[PATCH net-next] net: add a fast path in __netif_schedule()

Cpus serving NIC interrupts and specifically TX completions are often
trapped in also restarting a busy qdisc (because qdisc was stopped by BQL
or the driver's own flow control).

When they call netdev_tx_completed_queue() or netif_tx_wake_queue(),
they call __netif_schedule() so that the queue can be run
later from net_tx_action() (involving NET_TX_SOFTIRQ)

Quite often, by the time the cpu reaches net_tx_action(), another cpu
grabbed the qdisc spinlock from __dev_xmit_skb(), and we spend too much
time spinning on this lock.

We can detect in __netif_schedule() if a cpu is already at a specific
point in __dev_xmit_skb() where we have the guarantee the queue will
be run.

This patch gives a 13 % increase of throughput on an IDPF NIC (200Gbit),
32 TX qeues, sending UDP packets of 120 bytes.

This also helps __qdisc_run() to not force a NET_TX_SOFTIRQ
if another thread is waiting in __dev_xmit_skb()

Before:

sar -n DEV 5 5|grep eth1|grep Average
Average:         eth1   1496.44 52191462.56    210.00 13369396.90      0.00      0.00      0.00     54.76

After:

sar -n DEV 5 5|grep eth1|grep Average
Average:         eth1   1457.88 59363099.96    205.08 15206384.35      0.00      0.00      0.00     62.29

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/core/dev.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 821e7c718924405d0a7c10e41f677b98aa2d070b..9482b905c66a53501ad3b737ad4461533b9e7a4e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c

@@ -3373,6 +3373,13 @@ static void __netif_reschedule(struct Qdisc *q)
 
 void __netif_schedule(struct Qdisc *q)
 {
+	/* If q->defer_list is not empty, at least one thread is
+	 * in __dev_xmit_skb() before llist_del_all(&q->defer_list).
+	 * This thread will attempt to run the queue.
+	 */
+	if (!llist_empty(&q->defer_list))
+		return;
+
 	if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state))
 		__netif_reschedule(q);
 }

-- 
2.51.0.858.gf9c4a03a3a-goog