Merge branch 'lockless-qdisc-packet-stuck'

Yunsheng Lin says:

====================
ix packet stuck problem for lockless qdisc

This patchset fixes the packet stuck problem mentioned in [1].

Patch 1: Add STATE_MISSED flag to fix packet stuck problem.
Patch 2: Fix a tx_action rescheduling problem after STATE_MISSED
         flag is added in patch 1.
Patch 3: Fix the significantly higher CPU consumption problem when
         multiple threads are competing on a saturated outgoing
         device.

V8: Change function name as suggested by Jakub and fix some typo
    in patch 3, adjust commit log in patch 2, and add Acked-by
    from Jakub.
V7: Fix netif_tx_wake_queue() data race noted by Jakub.
V6: Some performance optimization in patch 1 suggested by Jakub
    and drop NET_XMIT_DROP checking in patch 3.
V5: add patch 3 to fix the problem reported by Michal Kubecek.
V4: Change STATE_NEED_RESCHEDULE to STATE_MISSED and add patch 2.

[1]. https://lkml.org/lkml/2019/10/9/42
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 35 insertions, 7 deletions

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index f5c1bee0cd6a..6d7b12cba015 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -128,12 +128,7 @@ void __qdisc_run(struct Qdisc *q);
 static inline void qdisc_run(struct Qdisc *q)
 {
 	if (qdisc_run_begin(q)) {
-		/* NOLOCK qdisc must check 'state' under the qdisc seqlock
-		 * to avoid racing with dev_qdisc_reset()
-		 */
-		if (!(q->flags & TCQ_F_NOLOCK) ||
-		    likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
-			__qdisc_run(q);
+		__qdisc_run(q);
 		qdisc_run_end(q);
 	}
 }
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f7a6e14491fb..1e625519ae96 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -36,6 +36,7 @@ struct qdisc_rate_table {
 enum qdisc_state_t {
 	__QDISC_STATE_SCHED,
 	__QDISC_STATE_DEACTIVATED,
+	__QDISC_STATE_MISSED,
 };
 
 struct qdisc_size_table {
@@ -159,8 +160,33 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK) {
+		if (spin_trylock(&qdisc->seqlock))
+			goto nolock_empty;
+
+		/* If the MISSED flag is set, it means other thread has
+		 * set the MISSED flag before second spin_trylock(), so
+		 * we can return false here to avoid multi cpus doing
+		 * the set_bit() and second spin_trylock() concurrently.
+		 */
+		if (test_bit(__QDISC_STATE_MISSED, &qdisc->state))
+			return false;
+
+		/* Set the MISSED flag before the second spin_trylock(),
+		 * if the second spin_trylock() return false, it means
+		 * other cpu holding the lock will do dequeuing for us
+		 * or it will see the MISSED flag set after releasing
+		 * lock and reschedule the net_tx_action() to do the
+		 * dequeuing.
+		 */
+		set_bit(__QDISC_STATE_MISSED, &qdisc->state);
+
+		/* Retry again in case other CPU may not see the new flag
+		 * after it releases the lock at the end of qdisc_run_end().
+		 */
 		if (!spin_trylock(&qdisc->seqlock))
 			return false;
+
+nolock_empty:
 		WRITE_ONCE(qdisc->empty, false);
 	} else if (qdisc_is_running(qdisc)) {
 		return false;
@@ -176,8 +202,15 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
 	write_seqcount_end(&qdisc->running);
-	if (qdisc->flags & TCQ_F_NOLOCK)
+	if (qdisc->flags & TCQ_F_NOLOCK) {
 		spin_unlock(&qdisc->seqlock);
+
+		if (unlikely(test_bit(__QDISC_STATE_MISSED,
+				      &qdisc->state))) {
+			clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+			__netif_schedule(qdisc);
+		}
+	}
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)