Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull more rdma updates from Doug Ledford:
 "Items of note:

   - two patches fix a regression in the 4.15 kernel. The 4.14 kernel
     worked fine with NVMe over Fabrics and mlx5 adapters. That broke in
     4.15. The fix is here.

   - one of the patches (the endian notation patch from Lijun) looks
     like a lot of lines of change, but it's mostly mechanical in
     nature. It amounts to the biggest chunk of change in it (it's about
     2/3rds of the overall pull request).

  Summary:

   - Clean up some function signatures in rxe for clarity

   - Tidy the RDMA netlink header to remove unimplemented constants

   - bnxt_re driver fixes, one is a regression this window.

   - Minor hns driver fixes

   - Various fixes from Dan Carpenter and his tool

   - Fix IRQ cleanup race in HFI1

   - HF1 performance optimizations and a fix to report counters in the right units

   - Fix for an IPoIB startup sequence race with the external manager

   - Oops fix for the new kabi path

   - Endian cleanups for hns

   - Fix for mlx5 related to the new automatic affinity support"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (38 commits)
  net/mlx5: increase async EQ to avoid EQ overrun
  mlx5: fix mlx5_get_vector_affinity to start from completion vector 0
  RDMA/hns: Fix the endian problem for hns
  IB/uverbs: Use the standard kConfig format for experimental
  IB: Update references to libibverbs
  IB/hfi1: Add 16B rcvhdr trace support
  IB/hfi1: Convert kzalloc_node and kcalloc to use kcalloc_node
  IB/core: Avoid a potential OOPs for an unused optional parameter
  IB/core: Map iWarp AH type to undefined in rdma_ah_find_type
  IB/ipoib: Fix for potential no-carrier state
  IB/hfi1: Show fault stats in both TX and RX directions
  IB/hfi1: Remove blind constants from 16B update
  IB/hfi1: Convert PortXmitWait/PortVLXmitWait counters to flit times
  IB/hfi1: Do not override given pcie_pset value
  IB/hfi1: Optimize process_receive_ib()
  IB/hfi1: Remove unnecessary fecn and becn fields
  IB/hfi1: Look up ibport using a pointer in receive path
  IB/hfi1: Optimize packet type comparison using 9B and bypass code paths
  IB/hfi1: Compute BTH only for RDMA_WRITE_LAST/SEND_LAST packet
  IB/hfi1: Remove dependence on qp->s_hdrwords
  ...

drivers/infiniband/hw/hfi1/chip.c

@@ -1083,6 +1083,7 @@ static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp,
 static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd);
 static int wait_link_transfer_active(struct hfi1_devdata *dd, int wait_ms);
 static void clear_rsm_rule(struct hfi1_devdata *dd, u8 rule_index);
+static void update_xmit_counters(struct hfi1_pportdata *ppd, u16 link_width);
 
 /*
  * Error interrupt table entry.  This is used as input to the interrupt
@@ -6905,6 +6906,32 @@ void handle_freeze(struct work_struct *work)
 	/* no longer frozen */
 }
 
+/**
+ * update_xmit_counters - update PortXmitWait/PortVlXmitWait
+ * counters.
+ * @ppd: info of physical Hfi port
+ * @link_width: new link width after link up or downgrade
+ *
+ * Update the PortXmitWait and PortVlXmitWait counters after
+ * a link up or downgrade event to reflect a link width change.
+ */
+static void update_xmit_counters(struct hfi1_pportdata *ppd, u16 link_width)
+{
+	int i;
+	u16 tx_width;
+	u16 link_speed;
+
+	tx_width = tx_link_width(link_width);
+	link_speed = get_link_speed(ppd->link_speed_active);
+
+	/*
+	 * There are C_VL_COUNT number of PortVLXmitWait counters.
+	 * Adding 1 to C_VL_COUNT to include the PortXmitWait counter.
+	 */
+	for (i = 0; i < C_VL_COUNT + 1; i++)
+		get_xmit_wait_counters(ppd, tx_width, link_speed, i);
+}
+
 /*
  * Handle a link up interrupt from the 8051.
  *
@@ -7526,18 +7553,29 @@ void handle_verify_cap(struct work_struct *work)
 	set_link_state(ppd, HLS_GOING_UP);
 }
 
-/*
- * Apply the link width downgrade enabled policy against the current active
- * link widths.
+/**
+ * apply_link_downgrade_policy - Apply the link width downgrade enabled
+ * policy against the current active link widths.
+ * @ppd: info of physical Hfi port
+ * @refresh_widths: True indicates link downgrade event
+ * @return: True indicates a successful link downgrade. False indicates
+ *	    link downgrade event failed and the link will bounce back to
+ *	    default link width.
  *
- * Called when the enabled policy changes or the active link widths change.
+ * Called when the enabled policy changes or the active link widths
+ * change.
+ * Refresh_widths indicates that a link downgrade occurred. The
+ * link_downgraded variable is set by refresh_widths and
+ * determines the success/failure of the policy application.
  */
-void apply_link_downgrade_policy(struct hfi1_pportdata *ppd, int refresh_widths)
+bool apply_link_downgrade_policy(struct hfi1_pportdata *ppd,
+				 bool refresh_widths)
 {
 	int do_bounce = 0;
 	int tries;
 	u16 lwde;
 	u16 tx, rx;
+	bool link_downgraded = refresh_widths;
 
 	/* use the hls lock to avoid a race with actual link up */
 	tries = 0;
@@ -7571,6 +7609,7 @@ retry:
 	    ppd->link_width_downgrade_rx_active == 0) {
 		/* the 8051 reported a dead link as a downgrade */
 		dd_dev_err(ppd->dd, "Link downgrade is really a link down, ignoring\n");
+		link_downgraded = false;
 	} else if (lwde == 0) {
 		/* downgrade is disabled */
 
@@ -7587,6 +7626,7 @@ retry:
 				   ppd->link_width_downgrade_tx_active,
 				   ppd->link_width_downgrade_rx_active);
 			do_bounce = 1;
+			link_downgraded = false;
 		}
 	} else if ((lwde & ppd->link_width_downgrade_tx_active) == 0 ||
 		   (lwde & ppd->link_width_downgrade_rx_active) == 0) {
@@ -7598,6 +7638,7 @@ retry:
 			   lwde, ppd->link_width_downgrade_tx_active,
 			   ppd->link_width_downgrade_rx_active);
 		do_bounce = 1;
+		link_downgraded = false;
 	}
 
 done:
@@ -7609,6 +7650,8 @@ done:
 		set_link_state(ppd, HLS_DN_OFFLINE);
 		start_link(ppd);
 	}
+
+	return link_downgraded;
 }
 
 /*
@@ -7622,7 +7665,8 @@ void handle_link_downgrade(struct work_struct *work)
 							link_downgrade_work);
 
 	dd_dev_info(ppd->dd, "8051: Link width downgrade\n");
-	apply_link_downgrade_policy(ppd, 1);
+	if (apply_link_downgrade_policy(ppd, true))
+		update_xmit_counters(ppd, ppd->link_width_downgrade_tx_active);
 }
 
 static char *dcc_err_string(char *buf, int buf_len, u64 flags)
@@ -8264,8 +8308,8 @@ static irqreturn_t sdma_interrupt(int irq, void *data)
 		/* handle the interrupt(s) */
 		sdma_engine_interrupt(sde, status);
 	} else {
-		dd_dev_err_ratelimited(dd, "SDMA engine %u interrupt, but no status bits set\n",
-				       sde->this_idx);
+		dd_dev_info_ratelimited(dd, "SDMA engine %u interrupt, but no status bits set\n",
+					sde->this_idx);
 	}
 	return IRQ_HANDLED;
 }
@@ -10597,6 +10641,14 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 		add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
 
 		handle_linkup_change(dd, 1);
+
+		/*
+		 * After link up, a new link width will have been set.
+		 * Update the xmit counters with regards to the new
+		 * link width.
+		 */
+		update_xmit_counters(ppd, ppd->link_width_active);
+
 		ppd->host_link_state = HLS_UP_INIT;
 		update_statusp(ppd, IB_PORT_INIT);
 		break;
@@ -12960,7 +13012,14 @@ static void disable_intx(struct pci_dev *pdev)
 	pci_intx(pdev, 0);
 }
 
-static void clean_up_interrupts(struct hfi1_devdata *dd)
+/**
+ * hfi1_clean_up_interrupts() - Free all IRQ resources
+ * @dd: valid device data data structure
+ *
+ * Free the MSI or INTx IRQs and assoicated PCI resources,
+ * if they have been allocated.
+ */
+void hfi1_clean_up_interrupts(struct hfi1_devdata *dd)
 {
 	int i;
 
@@ -13321,7 +13380,7 @@ static int set_up_interrupts(struct hfi1_devdata *dd)
 	return 0;
 
 fail:
-	clean_up_interrupts(dd);
+	hfi1_clean_up_interrupts(dd);
 	return ret;
 }
 
@@ -14748,7 +14807,6 @@ void hfi1_start_cleanup(struct hfi1_devdata *dd)
 	aspm_exit(dd);
 	free_cntrs(dd);
 	free_rcverr(dd);
-	clean_up_interrupts(dd);
 	finish_chip_resources(dd);
 }
 
@@ -15204,7 +15262,7 @@ bail_free_rcverr:
 bail_free_cntrs:
 	free_cntrs(dd);
 bail_clear_intr:
-	clean_up_interrupts(dd);
+	hfi1_clean_up_interrupts(dd);
 bail_cleanup:
 	hfi1_pcie_ddcleanup(dd);
 bail_free:

drivers/infiniband/hw/hfi1/chip.h

@@ -736,8 +736,8 @@ int read_8051_config(struct hfi1_devdata *, u8, u8, u32 *);
 int start_link(struct hfi1_pportdata *ppd);
 int bringup_serdes(struct hfi1_pportdata *ppd);
 void set_intr_state(struct hfi1_devdata *dd, u32 enable);
-void apply_link_downgrade_policy(struct hfi1_pportdata *ppd,
-				 int refresh_widths);
+bool apply_link_downgrade_policy(struct hfi1_pportdata *ppd,
+				 bool refresh_widths);
 void update_usrhead(struct hfi1_ctxtdata *rcd, u32 hd, u32 updegr, u32 egrhd,
 		    u32 intr_adjust, u32 npkts);
 int stop_drain_data_vls(struct hfi1_devdata *dd);

drivers/infiniband/hw/hfi1/debugfs.c

@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015-2017 Intel Corporation.
+ * Copyright(c) 2015-2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -1201,6 +1201,13 @@ static int _fault_stats_seq_show(struct seq_file *s, void *v)
 		}
 		hfi1_rcd_put(rcd);
 	}
+	for_each_possible_cpu(j) {
+		struct hfi1_opcode_stats_perctx *sp =
+			per_cpu_ptr(dd->tx_opstats, j);
+
+		n_packets += sp->stats[i].n_packets;
+		n_bytes += sp->stats[i].n_bytes;
+	}
 	if (!n_packets && !n_bytes)
 		return SEQ_SKIP;
 	if (!ibd->fault_opcode->n_rxfaults[i] &&

drivers/infiniband/hw/hfi1/driver.c

@@ -256,7 +256,12 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 	u32 mlid_base;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct hfi1_devdata *dd = ppd->dd;
-	struct rvt_dev_info *rdi = &dd->verbs_dev.rdi;
+	struct hfi1_ibdev *verbs_dev = &dd->verbs_dev;
+	struct rvt_dev_info *rdi = &verbs_dev->rdi;
+
+	if ((packet->rhf & RHF_DC_ERR) &&
+	    hfi1_dbg_fault_suppress_err(verbs_dev))
+		return;
 
 	if (packet->rhf & (RHF_VCRC_ERR | RHF_ICRC_ERR))
 		return;
@@ -634,9 +639,10 @@ next:
 	}
 }
 
-static void process_rcv_qp_work(struct hfi1_ctxtdata *rcd)
+static void process_rcv_qp_work(struct hfi1_packet *packet)
 {
 	struct rvt_qp *qp, *nqp;
+	struct hfi1_ctxtdata *rcd = packet->rcd;
 
 	/*
 	 * Iterate over all QPs waiting to respond.
@@ -646,7 +652,8 @@ static void process_rcv_qp_work(struct hfi1_ctxtdata *rcd)
 		list_del_init(&qp->rspwait);
 		if (qp->r_flags & RVT_R_RSP_NAK) {
 			qp->r_flags &= ~RVT_R_RSP_NAK;
-			hfi1_send_rc_ack(rcd, qp, 0);
+			packet->qp = qp;
+			hfi1_send_rc_ack(packet, 0);
 		}
 		if (qp->r_flags & RVT_R_RSP_SEND) {
 			unsigned long flags;
@@ -667,7 +674,7 @@ static noinline int max_packet_exceeded(struct hfi1_packet *packet, int thread)
 	if (thread) {
 		if ((packet->numpkt & (MAX_PKT_RECV_THREAD - 1)) == 0)
 			/* allow defered processing */
-			process_rcv_qp_work(packet->rcd);
+			process_rcv_qp_work(packet);
 		cond_resched();
 		return RCV_PKT_OK;
 	} else {
@@ -809,7 +816,7 @@ int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 			last = RCV_PKT_DONE;
 		process_rcv_update(last, &packet);
 	}
-	process_rcv_qp_work(rcd);
+	process_rcv_qp_work(&packet);
 	rcd->head = packet.rhqoff;
 bail:
 	finish_packet(&packet);
@@ -838,7 +845,7 @@ int handle_receive_interrupt_dma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 			last = RCV_PKT_DONE;
 		process_rcv_update(last, &packet);
 	}
-	process_rcv_qp_work(rcd);
+	process_rcv_qp_work(&packet);
 	rcd->head = packet.rhqoff;
 bail:
 	finish_packet(&packet);
@@ -1068,7 +1075,7 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 		process_rcv_update(last, &packet);
 	}
 
-	process_rcv_qp_work(rcd);
+	process_rcv_qp_work(&packet);
 	rcd->head = packet.rhqoff;
 
 bail:
@@ -1438,8 +1445,8 @@ static int hfi1_setup_9B_packet(struct hfi1_packet *packet)
 	packet->sc = hfi1_9B_get_sc5(hdr, packet->rhf);
 	packet->pad = ib_bth_get_pad(packet->ohdr);
 	packet->extra_byte = 0;
-	packet->fecn = ib_bth_get_fecn(packet->ohdr);
-	packet->becn = ib_bth_get_becn(packet->ohdr);
+	packet->pkey = ib_bth_get_pkey(packet->ohdr);
+	packet->migrated = ib_bth_is_migration(packet->ohdr);
 
 	return 0;
 drop:
@@ -1492,8 +1499,10 @@ static int hfi1_setup_bypass_packet(struct hfi1_packet *packet)
 
 	/* Query commonly used fields from packet header */
 	packet->opcode = ib_bth_get_opcode(packet->ohdr);
-	packet->hlen = hdr_len_by_opcode[packet->opcode] + 8 + grh_len;
-	packet->payload = packet->ebuf + packet->hlen - (4 * sizeof(u32));
+	/* hdr_len_by_opcode already has an IB LRH factored in */
+	packet->hlen = hdr_len_by_opcode[packet->opcode] +
+		(LRH_16B_BYTES - LRH_9B_BYTES) + grh_len;
+	packet->payload = packet->ebuf + packet->hlen - LRH_16B_BYTES;
 	packet->slid = hfi1_16B_get_slid(packet->hdr);
 	packet->dlid = hfi1_16B_get_dlid(packet->hdr);
 	if (unlikely(hfi1_is_16B_mcast(packet->dlid)))
@@ -1504,8 +1513,8 @@ static int hfi1_setup_bypass_packet(struct hfi1_packet *packet)
 	packet->sl = ibp->sc_to_sl[packet->sc];
 	packet->pad = hfi1_16B_bth_get_pad(packet->ohdr);
 	packet->extra_byte = SIZE_OF_LT;
-	packet->fecn = hfi1_16B_get_fecn(packet->hdr);
-	packet->becn = hfi1_16B_get_becn(packet->hdr);
+	packet->pkey = hfi1_16B_get_pkey(packet->hdr);
+	packet->migrated = opa_bth_is_migration(packet->ohdr);
 
 	if (hfi1_bypass_ingress_pkt_check(packet))
 		goto drop;
@@ -1550,19 +1559,7 @@ int process_receive_ib(struct hfi1_packet *packet)
 	if (hfi1_setup_9B_packet(packet))
 		return RHF_RCV_CONTINUE;
 
-	trace_hfi1_rcvhdr(packet->rcd->ppd->dd,
-			  packet->rcd->ctxt,
-			  rhf_err_flags(packet->rhf),
-			  RHF_RCV_TYPE_IB,
-			  packet->hlen,
-			  packet->tlen,
-			  packet->updegr,
-			  rhf_egr_index(packet->rhf));
-
-	if (unlikely(
-		 (hfi1_dbg_fault_suppress_err(&packet->rcd->dd->verbs_dev) &&
-		 (packet->rhf & RHF_DC_ERR))))
-		return RHF_RCV_CONTINUE;
+	trace_hfi1_rcvhdr(packet);
 
 	if (unlikely(rhf_err_flags(packet->rhf))) {
 		handle_eflags(packet);
@@ -1598,6 +1595,8 @@ int process_receive_bypass(struct hfi1_packet *packet)
 	if (hfi1_setup_bypass_packet(packet))
 		return RHF_RCV_CONTINUE;
 
+	trace_hfi1_rcvhdr(packet);
+
 	if (unlikely(rhf_err_flags(packet->rhf))) {
 		handle_eflags(packet);
 		return RHF_RCV_CONTINUE;

drivers/infiniband/hw/hfi1/file_ops.c

@@ -196,9 +196,6 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 	if (!atomic_inc_not_zero(&dd->user_refcount))
 		return -ENXIO;
 
-	/* Just take a ref now. Not all opens result in a context assign */
-	kobject_get(&dd->kobj);
-
 	/* The real work is performed later in assign_ctxt() */
 
 	fd = kzalloc(sizeof(*fd), GFP_KERNEL);
@@ -208,6 +205,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 		fd->mm = current->mm;
 		mmgrab(fd->mm);
 		fd->dd = dd;
+		kobject_get(&fd->dd->kobj);
 		fp->private_data = fd;
 	} else {
 		fp->private_data = NULL;

drivers/infiniband/hw/hfi1/hfi.h

@@ -341,6 +341,7 @@ struct hfi1_packet {
 	u32 slid;
 	u16 tlen;
 	s16 etail;
+	u16 pkey;
 	u8 hlen;
 	u8 numpkt;
 	u8 rsize;
@@ -351,8 +352,7 @@ struct hfi1_packet {
 	u8 sc;
 	u8 sl;
 	u8 opcode;
-	bool becn;
-	bool fecn;
+	bool migrated;
 };
 
 /* Packet types */
@@ -858,6 +858,13 @@ struct hfi1_pportdata {
 	struct work_struct linkstate_active_work;
 	/* Does this port need to prescan for FECNs */
 	bool cc_prescan;
+	/*
+	 * Sample sendWaitCnt & sendWaitVlCnt during link transition
+	 * and counter request.
+	 */
+	u64 port_vl_xmit_wait_last[C_VL_COUNT + 1];
+	u16 prev_link_width;
+	u64 vl_xmit_flit_cnt[C_VL_COUNT + 1];
 };
 
 typedef int (*rhf_rcv_function_ptr)(struct hfi1_packet *packet);
@@ -1779,19 +1786,15 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 static inline bool process_ecn(struct rvt_qp *qp, struct hfi1_packet *pkt,
 			       bool do_cnp)
 {
-	struct ib_other_headers *ohdr = pkt->ohdr;
-
-	u32 bth1;
-	bool becn = false;
-	bool fecn = false;
+	bool becn;
+	bool fecn;
 
 	if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
 		fecn = hfi1_16B_get_fecn(pkt->hdr);
 		becn = hfi1_16B_get_becn(pkt->hdr);
 	} else {
-		bth1 = be32_to_cpu(ohdr->bth[1]);
-		fecn = bth1 & IB_FECN_SMASK;
-		becn = bth1 & IB_BECN_SMASK;
+		fecn = ib_bth_get_fecn(pkt->ohdr);
+		becn = ib_bth_get_becn(pkt->ohdr);
 	}
 	if (unlikely(fecn || becn)) {
 		hfi1_process_ecn_slowpath(qp, pkt, do_cnp);
@@ -1957,6 +1960,7 @@ void hfi1_verbs_unregister_sysfs(struct hfi1_devdata *dd);
 int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len);
 
 int hfi1_pcie_init(struct pci_dev *pdev, const struct pci_device_id *ent);
+void hfi1_clean_up_interrupts(struct hfi1_devdata *dd);
 void hfi1_pcie_cleanup(struct pci_dev *pdev);
 int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev);
 void hfi1_pcie_ddcleanup(struct hfi1_devdata *);
@@ -2416,7 +2420,7 @@ static inline void hfi1_make_ib_hdr(struct ib_header *hdr,
 static inline void hfi1_make_16b_hdr(struct hfi1_16b_header *hdr,
 				     u32 slid, u32 dlid,
 				     u16 len, u16 pkey,
-				     u8 becn, u8 fecn, u8 l4,
+				     bool becn, bool fecn, u8 l4,
 				     u8 sc)
 {
 	u32 lrh0 = 0;

drivers/infiniband/hw/hfi1/init.c

@@ -172,7 +172,7 @@ int hfi1_create_kctxts(struct hfi1_devdata *dd)
 	u16 i;
 	int ret;
 
-	dd->rcd = kzalloc_node(dd->num_rcv_contexts * sizeof(*dd->rcd),
+	dd->rcd = kcalloc_node(dd->num_rcv_contexts, sizeof(*dd->rcd),
 			       GFP_KERNEL, dd->node);
 	if (!dd->rcd)
 		return -ENOMEM;
@@ -439,15 +439,16 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa,
 		 * The resulting value will be rounded down to the closest
 		 * multiple of dd->rcv_entries.group_size.
 		 */
-		rcd->egrbufs.buffers = kzalloc_node(
-			rcd->egrbufs.count * sizeof(*rcd->egrbufs.buffers),
-			GFP_KERNEL, numa);
+		rcd->egrbufs.buffers =
+			kcalloc_node(rcd->egrbufs.count,
+				     sizeof(*rcd->egrbufs.buffers),
+				     GFP_KERNEL, numa);
 		if (!rcd->egrbufs.buffers)
 			goto bail;
-		rcd->egrbufs.rcvtids = kzalloc_node(
-				rcd->egrbufs.count *
-				sizeof(*rcd->egrbufs.rcvtids),
-				GFP_KERNEL, numa);
+		rcd->egrbufs.rcvtids =
+			kcalloc_node(rcd->egrbufs.count,
+				     sizeof(*rcd->egrbufs.rcvtids),
+				     GFP_KERNEL, numa);
 		if (!rcd->egrbufs.rcvtids)
 			goto bail;
 		rcd->egrbufs.size = eager_buffer_size;
@@ -637,6 +638,15 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
 	ppd->dd = dd;
 	ppd->hw_pidx = hw_pidx;
 	ppd->port = port; /* IB port number, not index */
+	ppd->prev_link_width = LINK_WIDTH_DEFAULT;
+	/*
+	 * There are C_VL_COUNT number of PortVLXmitWait counters.
+	 * Adding 1 to C_VL_COUNT to include the PortXmitWait counter.
+	 */
+	for (i = 0; i < C_VL_COUNT + 1; i++) {
+		ppd->port_vl_xmit_wait_last[i] = 0;
+		ppd->vl_xmit_flit_cnt[i] = 0;
+	}
 
 	default_pkey_idx = 1;
 
@@ -1058,8 +1068,9 @@ static void shutdown_device(struct hfi1_devdata *dd)
 	}
 	dd->flags &= ~HFI1_INITTED;
 
-	/* mask interrupts, but not errors */
+	/* mask and clean up interrupts, but not errors */
 	set_intr_state(dd, 0);
+	hfi1_clean_up_interrupts(dd);
 
 	for (pidx = 0; pidx < dd->num_pports; ++pidx) {
 		ppd = dd->pport + pidx;
@@ -1218,6 +1229,7 @@ static void __hfi1_free_devdata(struct kobject *kobj)
 	free_percpu(dd->rcv_limit);
 	free_percpu(dd->send_schedule);
 	free_percpu(dd->tx_opstats);
+	sdma_clean(dd, dd->num_sdma);
 	rvt_dealloc_device(&dd->verbs_dev.rdi);
 }
 
@@ -1704,6 +1716,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dd_dev_err(dd, "Failed to create /dev devices: %d\n", -j);
 
 	if (initfail || ret) {
+		hfi1_clean_up_interrupts(dd);
 		stop_timers(dd);
 		flush_workqueue(ib_wq);
 		for (pidx = 0; pidx < dd->num_pports; ++pidx) {

drivers/infiniband/hw/hfi1/iowait.h

@@ -371,4 +371,13 @@ static inline void iowait_starve_find_max(struct iowait *w, u8 *max,
 	}
 }
 
+/**
+ * iowait_packet_queued() - determine if a packet is already built
+ * @wait: the wait structure
+ */
+static inline bool iowait_packet_queued(struct iowait *wait)
+{
+	return !list_empty(&wait->tx_head);
+}
+
 #endif

drivers/infiniband/hw/hfi1/mad.c

@@ -2649,6 +2649,79 @@ static void a0_portstatus(struct hfi1_pportdata *ppd,
 	}
 }
 
+/**
+ * tx_link_width - convert link width bitmask to integer
+ * value representing actual link width.
+ * @link_width: width of active link
+ * @return: return index of the bit set in link_width var
+ *
+ * The function convert and return the index of bit set
+ * that indicate the current link width.
+ */
+u16 tx_link_width(u16 link_width)
+{
+	int n = LINK_WIDTH_DEFAULT;
+	u16 tx_width = n;
+
+	while (link_width && n) {
+		if (link_width & (1 << (n - 1))) {
+			tx_width = n;
+			break;
+		}
+		n--;
+	}
+
+	return tx_width;
+}
+
+/**
+ * get_xmit_wait_counters - Convert HFI 's SendWaitCnt/SendWaitVlCnt
+ * counter in unit of TXE cycle times to flit times.
+ * @ppd: info of physical Hfi port
+ * @link_width: width of active link
+ * @link_speed: speed of active link
+ * @vl: represent VL0-VL7, VL15 for PortVLXmitWait counters request
+ * and if vl value is C_VL_COUNT, it represent SendWaitCnt
+ * counter request
+ * @return: return SendWaitCnt/SendWaitVlCnt counter value per vl.
+ *
+ * Convert SendWaitCnt/SendWaitVlCnt counter from TXE cycle times to
+ * flit times. Call this function to samples these counters. This
+ * function will calculate for previous state transition and update
+ * current state at end of function using ppd->prev_link_width and
+ * ppd->port_vl_xmit_wait_last to port_vl_xmit_wait_curr and link_width.
+ */
+u64 get_xmit_wait_counters(struct hfi1_pportdata *ppd,
+			   u16 link_width, u16 link_speed, int vl)
+{
+	u64 port_vl_xmit_wait_curr;
+	u64 delta_vl_xmit_wait;
+	u64 xmit_wait_val;
+
+	if (vl > C_VL_COUNT)
+		return  0;
+	if (vl < C_VL_COUNT)
+		port_vl_xmit_wait_curr =
+			read_port_cntr(ppd, C_TX_WAIT_VL, vl);
+	else
+		port_vl_xmit_wait_curr =
+			read_port_cntr(ppd, C_TX_WAIT, CNTR_INVALID_VL);
+
+	xmit_wait_val =
+		port_vl_xmit_wait_curr -
+		ppd->port_vl_xmit_wait_last[vl];
+	delta_vl_xmit_wait =
+		convert_xmit_counter(xmit_wait_val,
+				     ppd->prev_link_width,
+				     link_speed);
+
+	ppd->vl_xmit_flit_cnt[vl] += delta_vl_xmit_wait;
+	ppd->port_vl_xmit_wait_last[vl] = port_vl_xmit_wait_curr;
+	ppd->prev_link_width = link_width;
+
+	return ppd->vl_xmit_flit_cnt[vl];
+}
+
 static int pma_get_opa_portstatus(struct opa_pma_mad *pmp,
 				  struct ib_device *ibdev,
 				  u8 port, u32 *resp_len)
@@ -2668,6 +2741,8 @@ static int pma_get_opa_portstatus(struct opa_pma_mad *pmp,
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	int vfi;
 	u64 tmp, tmp2;
+	u16 link_width;
+	u16 link_speed;
 
 	response_data_size = sizeof(struct opa_port_status_rsp) +
 				num_vls * sizeof(struct _vls_pctrs);
@@ -2711,8 +2786,16 @@ static int pma_get_opa_portstatus(struct opa_pma_mad *pmp,
 	rsp->port_multicast_rcv_pkts =
 		cpu_to_be64(read_dev_cntr(dd, C_DC_MC_RCV_PKTS,
 					  CNTR_INVALID_VL));
+	/*
+	 * Convert PortXmitWait counter from TXE cycle times
+	 * to flit times.
+	 */
+	link_width =
+		tx_link_width(ppd->link_width_downgrade_tx_active);
+	link_speed = get_link_speed(ppd->link_speed_active);
 	rsp->port_xmit_wait =
-		cpu_to_be64(read_port_cntr(ppd, C_TX_WAIT, CNTR_INVALID_VL));
+		cpu_to_be64(get_xmit_wait_counters(ppd, link_width,
+						   link_speed, C_VL_COUNT));
 	rsp->port_rcv_fecn =
 		cpu_to_be64(read_dev_cntr(dd, C_DC_RCV_FCN, CNTR_INVALID_VL));
 	rsp->port_rcv_becn =
@@ -2777,10 +2860,14 @@ static int pma_get_opa_portstatus(struct opa_pma_mad *pmp,
 		rsp->vls[vfi].port_vl_xmit_pkts =
 			cpu_to_be64(read_port_cntr(ppd, C_TX_PKT_VL,
 						   idx_from_vl(vl)));
-
+		/*
+		 * Convert PortVlXmitWait counter from TXE cycle
+		 * times to flit times.
+		 */
 		rsp->vls[vfi].port_vl_xmit_wait =
-			cpu_to_be64(read_port_cntr(ppd, C_TX_WAIT_VL,
-						   idx_from_vl(vl)));
+			cpu_to_be64(get_xmit_wait_counters(ppd, link_width,
+							   link_speed,
+							   idx_from_vl(vl)));
 
 		rsp->vls[vfi].port_vl_rcv_fecn =
 			cpu_to_be64(read_dev_cntr(dd, C_DC_RCV_FCN_VL,
@@ -2910,6 +2997,8 @@ static int pma_get_opa_datacounters(struct opa_pma_mad *pmp,
 	unsigned long vl;
 	u32 vl_select_mask;
 	int vfi;
+	u16 link_width;
+	u16 link_speed;
 
 	num_ports = be32_to_cpu(pmp->mad_hdr.attr_mod) >> 24;
 	num_vls = hweight32(be32_to_cpu(req->vl_select_mask));
@@ -2959,8 +3048,16 @@ static int pma_get_opa_datacounters(struct opa_pma_mad *pmp,
 	rsp->link_quality_indicator = cpu_to_be32((u32)lq);
 	pma_get_opa_port_dctrs(ibdev, rsp);
 
+	/*
+	 * Convert PortXmitWait counter from TXE
+	 * cycle times to flit times.
+	 */
+	link_width =
+		tx_link_width(ppd->link_width_downgrade_tx_active);
+	link_speed = get_link_speed(ppd->link_speed_active);
 	rsp->port_xmit_wait =
-		cpu_to_be64(read_port_cntr(ppd, C_TX_WAIT, CNTR_INVALID_VL));
+		cpu_to_be64(get_xmit_wait_counters(ppd, link_width,
+						   link_speed, C_VL_COUNT));
 	rsp->port_rcv_fecn =
 		cpu_to_be64(read_dev_cntr(dd, C_DC_RCV_FCN, CNTR_INVALID_VL));
 	rsp->port_rcv_becn =
@@ -2996,9 +3093,14 @@ static int pma_get_opa_datacounters(struct opa_pma_mad *pmp,
 			cpu_to_be64(read_dev_cntr(dd, C_DC_RX_PKT_VL,
 						  idx_from_vl(vl)));
 
+		/*
+		 * Convert PortVlXmitWait counter from TXE
+		 * cycle times to flit times.
+		 */
 		rsp->vls[vfi].port_vl_xmit_wait =
-			cpu_to_be64(read_port_cntr(ppd, C_TX_WAIT_VL,
-						   idx_from_vl(vl)));
+			cpu_to_be64(get_xmit_wait_counters(ppd, link_width,
+							   link_speed,
+							   idx_from_vl(vl)));
 
 		rsp->vls[vfi].port_vl_rcv_fecn =
 			cpu_to_be64(read_dev_cntr(dd, C_DC_RCV_FCN_VL,
@@ -3416,9 +3518,11 @@ static int pma_set_opa_portstatus(struct opa_pma_mad *pmp,
 	if (counter_select & CS_PORT_MCAST_RCV_PKTS)
 		write_dev_cntr(dd, C_DC_MC_RCV_PKTS, CNTR_INVALID_VL, 0);
 
-	if (counter_select & CS_PORT_XMIT_WAIT)
+	if (counter_select & CS_PORT_XMIT_WAIT) {
 		write_port_cntr(ppd, C_TX_WAIT, CNTR_INVALID_VL, 0);
-
+		ppd->port_vl_xmit_wait_last[C_VL_COUNT] = 0;
+		ppd->vl_xmit_flit_cnt[C_VL_COUNT] = 0;
+	}
 	/* ignore cs_sw_portCongestion for HFIs */
 
 	if (counter_select & CS_PORT_RCV_FECN)
@@ -3491,8 +3595,11 @@ static int pma_set_opa_portstatus(struct opa_pma_mad *pmp,
 		if (counter_select & CS_PORT_RCV_PKTS)
 			write_dev_cntr(dd, C_DC_RX_PKT_VL, idx_from_vl(vl), 0);
 
-		if (counter_select & CS_PORT_XMIT_WAIT)
+		if (counter_select & CS_PORT_XMIT_WAIT) {
 			write_port_cntr(ppd, C_TX_WAIT_VL, idx_from_vl(vl), 0);
+			ppd->port_vl_xmit_wait_last[idx_from_vl(vl)] = 0;
+			ppd->vl_xmit_flit_cnt[idx_from_vl(vl)] = 0;
+		}
 
 		/* sw_port_vl_congestion is 0 for HFIs */
 		if (counter_select & CS_PORT_RCV_FECN)

drivers/infiniband/hw/hfi1/mad.h

@@ -180,6 +180,15 @@ struct opa_mad_notice_attr {
 #define OPA_VLARB_PREEMPT_MATRIX     3
 
 #define IB_PMA_PORT_COUNTERS_CONG       cpu_to_be16(0xFF00)
+#define LINK_SPEED_25G		1
+#define LINK_SPEED_12_5G	2
+#define LINK_WIDTH_DEFAULT	4
+#define DECIMAL_FACTORING	1000
+/*
+ * The default link width is multiplied by 1000
+ * to get accurate value after division.
+ */
+#define FACTOR_LINK_WIDTH	(LINK_WIDTH_DEFAULT * DECIMAL_FACTORING)
 
 struct ib_pma_portcounters_cong {
 	u8 reserved;
@@ -429,5 +438,41 @@ struct sc2vlnt {
 
 void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port);
 void hfi1_handle_trap_timer(struct timer_list *t);
+u16 tx_link_width(u16 link_width);
+u64 get_xmit_wait_counters(struct hfi1_pportdata *ppd, u16 link_width,
+			   u16 link_speed, int vl);
+/**
+ * get_link_speed - determine whether 12.5G or 25G speed
+ * @link_speed: the speed of active link
+ * @return: Return 2 if link speed identified as 12.5G
+ * or return 1 if link speed is 25G.
+ *
+ * The function indirectly calculate required link speed
+ * value for convert_xmit_counter function. If the link
+ * speed is 25G, the function return as 1 as it is required
+ * by xmit counter conversion formula :-( 25G / link_speed).
+ * This conversion will provide value 1 if current
+ * link speed is 25G or 2 if 12.5G.This is done to avoid
+ * 12.5 float number conversion.
+ */
+static inline u16 get_link_speed(u16 link_speed)
+{
+	return (link_speed == 1) ?
+		 LINK_SPEED_12_5G : LINK_SPEED_25G;
+}
 
+/**
+ * convert_xmit_counter - calculate flit times for given xmit counter
+ * value
+ * @xmit_wait_val: current xmit counter value
+ * @link_width: width of active link
+ * @link_speed: speed of active link
+ * @return: return xmit counter value in flit times.
+ */
+static inline u64 convert_xmit_counter(u64 xmit_wait_val, u16 link_width,
+				       u16 link_speed)
+{
+	return (xmit_wait_val * 2 * (FACTOR_LINK_WIDTH / link_width)
+		 * link_speed) / DECIMAL_FACTORING;
+}
 #endif				/* _HFI1_MAD_H */

drivers/infiniband/hw/hfi1/pcie.c

@@ -1034,6 +1034,7 @@ int do_pcie_gen3_transition(struct hfi1_devdata *dd)
 	int do_retry, retry_count = 0;
 	int intnum = 0;
 	uint default_pset;
+	uint pset = pcie_pset;
 	u16 target_vector, target_speed;
 	u16 lnkctl2, vendor;
 	u8 div;
@@ -1201,16 +1202,16 @@ retry:
 	 *
 	 * Set Gen3EqPsetReqVec, leave other fields 0.
 	 */
-	if (pcie_pset == UNSET_PSET)
-		pcie_pset = default_pset;
-	if (pcie_pset > 10) {	/* valid range is 0-10, inclusive */
+	if (pset == UNSET_PSET)
+		pset = default_pset;
+	if (pset > 10) {	/* valid range is 0-10, inclusive */
 		dd_dev_err(dd, "%s: Invalid Eq Pset %u, setting to %d\n",
-			   __func__, pcie_pset, default_pset);
-		pcie_pset = default_pset;
+			   __func__, pset, default_pset);
+		pset = default_pset;
 	}
-	dd_dev_info(dd, "%s: using EQ Pset %u\n", __func__, pcie_pset);
+	dd_dev_info(dd, "%s: using EQ Pset %u\n", __func__, pset);
 	pci_write_config_dword(dd->pcidev, PCIE_CFG_REG_PL106,
-			       ((1 << pcie_pset) <<
+			       ((1 << pset) <<
 			PCIE_CFG_REG_PL106_GEN3_EQ_PSET_REQ_VEC_SHIFT) |
 			PCIE_CFG_REG_PL106_GEN3_EQ_EVAL2MS_DISABLE_SMASK |
 			PCIE_CFG_REG_PL106_GEN3_EQ_PHASE23_EXIT_MODE_SMASK);
@@ -1240,10 +1241,10 @@ retry:
 		/* apply static CTLE tunings */
 		u8 pcie_dc, pcie_lf, pcie_hf, pcie_bw;
 
-		pcie_dc = ctle_tunings[pcie_pset][0];
-		pcie_lf = ctle_tunings[pcie_pset][1];
-		pcie_hf = ctle_tunings[pcie_pset][2];
-		pcie_bw = ctle_tunings[pcie_pset][3];
+		pcie_dc = ctle_tunings[pset][0];
+		pcie_lf = ctle_tunings[pset][1];
+		pcie_hf = ctle_tunings[pset][2];
+		pcie_bw = ctle_tunings[pset][3];
 		write_gasket_interrupt(dd, intnum++, 0x0026, 0x0200 | pcie_dc);
 		write_gasket_interrupt(dd, intnum++, 0x0026, 0x0100 | pcie_lf);
 		write_gasket_interrupt(dd, intnum++, 0x0026, 0x0000 | pcie_hf);

drivers/infiniband/hw/hfi1/pio.c

@@ -455,8 +455,8 @@ int init_send_contexts(struct hfi1_devdata *dd)
 	dd->hw_to_sw = kmalloc_array(TXE_NUM_CONTEXTS, sizeof(u8),
 					GFP_KERNEL);
 	dd->send_contexts = kcalloc(dd->num_send_contexts,
-					sizeof(struct send_context_info),
-					GFP_KERNEL);
+				    sizeof(struct send_context_info),
+				    GFP_KERNEL);
 	if (!dd->send_contexts || !dd->hw_to_sw) {
 		kfree(dd->hw_to_sw);
 		kfree(dd->send_contexts);
@@ -856,8 +856,9 @@ struct send_context *sc_alloc(struct hfi1_devdata *dd, int type,
 		 * so head == tail can mean empty.
 		 */
 		sc->sr_size = sci->credits + 1;
-		sc->sr = kzalloc_node(sizeof(union pio_shadow_ring) *
-				sc->sr_size, GFP_KERNEL, numa);
+		sc->sr = kcalloc_node(sc->sr_size,
+				      sizeof(union pio_shadow_ring),
+				      GFP_KERNEL, numa);
 		if (!sc->sr) {
 			sc_free(sc);
 			return NULL;
@@ -1958,9 +1959,9 @@ int init_pervl_scs(struct hfi1_devdata *dd)
 	hfi1_init_ctxt(dd->vld[15].sc);
 	dd->vld[15].mtu = enum_to_mtu(OPA_MTU_2048);
 
-	dd->kernel_send_context = kzalloc_node(dd->num_send_contexts *
-					sizeof(struct send_context *),
-					GFP_KERNEL, dd->node);
+	dd->kernel_send_context = kcalloc_node(dd->num_send_contexts,
+					       sizeof(struct send_context *),
+					       GFP_KERNEL, dd->node);
 	if (!dd->kernel_send_context)
 		goto freesc15;
 

drivers/infiniband/hw/hfi1/qp.c

@@ -565,7 +565,7 @@ void qp_iter_print(struct seq_file *s, struct rvt_qp_iter *iter)
 	if (qp->s_ack_queue)
 		e = &qp->s_ack_queue[qp->s_tail_ack_queue];
 	seq_printf(s,
-		   "N %d %s QP %x R %u %s %u %u %u f=%x %u %u %u %u %u %u SPSN %x %x %x %x %x RPSN %x S(%u %u %u %u %u %u %u) R(%u %u %u) RQP %x LID %x SL %u MTU %u %u %u %u %u SDE %p,%u SC %p,%u SCQ %u %u PID %d OS %x %x E %x %x %x RNR %d %s %d\n",
+		   "N %d %s QP %x R %u %s %u %u f=%x %u %u %u %u %u %u SPSN %x %x %x %x %x RPSN %x S(%u %u %u %u %u %u %u) R(%u %u %u) RQP %x LID %x SL %u MTU %u %u %u %u %u SDE %p,%u SC %p,%u SCQ %u %u PID %d OS %x %x E %x %x %x RNR %d %s %d\n",
 		   iter->n,
 		   qp_idle(qp) ? "I" : "B",
 		   qp->ibqp.qp_num,
@@ -573,7 +573,6 @@ void qp_iter_print(struct seq_file *s, struct rvt_qp_iter *iter)
 		   qp_type_str[qp->ibqp.qp_type],
 		   qp->state,
 		   wqe ? wqe->wr.opcode : 0,
-		   qp->s_hdrwords,
 		   qp->s_flags,
 		   iowait_sdma_pending(&priv->s_iowait),
 		   iowait_pio_pending(&priv->s_iowait),
@@ -795,7 +794,6 @@ void notify_error_qp(struct rvt_qp *qp)
 	}
 
 	if (!(qp->s_flags & RVT_S_BUSY)) {
-		qp->s_hdrwords = 0;
 		if (qp->s_rdma_mr) {
 			rvt_put_mr(qp->s_rdma_mr);
 			qp->s_rdma_mr = NULL;

drivers/infiniband/hw/hfi1/qp.h

@@ -51,11 +51,24 @@
 #include <rdma/rdmavt_qp.h>
 #include "verbs.h"
 #include "sdma.h"
+#include "verbs_txreq.h"
 
 extern unsigned int hfi1_qp_table_size;
 
 extern const struct rvt_operation_params hfi1_post_parms[];
 
+/*
+ * Send if not busy or waiting for I/O and either
+ * a RC response is pending or we can process send work requests.
+ */
+static inline int hfi1_send_ok(struct rvt_qp *qp)
+{
+	return !(qp->s_flags & (RVT_S_BUSY | RVT_S_ANY_WAIT_IO)) &&
+		(verbs_txreq_queued(qp) ||
+		(qp->s_flags & RVT_S_RESP_PENDING) ||
+		 !(qp->s_flags & RVT_S_ANY_WAIT_SEND));
+}
+
 /*
  * free_ahg - clear ahg from QP
  */

drivers/infiniband/hw/hfi1/rc.c

@@ -226,12 +226,10 @@ normal:
 		bth2 = mask_psn(qp->s_ack_psn);
 	}
 	qp->s_rdma_ack_cnt++;
-	qp->s_hdrwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
 	ps->s_txreq->s_cur_size = len;
+	ps->s_txreq->hdr_dwords = hwords;
 	hfi1_make_ruc_header(qp, ohdr, bth0, bth2, middle, ps);
-	/* pbc */
-	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 	return 1;
 
 bail:
@@ -385,7 +383,6 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 						       : IB_WC_SUCCESS);
 				if (local_ops)
 					atomic_dec(&qp->local_ops_pending);
-				qp->s_hdrwords = 0;
 				goto done_free_tx;
 			}
 
@@ -688,7 +685,7 @@ no_flow_control:
 		bth2 |= IB_BTH_REQ_ACK;
 	}
 	qp->s_len -= len;
-	qp->s_hdrwords = hwords;
+	ps->s_txreq->hdr_dwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
 	ps->s_txreq->ss = ss;
 	ps->s_txreq->s_cur_size = len;
@@ -699,8 +696,6 @@ no_flow_control:
 		bth2,
 		middle,
 		ps);
-	/* pbc */
-	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 	return 1;
 
 done_free_tx:
@@ -714,7 +709,6 @@ bail:
 bail_no_tx:
 	ps->s_txreq = NULL;
 	qp->s_flags &= ~RVT_S_BUSY;
-	qp->s_hdrwords = 0;
 	return 0;
 }
 
@@ -734,14 +728,16 @@ static inline void hfi1_make_bth_aeth(struct rvt_qp *qp,
 	ohdr->bth[2] = cpu_to_be32(mask_psn(qp->r_ack_psn));
 }
 
-static inline void hfi1_queue_rc_ack(struct rvt_qp *qp, bool is_fecn)
+static inline void hfi1_queue_rc_ack(struct hfi1_packet *packet, bool is_fecn)
 {
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct rvt_qp *qp = packet->qp;
+	struct hfi1_ibport *ibp;
 	unsigned long flags;
 
 	spin_lock_irqsave(&qp->s_lock, flags);
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK))
 		goto unlock;
+	ibp = rcd_to_iport(packet->rcd);
 	this_cpu_inc(*ibp->rvp.rc_qacks);
 	qp->s_flags |= RVT_S_ACK_PENDING | RVT_S_RESP_PENDING;
 	qp->s_nak_state = qp->r_nak_state;
@@ -755,13 +751,14 @@ unlock:
 	spin_unlock_irqrestore(&qp->s_lock, flags);
 }
 
-static inline void hfi1_make_rc_ack_9B(struct rvt_qp *qp,
+static inline void hfi1_make_rc_ack_9B(struct hfi1_packet *packet,
 				       struct hfi1_opa_header *opa_hdr,
 				       u8 sc5, bool is_fecn,
 				       u64 *pbc_flags, u32 *hwords,
 				       u32 *nwords)
 {
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct rvt_qp *qp = packet->qp;
+	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct ib_header *hdr = &opa_hdr->ibh;
 	struct ib_other_headers *ohdr;
@@ -802,19 +799,20 @@ static inline void hfi1_make_rc_ack_9B(struct rvt_qp *qp,
 	hfi1_make_bth_aeth(qp, ohdr, bth0, bth1);
 }
 
-static inline void hfi1_make_rc_ack_16B(struct rvt_qp *qp,
+static inline void hfi1_make_rc_ack_16B(struct hfi1_packet *packet,
 					struct hfi1_opa_header *opa_hdr,
 					u8 sc5, bool is_fecn,
 					u64 *pbc_flags, u32 *hwords,
 					u32 *nwords)
 {
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct rvt_qp *qp = packet->qp;
+	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct hfi1_16b_header *hdr = &opa_hdr->opah;
 	struct ib_other_headers *ohdr;
 	u32 bth0, bth1 = 0;
 	u16 len, pkey;
-	u8 becn = !!is_fecn;
+	bool becn = is_fecn;
 	u8 l4 = OPA_16B_L4_IB_LOCAL;
 	u8 extra_bytes;
 
@@ -854,7 +852,7 @@ static inline void hfi1_make_rc_ack_16B(struct rvt_qp *qp,
 	hfi1_make_bth_aeth(qp, ohdr, bth0, bth1);
 }
 
-typedef void (*hfi1_make_rc_ack)(struct rvt_qp *qp,
+typedef void (*hfi1_make_rc_ack)(struct hfi1_packet *packet,
 				 struct hfi1_opa_header *opa_hdr,
 				 u8 sc5, bool is_fecn,
 				 u64 *pbc_flags, u32 *hwords,
@@ -874,9 +872,10 @@ static const hfi1_make_rc_ack hfi1_make_rc_ack_tbl[2] = {
  * Note that RDMA reads and atomics are handled in the
  * send side QP state and send engine.
  */
-void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd,
-		      struct rvt_qp *qp, bool is_fecn)
+void hfi1_send_rc_ack(struct hfi1_packet *packet, bool is_fecn)
 {
+	struct hfi1_ctxtdata *rcd = packet->rcd;
+	struct rvt_qp *qp = packet->qp;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
@@ -893,13 +892,13 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd,
 
 	/* Don't send ACK or NAK if a RDMA read or atomic is pending. */
 	if (qp->s_flags & RVT_S_RESP_PENDING) {
-		hfi1_queue_rc_ack(qp, is_fecn);
+		hfi1_queue_rc_ack(packet, is_fecn);
 		return;
 	}
 
 	/* Ensure s_rdma_ack_cnt changes are committed */
 	if (qp->s_rdma_ack_cnt) {
-		hfi1_queue_rc_ack(qp, is_fecn);
+		hfi1_queue_rc_ack(packet, is_fecn);
 		return;
 	}
 
@@ -908,7 +907,7 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd,
 		return;
 
 	/* Make the appropriate header */
-	hfi1_make_rc_ack_tbl[priv->hdr_type](qp, &opa_hdr, sc5, is_fecn,
+	hfi1_make_rc_ack_tbl[priv->hdr_type](packet, &opa_hdr, sc5, is_fecn,
 					     &pbc_flags, &hwords, &nwords);
 
 	plen = 2 /* PBC */ + hwords + nwords;
@@ -922,7 +921,7 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd,
 		 * so that when enough buffer space becomes available,
 		 * the ACK is sent ahead of other outgoing packets.
 		 */
-		hfi1_queue_rc_ack(qp, is_fecn);
+		hfi1_queue_rc_ack(packet, is_fecn);
 		return;
 	}
 	trace_ack_output_ibhdr(dd_from_ibdev(qp->ibqp.device),
@@ -1540,7 +1539,7 @@ static void rc_rcv_resp(struct hfi1_packet *packet)
 	void *data = packet->payload;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_ibport *ibp;
 	struct ib_other_headers *ohdr = packet->ohdr;
 	struct rvt_swqe *wqe;
 	enum ib_wc_status status;
@@ -1697,6 +1696,7 @@ ack_op_err:
 	goto ack_err;
 
 ack_seq_err:
+	ibp = rcd_to_iport(rcd);
 	rdma_seq_err(qp, ibp, psn, rcd);
 	goto ack_done;
 
@@ -2037,7 +2037,6 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	struct rvt_qp *qp = packet->qp;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct ib_other_headers *ohdr = packet->ohdr;
-	u32 bth0 = be32_to_cpu(ohdr->bth[0]);
 	u32 opcode = packet->opcode;
 	u32 hdrsize = packet->hlen;
 	u32 psn = ib_bth_get_psn(packet->ohdr);
@@ -2235,7 +2234,7 @@ send_last:
 		wc.port_num = 0;
 		/* Signal completion event if the solicited bit is set. */
 		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-			     (bth0 & IB_BTH_SOLICITED) != 0);
+			     ib_bth_is_solicited(ohdr));
 		break;
 
 	case OP(RDMA_WRITE_ONLY):
@@ -2479,7 +2478,7 @@ nack_acc:
 	qp->r_nak_state = IB_NAK_REMOTE_ACCESS_ERROR;
 	qp->r_ack_psn = qp->r_psn;
 send_ack:
-	hfi1_send_rc_ack(rcd, qp, is_fecn);
+	hfi1_send_rc_ack(packet, is_fecn);
 }
 
 void hfi1_rc_hdrerr(

drivers/infiniband/hw/hfi1/ruc.c

@@ -225,19 +225,8 @@ int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_packet *packet)
 	u32 dlid = packet->dlid;
 	u32 slid = packet->slid;
 	u32 sl = packet->sl;
-	int migrated;
-	u32 bth0, bth1;
-	u16 pkey;
-
-	bth0 = be32_to_cpu(packet->ohdr->bth[0]);
-	bth1 = be32_to_cpu(packet->ohdr->bth[1]);
-	if (packet->etype == RHF_RCV_TYPE_BYPASS) {
-		pkey = hfi1_16B_get_pkey(packet->hdr);
-		migrated = bth1 & OPA_BTH_MIG_REQ;
-	} else {
-		pkey = ib_bth_get_pkey(packet->ohdr);
-		migrated = bth0 & IB_BTH_MIG_REQ;
-	}
+	bool migrated = packet->migrated;
+	u16 pkey = packet->pkey;
 
 	if (qp->s_mig_state == IB_MIG_ARMED && migrated) {
 		if (!packet->grh) {
@@ -756,19 +745,18 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 	u32 slid;
 	u16 pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
 	u8 l4 = OPA_16B_L4_IB_LOCAL;
-	u8 extra_bytes = hfi1_get_16b_padding((qp->s_hdrwords << 2),
-				   ps->s_txreq->s_cur_size);
+	u8 extra_bytes = hfi1_get_16b_padding(
+				(ps->s_txreq->hdr_dwords << 2),
+				ps->s_txreq->s_cur_size);
 	u32 nwords = SIZE_OF_CRC + ((ps->s_txreq->s_cur_size +
 				 extra_bytes + SIZE_OF_LT) >> 2);
-	u8 becn = 0;
+	bool becn = false;
 
 	if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH) &&
 	    hfi1_check_mcast(rdma_ah_get_dlid(&qp->remote_ah_attr))) {
 		struct ib_grh *grh;
 		struct ib_global_route *grd =
 			rdma_ah_retrieve_grh(&qp->remote_ah_attr);
-		int hdrwords;
-
 		/*
 		 * Ensure OPA GIDs are transformed to IB gids
 		 * before creating the GRH.
@@ -777,9 +765,10 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 			grd->sgid_index = 0;
 		grh = &ps->s_txreq->phdr.hdr.opah.u.l.grh;
 		l4 = OPA_16B_L4_IB_GLOBAL;
-		hdrwords = qp->s_hdrwords - 4;
-		qp->s_hdrwords += hfi1_make_grh(ibp, grh, grd,
-						hdrwords, nwords);
+		ps->s_txreq->hdr_dwords +=
+			hfi1_make_grh(ibp, grh, grd,
+				      ps->s_txreq->hdr_dwords - LRH_16B_DWORDS,
+				      nwords);
 		middle = 0;
 	}
 
@@ -798,7 +787,7 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 	if (qp->s_flags & RVT_S_ECN) {
 		qp->s_flags &= ~RVT_S_ECN;
 		/* we recently received a FECN, so return a BECN */
-		becn = 1;
+		becn = true;
 	}
 	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
 
@@ -813,7 +802,7 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 			  slid,
 			  opa_get_lid(rdma_ah_get_dlid(&qp->remote_ah_attr),
 				      16B),
-			  (qp->s_hdrwords + nwords) >> 1,
+			  (ps->s_txreq->hdr_dwords + nwords) >> 1,
 			  pkey, becn, 0, l4, priv->s_sc);
 }
 
@@ -833,13 +822,13 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 
 	if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)) {
 		struct ib_grh *grh = &ps->s_txreq->phdr.hdr.ibh.u.l.grh;
-		int hdrwords = qp->s_hdrwords - 2;
 
 		lrh0 = HFI1_LRH_GRH;
-		qp->s_hdrwords +=
+		ps->s_txreq->hdr_dwords +=
 			hfi1_make_grh(ibp, grh,
 				      rdma_ah_read_grh(&qp->remote_ah_attr),
-				      hdrwords, nwords);
+				      ps->s_txreq->hdr_dwords - LRH_9B_DWORDS,
+				      nwords);
 		middle = 0;
 	}
 	lrh0 |= (priv->s_sc & 0xf) << 12 |
@@ -865,7 +854,7 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
 	hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
 			 lrh0,
-			 qp->s_hdrwords + nwords,
+			 ps->s_txreq->hdr_dwords + nwords,
 			 opa_get_lid(rdma_ah_get_dlid(&qp->remote_ah_attr), 9B),
 			 ppd_from_ibp(ibp)->lid |
 				rdma_ah_get_path_bits(&qp->remote_ah_attr));
@@ -1030,7 +1019,7 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread)
 	ps.s_txreq = get_waiting_verbs_txreq(qp);
 	do {
 		/* Check for a constructed packet to be sent. */
-		if (qp->s_hdrwords != 0) {
+		if (ps.s_txreq) {
 			spin_unlock_irqrestore(&qp->s_lock, ps.flags);
 			/*
 			 * If the packet cannot be sent now, return and
@@ -1038,8 +1027,6 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread)
 			 */
 			if (hfi1_verbs_send(qp, &ps))
 				return;
-			/* Record that s_ahg is empty. */
-			qp->s_hdrwords = 0;
 			/* allow other tasks to run */
 			if (schedule_send_yield(qp, &ps))
 				return;

drivers/infiniband/hw/hfi1/sdma.c

@@ -1275,13 +1275,15 @@ bail:
 	return -ENOMEM;
 }
 
-/*
- * Clean up allocated memory.
- *
- * This routine is can be called regardless of the success of sdma_init()
+/**
+ * sdma_clean()  Clean up allocated memory
+ * @dd:          struct hfi1_devdata
+ * @num_engines: num sdma engines
  *
+ * This routine can be called regardless of the success of
+ * sdma_init()
  */
-static void sdma_clean(struct hfi1_devdata *dd, size_t num_engines)
+void sdma_clean(struct hfi1_devdata *dd, size_t num_engines)
 {
 	size_t i;
 	struct sdma_engine *sde;
@@ -1386,7 +1388,8 @@ int sdma_init(struct hfi1_devdata *dd, u8 port)
 		    num_engines, descq_cnt);
 
 	/* alloc memory for array of send engines */
-	dd->per_sdma = kcalloc(num_engines, sizeof(*dd->per_sdma), GFP_KERNEL);
+	dd->per_sdma = kcalloc_node(num_engines, sizeof(*dd->per_sdma),
+				    GFP_KERNEL, dd->node);
 	if (!dd->per_sdma)
 		return ret;
 
@@ -1617,7 +1620,6 @@ void sdma_exit(struct hfi1_devdata *dd)
 		 */
 		sdma_finalput(&sde->state);
 	}
-	sdma_clean(dd, dd->num_sdma);
 }
 
 /*

drivers/infiniband/hw/hfi1/sdma.h

@@ -420,6 +420,7 @@ struct sdma_engine {
 int sdma_init(struct hfi1_devdata *dd, u8 port);
 void sdma_start(struct hfi1_devdata *dd);
 void sdma_exit(struct hfi1_devdata *dd);
+void sdma_clean(struct hfi1_devdata *dd, size_t num_engines);
 void sdma_all_running(struct hfi1_devdata *dd);
 void sdma_all_idle(struct hfi1_devdata *dd);
 void sdma_freeze_notify(struct hfi1_devdata *dd, int go_idle);

drivers/infiniband/hw/hfi1/trace.c

@@ -138,7 +138,7 @@ static const char *parse_syndrome(u8 syndrome)
 }
 
 void hfi1_trace_parse_9b_bth(struct ib_other_headers *ohdr,
-			     u8 *ack, u8 *becn, u8 *fecn, u8 *mig,
+			     u8 *ack, bool *becn, bool *fecn, u8 *mig,
 			     u8 *se, u8 *pad, u8 *opcode, u8 *tver,
 			     u16 *pkey, u32 *psn, u32 *qpn)
 {
@@ -184,7 +184,7 @@ void hfi1_trace_parse_9b_hdr(struct ib_header *hdr, bool sc5,
 }
 
 void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
-			      u8 *age, u8 *becn, u8 *fecn,
+			      u8 *age, bool *becn, bool *fecn,
 			      u8 *l4, u8 *rc, u8 *sc,
 			      u16 *entropy, u16 *len, u16 *pkey,
 			      u32 *dlid, u32 *slid)
@@ -207,7 +207,7 @@ void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
 #define LRH_16B_PRN "age:%d becn:%d fecn:%d l4:%d " \
 		    "rc:%d sc:%d pkey:0x%.4x entropy:0x%.4x"
 const char *hfi1_trace_fmt_lrh(struct trace_seq *p, bool bypass,
-			       u8 age, u8 becn, u8 fecn, u8 l4,
+			       u8 age, bool becn, bool fecn, u8 l4,
 			       u8 lnh, const char *lnh_name, u8 lver,
 			       u8 rc, u8 sc, u8 sl, u16 entropy,
 			       u16 len, u16 pkey, u32 dlid, u32 slid)
@@ -235,7 +235,7 @@ const char *hfi1_trace_fmt_lrh(struct trace_seq *p, bool bypass,
 	"op:0x%.2x,%s se:%d m:%d pad:%d tver:%d " \
 	"qpn:0x%.6x a:%d psn:0x%.8x"
 const char *hfi1_trace_fmt_bth(struct trace_seq *p, bool bypass,
-			       u8 ack, u8 becn, u8 fecn, u8 mig,
+			       u8 ack, bool becn, bool fecn, u8 mig,
 			       u8 se, u8 pad, u8 opcode, const char *opname,
 			       u8 tver, u16 pkey, u32 psn, u32 qpn)
 {

drivers/infiniband/hw/hfi1/trace_ibhdrs.h

@@ -101,7 +101,7 @@ u8 hfi1_trace_opa_hdr_len(struct hfi1_opa_header *opah);
 u8 hfi1_trace_packet_hdr_len(struct hfi1_packet *packet);
 const char *hfi1_trace_get_packet_l4_str(u8 l4);
 void hfi1_trace_parse_9b_bth(struct ib_other_headers *ohdr,
-			     u8 *ack, u8 *becn, u8 *fecn, u8 *mig,
+			     u8 *ack, bool *becn, bool *fecn, u8 *mig,
 			     u8 *se, u8 *pad, u8 *opcode, u8 *tver,
 			     u16 *pkey, u32 *psn, u32 *qpn);
 void hfi1_trace_parse_9b_hdr(struct ib_header *hdr, bool sc5,
@@ -112,19 +112,19 @@ void hfi1_trace_parse_16b_bth(struct ib_other_headers *ohdr,
 			      u8 *pad, u8 *se, u8 *tver,
 			      u32 *psn, u32 *qpn);
 void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
-			      u8 *age, u8 *becn, u8 *fecn,
+			      u8 *age, bool *becn, bool *fecn,
 			      u8 *l4, u8 *rc, u8 *sc,
 			      u16 *entropy, u16 *len, u16 *pkey,
 			      u32 *dlid, u32 *slid);
 
 const char *hfi1_trace_fmt_lrh(struct trace_seq *p, bool bypass,
-			       u8 age, u8 becn, u8 fecn, u8 l4,
+			       u8 age, bool becn, bool fecn, u8 l4,
 			       u8 lnh, const char *lnh_name, u8 lver,
 			       u8 rc, u8 sc, u8 sl, u16 entropy,
 			       u16 len, u16 pkey, u32 dlid, u32 slid);
 
 const char *hfi1_trace_fmt_bth(struct trace_seq *p, bool bypass,
-			       u8 ack, u8 becn, u8 fecn, u8 mig,
+			       u8 ack, bool becn, bool fecn, u8 mig,
 			       u8 se, u8 pad, u8 opcode, const char *opname,
 			       u8 tver, u16 pkey, u32 psn, u32 qpn);
 
@@ -148,8 +148,8 @@ DECLARE_EVENT_CLASS(hfi1_input_ibhdr_template,
 			__field(u8, etype)
 			__field(u8, ack)
 			__field(u8, age)
-			__field(u8, becn)
-			__field(u8, fecn)
+			__field(bool, becn)
+			__field(bool, fecn)
 			__field(u8, l2)
 			__field(u8, l4)
 			__field(u8, lnh)
@@ -290,8 +290,8 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template,
 			__field(u8, hdr_type)
 			__field(u8, ack)
 			__field(u8, age)
-			__field(u8, becn)
-			__field(u8, fecn)
+			__field(bool, becn)
+			__field(bool, fecn)
 			__field(u8, l4)
 			__field(u8, lnh)
 			__field(u8, lver)

drivers/infiniband/hw/hfi1/trace_rx.h

@@ -63,17 +63,9 @@ __print_symbolic(type,                       \
 #define TRACE_SYSTEM hfi1_rx
 
 TRACE_EVENT(hfi1_rcvhdr,
-	    TP_PROTO(struct hfi1_devdata *dd,
-		     u32 ctxt,
-		     u64 eflags,
-		     u32 etype,
-		     u32 hlen,
-		     u32 tlen,
-		     u32 updegr,
-		     u32 etail
-		    ),
-	    TP_ARGS(dd, ctxt, eflags, etype, hlen, tlen, updegr, etail),
-	    TP_STRUCT__entry(DD_DEV_ENTRY(dd)
+	    TP_PROTO(struct hfi1_packet *packet),
+	    TP_ARGS(packet),
+	    TP_STRUCT__entry(DD_DEV_ENTRY(packet->rcd->dd)
 			     __field(u64, eflags)
 			     __field(u32, ctxt)
 			     __field(u32, etype)
@@ -82,14 +74,14 @@ TRACE_EVENT(hfi1_rcvhdr,
 			     __field(u32, updegr)
 			     __field(u32, etail)
 			     ),
-	     TP_fast_assign(DD_DEV_ASSIGN(dd);
-			    __entry->eflags = eflags;
-			    __entry->ctxt = ctxt;
-			    __entry->etype = etype;
-			    __entry->hlen = hlen;
-			    __entry->tlen = tlen;
-			    __entry->updegr = updegr;
-			    __entry->etail = etail;
+	     TP_fast_assign(DD_DEV_ASSIGN(packet->rcd->dd);
+			    __entry->eflags = rhf_err_flags(packet->rhf);
+			    __entry->ctxt = packet->rcd->ctxt;
+			    __entry->etype = packet->etype;
+			    __entry->hlen = packet->hlen;
+			    __entry->tlen = packet->tlen;
+			    __entry->updegr = packet->updegr;
+			    __entry->etail = rhf_egr_index(packet->rhf);
 			    ),
 	     TP_printk(
 		"[%s] ctxt %d eflags 0x%llx etype %d,%s hlen %d tlen %d updegr %d etail %d",

drivers/infiniband/hw/hfi1/uc.c

@@ -144,7 +144,6 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 							: IB_WC_SUCCESS);
 			if (local_ops)
 				atomic_dec(&qp->local_ops_pending);
-			qp->s_hdrwords = 0;
 			goto done_free_tx;
 		}
 		/*
@@ -267,14 +266,12 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		break;
 	}
 	qp->s_len -= len;
-	qp->s_hdrwords = hwords;
+	ps->s_txreq->hdr_dwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
 	ps->s_txreq->ss = &qp->s_sge;
 	ps->s_txreq->s_cur_size = len;
 	hfi1_make_ruc_header(qp, ohdr, bth0 | (qp->s_state << 24),
 			     mask_psn(qp->s_psn++), middle, ps);
-	/* pbc */
-	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 	return 1;
 
 done_free_tx:
@@ -288,7 +285,6 @@ bail:
 bail_no_tx:
 	ps->s_txreq = NULL;
 	qp->s_flags &= ~RVT_S_BUSY;
-	qp->s_hdrwords = 0;
 	return 0;
 }
 
@@ -480,8 +476,7 @@ last_imm:
 		wc.port_num = 0;
 		/* Signal completion event if the solicited bit is set. */
 		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-			     (ohdr->bth[0] &
-			      cpu_to_be32(IB_BTH_SOLICITED)) != 0);
+			     ib_bth_is_solicited(ohdr));
 		break;
 
 	case OP(RDMA_WRITE_FIRST):

drivers/infiniband/hw/hfi1/ud.c

@@ -340,15 +340,16 @@ void hfi1_make_ud_req_9B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	extra_bytes = -wqe->length & 3;
 	nwords = ((wqe->length + extra_bytes) >> 2) + SIZE_OF_CRC;
 	/* header size in dwords LRH+BTH+DETH = (8+12+8)/4. */
-	qp->s_hdrwords = 7;
+	ps->s_txreq->hdr_dwords = 7;
 	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM)
-		qp->s_hdrwords++;
+		ps->s_txreq->hdr_dwords++;
 
 	if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
 		grh = &ps->s_txreq->phdr.hdr.ibh.u.l.grh;
-		qp->s_hdrwords += hfi1_make_grh(ibp, grh,
-						rdma_ah_read_grh(ah_attr),
-						qp->s_hdrwords - 2, nwords);
+		ps->s_txreq->hdr_dwords +=
+			hfi1_make_grh(ibp, grh, rdma_ah_read_grh(ah_attr),
+				      ps->s_txreq->hdr_dwords - LRH_9B_DWORDS,
+				      nwords);
 		lrh0 = HFI1_LRH_GRH;
 		ohdr = &ps->s_txreq->phdr.hdr.ibh.u.l.oth;
 	} else {
@@ -381,7 +382,7 @@ void hfi1_make_ud_req_9B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		}
 	}
 	hfi1_make_bth_deth(qp, wqe, ohdr, &pkey, extra_bytes, false);
-	len = qp->s_hdrwords + nwords;
+	len = ps->s_txreq->hdr_dwords + nwords;
 
 	/* Setup the packet */
 	ps->s_txreq->phdr.hdr.hdr_type = HFI1_PKT_TYPE_9B;
@@ -405,12 +406,12 @@ void hfi1_make_ud_req_16B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	ppd = ppd_from_ibp(ibp);
 	ah_attr = &ibah_to_rvtah(wqe->ud_wr.ah)->attr;
 	/* header size in dwords 16B LRH+BTH+DETH = (16+12+8)/4. */
-	qp->s_hdrwords = 9;
+	ps->s_txreq->hdr_dwords = 9;
 	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM)
-		qp->s_hdrwords++;
+		ps->s_txreq->hdr_dwords++;
 
 	/* SW provides space for CRC and LT for bypass packets. */
-	extra_bytes = hfi1_get_16b_padding((qp->s_hdrwords << 2),
+	extra_bytes = hfi1_get_16b_padding((ps->s_txreq->hdr_dwords << 2),
 					   wqe->length);
 	nwords = ((wqe->length + extra_bytes + SIZE_OF_LT) >> 2) + SIZE_OF_CRC;
 
@@ -428,8 +429,10 @@ void hfi1_make_ud_req_16B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 			grd->sgid_index = 0;
 		}
 		grh = &ps->s_txreq->phdr.hdr.opah.u.l.grh;
-		qp->s_hdrwords += hfi1_make_grh(ibp, grh, grd,
-					qp->s_hdrwords - 4, nwords);
+		ps->s_txreq->hdr_dwords += hfi1_make_grh(
+			ibp, grh, grd,
+			ps->s_txreq->hdr_dwords - LRH_16B_DWORDS,
+			nwords);
 		ohdr = &ps->s_txreq->phdr.hdr.opah.u.l.oth;
 		l4 = OPA_16B_L4_IB_GLOBAL;
 	} else {
@@ -452,7 +455,7 @@ void hfi1_make_ud_req_16B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 
 	hfi1_make_bth_deth(qp, wqe, ohdr, &pkey, extra_bytes, true);
 	/* Convert dwords to flits */
-	len = (qp->s_hdrwords + nwords) >> 1;
+	len = (ps->s_txreq->hdr_dwords + nwords) >> 1;
 
 	/* Setup the packet */
 	ps->s_txreq->phdr.hdr.hdr_type = HFI1_PKT_TYPE_16B;
@@ -562,8 +565,6 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	priv->s_ahg->ahgcount = 0;
 	priv->s_ahg->ahgidx = 0;
 	priv->s_ahg->tx_flags = 0;
-	/* pbc */
-	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
 
 	return 1;
 
@@ -578,7 +579,6 @@ bail:
 bail_no_tx:
 	ps->s_txreq = NULL;
 	qp->s_flags &= ~RVT_S_BUSY;
-	qp->s_hdrwords = 0;
 	return 0;
 }
 
@@ -649,7 +649,8 @@ void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
 		struct ib_grh *grh = &hdr.u.l.grh;
 
 		grh->version_tclass_flow = old_grh->version_tclass_flow;
-		grh->paylen = cpu_to_be16((hwords - 4 + nwords) << 2);
+		grh->paylen = cpu_to_be16(
+			(hwords - LRH_16B_DWORDS + nwords) << 2);
 		grh->hop_limit = 0xff;
 		grh->sgid = old_grh->dgid;
 		grh->dgid = old_grh->sgid;
@@ -703,7 +704,8 @@ void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
 		struct ib_grh *grh = &hdr.u.l.grh;
 
 		grh->version_tclass_flow = old_grh->version_tclass_flow;
-		grh->paylen = cpu_to_be16((hwords - 2 + SIZE_OF_CRC) << 2);
+		grh->paylen = cpu_to_be16(
+			(hwords - LRH_9B_DWORDS + SIZE_OF_CRC) << 2);
 		grh->hop_limit = 0xff;
 		grh->sgid = old_grh->dgid;
 		grh->dgid = old_grh->sgid;
@@ -1046,8 +1048,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	wc.port_num = qp->port_num;
 	/* Signal completion event if the solicited bit is set. */
 	rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-		     (ohdr->bth[0] &
-		      cpu_to_be32(IB_BTH_SOLICITED)) != 0);
+		     ib_bth_is_solicited(ohdr));
 	return;
 
 drop:

drivers/infiniband/hw/hfi1/verbs.c

@@ -835,7 +835,7 @@ static int build_verbs_tx_desc(
 {
 	int ret = 0;
 	struct hfi1_sdma_header *phdr = &tx->phdr;
-	u16 hdrbytes = tx->hdr_dwords << 2;
+	u16 hdrbytes = (tx->hdr_dwords + sizeof(pbc) / 4) << 2;
 	u8 extra_bytes = 0;
 
 	if (tx->phdr.hdr.hdr_type) {
@@ -901,7 +901,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 {
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_ahg_info *ahg_info = priv->s_ahg;
-	u32 hdrwords = qp->s_hdrwords;
+	u32 hdrwords = ps->s_txreq->hdr_dwords;
 	u32 len = ps->s_txreq->s_cur_size;
 	u32 plen;
 	struct hfi1_ibdev *dev = ps->dev;
@@ -919,7 +919,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	} else {
 		dwords = (len + 3) >> 2;
 	}
-	plen = hdrwords + dwords + 2;
+	plen = hdrwords + dwords + sizeof(pbc) / 4;
 
 	tx = ps->s_txreq;
 	if (!sdma_txreq_built(&tx->txreq)) {
@@ -1038,7 +1038,7 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 			u64 pbc)
 {
 	struct hfi1_qp_priv *priv = qp->priv;
-	u32 hdrwords = qp->s_hdrwords;
+	u32 hdrwords = ps->s_txreq->hdr_dwords;
 	struct rvt_sge_state *ss = ps->s_txreq->ss;
 	u32 len = ps->s_txreq->s_cur_size;
 	u32 dwords;
@@ -1064,7 +1064,7 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		dwords = (len + 3) >> 2;
 		hdr = (u32 *)&ps->s_txreq->phdr.hdr.ibh;
 	}
-	plen = hdrwords + dwords + 2;
+	plen = hdrwords + dwords + sizeof(pbc) / 4;
 
 	/* only RC/UC use complete */
 	switch (qp->ibqp.qp_type) {

drivers/infiniband/hw/hfi1/verbs.h

@@ -105,6 +105,11 @@ enum {
 	HFI1_HAS_GRH = (1 << 0),
 };
 
+#define LRH_16B_BYTES (FIELD_SIZEOF(struct hfi1_16b_header, lrh))
+#define LRH_16B_DWORDS (LRH_16B_BYTES / sizeof(u32))
+#define LRH_9B_BYTES (FIELD_SIZEOF(struct ib_header, lrh))
+#define LRH_9B_DWORDS (LRH_9B_BYTES / sizeof(u32))
+
 struct hfi1_16b_header {
 	u32 lrh[4];
 	union {
@@ -245,17 +250,6 @@ static inline struct rvt_qp *iowait_to_qp(struct  iowait *s_iowait)
 	return priv->owner;
 }
 
-/*
- * Send if not busy or waiting for I/O and either
- * a RC response is pending or we can process send work requests.
- */
-static inline int hfi1_send_ok(struct rvt_qp *qp)
-{
-	return !(qp->s_flags & (RVT_S_BUSY | RVT_S_ANY_WAIT_IO)) &&
-		(qp->s_hdrwords || (qp->s_flags & RVT_S_RESP_PENDING) ||
-		 !(qp->s_flags & RVT_S_ANY_WAIT_SEND));
-}
-
 /*
  * This must be called with s_lock held.
  */
@@ -369,8 +363,7 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread);
 void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe,
 			enum ib_wc_status status);
 
-void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
-		      bool is_fecn);
+void hfi1_send_rc_ack(struct hfi1_packet *packet, bool is_fecn);
 
 int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps);
 
@@ -416,6 +409,11 @@ static inline void cacheless_memcpy(void *dst, void *src, size_t n)
 	__copy_user_nocache(dst, (void __user *)src, n, 0);
 }
 
+static inline bool opa_bth_is_migration(struct ib_other_headers *ohdr)
+{
+	return ohdr->bth[1] & cpu_to_be32(OPA_BTH_MIG_REQ);
+}
+
 extern const enum ib_wc_opcode ib_hfi1_wc_opcode[];
 
 extern const u8 hdr_len_by_opcode[];

drivers/infiniband/hw/hfi1/verbs_txreq.h

@@ -113,6 +113,13 @@ static inline struct verbs_txreq *get_waiting_verbs_txreq(struct rvt_qp *qp)
 	return NULL;
 }
 
+static inline bool verbs_txreq_queued(struct rvt_qp *qp)
+{
+	struct hfi1_qp_priv *priv = qp->priv;
+
+	return iowait_packet_queued(&priv->s_iowait);
+}
+
 void hfi1_put_txreq(struct verbs_txreq *tx);
 int verbs_txreq_init(struct hfi1_ibdev *dev);
 void verbs_txreq_exit(struct hfi1_ibdev *dev);