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:
  tcp: Revert 'process defer accept as established' changes.
  ipv6: Fix duplicate initialization of rawv6_prot.destroy
  bnx2x: Updating the Maintainer
  net: Eliminate flush_scheduled_work() calls while RTNL is held.
  drivers/net/r6040.c: correct bad use of round_jiffies()
  fec_mpc52xx: MPC52xx_MESSAGES_DEFAULT: 2nd NETIF_MSG_IFDOWN => IFUP
  ipg: fix receivemode IPG_RM_RECEIVEMULTICAST{,HASH} in ipg_nic_set_multicast_list()
  netfilter: nf_conntrack: fix ctnetlink related crash in nf_nat_setup_info()
  netfilter: Make nflog quiet when no one listen in userspace.
  ipv6: Fail with appropriate error code when setting not-applicable sockopt.
  ipv6: Check IPV6_MULTICAST_LOOP option value.
  ipv6: Check the hop limit setting in ancillary data.
  ipv6 route: Fix route lifetime in netlink message.
  ipv6 mcast: Check address family of gf_group in getsockopt(MS_FILTER).
  dccp: Bug in initial acknowledgment number assignment
  dccp ccid-3: X truncated due to type conversion
  dccp ccid-3: TFRC reverse-lookup Bug-Fix
  dccp ccid-2: Bug-Fix - Ack Vectors need to be ignored on request sockets
  dccp: Fix sparse warnings
  dccp ccid-3: Bug-Fix - Zero RTT is possible

MAINTAINERS

@@ -995,8 +995,8 @@ L:	netdev@vger.kernel.org
 S:	Supported
 
 BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-P:	Eliezer Tamir
+P:	Eilon Greenstein
-M:	eliezert@broadcom.com
+M:	eilong@broadcom.com
 L:	netdev@vger.kernel.org
 S:	Supported
 

drivers/net/bnx2.c

@@ -5724,14 +5724,12 @@ bnx2_reset_task(struct work_struct *work)
 	if (!netif_running(bp->dev))
 		return;
 
-	bp->in_reset_task = 1;
 	bnx2_netif_stop(bp);
 
 	bnx2_init_nic(bp);
 
 	atomic_set(&bp->intr_sem, 1);
 	bnx2_netif_start(bp);
-	bp->in_reset_task = 0;
 }
 
 static void
@@ -5907,12 +5905,7 @@ bnx2_close(struct net_device *dev)
 	struct bnx2 *bp = netdev_priv(dev);
 	u32 reset_code;
 
-	/* Calling flush_scheduled_work() may deadlock because
+	cancel_work_sync(&bp->reset_task);
-	 * linkwatch_event() may be on the workqueue and it will try to get
-	 * the rtnl_lock which we are holding.
-	 */
-	while (bp->in_reset_task)
-		msleep(1);
 
 	bnx2_disable_int_sync(bp);
 	bnx2_napi_disable(bp);

drivers/net/bnx2.h

@@ -6656,7 +6656,6 @@ struct bnx2 {
 	int			current_interval;
 	struct			timer_list timer;
 	struct work_struct	reset_task;
-	int			in_reset_task;
 
 	/* Used to synchronize phy accesses. */
 	spinlock_t		phy_lock;

drivers/net/bnx2x.c

@@ -6,7 +6,8 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Written by: Eliezer Tamir <eliezert@broadcom.com>
+ * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Written by: Eliezer Tamir
  * Based on code from Michael Chan's bnx2 driver
  * UDP CSUM errata workaround by Arik Gendelman
  * Slowpath rework by Vladislav Zolotarov
@@ -74,7 +75,7 @@ static char version[] __devinitdata =
 	"Broadcom NetXtreme II 5771X 10Gigabit Ethernet Driver "
 	DRV_MODULE_NAME " " DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
 
-MODULE_AUTHOR("Eliezer Tamir <eliezert@broadcom.com>");
+MODULE_AUTHOR("Eliezer Tamir");
 MODULE_DESCRIPTION("Broadcom NetXtreme II BCM57710 Driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_MODULE_VERSION);

drivers/net/bnx2x.h

@@ -6,7 +6,8 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Written by: Eliezer Tamir <eliezert@broadcom.com>
+ * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Written by: Eliezer Tamir
  * Based on code from Michael Chan's bnx2 driver
  */
 

drivers/net/bnx2x_init.h

@@ -6,7 +6,8 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Written by: Eliezer Tamir <eliezert@broadcom.com>
+ * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Written by: Eliezer Tamir
  */
 
 #ifndef BNX2X_INIT_H

drivers/net/ehea/ehea_main.c

@@ -2605,7 +2605,8 @@ static int ehea_stop(struct net_device *dev)
 	if (netif_msg_ifdown(port))
 		ehea_info("disabling port %s", dev->name);
 
-	flush_scheduled_work();
+	cancel_work_sync(&port->reset_task);
+
 	mutex_lock(&port->port_lock);
 	netif_stop_queue(dev);
 	port_napi_disable(port);

drivers/net/fec_mpc52xx.c

@@ -78,7 +78,7 @@ module_param_array_named(mac, mpc52xx_fec_mac_addr, byte, NULL, 0);
 MODULE_PARM_DESC(mac, "six hex digits, ie. 0x1,0x2,0xc0,0x01,0xba,0xbe");
 
 #define MPC52xx_MESSAGES_DEFAULT ( NETIF_MSG_DRV | NETIF_MSG_PROBE | \
-		NETIF_MSG_LINK | NETIF_MSG_IFDOWN | NETIF_MSG_IFDOWN )
+		NETIF_MSG_LINK | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP)
 static int debug = -1;	/* the above default */
 module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, "debugging messages level");

drivers/net/hamradio/baycom_epp.c

@@ -959,7 +959,7 @@ static int epp_close(struct net_device *dev)
 	unsigned char tmp[1];
 
 	bc->work_running = 0;
-	flush_scheduled_work();
+	cancel_delayed_work_sync(&bc->run_work);
 	bc->stat = EPP_DCDBIT;
 	tmp[0] = 0;
 	pp->ops->epp_write_addr(pp, tmp, 1, 0);

drivers/net/ipg.c

@@ -577,12 +577,12 @@ static void ipg_nic_set_multicast_list(struct net_device *dev)
 		/* NIC to be configured in promiscuous mode. */
 		receivemode = IPG_RM_RECEIVEALLFRAMES;
 	} else if ((dev->flags & IFF_ALLMULTI) ||
-		   (dev->flags & IFF_MULTICAST &
+		   ((dev->flags & IFF_MULTICAST) &&
 		    (dev->mc_count > IPG_MULTICAST_HASHTABLE_SIZE))) {
 		/* NIC to be configured to receive all multicast
 		 * frames. */
 		receivemode |= IPG_RM_RECEIVEMULTICAST;
-	} else if (dev->flags & IFF_MULTICAST & (dev->mc_count > 0)) {
+	} else if ((dev->flags & IFF_MULTICAST) && (dev->mc_count > 0)) {
 		/* NIC to be configured to receive selected
 		 * multicast addresses. */
 		receivemode |= IPG_RM_RECEIVEMULTICASTHASH;

drivers/net/r6040.c

@@ -733,7 +733,7 @@ static void r6040_timer(unsigned long data)
 	}
 
 	/* Timer active again */
-	mod_timer(&lp->timer, jiffies + round_jiffies(HZ));
+	mod_timer(&lp->timer, round_jiffies(jiffies + HZ));
 }
 
 /* Read/set MAC address routines */

drivers/net/smc911x.c

@@ -136,7 +136,6 @@ struct smc911x_local {
 
 	/* work queue */
 	struct work_struct phy_configure;
-	int work_pending;
 
 	int tx_throttle;
 	spinlock_t lock;
@@ -960,11 +959,11 @@ static void smc911x_phy_configure(struct work_struct *work)
 	 * We should not be called if phy_type is zero.
 	 */
 	if (lp->phy_type == 0)
-		 goto smc911x_phy_configure_exit_nolock;
+		return;
 
 	if (smc911x_phy_reset(dev, phyaddr)) {
 		printk("%s: PHY reset timed out\n", dev->name);
-		goto smc911x_phy_configure_exit_nolock;
+		return;
 	}
 	spin_lock_irqsave(&lp->lock, flags);
 
@@ -1033,8 +1032,6 @@ static void smc911x_phy_configure(struct work_struct *work)
 
 smc911x_phy_configure_exit:
 	spin_unlock_irqrestore(&lp->lock, flags);
-smc911x_phy_configure_exit_nolock:
-	lp->work_pending = 0;
 }
 
 /*
@@ -1356,11 +1353,8 @@ static void smc911x_timeout(struct net_device *dev)
 	 * smc911x_phy_configure() calls msleep() which calls schedule_timeout()
 	 * which calls schedule().	 Hence we use a work queue.
 	 */
-	if (lp->phy_type != 0) {
+	if (lp->phy_type != 0)
-		if (schedule_work(&lp->phy_configure)) {
+		schedule_work(&lp->phy_configure);
-			lp->work_pending = 1;
-		}
-	}
 
 	/* We can accept TX packets again */
 	dev->trans_start = jiffies;
@@ -1531,16 +1525,8 @@ static int smc911x_close(struct net_device *dev)
 	if (lp->phy_type != 0) {
 		/* We need to ensure that no calls to
 		 * smc911x_phy_configure are pending.
-
-		 * flush_scheduled_work() cannot be called because we
-		 * are running with the netlink semaphore held (from
-		 * devinet_ioctl()) and the pending work queue
-		 * contains linkwatch_event() (scheduled by
-		 * netif_carrier_off() above). linkwatch_event() also
-		 * wants the netlink semaphore.
 		 */
-		while (lp->work_pending)
+		cancel_work_sync(&lp->phy_configure);
-			schedule();
 		smc911x_phy_powerdown(dev, lp->mii.phy_id);
 	}
 

drivers/net/smc91x.c

@@ -1016,15 +1016,8 @@ static void smc_phy_powerdown(struct net_device *dev)
 
 	/* We need to ensure that no calls to smc_phy_configure are
 	   pending.
-
-	   flush_scheduled_work() cannot be called because we are
-	   running with the netlink semaphore held (from
-	   devinet_ioctl()) and the pending work queue contains
-	   linkwatch_event() (scheduled by netif_carrier_off()
-	   above). linkwatch_event() also wants the netlink semaphore.
 	*/
-	while(lp->work_pending)
+	cancel_work_sync(&lp->phy_configure);
-		yield();
 
 	bmcr = smc_phy_read(dev, phy, MII_BMCR);
 	smc_phy_write(dev, phy, MII_BMCR, bmcr | BMCR_PDOWN);
@@ -1161,7 +1154,6 @@ static void smc_phy_configure(struct work_struct *work)
 smc_phy_configure_exit:
 	SMC_SELECT_BANK(lp, 2);
 	spin_unlock_irq(&lp->lock);
-	lp->work_pending = 0;
 }
 
 /*
@@ -1389,11 +1381,8 @@ static void smc_timeout(struct net_device *dev)
 	 * smc_phy_configure() calls msleep() which calls schedule_timeout()
 	 * which calls schedule().  Hence we use a work queue.
 	 */
-	if (lp->phy_type != 0) {
+	if (lp->phy_type != 0)
-		if (schedule_work(&lp->phy_configure)) {
+		schedule_work(&lp->phy_configure);
-			lp->work_pending = 1;
-		}
-	}
 
 	/* We can accept TX packets again */
 	dev->trans_start = jiffies;

drivers/net/tulip/tulip_core.c

@@ -731,7 +731,7 @@ static void tulip_down (struct net_device *dev)
 	void __iomem *ioaddr = tp->base_addr;
 	unsigned long flags;
 
-	flush_scheduled_work();
+	cancel_work_sync(&tp->media_work);
 
 #ifdef CONFIG_TULIP_NAPI
 	napi_disable(&tp->napi);

drivers/net/usb/kaweth.c

@@ -706,7 +706,7 @@ static void kaweth_kill_urbs(struct kaweth_device *kaweth)
 	usb_kill_urb(kaweth->rx_urb);
 	usb_kill_urb(kaweth->tx_urb);
 
-	flush_scheduled_work();
+	cancel_delayed_work_sync(&kaweth->lowmem_work);
 
 	/* a scheduled work may have resubmitted,
 	   we hit them again */

drivers/net/wireless/hostap/hostap_main.c

@@ -682,7 +682,13 @@ static int prism2_close(struct net_device *dev)
 		netif_device_detach(dev);
 	}
 
-	flush_scheduled_work();
+	cancel_work_sync(&local->reset_queue);
+	cancel_work_sync(&local->set_multicast_list_queue);
+	cancel_work_sync(&local->set_tim_queue);
+#ifndef PRISM2_NO_STATION_MODES
+	cancel_work_sync(&local->info_queue);
+#endif
+	cancel_work_sync(&local->comms_qual_update);
 
 	module_put(local->hw_module);
 

include/linux/tcp.h

@@ -239,11 +239,6 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 	return (struct tcp_request_sock *)req;
 }
 
-struct tcp_deferred_accept_info {
-	struct sock *listen_sk;
-	struct request_sock *request;
-};
-
 struct tcp_sock {
 	/* inet_connection_sock has to be the first member of tcp_sock */
 	struct inet_connection_sock	inet_conn;
@@ -379,8 +374,6 @@ struct tcp_sock {
 	unsigned int		keepalive_intvl;  /* time interval between keep alive probes */
 	int			linger2;
 
-	struct tcp_deferred_accept_info defer_tcp_accept;
-
 	unsigned long last_synq_overflow; 
 
 	u32	tso_deferred;

include/net/request_sock.h

@@ -115,8 +115,8 @@ struct request_sock_queue {
 	struct request_sock	*rskq_accept_head;
 	struct request_sock	*rskq_accept_tail;
 	rwlock_t		syn_wait_lock;
-	u16			rskq_defer_accept;
+	u8			rskq_defer_accept;
-	/* 2 bytes hole, try to pack */
+	/* 3 bytes hole, try to pack */
 	struct listen_sock	*listen_opt;
 };
 

include/net/tcp.h

@@ -139,7 +139,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define MAX_TCP_KEEPINTVL	32767
 #define MAX_TCP_KEEPCNT		127
 #define MAX_TCP_SYNCNT		127
-#define MAX_TCP_ACCEPT_DEFERRED 65535
 
 #define TCP_SYNQ_INTERVAL	(HZ/5)	/* Period of SYNACK timer */
 

net/dccp/ackvec.c

@@ -290,12 +290,12 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk,
 
 		while (1) {
 			const u8 len = dccp_ackvec_len(av, index);
-			const u8 state = dccp_ackvec_state(av, index);
+			const u8 av_state = dccp_ackvec_state(av, index);
 			/*
 			 * valid packets not yet in av_buf have a reserved
 			 * entry, with a len equal to 0.
 			 */
-			if (state == DCCP_ACKVEC_STATE_NOT_RECEIVED &&
+			if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED &&
 			    len == 0 && delta == 0) { /* Found our
 							 reserved seat! */
 				dccp_pr_debug("Found %llu reserved seat!\n",
@@ -325,31 +325,6 @@ out_duplicate:
 	return -EILSEQ;
 }
 
-#ifdef CONFIG_IP_DCCP_DEBUG
-void dccp_ackvector_print(const u64 ackno, const unsigned char *vector, int len)
-{
-	dccp_pr_debug_cat("ACK vector len=%d, ackno=%llu |", len,
-			 (unsigned long long)ackno);
-
-	while (len--) {
-		const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6;
-		const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK;
-
-		dccp_pr_debug_cat("%d,%d|", state, rl);
-		++vector;
-	}
-
-	dccp_pr_debug_cat("\n");
-}
-
-void dccp_ackvec_print(const struct dccp_ackvec *av)
-{
-	dccp_ackvector_print(av->av_buf_ackno,
-			     av->av_buf + av->av_buf_head,
-			     av->av_vec_len);
-}
-#endif
-
 static void dccp_ackvec_throw_record(struct dccp_ackvec *av,
 				     struct dccp_ackvec_record *avr)
 {

net/dccp/ccids/ccid3.c

@@ -159,8 +159,8 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp)
 	} else if (ktime_us_delta(now, hctx->ccid3hctx_t_ld)
 				- (s64)hctx->ccid3hctx_rtt >= 0) {
 
-		hctx->ccid3hctx_x =
+		hctx->ccid3hctx_x = min(2 * hctx->ccid3hctx_x, min_rate);
-			max(min(2 * hctx->ccid3hctx_x, min_rate),
+		hctx->ccid3hctx_x = max(hctx->ccid3hctx_x,
 			    scaled_div(((__u64)hctx->ccid3hctx_s) << 6,
 				       hctx->ccid3hctx_rtt));
 		hctx->ccid3hctx_t_ld = now;
@@ -329,7 +329,13 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 			hctx->ccid3hctx_x    = rfc3390_initial_rate(sk);
 			hctx->ccid3hctx_t_ld = now;
 		} else {
-			/* Sender does not have RTT sample: X_pps = 1 pkt/sec */
+			/*
+			 * Sender does not have RTT sample:
+			 * - set fallback RTT (RFC 4340, 3.4) since a RTT value
+			 *   is needed in several parts (e.g.  window counter);
+			 * - set sending rate X_pps = 1pps as per RFC 3448, 4.2.
+			 */
+			hctx->ccid3hctx_rtt = DCCP_FALLBACK_RTT;
 			hctx->ccid3hctx_x   = hctx->ccid3hctx_s;
 			hctx->ccid3hctx_x <<= 6;
 		}

net/dccp/ccids/lib/tfrc.c

@@ -14,14 +14,6 @@ module_param(tfrc_debug, bool, 0444);
 MODULE_PARM_DESC(tfrc_debug, "Enable debug messages");
 #endif
 
-extern int  tfrc_tx_packet_history_init(void);
-extern void tfrc_tx_packet_history_exit(void);
-extern int  tfrc_rx_packet_history_init(void);
-extern void tfrc_rx_packet_history_exit(void);
-
-extern int  tfrc_li_init(void);
-extern void tfrc_li_exit(void);
-
 static int __init tfrc_module_init(void)
 {
 	int rc = tfrc_li_init();

net/dccp/ccids/lib/tfrc.h

@@ -15,7 +15,7 @@
  *  (at your option) any later version.
  */
 #include <linux/types.h>
-#include <asm/div64.h>
+#include <linux/math64.h>
 #include "../../dccp.h"
 /* internal includes that this module exports: */
 #include "loss_interval.h"
@@ -29,21 +29,19 @@ extern int tfrc_debug;
 #endif
 
 /* integer-arithmetic divisions of type (a * 1000000)/b */
-static inline u64 scaled_div(u64 a, u32 b)
+static inline u64 scaled_div(u64 a, u64 b)
 {
 	BUG_ON(b==0);
-	a *= 1000000;
+	return div64_u64(a * 1000000, b);
-	do_div(a, b);
-	return a;
 }
 
-static inline u32 scaled_div32(u64 a, u32 b)
+static inline u32 scaled_div32(u64 a, u64 b)
 {
 	u64 result = scaled_div(a, b);
 
 	if (result > UINT_MAX) {
-		DCCP_CRIT("Overflow: a(%llu)/b(%u) > ~0U",
+		DCCP_CRIT("Overflow: %llu/%llu > UINT_MAX",
-			  (unsigned long long)a, b);
+			  (unsigned long long)a, (unsigned long long)b);
 		return UINT_MAX;
 	}
 	return result;
@@ -61,4 +59,11 @@ static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight)
 extern u32  tfrc_calc_x(u16 s, u32 R, u32 p);
 extern u32  tfrc_calc_x_reverse_lookup(u32 fvalue);
 
+extern int  tfrc_tx_packet_history_init(void);
+extern void tfrc_tx_packet_history_exit(void);
+extern int  tfrc_rx_packet_history_init(void);
+extern void tfrc_rx_packet_history_exit(void);
+
+extern int  tfrc_li_init(void);
+extern void tfrc_li_exit(void);
 #endif /* _TFRC_H_ */

net/dccp/ccids/lib/tfrc_equation.c

@@ -661,7 +661,7 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p)
 
 EXPORT_SYMBOL_GPL(tfrc_calc_x);
 
-/*
+/**
  *  tfrc_calc_x_reverse_lookup  -  try to find p given f(p)
  *
  *  @fvalue: function value to match, scaled by 1000000
@@ -676,11 +676,11 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue)
 
 	/* Error cases. */
 	if (fvalue < tfrc_calc_x_lookup[0][1]) {
-		DCCP_WARN("fvalue %d smaller than resolution\n", fvalue);
+		DCCP_WARN("fvalue %u smaller than resolution\n", fvalue);
-		return tfrc_calc_x_lookup[0][1];
+		return TFRC_SMALLEST_P;
 	}
 	if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) {
-		DCCP_WARN("fvalue %d exceeds bounds!\n", fvalue);
+		DCCP_WARN("fvalue %u exceeds bounds!\n", fvalue);
 		return 1000000;
 	}
 

net/dccp/minisocks.c

@@ -165,12 +165,12 @@ out_free:
 		/* See dccp_v4_conn_request */
 		newdmsk->dccpms_sequence_window = req->rcv_wnd;
 
-		newdp->dccps_gar = newdp->dccps_isr = dreq->dreq_isr;
+		newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss;
-		dccp_update_gsr(newsk, dreq->dreq_isr);
-
-		newdp->dccps_iss = dreq->dreq_iss;
 		dccp_update_gss(newsk, dreq->dreq_iss);
 
+		newdp->dccps_isr = dreq->dreq_isr;
+		dccp_update_gsr(newsk, dreq->dreq_isr);
+
 		/*
 		 * SWL and AWL are initially adjusted so that they are not less than
 		 * the initial Sequence Numbers received and sent, respectively:

net/dccp/options.c

@@ -107,9 +107,11 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
 		 *
 		 * CCID-specific options are ignored during connection setup, as
 		 * negotiation may still be in progress (see RFC 4340, 10.3).
+		 * The same applies to Ack Vectors, as these depend on the CCID.
 		 *
 		 */
-		if (dreq != NULL && opt >= 128)
+		if (dreq != NULL && (opt >= 128 ||
+		    opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1))
 			goto ignore_option;
 
 		switch (opt) {

net/dccp/output.c

@@ -508,6 +508,7 @@ void dccp_send_ack(struct sock *sk)
 
 EXPORT_SYMBOL_GPL(dccp_send_ack);
 
+#if 0
 /* FIXME: Is this still necessary (11.3) - currently nowhere used by DCCP. */
 void dccp_send_delayed_ack(struct sock *sk)
 {
@@ -538,6 +539,7 @@ void dccp_send_delayed_ack(struct sock *sk)
 	icsk->icsk_ack.timeout = timeout;
 	sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
 }
+#endif
 
 void dccp_send_sync(struct sock *sk, const u64 ackno,
 		    const enum dccp_pkt_type pkt_type)

net/dccp/probe.c

@@ -42,7 +42,7 @@ static int bufsize = 64 * 1024;
 
 static const char procname[] = "dccpprobe";
 
-struct {
+static struct {
 	struct kfifo	  *fifo;
 	spinlock_t	  lock;
 	wait_queue_head_t wait;

net/ipv4/inet_connection_sock.c

@@ -419,7 +419,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 	struct inet_connection_sock *icsk = inet_csk(parent);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
 	struct listen_sock *lopt = queue->listen_opt;
-	int thresh = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
+	int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
+	int thresh = max_retries;
 	unsigned long now = jiffies;
 	struct request_sock **reqp, *req;
 	int i, budget;
@@ -455,6 +456,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 		}
 	}
 
+	if (queue->rskq_defer_accept)
+		max_retries = queue->rskq_defer_accept;
+
 	budget = 2 * (lopt->nr_table_entries / (timeout / interval));
 	i = lopt->clock_hand;
 
@@ -462,8 +466,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 		reqp=&lopt->syn_table[i];
 		while ((req = *reqp) != NULL) {
 			if (time_after_eq(now, req->expires)) {
-				if (req->retrans < thresh &&
+				if ((req->retrans < (inet_rsk(req)->acked ? max_retries : thresh)) &&
-				    !req->rsk_ops->rtx_syn_ack(parent, req)) {
+				    (inet_rsk(req)->acked ||
+				     !req->rsk_ops->rtx_syn_ack(parent, req))) {
 					unsigned long timeo;
 
 					if (req->retrans++ == 0)

net/ipv4/tcp.c

@@ -2112,12 +2112,15 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_DEFER_ACCEPT:
-		if (val < 0) {
+		icsk->icsk_accept_queue.rskq_defer_accept = 0;
-			err = -EINVAL;
+		if (val > 0) {
-		} else {
+			/* Translate value in seconds to number of
-			if (val > MAX_TCP_ACCEPT_DEFERRED)
+			 * retransmits */
-				val = MAX_TCP_ACCEPT_DEFERRED;
+			while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
-			icsk->icsk_accept_queue.rskq_defer_accept = val;
+			       val > ((TCP_TIMEOUT_INIT / HZ) <<
+				       icsk->icsk_accept_queue.rskq_defer_accept))
+				icsk->icsk_accept_queue.rskq_defer_accept++;
+			icsk->icsk_accept_queue.rskq_defer_accept++;
 		}
 		break;
 
@@ -2299,7 +2302,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			val = (val ? : sysctl_tcp_fin_timeout) / HZ;
 		break;
 	case TCP_DEFER_ACCEPT:
-		val = icsk->icsk_accept_queue.rskq_defer_accept;
+		val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :
+			((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1));
 		break;
 	case TCP_WINDOW_CLAMP:
 		val = tp->window_clamp;

net/ipv4/tcp_input.c

@@ -4541,49 +4541,6 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th)
 	}
 }
 
-static int tcp_defer_accept_check(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (tp->defer_tcp_accept.request) {
-		int queued_data =  tp->rcv_nxt - tp->copied_seq;
-		int hasfin =  !skb_queue_empty(&sk->sk_receive_queue) ?
-			tcp_hdr((struct sk_buff *)
-				sk->sk_receive_queue.prev)->fin : 0;
-
-		if (queued_data && hasfin)
-			queued_data--;
-
-		if (queued_data &&
-		    tp->defer_tcp_accept.listen_sk->sk_state == TCP_LISTEN) {
-			if (sock_flag(sk, SOCK_KEEPOPEN)) {
-				inet_csk_reset_keepalive_timer(sk,
-							       keepalive_time_when(tp));
-			} else {
-				inet_csk_delete_keepalive_timer(sk);
-			}
-
-			inet_csk_reqsk_queue_add(
-				tp->defer_tcp_accept.listen_sk,
-				tp->defer_tcp_accept.request,
-				sk);
-
-			tp->defer_tcp_accept.listen_sk->sk_data_ready(
-				tp->defer_tcp_accept.listen_sk, 0);
-
-			sock_put(tp->defer_tcp_accept.listen_sk);
-			sock_put(sk);
-			tp->defer_tcp_accept.listen_sk = NULL;
-			tp->defer_tcp_accept.request = NULL;
-		} else if (hasfin ||
-			   tp->defer_tcp_accept.listen_sk->sk_state != TCP_LISTEN) {
-			tcp_reset(sk);
-			return -1;
-		}
-	}
-	return 0;
-}
-
 static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -4944,8 +4901,6 @@ step5:
 
 	tcp_data_snd_check(sk);
 	tcp_ack_snd_check(sk);
-
-	tcp_defer_accept_check(sk);
 	return 0;
 
 csum_error:

net/ipv4/tcp_ipv4.c

@@ -1918,14 +1918,6 @@ int tcp_v4_destroy_sock(struct sock *sk)
 		sk->sk_sndmsg_page = NULL;
 	}
 
-	if (tp->defer_tcp_accept.request) {
-		reqsk_free(tp->defer_tcp_accept.request);
-		sock_put(tp->defer_tcp_accept.listen_sk);
-		sock_put(sk);
-		tp->defer_tcp_accept.listen_sk = NULL;
-		tp->defer_tcp_accept.request = NULL;
-	}
-
 	atomic_dec(&tcp_sockets_allocated);
 
 	return 0;

net/ipv4/tcp_minisocks.c

@@ -571,8 +571,10 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 	   does sequence test, SYN is truncated, and thus we consider
 	   it a bare ACK.
 
-	   Both ends (listening sockets) accept the new incoming
+	   If icsk->icsk_accept_queue.rskq_defer_accept, we silently drop this
-	   connection and try to talk to each other. 8-)
+	   bare ACK.  Otherwise, we create an established connection.  Both
+	   ends (listening sockets) accept the new incoming connection and try
+	   to talk to each other. 8-)
 
 	   Note: This case is both harmless, and rare.  Possibility is about the
 	   same as us discovering intelligent life on another plant tomorrow.
@@ -640,6 +642,13 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 		if (!(flg & TCP_FLAG_ACK))
 			return NULL;
 
+		/* If TCP_DEFER_ACCEPT is set, drop bare ACK. */
+		if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
+		    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
+			inet_rsk(req)->acked = 1;
+			return NULL;
+		}
+
 		/* OK, ACK is valid, create big socket and
 		 * feed this segment to it. It will repeat all
 		 * the tests. THIS SEGMENT MUST MOVE SOCKET TO
@@ -678,24 +687,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 		inet_csk_reqsk_queue_unlink(sk, req, prev);
 		inet_csk_reqsk_queue_removed(sk, req);
 
-		if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
-		    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
-
-			/* the accept queue handling is done is est recv slow
-			 * path so lets make sure to start there
-			 */
-			tcp_sk(child)->pred_flags = 0;
-			sock_hold(sk);
-			sock_hold(child);
-			tcp_sk(child)->defer_tcp_accept.listen_sk = sk;
-			tcp_sk(child)->defer_tcp_accept.request = req;
-
-			inet_csk_reset_keepalive_timer(child,
-						       inet_csk(sk)->icsk_accept_queue.rskq_defer_accept * HZ);
-		} else {
 		inet_csk_reqsk_queue_add(sk, req, child);
-		}
-
 		return child;
 
 	listen_overflow:

net/ipv4/tcp_timer.c

@@ -489,11 +489,6 @@ static void tcp_keepalive_timer (unsigned long data)
 		goto death;
 	}
 
-	if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) {
-		tcp_send_active_reset(sk, GFP_ATOMIC);
-		goto death;
-	}
-
 	if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE)
 		goto out;
 

net/ipv6/datagram.c

@@ -705,6 +705,11 @@ int datagram_send_ctl(struct net *net,
 			}
 
 			*hlimit = *(int *)CMSG_DATA(cmsg);
+			if (*hlimit < -1 || *hlimit > 0xff) {
+				err = -EINVAL;
+				goto exit_f;
+			}
+
 			break;
 
 		case IPV6_TCLASS:

net/ipv6/ipv6_sockglue.c

@@ -67,7 +67,7 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *))
 
 	/* RA packet may be delivered ONLY to IPPROTO_RAW socket */
 	if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW)
-		return -EINVAL;
+		return -ENOPROTOOPT;
 
 	new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
 
@@ -446,7 +446,7 @@ done:
 
 	case IPV6_MULTICAST_HOPS:
 		if (sk->sk_type == SOCK_STREAM)
-			goto e_inval;
+			break;
 		if (optlen < sizeof(int))
 			goto e_inval;
 		if (val > 255 || val < -1)
@@ -458,13 +458,15 @@ done:
 	case IPV6_MULTICAST_LOOP:
 		if (optlen < sizeof(int))
 			goto e_inval;
+		if (val != valbool)
+			goto e_inval;
 		np->mc_loop = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_MULTICAST_IF:
 		if (sk->sk_type == SOCK_STREAM)
-			goto e_inval;
+			break;
 		if (optlen < sizeof(int))
 			goto e_inval;
 
@@ -860,7 +862,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (sk->sk_protocol != IPPROTO_UDP &&
 		    sk->sk_protocol != IPPROTO_UDPLITE &&
 		    sk->sk_protocol != IPPROTO_TCP)
-			return -EINVAL;
+			return -ENOPROTOOPT;
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -ENOTCONN;
 		val = sk->sk_family;
@@ -874,6 +876,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0)))
 			return -EFAULT;
+		if (gsf.gf_group.ss_family != AF_INET6)
+			return -EADDRNOTAVAIL;
 		lock_sock(sk);
 		err = ip6_mc_msfget(sk, &gsf,
 			(struct group_filter __user *)optval, optlen);

net/ipv6/raw.c

@@ -1169,7 +1169,8 @@ static int raw6_destroy(struct sock *sk)
 	lock_sock(sk);
 	ip6_flush_pending_frames(sk);
 	release_sock(sk);
-	return 0;
+
+	return inet6_destroy_sock(sk);
 }
 
 static int rawv6_init_sk(struct sock *sk)
@@ -1200,7 +1201,6 @@ struct proto rawv6_prot = {
 	.disconnect	   = udp_disconnect,
 	.ioctl		   = rawv6_ioctl,
 	.init		   = rawv6_init_sk,
-	.destroy	   = inet6_destroy_sock,
 	.setsockopt	   = rawv6_setsockopt,
 	.getsockopt	   = rawv6_getsockopt,
 	.sendmsg	   = rawv6_sendmsg,

net/ipv6/route.c

@@ -2196,8 +2196,12 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
 
 	NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric);
 
-	expires = (rt->rt6i_flags & RTF_EXPIRES) ?
+	if (!(rt->rt6i_flags & RTF_EXPIRES))
-			rt->rt6i_expires - jiffies : 0;
+		expires = 0;
+	else if (rt->rt6i_expires - jiffies < INT_MAX)
+		expires = rt->rt6i_expires - jiffies;
+	else
+		expires = INT_MAX;
 
 	if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0,
 			       expires, rt->u.dst.error) < 0)

net/netfilter/nf_conntrack_core.c

@@ -196,8 +196,6 @@ destroy_conntrack(struct nf_conntrack *nfct)
 	if (l4proto && l4proto->destroy)
 		l4proto->destroy(ct);
 
-	nf_ct_ext_destroy(ct);
-
 	rcu_read_unlock();
 
 	spin_lock_bh(&nf_conntrack_lock);
@@ -520,6 +518,7 @@ static void nf_conntrack_free_rcu(struct rcu_head *head)
 
 void nf_conntrack_free(struct nf_conn *ct)
 {
+	nf_ct_ext_destroy(ct);
 	call_rcu(&ct->rcu, nf_conntrack_free_rcu);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_free);

net/netfilter/nf_log.c

@@ -92,10 +92,6 @@ void nf_log_packet(int pf,
 		vsnprintf(prefix, sizeof(prefix), fmt, args);
 		va_end(args);
 		logger->logfn(pf, hooknum, skb, in, out, loginfo, prefix);
-	} else if (net_ratelimit()) {
-		printk(KERN_WARNING "nf_log_packet: can\'t log since "
-		       "no backend logging module loaded in! Please either "
-		       "load one, or disable logging explicitly\n");
 	}
 	rcu_read_unlock();
 }