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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 127 insertions, 66 deletions

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 1825d956bb00..ca2ebdbd24d7 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -46,7 +46,7 @@ static const char i40evf_driver_string[] =
 
 #define DRV_VERSION_MAJOR 3
 #define DRV_VERSION_MINOR 0
-#define DRV_VERSION_BUILD 0
+#define DRV_VERSION_BUILD 1
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD) \
@@ -430,57 +430,26 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx)
  * group the rings as "efficiently" as possible.  You would add new
  * mapping configurations in here.
  **/
-static int i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter)
+static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter)
 {
+	int rings_remaining = adapter->num_active_queues;
+	int ridx = 0, vidx = 0;
 	int q_vectors;
-	int v_start = 0;
-	int rxr_idx = 0, txr_idx = 0;
-	int rxr_remaining = adapter->num_active_queues;
-	int txr_remaining = adapter->num_active_queues;
-	int i, j;
-	int rqpv, tqpv;
-	int err = 0;
 
 	q_vectors = adapter->num_msix_vectors - NONQ_VECS;
 
-	/* The ideal configuration...
-	 * We have enough vectors to map one per queue.
-	 */
-	if (q_vectors >= (rxr_remaining * 2)) {
-		for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++)
-			i40evf_map_vector_to_rxq(adapter, v_start, rxr_idx);
-
-		for (; txr_idx < txr_remaining; v_start++, txr_idx++)
-			i40evf_map_vector_to_txq(adapter, v_start, txr_idx);
-		goto out;
-	}
+	for (; ridx < rings_remaining; ridx++) {
+		i40evf_map_vector_to_rxq(adapter, vidx, ridx);
+		i40evf_map_vector_to_txq(adapter, vidx, ridx);
 
-	/* If we don't have enough vectors for a 1-to-1
-	 * mapping, we'll have to group them so there are
-	 * multiple queues per vector.
-	 * Re-adjusting *qpv takes care of the remainder.
-	 */
-	for (i = v_start; i < q_vectors; i++) {
-		rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i);
-		for (j = 0; j < rqpv; j++) {
-			i40evf_map_vector_to_rxq(adapter, i, rxr_idx);
-			rxr_idx++;
-			rxr_remaining--;
-		}
-	}
-	for (i = v_start; i < q_vectors; i++) {
-		tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i);
-		for (j = 0; j < tqpv; j++) {
-			i40evf_map_vector_to_txq(adapter, i, txr_idx);
-			txr_idx++;
-			txr_remaining--;
-		}
+		/* In the case where we have more queues than vectors, continue
+		 * round-robin on vectors until all queues are mapped.
+		 */
+		if (++vidx >= q_vectors)
+			vidx = 0;
 	}
 
-out:
 	adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS;
-
-	return err;
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -546,6 +515,7 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 	unsigned int vector, q_vectors;
 	unsigned int rx_int_idx = 0, tx_int_idx = 0;
 	int irq_num, err;
+	int cpu;
 
 	i40evf_irq_disable(adapter);
 	/* Decrement for Other and TCP Timer vectors */
@@ -584,10 +554,12 @@ 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);
-		/* get_cpu_mask returns a static constant mask with
-		 * a permanent lifetime so it's ok to use here.
+		/* Spread the IRQ affinity hints across online CPUs. Note that
+		 * get_cpu_mask returns a mask with a permanent lifetime so
+		 * it's safe to use as a hint for irq_set_affinity_hint.
 		 */
-		irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx));
+		cpu = cpumask_local_spread(q_vector->v_idx, -1);
+		irq_set_affinity_hint(irq_num, get_cpu_mask(cpu));
 	}
 
 	return 0;
@@ -908,6 +880,8 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter,
 		list_add_tail(&f->list, &adapter->mac_filter_list);
 		f->add = true;
 		adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
+	} else {
+		f->remove = false;
 	}
 
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
@@ -1217,9 +1191,18 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 {
 	int i, num_active_queues;
 
-	num_active_queues = min_t(int,
-				  adapter->vsi_res->num_queue_pairs,
-				  (int)(num_online_cpus()));
+	/* If we're in reset reallocating queues we don't actually know yet for
+	 * certain the PF gave us the number of queues we asked for but we'll
+	 * assume it did.  Once basic reset is finished we'll confirm once we
+	 * start negotiating config with PF.
+	 */
+	if (adapter->num_req_queues)
+		num_active_queues = adapter->num_req_queues;
+	else
+		num_active_queues = min_t(int,
+					  adapter->vsi_res->num_queue_pairs,
+					  (int)(num_online_cpus()));
+
 
 	adapter->tx_rings = kcalloc(num_active_queues,
 				    sizeof(struct i40e_ring), GFP_KERNEL);
@@ -1240,7 +1223,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		tx_ring->netdev = adapter->netdev;
 		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);
+		tx_ring->tx_itr_setting = I40E_ITR_TX_DEF;
 		if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE)
 			tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR;
 
@@ -1249,7 +1232,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		rx_ring->netdev = adapter->netdev;
 		rx_ring->dev = &adapter->pdev->dev;
 		rx_ring->count = adapter->rx_desc_count;
-		rx_ring->rx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF);
+		rx_ring->rx_itr_setting = I40E_ITR_RX_DEF;
 	}
 
 	adapter->num_active_queues = num_active_queues;
@@ -1568,12 +1551,53 @@ static void i40evf_free_rss(struct i40evf_adapter *adapter)
 }
 
 /**
+ * i40evf_reinit_interrupt_scheme - Reallocate queues and vectors
+ * @adapter: board private structure
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	int err;
+
+	if (netif_running(netdev))
+		i40evf_free_traffic_irqs(adapter);
+	i40evf_free_misc_irq(adapter);
+	i40evf_reset_interrupt_capability(adapter);
+	i40evf_free_q_vectors(adapter);
+	i40evf_free_queues(adapter);
+
+	err =  i40evf_init_interrupt_scheme(adapter);
+	if (err)
+		goto err;
+
+	netif_tx_stop_all_queues(netdev);
+
+	err = i40evf_request_misc_irq(adapter);
+	if (err)
+		goto err;
+
+	set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
+
+	i40evf_map_rings_to_vectors(adapter);
+
+	if (RSS_AQ(adapter))
+		adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS;
+	else
+		err = i40evf_init_rss(adapter);
+err:
+	return err;
+}
+
+/**
  * i40evf_watchdog_timer - Periodic call-back timer
  * @data: pointer to adapter disguised as unsigned long
  **/
-static void i40evf_watchdog_timer(unsigned long data)
+static void i40evf_watchdog_timer(struct timer_list *t)
 {
-	struct i40evf_adapter *adapter = (struct i40evf_adapter *)data;
+	struct i40evf_adapter *adapter = from_timer(adapter, t,
+						    watchdog_timer);
 
 	schedule_work(&adapter->watchdog_task);
 	/* timer will be rescheduled in watchdog task */
@@ -1913,8 +1937,15 @@ continue_reset:
 	if (err)
 		dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n",
 			 err);
+	adapter->aq_required = 0;
 
-	adapter->aq_required = I40EVF_FLAG_AQ_GET_CONFIG;
+	if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) {
+		err = i40evf_reinit_interrupt_scheme(adapter);
+		if (err)
+			goto reset_err;
+	}
+
+	adapter->aq_required |= I40EVF_FLAG_AQ_GET_CONFIG;
 	adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS;
 
 	/* re-add all MAC filters */
@@ -1944,6 +1975,15 @@ continue_reset:
 		if (err)
 			goto reset_err;
 
+		if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) {
+			err = i40evf_request_traffic_irqs(adapter,
+							  netdev->name);
+			if (err)
+				goto reset_err;
+
+			adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED;
+		}
+
 		i40evf_configure(adapter);
 
 		i40evf_up_complete(adapter);
@@ -2386,10 +2426,6 @@ out_err:
 	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 }
 
-#define I40EVF_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_TX |\
-			      NETIF_F_HW_VLAN_CTAG_RX |\
-			      NETIF_F_HW_VLAN_CTAG_FILTER)
-
 /**
  * i40evf_fix_features - fix up the netdev feature bits
  * @netdev: our net device
@@ -2402,9 +2438,11 @@ 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_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
-		features |= I40EVF_VLAN_FEATURES;
+	if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
+		features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
+			      NETIF_F_HW_VLAN_CTAG_RX |
+			      NETIF_F_HW_VLAN_CTAG_FILTER);
+
 	return features;
 }
 
@@ -2459,9 +2497,9 @@ static int i40evf_check_reset_complete(struct i40e_hw *hw)
 int i40evf_process_config(struct i40evf_adapter *adapter)
 {
 	struct virtchnl_vf_resource *vfres = adapter->vf_res;
+	int i, num_req_queues = adapter->num_req_queues;
 	struct net_device *netdev = adapter->netdev;
 	struct i40e_vsi *vsi = &adapter->vsi;
-	int i;
 	netdev_features_t hw_enc_features;
 	netdev_features_t hw_features;
 
@@ -2475,6 +2513,23 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 		return -ENODEV;
 	}
 
+	if (num_req_queues &&
+	    num_req_queues != adapter->vsi_res->num_queue_pairs) {
+		/* Problem.  The PF gave us fewer queues than what we had
+		 * negotiated in our request.  Need a reset to see if we can't
+		 * get back to a working state.
+		 */
+		dev_err(&adapter->pdev->dev,
+			"Requested %d queues, but PF only gave us %d.\n",
+			num_req_queues,
+			adapter->vsi_res->num_queue_pairs);
+		adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED;
+		adapter->num_req_queues = adapter->vsi_res->num_queue_pairs;
+		i40evf_schedule_reset(adapter);
+		return -ENODEV;
+	}
+	adapter->num_req_queues = 0;
+
 	hw_enc_features = NETIF_F_SG			|
 			  NETIF_F_IP_CSUM		|
 			  NETIF_F_IPV6_CSUM		|
@@ -2518,9 +2573,17 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 	 */
 	hw_features = hw_enc_features;
 
+	/* Enable VLAN features if supported */
+	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+		hw_features |= (NETIF_F_HW_VLAN_CTAG_TX |
+				NETIF_F_HW_VLAN_CTAG_RX);
+
 	netdev->hw_features |= hw_features;
 
-	netdev->features |= hw_features | I40EVF_VLAN_FEATURES;
+	netdev->features |= hw_features;
+
+	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+		netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	adapter->vsi.id = adapter->vsi_res->vsi_id;
 
@@ -2686,9 +2749,7 @@ static void i40evf_init_task(struct work_struct *work)
 		ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
 	}
 
-	init_timer(&adapter->watchdog_timer);
-	adapter->watchdog_timer.function = &i40evf_watchdog_timer;
-	adapter->watchdog_timer.data = (unsigned long)adapter;
+	timer_setup(&adapter->watchdog_timer, i40evf_watchdog_timer, 0);
 	mod_timer(&adapter->watchdog_timer, jiffies + 1);
 
 	adapter->tx_desc_count = I40EVF_DEFAULT_TXD;