MMerge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Stretch ACKs can kill performance with Reno and CUBIC congestion
    control, largely due to LRO and GRO.  Fix from Neal Cardwell.

 2) Fix userland breakage because we accidently emit zero length netlink
    messages from the bridging code.  From Roopa Prabhu.

 3) Carry handling in generic csum_tcpudp_nofold is broken, fix from
    Karl Beldan.

 4) Remove bogus dev_set_net() calls from CAIF driver, from Nicolas
    Dichtel.

 5) Make sure PPP deflation never returns a length greater then the
    output buffer, otherwise we overflow and trigger skb_over_panic().
    Fix from Florian Westphal.

 6) COSA driver needs VIRT_TO_BUS Kconfig dependencies, from Arnd
    Bergmann.

 7) Don't increase route cached MTU on datagram too big ICMPs.  From Li
    Wei.

 8) Fix error path leaks in nf_tables, from Pablo Neira Ayuso.

 9) Fix bitmask handling regression in netlink that broke things like
    acpi userland tools.  From Pablo Neira Ayuso.

10) Wrong header pointer passed to param_type2af() in SCTP code, from
    Saran Maruti Ramanara.

11) Stacked vlans not handled correctly by vlan_get_protocol(), from
    Toshiaki Makita.

12) Add missing DMA memory barrier to xgene driver, from Iyappan
    Subramanian.

13) Fix crash in rate estimators, from Eric Dumazet.

14) We've been adding various workarounds, one after another, for the
    change which added the per-net tcp_sock.  It was meant to reduce
    socket contention but added lots of problems.

    Reduce this instead to a proper per-cpu socket and that rids us of
    all the daemons.

    From Eric Dumazet.

15) Fix memory corruption and OOPS in mlx4 driver, from Jack
    Morgenstein.

16) When we disabled UFO in the virtio_net device, it introduces some
    serious performance regressions.  The orignal problem was IPV6
    fragment ID generation, so fix that properly instead.  From Vlad
    Yasevich.

17) sr9700 driver build breaks on xtensa because it defines macros with
    the same name as those used by the arch code.  Use more unique
    names.  From Chen Gang.

18) Fix endianness in new virio 1.0 mode of the vhost net driver, from
    Michael S Tsirkin.

19) Several sysctls were setting the maxlen attribute incorrectly, from
    Sasha Levin.

20) Don't accept an FQ scheduler quantum of zero, that leads to crashes.
    From Kenneth Klette Jonassen.

21) Fix dumping of non-existing actions in the packet scheduler
    classifier.  From Ignacy Gawędzki.

22) Return the write work_done value when doing TX work in the qlcnic
    driver.

23) ip6gre_err accesses the info field with the wrong endianness, from
    Sabrina Dubroca.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (54 commits)
  sit: fix some __be16/u16 mismatches
  ipv6: fix sparse errors in ip6_make_flowlabel()
  net: remove some sparse warnings
  flow_keys: n_proto type should be __be16
  ip6_gre: fix endianness errors in ip6gre_err
  qlcnic: Fix NAPI poll routine for Tx completion
  amd-xgbe: Set RSS enablement based on hardware features
  amd-xgbe: Adjust for zero-based traffic class count
  cls_api.c: Fix dumping of non-existing actions' stats.
  pkt_sched: fq: avoid hang when quantum 0
  net: rds: use correct size for max unacked packets and bytes
  vhost/net: fix up num_buffers endian-ness
  gianfar: correct the bad expression while writing bit-pattern
  net: usb: sr9700: Use 'SR_' prefix for the common register macros
  Revert "drivers/net: Disable UFO through virtio"
  Revert "drivers/net, ipv6: Select IPv6 fragment idents for virtio UFO packets"
  ipv6: Select fragment id during UFO segmentation if not set.
  xen-netback: stop the guest rx thread after a fatal error
  net/mlx4_core: Fix kernel Oops (mem corruption) when working with more than 80 VFs
  isdn: off by one in connect_res()
  ...

9 files changed, 80 insertions, 69 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b50861b..c373c07 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/route.c b/net/ipv4/route.c
index d58dd0e..52e1f2b 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;
 
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index bb395d4..c037644 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 27ead0d..8670e68 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 6b60024..4b276d1 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 a3f72d7..d22f544 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 6824afb..333bcb2 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 a4d2d2d..112151e 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 cd72732..17d3566 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.