15 files changed, 63 insertions, 56 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 68f6a94f7661..c929d9c1c4b6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1333,8 +1333,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
                                 iph->frag_off |= htons(IP_MF);
                         offset += (skb->len - skb->mac_len - iph->ihl * 4);
                 } else  {
-                        if (!(iph->frag_off & htons(IP_DF)))
-                                iph->id = htons(id++);
+                        iph->id = htons(id++);
                 }
                 iph->tot_len = htons(skb->len - skb->mac_len);
                 iph->check = 0;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f678507bc829..96083b7a436b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -802,8 +802,10 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg
                 if (nlh->nlmsg_flags & NLM_F_EXCL ||
                     !(nlh->nlmsg_flags & NLM_F_REPLACE))
                         return -EEXIST;
-
-                set_ifa_lifetime(ifa_existing, valid_lft, prefered_lft);
+                ifa = ifa_existing;
+                set_ifa_lifetime(ifa, valid_lft, prefered_lft);
+                rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
+                blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
         }
         return 0;
 }
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7d1874be1df3..786d97aee751 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -735,6 +735,7 @@ EXPORT_SYMBOL(inet_csk_destroy_sock);
  * tcp/dccp_create_openreq_child().
  */
 void inet_csk_prepare_forced_close(struct sock *sk)
+        __releases(&sk->sk_lock.slock)
 {
         /* sk_clone_lock locked the socket and set refcnt to 2 */
         bh_unlock_sock(sk);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 245ae078a07f..f4fd23de9b13 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -21,6 +21,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
 
+#include <net/sock.h>
 #include <net/inet_frag.h>
 
 static void inet_frag_secret_rebuild(unsigned long dummy)
@@ -277,6 +278,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
         __releases(&f->lock)
 {
         struct inet_frag_queue *q;
+        int depth = 0;
 
         hlist_for_each_entry(q, &f->hash[hash], list) {
                 if (q->net == nf && f->match(q, key)) {
@@ -284,9 +286,25 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
                         read_unlock(&f->lock);
                         return q;
                 }
+                depth++;
         }
         read_unlock(&f->lock);
 
-        return inet_frag_create(nf, f, key);
+        if (depth <= INETFRAGS_MAXDEPTH)
+                return inet_frag_create(nf, f, key);
+        else
+                return ERR_PTR(-ENOBUFS);
 }
 EXPORT_SYMBOL(inet_frag_find);
+
+void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
+                                   const char *prefix)
+{
+        static const char msg[] = "inet_frag_find: Fragment hash bucket"
+                " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
+                ". Dropping fragment.\n";
+
+        if (PTR_ERR(q) == -ENOBUFS)
+                LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg);
+}
+EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b6d30acb600c..a6445b843ef4 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -292,14 +292,11 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
         hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
 
         q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
-        if (q == NULL)
-                goto out_nomem;
-
+        if (IS_ERR_OR_NULL(q)) {
+                inet_frag_maybe_warn_overflow(q, pr_fmt());
+                return NULL;
+        }
         return container_of(q, struct ipq, q);
-
-out_nomem:
-        LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n"));
-        return NULL;
 }
 
 /* Is the fragment too far ahead to be part of ipq? */
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index d0ef0e674ec5..91d66dbde9c0 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -798,10 +798,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 
         if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
                 gre_hlen = 0;
-                if (skb->protocol == htons(ETH_P_IP))
-                        tiph = (const struct iphdr *)skb->data;
-                else
-                        tiph = &tunnel->parms.iph;
+                tiph = (const struct iphdr *)skb->data;
         } else {
                 gre_hlen = tunnel->hlen;
                 tiph = &tunnel->parms.iph;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 87abd3e2bd32..2bdf802e28e2 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -228,9 +228,11 @@ static int ip_local_deliver_finish(struct sk_buff *skb)
                                         icmp_send(skb, ICMP_DEST_UNREACH,
                                                   ICMP_PROT_UNREACH, 0);
                                 }
-                        } else
+                                kfree_skb(skb);
+                        } else {
                                 IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS);
-                        kfree_skb(skb);
+                                consume_skb(skb);
+                        }
                 }
         }
  out:
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index f6289bf6f332..ec7264514a82 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -370,7 +370,6 @@ int ip_options_compile(struct net *net,
                                 }
                                 switch (optptr[3]&0xF) {
                                       case IPOPT_TS_TSONLY:
-                                        opt->ts = optptr - iph;
                                         if (skb)
                                                 timeptr = &optptr[optptr[2]-1];
                                         opt->ts_needtime = 1;
@@ -381,7 +380,6 @@ int ip_options_compile(struct net *net,
                                                 pp_ptr = optptr + 2;
                                                 goto error;
                                         }
-                                        opt->ts = optptr - iph;
                                         if (rt)  {
                                                 spec_dst_fill(&spec_dst, skb);
                                                 memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
@@ -396,7 +394,6 @@ int ip_options_compile(struct net *net,
                                                 pp_ptr = optptr + 2;
                                                 goto error;
                                         }
-                                        opt->ts = optptr - iph;
                                         {
                                                 __be32 addr;
                                                 memcpy(&addr, &optptr[optptr[2]-1], 4);
@@ -423,18 +420,18 @@ int ip_options_compile(struct net *net,
                                         put_unaligned_be32(midtime, timeptr);
                                         opt->is_changed = 1;
                                 }
-                        } else {
+                        } else if ((optptr[3]&0xF) != IPOPT_TS_PRESPEC) {
                                 unsigned int overflow = optptr[3]>>4;
                                 if (overflow == 15) {
                                         pp_ptr = optptr + 3;
                                         goto error;
                                 }
-                                opt->ts = optptr - iph;
                                 if (skb) {
                                         optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4);
                                         opt->is_changed = 1;
                                 }
                         }
+                        opt->ts = optptr - iph;
                         break;
                       case IPOPT_RA:
                         if (optlen < 4) {
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 98cbc6877019..bf6c5cf31aed 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1522,7 +1522,8 @@ static int __init ip_auto_config(void)
                 }
         for (i++; i < CONF_NAMESERVERS_MAX; i++)
                 if (ic_nameservers[i] != NONE)
-                        pr_cont(", nameserver%u=%pI4\n", i, &ic_nameservers[i]);
+                        pr_cont(", nameserver%u=%pI4", i, &ic_nameservers[i]);
+        pr_cont("\n");
 #endif /* !SILENT */
 
         return 0;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index ce2d43e1f09f..0d755c50994b 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -36,19 +36,6 @@ config NF_CONNTRACK_PROC_COMPAT
 
           If unsure, say Y.
 
-config IP_NF_QUEUE
-        tristate "IP Userspace queueing via NETLINK (OBSOLETE)"
-        depends on NETFILTER_ADVANCED
-        help
-          Netfilter has the ability to queue packets to user space: the
-          netlink device can be used to access them using this driver.
-
-          This option enables the old IPv4-only "ip_queue" implementation
-          which has been obsoleted by the new "nfnetlink_queue" code (see
-          CONFIG_NETFILTER_NETLINK_QUEUE).
-
-          To compile it as a module, choose M here.  If unsure, say N.
-
 config IP_NF_IPTABLES
         tristate "IP tables support (required for filtering/masq/NAT)"
         default m if NETFILTER_ADVANCED=n
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 47e854fcae24..e22020790709 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -775,7 +775,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
                          * Make sure that we have exactly size bytes
                          * available to the caller, no more, no less.
                          */
-                        skb->avail_size = size;
+                        skb->reserved_tailroom = skb->end - skb->tail - size;
                         return skb;
                 }
                 __kfree_skb(skb);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a759e19496d2..3bd55bad230a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2059,11 +2059,8 @@ void tcp_enter_loss(struct sock *sk, int how)
         if (tcp_is_reno(tp))
                 tcp_reset_reno_sack(tp);
 
-        if (!how) {
-                /* Push undo marker, if it was plain RTO and nothing
-                 * was retransmitted. */
-                tp->undo_marker = tp->snd_una;
-        } else {
+        tp->undo_marker = tp->snd_una;
+        if (how) {
                 tp->sacked_out = 0;
                 tp->fackets_out = 0;
         }
@@ -5485,6 +5482,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
                                 if (tcp_checksum_complete_user(sk, skb))
                                         goto csum_error;
 
+                                if ((int)skb->truesize > sk->sk_forward_alloc)
+                                        goto step5;
+
                                 /* Predicted packet is in window by definition.
                                  * seq == rcv_nxt and rcv_wup <= rcv_nxt.
                                  * Hence, check seq<=rcv_wup reduces to:
@@ -5496,9 +5496,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 
                                 tcp_rcv_rtt_measure_ts(sk, skb);
 
-                                if ((int)skb->truesize > sk->sk_forward_alloc)
-                                        goto step5;
-
                                 NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS);
 
                                 /* Bulk data transfer: receiver */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4a8ec457310f..d09203c63264 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -274,13 +274,6 @@ static void tcp_v4_mtu_reduced(struct sock *sk)
         struct inet_sock *inet = inet_sk(sk);
         u32 mtu = tcp_sk(sk)->mtu_info;
 
-        /* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
-         * send out by Linux are always <576bytes so they should go through
-         * unfragmented).
-         */
-        if (sk->sk_state == TCP_LISTEN)
-                return;
-
         dst = inet_csk_update_pmtu(sk, mtu);
         if (!dst)
                 return;
@@ -408,6 +401,13 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
                         goto out;
 
                 if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
+                        /* We are not interested in TCP_LISTEN and open_requests
+                         * (SYN-ACKs send out by Linux are always <576bytes so
+                         * they should go through unfragmented).
+                         */
+                        if (sk->sk_state == TCP_LISTEN)
+                                goto out;
+
                         tp->mtu_info = info;
                         if (!sock_owned_by_user(sk)) {
                                 tcp_v4_mtu_reduced(sk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e2b4461074da..5d0b4387cba6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1298,7 +1298,6 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
         eat = min_t(int, len, skb_headlen(skb));
         if (eat) {
                 __skb_pull(skb, eat);
-                skb->avail_size -= eat;
                 len -= eat;
                 if (!len)
                         return;
@@ -1810,8 +1809,11 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
                         goto send_now;
         }
 
-        /* Ok, it looks like it is advisable to defer.  */
-        tp->tso_deferred = 1 | (jiffies << 1);
+        /* Ok, it looks like it is advisable to defer.
+         * Do not rearm the timer if already set to not break TCP ACK clocking.
+         */
+        if (!tp->tso_deferred)
+                tp->tso_deferred = 1 | (jiffies << 1);
 
         return true;
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 265c42cf963c..0a073a263720 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1762,9 +1762,16 @@ int udp_rcv(struct sk_buff *skb)
 
 void udp_destroy_sock(struct sock *sk)
 {
+        struct udp_sock *up = udp_sk(sk);
         bool slow = lock_sock_fast(sk);
         udp_flush_pending_frames(sk);
         unlock_sock_fast(sk, slow);
+        if (static_key_false(&udp_encap_needed) && up->encap_type) {
+                void (*encap_destroy)(struct sock *sk);
+                encap_destroy = ACCESS_ONCE(up->encap_destroy);
+                if (encap_destroy)
+                        encap_destroy(sk);
+        }
 }
 
 /*