diff options
| author | Roland Dreier <roland@purestorage.com> | 2012-12-19 09:16:43 -0800 |
|---|---|---|
| committer | Roland Dreier <roland@purestorage.com> | 2012-12-19 09:16:43 -0800 |
| commit | b13912bbb4a2d445c35db24586eb6ecf4707d52d (patch) | |
| tree | 1cd9be4af43845b21861384e66d93e9d71f690b2 /drivers/infiniband/ulp | |
| parent | 5bd665f28db2b04a8d6fe277342479906fc60b62 (diff) | |
IPoIB: Call skb_dst_drop() once skb is enqueued for sending
Currently, IPoIB delays collecting send completions for TX packets in
order to batch work more efficiently. It does skb_orphan() right after
queuing the packets so that destructors run early, to avoid problems
like holding socket send buffers for too long (since we might not
collect a send completion until a long time after the packet is
actually sent).
However, IPoIB clears IFF_XMIT_DST_RELEASE because it actually looks
at skb_dst() to update the PMTU when it gets a too-long packet. This
means that the packets sitting in the TX ring with uncollected send
completions are holding a reference on the dst. We've seen this lead
to pathological behavior with respect to route and neighbour GC. The
easy fix for this is to call skb_dst_drop() when we call skb_orphan().
Also, give packets sent via connected mode (CM) the same skb_orphan()
/ skb_dst_drop() treatment that packets sent via datagram mode get.
Signed-off-by: Roland Dreier <roland@purestorage.com>
Diffstat (limited to 'drivers/infiniband/ulp')
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_cm.c | 3 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ib.c | 3 |
2 files changed, 5 insertions, 1 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 72ae63f0072..03103d2bd64 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -752,6 +752,9 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ dev->trans_start = jiffies; ++tx->tx_head; + skb_orphan(skb); + skb_dst_drop(skb); + if (++priv->tx_outstanding == ipoib_sendq_size) { ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n", tx->qp->qp_num); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index f10221f4080..a1bca70e20a 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -615,8 +615,9 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, address->last_send = priv->tx_head; ++priv->tx_head; - skb_orphan(skb); + skb_orphan(skb); + skb_dst_drop(skb); } if (unlikely(priv->tx_outstanding > MAX_SEND_CQE)) |