[PATCH net-next v5 6/8] net: bcmgenet: pad transmit frames out of the packet ready window

@@ -59,6 +59,11 @@
 #define ENET_THLD_DEFAULT	0x80
 #define ENET_THLD_MAX		0xf0
 
+/* A frame ending just past the transmit threshold stops the transmitter once
+ * a shorter frame follows, so pad frames that land there this far past it.
+ */
+#define ENET_TX_SAFE_MARGIN	64
+
 /* Page pool RX buffer layout:
  * RSB(64) + pad(2) | frame data | skb_shared_info
  * The HW writes the 64B RSB before every descriptor of a frame. Only the

@@ -2176,6 +2181,42 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto out;
 	}
 
+	/* Both paths below write to the frame, which ether_setup() lets the
+	 * stack share. Match their conditions so nothing else is copied.
+	 */
+	if (unlikely(skb->len > priv->tx_thld_len &&
+		     (skb->ip_summed == CHECKSUM_PARTIAL ||
+		      skb->len < priv->tx_thld_len + ENET_TX_SAFE_MARGIN))) {
+		skb = skb_share_check(skb, GFP_ATOMIC);
+		if (!skb) {
+			BCMGENET_STATS64_INC((&ring->stats64), dropped);
+			goto drop;
+		}
+	}
+
+	/* The MAC only inserts a checksum into a frame it holds in full, and
+	 * silently drops a longer one, so fall back to software.
+	 */
+	if (unlikely(skb->len > priv->tx_thld_len) &&
+	    skb->ip_summed == CHECKSUM_PARTIAL) {
+		if (skb_checksum_help(skb)) {
+			BCMGENET_STATS64_INC((&ring->stats64), dropped);
+			dev_kfree_skb_any(skb);
+			goto drop;
+		}
+	}
+
+	/* Keep the frame out of the window just past the threshold */
+	if (unlikely(skb->len > priv->tx_thld_len &&
+		     skb->len < priv->tx_thld_len + ENET_TX_SAFE_MARGIN)) {
+		if (skb_put_padto(skb, priv->tx_thld_len + ENET_TX_SAFE_MARGIN)) {
+			BCMGENET_STATS64_INC((&ring->stats64), dropped);
+			goto drop;
+		}
+	}
+
+	nr_frags = skb_shinfo(skb)->nr_frags;
+
 	/* Retain how many bytes will be sent on the wire, without TSB inserted
 	 * by transmit checksum offload
 	 */

@@ -2662,6 +2703,27 @@ static unsigned int bcmgenet_pkt_rdy_thld(unsigned int mtu)
 		       ENET_THLD_MAX_LEN / ENET_THLD_UNIT);
 }
 
+/* Transmit threshold in register units. Frames landing in the window just
+ * past it are padded clear of it, so pick a threshold that leaves room for
+ * that padding inside the frame the MTU allows. Size the window against the
+ * longest frame the MAC has to accept, since the tag count is not bounded.
+ */
+static unsigned int bcmgenet_tx_pkt_rdy_thld(unsigned int mtu)
+{
+	unsigned int thld = ENET_THLD_MAX;
+
+	/* Keep the reset value while the MTU has no use for more */
+	if (mtu <= ETH_DATA_LEN)
+		return ENET_THLD_DEFAULT;
+
+	while (thld > ENET_THLD_DEFAULT &&
+	       ENET_MAX_FRAME_LEN(mtu) - ETH_FCS_LEN > thld * ENET_THLD_UNIT &&
+	       thld * ENET_THLD_UNIT + ENET_TX_SAFE_MARGIN > mtu + ETH_HLEN)
+		thld -= ENET_THLD_BURST / ENET_THLD_UNIT;
+
+	return thld;
+}
+
 /* A buffer has to hold everything the threshold lets the hardware deliver */
 static unsigned int bcmgenet_rx_buf_len(unsigned int mtu)
 {

@@ -2672,8 +2734,10 @@ static unsigned int bcmgenet_rx_buf_len(unsigned int mtu)
 /* Program the MTU dependent registers. Call with the MAC disabled. */
 static void bcmgenet_set_mtu_regs(struct bcmgenet_priv *priv, unsigned int mtu)
 {
+	u32 tx_thld = bcmgenet_tx_pkt_rdy_thld(mtu);
 	u32 thld = bcmgenet_pkt_rdy_thld(mtu);
 
+	priv->tx_thld_len = tx_thld * ENET_THLD_UNIT;
 	bcmgenet_umac_writel(priv, ENET_MAC_FRAME_LEN(mtu), UMAC_MAX_FRAME_LEN);
 
 	/* GENET v1 maps other registers at these offsets */

@@ -2681,6 +2745,8 @@ static void bcmgenet_set_mtu_regs(struct bcmgenet_priv *priv, unsigned int mtu)
 		return;
 
 	bcmgenet_rbuf_writel(priv, thld, RBUF_PKT_RDY_THLD);
+	bcmgenet_writel(tx_thld, priv->base + priv->hw_params->tbuf_offset +
+			TBUF_PKT_RDY_THLD);
 }
 
 static void init_umac(struct bcmgenet_priv *priv)

@@ -616,6 +616,7 @@ struct bcmgenet_priv {
 	void __iomem *tx_bds;
 	struct enet_cb *tx_cbs;
 	unsigned int num_tx_bds;
+	unsigned int tx_thld_len;
 
 	struct bcmgenet_tx_ring tx_rings[GENET_MAX_MQ_CNT + 1];