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

Pull networking updates from David Miller:

 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.

 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
    Benniston.

 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
    Mork.

 4) BPF now has a "random" opcode, from Chema Gonzalez.

 5) Add more BPF documentation and improve test framework, from Daniel
    Borkmann.

 6) Support TCP fastopen over ipv6, from Daniel Lee.

 7) Add software TSO helper functions and use them to support software
    TSO in mvneta and mv643xx_eth drivers.  From Ezequiel Garcia.

 8) Support software TSO in fec driver too, from Nimrod Andy.

 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.

10) Handle broadcasts more gracefully over macvlan when there are large
    numbers of interfaces configured, from Herbert Xu.

11) Allow more control over fwmark used for non-socket based responses,
    from Lorenzo Colitti.

12) Do TCP congestion window limiting based upon measurements, from Neal
    Cardwell.

13) Support busy polling in SCTP, from Neal Horman.

14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.

15) Bridge promisc mode handling improvements from Vlad Yasevich.

16) Don't use inetpeer entries to implement ID generation any more, it
    performs poorly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
  tcp: fixing TLP's FIN recovery
  net: fec: Add software TSO support
  net: fec: Add Scatter/gather support
  net: fec: Increase buffer descriptor entry number
  net: fec: Factorize feature setting
  net: fec: Enable IP header hardware checksum
  net: fec: Factorize the .xmit transmit function
  bridge: fix compile error when compiling without IPv6 support
  bridge: fix smatch warning / potential null pointer dereference
  via-rhine: fix full-duplex with autoneg disable
  bnx2x: Enlarge the dorq threshold for VFs
  bnx2x: Check for UNDI in uncommon branch
  bnx2x: Fix 1G-baseT link
  bnx2x: Fix link for KR with swapped polarity lane
  sctp: Fix sk_ack_backlog wrap-around problem
  net/core: Add VF link state control policy
  net/fsl: xgmac_mdio is dependent on OF_MDIO
  net/fsl: Make xgmac_mdio read error message useful
  net_sched: drr: warn when qdisc is not work conserving
  ...

1 files changed, 209 insertions, 10 deletions

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f195d9316e55..62e48cf84e60 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -72,25 +72,224 @@ error:		kfree(ctx);
 	return err;
 }
 
-/* Computes the fastopen cookie for the IP path.
- * The path is a 128 bits long (pad with zeros for IPv4).
- *
- * The caller must check foc->len to determine if a valid cookie
- * has been generated successfully.
-*/
-void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
-			     struct tcp_fastopen_cookie *foc)
+static bool __tcp_fastopen_cookie_gen(const void *path,
+				      struct tcp_fastopen_cookie *foc)
 {
-	__be32 path[4] = { src, dst, 0, 0 };
 	struct tcp_fastopen_context *ctx;
+	bool ok = false;
 
 	tcp_fastopen_init_key_once(true);
 
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
-		crypto_cipher_encrypt_one(ctx->tfm, foc->val, (__u8 *)path);
+		crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
 		foc->len = TCP_FASTOPEN_COOKIE_SIZE;
+		ok = true;
 	}
 	rcu_read_unlock();
+	return ok;
+}
+
+/* Generate the fastopen cookie by doing aes128 encryption on both
+ * the source and destination addresses. Pad 0s for IPv4 or IPv4-mapped-IPv6
+ * addresses. For the longer IPv6 addresses use CBC-MAC.
+ *
+ * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
+ */
+static bool tcp_fastopen_cookie_gen(struct request_sock *req,
+				    struct sk_buff *syn,
+				    struct tcp_fastopen_cookie *foc)
+{
+	if (req->rsk_ops->family == AF_INET) {
+		const struct iphdr *iph = ip_hdr(syn);
+
+		__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
+		return __tcp_fastopen_cookie_gen(path, foc);
+	}
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (req->rsk_ops->family == AF_INET6) {
+		const struct ipv6hdr *ip6h = ipv6_hdr(syn);
+		struct tcp_fastopen_cookie tmp;
+
+		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
+			struct in6_addr *buf = (struct in6_addr *) tmp.val;
+			int i = 4;
+
+			for (i = 0; i < 4; i++)
+				buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
+			return __tcp_fastopen_cookie_gen(buf, foc);
+		}
+	}
+#endif
+	return false;
+}
+
+static bool tcp_fastopen_create_child(struct sock *sk,
+				      struct sk_buff *skb,
+				      struct dst_entry *dst,
+				      struct request_sock *req)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
+	struct sock *child;
+
+	req->num_retrans = 0;
+	req->num_timeout = 0;
+	req->sk = NULL;
+
+	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
+	if (child == NULL)
+		return false;
+
+	spin_lock(&queue->fastopenq->lock);
+	queue->fastopenq->qlen++;
+	spin_unlock(&queue->fastopenq->lock);
+
+	/* Initialize the child socket. Have to fix some values to take
+	 * into account the child is a Fast Open socket and is created
+	 * only out of the bits carried in the SYN packet.
+	 */
+	tp = tcp_sk(child);
+
+	tp->fastopen_rsk = req;
+	/* Do a hold on the listner sk so that if the listener is being
+	 * closed, the child that has been accepted can live on and still
+	 * access listen_lock.
+	 */
+	sock_hold(sk);
+	tcp_rsk(req)->listener = sk;
+
+	/* RFC1323: The window in SYN & SYN/ACK segments is never
+	 * scaled. So correct it appropriately.
+	 */
+	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+
+	/* Activate the retrans timer so that SYNACK can be retransmitted.
+	 * The request socket is not added to the SYN table of the parent
+	 * because it's been added to the accept queue directly.
+	 */
+	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
+				  TCP_TIMEOUT_INIT, TCP_RTO_MAX);
+
+	/* Add the child socket directly into the accept queue */
+	inet_csk_reqsk_queue_add(sk, req, child);
+
+	/* Now finish processing the fastopen child socket. */
+	inet_csk(child)->icsk_af_ops->rebuild_header(child);
+	tcp_init_congestion_control(child);
+	tcp_mtup_init(child);
+	tcp_init_metrics(child);
+	tcp_init_buffer_space(child);
+
+	/* Queue the data carried in the SYN packet. We need to first
+	 * bump skb's refcnt because the caller will attempt to free it.
+	 *
+	 * XXX (TFO) - we honor a zero-payload TFO request for now,
+	 * (any reason not to?) but no need to queue the skb since
+	 * there is no data. How about SYN+FIN?
+	 */
+	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) {
+		skb = skb_get(skb);
+		skb_dst_drop(skb);
+		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
+		skb_set_owner_r(skb, child);
+		__skb_queue_tail(&child->sk_receive_queue, skb);
+		tp->syn_data_acked = 1;
+	}
+	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+	sk->sk_data_ready(sk);
+	bh_unlock_sock(child);
+	sock_put(child);
+	WARN_ON(req->sk == NULL);
+	return true;
+}
+EXPORT_SYMBOL(tcp_fastopen_create_child);
+
+static bool tcp_fastopen_queue_check(struct sock *sk)
+{
+	struct fastopen_queue *fastopenq;
+
+	/* Make sure the listener has enabled fastopen, and we don't
+	 * exceed the max # of pending TFO requests allowed before trying
+	 * to validating the cookie in order to avoid burning CPU cycles
+	 * unnecessarily.
+	 *
+	 * XXX (TFO) - The implication of checking the max_qlen before
+	 * processing a cookie request is that clients can't differentiate
+	 * between qlen overflow causing Fast Open to be disabled
+	 * temporarily vs a server not supporting Fast Open at all.
+	 */
+	fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
+	if (fastopenq == NULL || fastopenq->max_qlen == 0)
+		return false;
+
+	if (fastopenq->qlen >= fastopenq->max_qlen) {
+		struct request_sock *req1;
+		spin_lock(&fastopenq->lock);
+		req1 = fastopenq->rskq_rst_head;
+		if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
+			spin_unlock(&fastopenq->lock);
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
+			return false;
+		}
+		fastopenq->rskq_rst_head = req1->dl_next;
+		fastopenq->qlen--;
+		spin_unlock(&fastopenq->lock);
+		reqsk_free(req1);
+	}
+	return true;
+}
+
+/* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
+ * may be updated and return the client in the SYN-ACK later. E.g., Fast Open
+ * cookie request (foc->len == 0).
+ */
+bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
+		      struct request_sock *req,
+		      struct tcp_fastopen_cookie *foc,
+		      struct dst_entry *dst)
+{
+	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
+	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
+
+	if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+	      (syn_data || foc->len >= 0) &&
+	      tcp_fastopen_queue_check(sk))) {
+		foc->len = -1;
+		return false;
+	}
+
+	if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+		goto fastopen;
+
+	if (tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+	    foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
+	    foc->len == valid_foc.len &&
+	    !memcmp(foc->val, valid_foc.val, foc->len)) {
+		/* Cookie is valid. Create a (full) child socket to accept
+		 * the data in SYN before returning a SYN-ACK to ack the
+		 * data. If we fail to create the socket, fall back and
+		 * ack the ISN only but includes the same cookie.
+		 *
+		 * Note: Data-less SYN with valid cookie is allowed to send
+		 * data in SYN_RECV state.
+		 */
+fastopen:
+		if (tcp_fastopen_create_child(sk, skb, dst, req)) {
+			foc->len = -1;
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPFASTOPENPASSIVE);
+			return true;
+		}
+	}
+
+	NET_INC_STATS_BH(sock_net(sk), foc->len ?
+			 LINUX_MIB_TCPFASTOPENPASSIVEFAIL :
+			 LINUX_MIB_TCPFASTOPENCOOKIEREQD);
+	*foc = valid_foc;
+	return false;
 }
+EXPORT_SYMBOL(tcp_try_fastopen);