net: mana: Enforce TX SGE limit and fix error cleanup

index cccd5b63cee6..67ae5421f9ee 100644
@@ -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>

@@ -329,6 +330,20 @@ 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;
 
+	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.linear_pkt_tx_cnt++;
+	}
+
 	pkg.tx_oob.s_oob.vcq_num = cq->gdma_id;
 	pkg.tx_oob.s_oob.vsq_frame = txq->vsq_frame;
 

@@ -442,8 +457,6 @@ 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 {

@@ -518,6 +531,25 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	return NETDEV_TX_OK;
 }
 
+static netdev_features_t mana_features_check(struct sk_buff *skb,
+					     struct net_device *ndev,
+					     netdev_features_t features)
+{
+	if (MAX_SKB_FRAGS + 2 > MAX_TX_WQE_SGL_ENTRIES &&
+	    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.
+		 */
+		if (skb_is_gso(skb))
+			features &= ~NETIF_F_GSO_MASK;
+	}
+	return features;
+}
+
 static void mana_get_stats64(struct net_device *ndev,
 			     struct rtnl_link_stats64 *st)
 {

@@ -878,6 +910,7 @@ static const struct net_device_ops mana_devops = {
 	.ndo_open		= mana_open,
 	.ndo_stop		= mana_close,
 	.ndo_select_queue	= mana_select_queue,
+	.ndo_features_check	= mana_features_check,
 	.ndo_start_xmit		= mana_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_get_stats64	= mana_get_stats64,

index a1afa75a9463..fa5e1a2f06a9 100644
@@ -71,6 +71,8 @@ static const struct mana_stats_desc mana_eth_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)},
+	{"linear_pkt_tx_cnt", offsetof(struct mana_ethtool_stats,
+					linear_pkt_tx_cnt)},
 	{"rx_coalesced_err", offsetof(struct mana_ethtool_stats,
 					rx_coalesced_err)},
 	{"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,

index 637f42485dba..84614ebe0f4c 100644
@@ -592,6 +592,9 @@ enum {
 #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17)
 #define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6)
 
+/* Driver supports linearizing the skb when num_sge exceeds hardware limit */
+#define GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE BIT(20)
+
 #define GDMA_DRV_CAP_FLAGS1 \
 	(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
 	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \

@@ -601,7 +604,8 @@ enum {
 	 GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \
 	 GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \
 	 GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \
-	 GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE)
+	 GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \
+	 GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE)
 
 #define GDMA_DRV_CAP_FLAGS2 0
 

index 8906901535f5..50a532fb30d6 100644
@@ -404,6 +404,7 @@ struct mana_ethtool_stats {
 	u64 hc_tx_err_gdma;
 	u64 tx_cqe_err;
 	u64 tx_cqe_unknown_type;
+	u64 linear_pkt_tx_cnt;
 	u64 rx_coalesced_err;
 	u64 rx_cqe_unknown_type;
 };

index effe0a2f207a..65dd8060c7f4 100644
@@ -1332,7 +1332,6 @@ int mana_gd_post_work_request(struct gdma_queue *wq,
 
 	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");
 		return -ENOSPC;
 	}
 

index 67ae5421f9ee..066d822f68f0 100644
@@ -491,9 +491,9 @@ 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;

@@ -513,7 +513,6 @@ 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++;

@@ -1679,7 +1678,7 @@ 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;

index 50a532fb30d6..d05457d3e1ab 100644
@@ -585,6 +585,7 @@ int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
 void mana_query_phy_stats(struct mana_port_context *apc);
 int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues);
 void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
+void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc);
 
 extern const struct ethtool_ops mana_ethtool_ops;
 extern struct dentry *mana_debugfs_root;