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

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

1 files changed, 624 insertions, 186 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 214cd6eca405..69bff085acf7 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -6,8 +6,10 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include "ice.h"
+#include "ice_base.h"
 #include "ice_lib.h"
 #include "ice_dcb_lib.h"
+#include "ice_dcb_nl.h"
 
 #define DRV_VERSION_MAJOR 0
 #define DRV_VERSION_MINOR 8
@@ -42,6 +44,7 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)");
 static struct workqueue_struct *ice_wq;
 static const struct net_device_ops ice_netdev_safe_mode_ops;
 static const struct net_device_ops ice_netdev_ops;
+static int ice_vsi_open(struct ice_vsi *vsi);
 
 static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type);
 
@@ -159,7 +162,7 @@ unregister:
 	 * had an error
 	 */
 	if (status && vsi->netdev->reg_state == NETREG_REGISTERED) {
-		dev_err(&pf->pdev->dev,
+		dev_err(ice_pf_to_dev(pf),
 			"Could not add MAC filters error %d. Unregistering device\n",
 			status);
 		unregister_netdev(vsi->netdev);
@@ -435,42 +438,11 @@ static void ice_sync_fltr_subtask(struct ice_pf *pf)
 }
 
 /**
- * ice_dis_vsi - pause a VSI
- * @vsi: the VSI being paused
- * @locked: is the rtnl_lock already held
- */
-static void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
-{
-	if (test_bit(__ICE_DOWN, vsi->state))
-		return;
-
-	set_bit(__ICE_NEEDS_RESTART, vsi->state);
-
-	if (vsi->type == ICE_VSI_PF && vsi->netdev) {
-		if (netif_running(vsi->netdev)) {
-			if (!locked)
-				rtnl_lock();
-
-			ice_stop(vsi->netdev);
-
-			if (!locked)
-				rtnl_unlock();
-		} else {
-			ice_vsi_close(vsi);
-		}
-	}
-}
-
-/**
  * ice_pf_dis_all_vsi - Pause all VSIs on a PF
  * @pf: the PF
  * @locked: is the rtnl_lock already held
  */
-#ifdef CONFIG_DCB
-void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
-#else
 static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
-#endif /* CONFIG_DCB */
 {
 	int v;
 
@@ -524,7 +496,7 @@ ice_prepare_for_reset(struct ice_pf *pf)
  */
 static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 {
-	struct device *dev = &pf->pdev->dev;
+	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 
 	dev_dbg(dev, "reset_type 0x%x requested\n", reset_type);
@@ -636,8 +608,14 @@ static void ice_print_topo_conflict(struct ice_vsi *vsi)
 	switch (vsi->port_info->phy.link_info.topo_media_conflict) {
 	case ICE_AQ_LINK_TOPO_CONFLICT:
 	case ICE_AQ_LINK_MEDIA_CONFLICT:
+	case ICE_AQ_LINK_TOPO_UNREACH_PRT:
+	case ICE_AQ_LINK_TOPO_UNDRUTIL_PRT:
+	case ICE_AQ_LINK_TOPO_UNDRUTIL_MEDIA:
 		netdev_info(vsi->netdev, "Possible mis-configuration of the Ethernet port detected, please use the Intel(R) Ethernet Port Configuration Tool application to address the issue.\n");
 		break;
+	case ICE_AQ_LINK_TOPO_UNSUPP_MEDIA:
+		netdev_info(vsi->netdev, "Rx/Tx is disabled on this device because an unsupported module type was detected. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n");
+		break;
 	default:
 		break;
 	}
@@ -747,7 +725,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 		an = "False";
 
 	/* Get FEC mode requested based on PHY caps last SW configuration */
-	caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
+	caps = kzalloc(sizeof(*caps), GFP_KERNEL);
 	if (!caps) {
 		fec_req = "Unknown";
 		goto done;
@@ -767,7 +745,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 	else
 		fec_req = "NONE";
 
-	devm_kfree(&vsi->back->pdev->dev, caps);
+	kfree(caps);
 
 done:
 	netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Autoneg: %s, Flow Control: %s\n",
@@ -815,6 +793,7 @@ static int
 ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 	       u16 link_speed)
 {
+	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_phy_info *phy_info;
 	struct ice_vsi *vsi;
 	u16 old_link_speed;
@@ -832,7 +811,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 	 */
 	result = ice_update_link_info(pi);
 	if (result)
-		dev_dbg(&pf->pdev->dev,
+		dev_dbg(dev,
 			"Failed to update link status and re-enable link events for port %d\n",
 			pi->lport);
 
@@ -851,7 +830,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 
 		result = ice_aq_set_link_restart_an(pi, false, NULL);
 		if (result) {
-			dev_dbg(&pf->pdev->dev,
+			dev_dbg(dev,
 				"Failed to set link down, VSI %d error %d\n",
 				vsi->vsi_num, result);
 			return result;
@@ -947,7 +926,7 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 				!!(link_data->link_info & ICE_AQ_LINK_UP),
 				le16_to_cpu(link_data->link_speed));
 	if (status)
-		dev_dbg(&pf->pdev->dev,
+		dev_dbg(ice_pf_to_dev(pf),
 			"Could not process link event, error %d\n", status);
 
 	return status;
@@ -960,6 +939,7 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
  */
 static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 {
+	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_rq_event_info event;
 	struct ice_hw *hw = &pf->hw;
 	struct ice_ctl_q_info *cq;
@@ -981,8 +961,7 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		qtype = "Mailbox";
 		break;
 	default:
-		dev_warn(&pf->pdev->dev, "Unknown control queue type 0x%x\n",
-			 q_type);
+		dev_warn(dev, "Unknown control queue type 0x%x\n", q_type);
 		return 0;
 	}
 
@@ -994,15 +973,15 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		   PF_FW_ARQLEN_ARQCRIT_M)) {
 		oldval = val;
 		if (val & PF_FW_ARQLEN_ARQVFE_M)
-			dev_dbg(&pf->pdev->dev,
-				"%s Receive Queue VF Error detected\n", qtype);
+			dev_dbg(dev, "%s Receive Queue VF Error detected\n",
+				qtype);
 		if (val & PF_FW_ARQLEN_ARQOVFL_M) {
-			dev_dbg(&pf->pdev->dev,
+			dev_dbg(dev,
 				"%s Receive Queue Overflow Error detected\n",
 				qtype);
 		}
 		if (val & PF_FW_ARQLEN_ARQCRIT_M)
-			dev_dbg(&pf->pdev->dev,
+			dev_dbg(dev,
 				"%s Receive Queue Critical Error detected\n",
 				qtype);
 		val &= ~(PF_FW_ARQLEN_ARQVFE_M | PF_FW_ARQLEN_ARQOVFL_M |
@@ -1016,16 +995,14 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		   PF_FW_ATQLEN_ATQCRIT_M)) {
 		oldval = val;
 		if (val & PF_FW_ATQLEN_ATQVFE_M)
-			dev_dbg(&pf->pdev->dev,
+			dev_dbg(dev,
 				"%s Send Queue VF Error detected\n", qtype);
 		if (val & PF_FW_ATQLEN_ATQOVFL_M) {
-			dev_dbg(&pf->pdev->dev,
-				"%s Send Queue Overflow Error detected\n",
+			dev_dbg(dev, "%s Send Queue Overflow Error detected\n",
 				qtype);
 		}
 		if (val & PF_FW_ATQLEN_ATQCRIT_M)
-			dev_dbg(&pf->pdev->dev,
-				"%s Send Queue Critical Error detected\n",
+			dev_dbg(dev, "%s Send Queue Critical Error detected\n",
 				qtype);
 		val &= ~(PF_FW_ATQLEN_ATQVFE_M | PF_FW_ATQLEN_ATQOVFL_M |
 			 PF_FW_ATQLEN_ATQCRIT_M);
@@ -1034,8 +1011,7 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 	}
 
 	event.buf_len = cq->rq_buf_size;
-	event.msg_buf = devm_kzalloc(&pf->pdev->dev, event.buf_len,
-				     GFP_KERNEL);
+	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
 	if (!event.msg_buf)
 		return 0;
 
@@ -1047,8 +1023,7 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		if (ret == ICE_ERR_AQ_NO_WORK)
 			break;
 		if (ret) {
-			dev_err(&pf->pdev->dev,
-				"%s Receive Queue event error %d\n", qtype,
+			dev_err(dev, "%s Receive Queue event error %d\n", qtype,
 				ret);
 			break;
 		}
@@ -1058,8 +1033,7 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		switch (opcode) {
 		case ice_aqc_opc_get_link_status:
 			if (ice_handle_link_event(pf, &event))
-				dev_err(&pf->pdev->dev,
-					"Could not handle link event\n");
+				dev_err(dev, "Could not handle link event\n");
 			break;
 		case ice_mbx_opc_send_msg_to_pf:
 			ice_vc_process_vf_msg(pf, &event);
@@ -1071,14 +1045,14 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 			ice_dcb_process_lldp_set_mib_change(pf, &event);
 			break;
 		default:
-			dev_dbg(&pf->pdev->dev,
+			dev_dbg(dev,
 				"%s Receive Queue unknown event 0x%04x ignored\n",
 				qtype, opcode);
 			break;
 		}
 	} while (pending && (i++ < ICE_DFLT_IRQ_WORK));
 
-	devm_kfree(&pf->pdev->dev, event.msg_buf);
+	kfree(event.msg_buf);
 
 	return pending && (i == ICE_DFLT_IRQ_WORK);
 }
@@ -1222,6 +1196,7 @@ static void ice_service_timer(struct timer_list *t)
  */
 static void ice_handle_mdd_event(struct ice_pf *pf)
 {
+	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	bool mdd_detected = false;
 	u32 reg;
@@ -1243,7 +1218,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 				GL_MDET_TX_PQM_QNUM_S);
 
 		if (netif_msg_tx_err(pf))
-			dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
+			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
 		wr32(hw, GL_MDET_TX_PQM, 0xffffffff);
 		mdd_detected = true;
@@ -1261,7 +1236,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 				GL_MDET_TX_TCLAN_QNUM_S);
 
 		if (netif_msg_rx_err(pf))
-			dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
+			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
 		wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff);
 		mdd_detected = true;
@@ -1279,7 +1254,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 				GL_MDET_RX_QNUM_S);
 
 		if (netif_msg_rx_err(pf))
-			dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
+			dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
 		wr32(hw, GL_MDET_RX, 0xffffffff);
 		mdd_detected = true;
@@ -1291,21 +1266,21 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		reg = rd32(hw, PF_MDET_TX_PQM);
 		if (reg & PF_MDET_TX_PQM_VALID_M) {
 			wr32(hw, PF_MDET_TX_PQM, 0xFFFF);
-			dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n");
+			dev_info(dev, "TX driver issue detected, PF reset issued\n");
 			pf_mdd_detected = true;
 		}
 
 		reg = rd32(hw, PF_MDET_TX_TCLAN);
 		if (reg & PF_MDET_TX_TCLAN_VALID_M) {
 			wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF);
-			dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n");
+			dev_info(dev, "TX driver issue detected, PF reset issued\n");
 			pf_mdd_detected = true;
 		}
 
 		reg = rd32(hw, PF_MDET_RX);
 		if (reg & PF_MDET_RX_VALID_M) {
 			wr32(hw, PF_MDET_RX, 0xFFFF);
-			dev_info(&pf->pdev->dev, "RX driver issue detected, PF reset issued\n");
+			dev_info(dev, "RX driver issue detected, PF reset issued\n");
 			pf_mdd_detected = true;
 		}
 		/* Queue belongs to the PF initiate a reset */
@@ -1325,7 +1300,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (reg & VP_MDET_TX_PQM_VALID_M) {
 			wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF);
 			vf_mdd_detected = true;
-			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
+			dev_info(dev, "TX driver issue detected on VF %d\n",
 				 i);
 		}
 
@@ -1333,7 +1308,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (reg & VP_MDET_TX_TCLAN_VALID_M) {
 			wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF);
 			vf_mdd_detected = true;
-			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
+			dev_info(dev, "TX driver issue detected on VF %d\n",
 				 i);
 		}
 
@@ -1341,7 +1316,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (reg & VP_MDET_TX_TDPU_VALID_M) {
 			wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF);
 			vf_mdd_detected = true;
-			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
+			dev_info(dev, "TX driver issue detected on VF %d\n",
 				 i);
 		}
 
@@ -1349,7 +1324,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (reg & VP_MDET_RX_VALID_M) {
 			wr32(hw, VP_MDET_RX(i), 0xFFFF);
 			vf_mdd_detected = true;
-			dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
+			dev_info(dev, "RX driver issue detected on VF %d\n",
 				 i);
 		}
 
@@ -1357,7 +1332,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 			vf->num_mdd_events++;
 			if (vf->num_mdd_events &&
 			    vf->num_mdd_events <= ICE_MDD_EVENTS_THRESHOLD)
-				dev_info(&pf->pdev->dev,
+				dev_info(dev,
 					 "VF %d has had %llu MDD events since last boot, Admin might need to reload AVF driver with this number of events\n",
 					 i, vf->num_mdd_events);
 		}
@@ -1393,7 +1368,7 @@ static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up)
 
 	pi = vsi->port_info;
 
-	pcaps = devm_kzalloc(dev, sizeof(*pcaps), GFP_KERNEL);
+	pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL);
 	if (!pcaps)
 		return -ENOMEM;
 
@@ -1412,7 +1387,7 @@ static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up)
 	    link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP))
 		goto out;
 
-	cfg = devm_kzalloc(dev, sizeof(*cfg), GFP_KERNEL);
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
 	if (!cfg) {
 		retcode = -ENOMEM;
 		goto out;
@@ -1437,9 +1412,9 @@ static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up)
 		retcode = -EIO;
 	}
 
-	devm_kfree(dev, cfg);
+	kfree(cfg);
 out:
-	devm_kfree(dev, pcaps);
+	kfree(pcaps);
 	return retcode;
 }
 
@@ -1551,6 +1526,44 @@ static void ice_set_ctrlq_len(struct ice_hw *hw)
 }
 
 /**
+ * ice_schedule_reset - schedule a reset
+ * @pf: board private structure
+ * @reset: reset being requested
+ */
+int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+
+	/* bail out if earlier reset has failed */
+	if (test_bit(__ICE_RESET_FAILED, pf->state)) {
+		dev_dbg(dev, "earlier reset has failed\n");
+		return -EIO;
+	}
+	/* bail if reset/recovery already in progress */
+	if (ice_is_reset_in_progress(pf->state)) {
+		dev_dbg(dev, "Reset already in progress\n");
+		return -EBUSY;
+	}
+
+	switch (reset) {
+	case ICE_RESET_PFR:
+		set_bit(__ICE_PFR_REQ, pf->state);
+		break;
+	case ICE_RESET_CORER:
+		set_bit(__ICE_CORER_REQ, pf->state);
+		break;
+	case ICE_RESET_GLOBR:
+		set_bit(__ICE_GLOBR_REQ, pf->state);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ice_service_task_schedule(pf);
+	return 0;
+}
+
+/**
  * ice_irq_affinity_notify - Callback for affinity changes
  * @notify: context as to what irq was changed
  * @mask: the new affinity mask
@@ -1604,11 +1617,13 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 	int q_vectors = vsi->num_q_vectors;
 	struct ice_pf *pf = vsi->back;
 	int base = vsi->base_vector;
+	struct device *dev;
 	int rx_int_idx = 0;
 	int tx_int_idx = 0;
 	int vector, err;
 	int irq_num;
 
+	dev = ice_pf_to_dev(pf);
 	for (vector = 0; vector < q_vectors; vector++) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[vector];
 
@@ -1628,8 +1643,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 			/* skip this unused q_vector */
 			continue;
 		}
-		err = devm_request_irq(&pf->pdev->dev, irq_num,
-				       vsi->irq_handler, 0,
+		err = devm_request_irq(dev, irq_num, vsi->irq_handler, 0,
 				       q_vector->name, q_vector);
 		if (err) {
 			netdev_err(vsi->netdev,
@@ -1655,12 +1669,331 @@ free_q_irqs:
 		irq_num = pf->msix_entries[base + vector].vector,
 		irq_set_affinity_notifier(irq_num, NULL);
 		irq_set_affinity_hint(irq_num, NULL);
-		devm_free_irq(&pf->pdev->dev, irq_num, &vsi->q_vectors[vector]);
+		devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
 	}
 	return err;
 }
 
 /**
+ * ice_xdp_alloc_setup_rings - Allocate and setup Tx rings for XDP
+ * @vsi: VSI to setup Tx rings used by XDP
+ *
+ * Return 0 on success and negative value on error
+ */
+static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
+{
+	struct device *dev = &vsi->back->pdev->dev;
+	int i;
+
+	for (i = 0; i < vsi->num_xdp_txq; i++) {
+		u16 xdp_q_idx = vsi->alloc_txq + i;
+		struct ice_ring *xdp_ring;
+
+		xdp_ring = kzalloc(sizeof(*xdp_ring), GFP_KERNEL);
+
+		if (!xdp_ring)
+			goto free_xdp_rings;
+
+		xdp_ring->q_index = xdp_q_idx;
+		xdp_ring->reg_idx = vsi->txq_map[xdp_q_idx];
+		xdp_ring->ring_active = false;
+		xdp_ring->vsi = vsi;
+		xdp_ring->netdev = NULL;
+		xdp_ring->dev = dev;
+		xdp_ring->count = vsi->num_tx_desc;
+		vsi->xdp_rings[i] = xdp_ring;
+		if (ice_setup_tx_ring(xdp_ring))
+			goto free_xdp_rings;
+		ice_set_ring_xdp(xdp_ring);
+		xdp_ring->xsk_umem = ice_xsk_umem(xdp_ring);
+	}
+
+	return 0;
+
+free_xdp_rings:
+	for (; i >= 0; i--)
+		if (vsi->xdp_rings[i] && vsi->xdp_rings[i]->desc)
+			ice_free_tx_ring(vsi->xdp_rings[i]);
+	return -ENOMEM;
+}
+
+/**
+ * ice_vsi_assign_bpf_prog - set or clear bpf prog pointer on VSI
+ * @vsi: VSI to set the bpf prog on
+ * @prog: the bpf prog pointer
+ */
+static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog)
+{
+	struct bpf_prog *old_prog;
+	int i;
+
+	old_prog = xchg(&vsi->xdp_prog, prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	ice_for_each_rxq(vsi, i)
+		WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog);
+}
+
+/**
+ * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
+ * @vsi: VSI to bring up Tx rings used by XDP
+ * @prog: bpf program that will be assigned to VSI
+ *
+ * Return 0 on success and negative value on error
+ */
+int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
+{
+	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	int xdp_rings_rem = vsi->num_xdp_txq;
+	struct ice_pf *pf = vsi->back;
+	struct ice_qs_cfg xdp_qs_cfg = {
+		.qs_mutex = &pf->avail_q_mutex,
+		.pf_map = pf->avail_txqs,
+		.pf_map_size = pf->max_pf_txqs,
+		.q_count = vsi->num_xdp_txq,
+		.scatter_count = ICE_MAX_SCATTER_TXQS,
+		.vsi_map = vsi->txq_map,
+		.vsi_map_offset = vsi->alloc_txq,
+		.mapping_mode = ICE_VSI_MAP_CONTIG
+	};
+	enum ice_status status;
+	struct device *dev;
+	int i, v_idx;
+
+	dev = ice_pf_to_dev(pf);
+	vsi->xdp_rings = devm_kcalloc(dev, vsi->num_xdp_txq,
+				      sizeof(*vsi->xdp_rings), GFP_KERNEL);
+	if (!vsi->xdp_rings)
+		return -ENOMEM;
+
+	vsi->xdp_mapping_mode = xdp_qs_cfg.mapping_mode;
+	if (__ice_vsi_get_qs(&xdp_qs_cfg))
+		goto err_map_xdp;
+
+	if (ice_xdp_alloc_setup_rings(vsi))
+		goto clear_xdp_rings;
+
+	/* follow the logic from ice_vsi_map_rings_to_vectors */
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+		int xdp_rings_per_v, q_id, q_base;
+
+		xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem,
+					       vsi->num_q_vectors - v_idx);
+		q_base = vsi->num_xdp_txq - xdp_rings_rem;
+
+		for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) {
+			struct ice_ring *xdp_ring = vsi->xdp_rings[q_id];
+
+			xdp_ring->q_vector = q_vector;
+			xdp_ring->next = q_vector->tx.ring;
+			q_vector->tx.ring = xdp_ring;
+		}
+		xdp_rings_rem -= xdp_rings_per_v;
+	}
+
+	/* omit the scheduler update if in reset path; XDP queues will be
+	 * taken into account at the end of ice_vsi_rebuild, where
+	 * ice_cfg_vsi_lan is being called
+	 */
+	if (ice_is_reset_in_progress(pf->state))
+		return 0;
+
+	/* tell the Tx scheduler that right now we have
+	 * additional queues
+	 */
+	for (i = 0; i < vsi->tc_cfg.numtc; i++)
+		max_txqs[i] = vsi->num_txq + vsi->num_xdp_txq;
+
+	status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+				 max_txqs);
+	if (status) {
+		dev_err(dev, "Failed VSI LAN queue config for XDP, error:%d\n",
+			status);
+		goto clear_xdp_rings;
+	}
+	ice_vsi_assign_bpf_prog(vsi, prog);
+
+	return 0;
+clear_xdp_rings:
+	for (i = 0; i < vsi->num_xdp_txq; i++)
+		if (vsi->xdp_rings[i]) {
+			kfree_rcu(vsi->xdp_rings[i], rcu);
+			vsi->xdp_rings[i] = NULL;
+		}
+
+err_map_xdp:
+	mutex_lock(&pf->avail_q_mutex);
+	for (i = 0; i < vsi->num_xdp_txq; i++) {
+		clear_bit(vsi->txq_map[i + vsi->alloc_txq], pf->avail_txqs);
+		vsi->txq_map[i + vsi->alloc_txq] = ICE_INVAL_Q_INDEX;
+	}
+	mutex_unlock(&pf->avail_q_mutex);
+
+	devm_kfree(dev, vsi->xdp_rings);
+	return -ENOMEM;
+}
+
+/**
+ * ice_destroy_xdp_rings - undo the configuration made by ice_prepare_xdp_rings
+ * @vsi: VSI to remove XDP rings
+ *
+ * Detach XDP rings from irq vectors, clean up the PF bitmap and free
+ * resources
+ */
+int ice_destroy_xdp_rings(struct ice_vsi *vsi)
+{
+	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	struct ice_pf *pf = vsi->back;
+	int i, v_idx;
+
+	/* q_vectors are freed in reset path so there's no point in detaching
+	 * rings; in case of rebuild being triggered not from reset reset bits
+	 * in pf->state won't be set, so additionally check first q_vector
+	 * against NULL
+	 */
+	if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0])
+		goto free_qmap;
+
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+		struct ice_ring *ring;
+
+		ice_for_each_ring(ring, q_vector->tx)
+			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
+				break;
+
+		/* restore the value of last node prior to XDP setup */
+		q_vector->tx.ring = ring;
+	}
+
+free_qmap:
+	mutex_lock(&pf->avail_q_mutex);
+	for (i = 0; i < vsi->num_xdp_txq; i++) {
+		clear_bit(vsi->txq_map[i + vsi->alloc_txq], pf->avail_txqs);
+		vsi->txq_map[i + vsi->alloc_txq] = ICE_INVAL_Q_INDEX;
+	}
+	mutex_unlock(&pf->avail_q_mutex);
+
+	for (i = 0; i < vsi->num_xdp_txq; i++)
+		if (vsi->xdp_rings[i]) {
+			if (vsi->xdp_rings[i]->desc)
+				ice_free_tx_ring(vsi->xdp_rings[i]);
+			kfree_rcu(vsi->xdp_rings[i], rcu);
+			vsi->xdp_rings[i] = NULL;
+		}
+
+	devm_kfree(ice_pf_to_dev(pf), vsi->xdp_rings);
+	vsi->xdp_rings = NULL;
+
+	if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0])
+		return 0;
+
+	ice_vsi_assign_bpf_prog(vsi, NULL);
+
+	/* notify Tx scheduler that we destroyed XDP queues and bring
+	 * back the old number of child nodes
+	 */
+	for (i = 0; i < vsi->tc_cfg.numtc; i++)
+		max_txqs[i] = vsi->num_txq;
+
+	return ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+			       max_txqs);
+}
+
+/**
+ * ice_xdp_setup_prog - Add or remove XDP eBPF program
+ * @vsi: VSI to setup XDP for
+ * @prog: XDP program
+ * @extack: netlink extended ack
+ */
+static int
+ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
+		   struct netlink_ext_ack *extack)
+{
+	int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;
+	bool if_running = netif_running(vsi->netdev);
+	int ret = 0, xdp_ring_err = 0;
+
+	if (frame_size > vsi->rx_buf_len) {
+		NL_SET_ERR_MSG_MOD(extack, "MTU too large for loading XDP");
+		return -EOPNOTSUPP;
+	}
+
+	/* need to stop netdev while setting up the program for Rx rings */
+	if (if_running && !test_and_set_bit(__ICE_DOWN, vsi->state)) {
+		ret = ice_down(vsi);
+		if (ret) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Preparing device for XDP attach failed");
+			return ret;
+		}
+	}
+
+	if (!ice_is_xdp_ena_vsi(vsi) && prog) {
+		vsi->num_xdp_txq = vsi->alloc_txq;
+		xdp_ring_err = ice_prepare_xdp_rings(vsi, prog);
+		if (xdp_ring_err)
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Setting up XDP Tx resources failed");
+	} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
+		xdp_ring_err = ice_destroy_xdp_rings(vsi);
+		if (xdp_ring_err)
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Freeing XDP Tx resources failed");
+	} else {
+		ice_vsi_assign_bpf_prog(vsi, prog);
+	}
+
+	if (if_running)
+		ret = ice_up(vsi);
+
+	if (!ret && prog && vsi->xsk_umems) {
+		int i;
+
+		ice_for_each_rxq(vsi, i) {
+			struct ice_ring *rx_ring = vsi->rx_rings[i];
+
+			if (rx_ring->xsk_umem)
+				napi_schedule(&rx_ring->q_vector->napi);
+		}
+	}
+
+	return (ret || xdp_ring_err) ? -ENOMEM : 0;
+}
+
+/**
+ * ice_xdp - implements XDP handler
+ * @dev: netdevice
+ * @xdp: XDP command
+ */
+static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	struct ice_netdev_priv *np = netdev_priv(dev);
+	struct ice_vsi *vsi = np->vsi;
+
+	if (vsi->type != ICE_VSI_PF) {
+		NL_SET_ERR_MSG_MOD(xdp->extack,
+				   "XDP can be loaded only on PF VSI");
+		return -EINVAL;
+	}
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
+	case XDP_QUERY_PROG:
+		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
+		return 0;
+	case XDP_SETUP_XSK_UMEM:
+		return ice_xsk_umem_setup(vsi, xdp->xsk.umem,
+					  xdp->xsk.queue_id);
+	default:
+		return -EINVAL;
+	}
+}
+
+/**
  * ice_ena_misc_vector - enable the non-queue interrupts
  * @pf: board private structure
  */
@@ -1698,8 +2031,10 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 	struct ice_pf *pf = (struct ice_pf *)data;
 	struct ice_hw *hw = &pf->hw;
 	irqreturn_t ret = IRQ_NONE;
+	struct device *dev;
 	u32 oicr, ena_mask;
 
+	dev = ice_pf_to_dev(pf);
 	set_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state);
 	set_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state);
 
@@ -1735,8 +2070,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 		else if (reset == ICE_RESET_EMPR)
 			pf->empr_count++;
 		else
-			dev_dbg(&pf->pdev->dev, "Invalid reset type %d\n",
-				reset);
+			dev_dbg(dev, "Invalid reset type %d\n", reset);
 
 		/* If a reset cycle isn't already in progress, we set a bit in
 		 * pf->state so that the service task can start a reset/rebuild.
@@ -1770,8 +2104,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 	if (oicr & PFINT_OICR_HMC_ERR_M) {
 		ena_mask &= ~PFINT_OICR_HMC_ERR_M;
-		dev_dbg(&pf->pdev->dev,
-			"HMC Error interrupt - info 0x%x, data 0x%x\n",
+		dev_dbg(dev, "HMC Error interrupt - info 0x%x, data 0x%x\n",
 			rd32(hw, PFHMC_ERRORINFO),
 			rd32(hw, PFHMC_ERRORDATA));
 	}
@@ -1779,8 +2112,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 	/* Report any remaining unexpected interrupts */
 	oicr &= ena_mask;
 	if (oicr) {
-		dev_dbg(&pf->pdev->dev, "unhandled interrupt oicr=0x%08x\n",
-			oicr);
+		dev_dbg(dev, "unhandled interrupt oicr=0x%08x\n", oicr);
 		/* If a critical error is pending there is no choice but to
 		 * reset the device.
 		 */
@@ -1838,7 +2170,7 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
 
 	if (pf->msix_entries) {
 		synchronize_irq(pf->msix_entries[pf->oicr_idx].vector);
-		devm_free_irq(&pf->pdev->dev,
+		devm_free_irq(ice_pf_to_dev(pf),
 			      pf->msix_entries[pf->oicr_idx].vector, pf);
 	}
 
@@ -1882,13 +2214,13 @@ static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx)
  */
 static int ice_req_irq_msix_misc(struct ice_pf *pf)
 {
+	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	int oicr_idx, err = 0;
 
 	if (!pf->int_name[0])
 		snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
-			 dev_driver_string(&pf->pdev->dev),
-			 dev_name(&pf->pdev->dev));
+			 dev_driver_string(dev), dev_name(dev));
 
 	/* Do not request IRQ but do enable OICR interrupt since settings are
 	 * lost during reset. Note that this function is called only during
@@ -1905,12 +2237,10 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 	pf->num_avail_sw_msix -= 1;
 	pf->oicr_idx = oicr_idx;
 
-	err = devm_request_irq(&pf->pdev->dev,
-			       pf->msix_entries[pf->oicr_idx].vector,
+	err = devm_request_irq(dev, pf->msix_entries[pf->oicr_idx].vector,
 			       ice_misc_intr, 0, pf->int_name, pf);
 	if (err) {
-		dev_err(&pf->pdev->dev,
-			"devm_request_irq for %s failed: %d\n",
+		dev_err(dev, "devm_request_irq for %s failed: %d\n",
 			pf->int_name, err);
 		ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
 		pf->num_avail_sw_msix += 1;
@@ -2043,7 +2373,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 	ice_set_ops(netdev);
 
 	if (vsi->type == ICE_VSI_PF) {
-		SET_NETDEV_DEV(netdev, &pf->pdev->dev);
+		SET_NETDEV_DEV(netdev, ice_pf_to_dev(pf));
 		ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr);
 		ether_addr_copy(netdev->dev_addr, mac_addr);
 		ether_addr_copy(netdev->perm_addr, mac_addr);
@@ -2219,6 +2549,11 @@ static int ice_setup_pf_sw(struct ice_pf *pf)
 		status = -ENODEV;
 		goto unroll_vsi_setup;
 	}
+	/* netdev has to be configured before setting frame size */
+	ice_vsi_cfg_frame_size(vsi);
+
+	/* Setup DCB netlink interface */
+	ice_dcbnl_setup(vsi);
 
 	/* registering the NAPI handler requires both the queues and
 	 * netdev to be created, which are done in ice_pf_vsi_setup()
@@ -2300,6 +2635,7 @@ static void ice_deinit_pf(struct ice_pf *pf)
 {
 	ice_service_task_stop(pf);
 	mutex_destroy(&pf->sw_mutex);
+	mutex_destroy(&pf->tc_mutex);
 	mutex_destroy(&pf->avail_q_mutex);
 
 	if (pf->avail_txqs) {
@@ -2349,6 +2685,7 @@ static int ice_init_pf(struct ice_pf *pf)
 	ice_set_pf_caps(pf);
 
 	mutex_init(&pf->sw_mutex);
+	mutex_init(&pf->tc_mutex);
 
 	/* setup service timer and periodic service task */
 	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
@@ -2363,7 +2700,7 @@ static int ice_init_pf(struct ice_pf *pf)
 
 	pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL);
 	if (!pf->avail_rxqs) {
-		devm_kfree(&pf->pdev->dev, pf->avail_txqs);
+		devm_kfree(ice_pf_to_dev(pf), pf->avail_txqs);
 		pf->avail_txqs = NULL;
 		return -ENOMEM;
 	}
@@ -2380,6 +2717,7 @@ static int ice_init_pf(struct ice_pf *pf)
  */
 static int ice_ena_msix_range(struct ice_pf *pf)
 {
+	struct device *dev = ice_pf_to_dev(pf);
 	int v_left, v_actual, v_budget = 0;
 	int needed, err, i;
 
@@ -2400,7 +2738,7 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 	v_budget += needed;
 	v_left -= needed;
 
-	pf->msix_entries = devm_kcalloc(&pf->pdev->dev, v_budget,
+	pf->msix_entries = devm_kcalloc(dev, v_budget,
 					sizeof(*pf->msix_entries), GFP_KERNEL);
 
 	if (!pf->msix_entries) {
@@ -2416,13 +2754,13 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 					 ICE_MIN_MSIX, v_budget);
 
 	if (v_actual < 0) {
-		dev_err(&pf->pdev->dev, "unable to reserve MSI-X vectors\n");
+		dev_err(dev, "unable to reserve MSI-X vectors\n");
 		err = v_actual;
 		goto msix_err;
 	}
 
 	if (v_actual < v_budget) {
-		dev_warn(&pf->pdev->dev,
+		dev_warn(dev,
 			 "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
 			 v_budget, v_actual);
 /* 2 vectors for LAN (traffic + OICR) */
@@ -2441,11 +2779,11 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 	return v_actual;
 
 msix_err:
-	devm_kfree(&pf->pdev->dev, pf->msix_entries);
+	devm_kfree(dev, pf->msix_entries);
 	goto exit_err;
 
 no_hw_vecs_left_err:
-	dev_err(&pf->pdev->dev,
+	dev_err(dev,
 		"not enough device MSI-X vectors. requested = %d, available = %d\n",
 		needed, v_left);
 	err = -ERANGE;
@@ -2461,7 +2799,7 @@ exit_err:
 static void ice_dis_msix(struct ice_pf *pf)
 {
 	pci_disable_msix(pf->pdev);
-	devm_kfree(&pf->pdev->dev, pf->msix_entries);
+	devm_kfree(ice_pf_to_dev(pf), pf->msix_entries);
 	pf->msix_entries = NULL;
 }
 
@@ -2474,7 +2812,7 @@ static void ice_clear_interrupt_scheme(struct ice_pf *pf)
 	ice_dis_msix(pf);
 
 	if (pf->irq_tracker) {
-		devm_kfree(&pf->pdev->dev, pf->irq_tracker);
+		devm_kfree(ice_pf_to_dev(pf), pf->irq_tracker);
 		pf->irq_tracker = NULL;
 	}
 }
@@ -2494,7 +2832,7 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 
 	/* set up vector assignment tracking */
 	pf->irq_tracker =
-		devm_kzalloc(&pf->pdev->dev, sizeof(*pf->irq_tracker) +
+		devm_kzalloc(ice_pf_to_dev(pf), sizeof(*pf->irq_tracker) +
 			     (sizeof(u16) * vectors), GFP_KERNEL);
 	if (!pf->irq_tracker) {
 		ice_dis_msix(pf);
@@ -2510,6 +2848,52 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 }
 
 /**
+ * ice_vsi_recfg_qs - Change the number of queues on a VSI
+ * @vsi: VSI being changed
+ * @new_rx: new number of Rx queues
+ * @new_tx: new number of Tx queues
+ *
+ * Only change the number of queues if new_tx, or new_rx is non-0.
+ *
+ * Returns 0 on success.
+ */
+int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx)
+{
+	struct ice_pf *pf = vsi->back;
+	int err = 0, timeout = 50;
+
+	if (!new_rx && !new_tx)
+		return -EINVAL;
+
+	while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) {
+		timeout--;
+		if (!timeout)
+			return -EBUSY;
+		usleep_range(1000, 2000);
+	}
+
+	if (new_tx)
+		vsi->req_txq = new_tx;
+	if (new_rx)
+		vsi->req_rxq = new_rx;
+
+	/* set for the next time the netdev is started */
+	if (!netif_running(vsi->netdev)) {
+		ice_vsi_rebuild(vsi, false);
+		dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n");
+		goto done;
+	}
+
+	ice_vsi_close(vsi);
+	ice_vsi_rebuild(vsi, false);
+	ice_pf_dcb_recfg(pf);
+	ice_vsi_open(vsi);
+done:
+	clear_bit(__ICE_CFG_BUSY, pf->state);
+	return err;
+}
+
+/**
  * ice_log_pkg_init - log result of DDP package load
  * @hw: pointer to hardware info
  * @status: status of package load
@@ -2518,7 +2902,7 @@ static void
 ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status)
 {
 	struct ice_pf *pf = (struct ice_pf *)hw->back;
-	struct device *dev = &pf->pdev->dev;
+	struct device *dev = ice_pf_to_dev(pf);
 
 	switch (*status) {
 	case ICE_SUCCESS:
@@ -2598,7 +2982,7 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status)
 				ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR);
 		break;
 	case ICE_ERR_AQ_ERROR:
-		switch (hw->adminq.sq_last_status) {
+		switch (hw->pkg_dwnld_status) {
 		case ICE_AQ_RC_ENOSEC:
 		case ICE_AQ_RC_EBADSIG:
 			dev_err(dev,
@@ -2637,7 +3021,7 @@ static void
 ice_load_pkg(const struct firmware *firmware, struct ice_pf *pf)
 {
 	enum ice_status status = ICE_ERR_PARAM;
-	struct device *dev = &pf->pdev->dev;
+	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 
 	/* Load DDP Package */
@@ -2677,7 +3061,7 @@ ice_load_pkg(const struct firmware *firmware, struct ice_pf *pf)
 static void ice_verify_cacheline_size(struct ice_pf *pf)
 {
 	if (rd32(&pf->hw, GLPCI_CNF2) & GLPCI_CNF2_CACHELINE_SIZE_M)
-		dev_warn(&pf->pdev->dev,
+		dev_warn(ice_pf_to_dev(pf),
 			 "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n",
 			 ICE_CACHE_LINE_BYTES);
 }
@@ -2747,7 +3131,7 @@ static void ice_request_fw(struct ice_pf *pf)
 {
 	char *opt_fw_filename = ice_get_opt_fw_name(pf);
 	const struct firmware *firmware = NULL;
-	struct device *dev = &pf->pdev->dev;
+	struct device *dev = ice_pf_to_dev(pf);
 	int err = 0;
 
 	/* optional device-specific DDP (if present) overrides the default DDP
@@ -2831,6 +3215,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	hw = &pf->hw;
 	hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0];
+	pci_save_state(pdev);
+
 	hw->back = pf;
 	hw->vendor_id = pdev->vendor;
 	hw->device_id = pdev->device;
@@ -2936,7 +3322,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	err = ice_setup_pf_sw(pf);
 	if (err) {
-		dev_err(dev, "probe failed due to setup PF switch:%d\n", err);
+		dev_err(dev, "probe failed due to setup PF switch: %d\n", err);
 		goto err_alloc_sw_unroll;
 	}
 
@@ -2976,12 +3362,15 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		ice_cfg_lldp_mib_change(&pf->hw, true);
 	}
 
+	/* print PCI link speed and width */
+	pcie_print_link_status(pf->pdev);
+
 	return 0;
 
 err_alloc_sw_unroll:
 	set_bit(__ICE_SERVICE_DIS, pf->state);
 	set_bit(__ICE_DOWN, pf->state);
-	devm_kfree(&pf->pdev->dev, pf->first_sw);
+	devm_kfree(dev, pf->first_sw);
 err_msix_misc_unroll:
 	ice_free_irq_msix_misc(pf);
 err_init_interrupt_unroll:
@@ -3027,12 +3416,13 @@ static void ice_remove(struct pci_dev *pdev)
 	}
 	ice_deinit_pf(pf);
 	ice_deinit_hw(&pf->hw);
-	ice_clear_interrupt_scheme(pf);
 	/* Issue a PFR as part of the prescribed driver unload flow.  Do not
 	 * do it via ice_schedule_reset() since there is no need to rebuild
 	 * and the service task is already stopped.
 	 */
 	ice_reset(&pf->hw, ICE_RESET_PFR);
+	pci_wait_for_pending_transaction(pdev);
+	ice_clear_interrupt_scheme(pf);
 	pci_disable_pcie_error_reporting(pdev);
 }
 
@@ -3347,6 +3737,48 @@ static void ice_set_rx_mode(struct net_device *netdev)
 }
 
 /**
+ * ice_set_tx_maxrate - NDO callback to set the maximum per-queue bitrate
+ * @netdev: network interface device structure
+ * @queue_index: Queue ID
+ * @maxrate: maximum bandwidth in Mbps
+ */
+static int
+ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	enum ice_status status;
+	u16 q_handle;
+	u8 tc;
+
+	/* Validate maxrate requested is within permitted range */
+	if (maxrate && (maxrate > (ICE_SCHED_MAX_BW / 1000))) {
+		netdev_err(netdev,
+			   "Invalid max rate %d specified for the queue %d\n",
+			   maxrate, queue_index);
+		return -EINVAL;
+	}
+
+	q_handle = vsi->tx_rings[queue_index]->q_handle;
+	tc = ice_dcb_get_tc(vsi, queue_index);
+
+	/* Set BW back to default, when user set maxrate to 0 */
+	if (!maxrate)
+		status = ice_cfg_q_bw_dflt_lmt(vsi->port_info, vsi->idx, tc,
+					       q_handle, ICE_MAX_BW);
+	else
+		status = ice_cfg_q_bw_lmt(vsi->port_info, vsi->idx, tc,
+					  q_handle, ICE_MAX_BW, maxrate * 1000);
+	if (status) {
+		netdev_err(netdev,
+			   "Unable to set Tx max rate, error %d\n", status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
  * ice_fdb_add - add an entry to the hardware database
  * @ndm: the input from the stack
  * @tb: pointer to array of nladdr (unused)
@@ -3426,6 +3858,7 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
 	int ret = 0;
 
 	/* Don't set any netdev advanced features with device in Safe Mode */
@@ -3435,6 +3868,13 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
 		return ret;
 	}
 
+	/* Do not change setting during reset */
+	if (ice_is_reset_in_progress(pf->state)) {
+		dev_err(&vsi->back->pdev->dev,
+			"Device is resetting, changing advanced netdev features temporarily unavailable.\n");
+		return -EBUSY;
+	}
+
 	/* Multiple features can be changed in one call so keep features in
 	 * separate if/else statements to guarantee each feature is checked
 	 */
@@ -3505,6 +3945,8 @@ int ice_vsi_cfg(struct ice_vsi *vsi)
 	ice_vsi_cfg_dcb_rings(vsi);
 
 	err = ice_vsi_cfg_lan_txqs(vsi);
+	if (!err && ice_is_xdp_ena_vsi(vsi))
+		err = ice_vsi_cfg_xdp_txqs(vsi);
 	if (!err)
 		err = ice_vsi_cfg_rxqs(vsi);
 
@@ -3920,6 +4362,13 @@ int ice_down(struct ice_vsi *vsi)
 		netdev_err(vsi->netdev,
 			   "Failed stop Tx rings, VSI %d error %d\n",
 			   vsi->vsi_num, tx_err);
+	if (!tx_err && ice_is_xdp_ena_vsi(vsi)) {
+		tx_err = ice_vsi_stop_xdp_tx_rings(vsi);
+		if (tx_err)
+			netdev_err(vsi->netdev,
+				   "Failed stop XDP rings, VSI %d error %d\n",
+				   vsi->vsi_num, tx_err);
+	}
 
 	rx_err = ice_vsi_stop_rx_rings(vsi);
 	if (rx_err)
@@ -3970,8 +4419,13 @@ int ice_vsi_setup_tx_rings(struct ice_vsi *vsi)
 	}
 
 	ice_for_each_txq(vsi, i) {
-		vsi->tx_rings[i]->netdev = vsi->netdev;
-		err = ice_setup_tx_ring(vsi->tx_rings[i]);
+		struct ice_ring *ring = vsi->tx_rings[i];
+
+		if (!ring)
+			return -EINVAL;
+
+		ring->netdev = vsi->netdev;
+		err = ice_setup_tx_ring(ring);
 		if (err)
 			break;
 	}
@@ -3996,8 +4450,13 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi)
 	}
 
 	ice_for_each_rxq(vsi, i) {
-		vsi->rx_rings[i]->netdev = vsi->netdev;
-		err = ice_setup_rx_ring(vsi->rx_rings[i]);
+		struct ice_ring *ring = vsi->rx_rings[i];
+
+		if (!ring)
+			return -EINVAL;
+
+		ring->netdev = vsi->netdev;
+		err = ice_setup_rx_ring(ring);
 		if (err)
 			break;
 	}
@@ -4033,7 +4492,7 @@ static int ice_vsi_open(struct ice_vsi *vsi)
 		goto err_setup_rx;
 
 	snprintf(int_name, sizeof(int_name) - 1, "%s-%s",
-		 dev_driver_string(&pf->pdev->dev), vsi->netdev->name);
+		 dev_driver_string(ice_pf_to_dev(pf)), vsi->netdev->name);
 	err = ice_vsi_req_irq_msix(vsi, int_name);
 	if (err)
 		goto err_setup_rx;
@@ -4082,61 +4541,13 @@ static void ice_vsi_release_all(struct ice_pf *pf)
 
 		err = ice_vsi_release(pf->vsi[i]);
 		if (err)
-			dev_dbg(&pf->pdev->dev,
+			dev_dbg(ice_pf_to_dev(pf),
 				"Failed to release pf->vsi[%d], err %d, vsi_num = %d\n",
 				i, err, pf->vsi[i]->vsi_num);
 	}
 }
 
 /**
- * ice_ena_vsi - resume a VSI
- * @vsi: the VSI being resume
- * @locked: is the rtnl_lock already held
- */
-static int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
-{
-	int err = 0;
-
-	if (!test_bit(__ICE_NEEDS_RESTART, vsi->state))
-		return 0;
-
-	clear_bit(__ICE_NEEDS_RESTART, vsi->state);
-
-	if (vsi->netdev && vsi->type == ICE_VSI_PF) {
-		if (netif_running(vsi->netdev)) {
-			if (!locked)
-				rtnl_lock();
-
-			err = ice_open(vsi->netdev);
-
-			if (!locked)
-				rtnl_unlock();
-		}
-	}
-
-	return err;
-}
-
-/**
- * ice_pf_ena_all_vsi - Resume all VSIs on a PF
- * @pf: the PF
- * @locked: is the rtnl_lock already held
- */
-#ifdef CONFIG_DCB
-int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked)
-{
-	int v;
-
-	ice_for_each_vsi(pf, v)
-		if (pf->vsi[v])
-			if (ice_ena_vsi(pf->vsi[v], locked))
-				return -EIO;
-
-	return 0;
-}
-#endif /* CONFIG_DCB */
-
-/**
  * ice_vsi_rebuild_by_type - Rebuild VSI of a given type
  * @pf: pointer to the PF instance
  * @type: VSI type to rebuild
@@ -4145,6 +4556,7 @@ int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked)
  */
 static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type)
 {
+	struct device *dev = ice_pf_to_dev(pf);
 	enum ice_status status;
 	int i, err;
 
@@ -4155,20 +4567,20 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type)
 			continue;
 
 		/* rebuild the VSI */
-		err = ice_vsi_rebuild(vsi);
+		err = ice_vsi_rebuild(vsi, true);
 		if (err) {
-			dev_err(&pf->pdev->dev,
-				"rebuild VSI failed, err %d, VSI index %d, type %d\n",
-				err, vsi->idx, type);
+			dev_err(dev,
+				"rebuild VSI failed, err %d, VSI index %d, type %s\n",
+				err, vsi->idx, ice_vsi_type_str(type));
 			return err;
 		}
 
 		/* replay filters for the VSI */
 		status = ice_replay_vsi(&pf->hw, vsi->idx);
 		if (status) {
-			dev_err(&pf->pdev->dev,
-				"replay VSI failed, status %d, VSI index %d, type %d\n",
-				status, vsi->idx, type);
+			dev_err(dev,
+				"replay VSI failed, status %d, VSI index %d, type %s\n",
+				status, vsi->idx, ice_vsi_type_str(type));
 			return -EIO;
 		}
 
@@ -4180,14 +4592,14 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type)
 		/* enable the VSI */
 		err = ice_ena_vsi(vsi, false);
 		if (err) {
-			dev_err(&pf->pdev->dev,
-				"enable VSI failed, err %d, VSI index %d, type %d\n",
-				err, vsi->idx, type);
+			dev_err(dev,
+				"enable VSI failed, err %d, VSI index %d, type %s\n",
+				err, vsi->idx, ice_vsi_type_str(type));
 			return err;
 		}
 
-		dev_info(&pf->pdev->dev, "VSI rebuilt. VSI index %d, type %d\n",
-			 vsi->idx, type);
+		dev_info(dev, "VSI rebuilt. VSI index %d, type %s\n", vsi->idx,
+			 ice_vsi_type_str(type));
 	}
 
 	return 0;
@@ -4226,7 +4638,7 @@ static void ice_update_pf_netdev_link(struct ice_pf *pf)
  */
 static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 {
-	struct device *dev = &pf->pdev->dev;
+	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	enum ice_status ret;
 	int err;
@@ -4272,7 +4684,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	err = ice_update_link_info(hw->port_info);
 	if (err)
-		dev_err(&pf->pdev->dev, "Get link status error %d\n", err);
+		dev_err(dev, "Get link status error %d\n", err);
 
 	/* start misc vector */
 	err = ice_req_irq_msix_misc(pf);
@@ -4329,6 +4741,18 @@ clear_recovery:
 }
 
 /**
+ * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP
+ * @vsi: Pointer to VSI structure
+ */
+static int ice_max_xdp_frame_size(struct ice_vsi *vsi)
+{
+	if (PAGE_SIZE >= 8192 || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags))
+		return ICE_RXBUF_2048 - XDP_PACKET_HEADROOM;
+	else
+		return ICE_RXBUF_3072;
+}
+
+/**
  * ice_change_mtu - NDO callback to change the MTU
  * @netdev: network interface device structure
  * @new_mtu: new value for maximum frame size
@@ -4347,6 +4771,16 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 		return 0;
 	}
 
+	if (ice_is_xdp_ena_vsi(vsi)) {
+		int frame_size = ice_max_xdp_frame_size(vsi);
+
+		if (new_mtu + ICE_ETH_PKT_HDR_PAD > frame_size) {
+			netdev_err(netdev, "max MTU for XDP usage is %d\n",
+				   frame_size - ICE_ETH_PKT_HDR_PAD);
+			return -EINVAL;
+		}
+	}
+
 	if (new_mtu < netdev->min_mtu) {
 		netdev_err(netdev, "new MTU invalid. min_mtu is %d\n",
 			   netdev->min_mtu);
@@ -4409,7 +4843,9 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
 	enum ice_status status;
+	struct device *dev;
 
+	dev = ice_pf_to_dev(pf);
 	if (seed) {
 		struct ice_aqc_get_set_rss_keys *buf =
 				  (struct ice_aqc_get_set_rss_keys *)seed;
@@ -4417,8 +4853,7 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		status = ice_aq_set_rss_key(hw, vsi->idx, buf);
 
 		if (status) {
-			dev_err(&pf->pdev->dev,
-				"Cannot set RSS key, err %d aq_err %d\n",
+			dev_err(dev, "Cannot set RSS key, err %d aq_err %d\n",
 				status, hw->adminq.rq_last_status);
 			return -EIO;
 		}
@@ -4428,8 +4863,7 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		status = ice_aq_set_rss_lut(hw, vsi->idx, vsi->rss_lut_type,
 					    lut, lut_size);
 		if (status) {
-			dev_err(&pf->pdev->dev,
-				"Cannot set RSS lut, err %d aq_err %d\n",
+			dev_err(dev, "Cannot set RSS lut, err %d aq_err %d\n",
 				status, hw->adminq.rq_last_status);
 			return -EIO;
 		}
@@ -4452,15 +4886,16 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
 	enum ice_status status;
+	struct device *dev;
 
+	dev = ice_pf_to_dev(pf);
 	if (seed) {
 		struct ice_aqc_get_set_rss_keys *buf =
 				  (struct ice_aqc_get_set_rss_keys *)seed;
 
 		status = ice_aq_get_rss_key(hw, vsi->idx, buf);
 		if (status) {
-			dev_err(&pf->pdev->dev,
-				"Cannot get RSS key, err %d aq_err %d\n",
+			dev_err(dev, "Cannot get RSS key, err %d aq_err %d\n",
 				status, hw->adminq.rq_last_status);
 			return -EIO;
 		}
@@ -4470,8 +4905,7 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		status = ice_aq_get_rss_lut(hw, vsi->idx, vsi->rss_lut_type,
 					    lut, lut_size);
 		if (status) {
-			dev_err(&pf->pdev->dev,
-				"Cannot get RSS lut, err %d aq_err %d\n",
+			dev_err(dev, "Cannot get RSS lut, err %d aq_err %d\n",
 				status, hw->adminq.rq_last_status);
 			return -EIO;
 		}
@@ -4515,7 +4949,6 @@ ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
  */
 static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
 {
-	struct device *dev = &vsi->back->pdev->dev;
 	struct ice_aqc_vsi_props *vsi_props;
 	struct ice_hw *hw = &vsi->back->hw;
 	struct ice_vsi_ctx *ctxt;
@@ -4524,7 +4957,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
 
 	vsi_props = &vsi->info;
 
-	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
 	if (!ctxt)
 		return -ENOMEM;
 
@@ -4540,7 +4973,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
 
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		dev_err(dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n",
+		dev_err(&vsi->back->pdev->dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n",
 			bmode, status, hw->adminq.sq_last_status);
 		ret = -EIO;
 		goto out;
@@ -4549,7 +4982,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
 	vsi_props->sw_flags = ctxt->info.sw_flags;
 
 out:
-	devm_kfree(dev, ctxt);
+	kfree(ctxt);
 	return ret;
 }
 
@@ -4864,12 +5297,14 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_change_mtu = ice_change_mtu,
 	.ndo_get_stats64 = ice_get_stats64,
+	.ndo_set_tx_maxrate = ice_set_tx_maxrate,
 	.ndo_set_vf_spoofchk = ice_set_vf_spoofchk,
 	.ndo_set_vf_mac = ice_set_vf_mac,
 	.ndo_get_vf_config = ice_get_vf_cfg,
 	.ndo_set_vf_trust = ice_set_vf_trust,
 	.ndo_set_vf_vlan = ice_set_vf_port_vlan,
 	.ndo_set_vf_link_state = ice_set_vf_link_state,
+	.ndo_get_vf_stats = ice_get_vf_stats,
 	.ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid,
 	.ndo_set_features = ice_set_features,
@@ -4878,4 +5313,7 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_fdb_add = ice_fdb_add,
 	.ndo_fdb_del = ice_fdb_del,
 	.ndo_tx_timeout = ice_tx_timeout,
+	.ndo_bpf = ice_xdp,
+	.ndo_xdp_xmit = ice_xdp_xmit,
+	.ndo_xsk_wakeup = ice_xsk_wakeup,
 };