Merge branch 'net-lockless-stop-wake-combo-macros'

Jakub Kicinski says:

====================
net: lockless stop/wake combo macros

A lot of drivers follow the same scheme to stop / start queues
without introducing locks between xmit and NAPI tx completions.
I'm guessing they all copy'n'paste each other's code.
The original code dates back all the way to e1000 and Linux 2.6.19.

v3: https://lore.kernel.org/all/20230405223134.94665-1-kuba@kernel.org/
v2: https://lore.kernel.org/all/20230401051221.3160913-2-kuba@kernel.org/
v1: https://lore.kernel.org/all/20230322233028.269410-1-kuba@kernel.org/
rfc: https://lore.kernel.org/all/20230311050130.115138-1-kuba@kernel.org/
====================

Link: https://lore.kernel.org/r/20230407012536.273382-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 19 insertions, 65 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8ff5a4f98d6f..f7602d8d79e3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -56,6 +56,7 @@
 #include <linux/hwmon-sysfs.h>
 #include <net/page_pool.h>
 #include <linux/align.h>
+#include <net/netdev_queues.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -331,26 +332,6 @@ static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 	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);
@@ -384,7 +365,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		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))
+		if (!netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),
+					bp->tx_wake_thresh))
 			return NETDEV_TX_BUSY;
 	}
 
@@ -614,7 +596,8 @@ tx_done:
 		if (netdev_xmit_more() && !tx_buf->is_push)
 			bnxt_txr_db_kick(bp, txr, prod);
 
-		bnxt_txr_netif_try_stop_queue(bp, txr, txq);
+		netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),
+				   bp->tx_wake_thresh);
 	}
 	return NETDEV_TX_OK;
 
@@ -705,20 +688,11 @@ next_tx_int:
 		dev_kfree_skb_any(skb);
 	}
 
-	netdev_tx_completed_queue(txq, nr_pkts, tx_bytes);
 	txr->tx_cons = cons;
 
-	/* Need to make the tx_cons update visible to bnxt_start_xmit()
-	 * before checking for netif_tx_queue_stopped().  Without the
-	 * memory barrier, there is a small possibility that bnxt_start_xmit()
-	 * will miss it and cause the queue to be stopped forever.
-	 */
-	smp_mb();
-
-	if (unlikely(netif_tx_queue_stopped(txq)) &&
-	    bnxt_tx_avail(bp, txr) >= bp->tx_wake_thresh &&
-	    READ_ONCE(txr->dev_state) != BNXT_DEV_STATE_CLOSING)
-		netif_tx_wake_queue(txq);
+	__netif_txq_completed_wake(txq, nr_pkts, tx_bytes,
+				   bnxt_tx_avail(bp, txr), bp->tx_wake_thresh,
+				   READ_ONCE(txr->dev_state) != BNXT_DEV_STATE_CLOSING);
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 773c35fecace..f2604fc05991 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -36,6 +36,7 @@
 #include <net/tc_act/tc_mirred.h>
 #include <net/vxlan.h>
 #include <net/mpls.h>
+#include <net/netdev_queues.h>
 #include <net/xdp_sock_drv.h>
 #include <net/xfrm.h>
 
@@ -1119,6 +1120,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 	unsigned int total_bytes = 0, total_packets = 0, total_ipsec = 0;
 	unsigned int budget = q_vector->tx.work_limit;
 	unsigned int i = tx_ring->next_to_clean;
+	struct netdev_queue *txq;
 
 	if (test_bit(__IXGBE_DOWN, &adapter->state))
 		return true;
@@ -1249,24 +1251,14 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 	if (ring_is_xdp(tx_ring))
 		return !!budget;
 
-	netdev_tx_completed_queue(txring_txq(tx_ring),
-				  total_packets, total_bytes);
-
 #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
-	if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
-		     (ixgbe_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) {
-		/* Make sure that anybody stopping the queue after this
-		 * sees the new next_to_clean.
-		 */
-		smp_mb();
-		if (__netif_subqueue_stopped(tx_ring->netdev,
-					     tx_ring->queue_index)
-		    && !test_bit(__IXGBE_DOWN, &adapter->state)) {
-			netif_wake_subqueue(tx_ring->netdev,
-					    tx_ring->queue_index);
-			++tx_ring->tx_stats.restart_queue;
-		}
-	}
+	txq = netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
+	if (!__netif_txq_completed_wake(txq, total_packets, total_bytes,
+					ixgbe_desc_unused(tx_ring),
+					TX_WAKE_THRESHOLD,
+					netif_carrier_ok(tx_ring->netdev) &&
+					test_bit(__IXGBE_DOWN, &adapter->state)))
+		++tx_ring->tx_stats.restart_queue;
 
 	return !!budget;
 }
@@ -8270,22 +8262,10 @@ static void ixgbe_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc,
 
 static int __ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
 {
-	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
-
-	/* Herbert's original patch had:
-	 *  smp_mb__after_netif_stop_queue();
-	 * but since that doesn't exist yet, just open code it.
-	 */
-	smp_mb();
-
-	/* We need to check again in a case another CPU has just
-	 * made room available.
-	 */
-	if (likely(ixgbe_desc_unused(tx_ring) < size))
+	if (!netif_subqueue_try_stop(tx_ring->netdev, tx_ring->queue_index,
+				     ixgbe_desc_unused(tx_ring), size))
 		return -EBUSY;
 
-	/* A reprieve! - use start_queue because it doesn't call schedule */
-	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
 	++tx_ring->tx_stats.restart_queue;
 	return 0;
 }