summaryrefslogtreecommitdiffstats
path: root/drivers
diff options
context:
space:
mode:
authorMike Marciniszyn <mike.marciniszyn@qlogic.com>2011-02-16 15:48:25 +0000
committerRoland Dreier <roland@purestorage.com>2011-02-17 14:04:50 -0800
commitc0af2c057d7ce3f0b260f9380d187a82bb5cab28 (patch)
tree30b59bf396145825d5b005dcc8f6fa1abf5c2b1f /drivers
parent414ed90cee32486c50f91b28990443e0dc21c868 (diff)
downloadlinux-c0af2c057d7ce3f0b260f9380d187a82bb5cab28.tar.bz2
IB/qib: Prevent double completions after a timeout or RNR error
There is a double completion associated with error handling for RC QPs. The sequence is: - The do_rc_ack() routine fields an RNR nack and there are 0 rnr_retries configured on the QP. - qib_error_qp() stops the pending timer - qib_rc_send_complete() is called from sdma_complete() - qib_rc_send_complete() starts the timer because the msb of the psn just completed says an ack is needed. - a bunch of flushes occur as ipoib posts WQEs to an error'ed QP - rc_timeout() calls qib_restart_rc() - qib_restart_rc() calls qib_send_complete() with a IB_WC_RETRY_EXC_ERR on a wqe that has already been completed in the past The fix avoids starting the timer since another packet will never arrive. Signed-off-by: Mike Marciniszyn <mike.marciniszyn@qlogic.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/infiniband/hw/qib/qib_rc.c3
1 files changed, 2 insertions, 1 deletions
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index 31e09b05a1a7..eca0c41f1226 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -1005,7 +1005,8 @@ void qib_rc_send_complete(struct qib_qp *qp, struct qib_ib_header *hdr)
* there are still requests that haven't been acked.
*/
if ((psn & IB_BTH_REQ_ACK) && qp->s_acked != qp->s_tail &&
- !(qp->s_flags & (QIB_S_TIMER | QIB_S_WAIT_RNR | QIB_S_WAIT_PSN)))
+ !(qp->s_flags & (QIB_S_TIMER | QIB_S_WAIT_RNR | QIB_S_WAIT_PSN)) &&
+ (ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK))
start_timer(qp);
while (qp->s_last != qp->s_acked) {