Merge tag 'rxrpc-fixes-20180928' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

David Howells says:

====================
rxrpc: Fixes

Here are some miscellaneous fixes for AF_RXRPC:

 (1) Remove a duplicate variable initialisation.

 (2) Fix one of the checks made when we decide to set up a new incoming
     service call in which a flag is being checked in the wrong field of
     the packet header.  This check is abstracted out into helper
     functions.

 (3) Fix RTT gathering.  The code has been trying to make use of socket
     timestamps, but wasn't actually enabling them.  The code has also been
     recording a transmit time for the outgoing packet for which we're
     going to measure the RTT after sending the message - but we can get
     the incoming packet before we get to that and record a negative RTT.

 (4) Fix the emission of BUSY packets (we are emitting ABORTs instead).

 (5) Improve error checking on incoming packets.

 (6) Try to fix a bug in new service call handling whereby a BUG we should
     never be able to reach somehow got triggered.  Do this by moving much
     of the checking as early as possible and not repeating it later
     (depends on (5) above).

 (7) Fix the sockopts set on a UDP6 socket to include the ones set on a
     UDP4 socket so that we receive UDP4 errors and packet-too-large
     notifications too.

 (8) Fix the distribution of errors so that we do it at the point of
     receiving an error in the UDP callback rather than deferring it
     thereby cutting short any transmissions that would otherwise occur in
     the window.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/trace/events/rxrpc.h

@@ -56,7 +56,6 @@ enum rxrpc_peer_trace {
 	rxrpc_peer_new,
 	rxrpc_peer_processing,
 	rxrpc_peer_put,
-	rxrpc_peer_queued_error,
 };
 
 enum rxrpc_conn_trace {
@@ -257,8 +256,7 @@ enum rxrpc_tx_point {
 	EM(rxrpc_peer_got,			"GOT") \
 	EM(rxrpc_peer_new,			"NEW") \
 	EM(rxrpc_peer_processing,		"PRO") \
-	EM(rxrpc_peer_put,			"PUT") \
-	E_(rxrpc_peer_queued_error,		"QER")
+	E_(rxrpc_peer_put,			"PUT")
 
 #define rxrpc_conn_traces \
 	EM(rxrpc_conn_got,			"GOT") \

net/rxrpc/ar-internal.h

@@ -40,17 +40,12 @@ struct rxrpc_crypt {
 struct rxrpc_connection;
 
 /*
- * Mark applied to socket buffers.
+ * Mark applied to socket buffers in skb->mark.  skb->priority is used
+ * to pass supplementary information.
  */
 enum rxrpc_skb_mark {
-	RXRPC_SKB_MARK_DATA,		/* data message */
-	RXRPC_SKB_MARK_FINAL_ACK,	/* final ACK received message */
-	RXRPC_SKB_MARK_BUSY,		/* server busy message */
-	RXRPC_SKB_MARK_REMOTE_ABORT,	/* remote abort message */
-	RXRPC_SKB_MARK_LOCAL_ABORT,	/* local abort message */
-	RXRPC_SKB_MARK_NET_ERROR,	/* network error message */
-	RXRPC_SKB_MARK_LOCAL_ERROR,	/* local error message */
-	RXRPC_SKB_MARK_NEW_CALL,	/* local error message */
+	RXRPC_SKB_MARK_REJECT_BUSY,	/* Reject with BUSY */
+	RXRPC_SKB_MARK_REJECT_ABORT,	/* Reject with ABORT (code in skb->priority) */
 };
 
 /*
@@ -293,7 +288,6 @@ struct rxrpc_peer {
 	struct hlist_node	hash_link;
 	struct rxrpc_local	*local;
 	struct hlist_head	error_targets;	/* targets for net error distribution */
-	struct work_struct	error_distributor;
 	struct rb_root		service_conns;	/* Service connections */
 	struct list_head	keepalive_link;	/* Link in net->peer_keepalive[] */
 	time64_t		last_tx_at;	/* Last time packet sent here */
@@ -304,8 +298,6 @@ struct rxrpc_peer {
 	unsigned int		maxdata;	/* data size (MTU - hdrsize) */
 	unsigned short		hdrsize;	/* header size (IP + UDP + RxRPC) */
 	int			debug_id;	/* debug ID for printks */
-	int			error_report;	/* Net (+0) or local (+1000000) to distribute */
-#define RXRPC_LOCAL_ERROR_OFFSET 1000000
 	struct sockaddr_rxrpc	srx;		/* remote address */
 
 	/* calculated RTT cache */
@@ -463,6 +455,16 @@ struct rxrpc_connection {
 	u8			out_clientflag;	/* RXRPC_CLIENT_INITIATED if we are client */
 };
 
+static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp)
+{
+	return sp->hdr.flags & RXRPC_CLIENT_INITIATED;
+}
+
+static inline bool rxrpc_to_client(const struct rxrpc_skb_priv *sp)
+{
+	return !rxrpc_to_server(sp);
+}
+
 /*
  * Flags in call->flags.
  */
@@ -717,6 +719,8 @@ extern struct workqueue_struct *rxrpc_workqueue;
 int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t);
 void rxrpc_discard_prealloc(struct rxrpc_sock *);
 struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *,
+					   struct rxrpc_sock *,
+					   struct rxrpc_peer *,
 					   struct rxrpc_connection *,
 					   struct sk_buff *);
 void rxrpc_accept_incoming_calls(struct rxrpc_local *);
@@ -908,7 +912,8 @@ extern unsigned int rxrpc_closed_conn_expiry;
 
 struct rxrpc_connection *rxrpc_alloc_connection(gfp_t);
 struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *,
-						   struct sk_buff *);
+						   struct sk_buff *,
+						   struct rxrpc_peer **);
 void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *);
 void rxrpc_disconnect_call(struct rxrpc_call *);
 void rxrpc_kill_connection(struct rxrpc_connection *);
@@ -1031,7 +1036,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
  * peer_event.c
  */
 void rxrpc_error_report(struct sock *);
-void rxrpc_peer_error_distributor(struct work_struct *);
 void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
 			rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
 void rxrpc_peer_keepalive_worker(struct work_struct *);
@@ -1044,13 +1048,11 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
 struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *,
 				     struct sockaddr_rxrpc *, gfp_t);
 struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t);
-struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *,
-					      struct rxrpc_peer *);
+void rxrpc_new_incoming_peer(struct rxrpc_local *, struct rxrpc_peer *);
 void rxrpc_destroy_all_peers(struct rxrpc_net *);
 struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *);
 struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *);
 void rxrpc_put_peer(struct rxrpc_peer *);
-void __rxrpc_queue_peer_error(struct rxrpc_peer *);
 
 /*
  * proc.c

net/rxrpc/call_accept.c

@@ -249,11 +249,11 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
  */
 static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
 						    struct rxrpc_local *local,
+						    struct rxrpc_peer *peer,
 						    struct rxrpc_connection *conn,
 						    struct sk_buff *skb)
 {
 	struct rxrpc_backlog *b = rx->backlog;
-	struct rxrpc_peer *peer, *xpeer;
 	struct rxrpc_call *call;
 	unsigned short call_head, conn_head, peer_head;
 	unsigned short call_tail, conn_tail, peer_tail;
@@ -276,21 +276,18 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
 		return NULL;
 
 	if (!conn) {
-		/* No connection.  We're going to need a peer to start off
-		 * with.  If one doesn't yet exist, use a spare from the
-		 * preallocation set.  We dump the address into the spare in
-		 * anticipation - and to save on stack space.
-		 */
-		xpeer = b->peer_backlog[peer_tail];
-		if (rxrpc_extract_addr_from_skb(local, &xpeer->srx, skb) < 0)
-			return NULL;
-
-		peer = rxrpc_lookup_incoming_peer(local, xpeer);
-		if (peer == xpeer) {
+		if (peer && !rxrpc_get_peer_maybe(peer))
+			peer = NULL;
+		if (!peer) {
+			peer = b->peer_backlog[peer_tail];
+			if (rxrpc_extract_addr_from_skb(local, &peer->srx, skb) < 0)
+				return NULL;
 			b->peer_backlog[peer_tail] = NULL;
 			smp_store_release(&b->peer_backlog_tail,
 					  (peer_tail + 1) &
 					  (RXRPC_BACKLOG_MAX - 1));
+
+			rxrpc_new_incoming_peer(local, peer);
 		}
 
 		/* Now allocate and set up the connection */
@@ -335,45 +332,31 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
  * The call is returned with the user access mutex held.
  */
 struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
+					   struct rxrpc_sock *rx,
+					   struct rxrpc_peer *peer,
 					   struct rxrpc_connection *conn,
 					   struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-	struct rxrpc_sock *rx;
 	struct rxrpc_call *call;
-	u16 service_id = sp->hdr.serviceId;
 
 	_enter("");
 
-	/* Get the socket providing the service */
-	rx = rcu_dereference(local->service);
-	if (rx && (service_id == rx->srx.srx_service ||
-		   service_id == rx->second_service))
-		goto found_service;
-
-	trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
-			  RX_INVALID_OPERATION, EOPNOTSUPP);
-	skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
-	skb->priority = RX_INVALID_OPERATION;
-	_leave(" = NULL [service]");
-	return NULL;
-
-found_service:
 	spin_lock(&rx->incoming_lock);
 	if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
 	    rx->sk.sk_state == RXRPC_CLOSE) {
 		trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
 				  sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
-		skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
+		skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
 		skb->priority = RX_INVALID_OPERATION;
 		_leave(" = NULL [close]");
 		call = NULL;
 		goto out;
 	}
 
-	call = rxrpc_alloc_incoming_call(rx, local, conn, skb);
+	call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb);
 	if (!call) {
-		skb->mark = RXRPC_SKB_MARK_BUSY;
+		skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
 		_leave(" = NULL [busy]");
 		call = NULL;
 		goto out;

net/rxrpc/call_object.c

@@ -400,7 +400,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
 	rcu_assign_pointer(conn->channels[chan].call, call);
 
 	spin_lock(&conn->params.peer->lock);
-	hlist_add_head(&call->error_link, &conn->params.peer->error_targets);
+	hlist_add_head_rcu(&call->error_link, &conn->params.peer->error_targets);
 	spin_unlock(&conn->params.peer->lock);
 
 	_net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id);

net/rxrpc/conn_client.c

@@ -710,8 +710,8 @@ int rxrpc_connect_call(struct rxrpc_call *call,
 	}
 
 	spin_lock_bh(&call->conn->params.peer->lock);
-	hlist_add_head(&call->error_link,
-		       &call->conn->params.peer->error_targets);
+	hlist_add_head_rcu(&call->error_link,
+			   &call->conn->params.peer->error_targets);
 	spin_unlock_bh(&call->conn->params.peer->lock);
 
 out:

net/rxrpc/conn_object.c

@@ -69,10 +69,14 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
  * If successful, a pointer to the connection is returned, but no ref is taken.
  * NULL is returned if there is no match.
  *
+ * When searching for a service call, if we find a peer but no connection, we
+ * return that through *_peer in case we need to create a new service call.
+ *
  * The caller must be holding the RCU read lock.
  */
 struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
-						   struct sk_buff *skb)
+						   struct sk_buff *skb,
+						   struct rxrpc_peer **_peer)
 {
 	struct rxrpc_connection *conn;
 	struct rxrpc_conn_proto k;
@@ -85,9 +89,6 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
 	if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0)
 		goto not_found;
 
-	k.epoch	= sp->hdr.epoch;
-	k.cid	= sp->hdr.cid & RXRPC_CIDMASK;
-
 	/* We may have to handle mixing IPv4 and IPv6 */
 	if (srx.transport.family != local->srx.transport.family) {
 		pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n",
@@ -99,7 +100,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
 	k.epoch	= sp->hdr.epoch;
 	k.cid	= sp->hdr.cid & RXRPC_CIDMASK;
 
-	if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) {
+	if (rxrpc_to_server(sp)) {
 		/* We need to look up service connections by the full protocol
 		 * parameter set.  We look up the peer first as an intermediate
 		 * step and then the connection from the peer's tree.
@@ -107,6 +108,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
 		peer = rxrpc_lookup_peer_rcu(local, &srx);
 		if (!peer)
 			goto not_found;
+		*_peer = peer;
 		conn = rxrpc_find_service_conn_rcu(peer, skb);
 		if (!conn || atomic_read(&conn->usage) == 0)
 			goto not_found;
@@ -214,7 +216,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 	call->peer->cong_cwnd = call->cong_cwnd;
 
 	spin_lock_bh(&conn->params.peer->lock);
-	hlist_del_init(&call->error_link);
+	hlist_del_rcu(&call->error_link);
 	spin_unlock_bh(&conn->params.peer->lock);
 
 	if (rxrpc_is_client_call(call))

net/rxrpc/input.c

@@ -622,13 +622,14 @@ static void rxrpc_input_requested_ack(struct rxrpc_call *call,
 		if (!skb)
 			continue;
 
+		sent_at = skb->tstamp;
+		smp_rmb(); /* Read timestamp before serial. */
 		sp = rxrpc_skb(skb);
 		if (sp->hdr.serial != orig_serial)
 			continue;
-		smp_rmb();
-		sent_at = skb->tstamp;
 		goto found;
 	}
+
 	return;
 
 found:
@@ -1124,12 +1125,14 @@ void rxrpc_data_ready(struct sock *udp_sk)
 {
 	struct rxrpc_connection *conn;
 	struct rxrpc_channel *chan;
-	struct rxrpc_call *call;
+	struct rxrpc_call *call = NULL;
 	struct rxrpc_skb_priv *sp;
 	struct rxrpc_local *local = udp_sk->sk_user_data;
+	struct rxrpc_peer *peer = NULL;
+	struct rxrpc_sock *rx = NULL;
 	struct sk_buff *skb;
 	unsigned int channel;
-	int ret, skew;
+	int ret, skew = 0;
 
 	_enter("%p", udp_sk);
 
@@ -1143,6 +1146,9 @@ void rxrpc_data_ready(struct sock *udp_sk)
 		return;
 	}
 
+	if (skb->tstamp == 0)
+		skb->tstamp = ktime_get_real();
+
 	rxrpc_new_skb(skb, rxrpc_skb_rx_received);
 
 	_net("recv skb %p", skb);
@@ -1177,46 +1183,75 @@ void rxrpc_data_ready(struct sock *udp_sk)
 
 	trace_rxrpc_rx_packet(sp);
 
-	_net("Rx RxRPC %s ep=%x call=%x:%x",
-	     sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient",
-	     sp->hdr.epoch, sp->hdr.cid, sp->hdr.callNumber);
-
-	if (sp->hdr.type >= RXRPC_N_PACKET_TYPES ||
-	    !((RXRPC_SUPPORTED_PACKET_TYPES >> sp->hdr.type) & 1)) {
-		_proto("Rx Bad Packet Type %u", sp->hdr.type);
-		goto bad_message;
-	}
-
 	switch (sp->hdr.type) {
 	case RXRPC_PACKET_TYPE_VERSION:
-		if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED))
+		if (rxrpc_to_client(sp))
 			goto discard;
 		rxrpc_post_packet_to_local(local, skb);
 		goto out;
 
 	case RXRPC_PACKET_TYPE_BUSY:
-		if (sp->hdr.flags & RXRPC_CLIENT_INITIATED)
+		if (rxrpc_to_server(sp))
 			goto discard;
 		/* Fall through */
+	case RXRPC_PACKET_TYPE_ACK:
+	case RXRPC_PACKET_TYPE_ACKALL:
+		if (sp->hdr.callNumber == 0)
+			goto bad_message;
+		/* Fall through */
+	case RXRPC_PACKET_TYPE_ABORT:
+		break;
 
 	case RXRPC_PACKET_TYPE_DATA:
-		if (sp->hdr.callNumber == 0)
+		if (sp->hdr.callNumber == 0 ||
+		    sp->hdr.seq == 0)
 			goto bad_message;
 		if (sp->hdr.flags & RXRPC_JUMBO_PACKET &&
 		    !rxrpc_validate_jumbo(skb))
 			goto bad_message;
 		break;
 
+	case RXRPC_PACKET_TYPE_CHALLENGE:
+		if (rxrpc_to_server(sp))
+			goto discard;
+		break;
+	case RXRPC_PACKET_TYPE_RESPONSE:
+		if (rxrpc_to_client(sp))
+			goto discard;
+		break;
+
 		/* Packet types 9-11 should just be ignored. */
 	case RXRPC_PACKET_TYPE_PARAMS:
 	case RXRPC_PACKET_TYPE_10:
 	case RXRPC_PACKET_TYPE_11:
 		goto discard;
+
+	default:
+		_proto("Rx Bad Packet Type %u", sp->hdr.type);
+		goto bad_message;
 	}
 
+	if (sp->hdr.serviceId == 0)
+		goto bad_message;
+
 	rcu_read_lock();
 
-	conn = rxrpc_find_connection_rcu(local, skb);
+	if (rxrpc_to_server(sp)) {
+		/* Weed out packets to services we're not offering.  Packets
+		 * that would begin a call are explicitly rejected and the rest
+		 * are just discarded.
+		 */
+		rx = rcu_dereference(local->service);
+		if (!rx || (sp->hdr.serviceId != rx->srx.srx_service &&
+			    sp->hdr.serviceId != rx->second_service)) {
+			if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
+			    sp->hdr.seq == 1)
+				goto unsupported_service;
+			goto discard_unlock;
+		}
+	}
+
+	conn = rxrpc_find_connection_rcu(local, skb, &peer);
 	if (conn) {
 		if (sp->hdr.securityIndex != conn->security_ix)
 			goto wrong_security;
@@ -1280,7 +1315,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
 		call = rcu_dereference(chan->call);
 
 		if (sp->hdr.callNumber > chan->call_id) {
-			if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) {
+			if (rxrpc_to_client(sp)) {
 				rcu_read_unlock();
 				goto reject_packet;
 			}
@@ -1297,19 +1332,15 @@ void rxrpc_data_ready(struct sock *udp_sk)
 			if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags))
 				set_bit(RXRPC_CALL_RX_HEARD, &call->flags);
 		}
-	} else {
-		skew = 0;
-		call = NULL;
 	}
 
 	if (!call || atomic_read(&call->usage) == 0) {
-		if (!(sp->hdr.type & RXRPC_CLIENT_INITIATED) ||
-		    sp->hdr.callNumber == 0 ||
+		if (rxrpc_to_client(sp) ||
 		    sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
 			goto bad_message_unlock;
 		if (sp->hdr.seq != 1)
 			goto discard_unlock;
-		call = rxrpc_new_incoming_call(local, conn, skb);
+		call = rxrpc_new_incoming_call(local, rx, peer, conn, skb);
 		if (!call) {
 			rcu_read_unlock();
 			goto reject_packet;
@@ -1340,6 +1371,13 @@ void rxrpc_data_ready(struct sock *udp_sk)
 	skb->priority = RXKADINCONSISTENCY;
 	goto post_abort;
 
+unsupported_service:
+	rcu_read_unlock();
+	trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+			  RX_INVALID_OPERATION, EOPNOTSUPP);
+	skb->priority = RX_INVALID_OPERATION;
+	goto post_abort;
+
 reupgrade:
 	rcu_read_unlock();
 	trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
@@ -1354,7 +1392,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
 protocol_error:
 	skb->priority = RX_PROTOCOL_ERROR;
 post_abort:
-	skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
+	skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
 reject_packet:
 	trace_rxrpc_rx_done(skb->mark, skb->priority);
 	rxrpc_reject_packet(local, skb);

net/rxrpc/local_object.c

@@ -135,10 +135,10 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 	}
 
 	switch (local->srx.transport.family) {
-	case AF_INET:
-		/* we want to receive ICMP errors */
+	case AF_INET6:
+		/* we want to receive ICMPv6 errors */
 		opt = 1;
-		ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
 					(char *) &opt, sizeof(opt));
 		if (ret < 0) {
 			_debug("setsockopt failed");
@@ -146,19 +146,22 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 		}
 
 		/* we want to set the don't fragment bit */
-		opt = IP_PMTUDISC_DO;
-		ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+		opt = IPV6_PMTUDISC_DO;
+		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
 					(char *) &opt, sizeof(opt));
 		if (ret < 0) {
 			_debug("setsockopt failed");
 			goto error;
 		}
-		break;
 
-	case AF_INET6:
+		/* Fall through and set IPv4 options too otherwise we don't get
+		 * errors from IPv4 packets sent through the IPv6 socket.
+		 */
+
+	case AF_INET:
 		/* we want to receive ICMP errors */
 		opt = 1;
-		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
+		ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
 					(char *) &opt, sizeof(opt));
 		if (ret < 0) {
 			_debug("setsockopt failed");
@@ -166,13 +169,22 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 		}
 
 		/* we want to set the don't fragment bit */
-		opt = IPV6_PMTUDISC_DO;
-		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
+		opt = IP_PMTUDISC_DO;
+		ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
 					(char *) &opt, sizeof(opt));
 		if (ret < 0) {
 			_debug("setsockopt failed");
 			goto error;
 		}
+
+		/* We want receive timestamps. */
+		opt = 1;
+		ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS,
+					(char *)&opt, sizeof(opt));
+		if (ret < 0) {
+			_debug("setsockopt failed");
+			goto error;
+		}
 		break;
 
 	default:

net/rxrpc/output.c

@@ -124,7 +124,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	struct kvec iov[2];
 	rxrpc_serial_t serial;
 	rxrpc_seq_t hard_ack, top;
-	ktime_t now;
 	size_t len, n;
 	int ret;
 	u8 reason;
@@ -196,9 +195,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 		/* We need to stick a time in before we send the packet in case
 		 * the reply gets back before kernel_sendmsg() completes - but
 		 * asking UDP to send the packet can take a relatively long
-		 * time, so we update the time after, on the assumption that
-		 * the packet transmission is more likely to happen towards the
-		 * end of the kernel_sendmsg() call.
+		 * time.
 		 */
 		call->ping_time = ktime_get_real();
 		set_bit(RXRPC_CALL_PINGING, &call->flags);
@@ -206,9 +203,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	}
 
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
-	now = ktime_get_real();
-	if (ping)
-		call->ping_time = now;
 	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
@@ -363,8 +357,14 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 
 	/* If our RTT cache needs working on, request an ACK.  Also request
 	 * ACKs if a DATA packet appears to have been lost.
+	 *
+	 * However, we mustn't request an ACK on the last reply packet of a
+	 * service call, lest OpenAFS incorrectly send us an ACK with some
+	 * soft-ACKs in it and then never follow up with a proper hard ACK.
 	 */
-	if (!(sp->hdr.flags & RXRPC_LAST_PACKET) &&
+	if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) ||
+	     rxrpc_to_server(sp)
+	     ) &&
 	    (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
 	     retrans ||
 	     call->cong_mode == RXRPC_CALL_SLOW_START ||
@@ -390,6 +390,11 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		goto send_fragmentable;
 
 	down_read(&conn->params.local->defrag_sem);
+
+	sp->hdr.serial = serial;
+	smp_wmb(); /* Set serial before timestamp */
+	skb->tstamp = ktime_get_real();
+
 	/* send the packet by UDP
 	 * - returns -EMSGSIZE if UDP would have to fragment the packet
 	 *   to go out of the interface
@@ -413,12 +418,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags,
 			    retrans, lost);
 	if (ret >= 0) {
-		ktime_t now = ktime_get_real();
-		skb->tstamp = now;
-		smp_wmb();
-		sp->hdr.serial = serial;
 		if (whdr.flags & RXRPC_REQUEST_ACK) {
-			call->peer->rtt_last_req = now;
+			call->peer->rtt_last_req = skb->tstamp;
 			trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
 			if (call->peer->rtt_usage > 1) {
 				unsigned long nowj = jiffies, ack_lost_at;
@@ -457,6 +458,10 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 
 	down_write(&conn->params.local->defrag_sem);
 
+	sp->hdr.serial = serial;
+	smp_wmb(); /* Set serial before timestamp */
+	skb->tstamp = ktime_get_real();
+
 	switch (conn->params.local->srx.transport.family) {
 	case AF_INET:
 		opt = IP_PMTUDISC_DONT;
@@ -519,7 +524,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
 	struct kvec iov[2];
 	size_t size;
 	__be32 code;
-	int ret;
+	int ret, ioc;
 
 	_enter("%d", local->debug_id);
 
@@ -527,7 +532,6 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
 	iov[0].iov_len = sizeof(whdr);
 	iov[1].iov_base = &code;
 	iov[1].iov_len = sizeof(code);
-	size = sizeof(whdr) + sizeof(code);
 
 	msg.msg_name = &srx.transport;
 	msg.msg_control = NULL;
@@ -535,17 +539,31 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
 	msg.msg_flags = 0;
 
 	memset(&whdr, 0, sizeof(whdr));
-	whdr.type = RXRPC_PACKET_TYPE_ABORT;
 
 	while ((skb = skb_dequeue(&local->reject_queue))) {
 		rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
 		sp = rxrpc_skb(skb);
 
+		switch (skb->mark) {
+		case RXRPC_SKB_MARK_REJECT_BUSY:
+			whdr.type = RXRPC_PACKET_TYPE_BUSY;
+			size = sizeof(whdr);
+			ioc = 1;
+			break;
+		case RXRPC_SKB_MARK_REJECT_ABORT:
+			whdr.type = RXRPC_PACKET_TYPE_ABORT;
+			code = htonl(skb->priority);
+			size = sizeof(whdr) + sizeof(code);
+			ioc = 2;
+			break;
+		default:
+			rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+			continue;
+		}
+
 		if (rxrpc_extract_addr_from_skb(local, &srx, skb) == 0) {
 			msg.msg_namelen = srx.transport_len;
 
-			code = htonl(skb->priority);
-
 			whdr.epoch	= htonl(sp->hdr.epoch);
 			whdr.cid	= htonl(sp->hdr.cid);
 			whdr.callNumber	= htonl(sp->hdr.callNumber);

net/rxrpc/peer_event.c

@@ -23,6 +23,8 @@
 #include "ar-internal.h"
 
 static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
+static void rxrpc_distribute_error(struct rxrpc_peer *, int,
+				   enum rxrpc_call_completion);
 
 /*
  * Find the peer associated with an ICMP packet.
@@ -194,8 +196,6 @@ void rxrpc_error_report(struct sock *sk)
 	rcu_read_unlock();
 	rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
 
-	/* The ref we obtained is passed off to the work item */
-	__rxrpc_queue_peer_error(peer);
 	_leave("");
 }
 
@@ -205,6 +205,7 @@ void rxrpc_error_report(struct sock *sk)
 static void rxrpc_store_error(struct rxrpc_peer *peer,
 			      struct sock_exterr_skb *serr)
 {
+	enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR;
 	struct sock_extended_err *ee;
 	int err;
 
@@ -255,7 +256,7 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
 	case SO_EE_ORIGIN_NONE:
 	case SO_EE_ORIGIN_LOCAL:
 		_proto("Rx Received local error { error=%d }", err);
-		err += RXRPC_LOCAL_ERROR_OFFSET;
+		compl = RXRPC_CALL_LOCAL_ERROR;
 		break;
 
 	case SO_EE_ORIGIN_ICMP6:
@@ -264,48 +265,23 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
 		break;
 	}
 
-	peer->error_report = err;
+	rxrpc_distribute_error(peer, err, compl);
 }
 
 /*
- * Distribute an error that occurred on a peer
+ * Distribute an error that occurred on a peer.
  */
-void rxrpc_peer_error_distributor(struct work_struct *work)
+static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
+				   enum rxrpc_call_completion compl)
 {
-	struct rxrpc_peer *peer =
-		container_of(work, struct rxrpc_peer, error_distributor);
 	struct rxrpc_call *call;
-	enum rxrpc_call_completion compl;
-	int error;
-
-	_enter("");
-
-	error = READ_ONCE(peer->error_report);
-	if (error < RXRPC_LOCAL_ERROR_OFFSET) {
-		compl = RXRPC_CALL_NETWORK_ERROR;
-	} else {
-		compl = RXRPC_CALL_LOCAL_ERROR;
-		error -= RXRPC_LOCAL_ERROR_OFFSET;
-	}
 
-	_debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error);
-
-	spin_lock_bh(&peer->lock);
-
-	while (!hlist_empty(&peer->error_targets)) {
-		call = hlist_entry(peer->error_targets.first,
-				   struct rxrpc_call, error_link);
-		hlist_del_init(&call->error_link);
+	hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) {
 		rxrpc_see_call(call);
-
-		if (rxrpc_set_call_completion(call, compl, 0, -error))
+		if (call->state < RXRPC_CALL_COMPLETE &&
+		    rxrpc_set_call_completion(call, compl, 0, -error))
 			rxrpc_notify_socket(call);
 	}
-
-	spin_unlock_bh(&peer->lock);
-
-	rxrpc_put_peer(peer);
-	_leave("");
 }
 
 /*

net/rxrpc/peer_object.c

@@ -124,11 +124,9 @@ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu(
 	struct rxrpc_net *rxnet = local->rxnet;
 
 	hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) {
-		if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) {
-			if (atomic_read(&peer->usage) == 0)
-				return NULL;
+		if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 &&
+		    atomic_read(&peer->usage) > 0)
 			return peer;
-		}
 	}
 
 	return NULL;
@@ -222,8 +220,6 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
 		atomic_set(&peer->usage, 1);
 		peer->local = local;
 		INIT_HLIST_HEAD(&peer->error_targets);
-		INIT_WORK(&peer->error_distributor,
-			  &rxrpc_peer_error_distributor);
 		peer->service_conns = RB_ROOT;
 		seqlock_init(&peer->service_conn_lock);
 		spin_lock_init(&peer->lock);
@@ -299,34 +295,23 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
 }
 
 /*
- * Set up a new incoming peer.  The address is prestored in the preallocated
- * peer.
+ * Set up a new incoming peer.  There shouldn't be any other matching peers
+ * since we've already done a search in the list from the non-reentrant context
+ * (the data_ready handler) that is the only place we can add new peers.
  */
-struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local,
-					      struct rxrpc_peer *prealloc)
+void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
 {
-	struct rxrpc_peer *peer;
 	struct rxrpc_net *rxnet = local->rxnet;
 	unsigned long hash_key;
 
-	hash_key = rxrpc_peer_hash_key(local, &prealloc->srx);
-	prealloc->local = local;
-	rxrpc_init_peer(prealloc, hash_key);
+	hash_key = rxrpc_peer_hash_key(local, &peer->srx);
+	peer->local = local;
+	rxrpc_init_peer(peer, hash_key);
 
 	spin_lock(&rxnet->peer_hash_lock);
-
-	/* Need to check that we aren't racing with someone else */
-	peer = __rxrpc_lookup_peer_rcu(local, &prealloc->srx, hash_key);
-	if (peer && !rxrpc_get_peer_maybe(peer))
-		peer = NULL;
-	if (!peer) {
-		peer = prealloc;
-		hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
-		list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
-	}
-
+	hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
+	list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
 	spin_unlock(&rxnet->peer_hash_lock);
-	return peer;
 }
 
 /*
@@ -415,21 +400,6 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
 	return peer;
 }
 
-/*
- * Queue a peer record.  This passes the caller's ref to the workqueue.
- */
-void __rxrpc_queue_peer_error(struct rxrpc_peer *peer)
-{
-	const void *here = __builtin_return_address(0);
-	int n;
-
-	n = atomic_read(&peer->usage);
-	if (rxrpc_queue_work(&peer->error_distributor))
-		trace_rxrpc_peer(peer, rxrpc_peer_queued_error, n, here);
-	else
-		rxrpc_put_peer(peer);
-}
-
 /*
  * Discard a peer record.
  */

net/rxrpc/protocol.h

@@ -50,7 +50,6 @@ struct rxrpc_wire_header {
 #define RXRPC_PACKET_TYPE_10		10	/* Ignored */
 #define RXRPC_PACKET_TYPE_11		11	/* Ignored */
 #define RXRPC_PACKET_TYPE_VERSION	13	/* version string request */
-#define RXRPC_N_PACKET_TYPES		14	/* number of packet types (incl type 0) */
 
 	uint8_t		flags;		/* packet flags */
 #define RXRPC_CLIENT_INITIATED	0x01		/* signifies a packet generated by a client */
@@ -72,20 +71,6 @@ struct rxrpc_wire_header {
 
 } __packed;
 
-#define RXRPC_SUPPORTED_PACKET_TYPES (			\
-		(1 << RXRPC_PACKET_TYPE_DATA) |		\
-		(1 << RXRPC_PACKET_TYPE_ACK) |		\
-		(1 << RXRPC_PACKET_TYPE_BUSY) |		\
-		(1 << RXRPC_PACKET_TYPE_ABORT) |	\
-		(1 << RXRPC_PACKET_TYPE_ACKALL) |	\
-		(1 << RXRPC_PACKET_TYPE_CHALLENGE) |	\
-		(1 << RXRPC_PACKET_TYPE_RESPONSE) |	\
-		/*(1 << RXRPC_PACKET_TYPE_DEBUG) | */	\
-		(1 << RXRPC_PACKET_TYPE_PARAMS) |	\
-		(1 << RXRPC_PACKET_TYPE_10) |		\
-		(1 << RXRPC_PACKET_TYPE_11) |		\
-		(1 << RXRPC_PACKET_TYPE_VERSION))
-
 /*****************************************************************************/
 /*
  * jumbo packet secondary header