From 3d2e7424b3e18dc851a4b0efdc6676c09573f55f Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Tue, 26 Feb 2013 15:46:27 +0000 Subject: IPoIB: Fix send lockup due to missed TX completion commit 1ee9e2aa7b31427303466776f455d43e5e3c9275 upstream. Commit f0dc117abdfa ("IPoIB: Fix TX queue lockup with mixed UD/CM traffic") attempts to solve an issue where unprocessed UD send completions can deadlock the netdev. The patch doesn't fully resolve the issue because if more than half the tx_outstanding's were UD and all of the destinations are RC reachable, arming the CQ doesn't solve the issue. This patch uses the IB_CQ_REPORT_MISSED_EVENTS on the ib_req_notify_cq(). If the rc is above 0, the UD send cq completion callback is called directly to re-arm the send completion timer. This issue is seen in very large parallel filesystem deployments and the patch has been shown to correct the issue. Reviewed-by: Dean Luick Signed-off-by: Mike Marciniszyn Signed-off-by: Roland Dreier Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 014504d8e43..37678536442 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -755,9 +755,13 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ if (++priv->tx_outstanding == ipoib_sendq_size) { ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n", tx->qp->qp_num); - if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP)) - ipoib_warn(priv, "request notify on send CQ failed\n"); netif_stop_queue(dev); + rc = ib_req_notify_cq(priv->send_cq, + IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS); + if (rc < 0) + ipoib_warn(priv, "request notify on send CQ failed\n"); + else if (rc) + ipoib_send_comp_handler(priv->send_cq, dev); } } } -- cgit v1.2.3-18-g5258