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

Pull networking updates from David Miller:

 1) BPF debugger and asm tool by Daniel Borkmann.

 2) Speed up create/bind in AF_PACKET, also from Daniel Borkmann.

 3) Correct reciprocal_divide and update users, from Hannes Frederic
    Sowa and Daniel Borkmann.

 4) Currently we only have a "set" operation for the hw timestamp socket
    ioctl, add a "get" operation to match.  From Ben Hutchings.

 5) Add better trace events for debugging driver datapath problems, also
    from Ben Hutchings.

 6) Implement auto corking in TCP, from Eric Dumazet.  Basically, if we
    have a small send and a previous packet is already in the qdisc or
    device queue, defer until TX completion or we get more data.

 7) Allow userspace to manage ipv6 temporary addresses, from Jiri Pirko.

 8) Add a qdisc bypass option for AF_PACKET sockets, from Daniel
    Borkmann.

 9) Share IP header compression code between Bluetooth and IEEE802154
    layers, from Jukka Rissanen.

10) Fix ipv6 router reachability probing, from Jiri Benc.

11) Allow packets to be captured on macvtap devices, from Vlad Yasevich.

12) Support tunneling in GRO layer, from Jerry Chu.

13) Allow bonding to be configured fully using netlink, from Scott
    Feldman.

14) Allow AF_PACKET users to obtain the VLAN TPID, just like they can
    already get the TCI.  From Atzm Watanabe.

15) New "Heavy Hitter" qdisc, from Terry Lam.

16) Significantly improve the IPSEC support in pktgen, from Fan Du.

17) Allow ipv4 tunnels to cache routes, just like sockets.  From Tom
    Herbert.

18) Add Proportional Integral Enhanced packet scheduler, from Vijay
    Subramanian.

19) Allow openvswitch to mmap'd netlink, from Thomas Graf.

20) Key TCP metrics blobs also by source address, not just destination
    address.  From Christoph Paasch.

21) Support 10G in generic phylib.  From Andy Fleming.

22) Try to short-circuit GRO flow compares using device provided RX
    hash, if provided.  From Tom Herbert.

The wireless and netfilter folks have been busy little bees too.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2064 commits)
  net/cxgb4: Fix referencing freed adapter
  ipv6: reallocate addrconf router for ipv6 address when lo device up
  fib_frontend: fix possible NULL pointer dereference
  rtnetlink: remove IFLA_BOND_SLAVE definition
  rtnetlink: remove check for fill_slave_info in rtnl_have_link_slave_info
  qlcnic: update version to 5.3.55
  qlcnic: Enhance logic to calculate msix vectors.
  qlcnic: Refactor interrupt coalescing code for all adapters.
  qlcnic: Update poll controller code path
  qlcnic: Interrupt code cleanup
  qlcnic: Enhance Tx timeout debugging.
  qlcnic: Use bool for rx_mac_learn.
  bonding: fix u64 division
  rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC
  sfc: Use the correct maximum TX DMA ring size for SFC9100
  Add Shradha Shah as the sfc driver maintainer.
  net/vxlan: Share RX skb de-marking and checksum checks with ovs
  tulip: cleanup by using ARRAY_SIZE()
  ip_tunnel: clear IPCB in ip_tunnel_xmit() in case dst_link_failure() is called
  net/cxgb4: Don't retrieve stats during recovery
  ...

1 files changed, 170 insertions, 31 deletions

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index fd844b53e38..83d46434702 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -83,6 +83,7 @@ const char *const efx_reset_type_names[] = {
 	[RESET_TYPE_DMA_ERROR]          = "DMA_ERROR",
 	[RESET_TYPE_TX_SKIP]            = "TX_SKIP",
 	[RESET_TYPE_MC_FAILURE]         = "MC_FAILURE",
+	[RESET_TYPE_MC_BIST]		= "MC_BIST",
 };
 
 /* Reset workqueue. If any NIC has a hardware failure then a reset will be
@@ -91,6 +92,12 @@ const char *const efx_reset_type_names[] = {
  */
 static struct workqueue_struct *reset_workqueue;
 
+/* How often and how many times to poll for a reset while waiting for a
+ * BIST that another function started to complete.
+ */
+#define BIST_WAIT_DELAY_MS	100
+#define BIST_WAIT_DELAY_COUNT	100
+
 /**************************************************************************
  *
  * Configurable values
@@ -246,7 +253,7 @@ static int efx_process_channel(struct efx_channel *channel, int budget)
 			efx_channel_get_rx_queue(channel);
 
 		efx_rx_flush_packet(channel);
-		efx_fast_push_rx_descriptors(rx_queue);
+		efx_fast_push_rx_descriptors(rx_queue, true);
 	}
 
 	return spent;
@@ -639,7 +646,9 @@ static void efx_start_datapath(struct efx_nic *efx)
 		efx_for_each_channel_rx_queue(rx_queue, channel) {
 			efx_init_rx_queue(rx_queue);
 			atomic_inc(&efx->active_queues);
-			efx_nic_generate_fill_event(rx_queue);
+			efx_stop_eventq(channel);
+			efx_fast_push_rx_descriptors(rx_queue, false);
+			efx_start_eventq(channel);
 		}
 
 		WARN_ON(channel->rx_pkt_n_frags);
@@ -1051,18 +1060,23 @@ static void efx_start_port(struct efx_nic *efx)
 	mutex_lock(&efx->mac_lock);
 	efx->port_enabled = true;
 
-	/* efx_mac_work() might have been scheduled after efx_stop_port(),
-	 * and then cancelled by efx_flush_all() */
+	/* Ensure MAC ingress/egress is enabled */
 	efx->type->reconfigure_mac(efx);
 
 	mutex_unlock(&efx->mac_lock);
 }
 
-/* Prevent efx_mac_work() and efx_monitor() from working */
+/* Cancel work for MAC reconfiguration, periodic hardware monitoring
+ * and the async self-test, wait for them to finish and prevent them
+ * being scheduled again.  This doesn't cover online resets, which
+ * should only be cancelled when removing the device.
+ */
 static void efx_stop_port(struct efx_nic *efx)
 {
 	netif_dbg(efx, ifdown, efx->net_dev, "stop port\n");
 
+	EFX_ASSERT_RESET_SERIALISED(efx);
+
 	mutex_lock(&efx->mac_lock);
 	efx->port_enabled = false;
 	mutex_unlock(&efx->mac_lock);
@@ -1070,6 +1084,10 @@ static void efx_stop_port(struct efx_nic *efx)
 	/* Serialise against efx_set_multicast_list() */
 	netif_addr_lock_bh(efx->net_dev);
 	netif_addr_unlock_bh(efx->net_dev);
+
+	cancel_delayed_work_sync(&efx->monitor_work);
+	efx_selftest_async_cancel(efx);
+	cancel_work_sync(&efx->mac_work);
 }
 
 static void efx_fini_port(struct efx_nic *efx)
@@ -1099,6 +1117,77 @@ static void efx_remove_port(struct efx_nic *efx)
  *
  **************************************************************************/
 
+static LIST_HEAD(efx_primary_list);
+static LIST_HEAD(efx_unassociated_list);
+
+static bool efx_same_controller(struct efx_nic *left, struct efx_nic *right)
+{
+	return left->type == right->type &&
+		left->vpd_sn && right->vpd_sn &&
+		!strcmp(left->vpd_sn, right->vpd_sn);
+}
+
+static void efx_associate(struct efx_nic *efx)
+{
+	struct efx_nic *other, *next;
+
+	if (efx->primary == efx) {
+		/* Adding primary function; look for secondaries */
+
+		netif_dbg(efx, probe, efx->net_dev, "adding to primary list\n");
+		list_add_tail(&efx->node, &efx_primary_list);
+
+		list_for_each_entry_safe(other, next, &efx_unassociated_list,
+					 node) {
+			if (efx_same_controller(efx, other)) {
+				list_del(&other->node);
+				netif_dbg(other, probe, other->net_dev,
+					  "moving to secondary list of %s %s\n",
+					  pci_name(efx->pci_dev),
+					  efx->net_dev->name);
+				list_add_tail(&other->node,
+					      &efx->secondary_list);
+				other->primary = efx;
+			}
+		}
+	} else {
+		/* Adding secondary function; look for primary */
+
+		list_for_each_entry(other, &efx_primary_list, node) {
+			if (efx_same_controller(efx, other)) {
+				netif_dbg(efx, probe, efx->net_dev,
+					  "adding to secondary list of %s %s\n",
+					  pci_name(other->pci_dev),
+					  other->net_dev->name);
+				list_add_tail(&efx->node,
+					      &other->secondary_list);
+				efx->primary = other;
+				return;
+			}
+		}
+
+		netif_dbg(efx, probe, efx->net_dev,
+			  "adding to unassociated list\n");
+		list_add_tail(&efx->node, &efx_unassociated_list);
+	}
+}
+
+static void efx_dissociate(struct efx_nic *efx)
+{
+	struct efx_nic *other, *next;
+
+	list_del(&efx->node);
+	efx->primary = NULL;
+
+	list_for_each_entry_safe(other, next, &efx->secondary_list, node) {
+		list_del(&other->node);
+		netif_dbg(other, probe, other->net_dev,
+			  "moving to unassociated list\n");
+		list_add_tail(&other->node, &efx_unassociated_list);
+		other->primary = NULL;
+	}
+}
+
 /* This configures the PCI device to enable I/O and DMA. */
 static int efx_init_io(struct efx_nic *efx)
 {
@@ -1675,18 +1764,10 @@ static void efx_start_all(struct efx_nic *efx)
 	}
 
 	efx->type->start_stats(efx);
-}
-
-/* Flush all delayed work. Should only be called when no more delayed work
- * will be scheduled. This doesn't flush pending online resets (efx_reset),
- * since we're holding the rtnl_lock at this point. */
-static void efx_flush_all(struct efx_nic *efx)
-{
-	/* Make sure the hardware monitor and event self-test are stopped */
-	cancel_delayed_work_sync(&efx->monitor_work);
-	efx_selftest_async_cancel(efx);
-	/* Stop scheduled port reconfigurations */
-	cancel_work_sync(&efx->mac_work);
+	efx->type->pull_stats(efx);
+	spin_lock_bh(&efx->stats_lock);
+	efx->type->update_stats(efx, NULL, NULL);
+	spin_unlock_bh(&efx->stats_lock);
 }
 
 /* Quiesce the hardware and software data path, and regular activity
@@ -1702,12 +1783,16 @@ static void efx_stop_all(struct efx_nic *efx)
 	if (!efx->port_enabled)
 		return;
 
+	/* update stats before we go down so we can accurately count
+	 * rx_nodesc_drops
+	 */
+	efx->type->pull_stats(efx);
+	spin_lock_bh(&efx->stats_lock);
+	efx->type->update_stats(efx, NULL, NULL);
+	spin_unlock_bh(&efx->stats_lock);
 	efx->type->stop_stats(efx);
 	efx_stop_port(efx);
 
-	/* Flush efx_mac_work(), refill_workqueue, monitor_work */
-	efx_flush_all(efx);
-
 	/* Stop the kernel transmit interface.  This is only valid if
 	 * the device is stopped or detached; otherwise the watchdog
 	 * may fire immediately.
@@ -1851,7 +1936,9 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
 	struct mii_ioctl_data *data = if_mii(ifr);
 
 	if (cmd == SIOCSHWTSTAMP)
-		return efx_ptp_ioctl(efx, ifr, cmd);
+		return efx_ptp_set_ts_config(efx, ifr);
+	if (cmd == SIOCGHWTSTAMP)
+		return efx_ptp_get_ts_config(efx, ifr);
 
 	/* Convert phy_id from older PRTAD/DEVAD format */
 	if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) &&
@@ -2064,7 +2151,7 @@ static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
 
 	/* If disabling RX n-tuple filtering, clear existing filters */
 	if (net_dev->features & ~data & NETIF_F_NTUPLE)
-		efx_filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL);
+		return efx->type->filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL);
 
 	return 0;
 }
@@ -2198,6 +2285,8 @@ static int efx_register_netdev(struct efx_nic *efx)
 			efx_init_tx_queue_core_txq(tx_queue);
 	}
 
+	efx_associate(efx);
+
 	rtnl_unlock();
 
 	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_type);
@@ -2211,6 +2300,7 @@ static int efx_register_netdev(struct efx_nic *efx)
 
 fail_registered:
 	rtnl_lock();
+	efx_dissociate(efx);
 	unregister_netdevice(net_dev);
 fail_locked:
 	efx->state = STATE_UNINIT;
@@ -2387,6 +2477,24 @@ int efx_try_recovery(struct efx_nic *efx)
 	return 0;
 }
 
+static void efx_wait_for_bist_end(struct efx_nic *efx)
+{
+	int i;
+
+	for (i = 0; i < BIST_WAIT_DELAY_COUNT; ++i) {
+		if (efx_mcdi_poll_reboot(efx))
+			goto out;
+		msleep(BIST_WAIT_DELAY_MS);
+	}
+
+	netif_err(efx, drv, efx->net_dev, "Warning: No MC reboot after BIST mode\n");
+out:
+	/* Either way unset the BIST flag. If we found no reboot we probably
+	 * won't recover, but we should try.
+	 */
+	efx->mc_bist_for_other_fn = false;
+}
+
 /* The worker thread exists so that code that cannot sleep can
  * schedule a reset for later.
  */
@@ -2399,6 +2507,9 @@ static void efx_reset_work(struct work_struct *data)
 	pending = ACCESS_ONCE(efx->reset_pending);
 	method = fls(pending) - 1;
 
+	if (method == RESET_TYPE_MC_BIST)
+		efx_wait_for_bist_end(efx);
+
 	if ((method == RESET_TYPE_RECOVER_OR_DISABLE ||
 	     method == RESET_TYPE_RECOVER_OR_ALL) &&
 	    efx_try_recovery(efx))
@@ -2437,6 +2548,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type)
 	case RESET_TYPE_WORLD:
 	case RESET_TYPE_DISABLE:
 	case RESET_TYPE_RECOVER_OR_DISABLE:
+	case RESET_TYPE_MC_BIST:
 		method = type;
 		netif_dbg(efx, drv, efx->net_dev, "scheduling %s reset\n",
 			  RESET_TYPE(method));
@@ -2530,6 +2642,8 @@ static int efx_init_struct(struct efx_nic *efx,
 	int i;
 
 	/* Initialise common structures */
+	INIT_LIST_HEAD(&efx->node);
+	INIT_LIST_HEAD(&efx->secondary_list);
 	spin_lock_init(&efx->biu_lock);
 #ifdef CONFIG_SFC_MTD
 	INIT_LIST_HEAD(&efx->mtd_list);
@@ -2548,6 +2662,8 @@ static int efx_init_struct(struct efx_nic *efx,
 		NET_IP_ALIGN ? (efx->rx_prefix_size + NET_IP_ALIGN) % 4 : 0;
 	efx->rx_packet_hash_offset =
 		efx->type->rx_hash_offset - efx->type->rx_prefix_size;
+	efx->rx_packet_ts_offset =
+		efx->type->rx_ts_offset - efx->type->rx_prefix_size;
 	spin_lock_init(&efx->stats_lock);
 	mutex_init(&efx->mac_lock);
 	efx->phy_op = &efx_dummy_phy_operations;
@@ -2588,6 +2704,8 @@ static void efx_fini_struct(struct efx_nic *efx)
 	for (i = 0; i < EFX_MAX_CHANNELS; i++)
 		kfree(efx->channel[i]);
 
+	kfree(efx->vpd_sn);
+
 	if (efx->workqueue) {
 		destroy_workqueue(efx->workqueue);
 		efx->workqueue = NULL;
@@ -2632,6 +2750,7 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
 
 	/* Mark the NIC as fini, then stop the interface */
 	rtnl_lock();
+	efx_dissociate(efx);
 	dev_close(efx->net_dev);
 	efx_disable_interrupts(efx);
 	rtnl_unlock();
@@ -2647,7 +2766,6 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
 	netif_dbg(efx, drv, efx->net_dev, "shutdown successful\n");
 
 	efx_fini_struct(efx);
-	pci_set_drvdata(pci_dev, NULL);
 	free_netdev(efx->net_dev);
 
 	pci_disable_pcie_error_reporting(pci_dev);
@@ -2659,12 +2777,12 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
  * always appear within the first 512 bytes.
  */
 #define SFC_VPD_LEN 512
-static void efx_print_product_vpd(struct efx_nic *efx)
+static void efx_probe_vpd_strings(struct efx_nic *efx)
 {
 	struct pci_dev *dev = efx->pci_dev;
 	char vpd_data[SFC_VPD_LEN];
 	ssize_t vpd_size;
-	int i, j;
+	int ro_start, ro_size, i, j;
 
 	/* Get the vpd data from the device */
 	vpd_size = pci_read_vpd(dev, 0, sizeof(vpd_data), vpd_data);
@@ -2674,14 +2792,15 @@ static void efx_print_product_vpd(struct efx_nic *efx)
 	}
 
 	/* Get the Read only section */
-	i = pci_vpd_find_tag(vpd_data, 0, vpd_size, PCI_VPD_LRDT_RO_DATA);
-	if (i < 0) {
+	ro_start = pci_vpd_find_tag(vpd_data, 0, vpd_size, PCI_VPD_LRDT_RO_DATA);
+	if (ro_start < 0) {
 		netif_err(efx, drv, efx->net_dev, "VPD Read-only not found\n");
 		return;
 	}
 
-	j = pci_vpd_lrdt_size(&vpd_data[i]);
-	i += PCI_VPD_LRDT_TAG_SIZE;
+	ro_size = pci_vpd_lrdt_size(&vpd_data[ro_start]);
+	j = ro_size;
+	i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
 	if (i + j > vpd_size)
 		j = vpd_size - i;
 
@@ -2701,6 +2820,27 @@ static void efx_print_product_vpd(struct efx_nic *efx)
 
 	netif_info(efx, drv, efx->net_dev,
 		   "Part Number : %.*s\n", j, &vpd_data[i]);
+
+	i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
+	j = ro_size;
+	i = pci_vpd_find_info_keyword(vpd_data, i, j, "SN");
+	if (i < 0) {
+		netif_err(efx, drv, efx->net_dev, "Serial number not found\n");
+		return;
+	}
+
+	j = pci_vpd_info_field_size(&vpd_data[i]);
+	i += PCI_VPD_INFO_FLD_HDR_SIZE;
+	if (i + j > vpd_size) {
+		netif_err(efx, drv, efx->net_dev, "Incomplete serial number\n");
+		return;
+	}
+
+	efx->vpd_sn = kmalloc(j + 1, GFP_KERNEL);
+	if (!efx->vpd_sn)
+		return;
+
+	snprintf(efx->vpd_sn, j + 1, "%s", &vpd_data[i]);
 }
 
 
@@ -2797,7 +2937,7 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	netif_info(efx, probe, efx->net_dev,
 		   "Solarflare NIC detected\n");
 
-	efx_print_product_vpd(efx);
+	efx_probe_vpd_strings(efx);
 
 	/* Set up basic I/O (BAR mappings etc) */
 	rc = efx_init_io(efx);
@@ -2841,7 +2981,6 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
  fail2:
 	efx_fini_struct(efx);
  fail1:
-	pci_set_drvdata(pci_dev, NULL);
 	WARN_ON(rc > 0);
 	netif_dbg(efx, drv, efx->net_dev, "initialisation failed. rc=%d\n", rc);
 	free_netdev(net_dev);