1 files changed, 157 insertions, 47 deletions

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);