Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "This is a re-do of the net-next pull request for the current merge
  window.  The only difference from the one I made the other day is that
  this has Eliezer's interface renames and the timeout handling changes
  made based upon your feedback, as well as a few bug fixes that have
  trickeled in.

  Highlights:

   1) Low latency device polling, eliminating the cost of interrupt
      handling and context switches.  Allows direct polling of a network
      device from socket operations, such as recvmsg() and poll().

      Currently ixgbe, mlx4, and bnx2x support this feature.

      Full high level description, performance numbers, and design in
      commit 0a4db187a999 ("Merge branch 'll_poll'")

      From Eliezer Tamir.

   2) With the routing cache removed, ip_check_mc_rcu() gets exercised
      more than ever before in the case where we have lots of multicast
      addresses.  Use a hash table instead of a simple linked list, from
      Eric Dumazet.

   3) Add driver for Atheros CQA98xx 802.11ac wireless devices, from
      Bartosz Markowski, Janusz Dziedzic, Kalle Valo, Marek Kwaczynski,
      Marek Puzyniak, Michal Kazior, and Sujith Manoharan.

   4) Support reporting the TUN device persist flag to userspace, from
      Pavel Emelyanov.

   5) Allow controlling network device VF link state using netlink, from
      Rony Efraim.

   6) Support GRE tunneling in openvswitch, from Pravin B Shelar.

   7) Adjust SOCK_MIN_RCVBUF and SOCK_MIN_SNDBUF for modern times, from
      Daniel Borkmann and Eric Dumazet.

   8) Allow controlling of TCP quickack behavior on a per-route basis,
      from Cong Wang.

   9) Several bug fixes and improvements to vxlan from Stephen
      Hemminger, Pravin B Shelar, and Mike Rapoport.  In particular,
      support receiving on multiple UDP ports.

  10) Major cleanups, particular in the area of debugging and cookie
      lifetime handline, to the SCTP protocol code.  From Daniel
      Borkmann.

  11) Allow packets to cross network namespaces when traversing tunnel
      devices.  From Nicolas Dichtel.

  12) Allow monitoring netlink traffic via AF_PACKET sockets, in a
      manner akin to how we monitor real network traffic via ptype_all.
      From Daniel Borkmann.

  13) Several bug fixes and improvements for the new alx device driver,
      from Johannes Berg.

  14) Fix scalability issues in the netem packet scheduler's time queue,
      by using an rbtree.  From Eric Dumazet.

  15) Several bug fixes in TCP loss recovery handling, from Yuchung
      Cheng.

  16) Add support for GSO segmentation of MPLS packets, from Simon
      Horman.

  17) Make network notifiers have a real data type for the opaque
      pointer that's passed into them.  Use this to properly handle
      network device flag changes in arp_netdev_event().  From Jiri
      Pirko and Timo Teräs.

  18) Convert several drivers over to module_pci_driver(), from Peter
      Huewe.

  19) tcp_fixup_rcvbuf() can loop 500 times over loopback, just use a
      O(1) calculation instead.  From Eric Dumazet.

  20) Support setting of explicit tunnel peer addresses in ipv6, just
      like ipv4.  From Nicolas Dichtel.

  21) Protect x86 BPF JIT against spraying attacks, from Eric Dumazet.

  22) Prevent a single high rate flow from overruning an individual cpu
      during RX packet processing via selective flow shedding.  From
      Willem de Bruijn.

  23) Don't use spinlocks in TCP md5 signing fast paths, from Eric
      Dumazet.

  24) Don't just drop GSO packets which are above the TBF scheduler's
      burst limit, chop them up so they are in-bounds instead.  Also
      from Eric Dumazet.

  25) VLAN offloads are missed when configured on top of a bridge, fix
      from Vlad Yasevich.

  26) Support IPV6 in ping sockets.  From Lorenzo Colitti.

  27) Receive flow steering targets should be updated at poll() time
      too, from David Majnemer.

  28) Fix several corner case regressions in PMTU/redirect handling due
      to the routing cache removal, from Timo Teräs.

  29) We have to be mindful of ipv4 mapped ipv6 sockets in
      upd_v6_push_pending_frames().  From Hannes Frederic Sowa.

  30) Fix L2TP sequence number handling bugs, from James Chapman."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1214 commits)
  drivers/net: caif: fix wrong rtnl_is_locked() usage
  drivers/net: enic: release rtnl_lock on error-path
  vhost-net: fix use-after-free in vhost_net_flush
  net: mv643xx_eth: do not use port number as platform device id
  net: sctp: confirm route during forward progress
  virtio_net: fix race in RX VQ processing
  virtio: support unlocked queue poll
  net/cadence/macb: fix bug/typo in extracting gem_irq_read_clear bit
  Documentation: Fix references to defunct linux-net@vger.kernel.org
  net/fs: change busy poll time accounting
  net: rename low latency sockets functions to busy poll
  bridge: fix some kernel warning in multicast timer
  sfc: Fix memory leak when discarding scattered packets
  sit: fix tunnel update via netlink
  dt:net:stmmac: Add dt specific phy reset callback support.
  dt:net:stmmac: Add support to dwmac version 3.610 and 3.710
  dt:net:stmmac: Allocate platform data only if its NULL.
  net:stmmac: fix memleak in the open method
  ipv6: rt6_check_neigh should successfully verify neigh if no NUD information are available
  net: ipv6: fix wrong ping_v6_sendmsg return value
  ...

1 files changed, 28 insertions, 316 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ab450c099aa4..15cbfa94bd8e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,6 +279,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
+#include <net/ll_poll.h>
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 
@@ -436,6 +437,8 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	struct sock *sk = sock->sk;
 	const struct tcp_sock *tp = tcp_sk(sk);
 
+	sock_rps_record_flow(sk);
+
 	sock_poll_wait(file, sk_sleep(sk), wait);
 	if (sk->sk_state == TCP_LISTEN)
 		return inet_csk_listen_poll(sk);
@@ -1551,6 +1554,10 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct sk_buff *skb;
 	u32 urg_hole = 0;
 
+	if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
+	    (sk->sk_state == TCP_ESTABLISHED))
+		sk_busy_loop(sk, nonblock);
+
 	lock_sock(sk);
 
 	err = -ENOTCONN;
@@ -2875,249 +2882,9 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL(compat_tcp_getsockopt);
 #endif
 
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
-	netdev_features_t features)
-{
-	struct sk_buff *segs = ERR_PTR(-EINVAL);
-	struct tcphdr *th;
-	unsigned int thlen;
-	unsigned int seq;
-	__be32 delta;
-	unsigned int oldlen;
-	unsigned int mss;
-	struct sk_buff *gso_skb = skb;
-	__sum16 newcheck;
-	bool ooo_okay, copy_destructor;
-
-	if (!pskb_may_pull(skb, sizeof(*th)))
-		goto out;
-
-	th = tcp_hdr(skb);
-	thlen = th->doff * 4;
-	if (thlen < sizeof(*th))
-		goto out;
-
-	if (!pskb_may_pull(skb, thlen))
-		goto out;
-
-	oldlen = (u16)~skb->len;
-	__skb_pull(skb, thlen);
-
-	mss = skb_shinfo(skb)->gso_size;
-	if (unlikely(skb->len <= mss))
-		goto out;
-
-	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
-		/* Packet is from an untrusted source, reset gso_segs. */
-		int type = skb_shinfo(skb)->gso_type;
-
-		if (unlikely(type &
-			     ~(SKB_GSO_TCPV4 |
-			       SKB_GSO_DODGY |
-			       SKB_GSO_TCP_ECN |
-			       SKB_GSO_TCPV6 |
-			       SKB_GSO_GRE |
-			       SKB_GSO_UDP_TUNNEL |
-			       0) ||
-			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
-			goto out;
-
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
-
-		segs = NULL;
-		goto out;
-	}
-
-	copy_destructor = gso_skb->destructor == tcp_wfree;
-	ooo_okay = gso_skb->ooo_okay;
-	/* All segments but the first should have ooo_okay cleared */
-	skb->ooo_okay = 0;
-
-	segs = skb_segment(skb, features);
-	if (IS_ERR(segs))
-		goto out;
-
-	/* Only first segment might have ooo_okay set */
-	segs->ooo_okay = ooo_okay;
-
-	delta = htonl(oldlen + (thlen + mss));
-
-	skb = segs;
-	th = tcp_hdr(skb);
-	seq = ntohl(th->seq);
-
-	newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +
-					       (__force u32)delta));
-
-	do {
-		th->fin = th->psh = 0;
-		th->check = newcheck;
-
-		if (skb->ip_summed != CHECKSUM_PARTIAL)
-			th->check =
-			     csum_fold(csum_partial(skb_transport_header(skb),
-						    thlen, skb->csum));
-
-		seq += mss;
-		if (copy_destructor) {
-			skb->destructor = gso_skb->destructor;
-			skb->sk = gso_skb->sk;
-			/* {tcp|sock}_wfree() use exact truesize accounting :
-			 * sum(skb->truesize) MUST be exactly be gso_skb->truesize
-			 * So we account mss bytes of 'true size' for each segment.
-			 * The last segment will contain the remaining.
-			 */
-			skb->truesize = mss;
-			gso_skb->truesize -= mss;
-		}
-		skb = skb->next;
-		th = tcp_hdr(skb);
-
-		th->seq = htonl(seq);
-		th->cwr = 0;
-	} while (skb->next);
-
-	/* Following permits TCP Small Queues to work well with GSO :
-	 * The callback to TCP stack will be called at the time last frag
-	 * is freed at TX completion, and not right now when gso_skb
-	 * is freed by GSO engine
-	 */
-	if (copy_destructor) {
-		swap(gso_skb->sk, skb->sk);
-		swap(gso_skb->destructor, skb->destructor);
-		swap(gso_skb->truesize, skb->truesize);
-	}
-
-	delta = htonl(oldlen + (skb->tail - skb->transport_header) +
-		      skb->data_len);
-	th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
-				(__force u32)delta));
-	if (skb->ip_summed != CHECKSUM_PARTIAL)
-		th->check = csum_fold(csum_partial(skb_transport_header(skb),
-						   thlen, skb->csum));
-
-out:
-	return segs;
-}
-EXPORT_SYMBOL(tcp_tso_segment);
-
-struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
-{
-	struct sk_buff **pp = NULL;
-	struct sk_buff *p;
-	struct tcphdr *th;
-	struct tcphdr *th2;
-	unsigned int len;
-	unsigned int thlen;
-	__be32 flags;
-	unsigned int mss = 1;
-	unsigned int hlen;
-	unsigned int off;
-	int flush = 1;
-	int i;
-
-	off = skb_gro_offset(skb);
-	hlen = off + sizeof(*th);
-	th = skb_gro_header_fast(skb, off);
-	if (skb_gro_header_hard(skb, hlen)) {
-		th = skb_gro_header_slow(skb, hlen, off);
-		if (unlikely(!th))
-			goto out;
-	}
-
-	thlen = th->doff * 4;
-	if (thlen < sizeof(*th))
-		goto out;
-
-	hlen = off + thlen;
-	if (skb_gro_header_hard(skb, hlen)) {
-		th = skb_gro_header_slow(skb, hlen, off);
-		if (unlikely(!th))
-			goto out;
-	}
-
-	skb_gro_pull(skb, thlen);
-
-	len = skb_gro_len(skb);
-	flags = tcp_flag_word(th);
-
-	for (; (p = *head); head = &p->next) {
-		if (!NAPI_GRO_CB(p)->same_flow)
-			continue;
-
-		th2 = tcp_hdr(p);
-
-		if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
-			NAPI_GRO_CB(p)->same_flow = 0;
-			continue;
-		}
-
-		goto found;
-	}
-
-	goto out_check_final;
-
-found:
-	flush = NAPI_GRO_CB(p)->flush;
-	flush |= (__force int)(flags & TCP_FLAG_CWR);
-	flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
-		  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
-	flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
-	for (i = sizeof(*th); i < thlen; i += 4)
-		flush |= *(u32 *)((u8 *)th + i) ^
-			 *(u32 *)((u8 *)th2 + i);
-
-	mss = skb_shinfo(p)->gso_size;
-
-	flush |= (len - 1) >= mss;
-	flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
-
-	if (flush || skb_gro_receive(head, skb)) {
-		mss = 1;
-		goto out_check_final;
-	}
-
-	p = *head;
-	th2 = tcp_hdr(p);
-	tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
-
-out_check_final:
-	flush = len < mss;
-	flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH |
-					TCP_FLAG_RST | TCP_FLAG_SYN |
-					TCP_FLAG_FIN));
-
-	if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
-		pp = head;
-
-out:
-	NAPI_GRO_CB(skb)->flush |= flush;
-
-	return pp;
-}
-EXPORT_SYMBOL(tcp_gro_receive);
-
-int tcp_gro_complete(struct sk_buff *skb)
-{
-	struct tcphdr *th = tcp_hdr(skb);
-
-	skb->csum_start = skb_transport_header(skb) - skb->head;
-	skb->csum_offset = offsetof(struct tcphdr, check);
-	skb->ip_summed = CHECKSUM_PARTIAL;
-
-	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
-
-	if (th->cwr)
-		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
-
-	return 0;
-}
-EXPORT_SYMBOL(tcp_gro_complete);
-
 #ifdef CONFIG_TCP_MD5SIG
-static unsigned long tcp_md5sig_users;
-static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool;
-static DEFINE_SPINLOCK(tcp_md5sig_pool_lock);
+static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly;
+static DEFINE_MUTEX(tcp_md5sig_mutex);
 
 static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
 {
@@ -3132,30 +2899,14 @@ static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
 	free_percpu(pool);
 }
 
-void tcp_free_md5sig_pool(void)
-{
-	struct tcp_md5sig_pool __percpu *pool = NULL;
-
-	spin_lock_bh(&tcp_md5sig_pool_lock);
-	if (--tcp_md5sig_users == 0) {
-		pool = tcp_md5sig_pool;
-		tcp_md5sig_pool = NULL;
-	}
-	spin_unlock_bh(&tcp_md5sig_pool_lock);
-	if (pool)
-		__tcp_free_md5sig_pool(pool);
-}
-EXPORT_SYMBOL(tcp_free_md5sig_pool);
-
-static struct tcp_md5sig_pool __percpu *
-__tcp_alloc_md5sig_pool(struct sock *sk)
+static void __tcp_alloc_md5sig_pool(void)
 {
 	int cpu;
 	struct tcp_md5sig_pool __percpu *pool;
 
 	pool = alloc_percpu(struct tcp_md5sig_pool);
 	if (!pool)
-		return NULL;
+		return;
 
 	for_each_possible_cpu(cpu) {
 		struct crypto_hash *hash;
@@ -3166,53 +2917,27 @@ __tcp_alloc_md5sig_pool(struct sock *sk)
 
 		per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash;
 	}
-	return pool;
+	/* before setting tcp_md5sig_pool, we must commit all writes
+	 * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool()
+	 */
+	smp_wmb();
+	tcp_md5sig_pool = pool;
+	return;
 out_free:
 	__tcp_free_md5sig_pool(pool);
-	return NULL;
 }
 
-struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk)
+bool tcp_alloc_md5sig_pool(void)
 {
-	struct tcp_md5sig_pool __percpu *pool;
-	bool alloc = false;
-
-retry:
-	spin_lock_bh(&tcp_md5sig_pool_lock);
-	pool = tcp_md5sig_pool;
-	if (tcp_md5sig_users++ == 0) {
-		alloc = true;
-		spin_unlock_bh(&tcp_md5sig_pool_lock);
-	} else if (!pool) {
-		tcp_md5sig_users--;
-		spin_unlock_bh(&tcp_md5sig_pool_lock);
-		cpu_relax();
-		goto retry;
-	} else
-		spin_unlock_bh(&tcp_md5sig_pool_lock);
-
-	if (alloc) {
-		/* we cannot hold spinlock here because this may sleep. */
-		struct tcp_md5sig_pool __percpu *p;
-
-		p = __tcp_alloc_md5sig_pool(sk);
-		spin_lock_bh(&tcp_md5sig_pool_lock);
-		if (!p) {
-			tcp_md5sig_users--;
-			spin_unlock_bh(&tcp_md5sig_pool_lock);
-			return NULL;
-		}
-		pool = tcp_md5sig_pool;
-		if (pool) {
-			/* oops, it has already been assigned. */
-			spin_unlock_bh(&tcp_md5sig_pool_lock);
-			__tcp_free_md5sig_pool(p);
-		} else {
-			tcp_md5sig_pool = pool = p;
-			spin_unlock_bh(&tcp_md5sig_pool_lock);
-		}
+	if (unlikely(!tcp_md5sig_pool)) {
+		mutex_lock(&tcp_md5sig_mutex);
+
+		if (!tcp_md5sig_pool)
+			__tcp_alloc_md5sig_pool();
+
+		mutex_unlock(&tcp_md5sig_mutex);
 	}
-	return pool;
+	return tcp_md5sig_pool != NULL;
 }
 EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
 
@@ -3229,28 +2954,15 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 	struct tcp_md5sig_pool __percpu *p;
 
 	local_bh_disable();
-
-	spin_lock(&tcp_md5sig_pool_lock);
-	p = tcp_md5sig_pool;
+	p = ACCESS_ONCE(tcp_md5sig_pool);
 	if (p)
-		tcp_md5sig_users++;
-	spin_unlock(&tcp_md5sig_pool_lock);
-
-	if (p)
-		return this_cpu_ptr(p);
+		return __this_cpu_ptr(p);
 
 	local_bh_enable();
 	return NULL;
 }
 EXPORT_SYMBOL(tcp_get_md5sig_pool);
 
-void tcp_put_md5sig_pool(void)
-{
-	local_bh_enable();
-	tcp_free_md5sig_pool();
-}
-EXPORT_SYMBOL(tcp_put_md5sig_pool);
-
 int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
 			const struct tcphdr *th)
 {