summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2018-09-21 15:27:38 -0700
committerDavid S. Miller <davem@davemloft.net>2018-09-23 21:55:24 -0700
commitac3d9dd034e565df2c034ab2ca71f0a9f69153c1 (patch)
tree8cc679798aebb820bdbb0df3c817a6e114ddce8f /net
parent16fdf8ba98391650ce4bc4f3f71629d8a413bc21 (diff)
downloadlinux-stable-ac3d9dd034e565df2c034ab2ca71f0a9f69153c1.tar.gz
linux-stable-ac3d9dd034e565df2c034ab2ca71f0a9f69153c1.tar.bz2
linux-stable-ac3d9dd034e565df2c034ab2ca71f0a9f69153c1.zip
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>
Diffstat (limited to 'net')
-rw-r--r--net/core/netpoll.c19
1 files changed, 7 insertions, 12 deletions
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 57557a6a950c..3219a2932463 100644
--- 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;