[PATCH net-next v2 2/2] bnxt_en: Pad short SW USO segments to BNXT_MIN_PKT_SIZE

@@ -14268,6 +14268,18 @@ static netdev_features_t bnxt_features_check(struct sk_buff *skb,
 	u8 *l4_proto;
 
 	features = vlan_features_check(skb, features);
+
+	/* SW USO pads at most the last segment; let the stack segment skbs
+	 * where every segment would be shorter than BNXT_MIN_PKT_SIZE.
+	 */
+	if (skb_is_gso(skb) &&
+	    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) &&
+	    !(bp->flags & BNXT_FLAG_UDP_GSO_CAP) &&
+	    bnxt_sw_gso_pad_len(skb_transport_offset(skb) +
+				sizeof(struct udphdr),
+				skb_shinfo(skb)->gso_size))
+		features &= ~NETIF_F_GSO_MASK;
+
 	switch (vlan_get_protocol(skb)) {
 	case htons(ETH_P_IP):
 		if (!skb->encapsulation)

@@ -82,11 +82,19 @@ int bnxt_sw_udp_gso_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 	if (unlikely(num_segs <= 1))
 		goto drop;
 
+	/* bnxt_features_check() makes the stack segment these, but paths
+	 * that skip validate_xmit_skb() (e.g. generic XDP_TX of a GRO'd
+	 * skb) can still get here. Padding every segment would need more
+	 * BDs than bds_needed reserves below, so drop instead.
+	 */
+	if (unlikely(bnxt_sw_gso_pad_len(hdr_len, mss)))
+		goto drop;
+
 	/* Upper bound on the number of descriptors needed.
 	 *
 	 * Each segment uses 1 long BD + 1 ext BD + payload BDs, which is
 	 * at most num_segs + nr_frags (each frag boundary crossing adds at
-	 * most 1 extra BD).
+	 * most 1 extra BD). The last segment may need 1 pad BD.
 	 */
 	bds_needed = 3 * num_segs + skb_shinfo(skb)->nr_frags + 1;
 

@@ -133,12 +141,14 @@ int bnxt_sw_udp_gso_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 		dma_addr_t dma_addr;
 		struct tx_bd *txbd;
 		struct udphdr *uh;
+		unsigned int pad;
 		void *this_hdr;
 		int bd_count;
 		bool last;
 		u32 flags;
 
 		last = (i == num_segs - 1);
+		pad = bnxt_sw_gso_pad_len(hdr_len, seg_payload);
 		offset = slot * TSO_HEADER_SIZE;
 		this_hdr = txr->tx_inline_buf + offset;
 		this_hdr_dma = txr->tx_inline_dma + offset;

@@ -156,10 +166,18 @@ int bnxt_sw_udp_gso_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 			iph->check = 0;
 		}
 
+		/* Pad bytes follow the header in the inline slot. Zero them
+		 * so stale header bytes from an earlier packet are not sent.
+		 */
+		if (pad)
+			memset(this_hdr + hdr_len, 0, pad);
+
 		dma_sync_single_for_device(&pdev->dev, this_hdr_dma,
-					   hdr_len, DMA_TO_DEVICE);
+					   hdr_len + pad, DMA_TO_DEVICE);
 
 		bd_count = tso_dma_map_count(&map, seg_payload);
+		if (pad)
+			bd_count++;
 
 		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];

@@ -222,6 +240,12 @@ int bnxt_sw_udp_gso_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 			seg_payload -= chunk_len;
 		}
 
+		if (pad) {
+			prod = NEXT_TX(prod);
+			txbd = bnxt_sw_gso_data_bd(bp, txr, prod,
+						   this_hdr_dma + hdr_len, pad);
+		}
+
 		txbd->tx_bd_len_flags_type |=
 			cpu_to_le32(TX_BD_FLAGS_PACKET_END);
 

@@ -19,10 +19,25 @@
  * Each segment: 1 long BD + 1 ext BD + payload BDs.
  * Total payload BDs across all segs <= num_segs + nr_frags (each frag
  * boundary crossing adds at most 1 extra BD).
+ * The last segment may need 1 pad BD (see bnxt_sw_gso_pad_len()).
  * So: 3 * max_segs + MAX_SKB_FRAGS + 1 = 3 * 64 + 17 + 1 = 210.
  */
 #define BNXT_SW_USO_MAX_DESCS	(3 * BNXT_SW_USO_MAX_SEGS + MAX_SKB_FRAGS + 1)
 
+/* Bytes of padding needed to bring a segment carrying @seg_payload bytes
+ * up to BNXT_MIN_PKT_SIZE, or 0 if no padding is needed.
+ */
+static inline unsigned int bnxt_sw_gso_pad_len(unsigned int hdr_len,
+					       unsigned int seg_payload)
+{
+	unsigned int len = hdr_len + seg_payload;
+
+	if (len < BNXT_MIN_PKT_SIZE)
+		return BNXT_MIN_PKT_SIZE - len;
+	else
+		return 0;
+}
+
 static inline u16 bnxt_inline_avail(struct bnxt_tx_ring_info *txr)
 {
 	return BNXT_SW_USO_MAX_SEGS -