net: link_watch: prevent starvation when processing linkwatch wq

When user has configured a large number of virtual netdev, such
as 4K vlans, the carrier on/off operation of the real netdev
will also cause it's virtual netdev's link state to be processed
in linkwatch. Currently, the processing is done in a work queue,
which may cause rtnl locking starvation problem and worker
starvation problem for other work queue, such as irqfd_inject wq.

This patch releases the cpu when link watch worker has processed
a fixed number of netdev' link watch event, and schedule the
work queue again when there is still link watch event remaining.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 12 insertions, 1 deletions

diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 04fdc9535772..f153e0601838 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -163,9 +163,16 @@ static void linkwatch_do_dev(struct net_device *dev)
 
 static void __linkwatch_run_queue(int urgent_only)
 {
+#define MAX_DO_DEV_PER_LOOP     100
+
+        int do_dev = MAX_DO_DEV_PER_LOOP;
         struct net_device *dev;
         LIST_HEAD(wrk);
 
+        /* Give urgent case more budget */
+        if (urgent_only)
+                do_dev += MAX_DO_DEV_PER_LOOP;
+
         /*
          * Limit the number of linkwatch events to one
          * per second so that a runaway driver does not
@@ -184,7 +191,7 @@ static void __linkwatch_run_queue(int urgent_only)
         spin_lock_irq(&lweventlist_lock);
         list_splice_init(&lweventlist, &wrk);
 
-        while (!list_empty(&wrk)) {
+        while (!list_empty(&wrk) && do_dev > 0) {
 
                 dev = list_first_entry(&wrk, struct net_device, link_watch_list);
                 list_del_init(&dev->link_watch_list);
@@ -195,9 +202,13 @@ static void __linkwatch_run_queue(int urgent_only)
                 }
                 spin_unlock_irq(&lweventlist_lock);
                 linkwatch_do_dev(dev);
+                do_dev--;
                 spin_lock_irq(&lweventlist_lock);
         }
 
+        /* Add the remaining work back to lweventlist */
+        list_splice_init(&wrk, &lweventlist);
+
         if (!list_empty(&lweventlist))
                 linkwatch_schedule_work(0);
         spin_unlock_irq(&lweventlist_lock);