IB/hfi1: Add static trace for TID RDMA READ protocol

This patch makes the following changes to the static trace:
1. Adds the decoding of TID RDMA READ packets in IB header trace;
2. Tracks qpriv->s_flags and iow_flags in qpsleepwakeup trace;
3. Adds a new event to track RC ACK receiving;
4. Adds trace events for various stages of the TID RDMA READ
protocol. These events provide a fine-grained control for monitoring
and debugging the hfi1 driver in the filed.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/rc.c

@@ -121,6 +121,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 	bool last_pkt;
 	u32 delta;
 
+	trace_hfi1_rsp_make_rc_ack(qp, 0);
 	lockdep_assert_held(&qp->s_lock);
 	/* Don't send an ACK if we aren't supposed to. */
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK))
@@ -349,6 +350,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	int delta;
 	struct tid_rdma_flow *flow = NULL;
 
+	trace_hfi1_sender_make_rc_req(qp);
 	lockdep_assert_held(&qp->s_lock);
 	ps->s_txreq = get_txreq(ps->dev, qp);
 	if (!ps->s_txreq)
@@ -596,8 +598,13 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 			break;
 
 		case IB_WR_TID_RDMA_READ:
+			trace_hfi1_tid_read_sender_make_req(qp, newreq);
 			wpriv = wqe->priv;
 			req = wqe_to_tid_req(wqe);
+			trace_hfi1_tid_req_make_req_read(qp, newreq,
+							 wqe->wr.opcode,
+							 wqe->psn, wqe->lpsn,
+							 req);
 			delta = cmp_psn(qp->s_psn, wqe->psn);
 
 			/*
@@ -892,6 +899,8 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		    ++qp->s_cur == qp->s_size)
 			qp->s_cur = 0;
 		qp->s_psn = req->s_next_psn;
+		trace_hfi1_tid_req_make_req_read(qp, 0, wqe->wr.opcode,
+						 wqe->psn, wqe->lpsn, req);
 		break;
 	case TID_OP(READ_REQ):
 		req = wqe_to_tid_req(wqe);
@@ -933,6 +942,8 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		    ++qp->s_cur == qp->s_size)
 			qp->s_cur = 0;
 		qp->s_psn = req->s_next_psn;
+		trace_hfi1_tid_req_make_req_read(qp, 0, wqe->wr.opcode,
+						 wqe->psn, wqe->lpsn, req);
 		break;
 	}
 	qp->s_sending_hpsn = bth2;
@@ -1341,6 +1352,7 @@ static void reset_psn(struct rvt_qp *qp, u32 psn)
 	    (cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) <= 0))
 		qp->s_flags |= RVT_S_WAIT_PSN;
 	qp->s_flags &= ~HFI1_S_AHG_VALID;
+	trace_hfi1_sender_reset_psn(qp);
 }
 
 /*
@@ -1355,6 +1367,7 @@ void hfi1_restart_rc(struct rvt_qp *qp, u32 psn, int wait)
 
 	lockdep_assert_held(&qp->r_lock);
 	lockdep_assert_held(&qp->s_lock);
+	trace_hfi1_sender_restart_rc(qp);
 	if (qp->s_retry == 0) {
 		if (qp->s_mig_state == IB_MIG_ARMED) {
 			hfi1_migrate_qp(qp);
@@ -1558,6 +1571,7 @@ struct rvt_swqe *do_rc_completion(struct rvt_qp *qp,
 	 * completion if the SWQE is being resent until the send
 	 * is finished.
 	 */
+	trace_hfi1_rc_completion(qp, wqe->lpsn);
 	if (cmp_psn(wqe->lpsn, qp->s_sending_psn) < 0 ||
 	    cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) > 0) {
 		u32 s_last;
@@ -1742,6 +1756,8 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 			break;
 	}
 
+	trace_hfi1_rc_ack_do(qp, aeth, psn, wqe);
+	trace_hfi1_sender_do_rc_ack(qp);
 	switch (aeth >> IB_AETH_NAK_SHIFT) {
 	case 0:         /* ACK */
 		this_cpu_inc(*ibp->rvp.rc_acks);

drivers/infiniband/hw/hfi1/tid_rdma.c

@@ -1688,6 +1688,7 @@ u32 hfi1_build_tid_rdma_read_packet(struct rvt_swqe *wqe,
 
 	/* This is the IB psn used to send the request */
 	*bth2 = mask_psn(flow->flow_state.ib_spsn + flow->pkt);
+	trace_hfi1_tid_flow_build_read_pkt(qp, req->flow_idx, flow);
 
 	/* TID Entries for TID RDMA READ payload */
 	req_addr = &flow->tid_entry[flow->tid_idx];
@@ -1768,6 +1769,8 @@ u32 hfi1_build_tid_rdma_read_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 	bool retry = true;
 	u32 npkts = rvt_div_round_up_mtu(qp, *len);
 
+	trace_hfi1_tid_req_build_read_req(qp, 0, wqe->wr.opcode, wqe->psn,
+					  wqe->lpsn, req);
 	/*
 	 * Check sync conditions. Make sure that there are no pending
 	 * segments before freeing the flow.
@@ -1883,6 +1886,8 @@ static int tid_rdma_rcv_read_request(struct rvt_qp *qp,
 	 */
 	flow->npkts = rvt_div_round_up_mtu(qp, len);
 	for (i = 0; i < flow->tidcnt; i++) {
+		trace_hfi1_tid_entry_rcv_read_req(qp, i,
+						  flow->tid_entry[i]);
 		tlen = EXP_TID_GET(flow->tid_entry[i], LEN);
 		if (!tlen)
 			return 1;
@@ -1917,6 +1922,7 @@ static int tid_rdma_rcv_read_request(struct rvt_qp *qp,
 	flow->flow_state.ib_spsn = psn;
 	flow->flow_state.ib_lpsn = flow->flow_state.ib_spsn + flow->npkts - 1;
 
+	trace_hfi1_tid_flow_rcv_read_req(qp, req->setup_head, flow);
 	/* Set the initial flow index to the current flow. */
 	req->flow_idx = req->setup_head;
 
@@ -1942,6 +1948,8 @@ static int tid_rdma_rcv_read_request(struct rvt_qp *qp,
 	req->total_segs = 1;
 	req->r_flow_psn = e->psn;
 
+	trace_hfi1_tid_req_rcv_read_req(qp, 0, e->opcode, e->psn, e->lpsn,
+					req);
 	return 0;
 }
 
@@ -1957,6 +1965,8 @@ static int tid_rdma_rcv_error(struct hfi1_packet *packet,
 	u8 prev;
 	bool old_req;
 
+	trace_hfi1_rsp_tid_rcv_error(qp, psn);
+	trace_hfi1_tid_rdma_rcv_err(qp, 0, psn, diff);
 	if (diff > 0) {
 		/* sequence error */
 		if (!qp->r_nak_state) {
@@ -1977,7 +1987,7 @@ static int tid_rdma_rcv_error(struct hfi1_packet *packet,
 
 	req = ack_to_tid_req(e);
 	req->r_flow_psn = psn;
-
+	trace_hfi1_tid_req_rcv_err(qp, 0, e->opcode, e->psn, e->lpsn, req);
 	if (e->opcode == TID_OP(READ_REQ)) {
 		struct ib_reth *reth;
 		u32 offset;
@@ -2088,6 +2098,7 @@ void hfi1_rc_rcv_tid_rdma_read_req(struct hfi1_packet *packet)
 
 	is_fecn = process_ecn(qp, packet);
 	psn = mask_psn(be32_to_cpu(ohdr->bth[2]));
+	trace_hfi1_rsp_rcv_tid_read_req(qp, psn);
 
 	if (qp->state == IB_QPS_RTR && !(qp->r_flags & RVT_R_COMM_EST))
 		rvt_comm_est(qp);
@@ -2199,6 +2210,9 @@ u32 hfi1_build_tid_rdma_read_resp(struct rvt_qp *qp, struct rvt_ack_entry *e,
 	next_offset = flow->tid_offset + *len;
 	last_pkt = (flow->sent >= flow->length);
 
+	trace_hfi1_tid_entry_build_read_resp(qp, flow->tid_idx, tidentry);
+	trace_hfi1_tid_flow_build_read_resp(qp, req->clear_tail, flow);
+
 	rcu_read_lock();
 	remote = rcu_dereference(qpriv->tid_rdma.remote);
 	if (!remote) {
@@ -2293,6 +2307,7 @@ void hfi1_rc_rcv_tid_rdma_read_resp(struct hfi1_packet *packet)
 	unsigned long flags;
 	u32 kpsn, ipsn;
 
+	trace_hfi1_sender_rcv_tid_read_resp(qp);
 	is_fecn = process_ecn(qp, packet);
 	kpsn = mask_psn(be32_to_cpu(ohdr->bth[2]));
 	aeth = be32_to_cpu(ohdr->u.tid_rdma.r_rsp.aeth);
@@ -2322,6 +2337,12 @@ void hfi1_rc_rcv_tid_rdma_read_resp(struct hfi1_packet *packet)
 		hfi1_schedule_send(qp);
 	}
 
+	trace_hfi1_ack(qp, ipsn);
+	trace_hfi1_tid_req_rcv_read_resp(qp, 0, req->e.swqe->wr.opcode,
+					 req->e.swqe->psn, req->e.swqe->lpsn,
+					 req);
+	trace_hfi1_tid_flow_rcv_read_resp(qp, req->clear_tail, flow);
+
 	/* Release the tid resources */
 	hfi1_kern_exp_rcv_clear(req);
 
@@ -2671,6 +2692,8 @@ bool hfi1_handle_kdeth_eflags(struct hfi1_ctxtdata *rcd,
 	unsigned long flags;
 	bool ret = true;
 
+	trace_hfi1_msg_handle_kdeth_eflags(NULL, "Kdeth error: rhf ",
+					   packet->rhf);
 	if (packet->rhf & (RHF_VCRC_ERR | RHF_ICRC_ERR))
 		return ret;
 
@@ -2754,12 +2777,20 @@ void hfi1_tid_rdma_restart_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 	if (wqe->wr.opcode == IB_WR_TID_RDMA_READ) {
 		*bth2 = mask_psn(qp->s_psn);
 		flow = find_flow_ib(req, *bth2, &fidx);
-		if (!flow)
+		if (!flow) {
+			trace_hfi1_msg_tid_restart_req(/* msg */
+			   qp, "!!!!!! Could not find flow to restart: bth2 ",
+			   (u64)*bth2);
+			trace_hfi1_tid_req_restart_req(qp, 0, wqe->wr.opcode,
+						       wqe->psn, wqe->lpsn,
+						       req);
 			return;
+		}
 	} else {
 		return;
 	}
 
+	trace_hfi1_tid_flow_restart_req(qp, fidx, flow);
 	diff = delta_psn(*bth2, flow->flow_state.ib_spsn);
 
 	flow->sent = 0;
@@ -2794,6 +2825,9 @@ void hfi1_tid_rdma_restart_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 	/* Move flow_idx to correct index */
 	req->flow_idx = fidx;
 
+	trace_hfi1_tid_flow_restart_req(qp, fidx, flow);
+	trace_hfi1_tid_req_restart_req(qp, 0, wqe->wr.opcode, wqe->psn,
+				       wqe->lpsn, req);
 	req->state = TID_REQUEST_ACTIVE;
 }
 
@@ -2868,14 +2902,17 @@ bool hfi1_tid_rdma_wqe_interlock(struct rvt_qp *qp, struct rvt_swqe *wqe)
 }
 
 /* Does @sge meet the alignment requirements for tid rdma? */
-static inline bool hfi1_check_sge_align(struct rvt_sge *sge, int num_sge)
+static inline bool hfi1_check_sge_align(struct rvt_qp *qp,
+					struct rvt_sge *sge, int num_sge)
 {
 	int i;
 
-	for (i = 0; i < num_sge; i++, sge++)
+	for (i = 0; i < num_sge; i++, sge++) {
+		trace_hfi1_sge_check_align(qp, i, sge);
 		if ((u64)sge->vaddr & ~PAGE_MASK ||
 		    sge->sge_length & ~PAGE_MASK)
 			return false;
+	}
 	return true;
 }
 
@@ -2904,7 +2941,8 @@ void setup_tid_rdma_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe)
 		goto exit;
 
 	if (wqe->wr.opcode == IB_WR_RDMA_READ) {
-		if (hfi1_check_sge_align(&wqe->sg_list[0], wqe->wr.num_sge)) {
+		if (hfi1_check_sge_align(qp, &wqe->sg_list[0],
+					 wqe->wr.num_sge)) {
 			new_opcode = IB_WR_TID_RDMA_READ;
 			do_tid_rdma = true;
 		}
@@ -2930,6 +2968,9 @@ void setup_tid_rdma_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe)
 		priv->tid_req.comp_seg = 0;
 		priv->tid_req.ack_seg = 0;
 		priv->tid_req.state = TID_REQUEST_INACTIVE;
+		trace_hfi1_tid_req_setup_tid_wqe(qp, 1, wqe->wr.opcode,
+						 wqe->psn, wqe->lpsn,
+						 &priv->tid_req);
 	}
 exit:
 	rcu_read_unlock();

drivers/infiniband/hw/hfi1/trace.c

@@ -129,6 +129,10 @@ const char *hfi1_trace_get_packet_l2_str(u8 l2)
 #define IETH_PRN "ieth rkey:0x%.8x"
 #define ATOMICACKETH_PRN "origdata:%llx"
 #define ATOMICETH_PRN "vaddr:0x%llx rkey:0x%.8x sdata:%llx cdata:%llx"
+#define TID_RDMA_KDETH "kdeth0 0x%x kdeth1 0x%x"
+#define TID_RDMA_KDETH_DATA "kdeth0 0x%x: kver %u sh %u intr %u tidctrl %u tid %x offset %x kdeth1 0x%x: jkey %x"
+#define TID_READ_REQ_PRN "tid_flow_psn 0x%x tid_flow_qp 0x%x verbs_qp 0x%x"
+#define TID_READ_RSP_PRN "verbs_qp 0x%x"
 
 #define OP(transport, op) IB_OPCODE_## transport ## _ ## op
 
@@ -323,6 +327,38 @@ const char *parse_everbs_hdrs(
 				 parse_syndrome(be32_to_cpu(eh->aeth) >> 24),
 				 be32_to_cpu(eh->aeth) & IB_MSN_MASK);
 		break;
+	case OP(TID_RDMA, READ_REQ):
+		trace_seq_printf(p, TID_RDMA_KDETH " " RETH_PRN " "
+				 TID_READ_REQ_PRN,
+				 le32_to_cpu(eh->tid_rdma.r_req.kdeth0),
+				 le32_to_cpu(eh->tid_rdma.r_req.kdeth1),
+				 ib_u64_get(&eh->tid_rdma.r_req.reth.vaddr),
+				 be32_to_cpu(eh->tid_rdma.r_req.reth.rkey),
+				 be32_to_cpu(eh->tid_rdma.r_req.reth.length),
+				 be32_to_cpu(eh->tid_rdma.r_req.tid_flow_psn),
+				 be32_to_cpu(eh->tid_rdma.r_req.tid_flow_qp),
+				 be32_to_cpu(eh->tid_rdma.r_req.verbs_qp));
+		break;
+	case OP(TID_RDMA, READ_RESP):
+		trace_seq_printf(p, TID_RDMA_KDETH_DATA " " AETH_PRN " "
+				 TID_READ_RSP_PRN,
+				 le32_to_cpu(eh->tid_rdma.r_rsp.kdeth0),
+				 KDETH_GET(eh->tid_rdma.r_rsp.kdeth0, KVER),
+				 KDETH_GET(eh->tid_rdma.r_rsp.kdeth0, SH),
+				 KDETH_GET(eh->tid_rdma.r_rsp.kdeth0, INTR),
+				 KDETH_GET(eh->tid_rdma.r_rsp.kdeth0, TIDCTRL),
+				 KDETH_GET(eh->tid_rdma.r_rsp.kdeth0, TID),
+				 KDETH_GET(eh->tid_rdma.r_rsp.kdeth0, OFFSET),
+				 le32_to_cpu(eh->tid_rdma.r_rsp.kdeth1),
+				 KDETH_GET(eh->tid_rdma.r_rsp.kdeth1, JKEY),
+				 be32_to_cpu(eh->tid_rdma.r_rsp.aeth) >> 24,
+				 parse_syndrome(/* aeth */
+					 be32_to_cpu(eh->tid_rdma.r_rsp.aeth)
+					 >> 24),
+				 (be32_to_cpu(eh->tid_rdma.r_rsp.aeth) &
+				  IB_MSN_MASK),
+				 be32_to_cpu(eh->tid_rdma.r_rsp.verbs_qp));
+		break;
 	/* aeth + atomicacketh */
 	case OP(RC, ATOMIC_ACKNOWLEDGE):
 		trace_seq_printf(p, AETH_PRN " " ATOMICACKETH_PRN,

drivers/infiniband/hw/hfi1/trace_ibhdrs.h

@@ -79,6 +79,8 @@ __print_symbolic(opcode,                                   \
 	ib_opcode_name(RC_ATOMIC_ACKNOWLEDGE),             \
 	ib_opcode_name(RC_COMPARE_SWAP),                   \
 	ib_opcode_name(RC_FETCH_ADD),                      \
+	ib_opcode_name(TID_RDMA_READ_REQ),	           \
+	ib_opcode_name(TID_RDMA_READ_RESP),	           \
 	ib_opcode_name(UC_SEND_FIRST),                     \
 	ib_opcode_name(UC_SEND_MIDDLE),                    \
 	ib_opcode_name(UC_SEND_LAST),                      \

drivers/infiniband/hw/hfi1/trace_rc.h

@@ -109,6 +109,54 @@ DEFINE_EVENT(hfi1_rc_template, hfi1_rcv_error,
 	     TP_ARGS(qp, psn)
 );
 
+DEFINE_EVENT(/* event */
+	hfi1_rc_template, hfi1_rc_completion,
+	TP_PROTO(struct rvt_qp *qp, u32 psn),
+	TP_ARGS(qp, psn)
+);
+
+DECLARE_EVENT_CLASS(/* rc_ack */
+	hfi1_rc_ack_template,
+	TP_PROTO(struct rvt_qp *qp, u32 aeth, u32 psn,
+		 struct rvt_swqe *wqe),
+	TP_ARGS(qp, aeth, psn, wqe),
+	TP_STRUCT__entry(/* entry */
+		DD_DEV_ENTRY(dd_from_ibdev(qp->ibqp.device))
+		__field(u32, qpn)
+		__field(u32, aeth)
+		__field(u32, psn)
+		__field(u8, opcode)
+		__field(u32, spsn)
+		__field(u32, lpsn)
+	),
+	TP_fast_assign(/* assign */
+		DD_DEV_ASSIGN(dd_from_ibdev(qp->ibqp.device))
+		__entry->qpn = qp->ibqp.qp_num;
+		__entry->aeth = aeth;
+		__entry->psn = psn;
+		__entry->opcode = wqe->wr.opcode;
+		__entry->spsn = wqe->psn;
+		__entry->lpsn = wqe->lpsn;
+	),
+	TP_printk(/* print */
+		"[%s] qpn 0x%x aeth 0x%x psn 0x%x opcode 0x%x spsn 0x%x lpsn 0x%x",
+		__get_str(dev),
+		__entry->qpn,
+		__entry->aeth,
+		__entry->psn,
+		__entry->opcode,
+		__entry->spsn,
+		__entry->lpsn
+	)
+);
+
+DEFINE_EVENT(/* do_rc_ack */
+	hfi1_rc_ack_template, hfi1_rc_ack_do,
+	TP_PROTO(struct rvt_qp *qp, u32 aeth, u32 psn,
+		 struct rvt_swqe *wqe),
+	TP_ARGS(qp, aeth, psn, wqe)
+);
+
 #endif /* __HFI1_TRACE_RC_H */
 
 #undef TRACE_INCLUDE_PATH

drivers/infiniband/hw/hfi1/trace_tid.h

@@ -31,11 +31,41 @@ u16 hfi1_trace_get_tid_idx(u32 ent);
 
 #define TID_FLOW_PRN "[%s] qpn 0x%x flow %d: idx %d resp_ib_psn 0x%x " \
 		     "generation 0x%x fpsn 0x%x-%x r_next_psn 0x%x " \
-		     "npagesets %u tnode_cnt %u tidcnt %u length %u"
+		     "ib_psn 0x%x-%x npagesets %u tnode_cnt %u " \
+		     "tidcnt %u tid_idx %u tid_offset %u length %u sent %u"
 
 #define TID_NODE_PRN "[%s] qpn 0x%x  %s idx %u grp base 0x%x map 0x%x " \
 		     "used %u cnt %u"
 
+#define RSP_INFO_PRN "[%s] qpn 0x%x state 0x%x s_state 0x%x psn 0x%x " \
+		     "r_psn 0x%x r_state 0x%x r_flags 0x%x " \
+		     "r_head_ack_queue %u s_tail_ack_queue %u " \
+		     "s_ack_state 0x%x " \
+		     "s_nak_state 0x%x s_flags 0x%x ps_flags 0x%x " \
+		     "iow_flags 0x%lx"
+
+#define SENDER_INFO_PRN "[%s] qpn 0x%x state 0x%x s_cur %u s_tail %u " \
+			"s_head %u s_acked %u s_last %u s_psn 0x%x " \
+			"s_last_psn 0x%x s_flags 0x%x ps_flags 0x%x " \
+			"iow_flags 0x%lx s_state 0x%x s_num_rd %u s_retry %u"
+
+#define TID_READ_SENDER_PRN "[%s] qpn 0x%x newreq %u tid_r_reqs %u " \
+			    "tid_r_comp %u pending_tid_r_segs %u " \
+			    "s_flags 0x%x ps_flags 0x%x iow_flags 0x%lx " \
+			    "hw_flow_index %u generation 0x%x " \
+			    "fpsn 0x%x flow_flags 0x%x"
+
+#define TID_REQ_PRN "[%s] qpn 0x%x newreq %u opcode 0x%x psn 0x%x lpsn 0x%x " \
+		    "cur_seg %u comp_seg %u ack_seg %u " \
+		    "total_segs %u setup_head %u clear_tail %u flow_idx %u " \
+		    "state %u r_flow_psn 0x%x " \
+		    "s_next_psn 0x%x"
+
+#define RCV_ERR_PRN "[%s] qpn 0x%x s_flags 0x%x state 0x%x " \
+		    "s_tail_ack_queue %u " \
+		    "r_head_ack_queue %u opcode 0x%x psn 0x%x r_psn 0x%x " \
+		    " diff %d"
+
 DECLARE_EVENT_CLASS(/* class */
 	hfi1_exp_tid_reg_unreg,
 	TP_PROTO(unsigned int ctxt, u16 subctxt, u32 rarr, u32 npages,
@@ -340,6 +370,18 @@ DEFINE_EVENT(/* event */
 	TP_ARGS(qp, msg, more)
 );
 
+DEFINE_EVENT(/* event */
+	hfi1_msg_template, hfi1_msg_tid_restart_req,
+	TP_PROTO(struct rvt_qp *qp, const char *msg, u64 more),
+	TP_ARGS(qp, msg, more)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_msg_template, hfi1_msg_handle_kdeth_eflags,
+	TP_PROTO(struct rvt_qp *qp, const char *msg, u64 more),
+	TP_ARGS(qp, msg, more)
+);
+
 DECLARE_EVENT_CLASS(/* tid_flow_page */
 	hfi1_tid_flow_page_template,
 	TP_PROTO(struct rvt_qp *qp, struct tid_rdma_flow *flow, u32 index,
@@ -429,10 +471,15 @@ DECLARE_EVENT_CLASS(/* tid_fow */
 		__field(u32, fspsn)
 		__field(u32, flpsn)
 		__field(u32, r_next_psn)
+		__field(u32, ib_spsn)
+		__field(u32, ib_lpsn)
 		__field(u32, npagesets)
 		__field(u32, tnode_cnt)
 		__field(u32, tidcnt)
+		__field(u32, tid_idx)
+		__field(u32, tid_offset)
 		__field(u32, length)
+		__field(u32, sent)
 	),
 	TP_fast_assign(/* assign */
 		DD_DEV_ASSIGN(dd_from_ibdev(qp->ibqp.device));
@@ -446,10 +493,15 @@ DECLARE_EVENT_CLASS(/* tid_fow */
 		__entry->flpsn = full_flow_psn(flow,
 					       flow->flow_state.lpsn);
 		__entry->r_next_psn = flow->flow_state.r_next_psn;
+		__entry->ib_spsn = flow->flow_state.ib_spsn;
+		__entry->ib_lpsn = flow->flow_state.ib_lpsn;
 		__entry->npagesets = flow->npagesets;
 		__entry->tnode_cnt = flow->tnode_cnt;
 		__entry->tidcnt = flow->tidcnt;
+		__entry->tid_idx = flow->tid_idx;
+		__entry->tid_offset =  flow->tid_offset;
 		__entry->length = flow->length;
+		__entry->sent = flow->sent;
 	),
 	TP_printk(/* print */
 		TID_FLOW_PRN,
@@ -462,10 +514,15 @@ DECLARE_EVENT_CLASS(/* tid_fow */
 		__entry->fspsn,
 		__entry->flpsn,
 		__entry->r_next_psn,
+		__entry->ib_spsn,
+		__entry->ib_lpsn,
 		__entry->npagesets,
 		__entry->tnode_cnt,
 		__entry->tidcnt,
-		__entry->length
+		__entry->tid_idx,
+		__entry->tid_offset,
+		__entry->length,
+		__entry->sent
 	)
 );
 
@@ -475,6 +532,36 @@ DEFINE_EVENT(/* event */
 	TP_ARGS(qp, index, flow)
 );
 
+DEFINE_EVENT(/* event */
+	hfi1_tid_flow_template, hfi1_tid_flow_build_read_pkt,
+	TP_PROTO(struct rvt_qp *qp, int index, struct tid_rdma_flow *flow),
+	TP_ARGS(qp, index, flow)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_tid_flow_template, hfi1_tid_flow_build_read_resp,
+	TP_PROTO(struct rvt_qp *qp, int index, struct tid_rdma_flow *flow),
+	TP_ARGS(qp, index, flow)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_tid_flow_template, hfi1_tid_flow_rcv_read_req,
+	TP_PROTO(struct rvt_qp *qp, int index, struct tid_rdma_flow *flow),
+	TP_ARGS(qp, index, flow)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_tid_flow_template, hfi1_tid_flow_rcv_read_resp,
+	TP_PROTO(struct rvt_qp *qp, int index, struct tid_rdma_flow *flow),
+	TP_ARGS(qp, index, flow)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_tid_flow_template, hfi1_tid_flow_restart_req,
+	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,
@@ -557,6 +644,443 @@ DEFINE_EVENT(/* event */
 	TP_ARGS(qp, index, entry)
 );
 
+DEFINE_EVENT(/* event */
+	hfi1_tid_entry_template, hfi1_tid_entry_build_read_resp,
+	TP_PROTO(struct rvt_qp *qp, int index, u32 ent),
+	TP_ARGS(qp, index, ent)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_tid_entry_template, hfi1_tid_entry_rcv_read_req,
+	TP_PROTO(struct rvt_qp *qp, int index, u32 ent),
+	TP_ARGS(qp, index, ent)
+);
+
+DECLARE_EVENT_CLASS(/* rsp_info */
+	hfi1_responder_info_template,
+	TP_PROTO(struct rvt_qp *qp, u32 psn),
+	TP_ARGS(qp, psn),
+	TP_STRUCT__entry(/* entry */
+		DD_DEV_ENTRY(dd_from_ibdev(qp->ibqp.device))
+		__field(u32, qpn)
+		__field(u8, state)
+		__field(u8, s_state)
+		__field(u32, psn)
+		__field(u32, r_psn)
+		__field(u8, r_state)
+		__field(u8, r_flags)
+		__field(u8, r_head_ack_queue)
+		__field(u8, s_tail_ack_queue)
+		__field(u8, s_ack_state)
+		__field(u8, s_nak_state)
+		__field(u8, r_nak_state)
+		__field(u32, s_flags)
+		__field(u32, ps_flags)
+		__field(unsigned long, iow_flags)
+	),
+	TP_fast_assign(/* assign */
+		struct hfi1_qp_priv *priv = qp->priv;
+
+		DD_DEV_ASSIGN(dd_from_ibdev(qp->ibqp.device));
+		__entry->qpn = qp->ibqp.qp_num;
+		__entry->state = qp->state;
+		__entry->s_state = qp->s_state;
+		__entry->psn = psn;
+		__entry->r_psn = qp->r_psn;
+		__entry->r_state = qp->r_state;
+		__entry->r_flags = qp->r_flags;
+		__entry->r_head_ack_queue = qp->r_head_ack_queue;
+		__entry->s_tail_ack_queue = qp->s_tail_ack_queue;
+		__entry->s_ack_state = qp->s_ack_state;
+		__entry->s_nak_state = qp->s_nak_state;
+		__entry->s_flags = qp->s_flags;
+		__entry->ps_flags = priv->s_flags;
+		__entry->iow_flags = priv->s_iowait.flags;
+	),
+	TP_printk(/* print */
+		RSP_INFO_PRN,
+		__get_str(dev),
+		__entry->qpn,
+		__entry->state,
+		__entry->s_state,
+		__entry->psn,
+		__entry->r_psn,
+		__entry->r_state,
+		__entry->r_flags,
+		__entry->r_head_ack_queue,
+		__entry->s_tail_ack_queue,
+		__entry->s_ack_state,
+		__entry->s_nak_state,
+		__entry->s_flags,
+		__entry->ps_flags,
+		__entry->iow_flags
+	)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_responder_info_template, hfi1_rsp_make_rc_ack,
+	TP_PROTO(struct rvt_qp *qp, u32 psn),
+	TP_ARGS(qp, psn)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_responder_info_template, hfi1_rsp_rcv_tid_read_req,
+	TP_PROTO(struct rvt_qp *qp, u32 psn),
+	TP_ARGS(qp, psn)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_responder_info_template, hfi1_rsp_tid_rcv_error,
+	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),
+	TP_ARGS(qp),
+	TP_STRUCT__entry(/* entry */
+		DD_DEV_ENTRY(dd_from_ibdev(qp->ibqp.device))
+		__field(u32, qpn)
+		__field(u8, state)
+		__field(u32, s_cur)
+		__field(u32, s_tail)
+		__field(u32, s_head)
+		__field(u32, s_acked)
+		__field(u32, s_last)
+		__field(u32, s_psn)
+		__field(u32, s_last_psn)
+		__field(u32, s_flags)
+		__field(u32, ps_flags)
+		__field(unsigned long, iow_flags)
+		__field(u8, s_state)
+		__field(u8, s_num_rd)
+		__field(u8, s_retry)
+	),
+	TP_fast_assign(/* assign */
+		DD_DEV_ASSIGN(dd_from_ibdev(qp->ibqp.device))
+		__entry->qpn = qp->ibqp.qp_num;
+		__entry->state = qp->state;
+		__entry->s_cur = qp->s_cur;
+		__entry->s_tail = qp->s_tail;
+		__entry->s_head = qp->s_head;
+		__entry->s_acked = qp->s_acked;
+		__entry->s_last = qp->s_last;
+		__entry->s_psn = qp->s_psn;
+		__entry->s_last_psn = qp->s_last_psn;
+		__entry->s_flags = qp->s_flags;
+		__entry->ps_flags = ((struct hfi1_qp_priv *)qp->priv)->s_flags;
+		__entry->iow_flags =
+			((struct hfi1_qp_priv *)qp->priv)->s_iowait.flags;
+		__entry->s_state = qp->s_state;
+		__entry->s_num_rd = qp->s_num_rd_atomic;
+		__entry->s_retry = qp->s_retry;
+	),
+	TP_printk(/* print */
+		SENDER_INFO_PRN,
+		__get_str(dev),
+		__entry->qpn,
+		__entry->state,
+		__entry->s_cur,
+		__entry->s_tail,
+		__entry->s_head,
+		__entry->s_acked,
+		__entry->s_last,
+		__entry->s_psn,
+		__entry->s_last_psn,
+		__entry->s_flags,
+		__entry->ps_flags,
+		__entry->iow_flags,
+		__entry->s_state,
+		__entry->s_num_rd,
+		__entry->s_retry
+	)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_sender_info_template, hfi1_sender_make_rc_req,
+	TP_PROTO(struct rvt_qp *qp),
+	TP_ARGS(qp)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_sender_info_template, hfi1_sender_reset_psn,
+	TP_PROTO(struct rvt_qp *qp),
+	TP_ARGS(qp)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_sender_info_template, hfi1_sender_restart_rc,
+	TP_PROTO(struct rvt_qp *qp),
+	TP_ARGS(qp)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_sender_info_template, hfi1_sender_do_rc_ack,
+	TP_PROTO(struct rvt_qp *qp),
+	TP_ARGS(qp)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_sender_info_template, hfi1_sender_rcv_tid_read_resp,
+	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),
+	TP_ARGS(qp, newreq),
+	TP_STRUCT__entry(/* entry */
+		DD_DEV_ENTRY(dd_from_ibdev(qp->ibqp.device))
+		__field(u32, qpn)
+		__field(char, newreq)
+		__field(u32, tid_r_reqs)
+		__field(u32, tid_r_comp)
+		__field(u32, pending_tid_r_segs)
+		__field(u32, s_flags)
+		__field(u32, ps_flags)
+		__field(unsigned long, iow_flags)
+		__field(u32, hw_flow_index)
+		__field(u32, generation)
+		__field(u32, fpsn)
+		__field(u32, flow_flags)
+	),
+	TP_fast_assign(/* assign */
+		struct hfi1_qp_priv *priv = qp->priv;
+
+		DD_DEV_ASSIGN(dd_from_ibdev(qp->ibqp.device));
+		__entry->qpn = qp->ibqp.qp_num;
+		__entry->newreq = newreq;
+		__entry->tid_r_reqs = priv->tid_r_reqs;
+		__entry->tid_r_comp = priv->tid_r_comp;
+		__entry->pending_tid_r_segs = priv->pending_tid_r_segs;
+		__entry->s_flags = qp->s_flags;
+		__entry->ps_flags = priv->s_flags;
+		__entry->iow_flags = priv->s_iowait.flags;
+		__entry->hw_flow_index = priv->flow_state.index;
+		__entry->generation = priv->flow_state.generation;
+		__entry->fpsn = priv->flow_state.psn;
+		__entry->flow_flags = priv->flow_state.flags;
+	),
+	TP_printk(/* print */
+		TID_READ_SENDER_PRN,
+		__get_str(dev),
+		__entry->qpn,
+		__entry->newreq,
+		__entry->tid_r_reqs,
+		__entry->tid_r_comp,
+		__entry->pending_tid_r_segs,
+		__entry->s_flags,
+		__entry->ps_flags,
+		__entry->iow_flags,
+		__entry->hw_flow_index,
+		__entry->generation,
+		__entry->fpsn,
+		__entry->flow_flags
+	)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_tid_read_sender_template, hfi1_tid_read_sender_make_req,
+	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,
+		 struct tid_rdma_request *req),
+	TP_ARGS(qp, newreq, opcode, psn, lpsn, req),
+	TP_STRUCT__entry(/* entry */
+		DD_DEV_ENTRY(dd_from_ibdev(qp->ibqp.device))
+		__field(u32, qpn)
+		__field(char, newreq)
+		__field(u8, opcode)
+		__field(u32, psn)
+		__field(u32, lpsn)
+		__field(u32, cur_seg)
+		__field(u32, comp_seg)
+		__field(u32, ack_seg)
+		__field(u32, total_segs)
+		__field(u16, setup_head)
+		__field(u16, clear_tail)
+		__field(u16, flow_idx)
+		__field(u32, state)
+		__field(u32, r_flow_psn)
+		__field(u32, s_next_psn)
+	),
+	TP_fast_assign(/* assign */
+		DD_DEV_ASSIGN(dd_from_ibdev(qp->ibqp.device));
+		__entry->qpn = qp->ibqp.qp_num;
+		__entry->newreq = newreq;
+		__entry->opcode = opcode;
+		__entry->psn = psn;
+		__entry->lpsn = lpsn;
+		__entry->cur_seg = req->cur_seg;
+		__entry->comp_seg = req->comp_seg;
+		__entry->ack_seg = req->ack_seg;
+		__entry->total_segs = req->total_segs;
+		__entry->setup_head = req->setup_head;
+		__entry->clear_tail = req->clear_tail;
+		__entry->flow_idx = req->flow_idx;
+		__entry->state = req->state;
+		__entry->r_flow_psn = req->r_flow_psn;
+		__entry->s_next_psn = req->s_next_psn;
+	),
+	TP_printk(/* print */
+		TID_REQ_PRN,
+		__get_str(dev),
+		__entry->qpn,
+		__entry->newreq,
+		__entry->opcode,
+		__entry->psn,
+		__entry->lpsn,
+		__entry->cur_seg,
+		__entry->comp_seg,
+		__entry->ack_seg,
+		__entry->total_segs,
+		__entry->setup_head,
+		__entry->clear_tail,
+		__entry->flow_idx,
+		__entry->state,
+		__entry->r_flow_psn,
+		__entry->s_next_psn
+	)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_tid_rdma_request_template, hfi1_tid_req_make_req_read,
+	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_build_read_req,
+	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_rcv_read_req,
+	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_rcv_read_resp,
+	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_rcv_err,
+	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_restart_req,
+	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_setup_tid_wqe,
+	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),
+	TP_ARGS(qp, opcode, psn, diff),
+	TP_STRUCT__entry(/* entry */
+		DD_DEV_ENTRY(dd_from_ibdev(qp->ibqp.device))
+		__field(u32, qpn)
+		__field(u32, s_flags)
+		__field(u8, state)
+		__field(u8, s_tail_ack_queue)
+		__field(u8, r_head_ack_queue)
+		__field(u32, opcode)
+		__field(u32, psn)
+		__field(u32, r_psn)
+		__field(int, diff)
+	),
+	TP_fast_assign(/* assign */
+		DD_DEV_ASSIGN(dd_from_ibdev(qp->ibqp.device))
+		__entry->qpn = qp->ibqp.qp_num;
+		__entry->s_flags = qp->s_flags;
+		__entry->state = qp->state;
+		__entry->s_tail_ack_queue = qp->s_tail_ack_queue;
+		__entry->r_head_ack_queue = qp->r_head_ack_queue;
+		__entry->opcode = opcode;
+		__entry->psn = psn;
+		__entry->r_psn = qp->r_psn;
+		__entry->diff = diff;
+	),
+	TP_printk(/* print */
+		RCV_ERR_PRN,
+		__get_str(dev),
+		__entry->qpn,
+		__entry->s_flags,
+		__entry->state,
+		__entry->s_tail_ack_queue,
+		__entry->r_head_ack_queue,
+		__entry->opcode,
+		__entry->psn,
+		__entry->r_psn,
+		__entry->diff
+	)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_rc_rcv_err_template, hfi1_tid_rdma_rcv_err,
+	TP_PROTO(struct rvt_qp *qp, u32 opcode, u32 psn, int diff),
+	TP_ARGS(qp, opcode, psn, diff)
+);
+
+DECLARE_EVENT_CLASS(/* sge  */
+	hfi1_sge_template,
+	TP_PROTO(struct rvt_qp *qp, int index, struct rvt_sge *sge),
+	TP_ARGS(qp, index, sge),
+	TP_STRUCT__entry(/* entry */
+		DD_DEV_ENTRY(dd_from_ibdev(qp->ibqp.device))
+		__field(u32, qpn)
+		__field(int, index)
+		__field(u64, vaddr)
+		__field(u32, sge_length)
+	),
+	TP_fast_assign(/* assign */
+		DD_DEV_ASSIGN(dd_from_ibdev(qp->ibqp.device));
+		__entry->qpn = qp->ibqp.qp_num;
+		__entry->index = index;
+		__entry->vaddr = (u64)sge->vaddr;
+		__entry->sge_length = sge->sge_length;
+	),
+	TP_printk(/* print */
+		"[%s] qpn 0x%x sge %d: vaddr 0x%llx sge_length %u",
+		__get_str(dev),
+		__entry->qpn,
+		__entry->index,
+		__entry->vaddr,
+		__entry->sge_length
+	)
+);
+
+DEFINE_EVENT(/* event */
+	hfi1_sge_template, hfi1_sge_check_align,
+	TP_PROTO(struct rvt_qp *qp, int index, struct rvt_sge *sge),
+	TP_ARGS(qp, index, sge)
+);
+
 #endif /* __HFI1_TRACE_TID_H */
 
 #undef TRACE_INCLUDE_PATH

drivers/infiniband/hw/hfi1/trace_tx.h

@@ -114,19 +114,27 @@ DECLARE_EVENT_CLASS(hfi1_qpsleepwakeup_template,
 		    __field(u32, qpn)
 		    __field(u32, flags)
 		    __field(u32, s_flags)
+		    __field(u32, ps_flags)
+		    __field(unsigned long, iow_flags)
 		    ),
 		    TP_fast_assign(
 		    DD_DEV_ASSIGN(dd_from_ibdev(qp->ibqp.device))
 		    __entry->flags = flags;
 		    __entry->qpn = qp->ibqp.qp_num;
 		    __entry->s_flags = qp->s_flags;
+		    __entry->ps_flags =
+			((struct hfi1_qp_priv *)qp->priv)->s_flags;
+		    __entry->iow_flags =
+			((struct hfi1_qp_priv *)qp->priv)->s_iowait.flags;
 		    ),
 		    TP_printk(
-		    "[%s] qpn 0x%x flags 0x%x s_flags 0x%x",
+		    "[%s] qpn 0x%x flags 0x%x s_flags 0x%x ps_flags 0x%x iow_flags 0x%lx",
 		    __get_str(dev),
 		    __entry->qpn,
 		    __entry->flags,
-		    __entry->s_flags
+		    __entry->s_flags,
+		    __entry->ps_flags,
+		    __entry->iow_flags
 		    )
 );