From: Kaike Wan <kaike.wan@xxxxxxxxx> This patch adds traces to debug packet loss and retry for TID RDMA READ protocol. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@xxxxxxxxx> Signed-off-by: Kaike Wan <kaike.wan@xxxxxxxxx> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@xxxxxxxxx> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@xxxxxxxxx> --- drivers/infiniband/hw/hfi1/rc.c | 5 ++++ drivers/infiniband/hw/hfi1/tid_rdma.c | 8 +++++++ drivers/infiniband/hw/hfi1/trace_tid.h | 38 ++++++++++++++++++++++++++++++++ 3 files changed, 51 insertions(+) diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 024a7c2..eeca08d 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -1483,6 +1483,11 @@ static void update_num_rd_atomic(struct rvt_qp *qp, u32 psn, req->ack_pending = cur_seg - req->comp_seg; priv->pending_tid_r_segs += req->ack_pending; qp->s_num_rd_atomic += req->ack_pending; + trace_hfi1_tid_req_update_num_rd_atomic(qp, 0, + wqe->wr.opcode, + wqe->psn, + wqe->lpsn, + req); } else { priv->pending_tid_r_segs += req->total_segs; qp->s_num_rd_atomic += req->total_segs; diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 04061d5..ab126b1 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -2687,6 +2687,9 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd, u32 fpsn; lockdep_assert_held(&qp->r_lock); + trace_hfi1_rsp_read_kdeth_eflags(qp, ibpsn); + trace_hfi1_sender_read_kdeth_eflags(qp); + trace_hfi1_tid_read_sender_kdeth_eflags(qp, 0); spin_lock(&qp->s_lock); /* If the psn is out of valid range, drop the packet */ if (cmp_psn(ibpsn, qp->s_last_psn) < 0 || @@ -2748,6 +2751,8 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd, goto s_unlock; req = wqe_to_tid_req(wqe); + trace_hfi1_tid_req_read_kdeth_eflags(qp, 0, wqe->wr.opcode, wqe->psn, + wqe->lpsn, req); switch (rcv_type) { case RHF_RCV_TYPE_EXPECTED: switch (rte) { @@ -2762,6 +2767,9 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd, * packets that could be still in the fabric. */ flow = &req->flows[req->clear_tail]; + trace_hfi1_tid_flow_read_kdeth_eflags(qp, + req->clear_tail, + flow); if (priv->s_flags & HFI1_R_TID_SW_PSN) { diff = cmp_psn(psn, flow->flow_state.r_next_psn); diff --git a/drivers/infiniband/hw/hfi1/trace_tid.h b/drivers/infiniband/hw/hfi1/trace_tid.h index 4388b59..343fb98 100644 --- a/drivers/infiniband/hw/hfi1/trace_tid.h +++ b/drivers/infiniband/hw/hfi1/trace_tid.h @@ -627,6 +627,12 @@ TP_ARGS(qp, index, flow) ); +DEFINE_EVENT(/* event */ + hfi1_tid_flow_template, hfi1_tid_flow_read_kdeth_eflags, + TP_PROTO(struct rvt_qp *qp, int index, struct tid_rdma_flow *flow), + TP_ARGS(qp, index, flow) +); + DECLARE_EVENT_CLASS(/* tid_node */ hfi1_tid_node_template, TP_PROTO(struct rvt_qp *qp, const char *msg, u32 index, u32 base, @@ -851,6 +857,12 @@ TP_ARGS(qp, psn) ); +DEFINE_EVENT(/* event */ + hfi1_responder_info_template, hfi1_rsp_read_kdeth_eflags, + TP_PROTO(struct rvt_qp *qp, u32 psn), + TP_ARGS(qp, psn) +); + DECLARE_EVENT_CLASS(/* sender_info */ hfi1_sender_info_template, TP_PROTO(struct rvt_qp *qp), @@ -955,6 +967,12 @@ TP_ARGS(qp) ); +DEFINE_EVENT(/* event */ + hfi1_sender_info_template, hfi1_sender_read_kdeth_eflags, + TP_PROTO(struct rvt_qp *qp), + TP_ARGS(qp) +); + DECLARE_EVENT_CLASS(/* tid_read_sender */ hfi1_tid_read_sender_template, TP_PROTO(struct rvt_qp *qp, char newreq), @@ -1015,6 +1033,12 @@ TP_ARGS(qp, newreq) ); +DEFINE_EVENT(/* event */ + hfi1_tid_read_sender_template, hfi1_tid_read_sender_kdeth_eflags, + TP_PROTO(struct rvt_qp *qp, char newreq), + TP_ARGS(qp, newreq) +); + DECLARE_EVENT_CLASS(/* tid_rdma_request */ hfi1_tid_rdma_request_template, TP_PROTO(struct rvt_qp *qp, char newreq, u8 opcode, u32 psn, u32 lpsn, @@ -1216,6 +1240,13 @@ ); DEFINE_EVENT(/* event */ + hfi1_tid_rdma_request_template, hfi1_tid_req_read_kdeth_eflags, + TP_PROTO(struct rvt_qp *qp, char newreq, u8 opcode, u32 psn, u32 lpsn, + struct tid_rdma_request *req), + TP_ARGS(qp, newreq, opcode, psn, lpsn, req) +); + +DEFINE_EVENT(/* event */ hfi1_tid_rdma_request_template, hfi1_tid_req_make_rc_ack_write, TP_PROTO(struct rvt_qp *qp, char newreq, u8 opcode, u32 psn, u32 lpsn, struct tid_rdma_request *req), @@ -1229,6 +1260,13 @@ TP_ARGS(qp, newreq, opcode, psn, lpsn, req) ); +DEFINE_EVENT(/* event */ + hfi1_tid_rdma_request_template, hfi1_tid_req_update_num_rd_atomic, + TP_PROTO(struct rvt_qp *qp, char newreq, u8 opcode, u32 psn, u32 lpsn, + struct tid_rdma_request *req), + TP_ARGS(qp, newreq, opcode, psn, lpsn, req) +); + DECLARE_EVENT_CLASS(/* rc_rcv_err */ hfi1_rc_rcv_err_template, TP_PROTO(struct rvt_qp *qp, u32 opcode, u32 psn, int diff),