From: Ralph Campbell Date: Thu, 15 Mar 2007 21:44:50 +0000 (-0700) Subject: IB/ipath: NMI cpu lockup if local loopback used X-Git-Tag: v2.6.22-rc1~1126^2~40 X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=7b21d26ddad6912bf345e8e88a51a5ce98a036ad;p=linux-2.6 IB/ipath: NMI cpu lockup if local loopback used If a post send is done in loopback and there is no receive queue entry, the sending QP is put on a timeout list for a while so the receiver has a chance to post a receive buffer. If the another post send is done, the code incorrectly tried to put the QP on the timeout list again an corrupted the timeout list. This eventually leads to a spin lock deadlock NMI due to the timer function looping forever with the lock held. Signed-off-by: Bryan O'Sullivan Signed-off-by: Roland Dreier --- diff --git a/drivers/infiniband/hw/ipath/ipath_ruc.c b/drivers/infiniband/hw/ipath/ipath_ruc.c index 146db85169..cda84933bb 100644 --- a/drivers/infiniband/hw/ipath/ipath_ruc.c +++ b/drivers/infiniband/hw/ipath/ipath_ruc.c @@ -265,7 +265,8 @@ static void ipath_ruc_loopback(struct ipath_qp *sqp) again: spin_lock_irqsave(&sqp->s_lock, flags); - if (!(ib_ipath_state_ops[sqp->state] & IPATH_PROCESS_SEND_OK)) { + if (!(ib_ipath_state_ops[sqp->state] & IPATH_PROCESS_SEND_OK) || + qp->s_rnr_timeout) { spin_unlock_irqrestore(&sqp->s_lock, flags); goto done; }