Merge branch 'from-linus' into upstream

31 files changed, 249 insertions, 119 deletions

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 06abb6634f5b..53086fb75089 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -85,7 +85,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port)
                 goto err_out;
 
         err = br_fill_ifinfo(skb, port, current->pid, 0, event, 0);
-        if (err)
+        if (err < 0)
                 goto err_kfree;
 
         NETLINK_CB(skb).dst_group = RTNLGRP_LINK;
diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c
index 02693a230dc1..9f950db3b76f 100644
--- a/net/bridge/netfilter/ebt_ulog.c
+++ b/net/bridge/netfilter/ebt_ulog.c
@@ -74,6 +74,9 @@ static void ulog_send(unsigned int nlgroup)
         if (timer_pending(&ub->timer))
                 del_timer(&ub->timer);
 
+        if (!ub->skb)
+                return;
+
         /* last nlmsg needs NLMSG_DONE */
         if (ub->qlen > 1)
                 ub->lastnlh->nlmsg_type = NLMSG_DONE;
diff --git a/net/core/dst.c b/net/core/dst.c
index 470c05bc4cb2..1a5e49da0e77 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -95,12 +95,11 @@ static void dst_run_gc(unsigned long dummy)
                 dst_gc_timer_inc = DST_GC_INC;
                 dst_gc_timer_expires = DST_GC_MIN;
         }
-        dst_gc_timer.expires = jiffies + dst_gc_timer_expires;
 #if RT_CACHE_DEBUG >= 2
         printk("dst_total: %d/%d %ld\n",
                atomic_read(&dst_total), delayed,  dst_gc_timer_expires);
 #endif
-        add_timer(&dst_gc_timer);
+        mod_timer(&dst_gc_timer, jiffies + dst_gc_timer_expires);
 
 out:
         spin_unlock(&dst_lock);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 67ed14ddabd2..6a7320b39ed0 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2149,6 +2149,8 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
         skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32);
         skb->dev = odev;
         skb->pkt_type = PACKET_HOST;
+        skb->nh.iph = iph;
+        skb->h.uh = udph;
 
         if (pkt_dev->nfrags <= 0)
                 pgh = (struct pktgen_hdr *)skb_put(skb, datalen);
@@ -2460,6 +2462,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
         skb->protocol = protocol;
         skb->dev = odev;
         skb->pkt_type = PACKET_HOST;
+        skb->nh.ipv6h = iph;
+        skb->h.uh = udph;
 
         if (pkt_dev->nfrags <= 0)
                 pgh = (struct pktgen_hdr *)skb_put(skb, datalen);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 20e5bb73f147..30cc1ba6ed5c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -394,6 +394,9 @@ static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
         }
 
         if (ida[IFLA_ADDRESS - 1]) {
+                struct sockaddr *sa;
+                int len;
+
                 if (!dev->set_mac_address) {
                         err = -EOPNOTSUPP;
                         goto out;
@@ -405,7 +408,17 @@ static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
                 if (ida[IFLA_ADDRESS - 1]->rta_len != RTA_LENGTH(dev->addr_len))
                         goto out;
 
-                err = dev->set_mac_address(dev, RTA_DATA(ida[IFLA_ADDRESS - 1]));
+                len = sizeof(sa_family_t) + dev->addr_len;
+                sa = kmalloc(len, GFP_KERNEL);
+                if (!sa) {
+                        err = -ENOMEM;
+                        goto out;
+                }
+                sa->sa_family = dev->type;
+                memcpy(sa->sa_data, RTA_DATA(ida[IFLA_ADDRESS - 1]),
+                       dev->addr_len);
+                err = dev->set_mac_address(dev, sa);
+                kfree(sa);
                 if (err)
                         goto out;
                 send_addr_notify = 1;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 022d8894c11d..c54f3664bce5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -268,8 +268,10 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
         struct sk_buff *skb;
 
         skb = alloc_skb(length + NET_SKB_PAD, gfp_mask);
-        if (likely(skb))
+        if (likely(skb)) {
                 skb_reserve(skb, NET_SKB_PAD);
+                skb->dev = dev;
+        }
         return skb;
 }
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9bf307a29783..4c20f5546893 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -947,7 +947,7 @@ alloc_new_skb:
                                 skb_prev->csum = csum_sub(skb_prev->csum,
                                                           skb->csum);
                                 data += fraggap;
-                                skb_trim(skb_prev, maxfraglen);
+                                pskb_trim_unique(skb_prev, maxfraglen);
                         }
 
                         copy = datalen - transhdrlen - fraggap;
@@ -1142,7 +1142,7 @@ ssize_t	ip_append_page(struct sock *sk, struct page *page,
                                         data, fraggap, 0);
                                 skb_prev->csum = csum_sub(skb_prev->csum,
                                                           skb->csum);
-                                skb_trim(skb_prev, maxfraglen);
+                                pskb_trim_unique(skb_prev, maxfraglen);
                         }
 
                         /*
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 80c73ca90116..df4854cf598b 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1170,21 +1170,34 @@ static int __init arp_tables_init(void)
 {
         int ret;
 
-        xt_proto_init(NF_ARP);
+        ret = xt_proto_init(NF_ARP);
+        if (ret < 0)
+                goto err1;
 
         /* Noone else will be downing sem now, so we won't sleep */
-        xt_register_target(&arpt_standard_target);
-        xt_register_target(&arpt_error_target);
+        ret = xt_register_target(&arpt_standard_target);
+        if (ret < 0)
+                goto err2;
+        ret = xt_register_target(&arpt_error_target);
+        if (ret < 0)
+                goto err3;
 
         /* Register setsockopt */
         ret = nf_register_sockopt(&arpt_sockopts);
-        if (ret < 0) {
-                duprintf("Unable to register sockopts.\n");
-                return ret;
-        }
+        if (ret < 0)
+                goto err4;
 
         printk("arp_tables: (C) 2002 David S. Miller\n");
         return 0;
+
+err4:
+        xt_unregister_target(&arpt_error_target);
+err3:
+        xt_unregister_target(&arpt_standard_target);
+err2:
+        xt_proto_fini(NF_ARP);
+err1:
+        return ret;
 }
 
 static void __exit arp_tables_fini(void)
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index fc5bdd5eb7d3..f316ff5fd8a6 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -2239,22 +2239,39 @@ static int __init ip_tables_init(void)
 {
         int ret;
 
-        xt_proto_init(AF_INET);
+        ret = xt_proto_init(AF_INET);
+        if (ret < 0)
+                goto err1;
 
         /* Noone else will be downing sem now, so we won't sleep */
-        xt_register_target(&ipt_standard_target);
-        xt_register_target(&ipt_error_target);
-        xt_register_match(&icmp_matchstruct);
+        ret = xt_register_target(&ipt_standard_target);
+        if (ret < 0)
+                goto err2;
+        ret = xt_register_target(&ipt_error_target);
+        if (ret < 0)
+                goto err3;
+        ret = xt_register_match(&icmp_matchstruct);
+        if (ret < 0)
+                goto err4;
 
         /* Register setsockopt */
         ret = nf_register_sockopt(&ipt_sockopts);
-        if (ret < 0) {
-                duprintf("Unable to register sockopts.\n");
-                return ret;
-        }
+        if (ret < 0)
+                goto err5;
 
         printk("ip_tables: (C) 2000-2006 Netfilter Core Team\n");
         return 0;
+
+err5:
+        xt_unregister_match(&icmp_matchstruct);
+err4:
+        xt_unregister_target(&ipt_error_target);
+err3:
+        xt_unregister_target(&ipt_standard_target);
+err2:
+        xt_proto_fini(AF_INET);
+err1:
+        return ret;
 }
 
 static void __exit ip_tables_fini(void)
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index d7dd7fe7051c..d46fd677fa11 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -115,6 +115,11 @@ static void ulog_send(unsigned int nlgroupnum)
                 del_timer(&ub->timer);
         }
 
+        if (!ub->skb) {
+                DEBUGP("ipt_ULOG: ulog_send: nothing to send\n");
+                return;
+        }
+
         /* last nlmsg needs NLMSG_DONE */
         if (ub->qlen > 1)
                 ub->lastnlh->nlmsg_type = NLMSG_DONE;
diff --git a/net/ipv4/netfilter/ipt_hashlimit.c b/net/ipv4/netfilter/ipt_hashlimit.c
index 6b662449e825..3bd2368e1fc9 100644
--- a/net/ipv4/netfilter/ipt_hashlimit.c
+++ b/net/ipv4/netfilter/ipt_hashlimit.c
@@ -454,15 +454,12 @@ hashlimit_match(const struct sk_buff *skb,
                 dh->rateinfo.credit_cap = user2credits(hinfo->cfg.avg * 
                                                         hinfo->cfg.burst);
                 dh->rateinfo.cost = user2credits(hinfo->cfg.avg);
-
-                spin_unlock_bh(&hinfo->lock);
-                return 1;
+        } else {
+                /* update expiration timeout */
+                dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire);
+                rateinfo_recalc(dh, now);
         }
 
-        /* update expiration timeout */
-        dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire);
-
-        rateinfo_recalc(dh, now);
         if (dh->rateinfo.credit >= dh->rateinfo.cost) {
                 /* We're underlimit. */
                 dh->rateinfo.credit -= dh->rateinfo.cost;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 19bd49d69d9f..b873cbcdd0b8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3157,7 +3157,7 @@ int __init ip_rt_init(void)
                                         rhash_entries,
                                         (num_physpages >= 128 * 1024) ?
                                         15 : 17,
-                                        HASH_HIGHMEM,
+                                        0,
                                         &rt_hash_log,
                                         &rt_hash_mask,
                                         0);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 738dad9f7d49..104af5d5bcbc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3541,7 +3541,8 @@ void tcp_cwnd_application_limited(struct sock *sk)
         if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
             sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
                 /* Limited by application or receiver window. */
-                u32 win_used = max(tp->snd_cwnd_used, 2U);
+                u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
+                u32 win_used = max(tp->snd_cwnd_used, init_win);
                 if (win_used < tp->snd_cwnd) {
                         tp->snd_ssthresh = tcp_current_ssthresh(sk);
                         tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5c08ea20a18d..507adefbc17c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -466,7 +466,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
         if (skb->len != tcp_header_size)
                 tcp_event_data_sent(tp, skb, sk);
 
-        TCP_INC_STATS(TCP_MIB_OUTSEGS);
+        if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
+                TCP_INC_STATS(TCP_MIB_OUTSEGS);
 
         err = icsk->icsk_af_ops->queue_xmit(skb, 0);
         if (likely(err <= 0))
@@ -2157,10 +2158,9 @@ int tcp_connect(struct sock *sk)
         skb_shinfo(buff)->gso_size = 0;
         skb_shinfo(buff)->gso_type = 0;
         buff->csum = 0;
+        tp->snd_nxt = tp->write_seq;
         TCP_SKB_CB(buff)->seq = tp->write_seq++;
         TCP_SKB_CB(buff)->end_seq = tp->write_seq;
-        tp->snd_nxt = tp->write_seq;
-        tp->pushed_seq = tp->write_seq;
 
         /* Send it off. */
         TCP_SKB_CB(buff)->when = tcp_time_stamp;
@@ -2170,6 +2170,12 @@ int tcp_connect(struct sock *sk)
         sk_charge_skb(sk, buff);
         tp->packets_out += tcp_skb_pcount(buff);
         tcp_transmit_skb(sk, buff, 1, GFP_KERNEL);
+
+        /* We change tp->snd_nxt after the tcp_transmit_skb() call
+         * in order to make this packet get counted in tcpOutSegs.
+         */
+        tp->snd_nxt = tp->write_seq;
+        tp->pushed_seq = tp->write_seq;
         TCP_INC_STATS(TCP_MIB_ACTIVEOPENS);
 
         /* Timer for repeating the SYN until an answer. */
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index b3435324b573..dab37d2f65fc 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -130,11 +130,12 @@ static ssize_t tcpprobe_read(struct file *file, char __user *buf,
         error = wait_event_interruptible(tcpw.wait,
                                          __kfifo_len(tcpw.fifo) != 0);
         if (error)
-                return error;
+                goto out_free;
 
         cnt = kfifo_get(tcpw.fifo, tbuf, len);
         error = copy_to_user(buf, tbuf, cnt);
 
+out_free:
         vfree(tbuf);
 
         return error ? error : cnt;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8ea1e36bf8eb..0c5042e7380d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1909,11 +1909,11 @@ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen,
         ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags);
 
         if (!IS_ERR(ifp)) {
-                spin_lock(&ifp->lock);
+                spin_lock_bh(&ifp->lock);
                 ifp->valid_lft = valid_lft;
                 ifp->prefered_lft = prefered_lft;
                 ifp->tstamp = jiffies;
-                spin_unlock(&ifp->lock);
+                spin_unlock_bh(&ifp->lock);
 
                 addrconf_dad_start(ifp, 0);
                 in6_ifa_put(ifp);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 69451af6abe7..4fb47a252913 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1095,7 +1095,7 @@ alloc_new_skb:
                                 skb_prev->csum = csum_sub(skb_prev->csum,
                                                           skb->csum);
                                 data += fraggap;
-                                skb_trim(skb_prev, maxfraglen);
+                                pskb_trim_unique(skb_prev, maxfraglen);
                         }
                         copy = datalen - transhdrlen - fraggap;
                         if (copy < 0) {
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index f26898b00347..c9d6b23cd3f7 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1398,23 +1398,39 @@ static int __init ip6_tables_init(void)
 {
         int ret;
 
-        xt_proto_init(AF_INET6);
+        ret = xt_proto_init(AF_INET6);
+        if (ret < 0)
+                goto err1;
 
         /* Noone else will be downing sem now, so we won't sleep */
-        xt_register_target(&ip6t_standard_target);
-        xt_register_target(&ip6t_error_target);
-        xt_register_match(&icmp6_matchstruct);
+        ret = xt_register_target(&ip6t_standard_target);
+        if (ret < 0)
+                goto err2;
+        ret = xt_register_target(&ip6t_error_target);
+        if (ret < 0)
+                goto err3;
+        ret = xt_register_match(&icmp6_matchstruct);
+        if (ret < 0)
+                goto err4;
 
         /* Register setsockopt */
         ret = nf_register_sockopt(&ip6t_sockopts);
-        if (ret < 0) {
-                duprintf("Unable to register sockopts.\n");
-                xt_proto_fini(AF_INET6);
-                return ret;
-        }
+        if (ret < 0)
+                goto err5;
 
         printk("ip6_tables: (C) 2000-2006 Netfilter Core Team\n");
         return 0;
+
+err5:
+        xt_unregister_match(&icmp6_matchstruct);
+err4:
+        xt_unregister_target(&ip6t_error_target);
+err3:
+        xt_unregister_target(&ip6t_standard_target);
+err2:
+        xt_proto_fini(AF_INET6);
+err1:
+        return ret;
 }
 
 static void __exit ip6_tables_fini(void)
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index aa34ff4b707c..bef3f61569f7 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1642,13 +1642,17 @@ static int ipx_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_ty
         if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
                 goto out;
 
-        ipx             = ipx_hdr(skb);
-        ipx_pktsize     = ntohs(ipx->ipx_pktsize);
+        if (!pskb_may_pull(skb, sizeof(struct ipxhdr)))
+                goto drop;
+
+        ipx_pktsize = ntohs(ipx_hdr(skb)->ipx_pktsize);
         
         /* Too small or invalid header? */
-        if (ipx_pktsize < sizeof(struct ipxhdr) || ipx_pktsize > skb->len)
+        if (ipx_pktsize < sizeof(struct ipxhdr) ||
+            !pskb_may_pull(skb, ipx_pktsize))
                 goto drop;
                         
+        ipx = ipx_hdr(skb);
         if (ipx->ipx_checksum != IPX_NO_CHECKSUM &&
            ipx->ipx_checksum != ipx_cksum(ipx, ipx_pktsize))
                 goto drop;
diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index d504eed416f6..7e6bc41eeb21 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -238,11 +238,13 @@ int lapb_setparms(struct net_device *dev, struct lapb_parms_struct *parms)
                 goto out_put;
 
         if (lapb->state == LAPB_STATE_0) {
-                if (((parms->mode & LAPB_EXTENDED) &&
-                     (parms->window < 1 || parms->window > 127)) ||
-                    (parms->window < 1 || parms->window > 7))
-                        goto out_put;
-
+                if (parms->mode & LAPB_EXTENDED) {
+                        if (parms->window < 1 || parms->window > 127)
+                                goto out_put;
+                } else {
+                        if (parms->window < 1 || parms->window > 7)
+                                goto out_put;
+                }
                 lapb->mode    = parms->mode;
                 lapb->window  = parms->window;
         }
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index d6cfe84d521b..2652ead96c64 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -784,24 +784,20 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
                 copied += used;
                 len -= used;
 
-                if (used + offset < skb->len)
-                        continue;
-
                 if (!(flags & MSG_PEEK)) {
                         sk_eat_skb(sk, skb, 0);
                         *seq = 0;
                 }
+
+                /* For non stream protcols we get one packet per recvmsg call */
+                if (sk->sk_type != SOCK_STREAM)
+                        goto copy_uaddr;
+
+                /* Partial read */
+                if (used + offset < skb->len)
+                        continue;
         } while (len > 0);
 
-        /* 
-         * According to UNIX98, msg_name/msg_namelen are ignored
-         * on connected socket. -ANK
-         * But... af_llc still doesn't have separate sets of methods for
-         * SOCK_DGRAM and SOCK_STREAM :-( So we have to do this test, will
-         * eventually fix this tho :-) -acme
-         */
-        if (sk->sk_type == SOCK_DGRAM)
-                goto copy_uaddr;
 out:
         release_sock(sk);
         return copied;
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index 20c4eb5c1ac6..61cb8cf7d153 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -51,10 +51,10 @@ void llc_save_primitive(struct sock *sk, struct sk_buff* skb, u8 prim)
 {
         struct sockaddr_llc *addr;
 
-        if (skb->sk->sk_type == SOCK_STREAM) /* See UNIX98 */
-                return;
        /* save primitive for use by the user. */
         addr              = llc_ui_skb_cb(skb);
+
+        memset(addr, 0, sizeof(*addr));
         addr->sllc_family = sk->sk_family;
         addr->sllc_arphrd = skb->dev->type;
         addr->sllc_test   = prim == LLC_TEST_PRIM;
@@ -330,6 +330,9 @@ static void llc_sap_mcast(struct llc_sap *sap,
                 if (llc->laddr.lsap != laddr->lsap)
                         continue;
 
+                if (llc->dev != skb->dev)
+                        continue;
+
                 skb1 = skb_clone(skb, GFP_ATOMIC);
                 if (!skb1)
                         break;
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 61cdda4e5d3b..b59d3b2bde21 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -366,6 +366,9 @@ __nfulnl_send(struct nfulnl_instance *inst)
         if (timer_pending(&inst->timer))
                 del_timer(&inst->timer);
 
+        if (!inst->skb)
+                return 0;
+
         if (inst->qlen > 1)
                 inst->lastnlh->nlmsg_type = NLMSG_DONE;
 
diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c
index d8e3891b5f8b..275330fcdaaa 100644
--- a/net/netfilter/xt_string.c
+++ b/net/netfilter/xt_string.c
@@ -37,7 +37,7 @@ static int match(const struct sk_buff *skb,
 
         return (skb_find_text((struct sk_buff *)skb, conf->from_offset, 
                              conf->to_offset, conf->config, &state) 
-                             != UINT_MAX) && !conf->invert;
+                             != UINT_MAX) ^ conf->invert;
 }
 
 #define STRING_TEXT_PRIV(m) ((struct xt_string_info *) m)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index c7844bacbbcb..a19eff12cf78 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -430,7 +430,7 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp)
         }
 #endif
 
-        err = -EINVAL;
+        err = -ENOENT;
         if (ops == NULL)
                 goto err_out;
 
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 7026b0866b7b..00cb388ece03 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -71,7 +71,12 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
         new = detail->alloc();
         if (!new)
                 return NULL;
+        /* must fully initialise 'new', else
+         * we might get lose if we need to
+         * cache_put it soon.
+         */
         cache_init(new);
+        detail->init(new, key);
 
         write_lock(&detail->hash_lock);
 
@@ -85,7 +90,6 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
                         return tmp;
                 }
         }
-        detail->init(new, key);
         new->next = *head;
         *head = new;
         detail->entries++;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 4ba271f892c8..d6409e757219 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -921,26 +921,43 @@ call_transmit(struct rpc_task *task)
         task->tk_status = xprt_prepare_transmit(task);
         if (task->tk_status != 0)
                 return;
+        task->tk_action = call_transmit_status;
         /* Encode here so that rpcsec_gss can use correct sequence number. */
         if (rpc_task_need_encode(task)) {
-                task->tk_rqstp->rq_bytes_sent = 0;
+                BUG_ON(task->tk_rqstp->rq_bytes_sent != 0);
                 call_encode(task);
                 /* Did the encode result in an error condition? */
                 if (task->tk_status != 0)
-                        goto out_nosend;
+                        return;
         }
-        task->tk_action = call_transmit_status;
         xprt_transmit(task);
         if (task->tk_status < 0)
                 return;
-        if (!task->tk_msg.rpc_proc->p_decode) {
-                task->tk_action = rpc_exit_task;
-                rpc_wake_up_task(task);
-        }
-        return;
-out_nosend:
-        /* release socket write lock before attempting to handle error */
-        xprt_abort_transmit(task);
+        /*
+         * On success, ensure that we call xprt_end_transmit() before sleeping
+         * in order to allow access to the socket to other RPC requests.
+         */
+        call_transmit_status(task);
+        if (task->tk_msg.rpc_proc->p_decode != NULL)
+                return;
+        task->tk_action = rpc_exit_task;
+        rpc_wake_up_task(task);
+}
+
+/*
+ * 5a.  Handle cleanup after a transmission
+ */
+static void
+call_transmit_status(struct rpc_task *task)
+{
+        task->tk_action = call_status;
+        /*
+         * Special case: if we've been waiting on the socket's write_space()
+         * callback, then don't call xprt_end_transmit().
+         */
+        if (task->tk_status == -EAGAIN)
+                return;
+        xprt_end_transmit(task);
         rpc_task_force_reencode(task);
 }
 
@@ -992,18 +1009,7 @@ call_status(struct rpc_task *task)
 }
 
 /*
- * 6a.  Handle transmission errors.
- */
-static void
-call_transmit_status(struct rpc_task *task)
-{
-        if (task->tk_status != -EAGAIN)
-                rpc_task_force_reencode(task);
-        call_status(task);
-}
-
-/*
- * 6b.  Handle RPC timeout
+ * 6a.  Handle RPC timeout
  *      We do not release the request slot, so we keep using the
  *      same XID for all retransmits.
  */
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index dc6cb93c8830..a3bd2db2e024 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -667,10 +667,11 @@ rpc_mkdir(char *path, struct rpc_clnt *rpc_client)
                         RPCAUTH_info, RPCAUTH_EOF);
         if (error)
                 goto err_depopulate;
+        dget(dentry);
 out:
         mutex_unlock(&dir->i_mutex);
         rpc_release_path(&nd);
-        return dget(dentry);
+        return dentry;
 err_depopulate:
         rpc_depopulate(dentry);
         __rpc_rmdir(dir, dentry);
@@ -731,10 +732,11 @@ rpc_mkpipe(char *path, void *private, struct rpc_pipe_ops *ops, int flags)
         rpci->flags = flags;
         rpci->ops = ops;
         inode_dir_notify(dir, DN_CREATE);
+        dget(dentry);
 out:
         mutex_unlock(&dir->i_mutex);
         rpc_release_path(&nd);
-        return dget(dentry);
+        return dentry;
 err_dput:
         dput(dentry);
         dentry = ERR_PTR(-ENOMEM);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 313b68d892c6..e8c2bc4977f3 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -707,12 +707,9 @@ out_unlock:
         return err;
 }
 
-void
-xprt_abort_transmit(struct rpc_task *task)
+void xprt_end_transmit(struct rpc_task *task)
 {
-        struct rpc_xprt *xprt = task->tk_xprt;
-
-        xprt_release_write(xprt, task);
+        xprt_release_write(task->tk_xprt, task);
 }
 
 /**
@@ -761,8 +758,6 @@ void xprt_transmit(struct rpc_task *task)
                         task->tk_status = -ENOTCONN;
                 else if (!req->rq_received)
                         rpc_sleep_on(&xprt->pending, task, NULL, xprt_timer);
-
-                xprt->ops->release_xprt(xprt, task);
                 spin_unlock_bh(&xprt->transport_lock);
                 return;
         }
@@ -772,18 +767,8 @@ void xprt_transmit(struct rpc_task *task)
          *       schedq, and being picked up by a parallel run of rpciod().
          */
         task->tk_status = status;
-
-        switch (status) {
-        case -ECONNREFUSED:
+        if (status == -ECONNREFUSED)
                 rpc_sleep_on(&xprt->sending, task, NULL, NULL);
-        case -EAGAIN:
-        case -ENOTCONN:
-                return;
-        default:
-                break;
-        }
-        xprt_release_write(xprt, task);
-        return;
 }
 
 static inline void do_xprt_reserve(struct rpc_task *task)
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index ee678ed13b6f..441bd53f5eca 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -414,6 +414,33 @@ static int xs_tcp_send_request(struct rpc_task *task)
 }
 
 /**
+ * xs_tcp_release_xprt - clean up after a tcp transmission
+ * @xprt: transport
+ * @task: rpc task
+ *
+ * This cleans up if an error causes us to abort the transmission of a request.
+ * In this case, the socket may need to be reset in order to avoid confusing
+ * the server.
+ */
+static void xs_tcp_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
+{
+        struct rpc_rqst *req;
+
+        if (task != xprt->snd_task)
+                return;
+        if (task == NULL)
+                goto out_release;
+        req = task->tk_rqstp;
+        if (req->rq_bytes_sent == 0)
+                goto out_release;
+        if (req->rq_bytes_sent == req->rq_snd_buf.len)
+                goto out_release;
+        set_bit(XPRT_CLOSE_WAIT, &task->tk_xprt->state);
+out_release:
+        xprt_release_xprt(xprt, task);
+}
+
+/**
  * xs_close - close a socket
  * @xprt: transport
  *
@@ -1250,7 +1277,7 @@ static struct rpc_xprt_ops xs_udp_ops = {
 
 static struct rpc_xprt_ops xs_tcp_ops = {
         .reserve_xprt           = xprt_reserve_xprt,
-        .release_xprt           = xprt_release_xprt,
+        .release_xprt           = xs_tcp_release_xprt,
         .set_port               = xs_set_port,
         .connect                = xs_connect,
         .buf_alloc              = rpc_malloc,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f35bc676128c..3da67ca2c3ce 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1134,12 +1134,33 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
 }
 EXPORT_SYMBOL(__xfrm_route_forward);
 
+/* Optimize later using cookies and generation ids. */
+
 static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie)
 {
-        /* If it is marked obsolete, which is how we even get here,
-         * then we have purged it from the policy bundle list and we
-         * did that for a good reason.
+        /* Code (such as __xfrm4_bundle_create()) sets dst->obsolete
+         * to "-1" to force all XFRM destinations to get validated by
+         * dst_ops->check on every use.  We do this because when a
+         * normal route referenced by an XFRM dst is obsoleted we do
+         * not go looking around for all parent referencing XFRM dsts
+         * so that we can invalidate them.  It is just too much work.
+         * Instead we make the checks here on every use.  For example:
+         *
+         *      XFRM dst A --> IPv4 dst X
+         *
+         * X is the "xdst->route" of A (X is also the "dst->path" of A
+         * in this example).  If X is marked obsolete, "A" will not
+         * notice.  That's what we are validating here via the
+         * stale_bundle() check.
+         *
+         * When a policy's bundle is pruned, we dst_free() the XFRM
+         * dst which causes it's ->obsolete field to be set to a
+         * positive non-zero integer.  If an XFRM dst has been pruned
+         * like this, we want to force a new route lookup.
          */
+        if (dst->obsolete < 0 && !stale_bundle(dst))
+                return dst;
+
         return NULL;
 }