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

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1443 commits)
  phy/marvell: add 88ec048 support
  igb: Program MDICNFG register prior to PHY init
  e1000e: correct MAC-PHY interconnect register offset for 82579
  hso: Add new product ID
  can: Add driver for esd CAN-USB/2 device
  l2tp: fix export of header file for userspace
  can-raw: Fix skb_orphan_try handling
  Revert "net: remove zap_completion_queue"
  net: cleanup inclusion
  phy/marvell: add 88e1121 interface mode support
  u32: negative offset fix
  net: Fix a typo from "dev" to "ndev"
  igb: Use irq_synchronize per vector when using MSI-X
  ixgbevf: fix null pointer dereference due to filter being set for VLAN 0
  e1000e: Fix irq_synchronize in MSI-X case
  e1000e: register pm_qos request on hardware activation
  ip_fragment: fix subtracting PPPOE_SES_HLEN from mtu twice
  net: Add getsockopt support for TCP thin-streams
  cxgb4: update driver version
  cxgb4: add new PCI IDs
  ...

Manually fix up conflicts in:
 - drivers/net/e1000e/netdev.c: due to pm_qos registration
   infrastructure changes
 - drivers/net/phy/marvell.c: conflict between adding 88ec048 support
   and cleaning up the IDs
 - drivers/net/wireless/ipw2x00/ipw2100.c: trivial ipw2100_pm_qos_req
   conflict (registration change vs marking it static)

1 files changed, 34 insertions, 11 deletions

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index ce231780a2b1..6c40a8c46e79 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -239,7 +239,16 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
    sent to multicast group to reach destination designated router.
  */
 struct ip_ra_chain *ip_ra_chain;
-DEFINE_RWLOCK(ip_ra_lock);
+static DEFINE_SPINLOCK(ip_ra_lock);
+
+
+static void ip_ra_destroy_rcu(struct rcu_head *head)
+{
+	struct ip_ra_chain *ra = container_of(head, struct ip_ra_chain, rcu);
+
+	sock_put(ra->saved_sk);
+	kfree(ra);
+}
 
 int ip_ra_control(struct sock *sk, unsigned char on,
 		  void (*destructor)(struct sock *))
@@ -251,35 +260,42 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 
 	new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
 
-	write_lock_bh(&ip_ra_lock);
+	spin_lock_bh(&ip_ra_lock);
 	for (rap = &ip_ra_chain; (ra = *rap) != NULL; rap = &ra->next) {
 		if (ra->sk == sk) {
 			if (on) {
-				write_unlock_bh(&ip_ra_lock);
+				spin_unlock_bh(&ip_ra_lock);
 				kfree(new_ra);
 				return -EADDRINUSE;
 			}
-			*rap = ra->next;
-			write_unlock_bh(&ip_ra_lock);
+			/* dont let ip_call_ra_chain() use sk again */
+			ra->sk = NULL;
+			rcu_assign_pointer(*rap, ra->next);
+			spin_unlock_bh(&ip_ra_lock);
 
 			if (ra->destructor)
 				ra->destructor(sk);
-			sock_put(sk);
-			kfree(ra);
+			/*
+			 * Delay sock_put(sk) and kfree(ra) after one rcu grace
+			 * period. This guarantee ip_call_ra_chain() dont need
+			 * to mess with socket refcounts.
+			 */
+			ra->saved_sk = sk;
+			call_rcu(&ra->rcu, ip_ra_destroy_rcu);
 			return 0;
 		}
 	}
 	if (new_ra == NULL) {
-		write_unlock_bh(&ip_ra_lock);
+		spin_unlock_bh(&ip_ra_lock);
 		return -ENOBUFS;
 	}
 	new_ra->sk = sk;
 	new_ra->destructor = destructor;
 
 	new_ra->next = ra;
-	*rap = new_ra;
+	rcu_assign_pointer(*rap, new_ra);
 	sock_hold(sk);
-	write_unlock_bh(&ip_ra_lock);
+	spin_unlock_bh(&ip_ra_lock);
 
 	return 0;
 }
@@ -449,7 +465,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 			     (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) |
 			     (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) |
 			     (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) |
-			     (1<<IP_MINTTL))) ||
+			     (1<<IP_MINTTL) | (1<<IP_NODEFRAG))) ||
 	    optname == IP_MULTICAST_TTL ||
 	    optname == IP_MULTICAST_ALL ||
 	    optname == IP_MULTICAST_LOOP ||
@@ -572,6 +588,13 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		}
 		inet->hdrincl = val ? 1 : 0;
 		break;
+	case IP_NODEFRAG:
+		if (sk->sk_type != SOCK_RAW) {
+			err = -ENOPROTOOPT;
+			break;
+		}
+		inet->nodefrag = val ? 1 : 0;
+		break;
 	case IP_MTU_DISCOVER:
 		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
 			goto e_inval;