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

Pull networking fixes from David Miller:

1) Avoid negative netdev refcount in error flow of xfrm state add, from
Aviad Yehezkel.

2) Fix tcpdump decoding of IPSEC decap'd frames by filling in the
ethernet header protocol field in xfrm{4,6}_mode_tunnel_input().
From Yossi Kuperman.

3) Fix a syzbot triggered skb_under_panic in pppoe having to do with
failing to allocate an appropriate amount of headroom. From
Guillaume Nault.

4) Fix memory leak in vmxnet3 driver, from Neil Horman.

5) Cure out-of-bounds packet memory access in em_nbyte EMATCH module,
from Wolfgang Bumiller.

6) Restrict what kinds of sockets can be bound to the KCM multiplexer
and also disallow when another layer has attached to the socket and
made use of sk_user_data. From Tom Herbert.

7) Fix use before init of IOTLB in vhost code, from Jason Wang.

8) Correct STACR register write bit definition in IBM emac driver, from
Ivan Mikhaylov.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
net/ibm/emac: wrong bit is used for STA control register write
net/ibm/emac: add 8192 rx/tx fifo size
vhost: do not try to access device IOTLB when not initialized
vhost: use mutex_lock_nested() in vhost_dev_lock_vqs()
i40e: flower: check if TC offload is enabled on a netdev
qed: Free reserved MR tid
qed: Remove reserveration of dpi for kernel
kcm: Check if sk_user_data already set in kcm_attach
kcm: Only allow TCP sockets to be attached to a KCM mux
net: sched: fix TCF_LAYER_LINK case in tcf_get_base_ptr
net: sched: em_nbyte: don't add the data offset twice
mlxsw: spectrum_router: Don't log an error on missing neighbor
vmxnet3: repair memory leak
ipv6: Fix getsockopt() for sockets with default IPV6_AUTOFLOWLABEL
pppoe: take ->needed_headroom of lower device into account on xmit
xfrm: fix boolean assignment in xfrm_get_type_offload
xfrm: Fix eth_hdr(skb)->h_proto to reflect inner IP version
xfrm: fix error flow in case of add state fails
xfrm: Add SA to hardware at the end of xfrm_state_construct()

drivers/net/ethernet/ibm/emac/core.c

···
 	case 16384:
 		ret |= EMAC_MR1_RFS_16K;
 		break;
+	case 8192:
+		ret |= EMAC4_MR1_RFS_8K;
+		break;
 	case 4096:
 		ret |= EMAC_MR1_RFS_4K;
 		break;
···
 	switch(tx_size) {
 	case 16384:
 		ret |= EMAC4_MR1_TFS_16K;
+		break;
+	case 8192:
+		ret |= EMAC4_MR1_TFS_8K;
 		break;
 	case 4096:
 		ret |= EMAC4_MR1_TFS_4K;

drivers/net/ethernet/ibm/emac/emac.h

···
 
 #define EMAC4_MR1_RFS_2K		0x00100000
 #define EMAC4_MR1_RFS_4K		0x00180000
+#define EMAC4_MR1_RFS_8K		0x00200000
 #define EMAC4_MR1_RFS_16K		0x00280000
 #define EMAC4_MR1_TFS_2K       		0x00020000
 #define EMAC4_MR1_TFS_4K		0x00030000
+#define EMAC4_MR1_TFS_8K		0x00040000
 #define EMAC4_MR1_TFS_16K		0x00050000
 #define EMAC4_MR1_TR			0x00008000
 #define EMAC4_MR1_MWSW_001		0x00001000
···
 #define EMAC_STACR_PHYE			0x00004000
 #define EMAC_STACR_STAC_MASK		0x00003000
 #define EMAC_STACR_STAC_READ		0x00001000
-#define EMAC_STACR_STAC_WRITE		0x00002000
+#define EMAC_STACR_STAC_WRITE		0x00000800
 #define EMAC_STACR_OPBC_MASK		0x00000C00
 #define EMAC_STACR_OPBC_50		0x00000000
 #define EMAC_STACR_OPBC_66		0x00000400

drivers/net/ethernet/intel/i40e/i40e_main.c

···
 {
 	struct i40e_vsi *vsi = np->vsi;
 
+	if (!tc_can_offload(vsi->netdev))
+		return -EOPNOTSUPP;
 	if (cls_flower->common.chain_index)
 		return -EOPNOTSUPP;
 

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

···
 	dipn = htonl(dip);
 	dev = mlxsw_sp->router->rifs[rif]->dev;
 	n = neigh_lookup(&arp_tbl, &dipn, dev);
-	if (!n) {
-		netdev_err(dev, "Failed to find matching neighbour for IP=%pI4h\n",
-			   &dip);
+	if (!n)
 		return;
-	}
 
 	netdev_dbg(dev, "Updating neighbour with IP=%pI4h\n", &dip);
 	neigh_event_send(n, NULL);
···
 
 	dev = mlxsw_sp->router->rifs[rif]->dev;
 	n = neigh_lookup(&nd_tbl, &dip, dev);
-	if (!n) {
-		netdev_err(dev, "Failed to find matching neighbour for IP=%pI6c\n",
-			   &dip);
+	if (!n)
 		return;
-	}
 
 	netdev_dbg(dev, "Updating neighbour with IP=%pI6c\n", &dip);
 	neigh_event_send(n, NULL);

drivers/net/ethernet/qlogic/qed/qed_rdma.c

···
 	kfree(p_rdma_info);
 }
 
+static void qed_rdma_free_tid(void *rdma_cxt, u32 itid)
+{
+        struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
+
+        DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "itid = %08x\n", itid);
+
+        spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+        qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->tid_map, itid);
+        spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
+static void qed_rdma_free_reserved_lkey(struct qed_hwfn *p_hwfn)
+{
+	qed_rdma_free_tid(p_hwfn, p_hwfn->p_rdma_info->dev->reserved_lkey);
+}
+
 static void qed_rdma_free(struct qed_hwfn *p_hwfn)
 {
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Freeing RDMA\n");
 
+	qed_rdma_free_reserved_lkey(p_hwfn);
 	qed_rdma_resc_free(p_hwfn);
 }
 
···
 {
 	struct qed_rdma_device *dev = p_hwfn->p_rdma_info->dev;
 
-	/* The first DPI is reserved for the Kernel */
-	__set_bit(0, p_hwfn->p_rdma_info->dpi_map.bitmap);
-
 	/* Tid 0 will be used as the key for "reserved MR".
 	 * The driver should allocate memory for it so it can be loaded but no
 	 * ramrod should be passed on it.
···
 
 	/* Return struct with device parameters */
 	return p_hwfn->p_rdma_info->dev;
-}
-
-static void qed_rdma_free_tid(void *rdma_cxt, u32 itid)
-{
-	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "itid = %08x\n", itid);
-
-	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
-	qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->tid_map, itid);
-	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
 }
 
 static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)

drivers/net/ppp/pppoe.c

···
 	struct pppoe_hdr *ph;
 	struct net_device *dev;
 	char *start;
+	int hlen;
 
 	lock_sock(sk);
 	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) {
···
 	if (total_len > (dev->mtu + dev->hard_header_len))
 		goto end;
 
-
-	skb = sock_wmalloc(sk, total_len + dev->hard_header_len + 32,
-			   0, GFP_KERNEL);
+	hlen = LL_RESERVED_SPACE(dev);
+	skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len +
+			   dev->needed_tailroom, 0, GFP_KERNEL);
 	if (!skb) {
 		error = -ENOMEM;
 		goto end;
 	}
 
 	/* Reserve space for headers. */
-	skb_reserve(skb, dev->hard_header_len);
+	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
 	skb->dev = dev;
···
 	/* Copy the data if there is no space for the header or if it's
 	 * read-only.
 	 */
-	if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len))
+	if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph)))
 		goto abort;
 
 	__skb_push(skb, sizeof(*ph));

drivers/net/vmxnet3/vmxnet3_drv.c

···
 					  rq->rx_ring[i].basePA);
 			rq->rx_ring[i].base = NULL;
 		}
-		rq->buf_info[i] = NULL;
 	}
 
 	if (rq->data_ring.base) {
···
 			(rq->rx_ring[0].size + rq->rx_ring[1].size);
 		dma_free_coherent(&adapter->pdev->dev, sz, rq->buf_info[0],
 				  rq->buf_info_pa);
+		rq->buf_info[0] = rq->buf_info[1] = NULL;
 	}
 }
 

drivers/vhost/vhost.c

···
 {
 	int i = 0;
 	for (i = 0; i < d->nvqs; ++i)
-		mutex_lock(&d->vqs[i]->mutex);
+		mutex_lock_nested(&d->vqs[i]->mutex, i);
 }
 
 static void vhost_dev_unlock_vqs(struct vhost_dev *d)
···
 		vhost_iotlb_notify_vq(dev, msg);
 		break;
 	case VHOST_IOTLB_INVALIDATE:
+		if (!dev->iotlb) {
+			ret = -EFAULT;
+			break;
+		}
 		vhost_vq_meta_reset(dev);
 		vhost_del_umem_range(dev->iotlb, msg->iova,
 				     msg->iova + msg->size - 1);

include/net/ipv6.h

···
 			   int flags);
 int ip6_flowlabel_init(void);
 void ip6_flowlabel_cleanup(void);
+bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np);
 
 static inline void fl6_sock_release(struct ip6_flowlabel *fl)
 {

include/net/pkt_cls.h

···
 {
 	switch (layer) {
 		case TCF_LAYER_LINK:
-			return skb->data;
+			return skb_mac_header(skb);
 		case TCF_LAYER_NETWORK:
 			return skb_network_header(skb);
 		case TCF_LAYER_TRANSPORT:

net/ipv4/xfrm4_mode_tunnel.c

···
 
 	skb_reset_network_header(skb);
 	skb_mac_header_rebuild(skb);
+	eth_hdr(skb)->h_proto = skb->protocol;
 
 	err = 0;
 

net/ipv6/ip6_output.c

···
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
-static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
 {
 	if (!np->autoflowlabel_set)
 		return ip6_default_np_autolabel(net);

net/ipv6/ipv6_sockglue.c

···
 		break;
 
 	case IPV6_AUTOFLOWLABEL:
-		val = np->autoflowlabel;
+		val = ip6_autoflowlabel(sock_net(sk), np);
 		break;
 
 	case IPV6_RECVFRAGSIZE:

net/ipv6/xfrm6_mode_tunnel.c

···
 
 	skb_reset_network_header(skb);
 	skb_mac_header_rebuild(skb);
+	eth_hdr(skb)->h_proto = skb->protocol;
 
 	err = 0;
 

net/kcm/kcmsock.c

···
 	if (!csk)
 		return -EINVAL;
 
-	/* We must prevent loops or risk deadlock ! */
-	if (csk->sk_family == PF_KCM)
+	/* Only allow TCP sockets to be attached for now */
+	if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) ||
+	    csk->sk_protocol != IPPROTO_TCP)
+		return -EOPNOTSUPP;
+
+	/* Don't allow listeners or closed sockets */
+	if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE)
 		return -EOPNOTSUPP;
 
 	psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL);
···
 		return err;
 	}
 
-	sock_hold(csk);
-
 	write_lock_bh(&csk->sk_callback_lock);
+
+	/* Check if sk_user_data is aready by KCM or someone else.
+	 * Must be done under lock to prevent race conditions.
+	 */
+	if (csk->sk_user_data) {
+		write_unlock_bh(&csk->sk_callback_lock);
+		strp_done(&psock->strp);
+		kmem_cache_free(kcm_psockp, psock);
+		return -EALREADY;
+	}
+
 	psock->save_data_ready = csk->sk_data_ready;
 	psock->save_write_space = csk->sk_write_space;
 	psock->save_state_change = csk->sk_state_change;
···
 	csk->sk_data_ready = psock_data_ready;
 	csk->sk_write_space = psock_write_space;
 	csk->sk_state_change = psock_state_change;
+
 	write_unlock_bh(&csk->sk_callback_lock);
+
+	sock_hold(csk);
 
 	/* Finished initialization, now add the psock to the MUX. */
 	spin_lock_bh(&mux->lock);

net/sched/em_nbyte.c

···
 	if (!tcf_valid_offset(skb, ptr, nbyte->hdr.len))
 		return 0;
 
-	return !memcmp(ptr + nbyte->hdr.off, nbyte->pattern, nbyte->hdr.len);
+	return !memcmp(ptr, nbyte->pattern, nbyte->hdr.len);
 }
 
 static struct tcf_ematch_ops em_nbyte_ops = {

net/xfrm/xfrm_device.c

···
 
 	err = dev->xfrmdev_ops->xdo_dev_state_add(x);
 	if (err) {
+		xso->dev = NULL;
 		dev_put(dev);
 		return err;
 	}

net/xfrm/xfrm_state.c

···
 
 	if (!type && try_load) {
 		request_module("xfrm-offload-%d-%d", family, proto);
-		try_load = 0;
+		try_load = false;
 		goto retry;
 	}
 
···
 			goto error;
 	}
 
-	x->km.state = XFRM_STATE_VALID;
-
 error:
 	return err;
 }
···
 
 int xfrm_init_state(struct xfrm_state *x)
 {
-	return __xfrm_init_state(x, true, false);
+	int err;
+
+	err = __xfrm_init_state(x, true, false);
+	if (!err)
+		x->km.state = XFRM_STATE_VALID;
+
+	return err;
 }
 
 EXPORT_SYMBOL(xfrm_init_state);

net/xfrm/xfrm_user.c

···
 			goto error;
 	}
 
-	if (attrs[XFRMA_OFFLOAD_DEV]) {
-		err = xfrm_dev_state_add(net, x,
-					 nla_data(attrs[XFRMA_OFFLOAD_DEV]));
-		if (err)
-			goto error;
-	}
-
 	if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn,
 					       attrs[XFRMA_REPLAY_ESN_VAL])))
 		goto error;
···
 
 	/* override default values from above */
 	xfrm_update_ae_params(x, attrs, 0);
+
+	/* configure the hardware if offload is requested */
+	if (attrs[XFRMA_OFFLOAD_DEV]) {
+		err = xfrm_dev_state_add(net, x,
+					 nla_data(attrs[XFRMA_OFFLOAD_DEV]));
+		if (err)
+			goto error;
+	}
 
 	return x;
 
···
 		__xfrm_state_put(x);
 		goto out;
 	}
+
+	if (x->km.state == XFRM_STATE_VOID)
+		x->km.state = XFRM_STATE_VALID;
 
 	c.seq = nlh->nlmsg_seq;
 	c.portid = nlh->nlmsg_pid;