| Message ID | 1455719863-25730-1-git-send-email-phil@nwl.cc |
|---|---|
| State | Accepted, archived |
| Delegated to: | David Miller |
| Headers | show |
From: Phil Sutter <phil@nwl.cc> Date: Wed, 17 Feb 2016 15:37:43 +0100 > My implementation around IFF_NO_QUEUE driver flag assumed that leaving > tx_queue_len untouched (specifically: not setting it to zero) by drivers > would make it possible to assign a regular qdisc to them without having > to worry about setting tx_queue_len to a useful value. This was only > partially true: I overlooked that some drivers don't call ether_setup() > and therefore not initialize tx_queue_len to the default value of 1000. > Consequently, removing the workarounds in place for that case in qdisc > implementations which cared about it (namely, pfifo, bfifo, gred, htb, > plug and sfb) leads to problems with these specific interface types and > qdiscs. > > Luckily, there's already a sanitization point for drivers setting > tx_queue_len to zero, which can be reused to assign the fallback value > most qdisc implementations used, which is 1. > > Fixes: 348e3435cbefa ("net: sched: drop all special handling of tx_queue_len == 0") > Tested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> > Signed-off-by: Phil Sutter <phil@nwl.cc> Applied and queued up for -stable, thanks.
diff --git a/net/core/dev.c b/net/core/dev.c index 3f4071a84a03f..75383f40e7ced 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7440,8 +7440,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); - if (!dev->tx_queue_len) + if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; + dev->tx_queue_len = 1; + } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs;
My implementation around IFF_NO_QUEUE driver flag assumed that leaving tx_queue_len untouched (specifically: not setting it to zero) by drivers would make it possible to assign a regular qdisc to them without having to worry about setting tx_queue_len to a useful value. This was only partially true: I overlooked that some drivers don't call ether_setup() and therefore not initialize tx_queue_len to the default value of 1000. Consequently, removing the workarounds in place for that case in qdisc implementations which cared about it (namely, pfifo, bfifo, gred, htb, plug and sfb) leads to problems with these specific interface types and qdiscs. Luckily, there's already a sanitization point for drivers setting tx_queue_len to zero, which can be reused to assign the fallback value most qdisc implementations used, which is 1. Fixes: 348e3435cbefa ("net: sched: drop all special handling of tx_queue_len == 0") Tested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Phil Sutter <phil@nwl.cc> --- net/core/dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)