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

Pull networking changes from David Miller:

 1) Get rid of the error prone NLA_PUT*() macros that used an embedded
    goto.

 2) Kill off the token-ring and MCA networking drivers, from Paul
    Gortmaker.

 3) Reduce high-order allocations made by datagram AF_UNIX sockets, from
    Eric Dumazet.

 4) Add PTP hardware clock support to IGB and IXGBE, from Richard
    Cochran and Jacob Keller.

 5) Allow users to query timestamping capabilities of a card via
    ethtool, from Richard Cochran.

 6) Add loadbalance mode to the teaming driver, from Jiri Pirko.  Part
    of this is that we can now have BPF filters not attached to sockets,
    and the loadbalancing function is calculated using one.

 7) Francois Romieu went through the network drivers removing gratuitous
    uses of netdev->base_addr, perhaps some day we can remove it
    completely but it's used for ISA probing still.

 8) Add a BPF JIT for sparc.  I know, who cares, right? :-)

 9) Move networking sysctl registry away from using the compatability
    mode interfaces in the sysctl code.  From Eric W Biederman.

10) Pavel Emelyanov added a way to save and restore TCP socket state via
    TCP_REPAIR, TCP_REPAIR_QUEUE, and TCP_QUEUE_SEQ socket options as
    well as a way to forcefully bind a socket to a port via the
    sk->sk_reuse value SK_FORCE_REUSE.  There is also a
    TCP_REPAIR_OPTIONS which allows to reinstante the TCP options
    enabled on the connection.

11) Several enhancements from Eric Dumazet that, in particular, can
    enhance splice performance on TCP sockets significantly.

     a) Reset the offset of the per-socket sendmsg page when we know
        we're the only use of the page in linear_to_page().

     b) Add facilities such that skb->data can be backed a page rather
        than SLAB kmalloc'd memory.  In particular devices which were
        receiving into linear RX buffers can now end up providing paged
        data.

    The big result is that code like splice and GRO do not have to copy
    any more.

12) Allow a pure sender to more gracefully handle ACK backlogs in TCP.
    What can happen at high rates is that the sender hasn't grown his
    receive buffer limits at all (he's not receiving data so really
    doesn't need to), but the non-data ACKs consume receive buffer
    space.

    sk_add_backlog() is too aggressive in dropping frames in this case,
    so relax it's requirements by using the receive buffer plus the send
    buffer limit as the backlog limit instead of just the former.

    Also from Eric Dumazet.

13) Add ipv6 support to L2TP, from Benjamin LaHaise, James Chapman, and
    Chris Elston.

14) Implement TCP early retransmit (RFC 5827), from Yuchung Cheng.
    Basically, we can start fast retransmit before hiting the dupack
    threshold under certain conditions.

15) New CODEL active queue management packet scheduler, from Eric
    Dumazet based upon initial work by Dave Taht.

    Basically, the big feature is that packets are dropped (or ECN bits
    are set) based upon how long packets live in the queue, rather than
    the queue length (which is what RED uses).

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1341 commits)
  drivers/net/stmmac: seq_file fix memory leak
  ipv6/exthdrs: strict Pad1 and PadN check
  USB: qmi_wwan: Add ZTE (Vodafone) K3520-Z
  USB: qmi_wwan: Add ZTE (Vodafone) K3765-Z
  USB: qmi_wwan: Make forced int 4 whitelist generic
  net/ipv4: replace simple_strtoul with kstrtoul
  net/ipv4/ipconfig: neaten __setup placement
  net: qmi_wwan: Add Vodafone/Huawei K5005 support
  net: cdc_ether: Add ZTE WWAN matches before generic Ethernet
  ipv6: use skb coalescing in reassembly
  ipv4: use skb coalescing in defragmentation
  net: introduce skb_try_coalesce()
  net:ipv6:fixed space issues relating to operators.
  net:ipv6:fixed a trailing white space issue.
  ipv6: disable GSO on sockets hitting dst_allfrag
  tg3: use netdev_alloc_frag() API
  net: napi_frags_skb() is static
  ppp: avoid false drop_monitor false positives
  ipv6: bool/const conversions phase2
  ipx: Remove spurious NULL checking in ipx_ioctl().
  ...

1 files changed, 89 insertions, 62 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7ac6423117a..803cbfe82fb 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -34,6 +34,8 @@
  *
  */
 
+#define pr_fmt(fmt) "TCP: " fmt
+
 #include <net/tcp.h>
 
 #include <linux/compiler.h>
@@ -78,9 +80,8 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
 		tp->frto_counter = 3;
 
 	tp->packets_out += tcp_skb_pcount(skb);
-	if (!prior_packets)
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-					  inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
+	if (!prior_packets || tp->early_retrans_delayed)
+		tcp_rearm_rto(sk);
 }
 
 /* SND.NXT, if window was not shrunk.
@@ -369,7 +370,7 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
 	TCP_SKB_CB(skb)->end_seq = seq;
 }
 
-static inline int tcp_urg_mode(const struct tcp_sock *tp)
+static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 {
 	return tp->snd_una != tp->snd_up;
 }
@@ -563,13 +564,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 /* Compute TCP options for SYN packets. This is not the final
  * network wire format yet.
  */
-static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
+static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 				struct tcp_out_options *opts,
 				struct tcp_md5sig_key **md5)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_cookie_values *cvp = tp->cookie_values;
-	unsigned remaining = MAX_TCP_OPTION_SPACE;
+	unsigned int remaining = MAX_TCP_OPTION_SPACE;
 	u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
 			 tcp_cookie_size_check(cvp->cookie_desired) :
 			 0;
@@ -663,15 +664,15 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 }
 
 /* Set up TCP options for SYN-ACKs. */
-static unsigned tcp_synack_options(struct sock *sk,
+static unsigned int tcp_synack_options(struct sock *sk,
 				   struct request_sock *req,
-				   unsigned mss, struct sk_buff *skb,
+				   unsigned int mss, struct sk_buff *skb,
 				   struct tcp_out_options *opts,
 				   struct tcp_md5sig_key **md5,
 				   struct tcp_extend_values *xvp)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
-	unsigned remaining = MAX_TCP_OPTION_SPACE;
+	unsigned int remaining = MAX_TCP_OPTION_SPACE;
 	u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ?
 			 xvp->cookie_plus :
 			 0;
@@ -742,13 +743,13 @@ static unsigned tcp_synack_options(struct sock *sk,
 /* Compute TCP options for ESTABLISHED sockets. This is not the
  * final wire format yet.
  */
-static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb,
+static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb,
 					struct tcp_out_options *opts,
 					struct tcp_md5sig_key **md5)
 {
 	struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL;
 	struct tcp_sock *tp = tcp_sk(sk);
-	unsigned size = 0;
+	unsigned int size = 0;
 	unsigned int eff_sacks;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -770,9 +771,9 @@ static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb,
 
 	eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
 	if (unlikely(eff_sacks)) {
-		const unsigned remaining = MAX_TCP_OPTION_SPACE - size;
+		const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
 		opts->num_sack_blocks =
-			min_t(unsigned, eff_sacks,
+			min_t(unsigned int, eff_sacks,
 			      (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
 			      TCPOLEN_SACK_PERBLOCK);
 		size += TCPOLEN_SACK_BASE_ALIGNED +
@@ -801,7 +802,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	struct tcp_sock *tp;
 	struct tcp_skb_cb *tcb;
 	struct tcp_out_options opts;
-	unsigned tcp_options_size, tcp_header_size;
+	unsigned int tcp_options_size, tcp_header_size;
 	struct tcp_md5sig_key *md5;
 	struct tcphdr *th;
 	int err;
@@ -1150,7 +1151,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 }
 
 /* Calculate MSS. Not accounting for SACKs here.  */
-int tcp_mtu_to_mss(const struct sock *sk, int pmtu)
+int tcp_mtu_to_mss(struct sock *sk, int pmtu)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1161,6 +1162,14 @@ int tcp_mtu_to_mss(const struct sock *sk, int pmtu)
 	 */
 	mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr);
 
+	/* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
+	if (icsk->icsk_af_ops->net_frag_header_len) {
+		const struct dst_entry *dst = __sk_dst_get(sk);
+
+		if (dst && dst_allfrag(dst))
+			mss_now -= icsk->icsk_af_ops->net_frag_header_len;
+	}
+
 	/* Clamp it (mss_clamp does not include tcp options) */
 	if (mss_now > tp->rx_opt.mss_clamp)
 		mss_now = tp->rx_opt.mss_clamp;
@@ -1179,7 +1188,7 @@ int tcp_mtu_to_mss(const struct sock *sk, int pmtu)
 }
 
 /* Inverse of above */
-int tcp_mss_to_mtu(const struct sock *sk, int mss)
+int tcp_mss_to_mtu(struct sock *sk, int mss)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1190,6 +1199,13 @@ int tcp_mss_to_mtu(const struct sock *sk, int mss)
 	      icsk->icsk_ext_hdr_len +
 	      icsk->icsk_af_ops->net_header_len;
 
+	/* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
+	if (icsk->icsk_af_ops->net_frag_header_len) {
+		const struct dst_entry *dst = __sk_dst_get(sk);
+
+		if (dst && dst_allfrag(dst))
+			mtu += icsk->icsk_af_ops->net_frag_header_len;
+	}
 	return mtu;
 }
 
@@ -1259,7 +1275,7 @@ unsigned int tcp_current_mss(struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct dst_entry *dst = __sk_dst_get(sk);
 	u32 mss_now;
-	unsigned header_len;
+	unsigned int header_len;
 	struct tcp_out_options opts;
 	struct tcp_md5sig_key *md5;
 
@@ -1375,33 +1391,33 @@ static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb,
 }
 
 /* Minshall's variant of the Nagle send check. */
-static inline int tcp_minshall_check(const struct tcp_sock *tp)
+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 0, if packet can be sent now without violation Nagle's rules:
+/* 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 int tcp_nagle_check(const struct tcp_sock *tp,
+static inline bool tcp_nagle_check(const struct tcp_sock *tp,
 				  const struct sk_buff *skb,
-				  unsigned mss_now, int nonagle)
+				  unsigned int mss_now, int nonagle)
 {
 	return skb->len < mss_now &&
 		((nonagle & TCP_NAGLE_CORK) ||
 		 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
 }
 
-/* Return non-zero if the Nagle test allows this packet to be
+/* Return true if the Nagle test allows this packet to be
  * sent now.
  */
-static inline int tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb,
-				 unsigned int cur_mss, int nonagle)
+static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb,
+				  unsigned int cur_mss, int nonagle)
 {
 	/* Nagle rule does not apply to frames, which sit in the middle of the
 	 * write_queue (they have no chances to get new data).
@@ -1410,24 +1426,25 @@ static inline int tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff
 	 * argument based upon the location of SKB in the send queue.
 	 */
 	if (nonagle & TCP_NAGLE_PUSH)
-		return 1;
+		return true;
 
 	/* Don't use the nagle rule for urgent data (or for the final FIN).
 	 * Nagle can be ignored during F-RTO too (see RFC4138).
 	 */
 	if (tcp_urg_mode(tp) || (tp->frto_counter == 2) ||
 	    (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
-		return 1;
+		return true;
 
 	if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 
 /* Does at least the first segment of SKB fit into the send window? */
-static inline int tcp_snd_wnd_test(const struct tcp_sock *tp, const struct sk_buff *skb,
-				   unsigned int cur_mss)
+static bool tcp_snd_wnd_test(const struct tcp_sock *tp,
+			     const struct sk_buff *skb,
+			     unsigned int cur_mss)
 {
 	u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
@@ -1460,7 +1477,7 @@ static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb,
 }
 
 /* Test if sending is allowed right now. */
-int tcp_may_send_now(struct sock *sk)
+bool tcp_may_send_now(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb = tcp_send_head(sk);
@@ -1530,7 +1547,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
  *
  * This algorithm is from John Heffner.
  */
-static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
+static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1590,11 +1607,11 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 	/* Ok, it looks like it is advisable to defer.  */
 	tp->tso_deferred = 1 | (jiffies << 1);
 
-	return 1;
+	return true;
 
 send_now:
 	tp->tso_deferred = 0;
-	return 0;
+	return false;
 }
 
 /* Create a new MTU probe if we are ready.
@@ -1736,11 +1753,11 @@ static int tcp_mtu_probe(struct sock *sk)
  * snd_up-64k-mss .. snd_up cannot be large. However, taking into
  * account rare use of URG, this is not a big flaw.
  *
- * Returns 1, if no segments are in flight and we have queued segments, but
- * cannot send anything now because of SWS or another problem.
+ * Returns true, if no segments are in flight and we have queued segments,
+ * but cannot send anything now because of SWS or another problem.
  */
-static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
-			  int push_one, gfp_t gfp)
+static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
+			   int push_one, gfp_t gfp)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
@@ -1754,7 +1771,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		/* Do MTU probing. */
 		result = tcp_mtu_probe(sk);
 		if (!result) {
-			return 0;
+			return false;
 		} else if (result > 0) {
 			sent_pkts = 1;
 		}
@@ -1813,7 +1830,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 	if (likely(sent_pkts)) {
 		tcp_cwnd_validate(sk);
-		return 0;
+		return false;
 	}
 	return !tp->packets_out && tcp_send_head(sk);
 }
@@ -2012,22 +2029,22 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 }
 
 /* Check if coalescing SKBs is legal. */
-static int tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb)
+static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb)
 {
 	if (tcp_skb_pcount(skb) > 1)
-		return 0;
+		return false;
 	/* TODO: SACK collapsing could be used to remove this condition */
 	if (skb_shinfo(skb)->nr_frags != 0)
-		return 0;
+		return false;
 	if (skb_cloned(skb))
-		return 0;
+		return false;
 	if (skb == tcp_send_head(sk))
-		return 0;
+		return false;
 	/* Some heurestics for collapsing over SACK'd could be invented */
 	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
 
 /* Collapse packets in the retransmit queue to make to create
@@ -2038,7 +2055,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb = to, *tmp;
-	int first = 1;
+	bool first = true;
 
 	if (!sysctl_tcp_retrans_collapse)
 		return;
@@ -2052,7 +2069,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 		space -= skb->len;
 
 		if (first) {
-			first = 0;
+			first = false;
 			continue;
 		}
 
@@ -2167,8 +2184,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 
 #if FASTRETRANS_DEBUG > 0
 		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
-			if (net_ratelimit())
-				printk(KERN_DEBUG "retrans_out leaked.\n");
+			net_dbg_ratelimited("retrans_out leaked\n");
 		}
 #endif
 		if (!tp->retrans_out)
@@ -2193,18 +2209,18 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 /* Check if we forward retransmits are possible in the current
  * window/congestion state.
  */
-static int tcp_can_forward_retransmit(struct sock *sk)
+static bool tcp_can_forward_retransmit(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Forward retransmissions are possible only during Recovery. */
 	if (icsk->icsk_ca_state != TCP_CA_Recovery)
-		return 0;
+		return false;
 
 	/* No forward retransmissions in Reno are possible. */
 	if (tcp_is_reno(tp))
-		return 0;
+		return false;
 
 	/* Yeah, we have to make difficult choice between forward transmission
 	 * and retransmission... Both ways have their merits...
@@ -2215,9 +2231,9 @@ static int tcp_can_forward_retransmit(struct sock *sk)
 	 */
 
 	if (tcp_may_send_now(sk))
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
 
 /* This gets called after a retransmit timeout, and the initially
@@ -2402,7 +2418,7 @@ int tcp_send_synack(struct sock *sk)
 
 	skb = tcp_write_queue_head(sk);
 	if (skb == NULL || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
-		printk(KERN_DEBUG "tcp_send_synack: wrong queue state\n");
+		pr_debug("%s: wrong queue state\n", __func__);
 		return -EFAULT;
 	}
 	if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) {
@@ -2562,7 +2578,7 @@ 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. */
-static void tcp_connect_init(struct sock *sk)
+void tcp_connect_init(struct sock *sk)
 {
 	const struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2617,9 +2633,12 @@ static void tcp_connect_init(struct sock *sk)
 	tp->snd_una = tp->write_seq;
 	tp->snd_sml = tp->write_seq;
 	tp->snd_up = tp->write_seq;
-	tp->rcv_nxt = 0;
-	tp->rcv_wup = 0;
-	tp->copied_seq = 0;
+	tp->snd_nxt = tp->write_seq;
+
+	if (likely(!tp->repair))
+		tp->rcv_nxt = 0;
+	tp->rcv_wup = tp->rcv_nxt;
+	tp->copied_seq = tp->rcv_nxt;
 
 	inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
 	inet_csk(sk)->icsk_retransmits = 0;
@@ -2642,7 +2661,6 @@ int tcp_connect(struct sock *sk)
 	/* Reserve space for headers. */
 	skb_reserve(buff, MAX_TCP_HEADER);
 
-	tp->snd_nxt = tp->write_seq;
 	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
 	TCP_ECN_send_syn(sk, buff);
 
@@ -2791,6 +2809,15 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 	return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
 }
 
+void tcp_send_window_probe(struct sock *sk)
+{
+	if (sk->sk_state == TCP_ESTABLISHED) {
+		tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
+		tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
+		tcp_xmit_probe_skb(sk, 0);
+	}
+}
+
 /* Initiate keepalive or window probe from timer. */
 int tcp_write_wakeup(struct sock *sk)
 {