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

Pull networking updates from David Miller:

 1) BPF debugger and asm tool by Daniel Borkmann.

 2) Speed up create/bind in AF_PACKET, also from Daniel Borkmann.

 3) Correct reciprocal_divide and update users, from Hannes Frederic
    Sowa and Daniel Borkmann.

 4) Currently we only have a "set" operation for the hw timestamp socket
    ioctl, add a "get" operation to match.  From Ben Hutchings.

 5) Add better trace events for debugging driver datapath problems, also
    from Ben Hutchings.

 6) Implement auto corking in TCP, from Eric Dumazet.  Basically, if we
    have a small send and a previous packet is already in the qdisc or
    device queue, defer until TX completion or we get more data.

 7) Allow userspace to manage ipv6 temporary addresses, from Jiri Pirko.

 8) Add a qdisc bypass option for AF_PACKET sockets, from Daniel
    Borkmann.

 9) Share IP header compression code between Bluetooth and IEEE802154
    layers, from Jukka Rissanen.

10) Fix ipv6 router reachability probing, from Jiri Benc.

11) Allow packets to be captured on macvtap devices, from Vlad Yasevich.

12) Support tunneling in GRO layer, from Jerry Chu.

13) Allow bonding to be configured fully using netlink, from Scott
    Feldman.

14) Allow AF_PACKET users to obtain the VLAN TPID, just like they can
    already get the TCI.  From Atzm Watanabe.

15) New "Heavy Hitter" qdisc, from Terry Lam.

16) Significantly improve the IPSEC support in pktgen, from Fan Du.

17) Allow ipv4 tunnels to cache routes, just like sockets.  From Tom
    Herbert.

18) Add Proportional Integral Enhanced packet scheduler, from Vijay
    Subramanian.

19) Allow openvswitch to mmap'd netlink, from Thomas Graf.

20) Key TCP metrics blobs also by source address, not just destination
    address.  From Christoph Paasch.

21) Support 10G in generic phylib.  From Andy Fleming.

22) Try to short-circuit GRO flow compares using device provided RX
    hash, if provided.  From Tom Herbert.

The wireless and netfilter folks have been busy little bees too.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2064 commits)
  net/cxgb4: Fix referencing freed adapter
  ipv6: reallocate addrconf router for ipv6 address when lo device up
  fib_frontend: fix possible NULL pointer dereference
  rtnetlink: remove IFLA_BOND_SLAVE definition
  rtnetlink: remove check for fill_slave_info in rtnl_have_link_slave_info
  qlcnic: update version to 5.3.55
  qlcnic: Enhance logic to calculate msix vectors.
  qlcnic: Refactor interrupt coalescing code for all adapters.
  qlcnic: Update poll controller code path
  qlcnic: Interrupt code cleanup
  qlcnic: Enhance Tx timeout debugging.
  qlcnic: Use bool for rx_mac_learn.
  bonding: fix u64 division
  rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC
  sfc: Use the correct maximum TX DMA ring size for SFC9100
  Add Shradha Shah as the sfc driver maintainer.
  net/vxlan: Share RX skb de-marking and checksum checks with ovs
  tulip: cleanup by using ARRAY_SIZE()
  ip_tunnel: clear IPCB in ip_tunnel_xmit() in case dst_link_failure() is called
  net/cxgb4: Don't retrieve stats during recovery
  ...

1 files changed, 81 insertions, 60 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7820f3a7dd7..03d26b85eab 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -363,15 +363,17 @@ static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
  */
 static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
 {
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+
 	skb->ip_summed = CHECKSUM_PARTIAL;
 	skb->csum = 0;
 
 	TCP_SKB_CB(skb)->tcp_flags = flags;
 	TCP_SKB_CB(skb)->sacked = 0;
 
-	skb_shinfo(skb)->gso_segs = 1;
-	skb_shinfo(skb)->gso_size = 0;
-	skb_shinfo(skb)->gso_type = 0;
+	shinfo->gso_segs = 1;
+	shinfo->gso_size = 0;
+	shinfo->gso_type = 0;
 
 	TCP_SKB_CB(skb)->seq = seq;
 	if (flags & (TCPHDR_SYN | TCPHDR_FIN))
@@ -406,7 +408,7 @@ struct tcp_out_options {
  * Beware: Something in the Internet is very sensitive to the ordering of
  * TCP options, we learned this through the hard way, so be careful here.
  * Luckily we can at least blame others for their non-compliance but from
- * inter-operatibility perspective it seems that we're somewhat stuck with
+ * inter-operability perspective it seems that we're somewhat stuck with
  * the ordering which we have been using if we want to keep working with
  * those broken things (not that it currently hurts anybody as there isn't
  * particular reason why the ordering would need to be changed).
@@ -679,7 +681,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
  *
  * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb
  * needs to be reallocated in a driver.
- * The invariant being skb->truesize substracted from sk->sk_wmem_alloc
+ * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc
  *
  * Since transmit from skb destructor is forbidden, we use a tasklet
  * to process all sockets that eventually need to send more skbs.
@@ -699,9 +701,9 @@ static void tcp_tsq_handler(struct sock *sk)
 		tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
 }
 /*
- * One tasklest per cpu tries to send more skbs.
+ * One tasklet per cpu tries to send more skbs.
  * We run in tasklet context but need to disable irqs when
- * transfering tsq->head because tcp_wfree() might
+ * transferring tsq->head because tcp_wfree() might
  * interrupt us (non NAPI drivers)
  */
 static void tcp_tasklet_func(unsigned long data)
@@ -795,7 +797,7 @@ void __init tcp_tasklet_init(void)
 
 /*
  * Write buffer destructor automatically called from kfree_skb.
- * We cant xmit new skbs from this context, as we might already
+ * We can't xmit new skbs from this context, as we might already
  * hold qdisc lock.
  */
 void tcp_wfree(struct sk_buff *skb)
@@ -986,6 +988,8 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
 				 unsigned int mss_now)
 {
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+
 	/* Make sure we own this skb before messing gso_size/gso_segs */
 	WARN_ON_ONCE(skb_cloned(skb));
 
@@ -993,13 +997,13 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
 		/* Avoid the costly divide in the normal
 		 * non-TSO case.
 		 */
-		skb_shinfo(skb)->gso_segs = 1;
-		skb_shinfo(skb)->gso_size = 0;
-		skb_shinfo(skb)->gso_type = 0;
+		shinfo->gso_segs = 1;
+		shinfo->gso_size = 0;
+		shinfo->gso_type = 0;
 	} else {
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now);
-		skb_shinfo(skb)->gso_size = mss_now;
-		skb_shinfo(skb)->gso_type = sk->sk_gso_type;
+		shinfo->gso_segs = DIV_ROUND_UP(skb->len, mss_now);
+		shinfo->gso_size = mss_now;
+		shinfo->gso_type = sk->sk_gso_type;
 	}
 }
 
@@ -1146,6 +1150,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
  */
 static void __pskb_trim_head(struct sk_buff *skb, int len)
 {
+	struct skb_shared_info *shinfo;
 	int i, k, eat;
 
 	eat = min_t(int, len, skb_headlen(skb));
@@ -1157,23 +1162,24 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 	}
 	eat = len;
 	k = 0;
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
+	shinfo = skb_shinfo(skb);
+	for (i = 0; i < shinfo->nr_frags; i++) {
+		int size = skb_frag_size(&shinfo->frags[i]);
 
 		if (size <= eat) {
 			skb_frag_unref(skb, i);
 			eat -= size;
 		} else {
-			skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
+			shinfo->frags[k] = shinfo->frags[i];
 			if (eat) {
-				skb_shinfo(skb)->frags[k].page_offset += eat;
-				skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat);
+				shinfo->frags[k].page_offset += eat;
+				skb_frag_size_sub(&shinfo->frags[k], eat);
 				eat = 0;
 			}
 			k++;
 		}
 	}
-	skb_shinfo(skb)->nr_frags = k;
+	shinfo->nr_frags = k;
 
 	skb_reset_tail_pointer(skb);
 	skb->data_len -= len;
@@ -1378,23 +1384,51 @@ static void tcp_cwnd_validate(struct sock *sk)
 	}
 }
 
-/* Returns the portion of skb which can be sent right away without
- * introducing MSS oddities to segment boundaries. In rare cases where
- * mss_now != mss_cache, we will request caller to create a small skb
- * per input skb which could be mostly avoided here (if desired).
- *
- * We explicitly want to create a request for splitting write queue tail
- * to a small skb for Nagle purposes while avoiding unnecessary modulos,
- * thus all the complexity (cwnd_len is always MSS multiple which we
- * return whenever allowed by the other factors). Basically we need the
- * modulo only when the receiver window alone is the limiting factor or
- * when we would be allowed to send the split-due-to-Nagle skb fully.
+/* Minshall's variant of the Nagle send check. */
+static bool tcp_minshall_check(const struct tcp_sock *tp)
+{
+	return after(tp->snd_sml, tp->snd_una) &&
+		!after(tp->snd_sml, tp->snd_nxt);
+}
+
+/* Update snd_sml if this skb is under mss
+ * Note that a TSO packet might end with a sub-mss segment
+ * The test is really :
+ * if ((skb->len % mss) != 0)
+ *        tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
+ * But we can avoid doing the divide again given we already have
+ *  skb_pcount = skb->len / mss_now
+ */
+static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now,
+				const struct sk_buff *skb)
+{
+	if (skb->len < tcp_skb_pcount(skb) * mss_now)
+		tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
+}
+
+/* Return false, if packet can be sent now without violation Nagle's rules:
+ * 1. It is full sized. (provided by caller in %partial bool)
+ * 2. Or it contains FIN. (already checked by caller)
+ * 3. Or TCP_CORK is not set, and TCP_NODELAY is set.
+ * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
+ *    With Minshall's modification: all sent small packets are ACKed.
  */
-static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb,
-					unsigned int mss_now, unsigned int max_segs)
+static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
+			    unsigned int mss_now, int nonagle)
+{
+	return partial &&
+		((nonagle & TCP_NAGLE_CORK) ||
+		 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
+}
+/* Returns the portion of skb which can be sent right away */
+static unsigned int tcp_mss_split_point(const struct sock *sk,
+					const struct sk_buff *skb,
+					unsigned int mss_now,
+					unsigned int max_segs,
+					int nonagle)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	u32 needed, window, max_len;
+	u32 partial, needed, window, max_len;
 
 	window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
 	max_len = mss_now * max_segs;
@@ -1407,7 +1441,15 @@ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_b
 	if (max_len <= needed)
 		return max_len;
 
-	return needed - needed % mss_now;
+	partial = needed % mss_now;
+	/* If last segment is not a full MSS, check if Nagle rules allow us
+	 * to include this last segment in this skb.
+	 * Otherwise, we'll split the skb at last MSS boundary
+	 */
+	if (tcp_nagle_check(partial != 0, tp, mss_now, nonagle))
+		return needed - partial;
+
+	return needed;
 }
 
 /* Can at least one segment of SKB be sent right now, according to the
@@ -1447,28 +1489,6 @@ static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb,
 	return tso_segs;
 }
 
-/* Minshall's variant of the Nagle send check. */
-static inline bool tcp_minshall_check(const struct tcp_sock *tp)
-{
-	return after(tp->snd_sml, tp->snd_una) &&
-		!after(tp->snd_sml, tp->snd_nxt);
-}
-
-/* Return false, if packet can be sent now without violation Nagle's rules:
- * 1. It is full sized.
- * 2. Or it contains FIN. (already checked by caller)
- * 3. Or TCP_CORK is not set, and TCP_NODELAY is set.
- * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
- *    With Minshall's modification: all sent small packets are ACKed.
- */
-static inline bool tcp_nagle_check(const struct tcp_sock *tp,
-				  const struct sk_buff *skb,
-				  unsigned int mss_now, int nonagle)
-{
-	return skb->len < mss_now &&
-		((nonagle & TCP_NAGLE_CORK) ||
-		 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
-}
 
 /* Return true if the Nagle test allows this packet to be
  * sent now.
@@ -1489,7 +1509,7 @@ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buf
 	if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
 		return true;
 
-	if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
+	if (!tcp_nagle_check(skb->len < cur_mss, tp, cur_mss, nonagle))
 		return true;
 
 	return false;
@@ -1892,7 +1912,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			limit = tcp_mss_split_point(sk, skb, mss_now,
 						    min_t(unsigned int,
 							  cwnd_quota,
-							  sk->sk_gso_max_segs));
+							  sk->sk_gso_max_segs),
+						    nonagle);
 
 		if (skb->len > limit &&
 		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
@@ -2756,7 +2777,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 EXPORT_SYMBOL(tcp_make_synack);
 
 /* Do all connect socket setups that can be done AF independent. */
-void tcp_connect_init(struct sock *sk)
+static void tcp_connect_init(struct sock *sk)
 {
 	const struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_sock *tp = tcp_sk(sk);