From: Kaike Wan <kaike.wan@xxxxxxxxx>
commit 90fdae66e72bf0381d168f12dca0259617927895 upstream.
In a congested fabric with adaptive routing enabled, traces show that
packets could be delivered out of order, which could cause incorrect
processing of stale packets. For stale TID RDMA WRITE DATA packets that
cause KDETH EFLAGS errors, this patch adds additional checks before
processing the packets.
Fixes: d72fe7d5008b ("IB/hfi1: Add a function to receive TID RDMA WRITE DATA packet")
Cc: <stable@xxxxxxxxxxxxxxx>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@xxxxxxxxx>
Signed-off-by: Kaike Wan <kaike.wan@xxxxxxxxx>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@xxxxxxxxx>
Link: https://lore.kernel.org/r/20190815192051.105923.69979.stgit@xxxxxxxxxxxxxxxxxxxx
Signed-off-by: Doug Ledford <dledford@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/infiniband/hw/hfi1/tid_rdma.c | 7 +++++++
1 file changed, 7 insertions(+)
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -2947,8 +2947,15 @@ bool hfi1_handle_kdeth_eflags(struct hfi
*/
spin_lock(&qp->s_lock);
qpriv = qp->priv;
+ if (qpriv->r_tid_tail == HFI1_QP_WQE_INVALID ||
+ qpriv->r_tid_tail == qpriv->r_tid_head)
+ goto unlock;
e = &qp->s_ack_queue[qpriv->r_tid_tail];
+ if (e->opcode != TID_OP(WRITE_REQ))
+ goto unlock;
req = ack_to_tid_req(e);
+ if (req->comp_seg == req->cur_seg)
+ goto unlock;
flow = &req->flows[req->clear_tail];
trace_hfi1_eflags_err_write(qp, rcv_type, rte, psn);
trace_hfi1_rsp_handle_kdeth_eflags(qp, psn);
