Merge tag 'rxrpc-next-20181004' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

David Howells says:

====================
rxrpc: Development

Here are some development patches for AF_RXRPC.  The most significant points
are:

 (1) Change the tracepoint that indicates a packet has been transmitted
     into one that indicates a packet is about to be transmitted.  Without
     this, the response tracepoint may occur first if the round trip is
     fast enough.

 (2) Sort out AFS address list handling to better enforce maximum capacity
     to use helper functions to fill them and to do an insertion sort to
     order them.  This is here to make (3) easier.

 (3) Keep AF_INET addresses as AF_INET addresses rather than converting
     them to AF_INET6 in both AF_RXRPC and kAFS.  I hadn't realised that a
     UDP6 socket would just call down into UDP4 if given an AF_INET
     address.

 (4) Allow the timestamp on the first DATA packet of a reply to be
     retrieved by a kernel service.  This will give the kAFS a more
     accurate base from which to calculate the callback promise expiration.

 (5) Allow the rxrpc protocol epoch value to be retrieved from an incoming
     call.  This will allow kAFS to determine if the fileserver restarted
     and if two addresses apparently assigned to the same fileserver
     actually are different boxes.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 85 insertions, 52 deletions

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index ac44d8afffb1..013dbcb052e5 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -97,7 +97,8 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx,
 	    srx->transport_len > len)
 		return -EINVAL;
 
-	if (srx->transport.family != rx->family)
+	if (srx->transport.family != rx->family &&
+	    srx->transport.family == AF_INET && rx->family != AF_INET6)
 		return -EAFNOSUPPORT;
 
 	switch (srx->transport.family) {
@@ -385,6 +386,20 @@ u32 rxrpc_kernel_check_life(struct socket *sock, struct rxrpc_call *call)
 EXPORT_SYMBOL(rxrpc_kernel_check_life);
 
 /**
+ * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call.
+ * @sock: The socket the call is on
+ * @call: The call to query
+ *
+ * Allow a kernel service to retrieve the epoch value from a service call to
+ * see if the client at the other end rebooted.
+ */
+u32 rxrpc_kernel_get_epoch(struct socket *sock, struct rxrpc_call *call)
+{
+	return call->conn->proto.epoch;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_epoch);
+
+/**
  * rxrpc_kernel_check_call - Check a call's state
  * @sock: The socket the call is on
  * @call: The call to check
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index ef9554131434..76569c178915 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -1095,7 +1095,6 @@ void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace);
 void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace);
 void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace);
 void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace);
-void rxrpc_lose_skb(struct sk_buff *, enum rxrpc_skb_trace);
 void rxrpc_purge_queue(struct sk_buff_head *);
 
 /*
@@ -1112,8 +1111,7 @@ static inline void rxrpc_sysctl_exit(void) {}
 /*
  * utils.c
  */
-int rxrpc_extract_addr_from_skb(struct rxrpc_local *, struct sockaddr_rxrpc *,
-				struct sk_buff *);
+int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *);
 
 static inline bool before(u32 seq1, u32 seq2)
 {
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 9c7f26d06a52..8354cadbb839 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -280,7 +280,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
 			peer = NULL;
 		if (!peer) {
 			peer = b->peer_backlog[peer_tail];
-			if (rxrpc_extract_addr_from_skb(local, &peer->srx, skb) < 0)
+			if (rxrpc_extract_addr_from_skb(&peer->srx, skb) < 0)
 				return NULL;
 			b->peer_backlog[peer_tail] = NULL;
 			smp_store_release(&b->peer_backlog_tail,
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 885dae829f4a..c332722820c2 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -86,11 +86,12 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
 
 	_enter(",%x", sp->hdr.cid & RXRPC_CIDMASK);
 
-	if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0)
+	if (rxrpc_extract_addr_from_skb(&srx, skb) < 0)
 		goto not_found;
 
-	/* We may have to handle mixing IPv4 and IPv6 */
-	if (srx.transport.family != local->srx.transport.family) {
+	if (srx.transport.family != local->srx.transport.family &&
+	    (srx.transport.family == AF_INET &&
+	     local->srx.transport.family != AF_INET6)) {
 		pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n",
 				    srx.transport.family,
 				    local->srx.transport.family);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 4b86b6be6c1f..5b2626929822 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1176,7 +1176,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
 		static int lose;
 		if ((lose++ & 7) == 7) {
 			trace_rxrpc_rx_lose(sp);
-			rxrpc_lose_skb(skb, rxrpc_skb_rx_lost);
+			rxrpc_free_skb(skb, rxrpc_skb_rx_lost);
 			return;
 		}
 	}
diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c
index 13bd8a4dfac7..927ead43df42 100644
--- a/net/rxrpc/local_event.c
+++ b/net/rxrpc/local_event.c
@@ -39,7 +39,7 @@ static void rxrpc_send_version_request(struct rxrpc_local *local,
 
 	_enter("");
 
-	if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0)
+	if (rxrpc_extract_addr_from_skb(&srx, skb) < 0)
 		return;
 
 	msg.msg_name	= &srx.transport;
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index e8fb8922bca8..0f0b499d1202 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -378,11 +378,13 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		if ((lose++ & 7) == 7) {
 			ret = 0;
 			lost = true;
-			goto done;
 		}
 	}
 
-	_proto("Tx DATA %%%u { #%u }", serial, sp->hdr.seq);
+	trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags,
+			    retrans, lost);
+	if (lost)
+		goto done;
 
 	/* send the packet with the don't fragment bit set if we currently
 	 * think it's small enough */
@@ -415,8 +417,6 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		goto send_fragmentable;
 
 done:
-	trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags,
-			    retrans, lost);
 	if (ret >= 0) {
 		if (whdr.flags & RXRPC_REQUEST_ACK) {
 			call->peer->rtt_last_req = skb->tstamp;
@@ -561,7 +561,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
 			continue;
 		}
 
-		if (rxrpc_extract_addr_from_skb(local, &srx, skb) == 0) {
+		if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) {
 			msg.msg_namelen = srx.transport_len;
 
 			whdr.epoch	= htonl(sp->hdr.epoch);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index f3e6fc670da2..81a7869325a6 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -47,6 +47,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 	 */
 	switch (srx->transport.family) {
 	case AF_INET:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
 		srx->transport.sin.sin_port = serr->port;
 		switch (serr->ee.ee_origin) {
 		case SO_EE_ORIGIN_ICMP:
@@ -70,20 +72,20 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 
 #ifdef CONFIG_AF_RXRPC_IPV6
 	case AF_INET6:
-		srx->transport.sin6.sin6_port = serr->port;
 		switch (serr->ee.ee_origin) {
 		case SO_EE_ORIGIN_ICMP6:
 			_net("Rx ICMP6");
+			srx->transport.sin6.sin6_port = serr->port;
 			memcpy(&srx->transport.sin6.sin6_addr,
 			       skb_network_header(skb) + serr->addr_offset,
 			       sizeof(struct in6_addr));
 			break;
 		case SO_EE_ORIGIN_ICMP:
 			_net("Rx ICMP on v6 sock");
-			srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
-			srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
-			srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
-			memcpy(srx->transport.sin6.sin6_addr.s6_addr + 12,
+			srx->transport_len = sizeof(srx->transport.sin);
+			srx->transport.family = AF_INET;
+			srx->transport.sin.sin_port = serr->port;
+			memcpy(&srx->transport.sin.sin_addr,
 			       skb_network_header(skb) + serr->addr_offset,
 			       sizeof(struct in_addr));
 			break;
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 816b19a78809..eaf19ebaa964 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -715,3 +715,46 @@ call_complete:
 	goto out;
 }
 EXPORT_SYMBOL(rxrpc_kernel_recv_data);
+
+/**
+ * rxrpc_kernel_get_reply_time - Get timestamp on first reply packet
+ * @sock: The socket that the call exists on
+ * @call: The call to query
+ * @_ts: Where to put the timestamp
+ *
+ * Retrieve the timestamp from the first DATA packet of the reply if it is
+ * in the ring.  Returns true if successful, false if not.
+ */
+bool rxrpc_kernel_get_reply_time(struct socket *sock, struct rxrpc_call *call,
+				 ktime_t *_ts)
+{
+	struct sk_buff *skb;
+	rxrpc_seq_t hard_ack, top, seq;
+	bool success = false;
+
+	mutex_lock(&call->user_mutex);
+
+	if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_RECV_REPLY)
+		goto out;
+
+	hard_ack = call->rx_hard_ack;
+	if (hard_ack != 0)
+		goto out;
+
+	seq = hard_ack + 1;
+	top = smp_load_acquire(&call->rx_top);
+	if (after(seq, top))
+		goto out;
+
+	skb = call->rxtx_buffer[seq & RXRPC_RXTX_BUFF_MASK];
+	if (!skb)
+		goto out;
+
+	*_ts = skb_get_ktime(skb);
+	success = true;
+
+out:
+	mutex_unlock(&call->user_mutex);
+	return success;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_reply_time);
diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c
index b8985d01876a..913dca65cc65 100644
--- a/net/rxrpc/skbuff.c
+++ b/net/rxrpc/skbuff.c
@@ -69,21 +69,6 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
 }
 
 /*
- * Note the injected loss of a socket buffer.
- */
-void rxrpc_lose_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
-{
-	const void *here = __builtin_return_address(0);
-	if (skb) {
-		int n;
-		CHECK_SLAB_OKAY(&skb->users);
-		n = atomic_dec_return(select_skb_count(op));
-		trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
-		kfree_skb(skb);
-	}
-}
-
-/*
  * Clear a queue of socket buffers.
  */
 void rxrpc_purge_queue(struct sk_buff_head *list)
diff --git a/net/rxrpc/utils.c b/net/rxrpc/utils.c
index e801171fa351..ff7af71c4b49 100644
--- a/net/rxrpc/utils.c
+++ b/net/rxrpc/utils.c
@@ -17,28 +17,17 @@
 /*
  * Fill out a peer address from a socket buffer containing a packet.
  */
-int rxrpc_extract_addr_from_skb(struct rxrpc_local *local,
-				struct sockaddr_rxrpc *srx,
-				struct sk_buff *skb)
+int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *srx, struct sk_buff *skb)
 {
 	memset(srx, 0, sizeof(*srx));
 
 	switch (ntohs(skb->protocol)) {
 	case ETH_P_IP:
-		if (local->srx.transport.family == AF_INET6) {
-			srx->transport_type = SOCK_DGRAM;
-			srx->transport_len = sizeof(srx->transport.sin6);
-			srx->transport.sin6.sin6_family = AF_INET6;
-			srx->transport.sin6.sin6_port = udp_hdr(skb)->source;
-			srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
-			srx->transport.sin6.sin6_addr.s6_addr32[3] = ip_hdr(skb)->saddr;
-		} else {
-			srx->transport_type = SOCK_DGRAM;
-			srx->transport_len = sizeof(srx->transport.sin);
-			srx->transport.sin.sin_family = AF_INET;
-			srx->transport.sin.sin_port = udp_hdr(skb)->source;
-			srx->transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
-		}
+		srx->transport_type = SOCK_DGRAM;
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.sin.sin_family = AF_INET;
+		srx->transport.sin.sin_port = udp_hdr(skb)->source;
+		srx->transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
 		return 0;
 
 #ifdef CONFIG_AF_RXRPC_IPV6