4 files changed, 378 insertions, 108 deletions

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 43f034e180c4..efb4e412ec7e 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -15,6 +15,20 @@
 
 struct dentry *mana_debugfs_root;
 
+struct mana_dev_recovery {
+	struct list_head list;
+	struct pci_dev *pdev;
+	enum gdma_eqe_type type;
+};
+
+static struct mana_dev_recovery_work {
+	struct list_head dev_list;
+	struct delayed_work work;
+
+	/* Lock for dev_list above */
+	spinlock_t lock;
+} mana_dev_recovery_work;
+
 static u32 mana_gd_r32(struct gdma_context *g, u64 offset)
 {
 	return readl(g->bar0_va + offset);
@@ -387,6 +401,25 @@ EXPORT_SYMBOL_NS(mana_gd_ring_cq, "NET_MANA");
 
 #define MANA_SERVICE_PERIOD 10
 
+static void mana_serv_rescan(struct pci_dev *pdev)
+{
+	struct pci_bus *parent;
+
+	pci_lock_rescan_remove();
+
+	parent = pdev->bus;
+	if (!parent) {
+		dev_err(&pdev->dev, "MANA service: no parent bus\n");
+		goto out;
+	}
+
+	pci_stop_and_remove_bus_device(pdev);
+	pci_rescan_bus(parent);
+
+out:
+	pci_unlock_rescan_remove();
+}
+
 static void mana_serv_fpga(struct pci_dev *pdev)
 {
 	struct pci_bus *bus, *parent;
@@ -419,9 +452,12 @@ static void mana_serv_reset(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 	struct hw_channel_context *hwc;
+	int ret;
 
 	if (!gc) {
-		dev_err(&pdev->dev, "MANA service: no GC\n");
+		/* Perform PCI rescan on device if GC is not set up */
+		dev_err(&pdev->dev, "MANA service: GC not setup, rescanning\n");
+		mana_serv_rescan(pdev);
 		return;
 	}
 
@@ -440,9 +476,18 @@ static void mana_serv_reset(struct pci_dev *pdev)
 
 	msleep(MANA_SERVICE_PERIOD * 1000);
 
-	mana_gd_resume(pdev);
+	ret = mana_gd_resume(pdev);
+	if (ret == -ETIMEDOUT || ret == -EPROTO) {
+		/* Perform PCI rescan on device if we failed on HWC */
+		dev_err(&pdev->dev, "MANA service: resume failed, rescanning\n");
+		mana_serv_rescan(pdev);
+		goto out;
+	}
 
-	dev_info(&pdev->dev, "MANA reset cycle completed\n");
+	if (ret)
+		dev_info(&pdev->dev, "MANA reset cycle failed err %d\n", ret);
+	else
+		dev_info(&pdev->dev, "MANA reset cycle completed\n");
 
 out:
 	gc->in_service = false;
@@ -454,18 +499,9 @@ struct mana_serv_work {
 	enum gdma_eqe_type type;
 };
 
-static void mana_serv_func(struct work_struct *w)
+static void mana_do_service(enum gdma_eqe_type type, struct pci_dev *pdev)
 {
-	struct mana_serv_work *mns_wk;
-	struct pci_dev *pdev;
-
-	mns_wk = container_of(w, struct mana_serv_work, serv_work);
-	pdev = mns_wk->pdev;
-
-	if (!pdev)
-		goto out;
-
-	switch (mns_wk->type) {
+	switch (type) {
 	case GDMA_EQE_HWC_FPGA_RECONFIG:
 		mana_serv_fpga(pdev);
 		break;
@@ -475,12 +511,48 @@ static void mana_serv_func(struct work_struct *w)
 		break;
 
 	default:
-		dev_err(&pdev->dev, "MANA service: unknown type %d\n",
-			mns_wk->type);
+		dev_err(&pdev->dev, "MANA service: unknown type %d\n", type);
 		break;
 	}
+}
+
+static void mana_recovery_delayed_func(struct work_struct *w)
+{
+	struct mana_dev_recovery_work *work;
+	struct mana_dev_recovery *dev;
+	unsigned long flags;
+
+	work = container_of(w, struct mana_dev_recovery_work, work.work);
+
+	spin_lock_irqsave(&work->lock, flags);
+
+	while (!list_empty(&work->dev_list)) {
+		dev = list_first_entry(&work->dev_list,
+				       struct mana_dev_recovery, list);
+		list_del(&dev->list);
+		spin_unlock_irqrestore(&work->lock, flags);
+
+		mana_do_service(dev->type, dev->pdev);
+		pci_dev_put(dev->pdev);
+		kfree(dev);
+
+		spin_lock_irqsave(&work->lock, flags);
+	}
+
+	spin_unlock_irqrestore(&work->lock, flags);
+}
+
+static void mana_serv_func(struct work_struct *w)
+{
+	struct mana_serv_work *mns_wk;
+	struct pci_dev *pdev;
+
+	mns_wk = container_of(w, struct mana_serv_work, serv_work);
+	pdev = mns_wk->pdev;
+
+	if (pdev)
+		mana_do_service(mns_wk->type, pdev);
 
-out:
 	pci_dev_put(pdev);
 	kfree(mns_wk);
 	module_put(THIS_MODULE);
@@ -528,6 +600,7 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
 	case GDMA_EQE_HWC_INIT_DONE:
 	case GDMA_EQE_HWC_SOC_SERVICE:
 	case GDMA_EQE_RNIC_QP_FATAL:
+	case GDMA_EQE_HWC_SOC_RECONFIG_DATA:
 		if (!eq->eq.callback)
 			break;
 
@@ -540,6 +613,17 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
 	case GDMA_EQE_HWC_RESET_REQUEST:
 		dev_info(gc->dev, "Recv MANA service type:%d\n", type);
 
+		if (!test_and_set_bit(GC_PROBE_SUCCEEDED, &gc->flags)) {
+			/*
+			 * Device is in probe and we received a hardware reset
+			 * event, the probe function will detect that the flag
+			 * has changed and perform service procedure.
+			 */
+			dev_info(gc->dev,
+				 "Service is to be processed in probe\n");
+			break;
+		}
+
 		if (gc->in_service) {
 			dev_info(gc->dev, "Already in service\n");
 			break;
@@ -1299,7 +1383,6 @@ int mana_gd_post_work_request(struct gdma_queue *wq,
 			      struct gdma_posted_wqe_info *wqe_info)
 {
 	u32 client_oob_size = wqe_req->inline_oob_size;
-	struct gdma_context *gc;
 	u32 sgl_data_size;
 	u32 max_wqe_size;
 	u32 wqe_size;
@@ -1329,11 +1412,8 @@ int mana_gd_post_work_request(struct gdma_queue *wq,
 	if (wqe_size > max_wqe_size)
 		return -EINVAL;
 
-	if (wq->monitor_avl_buf && wqe_size > mana_gd_wq_avail_space(wq)) {
-		gc = wq->gdma_dev->gdma_context;
-		dev_err(gc->dev, "unsuccessful flow control!\n");
+	if (wq->monitor_avl_buf && wqe_size > mana_gd_wq_avail_space(wq))
 		return -ENOSPC;
-	}
 
 	if (wqe_info)
 		wqe_info->wqe_size_in_bu = wqe_size / GDMA_WQE_BU_SIZE;
@@ -1941,8 +2021,19 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto cleanup_mana;
 
+	/*
+	 * If a hardware reset event has occurred over HWC during probe,
+	 * rollback and perform hardware reset procedure.
+	 */
+	if (test_and_set_bit(GC_PROBE_SUCCEEDED, &gc->flags)) {
+		err = -EPROTO;
+		goto cleanup_mana_rdma;
+	}
+
 	return 0;
 
+cleanup_mana_rdma:
+	mana_rdma_remove(&gc->mana_ib);
 cleanup_mana:
 	mana_remove(&gc->mana, false);
 cleanup_gd:
@@ -1966,6 +2057,35 @@ release_region:
 disable_dev:
 	pci_disable_device(pdev);
 	dev_err(&pdev->dev, "gdma probe failed: err = %d\n", err);
+
+	/*
+	 * Hardware could be in recovery mode and the HWC returns TIMEDOUT or
+	 * EPROTO from mana_gd_setup(), mana_probe() or mana_rdma_probe(), or
+	 * we received a hardware reset event over HWC interrupt. In this case,
+	 * perform the device recovery procedure after MANA_SERVICE_PERIOD
+	 * seconds.
+	 */
+	if (err == -ETIMEDOUT || err == -EPROTO) {
+		struct mana_dev_recovery *dev;
+		unsigned long flags;
+
+		dev_info(&pdev->dev, "Start MANA recovery mode\n");
+
+		dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+		if (!dev)
+			return err;
+
+		dev->pdev = pci_dev_get(pdev);
+		dev->type = GDMA_EQE_HWC_RESET_REQUEST;
+
+		spin_lock_irqsave(&mana_dev_recovery_work.lock, flags);
+		list_add_tail(&dev->list, &mana_dev_recovery_work.dev_list);
+		spin_unlock_irqrestore(&mana_dev_recovery_work.lock, flags);
+
+		schedule_delayed_work(&mana_dev_recovery_work.work,
+				      secs_to_jiffies(MANA_SERVICE_PERIOD));
+	}
+
 	return err;
 }
 
@@ -2070,6 +2190,10 @@ static int __init mana_driver_init(void)
 {
 	int err;
 
+	INIT_LIST_HEAD(&mana_dev_recovery_work.dev_list);
+	spin_lock_init(&mana_dev_recovery_work.lock);
+	INIT_DELAYED_WORK(&mana_dev_recovery_work.work, mana_recovery_delayed_func);
+
 	mana_debugfs_root = debugfs_create_dir("mana", NULL);
 
 	err = pci_register_driver(&mana_driver);
@@ -2083,6 +2207,21 @@ static int __init mana_driver_init(void)
 
 static void __exit mana_driver_exit(void)
 {
+	struct mana_dev_recovery *dev;
+	unsigned long flags;
+
+	disable_delayed_work_sync(&mana_dev_recovery_work.work);
+
+	spin_lock_irqsave(&mana_dev_recovery_work.lock, flags);
+	while (!list_empty(&mana_dev_recovery_work.dev_list)) {
+		dev = list_first_entry(&mana_dev_recovery_work.dev_list,
+				       struct mana_dev_recovery, list);
+		list_del(&dev->list);
+		pci_dev_put(dev->pdev);
+		kfree(dev);
+	}
+	spin_unlock_irqrestore(&mana_dev_recovery_work.lock, flags);
+
 	pci_unregister_driver(&mana_driver);
 
 	debugfs_remove(mana_debugfs_root);
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index ada6c78a2bef..aa4e2731e2ba 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -118,6 +118,7 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
 	struct gdma_dev *gd = hwc->gdma_dev;
 	union hwc_init_type_data type_data;
 	union hwc_init_eq_id_db eq_db;
+	struct mana_context *ac;
 	u32 type, val;
 	int ret;
 
@@ -196,6 +197,17 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
 			hwc->hwc_timeout = val;
 			break;
 
+		case HWC_DATA_HW_LINK_CONNECT:
+		case HWC_DATA_HW_LINK_DISCONNECT:
+			ac = gd->gdma_context->mana.driver_data;
+			if (!ac)
+				break;
+
+			WRITE_ONCE(ac->link_event, type);
+			schedule_work(&ac->link_change_work);
+
+			break;
+
 		default:
 			dev_warn(hwc->dev, "Received unknown reconfig type %u\n", type);
 			break;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 0142fd98392c..1ad154f9db1a 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -11,6 +11,7 @@
 #include <linux/mm.h>
 #include <linux/pci.h>
 #include <linux/export.h>
+#include <linux/skbuff.h>
 
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
@@ -20,6 +21,7 @@
 
 #include <net/mana/mana.h>
 #include <net/mana/mana_auxiliary.h>
+#include <net/mana/hw_channel.h>
 
 static DEFINE_IDA(mana_adev_ida);
 
@@ -84,7 +86,6 @@ static int mana_open(struct net_device *ndev)
 	/* Ensure port state updated before txq state */
 	smp_wmb();
 
-	netif_carrier_on(ndev);
 	netif_tx_wake_all_queues(ndev);
 	netdev_dbg(ndev, "%s successful\n", __func__);
 	return 0;
@@ -100,6 +101,46 @@ static int mana_close(struct net_device *ndev)
 	return mana_detach(ndev, true);
 }
 
+static void mana_link_state_handle(struct work_struct *w)
+{
+	struct mana_context *ac;
+	struct net_device *ndev;
+	u32 link_event;
+	bool link_up;
+	int i;
+
+	ac = container_of(w, struct mana_context, link_change_work);
+
+	rtnl_lock();
+
+	link_event = READ_ONCE(ac->link_event);
+
+	if (link_event == HWC_DATA_HW_LINK_CONNECT)
+		link_up = true;
+	else if (link_event == HWC_DATA_HW_LINK_DISCONNECT)
+		link_up = false;
+	else
+		goto out;
+
+	/* Process all ports */
+	for (i = 0; i < ac->num_ports; i++) {
+		ndev = ac->ports[i];
+		if (!ndev)
+			continue;
+
+		if (link_up) {
+			netif_carrier_on(ndev);
+
+			__netdev_notify_peers(ndev);
+		} else {
+			netif_carrier_off(ndev);
+		}
+	}
+
+out:
+	rtnl_unlock();
+}
+
 static bool mana_can_tx(struct gdma_queue *wq)
 {
 	return mana_gd_wq_avail_space(wq) >= MAX_TX_WQE_SIZE;
@@ -289,6 +330,21 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	cq = &apc->tx_qp[txq_idx].tx_cq;
 	tx_stats = &txq->stats;
 
+	BUILD_BUG_ON(MAX_TX_WQE_SGL_ENTRIES != MANA_MAX_TX_WQE_SGL_ENTRIES);
+	if (MAX_SKB_FRAGS + 2 > MAX_TX_WQE_SGL_ENTRIES &&
+	    skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
+		/* GSO skb with Hardware SGE limit exceeded is not expected here
+		 * as they are handled in mana_features_check() callback
+		 */
+		if (skb_linearize(skb)) {
+			netdev_warn_once(ndev, "Failed to linearize skb with nr_frags=%d and is_gso=%d\n",
+					 skb_shinfo(skb)->nr_frags,
+					 skb_is_gso(skb));
+			goto tx_drop_count;
+		}
+		apc->eth_stats.tx_linear_pkt_cnt++;
+	}
+
 	pkg.tx_oob.s_oob.vcq_num = cq->gdma_id;
 	pkg.tx_oob.s_oob.vsq_frame = txq->vsq_frame;
 
@@ -402,8 +458,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		}
 	}
 
-	WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES);
-
 	if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) {
 		pkg.wqe_req.sgl = pkg.sgl_array;
 	} else {
@@ -438,9 +492,9 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	if (err) {
 		(void)skb_dequeue_tail(&txq->pending_skbs);
+		mana_unmap_skb(skb, apc);
 		netdev_warn(ndev, "Failed to post TX OOB: %d\n", err);
-		err = NETDEV_TX_BUSY;
-		goto tx_busy;
+		goto free_sgl_ptr;
 	}
 
 	err = NETDEV_TX_OK;
@@ -460,7 +514,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	tx_stats->bytes += len + ((num_gso_seg - 1) * gso_hs);
 	u64_stats_update_end(&tx_stats->syncp);
 
-tx_busy:
 	if (netif_tx_queue_stopped(net_txq) && mana_can_tx(gdma_sq)) {
 		netif_tx_wake_queue(net_txq);
 		apc->eth_stats.wake_queue++;
@@ -478,6 +531,25 @@ tx_drop:
 	return NETDEV_TX_OK;
 }
 
+#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES)
+static netdev_features_t mana_features_check(struct sk_buff *skb,
+					     struct net_device *ndev,
+					     netdev_features_t features)
+{
+	if (skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
+		/* Exceeds HW SGE limit.
+		 * GSO case:
+		 *   Disable GSO so the stack will software-segment the skb
+		 *   into smaller skbs that fit the SGE budget.
+		 * Non-GSO case:
+		 *   The xmit path will attempt skb_linearize() as a fallback.
+		 */
+		features &= ~NETIF_F_GSO_MASK;
+	}
+	return features;
+}
+#endif
+
 static void mana_get_stats64(struct net_device *ndev,
 			     struct rtnl_link_stats64 *st)
 {
@@ -494,6 +566,11 @@ static void mana_get_stats64(struct net_device *ndev,
 
 	netdev_stats_to_stats64(st, &ndev->stats);
 
+	if (apc->ac->hwc_timeout_occurred)
+		netdev_warn_once(ndev, "HWC timeout occurred\n");
+
+	st->rx_missed_errors = apc->ac->hc_stats.hc_rx_discards_no_wqe;
+
 	for (q = 0; q < num_queues; q++) {
 		rx_stats = &apc->rxqs[q]->stats;
 
@@ -814,7 +891,7 @@ static int mana_shaper_del(struct net_shaper_binding *binding,
 		/* Reset mana port context parameters */
 		apc->handle.id = 0;
 		apc->handle.scope = NET_SHAPER_SCOPE_UNSPEC;
-		apc->speed = 0;
+		apc->speed = apc->max_speed;
 	}
 
 	return err;
@@ -838,6 +915,9 @@ static const struct net_device_ops mana_devops = {
 	.ndo_open		= mana_open,
 	.ndo_stop		= mana_close,
 	.ndo_select_queue	= mana_select_queue,
+#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES)
+	.ndo_features_check	= mana_features_check,
+#endif
 	.ndo_start_xmit		= mana_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_get_stats64	= mana_get_stats64,
@@ -1606,7 +1686,7 @@ static int mana_move_wq_tail(struct gdma_queue *wq, u32 num_units)
 	return 0;
 }
 
-static void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc)
+void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc)
 {
 	struct mana_skb_head *ash = (struct mana_skb_head *)skb->head;
 	struct gdma_context *gc = apc->ac->gdma_dev->gdma_context;
@@ -2769,11 +2849,12 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx,
 	return 0;
 }
 
-void mana_query_gf_stats(struct mana_port_context *apc)
+int mana_query_gf_stats(struct mana_context *ac)
 {
+	struct gdma_context *gc = ac->gdma_dev->gdma_context;
 	struct mana_query_gf_stat_resp resp = {};
 	struct mana_query_gf_stat_req req = {};
-	struct net_device *ndev = apc->ndev;
+	struct device *dev = gc->dev;
 	int err;
 
 	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT,
@@ -2807,52 +2888,54 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 			STATISTICS_FLAGS_HC_TX_BCAST_BYTES |
 			STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR;
 
-	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
+	err = mana_send_request(ac, &req, sizeof(req), &resp,
 				sizeof(resp));
 	if (err) {
-		netdev_err(ndev, "Failed to query GF stats: %d\n", err);
-		return;
+		dev_err(dev, "Failed to query GF stats: %d\n", err);
+		return err;
 	}
 	err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT,
 				   sizeof(resp));
 	if (err || resp.hdr.status) {
-		netdev_err(ndev, "Failed to query GF stats: %d, 0x%x\n", err,
-			   resp.hdr.status);
-		return;
+		dev_err(dev, "Failed to query GF stats: %d, 0x%x\n", err,
+			resp.hdr.status);
+		return err;
 	}
 
-	apc->eth_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe;
-	apc->eth_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled;
-	apc->eth_stats.hc_rx_bytes = resp.hc_rx_bytes;
-	apc->eth_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts;
-	apc->eth_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes;
-	apc->eth_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts;
-	apc->eth_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes;
-	apc->eth_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts;
-	apc->eth_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes;
-	apc->eth_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled;
-	apc->eth_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled;
-	apc->eth_stats.hc_tx_err_inval_vportoffset_pkt =
+	ac->hc_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe;
+	ac->hc_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled;
+	ac->hc_stats.hc_rx_bytes = resp.hc_rx_bytes;
+	ac->hc_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts;
+	ac->hc_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes;
+	ac->hc_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts;
+	ac->hc_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes;
+	ac->hc_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts;
+	ac->hc_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes;
+	ac->hc_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled;
+	ac->hc_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled;
+	ac->hc_stats.hc_tx_err_inval_vportoffset_pkt =
 					     resp.tx_err_inval_vport_offset_pkt;
-	apc->eth_stats.hc_tx_err_vlan_enforcement =
+	ac->hc_stats.hc_tx_err_vlan_enforcement =
 					     resp.tx_err_vlan_enforcement;
-	apc->eth_stats.hc_tx_err_eth_type_enforcement =
+	ac->hc_stats.hc_tx_err_eth_type_enforcement =
 					     resp.tx_err_ethtype_enforcement;
-	apc->eth_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement;
-	apc->eth_stats.hc_tx_err_sqpdid_enforcement =
+	ac->hc_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement;
+	ac->hc_stats.hc_tx_err_sqpdid_enforcement =
 					     resp.tx_err_SQPDID_enforcement;
-	apc->eth_stats.hc_tx_err_cqpdid_enforcement =
+	ac->hc_stats.hc_tx_err_cqpdid_enforcement =
 					     resp.tx_err_CQPDID_enforcement;
-	apc->eth_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation;
-	apc->eth_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob;
-	apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes;
-	apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts;
-	apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes;
-	apc->eth_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts;
-	apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes;
-	apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts;
-	apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes;
-	apc->eth_stats.hc_tx_err_gdma = resp.tx_err_gdma;
+	ac->hc_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation;
+	ac->hc_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob;
+	ac->hc_stats.hc_tx_bytes = resp.hc_tx_bytes;
+	ac->hc_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts;
+	ac->hc_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes;
+	ac->hc_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts;
+	ac->hc_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes;
+	ac->hc_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts;
+	ac->hc_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes;
+	ac->hc_stats.hc_tx_err_gdma = resp.tx_err_gdma;
+
+	return 0;
 }
 
 void mana_query_phy_stats(struct mana_port_context *apc)
@@ -3059,9 +3142,6 @@ int mana_attach(struct net_device *ndev)
 	/* Ensure port state updated before txq state */
 	smp_wmb();
 
-	if (apc->port_is_up)
-		netif_carrier_on(ndev);
-
 	netif_device_attach(ndev);
 
 	return 0;
@@ -3154,7 +3234,6 @@ int mana_detach(struct net_device *ndev, bool from_close)
 	smp_wmb();
 
 	netif_tx_disable(ndev);
-	netif_carrier_off(ndev);
 
 	if (apc->port_st_save) {
 		err = mana_dealloc_queues(ndev);
@@ -3243,6 +3322,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 		goto free_indir;
 	}
 
+	netif_carrier_on(ndev);
+
 	debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, &apc->speed);
 
 	return 0;
@@ -3389,6 +3470,24 @@ int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type even
 	return 0;
 }
 
+#define MANA_GF_STATS_PERIOD (2 * HZ)
+
+static void mana_gf_stats_work_handler(struct work_struct *work)
+{
+	struct mana_context *ac =
+		container_of(to_delayed_work(work), struct mana_context, gf_stats_work);
+	int err;
+
+	err = mana_query_gf_stats(ac);
+	if (err == -ETIMEDOUT) {
+		/* HWC timeout detected - reset stats and stop rescheduling */
+		ac->hwc_timeout_occurred = true;
+		memset(&ac->hc_stats, 0, sizeof(ac->hc_stats));
+		return;
+	}
+	schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD);
+}
+
 int mana_probe(struct gdma_dev *gd, bool resuming)
 {
 	struct gdma_context *gc = gd->gdma_context;
@@ -3431,6 +3530,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 
 	if (!resuming) {
 		ac->num_ports = num_ports;
+
+		INIT_WORK(&ac->link_change_work, mana_link_state_handle);
 	} else {
 		if (ac->num_ports != num_ports) {
 			dev_err(dev, "The number of vPorts changed: %d->%d\n",
@@ -3438,6 +3539,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 			err = -EPROTO;
 			goto out;
 		}
+
+		enable_work(&ac->link_change_work);
 	}
 
 	if (ac->num_ports == 0)
@@ -3477,6 +3580,10 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 	}
 
 	err = add_adev(gd, "eth");
+
+	INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler);
+	schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD);
+
 out:
 	if (err) {
 		mana_remove(gd, false);
@@ -3500,6 +3607,9 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
 	int err;
 	int i;
 
+	disable_work_sync(&ac->link_change_work);
+	cancel_delayed_work_sync(&ac->gf_stats_work);
+
 	/* adev currently doesn't support suspending, always remove it */
 	if (gd->adev)
 		remove_adev(gd);
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index a1afa75a9463..0e2f4343ac67 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -15,66 +15,71 @@ struct mana_stats_desc {
 static const struct mana_stats_desc mana_eth_stats[] = {
 	{"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)},
 	{"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)},
-	{"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_stats,
+	{"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)},
+	{"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
+					tx_cqe_unknown_type)},
+	{"tx_linear_pkt_cnt", offsetof(struct mana_ethtool_stats,
+				       tx_linear_pkt_cnt)},
+	{"rx_coalesced_err", offsetof(struct mana_ethtool_stats,
+					rx_coalesced_err)},
+	{"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
+					rx_cqe_unknown_type)},
+};
+
+static const struct mana_stats_desc mana_hc_stats[] = {
+	{"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_hc_stats,
 					   hc_rx_discards_no_wqe)},
-	{"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_stats,
+	{"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_hc_stats,
 					      hc_rx_err_vport_disabled)},
-	{"hc_rx_bytes", offsetof(struct mana_ethtool_stats, hc_rx_bytes)},
-	{"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_stats,
+	{"hc_rx_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_bytes)},
+	{"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_hc_stats,
 				      hc_rx_ucast_pkts)},
-	{"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_stats,
+	{"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_hc_stats,
 				       hc_rx_ucast_bytes)},
-	{"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_stats,
+	{"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_hc_stats,
 				      hc_rx_bcast_pkts)},
-	{"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_stats,
+	{"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_hc_stats,
 				       hc_rx_bcast_bytes)},
-	{"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_stats,
-			hc_rx_mcast_pkts)},
-	{"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_stats,
+	{"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_hc_stats,
+				      hc_rx_mcast_pkts)},
+	{"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_hc_stats,
 				       hc_rx_mcast_bytes)},
-	{"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_hc_stats,
 					   hc_tx_err_gf_disabled)},
-	{"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_hc_stats,
 					      hc_tx_err_vport_disabled)},
 	{"hc_tx_err_inval_vportoffset_pkt",
-	 offsetof(struct mana_ethtool_stats,
+	 offsetof(struct mana_ethtool_hc_stats,
 		  hc_tx_err_inval_vportoffset_pkt)},
-	{"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_hc_stats,
 						hc_tx_err_vlan_enforcement)},
 	{"hc_tx_err_eth_type_enforcement",
-	 offsetof(struct mana_ethtool_stats, hc_tx_err_eth_type_enforcement)},
-	{"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_stats,
+	 offsetof(struct mana_ethtool_hc_stats, hc_tx_err_eth_type_enforcement)},
+	{"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_hc_stats,
 					      hc_tx_err_sa_enforcement)},
 	{"hc_tx_err_sqpdid_enforcement",
-	 offsetof(struct mana_ethtool_stats, hc_tx_err_sqpdid_enforcement)},
+	 offsetof(struct mana_ethtool_hc_stats, hc_tx_err_sqpdid_enforcement)},
 	{"hc_tx_err_cqpdid_enforcement",
-	 offsetof(struct mana_ethtool_stats, hc_tx_err_cqpdid_enforcement)},
-	{"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_stats,
+	 offsetof(struct mana_ethtool_hc_stats, hc_tx_err_cqpdid_enforcement)},
+	{"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_hc_stats,
 					     hc_tx_err_mtu_violation)},
-	{"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_hc_stats,
 					 hc_tx_err_inval_oob)},
-	{"hc_tx_err_gdma", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_err_gdma", offsetof(struct mana_ethtool_hc_stats,
 				    hc_tx_err_gdma)},
-	{"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)},
-	{"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_bytes)},
+	{"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_hc_stats,
 					hc_tx_ucast_pkts)},
-	{"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_hc_stats,
 					hc_tx_ucast_bytes)},
-	{"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_hc_stats,
 					hc_tx_bcast_pkts)},
-	{"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_hc_stats,
 					hc_tx_bcast_bytes)},
-	{"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_hc_stats,
 					hc_tx_mcast_pkts)},
-	{"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_stats,
+	{"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_hc_stats,
 					hc_tx_mcast_bytes)},
-	{"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)},
-	{"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
-					tx_cqe_unknown_type)},
-	{"rx_coalesced_err", offsetof(struct mana_ethtool_stats,
-					rx_coalesced_err)},
-	{"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
-					rx_cqe_unknown_type)},
 };
 
 static const struct mana_stats_desc mana_phy_stats[] = {
@@ -138,7 +143,7 @@ static int mana_get_sset_count(struct net_device *ndev, int stringset)
 	if (stringset != ETH_SS_STATS)
 		return -EINVAL;
 
-	return ARRAY_SIZE(mana_eth_stats) + ARRAY_SIZE(mana_phy_stats) +
+	return ARRAY_SIZE(mana_eth_stats) + ARRAY_SIZE(mana_phy_stats) + ARRAY_SIZE(mana_hc_stats) +
 			num_queues * (MANA_STATS_RX_COUNT + MANA_STATS_TX_COUNT);
 }
 
@@ -150,10 +155,12 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 
 	if (stringset != ETH_SS_STATS)
 		return;
-
 	for (i = 0; i < ARRAY_SIZE(mana_eth_stats); i++)
 		ethtool_puts(&data, mana_eth_stats[i].name);
 
+	for (i = 0; i < ARRAY_SIZE(mana_hc_stats); i++)
+		ethtool_puts(&data, mana_hc_stats[i].name);
+
 	for (i = 0; i < ARRAY_SIZE(mana_phy_stats); i++)
 		ethtool_puts(&data, mana_phy_stats[i].name);
 
@@ -186,6 +193,7 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
 	struct mana_port_context *apc = netdev_priv(ndev);
 	unsigned int num_queues = apc->num_queues;
 	void *eth_stats = &apc->eth_stats;
+	void *hc_stats = &apc->ac->hc_stats;
 	void *phy_stats = &apc->phy_stats;
 	struct mana_stats_rx *rx_stats;
 	struct mana_stats_tx *tx_stats;
@@ -207,8 +215,6 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
 
 	if (!apc->port_is_up)
 		return;
-	/* we call mana function to update stats from GDMA */
-	mana_query_gf_stats(apc);
 
 	/* We call this mana function to get the phy stats from GDMA and includes
 	 * aggregate tx/rx drop counters, Per-TC(Traffic Channel) tx/rx and pause
@@ -219,6 +225,9 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
 	for (q = 0; q < ARRAY_SIZE(mana_eth_stats); q++)
 		data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset);
 
+	for (q = 0; q < ARRAY_SIZE(mana_hc_stats); q++)
+		data[i++] = *(u64 *)(hc_stats + mana_hc_stats[q].offset);
+
 	for (q = 0; q < ARRAY_SIZE(mana_phy_stats); q++)
 		data[i++] = *(u64 *)(phy_stats + mana_phy_stats[q].offset);