bnxt: make sure xmit_more + errors does not miss doorbells

skbs are freed on error and not put on the ring. We may, however,
be in a situation where we're freeing the last skb of a batch,
and there is a doorbell ring pending because of xmit_more() being
true earlier. Make sure we ring the door bell in such situations.

Since errors are rare don't pay attention to xmit_more() and just
always flush the pending frames.

The busy case should be safe to be left alone because it can
only happen if start_xmit races with completions and they
both enable the queue. In that case the kick can't be pending.

Noticed while reading the code.

Fixes: 4d172f21cefe ("bnxt_en: Implement xmit_more.")
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 721b5df..389016e 100644 (file)
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -72,7 +72,8 @@
 #include "bnxt_debugfs.h"
 
 #define BNXT_TX_TIMEOUT                (5 * HZ)
-#define BNXT_DEF_MSG_ENABLE    (NETIF_MSG_DRV | NETIF_MSG_HW)
+#define BNXT_DEF_MSG_ENABLE    (NETIF_MSG_DRV | NETIF_MSG_HW | \
+                                NETIF_MSG_TX_ERR)
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Broadcom BCM573xx network driver");
@@ -365,6 +366,13 @@ static u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb)
        return md_dst->u.port_info.port_id;
 }
 
+static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+                            u16 prod)
+{
+       bnxt_db_write(bp, &txr->tx_db, prod);
+       txr->kick_pending = 0;
+}
+
 static bool bnxt_txr_netif_try_stop_queue(struct bnxt *bp,
                                          struct bnxt_tx_ring_info *txr,
                                          struct netdev_queue *txq)
@@ -413,6 +421,10 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
        free_size = bnxt_tx_avail(bp, txr);
        if (unlikely(free_size < skb_shinfo(skb)->nr_frags + 2)) {
+               /* We must have raced with NAPI cleanup */
+               if (net_ratelimit() && txr->kick_pending)
+                       netif_warn(bp, tx_err, dev,
+                                  "bnxt: ring busy w/ flush pending!\n");
                if (bnxt_txr_netif_try_stop_queue(bp, txr, txq))
                        return NETDEV_TX_BUSY;
        }
@@ -537,21 +549,16 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 normal_tx:
        if (length < BNXT_MIN_PKT_SIZE) {
                pad = BNXT_MIN_PKT_SIZE - length;
-               if (skb_pad(skb, pad)) {
+               if (skb_pad(skb, pad))
                        /* SKB already freed. */
-                       tx_buf->skb = NULL;
-                       return NETDEV_TX_OK;
-               }
+                       goto tx_kick_pending;
                length = BNXT_MIN_PKT_SIZE;
        }
 
        mapping = dma_map_single(&pdev->dev, skb->data, len, DMA_TO_DEVICE);
 
-       if (unlikely(dma_mapping_error(&pdev->dev, mapping))) {
-               dev_kfree_skb_any(skb);
-               tx_buf->skb = NULL;
-               return NETDEV_TX_OK;
-       }
+       if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
+               goto tx_free;
 
        dma_unmap_addr_set(tx_buf, mapping, mapping);
        flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
@@ -638,13 +645,15 @@ normal_tx:
        txr->tx_prod = prod;
 
        if (!netdev_xmit_more() || netif_xmit_stopped(txq))
-               bnxt_db_write(bp, &txr->tx_db, prod);
+               bnxt_txr_db_kick(bp, txr, prod);
+       else
+               txr->kick_pending = 1;
 
 tx_done:
 
        if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
                if (netdev_xmit_more() && !tx_buf->is_push)
-                       bnxt_db_write(bp, &txr->tx_db, prod);
+                       bnxt_txr_db_kick(bp, txr, prod);
 
                bnxt_txr_netif_try_stop_queue(bp, txr, txq);
        }
@@ -659,7 +668,6 @@ tx_dma_error:
        /* start back at beginning and unmap skb */
        prod = txr->tx_prod;
        tx_buf = &txr->tx_buf_ring[prod];
-       tx_buf->skb = NULL;
        dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
                         skb_headlen(skb), PCI_DMA_TODEVICE);
        prod = NEXT_TX(prod);
@@ -673,7 +681,12 @@ tx_dma_error:
                               PCI_DMA_TODEVICE);
        }
 
+tx_free:
        dev_kfree_skb_any(skb);
+tx_kick_pending:
+       if (txr->kick_pending)
+               bnxt_txr_db_kick(bp, txr, txr->tx_prod);
+       txr->tx_buf_ring[txr->tx_prod].skb = NULL;
        return NETDEV_TX_OK;
 }
 

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index bcf8d00..ba4e0fc 100644 (file)
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -786,6 +786,7 @@ struct bnxt_tx_ring_info {
        u16                     tx_prod;
        u16                     tx_cons;
        u16                     txq_index;
+       u8                      kick_pending;
        struct bnxt_db_info     tx_db;
 
        struct tx_bd            *tx_desc_ring[MAX_TX_PAGES];