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()
  ...

6 files changed, 79 insertions, 52 deletions

diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 0641c0098738..afb7ebe20b24 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -398,6 +398,7 @@
 #define E1000_ICR_LSC           0x00000004 /* Link Status Change */
 #define E1000_ICR_RXSEQ         0x00000008 /* Rx sequence error */
 #define E1000_ICR_RXDMT0        0x00000010 /* Rx desc min. threshold (0) */
+#define E1000_ICR_RXO           0x00000040 /* Receiver Overrun */
 #define E1000_ICR_RXT0          0x00000080 /* Rx timer intr (ring 0) */
 #define E1000_ICR_ECCER         0x00400000 /* Uncorrectable ECC Error */
 /* If this bit asserted, the driver should claim the interrupt */
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 98e68888abb1..2311b31bdcac 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -94,10 +94,6 @@ struct e1000_info;
  */
 #define E1000_CHECK_RESET_COUNT		25
 
-#define DEFAULT_RDTR			0
-#define DEFAULT_RADV			8
-#define BURST_RDTR			0x20
-#define BURST_RADV			0x20
 #define PCICFG_DESC_RING_STATUS		0xe4
 #define FLUSH_DESC_REQUIRED		0x100
 
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index b322011ec282..f457c5703d0c 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -410,6 +410,9 @@ void e1000e_clear_hw_cntrs_base(struct e1000_hw *hw)
  *  Checks to see of the link status of the hardware has changed.  If a
  *  change in link status has been detected, then we read the PHY registers
  *  to get the current speed/duplex if link exists.
+ *
+ *  Returns a negative error code (-E1000_ERR_*) or 0 (link down) or 1 (link
+ *  up).
  **/
 s32 e1000e_check_for_copper_link(struct e1000_hw *hw)
 {
@@ -423,7 +426,7 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw)
 	 * Change or Rx Sequence Error interrupt.
 	 */
 	if (!mac->get_link_status)
-		return 0;
+		return 1;
 
 	/* First we want to see if the MII Status Register reports
 	 * link.  If so, then we want to get the current speed/duplex
@@ -461,10 +464,12 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw)
 	 * different link partner.
 	 */
 	ret_val = e1000e_config_fc_after_link_up(hw);
-	if (ret_val)
+	if (ret_val) {
 		e_dbg("Error configuring flow control\n");
+		return ret_val;
+	}
 
-	return ret_val;
+	return 1;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 327dfe5bedc0..f2f49239b015 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1071,7 +1071,8 @@ next_desc:
 }
 
 static void e1000_put_txbuf(struct e1000_ring *tx_ring,
-			    struct e1000_buffer *buffer_info)
+			    struct e1000_buffer *buffer_info,
+			    bool drop)
 {
 	struct e1000_adapter *adapter = tx_ring->adapter;
 
@@ -1085,7 +1086,10 @@ static void e1000_put_txbuf(struct e1000_ring *tx_ring,
 		buffer_info->dma = 0;
 	}
 	if (buffer_info->skb) {
-		dev_kfree_skb_any(buffer_info->skb);
+		if (drop)
+			dev_kfree_skb_any(buffer_info->skb);
+		else
+			dev_consume_skb_any(buffer_info->skb);
 		buffer_info->skb = NULL;
 	}
 	buffer_info->time_stamp = 0;
@@ -1199,7 +1203,7 @@ static void e1000e_tx_hwtstamp_work(struct work_struct *work)
 		wmb(); /* force write prior to skb_tstamp_tx */
 
 		skb_tstamp_tx(skb, &shhwtstamps);
-		dev_kfree_skb_any(skb);
+		dev_consume_skb_any(skb);
 	} else if (time_after(jiffies, adapter->tx_hwtstamp_start
 			      + adapter->tx_timeout_factor * HZ)) {
 		dev_kfree_skb_any(adapter->tx_hwtstamp_skb);
@@ -1254,7 +1258,7 @@ static bool e1000_clean_tx_irq(struct e1000_ring *tx_ring)
 				}
 			}
 
-			e1000_put_txbuf(tx_ring, buffer_info);
+			e1000_put_txbuf(tx_ring, buffer_info, false);
 			tx_desc->upper.data = 0;
 
 			i++;
@@ -1910,14 +1914,30 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data)
 	struct net_device *netdev = data;
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 icr;
+	bool enable = true;
+
+	icr = er32(ICR);
+	if (icr & E1000_ICR_RXO) {
+		ew32(ICR, E1000_ICR_RXO);
+		enable = false;
+		/* napi poll will re-enable Other, make sure it runs */
+		if (napi_schedule_prep(&adapter->napi)) {
+			adapter->total_rx_bytes = 0;
+			adapter->total_rx_packets = 0;
+			__napi_schedule(&adapter->napi);
+		}
+	}
+	if (icr & E1000_ICR_LSC) {
+		ew32(ICR, E1000_ICR_LSC);
+		hw->mac.get_link_status = true;
+		/* guard against interrupt when we're going down */
+		if (!test_bit(__E1000_DOWN, &adapter->state))
+			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+	}
 
-	hw->mac.get_link_status = true;
-
-	/* guard against interrupt when we're going down */
-	if (!test_bit(__E1000_DOWN, &adapter->state)) {
-		mod_timer(&adapter->watchdog_timer, jiffies + 1);
+	if (enable && !test_bit(__E1000_DOWN, &adapter->state))
 		ew32(IMS, E1000_IMS_OTHER);
-	}
 
 	return IRQ_HANDLED;
 }
@@ -2421,7 +2441,7 @@ static void e1000_clean_tx_ring(struct e1000_ring *tx_ring)
 
 	for (i = 0; i < tx_ring->count; i++) {
 		buffer_info = &tx_ring->buffer_info[i];
-		e1000_put_txbuf(tx_ring, buffer_info);
+		e1000_put_txbuf(tx_ring, buffer_info, false);
 	}
 
 	netdev_reset_queue(adapter->netdev);
@@ -2687,7 +2707,8 @@ static int e1000e_poll(struct napi_struct *napi, int weight)
 		napi_complete_done(napi, work_done);
 		if (!test_bit(__E1000_DOWN, &adapter->state)) {
 			if (adapter->msix_entries)
-				ew32(IMS, adapter->rx_ring->ims_val);
+				ew32(IMS, adapter->rx_ring->ims_val |
+				     E1000_IMS_OTHER);
 			else
 				e1000_irq_enable(adapter);
 		}
@@ -3004,8 +3025,8 @@ static void e1000_configure_tx(struct e1000_adapter *adapter)
 
 	hw->mac.ops.config_collision_dist(hw);
 
-	/* SPT and CNP Si errata workaround to avoid data corruption */
-	if (hw->mac.type >= e1000_pch_spt) {
+	/* SPT and KBL Si errata workaround to avoid data corruption */
+	if (hw->mac.type == e1000_pch_spt) {
 		u32 reg_val;
 
 		reg_val = er32(IOSFPC);
@@ -3013,7 +3034,9 @@ static void e1000_configure_tx(struct e1000_adapter *adapter)
 		ew32(IOSFPC, reg_val);
 
 		reg_val = er32(TARC(0));
-		reg_val |= E1000_TARC0_CB_MULTIQ_3_REQ;
+		/* SPT and KBL Si errata workaround to avoid Tx hang */
+		reg_val &= ~BIT(28);
+		reg_val |= BIT(29);
 		ew32(TARC(0), reg_val);
 	}
 }
@@ -3223,14 +3246,6 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
 		 */
 		ew32(RXDCTL(0), E1000_RXDCTL_DMA_BURST_ENABLE);
 		ew32(RXDCTL(1), E1000_RXDCTL_DMA_BURST_ENABLE);
-
-		/* override the delay timers for enabling bursting, only if
-		 * the value was not set by the user via module options
-		 */
-		if (adapter->rx_int_delay == DEFAULT_RDTR)
-			adapter->rx_int_delay = BURST_RDTR;
-		if (adapter->rx_abs_int_delay == DEFAULT_RADV)
-			adapter->rx_abs_int_delay = BURST_RADV;
 	}
 
 	/* set the Receive Delay Timer Register */
@@ -4204,7 +4219,7 @@ static void e1000e_trigger_lsc(struct e1000_adapter *adapter)
 	struct e1000_hw *hw = &adapter->hw;
 
 	if (adapter->msix_entries)
-		ew32(ICS, E1000_ICS_OTHER);
+		ew32(ICS, E1000_ICS_LSC | E1000_ICS_OTHER);
 	else
 		ew32(ICS, E1000_ICS_LSC);
 }
@@ -4808,9 +4823,9 @@ static void e1000e_update_phy_task(struct work_struct *work)
  * Need to wait a few seconds after link up to get diagnostic information from
  * the phy
  **/
-static void e1000_update_phy_info(unsigned long data)
+static void e1000_update_phy_info(struct timer_list *t)
 {
-	struct e1000_adapter *adapter = (struct e1000_adapter *)data;
+	struct e1000_adapter *adapter = from_timer(adapter, t, phy_info_timer);
 
 	if (test_bit(__E1000_DOWN, &adapter->state))
 		return;
@@ -5074,14 +5089,14 @@ static bool e1000e_has_link(struct e1000_adapter *adapter)
 
 	/* get_link_status is set on LSC (link status) interrupt or
 	 * Rx sequence error interrupt.  get_link_status will stay
-	 * false until the check_for_link establishes link
+	 * true until the check_for_link establishes link
 	 * for copper adapters ONLY
 	 */
 	switch (hw->phy.media_type) {
 	case e1000_media_type_copper:
 		if (hw->mac.get_link_status) {
 			ret_val = hw->mac.ops.check_for_link(hw);
-			link_active = !hw->mac.get_link_status;
+			link_active = ret_val > 0;
 		} else {
 			link_active = true;
 		}
@@ -5092,14 +5107,14 @@ static bool e1000e_has_link(struct e1000_adapter *adapter)
 		break;
 	case e1000_media_type_internal_serdes:
 		ret_val = hw->mac.ops.check_for_link(hw);
-		link_active = adapter->hw.mac.serdes_has_link;
+		link_active = hw->mac.serdes_has_link;
 		break;
 	default:
 	case e1000_media_type_unknown:
 		break;
 	}
 
-	if ((ret_val == E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) &&
+	if ((ret_val == -E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) &&
 	    (er32(CTRL) & E1000_PHY_CTRL_GBE_DISABLE)) {
 		/* See e1000_kmrn_lock_loss_workaround_ich8lan() */
 		e_info("Gigabit has been disabled, downgrading speed\n");
@@ -5144,9 +5159,9 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter)
  * e1000_watchdog - Timer Call-back
  * @data: pointer to adapter cast into an unsigned long
  **/
-static void e1000_watchdog(unsigned long data)
+static void e1000_watchdog(struct timer_list *t)
 {
-	struct e1000_adapter *adapter = (struct e1000_adapter *)data;
+	struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer);
 
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
@@ -5614,7 +5629,7 @@ dma_error:
 			i += tx_ring->count;
 		i--;
 		buffer_info = &tx_ring->buffer_info[i];
-		e1000_put_txbuf(tx_ring, buffer_info);
+		e1000_put_txbuf(tx_ring, buffer_info, true);
 	}
 
 	return 0;
@@ -7252,13 +7267,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_eeprom;
 	}
 
-	init_timer(&adapter->watchdog_timer);
-	adapter->watchdog_timer.function = e1000_watchdog;
-	adapter->watchdog_timer.data = (unsigned long)adapter;
-
-	init_timer(&adapter->phy_info_timer);
-	adapter->phy_info_timer.function = e1000_update_phy_info;
-	adapter->phy_info_timer.data = (unsigned long)adapter;
+	timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0);
+	timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0);
 
 	INIT_WORK(&adapter->reset_task, e1000_reset_task);
 	INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
@@ -7411,7 +7421,7 @@ static void e1000_remove(struct pci_dev *pdev)
 	if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) {
 		cancel_work_sync(&adapter->tx_hwtstamp_work);
 		if (adapter->tx_hwtstamp_skb) {
-			dev_kfree_skb_any(adapter->tx_hwtstamp_skb);
+			dev_consume_skb_any(adapter->tx_hwtstamp_skb);
 			adapter->tx_hwtstamp_skb = NULL;
 		}
 	}
diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c
index 6d8c39abee16..47da51864543 100644
--- a/drivers/net/ethernet/intel/e1000e/param.c
+++ b/drivers/net/ethernet/intel/e1000e/param.c
@@ -73,17 +73,25 @@ E1000_PARAM(TxAbsIntDelay, "Transmit Absolute Interrupt Delay");
 /* Receive Interrupt Delay in units of 1.024 microseconds
  * hardware will likely hang if you set this to anything but zero.
  *
+ * Burst variant is used as default if device has FLAG2_DMA_BURST.
+ *
  * Valid Range: 0-65535
  */
 E1000_PARAM(RxIntDelay, "Receive Interrupt Delay");
+#define DEFAULT_RDTR	0
+#define BURST_RDTR	0x20
 #define MAX_RXDELAY 0xFFFF
 #define MIN_RXDELAY 0
 
 /* Receive Absolute Interrupt Delay in units of 1.024 microseconds
  *
+ * Burst variant is used as default if device has FLAG2_DMA_BURST.
+ *
  * Valid Range: 0-65535
  */
 E1000_PARAM(RxAbsIntDelay, "Receive Absolute Interrupt Delay");
+#define DEFAULT_RADV	8
+#define BURST_RADV	0x20
 #define MAX_RXABSDELAY 0xFFFF
 #define MIN_RXABSDELAY 0
 
@@ -297,6 +305,9 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 					 .max = MAX_RXDELAY } }
 		};
 
+		if (adapter->flags2 & FLAG2_DMA_BURST)
+			opt.def = BURST_RDTR;
+
 		if (num_RxIntDelay > bd) {
 			adapter->rx_int_delay = RxIntDelay[bd];
 			e1000_validate_option(&adapter->rx_int_delay, &opt,
@@ -307,7 +318,7 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 	}
 	/* Receive Absolute Interrupt Delay */
 	{
-		static const struct e1000_option opt = {
+		static struct e1000_option opt = {
 			.type = range_option,
 			.name = "Receive Absolute Interrupt Delay",
 			.err  = "using default of "
@@ -317,6 +328,9 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 					 .max = MAX_RXABSDELAY } }
 		};
 
+		if (adapter->flags2 & FLAG2_DMA_BURST)
+			opt.def = BURST_RADV;
+
 		if (num_RxAbsIntDelay > bd) {
 			adapter->rx_abs_int_delay = RxAbsIntDelay[bd];
 			e1000_validate_option(&adapter->rx_abs_int_delay, &opt,
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index d78d47b41a71..86ff0969efb6 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -1744,6 +1744,7 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations,
 	s32 ret_val = 0;
 	u16 i, phy_status;
 
+	*success = false;
 	for (i = 0; i < iterations; i++) {
 		/* Some PHYs require the MII_BMSR register to be read
 		 * twice due to the link bit being sticky.  No harm doing
@@ -1763,16 +1764,16 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations,
 		ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
 		if (ret_val)
 			break;
-		if (phy_status & BMSR_LSTATUS)
+		if (phy_status & BMSR_LSTATUS) {
+			*success = true;
 			break;
+		}
 		if (usec_interval >= 1000)
 			msleep(usec_interval / 1000);
 		else
 			udelay(usec_interval);
 	}
 
-	*success = (i < iterations);
-
 	return ret_val;
 }