net: stmmac: Rework TX Coalesce logic

Coalesce logic currently increments the number of packets and sets the
IC bit when the coalesced packets have passed a given limit. This does
not reflect very well what coalesce was meant for as we can have a large
number of packets that are coalesced and then a single one, sent later
on that has the IC bit.

Rework the logic so that it coalesces only upon a limit of packets and
sets the IC bit for large number of packets.

Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 400fbb727fd5f3f04cb9ac38e42ddaaa91247aad..4ba250a9008f276ab854d2e7dd4491279cc1e5cf 100644 (file)
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2916,16 +2916,17 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
        struct stmmac_priv *priv = netdev_priv(dev);
        int nfrags = skb_shinfo(skb)->nr_frags;
        u32 queue = skb_get_queue_mapping(skb);
+       unsigned int first_entry, tx_packets;
+       int tmp_pay_len = 0, first_tx;
        struct stmmac_tx_queue *tx_q;
-       unsigned int first_entry;
        u8 proto_hdr_len, hdr;
-       int tmp_pay_len = 0;
+       bool has_vlan, set_ic;
        u32 pay_len, mss;
        dma_addr_t des;
-       bool has_vlan;
        int i;
 
        tx_q = &priv->tx_queue[queue];
+       first_tx = tx_q->cur_tx;
 
        /* Compute header lengths */
        if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
@@ -3033,16 +3034,27 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
        tx_q->tx_skbuff[tx_q->cur_tx] = skb;
 
        /* Manage tx mitigation */
-       tx_q->tx_count_frames += nfrags + 1;
-       if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
-           !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-             priv->hwts_tx_en)) {
-               stmmac_tx_timer_arm(priv, queue);
-       } else {
+       tx_packets = (tx_q->cur_tx + 1) - first_tx;
+       tx_q->tx_count_frames += tx_packets;
+
+       if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && priv->hwts_tx_en)
+               set_ic = true;
+       else if (!priv->tx_coal_frames)
+               set_ic = false;
+       else if (tx_packets > priv->tx_coal_frames)
+               set_ic = true;
+       else if ((tx_q->tx_count_frames % priv->tx_coal_frames) < tx_packets)
+               set_ic = true;
+       else
+               set_ic = false;
+
+       if (set_ic) {
                desc = &tx_q->dma_tx[tx_q->cur_tx];
                tx_q->tx_count_frames = 0;
                stmmac_set_tx_ic(priv, desc);
                priv->xstats.tx_set_ic_bit++;
+       } else {
+               stmmac_tx_timer_arm(priv, queue);
        }
 
        /* We've used all descriptors we need for this skb, however,
@@ -3133,6 +3145,7 @@ dma_map_err:
  */
 static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+       unsigned int first_entry, tx_packets, enh_desc;
        struct stmmac_priv *priv = netdev_priv(dev);
        unsigned int nopaged_len = skb_headlen(skb);
        int i, csum_insertion = 0, is_jumbo = 0;
@@ -3141,13 +3154,12 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
        int gso = skb_shinfo(skb)->gso_type;
        struct dma_desc *desc, *first;
        struct stmmac_tx_queue *tx_q;
-       unsigned int first_entry;
-       unsigned int enh_desc;
+       bool has_vlan, set_ic;
+       int entry, first_tx;
        dma_addr_t des;
-       bool has_vlan;
-       int entry;
 
        tx_q = &priv->tx_queue[queue];
+       first_tx = tx_q->cur_tx;
 
        if (priv->tx_path_in_lpi_mode)
                stmmac_disable_eee_mode(priv);
@@ -3241,12 +3253,21 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
         * This approach takes care about the fragments: desc is the first
         * element in case of no SG.
         */
-       tx_q->tx_count_frames += nfrags + 1;
-       if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
-           !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-             priv->hwts_tx_en)) {
-               stmmac_tx_timer_arm(priv, queue);
-       } else {
+       tx_packets = (entry + 1) - first_tx;
+       tx_q->tx_count_frames += tx_packets;
+
+       if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && priv->hwts_tx_en)
+               set_ic = true;
+       else if (!priv->tx_coal_frames)
+               set_ic = false;
+       else if (tx_packets > priv->tx_coal_frames)
+               set_ic = true;
+       else if ((tx_q->tx_count_frames % priv->tx_coal_frames) < tx_packets)
+               set_ic = true;
+       else
+               set_ic = false;
+
+       if (set_ic) {
                if (likely(priv->extend_desc))
                        desc = &tx_q->dma_etx[entry].basic;
                else
@@ -3255,6 +3276,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
                tx_q->tx_count_frames = 0;
                stmmac_set_tx_ic(priv, desc);
                priv->xstats.tx_set_ic_bit++;
+       } else {
+               stmmac_tx_timer_arm(priv, queue);
        }
 
        /* We've used all descriptors we need for this skb, however,