net: ti: icssg_prueth: Add SW TX / RX Coalescing based on hrtimers

Add SW IRQ coalescing based on hrtimers for RX and TX data path for ICSSG
driver, which can be enabled by ethtool commands:

- RX coalescing
  ethtool -C eth1 rx-usecs 50

- TX coalescing can be enabled per TX queue

  - by default enables coalescing for TX0
  ethtool -C eth1 tx-usecs 50
  - configure TX0
  ethtool -Q eth0 queue_mask 1 --coalesce tx-usecs 100
  - configure TX1
  ethtool -Q eth0 queue_mask 2 --coalesce tx-usecs 100
  - configure TX0 and TX1
  ethtool -Q eth0 queue_mask 3 --coalesce tx-usecs 100 --coalesce
tx-usecs 100

Minimum value for both rx-usecs and tx-usecs is 20us.

Compared to gro_flush_timeout and napi_defer_hard_irqs this patch allows
to enable IRQ coalescing for RX path separately.

Benchmarking numbers:
 ===============================================================
| Method                  | Tput_TX | CPU_TX | Tput_RX | CPU_RX |
| ==============================================================
| Default Driver           943 Mbps    31%      517 Mbps  38%   |
| IRQ Coalescing (Patch)   943 Mbps    28%      518 Mbps  25%   |
 ===============================================================

Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240430120634.1558998-1-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 93 insertions, 0 deletions

diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
index ca20325d4d3e..c8d0f45cc5b1 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
@@ -201,6 +201,93 @@ static void emac_get_rmon_stats(struct net_device *ndev,
 	rmon_stats->hist_tx[4] = emac_get_stat_by_name(emac, "tx_bucket5_frames");
 }
 
+static int emac_get_coalesce(struct net_device *ndev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth_tx_chn *tx_chn;
+
+	tx_chn = &emac->tx_chns[0];
+
+	coal->rx_coalesce_usecs = emac->rx_pace_timeout_ns / 1000;
+	coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout_ns / 1000;
+
+	return 0;
+}
+
+static int emac_get_per_queue_coalesce(struct net_device *ndev, u32 queue,
+				       struct ethtool_coalesce *coal)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth_tx_chn *tx_chn;
+
+	if (queue >= PRUETH_MAX_TX_QUEUES)
+		return -EINVAL;
+
+	tx_chn = &emac->tx_chns[queue];
+
+	coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout_ns / 1000;
+
+	return 0;
+}
+
+static int emac_set_coalesce(struct net_device *ndev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+	struct prueth_tx_chn *tx_chn;
+
+	tx_chn = &emac->tx_chns[0];
+
+	if (coal->rx_coalesce_usecs &&
+	    coal->rx_coalesce_usecs < ICSSG_MIN_COALESCE_USECS) {
+		dev_info(prueth->dev, "defaulting to min value of %dus for rx-usecs\n",
+			 ICSSG_MIN_COALESCE_USECS);
+		coal->rx_coalesce_usecs = ICSSG_MIN_COALESCE_USECS;
+	}
+
+	if (coal->tx_coalesce_usecs &&
+	    coal->tx_coalesce_usecs < ICSSG_MIN_COALESCE_USECS) {
+		dev_info(prueth->dev, "defaulting to min value of %dus for tx-usecs\n",
+			 ICSSG_MIN_COALESCE_USECS);
+		coal->tx_coalesce_usecs = ICSSG_MIN_COALESCE_USECS;
+	}
+
+	emac->rx_pace_timeout_ns = coal->rx_coalesce_usecs * 1000;
+	tx_chn->tx_pace_timeout_ns = coal->tx_coalesce_usecs * 1000;
+
+	return 0;
+}
+
+static int emac_set_per_queue_coalesce(struct net_device *ndev, u32 queue,
+				       struct ethtool_coalesce *coal)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+	struct prueth_tx_chn *tx_chn;
+
+	if (queue >= PRUETH_MAX_TX_QUEUES)
+		return -EINVAL;
+
+	tx_chn = &emac->tx_chns[queue];
+
+	if (coal->tx_coalesce_usecs &&
+	    coal->tx_coalesce_usecs < ICSSG_MIN_COALESCE_USECS) {
+		dev_info(prueth->dev, "defaulting to min value of %dus for tx-usecs for tx-%u\n",
+			 ICSSG_MIN_COALESCE_USECS, queue);
+		coal->tx_coalesce_usecs = ICSSG_MIN_COALESCE_USECS;
+	}
+
+	tx_chn->tx_pace_timeout_ns = coal->tx_coalesce_usecs * 1000;
+
+	return 0;
+}
+
 const struct ethtool_ops icssg_ethtool_ops = {
 	.get_drvinfo = emac_get_drvinfo,
 	.get_msglevel = emac_get_msglevel,
@@ -209,6 +296,12 @@ const struct ethtool_ops icssg_ethtool_ops = {
 	.get_ethtool_stats = emac_get_ethtool_stats,
 	.get_strings = emac_get_strings,
 	.get_ts_info = emac_get_ts_info,
+	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS |
+				     ETHTOOL_COALESCE_TX_USECS,
+	.get_coalesce = emac_get_coalesce,
+	.set_coalesce = emac_set_coalesce,
+	.get_per_queue_coalesce = emac_get_per_queue_coalesce,
+	.set_per_queue_coalesce = emac_set_per_queue_coalesce,
 	.get_channels = emac_get_channels,
 	.set_channels = emac_set_channels,
 	.get_link_ksettings = emac_get_link_ksettings,