Merge branch 'bnxt-tx-napi-disabling-resiliency-improvements'

Jakub Kicinski says:

====================
bnxt: Tx NAPI disabling resiliency improvements

A lockdep warning was triggered by netpoll because napi poll
was taking the xmit lock. Fix that and a couple more issues
noticed while reading the code.
====================

Link: https://lore.kernel.org/r/20210812214242.578039-1-kuba@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

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 +366,33 @@ 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)
+{
+	netif_tx_stop_queue(txq);
+
+	/* netif_tx_stop_queue() must be done before checking
+	 * tx index in bnxt_tx_avail() below, because in
+	 * bnxt_tx_int(), we update tx index before checking for
+	 * netif_tx_queue_stopped().
+	 */
+	smp_mb();
+	if (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh) {
+		netif_tx_wake_queue(txq);
+		return false;
+	}
+
+	return true;
+}
+
 static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -384,6 +412,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	i = skb_get_queue_mapping(skb);
 	if (unlikely(i >= bp->tx_nr_rings)) {
 		dev_kfree_skb_any(skb);
+		atomic_long_inc(&dev->tx_dropped);
 		return NETDEV_TX_OK;
 	}
 
@@ -393,8 +422,12 @@ 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)) {
-		netif_tx_stop_queue(txq);
-		return NETDEV_TX_BUSY;
+		/* 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;
 	}
 
 	length = skb->len;
@@ -517,21 +550,16 @@ 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 |
@@ -618,24 +646,17 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	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);
-
-		netif_tx_stop_queue(txq);
+			bnxt_txr_db_kick(bp, txr, prod);
 
-		/* netif_tx_stop_queue() must be done before checking
-		 * tx index in bnxt_tx_avail() below, because in
-		 * bnxt_tx_int(), we update tx index before checking for
-		 * netif_tx_queue_stopped().
-		 */
-		smp_mb();
-		if (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh)
-			netif_tx_wake_queue(txq);
+		bnxt_txr_netif_try_stop_queue(bp, txr, txq);
 	}
 	return NETDEV_TX_OK;
 
@@ -648,7 +669,6 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* 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);
@@ -662,7 +682,13 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			       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;
+	atomic_long_inc(&dev->tx_dropped);
 	return NETDEV_TX_OK;
 }
 
@@ -732,14 +758,9 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 	smp_mb();
 
 	if (unlikely(netif_tx_queue_stopped(txq)) &&
-	    (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh)) {
-		__netif_tx_lock(txq, smp_processor_id());
-		if (netif_tx_queue_stopped(txq) &&
-		    bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh &&
-		    txr->dev_state != BNXT_DEV_STATE_CLOSING)
-			netif_tx_wake_queue(txq);
-		__netif_tx_unlock(txq);
-	}
+	    bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh &&
+	    READ_ONCE(txr->dev_state) != BNXT_DEV_STATE_CLOSING)
+		netif_tx_wake_queue(txq);
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
@@ -9128,10 +9149,9 @@ static void bnxt_disable_napi(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
 
+		napi_disable(&bp->bnapi[i]->napi);
 		if (bp->bnapi[i]->rx_ring)
 			cancel_work_sync(&cpr->dim.work);
-
-		napi_disable(&bp->bnapi[i]->napi);
 	}
 }
 
@@ -9165,9 +9185,11 @@ void bnxt_tx_disable(struct bnxt *bp)
 	if (bp->tx_ring) {
 		for (i = 0; i < bp->tx_nr_rings; i++) {
 			txr = &bp->tx_ring[i];
-			txr->dev_state = BNXT_DEV_STATE_CLOSING;
+			WRITE_ONCE(txr->dev_state, BNXT_DEV_STATE_CLOSING);
 		}
 	}
+	/* Make sure napi polls see @dev_state change */
+	synchronize_net();
 	/* Drop carrier first to prevent TX timeout */
 	netif_carrier_off(bp->dev);
 	/* Stop all TX queues */
@@ -9181,8 +9203,10 @@ void bnxt_tx_enable(struct bnxt *bp)
 
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		txr = &bp->tx_ring[i];
-		txr->dev_state = 0;
+		WRITE_ONCE(txr->dev_state, 0);
 	}
+	/* Make sure napi polls see @dev_state change */
+	synchronize_net();
 	netif_tx_wake_all_queues(bp->dev);
 	if (bp->link_info.link_up)
 		netif_carrier_on(bp->dev);

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];