Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-3.6

Conflicts:
	drivers/net/benet/be_main.c

24 files changed, 307 insertions, 176 deletions

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 718d635d3379..b2274d1fd605 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -119,6 +119,9 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
 
         grp->nr_vlans--;
 
+        if (vlan->flags & VLAN_FLAG_GVRP)
+                vlan_gvrp_request_leave(dev);
+
         vlan_group_set_device(grp, vlan_id, NULL);
         /* Because unregister_netdevice_queue() makes sure at least one rcu
          * grace period is respected before device freeing,
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index d174c312b7f1..58f8010e1aef 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -314,9 +314,6 @@ static int vlan_dev_stop(struct net_device *dev)
         struct vlan_dev_info *vlan = vlan_dev_info(dev);
         struct net_device *real_dev = vlan->real_dev;
 
-        if (vlan->flags & VLAN_FLAG_GVRP)
-                vlan_gvrp_request_leave(dev);
-
         dev_mc_unsync(real_dev, dev);
         dev_uc_unsync(real_dev, dev);
         if (dev->flags & IFF_ALLMULTI)
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 893669caa8de..1a92b369c820 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1766,7 +1766,7 @@ static int compat_table_info(const struct ebt_table_info *info,
 
         newinfo->entries_size = size;
 
-        xt_compat_init_offsets(AF_INET, info->nentries);
+        xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries);
         return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
                                                         entries, newinfo);
 }
@@ -1882,7 +1882,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt,
         struct xt_match *match;
         struct xt_target *wt;
         void *dst = NULL;
-        int off, pad = 0, ret = 0;
+        int off, pad = 0;
         unsigned int size_kern, entry_offset, match_size = mwt->match_size;
 
         strlcpy(name, mwt->u.name, sizeof(name));
@@ -1935,13 +1935,6 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt,
                 break;
         }
 
-        if (!dst) {
-                ret = xt_compat_add_offset(NFPROTO_BRIDGE, entry_offset,
-                                        off + ebt_compat_entry_padsize());
-                if (ret < 0)
-                        return ret;
-        }
-
         state->buf_kern_offset += match_size + off;
         state->buf_user_offset += match_size;
         pad = XT_ALIGN(size_kern) - size_kern;
@@ -2016,50 +2009,6 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32,
         return growth;
 }
 
-#define EBT_COMPAT_WATCHER_ITERATE(e, fn, args...)          \
-({                                                          \
-        unsigned int __i;                                   \
-        int __ret = 0;                                      \
-        struct compat_ebt_entry_mwt *__watcher;             \
-                                                            \
-        for (__i = e->watchers_offset;                      \
-             __i < (e)->target_offset;                      \
-             __i += __watcher->watcher_size +               \
-             sizeof(struct compat_ebt_entry_mwt)) {         \
-                __watcher = (void *)(e) + __i;              \
-                __ret = fn(__watcher , ## args);            \
-                if (__ret != 0)                             \
-                        break;                              \
-        }                                                   \
-        if (__ret == 0) {                                   \
-                if (__i != (e)->target_offset)              \
-                        __ret = -EINVAL;                    \
-        }                                                   \
-        __ret;                                              \
-})
-
-#define EBT_COMPAT_MATCH_ITERATE(e, fn, args...)            \
-({                                                          \
-        unsigned int __i;                                   \
-        int __ret = 0;                                      \
-        struct compat_ebt_entry_mwt *__match;               \
-                                                            \
-        for (__i = sizeof(struct ebt_entry);                \
-             __i < (e)->watchers_offset;                    \
-             __i += __match->match_size +                   \
-             sizeof(struct compat_ebt_entry_mwt)) {         \
-                __match = (void *)(e) + __i;                \
-                __ret = fn(__match , ## args);              \
-                if (__ret != 0)                             \
-                        break;                              \
-        }                                                   \
-        if (__ret == 0) {                                   \
-                if (__i != (e)->watchers_offset)            \
-                        __ret = -EINVAL;                    \
-        }                                                   \
-        __ret;                                              \
-})
-
 /* called for all ebt_entry structures. */
 static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base,
                           unsigned int *total,
@@ -2132,6 +2081,14 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base,
                 }
         }
 
+        if (state->buf_kern_start == NULL) {
+                unsigned int offset = buf_start - (char *) base;
+
+                ret = xt_compat_add_offset(NFPROTO_BRIDGE, offset, new_offset);
+                if (ret < 0)
+                        return ret;
+        }
+
         startoff = state->buf_user_offset - startoff;
 
         BUG_ON(*total < startoff);
@@ -2240,6 +2197,7 @@ static int compat_do_replace(struct net *net, void __user *user,
 
         xt_compat_lock(NFPROTO_BRIDGE);
 
+        xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
         ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
         if (ret < 0)
                 goto out_unlock;
diff --git a/net/core/dev.c b/net/core/dev.c
index 44ef8f8998ca..75898a32c038 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1284,11 +1284,13 @@ static int dev_close_many(struct list_head *head)
  */
 int dev_close(struct net_device *dev)
 {
-        LIST_HEAD(single);
+        if (dev->flags & IFF_UP) {
+                LIST_HEAD(single);
 
-        list_add(&dev->unreg_list, &single);
-        dev_close_many(&single);
-        list_del(&single);
+                list_add(&dev->unreg_list, &single);
+                dev_close_many(&single);
+                list_del(&single);
+        }
         return 0;
 }
 EXPORT_SYMBOL(dev_close);
diff --git a/net/dccp/options.c b/net/dccp/options.c
index f06ffcfc8d71..4b2ab657ac8e 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -123,6 +123,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
                 case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R:
                         if (pkt_type == DCCP_PKT_DATA)      /* RFC 4340, 6 */
                                 break;
+                        if (len == 0)
+                                goto out_invalid_option;
                         rc = dccp_feat_parse_options(sk, dreq, mandatory, opt,
                                                     *value, value + 1, len - 1);
                         if (rc)
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 34340c9c95fa..f376b05cca81 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -93,6 +93,7 @@ struct bictcp {
         u32     ack_cnt;        /* number of acks */
         u32     tcp_cwnd;       /* estimated tcp cwnd */
 #define ACK_RATIO_SHIFT 4
+#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT)
         u16     delayed_ack;    /* estimate the ratio of Packets/ACKs << 4 */
         u8      sample_cnt;     /* number of samples to decide curr_rtt */
         u8      found;          /* the exit point is found? */
@@ -398,8 +399,12 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
         u32 delay;
 
         if (icsk->icsk_ca_state == TCP_CA_Open) {
-                cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
-                ca->delayed_ack += cnt;
+                u32 ratio = ca->delayed_ack;
+
+                ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
+                ratio += cnt;
+
+                ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT);
         }
 
         /* Some calls are for duplicates without timetamps */
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 571aa96a175c..2d51840e53a1 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -69,7 +69,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(xfrm4_prepare_output);
 
-static int xfrm4_output_finish(struct sk_buff *skb)
+int xfrm4_output_finish(struct sk_buff *skb)
 {
 #ifdef CONFIG_NETFILTER
         if (!skb_dst(skb)->xfrm) {
@@ -86,7 +86,11 @@ static int xfrm4_output_finish(struct sk_buff *skb)
 
 int xfrm4_output(struct sk_buff *skb)
 {
+        struct dst_entry *dst = skb_dst(skb);
+        struct xfrm_state *x = dst->xfrm;
+
         return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb,
-                            NULL, skb_dst(skb)->dev, xfrm4_output_finish,
+                            NULL, dst->dev,
+                            x->outer_mode->afinfo->output_finish,
                             !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index ea983ae96ae6..d9ac0a0058b5 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -78,6 +78,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = {
         .init_tempsel           = __xfrm4_init_tempsel,
         .init_temprop           = xfrm4_init_temprop,
         .output                 = xfrm4_output,
+        .output_finish          = xfrm4_output_finish,
         .extract_input          = xfrm4_extract_input,
         .extract_output         = xfrm4_extract_output,
         .transport_finish       = xfrm4_transport_finish,
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 28e74488a329..a5a4c5dd5396 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -45,6 +45,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
         int tcphoff, needs_ack;
         const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
         struct ipv6hdr *ip6h;
+#define DEFAULT_TOS_VALUE       0x0U
+        const __u8 tclass = DEFAULT_TOS_VALUE;
         struct dst_entry *dst = NULL;
         u8 proto;
         struct flowi6 fl6;
@@ -124,7 +126,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
         skb_put(nskb, sizeof(struct ipv6hdr));
         skb_reset_network_header(nskb);
         ip6h = ipv6_hdr(nskb);
-        ip6h->version = 6;
+        *(__be32 *)ip6h =  htonl(0x60000000 | (tclass << 20));
         ip6h->hop_limit = ip6_dst_hoplimit(dst);
         ip6h->nexthdr = IPPROTO_TCP;
         ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr);
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 8e688b3de9ab..49a91c5f5623 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -79,7 +79,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(xfrm6_prepare_output);
 
-static int xfrm6_output_finish(struct sk_buff *skb)
+int xfrm6_output_finish(struct sk_buff *skb)
 {
 #ifdef CONFIG_NETFILTER
         IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
@@ -97,9 +97,9 @@ static int __xfrm6_output(struct sk_buff *skb)
         if ((x && x->props.mode == XFRM_MODE_TUNNEL) &&
             ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
                 dst_allfrag(skb_dst(skb)))) {
-                        return ip6_fragment(skb, xfrm6_output_finish);
+                        return ip6_fragment(skb, x->outer_mode->afinfo->output_finish);
         }
-        return xfrm6_output_finish(skb);
+        return x->outer_mode->afinfo->output_finish(skb);
 }
 
 int xfrm6_output(struct sk_buff *skb)
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index afe941e9415c..248f0b2a7ee9 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -178,6 +178,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = {
         .tmpl_sort              = __xfrm6_tmpl_sort,
         .state_sort             = __xfrm6_state_sort,
         .output                 = xfrm6_output,
+        .output_finish          = xfrm6_output_finish,
         .extract_input          = xfrm6_extract_input,
         .extract_output         = xfrm6_extract_output,
         .transport_finish       = xfrm6_transport_finish,
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 2dc6de13ac18..51f3af7c4743 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -576,7 +576,7 @@ static const struct file_operations ip_vs_app_fops = {
 };
 #endif
 
-static int __net_init __ip_vs_app_init(struct net *net)
+int __net_init __ip_vs_app_init(struct net *net)
 {
         struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -585,26 +585,17 @@ static int __net_init __ip_vs_app_init(struct net *net)
         return 0;
 }
 
-static void __net_exit __ip_vs_app_cleanup(struct net *net)
+void __net_exit __ip_vs_app_cleanup(struct net *net)
 {
         proc_net_remove(net, "ip_vs_app");
 }
 
-static struct pernet_operations ip_vs_app_ops = {
-        .init = __ip_vs_app_init,
-        .exit = __ip_vs_app_cleanup,
-};
-
 int __init ip_vs_app_init(void)
 {
-        int rv;
-
-        rv = register_pernet_subsys(&ip_vs_app_ops);
-        return rv;
+        return 0;
 }
 
 
 void ip_vs_app_cleanup(void)
 {
-        unregister_pernet_subsys(&ip_vs_app_ops);
 }
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index c97bd45975be..d3fd91bbba49 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1258,22 +1258,17 @@ int __net_init __ip_vs_conn_init(struct net *net)
         return 0;
 }
 
-static void __net_exit __ip_vs_conn_cleanup(struct net *net)
+void __net_exit __ip_vs_conn_cleanup(struct net *net)
 {
         /* flush all the connection entries first */
         ip_vs_conn_flush(net);
         proc_net_remove(net, "ip_vs_conn");
         proc_net_remove(net, "ip_vs_conn_sync");
 }
-static struct pernet_operations ipvs_conn_ops = {
-        .init = __ip_vs_conn_init,
-        .exit = __ip_vs_conn_cleanup,
-};
 
 int __init ip_vs_conn_init(void)
 {
         int idx;
-        int retc;
 
         /* Compute size and mask */
         ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
@@ -1309,17 +1304,14 @@ int __init ip_vs_conn_init(void)
                 rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
         }
 
-        retc = register_pernet_subsys(&ipvs_conn_ops);
-
         /* calculate the random value for connection hash */
         get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd));
 
-        return retc;
+        return 0;
 }
 
 void ip_vs_conn_cleanup(void)
 {
-        unregister_pernet_subsys(&ipvs_conn_ops);
         /* Release the empty cache */
         kmem_cache_destroy(ip_vs_conn_cachep);
         vfree(ip_vs_conn_tab);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 07accf6b2401..a74dae6c5dbc 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1113,6 +1113,9 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
                 return NF_ACCEPT;
 
         net = skb_net(skb);
+        if (!net_ipvs(net)->enable)
+                return NF_ACCEPT;
+
         ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 #ifdef CONFIG_IP_VS_IPV6
         if (af == AF_INET6) {
@@ -1343,6 +1346,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
                 return NF_ACCEPT; /* The packet looks wrong, ignore */
 
         net = skb_net(skb);
+
         pd = ip_vs_proto_data_get(net, cih->protocol);
         if (!pd)
                 return NF_ACCEPT;
@@ -1529,6 +1533,11 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
                               IP_VS_DBG_ADDR(af, &iph.daddr), hooknum);
                 return NF_ACCEPT;
         }
+        /* ipvs enabled in this netns ? */
+        net = skb_net(skb);
+        if (!net_ipvs(net)->enable)
+                return NF_ACCEPT;
+
         ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 
         /* Bad... Do not break raw sockets */
@@ -1562,7 +1571,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
                         ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
                 }
 
-        net = skb_net(skb);
         /* Protocol supported? */
         pd = ip_vs_proto_data_get(net, iph.protocol);
         if (unlikely(!pd))
@@ -1588,7 +1596,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
         }
 
         IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
-        net = skb_net(skb);
         ipvs = net_ipvs(net);
         /* Check the server status */
         if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
@@ -1743,10 +1750,16 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
                    int (*okfn)(struct sk_buff *))
 {
         int r;
+        struct net *net;
 
         if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
                 return NF_ACCEPT;
 
+        /* ipvs enabled in this netns ? */
+        net = skb_net(skb);
+        if (!net_ipvs(net)->enable)
+                return NF_ACCEPT;
+
         return ip_vs_in_icmp(skb, &r, hooknum);
 }
 
@@ -1757,10 +1770,16 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
                       int (*okfn)(struct sk_buff *))
 {
         int r;
+        struct net *net;
 
         if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6)
                 return NF_ACCEPT;
 
+        /* ipvs enabled in this netns ? */
+        net = skb_net(skb);
+        if (!net_ipvs(net)->enable)
+                return NF_ACCEPT;
+
         return ip_vs_in_icmp_v6(skb, &r, hooknum);
 }
 #endif
@@ -1884,19 +1903,70 @@ static int __net_init __ip_vs_init(struct net *net)
                 pr_err("%s(): no memory.\n", __func__);
                 return -ENOMEM;
         }
+        /* Hold the beast until a service is registerd */
+        ipvs->enable = 0;
         ipvs->net = net;
         /* Counters used for creating unique names */
         ipvs->gen = atomic_read(&ipvs_netns_cnt);
         atomic_inc(&ipvs_netns_cnt);
         net->ipvs = ipvs;
+
+        if (__ip_vs_estimator_init(net) < 0)
+                goto estimator_fail;
+
+        if (__ip_vs_control_init(net) < 0)
+                goto control_fail;
+
+        if (__ip_vs_protocol_init(net) < 0)
+                goto protocol_fail;
+
+        if (__ip_vs_app_init(net) < 0)
+                goto app_fail;
+
+        if (__ip_vs_conn_init(net) < 0)
+                goto conn_fail;
+
+        if (__ip_vs_sync_init(net) < 0)
+                goto sync_fail;
+
         printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n",
                          sizeof(struct netns_ipvs), ipvs->gen);
         return 0;
+/*
+ * Error handling
+ */
+
+sync_fail:
+        __ip_vs_conn_cleanup(net);
+conn_fail:
+        __ip_vs_app_cleanup(net);
+app_fail:
+        __ip_vs_protocol_cleanup(net);
+protocol_fail:
+        __ip_vs_control_cleanup(net);
+control_fail:
+        __ip_vs_estimator_cleanup(net);
+estimator_fail:
+        return -ENOMEM;
 }
 
 static void __net_exit __ip_vs_cleanup(struct net *net)
 {
-        IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen);
+        __ip_vs_service_cleanup(net);   /* ip_vs_flush() with locks */
+        __ip_vs_conn_cleanup(net);
+        __ip_vs_app_cleanup(net);
+        __ip_vs_protocol_cleanup(net);
+        __ip_vs_control_cleanup(net);
+        __ip_vs_estimator_cleanup(net);
+        IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen);
+}
+
+static void __net_exit __ip_vs_dev_cleanup(struct net *net)
+{
+        EnterFunction(2);
+        net_ipvs(net)->enable = 0;      /* Disable packet reception */
+        __ip_vs_sync_cleanup(net);
+        LeaveFunction(2);
 }
 
 static struct pernet_operations ipvs_core_ops = {
@@ -1906,6 +1976,10 @@ static struct pernet_operations ipvs_core_ops = {
         .size = sizeof(struct netns_ipvs),
 };
 
+static struct pernet_operations ipvs_core_dev_ops = {
+        .exit = __ip_vs_dev_cleanup,
+};
+
 /*
  *      Initialize IP Virtual Server
  */
@@ -1913,10 +1987,6 @@ static int __init ip_vs_init(void)
 {
         int ret;
 
-        ret = register_pernet_subsys(&ipvs_core_ops);   /* Alloc ip_vs struct */
-        if (ret < 0)
-                return ret;
-
         ip_vs_estimator_init();
         ret = ip_vs_control_init();
         if (ret < 0) {
@@ -1944,15 +2014,28 @@ static int __init ip_vs_init(void)
                 goto cleanup_conn;
         }
 
+        ret = register_pernet_subsys(&ipvs_core_ops);   /* Alloc ip_vs struct */
+        if (ret < 0)
+                goto cleanup_sync;
+
+        ret = register_pernet_device(&ipvs_core_dev_ops);
+        if (ret < 0)
+                goto cleanup_sub;
+
         ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
         if (ret < 0) {
                 pr_err("can't register hooks.\n");
-                goto cleanup_sync;
+                goto cleanup_dev;
         }
 
         pr_info("ipvs loaded.\n");
+
         return ret;
 
+cleanup_dev:
+        unregister_pernet_device(&ipvs_core_dev_ops);
+cleanup_sub:
+        unregister_pernet_subsys(&ipvs_core_ops);
 cleanup_sync:
         ip_vs_sync_cleanup();
   cleanup_conn:
@@ -1964,20 +2047,20 @@ cleanup_sync:
         ip_vs_control_cleanup();
   cleanup_estimator:
         ip_vs_estimator_cleanup();
-        unregister_pernet_subsys(&ipvs_core_ops);       /* free ip_vs struct */
         return ret;
 }
 
 static void __exit ip_vs_cleanup(void)
 {
         nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
+        unregister_pernet_device(&ipvs_core_dev_ops);
+        unregister_pernet_subsys(&ipvs_core_ops);       /* free ip_vs struct */
         ip_vs_sync_cleanup();
         ip_vs_conn_cleanup();
         ip_vs_app_cleanup();
         ip_vs_protocol_cleanup();
         ip_vs_control_cleanup();
         ip_vs_estimator_cleanup();
-        unregister_pernet_subsys(&ipvs_core_ops);       /* free ip_vs struct */
         pr_info("ipvs unloaded.\n");
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 9930f340908a..89842f06931d 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -69,6 +69,11 @@ int ip_vs_get_debug_level(void)
 }
 #endif
 
+
+/*  Protos */
+static void __ip_vs_del_service(struct ip_vs_service *svc);
+
+
 #ifdef CONFIG_IP_VS_IPV6
 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */
 static int __ip_vs_addr_is_local_v6(struct net *net,
@@ -1214,6 +1219,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
         write_unlock_bh(&__ip_vs_svc_lock);
 
         *svc_p = svc;
+        /* Now there is a service - full throttle */
+        ipvs->enable = 1;
         return 0;
 
 
@@ -1472,6 +1479,84 @@ static int ip_vs_flush(struct net *net)
         return 0;
 }
 
+/*
+ *      Delete service by {netns} in the service table.
+ *      Called by __ip_vs_cleanup()
+ */
+void __ip_vs_service_cleanup(struct net *net)
+{
+        EnterFunction(2);
+        /* Check for "full" addressed entries */
+        mutex_lock(&__ip_vs_mutex);
+        ip_vs_flush(net);
+        mutex_unlock(&__ip_vs_mutex);
+        LeaveFunction(2);
+}
+/*
+ * Release dst hold by dst_cache
+ */
+static inline void
+__ip_vs_dev_reset(struct ip_vs_dest *dest, struct net_device *dev)
+{
+        spin_lock_bh(&dest->dst_lock);
+        if (dest->dst_cache && dest->dst_cache->dev == dev) {
+                IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n",
+                              dev->name,
+                              IP_VS_DBG_ADDR(dest->af, &dest->addr),
+                              ntohs(dest->port),
+                              atomic_read(&dest->refcnt));
+                ip_vs_dst_reset(dest);
+        }
+        spin_unlock_bh(&dest->dst_lock);
+
+}
+/*
+ * Netdev event receiver
+ * Currently only NETDEV_UNREGISTER is handled, i.e. if we hold a reference to
+ * a device that is "unregister" it must be released.
+ */
+static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
+                            void *ptr)
+{
+        struct net_device *dev = ptr;
+        struct net *net = dev_net(dev);
+        struct ip_vs_service *svc;
+        struct ip_vs_dest *dest;
+        unsigned int idx;
+
+        if (event != NETDEV_UNREGISTER)
+                return NOTIFY_DONE;
+        IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name);
+        EnterFunction(2);
+        mutex_lock(&__ip_vs_mutex);
+        for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
+                list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
+                        if (net_eq(svc->net, net)) {
+                                list_for_each_entry(dest, &svc->destinations,
+                                                    n_list) {
+                                        __ip_vs_dev_reset(dest, dev);
+                                }
+                        }
+                }
+
+                list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
+                        if (net_eq(svc->net, net)) {
+                                list_for_each_entry(dest, &svc->destinations,
+                                                    n_list) {
+                                        __ip_vs_dev_reset(dest, dev);
+                                }
+                        }
+
+                }
+        }
+
+        list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) {
+                __ip_vs_dev_reset(dest, dev);
+        }
+        mutex_unlock(&__ip_vs_mutex);
+        LeaveFunction(2);
+        return NOTIFY_DONE;
+}
 
 /*
  *      Zero counters in a service or all services
@@ -3585,6 +3670,10 @@ void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { }
 
 #endif
 
+static struct notifier_block ip_vs_dst_notifier = {
+        .notifier_call = ip_vs_dst_event,
+};
+
 int __net_init __ip_vs_control_init(struct net *net)
 {
         int idx;
@@ -3623,7 +3712,7 @@ err:
         return -ENOMEM;
 }
 
-static void __net_exit __ip_vs_control_cleanup(struct net *net)
+void __net_exit __ip_vs_control_cleanup(struct net *net)
 {
         struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -3636,11 +3725,6 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
         free_percpu(ipvs->tot_stats.cpustats);
 }
 
-static struct pernet_operations ipvs_control_ops = {
-        .init = __ip_vs_control_init,
-        .exit = __ip_vs_control_cleanup,
-};
-
 int __init ip_vs_control_init(void)
 {
         int idx;
@@ -3654,33 +3738,32 @@ int __init ip_vs_control_init(void)
                 INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]);
         }
 
-        ret = register_pernet_subsys(&ipvs_control_ops);
-        if (ret) {
-                pr_err("cannot register namespace.\n");
-                goto err;
-        }
-
         smp_wmb();      /* Do we really need it now ? */
 
         ret = nf_register_sockopt(&ip_vs_sockopts);
         if (ret) {
                 pr_err("cannot register sockopt.\n");
-                goto err_net;
+                goto err_sock;
         }
 
         ret = ip_vs_genl_register();
         if (ret) {
                 pr_err("cannot register Generic Netlink interface.\n");
-                nf_unregister_sockopt(&ip_vs_sockopts);
-                goto err_net;
+                goto err_genl;
         }
 
+        ret = register_netdevice_notifier(&ip_vs_dst_notifier);
+        if (ret < 0)
+                goto err_notf;
+
         LeaveFunction(2);
         return 0;
 
-err_net:
-        unregister_pernet_subsys(&ipvs_control_ops);
-err:
+err_notf:
+        ip_vs_genl_unregister();
+err_genl:
+        nf_unregister_sockopt(&ip_vs_sockopts);
+err_sock:
         return ret;
 }
 
@@ -3688,7 +3771,6 @@ err:
 void ip_vs_control_cleanup(void)
 {
         EnterFunction(2);
-        unregister_pernet_subsys(&ipvs_control_ops);
         ip_vs_genl_unregister();
         nf_unregister_sockopt(&ip_vs_sockopts);
         LeaveFunction(2);
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 8c8766ca56ad..508cce98777c 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -192,7 +192,7 @@ void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
         dst->outbps = (e->outbps + 0xF) >> 5;
 }
 
-static int __net_init __ip_vs_estimator_init(struct net *net)
+int __net_init __ip_vs_estimator_init(struct net *net)
 {
         struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -203,24 +203,16 @@ static int __net_init __ip_vs_estimator_init(struct net *net)
         return 0;
 }
 
-static void __net_exit __ip_vs_estimator_exit(struct net *net)
+void __net_exit __ip_vs_estimator_cleanup(struct net *net)
 {
         del_timer_sync(&net_ipvs(net)->est_timer);
 }
-static struct pernet_operations ip_vs_app_ops = {
-        .init = __ip_vs_estimator_init,
-        .exit = __ip_vs_estimator_exit,
-};
 
 int __init ip_vs_estimator_init(void)
 {
-        int rv;
-
-        rv = register_pernet_subsys(&ip_vs_app_ops);
-        return rv;
+        return 0;
 }
 
 void ip_vs_estimator_cleanup(void)
 {
-        unregister_pernet_subsys(&ip_vs_app_ops);
 }
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 17484a4416ef..eb86028536fc 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -316,7 +316,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
 /*
  * per network name-space init
  */
-static int __net_init __ip_vs_protocol_init(struct net *net)
+int __net_init __ip_vs_protocol_init(struct net *net)
 {
 #ifdef CONFIG_IP_VS_PROTO_TCP
         register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp);
@@ -336,7 +336,7 @@ static int __net_init __ip_vs_protocol_init(struct net *net)
         return 0;
 }
 
-static void __net_exit __ip_vs_protocol_cleanup(struct net *net)
+void __net_exit __ip_vs_protocol_cleanup(struct net *net)
 {
         struct netns_ipvs *ipvs = net_ipvs(net);
         struct ip_vs_proto_data *pd;
@@ -349,11 +349,6 @@ static void __net_exit __ip_vs_protocol_cleanup(struct net *net)
         }
 }
 
-static struct pernet_operations ipvs_proto_ops = {
-        .init = __ip_vs_protocol_init,
-        .exit = __ip_vs_protocol_cleanup,
-};
-
 int __init ip_vs_protocol_init(void)
 {
         char protocols[64];
@@ -382,7 +377,6 @@ int __init ip_vs_protocol_init(void)
         REGISTER_PROTOCOL(&ip_vs_protocol_esp);
 #endif
         pr_info("Registered protocols (%s)\n", &protocols[2]);
-        return register_pernet_subsys(&ipvs_proto_ops);
 
         return 0;
 }
@@ -393,7 +387,6 @@ void ip_vs_protocol_cleanup(void)
         struct ip_vs_protocol *pp;
         int i;
 
-        unregister_pernet_subsys(&ipvs_proto_ops);
         /* unregister all the ipvs protocols */
         for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
                 while ((pp = ip_vs_proto_table[i]) != NULL)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3e7961e85e9c..e292e5bddc70 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1303,13 +1303,18 @@ static struct socket *make_send_sock(struct net *net)
         struct socket *sock;
         int result;
 
-        /* First create a socket */
-        result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1);
+        /* First create a socket move it to right name space later */
+        result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
         if (result < 0) {
                 pr_err("Error during creation of socket; terminating\n");
                 return ERR_PTR(result);
         }
-
+        /*
+         * Kernel sockets that are a part of a namespace, should not
+         * hold a reference to a namespace in order to allow to stop it.
+         * After sk_change_net should be released using sk_release_kernel.
+         */
+        sk_change_net(sock->sk, net);
         result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn);
         if (result < 0) {
                 pr_err("Error setting outbound mcast interface\n");
@@ -1334,8 +1339,8 @@ static struct socket *make_send_sock(struct net *net)
 
         return sock;
 
-  error:
-        sock_release(sock);
+error:
+        sk_release_kernel(sock->sk);
         return ERR_PTR(result);
 }
 
@@ -1350,12 +1355,17 @@ static struct socket *make_receive_sock(struct net *net)
         int result;
 
         /* First create a socket */
-        result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1);
+        result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
         if (result < 0) {
                 pr_err("Error during creation of socket; terminating\n");
                 return ERR_PTR(result);
         }
-
+        /*
+         * Kernel sockets that are a part of a namespace, should not
+         * hold a reference to a namespace in order to allow to stop it.
+         * After sk_change_net should be released using sk_release_kernel.
+         */
+        sk_change_net(sock->sk, net);
         /* it is equivalent to the REUSEADDR option in user-space */
         sock->sk->sk_reuse = 1;
 
@@ -1377,8 +1387,8 @@ static struct socket *make_receive_sock(struct net *net)
 
         return sock;
 
-  error:
-        sock_release(sock);
+error:
+        sk_release_kernel(sock->sk);
         return ERR_PTR(result);
 }
 
@@ -1473,7 +1483,7 @@ static int sync_thread_master(void *data)
                 ip_vs_sync_buff_release(sb);
 
         /* release the sending multicast socket */
-        sock_release(tinfo->sock);
+        sk_release_kernel(tinfo->sock->sk);
         kfree(tinfo);
 
         return 0;
@@ -1513,7 +1523,7 @@ static int sync_thread_backup(void *data)
         }
 
         /* release the sending multicast socket */
-        sock_release(tinfo->sock);
+        sk_release_kernel(tinfo->sock->sk);
         kfree(tinfo->buf);
         kfree(tinfo);
 
@@ -1601,7 +1611,7 @@ outtinfo:
 outbuf:
         kfree(buf);
 outsocket:
-        sock_release(sock);
+        sk_release_kernel(sock->sk);
 out:
         return result;
 }
@@ -1610,6 +1620,7 @@ out:
 int stop_sync_thread(struct net *net, int state)
 {
         struct netns_ipvs *ipvs = net_ipvs(net);
+        int retc = -EINVAL;
 
         IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
 
@@ -1629,7 +1640,7 @@ int stop_sync_thread(struct net *net, int state)
                 spin_lock_bh(&ipvs->sync_lock);
                 ipvs->sync_state &= ~IP_VS_STATE_MASTER;
                 spin_unlock_bh(&ipvs->sync_lock);
-                kthread_stop(ipvs->master_thread);
+                retc = kthread_stop(ipvs->master_thread);
                 ipvs->master_thread = NULL;
         } else if (state == IP_VS_STATE_BACKUP) {
                 if (!ipvs->backup_thread)
@@ -1639,22 +1650,20 @@ int stop_sync_thread(struct net *net, int state)
                         task_pid_nr(ipvs->backup_thread));
 
                 ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
-                kthread_stop(ipvs->backup_thread);
+                retc = kthread_stop(ipvs->backup_thread);
                 ipvs->backup_thread = NULL;
-        } else {
-                return -EINVAL;
         }
 
         /* decrease the module use count */
         ip_vs_use_count_dec();
 
-        return 0;
+        return retc;
 }
 
 /*
  * Initialize data struct for each netns
  */
-static int __net_init __ip_vs_sync_init(struct net *net)
+int __net_init __ip_vs_sync_init(struct net *net)
 {
         struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -1668,24 +1677,24 @@ static int __net_init __ip_vs_sync_init(struct net *net)
         return 0;
 }
 
-static void __ip_vs_sync_cleanup(struct net *net)
+void __ip_vs_sync_cleanup(struct net *net)
 {
-        stop_sync_thread(net, IP_VS_STATE_MASTER);
-        stop_sync_thread(net, IP_VS_STATE_BACKUP);
-}
+        int retc;
 
-static struct pernet_operations ipvs_sync_ops = {
-        .init = __ip_vs_sync_init,
-        .exit = __ip_vs_sync_cleanup,
-};
+        retc = stop_sync_thread(net, IP_VS_STATE_MASTER);
+        if (retc && retc != -ESRCH)
+                pr_err("Failed to stop Master Daemon\n");
 
+        retc = stop_sync_thread(net, IP_VS_STATE_BACKUP);
+        if (retc && retc != -ESRCH)
+                pr_err("Failed to stop Backup Daemon\n");
+}
 
 int __init ip_vs_sync_init(void)
 {
-        return register_pernet_subsys(&ipvs_sync_ops);
+        return 0;
 }
 
 void ip_vs_sync_cleanup(void)
 {
-        unregister_pernet_subsys(&ipvs_sync_ops);
 }
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 30bf8a167fc8..482e90c61850 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1334,6 +1334,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
         struct nf_conn *ct;
         int err = -EINVAL;
         struct nf_conntrack_helper *helper;
+        struct nf_conn_tstamp *tstamp;
 
         ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC);
         if (IS_ERR(ct))
@@ -1451,6 +1452,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
                 __set_bit(IPS_EXPECTED_BIT, &ct->status);
                 ct->master = master_ct;
         }
+        tstamp = nf_conn_tstamp_find(ct);
+        if (tstamp)
+                tstamp->start = ktime_to_ns(ktime_get_real());
 
         add_timer(&ct->timeout);
         nf_conntrack_hash_insert(ct);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 52959efca858..b0869fe3633b 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -455,6 +455,7 @@ void xt_compat_flush_offsets(u_int8_t af)
                 vfree(xt[af].compat_tab);
                 xt[af].compat_tab = NULL;
                 xt[af].number = 0;
+                xt[af].cur = 0;
         }
 }
 EXPORT_SYMBOL_GPL(xt_compat_flush_offsets);
@@ -473,8 +474,7 @@ int xt_compat_calc_jump(u_int8_t af, unsigned int offset)
                 else
                         return mid ? tmp[mid - 1].delta : 0;
         }
-        WARN_ON_ONCE(1);
-        return 0;
+        return left ? tmp[left - 1].delta : 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_calc_jump);
 
diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c
index 0a229191e55b..ae8271652efa 100644
--- a/net/netfilter/xt_DSCP.c
+++ b/net/netfilter/xt_DSCP.c
@@ -99,7 +99,7 @@ tos_tg6(struct sk_buff *skb, const struct xt_action_param *par)
         u_int8_t orig, nv;
 
         orig = ipv6_get_dsfield(iph);
-        nv   = (orig & info->tos_mask) ^ info->tos_value;
+        nv   = (orig & ~info->tos_mask) ^ info->tos_value;
 
         if (orig != nv) {
                 if (!skb_make_writable(skb, sizeof(struct iphdr)))
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index 481a86fdc409..61805d7b38aa 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -272,11 +272,6 @@ static int conntrack_mt_check(const struct xt_mtchk_param *par)
 {
         int ret;
 
-        if (strcmp(par->table, "raw") == 0) {
-                pr_info("state is undetermined at the time of raw table\n");
-                return -EINVAL;
-        }
-
         ret = nf_ct_l3proto_try_module_get(par->family);
         if (ret < 0)
                 pr_info("cannot load conntrack support for proto=%u\n",
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 00bcb88386c2..9bec2e8a838c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1407,6 +1407,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
         struct net *net = xp_net(policy);
         unsigned long now = jiffies;
         struct net_device *dev;
+        struct xfrm_mode *inner_mode;
         struct dst_entry *dst_prev = NULL;
         struct dst_entry *dst0 = NULL;
         int i = 0;
@@ -1437,6 +1438,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
                         goto put_states;
                 }
 
+                if (xfrm[i]->sel.family == AF_UNSPEC) {
+                        inner_mode = xfrm_ip2inner_mode(xfrm[i],
+                                                        xfrm_af2proto(family));
+                        if (!inner_mode) {
+                                err = -EAFNOSUPPORT;
+                                dst_release(dst);
+                                goto put_states;
+                        }
+                } else
+                        inner_mode = xfrm[i]->inner_mode;
+
                 if (!dst_prev)
                         dst0 = dst1;
                 else {
@@ -1465,7 +1477,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
                 dst1->lastuse = now;
 
                 dst1->input = dst_discard;
-                dst1->output = xfrm[i]->outer_mode->afinfo->output;
+                dst1->output = inner_mode->afinfo->output;
 
                 dst1->next = dst_prev;
                 dst_prev = dst1;
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index e8a781422feb..47f1b8638df9 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -535,6 +535,9 @@ int xfrm_init_replay(struct xfrm_state *x)
                     replay_esn->bmp_len * sizeof(__u32) * 8)
                         return -EINVAL;
 
+        if ((x->props.flags & XFRM_STATE_ESN) && replay_esn->replay_window == 0)
+                return -EINVAL;
+
         if ((x->props.flags & XFRM_STATE_ESN) && x->replay_esn)
                 x->repl = &xfrm_replay_esn;
         else