ice: Make Tx threshold dependent on ring length

XDP_TX workloads use a concept of Tx threshold that indicates the
interval of setting RS bit on descriptors which in turn tells the HW to
generate an interrupt to signal the completion of Tx on HW side. It is
currently based on a constant value of 32 which might not work out well
for various sizes of ring combined with for example batch size that can
be set via SO_BUSY_POLL_BUDGET.

Internal tests based on AF_XDP showed that most convenient setup of
mentioned threshold is when it is equal to quarter of a ring length.

Make use of recently introduced ICE_RING_QUARTER macro and use this
value as a substitute for ICE_TX_THRESH.

Align also ethtool -G callback so that next_dd/next_rs fields are up to
date in terms of the ring size.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20220125160446.78976-5-maciej.fijalkowski@intel.com

Author: mfijalko

Diff for: drivers/net/ethernet/intel/ice/ice_ethtool.c

@@ -2803,6 +2803,8 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 		/* clone ring and setup updated count */
 		xdp_rings[i] = *vsi->xdp_rings[i];
 		xdp_rings[i].count = new_tx_cnt;
+		xdp_rings[i].next_dd = ICE_RING_QUARTER(&xdp_rings[i]) - 1;
+		xdp_rings[i].next_rs = ICE_RING_QUARTER(&xdp_rings[i]) - 1;
 		xdp_rings[i].desc = NULL;
 		xdp_rings[i].tx_buf = NULL;
 		err = ice_setup_tx_ring(&xdp_rings[i]);

Diff for: drivers/net/ethernet/intel/ice/ice_main.c

@@ -2495,10 +2495,10 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
 		xdp_ring->reg_idx = vsi->txq_map[xdp_q_idx];
 		xdp_ring->vsi = vsi;
 		xdp_ring->netdev = NULL;
-		xdp_ring->next_dd = ICE_TX_THRESH - 1;
-		xdp_ring->next_rs = ICE_TX_THRESH - 1;
 		xdp_ring->dev = dev;
 		xdp_ring->count = vsi->num_tx_desc;
+		xdp_ring->next_dd = ICE_RING_QUARTER(xdp_ring) - 1;
+		xdp_ring->next_rs = ICE_RING_QUARTER(xdp_ring) - 1;
 		WRITE_ONCE(vsi->xdp_rings[i], xdp_ring);
 		if (ice_setup_tx_ring(xdp_ring))
 			goto free_xdp_rings;

Diff for: drivers/net/ethernet/intel/ice/ice_txrx.h

@@ -13,7 +13,6 @@
 #define ICE_MAX_CHAINED_RX_BUFS	5
 #define ICE_MAX_BUF_TXD		8
 #define ICE_MIN_TX_LEN		17
-#define ICE_TX_THRESH		32
 
 /* The size limit for a transmit buffer in a descriptor is (16K - 1).
  * In order to align with the read requests we will align the value to

Diff for: drivers/net/ethernet/intel/ice/ice_txrx_lib.c

@@ -222,6 +222,7 @@ ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag)
 static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
 {
 	unsigned int total_bytes = 0, total_pkts = 0;
+	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
 	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *next_dd_desc;
 	u16 next_dd = xdp_ring->next_dd;
@@ -233,7 +234,7 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
 	    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
 		return;
 
-	for (i = 0; i < ICE_TX_THRESH; i++) {
+	for (i = 0; i < tx_thresh; i++) {
 		tx_buf = &xdp_ring->tx_buf[ntc];
 
 		total_bytes += tx_buf->bytecount;
@@ -254,9 +255,9 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
 	}
 
 	next_dd_desc->cmd_type_offset_bsz = 0;
-	xdp_ring->next_dd = xdp_ring->next_dd + ICE_TX_THRESH;
+	xdp_ring->next_dd = xdp_ring->next_dd + tx_thresh;
 	if (xdp_ring->next_dd > xdp_ring->count)
-		xdp_ring->next_dd = ICE_TX_THRESH - 1;
+		xdp_ring->next_dd = tx_thresh - 1;
 	xdp_ring->next_to_clean = ntc;
 	ice_update_tx_ring_stats(xdp_ring, total_pkts, total_bytes);
 }
@@ -269,12 +270,13 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
  */
 int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring)
 {
+	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
 	u16 i = xdp_ring->next_to_use;
 	struct ice_tx_desc *tx_desc;
 	struct ice_tx_buf *tx_buf;
 	dma_addr_t dma;
 
-	if (ICE_DESC_UNUSED(xdp_ring) < ICE_TX_THRESH)
+	if (ICE_DESC_UNUSED(xdp_ring) < tx_thresh)
 		ice_clean_xdp_irq(xdp_ring);
 
 	if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) {
@@ -306,15 +308,15 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring)
 		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
 		tx_desc->cmd_type_offset_bsz |=
 			cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-		xdp_ring->next_rs = ICE_TX_THRESH - 1;
+		xdp_ring->next_rs = tx_thresh - 1;
 	}
 	xdp_ring->next_to_use = i;
 
 	if (i > xdp_ring->next_rs) {
 		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
 		tx_desc->cmd_type_offset_bsz |=
 			cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-		xdp_ring->next_rs += ICE_TX_THRESH;
+		xdp_ring->next_rs += tx_thresh;
 	}
 
 	return ICE_XDP_TX;