1 files changed, 82 insertions, 20 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 6deba68ad9e4..369dcc8efc01 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4902,6 +4902,12 @@ void __napi_complete(struct napi_struct *n)
 {
         BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
 
+        /* Some drivers call us directly, instead of calling
+         * napi_complete_done().
+         */
+        if (unlikely(test_bit(NAPI_STATE_IN_BUSY_POLL, &n->state)))
+                return;
+
         list_del_init(&n->poll_list);
         smp_mb__before_atomic();
         clear_bit(NAPI_STATE_SCHED, &n->state);
@@ -4913,10 +4919,13 @@ void napi_complete_done(struct napi_struct *n, int work_done)
         unsigned long flags;
 
         /*
-         * don't let napi dequeue from the cpu poll list
-         * just in case its running on a different cpu
+         * 1) Don't let napi dequeue from the cpu poll list
+         *    just in case its running on a different cpu.
+         * 2) If we are busy polling, do nothing here, we have
+         *    the guarantee we will be called later.
          */
-        if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
+        if (unlikely(n->state & (NAPIF_STATE_NPSVC |
+                                 NAPIF_STATE_IN_BUSY_POLL)))
                 return;
 
         if (n->gro_list) {
@@ -4956,13 +4965,41 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)
 }
 
 #if defined(CONFIG_NET_RX_BUSY_POLL)
+
 #define BUSY_POLL_BUDGET 8
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
+{
+        int rc;
+
+        clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state);
+
+        local_bh_disable();
+
+        /* All we really want here is to re-enable device interrupts.
+         * Ideally, a new ndo_busy_poll_stop() could avoid another round.
+         */
+        rc = napi->poll(napi, BUSY_POLL_BUDGET);
+        netpoll_poll_unlock(have_poll_lock);
+        if (rc == BUSY_POLL_BUDGET)
+                __napi_schedule(napi);
+        local_bh_enable();
+        if (local_softirq_pending())
+                do_softirq();
+}
+
 bool sk_busy_loop(struct sock *sk, int nonblock)
 {
         unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
+        int (*napi_poll)(struct napi_struct *napi, int budget);
         int (*busy_poll)(struct napi_struct *dev);
+        void *have_poll_lock = NULL;
         struct napi_struct *napi;
-        int rc = false;
+        int rc;
+
+restart:
+        rc = false;
+        napi_poll = NULL;
 
         rcu_read_lock();
 
@@ -4973,24 +5010,33 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
         /* Note: ndo_busy_poll method is optional in linux-4.5 */
         busy_poll = napi->dev->netdev_ops->ndo_busy_poll;
 
-        do {
+        preempt_disable();
+        for (;;) {
                 rc = 0;
                 local_bh_disable();
                 if (busy_poll) {
                         rc = busy_poll(napi);
-                } else if (napi_schedule_prep(napi)) {
-                        void *have = netpoll_poll_lock(napi);
-
-                        if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
-                                rc = napi->poll(napi, BUSY_POLL_BUDGET);
-                                trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
-                                if (rc == BUSY_POLL_BUDGET) {
-                                        napi_complete_done(napi, rc);
-                                        napi_schedule(napi);
-                                }
-                        }
-                        netpoll_poll_unlock(have);
+                        goto count;
                 }
+                if (!napi_poll) {
+                        unsigned long val = READ_ONCE(napi->state);
+
+                        /* If multiple threads are competing for this napi,
+                         * we avoid dirtying napi->state as much as we can.
+                         */
+                        if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
+                                   NAPIF_STATE_IN_BUSY_POLL))
+                                goto count;
+                        if (cmpxchg(&napi->state, val,
+                                    val | NAPIF_STATE_IN_BUSY_POLL |
+                                          NAPIF_STATE_SCHED) != val)
+                                goto count;
+                        have_poll_lock = netpoll_poll_lock(napi);
+                        napi_poll = napi->poll;
+                }
+                rc = napi_poll(napi, BUSY_POLL_BUDGET);
+                trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+count:
                 if (rc > 0)
                         __NET_ADD_STATS(sock_net(sk),
                                         LINUX_MIB_BUSYPOLLRXPACKETS, rc);
@@ -4999,10 +5045,26 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
                 if (rc == LL_FLUSH_FAILED)
                         break; /* permanent failure */
 
-                cpu_relax();
-        } while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) &&
-                 !need_resched() && !busy_loop_timeout(end_time));
+                if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) ||
+                    busy_loop_timeout(end_time))
+                        break;
 
+                if (unlikely(need_resched())) {
+                        if (napi_poll)
+                                busy_poll_stop(napi, have_poll_lock);
+                        preempt_enable();
+                        rcu_read_unlock();
+                        cond_resched();
+                        rc = !skb_queue_empty(&sk->sk_receive_queue);
+                        if (rc || busy_loop_timeout(end_time))
+                                return rc;
+                        goto restart;
+                }
+                cpu_relax_lowlatency();
+        }
+        if (napi_poll)
+                busy_poll_stop(napi, have_poll_lock);
+        preempt_enable();
         rc = !skb_queue_empty(&sk->sk_receive_queue);
 out:
         rcu_read_unlock();