5 files changed, 389 insertions, 248 deletions

diff --git a/drivers/net/cxgb4vf/adapter.h b/drivers/net/cxgb4vf/adapter.h
index 8ea01962e045..4fd821aadc8a 100644
--- a/drivers/net/cxgb4vf/adapter.h
+++ b/drivers/net/cxgb4vf/adapter.h
@@ -60,7 +60,7 @@ enum {
          * MSI-X interrupt index usage.
          */
         MSIX_FW         = 0,            /* MSI-X index for firmware Q */
-        MSIX_NIQFLINT   = 1,            /* MSI-X index base for Ingress Qs */
+        MSIX_IQFLINT    = 1,            /* MSI-X index base for Ingress Qs */
         MSIX_EXTRAS     = 1,
         MSIX_ENTRIES    = MAX_ETH_QSETS + MSIX_EXTRAS,
 
@@ -97,17 +97,11 @@ struct port_info {
         u16 rss_size;                   /* size of VI's RSS table slice */
         u8 pidx;                        /* index into adapter port[] */
         u8 port_id;                     /* physical port ID */
-        u8 rx_offload;                  /* CSO, etc. */
         u8 nqsets;                      /* # of "Queue Sets" */
         u8 first_qset;                  /* index of first "Queue Set" */
         struct link_config link_cfg;    /* physical port configuration */
 };
 
-/* port_info.rx_offload flags */
-enum {
-        RX_CSO = 1 << 0,
-};
-
 /*
  * Scatter Gather Engine resources for the "adapter".  Our ingress and egress
  * queues are organized into "Queue Sets" with one ingress and one egress
diff --git a/drivers/net/cxgb4vf/cxgb4vf_main.c b/drivers/net/cxgb4vf/cxgb4vf_main.c
index 7b6d07f50c71..e71c08e547e4 100644
--- a/drivers/net/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/cxgb4vf/cxgb4vf_main.c
@@ -280,9 +280,7 @@ static void name_msix_vecs(struct adapter *adapter)
                 const struct port_info *pi = netdev_priv(dev);
                 int qs, msi;
 
-                for (qs = 0, msi = MSIX_NIQFLINT;
-                     qs < pi->nqsets;
-                     qs++, msi++) {
+                for (qs = 0, msi = MSIX_IQFLINT; qs < pi->nqsets; qs++, msi++) {
                         snprintf(adapter->msix_info[msi].desc, namelen,
                                  "%s-%d", dev->name, qs);
                         adapter->msix_info[msi].desc[namelen] = 0;
@@ -309,7 +307,7 @@ static int request_msix_queue_irqs(struct adapter *adapter)
         /*
          * Ethernet queues.
          */
-        msi = MSIX_NIQFLINT;
+        msi = MSIX_IQFLINT;
         for_each_ethrxq(s, rxq) {
                 err = request_irq(adapter->msix_info[msi].vec,
                                   t4vf_sge_intr_msix, 0,
@@ -337,7 +335,7 @@ static void free_msix_queue_irqs(struct adapter *adapter)
         int rxq, msi;
 
         free_irq(adapter->msix_info[MSIX_FW].vec, &s->fw_evtq);
-        msi = MSIX_NIQFLINT;
+        msi = MSIX_IQFLINT;
         for_each_ethrxq(s, rxq)
                 free_irq(adapter->msix_info[msi++].vec,
                          &s->ethrxq[rxq].rspq);
@@ -527,7 +525,7 @@ static int setup_sge_queues(struct adapter *adapter)
          * brought up at which point lots of things get nailed down
          * permanently ...
          */
-        msix = MSIX_NIQFLINT;
+        msix = MSIX_IQFLINT;
         for_each_port(adapter, pidx) {
                 struct net_device *dev = adapter->port[pidx];
                 struct port_info *pi = netdev_priv(dev);
@@ -748,11 +746,22 @@ static int cxgb4vf_open(struct net_device *dev)
         /*
          * Note that this interface is up and start everything up ...
          */
-        dev->real_num_tx_queues = pi->nqsets;
-        set_bit(pi->port_id, &adapter->open_device_map);
-        link_start(dev);
+        netif_set_real_num_tx_queues(dev, pi->nqsets);
+        err = netif_set_real_num_rx_queues(dev, pi->nqsets);
+        if (err)
+                goto err_unwind;
+        err = link_start(dev);
+        if (err)
+                goto err_unwind;
+
         netif_tx_start_all_queues(dev);
+        set_bit(pi->port_id, &adapter->open_device_map);
         return 0;
+
+err_unwind:
+        if (adapter->open_device_map == 0)
+                adapter_down(adapter);
+        return err;
 }
 
 /*
@@ -761,13 +770,12 @@ static int cxgb4vf_open(struct net_device *dev)
  */
 static int cxgb4vf_stop(struct net_device *dev)
 {
-        int ret;
         struct port_info *pi = netdev_priv(dev);
         struct adapter *adapter = pi->adapter;
 
         netif_tx_stop_all_queues(dev);
         netif_carrier_off(dev);
-        ret = t4vf_enable_vi(adapter, pi->viid, false, false);
+        t4vf_enable_vi(adapter, pi->viid, false, false);
         pi->link_cfg.link_ok = 0;
 
         clear_bit(pi->port_id, &adapter->open_device_map);
@@ -811,40 +819,48 @@ static struct net_device_stats *cxgb4vf_get_stats(struct net_device *dev)
 }
 
 /*
- * Collect up to maxaddrs worth of a netdevice's unicast addresses into an
- * array of addrss pointers and return the number collected.
+ * Collect up to maxaddrs worth of a netdevice's unicast addresses, starting
+ * at a specified offset within the list, into an array of addrss pointers and
+ * return the number collected.
  */
-static inline int collect_netdev_uc_list_addrs(const struct net_device *dev,
-                                               const u8 **addr,
-                                               unsigned int maxaddrs)
+static inline unsigned int collect_netdev_uc_list_addrs(const struct net_device *dev,
+                                                        const u8 **addr,
+                                                        unsigned int offset,
+                                                        unsigned int maxaddrs)
 {
+        unsigned int index = 0;
         unsigned int naddr = 0;
         const struct netdev_hw_addr *ha;
 
-        for_each_dev_addr(dev, ha) {
-                addr[naddr++] = ha->addr;
-                if (naddr >= maxaddrs)
-                        break;
-        }
+        for_each_dev_addr(dev, ha)
+                if (index++ >= offset) {
+                        addr[naddr++] = ha->addr;
+                        if (naddr >= maxaddrs)
+                                break;
+                }
         return naddr;
 }
 
 /*
- * Collect up to maxaddrs worth of a netdevice's multicast addresses into an
- * array of addrss pointers and return the number collected.
+ * Collect up to maxaddrs worth of a netdevice's multicast addresses, starting
+ * at a specified offset within the list, into an array of addrss pointers and
+ * return the number collected.
  */
-static inline int collect_netdev_mc_list_addrs(const struct net_device *dev,
-                                               const u8 **addr,
-                                               unsigned int maxaddrs)
+static inline unsigned int collect_netdev_mc_list_addrs(const struct net_device *dev,
+                                                        const u8 **addr,
+                                                        unsigned int offset,
+                                                        unsigned int maxaddrs)
 {
+        unsigned int index = 0;
         unsigned int naddr = 0;
         const struct netdev_hw_addr *ha;
 
-        netdev_for_each_mc_addr(ha, dev) {
-                addr[naddr++] = ha->addr;
-                if (naddr >= maxaddrs)
-                        break;
-        }
+        netdev_for_each_mc_addr(ha, dev)
+                if (index++ >= offset) {
+                        addr[naddr++] = ha->addr;
+                        if (naddr >= maxaddrs)
+                                break;
+                }
         return naddr;
 }
 
@@ -857,16 +873,20 @@ static int set_addr_filters(const struct net_device *dev, bool sleep)
         u64 mhash = 0;
         u64 uhash = 0;
         bool free = true;
-        u16 filt_idx[7];
+        unsigned int offset, naddr;
         const u8 *addr[7];
-        int ret, naddr = 0;
+        int ret;
         const struct port_info *pi = netdev_priv(dev);
 
         /* first do the secondary unicast addresses */
-        naddr = collect_netdev_uc_list_addrs(dev, addr, ARRAY_SIZE(addr));
-        if (naddr > 0) {
+        for (offset = 0; ; offset += naddr) {
+                naddr = collect_netdev_uc_list_addrs(dev, addr, offset,
+                                                     ARRAY_SIZE(addr));
+                if (naddr == 0)
+                        break;
+
                 ret = t4vf_alloc_mac_filt(pi->adapter, pi->viid, free,
-                                          naddr, addr, filt_idx, &uhash, sleep);
+                                          naddr, addr, NULL, &uhash, sleep);
                 if (ret < 0)
                         return ret;
 
@@ -874,12 +894,17 @@ static int set_addr_filters(const struct net_device *dev, bool sleep)
         }
 
         /* next set up the multicast addresses */
-        naddr = collect_netdev_mc_list_addrs(dev, addr, ARRAY_SIZE(addr));
-        if (naddr > 0) {
+        for (offset = 0; ; offset += naddr) {
+                naddr = collect_netdev_mc_list_addrs(dev, addr, offset,
+                                                     ARRAY_SIZE(addr));
+                if (naddr == 0)
+                        break;
+
                 ret = t4vf_alloc_mac_filt(pi->adapter, pi->viid, free,
-                                          naddr, addr, filt_idx, &mhash, sleep);
+                                          naddr, addr, NULL, &mhash, sleep);
                 if (ret < 0)
                         return ret;
+                free = false;
         }
 
         return t4vf_set_addr_hash(pi->adapter, pi->viid, uhash != 0,
@@ -1100,18 +1125,6 @@ static int cxgb4vf_set_mac_addr(struct net_device *dev, void *_addr)
         return 0;
 }
 
-/*
- * Return a TX Queue on which to send the specified skb.
- */
-static u16 cxgb4vf_select_queue(struct net_device *dev, struct sk_buff *skb)
-{
-        /*
-         * XXX For now just use the default hash but we probably want to
-         * XXX look at other possibilities ...
-         */
-        return skb_tx_hash(dev, skb);
-}
-
 #ifdef CONFIG_NET_POLL_CONTROLLER
 /*
  * Poll all of our receive queues.  This is called outside of normal interrupt
@@ -1154,7 +1167,8 @@ static int cxgb4vf_get_settings(struct net_device *dev,
 
         cmd->supported = pi->link_cfg.supported;
         cmd->advertising = pi->link_cfg.advertising;
-        cmd->speed = netif_carrier_ok(dev) ? pi->link_cfg.speed : -1;
+        ethtool_cmd_speed_set(cmd,
+                              netif_carrier_ok(dev) ? pi->link_cfg.speed : -1);
         cmd->duplex = DUPLEX_FULL;
 
         cmd->port = (cmd->supported & SUPPORTED_TP) ? PORT_TP : PORT_FIBRE;
@@ -1313,37 +1327,22 @@ static void cxgb4vf_get_pauseparam(struct net_device *dev,
 }
 
 /*
- * Return whether RX Checksum Offloading is currently enabled for the device.
- */
-static u32 cxgb4vf_get_rx_csum(struct net_device *dev)
-{
-        struct port_info *pi = netdev_priv(dev);
-
-        return (pi->rx_offload & RX_CSO) != 0;
-}
-
-/*
- * Turn RX Checksum Offloading on or off for the device.
+ * Identify the port by blinking the port's LED.
  */
-static int cxgb4vf_set_rx_csum(struct net_device *dev, u32 csum)
+static int cxgb4vf_phys_id(struct net_device *dev,
+                           enum ethtool_phys_id_state state)
 {
+        unsigned int val;
         struct port_info *pi = netdev_priv(dev);
 
-        if (csum)
-                pi->rx_offload |= RX_CSO;
+        if (state == ETHTOOL_ID_ACTIVE)
+                val = 0xffff;
+        else if (state == ETHTOOL_ID_INACTIVE)
+                val = 0;
         else
-                pi->rx_offload &= ~RX_CSO;
-        return 0;
-}
-
-/*
- * Identify the port by blinking the port's LED.
- */
-static int cxgb4vf_phys_id(struct net_device *dev, u32 id)
-{
-        struct port_info *pi = netdev_priv(dev);
+                return -EINVAL;
 
-        return t4vf_identify_port(pi->adapter, pi->viid, 5);
+        return t4vf_identify_port(pi->adapter, pi->viid, val);
 }
 
 /*
@@ -1355,6 +1354,8 @@ struct queue_port_stats {
         u64 rx_csum;
         u64 vlan_ex;
         u64 vlan_ins;
+        u64 lro_pkts;
+        u64 lro_merged;
 };
 
 /*
@@ -1392,6 +1393,8 @@ static const char stats_strings[][ETH_GSTRING_LEN] = {
         "RxCsumGood        ",
         "VLANextractions   ",
         "VLANinsertions    ",
+        "GROPackets        ",
+        "GROMerged         ",
 };
 
 /*
@@ -1441,6 +1444,8 @@ static void collect_sge_port_stats(const struct adapter *adapter,
                 stats->rx_csum += rxq->stats.rx_cso;
                 stats->vlan_ex += rxq->stats.vlan_ex;
                 stats->vlan_ins += txq->vlan_ins;
+                stats->lro_pkts += rxq->stats.lro_pkts;
+                stats->lro_merged += rxq->stats.lro_merged;
         }
 }
 
@@ -1537,16 +1542,9 @@ static void cxgb4vf_get_wol(struct net_device *dev,
 }
 
 /*
- * Set TCP Segmentation Offloading feature capabilities.
+ * TCP Segmentation Offload flags which we support.
  */
-static int cxgb4vf_set_tso(struct net_device *dev, u32 tso)
-{
-        if (tso)
-                dev->features |= NETIF_F_TSO | NETIF_F_TSO6;
-        else
-                dev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
-        return 0;
-}
+#define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
 
 static struct ethtool_ops cxgb4vf_ethtool_ops = {
         .get_settings           = cxgb4vf_get_settings,
@@ -1558,19 +1556,14 @@ static struct ethtool_ops cxgb4vf_ethtool_ops = {
         .get_coalesce           = cxgb4vf_get_coalesce,
         .set_coalesce           = cxgb4vf_set_coalesce,
         .get_pauseparam         = cxgb4vf_get_pauseparam,
-        .get_rx_csum            = cxgb4vf_get_rx_csum,
-        .set_rx_csum            = cxgb4vf_set_rx_csum,
-        .set_tx_csum            = ethtool_op_set_tx_ipv6_csum,
-        .set_sg                 = ethtool_op_set_sg,
         .get_link               = ethtool_op_get_link,
         .get_strings            = cxgb4vf_get_strings,
-        .phys_id                = cxgb4vf_phys_id,
+        .set_phys_id            = cxgb4vf_phys_id,
         .get_sset_count         = cxgb4vf_get_sset_count,
         .get_ethtool_stats      = cxgb4vf_get_ethtool_stats,
         .get_regs_len           = cxgb4vf_get_regs_len,
         .get_regs               = cxgb4vf_get_regs,
         .get_wol                = cxgb4vf_get_wol,
-        .set_tso                = cxgb4vf_set_tso,
 };
 
 /*
@@ -2016,7 +2009,7 @@ static int __devinit setup_debugfs(struct adapter *adapter)
 {
         int i;
 
-        BUG_ON(adapter->debugfs_root == NULL);
+        BUG_ON(IS_ERR_OR_NULL(adapter->debugfs_root));
 
         /*
          * Debugfs support is best effort.
@@ -2035,9 +2028,9 @@ static int __devinit setup_debugfs(struct adapter *adapter)
  * Tear down the /sys/kernel/debug/cxgb4vf sub-nodes created above.  We leave
  * it to our caller to tear down the directory (debugfs_root).
  */
-static void __devexit cleanup_debugfs(struct adapter *adapter)
+static void cleanup_debugfs(struct adapter *adapter)
 {
-        BUG_ON(adapter->debugfs_root == NULL);
+        BUG_ON(IS_ERR_OR_NULL(adapter->debugfs_root));
 
         /*
          * Unlike our sister routine cleanup_proc(), we don't need to remove
@@ -2053,7 +2046,7 @@ static void __devexit cleanup_debugfs(struct adapter *adapter)
  * adapter parameters we're going to be using and initialize basic adapter
  * hardware support.
  */
-static int adap_init0(struct adapter *adapter)
+static int __devinit adap_init0(struct adapter *adapter)
 {
         struct vf_resources *vfres = &adapter->params.vfres;
         struct sge_params *sge_params = &adapter->params.sge;
@@ -2072,6 +2065,22 @@ static int adap_init0(struct adapter *adapter)
         }
 
         /*
+         * Some environments do not properly handle PCIE FLRs -- e.g. in Linux
+         * 2.6.31 and later we can't call pci_reset_function() in order to
+         * issue an FLR because of a self- deadlock on the device semaphore.
+         * Meanwhile, the OS infrastructure doesn't issue FLRs in all the
+         * cases where they're needed -- for instance, some versions of KVM
+         * fail to reset "Assigned Devices" when the VM reboots.  Therefore we
+         * use the firmware based reset in order to reset any per function
+         * state.
+         */
+        err = t4vf_fw_reset(adapter);
+        if (err < 0) {
+                dev_err(adapter->pdev_dev, "FW reset failed: err=%d\n", err);
+                return err;
+        }
+
+        /*
          * Grab basic operational parameters.  These will predominantly have
          * been set up by the Physical Function Driver or will be hard coded
          * into the adapter.  We just have to live with them ...  Note that
@@ -2243,6 +2252,7 @@ static void __devinit cfg_queues(struct adapter *adapter)
 {
         struct sge *s = &adapter->sge;
         int q10g, n10g, qidx, pidx, qs;
+        size_t iqe_size;
 
         /*
          * We should not be called till we know how many Queue Sets we can
@@ -2287,6 +2297,13 @@ static void __devinit cfg_queues(struct adapter *adapter)
         s->ethqsets = qidx;
 
         /*
+         * The Ingress Queue Entry Size for our various Response Queues needs
+         * to be big enough to accommodate the largest message we can receive
+         * from the chip/firmware; which is 64 bytes ...
+         */
+        iqe_size = 64;
+
+        /*
          * Set up default Queue Set parameters ...  Start off with the
          * shortest interrupt holdoff timer.
          */
@@ -2294,7 +2311,7 @@ static void __devinit cfg_queues(struct adapter *adapter)
                 struct sge_eth_rxq *rxq = &s->ethrxq[qs];
                 struct sge_eth_txq *txq = &s->ethtxq[qs];
 
-                init_rspq(&rxq->rspq, 0, 0, 1024, L1_CACHE_BYTES);
+                init_rspq(&rxq->rspq, 0, 0, 1024, iqe_size);
                 rxq->fl.size = 72;
                 txq->q.size = 1024;
         }
@@ -2303,8 +2320,7 @@ static void __devinit cfg_queues(struct adapter *adapter)
          * The firmware event queue is used for link state changes and
          * notifications of TX DMA completions.
          */
-        init_rspq(&s->fw_evtq, SGE_TIMER_RSTRT_CNTR, 0, 512,
-                  L1_CACHE_BYTES);
+        init_rspq(&s->fw_evtq, SGE_TIMER_RSTRT_CNTR, 0, 512, iqe_size);
 
         /*
          * The forwarded interrupt queue is used when we're in MSI interrupt
@@ -2320,7 +2336,7 @@ static void __devinit cfg_queues(struct adapter *adapter)
          * any time ...
          */
         init_rspq(&s->intrq, SGE_TIMER_RSTRT_CNTR, 0, MSIX_ENTRIES + 1,
-                  L1_CACHE_BYTES);
+                  iqe_size);
 }
 
 /*
@@ -2414,7 +2430,6 @@ static const struct net_device_ops cxgb4vf_netdev_ops	= {
         .ndo_get_stats          = cxgb4vf_get_stats,
         .ndo_set_rx_mode        = cxgb4vf_set_rxmode,
         .ndo_set_mac_address    = cxgb4vf_set_mac_addr,
-        .ndo_select_queue       = cxgb4vf_select_queue,
         .ndo_validate_addr      = eth_validate_addr,
         .ndo_do_ioctl           = cxgb4vf_do_ioctl,
         .ndo_change_mtu         = cxgb4vf_change_mtu,
@@ -2443,17 +2458,6 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
         struct net_device *netdev;
 
         /*
-         * Vet our module parameters.
-         */
-        if (msi != MSI_MSIX && msi != MSI_MSI) {
-                dev_err(&pdev->dev, "bad module parameter msi=%d; must be %d"
-                        " (MSI-X or MSI) or %d (MSI)\n", msi, MSI_MSIX,
-                        MSI_MSI);
-                err = -EINVAL;
-                goto err_out;
-        }
-
-        /*
          * Print our driver banner the first time we're called to initialize a
          * device.
          */
@@ -2462,7 +2466,6 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
                 version_printed = 1;
         }
 
-
         /*
          * Initialize generic PCI device state.
          */
@@ -2595,20 +2598,19 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
                  * it.
                  */
                 pi->xact_addr_filt = -1;
-                pi->rx_offload = RX_CSO;
                 netif_carrier_off(netdev);
-                netif_tx_stop_all_queues(netdev);
                 netdev->irq = pdev->irq;
 
-                netdev->features = (NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
-                                    NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-                                    NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX |
-                                    NETIF_F_GRO);
+                netdev->hw_features = NETIF_F_SG | TSO_FLAGS |
+                        NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+                        NETIF_F_HW_VLAN_TX | NETIF_F_RXCSUM;
+                netdev->vlan_features = NETIF_F_SG | TSO_FLAGS |
+                        NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+                        NETIF_F_HIGHDMA;
+                netdev->features = netdev->hw_features |
+                        NETIF_F_HW_VLAN_RX;
                 if (pci_using_dac)
                         netdev->features |= NETIF_F_HIGHDMA;
-                netdev->vlan_features =
-                        (netdev->features &
-                         ~(NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX));
 
 #ifdef HAVE_NET_DEVICE_OPS
                 netdev->netdev_ops = &cxgb4vf_netdev_ops;
@@ -2622,7 +2624,6 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
                 netdev->do_ioctl = cxgb4vf_do_ioctl;
                 netdev->change_mtu = cxgb4vf_change_mtu;
                 netdev->set_mac_address = cxgb4vf_set_mac_addr;
-                netdev->select_queue = cxgb4vf_select_queue;
 #ifdef CONFIG_NET_POLL_CONTROLLER
                 netdev->poll_controller = cxgb4vf_poll_controller;
 #endif
@@ -2668,11 +2669,11 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
         /*
          * Set up our debugfs entries.
          */
-        if (cxgb4vf_debugfs_root) {
+        if (!IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) {
                 adapter->debugfs_root =
                         debugfs_create_dir(pci_name(pdev),
                                            cxgb4vf_debugfs_root);
-                if (adapter->debugfs_root == NULL)
+                if (IS_ERR_OR_NULL(adapter->debugfs_root))
                         dev_warn(&pdev->dev, "could not create debugfs"
                                  " directory");
                 else
@@ -2706,7 +2707,7 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
         cfg_queues(adapter);
 
         /*
-         * Print a short notice on the existance and configuration of the new
+         * Print a short notice on the existence and configuration of the new
          * VF network device ...
          */
         for_each_port(adapter, pidx) {
@@ -2727,7 +2728,7 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
          */
 
 err_free_debugfs:
-        if (adapter->debugfs_root) {
+        if (!IS_ERR_OR_NULL(adapter->debugfs_root)) {
                 cleanup_debugfs(adapter);
                 debugfs_remove_recursive(adapter->debugfs_root);
         }
@@ -2759,7 +2760,6 @@ err_release_regions:
 err_disable_device:
         pci_disable_device(pdev);
 
-err_out:
         return err;
 }
 
@@ -2797,7 +2797,7 @@ static void __devexit cxgb4vf_pci_remove(struct pci_dev *pdev)
                 /*
                  * Tear down our debugfs entries.
                  */
-                if (adapter->debugfs_root) {
+                if (!IS_ERR_OR_NULL(adapter->debugfs_root)) {
                         cleanup_debugfs(adapter);
                         debugfs_remove_recursive(adapter->debugfs_root);
                 }
@@ -2831,6 +2831,46 @@ static void __devexit cxgb4vf_pci_remove(struct pci_dev *pdev)
 }
 
 /*
+ * "Shutdown" quiesce the device, stopping Ingress Packet and Interrupt
+ * delivery.
+ */
+static void __devexit cxgb4vf_pci_shutdown(struct pci_dev *pdev)
+{
+        struct adapter *adapter;
+        int pidx;
+
+        adapter = pci_get_drvdata(pdev);
+        if (!adapter)
+                return;
+
+        /*
+         * Disable all Virtual Interfaces.  This will shut down the
+         * delivery of all ingress packets into the chip for these
+         * Virtual Interfaces.
+         */
+        for_each_port(adapter, pidx) {
+                struct net_device *netdev;
+                struct port_info *pi;
+
+                if (!test_bit(pidx, &adapter->registered_device_map))
+                        continue;
+
+                netdev = adapter->port[pidx];
+                if (!netdev)
+                        continue;
+
+                pi = netdev_priv(netdev);
+                t4vf_enable_vi(adapter, pi->viid, false, false);
+        }
+
+        /*
+         * Free up all Queues which will prevent further DMA and
+         * Interrupts allowing various internal pathways to drain.
+         */
+        t4vf_free_sge_resources(adapter);
+}
+
+/*
  * PCI Device registration data structures.
  */
 #define CH_DEVICE(devid, idx) \
@@ -2841,6 +2881,14 @@ static struct pci_device_id cxgb4vf_pci_tbl[] = {
         CH_DEVICE(0x4800, 0),   /* T440-dbg */
         CH_DEVICE(0x4801, 0),   /* T420-cr */
         CH_DEVICE(0x4802, 0),   /* T422-cr */
+        CH_DEVICE(0x4803, 0),   /* T440-cr */
+        CH_DEVICE(0x4804, 0),   /* T420-bch */
+        CH_DEVICE(0x4805, 0),   /* T440-bch */
+        CH_DEVICE(0x4806, 0),   /* T460-ch */
+        CH_DEVICE(0x4807, 0),   /* T420-so */
+        CH_DEVICE(0x4808, 0),   /* T420-cx */
+        CH_DEVICE(0x4809, 0),   /* T420-bt */
+        CH_DEVICE(0x480a, 0),   /* T404-bt */
         { 0, }
 };
 
@@ -2855,6 +2903,7 @@ static struct pci_driver cxgb4vf_driver = {
         .id_table       = cxgb4vf_pci_tbl,
         .probe          = cxgb4vf_pci_probe,
         .remove         = __devexit_p(cxgb4vf_pci_remove),
+        .shutdown       = __devexit_p(cxgb4vf_pci_shutdown),
 };
 
 /*
@@ -2864,14 +2913,25 @@ static int __init cxgb4vf_module_init(void)
 {
         int ret;
 
+        /*
+         * Vet our module parameters.
+         */
+        if (msi != MSI_MSIX && msi != MSI_MSI) {
+                printk(KERN_WARNING KBUILD_MODNAME
+                       ": bad module parameter msi=%d; must be %d"
+                       " (MSI-X or MSI) or %d (MSI)\n",
+                       msi, MSI_MSIX, MSI_MSI);
+                return -EINVAL;
+        }
+
         /* Debugfs support is optional, just warn if this fails */
         cxgb4vf_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL);
-        if (!cxgb4vf_debugfs_root)
+        if (IS_ERR_OR_NULL(cxgb4vf_debugfs_root))
                 printk(KERN_WARNING KBUILD_MODNAME ": could not create"
                        " debugfs entry, continuing\n");
 
         ret = pci_register_driver(&cxgb4vf_driver);
-        if (ret < 0)
+        if (ret < 0 && !IS_ERR_OR_NULL(cxgb4vf_debugfs_root))
                 debugfs_remove(cxgb4vf_debugfs_root);
         return ret;
 }
diff --git a/drivers/net/cxgb4vf/sge.c b/drivers/net/cxgb4vf/sge.c
index eb5a1c9cb2d3..5fd75fdaa631 100644
--- a/drivers/net/cxgb4vf/sge.c
+++ b/drivers/net/cxgb4vf/sge.c
@@ -41,6 +41,7 @@
 #include <net/ipv6.h>
 #include <net/tcp.h>
 #include <linux/dma-mapping.h>
+#include <linux/prefetch.h>
 
 #include "t4vf_common.h"
 #include "t4vf_defs.h"
@@ -154,13 +155,14 @@ enum {
          */
         RX_COPY_THRES = 256,
         RX_PULL_LEN = 128,
-};
 
-/*
- * Can't define this in the above enum because PKTSHIFT isn't a constant in
- * the VF Driver ...
- */
-#define RX_PKT_PULL_LEN (RX_PULL_LEN + PKTSHIFT)
+        /*
+         * Main body length for sk_buffs used for RX Ethernet packets with
+         * fragments.  Should be >= RX_PULL_LEN but possibly bigger to give
+         * pskb_may_pull() some room.
+         */
+        RX_SKB_LEN = 512,
+};
 
 /*
  * Software state per TX descriptor.
@@ -223,8 +225,8 @@ static inline bool is_buf_mapped(const struct rx_sw_desc *sdesc)
 /**
  *      need_skb_unmap - does the platform need unmapping of sk_buffs?
  *
- *      Returns true if the platfrom needs sk_buff unmapping.  The compiler
- *      optimizes away unecessary code if this returns true.
+ *      Returns true if the platform needs sk_buff unmapping.  The compiler
+ *      optimizes away unnecessary code if this returns true.
  */
 static inline int need_skb_unmap(void)
 {
@@ -266,7 +268,7 @@ static inline unsigned int fl_cap(const struct sge_fl *fl)
  *
  *      Tests specified Free List to see whether the number of buffers
  *      available to the hardware has falled below our "starvation"
- *      threshhold.
+ *      threshold.
  */
 static inline bool fl_starving(const struct sge_fl *fl)
 {
@@ -1148,7 +1150,7 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev)
         if (unlikely(credits < ETHTXQ_STOP_THRES)) {
                 /*
                  * After we're done injecting the Work Request for this
-                 * packet, we'll be below our "stop threshhold" so stop the TX
+                 * packet, we'll be below our "stop threshold" so stop the TX
                  * Queue now and schedule a request for an SGE Egress Queue
                  * Update message.  The queue will get started later on when
                  * the firmware processes this Work Request and sends us an
@@ -1355,6 +1357,67 @@ out_free:
 }
 
 /**
+ *      t4vf_pktgl_to_skb - build an sk_buff from a packet gather list
+ *      @gl: the gather list
+ *      @skb_len: size of sk_buff main body if it carries fragments
+ *      @pull_len: amount of data to move to the sk_buff's main body
+ *
+ *      Builds an sk_buff from the given packet gather list.  Returns the
+ *      sk_buff or %NULL if sk_buff allocation failed.
+ */
+struct sk_buff *t4vf_pktgl_to_skb(const struct pkt_gl *gl,
+                                  unsigned int skb_len, unsigned int pull_len)
+{
+        struct sk_buff *skb;
+        struct skb_shared_info *ssi;
+
+        /*
+         * If the ingress packet is small enough, allocate an skb large enough
+         * for all of the data and copy it inline.  Otherwise, allocate an skb
+         * with enough room to pull in the header and reference the rest of
+         * the data via the skb fragment list.
+         *
+         * Below we rely on RX_COPY_THRES being less than the smallest Rx
+         * buff!  size, which is expected since buffers are at least
+         * PAGE_SIZEd.  In this case packets up to RX_COPY_THRES have only one
+         * fragment.
+         */
+        if (gl->tot_len <= RX_COPY_THRES) {
+                /* small packets have only one fragment */
+                skb = alloc_skb(gl->tot_len, GFP_ATOMIC);
+                if (unlikely(!skb))
+                        goto out;
+                __skb_put(skb, gl->tot_len);
+                skb_copy_to_linear_data(skb, gl->va, gl->tot_len);
+        } else {
+                skb = alloc_skb(skb_len, GFP_ATOMIC);
+                if (unlikely(!skb))
+                        goto out;
+                __skb_put(skb, pull_len);
+                skb_copy_to_linear_data(skb, gl->va, pull_len);
+
+                ssi = skb_shinfo(skb);
+                ssi->frags[0].page = gl->frags[0].page;
+                ssi->frags[0].page_offset = gl->frags[0].page_offset + pull_len;
+                ssi->frags[0].size = gl->frags[0].size - pull_len;
+                if (gl->nfrags > 1)
+                        memcpy(&ssi->frags[1], &gl->frags[1],
+                               (gl->nfrags-1) * sizeof(skb_frag_t));
+                ssi->nr_frags = gl->nfrags;
+
+                skb->len = gl->tot_len;
+                skb->data_len = skb->len - pull_len;
+                skb->truesize += skb->data_len;
+
+                /* Get a reference for the last page, we don't own it */
+                get_page(gl->frags[gl->nfrags - 1].page);
+        }
+
+out:
+        return skb;
+}
+
+/**
  *      t4vf_pktgl_free - free a packet gather list
  *      @gl: the gather list
  *
@@ -1463,10 +1526,8 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
 {
         struct sk_buff *skb;
         struct port_info *pi;
-        struct skb_shared_info *ssi;
         const struct cpl_rx_pkt *pkt = (void *)&rsp[1];
         bool csum_ok = pkt->csum_calc && !pkt->err_vec;
-        unsigned int len = be16_to_cpu(pkt->len);
         struct sge_eth_rxq *rxq = container_of(rspq, struct sge_eth_rxq, rspq);
 
         /*
@@ -1481,51 +1542,22 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
         }
 
         /*
-         * If the ingress packet is small enough, allocate an skb large enough
-         * for all of the data and copy it inline.  Otherwise, allocate an skb
-         * with enough room to pull in the header and reference the rest of
-         * the data via the skb fragment list.
+         * Convert the Packet Gather List into an skb.
          */
-        if (len <= RX_COPY_THRES) {
-                /* small packets have only one fragment */
-                skb = alloc_skb(gl->frags[0].size, GFP_ATOMIC);
-                if (!skb)
-                        goto nomem;
-                __skb_put(skb, gl->frags[0].size);
-                skb_copy_to_linear_data(skb, gl->va, gl->frags[0].size);
-        } else {
-                skb = alloc_skb(RX_PKT_PULL_LEN, GFP_ATOMIC);
-                if (!skb)
-                        goto nomem;
-                __skb_put(skb, RX_PKT_PULL_LEN);
-                skb_copy_to_linear_data(skb, gl->va, RX_PKT_PULL_LEN);
-
-                ssi = skb_shinfo(skb);
-                ssi->frags[0].page = gl->frags[0].page;
-                ssi->frags[0].page_offset = (gl->frags[0].page_offset +
-                                             RX_PKT_PULL_LEN);
-                ssi->frags[0].size = gl->frags[0].size - RX_PKT_PULL_LEN;
-                if (gl->nfrags > 1)
-                        memcpy(&ssi->frags[1], &gl->frags[1],
-                               (gl->nfrags-1) * sizeof(skb_frag_t));
-                ssi->nr_frags = gl->nfrags;
-                skb->len = len + PKTSHIFT;
-                skb->data_len = skb->len - RX_PKT_PULL_LEN;
-                skb->truesize += skb->data_len;
-
-                /* Get a reference for the last page, we don't own it */
-                get_page(gl->frags[gl->nfrags - 1].page);
+        skb = t4vf_pktgl_to_skb(gl, RX_SKB_LEN, RX_PULL_LEN);
+        if (unlikely(!skb)) {
+                t4vf_pktgl_free(gl);
+                rxq->stats.rx_drops++;
+                return 0;
         }
-
         __skb_pull(skb, PKTSHIFT);
         skb->protocol = eth_type_trans(skb, rspq->netdev);
         skb_record_rx_queue(skb, rspq->idx);
-        skb->dev->last_rx = jiffies;                  /* XXX removed 2.6.29 */
         pi = netdev_priv(skb->dev);
         rxq->stats.pkts++;
 
-        if (csum_ok && (pi->rx_offload & RX_CSO) && !pkt->err_vec &&
-            (be32_to_cpu(pkt->l2info) & (RXF_UDP|RXF_TCP))) {
+        if (csum_ok && (rspq->netdev->features & NETIF_F_RXCSUM) &&
+            !pkt->err_vec && (be32_to_cpu(pkt->l2info) & (RXF_UDP|RXF_TCP))) {
                 if (!pkt->ip_frag)
                         skb->ip_summed = CHECKSUM_UNNECESSARY;
                 else {
@@ -1535,8 +1567,11 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
                 }
                 rxq->stats.rx_cso++;
         } else
-                skb->ip_summed = CHECKSUM_NONE;
+                skb_checksum_none_assert(skb);
 
+        /*
+         * Deliver the packet to the stack.
+         */
         if (unlikely(pkt->vlan_ex)) {
                 struct vlan_group *grp = pi->vlan_grp;
 
@@ -1550,11 +1585,6 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
                 netif_receive_skb(skb);
 
         return 0;
-
-nomem:
-        t4vf_pktgl_free(gl);
-        rxq->stats.rx_drops++;
-        return 0;
 }
 
 /**
@@ -1680,6 +1710,7 @@ int process_responses(struct sge_rspq *rspq, int budget)
                                 }
                                 len = RSPD_LEN(len);
                         }
+                        gl.tot_len = len;
 
                         /*
                          * Gather packet fragments.
@@ -2116,7 +2147,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 
                 /*
                  * Calculate the size of the hardware free list ring plus
-                 * status page (which the SGE will place at the end of the
+                 * Status Page (which the SGE will place after the end of the
                  * free list ring) in Egress Queue Units.
                  */
                 flsz = (fl->size / FL_PER_EQ_UNIT +
@@ -2213,8 +2244,8 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq,
         struct port_info *pi = netdev_priv(dev);
 
         /*
-         * Calculate the size of the hardware TX Queue (including the
-         * status age on the end) in units of TX Descriptors.
+         * Calculate the size of the hardware TX Queue (including the Status
+         * Page on the end of the TX Queue) in units of TX Descriptors.
          */
         nentries = txq->q.size + STAT_LEN / sizeof(struct tx_desc);
 
diff --git a/drivers/net/cxgb4vf/t4vf_common.h b/drivers/net/cxgb4vf/t4vf_common.h
index 5c7bde7f9bae..a65c80aed1f2 100644
--- a/drivers/net/cxgb4vf/t4vf_common.h
+++ b/drivers/net/cxgb4vf/t4vf_common.h
@@ -132,15 +132,15 @@ struct rss_params {
         unsigned int mode;              /* RSS mode */
         union {
             struct {
-                int synmapen:1;         /* SYN Map Enable */
-                int syn4tupenipv6:1;    /* enable hashing 4-tuple IPv6 SYNs */
-                int syn2tupenipv6:1;    /* enable hashing 2-tuple IPv6 SYNs */
-                int syn4tupenipv4:1;    /* enable hashing 4-tuple IPv4 SYNs */
-                int syn2tupenipv4:1;    /* enable hashing 2-tuple IPv4 SYNs */
-                int ofdmapen:1;         /* Offload Map Enable */
-                int tnlmapen:1;         /* Tunnel Map Enable */
-                int tnlalllookup:1;     /* Tunnel All Lookup */
-                int hashtoeplitz:1;     /* use Toeplitz hash */
+                unsigned int synmapen:1;        /* SYN Map Enable */
+                unsigned int syn4tupenipv6:1;   /* enable hashing 4-tuple IPv6 SYNs */
+                unsigned int syn2tupenipv6:1;   /* enable hashing 2-tuple IPv6 SYNs */
+                unsigned int syn4tupenipv4:1;   /* enable hashing 4-tuple IPv4 SYNs */
+                unsigned int syn2tupenipv4:1;   /* enable hashing 2-tuple IPv4 SYNs */
+                unsigned int ofdmapen:1;        /* Offload Map Enable */
+                unsigned int tnlmapen:1;        /* Tunnel Map Enable */
+                unsigned int tnlalllookup:1;    /* Tunnel All Lookup */
+                unsigned int hashtoeplitz:1;    /* use Toeplitz hash */
             } basicvirtual;
         } u;
 };
@@ -151,10 +151,10 @@ struct rss_params {
 union rss_vi_config {
     struct {
         u16 defaultq;                   /* Ingress Queue ID for !tnlalllookup */
-        int ip6fourtupen:1;             /* hash 4-tuple IPv6 ingress packets */
-        int ip6twotupen:1;              /* hash 2-tuple IPv6 ingress packets */
-        int ip4fourtupen:1;             /* hash 4-tuple IPv4 ingress packets */
-        int ip4twotupen:1;              /* hash 2-tuple IPv4 ingress packets */
+        unsigned int ip6fourtupen:1;    /* hash 4-tuple IPv6 ingress packets */
+        unsigned int ip6twotupen:1;     /* hash 2-tuple IPv6 ingress packets */
+        unsigned int ip4fourtupen:1;    /* hash 4-tuple IPv4 ingress packets */
+        unsigned int ip4twotupen:1;     /* hash 2-tuple IPv4 ingress packets */
         int udpen;                      /* hash 4-tuple UDP ingress packets */
     } basicvirtual;
 };
@@ -235,6 +235,7 @@ static inline int t4vf_wr_mbox_ns(struct adapter *adapter, const void *cmd,
 int __devinit t4vf_wait_dev_ready(struct adapter *);
 int __devinit t4vf_port_init(struct adapter *, int);
 
+int t4vf_fw_reset(struct adapter *);
 int t4vf_query_params(struct adapter *, unsigned int, const u32 *, u32 *);
 int t4vf_set_params(struct adapter *, unsigned int, const u32 *, const u32 *);
 
diff --git a/drivers/net/cxgb4vf/t4vf_hw.c b/drivers/net/cxgb4vf/t4vf_hw.c
index ea1c123f0cb4..192db226ec7f 100644
--- a/drivers/net/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/cxgb4vf/t4vf_hw.c
@@ -116,7 +116,7 @@ static void dump_mbox(struct adapter *adapter, const char *tag, u32 mbox_data)
 int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
                       void *rpl, bool sleep_ok)
 {
-        static int delay[] = {
+        static const int delay[] = {
                 1, 1, 3, 5, 10, 10, 20, 50, 100
         };
 
@@ -147,9 +147,20 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
         /*
          * Write the command array into the Mailbox Data register array and
          * transfer ownership of the mailbox to the firmware.
+         *
+         * For the VFs, the Mailbox Data "registers" are actually backed by
+         * T4's "MA" interface rather than PL Registers (as is the case for
+         * the PFs).  Because these are in different coherency domains, the
+         * write to the VF's PL-register-backed Mailbox Control can race in
+         * front of the writes to the MA-backed VF Mailbox Data "registers".
+         * So we need to do a read-back on at least one byte of the VF Mailbox
+         * Data registers before doing the write to the VF Mailbox Control
+         * register.
          */
         for (i = 0, p = cmd; i < size; i += 8)
                 t4_write_reg64(adapter, mbox_data + i, be64_to_cpu(*p++));
+        t4_read_reg(adapter, mbox_data);         /* flush write */
+
         t4_write_reg(adapter, mbox_ctl,
                      MBMSGVALID | MBOWNER(MBOX_OWNER_FW));
         t4_read_reg(adapter, mbox_ctl);          /* flush write */
@@ -160,7 +171,7 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
         delay_idx = 0;
         ms = delay[0];
 
-        for (i = 0; i < 500; i += ms) {
+        for (i = 0; i < FW_CMD_MAX_TIMEOUT; i += ms) {
                 if (sleep_ok) {
                         ms = delay[delay_idx];
                         if (delay_idx < ARRAY_SIZE(delay) - 1)
@@ -326,6 +337,25 @@ int __devinit t4vf_port_init(struct adapter *adapter, int pidx)
 }
 
 /**
+ *      t4vf_fw_reset - issue a reset to FW
+ *      @adapter: the adapter
+ *
+ *      Issues a reset command to FW.  For a Physical Function this would
+ *      result in the Firmware reseting all of its state.  For a Virtual
+ *      Function this just resets the state associated with the VF.
+ */
+int t4vf_fw_reset(struct adapter *adapter)
+{
+        struct fw_reset_cmd cmd;
+
+        memset(&cmd, 0, sizeof(cmd));
+        cmd.op_to_write = cpu_to_be32(FW_CMD_OP(FW_RESET_CMD) |
+                                      FW_CMD_WRITE);
+        cmd.retval_len16 = cpu_to_be32(FW_LEN16(cmd));
+        return t4vf_wr_mbox(adapter, &cmd, sizeof(cmd), NULL);
+}
+
+/**
  *      t4vf_query_params - query FW or device parameters
  *      @adapter: the adapter
  *      @nparams: the number of parameters
@@ -995,48 +1025,72 @@ int t4vf_alloc_mac_filt(struct adapter *adapter, unsigned int viid, bool free,
                         unsigned int naddr, const u8 **addr, u16 *idx,
                         u64 *hash, bool sleep_ok)
 {
-        int i, ret;
+        int offset, ret = 0;
+        unsigned nfilters = 0;
+        unsigned int rem = naddr;
         struct fw_vi_mac_cmd cmd, rpl;
-        struct fw_vi_mac_exact *p;
-        size_t len16;
 
-        if (naddr > ARRAY_SIZE(cmd.u.exact))
+        if (naddr > FW_CLS_TCAM_NUM_ENTRIES)
                 return -EINVAL;
-        len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd,
-                                      u.exact[naddr]), 16);
 
-        memset(&cmd, 0, sizeof(cmd));
-        cmd.op_to_viid = cpu_to_be32(FW_CMD_OP(FW_VI_MAC_CMD) |
-                                     FW_CMD_REQUEST |
-                                     FW_CMD_WRITE |
-                                     (free ? FW_CMD_EXEC : 0) |
-                                     FW_VI_MAC_CMD_VIID(viid));
-        cmd.freemacs_to_len16 = cpu_to_be32(FW_VI_MAC_CMD_FREEMACS(free) |
-                                            FW_CMD_LEN16(len16));
+        for (offset = 0; offset < naddr; /**/) {
+                unsigned int fw_naddr = (rem < ARRAY_SIZE(cmd.u.exact)
+                                         ? rem
+                                         : ARRAY_SIZE(cmd.u.exact));
+                size_t len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd,
+                                                     u.exact[fw_naddr]), 16);
+                struct fw_vi_mac_exact *p;
+                int i;
+
+                memset(&cmd, 0, sizeof(cmd));
+                cmd.op_to_viid = cpu_to_be32(FW_CMD_OP(FW_VI_MAC_CMD) |
+                                             FW_CMD_REQUEST |
+                                             FW_CMD_WRITE |
+                                             (free ? FW_CMD_EXEC : 0) |
+                                             FW_VI_MAC_CMD_VIID(viid));
+                cmd.freemacs_to_len16 =
+                        cpu_to_be32(FW_VI_MAC_CMD_FREEMACS(free) |
+                                    FW_CMD_LEN16(len16));
+
+                for (i = 0, p = cmd.u.exact; i < fw_naddr; i++, p++) {
+                        p->valid_to_idx = cpu_to_be16(
+                                FW_VI_MAC_CMD_VALID |
+                                FW_VI_MAC_CMD_IDX(FW_VI_MAC_ADD_MAC));
+                        memcpy(p->macaddr, addr[offset+i], sizeof(p->macaddr));
+                }
 
-        for (i = 0, p = cmd.u.exact; i < naddr; i++, p++) {
-                p->valid_to_idx =
-                        cpu_to_be16(FW_VI_MAC_CMD_VALID |
-                                    FW_VI_MAC_CMD_IDX(FW_VI_MAC_ADD_MAC));
-                memcpy(p->macaddr, addr[i], sizeof(p->macaddr));
-        }
 
-        ret = t4vf_wr_mbox_core(adapter, &cmd, sizeof(cmd), &rpl, sleep_ok);
-        if (ret)
-                return ret;
-
-        for (i = 0, p = rpl.u.exact; i < naddr; i++, p++) {
-                u16 index = FW_VI_MAC_CMD_IDX_GET(be16_to_cpu(p->valid_to_idx));
-
-                if (idx)
-                        idx[i] = (index >= FW_CLS_TCAM_NUM_ENTRIES
-                                  ? 0xffff
-                                  : index);
-                if (index < FW_CLS_TCAM_NUM_ENTRIES)
-                        ret++;
-                else if (hash)
-                        *hash |= (1 << hash_mac_addr(addr[i]));
+                ret = t4vf_wr_mbox_core(adapter, &cmd, sizeof(cmd), &rpl,
+                                        sleep_ok);
+                if (ret && ret != -ENOMEM)
+                        break;
+
+                for (i = 0, p = rpl.u.exact; i < fw_naddr; i++, p++) {
+                        u16 index = FW_VI_MAC_CMD_IDX_GET(
+                                be16_to_cpu(p->valid_to_idx));
+
+                        if (idx)
+                                idx[offset+i] =
+                                        (index >= FW_CLS_TCAM_NUM_ENTRIES
+                                         ? 0xffff
+                                         : index);
+                        if (index < FW_CLS_TCAM_NUM_ENTRIES)
+                                nfilters++;
+                        else if (hash)
+                                *hash |= (1ULL << hash_mac_addr(addr[offset+i]));
+                }
+
+                free = false;
+                offset += fw_naddr;
+                rem -= fw_naddr;
         }
+
+        /*
+         * If there were no errors or we merely ran out of room in our MAC
+         * address arena, return the number of filters actually written.
+         */
+        if (ret == 0 || ret == -ENOMEM)
+                ret = nfilters;
         return ret;
 }
 
@@ -1257,7 +1311,7 @@ int t4vf_eth_eq_free(struct adapter *adapter, unsigned int eqid)
  */
 int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl)
 {
-        struct fw_cmd_hdr *cmd_hdr = (struct fw_cmd_hdr *)rpl;
+        const struct fw_cmd_hdr *cmd_hdr = (const struct fw_cmd_hdr *)rpl;
         u8 opcode = FW_CMD_OP_GET(be32_to_cpu(cmd_hdr->hi));
 
         switch (opcode) {
@@ -1265,7 +1319,8 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl)
                 /*
                  * Link/module state change message.
                  */
-                const struct fw_port_cmd *port_cmd = (void *)rpl;
+                const struct fw_port_cmd *port_cmd =
+                        (const struct fw_port_cmd *)rpl;
                 u32 word;
                 int action, port_id, link_ok, speed, fc, pidx;