rxrpc: Fix data-race warning and potential load/store tearing

Fix the following:

BUG: KCSAN: data-race in rxrpc_peer_keepalive_worker / rxrpc_send_data_packet

which is reporting an issue with the reads and writes to ->last_tx_at in:

conn->peer->last_tx_at = ktime_get_seconds();

and:

keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;

The lockless accesses to these to values aren't actually a problem as the
read only needs an approximate time of last transmission for the purposes
of deciding whether or not the transmission of a keepalive packet is
warranted yet.

Also, as ->last_tx_at is a 64-bit value, tearing can occur on a 32-bit
arch.

Fix both of these by switching to an unsigned int for ->last_tx_at and only
storing the LSW of the time64_t. It can then be reconstructed at need
provided no more than 68 years has elapsed since the last transmission.

Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive")
Reported-by: [e-mail]
Closes: https://lore.kernel.org/r/[e-mail]/
Signed-off-by: David Howells <[e-mail]>
cc: Marc Dionne <[e-mail]>
cc: Simon Horman <[e-mail]>
cc: [e-mail]
cc: [e-mail]
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

net/rxrpc/ar-internal.h

···
 	struct rb_root		service_conns;	/* Service connections */
 	struct list_head	keepalive_link;	/* Link in net->peer_keepalive[] */
 	unsigned long		app_data;	/* Application data (e.g. afs_server) */
-	time64_t		last_tx_at;	/* Last time packet sent here */
+	unsigned int		last_tx_at;	/* Last time packet sent here (time64_t LSW) */
 	seqlock_t		service_conn_lock;
 	spinlock_t		lock;		/* access lock */
 	int			debug_id;	/* debug ID for printks */
···
 void rxrpc_peer_keepalive_worker(struct work_struct *);
 void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t acked_serial,
 				 bool sendmsg_fail);
+
+/* Update the last transmission time on a peer for keepalive purposes. */
+static inline void rxrpc_peer_mark_tx(struct rxrpc_peer *peer)
+{
+	/* To avoid tearing on 32-bit systems, we only keep the LSW. */
+	WRITE_ONCE(peer->last_tx_at, ktime_get_seconds());
+}
 
 /*
  * peer_object.c

net/rxrpc/conn_event.c

···
 	}
 
 	ret = kernel_sendmsg(conn->local->socket, &msg, iov, ioc, len);
-	conn->peer->last_tx_at = ktime_get_seconds();
+	rxrpc_peer_mark_tx(conn->peer);
 	if (ret < 0)
 		trace_rxrpc_tx_fail(chan->call_debug_id, serial, ret,
 				    rxrpc_tx_point_call_final_resend);

net/rxrpc/output.c

···
 	rxrpc_local_dont_fragment(conn->local, why == rxrpc_propose_ack_ping_for_mtu_probe);
 
 	ret = do_udp_sendmsg(conn->local->socket, &msg, len);
-	call->peer->last_tx_at = ktime_get_seconds();
+	rxrpc_peer_mark_tx(call->peer);
 	if (ret < 0) {
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_point_call_ack);
···
 
 	iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt));
 	ret = do_udp_sendmsg(conn->local->socket, &msg, sizeof(pkt));
-	conn->peer->last_tx_at = ktime_get_seconds();
+	rxrpc_peer_mark_tx(conn->peer);
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_point_call_abort);
···
 			ret = 0;
 			trace_rxrpc_tx_data(call, txb->seq, txb->serial, txb->flags,
 					    rxrpc_txdata_inject_loss);
-			conn->peer->last_tx_at = ktime_get_seconds();
+			rxrpc_peer_mark_tx(conn->peer);
 			goto done;
 		}
 	}
···
 	 */
 	rxrpc_inc_stat(call->rxnet, stat_tx_data_send);
 	ret = do_udp_sendmsg(conn->local->socket, &msg, len);
-	conn->peer->last_tx_at = ktime_get_seconds();
+	rxrpc_peer_mark_tx(conn->peer);
 
 	if (ret == -EMSGSIZE) {
 		rxrpc_inc_stat(call->rxnet, stat_tx_data_send_msgsize);
···
 
 	trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort);
 
-	conn->peer->last_tx_at = ktime_get_seconds();
+	rxrpc_peer_mark_tx(conn->peer);
 }
 
 /*
···
 		trace_rxrpc_tx_packet(peer->debug_id, &whdr,
 				      rxrpc_tx_point_version_keepalive);
 
-	peer->last_tx_at = ktime_get_seconds();
+	rxrpc_peer_mark_tx(peer);
 	_leave("");
 }
 
···
 	if (ret < 0)
 		goto fail;
 
-	conn->peer->last_tx_at = ktime_get_seconds();
+	rxrpc_peer_mark_tx(conn->peer);
 	return;
 
 fail:

net/rxrpc/peer_event.c

···
 }
 
 /*
+ * Reconstruct the last transmission time.  The difference calculated should be
+ * valid provided no more than ~68 years elapsed since the last transmission.
+ */
+static time64_t rxrpc_peer_get_tx_mark(const struct rxrpc_peer *peer, time64_t base)
+{
+	s32 last_tx_at = READ_ONCE(peer->last_tx_at);
+	s32 base_lsw = base;
+	s32 diff = last_tx_at - base_lsw;
+
+	diff = clamp(diff, -RXRPC_KEEPALIVE_TIME, RXRPC_KEEPALIVE_TIME);
+
+	return diff + base;
+}
+
+/*
  * Perform keep-alive pings.
  */
 static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
···
 		spin_unlock_bh(&rxnet->peer_hash_lock);
 
 		if (use) {
-			keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+			keepalive_at = rxrpc_peer_get_tx_mark(peer, base) + RXRPC_KEEPALIVE_TIME;
 			slot = keepalive_at - base;
 			_debug("%02x peer %u t=%d {%pISp}",
 			       cursor, peer->debug_id, slot, &peer->srx.transport);

net/rxrpc/proc.c

···
 
 	now = ktime_get_seconds();
 	seq_printf(seq,
-		   "UDP   %-47.47s %-47.47s %3u %4u %5u %6llus %8d %8d\n",
+		   "UDP   %-47.47s %-47.47s %3u %4u %5u %6ds %8d %8d\n",
 		   lbuff,
 		   rbuff,
 		   refcount_read(&peer->ref),
 		   peer->cong_ssthresh,
 		   peer->max_data,
-		   now - peer->last_tx_at,
+		   (s32)now - (s32)READ_ONCE(peer->last_tx_at),
 		   READ_ONCE(peer->recent_srtt_us),
 		   READ_ONCE(peer->recent_rto_us));
 

net/rxrpc/rxgk.c

···
 
 	ret = do_udp_sendmsg(conn->local->socket, &msg, len);
 	if (ret > 0)
-		conn->peer->last_tx_at = ktime_get_seconds();
+		rxrpc_peer_mark_tx(conn->peer);
 	__free_page(page);
 
 	if (ret < 0) {

net/rxrpc/rxkad.c

···
 		return -EAGAIN;
 	}
 
-	conn->peer->last_tx_at = ktime_get_seconds();
+	rxrpc_peer_mark_tx(conn->peer);
 	trace_rxrpc_tx_packet(conn->debug_id, &whdr,
 			      rxrpc_tx_point_rxkad_challenge);
 	_leave(" = 0");