,19 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk)
 	if (m < 0)
 		m = -m;
 
-	if (rhz != 0) {
+	if (rhz > 0) {
 		m -= rhz >> 6;	/* m is now error in remote HZ est */
 		rhz += m;	/* 63/64 old + 1/64 new */
 	} else
 		rhz = m << 6;
 
-	/* record time for successful remote HZ calc */
-	lp->flag |= LP_VALID_RHZ;
-
  out:
+	/* record time for successful remote HZ calc */
+	if (rhz > 0)
+		lp->flag |= LP_VALID_RHZ;
+	else
+		lp->flag &= ~LP_VALID_RHZ;
+
 	/* record reference time stamp */
 	lp->remote_ref_time = tp->rx_opt.rcv_tsval;
 	lp->local_ref_time = tp->rx_opt.rcv_tsecr;
@@ -333,6 +340,6 @@ static void __exit tcp_lp_unregister(void)
 module_init(tcp_lp_register);
 module_exit(tcp_lp_unregister);
 
-MODULE_AUTHOR("Wong Hoi Sing Edison, Hung Hing Lun");
+MODULE_AUTHOR("Wong Hoi Sing Edison, Hung Hing Lun Mike");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("TCP Low Priority");

net/ipv6/datagram.c

@@ -696,7 +696,7 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
 			}
 
 			tc = *(int *)CMSG_DATA(cmsg);
-			if (tc < 0 || tc > 0xff)
+			if (tc < -1 || tc > 0xff)
 				goto exit_f;
 
 			err = 0;

net/ipv6/icmp.c

@@ -401,7 +401,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	if (hlimit < 0)
 		hlimit = ipv6_get_hoplimit(dst->dev);
 
-	tclass = np->cork.tclass;
+	tclass = np->tclass;
 	if (tclass < 0)
 		tclass = 0;
 
@@ -497,7 +497,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	if (hlimit < 0)
 		hlimit = ipv6_get_hoplimit(dst->dev);
 
-	tclass = np->cork.tclass;
+	tclass = np->tclass;
 	if (tclass < 0)
 		tclass = 0;
 

net/ipv6/ipv6_sockglue.c

@@ -362,7 +362,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_TCLASS:
-		if (val < 0 || val > 0xff)
+		if (val < -1 || val > 0xff)
 			goto e_inval;
 		np->tclass = val;
 		retv = 0;
@@ -947,6 +947,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 
 	case IPV6_TCLASS:
 		val = np->tclass;
+		if (val < 0)
+			val = 0;
 		break;
 
 	case IPV6_RECVTCLASS:

net/ipv6/raw.c

@@ -781,7 +781,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	}
 
 	if (tclass < 0) {
-		tclass = np->cork.tclass;
+		tclass = np->tclass;
 		if (tclass < 0)
 			tclass = 0;
 	}

net/packet/af_packet.c

@@ -626,8 +626,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe
 		if ((int)snaplen < 0)
 			snaplen = 0;
 	}
-	if (snaplen > skb->len-skb->data_len)
-		snaplen = skb->len-skb->data_len;
 
 	spin_lock(&sk->sk_receive_queue.lock);
 	h = (struct tpacket_hdr *)packet_lookup_frame(po, po->head);
@@ -644,7 +642,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe
 		status &= ~TP_STATUS_LOSING;
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	memcpy((u8*)h + macoff, skb->data, snaplen);
+	skb_copy_bits(skb, 0, (u8*)h + macoff, snaplen);
 
 	h->tp_len = skb->len;
 	h->tp_snaplen = snaplen;

net/sched/sch_generic.c

@@ -238,9 +238,7 @@ void __netdev_watchdog_up(struct net_device *dev)
 
 static void dev_watchdog_up(struct net_device *dev)
 {
-	netif_tx_lock_bh(dev);
 	__netdev_watchdog_up(dev);
-	netif_tx_unlock_bh(dev);
 }
 
 static void dev_watchdog_down(struct net_device *dev)