[PATCH net-next v3 RESEND 3/4] octeon_ep: implement xmit_more in transmit

[Shinas Rasheed <srasheed@marvell.com>]

Add xmit_more handling in tx datapath for octeon_ep pf.

Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
---
V3:
  - Stop returning NETDEV_TX_BUSY when ring is full in xmit_patch.
    Change to inspect early if next packet can fit in ring instead of
    current packet, and stop queue if not.
  - Add smp_mb between stopping tx queue and checking if tx queue has
    free entries again, in queue full check function to let reflect
    IQ process completions that might have happened on other cpus.
V2: https://lore.kernel.org/all/20231024145119.2366588-4-srasheed@marvell.com/
  - Updated changelog to have imperative tone.
V1: https://lore.kernel.org/all/20231023114449.2362147-3-srasheed@marvell.com/

 .../ethernet/marvell/octeon_ep/octep_config.h |  2 +-
 .../ethernet/marvell/octeon_ep/octep_main.c   | 36 ++++++++++++++-----
 2 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_config.h b/drivers/net/ethernet/marvell/octeon_ep/octep_config.h
index 1622a6ebf036..ed8b1ace56b9 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_config.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_config.h
@@ -15,7 +15,7 @@
 /* Tx Queue: maximum descriptors per ring */
 #define OCTEP_IQ_MAX_DESCRIPTORS    1024
 /* Minimum input (Tx) requests to be enqueued to ring doorbell */
-#define OCTEP_DB_MIN                1
+#define OCTEP_DB_MIN                8
 /* Packet threshold for Tx queue interrupt */
 #define OCTEP_IQ_INTR_THRESHOLD     0x0
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 1c02304677c9..2d1bcdc589f3 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -784,6 +784,13 @@ static inline int octep_iq_full_check(struct octep_iq *iq)
 	/* Stop the queue if unable to send */
 	netif_stop_subqueue(iq->netdev, iq->q_no);
 
+	/* Allow for pending updates in write index
+	 * from iq_process_completion in other cpus
+	 * to reflect, in case queue gets free
+	 * entries.
+	 */
+	smp_mb();
+
 	/* check again and restart the queue, in case NAPI has just freed
 	 * enough Tx ring entries.
 	 */
@@ -818,6 +825,7 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 	struct octep_iq *iq;
 	skb_frag_t *frag;
 	u16 nr_frags, si;
+	int xmit_more;
 	u16 q_no, wi;
 
 	if (skb_put_padto(skb, ETH_ZLEN))
@@ -830,10 +838,6 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 	}
 
 	iq = oct->iq[q_no];
-	if (octep_iq_full_check(iq)) {
-		iq->stats.tx_busy++;
-		return NETDEV_TX_BUSY;
-	}
 
 	shinfo = skb_shinfo(skb);
 	nr_frags = shinfo->nr_frags;
@@ -894,19 +898,33 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 		hw_desc->dptr = tx_buffer->sglist_dma;
 	}
 
-	netdev_tx_sent_queue(iq->netdev_q, skb->len);
+	xmit_more = netdev_xmit_more();
+
+	__netdev_tx_sent_queue(iq->netdev_q, skb->len, xmit_more);
+
 	skb_tx_timestamp(skb);
 	atomic_inc(&iq->instr_pending);
+	iq->fill_cnt++;
 	wi++;
 	if (wi == iq->max_count)
 		wi = 0;
 	iq->host_write_index = wi;
+
+	/* octep_iq_full_check stops the queue and returns
+	 * true if so, in case the queue has become full
+	 * by inserting current packet. If so, we can
+	 * go ahead and ring doorbell.
+	 */
+	if (!octep_iq_full_check(iq) && xmit_more &&
+	    iq->fill_cnt < iq->fill_threshold)
+		return NETDEV_TX_OK;
+
 	/* Flush the hw descriptor before writing to doorbell */
 	wmb();
-
-	/* Ring Doorbell to notify the NIC there is a new packet */
-	writel(1, iq->doorbell_reg);
-	iq->stats.instr_posted++;
+	/* Ring Doorbell to notify the NIC of new packets */
+	writel(iq->fill_cnt, iq->doorbell_reg);
+	iq->stats.instr_posted += iq->fill_cnt;
+	iq->fill_cnt = 0;
 	return NETDEV_TX_OK;
 
 dma_map_sg_err:
-- 
2.25.1