Merge tag 'net-5.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski.
 "Including fixes from bpf and netfilter.

  Current release - regressions:

   - sock: fix parameter order in sock_setsockopt()

  Current release - new code bugs:

   - netfilter: nft_last:
       - fix incorrect arithmetic when restoring last used
       - honor NFTA_LAST_SET on restoration

  Previous releases - regressions:

   - udp: properly flush normal packet at GRO time

   - sfc: ensure correct number of XDP queues; don't allow enabling the
     feature if there isn't sufficient resources to Tx from any CPU

   - dsa: sja1105: fix address learning getting disabled on the CPU port

   - mptcp: addresses a rmem accounting issue that could keep packets in
     subflow receive buffers longer than necessary, delaying MPTCP-level
     ACKs

   - ip_tunnel: fix mtu calculation for ETHER tunnel devices

   - do not reuse skbs allocated from skbuff_fclone_cache in the napi
     skb cache, we'd try to return them to the wrong slab cache

   - tcp: consistently disable header prediction for mptcp

  Previous releases - always broken:

   - bpf: fix subprog poke descriptor tracking use-after-free

   - ipv6:
       - allocate enough headroom in ip6_finish_output2() in case
         iptables TEE is used
       - tcp: drop silly ICMPv6 packet too big messages to avoid
         expensive and pointless lookups (which may serve as a DDOS
         vector)
       - make sure fwmark is copied in SYNACK packets
       - fix 'disable_policy' for forwarded packets (align with IPv4)

   - netfilter: conntrack:
       - do not renew entry stuck in tcp SYN_SENT state
       - do not mark RST in the reply direction coming after SYN packet
         for an out-of-sync entry

   - mptcp: cleanly handle error conditions with MP_JOIN and syncookies

   - mptcp: fix double free when rejecting a join due to port mismatch

   - validate lwtstate->data before returning from skb_tunnel_info()

   - tcp: call sk_wmem_schedule before sk_mem_charge in zerocopy path

   - mt76: mt7921: continue to probe driver when fw already downloaded

   - bonding: fix multiple issues with offloading IPsec to (thru?) bond

   - stmmac: ptp: fix issues around Qbv support and setting time back

   - bcmgenet: always clear wake-up based on energy detection

  Misc:

   - sctp: move 198 addresses from unusable to private scope

   - ptp: support virtual clocks and timestamping

   - openvswitch: optimize operation for key comparison"

* tag 'net-5.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (158 commits)
  net: dsa: properly check for the bridge_leave methods in dsa_switch_bridge_leave()
  sfc: add logs explaining XDP_TX/REDIRECT is not available
  sfc: ensure correct number of XDP queues
  sfc: fix lack of XDP TX queues - error XDP TX failed (-22)
  net: fddi: fix UAF in fza_probe
  net: dsa: sja1105: fix address learning getting disabled on the CPU port
  net: ocelot: fix switchdev objects synced for wrong netdev with LAG offload
  net: Use nlmsg_unicast() instead of netlink_unicast()
  octeontx2-pf: Fix uninitialized boolean variable pps
  ipv6: allocate enough headroom in ip6_finish_output2()
  net: hdlc: rename 'mod_init' & 'mod_exit' functions to be module-specific
  net: bridge: multicast: fix MRD advertisement router port marking race
  net: bridge: multicast: fix PIM hello router port marking race
  net: phy: marvell10g: fix differentiation of 88X3310 from 88X3340
  dsa: fix for_each_child.cocci warnings
  virtio_net: check virtqueue_add_sgs() return value
  mptcp: properly account bulk freed memory
  selftests: mptcp: fix case multiple subflows limited by server
  mptcp: avoid processing packet if a subflow reset
  mptcp: fix syncookie process if mptcp can not_accept new subflow
  ...

1 files changed, 153 insertions, 28 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 0ff7567bd04f..d22d78303311 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -401,24 +401,85 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
 static int bond_ipsec_add_sa(struct xfrm_state *xs)
 {
 	struct net_device *bond_dev = xs->xso.dev;
+	struct bond_ipsec *ipsec;
 	struct bonding *bond;
 	struct slave *slave;
+	int err;
 
 	if (!bond_dev)
 		return -EINVAL;
 
+	rcu_read_lock();
 	bond = netdev_priv(bond_dev);
 	slave = rcu_dereference(bond->curr_active_slave);
-	xs->xso.real_dev = slave->dev;
-	bond->xs = xs;
+	if (!slave) {
+		rcu_read_unlock();
+		return -ENODEV;
+	}
 
-	if (!(slave->dev->xfrmdev_ops
-	      && slave->dev->xfrmdev_ops->xdo_dev_state_add)) {
+	if (!slave->dev->xfrmdev_ops ||
+	    !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
+	    netif_is_bond_master(slave->dev)) {
 		slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n");
+		rcu_read_unlock();
 		return -EINVAL;
 	}
 
-	return slave->dev->xfrmdev_ops->xdo_dev_state_add(xs);
+	ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC);
+	if (!ipsec) {
+		rcu_read_unlock();
+		return -ENOMEM;
+	}
+	xs->xso.real_dev = slave->dev;
+
+	err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs);
+	if (!err) {
+		ipsec->xs = xs;
+		INIT_LIST_HEAD(&ipsec->list);
+		spin_lock_bh(&bond->ipsec_lock);
+		list_add(&ipsec->list, &bond->ipsec_list);
+		spin_unlock_bh(&bond->ipsec_lock);
+	} else {
+		kfree(ipsec);
+	}
+	rcu_read_unlock();
+	return err;
+}
+
+static void bond_ipsec_add_sa_all(struct bonding *bond)
+{
+	struct net_device *bond_dev = bond->dev;
+	struct bond_ipsec *ipsec;
+	struct slave *slave;
+
+	rcu_read_lock();
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (!slave)
+		goto out;
+
+	if (!slave->dev->xfrmdev_ops ||
+	    !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
+	    netif_is_bond_master(slave->dev)) {
+		spin_lock_bh(&bond->ipsec_lock);
+		if (!list_empty(&bond->ipsec_list))
+			slave_warn(bond_dev, slave->dev,
+				   "%s: no slave xdo_dev_state_add\n",
+				   __func__);
+		spin_unlock_bh(&bond->ipsec_lock);
+		goto out;
+	}
+
+	spin_lock_bh(&bond->ipsec_lock);
+	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+		ipsec->xs->xso.real_dev = slave->dev;
+		if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs)) {
+			slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__);
+			ipsec->xs->xso.real_dev = NULL;
+		}
+	}
+	spin_unlock_bh(&bond->ipsec_lock);
+out:
+	rcu_read_unlock();
 }
 
 /**
@@ -428,27 +489,77 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs)
 static void bond_ipsec_del_sa(struct xfrm_state *xs)
 {
 	struct net_device *bond_dev = xs->xso.dev;
+	struct bond_ipsec *ipsec;
 	struct bonding *bond;
 	struct slave *slave;
 
 	if (!bond_dev)
 		return;
 
+	rcu_read_lock();
 	bond = netdev_priv(bond_dev);
 	slave = rcu_dereference(bond->curr_active_slave);
 
 	if (!slave)
-		return;
+		goto out;
 
-	xs->xso.real_dev = slave->dev;
+	if (!xs->xso.real_dev)
+		goto out;
+
+	WARN_ON(xs->xso.real_dev != slave->dev);
 
-	if (!(slave->dev->xfrmdev_ops
-	      && slave->dev->xfrmdev_ops->xdo_dev_state_delete)) {
+	if (!slave->dev->xfrmdev_ops ||
+	    !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
+	    netif_is_bond_master(slave->dev)) {
 		slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__);
-		return;
+		goto out;
 	}
 
 	slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs);
+out:
+	spin_lock_bh(&bond->ipsec_lock);
+	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+		if (ipsec->xs == xs) {
+			list_del(&ipsec->list);
+			kfree(ipsec);
+			break;
+		}
+	}
+	spin_unlock_bh(&bond->ipsec_lock);
+	rcu_read_unlock();
+}
+
+static void bond_ipsec_del_sa_all(struct bonding *bond)
+{
+	struct net_device *bond_dev = bond->dev;
+	struct bond_ipsec *ipsec;
+	struct slave *slave;
+
+	rcu_read_lock();
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (!slave) {
+		rcu_read_unlock();
+		return;
+	}
+
+	spin_lock_bh(&bond->ipsec_lock);
+	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+		if (!ipsec->xs->xso.real_dev)
+			continue;
+
+		if (!slave->dev->xfrmdev_ops ||
+		    !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
+		    netif_is_bond_master(slave->dev)) {
+			slave_warn(bond_dev, slave->dev,
+				   "%s: no slave xdo_dev_state_delete\n",
+				   __func__);
+		} else {
+			slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+		}
+		ipsec->xs->xso.real_dev = NULL;
+	}
+	spin_unlock_bh(&bond->ipsec_lock);
+	rcu_read_unlock();
 }
 
 /**
@@ -459,21 +570,37 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
 static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
 {
 	struct net_device *bond_dev = xs->xso.dev;
-	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *curr_active = rcu_dereference(bond->curr_active_slave);
-	struct net_device *slave_dev = curr_active->dev;
+	struct net_device *real_dev;
+	struct slave *curr_active;
+	struct bonding *bond;
+	int err;
 
-	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
-		return true;
+	bond = netdev_priv(bond_dev);
+	rcu_read_lock();
+	curr_active = rcu_dereference(bond->curr_active_slave);
+	real_dev = curr_active->dev;
 
-	if (!(slave_dev->xfrmdev_ops
-	      && slave_dev->xfrmdev_ops->xdo_dev_offload_ok)) {
-		slave_warn(bond_dev, slave_dev, "%s: no slave xdo_dev_offload_ok\n", __func__);
-		return false;
+	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
+		err = false;
+		goto out;
 	}
 
-	xs->xso.real_dev = slave_dev;
-	return slave_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+	if (!xs->xso.real_dev) {
+		err = false;
+		goto out;
+	}
+
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
+	    netif_is_bond_master(real_dev)) {
+		err = false;
+		goto out;
+	}
+
+	err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+out:
+	rcu_read_unlock();
+	return err;
 }
 
 static const struct xfrmdev_ops bond_xfrmdev_ops = {
@@ -990,8 +1117,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 		return;
 
 #ifdef CONFIG_XFRM_OFFLOAD
-	if (old_active && bond->xs)
-		bond_ipsec_del_sa(bond->xs);
+	bond_ipsec_del_sa_all(bond);
 #endif /* CONFIG_XFRM_OFFLOAD */
 
 	if (new_active) {
@@ -1066,10 +1192,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 	}
 
 #ifdef CONFIG_XFRM_OFFLOAD
-	if (new_active && bond->xs) {
-		xfrm_dev_state_flush(dev_net(bond->dev), bond->dev, true);
-		bond_ipsec_add_sa(bond->xs);
-	}
+	bond_ipsec_add_sa_all(bond);
 #endif /* CONFIG_XFRM_OFFLOAD */
 
 	/* resend IGMP joins since active slave has changed or
@@ -3327,6 +3450,7 @@ static int bond_master_netdev_event(unsigned long event,
 		return bond_event_changename(event_bond);
 	case NETDEV_UNREGISTER:
 		bond_remove_proc_entry(event_bond);
+		xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true);
 		break;
 	case NETDEV_REGISTER:
 		bond_create_proc_entry(event_bond);
@@ -4894,7 +5018,8 @@ void bond_setup(struct net_device *bond_dev)
 #ifdef CONFIG_XFRM_OFFLOAD
 	/* set up xfrm device ops (only supported in active-backup right now) */
 	bond_dev->xfrmdev_ops = &bond_xfrmdev_ops;
-	bond->xs = NULL;
+	INIT_LIST_HEAD(&bond->ipsec_list);
+	spin_lock_init(&bond->ipsec_lock);
 #endif /* CONFIG_XFRM_OFFLOAD */
 
 	/* don't acquire bond device's netif_tx_lock when transmitting */