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

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
Phonet: keep TX queue disabled when the device is off
SCHED: netem: Correct documentation comment in code.
netfilter: update rwlock initialization for nat_table
netlabel: Compiler warning and NULL pointer dereference fix
e1000e: fix double release of mutex
IA64: HP_SIMETH needs to depend upon NET
netpoll: fix race on poll_list resulting in garbage entry
ipv6: silence log messages for locally generated multicast
sungem: improve ethtool output with internal pcs and serdes
tcp: tcp_vegas cong avoid fix
sungem: Make PCS PHY support partially work again.

arch/ia64/hp/sim/Kconfig

···
 
 config HP_SIMETH
 	bool "Simulated Ethernet "
+	depends on NET
 
 config HP_SIMSERIAL
 	bool "Simulated serial driver support"

drivers/net/e1000e/ich8lan.c

···
 		ctrl |= E1000_CTRL_PHY_RST;
 	}
 	ret_val = e1000_acquire_swflag_ich8lan(hw);
+	/* Whether or not the swflag was acquired, we need to reset the part */
 	hw_dbg(hw, "Issuing a global reset to ich8lan");
 	ew32(CTRL, (ctrl | E1000_CTRL_RST));
 	msleep(20);
 
-	/* release the swflag because it is not reset by hardware reset */
-	e1000_release_swflag_ich8lan(hw);
+	if (!ret_val) {
+		/* release the swflag because it is not reset by
+		 * hardware reset
+		 */
+		e1000_release_swflag_ich8lan(hw);
+	}
 
 	ret_val = e1000e_get_auto_rd_done(hw);
 	if (ret_val) {

drivers/net/sungem.c

···
 	return NETDEV_TX_OK;
 }
 
+static void gem_pcs_reset(struct gem *gp)
+{
+	int limit;
+	u32 val;
+
+	/* Reset PCS unit. */
+	val = readl(gp->regs + PCS_MIICTRL);
+	val |= PCS_MIICTRL_RST;
+	writel(val, gp->regs + PCS_MIICTRL);
+
+	limit = 32;
+	while (readl(gp->regs + PCS_MIICTRL) & PCS_MIICTRL_RST) {
+		udelay(100);
+		if (limit-- <= 0)
+			break;
+	}
+	if (limit <= 0)
+		printk(KERN_WARNING "%s: PCS reset bit would not clear.\n",
+		       gp->dev->name);
+}
+
+static void gem_pcs_reinit_adv(struct gem *gp)
+{
+	u32 val;
+
+	/* Make sure PCS is disabled while changing advertisement
+	 * configuration.
+	 */
+	val = readl(gp->regs + PCS_CFG);
+	val &= ~(PCS_CFG_ENABLE | PCS_CFG_TO);
+	writel(val, gp->regs + PCS_CFG);
+
+	/* Advertise all capabilities except assymetric
+	 * pause.
+	 */
+	val = readl(gp->regs + PCS_MIIADV);
+	val |= (PCS_MIIADV_FD | PCS_MIIADV_HD |
+		PCS_MIIADV_SP | PCS_MIIADV_AP);
+	writel(val, gp->regs + PCS_MIIADV);
+
+	/* Enable and restart auto-negotiation, disable wrapback/loopback,
+	 * and re-enable PCS.
+	 */
+	val = readl(gp->regs + PCS_MIICTRL);
+	val |= (PCS_MIICTRL_RAN | PCS_MIICTRL_ANE);
+	val &= ~PCS_MIICTRL_WB;
+	writel(val, gp->regs + PCS_MIICTRL);
+
+	val = readl(gp->regs + PCS_CFG);
+	val |= PCS_CFG_ENABLE;
+	writel(val, gp->regs + PCS_CFG);
+
+	/* Make sure serialink loopback is off.  The meaning
+	 * of this bit is logically inverted based upon whether
+	 * you are in Serialink or SERDES mode.
+	 */
+	val = readl(gp->regs + PCS_SCTRL);
+	if (gp->phy_type == phy_serialink)
+		val &= ~PCS_SCTRL_LOOP;
+	else
+		val |= PCS_SCTRL_LOOP;
+	writel(val, gp->regs + PCS_SCTRL);
+}
+
 #define STOP_TRIES 32
 
 /* Must be invoked under gp->lock and gp->tx_lock. */
···
 
 	if (limit <= 0)
 		printk(KERN_ERR "%s: SW reset is ghetto.\n", gp->dev->name);
+
+	if (gp->phy_type == phy_serialink || gp->phy_type == phy_serdes)
+		gem_pcs_reinit_adv(gp);
 }
 
 /* Must be invoked under gp->lock and gp->tx_lock. */
···
 	    	   gp->phy_type == phy_serdes) {
 		u32 pcs_lpa = readl(gp->regs + PCS_MIILP);
 
-		if (pcs_lpa & PCS_MIIADV_FD)
+		if ((pcs_lpa & PCS_MIIADV_FD) || gp->phy_type == phy_serdes)
 			full_duplex = 1;
 		speed = SPEED_1000;
 	}
···
 			val = readl(gp->regs + PCS_MIISTAT);
 
 		if ((val & PCS_MIISTAT_LS) != 0) {
+			if (gp->lstate == link_up)
+				goto restart;
+
 			gp->lstate = link_up;
 			netif_carrier_on(gp->dev);
 			(void)gem_set_link_modes(gp);
···
 		if (gp->phy_mii.def && gp->phy_mii.def->ops->init)
 			gp->phy_mii.def->ops->init(&gp->phy_mii);
 	} else {
-		u32 val;
-		int limit;
-
-		/* Reset PCS unit. */
-		val = readl(gp->regs + PCS_MIICTRL);
-		val |= PCS_MIICTRL_RST;
-		writel(val, gp->regs + PCS_MIICTRL);
-
-		limit = 32;
-		while (readl(gp->regs + PCS_MIICTRL) & PCS_MIICTRL_RST) {
-			udelay(100);
-			if (limit-- <= 0)
-				break;
-		}
-		if (limit <= 0)
-			printk(KERN_WARNING "%s: PCS reset bit would not clear.\n",
-			       gp->dev->name);
-
-		/* Make sure PCS is disabled while changing advertisement
-		 * configuration.
-		 */
-		val = readl(gp->regs + PCS_CFG);
-		val &= ~(PCS_CFG_ENABLE | PCS_CFG_TO);
-		writel(val, gp->regs + PCS_CFG);
-
-		/* Advertise all capabilities except assymetric
-		 * pause.
-		 */
-		val = readl(gp->regs + PCS_MIIADV);
-		val |= (PCS_MIIADV_FD | PCS_MIIADV_HD |
-			PCS_MIIADV_SP | PCS_MIIADV_AP);
-		writel(val, gp->regs + PCS_MIIADV);
-
-		/* Enable and restart auto-negotiation, disable wrapback/loopback,
-		 * and re-enable PCS.
-		 */
-		val = readl(gp->regs + PCS_MIICTRL);
-		val |= (PCS_MIICTRL_RAN | PCS_MIICTRL_ANE);
-		val &= ~PCS_MIICTRL_WB;
-		writel(val, gp->regs + PCS_MIICTRL);
-
-		val = readl(gp->regs + PCS_CFG);
-		val |= PCS_CFG_ENABLE;
-		writel(val, gp->regs + PCS_CFG);
-
-		/* Make sure serialink loopback is off.  The meaning
-		 * of this bit is logically inverted based upon whether
-		 * you are in Serialink or SERDES mode.
-		 */
-		val = readl(gp->regs + PCS_SCTRL);
-		if (gp->phy_type == phy_serialink)
-			val &= ~PCS_SCTRL_LOOP;
-		else
-			val |= PCS_SCTRL_LOOP;
-		writel(val, gp->regs + PCS_SCTRL);
+		gem_pcs_reset(gp);
+		gem_pcs_reinit_adv(gp);
 	}
 
 	/* Default aneg parameters */
···
 		cmd->speed = 0;
 		cmd->duplex = cmd->port = cmd->phy_address =
 			cmd->transceiver = cmd->autoneg = 0;
+
+		/* serdes means usually a Fibre connector, with most fixed */
+		if (gp->phy_type == phy_serdes) {
+			cmd->port = PORT_FIBRE;
+			cmd->supported = (SUPPORTED_1000baseT_Half |
+				SUPPORTED_1000baseT_Full |
+				SUPPORTED_FIBRE | SUPPORTED_Autoneg |
+				SUPPORTED_Pause | SUPPORTED_Asym_Pause);
+			cmd->advertising = cmd->supported;
+			cmd->transceiver = XCVR_INTERNAL;
+			if (gp->lstate == link_up)
+				cmd->speed = SPEED_1000;
+			cmd->duplex = DUPLEX_FULL;
+			cmd->autoneg = 1;
+		}
 	}
 	cmd->maxtxpkt = cmd->maxrxpkt = 0;
 

include/linux/netdevice.h

···
 {
 	NAPI_STATE_SCHED,	/* Poll is scheduled */
 	NAPI_STATE_DISABLE,	/* Disable pending */
+	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
 };
 
 extern void __napi_schedule(struct napi_struct *n);
···
 {
 	unsigned long flags;
 
+	/*
+	 * don't let napi dequeue from the cpu poll list
+	 * just in case its running on a different cpu
+	 */
+	if (unlikely(test_bit(NAPI_STATE_NPSVC, &napi->state)))
+		return;
 	local_irq_save(flags);
 	__netif_rx_complete(dev, napi);
 	local_irq_restore(flags);

net/core/netpoll.c

···
 
 	npinfo->rx_flags |= NETPOLL_RX_DROP;
 	atomic_inc(&trapped);
+	set_bit(NAPI_STATE_NPSVC, &napi->state);
 
 	work = napi->poll(napi, budget);
 
+	clear_bit(NAPI_STATE_NPSVC, &napi->state);
 	atomic_dec(&trapped);
 	npinfo->rx_flags &= ~NETPOLL_RX_DROP;
 

net/ipv4/netfilter/nf_nat_rule.c

···
 static struct xt_table nat_table = {
 	.name		= "nat",
 	.valid_hooks	= NAT_VALID_HOOKS,
-	.lock		= __RW_LOCK_UNLOCKED(__nat_table.lock),
+	.lock		= __RW_LOCK_UNLOCKED(nat_table.lock),
 	.me		= THIS_MODULE,
 	.af		= AF_INET,
 };

net/ipv4/tcp_vegas.c

···
 
 #include "tcp_vegas.h"
 
-/* Default values of the Vegas variables, in fixed-point representation
- * with V_PARAM_SHIFT bits to the right of the binary point.
- */
-#define V_PARAM_SHIFT 1
-static int alpha = 2<<V_PARAM_SHIFT;
-static int beta  = 4<<V_PARAM_SHIFT;
-static int gamma = 1<<V_PARAM_SHIFT;
+static int alpha = 2;
+static int beta  = 4;
+static int gamma = 1;
 
 module_param(alpha, int, 0644);
-MODULE_PARM_DESC(alpha, "lower bound of packets in network (scale by 2)");
+MODULE_PARM_DESC(alpha, "lower bound of packets in network");
 module_param(beta, int, 0644);
-MODULE_PARM_DESC(beta, "upper bound of packets in network (scale by 2)");
+MODULE_PARM_DESC(beta, "upper bound of packets in network");
 module_param(gamma, int, 0644);
 MODULE_PARM_DESC(gamma, "limit on increase (scale by 2)");
 
···
 		return;
 	}
 
-	/* The key players are v_beg_snd_una and v_beg_snd_nxt.
-	 *
-	 * These are so named because they represent the approximate values
-	 * of snd_una and snd_nxt at the beginning of the current RTT. More
-	 * precisely, they represent the amount of data sent during the RTT.
-	 * At the end of the RTT, when we receive an ACK for v_beg_snd_nxt,
-	 * we will calculate that (v_beg_snd_nxt - v_beg_snd_una) outstanding
-	 * bytes of data have been ACKed during the course of the RTT, giving
-	 * an "actual" rate of:
-	 *
-	 *     (v_beg_snd_nxt - v_beg_snd_una) / (rtt duration)
-	 *
-	 * Unfortunately, v_beg_snd_una is not exactly equal to snd_una,
-	 * because delayed ACKs can cover more than one segment, so they
-	 * don't line up nicely with the boundaries of RTTs.
-	 *
-	 * Another unfortunate fact of life is that delayed ACKs delay the
-	 * advance of the left edge of our send window, so that the number
-	 * of bytes we send in an RTT is often less than our cwnd will allow.
-	 * So we keep track of our cwnd separately, in v_beg_snd_cwnd.
-	 */
-
 	if (after(ack, vegas->beg_snd_nxt)) {
 		/* Do the Vegas once-per-RTT cwnd adjustment. */
-		u32 old_wnd, old_snd_cwnd;
-
-
-		/* Here old_wnd is essentially the window of data that was
-		 * sent during the previous RTT, and has all
-		 * been acknowledged in the course of the RTT that ended
-		 * with the ACK we just received. Likewise, old_snd_cwnd
-		 * is the cwnd during the previous RTT.
-		 */
-		old_wnd = (vegas->beg_snd_nxt - vegas->beg_snd_una) /
-			tp->mss_cache;
-		old_snd_cwnd = vegas->beg_snd_cwnd;
 
 		/* Save the extent of the current window so we can use this
 		 * at the end of the next RTT.
 		 */
-		vegas->beg_snd_una  = vegas->beg_snd_nxt;
 		vegas->beg_snd_nxt  = tp->snd_nxt;
-		vegas->beg_snd_cwnd = tp->snd_cwnd;
 
 		/* We do the Vegas calculations only if we got enough RTT
 		 * samples that we can be reasonably sure that we got
···
 			 *
 			 * This is:
 			 *     (actual rate in segments) * baseRTT
-			 * We keep it as a fixed point number with
-			 * V_PARAM_SHIFT bits to the right of the binary point.
 			 */
-			target_cwnd = ((u64)old_wnd * vegas->baseRTT);
-			target_cwnd <<= V_PARAM_SHIFT;
-			do_div(target_cwnd, rtt);
+			target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt;
 
 			/* Calculate the difference between the window we had,
 			 * and the window we would like to have. This quantity
 			 * is the "Diff" from the Arizona Vegas papers.
-			 *
-			 * Again, this is a fixed point number with
-			 * V_PARAM_SHIFT bits to the right of the binary
-			 * point.
 			 */
-			diff = (old_wnd << V_PARAM_SHIFT) - target_cwnd;
+			diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT;
 
 			if (diff > gamma && tp->snd_ssthresh > 2 ) {
 				/* Going too fast. Time to slow down
···
 				 * truncation robs us of full link
 				 * utilization.
 				 */
-				tp->snd_cwnd = min(tp->snd_cwnd,
-						   ((u32)target_cwnd >>
-						    V_PARAM_SHIFT)+1);
+				tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1);
 
 			} else if (tp->snd_cwnd <= tp->snd_ssthresh) {
 				/* Slow start.  */
 				tcp_slow_start(tp);
 			} else {
 				/* Congestion avoidance. */
-				u32 next_snd_cwnd;
 
 				/* Figure out where we would like cwnd
 				 * to be.
···
 					/* The old window was too fast, so
 					 * we slow down.
 					 */
-					next_snd_cwnd = old_snd_cwnd - 1;
+					tp->snd_cwnd--;
 				} else if (diff < alpha) {
 					/* We don't have enough extra packets
 					 * in the network, so speed up.
 					 */
-					next_snd_cwnd = old_snd_cwnd + 1;
+					tp->snd_cwnd++;
 				} else {
 					/* Sending just as fast as we
 					 * should be.
 					 */
-					next_snd_cwnd = old_snd_cwnd;
 				}
-
-				/* Adjust cwnd upward or downward, toward the
-				 * desired value.
-				 */
-				if (next_snd_cwnd > tp->snd_cwnd)
-					tp->snd_cwnd++;
-				else if (next_snd_cwnd < tp->snd_cwnd)
-					tp->snd_cwnd--;
 			}
 
 			if (tp->snd_cwnd < 2)

net/ipv6/ndisc.c

···
 		   is invalid, but ndisc specs say nothing
 		   about it. It could be misconfiguration, or
 		   an smart proxy agent tries to help us :-)
+
+		   We should not print the error if NA has been
+		   received from loopback - it is just our own
+		   unsolicited advertisement.
 		 */
-		ND_PRINTK1(KERN_WARNING
+		if (skb->pkt_type != PACKET_LOOPBACK)
+			ND_PRINTK1(KERN_WARNING
 			   "ICMPv6 NA: someone advertises our address on %s!\n",
 			   ifp->idev->dev->name);
 		in6_ifa_put(ifp);

net/netlabel/netlabel_unlabeled.c

···
 				      const struct in_addr *mask,
 				      struct netlbl_audit *audit_info)
 {
-	int ret_val = 0;
 	struct netlbl_af4list *list_entry;
 	struct netlbl_unlhsh_addr4 *entry;
 	struct audit_buffer *audit_buf;
···
 	if (list_entry != NULL)
 		entry = netlbl_unlhsh_addr4_entry(list_entry);
 	else
-		ret_val = -ENOENT;
+		entry = NULL;
 
 	audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCDEL,
 					      audit_info);
···
 					  addr->s_addr, mask->s_addr);
 		if (dev != NULL)
 			dev_put(dev);
-		if (entry && security_secid_to_secctx(entry->secid,
-						      &secctx,
-						      &secctx_len) == 0) {
+		if (entry != NULL &&
+		    security_secid_to_secctx(entry->secid,
+					     &secctx, &secctx_len) == 0) {
 			audit_log_format(audit_buf, " sec_obj=%s", secctx);
 			security_release_secctx(secctx, secctx_len);
 		}
-		audit_log_format(audit_buf, " res=%u", ret_val == 0 ? 1 : 0);
+		audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0);
 		audit_log_end(audit_buf);
 	}
 
-	if (ret_val == 0)
-		call_rcu(&entry->rcu, netlbl_unlhsh_free_addr4);
-	return ret_val;
+	if (entry == NULL)
+		return -ENOENT;
+
+	call_rcu(&entry->rcu, netlbl_unlhsh_free_addr4);
+	return 0;
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
···
 				      const struct in6_addr *mask,
 				      struct netlbl_audit *audit_info)
 {
-	int ret_val = 0;
 	struct netlbl_af6list *list_entry;
 	struct netlbl_unlhsh_addr6 *entry;
 	struct audit_buffer *audit_buf;
···
 	if (list_entry != NULL)
 		entry = netlbl_unlhsh_addr6_entry(list_entry);
 	else
-		ret_val = -ENOENT;
+		entry = NULL;
 
 	audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCDEL,
 					      audit_info);
···
 					  addr, mask);
 		if (dev != NULL)
 			dev_put(dev);
-		if (entry && security_secid_to_secctx(entry->secid,
-						      &secctx,
-						      &secctx_len) == 0) {
+		if (entry != NULL &&
+		    security_secid_to_secctx(entry->secid,
+					     &secctx, &secctx_len) == 0) {
 			audit_log_format(audit_buf, " sec_obj=%s", secctx);
 			security_release_secctx(secctx, secctx_len);
 		}
-		audit_log_format(audit_buf, " res=%u", ret_val == 0 ? 1 : 0);
+		audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0);
 		audit_log_end(audit_buf);
 	}
 
-	if (ret_val == 0)
-		call_rcu(&entry->rcu, netlbl_unlhsh_free_addr6);
-	return ret_val;
+	if (entry == NULL)
+		return -ENOENT;
+
+	call_rcu(&entry->rcu, netlbl_unlhsh_free_addr6);
+	return 0;
 }
 #endif /* IPv6 */
 

net/phonet/pep-gprs.c

···
 static void gprs_write_space(struct sock *sk)
 {
 	struct gprs_dev *dev = sk->sk_user_data;
+	struct net_device *net = dev->net;
 	unsigned credits = pep_writeable(sk);
 
 	spin_lock_bh(&dev->tx_lock);
 	dev->tx_max = credits;
-	if (credits > skb_queue_len(&dev->tx_queue))
-		netif_wake_queue(dev->net);
+	if (credits > skb_queue_len(&dev->tx_queue) && netif_running(net))
+		netif_wake_queue(net);
 	spin_unlock_bh(&dev->tx_lock);
 }
 
 /*
  * Network device callbacks
  */
+
+static int gprs_open(struct net_device *dev)
+{
+	struct gprs_dev *gp = netdev_priv(dev);
+
+	gprs_write_space(gp->sk);
+	return 0;
+}
+
+static int gprs_close(struct net_device *dev)
+{
+	struct gprs_dev *gp = netdev_priv(dev);
+
+	netif_stop_queue(dev);
+	flush_work(&gp->tx_work);
+	return 0;
+}
 
 static int gprs_xmit(struct sk_buff *skb, struct net_device *net)
 {
···
 	net->tx_queue_len	= 10;
 
 	net->destructor		= free_netdev;
+	net->open		= gprs_open;
+	net->stop		= gprs_close;
 	net->hard_start_xmit	= gprs_xmit; /* mandatory */
 	net->change_mtu		= gprs_set_mtu;
 	net->get_stats		= gprs_get_stats;
···
 	dev->sk = sk;
 
 	printk(KERN_DEBUG"%s: attached\n", net->name);
-	gprs_write_space(sk); /* kick off TX */
 	return net->ifindex;
 
 out_rel:
···
 
 	printk(KERN_DEBUG"%s: detached\n", net->name);
 	unregister_netdev(net);
-	flush_scheduled_work();
 	sock_put(sk);
-	skb_queue_purge(&dev->tx_queue);
 }

net/sched/sch_netem.c

···
 	 layering other disciplines.  It does not need to do bandwidth
 	 control either since that can be handled by using token
 	 bucket or other rate control.
-
-	 The simulator is limited by the Linux timer resolution
-	 and will create packet bursts on the HZ boundary (1ms).
 */
 
 struct netem_sched_data {