IB/ehca: Discard double CQE for one WR

Under rare circumstances, the ehca hardware might erroneously generate
two CQEs for the same WQE, which is not compliant to the IB spec and
will cause unpredictable errors like memory being freed twice. To
avoid this problem, the driver needs to detect the second CQE and
discard it.

For this purpose, introduce an array holding as many elements as the
SQ of the QP, called sq_map. Each sq_map entry stores a "reported"
flag for one WQE in the SQ. When a work request is posted to the SQ,
the respective "reported" flag is set to zero. After the arrival of a
CQE, the flag is set to 1, which allows to detect the occurence of a
second CQE.

The mapping between WQE / CQE and the corresponding sq_map element is
implemented by replacing the lowest 16 Bits of the wr_id with the
index in the queue map. The original 16 Bits are stored in the sq_map
entry and are restored when the CQE is passed to the application.

Signed-off-by: Alexander Schmidt <alexs@linux.vnet.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 43 insertions, 11 deletions

diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c b/drivers/infiniband/hw/ehca/ehca_reqs.c
index cea3eba9c83..4426d82fe79 100644
--- a/drivers/infiniband/hw/ehca/ehca_reqs.c
+++ b/drivers/infiniband/hw/ehca/ehca_reqs.c
@@ -139,6 +139,7 @@ static void trace_send_wr_ud(const struct ib_send_wr *send_wr)
 static inline int ehca_write_swqe(struct ehca_qp *qp,
 				  struct ehca_wqe *wqe_p,
 				  const struct ib_send_wr *send_wr,
+				  u32 sq_map_idx,
 				  int hidden)
 {
 	u32 idx;
@@ -157,7 +158,11 @@ static inline int ehca_write_swqe(struct ehca_qp *qp,
 	/* clear wqe header until sglist */
 	memset(wqe_p, 0, offsetof(struct ehca_wqe, u.ud_av.sg_list));
 
-	wqe_p->work_request_id = send_wr->wr_id;
+	wqe_p->work_request_id = send_wr->wr_id & ~QMAP_IDX_MASK;
+	wqe_p->work_request_id |= sq_map_idx & QMAP_IDX_MASK;
+
+	qp->sq_map[sq_map_idx].app_wr_id = send_wr->wr_id & QMAP_IDX_MASK;
+	qp->sq_map[sq_map_idx].reported = 0;
 
 	switch (send_wr->opcode) {
 	case IB_WR_SEND:
@@ -381,6 +386,7 @@ static inline int post_one_send(struct ehca_qp *my_qp,
 {
 	struct ehca_wqe *wqe_p;
 	int ret;
+	u32 sq_map_idx;
 	u64 start_offset = my_qp->ipz_squeue.current_q_offset;
 
 	/* get pointer next to free WQE */
@@ -393,8 +399,15 @@ static inline int post_one_send(struct ehca_qp *my_qp,
 			 "qp_num=%x", my_qp->ib_qp.qp_num);
 		return -ENOMEM;
 	}
+
+	/*
+	 * Get the index of the WQE in the send queue. The same index is used
+	 * for writing into the sq_map.
+	 */
+	sq_map_idx = start_offset / my_qp->ipz_squeue.qe_size;
+
 	/* write a SEND WQE into the QUEUE */
-	ret = ehca_write_swqe(my_qp, wqe_p, cur_send_wr, hidden);
+	ret = ehca_write_swqe(my_qp, wqe_p, cur_send_wr, sq_map_idx, hidden);
 	/*
 	 * if something failed,
 	 * reset the free entry pointer to the start value
@@ -654,8 +667,34 @@ repoll:
 			 my_cq, my_cq->cq_number);
 	}
 
-	/* we got a completion! */
-	wc->wr_id = cqe->work_request_id;
+	read_lock(&ehca_qp_idr_lock);
+	my_qp = idr_find(&ehca_qp_idr, cqe->qp_token);
+	read_unlock(&ehca_qp_idr_lock);
+	if (!my_qp)
+		goto repoll;
+	wc->qp = &my_qp->ib_qp;
+
+	if (!(cqe->w_completion_flags & WC_SEND_RECEIVE_BIT)) {
+		struct ehca_qmap_entry *qmap_entry;
+		/*
+		 * We got a send completion and need to restore the original
+		 * wr_id.
+		 */
+		qmap_entry = &my_qp->sq_map[cqe->work_request_id &
+					    QMAP_IDX_MASK];
+
+		if (qmap_entry->reported) {
+			ehca_warn(cq->device, "Double cqe on qp_num=%#x",
+				  my_qp->real_qp_num);
+			/* found a double cqe, discard it and read next one */
+			goto repoll;
+		}
+		wc->wr_id = cqe->work_request_id & ~QMAP_IDX_MASK;
+		wc->wr_id |= qmap_entry->app_wr_id;
+		qmap_entry->reported = 1;
+	} else
+		/* We got a receive completion. */
+		wc->wr_id = cqe->work_request_id;
 
 	/* eval ib_wc_opcode */
 	wc->opcode = ib_wc_opcode[cqe->optype]-1;
@@ -678,13 +717,6 @@ repoll:
 	} else
 		wc->status = IB_WC_SUCCESS;
 
-	read_lock(&ehca_qp_idr_lock);
-	my_qp = idr_find(&ehca_qp_idr, cqe->qp_token);
-	read_unlock(&ehca_qp_idr_lock);
-	if (!my_qp)
-		goto repoll;
-	wc->qp = &my_qp->ib_qp;
-
 	wc->byte_len = cqe->nr_bytes_transferred;
 	wc->pkey_index = cqe->pkey_index;
 	wc->slid = cqe->rlid;