Merge tag 'rxrpc-fixes-20220901' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

David Howells says:

====================
rxrpc fixes
Here are some fixes for AF_RXRPC:

 (1) Fix the handling of ICMP/ICMP6 packets.  This is a problem due to
     rxrpc being switched to acting as a UDP tunnel, thereby allowing it to
     steal the packets before they go through the UDP Rx queue.  UDP
     tunnels can't get ICMP/ICMP6 packets, however.  This patch adds an
     additional encap hook so that they can.

 (2) Fix the encryption routines in rxkad to handle packets that have more
     than three parts correctly.  The problem is that ->nr_frags doesn't
     count the initial fragment, so the sglist ends up too short.

 (3) Fix a problem with destruction of the local endpoint potentially
     getting repeated.

 (4) Fix the calculation of the time at which to resend.
     jiffies_to_usecs() gives microseconds, not nanoseconds.

 (5) Fix AFS to work out when callback promises and locks expire based on
     the time an op was issued rather than the time the first reply packet
     arrives.  We don't know how long the server took between calculating
     the expiry interval and transmitting the reply.

 (6) Given (5), rxrpc_get_reply_time() is no longer used, so remove it.
====================

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

9 files changed, 270 insertions, 83 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 34eda973bbf1..cd72158e953a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -783,6 +783,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	 */
 	if (tunnel) {
 		/* ...not for tunnels though: we don't have a sending socket */
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2);
 		goto out;
 	}
 	if (!inet->recverr) {
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index 8efaf8c3fe2a..8242c8947340 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -72,6 +72,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_sk(sk)->encap_type = cfg->encap_type;
 	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv;
 	udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup;
 	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
 	udp_sk(sk)->gro_receive = cfg->gro_receive;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 16c176e7c69a..3366d6a77ff2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -616,8 +616,11 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	}
 
 	/* Tunnels don't have an application socket: don't pass errors back */
-	if (tunnel)
+	if (tunnel) {
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, offset);
 		goto out;
+	}
 
 	if (!np->recverr) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 571436064cd6..62c70709d798 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -982,6 +982,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
 /*
  * peer_event.c
  */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 void rxrpc_error_report(struct sock *);
 void rxrpc_peer_keepalive_worker(struct work_struct *);
 
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index f8ecad2b730e..2a93e7b5fbd0 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -166,7 +166,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 	_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
 
 	now = ktime_get_real();
-	max_age = ktime_sub(now, jiffies_to_usecs(call->peer->rto_j));
+	max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j));
 
 	spin_lock_bh(&call->lock);
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 96ecb7356c0f..38ea98ff426b 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -137,6 +137,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 
 	tuncfg.encap_type = UDP_ENCAP_RXRPC;
 	tuncfg.encap_rcv = rxrpc_input_packet;
+	tuncfg.encap_err_rcv = rxrpc_encap_err_rcv;
 	tuncfg.sk_user_data = local;
 	setup_udp_tunnel_sock(net, local->socket, &tuncfg);
 
@@ -405,6 +406,9 @@ static void rxrpc_local_processor(struct work_struct *work)
 		container_of(work, struct rxrpc_local, processor);
 	bool again;
 
+	if (local->dead)
+		return;
+
 	trace_rxrpc_local(local->debug_id, rxrpc_local_processing,
 			  refcount_read(&local->ref), NULL);
 
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index be032850ae8c..32561e9567fe 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -16,22 +16,105 @@
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include <net/ip.h>
+#include <net/icmp.h>
 #include "ar-internal.h"
 
+static void rxrpc_adjust_mtu(struct rxrpc_peer *, unsigned int);
 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.
+ * Find the peer associated with an ICMPv4 packet.
  */
 static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
-						     const struct sk_buff *skb,
+						     struct sk_buff *skb,
+						     unsigned int udp_offset,
+						     unsigned int *info,
 						     struct sockaddr_rxrpc *srx)
 {
-	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+	struct iphdr *ip, *ip0 = ip_hdr(skb);
+	struct icmphdr *icmp = icmp_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
 
-	_enter("");
+	_enter("%u,%u,%u", ip0->protocol, icmp->type, icmp->code);
+
+	switch (icmp->type) {
+	case ICMP_DEST_UNREACH:
+		*info = ntohs(icmp->un.frag.mtu);
+		fallthrough;
+	case ICMP_TIME_EXCEEDED:
+	case ICMP_PARAMETERPROB:
+		ip = (struct iphdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
+	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
+	 * versa?
+	 */
+	switch (srx->transport.family) {
+	case AF_INET:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case AF_INET6:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+#endif
+
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+/*
+ * Find the peer associated with an ICMPv6 packet.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local,
+						      struct sk_buff *skb,
+						      unsigned int udp_offset,
+						      unsigned int *info,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct icmp6hdr *icmp = icmp6_hdr(skb);
+	struct ipv6hdr *ip, *ip0 = ipv6_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
+
+	_enter("%u,%u,%u", ip0->nexthdr, icmp->icmp6_type, icmp->icmp6_code);
+
+	switch (icmp->icmp6_type) {
+	case ICMPV6_DEST_UNREACH:
+		*info = ntohl(icmp->icmp6_mtu);
+		fallthrough;
+	case ICMPV6_PKT_TOOBIG:
+	case ICMPV6_TIME_EXCEED:
+	case ICMPV6_PARAMPROB:
+		ip = (struct ipv6hdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
 
 	memset(srx, 0, sizeof(*srx));
 	srx->transport_type = local->srx.transport_type;
@@ -43,6 +126,165 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 	 */
 	switch (srx->transport.family) {
 	case AF_INET:
+		_net("Rx ICMP6 on v4 sock");
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr,
+		       &ip->daddr.s6_addr32[3], sizeof(struct in_addr));
+		break;
+	case AF_INET6:
+		_net("Rx ICMP6");
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin6.sin6_addr, &ip->daddr,
+		       sizeof(struct in6_addr));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+#endif /* CONFIG_AF_RXRPC_IPV6 */
+
+/*
+ * Handle an error received on the local endpoint as a tunnel.
+ */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb,
+			 unsigned int udp_offset)
+{
+	struct sock_extended_err ee;
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_local *local;
+	struct rxrpc_peer *peer;
+	unsigned int info = 0;
+	int err;
+	u8 version = ip_hdr(skb)->version;
+	u8 type = icmp_hdr(skb)->type;
+	u8 code = icmp_hdr(skb)->code;
+
+	rcu_read_lock();
+	local = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!local)) {
+		rcu_read_unlock();
+		return;
+	}
+
+	rxrpc_new_skb(skb, rxrpc_skb_received);
+
+	switch (ip_hdr(skb)->version) {
+	case IPVERSION:
+		peer = rxrpc_lookup_peer_icmp_rcu(local, skb, udp_offset,
+						  &info, &srx);
+		break;
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, udp_offset,
+						   &info, &srx);
+		break;
+#endif
+	default:
+		rcu_read_unlock();
+		return;
+	}
+
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	if (!peer) {
+		rcu_read_unlock();
+		return;
+	}
+
+	memset(&ee, 0, sizeof(ee));
+
+	switch (version) {
+	case IPVERSION:
+		switch (type) {
+		case ICMP_DEST_UNREACH:
+			switch (code) {
+			case ICMP_FRAG_NEEDED:
+				rxrpc_adjust_mtu(peer, info);
+				rcu_read_unlock();
+				rxrpc_put_peer(peer);
+				return;
+			default:
+				break;
+			}
+
+			err = EHOSTUNREACH;
+			if (code <= NR_ICMP_UNREACH) {
+				/* Might want to do something different with
+				 * non-fatal errors
+				 */
+				//harderr = icmp_err_convert[code].fatal;
+				err = icmp_err_convert[code].errno;
+			}
+			break;
+
+		case ICMP_TIME_EXCEEDED:
+			err = EHOSTUNREACH;
+			break;
+		default:
+			err = EPROTO;
+			break;
+		}
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		switch (type) {
+		case ICMPV6_PKT_TOOBIG:
+			rxrpc_adjust_mtu(peer, info);
+			rcu_read_unlock();
+			rxrpc_put_peer(peer);
+			return;
+		}
+
+		icmpv6_err_convert(type, code, &err);
+
+		if (err == EACCES)
+			err = EHOSTUNREACH;
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP6;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+#endif
+	}
+
+	trace_rxrpc_rx_icmp(peer, &ee, &srx);
+
+	rxrpc_distribute_error(peer, err, RXRPC_CALL_NETWORK_ERROR);
+	rcu_read_unlock();
+	rxrpc_put_peer(peer);
+}
+
+/*
+ * Find the peer associated with a local error.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local,
+						      const struct sk_buff *skb,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+
+	_enter("");
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
+	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;
@@ -104,10 +346,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 /*
  * Handle an MTU/fragmentation problem.
  */
-static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
+static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu)
 {
-	u32 mtu = serr->ee.ee_info;
-
 	_net("Rx ICMP Fragmentation Needed (%d)", mtu);
 
 	/* wind down the local interface MTU */
@@ -148,7 +388,7 @@ void rxrpc_error_report(struct sock *sk)
 	struct sock_exterr_skb *serr;
 	struct sockaddr_rxrpc srx;
 	struct rxrpc_local *local;
-	struct rxrpc_peer *peer;
+	struct rxrpc_peer *peer = NULL;
 	struct sk_buff *skb;
 
 	rcu_read_lock();
@@ -172,41 +412,20 @@ void rxrpc_error_report(struct sock *sk)
 	}
 	rxrpc_new_skb(skb, rxrpc_skb_received);
 	serr = SKB_EXT_ERR(skb);
-	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
-		_leave("UDP empty message");
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		return;
-	}
 
-	peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
-	if (peer && !rxrpc_get_peer_maybe(peer))
-		peer = NULL;
-	if (!peer) {
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		_leave(" [no peer]");
-		return;
-	}
-
-	trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
-
-	if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
-	     serr->ee.ee_type == ICMP_DEST_UNREACH &&
-	     serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
-		rxrpc_adjust_mtu(peer, serr);
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		rxrpc_put_peer(peer);
-		_leave(" [MTU update]");
-		return;
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) {
+		peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx);
+		if (peer && !rxrpc_get_peer_maybe(peer))
+			peer = NULL;
+		if (peer) {
+			trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
+			rxrpc_store_error(peer, serr);
+		}
 	}
 
-	rxrpc_store_error(peer, serr);
 	rcu_read_unlock();
 	rxrpc_free_skb(skb, rxrpc_skb_freed);
 	rxrpc_put_peer(peer);
-
 	_leave("");
 }
 
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 250f23bc1c07..7e39c262fd79 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -771,46 +771,3 @@ 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/rxkad.c b/net/rxrpc/rxkad.c
index 258917a714c8..78fa0524156f 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -540,7 +540,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 	 * directly into the target buffer.
 	 */
 	sg = _sg;
-	nsg = skb_shinfo(skb)->nr_frags;
+	nsg = skb_shinfo(skb)->nr_frags + 1;
 	if (nsg <= 4) {
 		nsg = 4;
 	} else {