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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

6 files changed, 165 insertions, 54 deletions

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 7b16704..0095b9a 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -441,8 +441,7 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr,
  *   - sends a call data packet
  *   - may send an abort (abort code in control data)
  */
-static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock,
-			 struct msghdr *m, size_t len)
+static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 {
 	struct rxrpc_transport *trans;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
@@ -482,7 +481,7 @@ static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock,
 	switch (rx->sk.sk_state) {
 	case RXRPC_SERVER_LISTENING:
 		if (!m->msg_name) {
-			ret = rxrpc_server_sendmsg(iocb, rx, m, len);
+			ret = rxrpc_server_sendmsg(rx, m, len);
 			break;
 		}
 	case RXRPC_SERVER_BOUND:
@@ -492,7 +491,7 @@ static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock,
 			break;
 		}
 	case RXRPC_CLIENT_CONNECTED:
-		ret = rxrpc_client_sendmsg(iocb, rx, trans, m, len);
+		ret = rxrpc_client_sendmsg(rx, trans, m, len);
 		break;
 	default:
 		ret = -ENOTCONN;
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c
index 481f89f..4505a69 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/ar-input.c
@@ -28,7 +28,7 @@
 const char *rxrpc_pkts[] = {
 	"?00",
 	"DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG",
-	"?09", "?10", "?11", "?12", "?13", "?14", "?15"
+	"?09", "?10", "?11", "?12", "VERSION", "?14", "?15"
 };
 
 /*
@@ -593,6 +593,20 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn,
 	rxrpc_queue_conn(conn);
 }
 
+/*
+ * post endpoint-level events to the local endpoint
+ * - this includes debug and version messages
+ */
+static void rxrpc_post_packet_to_local(struct rxrpc_local *local,
+				       struct sk_buff *skb)
+{
+	_enter("%p,%p", local, skb);
+
+	atomic_inc(&local->usage);
+	skb_queue_tail(&local->event_queue, skb);
+	rxrpc_queue_work(&local->event_processor);
+}
+
 static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local,
 					       struct sk_buff *skb,
 					       struct rxrpc_skb_priv *sp)
@@ -699,6 +713,11 @@ void rxrpc_data_ready(struct sock *sk)
 		goto bad_message;
 	}
 
+	if (sp->hdr.type == RXRPC_PACKET_TYPE_VERSION) {
+		rxrpc_post_packet_to_local(local, skb);
+		goto out;
+	}
+	
 	if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
 	    (sp->hdr.callNumber == 0 || sp->hdr.seq == 0))
 		goto bad_message;
@@ -731,6 +750,8 @@ void rxrpc_data_ready(struct sock *sk)
 		else
 			goto cant_route_call;
 	}
+
+out:
 	rxrpc_put_local(local);
 	return;
 
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index ba9fd36..aef1bd2 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -152,11 +152,13 @@ struct rxrpc_local {
 	struct work_struct	destroyer;	/* endpoint destroyer */
 	struct work_struct	acceptor;	/* incoming call processor */
 	struct work_struct	rejecter;	/* packet reject writer */
+	struct work_struct	event_processor; /* endpoint event processor */
 	struct list_head	services;	/* services listening on this endpoint */
 	struct list_head	link;		/* link in endpoint list */
 	struct rw_semaphore	defrag_sem;	/* control re-enablement of IP DF bit */
 	struct sk_buff_head	accept_queue;	/* incoming calls awaiting acceptance */
 	struct sk_buff_head	reject_queue;	/* packets awaiting rejection */
+	struct sk_buff_head	event_queue;	/* endpoint event packets awaiting processing */
 	spinlock_t		lock;		/* access lock */
 	rwlock_t		services_lock;	/* lock for services list */
 	atomic_t		usage;
@@ -548,10 +550,9 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t,
 extern unsigned rxrpc_resend_timeout;
 
 int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *);
-int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *,
-			 struct rxrpc_transport *, struct msghdr *, size_t);
-int rxrpc_server_sendmsg(struct kiocb *, struct rxrpc_sock *, struct msghdr *,
-			 size_t);
+int rxrpc_client_sendmsg(struct rxrpc_sock *, struct rxrpc_transport *,
+			 struct msghdr *, size_t);
+int rxrpc_server_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
 
 /*
  * ar-peer.c
@@ -572,8 +573,7 @@ extern const struct file_operations rxrpc_connection_seq_fops;
  * ar-recvmsg.c
  */
 void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *);
-int rxrpc_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t,
-		  int);
+int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
 
 /*
  * ar-security.c
diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c
index 87f7135..ca904ed 100644
--- a/net/rxrpc/ar-local.c
+++ b/net/rxrpc/ar-local.c
@@ -13,16 +13,22 @@
 #include <linux/net.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
+#include <linux/udp.h>
+#include <linux/ip.h>
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
+#include <generated/utsrelease.h>
 #include "ar-internal.h"
 
+static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC";
+
 static LIST_HEAD(rxrpc_locals);
 DEFINE_RWLOCK(rxrpc_local_lock);
 static DECLARE_RWSEM(rxrpc_local_sem);
 static DECLARE_WAIT_QUEUE_HEAD(rxrpc_local_wq);
 
 static void rxrpc_destroy_local(struct work_struct *work);
+static void rxrpc_process_local_events(struct work_struct *work);
 
 /*
  * allocate a new local
@@ -37,11 +43,13 @@ struct rxrpc_local *rxrpc_alloc_local(struct sockaddr_rxrpc *srx)
 		INIT_WORK(&local->destroyer, &rxrpc_destroy_local);
 		INIT_WORK(&local->acceptor, &rxrpc_accept_incoming_calls);
 		INIT_WORK(&local->rejecter, &rxrpc_reject_packets);
+		INIT_WORK(&local->event_processor, &rxrpc_process_local_events);
 		INIT_LIST_HEAD(&local->services);
 		INIT_LIST_HEAD(&local->link);
 		init_rwsem(&local->defrag_sem);
 		skb_queue_head_init(&local->accept_queue);
 		skb_queue_head_init(&local->reject_queue);
+		skb_queue_head_init(&local->event_queue);
 		spin_lock_init(&local->lock);
 		rwlock_init(&local->services_lock);
 		atomic_set(&local->usage, 1);
@@ -264,10 +272,12 @@ static void rxrpc_destroy_local(struct work_struct *work)
 	ASSERT(list_empty(&local->services));
 	ASSERT(!work_pending(&local->acceptor));
 	ASSERT(!work_pending(&local->rejecter));
+	ASSERT(!work_pending(&local->event_processor));
 
 	/* finish cleaning up the local descriptor */
 	rxrpc_purge_queue(&local->accept_queue);
 	rxrpc_purge_queue(&local->reject_queue);
+	rxrpc_purge_queue(&local->event_queue);
 	kernel_sock_shutdown(local->socket, SHUT_RDWR);
 	sock_release(local->socket);
 
@@ -308,3 +318,91 @@ void __exit rxrpc_destroy_all_locals(void)
 
 	_leave("");
 }
+
+/*
+ * Reply to a version request
+ */
+static void rxrpc_send_version_request(struct rxrpc_local *local,
+				       struct rxrpc_header *hdr,
+				       struct sk_buff *skb)
+{
+	struct sockaddr_in sin;
+	struct msghdr msg;
+	struct kvec iov[2];
+	size_t len;
+	int ret;
+
+	_enter("");
+
+	sin.sin_family = AF_INET;
+	sin.sin_port = udp_hdr(skb)->source;
+	sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
+
+	msg.msg_name	= &sin;
+	msg.msg_namelen	= sizeof(sin);
+	msg.msg_control	= NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags	= 0;
+
+	hdr->seq	= 0;
+	hdr->serial	= 0;
+	hdr->type	= RXRPC_PACKET_TYPE_VERSION;
+	hdr->flags	= RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED);
+	hdr->userStatus	= 0;
+	hdr->_rsvd	= 0;
+
+	iov[0].iov_base	= hdr;
+	iov[0].iov_len	= sizeof(*hdr);
+	iov[1].iov_base	= (char *)rxrpc_version_string;
+	iov[1].iov_len	= sizeof(rxrpc_version_string);
+
+	len = iov[0].iov_len + iov[1].iov_len;
+
+	_proto("Tx VERSION (reply)");
+
+	ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
+	if (ret < 0)
+		_debug("sendmsg failed: %d", ret);
+
+	_leave("");
+}
+
+/*
+ * Process event packets targetted at a local endpoint.
+ */
+static void rxrpc_process_local_events(struct work_struct *work)
+{
+	struct rxrpc_local *local = container_of(work, struct rxrpc_local, event_processor);
+	struct sk_buff *skb;
+	char v;
+
+	_enter("");
+
+	atomic_inc(&local->usage);
+	
+	while ((skb = skb_dequeue(&local->event_queue))) {
+		struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+		kdebug("{%d},{%u}", local->debug_id, sp->hdr.type);
+
+		switch (sp->hdr.type) {
+		case RXRPC_PACKET_TYPE_VERSION:
+			if (skb_copy_bits(skb, 0, &v, 1) < 0)
+				return;
+			_proto("Rx VERSION { %02x }", v);
+			if (v == 0)
+				rxrpc_send_version_request(local, &sp->hdr, skb);
+			break;
+
+		default:
+			/* Just ignore anything we don't understand */
+			break;
+		}
+
+		rxrpc_put_local(local);
+		rxrpc_free_skb(skb);
+	}
+
+	rxrpc_put_local(local);
+	_leave("");
+}
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index 8331c95..c004280 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -23,8 +23,7 @@
  */
 unsigned rxrpc_resend_timeout = 4 * HZ;
 
-static int rxrpc_send_data(struct kiocb *iocb,
-			   struct rxrpc_sock *rx,
+static int rxrpc_send_data(struct rxrpc_sock *rx,
 			   struct rxrpc_call *call,
 			   struct msghdr *msg, size_t len);
 
@@ -129,9 +128,8 @@ static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code)
  * - caller holds the socket locked
  * - the socket may be either a client socket or a server socket
  */
-int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
-			 struct rxrpc_transport *trans, struct msghdr *msg,
-			 size_t len)
+int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans,
+			 struct msghdr *msg, size_t len)
 {
 	struct rxrpc_conn_bundle *bundle;
 	enum rxrpc_command cmd;
@@ -191,7 +189,7 @@ int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
 		/* request phase complete for this client call */
 		ret = -EPROTO;
 	} else {
-		ret = rxrpc_send_data(iocb, rx, call, msg, len);
+		ret = rxrpc_send_data(rx, call, msg, len);
 	}
 
 	rxrpc_put_call(call);
@@ -232,7 +230,7 @@ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg,
 		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
 		ret = -EPROTO; /* request phase complete for this client call */
 	} else {
-		ret = rxrpc_send_data(NULL, call->socket, call, msg, len);
+		ret = rxrpc_send_data(call->socket, call, msg, len);
 	}
 
 	release_sock(&call->socket->sk);
@@ -271,8 +269,7 @@ EXPORT_SYMBOL(rxrpc_kernel_abort_call);
  * send a message through a server socket
  * - caller holds the socket locked
  */
-int rxrpc_server_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
-			 struct msghdr *msg, size_t len)
+int rxrpc_server_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 {
 	enum rxrpc_command cmd;
 	struct rxrpc_call *call;
@@ -313,7 +310,7 @@ int rxrpc_server_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
 			break;
 		}
 
-		ret = rxrpc_send_data(iocb, rx, call, msg, len);
+		ret = rxrpc_send_data(rx, call, msg, len);
 		break;
 
 	case RXRPC_CMD_SEND_ABORT:
@@ -520,8 +517,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
  * - must be called in process context
  * - caller holds the socket locked
  */
-static int rxrpc_send_data(struct kiocb *iocb,
-			   struct rxrpc_sock *rx,
+static int rxrpc_send_data(struct rxrpc_sock *rx,
 			   struct rxrpc_call *call,
 			   struct msghdr *msg, size_t len)
 {
@@ -546,11 +542,7 @@ static int rxrpc_send_data(struct kiocb *iocb,
 	call->tx_pending = NULL;
 
 	copied = 0;
-	if (len > iov_iter_count(&msg->msg_iter))
-		len = iov_iter_count(&msg->msg_iter);
-	while (len) {
-		int copy;
-
+	do {
 		if (!skb) {
 			size_t size, chunk, max, space;
 
@@ -572,8 +564,8 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			max &= ~(call->conn->size_align - 1UL);
 
 			chunk = max;
-			if (chunk > len && !more)
-				chunk = len;
+			if (chunk > msg_data_left(msg) && !more)
+				chunk = msg_data_left(msg);
 
 			space = chunk + call->conn->size_align;
 			space &= ~(call->conn->size_align - 1UL);
@@ -616,23 +608,23 @@ static int rxrpc_send_data(struct kiocb *iocb,
 		sp = rxrpc_skb(skb);
 
 		/* append next segment of data to the current buffer */
-		copy = skb_tailroom(skb);
-		ASSERTCMP(copy, >, 0);
-		if (copy > len)
-			copy = len;
-		if (copy > sp->remain)
-			copy = sp->remain;
-
-		_debug("add");
-		ret = skb_add_data(skb, &msg->msg_iter, copy);
-		_debug("added");
-		if (ret < 0)
-			goto efault;
-		sp->remain -= copy;
-		skb->mark += copy;
-		copied += copy;
-
-		len -= copy;
+		if (msg_data_left(msg) > 0) {
+			int copy = skb_tailroom(skb);
+			ASSERTCMP(copy, >, 0);
+			if (copy > msg_data_left(msg))
+				copy = msg_data_left(msg);
+			if (copy > sp->remain)
+				copy = sp->remain;
+
+			_debug("add");
+			ret = skb_add_data(skb, &msg->msg_iter, copy);
+			_debug("added");
+			if (ret < 0)
+				goto efault;
+			sp->remain -= copy;
+			skb->mark += copy;
+			copied += copy;
+		}
 
 		/* check for the far side aborting the call or a network error
 		 * occurring */
@@ -640,7 +632,8 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			goto call_aborted;
 
 		/* add the packet to the send queue if it's now full */
-		if (sp->remain <= 0 || (!len && !more)) {
+		if (sp->remain <= 0 ||
+		    (msg_data_left(msg) == 0 && !more)) {
 			struct rxrpc_connection *conn = call->conn;
 			uint32_t seq;
 			size_t pad;
@@ -670,7 +663,7 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			sp->hdr.serviceId = conn->service_id;
 
 			sp->hdr.flags = conn->out_clientflag;
-			if (len == 0 && !more)
+			if (msg_data_left(msg) == 0 && !more)
 				sp->hdr.flags |= RXRPC_LAST_PACKET;
 			else if (CIRC_SPACE(call->acks_head, call->acks_tail,
 					    call->acks_winsz) > 1)
@@ -686,10 +679,10 @@ static int rxrpc_send_data(struct kiocb *iocb,
 
 			memcpy(skb->head, &sp->hdr,
 			       sizeof(struct rxrpc_header));
-			rxrpc_queue_packet(call, skb, !iov_iter_count(&msg->msg_iter) && !more);
+			rxrpc_queue_packet(call, skb, !msg_data_left(msg) && !more);
 			skb = NULL;
 		}
-	}
+	} while (msg_data_left(msg) > 0);
 
 success:
 	ret = copied;
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 19a5606..b92bede 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -43,8 +43,8 @@ void rxrpc_remove_user_ID(struct rxrpc_sock *rx, struct rxrpc_call *call)
  * - we need to be careful about two or more threads calling recvmsg
  *   simultaneously
  */
-int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
-		  struct msghdr *msg, size_t len, int flags)
+int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+		  int flags)
 {
 	struct rxrpc_skb_priv *sp;
 	struct rxrpc_call *call = NULL, *continue_call = NULL;
@@ -150,7 +150,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 				       &call->conn->trans->peer->srx, len);
 				msg->msg_namelen = len;
 			}
-			sock_recv_ts_and_drops(msg, &rx->sk, skb);
+			sock_recv_timestamp(msg, &rx->sk, skb);
 		}
 
 		/* receive the message */