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

davem330 · davem330 · commit e7506d344bf1 · 2022-09-02T12:45:32.000+01:00
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 -&gt;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 &lt;davem@davemloft.net&gt;
diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst
@@ -1055,17 +1055,6 @@ The kernel interface functions are as follows:
      first function to change.  Note that this must be called in TASK_RUNNING
      state.
 
- (#) Get reply timestamp::
-
-	bool rxrpc_kernel_get_reply_time(struct socket *sock,
-					 struct rxrpc_call *call,
-					 ktime_t *_ts)
-
-     This allows the timestamp on the first DATA packet of the reply of a
-     client call to be queried, provided that it is still in the Rx ring.  If
-     successful, the timestamp will be stored into ``*_ts`` and true will be
-     returned; false will be returned otherwise.
-
  (#) Get remote client epoch::
 
 	u32 rxrpc_kernel_get_epoch(struct socket *sock,
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
@@ -76,7 +76,7 @@ void afs_lock_op_done(struct afs_call *call)
 	if (call->error == 0) {
 		spin_lock(&vnode->lock);
 		trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0);
-		vnode->locked_at = call->reply_time;
+		vnode->locked_at = call->issue_time;
 		afs_schedule_lock_extension(vnode);
 		spin_unlock(&vnode->lock);
 	}
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
@@ -131,7 +131,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
 
 static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry)
 {
-	return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry;
+	return ktime_divns(call->issue_time, NSEC_PER_SEC) + expiry;
 }
 
 static void xdr_decode_AFSCallBack(const __be32 **_bp,
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
@@ -137,7 +137,6 @@ struct afs_call {
 	bool			need_attention;	/* T if RxRPC poked us */
 	bool			async;		/* T if asynchronous */
 	bool			upgrade;	/* T to request service upgrade */
-	bool			have_reply_time; /* T if have got reply_time */
 	bool			intr;		/* T if interruptible */
 	bool			unmarshalling_error; /* T if an unmarshalling error occurred */
 	u16			service_id;	/* Actual service ID (after upgrade) */
@@ -151,7 +150,7 @@ struct afs_call {
 		} __attribute__((packed));
 		__be64		tmp64;
 	};
-	ktime_t			reply_time;	/* Time of first reply packet */
+	ktime_t			issue_time;	/* Time of issue of operation */
 };
 
 struct afs_call_type {
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
@@ -351,6 +351,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	if (call->max_lifespan)
 		rxrpc_kernel_set_max_life(call->net->socket, rxcall,
 					  call->max_lifespan);
+	call->issue_time = ktime_get_real();
 
 	/* send the request */
 	iov[0].iov_base	= call->request;
@@ -501,12 +502,6 @@ static void afs_deliver_to_call(struct afs_call *call)
 			return;
 		}
 
-		if (!call->have_reply_time &&
-		    rxrpc_kernel_get_reply_time(call->net->socket,
-						call->rxcall,
-						&call->reply_time))
-			call->have_reply_time = true;
-
 		ret = call->type->deliver(call);
 		state = READ_ONCE(call->state);
 		if (ret == 0 && call->unmarshalling_error)
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
@@ -232,8 +232,7 @@ static void xdr_decode_YFSCallBack(const __be32 **_bp,
 	struct afs_callback *cb = &scb->callback;
 	ktime_t cb_expiry;
 
-	cb_expiry = call->reply_time;
-	cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100);
+	cb_expiry = ktime_add(call->issue_time, xdr_to_u64(x->expiration_time) * 100);
 	cb->expires_at	= ktime_divns(cb_expiry, NSEC_PER_SEC);
 	scb->have_cb	= true;
 	*_bp += xdr_size(x);
diff --git a/include/linux/udp.h b/include/linux/udp.h
@@ -70,6 +70,7 @@ struct udp_sock {
 	 * For encapsulation sockets.
 	 */
 	int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
+	void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 	int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb);
 	void (*encap_destroy)(struct sock *sk);
 
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
@@ -66,8 +66,6 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
 bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *);
 u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *);
-bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *,
-				 ktime_t *);
 bool rxrpc_kernel_call_is_complete(struct rxrpc_call *);
 void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *,
 			       unsigned long);
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
@@ -67,6 +67,9 @@ static inline int udp_sock_create(struct net *net,
 typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
 typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk,
 					     struct sk_buff *skb);
+typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk,
+					   struct sk_buff *skb,
+					   unsigned int udp_offset);
 typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
 typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
 						    struct list_head *head,
@@ -80,6 +83,7 @@ struct udp_tunnel_sock_cfg {
 	__u8  encap_type;
 	udp_tunnel_encap_rcv_t encap_rcv;
 	udp_tunnel_encap_err_lookup_t encap_err_lookup;
+	udp_tunnel_encap_err_rcv_t encap_err_rcv;
 	udp_tunnel_encap_destroy_t encap_destroy;
 	udp_tunnel_gro_receive_t gro_receive;
 	udp_tunnel_gro_complete_t gro_complete;
diff --git 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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c

Original file line number	Diff line number	Diff line change
`@@ -76,7 +76,7 @@ void afs_lock_op_done(struct afs_call *call)`
`76`	`76`	`if (call->error == 0) {`
`77`	`77`	`spin_lock(&vnode->lock);`
`78`	`78`	`trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0);`
`79`		`- vnode->locked_at = call->reply_time;`
	`79`	`+ vnode->locked_at = call->issue_time;`
`80`	`80`	`afs_schedule_lock_extension(vnode);`
`81`	`81`	`spin_unlock(&vnode->lock);`
`82`	`82`	`}`
Original file line number	Diff line number	Diff line change
`@@ -131,7 +131,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,`
`131`	`131`
`132`	`132`	`static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry)`
`133`	`133`	`{`
`134`		`- return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry;`
	`134`	`+ return ktime_divns(call->issue_time, NSEC_PER_SEC) + expiry;`
`135`	`135`	`}`
`136`	`136`
`137`	`137`	`static void xdr_decode_AFSCallBack(const __be32 **_bp,`
Original file line number	Diff line number	Diff line change
`@@ -783,6 +783,8 @@ int __udp4_lib_err(struct sk_buff skb, u32 info, struct udp_table udptable)`
`783`	`783`	`*/`
`784`	`784`	`if (tunnel) {`
`785`	`785`	`/* ...not for tunnels though: we don't have a sending socket */`
	`786`	`+ if (udp_sk(sk)->encap_err_rcv)`
	`787`	`+ udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2);`
`786`	`788`	`goto out;`
`787`	`789`	`}`
`788`	`790`	`if (!inet->recverr) {`