Merge branch 'next' into for-linus

Second round of updates for 3.20.

14 files changed, 100 insertions, 86 deletions

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3a83ce5efa80..787b3c294ce6 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -129,7 +129,8 @@ int ip_forward(struct sk_buff *skb)
          *      We now generate an ICMP HOST REDIRECT giving the route
          *      we calculated.
          */
-        if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
+        if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
+            !skb_sec_path(skb))
                 ip_rt_send_redirect(skb);
 
         skb->priority = rt_tos2priority(iph->tos);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b50861b22b6b..c373c0708d97 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1506,23 +1506,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
 /*
  *      Generic function to send a packet as reply to another packet.
  *      Used to send some TCP resets/acks so far.
- *
- *      Use a fake percpu inet socket to avoid false sharing and contention.
  */
-static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
-        .sk = {
-                .__sk_common = {
-                        .skc_refcnt = ATOMIC_INIT(1),
-                },
-                .sk_wmem_alloc  = ATOMIC_INIT(1),
-                .sk_allocation  = GFP_ATOMIC,
-                .sk_flags       = (1UL << SOCK_USE_WRITE_QUEUE),
-        },
-        .pmtudisc       = IP_PMTUDISC_WANT,
-        .uc_ttl         = -1,
-};
-
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
                            const struct ip_options *sopt,
                            __be32 daddr, __be32 saddr,
                            const struct ip_reply_arg *arg,
@@ -1532,9 +1517,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
         struct ipcm_cookie ipc;
         struct flowi4 fl4;
         struct rtable *rt = skb_rtable(skb);
+        struct net *net = sock_net(sk);
         struct sk_buff *nskb;
-        struct sock *sk;
-        struct inet_sock *inet;
         int err;
 
         if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))
@@ -1565,15 +1549,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
         if (IS_ERR(rt))
                 return;
 
-        inet = &get_cpu_var(unicast_sock);
+        inet_sk(sk)->tos = arg->tos;
 
-        inet->tos = arg->tos;
-        sk = &inet->sk;
         sk->sk_priority = skb->priority;
         sk->sk_protocol = ip_hdr(skb)->protocol;
         sk->sk_bound_dev_if = arg->bound_dev_if;
-        sock_net_set(sk, net);
-        __skb_queue_head_init(&sk->sk_write_queue);
         sk->sk_sndbuf = sysctl_wmem_default;
         err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
                              len, 0, &ipc, &rt, MSG_DONTWAIT);
@@ -1589,13 +1569,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
                           arg->csumoffset) = csum_fold(csum_add(nskb->csum,
                                                                 arg->csum));
                 nskb->ip_summed = CHECKSUM_NONE;
-                skb_orphan(nskb);
                 skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
                 ip_push_pending_frames(sk, &fl4);
         }
 out:
-        put_cpu_var(unicast_sock);
-
         ip_rt_put(rt);
 }
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8a89c738b7a3..6b85adb05003 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -461,17 +461,13 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
         memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
         sin = &errhdr.offender;
-        sin->sin_family = AF_UNSPEC;
+        memset(sin, 0, sizeof(*sin));
 
         if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
             ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin)) {
-                struct inet_sock *inet = inet_sk(sk);
-
                 sin->sin_family = AF_INET;
                 sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
-                sin->sin_port = 0;
-                memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
-                if (inet->cmsg_flags)
+                if (inet_sk(sk)->cmsg_flags)
                         ip_cmsg_recv(msg, skb);
         }
 
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index ff2d23d8c87a..6ecfce63201a 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -27,10 +27,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
 
         memset(&mr, 0, sizeof(mr));
         if (priv->sreg_proto_min) {
-                mr.range[0].min.all = (__force __be16)
-                                        data[priv->sreg_proto_min].data[0];
-                mr.range[0].max.all = (__force __be16)
-                                        data[priv->sreg_proto_max].data[0];
+                mr.range[0].min.all =
+                        *(__be16 *)&data[priv->sreg_proto_min].data[0];
+                mr.range[0].max.all =
+                        *(__be16 *)&data[priv->sreg_proto_max].data[0];
                 mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
         }
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index c0d82f78d364..2a3720fb5a5f 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -966,8 +966,11 @@ bool ping_rcv(struct sk_buff *skb)
 
         sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
         if (sk != NULL) {
+                struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
+
                 pr_debug("rcv on socket %p\n", sk);
-                ping_queue_rcv_skb(sk, skb_get(skb));
+                if (skb2)
+                        ping_queue_rcv_skb(sk, skb2);
                 sock_put(sk);
                 return true;
         }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a2155b02602..52e1f2bf0ca2 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -966,6 +966,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
         if (dst->dev->mtu < mtu)
                 return;
 
+        if (rt->rt_pmtu && rt->rt_pmtu < mtu)
+                return;
+
         if (mtu < ip_rt_min_pmtu)
                 mtu = ip_rt_min_pmtu;
 
@@ -1554,11 +1557,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
         do_cache = res->fi && !itag;
         if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
+            skb->protocol == htons(ETH_P_IP) &&
             (IN_DEV_SHARED_MEDIA(out_dev) ||
-             inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
-                flags |= RTCF_DOREDIRECT;
-                do_cache = false;
-        }
+             inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+                IPCB(skb)->flags |= IPSKB_DOREDIRECT;
 
         if (skb->protocol != htons(ETH_P_IP)) {
                 /* Not IP (i.e. ARP). Do not create route, if it is
@@ -2303,6 +2305,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
         r->rtm_flags    = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
         if (rt->rt_flags & RTCF_NOTIFY)
                 r->rtm_flags |= RTM_F_NOTIFY;
+        if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
+                r->rtm_flags |= RTCF_DOREDIRECT;
 
         if (nla_put_be32(skb, RTA_DST, dst))
                 goto nla_put_failure;
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index bb395d46a389..c037644eafb7 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -150,7 +150,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
                 tcp_slow_start(tp, acked);
         else {
                 bictcp_update(ca, tp->snd_cwnd);
-                tcp_cong_avoid_ai(tp, ca->cnt);
+                tcp_cong_avoid_ai(tp, ca->cnt, 1);
         }
 }
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 27ead0dd16bc..8670e68e2ce6 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -291,26 +291,32 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
  * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
  * returns the leftover acks to adjust cwnd in congestion avoidance mode.
  */
-void tcp_slow_start(struct tcp_sock *tp, u32 acked)
+u32 tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
         u32 cwnd = tp->snd_cwnd + acked;
 
         if (cwnd > tp->snd_ssthresh)
                 cwnd = tp->snd_ssthresh + 1;
+        acked -= cwnd - tp->snd_cwnd;
         tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+
+        return acked;
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
-/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
+/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w),
+ * for every packet that was ACKed.
+ */
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 {
+        tp->snd_cwnd_cnt += acked;
         if (tp->snd_cwnd_cnt >= w) {
-                if (tp->snd_cwnd < tp->snd_cwnd_clamp)
-                        tp->snd_cwnd++;
-                tp->snd_cwnd_cnt = 0;
-        } else {
-                tp->snd_cwnd_cnt++;
+                u32 delta = tp->snd_cwnd_cnt / w;
+
+                tp->snd_cwnd_cnt -= delta * w;
+                tp->snd_cwnd += delta;
         }
+        tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
 }
 EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
 
@@ -329,11 +335,13 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
                 return;
 
         /* In "safe" area, increase. */
-        if (tp->snd_cwnd <= tp->snd_ssthresh)
-                tcp_slow_start(tp, acked);
+        if (tp->snd_cwnd <= tp->snd_ssthresh) {
+                acked = tcp_slow_start(tp, acked);
+                if (!acked)
+                        return;
+        }
         /* In dangerous area, increase slowly. */
-        else
-                tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+        tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
 }
 EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 6b6002416a73..4b276d1ed980 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -93,9 +93,7 @@ struct bictcp {
         u32     epoch_start;    /* beginning of an epoch */
         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 */
+        u16     unused;
         u8      sample_cnt;     /* number of samples to decide curr_rtt */
         u8      found;          /* the exit point is found? */
         u32     round_start;    /* beginning of each round */
@@ -114,7 +112,6 @@ static inline void bictcp_reset(struct bictcp *ca)
         ca->bic_K = 0;
         ca->delay_min = 0;
         ca->epoch_start = 0;
-        ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
         ca->ack_cnt = 0;
         ca->tcp_cwnd = 0;
         ca->found = 0;
@@ -205,23 +202,30 @@ static u32 cubic_root(u64 a)
 /*
  * Compute congestion window to use.
  */
-static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
+static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked)
 {
         u32 delta, bic_target, max_cnt;
         u64 offs, t;
 
-        ca->ack_cnt++;  /* count the number of ACKs */
+        ca->ack_cnt += acked;   /* count the number of ACKed packets */
 
         if (ca->last_cwnd == cwnd &&
             (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32)
                 return;
 
+        /* The CUBIC function can update ca->cnt at most once per jiffy.
+         * On all cwnd reduction events, ca->epoch_start is set to 0,
+         * which will force a recalculation of ca->cnt.
+         */
+        if (ca->epoch_start && tcp_time_stamp == ca->last_time)
+                goto tcp_friendliness;
+
         ca->last_cwnd = cwnd;
         ca->last_time = tcp_time_stamp;
 
         if (ca->epoch_start == 0) {
                 ca->epoch_start = tcp_time_stamp;       /* record beginning */
-                ca->ack_cnt = 1;                        /* start counting */
+                ca->ack_cnt = acked;                    /* start counting */
                 ca->tcp_cwnd = cwnd;                    /* syn with cubic */
 
                 if (ca->last_max_cwnd <= cwnd) {
@@ -283,6 +287,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
         if (ca->last_max_cwnd == 0 && ca->cnt > 20)
                 ca->cnt = 20;   /* increase cwnd 5% per RTT */
 
+tcp_friendliness:
         /* TCP Friendly */
         if (tcp_friendliness) {
                 u32 scale = beta_scale;
@@ -301,7 +306,6 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
                 }
         }
 
-        ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
         if (ca->cnt == 0)                       /* cannot be zero */
                 ca->cnt = 1;
 }
@@ -317,11 +321,12 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
         if (tp->snd_cwnd <= tp->snd_ssthresh) {
                 if (hystart && after(ack, ca->end_seq))
                         bictcp_hystart_reset(sk);
-                tcp_slow_start(tp, acked);
-        } else {
-                bictcp_update(ca, tp->snd_cwnd);
-                tcp_cong_avoid_ai(tp, ca->cnt);
+                acked = tcp_slow_start(tp, acked);
+                if (!acked)
+                        return;
         }
+        bictcp_update(ca, tp->snd_cwnd, acked);
+        tcp_cong_avoid_ai(tp, ca->cnt, acked);
 }
 
 static u32 bictcp_recalc_ssthresh(struct sock *sk)
@@ -411,20 +416,10 @@ static void hystart_update(struct sock *sk, u32 delay)
  */
 static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 {
-        const struct inet_connection_sock *icsk = inet_csk(sk);
         const struct tcp_sock *tp = tcp_sk(sk);
         struct bictcp *ca = inet_csk_ca(sk);
         u32 delay;
 
-        if (icsk->icsk_ca_state == TCP_CA_Open) {
-                u32 ratio = ca->delayed_ack;
-
-                ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
-                ratio += cnt;
-
-                ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
-        }
-
         /* Some calls are for duplicates without timetamps */
         if (rtt_us < 0)
                 return;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a3f72d7fc06c..d22f54482bab 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -683,7 +683,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
                 arg.bound_dev_if = sk->sk_bound_dev_if;
 
         arg.tos = ip_hdr(skb)->tos;
-        ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+        ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+                              skb, &TCP_SKB_CB(skb)->header.h4.opt,
                               ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
                               &arg, arg.iov[0].iov_len);
 
@@ -767,7 +768,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
         if (oif)
                 arg.bound_dev_if = oif;
         arg.tos = tos;
-        ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+        ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+                              skb, &TCP_SKB_CB(skb)->header.h4.opt,
                               ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
                               &arg, arg.iov[0].iov_len);
 
@@ -2428,14 +2430,39 @@ struct proto tcp_prot = {
 };
 EXPORT_SYMBOL(tcp_prot);
 
+static void __net_exit tcp_sk_exit(struct net *net)
+{
+        int cpu;
+
+        for_each_possible_cpu(cpu)
+                inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
+        free_percpu(net->ipv4.tcp_sk);
+}
+
 static int __net_init tcp_sk_init(struct net *net)
 {
+        int res, cpu;
+
+        net->ipv4.tcp_sk = alloc_percpu(struct sock *);
+        if (!net->ipv4.tcp_sk)
+                return -ENOMEM;
+
+        for_each_possible_cpu(cpu) {
+                struct sock *sk;
+
+                res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+                                           IPPROTO_TCP, net);
+                if (res)
+                        goto fail;
+                *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
+        }
         net->ipv4.sysctl_tcp_ecn = 2;
         return 0;
-}
 
-static void __net_exit tcp_sk_exit(struct net *net)
-{
+fail:
+        tcp_sk_exit(net);
+
+        return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 6824afb65d93..333bcb2415ff 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -25,7 +25,8 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
         if (tp->snd_cwnd <= tp->snd_ssthresh)
                 tcp_slow_start(tp, acked);
         else
-                tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT));
+                tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT),
+                                  1);
 }
 
 static u32 tcp_scalable_ssthresh(struct sock *sk)
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index a4d2d2d88dca..112151eeee45 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -159,7 +159,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
                                 /* In the "non-congestive state", increase cwnd
                                  *  every rtt.
                                  */
-                                tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+                                tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
                         } else {
                                 /* In the "congestive state", increase cwnd
                                  * every other rtt.
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index cd7273218598..17d35662930d 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -92,7 +92,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 
         } else {
                 /* Reno */
-                tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+                tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
         }
 
         /* The key players are v_vegas.beg_snd_una and v_beg_snd_nxt.
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 7927db0a9279..4a000f1dd757 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -99,11 +99,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin
         s_slot = cb->args[0];
         num = s_num = cb->args[1];
 
-        for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) {
+        for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) {
                 struct sock *sk;
                 struct hlist_nulls_node *node;
                 struct udp_hslot *hslot = &table->hash[slot];
 
+                num = 0;
+
                 if (hlist_nulls_empty(&hslot->head))
                         continue;