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

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 84 insertions, 32 deletions

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 7c213a347909..1825d956bb00 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -520,7 +520,7 @@ static void i40evf_irq_affinity_notify(struct irq_affinity_notify *notify,
 	struct i40e_q_vector *q_vector =
 		container_of(notify, struct i40e_q_vector, affinity_notify);
 
-	q_vector->affinity_mask = *mask;
+	cpumask_copy(&q_vector->affinity_mask, mask);
 }
 
 /**
@@ -543,9 +543,9 @@ static void i40evf_irq_affinity_release(struct kref *ref) {}
 static int
 i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 {
-	int vector, err, q_vectors;
-	int rx_int_idx = 0, tx_int_idx = 0;
-	int irq_num;
+	unsigned int vector, q_vectors;
+	unsigned int rx_int_idx = 0, tx_int_idx = 0;
+	int irq_num, err;
 
 	i40evf_irq_disable(adapter);
 	/* Decrement for Other and TCP Timer vectors */
@@ -556,18 +556,15 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 		irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
 
 		if (q_vector->tx.ring && q_vector->rx.ring) {
-			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
-				 "i40evf-%s-%s-%d", basename,
-				 "TxRx", rx_int_idx++);
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "i40evf-%s-TxRx-%d", basename, rx_int_idx++);
 			tx_int_idx++;
 		} else if (q_vector->rx.ring) {
-			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
-				 "i40evf-%s-%s-%d", basename,
-				 "rx", rx_int_idx++);
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "i40evf-%s-rx-%d", basename, rx_int_idx++);
 		} else if (q_vector->tx.ring) {
-			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
-				 "i40evf-%s-%s-%d", basename,
-				 "tx", tx_int_idx++);
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "i40evf-%s-tx-%d", basename, tx_int_idx++);
 		} else {
 			/* skip this unused q_vector */
 			continue;
@@ -587,8 +584,10 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 		q_vector->affinity_notify.release =
 						   i40evf_irq_affinity_release;
 		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
-		/* assign the mask for this irq */
-		irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
+		/* get_cpu_mask returns a static constant mask with
+		 * a permanent lifetime so it's ok to use here.
+		 */
+		irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx));
 	}
 
 	return 0;
@@ -1143,6 +1142,7 @@ void i40evf_down(struct i40evf_adapter *adapter)
 	}
 
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
 }
 
 /**
@@ -1241,7 +1241,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		tx_ring->dev = &adapter->pdev->dev;
 		tx_ring->count = adapter->tx_desc_count;
 		tx_ring->tx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF);
-		if (adapter->flags & I40E_FLAG_WB_ON_ITR_CAPABLE)
+		if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE)
 			tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR;
 
 		rx_ring = &adapter->rx_rings[i];
@@ -1417,7 +1417,7 @@ static int i40evf_init_rss(struct i40evf_adapter *adapter)
 
 	if (!RSS_PF(adapter)) {
 		/* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */
-		if (adapter->vf_res->vf_offload_flags &
+		if (adapter->vf_res->vf_cap_flags &
 		    VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
 			adapter->hena = I40E_DEFAULT_RSS_HENA_EXPANDED;
 		else
@@ -1458,6 +1458,7 @@ static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter)
 		q_vector->adapter = adapter;
 		q_vector->vsi = &adapter->vsi;
 		q_vector->v_idx = q_idx;
+		cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask);
 		netif_napi_add(adapter->netdev, &q_vector->napi,
 			       i40evf_napi_poll, NAPI_POLL_WEIGHT);
 	}
@@ -1678,6 +1679,16 @@ static void i40evf_watchdog_task(struct work_struct *work)
 		goto watchdog_done;
 	}
 
+	if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) {
+		i40evf_enable_vlan_stripping(adapter);
+		goto watchdog_done;
+	}
+
+	if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) {
+		i40evf_disable_vlan_stripping(adapter);
+		goto watchdog_done;
+	}
+
 	if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_QUEUES) {
 		i40evf_configure_queues(adapter);
 		goto watchdog_done;
@@ -1794,6 +1805,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter)
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
 	adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
 	adapter->state = __I40EVF_DOWN;
+	wake_up(&adapter->down_waitqueue);
 	dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n");
 }
 
@@ -1877,7 +1889,7 @@ static void i40evf_reset_task(struct work_struct *work)
 	}
 
 continue_reset:
-	if (netif_running(adapter->netdev)) {
+	if (netif_running(netdev)) {
 		netif_carrier_off(netdev);
 		netif_tx_stop_all_queues(netdev);
 		adapter->link_up = false;
@@ -1939,12 +1951,13 @@ continue_reset:
 		i40evf_irq_enable(adapter, true);
 	} else {
 		adapter->state = __I40EVF_DOWN;
+		wake_up(&adapter->down_waitqueue);
 	}
 
 	return;
 reset_err:
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
-	i40evf_close(adapter->netdev);
+	i40evf_close(netdev);
 }
 
 /**
@@ -1957,8 +1970,8 @@ static void i40evf_adminq_task(struct work_struct *work)
 		container_of(work, struct i40evf_adapter, adminq_task);
 	struct i40e_hw *hw = &adapter->hw;
 	struct i40e_arq_event_info event;
-	struct virtchnl_msg *v_msg;
-	i40e_status ret;
+	enum virtchnl_ops v_op;
+	i40e_status ret, v_ret;
 	u32 val, oldval;
 	u16 pending;
 
@@ -1970,15 +1983,15 @@ static void i40evf_adminq_task(struct work_struct *work)
 	if (!event.msg_buf)
 		goto out;
 
-	v_msg = (struct virtchnl_msg *)&event.desc;
 	do {
 		ret = i40evf_clean_arq_element(hw, &event, &pending);
-		if (ret || !v_msg->v_opcode)
+		v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high);
+		v_ret = (i40e_status)le32_to_cpu(event.desc.cookie_low);
+
+		if (ret || !v_op)
 			break; /* No event to process or error cleaning ARQ */
 
-		i40evf_virtchnl_completion(adapter, v_msg->v_opcode,
-					   (i40e_status)v_msg->v_retval,
-					   event.msg_buf,
+		i40evf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf,
 					   event.msg_len);
 		if (pending != 0)
 			memset(event.msg_buf, 0, I40EVF_MAX_AQ_BUF_SIZE);
@@ -2238,6 +2251,7 @@ err_setup_tx:
 static int i40evf_close(struct net_device *netdev)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	int status;
 
 	if (adapter->state <= __I40EVF_DOWN_PENDING)
 		return 0;
@@ -2255,7 +2269,18 @@ static int i40evf_close(struct net_device *netdev)
 	 * still active and can DMA into memory. Resources are cleared in
 	 * i40evf_virtchnl_completion() after we get confirmation from the PF
 	 * driver that the rings have been stopped.
+	 *
+	 * Also, we wait for state to transition to __I40EVF_DOWN before
+	 * returning. State change occurs in i40evf_virtchnl_completion() after
+	 * VF resources are released (which occurs after PF driver processes and
+	 * responds to admin queue commands).
 	 */
+
+	status = wait_event_timeout(adapter->down_waitqueue,
+				    adapter->state == __I40EVF_DOWN,
+				    msecs_to_jiffies(200));
+	if (!status)
+		netdev_warn(netdev, "Device resources not yet released\n");
 	return 0;
 }
 
@@ -2282,6 +2307,28 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu)
 }
 
 /**
+ * i40e_set_features - set the netdev feature flags
+ * @netdev: ptr to the netdev being adjusted
+ * @features: the feature set that the stack is suggesting
+ * Note: expects to be called while under rtnl_lock()
+ **/
+static int i40evf_set_features(struct net_device *netdev,
+			       netdev_features_t features)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+
+	if (!VLAN_ALLOWED(adapter))
+		return -EINVAL;
+
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING;
+	else
+		adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING;
+
+	return 0;
+}
+
+/**
  * i40evf_features_check - Validate encapsulated packet conforms to limits
  * @skb: skb buff
  * @netdev: This physical port's netdev
@@ -2356,7 +2403,7 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev,
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	features &= ~I40EVF_VLAN_FEATURES;
-	if (adapter->vf_res->vf_offload_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+	if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
 		features |= I40EVF_VLAN_FEATURES;
 	return features;
 }
@@ -2374,6 +2421,7 @@ static const struct net_device_ops i40evf_netdev_ops = {
 	.ndo_vlan_rx_kill_vid	= i40evf_vlan_rx_kill_vid,
 	.ndo_features_check	= i40evf_features_check,
 	.ndo_fix_features	= i40evf_fix_features,
+	.ndo_set_features	= i40evf_set_features,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= i40evf_netpoll,
 #endif
@@ -2443,7 +2491,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 	/* advertise to stack only if offloads for encapsulated packets is
 	 * supported
 	 */
-	if (vfres->vf_offload_flags & VIRTCHNL_VF_OFFLOAD_ENCAP) {
+	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ENCAP) {
 		hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL	|
 				   NETIF_F_GSO_GRE		|
 				   NETIF_F_GSO_GRE_CSUM		|
@@ -2453,7 +2501,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 				   NETIF_F_GSO_PARTIAL		|
 				   0;
 
-		if (!(vfres->vf_offload_flags &
+		if (!(vfres->vf_cap_flags &
 		      VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM))
 			netdev->gso_partial_features |=
 				NETIF_F_GSO_UDP_TUNNEL_CSUM;
@@ -2481,7 +2529,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 	adapter->vsi.work_limit = I40E_DEFAULT_IRQ_WORK;
 	vsi->netdev = adapter->netdev;
 	vsi->qs_handle = adapter->vsi_res->qset_handle;
-	if (vfres->vf_offload_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
+	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
 		adapter->rss_key_size = vfres->rss_key_size;
 		adapter->rss_lut_size = vfres->rss_lut_size;
 	} else {
@@ -2625,7 +2673,7 @@ static void i40evf_init_task(struct work_struct *work)
 
 	/* MTU range: 68 - 9710 */
 	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = I40E_MAX_RXBUFFER - (ETH_HLEN + ETH_FCS_LEN);
+	netdev->max_mtu = I40E_MAX_RXBUFFER - I40E_PACKET_HDR_PAD;
 
 	if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
 		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
@@ -2649,7 +2697,7 @@ static void i40evf_init_task(struct work_struct *work)
 	if (err)
 		goto err_sw_init;
 	i40evf_map_rings_to_vectors(adapter);
-	if (adapter->vf_res->vf_offload_flags &
+	if (adapter->vf_res->vf_cap_flags &
 	    VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
 		adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE;
 
@@ -2683,6 +2731,7 @@ static void i40evf_init_task(struct work_struct *work)
 	adapter->state = __I40EVF_DOWN;
 	set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
 	i40evf_misc_irq_enable(adapter);
+	wake_up(&adapter->down_waitqueue);
 
 	adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL);
 	adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL);
@@ -2844,6 +2893,9 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	schedule_delayed_work(&adapter->init_task,
 			      msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
 
+	/* Setup the wait queue for indicating transition to down status */
+	init_waitqueue_head(&adapter->down_waitqueue);
+
 	return 0;
 
 err_ioremap: