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

Pull networking updates from David Miller:
 "Highlights:

   1) Support TX_RING in AF_PACKET TPACKET_V3 mode, from Sowmini
      Varadhan.

   2) Simplify classifier state on sk_buff in order to shrink it a bit.
      From Willem de Bruijn.

   3) Introduce SIPHASH and it's usage for secure sequence numbers and
      syncookies. From Jason A. Donenfeld.

   4) Reduce CPU usage for ICMP replies we are going to limit or
      suppress, from Jesper Dangaard Brouer.

   5) Introduce Shared Memory Communications socket layer, from Ursula
      Braun.

   6) Add RACK loss detection and allow it to actually trigger fast
      recovery instead of just assisting after other algorithms have
      triggered it. From Yuchung Cheng.

   7) Add xmit_more and BQL support to mvneta driver, from Simon Guinot.

   8) skb_cow_data avoidance in esp4 and esp6, from Steffen Klassert.

   9) Export MPLS packet stats via netlink, from Robert Shearman.

  10) Significantly improve inet port bind conflict handling, especially
      when an application is restarted and changes it's setting of
      reuseport. From Josef Bacik.

  11) Implement TX batching in vhost_net, from Jason Wang.

  12) Extend the dummy device so that VF (virtual function) features,
      such as configuration, can be more easily tested. From Phil
      Sutter.

  13) Avoid two atomic ops per page on x86 in bnx2x driver, from Eric
      Dumazet.

  14) Add new bpf MAP, implementing a longest prefix match trie. From
      Daniel Mack.

  15) Packet sample offloading support in mlxsw driver, from Yotam Gigi.

  16) Add new aquantia driver, from David VomLehn.

  17) Add bpf tracepoints, from Daniel Borkmann.

  18) Add support for port mirroring to b53 and bcm_sf2 drivers, from
      Florian Fainelli.

  19) Remove custom busy polling in many drivers, it is done in the core
      networking since 4.5 times. From Eric Dumazet.

  20) Support XDP adjust_head in virtio_net, from John Fastabend.

  21) Fix several major holes in neighbour entry confirmation, from
      Julian Anastasov.

  22) Add XDP support to bnxt_en driver, from Michael Chan.

  23) VXLAN offloads for enic driver, from Govindarajulu Varadarajan.

  24) Add IPVTAP driver (IP-VLAN based tap driver) from Sainath Grandhi.

  25) Support GRO in IPSEC protocols, from Steffen Klassert"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1764 commits)
  Revert "ath10k: Search SMBIOS for OEM board file extension"
  net: socket: fix recvmmsg not returning error from sock_error
  bnxt_en: use eth_hw_addr_random()
  bpf: fix unlocking of jited image when module ronx not set
  arch: add ARCH_HAS_SET_MEMORY config
  net: napi_watchdog() can use napi_schedule_irqoff()
  tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"
  net/hsr: use eth_hw_addr_random()
  net: mvpp2: enable building on 64-bit platforms
  net: mvpp2: switch to build_skb() in the RX path
  net: mvpp2: simplify MVPP2_PRS_RI_* definitions
  net: mvpp2: fix indentation of MVPP2_EXT_GLOBAL_CTRL_DEFAULT
  net: mvpp2: remove unused register definitions
  net: mvpp2: simplify mvpp2_bm_bufs_add()
  net: mvpp2: drop useless fields in mvpp2_bm_pool and related code
  net: mvpp2: remove unused 'tx_skb' field of 'struct mvpp2_tx_queue'
  net: mvpp2: release reference to txq_cpu[] entry after unmapping
  net: mvpp2: handle too large value in mvpp2_rx_time_coal_set()
  net: mvpp2: handle too large value handling in mvpp2_rx_pkts_coal_set()
  net: mvpp2: remove useless arguments in mvpp2_rx_{pkts, time}_coal_set
  ...

1 files changed, 187 insertions, 92 deletions

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 5a5dcad8c49a..334bcc6df6b2 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -23,12 +23,15 @@
 #include <linux/aer.h>
 #include <linux/interrupt.h>
 #include "net_driver.h"
+#include <net/gre.h>
+#include <net/udp_tunnel.h>
 #include "efx.h"
 #include "nic.h"
 #include "selftest.h"
 #include "sriov.h"
 
 #include "mcdi.h"
+#include "mcdi_pcol.h"
 #include "workarounds.h"
 
 /**************************************************************************
@@ -88,6 +91,21 @@ const char *const efx_reset_type_names[] = {
 	[RESET_TYPE_MCDI_TIMEOUT]	= "MCDI_TIMEOUT (FLR)",
 };
 
+/* UDP tunnel type names */
+static const char *const efx_udp_tunnel_type_names[] = {
+	[TUNNEL_ENCAP_UDP_PORT_ENTRY_VXLAN] = "vxlan",
+	[TUNNEL_ENCAP_UDP_PORT_ENTRY_GENEVE] = "geneve",
+};
+
+void efx_get_udp_tunnel_type_name(u16 type, char *buf, size_t buflen)
+{
+	if (type < ARRAY_SIZE(efx_udp_tunnel_type_names) &&
+	    efx_udp_tunnel_type_names[type] != NULL)
+		snprintf(buf, buflen, "%s", efx_udp_tunnel_type_names[type]);
+	else
+		snprintf(buf, buflen, "type %d", type);
+}
+
 /* Reset workqueue. If any NIC has a hardware failure then a reset will be
  * queued onto this work queue. This is not a per-nic work queue, because
  * efx_reset_work() acquires the rtnl lock, so resets are naturally serialised.
@@ -308,9 +326,6 @@ static int efx_poll(struct napi_struct *napi, int budget)
 	struct efx_nic *efx = channel->efx;
 	int spent;
 
-	if (!efx_channel_lock_napi(channel))
-		return budget;
-
 	netif_vdbg(efx, intr, efx->net_dev,
 		   "channel %d NAPI poll executing on CPU %d\n",
 		   channel->channel, raw_smp_processor_id());
@@ -331,11 +346,10 @@ static int efx_poll(struct napi_struct *napi, int budget)
 		 * since efx_nic_eventq_read_ack() will have no effect if
 		 * interrupts have already been disabled.
 		 */
-		napi_complete(napi);
-		efx_nic_eventq_read_ack(channel);
+		if (napi_complete_done(napi, spent))
+			efx_nic_eventq_read_ack(channel);
 	}
 
-	efx_channel_unlock_napi(channel);
 	return spent;
 }
 
@@ -391,7 +405,6 @@ void efx_start_eventq(struct efx_channel *channel)
 	channel->enabled = true;
 	smp_wmb();
 
-	efx_channel_enable(channel);
 	napi_enable(&channel->napi_str);
 	efx_nic_eventq_read_ack(channel);
 }
@@ -403,8 +416,6 @@ void efx_stop_eventq(struct efx_channel *channel)
 		return;
 
 	napi_disable(&channel->napi_str);
-	while (!efx_channel_disable(channel))
-		usleep_range(1000, 20000);
 	channel->enabled = false;
 }
 
@@ -865,7 +876,7 @@ out:
 		efx_schedule_reset(efx, RESET_TYPE_DISABLE);
 	} else {
 		efx_start_all(efx);
-		netif_device_attach(efx->net_dev);
+		efx_device_attach_if_not_resetting(efx);
 	}
 	return rc;
 
@@ -1409,9 +1420,12 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 					   xentries, 1, n_channels);
 		if (rc < 0) {
 			/* Fall back to single channel MSI */
-			efx->interrupt_mode = EFX_INT_MODE_MSI;
 			netif_err(efx, drv, efx->net_dev,
 				  "could not enable MSI-X\n");
+			if (efx->type->min_interrupt_mode >= EFX_INT_MODE_MSI)
+				efx->interrupt_mode = EFX_INT_MODE_MSI;
+			else
+				return rc;
 		} else if (rc < n_channels) {
 			netif_err(efx, drv, efx->net_dev,
 				  "WARNING: Insufficient MSI-X vectors"
@@ -1454,7 +1468,10 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 		} else {
 			netif_err(efx, drv, efx->net_dev,
 				  "could not enable MSI\n");
-			efx->interrupt_mode = EFX_INT_MODE_LEGACY;
+			if (efx->type->min_interrupt_mode >= EFX_INT_MODE_LEGACY)
+				efx->interrupt_mode = EFX_INT_MODE_LEGACY;
+			else
+				return rc;
 		}
 	}
 
@@ -2088,7 +2105,6 @@ static void efx_init_napi_channel(struct efx_channel *channel)
 	channel->napi_dev = efx->net_dev;
 	netif_napi_add(channel->napi_dev, &channel->napi_str,
 		       efx_poll, napi_weight);
-	efx_channel_busy_poll_init(channel);
 }
 
 static void efx_init_napi(struct efx_nic *efx)
@@ -2138,37 +2154,6 @@ static void efx_netpoll(struct net_device *net_dev)
 
 #endif
 
-#ifdef CONFIG_NET_RX_BUSY_POLL
-static int efx_busy_poll(struct napi_struct *napi)
-{
-	struct efx_channel *channel =
-		container_of(napi, struct efx_channel, napi_str);
-	struct efx_nic *efx = channel->efx;
-	int budget = 4;
-	int old_rx_packets, rx_packets;
-
-	if (!netif_running(efx->net_dev))
-		return LL_FLUSH_FAILED;
-
-	if (!efx_channel_try_lock_poll(channel))
-		return LL_FLUSH_BUSY;
-
-	old_rx_packets = channel->rx_queue.rx_packets;
-	efx_process_channel(channel, budget);
-
-	rx_packets = channel->rx_queue.rx_packets - old_rx_packets;
-
-	/* There is no race condition with NAPI here.
-	 * NAPI will automatically be rescheduled if it yielded during busy
-	 * polling, because it was not able to take the lock and thus returned
-	 * the full budget.
-	 */
-	efx_channel_unlock_poll(channel);
-
-	return rx_packets;
-}
-#endif
-
 /**************************************************************************
  *
  * Kernel net device interface
@@ -2197,6 +2182,8 @@ int efx_net_open(struct net_device *net_dev)
 	efx_link_status_changed(efx);
 
 	efx_start_all(efx);
+	if (efx->state == STATE_DISABLED || efx->reset_pending)
+		netif_device_detach(efx->net_dev);
 	efx_selftest_async_start(efx);
 	return 0;
 }
@@ -2219,16 +2206,14 @@ int efx_net_stop(struct net_device *net_dev)
 }
 
 /* Context: process, dev_base_lock or RTNL held, non-blocking. */
-static struct rtnl_link_stats64 *efx_net_stats(struct net_device *net_dev,
-					       struct rtnl_link_stats64 *stats)
+static void efx_net_stats(struct net_device *net_dev,
+			  struct rtnl_link_stats64 *stats)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
 	spin_lock_bh(&efx->stats_lock);
 	efx->type->update_stats(efx, NULL, stats);
 	spin_unlock_bh(&efx->stats_lock);
-
-	return stats;
 }
 
 /* Context: netif_tx_lock held, BHs disabled. */
@@ -2265,7 +2250,7 @@ static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
 	mutex_unlock(&efx->mac_lock);
 
 	efx_start_all(efx);
-	netif_device_attach(efx->net_dev);
+	efx_device_attach_if_not_resetting(efx);
 	return 0;
 }
 
@@ -2336,6 +2321,27 @@ static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
 	return 0;
 }
 
+static int efx_get_phys_port_id(struct net_device *net_dev,
+				struct netdev_phys_item_id *ppid)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->get_phys_port_id)
+		return efx->type->get_phys_port_id(efx, ppid);
+	else
+		return -EOPNOTSUPP;
+}
+
+static int efx_get_phys_port_name(struct net_device *net_dev,
+				  char *name, size_t len)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (snprintf(name, len, "p%u", efx->port_num) >= len)
+		return -EINVAL;
+	return 0;
+}
+
 static int efx_vlan_rx_add_vid(struct net_device *net_dev, __be16 proto, u16 vid)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
@@ -2356,6 +2362,52 @@ static int efx_vlan_rx_kill_vid(struct net_device *net_dev, __be16 proto, u16 vi
 		return -EOPNOTSUPP;
 }
 
+static int efx_udp_tunnel_type_map(enum udp_parsable_tunnel_type in)
+{
+	switch (in) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		return TUNNEL_ENCAP_UDP_PORT_ENTRY_VXLAN;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		return TUNNEL_ENCAP_UDP_PORT_ENTRY_GENEVE;
+	default:
+		return -1;
+	}
+}
+
+static void efx_udp_tunnel_add(struct net_device *dev, struct udp_tunnel_info *ti)
+{
+	struct efx_nic *efx = netdev_priv(dev);
+	struct efx_udp_tunnel tnl;
+	int efx_tunnel_type;
+
+	efx_tunnel_type = efx_udp_tunnel_type_map(ti->type);
+	if (efx_tunnel_type < 0)
+		return;
+
+	tnl.type = (u16)efx_tunnel_type;
+	tnl.port = ti->port;
+
+	if (efx->type->udp_tnl_add_port)
+		(void)efx->type->udp_tnl_add_port(efx, tnl);
+}
+
+static void efx_udp_tunnel_del(struct net_device *dev, struct udp_tunnel_info *ti)
+{
+	struct efx_nic *efx = netdev_priv(dev);
+	struct efx_udp_tunnel tnl;
+	int efx_tunnel_type;
+
+	efx_tunnel_type = efx_udp_tunnel_type_map(ti->type);
+	if (efx_tunnel_type < 0)
+		return;
+
+	tnl.type = (u16)efx_tunnel_type;
+	tnl.port = ti->port;
+
+	if (efx->type->udp_tnl_add_port)
+		(void)efx->type->udp_tnl_del_port(efx, tnl);
+}
+
 static const struct net_device_ops efx_netdev_ops = {
 	.ndo_open		= efx_net_open,
 	.ndo_stop		= efx_net_stop,
@@ -2376,18 +2428,18 @@ static const struct net_device_ops efx_netdev_ops = {
 	.ndo_set_vf_spoofchk	= efx_sriov_set_vf_spoofchk,
 	.ndo_get_vf_config	= efx_sriov_get_vf_config,
 	.ndo_set_vf_link_state  = efx_sriov_set_vf_link_state,
-	.ndo_get_phys_port_id   = efx_sriov_get_phys_port_id,
 #endif
+	.ndo_get_phys_port_id   = efx_get_phys_port_id,
+	.ndo_get_phys_port_name	= efx_get_phys_port_name,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = efx_netpoll,
 #endif
 	.ndo_setup_tc		= efx_setup_tc,
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	.ndo_busy_poll		= efx_busy_poll,
-#endif
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	= efx_filter_rfs,
 #endif
+	.ndo_udp_tunnel_add	= efx_udp_tunnel_add,
+	.ndo_udp_tunnel_del	= efx_udp_tunnel_del,
 };
 
 static void efx_update_name(struct efx_nic *efx)
@@ -2627,6 +2679,9 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 
 	efx_start_all(efx);
 
+	if (efx->type->udp_tnl_push_ports)
+		efx->type->udp_tnl_push_ports(efx);
+
 	return 0;
 
 fail:
@@ -2691,7 +2746,7 @@ out:
 		efx->state = STATE_DISABLED;
 	} else {
 		netif_dbg(efx, drv, efx->net_dev, "reset complete\n");
-		netif_device_attach(efx->net_dev);
+		efx_device_attach_if_not_resetting(efx);
 	}
 	return rc;
 }
@@ -2888,7 +2943,7 @@ static const struct efx_phy_operations efx_dummy_phy_operations = {
 static int efx_init_struct(struct efx_nic *efx,
 			   struct pci_dev *pci_dev, struct net_device *net_dev)
 {
-	int i;
+	int rc = -ENOMEM, i;
 
 	/* Initialise common structures */
 	INIT_LIST_HEAD(&efx->node);
@@ -2929,8 +2984,15 @@ static int efx_init_struct(struct efx_nic *efx,
 	}
 
 	/* Higher numbered interrupt modes are less capable! */
+	if (WARN_ON_ONCE(efx->type->max_interrupt_mode >
+			 efx->type->min_interrupt_mode)) {
+		rc = -EIO;
+		goto fail;
+	}
 	efx->interrupt_mode = max(efx->type->max_interrupt_mode,
 				  interrupt_mode);
+	efx->interrupt_mode = min(efx->type->min_interrupt_mode,
+				  interrupt_mode);
 
 	/* Would be good to use the net_dev name, but we're too early */
 	snprintf(efx->workqueue_name, sizeof(efx->workqueue_name), "sfc%s",
@@ -2943,7 +3005,7 @@ static int efx_init_struct(struct efx_nic *efx,
 
 fail:
 	efx_fini_struct(efx);
-	return -ENOMEM;
+	return rc;
 }
 
 static void efx_fini_struct(struct efx_nic *efx)
@@ -3158,6 +3220,51 @@ static int efx_pci_probe_main(struct efx_nic *efx)
 	return rc;
 }
 
+static int efx_pci_probe_post_io(struct efx_nic *efx)
+{
+	struct net_device *net_dev = efx->net_dev;
+	int rc = efx_pci_probe_main(efx);
+
+	if (rc)
+		return rc;
+
+	if (efx->type->sriov_init) {
+		rc = efx->type->sriov_init(efx);
+		if (rc)
+			netif_err(efx, probe, efx->net_dev,
+				  "SR-IOV can't be enabled rc %d\n", rc);
+	}
+
+	/* Determine netdevice features */
+	net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
+			      NETIF_F_TSO | NETIF_F_RXCSUM);
+	if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
+		net_dev->features |= NETIF_F_TSO6;
+	/* Check whether device supports TSO */
+	if (!efx->type->tso_versions || !efx->type->tso_versions(efx))
+		net_dev->features &= ~NETIF_F_ALL_TSO;
+	/* Mask for features that also apply to VLAN devices */
+	net_dev->vlan_features |= (NETIF_F_HW_CSUM | NETIF_F_SG |
+				   NETIF_F_HIGHDMA | NETIF_F_ALL_TSO |
+				   NETIF_F_RXCSUM);
+
+	net_dev->hw_features = net_dev->features & ~efx->fixed_features;
+
+	/* Disable VLAN filtering by default.  It may be enforced if
+	 * the feature is fixed (i.e. VLAN filters are required to
+	 * receive VLAN tagged packets due to vPort restrictions).
+	 */
+	net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+	net_dev->features |= efx->fixed_features;
+
+	rc = efx_register_netdev(efx);
+	if (!rc)
+		return 0;
+
+	efx_pci_remove_main(efx);
+	return rc;
+}
+
 /* NIC initialisation
  *
  * This is called at module load (or hotplug insertion,
@@ -3200,42 +3307,28 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	if (rc)
 		goto fail2;
 
-	rc = efx_pci_probe_main(efx);
+	rc = efx_pci_probe_post_io(efx);
+	if (rc) {
+		/* On failure, retry once immediately.
+		 * If we aborted probe due to a scheduled reset, dismiss it.
+		 */
+		efx->reset_pending = 0;
+		rc = efx_pci_probe_post_io(efx);
+		if (rc) {
+			/* On another failure, retry once more
+			 * after a 50-305ms delay.
+			 */
+			unsigned char r;
+
+			get_random_bytes(&r, 1);
+			msleep((unsigned int)r + 50);
+			efx->reset_pending = 0;
+			rc = efx_pci_probe_post_io(efx);
+		}
+	}
 	if (rc)
 		goto fail3;
 
-	net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
-			      NETIF_F_TSO | NETIF_F_RXCSUM);
-	if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
-		net_dev->features |= NETIF_F_TSO6;
-	/* Check whether device supports TSO */
-	if (!efx->type->tso_versions || !efx->type->tso_versions(efx))
-		net_dev->features &= ~NETIF_F_ALL_TSO;
-	/* Mask for features that also apply to VLAN devices */
-	net_dev->vlan_features |= (NETIF_F_HW_CSUM | NETIF_F_SG |
-				   NETIF_F_HIGHDMA | NETIF_F_ALL_TSO |
-				   NETIF_F_RXCSUM);
-
-	net_dev->hw_features = net_dev->features & ~efx->fixed_features;
-
-	/* Disable VLAN filtering by default.  It may be enforced if
-	 * the feature is fixed (i.e. VLAN filters are required to
-	 * receive VLAN tagged packets due to vPort restrictions).
-	 */
-	net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
-	net_dev->features |= efx->fixed_features;
-
-	rc = efx_register_netdev(efx);
-	if (rc)
-		goto fail4;
-
-	if (efx->type->sriov_init) {
-		rc = efx->type->sriov_init(efx);
-		if (rc)
-			netif_err(efx, probe, efx->net_dev,
-				  "SR-IOV can't be enabled rc %d\n", rc);
-	}
-
 	netif_dbg(efx, probe, efx->net_dev, "initialisation successful\n");
 
 	/* Try to create MTDs, but allow this to fail */
@@ -3252,10 +3345,11 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 			     "PCIE error reporting unavailable (%d).\n",
 			     rc);
 
+	if (efx->type->udp_tnl_push_ports)
+		efx->type->udp_tnl_push_ports(efx);
+
 	return 0;
 
- fail4:
-	efx_pci_remove_main(efx);
  fail3:
 	efx_fini_io(efx);
  fail2:
@@ -3325,7 +3419,7 @@ static int efx_pm_thaw(struct device *dev)
 
 		efx_start_all(efx);
 
-		netif_device_attach(efx->net_dev);
+		efx_device_attach_if_not_resetting(efx);
 
 		efx->state = STATE_READY;
 
@@ -3585,3 +3679,4 @@ MODULE_AUTHOR("Solarflare Communications and "
 MODULE_DESCRIPTION("Solarflare network driver");
 MODULE_LICENSE("GPL");
 MODULE_DEVICE_TABLE(pci, efx_pci_table);
+MODULE_VERSION(EFX_DRIVER_VERSION);