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

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

1 files changed, 352 insertions, 61 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b1c265012c8a..320562b39686 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -27,7 +27,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 2
 #define DRV_VERSION_MINOR 8
-#define DRV_VERSION_BUILD 10
+#define DRV_VERSION_BUILD 20
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -46,6 +46,10 @@ static int i40e_setup_pf_filter_control(struct i40e_pf *pf);
 static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired);
 static int i40e_reset(struct i40e_pf *pf);
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
+static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf);
+static int i40e_restore_interrupt_scheme(struct i40e_pf *pf);
+static bool i40e_check_recovery_mode(struct i40e_pf *pf);
+static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw);
 static void i40e_fdir_sb_setup(struct i40e_pf *pf);
 static int i40e_veb_get_bw_info(struct i40e_veb *veb);
 static int i40e_get_capabilities(struct i40e_pf *pf,
@@ -69,6 +73,8 @@ static const struct pci_device_id i40e_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_SFP), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_B), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0},
@@ -77,6 +83,8 @@ static const struct pci_device_id i40e_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_I_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2_A), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_X710_N3000), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_XXV710_N3000), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_B), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_SFP28), 0},
 	/* required last entry */
@@ -278,8 +286,9 @@ struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id)
  **/
 void i40e_service_event_schedule(struct i40e_pf *pf)
 {
-	if (!test_bit(__I40E_DOWN, pf->state) &&
-	    !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+	if ((!test_bit(__I40E_DOWN, pf->state) &&
+	     !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) ||
+	      test_bit(__I40E_RECOVERY_MODE, pf->state))
 		queue_work(i40e_wq, &pf->service_task);
 }
 
@@ -2107,11 +2116,22 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
 	fcnt = i40e_update_filter_state(num_add, list, add_head);
 
 	if (fcnt != num_add) {
-		set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
-		dev_warn(&vsi->back->pdev->dev,
-			 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
-			 i40e_aq_str(hw, aq_err),
-			 vsi_name);
+		if (vsi->type == I40E_VSI_MAIN) {
+			set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
+			dev_warn(&vsi->back->pdev->dev,
+				 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
+				 i40e_aq_str(hw, aq_err), vsi_name);
+		} else if (vsi->type == I40E_VSI_SRIOV ||
+			   vsi->type == I40E_VSI_VMDQ1 ||
+			   vsi->type == I40E_VSI_VMDQ2) {
+			dev_warn(&vsi->back->pdev->dev,
+				 "Error %s adding RX filters on %s, please set promiscuous on manually for %s\n",
+				 i40e_aq_str(hw, aq_err), vsi_name, vsi_name);
+		} else {
+			dev_warn(&vsi->back->pdev->dev,
+				 "Error %s adding RX filters on %s, incorrect VSI type: %i.\n",
+				 i40e_aq_str(hw, aq_err), vsi_name, vsi->type);
+		}
 	}
 }
 
@@ -2654,6 +2674,10 @@ void i40e_vlan_stripping_enable(struct i40e_vsi *vsi)
 	struct i40e_vsi_context ctxt;
 	i40e_status ret;
 
+	/* Don't modify stripping options if a port VLAN is active */
+	if (vsi->info.pvid)
+		return;
+
 	if ((vsi->info.valid_sections &
 	     cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
 	    ((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_MODE_MASK) == 0))
@@ -2684,6 +2708,10 @@ void i40e_vlan_stripping_disable(struct i40e_vsi *vsi)
 	struct i40e_vsi_context ctxt;
 	i40e_status ret;
 
+	/* Don't modify stripping options if a port VLAN is active */
+	if (vsi->info.pvid)
+		return;
+
 	if ((vsi->info.valid_sections &
 	     cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
 	    ((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_EMOD_MASK) ==
@@ -2949,9 +2977,9 @@ int i40e_vsi_add_pvid(struct i40e_vsi *vsi, u16 vid)
  **/
 void i40e_vsi_remove_pvid(struct i40e_vsi *vsi)
 {
-	i40e_vlan_stripping_disable(vsi);
-
 	vsi->info.pvid = 0;
+
+	i40e_vlan_stripping_disable(vsi);
 }
 
 /**
@@ -4000,7 +4028,8 @@ static irqreturn_t i40e_intr(int irq, void *data)
 enable_intr:
 	/* re-enable interrupt causes */
 	wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
-	if (!test_bit(__I40E_DOWN, pf->state)) {
+	if (!test_bit(__I40E_DOWN, pf->state) ||
+	    test_bit(__I40E_RECOVERY_MODE, pf->state)) {
 		i40e_service_event_schedule(pf);
 		i40e_irq_dynamic_enable_icr0(pf);
 	}
@@ -6403,7 +6432,7 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 		goto out;
 
 	/* Get the initial DCB configuration */
-	err = i40e_init_dcb(hw);
+	err = i40e_init_dcb(hw, true);
 	if (!err) {
 		/* Device/Function is not DCBX capable */
 		if ((!hw->func_caps.dcb) ||
@@ -6493,6 +6522,12 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
 	case I40E_LINK_SPEED_10GB:
 		speed = "10 G";
 		break;
+	case I40E_LINK_SPEED_5GB:
+		speed = "5 G";
+		break;
+	case I40E_LINK_SPEED_2_5GB:
+		speed = "2.5 G";
+		break;
 	case I40E_LINK_SPEED_1GB:
 		speed = "1000 M";
 		break;
@@ -6846,10 +6881,12 @@ static int i40e_setup_tc(struct net_device *netdev, void *type_data)
 	struct i40e_pf *pf = vsi->back;
 	u8 enabled_tc = 0, num_tc, hw;
 	bool need_reset = false;
+	int old_queue_pairs;
 	int ret = -EINVAL;
 	u16 mode;
 	int i;
 
+	old_queue_pairs = vsi->num_queue_pairs;
 	num_tc = mqprio_qopt->qopt.num_tc;
 	hw = mqprio_qopt->qopt.hw;
 	mode = mqprio_qopt->mode;
@@ -6950,6 +6987,7 @@ config_tc:
 		}
 		ret = i40e_configure_queue_channels(vsi);
 		if (ret) {
+			vsi->num_queue_pairs = old_queue_pairs;
 			netdev_info(netdev,
 				    "Failed configuring queue channels\n");
 			need_reset = true;
@@ -9290,6 +9328,11 @@ static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired)
 			dev_warn(&pf->pdev->dev,
 				 "shutdown_lan_hmc failed: %d\n", ret);
 	}
+
+	/* Save the current PTP time so that we can restore the time after the
+	 * reset completes.
+	 */
+	i40e_ptp_save_hw_time(pf);
 }
 
 /**
@@ -9382,6 +9425,7 @@ static int i40e_reset(struct i40e_pf *pf)
  **/
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 {
+	int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state);
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	struct i40e_hw *hw = &pf->hw;
 	u8 set_fc_aq_fail = 0;
@@ -9389,7 +9433,14 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	u32 val;
 	int v;
 
-	if (test_bit(__I40E_DOWN, pf->state))
+	if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) &&
+	    i40e_check_recovery_mode(pf)) {
+		i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev);
+	}
+
+	if (test_bit(__I40E_DOWN, pf->state) &&
+	    !test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+	    !old_recovery_mode_bit)
 		goto clear_recovery;
 	dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
 
@@ -9418,6 +9469,44 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state))
 		i40e_verify_eeprom(pf);
 
+	/* if we are going out of or into recovery mode we have to act
+	 * accordingly with regard to resources initialization
+	 * and deinitialization
+	 */
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state) ||
+	    old_recovery_mode_bit) {
+		if (i40e_get_capabilities(pf,
+					  i40e_aqc_opc_list_func_capabilities))
+			goto end_unlock;
+
+		if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+			/* we're staying in recovery mode so we'll reinitialize
+			 * misc vector here
+			 */
+			if (i40e_setup_misc_vector_for_recovery_mode(pf))
+				goto end_unlock;
+		} else {
+			if (!lock_acquired)
+				rtnl_lock();
+			/* we're going out of recovery mode so we'll free
+			 * the IRQ allocated specifically for recovery mode
+			 * and restore the interrupt scheme
+			 */
+			free_irq(pf->pdev->irq, pf);
+			i40e_clear_interrupt_scheme(pf);
+			if (i40e_restore_interrupt_scheme(pf))
+				goto end_unlock;
+		}
+
+		/* tell the firmware that we're starting */
+		i40e_send_version(pf);
+
+		/* bail out in case recovery mode was detected, as there is
+		 * no need for further configuration.
+		 */
+		goto end_unlock;
+	}
+
 	i40e_clear_pxe_mode(hw);
 	ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
 	if (ret)
@@ -9669,7 +9758,6 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
 	bool mdd_detected = false;
-	bool pf_mdd_detected = false;
 	struct i40e_vf *vf;
 	u32 reg;
 	int i;
@@ -9715,19 +9803,12 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 		reg = rd32(hw, I40E_PF_MDET_TX);
 		if (reg & I40E_PF_MDET_TX_VALID_MASK) {
 			wr32(hw, I40E_PF_MDET_TX, 0xFFFF);
-			dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n");
-			pf_mdd_detected = true;
+			dev_dbg(&pf->pdev->dev, "TX driver issue detected on PF\n");
 		}
 		reg = rd32(hw, I40E_PF_MDET_RX);
 		if (reg & I40E_PF_MDET_RX_VALID_MASK) {
 			wr32(hw, I40E_PF_MDET_RX, 0xFFFF);
-			dev_info(&pf->pdev->dev, "RX driver issue detected, PF reset issued\n");
-			pf_mdd_detected = true;
-		}
-		/* Queue belongs to the PF, initiate a reset */
-		if (pf_mdd_detected) {
-			set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
-			i40e_service_event_schedule(pf);
+			dev_dbg(&pf->pdev->dev, "RX driver issue detected on PF\n");
 		}
 	}
 
@@ -9740,6 +9821,9 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 			vf->num_mdd_events++;
 			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
 				 i);
+			dev_info(&pf->pdev->dev,
+				 "Use PF Control I/F to re-enable the VF\n");
+			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
 		}
 
 		reg = rd32(hw, I40E_VP_MDET_RX(i));
@@ -9748,11 +9832,6 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 			vf->num_mdd_events++;
 			dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
 				 i);
-		}
-
-		if (vf->num_mdd_events > I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED) {
-			dev_info(&pf->pdev->dev,
-				 "Too many MDD events on VF %d, disabled\n", i);
 			dev_info(&pf->pdev->dev,
 				 "Use PF Control I/F to re-enable the VF\n");
 			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
@@ -9879,31 +9958,38 @@ static void i40e_service_task(struct work_struct *work)
 	unsigned long start_time = jiffies;
 
 	/* don't bother with service tasks if a reset is in progress */
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+	    test_bit(__I40E_SUSPENDED, pf->state))
 		return;
 
 	if (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state))
 		return;
 
-	i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
-	i40e_sync_filters_subtask(pf);
-	i40e_reset_subtask(pf);
-	i40e_handle_mdd_event(pf);
-	i40e_vc_process_vflr_event(pf);
-	i40e_watchdog_subtask(pf);
-	i40e_fdir_reinit_subtask(pf);
-	if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) {
-		/* Client subtask will reopen next time through. */
-		i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true);
+	if (!test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+		i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
+		i40e_sync_filters_subtask(pf);
+		i40e_reset_subtask(pf);
+		i40e_handle_mdd_event(pf);
+		i40e_vc_process_vflr_event(pf);
+		i40e_watchdog_subtask(pf);
+		i40e_fdir_reinit_subtask(pf);
+		if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) {
+			/* Client subtask will reopen next time through. */
+			i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi],
+							   true);
+		} else {
+			i40e_client_subtask(pf);
+			if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE,
+					       pf->state))
+				i40e_notify_client_of_l2_param_changes(
+								pf->vsi[pf->lan_vsi]);
+		}
+		i40e_sync_filters_subtask(pf);
+		i40e_sync_udp_filters_subtask(pf);
 	} else {
-		i40e_client_subtask(pf);
-		if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE,
-				       pf->state))
-			i40e_notify_client_of_l2_param_changes(
-							pf->vsi[pf->lan_vsi]);
-	}
-	i40e_sync_filters_subtask(pf);
-	i40e_sync_udp_filters_subtask(pf);
+		i40e_reset_subtask(pf);
+	}
+
 	i40e_clean_adminq_subtask(pf);
 
 	/* flush memory to make sure state is correct before next watchdog */
@@ -10726,6 +10812,48 @@ err_unwind:
 }
 
 /**
+ * i40e_setup_misc_vector_for_recovery_mode - Setup the misc vector to handle
+ * non queue events in recovery mode
+ * @pf: board private structure
+ *
+ * This sets up the handler for MSIX 0 or MSI/legacy, which is used to manage
+ * the non-queue interrupts, e.g. AdminQ and errors in recovery mode.
+ * This is handled differently than in recovery mode since no Tx/Rx resources
+ * are being allocated.
+ **/
+static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf)
+{
+	int err;
+
+	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+		err = i40e_setup_misc_vector(pf);
+
+		if (err) {
+			dev_info(&pf->pdev->dev,
+				 "MSI-X misc vector request failed, error %d\n",
+				 err);
+			return err;
+		}
+	} else {
+		u32 flags = pf->flags & I40E_FLAG_MSI_ENABLED ? 0 : IRQF_SHARED;
+
+		err = request_irq(pf->pdev->irq, i40e_intr, flags,
+				  pf->int_name, pf);
+
+		if (err) {
+			dev_info(&pf->pdev->dev,
+				 "MSI/legacy misc vector request failed, error %d\n",
+				 err);
+			return err;
+		}
+		i40e_enable_misc_int_causes(pf);
+		i40e_irq_dynamic_enable_icr0(pf);
+	}
+
+	return 0;
+}
+
+/**
  * i40e_setup_misc_vector - Setup the misc vector to handle non queue events
  * @pf: board private structure
  *
@@ -13888,6 +14016,125 @@ void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags)
 }
 
 /**
+ * i40e_check_recovery_mode - check if we are running transition firmware
+ * @pf: board private structure
+ *
+ * Check registers indicating the firmware runs in recovery mode. Sets the
+ * appropriate driver state.
+ *
+ * Returns true if the recovery mode was detected, false otherwise
+ **/
+static bool i40e_check_recovery_mode(struct i40e_pf *pf)
+{
+	u32 val = rd32(&pf->hw, I40E_GL_FWSTS);
+
+	if (val & I40E_GL_FWSTS_FWS1B_MASK) {
+		dev_notice(&pf->pdev->dev, "Firmware recovery mode detected. Limiting functionality.\n");
+		dev_notice(&pf->pdev->dev, "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
+		set_bit(__I40E_RECOVERY_MODE, pf->state);
+
+		return true;
+	}
+	if (test_and_clear_bit(__I40E_RECOVERY_MODE, pf->state))
+		dev_info(&pf->pdev->dev, "Reinitializing in normal mode with full functionality.\n");
+
+	return false;
+}
+
+/**
+ * i40e_init_recovery_mode - initialize subsystems needed in recovery mode
+ * @pf: board private structure
+ * @hw: ptr to the hardware info
+ *
+ * This function does a minimal setup of all subsystems needed for running
+ * recovery mode.
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw)
+{
+	struct i40e_vsi *vsi;
+	int err;
+	int v_idx;
+
+	pci_save_state(pf->pdev);
+
+	/* set up periodic task facility */
+	timer_setup(&pf->service_timer, i40e_service_timer, 0);
+	pf->service_timer_period = HZ;
+
+	INIT_WORK(&pf->service_task, i40e_service_task);
+	clear_bit(__I40E_SERVICE_SCHED, pf->state);
+
+	err = i40e_init_interrupt_scheme(pf);
+	if (err)
+		goto err_switch_setup;
+
+	/* The number of VSIs reported by the FW is the minimum guaranteed
+	 * to us; HW supports far more and we share the remaining pool with
+	 * the other PFs. We allocate space for more than the guarantee with
+	 * the understanding that we might not get them all later.
+	 */
+	if (pf->hw.func_caps.num_vsis < I40E_MIN_VSI_ALLOC)
+		pf->num_alloc_vsi = I40E_MIN_VSI_ALLOC;
+	else
+		pf->num_alloc_vsi = pf->hw.func_caps.num_vsis;
+
+	/* Set up the vsi struct and our local tracking of the MAIN PF vsi. */
+	pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *),
+			  GFP_KERNEL);
+	if (!pf->vsi) {
+		err = -ENOMEM;
+		goto err_switch_setup;
+	}
+
+	/* We allocate one VSI which is needed as absolute minimum
+	 * in order to register the netdev
+	 */
+	v_idx = i40e_vsi_mem_alloc(pf, I40E_VSI_MAIN);
+	if (v_idx < 0)
+		goto err_switch_setup;
+	pf->lan_vsi = v_idx;
+	vsi = pf->vsi[v_idx];
+	if (!vsi)
+		goto err_switch_setup;
+	vsi->alloc_queue_pairs = 1;
+	err = i40e_config_netdev(vsi);
+	if (err)
+		goto err_switch_setup;
+	err = register_netdev(vsi->netdev);
+	if (err)
+		goto err_switch_setup;
+	vsi->netdev_registered = true;
+	i40e_dbg_pf_init(pf);
+
+	err = i40e_setup_misc_vector_for_recovery_mode(pf);
+	if (err)
+		goto err_switch_setup;
+
+	/* tell the firmware that we're starting */
+	i40e_send_version(pf);
+
+	/* since everything's happy, start the service_task timer */
+	mod_timer(&pf->service_timer,
+		  round_jiffies(jiffies + pf->service_timer_period));
+
+	return 0;
+
+err_switch_setup:
+	i40e_reset_interrupt_capability(pf);
+	del_timer_sync(&pf->service_timer);
+	i40e_shutdown_adminq(hw);
+	iounmap(hw->hw_addr);
+	pci_disable_pcie_error_reporting(pf->pdev);
+	pci_release_mem_regions(pf->pdev);
+	pci_disable_device(pf->pdev);
+	kfree(pf);
+
+	return err;
+}
+
+/**
  * i40e_probe - Device initialization routine
  * @pdev: PCI device information struct
  * @ent: entry in i40e_pci_tbl
@@ -13984,6 +14231,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_LIST_HEAD(&pf->l3_flex_pit_list);
 	INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+	INIT_LIST_HEAD(&pf->ddp_old_prof);
 
 	/* set up the locks for the AQ, do this only once in probe
 	 * and destroy them only once in remove
@@ -14011,13 +14259,14 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Reset here to make sure all is clean and to define PF 'n' */
 	i40e_clear_hw(hw);
-	err = i40e_pf_reset(hw);
-	if (err) {
-		dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err);
-		goto err_pf_reset;
+	if (!i40e_check_recovery_mode(pf)) {
+		err = i40e_pf_reset(hw);
+		if (err) {
+			dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err);
+			goto err_pf_reset;
+		}
+		pf->pfr_count++;
 	}
-	pf->pfr_count++;
-
 	hw->aq.num_arq_entries = I40E_AQ_LEN;
 	hw->aq.num_asq_entries = I40E_AQ_LEN;
 	hw->aq.arq_buf_size = I40E_MAX_AQ_BUF_SIZE;
@@ -14042,7 +14291,11 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err) {
 		if (err == I40E_ERR_FIRMWARE_API_VERSION)
 			dev_info(&pdev->dev,
-				 "The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n");
+				 "The driver for the device stopped because the NVM image v%u.%u is newer than expected v%u.%u. You must install the most recent version of the network driver.\n",
+				 hw->aq.api_maj_ver,
+				 hw->aq.api_min_ver,
+				 I40E_FW_API_VERSION_MAJOR,
+				 I40E_FW_MINOR_VERSION(hw));
 		else
 			dev_info(&pdev->dev,
 				 "The driver for the device stopped because the device firmware failed to init. Try updating your NVM image.\n");
@@ -14051,19 +14304,28 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	i40e_get_oem_version(hw);
 
-	/* provide nvm, fw, api versions */
-	dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s\n",
+	/* provide nvm, fw, api versions, vendor:device id, subsys vendor:device id */
+	dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s [%04x:%04x] [%04x:%04x]\n",
 		 hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build,
 		 hw->aq.api_maj_ver, hw->aq.api_min_ver,
-		 i40e_nvm_version_str(hw));
+		 i40e_nvm_version_str(hw), hw->vendor_id, hw->device_id,
+		 hw->subsystem_vendor_id, hw->subsystem_device_id);
 
 	if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
 	    hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
 		dev_info(&pdev->dev,
-			 "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
+			 "The driver for the device detected a newer version of the NVM image v%u.%u than expected v%u.%u. Please install the most recent version of the network driver.\n",
+			 hw->aq.api_maj_ver,
+			 hw->aq.api_min_ver,
+			 I40E_FW_API_VERSION_MAJOR,
+			 I40E_FW_MINOR_VERSION(hw));
 	else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4)
 		dev_info(&pdev->dev,
-			 "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+			 "The driver for the device detected an older version of the NVM image v%u.%u than expected v%u.%u. Please update the NVM image.\n",
+			 hw->aq.api_maj_ver,
+			 hw->aq.api_min_ver,
+			 I40E_FW_API_VERSION_MAJOR,
+			 I40E_FW_MINOR_VERSION(hw));
 
 	i40e_verify_eeprom(pf);
 
@@ -14072,6 +14334,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_warn(&pdev->dev, "This device is a pre-production adapter/LOM. Please be aware there may be issues with your hardware. If you are experiencing problems please contact your Intel or hardware representative who provided you with this hardware.\n");
 
 	i40e_clear_pxe_mode(hw);
+
 	err = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
 	if (err)
 		goto err_adminq_setup;
@@ -14082,6 +14345,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_sw_init;
 	}
 
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state))
+		return i40e_init_recovery_mode(pf, hw);
+
 	err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
 				hw->func_caps.num_rx_qp, 0, 0);
 	if (err) {
@@ -14102,7 +14368,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 	if (pf->hw_features & I40E_HW_STOP_FW_LLDP) {
 		dev_info(&pdev->dev, "Stopping firmware LLDP agent.\n");
-		i40e_aq_stop_lldp(hw, true, NULL);
+		i40e_aq_stop_lldp(hw, true, false, NULL);
 	}
 
 	/* allow a platform config to override the HW addr */
@@ -14467,6 +14733,19 @@ static void i40e_remove(struct pci_dev *pdev)
 	if (pf->service_task.func)
 		cancel_work_sync(&pf->service_task);
 
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+		struct i40e_vsi *vsi = pf->vsi[0];
+
+		/* We know that we have allocated only one vsi for this PF,
+		 * it was just for registering netdevice, so the interface
+		 * could be visible in the 'ifconfig' output
+		 */
+		unregister_netdev(vsi->netdev);
+		free_netdev(vsi->netdev);
+
+		goto unmap;
+	}
+
 	/* Client close must be called explicitly here because the timer
 	 * has been stopped.
 	 */
@@ -14516,6 +14795,12 @@ static void i40e_remove(struct pci_dev *pdev)
 				 ret_code);
 	}
 
+unmap:
+	/* Free MSI/legacy interrupt 0 when in recovery mode. */
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+	    !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+		free_irq(pf->pdev->irq, pf);
+
 	/* shutdown the adminq */
 	i40e_shutdown_adminq(hw);
 
@@ -14528,7 +14813,8 @@ static void i40e_remove(struct pci_dev *pdev)
 	i40e_clear_interrupt_scheme(pf);
 	for (i = 0; i < pf->num_alloc_vsi; i++) {
 		if (pf->vsi[i]) {
-			i40e_vsi_clear_rings(pf->vsi[i]);
+			if (!test_bit(__I40E_RECOVERY_MODE, pf->state))
+				i40e_vsi_clear_rings(pf->vsi[i]);
 			i40e_vsi_clear(pf->vsi[i]);
 			pf->vsi[i] = NULL;
 		}
@@ -14736,6 +15022,11 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	wr32(hw, I40E_PFPM_WUFC,
 	     (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
 
+	/* Free MSI/legacy interrupt 0 when in recovery mode. */
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+	    !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+		free_irq(pf->pdev->irq, pf);
+
 	/* Since we're going to destroy queues during the
 	 * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this
 	 * whole section