Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) The real fix for the ipv6 route metric leak Sabrina was seeing, from
    Cong Wang.

 2) Fix syzbot triggers AF_PACKET v3 ring buffer insufficient room
    conditions, from Willem de Bruijn.

 3) vsock can reinitialize active work struct, fix from Cong Wang.

 4) RXRPC keepalive generator can wedge a cpu, fix from David Howells.

 5) Fix locking in AF_SMC ioctl, from Ursula Braun.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  dsa: slave: eee: Allow ports to use phylink
  net/smc: move sock lock in smc_ioctl()
  net/smc: allow sysctl rmem and wmem defaults for servers
  net/smc: no shutdown in state SMC_LISTEN
  net: aquantia: Fix IFF_ALLMULTI flag functionality
  rxrpc: Fix the keepalive generator [ver #2]
  net/mlx5e: Cleanup of dcbnl related fields
  net/mlx5e: Properly check if hairpin is possible between two functions
  vhost: reset metadata cache when initializing new IOTLB
  llc: use refcount_inc_not_zero() for llc_sap_find()
  dccp: fix undefined behavior with 'cwnd' shift in ccid2_cwnd_restart()
  tipc: fix an interrupt unsafe locking scenario
  vsock: split dwork to avoid reinitializations
  net: thunderx: check for failed allocation lmac->dmacs
  cxgb4: mk_act_open_req() buggers ->{local, peer}_ip on big-endian hosts
  packet: refine ring v3 block size test to hold one frame
  ip6_tunnel: use the right value for ipv4 min mtu check in ip6_tnl_xmit
  ipv6: fix double refcount of fib6_metrics

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c

@@ -762,7 +762,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 
 	hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC));
 	hw_atl_rpfl2multicast_flr_en_set(self,
-					 IS_FILTER_ENABLED(IFF_MULTICAST), 0);
+					 IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
 
 	hw_atl_rpfl2_accept_all_mc_packets_set(self,
 					       IS_FILTER_ENABLED(IFF_ALLMULTI));

drivers/net/ethernet/cavium/thunder/thunder_bgx.c

@@ -1083,6 +1083,8 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 	lmac->dmacs_count = (RX_DMAC_COUNT / bgx->lmac_count);
 	lmac->dmacs = kcalloc(lmac->dmacs_count, sizeof(*lmac->dmacs),
 			      GFP_KERNEL);
+	if (!lmac->dmacs)
+		return -ENOMEM;
 
 	/* Enable lmac */
 	bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN);

drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c

@@ -1038,10 +1038,8 @@ static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb,
 	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, qid_filterid));
 	req->local_port = cpu_to_be16(f->fs.val.lport);
 	req->peer_port = cpu_to_be16(f->fs.val.fport);
-	req->local_ip = f->fs.val.lip[0] | f->fs.val.lip[1] << 8 |
-		f->fs.val.lip[2] << 16 | f->fs.val.lip[3] << 24;
-	req->peer_ip = f->fs.val.fip[0] | f->fs.val.fip[1] << 8 |
-		f->fs.val.fip[2] << 16 | f->fs.val.fip[3] << 24;
+	memcpy(&req->local_ip, f->fs.val.lip, 4);
+	memcpy(&req->peer_ip, f->fs.val.fip, 4);
 	req->opt0 = cpu_to_be64(NAGLE_V(f->fs.newvlan == VLAN_REMOVE ||
 					f->fs.newvlan == VLAN_REWRITE) |
 				DELACK_V(f->fs.hitcnts) |

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -858,8 +858,6 @@ struct mlx5e_profile {
 		mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 		mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
 	} rx_handlers;
-	void	(*netdev_registered_init)(struct mlx5e_priv *priv);
-	void    (*netdev_registered_remove)(struct mlx5e_priv *priv);
 	int	max_tc;
 };
 

drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c

@@ -443,16 +443,12 @@ static int mlx5e_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app)
 	bool is_new;
 	int err;
 
-	if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
-		return -EINVAL;
-
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
-		return -EINVAL;
-
-	if (!MLX5_DSCP_SUPPORTED(priv->mdev))
-		return -EINVAL;
+	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) ||
+	    !MLX5_DSCP_SUPPORTED(priv->mdev))
+		return -EOPNOTSUPP;
 
-	if (app->protocol >= MLX5E_MAX_DSCP)
+	if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) ||
+	    (app->protocol >= MLX5E_MAX_DSCP))
 		return -EINVAL;
 
 	/* Save the old entry info */
@@ -500,16 +496,12 @@ static int mlx5e_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int err;
 
-	if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
-		return -EINVAL;
-
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
-		return -EINVAL;
-
-	if (!MLX5_DSCP_SUPPORTED(priv->mdev))
-		return -EINVAL;
+	if  (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) ||
+	     !MLX5_DSCP_SUPPORTED(priv->mdev))
+		return -EOPNOTSUPP;
 
-	if (app->protocol >= MLX5E_MAX_DSCP)
+	if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) ||
+	    (app->protocol >= MLX5E_MAX_DSCP))
 		return -EINVAL;
 
 	/* Skip if no dscp app entry */
@@ -1146,7 +1138,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state)
 {
 	int err;
 
-	err =  mlx5_set_trust_state(priv->mdev, trust_state);
+	err = mlx5_set_trust_state(priv->mdev, trust_state);
 	if (err)
 		return err;
 	priv->dcbx_dp.trust_state = trust_state;

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -1970,15 +1970,15 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
 {
 	struct mlx5_core_dev *fmdev, *pmdev;
-	u16 func_id, peer_id;
+	u64 fsystem_guid, psystem_guid;
 
 	fmdev = priv->mdev;
 	pmdev = peer_priv->mdev;
 
-	func_id = (u16)((fmdev->pdev->bus->number << 8) | PCI_SLOT(fmdev->pdev->devfn));
-	peer_id = (u16)((pmdev->pdev->bus->number << 8) | PCI_SLOT(pmdev->pdev->devfn));
+	mlx5_query_nic_vport_system_image_guid(fmdev, &fsystem_guid);
+	mlx5_query_nic_vport_system_image_guid(pmdev, &psystem_guid);
 
-	return (func_id == peer_id);
+	return (fsystem_guid == psystem_guid);
 }
 
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,

drivers/vhost/vhost.c

@@ -1560,9 +1560,12 @@ int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
 	d->iotlb = niotlb;
 
 	for (i = 0; i < d->nvqs; ++i) {
-		mutex_lock(&d->vqs[i]->mutex);
-		d->vqs[i]->iotlb = niotlb;
-		mutex_unlock(&d->vqs[i]->mutex);
+		struct vhost_virtqueue *vq = d->vqs[i];
+
+		mutex_lock(&vq->mutex);
+		vq->iotlb = niotlb;
+		__vhost_vq_meta_reset(vq);
+		mutex_unlock(&vq->mutex);
 	}
 
 	vhost_umem_clean(oiotlb);

include/net/af_vsock.h

@@ -64,7 +64,8 @@ struct vsock_sock {
 	struct list_head pending_links;
 	struct list_head accept_queue;
 	bool rejected;
-	struct delayed_work dwork;
+	struct delayed_work connect_work;
+	struct delayed_work pending_work;
 	struct delayed_work close_work;
 	bool close_work_scheduled;
 	u32 peer_shutdown;
@@ -77,7 +78,6 @@ struct vsock_sock {
 
 s64 vsock_stream_has_data(struct vsock_sock *vsk);
 s64 vsock_stream_has_space(struct vsock_sock *vsk);
-void vsock_pending_work(struct work_struct *work);
 struct sock *__vsock_create(struct net *net,
 			    struct socket *sock,
 			    struct sock *parent,

include/net/llc.h

@@ -116,6 +116,11 @@ static inline void llc_sap_hold(struct llc_sap *sap)
 	refcount_inc(&sap->refcnt);
 }
 
+static inline bool llc_sap_hold_safe(struct llc_sap *sap)
+{
+	return refcount_inc_not_zero(&sap->refcnt);
+}
+
 void llc_sap_close(struct llc_sap *sap);
 
 static inline void llc_sap_put(struct llc_sap *sap)

net/dccp/ccids/ccid2.c

@@ -229,14 +229,16 @@ static void ccid2_cwnd_restart(struct sock *sk, const u32 now)
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
 	u32 cwnd = hc->tx_cwnd, restart_cwnd,
 	    iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache);
+	s32 delta = now - hc->tx_lsndtime;
 
 	hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2));
 
 	/* don't reduce cwnd below the initial window (IW) */
 	restart_cwnd = min(cwnd, iwnd);
-	cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto;
-	hc->tx_cwnd = max(cwnd, restart_cwnd);
 
+	while ((delta -= hc->tx_rto) >= 0 && cwnd > restart_cwnd)
+		cwnd >>= 1;
+	hc->tx_cwnd = max(cwnd, restart_cwnd);
 	hc->tx_cwnd_stamp = now;
 	hc->tx_cwnd_used  = 0;
 

net/dsa/slave.c

@@ -639,7 +639,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev)
+	if (!dev->phydev && !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->set_mac_eee)
@@ -659,7 +659,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev)
+	if (!dev->phydev && !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->get_mac_eee)

net/ipv6/ip6_tunnel.c

@@ -1133,12 +1133,8 @@ route_lookup:
 		max_headroom += 8;
 		mtu -= 8;
 	}
-	if (skb->protocol == htons(ETH_P_IPV6)) {
-		if (mtu < IPV6_MIN_MTU)
-			mtu = IPV6_MIN_MTU;
-	} else if (mtu < 576) {
-		mtu = 576;
-	}
+	mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
+		       IPV6_MIN_MTU : IPV4_MIN_MTU);
 
 	skb_dst_update_pmtu(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {

net/ipv6/route.c

@@ -978,10 +978,6 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
 	rt->rt6i_flags &= ~RTF_EXPIRES;
 	rcu_assign_pointer(rt->from, from);
 	dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
-	if (from->fib6_metrics != &dst_default_metrics) {
-		rt->dst._metrics |= DST_METRICS_REFCOUNTED;
-		refcount_inc(&from->fib6_metrics->refcnt);
-	}
 }
 
 /* Caller must already hold reference to @ort */

net/llc/llc_core.c

@@ -73,8 +73,8 @@ struct llc_sap *llc_sap_find(unsigned char sap_value)
 
 	rcu_read_lock_bh();
 	sap = __llc_sap_find(sap_value);
-	if (sap)
-		llc_sap_hold(sap);
+	if (!sap || !llc_sap_hold_safe(sap))
+		sap = NULL;
 	rcu_read_unlock_bh();
 	return sap;
 }

net/packet/af_packet.c

@@ -4226,6 +4226,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	}
 
 	if (req->tp_block_nr) {
+		unsigned int min_frame_size;
+
 		/* Sanity tests and some calculations */
 		err = -EBUSY;
 		if (unlikely(rb->pg_vec))
@@ -4248,12 +4250,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 		if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
 			goto out;
+		min_frame_size = po->tp_hdrlen + po->tp_reserve;
 		if (po->tp_version >= TPACKET_V3 &&
-		    req->tp_block_size <=
-		    BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr))
+		    req->tp_block_size <
+		    BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size)
 			goto out;
-		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
-					po->tp_reserve))
+		if (unlikely(req->tp_frame_size < min_frame_size))
 			goto out;
 		if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1)))
 			goto out;

net/rxrpc/ar-internal.h

@@ -104,9 +104,9 @@ struct rxrpc_net {
 
 #define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */
 	u8			peer_keepalive_cursor;
-	ktime_t			peer_keepalive_base;
-	struct hlist_head	peer_keepalive[RXRPC_KEEPALIVE_TIME + 1];
-	struct hlist_head	peer_keepalive_new;
+	time64_t		peer_keepalive_base;
+	struct list_head	peer_keepalive[32];
+	struct list_head	peer_keepalive_new;
 	struct timer_list	peer_keepalive_timer;
 	struct work_struct	peer_keepalive_work;
 };
@@ -295,7 +295,7 @@ struct rxrpc_peer {
 	struct hlist_head	error_targets;	/* targets for net error distribution */
 	struct work_struct	error_distributor;
 	struct rb_root		service_conns;	/* Service connections */
-	struct hlist_node	keepalive_link;	/* Link in net->peer_keepalive[] */
+	struct list_head	keepalive_link;	/* Link in net->peer_keepalive[] */
 	time64_t		last_tx_at;	/* Last time packet sent here */
 	seqlock_t		service_conn_lock;
 	spinlock_t		lock;		/* access lock */

net/rxrpc/conn_event.c

@@ -136,7 +136,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 	}
 
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_final_resend);
@@ -245,7 +245,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 
 	_leave(" = 0");
 	return 0;

net/rxrpc/net_ns.c

@@ -85,12 +85,12 @@ static __net_init int rxrpc_init_net(struct net *net)
 	hash_init(rxnet->peer_hash);
 	spin_lock_init(&rxnet->peer_hash_lock);
 	for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++)
-		INIT_HLIST_HEAD(&rxnet->peer_keepalive[i]);
-	INIT_HLIST_HEAD(&rxnet->peer_keepalive_new);
+		INIT_LIST_HEAD(&rxnet->peer_keepalive[i]);
+	INIT_LIST_HEAD(&rxnet->peer_keepalive_new);
 	timer_setup(&rxnet->peer_keepalive_timer,
 		    rxrpc_peer_keepalive_timeout, 0);
 	INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker);
-	rxnet->peer_keepalive_base = ktime_add(ktime_get_real(), NSEC_PER_SEC);
+	rxnet->peer_keepalive_base = ktime_get_seconds();
 
 	ret = -ENOMEM;
 	rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net);

net/rxrpc/output.c

@@ -209,7 +209,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	now = ktime_get_real();
 	if (ping)
 		call->ping_time = now;
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_ack);
@@ -296,7 +296,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 
 	ret = kernel_sendmsg(conn->params.local->socket,
 			     &msg, iov, 1, sizeof(pkt));
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_abort);
@@ -391,7 +391,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	 *     message and update the peer record
 	 */
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 
 	up_read(&conn->params.local->defrag_sem);
 	if (ret < 0)
@@ -457,7 +457,7 @@ send_fragmentable:
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
 					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_real();
+			conn->params.peer->last_tx_at = ktime_get_seconds();
 
 			opt = IP_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket, SOL_IP,
@@ -475,7 +475,7 @@ send_fragmentable:
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
 					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_real();
+			conn->params.peer->last_tx_at = ktime_get_seconds();
 
 			opt = IPV6_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket,
@@ -599,6 +599,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer)
 		trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
 				    rxrpc_tx_fail_version_keepalive);
 
-	peer->last_tx_at = ktime_get_real();
+	peer->last_tx_at = ktime_get_seconds();
 	_leave("");
 }

net/rxrpc/peer_event.c

@@ -350,97 +350,117 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
 }
 
 /*
- * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ * Perform keep-alive pings.
  */
-void rxrpc_peer_keepalive_worker(struct work_struct *work)
+static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
+					  struct list_head *collector,
+					  time64_t base,
+					  u8 cursor)
 {
-	struct rxrpc_net *rxnet =
-		container_of(work, struct rxrpc_net, peer_keepalive_work);
 	struct rxrpc_peer *peer;
-	unsigned long delay;
-	ktime_t base, now = ktime_get_real();
-	s64 diff;
-	u8 cursor, slot;
+	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+	time64_t keepalive_at;
+	int slot;
 
-	base = rxnet->peer_keepalive_base;
-	cursor = rxnet->peer_keepalive_cursor;
+	spin_lock_bh(&rxnet->peer_hash_lock);
 
-	_enter("%u,%lld", cursor, ktime_sub(now, base));
+	while (!list_empty(collector)) {
+		peer = list_entry(collector->next,
+				  struct rxrpc_peer, keepalive_link);
 
-next_bucket:
-	diff = ktime_to_ns(ktime_sub(now, base));
-	if (diff < 0)
-		goto resched;
+		list_del_init(&peer->keepalive_link);
+		if (!rxrpc_get_peer_maybe(peer))
+			continue;
 
-	_debug("at %u", cursor);
-	spin_lock_bh(&rxnet->peer_hash_lock);
-next_peer:
-	if (!rxnet->live) {
 		spin_unlock_bh(&rxnet->peer_hash_lock);
-		goto out;
-	}
 
-	/* Everything in the bucket at the cursor is processed this second; the
-	 * bucket at cursor + 1 goes now + 1s and so on...
-	 */
-	if (hlist_empty(&rxnet->peer_keepalive[cursor])) {
-		if (hlist_empty(&rxnet->peer_keepalive_new)) {
-			spin_unlock_bh(&rxnet->peer_hash_lock);
-			goto emptied_bucket;
+		keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+		slot = keepalive_at - base;
+		_debug("%02x peer %u t=%d {%pISp}",
+		       cursor, peer->debug_id, slot, &peer->srx.transport);
+
+		if (keepalive_at <= base ||
+		    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+			rxrpc_send_keepalive(peer);
+			slot = RXRPC_KEEPALIVE_TIME;
 		}
 
-		hlist_move_list(&rxnet->peer_keepalive_new,
-				&rxnet->peer_keepalive[cursor]);
+		/* A transmission to this peer occurred since last we examined
+		 * it so put it into the appropriate future bucket.
+		 */
+		slot += cursor;
+		slot &= mask;
+		spin_lock_bh(&rxnet->peer_hash_lock);
+		list_add_tail(&peer->keepalive_link,
+			      &rxnet->peer_keepalive[slot & mask]);
+		rxrpc_put_peer(peer);
 	}
 
-	peer = hlist_entry(rxnet->peer_keepalive[cursor].first,
-			   struct rxrpc_peer, keepalive_link);
-	hlist_del_init(&peer->keepalive_link);
-	if (!rxrpc_get_peer_maybe(peer))
-		goto next_peer;
-
 	spin_unlock_bh(&rxnet->peer_hash_lock);
+}
 
-	_debug("peer %u {%pISp}", peer->debug_id, &peer->srx.transport);
+/*
+ * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ */
+void rxrpc_peer_keepalive_worker(struct work_struct *work)
+{
+	struct rxrpc_net *rxnet =
+		container_of(work, struct rxrpc_net, peer_keepalive_work);
+	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+	time64_t base, now, delay;
+	u8 cursor, stop;
+	LIST_HEAD(collector);
 
-recalc:
-	diff = ktime_divns(ktime_sub(peer->last_tx_at, base), NSEC_PER_SEC);
-	if (diff < -30 || diff > 30)
-		goto send; /* LSW of 64-bit time probably wrapped on 32-bit */
-	diff += RXRPC_KEEPALIVE_TIME - 1;
-	if (diff < 0)
-		goto send;
+	now = ktime_get_seconds();
+	base = rxnet->peer_keepalive_base;
+	cursor = rxnet->peer_keepalive_cursor;
+	_enter("%lld,%u", base - now, cursor);
 
-	slot = (diff > RXRPC_KEEPALIVE_TIME - 1) ? RXRPC_KEEPALIVE_TIME - 1 : diff;
-	if (slot == 0)
-		goto send;
+	if (!rxnet->live)
+		return;
 
-	/* A transmission to this peer occurred since last we examined it so
-	 * put it into the appropriate future bucket.
+	/* Remove to a temporary list all the peers that are currently lodged
+	 * in expired buckets plus all new peers.
+	 *
+	 * Everything in the bucket at the cursor is processed this
+	 * second; the bucket at cursor + 1 goes at now + 1s and so
+	 * on...
 	 */
-	slot = (slot + cursor) % ARRAY_SIZE(rxnet->peer_keepalive);
 	spin_lock_bh(&rxnet->peer_hash_lock);
-	hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive[slot]);
-	rxrpc_put_peer(peer);
-	goto next_peer;
-
-send:
-	rxrpc_send_keepalive(peer);
-	now = ktime_get_real();
-	goto recalc;
+	list_splice_init(&rxnet->peer_keepalive_new, &collector);
+
+	stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive);
+	while (base <= now && (s8)(cursor - stop) < 0) {
+		list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask],
+				      &collector);
+		base++;
+		cursor++;
+	}
 
-emptied_bucket:
-	cursor++;
-	if (cursor >= ARRAY_SIZE(rxnet->peer_keepalive))
-		cursor = 0;
-	base = ktime_add_ns(base, NSEC_PER_SEC);
-	goto next_bucket;
+	base = now;
+	spin_unlock_bh(&rxnet->peer_hash_lock);
 
-resched:
 	rxnet->peer_keepalive_base = base;
 	rxnet->peer_keepalive_cursor = cursor;
-	delay = nsecs_to_jiffies(-diff) + 1;
-	timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
-out:
+	rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor);
+	ASSERT(list_empty(&collector));
+
+	/* Schedule the timer for the next occupied timeslot. */
+	cursor = rxnet->peer_keepalive_cursor;
+	stop = cursor + RXRPC_KEEPALIVE_TIME - 1;
+	for (; (s8)(cursor - stop) < 0; cursor++) {
+		if (!list_empty(&rxnet->peer_keepalive[cursor & mask]))
+			break;
+		base++;
+	}
+
+	now = ktime_get_seconds();
+	delay = base - now;
+	if (delay < 1)
+		delay = 1;
+	delay *= HZ;
+	if (rxnet->live)
+		timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
+
 	_leave("");
 }

net/rxrpc/peer_object.c

@@ -322,7 +322,7 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local,
 	if (!peer) {
 		peer = prealloc;
 		hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
-		hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive_new);
+		list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
 	}
 
 	spin_unlock(&rxnet->peer_hash_lock);
@@ -367,8 +367,8 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
 		if (!peer) {
 			hash_add_rcu(rxnet->peer_hash,
 				     &candidate->hash_link, hash_key);
-			hlist_add_head(&candidate->keepalive_link,
-				       &rxnet->peer_keepalive_new);
+			list_add_tail(&candidate->keepalive_link,
+				      &rxnet->peer_keepalive_new);
 		}
 
 		spin_unlock_bh(&rxnet->peer_hash_lock);
@@ -441,7 +441,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
 
 	spin_lock_bh(&rxnet->peer_hash_lock);
 	hash_del_rcu(&peer->hash_link);
-	hlist_del_init(&peer->keepalive_link);
+	list_del_init(&peer->keepalive_link);
 	spin_unlock_bh(&rxnet->peer_hash_lock);
 
 	kfree_rcu(peer, rcu);

net/rxrpc/rxkad.c

@@ -669,7 +669,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	_leave(" = 0");
 	return 0;
 }
@@ -725,7 +725,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	_leave(" = 0");
 	return 0;
 }

net/smc/af_smc.c

@@ -1122,6 +1122,8 @@ static void smc_tcp_listen_work(struct work_struct *work)
 		sock_hold(lsk); /* sock_put in smc_listen_work */
 		INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
 		smc_copy_sock_settings_to_smc(new_smc);
+		new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf;
+		new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf;
 		sock_hold(&new_smc->sk); /* sock_put in passive closing */
 		if (!schedule_work(&new_smc->smc_listen_work))
 			sock_put(&new_smc->sk);
@@ -1397,8 +1399,7 @@ static int smc_shutdown(struct socket *sock, int how)
 	lock_sock(sk);
 
 	rc = -ENOTCONN;
-	if ((sk->sk_state != SMC_LISTEN) &&
-	    (sk->sk_state != SMC_ACTIVE) &&
+	if ((sk->sk_state != SMC_ACTIVE) &&
 	    (sk->sk_state != SMC_PEERCLOSEWAIT1) &&
 	    (sk->sk_state != SMC_PEERCLOSEWAIT2) &&
 	    (sk->sk_state != SMC_APPCLOSEWAIT1) &&
@@ -1521,12 +1522,16 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 
 	smc = smc_sk(sock->sk);
 	conn = &smc->conn;
+	lock_sock(&smc->sk);
 	if (smc->use_fallback) {
-		if (!smc->clcsock)
+		if (!smc->clcsock) {
+			release_sock(&smc->sk);
 			return -EBADF;
-		return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+		}
+		answ = smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+		release_sock(&smc->sk);
+		return answ;
 	}
-	lock_sock(&smc->sk);
 	switch (cmd) {
 	case SIOCINQ: /* same as FIONREAD */
 		if (smc->sk.sk_state == SMC_LISTEN) {

net/tipc/net.c

@@ -123,15 +123,13 @@ void tipc_net_finalize(struct net *net, u32 addr)
 {
 	struct tipc_net *tn = tipc_net(net);
 
-	spin_lock_bh(&tn->node_list_lock);
-	if (!tipc_own_addr(net)) {
+	if (!cmpxchg(&tn->node_addr, 0, addr)) {
 		tipc_set_node_addr(net, addr);
 		tipc_named_reinit(net);
 		tipc_sk_reinit(net);
 		tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
 				     TIPC_CLUSTER_SCOPE, 0, addr);
 	}
-	spin_unlock_bh(&tn->node_list_lock);
 }
 
 void tipc_net_stop(struct net *net)

net/vmw_vsock/af_vsock.c

@@ -451,14 +451,14 @@ static int vsock_send_shutdown(struct sock *sk, int mode)
 	return transport->shutdown(vsock_sk(sk), mode);
 }
 
-void vsock_pending_work(struct work_struct *work)
+static void vsock_pending_work(struct work_struct *work)
 {
 	struct sock *sk;
 	struct sock *listener;
 	struct vsock_sock *vsk;
 	bool cleanup;
 
-	vsk = container_of(work, struct vsock_sock, dwork.work);
+	vsk = container_of(work, struct vsock_sock, pending_work.work);
 	sk = sk_vsock(vsk);
 	listener = vsk->listener;
 	cleanup = true;
@@ -498,7 +498,6 @@ out:
 	sock_put(sk);
 	sock_put(listener);
 }
-EXPORT_SYMBOL_GPL(vsock_pending_work);
 
 /**** SOCKET OPERATIONS ****/
 
@@ -597,6 +596,8 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
 	return retval;
 }
 
+static void vsock_connect_timeout(struct work_struct *work);
+
 struct sock *__vsock_create(struct net *net,
 			    struct socket *sock,
 			    struct sock *parent,
@@ -638,6 +639,8 @@ struct sock *__vsock_create(struct net *net,
 	vsk->sent_request = false;
 	vsk->ignore_connecting_rst = false;
 	vsk->peer_shutdown = 0;
+	INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout);
+	INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work);
 
 	psk = parent ? vsock_sk(parent) : NULL;
 	if (parent) {
@@ -1117,7 +1120,7 @@ static void vsock_connect_timeout(struct work_struct *work)
 	struct vsock_sock *vsk;
 	int cancel = 0;
 
-	vsk = container_of(work, struct vsock_sock, dwork.work);
+	vsk = container_of(work, struct vsock_sock, connect_work.work);
 	sk = sk_vsock(vsk);
 
 	lock_sock(sk);
@@ -1221,9 +1224,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 			 * timeout fires.
 			 */
 			sock_hold(sk);
-			INIT_DELAYED_WORK(&vsk->dwork,
-					  vsock_connect_timeout);
-			schedule_delayed_work(&vsk->dwork, timeout);
+			schedule_delayed_work(&vsk->connect_work, timeout);
 
 			/* Skip ahead to preserve error code set above. */
 			goto out_wait;

net/vmw_vsock/vmci_transport.c

@@ -1094,8 +1094,7 @@ static int vmci_transport_recv_listen(struct sock *sk,
 	vpending->listener = sk;
 	sock_hold(sk);
 	sock_hold(pending);
-	INIT_DELAYED_WORK(&vpending->dwork, vsock_pending_work);
-	schedule_delayed_work(&vpending->dwork, HZ);
+	schedule_delayed_work(&vpending->pending_work, HZ);
 
 out:
 	return err;