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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 68 insertions, 43 deletions

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 0e09bede42a2..e4baa13b3cda 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1780,7 +1780,8 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data)
 		}
 		/* guard against interrupt when we're going down */
 		if (!test_bit(__E1000_DOWN, &adapter->state))
-			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+			queue_delayed_work(adapter->e1000_workqueue,
+					   &adapter->watchdog_task, 1);
 	}
 
 	/* Reset on uncorrectable ECC error */
@@ -1860,7 +1861,8 @@ static irqreturn_t e1000_intr(int __always_unused irq, void *data)
 		}
 		/* guard against interrupt when we're going down */
 		if (!test_bit(__E1000_DOWN, &adapter->state))
-			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+			queue_delayed_work(adapter->e1000_workqueue,
+					   &adapter->watchdog_task, 1);
 	}
 
 	/* Reset on uncorrectable ECC error */
@@ -1905,7 +1907,8 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data)
 		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);
+			queue_delayed_work(adapter->e1000_workqueue,
+					   &adapter->watchdog_task, 1);
 	}
 
 	if (!test_bit(__E1000_DOWN, &adapter->state))
@@ -3208,7 +3211,7 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
 	if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX))
 		ew32(RCTL, rctl & ~E1000_RCTL_EN);
 	e1e_flush();
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	if (adapter->flags2 & FLAG2_DMA_BURST) {
 		/* set the writeback threshold (only takes effect if the RDTR
@@ -4046,12 +4049,12 @@ void e1000e_reset(struct e1000_adapter *adapter)
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
 	case e1000_pch_cnp:
-		fc->refresh_time = 0x0400;
+		fc->refresh_time = 0xFFFF;
+		fc->pause_time = 0xFFFF;
 
 		if (adapter->netdev->mtu <= ETH_DATA_LEN) {
 			fc->high_water = 0x05C20;
 			fc->low_water = 0x05048;
-			fc->pause_time = 0x0650;
 			break;
 		}
 
@@ -4208,7 +4211,7 @@ void e1000e_up(struct e1000_adapter *adapter)
 		e1000_configure_msix(adapter);
 	e1000_irq_enable(adapter);
 
-	netif_start_queue(adapter->netdev);
+	/* Tx queue started by watchdog timer when link is up */
 
 	e1000e_trigger_lsc(adapter);
 }
@@ -4272,13 +4275,12 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset)
 
 	/* flush both disables and wait for them to finish */
 	e1e_flush();
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	e1000_irq_disable(adapter);
 
 	napi_synchronize(&adapter->napi);
 
-	del_timer_sync(&adapter->watchdog_timer);
 	del_timer_sync(&adapter->phy_info_timer);
 
 	spin_lock(&adapter->stats64_lock);
@@ -4310,7 +4312,7 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter)
 {
 	might_sleep();
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
-		usleep_range(1000, 2000);
+		usleep_range(1000, 1100);
 	e1000e_down(adapter, true);
 	e1000e_up(adapter);
 	clear_bit(__E1000_RESETTING, &adapter->state);
@@ -4606,6 +4608,7 @@ int e1000e_open(struct net_device *netdev)
 	pm_runtime_get_sync(&pdev->dev);
 
 	netif_carrier_off(netdev);
+	netif_stop_queue(netdev);
 
 	/* allocate transmit descriptors */
 	err = e1000e_setup_tx_resources(adapter->tx_ring);
@@ -4666,7 +4669,6 @@ int e1000e_open(struct net_device *netdev)
 	e1000_irq_enable(adapter);
 
 	adapter->tx_hang_recheck = false;
-	netif_start_queue(netdev);
 
 	hw->mac.get_link_status = true;
 	pm_runtime_put(&pdev->dev);
@@ -4707,7 +4709,7 @@ int e1000e_close(struct net_device *netdev)
 	int count = E1000_CHECK_RESET_COUNT;
 
 	while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
-		usleep_range(10000, 20000);
+		usleep_range(10000, 11000);
 
 	WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
 
@@ -5150,31 +5152,18 @@ 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(struct timer_list *t)
-{
-	struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer);
-
-	/* Do the rest outside of interrupt context */
-	schedule_work(&adapter->watchdog_task);
-
-	/* TODO: make this use queue_delayed_work() */
-}
-
 static void e1000_watchdog_task(struct work_struct *work)
 {
 	struct e1000_adapter *adapter = container_of(work,
 						     struct e1000_adapter,
-						     watchdog_task);
+						     watchdog_task.work);
 	struct net_device *netdev = adapter->netdev;
 	struct e1000_mac_info *mac = &adapter->hw.mac;
 	struct e1000_phy_info *phy = &adapter->hw.phy;
 	struct e1000_ring *tx_ring = adapter->tx_ring;
+	u32 dmoff_exit_timeout = 100, tries = 0;
 	struct e1000_hw *hw = &adapter->hw;
-	u32 link, tctl;
+	u32 link, tctl, pcim_state;
 
 	if (test_bit(__E1000_DOWN, &adapter->state))
 		return;
@@ -5199,6 +5188,21 @@ static void e1000_watchdog_task(struct work_struct *work)
 			/* Cancel scheduled suspend requests. */
 			pm_runtime_resume(netdev->dev.parent);
 
+			/* Checking if MAC is in DMoff state*/
+			pcim_state = er32(STATUS);
+			while (pcim_state & E1000_STATUS_PCIM_STATE) {
+				if (tries++ == dmoff_exit_timeout) {
+					e_dbg("Error in exiting dmoff\n");
+					break;
+				}
+				usleep_range(10000, 20000);
+				pcim_state = er32(STATUS);
+
+				/* Checking if MAC exited DMoff state */
+				if (!(pcim_state & E1000_STATUS_PCIM_STATE))
+					e1000_phy_hw_reset(&adapter->hw);
+			}
+
 			/* update snapshot of PHY registers on LSC */
 			e1000_phy_read_status(adapter);
 			mac->ops.get_link_up_info(&adapter->hw,
@@ -5288,6 +5292,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 			if (phy->ops.cfg_on_link_up)
 				phy->ops.cfg_on_link_up(hw);
 
+			netif_wake_queue(netdev);
 			netif_carrier_on(netdev);
 
 			if (!test_bit(__E1000_DOWN, &adapter->state))
@@ -5301,6 +5306,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 			/* Link status message must follow this format */
 			pr_info("%s NIC Link is Down\n", adapter->netdev->name);
 			netif_carrier_off(netdev);
+			netif_stop_queue(netdev);
 			if (!test_bit(__E1000_DOWN, &adapter->state))
 				mod_timer(&adapter->phy_info_timer,
 					  round_jiffies(jiffies + 2 * HZ));
@@ -5308,13 +5314,8 @@ static void e1000_watchdog_task(struct work_struct *work)
 			/* 8000ES2LAN requires a Rx packet buffer work-around
 			 * on link down event; reset the controller to flush
 			 * the Rx packet buffer.
-			 *
-			 * If the link is lost the controller stops DMA, but
-			 * if there is queued Tx work it cannot be done.  So
-			 * reset the controller to flush the Tx packet buffers.
 			 */
-			if ((adapter->flags & FLAG_RX_NEEDS_RESTART) ||
-			    e1000_desc_unused(tx_ring) + 1 < tx_ring->count)
+			if (adapter->flags & FLAG_RX_NEEDS_RESTART)
 				adapter->flags |= FLAG_RESTART_NOW;
 			else
 				pm_schedule_suspend(netdev->dev.parent,
@@ -5337,6 +5338,14 @@ link_up:
 	adapter->gotc_old = adapter->stats.gotc;
 	spin_unlock(&adapter->stats64_lock);
 
+	/* If the link is lost the controller stops DMA, but
+	 * if there is queued Tx work it cannot be done.  So
+	 * reset the controller to flush the Tx packet buffers.
+	 */
+	if (!netif_carrier_ok(netdev) &&
+	    (e1000_desc_unused(tx_ring) + 1 < tx_ring->count))
+		adapter->flags |= FLAG_RESTART_NOW;
+
 	/* If reset is necessary, do it outside of interrupt context. */
 	if (adapter->flags & FLAG_RESTART_NOW) {
 		schedule_work(&adapter->reset_task);
@@ -5395,8 +5404,9 @@ link_up:
 
 	/* Reset the timer */
 	if (!test_bit(__E1000_DOWN, &adapter->state))
-		mod_timer(&adapter->watchdog_timer,
-			  round_jiffies(jiffies + 2 * HZ));
+		queue_delayed_work(adapter->e1000_workqueue,
+				   &adapter->watchdog_task,
+				   round_jiffies(2 * HZ));
 }
 
 #define E1000_TX_FLAGS_CSUM		0x00000001
@@ -6016,7 +6026,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 	}
 
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
-		usleep_range(1000, 2000);
+		usleep_range(1000, 1100);
 	/* e1000e_down -> e1000e_reset dependent on max_frame_size & mtu */
 	adapter->max_frame_size = max_frame;
 	e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu);
@@ -6296,7 +6306,7 @@ static int e1000e_pm_freeze(struct device *dev)
 		int count = E1000_CHECK_RESET_COUNT;
 
 		while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
-			usleep_range(10000, 20000);
+			usleep_range(10000, 11000);
 
 		WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
 
@@ -6711,7 +6721,7 @@ static int e1000e_pm_runtime_suspend(struct device *dev)
 		int count = E1000_CHECK_RESET_COUNT;
 
 		while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
-			usleep_range(10000, 20000);
+			usleep_range(10000, 11000);
 
 		WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
 
@@ -7251,11 +7261,21 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_eeprom;
 	}
 
-	timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0);
+	adapter->e1000_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+						   e1000e_driver_name);
+
+	if (!adapter->e1000_workqueue) {
+		err = -ENOMEM;
+		goto err_workqueue;
+	}
+
+	INIT_DELAYED_WORK(&adapter->watchdog_task, e1000_watchdog_task);
+	queue_delayed_work(adapter->e1000_workqueue, &adapter->watchdog_task,
+			   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);
 	INIT_WORK(&adapter->downshift_task, e1000e_downshift_workaround);
 	INIT_WORK(&adapter->update_phy_task, e1000e_update_phy_task);
 	INIT_WORK(&adapter->print_hang_task, e1000_print_hw_hang);
@@ -7349,6 +7369,9 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
 err_register:
+	flush_workqueue(adapter->e1000_workqueue);
+	destroy_workqueue(adapter->e1000_workqueue);
+err_workqueue:
 	if (!(adapter->flags & FLAG_HAS_AMT))
 		e1000e_release_hw_control(adapter);
 err_eeprom:
@@ -7395,15 +7418,17 @@ static void e1000_remove(struct pci_dev *pdev)
 	 */
 	if (!down)
 		set_bit(__E1000_DOWN, &adapter->state);
-	del_timer_sync(&adapter->watchdog_timer);
 	del_timer_sync(&adapter->phy_info_timer);
 
 	cancel_work_sync(&adapter->reset_task);
-	cancel_work_sync(&adapter->watchdog_task);
 	cancel_work_sync(&adapter->downshift_task);
 	cancel_work_sync(&adapter->update_phy_task);
 	cancel_work_sync(&adapter->print_hang_task);
 
+	cancel_delayed_work(&adapter->watchdog_task);
+	flush_workqueue(adapter->e1000_workqueue);
+	destroy_workqueue(adapter->e1000_workqueue);
+
 	if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) {
 		cancel_work_sync(&adapter->tx_hwtstamp_work);
 		if (adapter->tx_hwtstamp_skb) {