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

Pull networking fixes from David Miller:

 1) Various TCP control block fixes, including one that crashes with
    SELinux, from David Ahern and Eric Dumazet.

 2) Fix ACK generation in rxrpc, from David Howells.

 3) ipvlan doesn't set the mark properly in the ipv4 route lookup key,
    from Gao Feng.

 4) SIT configuration doesn't take on the frag_off ipv4 field
    configuration properly, fix from Hangbin Liu.

 5) TSO can fail after device down/up on stmmac, fix from Lars Persson.

 6) Various bpftool fixes (mostly in JSON handling) from Quentin Monnet.

 7) Various SKB leak fixes in vhost/tun/tap (mostly observed as
    performance problems). From Wei Xu.

 8) mvpps's TX descriptors were not zero initialized, from Yan Markman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (57 commits)
  tcp: use IPCB instead of TCP_SKB_CB in inet_exact_dif_match()
  tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb()
  rxrpc: Fix the MAINTAINERS record
  rxrpc: Use correct netns source in rxrpc_release_sock()
  liquidio: fix incorrect indentation of assignment statement
  stmmac: reset last TSO segment size after device open
  ipvlan: Add the skb->mark as flow4's member to lookup route
  s390/qeth: build max size GSO skbs on L2 devices
  s390/qeth: fix GSO throughput regression
  s390/qeth: fix thinko in IPv4 multicast address tracking
  tap: free skb if flags error
  tun: free skb in early errors
  vhost: fix skb leak in handle_rx()
  bnxt_en: Fix a variable scoping in bnxt_hwrm_do_send_msg()
  bnxt_en: fix dst/src fid for vxlan encap/decap actions
  bnxt_en: wildcard smac while creating tunnel decap filter
  bnxt_en: Need to unconditionally shut down RoCE in bnxt_shutdown
  phylink: ensure we take the link down when phylink_stop() is called
  sfp: warn about modules requiring address change sequence
  sfp: improve RX_LOS handling
  ...

24 files changed, 177 insertions, 83 deletions

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index a13a4896a8bd..0626dcfd1f3d 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -184,12 +184,12 @@
  * Below is some version info we got:
  *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT IRQ Err Memory err RTR re-
  *                                Filter? connected?  Passive detection  ception in MB
- *   MX25  FlexCAN2  03.00.00.00     no        no         ?       no        no
+ *   MX25  FlexCAN2  03.00.00.00     no        no        no       no        no
  *   MX28  FlexCAN2  03.00.04.00    yes       yes        no       no        no
- *   MX35  FlexCAN2  03.00.00.00     no        no         ?       no        no
+ *   MX35  FlexCAN2  03.00.00.00     no        no        no       no        no
  *   MX53  FlexCAN2  03.00.00.00    yes        no        no       no        no
  *   MX6s  FlexCAN3  10.00.12.00    yes       yes        no       no       yes
- *   VF610 FlexCAN3  ?               no       yes         ?      yes       yes?
+ *   VF610 FlexCAN3  ?               no       yes        no      yes       yes?
  *
  * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected.
  */
@@ -297,7 +297,8 @@ static const struct flexcan_devtype_data fsl_imx6q_devtype_data = {
 
 static const struct flexcan_devtype_data fsl_vf610_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
-		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
+		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP |
+		FLEXCAN_QUIRK_BROKEN_PERR_STATE,
 };
 
 static const struct can_bittiming_const flexcan_bittiming_const = {
diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index b4efd711f824..788c3464a3b0 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -825,7 +825,10 @@ err_release_regions:
 err_disable_pci:
 	pci_disable_device(pdev);
 
-	return err;
+	/* pci_xxx_config_word() return positive PCIBIOS_xxx error codes while
+	 * the probe() function must return a negative errno in case of failure
+	 * (err is unchanged if negative) */
+	return pcibios_err_to_errno(err);
 }
 
 /* free the board structure object, as well as its resources: */
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 131026fbc2d7..5adc95c922ee 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -717,7 +717,10 @@ failure_release_regions:
 failure_disable_pci:
 	pci_disable_device(pdev);
 
-	return err;
+	/* pci_xxx_config_word() return positive PCIBIOS_xxx error codes while
+	 * the probe() function must return a negative errno in case of failure
+	 * (err is unchanged if negative) */
+	return pcibios_err_to_errno(err);
 }
 
 static void peak_pci_remove(struct pci_dev *pdev)
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 4d4941469cfc..db6ea936dc3f 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -637,6 +637,9 @@ static int ti_hecc_rx_poll(struct napi_struct *napi, int quota)
 		mbx_mask = hecc_read(priv, HECC_CANMIM);
 		mbx_mask |= HECC_TX_MBOX_MASK;
 		hecc_write(priv, HECC_CANMIM, mbx_mask);
+	} else {
+		/* repoll is done only if whole budget is used */
+		num_pkts = quota;
 	}
 
 	return num_pkts;
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 9b18d96ef526..f95945915d20 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -609,8 +609,8 @@ static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id,
 			}
 
 			if (pos + tmp->len > actual_len) {
-				dev_err(dev->udev->dev.parent,
-					"Format error\n");
+				dev_err_ratelimited(dev->udev->dev.parent,
+						    "Format error\n");
 				break;
 			}
 
@@ -813,6 +813,7 @@ static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv,
 	if (err) {
 		netdev_err(netdev, "Error transmitting URB\n");
 		usb_unanchor_urb(urb);
+		kfree(buf);
 		usb_free_urb(urb);
 		return err;
 	}
@@ -1333,7 +1334,7 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb)
 		goto resubmit_urb;
 	}
 
-	while (pos <= urb->actual_length - MSG_HEADER_LEN) {
+	while (pos <= (int)(urb->actual_length - MSG_HEADER_LEN)) {
 		msg = urb->transfer_buffer + pos;
 
 		/* The Kvaser firmware can only read and write messages that
@@ -1352,7 +1353,8 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb)
 		}
 
 		if (pos + msg->len > urb->actual_length) {
-			dev_err(dev->udev->dev.parent, "Format error\n");
+			dev_err_ratelimited(dev->udev->dev.parent,
+					    "Format error\n");
 			break;
 		}
 
@@ -1768,6 +1770,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
 		spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
 
 		usb_unanchor_urb(urb);
+		kfree(buf);
 
 		stats->tx_dropped++;
 
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index 7f0272558bef..ef417dcddbf7 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -592,6 +592,7 @@ static void mcba_usb_read_bulk_callback(struct urb *urb)
 		break;
 
 	case -ENOENT:
+	case -EPIPE:
 	case -ESHUTDOWN:
 		return;
 
@@ -862,7 +863,7 @@ static int mcba_usb_probe(struct usb_interface *intf,
 		goto cleanup_unregister_candev;
 	}
 
-	dev_info(&intf->dev, "Microchip CAN BUS analizer connected\n");
+	dev_info(&intf->dev, "Microchip CAN BUS Analyzer connected\n");
 
 	return 0;
 
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index b721a2009b50..23b45da784cb 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -625,7 +625,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
 	bcm_sf2_cfp_slice_ipv6(priv, v6_spec->ip6src, v6_spec->psrc,
 				slice_num, false);
 	bcm_sf2_cfp_slice_ipv6(priv, v6_m_spec->ip6src, v6_m_spec->psrc,
-				slice_num, true);
+				SLICE_NUM_MASK, true);
 
 	/* Insert into TCAM now because we need to insert a second rule */
 	bcm_sf2_cfp_rule_addr_set(priv, rule_index[0]);
@@ -699,7 +699,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
 	/* Insert into Action and policer RAMs now, set chain ID to
 	 * the one we are chained to
 	 */
-	ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port_num,
+	ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[1], port_num,
 				      queue_num, true);
 	if (ret)
 		goto out_err;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c5c38d4b7d1c..28f5e94274ee 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3368,6 +3368,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	u16 cp_ring_id, len = 0;
 	struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN;
+	struct hwrm_short_input short_input = {0};
 
 	req->seq_id = cpu_to_le16(bp->hwrm_cmd_seq++);
 	memset(resp, 0, PAGE_SIZE);
@@ -3376,7 +3377,6 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 
 	if (bp->flags & BNXT_FLAG_SHORT_CMD) {
 		void *short_cmd_req = bp->hwrm_short_cmd_req_addr;
-		struct hwrm_short_input short_input = {0};
 
 		memcpy(short_cmd_req, req, msg_len);
 		memset(short_cmd_req + msg_len, 0, BNXT_HWRM_MAX_REQ_LEN -
@@ -8263,8 +8263,9 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 	if (netif_running(dev))
 		dev_close(dev);
 
+	bnxt_ulp_shutdown(bp);
+
 	if (system_state == SYSTEM_POWER_OFF) {
-		bnxt_ulp_shutdown(bp);
 		bnxt_clear_int_mode(bp);
 		pci_wake_from_d3(pdev, bp->wol);
 		pci_set_power_state(pdev, PCI_D3hot);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index d5031f436f83..3d201d7324bd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -56,7 +56,6 @@ static int bnxt_tc_parse_redir(struct bnxt *bp,
 {
 	int ifindex = tcf_mirred_ifindex(tc_act);
 	struct net_device *dev;
-	u16 dst_fid;
 
 	dev = __dev_get_by_index(dev_net(bp->dev), ifindex);
 	if (!dev) {
@@ -64,15 +63,7 @@ static int bnxt_tc_parse_redir(struct bnxt *bp,
 		return -EINVAL;
 	}
 
-	/* find the FID from dev */
-	dst_fid = bnxt_flow_get_dst_fid(bp, dev);
-	if (dst_fid == BNXT_FID_INVALID) {
-		netdev_info(bp->dev, "can't get fid for ifindex=%d", ifindex);
-		return -EINVAL;
-	}
-
 	actions->flags |= BNXT_TC_ACTION_FLAG_FWD;
-	actions->dst_fid = dst_fid;
 	actions->dst_dev = dev;
 	return 0;
 }
@@ -160,13 +151,17 @@ static int bnxt_tc_parse_actions(struct bnxt *bp,
 	if (rc)
 		return rc;
 
-	/* Tunnel encap/decap action must be accompanied by a redirect action */
-	if ((actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP ||
-	     actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP) &&
-	    !(actions->flags & BNXT_TC_ACTION_FLAG_FWD)) {
-		netdev_info(bp->dev,
-			    "error: no redir action along with encap/decap");
-		return -EINVAL;
+	if (actions->flags & BNXT_TC_ACTION_FLAG_FWD) {
+		if (actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP) {
+			/* dst_fid is PF's fid */
+			actions->dst_fid = bp->pf.fw_fid;
+		} else {
+			/* find the FID from dst_dev */
+			actions->dst_fid =
+				bnxt_flow_get_dst_fid(bp, actions->dst_dev);
+			if (actions->dst_fid == BNXT_FID_INVALID)
+				return -EINVAL;
+		}
 	}
 
 	return rc;
@@ -532,10 +527,8 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
 	}
 
 	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS) {
-		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR |
-			   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR;
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR;
 		ether_addr_copy(req.dst_macaddr, l2_info->dmac);
-		ether_addr_copy(req.src_macaddr, l2_info->smac);
 	}
 	if (l2_info->num_vlans) {
 		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID;
@@ -901,10 +894,10 @@ static void bnxt_tc_put_decap_handle(struct bnxt *bp,
 
 static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp,
 				       struct ip_tunnel_key *tun_key,
-				       struct bnxt_tc_l2_key *l2_info,
-				       struct net_device *real_dst_dev)
+				       struct bnxt_tc_l2_key *l2_info)
 {
 #ifdef CONFIG_INET
+	struct net_device *real_dst_dev = bp->dev;
 	struct flowi4 flow = { {0} };
 	struct net_device *dst_dev;
 	struct neighbour *nbr;
@@ -1008,14 +1001,13 @@ static int bnxt_tc_get_decap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
 	 */
 	tun_key.u.ipv4.dst = flow->tun_key.u.ipv4.src;
 	tun_key.tp_dst = flow->tun_key.tp_dst;
-	rc = bnxt_tc_resolve_tunnel_hdrs(bp, &tun_key, &l2_info, bp->dev);
+	rc = bnxt_tc_resolve_tunnel_hdrs(bp, &tun_key, &l2_info);
 	if (rc)
 		goto put_decap;
 
-	decap_key->ttl = tun_key.ttl;
 	decap_l2_info = &decap_node->l2_info;
+	/* decap smac is wildcarded */
 	ether_addr_copy(decap_l2_info->dmac, l2_info.smac);
-	ether_addr_copy(decap_l2_info->smac, l2_info.dmac);
 	if (l2_info.num_vlans) {
 		decap_l2_info->num_vlans = l2_info.num_vlans;
 		decap_l2_info->inner_vlan_tpid = l2_info.inner_vlan_tpid;
@@ -1095,8 +1087,7 @@ static int bnxt_tc_get_encap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
 	if (encap_node->tunnel_handle != INVALID_TUNNEL_HANDLE)
 		goto done;
 
-	rc = bnxt_tc_resolve_tunnel_hdrs(bp, encap_key, &encap_node->l2_info,
-					 flow->actions.dst_dev);
+	rc = bnxt_tc_resolve_tunnel_hdrs(bp, encap_key, &encap_node->l2_info);
 	if (rc)
 		goto put_encap;
 
@@ -1169,6 +1160,15 @@ static int __bnxt_tc_del_flow(struct bnxt *bp,
 	return 0;
 }
 
+static void bnxt_tc_set_src_fid(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				u16 src_fid)
+{
+	if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP)
+		flow->src_fid = bp->pf.fw_fid;
+	else
+		flow->src_fid = src_fid;
+}
+
 /* Add a new flow or replace an existing flow.
  * Notes on locking:
  * There are essentially two critical sections here.
@@ -1204,7 +1204,8 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 	rc = bnxt_tc_parse_flow(bp, tc_flow_cmd, flow);
 	if (rc)
 		goto free_node;
-	flow->src_fid = src_fid;
+
+	bnxt_tc_set_src_fid(bp, flow, src_fid);
 
 	if (!bnxt_tc_can_offload(bp, flow)) {
 		rc = -ENOSPC;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 6aa0eee88ea5..a5eecd895a82 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -1113,7 +1113,7 @@ static int liquidio_watchdog(void *param)
 				dev_err(&oct->pci_dev->dev,
 					"ERROR: Octeon core %d crashed or got stuck!  See oct-fwdump for details.\n",
 					core);
-					err_msg_was_printed[core] = true;
+				err_msg_was_printed[core] = true;
 			}
 		}
 
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index d83a78be98a2..fed2b2f909fc 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -5598,7 +5598,7 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev,
 	u32 txq_dma;
 
 	/* Allocate memory for TX descriptors */
-	aggr_txq->descs = dma_alloc_coherent(&pdev->dev,
+	aggr_txq->descs = dma_zalloc_coherent(&pdev->dev,
 				MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE,
 				&aggr_txq->descs_dma, GFP_KERNEL);
 	if (!aggr_txq->descs)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index e5ff734d4f9b..9eb7f65d8000 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -808,8 +808,7 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 			 val, reg);
 
 	if (gmac->variant->soc_has_internal_phy) {
-		if (of_property_read_bool(priv->plat->phy_node,
-					  "allwinner,leds-active-low"))
+		if (of_property_read_bool(node, "allwinner,leds-active-low"))
 			reg |= H3_EPHY_LED_POL;
 		else
 			reg &= ~H3_EPHY_LED_POL;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index f63c2ddced3c..d7250539d0bd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2588,6 +2588,7 @@ static int stmmac_open(struct net_device *dev)
 
 	priv->dma_buf_sz = STMMAC_ALIGN(buf_sz);
 	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
+	priv->mss = 0;
 
 	ret = alloc_dma_desc_resources(priv);
 	if (ret < 0) {
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 11c1e7950fe5..77cc4fbaeace 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -393,6 +393,7 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb)
 		.flowi4_oif = dev->ifindex,
 		.flowi4_tos = RT_TOS(ip4h->tos),
 		.flowi4_flags = FLOWI_FLAG_ANYSRC,
+		.flowi4_mark = skb->mark,
 		.daddr = ip4h->daddr,
 		.saddr = ip4h->saddr,
 	};
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index fdb43dd9b5cd..ab4614113403 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -496,16 +496,18 @@ static int ksz9031_of_load_skew_values(struct phy_device *phydev,
 	return ksz9031_extended_write(phydev, OP_DATA, 2, reg, newval);
 }
 
+/* Center KSZ9031RNX FLP timing at 16ms. */
 static int ksz9031_center_flp_timing(struct phy_device *phydev)
 {
 	int result;
 
-	/* Center KSZ9031RNX FLP timing at 16ms. */
 	result = ksz9031_extended_write(phydev, OP_DATA, 0,
 					MII_KSZ9031RN_FLP_BURST_TX_HI, 0x0006);
+	if (result)
+		return result;
+
 	result = ksz9031_extended_write(phydev, OP_DATA, 0,
 					MII_KSZ9031RN_FLP_BURST_TX_LO, 0x1A80);
-
 	if (result)
 		return result;
 
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index e3bbc70372d3..5dc9668dde34 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -773,6 +773,7 @@ void phylink_stop(struct phylink *pl)
 		sfp_upstream_stop(pl->sfp_bus);
 
 	set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
+	queue_work(system_power_efficient_wq, &pl->resolve);
 	flush_work(&pl->resolve);
 }
 EXPORT_SYMBOL_GPL(phylink_stop);
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index e381811e5f11..9dfc1c4c954f 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -351,12 +351,13 @@ static void sfp_sm_link_check_los(struct sfp *sfp)
 {
 	unsigned int los = sfp->state & SFP_F_LOS;
 
-	/* FIXME: what if neither SFP_OPTIONS_LOS_INVERTED nor
-	 * SFP_OPTIONS_LOS_NORMAL are set?  For now, we assume
-	 * the same as SFP_OPTIONS_LOS_NORMAL set.
+	/* If neither SFP_OPTIONS_LOS_INVERTED nor SFP_OPTIONS_LOS_NORMAL
+	 * are set, we assume that no LOS signal is available.
 	 */
-	if (sfp->id.ext.options & SFP_OPTIONS_LOS_INVERTED)
+	if (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_INVERTED))
 		los ^= SFP_F_LOS;
+	else if (!(sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_NORMAL)))
+		los = 0;
 
 	if (los)
 		sfp_sm_next(sfp, SFP_S_WAIT_LOS, 0);
@@ -364,6 +365,22 @@ static void sfp_sm_link_check_los(struct sfp *sfp)
 		sfp_sm_link_up(sfp);
 }
 
+static bool sfp_los_event_active(struct sfp *sfp, unsigned int event)
+{
+	return (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_INVERTED) &&
+		event == SFP_E_LOS_LOW) ||
+	       (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_NORMAL) &&
+		event == SFP_E_LOS_HIGH);
+}
+
+static bool sfp_los_event_inactive(struct sfp *sfp, unsigned int event)
+{
+	return (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_INVERTED) &&
+		event == SFP_E_LOS_HIGH) ||
+	       (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_NORMAL) &&
+		event == SFP_E_LOS_LOW);
+}
+
 static void sfp_sm_fault(struct sfp *sfp, bool warn)
 {
 	if (sfp->sm_retries && !--sfp->sm_retries) {
@@ -470,6 +487,11 @@ static int sfp_sm_mod_probe(struct sfp *sfp)
 		return -EINVAL;
 	}
 
+	/* If the module requires address swap mode, warn about it */
+	if (sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE)
+		dev_warn(sfp->dev,
+			 "module address swap to access page 0xA2 is not supported.\n");
+
 	return sfp_module_insert(sfp->sfp_bus, &sfp->id);
 }
 
@@ -581,9 +603,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 	case SFP_S_WAIT_LOS:
 		if (event == SFP_E_TX_FAULT)
 			sfp_sm_fault(sfp, true);
-		else if (event ==
-			 (sfp->id.ext.options & SFP_OPTIONS_LOS_INVERTED ?
-			  SFP_E_LOS_HIGH : SFP_E_LOS_LOW))
+		else if (sfp_los_event_inactive(sfp, event))
 			sfp_sm_link_up(sfp);
 		break;
 
@@ -591,9 +611,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 		if (event == SFP_E_TX_FAULT) {
 			sfp_sm_link_down(sfp);
 			sfp_sm_fault(sfp, true);
-		} else if (event ==
-			   (sfp->id.ext.options & SFP_OPTIONS_LOS_INVERTED ?
-			    SFP_E_LOS_LOW : SFP_E_LOS_HIGH)) {
+		} else if (sfp_los_event_active(sfp, event)) {
 			sfp_sm_link_down(sfp);
 			sfp_sm_next(sfp, SFP_S_WAIT_LOS, 0);
 		}
@@ -639,7 +657,8 @@ static int sfp_module_info(struct sfp *sfp, struct ethtool_modinfo *modinfo)
 {
 	/* locking... and check module is present */
 
-	if (sfp->id.ext.sff8472_compliance) {
+	if (sfp->id.ext.sff8472_compliance &&
+	    !(sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE)) {
 		modinfo->type = ETH_MODULE_SFF_8472;
 		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
 	} else {
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index e9489b88407c..0a886fda0129 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -829,8 +829,11 @@ static ssize_t tap_do_read(struct tap_queue *q,
 	DEFINE_WAIT(wait);
 	ssize_t ret = 0;
 
-	if (!iov_iter_count(to))
+	if (!iov_iter_count(to)) {
+		if (skb)
+			kfree_skb(skb);
 		return 0;
+	}
 
 	if (skb)
 		goto put;
@@ -1154,11 +1157,14 @@ static int tap_recvmsg(struct socket *sock, struct msghdr *m,
 		       size_t total_len, int flags)
 {
 	struct tap_queue *q = container_of(sock, struct tap_queue, sock);
+	struct sk_buff *skb = m->msg_control;
 	int ret;
-	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
+	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) {
+		if (skb)
+			kfree_skb(skb);
 		return -EINVAL;
-	ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT,
-			  m->msg_control);
+	}
+	ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT, skb);
 	if (ret > total_len) {
 		m->msg_flags |= MSG_TRUNC;
 		ret = flags & MSG_TRUNC ? ret : total_len;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 95749006d687..4f4a842a1c9c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1952,8 +1952,11 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 
 	tun_debug(KERN_INFO, tun, "tun_do_read\n");
 
-	if (!iov_iter_count(to))
+	if (!iov_iter_count(to)) {
+		if (skb)
+			kfree_skb(skb);
 		return 0;
+	}
 
 	if (!skb) {
 		/* Read frames from ring */
@@ -2069,22 +2072,24 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
 {
 	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
 	struct tun_struct *tun = tun_get(tfile);
+	struct sk_buff *skb = m->msg_control;
 	int ret;
 
-	if (!tun)
-		return -EBADFD;
+	if (!tun) {
+		ret = -EBADFD;
+		goto out_free_skb;
+	}
 
 	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) {
 		ret = -EINVAL;
-		goto out;
+		goto out_put_tun;
 	}
 	if (flags & MSG_ERRQUEUE) {
 		ret = sock_recv_errqueue(sock->sk, m, total_len,
 					 SOL_PACKET, TUN_TX_TIMESTAMP);
 		goto out;
 	}
-	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT,
-			  m->msg_control);
+	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, skb);
 	if (ret > (ssize_t)total_len) {
 		m->msg_flags |= MSG_TRUNC;
 		ret = flags & MSG_TRUNC ? ret : total_len;
@@ -2092,6 +2097,13 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
 out:
 	tun_put(tun);
 	return ret;
+
+out_put_tun:
+	tun_put(tun);
+out_free_skb:
+	if (skb)
+		kfree_skb(skb);
+	return ret;
 }
 
 static int tun_peek_len(struct socket *sock)
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 9cd569ef43ec..15015a24f8ad 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -987,6 +987,9 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *,
 int qeth_set_features(struct net_device *, netdev_features_t);
 void qeth_recover_features(struct net_device *dev);
 netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
+netdev_features_t qeth_features_check(struct sk_buff *skb,
+				      struct net_device *dev,
+				      netdev_features_t features);
 int qeth_vm_request_mac(struct qeth_card *card);
 int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len);
 
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 98a7f84540ab..430e3214f7e2 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -20,6 +20,11 @@
 #include <linux/mii.h>
 #include <linux/kthread.h>
 #include <linux/slab.h>
+#include <linux/if_vlan.h>
+#include <linux/netdevice.h>
+#include <linux/netdev_features.h>
+#include <linux/skbuff.h>
+
 #include <net/iucv/af_iucv.h>
 #include <net/dsfield.h>
 
@@ -6439,6 +6444,32 @@ netdev_features_t qeth_fix_features(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(qeth_fix_features);
 
+netdev_features_t qeth_features_check(struct sk_buff *skb,
+				      struct net_device *dev,
+				      netdev_features_t features)
+{
+	/* GSO segmentation builds skbs with
+	 *	a (small) linear part for the headers, and
+	 *	page frags for the data.
+	 * Compared to a linear skb, the header-only part consumes an
+	 * additional buffer element. This reduces buffer utilization, and
+	 * hurts throughput. So compress small segments into one element.
+	 */
+	if (netif_needs_gso(skb, features)) {
+		/* match skb_segment(): */
+		unsigned int doffset = skb->data - skb_mac_header(skb);
+		unsigned int hsize = skb_shinfo(skb)->gso_size;
+		unsigned int hroom = skb_headroom(skb);
+
+		/* linearize only if resulting skb allocations are order-0: */
+		if (SKB_DATA_ALIGN(hroom + doffset + hsize) <= SKB_MAX_HEAD(0))
+			features &= ~NETIF_F_SG;
+	}
+
+	return vlan_features_check(skb, features);
+}
+EXPORT_SYMBOL_GPL(qeth_features_check);
+
 static int __init qeth_core_init(void)
 {
 	int rc;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 93d7e345d180..5863ea170ff2 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -961,6 +961,7 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 	.ndo_stop		= qeth_l2_stop,
 	.ndo_get_stats		= qeth_get_stats,
 	.ndo_start_xmit		= qeth_l2_hard_start_xmit,
+	.ndo_features_check	= qeth_features_check,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l2_set_rx_mode,
 	.ndo_do_ioctl		= qeth_do_ioctl,
@@ -1011,6 +1012,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->hw_features = NETIF_F_SG;
 		card->dev->vlan_features = NETIF_F_SG;
+		card->dev->features |= NETIF_F_SG;
 		/* OSA 3S and earlier has no RX/TX support */
 		if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) {
 			card->dev->hw_features |= NETIF_F_IP_CSUM;
@@ -1029,8 +1031,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 
 	card->info.broadcast_capable = 1;
 	qeth_l2_request_initial_mac(card);
-	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
-				  PAGE_SIZE;
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
 	netif_carrier_off(card->dev);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 0f8c12738b06..6a73894b0cb5 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1377,6 +1377,7 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
 
 		tmp->u.a4.addr = be32_to_cpu(im4->multiaddr);
 		memcpy(tmp->mac, buf, sizeof(tmp->mac));
+		tmp->is_multicast = 1;
 
 		ipm = qeth_l3_ip_from_hash(card, tmp);
 		if (ipm) {
@@ -2918,6 +2919,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = {
 	.ndo_stop		= qeth_l3_stop,
 	.ndo_get_stats		= qeth_get_stats,
 	.ndo_start_xmit		= qeth_l3_hard_start_xmit,
+	.ndo_features_check	= qeth_features_check,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
 	.ndo_do_ioctl		= qeth_do_ioctl,
@@ -2958,6 +2960,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				card->dev->vlan_features = NETIF_F_SG |
 					NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
 					NETIF_F_TSO;
+				card->dev->features |= NETIF_F_SG;
 			}
 		}
 	} else if (card->info.type == QETH_CARD_TYPE_IQD) {
@@ -2985,8 +2988,8 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 	netif_keep_dst(card->dev);
-	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
-				  PAGE_SIZE;
+	netif_set_gso_max_size(card->dev, (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
+					  PAGE_SIZE);
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 8d626d7c2e7e..c7bdeb655646 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -778,16 +778,6 @@ static void handle_rx(struct vhost_net *net)
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			goto out;
-		if (nvq->rx_array)
-			msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
-		/* On overrun, truncate and discard */
-		if (unlikely(headcount > UIO_MAXIOV)) {
-			iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
-			err = sock->ops->recvmsg(sock, &msg,
-						 1, MSG_DONTWAIT | MSG_TRUNC);
-			pr_debug("Discarded rx packet: len %zd\n", sock_len);
-			continue;
-		}
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
@@ -800,6 +790,16 @@ static void handle_rx(struct vhost_net *net)
 			 * they refilled. */
 			goto out;
 		}
+		if (nvq->rx_array)
+			msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
+		/* On overrun, truncate and discard */
+		if (unlikely(headcount > UIO_MAXIOV)) {
+			iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
+			err = sock->ops->recvmsg(sock, &msg,
+						 1, MSG_DONTWAIT | MSG_TRUNC);
+			pr_debug("Discarded rx packet: len %zd\n", sock_len);
+			continue;
+		}
 		/* We don't need to be notified again. */
 		iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len);
 		fixup = msg.msg_iter;