netpoll: make ndo_poll_controller() optional

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

It seems that all networking drivers that do use NAPI
for their TX completions, should not provide a ndo_poll_controller().

NAPI drivers have netpoll support already handled
in core networking stack, since netpoll_poll_dev()
uses poll_napi(dev) to iterate through registered
NAPI contexts for a device.

This patch allows netpoll_poll_dev() to process NAPI
contexts even for drivers not providing ndo_poll_controller(),
allowing for following patches in NAPI drivers.

Also we export netpoll_poll_dev() so that it can be called
by bonding/team drivers in following patches.

Reported-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 67662d01130a7b4f69c8b4ec176f59b11e8ae33d..3ef82d3a78db51d958858470f8158f72cfd74fb3 100644 (file)
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -49,8 +49,9 @@ struct netpoll_info {
 };
 
 #ifdef CONFIG_NETPOLL
-extern void netpoll_poll_disable(struct net_device *dev);
-extern void netpoll_poll_enable(struct net_device *dev);
+void netpoll_poll_dev(struct net_device *dev);
+void netpoll_poll_disable(struct net_device *dev);
+void netpoll_poll_enable(struct net_device *dev);
 #else
 static inline void netpoll_poll_disable(struct net_device *dev) { return; }
 static inline void netpoll_poll_enable(struct net_device *dev) { return; }

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 57557a6a950cc9cdff959391576a03381d328c1a..3219a2932463096566ce8ff336ecdf699422dd65 100644 (file)
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -187,16 +187,16 @@ static void poll_napi(struct net_device *dev)
        }
 }
 
-static void netpoll_poll_dev(struct net_device *dev)
+void netpoll_poll_dev(struct net_device *dev)
 {
-       const struct net_device_ops *ops;
        struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
+       const struct net_device_ops *ops;
 
        /* Don't do any rx activity if the dev_lock mutex is held
         * the dev_open/close paths use this to block netpoll activity
         * while changing device state
         */
-       if (down_trylock(&ni->dev_lock))
+       if (!ni || down_trylock(&ni->dev_lock))
                return;
 
        if (!netif_running(dev)) {
@@ -205,13 +205,8 @@ static void netpoll_poll_dev(struct net_device *dev)
        }
 
        ops = dev->netdev_ops;
-       if (!ops->ndo_poll_controller) {
-               up(&ni->dev_lock);
-               return;
-       }
-
-       /* Process pending work on NIC */
-       ops->ndo_poll_controller(dev);
+       if (ops->ndo_poll_controller)
+               ops->ndo_poll_controller(dev);
 
        poll_napi(dev);
 
@@ -219,6 +214,7 @@ static void netpoll_poll_dev(struct net_device *dev)
 
        zap_completion_queue();
 }
+EXPORT_SYMBOL(netpoll_poll_dev);
 
 void netpoll_poll_disable(struct net_device *dev)
 {
@@ -613,8 +609,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
        strlcpy(np->dev_name, ndev->name, IFNAMSIZ);
        INIT_WORK(&np->cleanup_work, netpoll_async_cleanup);
 
-       if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) ||
-           !ndev->netdev_ops->ndo_poll_controller) {
+       if (ndev->priv_flags & IFF_DISABLE_NETPOLL) {
                np_err(np, "%s doesn't support polling, aborting\n",
                       np->dev_name);
                err = -ENOTSUPP;