17 files changed, 78 insertions, 68 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 83673d23d4dd..0600f0fbe325 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -676,6 +676,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags)
        lock_sock(sk2);
+        sock_rps_record_flow(sk2);
        WARN_ON(!((1 << sk2->sk_state) &
                  (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 5ff47656fced..389a2e6a17fd 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -437,7 +437,7 @@ static int valid_cc(const void *bc, int len, int cc)
                        return 0;
                if (cc == len)
                        return 1;
-                if (op->yes < 4)
+                if (op->yes < 4 || op->yes & 3)
                        return 0;
                len -= op->yes;
                bc  += op->yes;
@@ -447,11 +447,11 @@ static int valid_cc(const void *bc, int len, int cc)
 static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 {
-        const unsigned char *bc = bytecode;
+        const void *bc = bytecode;
        int  len = bytecode_len;
        while (len > 0) {
-                struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)bc;
+                const struct inet_diag_bc_op *op = bc;
 //printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len);
                switch (op->code) {
@@ -462,22 +462,20 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
                case INET_DIAG_BC_S_LE:
                case INET_DIAG_BC_D_GE:
                case INET_DIAG_BC_D_LE:
-                        if (op->yes < 4 || op->yes > len + 4)
-                                return -EINVAL;
                case INET_DIAG_BC_JMP:
-                        if (op->no < 4 || op->no > len + 4)
+                        if (op->no < 4 || op->no > len + 4 || op->no & 3)
                                return -EINVAL;
                        if (op->no < len &&
                            !valid_cc(bytecode, bytecode_len, len - op->no))
                                return -EINVAL;
                        break;
                case INET_DIAG_BC_NOP:
-                        if (op->yes < 4 || op->yes > len + 4)
-                                return -EINVAL;
                        break;
                default:
                        return -EINVAL;
                }
+                if (op->yes < 4 || op->yes > len + 4 || op->yes & 3)
+                        return -EINVAL;
                bc  += op->yes;
                len -= op->yes;
        }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 98af3697c718..a8024eaa0e87 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -799,7 +799,9 @@ static int __ip_append_data(struct sock *sk,
        int csummode = CHECKSUM_NONE;
        struct rtable *rt = (struct rtable *)cork->dst;
-        exthdrlen = transhdrlen ? rt->dst.header_len : 0;
+        skb = skb_peek_tail(queue);
+        exthdrlen = !skb ? rt->dst.header_len : 0;
        length += exthdrlen;
        transhdrlen += exthdrlen;
        mtu = cork->fragsize;
@@ -825,8 +827,6 @@ static int __ip_append_data(struct sock *sk,
            !exthdrlen)
                csummode = CHECKSUM_PARTIAL;
-        skb = skb_peek_tail(queue);
        cork->length += length;
        if (((length > mtu) || (skb && skb_is_gso(skb))) &&
            (sk->sk_protocol == IPPROTO_UDP) &&
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index d2c1311cb28d..5c9b9d963918 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -203,7 +203,8 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
        else
                pmsg->outdev_name[0] = '\0';
-        if (entry->indev && entry->skb->dev) {
+        if (entry->indev && entry->skb->dev &&
+            entry->skb->mac_header != entry->skb->network_header) {
                pmsg->hw_type = entry->skb->dev->type;
                pmsg->hw_addrlen = dev_parse_header(entry->skb,
                                                    pmsg->hw_addr);
@@ -402,7 +403,8 @@ ipq_dev_drop(int ifindex)
 static inline void
 __ipq_rcv_skb(struct sk_buff *skb)
 {
-        int status, type, pid, flags, nlmsglen, skblen;
+        int status, type, pid, flags;
+        unsigned int nlmsglen, skblen;
        struct nlmsghdr *nlh;
        skblen = skb->len;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 764743843503..24e556e83a3b 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -566,7 +566,7 @@ check_entry(const struct ipt_entry *e, const char *name)
        const struct xt_entry_target *t;
        if (!ip_checkentry(&e->ip)) {
-                duprintf("ip check failed %p %s.\n", e, par->match->name);
+                duprintf("ip check failed %p %s.\n", e, name);
                return -EINVAL;
        }
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index d609ac3cb9a4..5c9e97c79017 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -307,7 +307,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
         * error messages (RELATED) and information requests (see below) */
        if (ip_hdr(skb)->protocol == IPPROTO_ICMP &&
            (ctinfo == IP_CT_RELATED ||
-             ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY))
+             ctinfo == IP_CT_RELATED_REPLY))
                return XT_CONTINUE;
        /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO,
@@ -321,12 +321,12 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
                        ct->mark = hash;
                        break;
                case IP_CT_RELATED:
-                case IP_CT_RELATED+IP_CT_IS_REPLY:
+                case IP_CT_RELATED_REPLY:
                        /* FIXME: we don't handle expectations at the
                         * moment.  they can arrive on a different node than
                         * the master connection (e.g. FTP passive mode) */
                case IP_CT_ESTABLISHED:
-                case IP_CT_ESTABLISHED+IP_CT_IS_REPLY:
+                case IP_CT_ESTABLISHED_REPLY:
                        break;
                default:
                        break;
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index d2ed9dc74ebc..9931152a78b5 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -60,7 +60,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
        nat = nfct_nat(ct);
        NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-                            ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY));
+                            ctinfo == IP_CT_RELATED_REPLY));
        /* Source address is 0.0.0.0 - locally generated packet that is
         * probably not supposed to be masqueraded.
diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c
index af6e9c778345..2b57e52c746c 100644
--- a/net/ipv4/netfilter/ipt_ecn.c
+++ b/net/ipv4/netfilter/ipt_ecn.c
@@ -25,7 +25,8 @@ MODULE_LICENSE("GPL");
 static inline bool match_ip(const struct sk_buff *skb,
                            const struct ipt_ecn_info *einfo)
 {
-        return (ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect;
+        return ((ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect) ^
+               !!(einfo->invert & IPT_ECN_OP_MATCH_IP);
 }
 static inline bool match_tcp(const struct sk_buff *skb,
@@ -76,8 +77,6 @@ static bool ecn_mt(const struct sk_buff *skb, struct xt_action_param *par)
                        return false;
        if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR)) {
-                if (ip_hdr(skb)->protocol != IPPROTO_TCP)
-                        return false;
                if (!match_tcp(skb, info, &par->hotdrop))
                        return false;
        }
@@ -97,7 +96,7 @@ static int ecn_mt_check(const struct xt_mtchk_param *par)
                return -EINVAL;
        if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) &&
-            ip->proto != IPPROTO_TCP) {
+            (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) {
                pr_info("cannot match TCP bits in rule for non-tcp packets\n");
                return -EINVAL;
        }
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 5a03c02af999..de9da21113a1 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -101,7 +101,7 @@ static unsigned int ipv4_confirm(unsigned int hooknum,
        /* This is where we call the helper: as the packet goes out. */
        ct = nf_ct_get(skb, &ctinfo);
-        if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)
+        if (!ct || ctinfo == IP_CT_RELATED_REPLY)
                goto out;
        help = nfct_help(ct);
@@ -121,7 +121,9 @@ static unsigned int ipv4_confirm(unsigned int hooknum,
                return ret;
        }
-        if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) {
+        /* adjust seqs for loopback traffic only in outgoing direction */
+        if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
+            !nf_is_loopback_packet(skb)) {
                typeof(nf_nat_seq_adjust_hook) seq_adjust;
                seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 7404bde95994..ab5b27a2916f 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -160,7 +160,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
        /* Update skb to refer to this connection */
        skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general;
        skb->nfctinfo = *ctinfo;
-        return -NF_ACCEPT;
+        return NF_ACCEPT;
 }
 /* Small and modified version of icmp_rcv */
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 9c71b2755ce3..3346de5d94d0 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -433,7 +433,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
        /* Must be RELATED */
        NF_CT_ASSERT(skb->nfctinfo == IP_CT_RELATED ||
-                     skb->nfctinfo == IP_CT_RELATED+IP_CT_IS_REPLY);
+                     skb->nfctinfo == IP_CT_RELATED_REPLY);
        /* Redirects on non-null nats must be dropped, else they'll
           start talking to each other without our translation, and be
diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c
index 99cfa28b6d38..ebc5f8894f99 100644
--- a/net/ipv4/netfilter/nf_nat_helper.c
+++ b/net/ipv4/netfilter/nf_nat_helper.c
@@ -160,7 +160,7 @@ static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data
        if (skb->ip_summed != CHECKSUM_PARTIAL) {
                if (!(rt->rt_flags & RTCF_LOCAL) &&
-                    skb->dev->features & NETIF_F_V4_CSUM) {
+                    (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) {
                        skb->ip_summed = CHECKSUM_PARTIAL;
                        skb->csum_start = skb_headroom(skb) +
                                          skb_network_offset(skb) +
diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c
index 21c30426480b..733c9abc1cbd 100644
--- a/net/ipv4/netfilter/nf_nat_rule.c
+++ b/net/ipv4/netfilter/nf_nat_rule.c
@@ -53,7 +53,7 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par)
        /* Connection must be valid and new. */
        NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-                            ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY));
+                            ctinfo == IP_CT_RELATED_REPLY));
        NF_CT_ASSERT(par->out != NULL);
        return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC);
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index 7317bdf1d457..483b76d042da 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -116,7 +116,7 @@ nf_nat_fn(unsigned int hooknum,
        switch (ctinfo) {
        case IP_CT_RELATED:
-        case IP_CT_RELATED+IP_CT_IS_REPLY:
+        case IP_CT_RELATED_REPLY:
                if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
                        if (!nf_nat_icmp_reply_translation(ct, ctinfo,
                                                           hooknum, skb))
@@ -144,7 +144,7 @@ nf_nat_fn(unsigned int hooknum,
        default:
                /* ESTABLISHED */
                NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
-                             ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
+                             ctinfo == IP_CT_ESTABLISHED_REPLY);
        }
        return nf_nat_packet(ct, ctinfo, hooknum, skb);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 9aaa67165f42..39b403f854c6 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -41,7 +41,6 @@
 #include <linux/proc_fs.h>
 #include <net/sock.h>
 #include <net/ping.h>
-#include <net/icmp.h>
 #include <net/udp.h>
 #include <net/route.h>
 #include <net/inet_common.h>
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index aa29c6291353..f24c3359e5d0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1316,6 +1316,23 @@ reject_redirect:
        ;
 }
+static bool peer_pmtu_expired(struct inet_peer *peer)
+{
+        unsigned long orig = ACCESS_ONCE(peer->pmtu_expires);
+        return orig &&
+               time_after_eq(jiffies, orig) &&
+               cmpxchg(&peer->pmtu_expires, orig, 0) == orig;
+}
+static bool peer_pmtu_cleaned(struct inet_peer *peer)
+{
+        unsigned long orig = ACCESS_ONCE(peer->pmtu_expires);
+        return orig &&
+               cmpxchg(&peer->pmtu_expires, orig, 0) == orig;
+}
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 {
        struct rtable *rt = (struct rtable *)dst;
@@ -1331,14 +1348,8 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
                                                rt_genid(dev_net(dst->dev)));
                        rt_del(hash, rt);
                        ret = NULL;
-                } else if (rt->peer &&
+                } else if (rt->peer && peer_pmtu_expired(rt->peer)) {
-                           rt->peer->pmtu_expires &&
+                        dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig);
-                           time_after_eq(jiffies, rt->peer->pmtu_expires)) {
-                        unsigned long orig = rt->peer->pmtu_expires;
-                        if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig)
-                                dst_metric_set(dst, RTAX_MTU,
-                                               rt->peer->pmtu_orig);
                }
        }
        return ret;
@@ -1531,8 +1542,10 @@ unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph,
 static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer)
 {
-        unsigned long expires = peer->pmtu_expires;
+        unsigned long expires = ACCESS_ONCE(peer->pmtu_expires);
+        if (!expires)
+                return;
        if (time_before(jiffies, expires)) {
                u32 orig_dst_mtu = dst_mtu(dst);
                if (peer->pmtu_learned < orig_dst_mtu) {
@@ -1555,10 +1568,11 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
                rt_bind_peer(rt, rt->rt_dst, 1);
        peer = rt->peer;
        if (peer) {
+                unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires);
                if (mtu < ip_rt_min_pmtu)
                        mtu = ip_rt_min_pmtu;
-                if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
+                if (!pmtu_expires || mtu < peer->pmtu_learned) {
-                        unsigned long pmtu_expires;
                        pmtu_expires = jiffies + ip_rt_mtu_expires;
                        if (!pmtu_expires)
@@ -1612,13 +1626,14 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
                        rt_bind_peer(rt, rt->rt_dst, 0);
                peer = rt->peer;
-                if (peer && peer->pmtu_expires)
+                if (peer) {
                        check_peer_pmtu(dst, peer);
-                if (peer && peer->redirect_learned.a4 &&
+                        if (peer->redirect_learned.a4 &&
-                    peer->redirect_learned.a4 != rt->rt_gateway) {
+                            peer->redirect_learned.a4 != rt->rt_gateway) {
-                        if (check_peer_redir(dst, peer))
+                                if (check_peer_redir(dst, peer))
-                                return NULL;
+                                        return NULL;
+                        }
                }
                rt->rt_peer_genid = rt_peer_genid();
@@ -1649,14 +1664,8 @@ static void ipv4_link_failure(struct sk_buff *skb)
        icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
        rt = skb_rtable(skb);
-        if (rt &&
+        if (rt && rt->peer && peer_pmtu_cleaned(rt->peer))
-            rt->peer &&
+                dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig);
-            rt->peer->pmtu_expires) {
-                unsigned long orig = rt->peer->pmtu_expires;
-                if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig)
-                        dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig);
-        }
 }
 static int ip_rt_bug(struct sk_buff *skb)
@@ -1770,8 +1779,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
                               sizeof(u32) * RTAX_MAX);
                dst_init_metrics(&rt->dst, peer->metrics, false);
-                if (peer->pmtu_expires)
+                check_peer_pmtu(&rt->dst, peer);
-                        check_peer_pmtu(&rt->dst, peer);
                if (peer->redirect_learned.a4 &&
                    peer->redirect_learned.a4 != rt->rt_gateway) {
                        rt->rt_gateway = peer->redirect_learned.a4;
@@ -1894,9 +1902,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
        hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
        rth = rt_intern_hash(hash, rth, skb, dev->ifindex);
-        err = 0;
+        return IS_ERR(rth) ? PTR_ERR(rth) : 0;
-        if (IS_ERR(rth))
-                err = PTR_ERR(rth);
 e_nobufs:
        return -ENOBUFS;
@@ -2775,7 +2781,8 @@ static int rt_fill_info(struct net *net,
        struct rtable *rt = skb_rtable(skb);
        struct rtmsg *r;
        struct nlmsghdr *nlh;
-        long expires;
+        long expires = 0;
+        const struct inet_peer *peer = rt->peer;
        u32 id = 0, ts = 0, tsage = 0, error;
        nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
@@ -2823,15 +2830,16 @@ static int rt_fill_info(struct net *net,
                NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark);
        error = rt->dst.error;
-        expires = (rt->peer && rt->peer->pmtu_expires) ?
+        if (peer) {
-                rt->peer->pmtu_expires - jiffies : 0;
-        if (rt->peer) {
                inet_peer_refcheck(rt->peer);
-                id = atomic_read(&rt->peer->ip_id_count) & 0xffff;
+                id = atomic_read(&peer->ip_id_count) & 0xffff;
-                if (rt->peer->tcp_ts_stamp) {
+                if (peer->tcp_ts_stamp) {
-                        ts = rt->peer->tcp_ts;
+                        ts = peer->tcp_ts;
-                        tsage = get_seconds() - rt->peer->tcp_ts_stamp;
+                        tsage = get_seconds() - peer->tcp_ts_stamp;
                }
+                expires = ACCESS_ONCE(peer->pmtu_expires);
+                if (expires)
+                        expires -= jiffies;
        }
        if (rt_is_input_route(rt)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 617dee3ccfb1..955b8e65b69e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1594,6 +1594,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
                        goto discard;
                if (nsk != sk) {
+                        sock_rps_save_rxhash(nsk, skb->rxhash);
                        if (tcp_child_process(sk, nsk, skb)) {
                                rsk = nsk;
                                goto reset;