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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 247 insertions, 220 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2ecd55856c50..38b4e4899490 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1,30 +1,5 @@
-/*******************************************************************************
-
-  Intel 10 Gigabit PCI Express Linux driver
-  Copyright(c) 1999 - 2016 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, write to the Free Software Foundation, Inc.,
-  51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  Linux NICS <linux.nics@intel.com>
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
 
 #include <linux/types.h>
 #include <linux/module.h>
@@ -752,8 +727,8 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
 					ring_desc = "";
 				pr_info("T [0x%03X]    %016llX %016llX %016llX %08X %p %016llX %p%s",
 					i,
-					le64_to_cpu(u0->a),
-					le64_to_cpu(u0->b),
+					le64_to_cpu((__force __le64)u0->a),
+					le64_to_cpu((__force __le64)u0->b),
 					(u64)dma_unmap_addr(tx_buffer, dma),
 					dma_unmap_len(tx_buffer, len),
 					tx_buffer->next_to_watch,
@@ -864,15 +839,15 @@ rx_ring_summary:
 				/* Descriptor Done */
 				pr_info("RWB[0x%03X]     %016llX %016llX ---------------- %p%s\n",
 					i,
-					le64_to_cpu(u0->a),
-					le64_to_cpu(u0->b),
+					le64_to_cpu((__force __le64)u0->a),
+					le64_to_cpu((__force __le64)u0->b),
 					rx_buffer_info->skb,
 					ring_desc);
 			} else {
 				pr_info("R  [0x%03X]     %016llX %016llX %016llX %p%s\n",
 					i,
-					le64_to_cpu(u0->a),
-					le64_to_cpu(u0->b),
+					le64_to_cpu((__force __le64)u0->a),
+					le64_to_cpu((__force __le64)u0->b),
 					(u64)rx_buffer_info->dma,
 					rx_buffer_info->skb,
 					ring_desc);
@@ -1216,7 +1191,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 
 		/* free the skb */
 		if (ring_is_xdp(tx_ring))
-			page_frag_free(tx_buffer->data);
+			xdp_return_frame(tx_buffer->xdpf);
 		else
 			napi_consume_skb(tx_buffer->skb, napi_budget);
 
@@ -1768,15 +1743,14 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
 	if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP))
 		ixgbe_ipsec_rx(rx_ring, rx_desc, skb);
 
-	skb->protocol = eth_type_trans(skb, dev);
-
 	/* record Rx queue, or update MACVLAN statistics */
 	if (netif_is_ixgbe(dev))
 		skb_record_rx_queue(skb, rx_ring->queue_index);
 	else
 		macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true,
-				 (skb->pkt_type == PACKET_BROADCAST) ||
-				 (skb->pkt_type == PACKET_MULTICAST));
+				 false);
+
+	skb->protocol = eth_type_trans(skb, dev);
 }
 
 static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
@@ -2262,7 +2236,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 #define IXGBE_XDP_TX 2
 
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
-			       struct xdp_buff *xdp);
+			       struct xdp_frame *xdpf);
 
 static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 				     struct ixgbe_ring *rx_ring,
@@ -2270,6 +2244,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 {
 	int err, result = IXGBE_XDP_PASS;
 	struct bpf_prog *xdp_prog;
+	struct xdp_frame *xdpf;
 	u32 act;
 
 	rcu_read_lock();
@@ -2278,12 +2253,19 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 	if (!xdp_prog)
 		goto xdp_out;
 
+	prefetchw(xdp->data_hard_start); /* xdp_frame write */
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		result = ixgbe_xmit_xdp_ring(adapter, xdp);
+		xdpf = convert_to_xdp_frame(xdp);
+		if (unlikely(!xdpf)) {
+			result = IXGBE_XDP_CONSUMED;
+			break;
+		}
+		result = ixgbe_xmit_xdp_ring(adapter, xdpf);
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
@@ -4211,7 +4193,8 @@ static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter)
 static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
-	u32 reg_offset, vf_shift;
+	u16 pool = adapter->num_rx_pools;
+	u32 reg_offset, vf_shift, vmolr;
 	u32 gcr_ext, vmdctl;
 	int i;
 
@@ -4225,6 +4208,13 @@ static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter)
 	vmdctl |= IXGBE_VT_CTL_REPLEN;
 	IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl);
 
+	/* accept untagged packets until a vlan tag is
+	 * specifically set for the VMDQ queue/pool
+	 */
+	vmolr = IXGBE_VMOLR_AUPE;
+	while (pool--)
+		IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(pool)), vmolr);
+
 	vf_shift = VMDQ_P(0) % 32;
 	reg_offset = (VMDQ_P(0) >= 32) ? 1 : 0;
 
@@ -4892,36 +4882,6 @@ int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter,
 	return -ENOMEM;
 }
 
-/**
- * ixgbe_write_uc_addr_list - write unicast addresses to RAR table
- * @netdev: network interface device structure
- * @vfn: pool to associate with unicast addresses
- *
- * Writes unicast address list to the RAR table.
- * Returns: -ENOMEM on failure/insufficient address space
- *                0 on no addresses written
- *                X on writing X addresses to the RAR table
- **/
-static int ixgbe_write_uc_addr_list(struct net_device *netdev, int vfn)
-{
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	int count = 0;
-
-	/* return ENOMEM indicating insufficient memory for addresses */
-	if (netdev_uc_count(netdev) > ixgbe_available_rars(adapter, vfn))
-		return -ENOMEM;
-
-	if (!netdev_uc_empty(netdev)) {
-		struct netdev_hw_addr *ha;
-		netdev_for_each_uc_addr(ha, netdev) {
-			ixgbe_del_mac_filter(adapter, ha->addr, vfn);
-			ixgbe_add_mac_filter(adapter, ha->addr, vfn);
-			count++;
-		}
-	}
-	return count;
-}
-
 static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
@@ -5301,29 +5261,6 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
 	spin_unlock(&adapter->fdir_perfect_lock);
 }
 
-static void ixgbe_macvlan_set_rx_mode(struct net_device *dev, unsigned int pool,
-				      struct ixgbe_adapter *adapter)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	u32 vmolr;
-
-	/* No unicast promiscuous support for VMDQ devices. */
-	vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(pool));
-	vmolr |= (IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE);
-
-	/* clear the affected bit */
-	vmolr &= ~IXGBE_VMOLR_MPE;
-
-	if (dev->flags & IFF_ALLMULTI) {
-		vmolr |= IXGBE_VMOLR_MPE;
-	} else {
-		vmolr |= IXGBE_VMOLR_ROMPE;
-		hw->mac.ops.update_mc_addr_list(hw, dev);
-	}
-	ixgbe_write_uc_addr_list(adapter->netdev, pool);
-	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(pool), vmolr);
-}
-
 /**
  * ixgbe_clean_rx_ring - Free Rx Buffers per Queue
  * @rx_ring: ring to free buffers from
@@ -5376,21 +5313,17 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 	rx_ring->next_to_use = 0;
 }
 
-static int ixgbe_fwd_ring_up(struct net_device *vdev,
+static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 			     struct ixgbe_fwd_adapter *accel)
 {
-	struct ixgbe_adapter *adapter = accel->real_adapter;
+	struct net_device *vdev = accel->netdev;
 	int i, baseq, err;
 
-	if (!test_bit(accel->pool, adapter->fwd_bitmask))
-		return 0;
-
 	baseq = accel->pool * adapter->num_rx_queues_per_pool;
 	netdev_dbg(vdev, "pool %i:%i queues %i:%i\n",
 		   accel->pool, adapter->num_rx_pools,
 		   baseq, baseq + adapter->num_rx_queues_per_pool);
 
-	accel->netdev = vdev;
 	accel->rx_base_queue = baseq;
 	accel->tx_base_queue = baseq;
 
@@ -5407,26 +5340,36 @@ static int ixgbe_fwd_ring_up(struct net_device *vdev,
 	 */
 	err = ixgbe_add_mac_filter(adapter, vdev->dev_addr,
 				   VMDQ_P(accel->pool));
-	if (err >= 0) {
-		ixgbe_macvlan_set_rx_mode(vdev, accel->pool, adapter);
+	if (err >= 0)
 		return 0;
-	}
+
+	/* if we cannot add the MAC rule then disable the offload */
+	macvlan_release_l2fw_offload(vdev);
 
 	for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
 		adapter->rx_ring[baseq + i]->netdev = NULL;
 
+	netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n");
+
+	clear_bit(accel->pool, adapter->fwd_bitmask);
+	kfree(accel);
+
 	return err;
 }
 
-static int ixgbe_upper_dev_walk(struct net_device *upper, void *data)
+static int ixgbe_macvlan_up(struct net_device *vdev, void *data)
 {
-	if (netif_is_macvlan(upper)) {
-		struct macvlan_dev *dfwd = netdev_priv(upper);
-		struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
+	struct ixgbe_adapter *adapter = data;
+	struct ixgbe_fwd_adapter *accel;
 
-		if (dfwd->fwd_priv)
-			ixgbe_fwd_ring_up(upper, vadapter);
-	}
+	if (!netif_is_macvlan(vdev))
+		return 0;
+
+	accel = macvlan_accel_priv(vdev);
+	if (!accel)
+		return 0;
+
+	ixgbe_fwd_ring_up(adapter, accel);
 
 	return 0;
 }
@@ -5434,7 +5377,7 @@ static int ixgbe_upper_dev_walk(struct net_device *upper, void *data)
 static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
 {
 	netdev_walk_all_upper_dev_rcu(adapter->netdev,
-				      ixgbe_upper_dev_walk, NULL);
+				      ixgbe_macvlan_up, adapter);
 }
 
 static void ixgbe_configure(struct ixgbe_adapter *adapter)
@@ -5797,7 +5740,7 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring)
 
 		/* Free all the Tx ring sk_buffs */
 		if (ring_is_xdp(tx_ring))
-			page_frag_free(tx_buffer->data);
+			xdp_return_frame(tx_buffer->xdpf);
 		else
 			dev_kfree_skb_any(tx_buffer->skb);
 
@@ -6370,7 +6313,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
 	struct device *dev = rx_ring->dev;
 	int orig_node = dev_to_node(dev);
 	int ring_node = -1;
-	int size;
+	int size, err;
 
 	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
 
@@ -6407,6 +6350,13 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
 			     rx_ring->queue_index) < 0)
 		goto err;
 
+	err = xdp_rxq_info_reg_mem_model(&rx_ring->xdp_rxq,
+					 MEM_TYPE_PAGE_SHARED, NULL);
+	if (err) {
+		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+		goto err;
+	}
+
 	rx_ring->xdp_prog = adapter->xdp_prog;
 
 	return 0;
@@ -7671,17 +7621,19 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter)
 	if (!test_and_clear_bit(__IXGBE_RESET_REQUESTED, &adapter->state))
 		return;
 
+	rtnl_lock();
 	/* If we're already down, removing or resetting, just bail */
 	if (test_bit(__IXGBE_DOWN, &adapter->state) ||
 	    test_bit(__IXGBE_REMOVING, &adapter->state) ||
-	    test_bit(__IXGBE_RESETTING, &adapter->state))
+	    test_bit(__IXGBE_RESETTING, &adapter->state)) {
+		rtnl_unlock();
 		return;
+	}
 
 	ixgbe_dump(adapter);
 	netdev_err(adapter->netdev, "Reset adapter\n");
 	adapter->tx_timeout_count++;
 
-	rtnl_lock();
 	ixgbe_reinit_locked(adapter);
 	rtnl_unlock();
 }
@@ -7801,7 +7753,7 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring,
 
 	/* remove payload length from inner checksum */
 	paylen = skb->len - l4_offset;
-	csum_replace_by_diff(&l4.tcp->check, htonl(paylen));
+	csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen));
 
 	/* update gso size and bytecount with header size */
 	first->gso_segs = skb_shinfo(skb)->gso_segs;
@@ -8336,7 +8288,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 }
 
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
-			       struct xdp_buff *xdp)
+			       struct xdp_frame *xdpf)
 {
 	struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
 	struct ixgbe_tx_buffer *tx_buffer;
@@ -8345,12 +8297,12 @@ static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 	dma_addr_t dma;
 	u16 i;
 
-	len = xdp->data_end - xdp->data;
+	len = xdpf->len;
 
 	if (unlikely(!ixgbe_desc_unused(ring)))
 		return IXGBE_XDP_CONSUMED;
 
-	dma = dma_map_single(ring->dev, xdp->data, len, DMA_TO_DEVICE);
+	dma = dma_map_single(ring->dev, xdpf->data, len, DMA_TO_DEVICE);
 	if (dma_mapping_error(ring->dev, dma))
 		return IXGBE_XDP_CONSUMED;
 
@@ -8365,7 +8317,8 @@ static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 
 	dma_unmap_len_set(tx_buffer, len, len);
 	dma_unmap_addr_set(tx_buffer, dma, dma);
-	tx_buffer->data = xdp->data;
+	tx_buffer->xdpf = xdpf;
+
 	tx_desc->read.buffer_addr = cpu_to_le64(dma);
 
 	/* put descriptor type bits */
@@ -8827,6 +8780,49 @@ static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter)
 }
 
 #endif /* CONFIG_IXGBE_DCB */
+static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data)
+{
+	struct ixgbe_adapter *adapter = data;
+	struct ixgbe_fwd_adapter *accel;
+	int pool;
+
+	/* we only care about macvlans... */
+	if (!netif_is_macvlan(vdev))
+		return 0;
+
+	/* that have hardware offload enabled... */
+	accel = macvlan_accel_priv(vdev);
+	if (!accel)
+		return 0;
+
+	/* If we can relocate to a different bit do so */
+	pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
+	if (pool < adapter->num_rx_pools) {
+		set_bit(pool, adapter->fwd_bitmask);
+		accel->pool = pool;
+		return 0;
+	}
+
+	/* if we cannot find a free pool then disable the offload */
+	netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n");
+	macvlan_release_l2fw_offload(vdev);
+	kfree(accel);
+
+	return 0;
+}
+
+static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+
+	/* flush any stale bits out of the fwd bitmask */
+	bitmap_clear(adapter->fwd_bitmask, 1, 63);
+
+	/* walk through upper devices reassigning pools */
+	netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool,
+				      adapter);
+}
+
 /**
  * ixgbe_setup_tc - configure net_device for multiple traffic classes
  *
@@ -8894,6 +8890,8 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 #endif /* CONFIG_IXGBE_DCB */
 	ixgbe_init_interrupt_scheme(adapter);
 
+	ixgbe_defrag_macvlan_pools(dev);
+
 	if (netif_running(dev))
 		return ixgbe_open(dev);
 
@@ -8998,13 +8996,12 @@ struct upper_walk_data {
 static int get_macvlan_queue(struct net_device *upper, void *_data)
 {
 	if (netif_is_macvlan(upper)) {
-		struct macvlan_dev *dfwd = netdev_priv(upper);
-		struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
+		struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper);
 		struct upper_walk_data *data = _data;
 		struct ixgbe_adapter *adapter = data->adapter;
 		int ifindex = data->ifindex;
 
-		if (vadapter && vadapter->netdev->ifindex == ifindex) {
+		if (vadapter && upper->ifindex == ifindex) {
 			data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx;
 			data->action = data->queue;
 			return 1;
@@ -9108,7 +9105,8 @@ static int ixgbe_clsu32_build_input(struct ixgbe_fdir_filter *input,
 
 		for (j = 0; field_ptr[j].val; j++) {
 			if (field_ptr[j].off == off) {
-				field_ptr[j].val(input, mask, val, m);
+				field_ptr[j].val(input, mask, (__force u32)val,
+						 (__force u32)m);
 				input->filter.formatted.flow_type |=
 					field_ptr[j].type;
 				found_entry = true;
@@ -9117,8 +9115,10 @@ static int ixgbe_clsu32_build_input(struct ixgbe_fdir_filter *input,
 		}
 		if (nexthdr) {
 			if (nexthdr->off == cls->knode.sel->keys[i].off &&
-			    nexthdr->val == cls->knode.sel->keys[i].val &&
-			    nexthdr->mask == cls->knode.sel->keys[i].mask)
+			    nexthdr->val ==
+			    (__force u32)cls->knode.sel->keys[i].val &&
+			    nexthdr->mask ==
+			    (__force u32)cls->knode.sel->keys[i].mask)
 				found_jump_field = true;
 			else
 				continue;
@@ -9222,7 +9222,8 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter,
 		for (i = 0; nexthdr[i].jump; i++) {
 			if (nexthdr[i].o != cls->knode.sel->offoff ||
 			    nexthdr[i].s != cls->knode.sel->offshift ||
-			    nexthdr[i].m != cls->knode.sel->offmask)
+			    nexthdr[i].m !=
+			    (__force u32)cls->knode.sel->offmask)
 				return err;
 
 			jump = kzalloc(sizeof(*jump), GFP_KERNEL);
@@ -9443,6 +9444,22 @@ static netdev_features_t ixgbe_fix_features(struct net_device *netdev,
 	return features;
 }
 
+static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter)
+{
+	int rss = min_t(int, ixgbe_max_rss_indices(adapter),
+			num_online_cpus());
+
+	/* go back to full RSS if we're not running SR-IOV */
+	if (!adapter->ring_feature[RING_F_VMDQ].offset)
+		adapter->flags &= ~(IXGBE_FLAG_VMDQ_ENABLED |
+				    IXGBE_FLAG_SRIOV_ENABLED);
+
+	adapter->ring_feature[RING_F_RSS].limit = rss;
+	adapter->ring_feature[RING_F_VMDQ].limit = 1;
+
+	ixgbe_setup_tc(adapter->netdev, adapter->hw_tcs);
+}
+
 static int ixgbe_set_features(struct net_device *netdev,
 			      netdev_features_t features)
 {
@@ -9523,7 +9540,9 @@ static int ixgbe_set_features(struct net_device *netdev,
 		}
 	}
 
-	if (need_reset)
+	if ((changed & NETIF_F_HW_L2FW_DOFFLOAD) && adapter->num_rx_pools > 1)
+		ixgbe_reset_l2fw_offload(adapter);
+	else if (need_reset)
 		ixgbe_do_reset(netdev);
 	else if (changed & (NETIF_F_HW_VLAN_CTAG_RX |
 			    NETIF_F_HW_VLAN_CTAG_FILTER))
@@ -9786,71 +9805,98 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 
 static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 {
-	struct ixgbe_fwd_adapter *fwd_adapter = NULL;
 	struct ixgbe_adapter *adapter = netdev_priv(pdev);
-	int used_pools = adapter->num_vfs + adapter->num_rx_pools;
+	struct ixgbe_fwd_adapter *accel;
 	int tcs = adapter->hw_tcs ? : 1;
-	unsigned int limit;
 	int pool, err;
 
-	/* Hardware has a limited number of available pools. Each VF, and the
-	 * PF require a pool. Check to ensure we don't attempt to use more
-	 * then the available number of pools.
+	/* The hardware supported by ixgbe only filters on the destination MAC
+	 * address. In order to avoid issues we only support offloading modes
+	 * where the hardware can actually provide the functionality.
 	 */
-	if (used_pools >= IXGBE_MAX_VF_FUNCTIONS)
-		return ERR_PTR(-EINVAL);
+	if (!macvlan_supports_dest_filter(vdev))
+		return ERR_PTR(-EMEDIUMTYPE);
+
+	pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
+	if (pool == adapter->num_rx_pools) {
+		u16 used_pools = adapter->num_vfs + adapter->num_rx_pools;
+		u16 reserved_pools;
+
+		if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) &&
+		     adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) ||
+		    adapter->num_rx_pools > IXGBE_MAX_MACVLANS)
+			return ERR_PTR(-EBUSY);
+
+		/* Hardware has a limited number of available pools. Each VF,
+		 * and the PF require a pool. Check to ensure we don't
+		 * attempt to use more then the available number of pools.
+		 */
+		if (used_pools >= IXGBE_MAX_VF_FUNCTIONS)
+			return ERR_PTR(-EBUSY);
 
-	if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) &&
-	      adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) ||
-	    (adapter->num_rx_pools > IXGBE_MAX_MACVLANS))
-		return ERR_PTR(-EBUSY);
+		/* Enable VMDq flag so device will be set in VM mode */
+		adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED |
+				  IXGBE_FLAG_SRIOV_ENABLED;
 
-	fwd_adapter = kzalloc(sizeof(*fwd_adapter), GFP_KERNEL);
-	if (!fwd_adapter)
-		return ERR_PTR(-ENOMEM);
+		/* Try to reserve as many queues per pool as possible,
+		 * we start with the configurations that support 4 queues
+		 * per pools, followed by 2, and then by just 1 per pool.
+		 */
+		if (used_pools < 32 && adapter->num_rx_pools < 16)
+			reserved_pools = min_t(u16,
+					       32 - used_pools,
+					       16 - adapter->num_rx_pools);
+		else if (adapter->num_rx_pools < 32)
+			reserved_pools = min_t(u16,
+					       64 - used_pools,
+					       32 - adapter->num_rx_pools);
+		else
+			reserved_pools = 64 - used_pools;
 
-	pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
-	set_bit(pool, adapter->fwd_bitmask);
-	limit = find_last_bit(adapter->fwd_bitmask, adapter->num_rx_pools + 1);
 
-	/* Enable VMDq flag so device will be set in VM mode */
-	adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | IXGBE_FLAG_SRIOV_ENABLED;
-	adapter->ring_feature[RING_F_VMDQ].limit = limit + 1;
+		if (!reserved_pools)
+			return ERR_PTR(-EBUSY);
 
-	fwd_adapter->pool = pool;
-	fwd_adapter->real_adapter = adapter;
+		adapter->ring_feature[RING_F_VMDQ].limit += reserved_pools;
 
-	/* Force reinit of ring allocation with VMDQ enabled */
-	err = ixgbe_setup_tc(pdev, adapter->hw_tcs);
+		/* Force reinit of ring allocation with VMDQ enabled */
+		err = ixgbe_setup_tc(pdev, adapter->hw_tcs);
+		if (err)
+			return ERR_PTR(err);
 
-	if (!err && netif_running(pdev))
-		err = ixgbe_fwd_ring_up(vdev, fwd_adapter);
+		if (pool >= adapter->num_rx_pools)
+			return ERR_PTR(-ENOMEM);
+	}
 
-	if (!err)
-		return fwd_adapter;
+	accel = kzalloc(sizeof(*accel), GFP_KERNEL);
+	if (!accel)
+		return ERR_PTR(-ENOMEM);
 
-	/* unwind counter and free adapter struct */
-	netdev_info(pdev,
-		    "%s: dfwd hardware acceleration failed\n", vdev->name);
-	clear_bit(pool, adapter->fwd_bitmask);
-	kfree(fwd_adapter);
-	return ERR_PTR(err);
+	set_bit(pool, adapter->fwd_bitmask);
+	accel->pool = pool;
+	accel->netdev = vdev;
+
+	if (!netif_running(pdev))
+		return accel;
+
+	err = ixgbe_fwd_ring_up(adapter, accel);
+	if (err)
+		return ERR_PTR(err);
+
+	return accel;
 }
 
 static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 {
 	struct ixgbe_fwd_adapter *accel = priv;
-	struct ixgbe_adapter *adapter = accel->real_adapter;
+	struct ixgbe_adapter *adapter = netdev_priv(pdev);
 	unsigned int rxbase = accel->rx_base_queue;
-	unsigned int limit, i;
+	unsigned int i;
 
 	/* delete unicast filter associated with offloaded interface */
 	ixgbe_del_mac_filter(adapter, accel->netdev->dev_addr,
 			     VMDQ_P(accel->pool));
 
-	/* disable ability to receive packets for this pool */
-	IXGBE_WRITE_REG(&adapter->hw, IXGBE_VMOLR(accel->pool), 0);
-
 	/* Allow remaining Rx packets to get flushed out of the
 	 * Rx FIFO before we drop the netdev for the ring.
 	 */
@@ -9869,25 +9915,6 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 	}
 
 	clear_bit(accel->pool, adapter->fwd_bitmask);
-	limit = find_last_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
-	adapter->ring_feature[RING_F_VMDQ].limit = limit + 1;
-
-	/* go back to full RSS if we're done with our VMQs */
-	if (adapter->ring_feature[RING_F_VMDQ].limit == 1) {
-		int rss = min_t(int, ixgbe_max_rss_indices(adapter),
-				num_online_cpus());
-
-		adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED;
-		adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
-		adapter->ring_feature[RING_F_RSS].limit = rss;
-	}
-
-	ixgbe_setup_tc(pdev, adapter->hw_tcs);
-	netdev_dbg(pdev, "pool %i:%i queues %i:%i\n",
-		   accel->pool, adapter->num_rx_pools,
-		   accel->rx_base_queue,
-		   accel->rx_base_queue +
-		   adapter->num_rx_queues_per_pool);
 	kfree(accel);
 }
 
@@ -9969,7 +9996,8 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 		}
 	} else {
 		for (i = 0; i < adapter->num_rx_queues; i++)
-			xchg(&adapter->rx_ring[i]->xdp_prog, adapter->xdp_prog);
+			(void)xchg(&adapter->rx_ring[i]->xdp_prog,
+			    adapter->xdp_prog);
 	}
 
 	if (old_prog)
@@ -9995,15 +10023,29 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
-static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+static void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring)
+{
+	/* Force memory writes to complete before letting h/w know there
+	 * are new descriptors to fetch.
+	 */
+	wmb();
+	writel(ring->next_to_use, ring->tail);
+}
+
+static int ixgbe_xdp_xmit(struct net_device *dev, int n,
+			  struct xdp_frame **frames, u32 flags)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_ring *ring;
-	int err;
+	int drops = 0;
+	int i;
 
 	if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state)))
 		return -ENETDOWN;
 
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
 	/* During program transitions its possible adapter->xdp_prog is assigned
 	 * but ring has not been configured yet. In this case simply abort xmit.
 	 */
@@ -10011,35 +10053,21 @@ static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
 	if (unlikely(!ring))
 		return -ENXIO;
 
-	err = ixgbe_xmit_xdp_ring(adapter, xdp);
-	if (err != IXGBE_XDP_TX)
-		return -ENOSPC;
-
-	return 0;
-}
-
-static void ixgbe_xdp_flush(struct net_device *dev)
-{
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
-	struct ixgbe_ring *ring;
-
-	/* Its possible the device went down between xdp xmit and flush so
-	 * we need to ensure device is still up.
-	 */
-	if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state)))
-		return;
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		int err;
 
-	ring = adapter->xdp_prog ? adapter->xdp_ring[smp_processor_id()] : NULL;
-	if (unlikely(!ring))
-		return;
+		err = ixgbe_xmit_xdp_ring(adapter, xdpf);
+		if (err != IXGBE_XDP_TX) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		}
+	}
 
-	/* Force memory writes to complete before letting h/w know there
-	 * are new descriptors to fetch.
-	 */
-	wmb();
-	writel(ring->next_to_use, ring->tail);
+	if (unlikely(flags & XDP_XMIT_FLUSH))
+		ixgbe_xdp_ring_update_tail(ring);
 
-	return;
+	return n - drops;
 }
 
 static const struct net_device_ops ixgbe_netdev_ops = {
@@ -10089,7 +10117,6 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_features_check	= ixgbe_features_check,
 	.ndo_bpf		= ixgbe_xdp,
 	.ndo_xdp_xmit		= ixgbe_xdp_xmit,
-	.ndo_xdp_flush		= ixgbe_xdp_flush,
 };
 
 /**
@@ -10908,14 +10935,14 @@ skip_bad_vf_detection:
 	rtnl_lock();
 	netif_device_detach(netdev);
 
+	if (netif_running(netdev))
+		ixgbe_close_suspend(adapter);
+
 	if (state == pci_channel_io_perm_failure) {
 		rtnl_unlock();
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
-	if (netif_running(netdev))
-		ixgbe_close_suspend(adapter);
-
 	if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state))
 		pci_disable_device(pdev);
 	rtnl_unlock();