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

Pull rdma updates from Jason Gunthorpe:
 "A very quiet cycle with few notable changes. Mostly the usual list of
  one or two patches to drivers changing something that isn't quite rc
  worthy. The subsystem seems to be seeing a larger number of rework and
  cleanup style patches right now, I feel that several vendors are
  prepping their drivers for new silicon.

  Summary:

   - Driver updates and cleanup for qedr, bnxt_re, hns, siw, mlx5, mlx4,
     rxe, i40iw

   - Larger series doing cleanup and rework for hns and hfi1.

   - Some general reworking of the CM code to make it a little more
     understandable

   - Unify the different code paths connected to the uverbs FD scheme

   - New UAPI ioctls conversions for get context and get async fd

   - Trace points for CQ and CM portions of the RDMA stack

   - mlx5 driver support for virtio-net formatted rings as RDMA raw
     ethernet QPs

   - verbs support for setting the PCI-E relaxed ordering bit on DMA
     traffic connected to a MR

   - A couple of bug fixes that came too late to make rc7"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (108 commits)
  RDMA/core: Make the entire API tree static
  RDMA/efa: Mask access flags with the correct optional range
  RDMA/cma: Fix unbalanced cm_id reference count during address resolve
  RDMA/umem: Fix ib_umem_find_best_pgsz()
  IB/mlx4: Fix leak in id_map_find_del
  IB/opa_vnic: Spelling correction of 'erorr' to 'error'
  IB/hfi1: Fix logical condition in msix_request_irq
  RDMA/cm: Remove CM message structs
  RDMA/cm: Use IBA functions for complex structure members
  RDMA/cm: Use IBA functions for simple structure members
  RDMA/cm: Use IBA functions for swapping get/set acessors
  RDMA/cm: Use IBA functions for simple get/set acessors
  RDMA/cm: Add SET/GET implementations to hide IBA wire format
  RDMA/cm: Add accessors for CM_REQ transport_type
  IB/mlx5: Return the administrative GUID if exists
  RDMA/core: Ensure that rdma_user_mmap_entry_remove() is a fence
  IB/mlx4: Fix memory leak in add_gid error flow
  IB/mlx5: Expose RoCE accelerator counters
  RDMA/mlx5: Set relaxed ordering when requested
  RDMA/core: Add the core support field to METHOD_GET_CONTEXT
  ...

15 files changed, 529 insertions, 342 deletions

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 9b1fb84a3d45..e0b1238d31df 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1685,6 +1685,14 @@ static u64 access_sw_pio_drain(const struct cntr_entry *entry,
 	return dd->verbs_dev.n_piodrain;
 }
 
+static u64 access_sw_ctx0_seq_drop(const struct cntr_entry *entry,
+				   void *context, int vl, int mode, u64 data)
+{
+	struct hfi1_devdata *dd = context;
+
+	return dd->ctx0_seq_drop;
+}
+
 static u64 access_sw_vtx_wait(const struct cntr_entry *entry,
 			      void *context, int vl, int mode, u64 data)
 {
@@ -4106,6 +4114,7 @@ def_access_ibp_counter(rc_crwaits);
 static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
 [C_RCV_OVF] = RXE32_DEV_CNTR_ELEM(RcvOverflow, RCV_BUF_OVFL_CNT, CNTR_SYNTH),
 [C_RX_LEN_ERR] = RXE32_DEV_CNTR_ELEM(RxLenErr, RCV_LENGTH_ERR_CNT, CNTR_SYNTH),
+[C_RX_SHORT_ERR] = RXE32_DEV_CNTR_ELEM(RxShrErr, RCV_SHORT_ERR_CNT, CNTR_SYNTH),
 [C_RX_ICRC_ERR] = RXE32_DEV_CNTR_ELEM(RxICrcErr, RCV_ICRC_ERR_CNT, CNTR_SYNTH),
 [C_RX_EBP] = RXE32_DEV_CNTR_ELEM(RxEbpCnt, RCV_EBP_CNT, CNTR_SYNTH),
 [C_RX_TID_FULL] = RXE32_DEV_CNTR_ELEM(RxTIDFullEr, RCV_TID_FULL_ERR_CNT,
@@ -4249,6 +4258,8 @@ static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
 			    access_sw_cpu_intr),
 [C_SW_CPU_RCV_LIM] = CNTR_ELEM("RcvLimit", 0, 0, CNTR_NORMAL,
 			    access_sw_cpu_rcv_limit),
+[C_SW_CTX0_SEQ_DROP] = CNTR_ELEM("SeqDrop0", 0, 0, CNTR_NORMAL,
+			    access_sw_ctx0_seq_drop),
 [C_SW_VTX_WAIT] = CNTR_ELEM("vTxWait", 0, 0, CNTR_NORMAL,
 			    access_sw_vtx_wait),
 [C_SW_PIO_WAIT] = CNTR_ELEM("PioWait", 0, 0, CNTR_NORMAL,
@@ -6862,7 +6873,7 @@ static void rxe_kernel_unfreeze(struct hfi1_devdata *dd)
 		}
 		rcvmask = HFI1_RCVCTRL_CTXT_ENB;
 		/* HFI1_RCVCTRL_TAILUPD_[ENB|DIS] needs to be set explicitly */
-		rcvmask |= rcd->rcvhdrtail_kvaddr ?
+		rcvmask |= hfi1_rcvhdrtail_kvaddr(rcd) ?
 			HFI1_RCVCTRL_TAILUPD_ENB : HFI1_RCVCTRL_TAILUPD_DIS;
 		hfi1_rcvctrl(dd, rcvmask, rcd);
 		hfi1_rcd_put(rcd);
@@ -8394,20 +8405,62 @@ void force_recv_intr(struct hfi1_ctxtdata *rcd)
 static inline int check_packet_present(struct hfi1_ctxtdata *rcd)
 {
 	u32 tail;
-	int present;
 
-	if (!rcd->rcvhdrtail_kvaddr)
-		present = (rcd->seq_cnt ==
-				rhf_rcv_seq(rhf_to_cpu(get_rhf_addr(rcd))));
-	else /* is RDMA rtail */
-		present = (rcd->head != get_rcvhdrtail(rcd));
-
-	if (present)
+	if (hfi1_packet_present(rcd))
 		return 1;
 
 	/* fall back to a CSR read, correct indpendent of DMA_RTAIL */
 	tail = (u32)read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL);
-	return rcd->head != tail;
+	return hfi1_rcd_head(rcd) != tail;
+}
+
+/**
+ * Common code for receive contexts interrupt handlers.
+ * Update traces, increment kernel IRQ counter and
+ * setup ASPM when needed.
+ */
+static void receive_interrupt_common(struct hfi1_ctxtdata *rcd)
+{
+	struct hfi1_devdata *dd = rcd->dd;
+
+	trace_hfi1_receive_interrupt(dd, rcd);
+	this_cpu_inc(*dd->int_counter);
+	aspm_ctx_disable(rcd);
+}
+
+/**
+ * __hfi1_rcd_eoi_intr() - Make HW issue receive interrupt
+ * when there are packets present in the queue. When calling
+ * with interrupts enabled please use hfi1_rcd_eoi_intr.
+ *
+ * @rcd: valid receive context
+ */
+static void __hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
+{
+	clear_recv_intr(rcd);
+	if (check_packet_present(rcd))
+		force_recv_intr(rcd);
+}
+
+/**
+ * hfi1_rcd_eoi_intr() - End of Interrupt processing action
+ *
+ * @rcd: Ptr to hfi1_ctxtdata of receive context
+ *
+ *  Hold IRQs so we can safely clear the interrupt and
+ *  recheck for a packet that may have arrived after the previous
+ *  check and the interrupt clear.  If a packet arrived, force another
+ *  interrupt. This routine can be called at the end of receive packet
+ *  processing in interrupt service routines, interrupt service thread
+ *  and softirqs
+ */
+static void hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__hfi1_rcd_eoi_intr(rcd);
+	local_irq_restore(flags);
 }
 
 /*
@@ -8421,13 +8474,9 @@ static inline int check_packet_present(struct hfi1_ctxtdata *rcd)
 irqreturn_t receive_context_interrupt(int irq, void *data)
 {
 	struct hfi1_ctxtdata *rcd = data;
-	struct hfi1_devdata *dd = rcd->dd;
 	int disposition;
-	int present;
 
-	trace_hfi1_receive_interrupt(dd, rcd);
-	this_cpu_inc(*dd->int_counter);
-	aspm_ctx_disable(rcd);
+	receive_interrupt_common(rcd);
 
 	/* receive interrupt remains blocked while processing packets */
 	disposition = rcd->do_interrupt(rcd, 0);
@@ -8440,17 +8489,7 @@ irqreturn_t receive_context_interrupt(int irq, void *data)
 	if (disposition == RCV_PKT_LIMIT)
 		return IRQ_WAKE_THREAD;
 
-	/*
-	 * The packet processor detected no more packets.  Clear the receive
-	 * interrupt and recheck for a packet packet that may have arrived
-	 * after the previous check and interrupt clear.  If a packet arrived,
-	 * force another interrupt.
-	 */
-	clear_recv_intr(rcd);
-	present = check_packet_present(rcd);
-	if (present)
-		force_recv_intr(rcd);
-
+	__hfi1_rcd_eoi_intr(rcd);
 	return IRQ_HANDLED;
 }
 
@@ -8461,24 +8500,11 @@ irqreturn_t receive_context_interrupt(int irq, void *data)
 irqreturn_t receive_context_thread(int irq, void *data)
 {
 	struct hfi1_ctxtdata *rcd = data;
-	int present;
 
 	/* receive interrupt is still blocked from the IRQ handler */
 	(void)rcd->do_interrupt(rcd, 1);
 
-	/*
-	 * The packet processor will only return if it detected no more
-	 * packets.  Hold IRQs here so we can safely clear the interrupt and
-	 * recheck for a packet that may have arrived after the previous
-	 * check and the interrupt clear.  If a packet arrived, force another
-	 * interrupt.
-	 */
-	local_irq_disable();
-	clear_recv_intr(rcd);
-	present = check_packet_present(rcd);
-	if (present)
-		force_recv_intr(rcd);
-	local_irq_enable();
+	hfi1_rcd_eoi_intr(rcd);
 
 	return IRQ_HANDLED;
 }
@@ -10049,7 +10075,7 @@ u32 lrh_max_header_bytes(struct hfi1_devdata *dd)
 	 * the first kernel context would have been allocated by now so
 	 * we are guaranteed a valid value.
 	 */
-	return (dd->rcd[0]->rcvhdrqentsize - 2/*PBC/RHF*/ + 1/*ICRC*/) << 2;
+	return (get_hdrqentsize(dd->rcd[0]) - 2/*PBC/RHF*/ + 1/*ICRC*/) << 2;
 }
 
 /*
@@ -10094,7 +10120,7 @@ static void set_send_length(struct hfi1_pportdata *ppd)
 		thres = min(sc_percent_to_threshold(dd->vld[i].sc, 50),
 			    sc_mtu_to_threshold(dd->vld[i].sc,
 						dd->vld[i].mtu,
-						dd->rcd[0]->rcvhdrqentsize));
+						get_hdrqentsize(dd->rcd[0])));
 		for (j = 0; j < INIT_SC_PER_VL; j++)
 			sc_set_cr_threshold(
 					pio_select_send_context_vl(dd, j, i),
@@ -11821,7 +11847,7 @@ u32 hdrqempty(struct hfi1_ctxtdata *rcd)
 	head = (read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_HEAD)
 		& RCV_HDR_HEAD_HEAD_SMASK) >> RCV_HDR_HEAD_HEAD_SHIFT;
 
-	if (rcd->rcvhdrtail_kvaddr)
+	if (hfi1_rcvhdrtail_kvaddr(rcd))
 		tail = get_rcvhdrtail(rcd);
 	else
 		tail = read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL);
@@ -11865,6 +11891,84 @@ static u32 encoded_size(u32 size)
 	return 0x1;	/* if invalid, go with the minimum size */
 }
 
+/**
+ * encode_rcv_header_entry_size - return chip specific encoding for size
+ * @size: size in dwords
+ *
+ * Convert a receive header entry size that to the encoding used in the CSR.
+ *
+ * Return a zero if the given size is invalid, otherwise the encoding.
+ */
+u8 encode_rcv_header_entry_size(u8 size)
+{
+	/* there are only 3 valid receive header entry sizes */
+	if (size == 2)
+		return 1;
+	if (size == 16)
+		return 2;
+	if (size == 32)
+		return 4;
+	return 0; /* invalid */
+}
+
+/**
+ * hfi1_validate_rcvhdrcnt - validate hdrcnt
+ * @dd: the device data
+ * @thecnt: the header count
+ */
+int hfi1_validate_rcvhdrcnt(struct hfi1_devdata *dd, uint thecnt)
+{
+	if (thecnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) {
+		dd_dev_err(dd, "Receive header queue count too small\n");
+		return -EINVAL;
+	}
+
+	if (thecnt > HFI1_MAX_HDRQ_EGRBUF_CNT) {
+		dd_dev_err(dd,
+			   "Receive header queue count cannot be greater than %u\n",
+			   HFI1_MAX_HDRQ_EGRBUF_CNT);
+		return -EINVAL;
+	}
+
+	if (thecnt % HDRQ_INCREMENT) {
+		dd_dev_err(dd, "Receive header queue count %d must be divisible by %lu\n",
+			   thecnt, HDRQ_INCREMENT);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * set_hdrq_regs - set header queue registers for context
+ * @dd: the device data
+ * @ctxt: the context
+ * @entsize: the dword entry size
+ * @hdrcnt: the number of header entries
+ */
+void set_hdrq_regs(struct hfi1_devdata *dd, u8 ctxt, u8 entsize, u16 hdrcnt)
+{
+	u64 reg;
+
+	reg = (((u64)hdrcnt >> HDRQ_SIZE_SHIFT) & RCV_HDR_CNT_CNT_MASK) <<
+	      RCV_HDR_CNT_CNT_SHIFT;
+	write_kctxt_csr(dd, ctxt, RCV_HDR_CNT, reg);
+	reg = ((u64)encode_rcv_header_entry_size(entsize) &
+	       RCV_HDR_ENT_SIZE_ENT_SIZE_MASK) <<
+	      RCV_HDR_ENT_SIZE_ENT_SIZE_SHIFT;
+	write_kctxt_csr(dd, ctxt, RCV_HDR_ENT_SIZE, reg);
+	reg = ((u64)DEFAULT_RCVHDRSIZE & RCV_HDR_SIZE_HDR_SIZE_MASK) <<
+	      RCV_HDR_SIZE_HDR_SIZE_SHIFT;
+	write_kctxt_csr(dd, ctxt, RCV_HDR_SIZE, reg);
+
+	/*
+	 * Program dummy tail address for every receive context
+	 * before enabling any receive context
+	 */
+	write_kctxt_csr(dd, ctxt, RCV_HDR_TAIL_ADDR,
+			dd->rcvhdrtail_dummy_dma);
+}
+
 void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
 		  struct hfi1_ctxtdata *rcd)
 {
@@ -11886,13 +11990,13 @@ void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
 		/* reset the tail and hdr addresses, and sequence count */
 		write_kctxt_csr(dd, ctxt, RCV_HDR_ADDR,
 				rcd->rcvhdrq_dma);
-		if (rcd->rcvhdrtail_kvaddr)
+		if (hfi1_rcvhdrtail_kvaddr(rcd))
 			write_kctxt_csr(dd, ctxt, RCV_HDR_TAIL_ADDR,
 					rcd->rcvhdrqtailaddr_dma);
-		rcd->seq_cnt = 1;
+		hfi1_set_seq_cnt(rcd, 1);
 
 		/* reset the cached receive header queue head value */
-		rcd->head = 0;
+		hfi1_set_rcd_head(rcd, 0);
 
 		/*
 		 * Zero the receive header queue so we don't get false
@@ -11972,7 +12076,7 @@ void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
 			      IS_RCVAVAIL_START + rcd->ctxt, false);
 		rcvctrl &= ~RCV_CTXT_CTRL_INTR_AVAIL_SMASK;
 	}
-	if ((op & HFI1_RCVCTRL_TAILUPD_ENB) && rcd->rcvhdrtail_kvaddr)
+	if ((op & HFI1_RCVCTRL_TAILUPD_ENB) && hfi1_rcvhdrtail_kvaddr(rcd))
 		rcvctrl |= RCV_CTXT_CTRL_TAIL_UPD_SMASK;
 	if (op & HFI1_RCVCTRL_TAILUPD_DIS) {
 		/* See comment on RcvCtxtCtrl.TailUpd above */
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index 4ca5ac8d7e9e..725509261016 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -358,6 +358,8 @@
 #define MAX_EAGER_BUFFER       (256 * 1024)
 #define MAX_EAGER_BUFFER_TOTAL (64 * (1 << 20)) /* max per ctxt 64MB */
 #define MAX_EXPECTED_BUFFER    (2048 * 1024)
+#define HFI1_MIN_HDRQ_EGRBUF_CNT 32
+#define HFI1_MAX_HDRQ_EGRBUF_CNT 16352
 
 /*
  * Receive expected base and count and eager base and count increment -
@@ -699,6 +701,10 @@ static inline u32 chip_rcv_array_count(struct hfi1_devdata *dd)
 	return read_csr(dd, RCV_ARRAY_CNT);
 }
 
+u8 encode_rcv_header_entry_size(u8 size);
+int hfi1_validate_rcvhdrcnt(struct hfi1_devdata *dd, uint thecnt);
+void set_hdrq_regs(struct hfi1_devdata *dd, u8 ctxt, u8 entsize, u16 hdrcnt);
+
 u64 create_pbc(struct hfi1_pportdata *ppd, u64 flags, int srate_mbs, u32 vl,
 	       u32 dw_len);
 
@@ -859,6 +865,7 @@ static inline int idx_from_vl(int vl)
 enum {
 	C_RCV_OVF = 0,
 	C_RX_LEN_ERR,
+	C_RX_SHORT_ERR,
 	C_RX_ICRC_ERR,
 	C_RX_EBP,
 	C_RX_TID_FULL,
@@ -926,6 +933,7 @@ enum {
 	C_DC_PG_STS_TX_MBE_CNT,
 	C_SW_CPU_INTR,
 	C_SW_CPU_RCV_LIM,
+	C_SW_CTX0_SEQ_DROP,
 	C_SW_VTX_WAIT,
 	C_SW_PIO_WAIT,
 	C_SW_PIO_DRAIN,
diff --git a/drivers/infiniband/hw/hfi1/chip_registers.h b/drivers/infiniband/hw/hfi1/chip_registers.h
index ab3589d17aee..fb3ec9bff7a2 100644
--- a/drivers/infiniband/hw/hfi1/chip_registers.h
+++ b/drivers/infiniband/hw/hfi1/chip_registers.h
@@ -381,6 +381,7 @@
 #define DC_LCB_STS_LINK_TRANSFER_ACTIVE (DC_LCB_CSRS + 0x000000000468)
 #define DC_LCB_STS_ROUND_TRIP_LTP_CNT (DC_LCB_CSRS + 0x0000000004B0)
 #define RCV_LENGTH_ERR_CNT 0
+#define RCV_SHORT_ERR_CNT 2
 #define RCV_ICRC_ERR_CNT 6
 #define RCV_EBP_CNT 9
 #define RCV_BUF_OVFL_CNT 10
diff --git a/drivers/infiniband/hw/hfi1/common.h b/drivers/infiniband/hw/hfi1/common.h
index d47da7b0438f..40a1ff0c8a8e 100644
--- a/drivers/infiniband/hw/hfi1/common.h
+++ b/drivers/infiniband/hw/hfi1/common.h
@@ -323,6 +323,9 @@ struct diag_pkt {
 /* RHF receive type error - bypass packet errors */
 #define RHF_RTE_BYPASS_NO_ERR		0x0
 
+/* MAX RcvSEQ */
+#define RHF_MAX_SEQ 13
+
 /* IB - LRH header constants */
 #define HFI1_LRH_GRH 0x0003      /* 1. word of IB LRH - next header: GRH */
 #define HFI1_LRH_BTH 0x0002      /* 1. word of IB LRH - next header: BTH */
diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index d268bf9c42ee..4633a0ce1a8c 100644
--- a/drivers/infiniband/hw/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
@@ -379,7 +379,7 @@ static void *_rcds_seq_next(struct seq_file *s, void *v, loff_t *pos)
 	struct hfi1_devdata *dd = dd_from_dev(ibd);
 
 	++*pos;
-	if (!dd->rcd || *pos >= dd->n_krcv_queues)
+	if (!dd->rcd || *pos >= dd->num_rcv_contexts)
 		return NULL;
 	return pos;
 }
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 01aa1f132f55..049d15befe58 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -411,14 +411,14 @@ drop:
 static inline void init_packet(struct hfi1_ctxtdata *rcd,
 			       struct hfi1_packet *packet)
 {
-	packet->rsize = rcd->rcvhdrqentsize; /* words */
-	packet->maxcnt = rcd->rcvhdrq_cnt * packet->rsize; /* words */
+	packet->rsize = get_hdrqentsize(rcd); /* words */
+	packet->maxcnt = get_hdrq_cnt(rcd) * packet->rsize; /* words */
 	packet->rcd = rcd;
 	packet->updegr = 0;
 	packet->etail = -1;
 	packet->rhf_addr = get_rhf_addr(rcd);
 	packet->rhf = rhf_to_cpu(packet->rhf_addr);
-	packet->rhqoff = rcd->head;
+	packet->rhqoff = hfi1_rcd_head(rcd);
 	packet->numpkt = 0;
 }
 
@@ -551,22 +551,22 @@ static inline void init_ps_mdata(struct ps_mdata *mdata,
 	mdata->maxcnt = packet->maxcnt;
 	mdata->ps_head = packet->rhqoff;
 
-	if (HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL)) {
+	if (get_dma_rtail_setting(rcd)) {
 		mdata->ps_tail = get_rcvhdrtail(rcd);
 		if (rcd->ctxt == HFI1_CTRL_CTXT)
-			mdata->ps_seq = rcd->seq_cnt;
+			mdata->ps_seq = hfi1_seq_cnt(rcd);
 		else
 			mdata->ps_seq = 0; /* not used with DMA_RTAIL */
 	} else {
 		mdata->ps_tail = 0; /* used only with DMA_RTAIL*/
-		mdata->ps_seq = rcd->seq_cnt;
+		mdata->ps_seq = hfi1_seq_cnt(rcd);
 	}
 }
 
 static inline int ps_done(struct ps_mdata *mdata, u64 rhf,
 			  struct hfi1_ctxtdata *rcd)
 {
-	if (HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL))
+	if (get_dma_rtail_setting(rcd))
 		return mdata->ps_head == mdata->ps_tail;
 	return mdata->ps_seq != rhf_rcv_seq(rhf);
 }
@@ -592,11 +592,9 @@ static inline void update_ps_mdata(struct ps_mdata *mdata,
 		mdata->ps_head = 0;
 
 	/* Control context must do seq counting */
-	if (!HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL) ||
-	    (rcd->ctxt == HFI1_CTRL_CTXT)) {
-		if (++mdata->ps_seq > 13)
-			mdata->ps_seq = 1;
-	}
+	if (!get_dma_rtail_setting(rcd) ||
+	    rcd->ctxt == HFI1_CTRL_CTXT)
+		mdata->ps_seq = hfi1_seq_incr_wrap(mdata->ps_seq);
 }
 
 /*
@@ -734,6 +732,7 @@ static noinline int skip_rcv_packet(struct hfi1_packet *packet, int thread)
 {
 	int ret;
 
+	packet->rcd->dd->ctx0_seq_drop++;
 	/* Set up for the next packet */
 	packet->rhqoff += packet->rsize;
 	if (packet->rhqoff >= packet->maxcnt)
@@ -769,7 +768,7 @@ static inline int process_rcv_packet(struct hfi1_packet *packet, int thread)
 		 * The +2 is the size of the RHF.
 		 */
 		prefetch_range(packet->ebuf,
-			       packet->tlen - ((packet->rcd->rcvhdrqentsize -
+			       packet->tlen - ((get_hdrqentsize(packet->rcd) -
 					       (rhf_hdrq_offset(packet->rhf)
 						+ 2)) * 4));
 	}
@@ -823,7 +822,7 @@ static inline void finish_packet(struct hfi1_packet *packet)
 	 * The only thing we need to do is a final update and call for an
 	 * interrupt
 	 */
-	update_usrhead(packet->rcd, packet->rcd->head, packet->updegr,
+	update_usrhead(packet->rcd, hfi1_rcd_head(packet->rcd), packet->updegr,
 		       packet->etail, rcv_intr_dynamic, packet->numpkt);
 }
 
@@ -832,13 +831,11 @@ static inline void finish_packet(struct hfi1_packet *packet)
  */
 int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 {
-	u32 seq;
 	int last = RCV_PKT_OK;
 	struct hfi1_packet packet;
 
 	init_packet(rcd, &packet);
-	seq = rhf_rcv_seq(packet.rhf);
-	if (seq != rcd->seq_cnt) {
+	if (last_rcv_seq(rcd, rhf_rcv_seq(packet.rhf))) {
 		last = RCV_PKT_DONE;
 		goto bail;
 	}
@@ -847,15 +844,12 @@ int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 
 	while (last == RCV_PKT_OK) {
 		last = process_rcv_packet(&packet, thread);
-		seq = rhf_rcv_seq(packet.rhf);
-		if (++rcd->seq_cnt > 13)
-			rcd->seq_cnt = 1;
-		if (seq != rcd->seq_cnt)
+		if (hfi1_seq_incr(rcd, rhf_rcv_seq(packet.rhf)))
 			last = RCV_PKT_DONE;
 		process_rcv_update(last, &packet);
 	}
 	process_rcv_qp_work(&packet);
-	rcd->head = packet.rhqoff;
+	hfi1_set_rcd_head(rcd, packet.rhqoff);
 bail:
 	finish_packet(&packet);
 	return last;
@@ -884,15 +878,14 @@ int handle_receive_interrupt_dma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 		process_rcv_update(last, &packet);
 	}
 	process_rcv_qp_work(&packet);
-	rcd->head = packet.rhqoff;
+	hfi1_set_rcd_head(rcd, packet.rhqoff);
 bail:
 	finish_packet(&packet);
 	return last;
 }
 
-static inline void set_nodma_rtail(struct hfi1_devdata *dd, u16 ctxt)
+static void set_all_fastpath(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 {
-	struct hfi1_ctxtdata *rcd;
 	u16 i;
 
 	/*
@@ -900,50 +893,17 @@ static inline void set_nodma_rtail(struct hfi1_devdata *dd, u16 ctxt)
 	 * interrupt handler only for that context. Otherwise, switch
 	 * interrupt handler for all statically allocated kernel contexts.
 	 */
-	if (ctxt >= dd->first_dyn_alloc_ctxt) {
-		rcd = hfi1_rcd_get_by_index_safe(dd, ctxt);
-		if (rcd) {
-			rcd->do_interrupt =
-				&handle_receive_interrupt_nodma_rtail;
-			hfi1_rcd_put(rcd);
-		}
-		return;
-	}
-
-	for (i = HFI1_CTRL_CTXT + 1; i < dd->first_dyn_alloc_ctxt; i++) {
-		rcd = hfi1_rcd_get_by_index(dd, i);
-		if (rcd)
-			rcd->do_interrupt =
-				&handle_receive_interrupt_nodma_rtail;
+	if (rcd->ctxt >= dd->first_dyn_alloc_ctxt && !rcd->is_vnic) {
+		hfi1_rcd_get(rcd);
+		hfi1_set_fast(rcd);
 		hfi1_rcd_put(rcd);
-	}
-}
-
-static inline void set_dma_rtail(struct hfi1_devdata *dd, u16 ctxt)
-{
-	struct hfi1_ctxtdata *rcd;
-	u16 i;
-
-	/*
-	 * For dynamically allocated kernel contexts (like vnic) switch
-	 * interrupt handler only for that context. Otherwise, switch
-	 * interrupt handler for all statically allocated kernel contexts.
-	 */
-	if (ctxt >= dd->first_dyn_alloc_ctxt) {
-		rcd = hfi1_rcd_get_by_index_safe(dd, ctxt);
-		if (rcd) {
-			rcd->do_interrupt =
-				&handle_receive_interrupt_dma_rtail;
-			hfi1_rcd_put(rcd);
-		}
 		return;
 	}
 
-	for (i = HFI1_CTRL_CTXT + 1; i < dd->first_dyn_alloc_ctxt; i++) {
+	for (i = HFI1_CTRL_CTXT + 1; i < dd->num_rcv_contexts; i++) {
 		rcd = hfi1_rcd_get_by_index(dd, i);
-		if (rcd)
-			rcd->do_interrupt =
-				&handle_receive_interrupt_dma_rtail;
+		if (rcd && (i < dd->first_dyn_alloc_ctxt || rcd->is_vnic))
+			hfi1_set_fast(rcd);
 		hfi1_rcd_put(rcd);
 	}
 }
@@ -959,17 +919,14 @@ void set_all_slowpath(struct hfi1_devdata *dd)
 		if (!rcd)
 			continue;
 		if (i < dd->first_dyn_alloc_ctxt || rcd->is_vnic)
-			rcd->do_interrupt = &handle_receive_interrupt;
+			rcd->do_interrupt = rcd->slow_handler;
 
 		hfi1_rcd_put(rcd);
 	}
 }
 
-static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd,
-				      struct hfi1_packet *packet,
-				      struct hfi1_devdata *dd)
+static bool __set_armed_to_active(struct hfi1_packet *packet)
 {
-	struct work_struct *lsaw = &rcd->ppd->linkstate_active_work;
 	u8 etype = rhf_rcv_type(packet->rhf);
 	u8 sc = SC15_PACKET;
 
@@ -984,19 +941,34 @@ static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd,
 		sc = hfi1_16B_get_sc(hdr);
 	}
 	if (sc != SC15_PACKET) {
-		int hwstate = driver_lstate(rcd->ppd);
+		int hwstate = driver_lstate(packet->rcd->ppd);
+		struct work_struct *lsaw =
+				&packet->rcd->ppd->linkstate_active_work;
 
 		if (hwstate != IB_PORT_ACTIVE) {
-			dd_dev_info(dd,
+			dd_dev_info(packet->rcd->dd,
 				    "Unexpected link state %s\n",
 				    opa_lstate_name(hwstate));
-			return 0;
+			return false;
 		}
 
-		queue_work(rcd->ppd->link_wq, lsaw);
-		return 1;
+		queue_work(packet->rcd->ppd->link_wq, lsaw);
+		return true;
 	}
-	return 0;
+	return false;
+}
+
+/**
+ * armed to active - the fast path for armed to active
+ * @packet: the packet structure
+ *
+ * Return true if packet processing needs to bail.
+ */
+static bool set_armed_to_active(struct hfi1_packet *packet)
+{
+	if (likely(packet->rcd->ppd->host_link_state != HLS_UP_ARMED))
+		return false;
+	return __set_armed_to_active(packet);
 }
 
 /*
@@ -1019,10 +991,8 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 
 	init_packet(rcd, &packet);
 
-	if (!HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL)) {
-		u32 seq = rhf_rcv_seq(packet.rhf);
-
-		if (seq != rcd->seq_cnt) {
+	if (!get_dma_rtail_setting(rcd)) {
+		if (last_rcv_seq(rcd, rhf_rcv_seq(packet.rhf))) {
 			last = RCV_PKT_DONE;
 			goto bail;
 		}
@@ -1039,22 +1009,15 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 		 * Control context can potentially receive an invalid
 		 * rhf. Drop such packets.
 		 */
-		if (rcd->ctxt == HFI1_CTRL_CTXT) {
-			u32 seq = rhf_rcv_seq(packet.rhf);
-
-			if (seq != rcd->seq_cnt)
+		if (rcd->ctxt == HFI1_CTRL_CTXT)
+			if (last_rcv_seq(rcd, rhf_rcv_seq(packet.rhf)))
 				skip_pkt = 1;
-		}
 	}
 
 	prescan_rxq(rcd, &packet);
 
 	while (last == RCV_PKT_OK) {
-		if (unlikely(dd->do_drop &&
-			     atomic_xchg(&dd->drop_packet, DROP_PACKET_OFF) ==
-			     DROP_PACKET_ON)) {
-			dd->do_drop = 0;
-
+		if (hfi1_need_drop(dd)) {
 			/* On to the next packet */
 			packet.rhqoff += packet.rsize;
 			packet.rhf_addr = (__le32 *)rcd->rcvhdrq +
@@ -1066,26 +1029,14 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 			last = skip_rcv_packet(&packet, thread);
 			skip_pkt = 0;
 		} else {
-			/* Auto activate link on non-SC15 packet receive */
-			if (unlikely(rcd->ppd->host_link_state ==
-				     HLS_UP_ARMED) &&
-			    set_armed_to_active(rcd, &packet, dd))
+			if (set_armed_to_active(&packet))
 				goto bail;
 			last = process_rcv_packet(&packet, thread);
 		}
 
-		if (!HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL)) {
-			u32 seq = rhf_rcv_seq(packet.rhf);
-
-			if (++rcd->seq_cnt > 13)
-				rcd->seq_cnt = 1;
-			if (seq != rcd->seq_cnt)
+		if (!get_dma_rtail_setting(rcd)) {
+			if (hfi1_seq_incr(rcd, rhf_rcv_seq(packet.rhf)))
 				last = RCV_PKT_DONE;
-			if (needset) {
-				dd_dev_info(dd, "Switching to NO_DMA_RTAIL\n");
-				set_nodma_rtail(dd, rcd->ctxt);
-				needset = 0;
-			}
 		} else {
 			if (packet.rhqoff == hdrqtail)
 				last = RCV_PKT_DONE;
@@ -1094,27 +1045,24 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 			 * rhf. Drop such packets.
 			 */
 			if (rcd->ctxt == HFI1_CTRL_CTXT) {
-				u32 seq = rhf_rcv_seq(packet.rhf);
+				bool lseq;
 
-				if (++rcd->seq_cnt > 13)
-					rcd->seq_cnt = 1;
-				if (!last && (seq != rcd->seq_cnt))
+				lseq = hfi1_seq_incr(rcd,
+						     rhf_rcv_seq(packet.rhf));
+				if (!last && lseq)
 					skip_pkt = 1;
 			}
-
-			if (needset) {
-				dd_dev_info(dd,
-					    "Switching to DMA_RTAIL\n");
-				set_dma_rtail(dd, rcd->ctxt);
-				needset = 0;
-			}
 		}
 
+		if (needset) {
+			needset = false;
+			set_all_fastpath(dd, rcd);
+		}
 		process_rcv_update(last, &packet);
 	}
 
 	process_rcv_qp_work(&packet);
-	rcd->head = packet.rhqoff;
+	hfi1_set_rcd_head(rcd, packet.rhqoff);
 
 bail:
 	/*
@@ -1606,23 +1554,22 @@ void handle_eflags(struct hfi1_packet *packet)
  * The following functions are called by the interrupt handler. They are type
  * specific handlers for each packet type.
  */
-static int process_receive_ib(struct hfi1_packet *packet)
+static void process_receive_ib(struct hfi1_packet *packet)
 {
 	if (hfi1_setup_9B_packet(packet))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	if (unlikely(hfi1_dbg_should_fault_rx(packet)))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	trace_hfi1_rcvhdr(packet);
 
 	if (unlikely(rhf_err_flags(packet->rhf))) {
 		handle_eflags(packet);
-		return RHF_RCV_CONTINUE;
+		return;
 	}
 
 	hfi1_ib_rcv(packet);
-	return RHF_RCV_CONTINUE;
 }
 
 static inline bool hfi1_is_vnic_packet(struct hfi1_packet *packet)
@@ -1638,23 +1585,23 @@ static inline bool hfi1_is_vnic_packet(struct hfi1_packet *packet)
 	return false;
 }
 
-static int process_receive_bypass(struct hfi1_packet *packet)
+static void process_receive_bypass(struct hfi1_packet *packet)
 {
 	struct hfi1_devdata *dd = packet->rcd->dd;
 
 	if (hfi1_is_vnic_packet(packet)) {
 		hfi1_vnic_bypass_rcv(packet);
-		return RHF_RCV_CONTINUE;
+		return;
 	}
 
 	if (hfi1_setup_bypass_packet(packet))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	trace_hfi1_rcvhdr(packet);
 
 	if (unlikely(rhf_err_flags(packet->rhf))) {
 		handle_eflags(packet);
-		return RHF_RCV_CONTINUE;
+		return;
 	}
 
 	if (hfi1_16B_get_l2(packet->hdr) == 0x2) {
@@ -1677,17 +1624,16 @@ static int process_receive_bypass(struct hfi1_packet *packet)
 				(OPA_EI_STATUS_SMASK | BAD_L2_ERR);
 		}
 	}
-	return RHF_RCV_CONTINUE;
 }
 
-static int process_receive_error(struct hfi1_packet *packet)
+static void process_receive_error(struct hfi1_packet *packet)
 {
 	/* KHdrHCRCErr -- KDETH packet with a bad HCRC */
 	if (unlikely(
 		 hfi1_dbg_fault_suppress_err(&packet->rcd->dd->verbs_dev) &&
 		 (rhf_rcv_type_err(packet->rhf) == RHF_RCV_TYPE_ERROR ||
 		  packet->rhf & RHF_DC_ERR)))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	hfi1_setup_ib_header(packet);
 	handle_eflags(packet);
@@ -1695,32 +1641,29 @@ static int process_receive_error(struct hfi1_packet *packet)
 	if (unlikely(rhf_err_flags(packet->rhf)))
 		dd_dev_err(packet->rcd->dd,
 			   "Unhandled error packet received. Dropping.\n");
-
-	return RHF_RCV_CONTINUE;
 }
 
-static int kdeth_process_expected(struct hfi1_packet *packet)
+static void kdeth_process_expected(struct hfi1_packet *packet)
 {
 	hfi1_setup_9B_packet(packet);
 	if (unlikely(hfi1_dbg_should_fault_rx(packet)))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	if (unlikely(rhf_err_flags(packet->rhf))) {
 		struct hfi1_ctxtdata *rcd = packet->rcd;
 
 		if (hfi1_handle_kdeth_eflags(rcd, rcd->ppd, packet))
-			return RHF_RCV_CONTINUE;
+			return;
 	}
 
 	hfi1_kdeth_expected_rcv(packet);
-	return RHF_RCV_CONTINUE;
 }
 
-static int kdeth_process_eager(struct hfi1_packet *packet)
+static void kdeth_process_eager(struct hfi1_packet *packet)
 {
 	hfi1_setup_9B_packet(packet);
 	if (unlikely(hfi1_dbg_should_fault_rx(packet)))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	trace_hfi1_rcvhdr(packet);
 	if (unlikely(rhf_err_flags(packet->rhf))) {
@@ -1728,37 +1671,41 @@ static int kdeth_process_eager(struct hfi1_packet *packet)
 
 		show_eflags_errs(packet);
 		if (hfi1_handle_kdeth_eflags(rcd, rcd->ppd, packet))
-			return RHF_RCV_CONTINUE;
+			return;
 	}
 
 	hfi1_kdeth_eager_rcv(packet);
-	return RHF_RCV_CONTINUE;
 }
 
-static int process_receive_invalid(struct hfi1_packet *packet)
+static void process_receive_invalid(struct hfi1_packet *packet)
 {
 	dd_dev_err(packet->rcd->dd, "Invalid packet type %d. Dropping\n",
 		   rhf_rcv_type(packet->rhf));
-	return RHF_RCV_CONTINUE;
 }
 
+#define HFI1_RCVHDR_DUMP_MAX	5
+
 void seqfile_dump_rcd(struct seq_file *s, struct hfi1_ctxtdata *rcd)
 {
 	struct hfi1_packet packet;
 	struct ps_mdata mdata;
+	int i;
 
-	seq_printf(s, "Rcd %u: RcvHdr cnt %u entsize %u %s head %llu tail %llu\n",
-		   rcd->ctxt, rcd->rcvhdrq_cnt, rcd->rcvhdrqentsize,
-		   HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL) ?
+	seq_printf(s, "Rcd %u: RcvHdr cnt %u entsize %u %s ctrl 0x%08llx status 0x%08llx, head %llu tail %llu  sw head %u\n",
+		   rcd->ctxt, get_hdrq_cnt(rcd), get_hdrqentsize(rcd),
+		   get_dma_rtail_setting(rcd) ?
 		   "dma_rtail" : "nodma_rtail",
+		   read_kctxt_csr(rcd->dd, rcd->ctxt, RCV_CTXT_CTRL),
+		   read_kctxt_csr(rcd->dd, rcd->ctxt, RCV_CTXT_STATUS),
 		   read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_HEAD) &
 		   RCV_HDR_HEAD_HEAD_MASK,
-		   read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL));
+		   read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL),
+		   rcd->head);
 
 	init_packet(rcd, &packet);
 	init_ps_mdata(&mdata, &packet);
 
-	while (1) {
+	for (i = 0; i < HFI1_RCVHDR_DUMP_MAX; i++) {
 		__le32 *rhf_addr = (__le32 *)rcd->rcvhdrq + mdata.ps_head +
 					 rcd->rhf_offset;
 		struct ib_header *hdr;
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 7c5e3fb22413..bef6946861b2 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -505,12 +505,12 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma)
 			ret = -EINVAL;
 			goto done;
 		}
-		if ((flags & VM_WRITE) || !uctxt->rcvhdrtail_kvaddr) {
+		if ((flags & VM_WRITE) || !hfi1_rcvhdrtail_kvaddr(uctxt)) {
 			ret = -EPERM;
 			goto done;
 		}
 		memlen = PAGE_SIZE;
-		memvirt = (void *)uctxt->rcvhdrtail_kvaddr;
+		memvirt = (void *)hfi1_rcvhdrtail_kvaddr(uctxt);
 		flags &= ~VM_MAYWRITE;
 		break;
 	case SUBCTXT_UREGS:
@@ -1090,7 +1090,7 @@ static void user_init(struct hfi1_ctxtdata *uctxt)
 	 * don't have to wait to be sure the DMA update has happened
 	 * (chip resets head/tail to 0 on transition to enable).
 	 */
-	if (uctxt->rcvhdrtail_kvaddr)
+	if (hfi1_rcvhdrtail_kvaddr(uctxt))
 		clear_rcvhdrtail(uctxt);
 
 	/* Setup J_KEY before enabling the context */
@@ -1154,8 +1154,8 @@ static int get_ctxt_info(struct hfi1_filedata *fd, unsigned long arg, u32 len)
 	cinfo.send_ctxt = uctxt->sc->hw_context;
 
 	cinfo.egrtids = uctxt->egrbufs.alloced;
-	cinfo.rcvhdrq_cnt = uctxt->rcvhdrq_cnt;
-	cinfo.rcvhdrq_entsize = uctxt->rcvhdrqentsize << 2;
+	cinfo.rcvhdrq_cnt = get_hdrq_cnt(uctxt);
+	cinfo.rcvhdrq_entsize = get_hdrqentsize(uctxt) << 2;
 	cinfo.sdma_ring_size = fd->cq->nentries;
 	cinfo.rcvegr_size = uctxt->egrbufs.rcvtid_size;
 
@@ -1543,7 +1543,7 @@ static int manage_rcvq(struct hfi1_ctxtdata *uctxt, u16 subctxt,
 		 * always resets it's tail register back to 0 on a
 		 * transition from disabled to enabled.
 		 */
-		if (uctxt->rcvhdrtail_kvaddr)
+		if (hfi1_rcvhdrtail_kvaddr(uctxt))
 			clear_rcvhdrtail(uctxt);
 		rcvctrl_op = HFI1_RCVCTRL_CTXT_ENB;
 	} else {
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index fc10d65fc3e1..6365e8ffed9d 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -197,7 +197,9 @@ struct exp_tid_set {
 	u32 count;
 };
 
-typedef int (*rhf_rcv_function_ptr)(struct hfi1_packet *packet);
+struct hfi1_ctxtdata;
+typedef int (*intr_handler)(struct hfi1_ctxtdata *rcd, int data);
+typedef void (*rhf_rcv_function_ptr)(struct hfi1_packet *packet);
 
 struct tid_queue {
 	struct list_head queue_head;
@@ -226,7 +228,11 @@ struct hfi1_ctxtdata {
 	 * be valid. Worst case is we process an extra interrupt and up to 64
 	 * packets with the wrong interrupt handler.
 	 */
-	int (*do_interrupt)(struct hfi1_ctxtdata *rcd, int threaded);
+	intr_handler do_interrupt;
+	/** fast handler after autoactive */
+	intr_handler fast_handler;
+	/** slow handler */
+	intr_handler slow_handler;
 	/* verbs rx_stats per rcd */
 	struct hfi1_opcode_stats_perctx *opstats;
 	/* clear interrupt mask */
@@ -1153,6 +1159,8 @@ struct hfi1_devdata {
 
 	char *boardname; /* human readable board info */
 
+	u64 ctx0_seq_drop;
+
 	/* reset value */
 	u64 z_int_counter;
 	u64 z_rcv_limit;
@@ -1310,7 +1318,7 @@ struct hfi1_devdata {
 	struct err_info_constraint err_info_xmit_constraint;
 
 	atomic_t drop_packet;
-	u8 do_drop;
+	bool do_drop;
 	u8 err_info_uncorrectable;
 	u8 err_info_fmconfig;
 
@@ -1507,12 +1515,148 @@ void hfi1_make_ud_req_16B(struct rvt_qp *qp,
 #define RCV_PKT_LIMIT   0x1 /* stop, hit limit, start thread */
 #define RCV_PKT_DONE    0x2 /* stop, no more packets detected */
 
+/**
+ * hfi1_rcd_head - add accessor for rcd head
+ * @rcd: the context
+ */
+static inline u32 hfi1_rcd_head(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->head;
+}
+
+/**
+ * hfi1_set_rcd_head - add accessor for rcd head
+ * @rcd: the context
+ * @head: the new head
+ */
+static inline void hfi1_set_rcd_head(struct hfi1_ctxtdata *rcd, u32 head)
+{
+	rcd->head = head;
+}
+
 /* calculate the current RHF address */
 static inline __le32 *get_rhf_addr(struct hfi1_ctxtdata *rcd)
 {
 	return (__le32 *)rcd->rcvhdrq + rcd->head + rcd->rhf_offset;
 }
 
+/* return DMA_RTAIL configuration */
+static inline bool get_dma_rtail_setting(struct hfi1_ctxtdata *rcd)
+{
+	return !!HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL);
+}
+
+/**
+ * hfi1_seq_incr_wrap - wrapping increment for sequence
+ * @seq: the current sequence number
+ *
+ * Returns: the incremented seq
+ */
+static inline u8 hfi1_seq_incr_wrap(u8 seq)
+{
+	if (++seq > RHF_MAX_SEQ)
+		seq = 1;
+	return seq;
+}
+
+/**
+ * hfi1_seq_cnt - return seq_cnt member
+ * @rcd: the receive context
+ *
+ * Return seq_cnt member
+ */
+static inline u8 hfi1_seq_cnt(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->seq_cnt;
+}
+
+/**
+ * hfi1_set_seq_cnt - return seq_cnt member
+ * @rcd: the receive context
+ *
+ * Return seq_cnt member
+ */
+static inline void hfi1_set_seq_cnt(struct hfi1_ctxtdata *rcd, u8 cnt)
+{
+	rcd->seq_cnt = cnt;
+}
+
+/**
+ * last_rcv_seq - is last
+ * @rcd: the receive context
+ * @seq: sequence
+ *
+ * return true if last packet
+ */
+static inline bool last_rcv_seq(struct hfi1_ctxtdata *rcd, u32 seq)
+{
+	return seq != rcd->seq_cnt;
+}
+
+/**
+ * rcd_seq_incr - increment context sequence number
+ * @rcd: the receive context
+ * @seq: the current sequence number
+ *
+ * Returns: true if the this was the last packet
+ */
+static inline bool hfi1_seq_incr(struct hfi1_ctxtdata *rcd, u32 seq)
+{
+	rcd->seq_cnt = hfi1_seq_incr_wrap(rcd->seq_cnt);
+	return last_rcv_seq(rcd, seq);
+}
+
+/**
+ * get_hdrqentsize - return hdrq entry size
+ * @rcd: the receive context
+ */
+static inline u8 get_hdrqentsize(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->rcvhdrqentsize;
+}
+
+/**
+ * get_hdrq_cnt - return hdrq count
+ * @rcd: the receive context
+ */
+static inline u16 get_hdrq_cnt(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->rcvhdrq_cnt;
+}
+
+/**
+ * hfi1_is_slowpath - check if this context is slow path
+ * @rcd: the receive context
+ */
+static inline bool hfi1_is_slowpath(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->do_interrupt == rcd->slow_handler;
+}
+
+/**
+ * hfi1_is_fastpath - check if this context is fast path
+ * @rcd: the receive context
+ */
+static inline bool hfi1_is_fastpath(struct hfi1_ctxtdata *rcd)
+{
+	if (rcd->ctxt == HFI1_CTRL_CTXT)
+		return false;
+
+	return rcd->do_interrupt == rcd->fast_handler;
+}
+
+/**
+ * hfi1_set_fast - change to the fast handler
+ * @rcd: the receive context
+ */
+static inline void hfi1_set_fast(struct hfi1_ctxtdata *rcd)
+{
+	if (unlikely(!rcd))
+		return;
+	if (unlikely(!hfi1_is_fastpath(rcd)))
+		rcd->do_interrupt = rcd->fast_handler;
+}
+
 int hfi1_reset_device(int);
 
 void receive_interrupt_work(struct work_struct *work);
@@ -2015,9 +2159,21 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr,
 void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
 			     size_t npages, bool dirty);
 
+/**
+ * hfi1_rcvhdrtail_kvaddr - return tail kvaddr
+ * @rcd - the receive context
+ */
+static inline __le64 *hfi1_rcvhdrtail_kvaddr(const struct hfi1_ctxtdata *rcd)
+{
+	return (__le64 *)rcd->rcvhdrtail_kvaddr;
+}
+
 static inline void clear_rcvhdrtail(const struct hfi1_ctxtdata *rcd)
 {
-	*((u64 *)rcd->rcvhdrtail_kvaddr) = 0ULL;
+	u64 *kv = (u64 *)hfi1_rcvhdrtail_kvaddr(rcd);
+
+	if (kv)
+		*kv = 0ULL;
 }
 
 static inline u32 get_rcvhdrtail(const struct hfi1_ctxtdata *rcd)
@@ -2026,7 +2182,17 @@ static inline u32 get_rcvhdrtail(const struct hfi1_ctxtdata *rcd)
 	 * volatile because it's a DMA target from the chip, routine is
 	 * inlined, and don't want register caching or reordering.
 	 */
-	return (u32)le64_to_cpu(*rcd->rcvhdrtail_kvaddr);
+	return (u32)le64_to_cpu(*hfi1_rcvhdrtail_kvaddr(rcd));
+}
+
+static inline bool hfi1_packet_present(struct hfi1_ctxtdata *rcd)
+{
+	if (likely(!rcd->rcvhdrtail_kvaddr)) {
+		u32 seq = rhf_rcv_seq(rhf_to_cpu(get_rhf_addr(rcd)));
+
+		return !last_rcv_seq(rcd, seq);
+	}
+	return hfi1_rcd_head(rcd) != get_rcvhdrtail(rcd);
 }
 
 /*
@@ -2298,6 +2464,25 @@ static inline bool is_integrated(struct hfi1_devdata *dd)
 	return dd->pcidev->device == PCI_DEVICE_ID_INTEL1;
 }
 
+/**
+ * hfi1_need_drop - detect need for drop
+ * @dd: - the device
+ *
+ * In some cases, the first packet needs to be dropped.
+ *
+ * Return true is the current packet needs to be dropped and false otherwise.
+ */
+static inline bool hfi1_need_drop(struct hfi1_devdata *dd)
+{
+	if (unlikely(dd->do_drop &&
+		     atomic_xchg(&dd->drop_packet, DROP_PACKET_OFF) ==
+		     DROP_PACKET_ON)) {
+		dd->do_drop = false;
+		return true;
+	}
+	return false;
+}
+
 int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp);
 
 #define DD_DEV_ENTRY(dd)       __string(dev, dev_name(&(dd)->pcidev->dev))
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 26b792bb1027..e3acda7a0800 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -78,8 +78,6 @@
  */
 #define HFI1_MIN_USER_CTXT_BUFCNT 7
 
-#define HFI1_MIN_HDRQ_EGRBUF_CNT 2
-#define HFI1_MAX_HDRQ_EGRBUF_CNT 16352
 #define HFI1_MIN_EAGER_BUFFER_SIZE (4 * 1024) /* 4KB */
 #define HFI1_MAX_EAGER_BUFFER_SIZE (256 * 1024) /* 256KB */
 
@@ -122,8 +120,6 @@ unsigned int user_credit_return_threshold = 33;	/* default is 33% */
 module_param(user_credit_return_threshold, uint, S_IRUGO);
 MODULE_PARM_DESC(user_credit_return_threshold, "Credit return threshold for user send contexts, return when unreturned credits passes this many blocks (in percent of allocated blocks, 0 is off)");
 
-static inline u64 encode_rcv_header_entry_size(u16 size);
-
 DEFINE_XARRAY_FLAGS(hfi1_dev_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
 
 static int hfi1_create_kctxt(struct hfi1_devdata *dd,
@@ -154,7 +150,12 @@ static int hfi1_create_kctxt(struct hfi1_devdata *dd,
 	/* Control context must use DMA_RTAIL */
 	if (rcd->ctxt == HFI1_CTRL_CTXT)
 		rcd->flags |= HFI1_CAP_DMA_RTAIL;
-	rcd->seq_cnt = 1;
+	rcd->fast_handler = get_dma_rtail_setting(rcd) ?
+				handle_receive_interrupt_dma_rtail :
+				handle_receive_interrupt_nodma_rtail;
+	rcd->slow_handler = handle_receive_interrupt;
+
+	hfi1_set_seq_cnt(rcd, 1);
 
 	rcd->sc = sc_alloc(dd, SC_ACK, rcd->rcvhdrqentsize, dd->node);
 	if (!rcd->sc) {
@@ -511,23 +512,6 @@ void hfi1_free_ctxt(struct hfi1_ctxtdata *rcd)
 }
 
 /*
- * Convert a receive header entry size that to the encoding used in the CSR.
- *
- * Return a zero if the given size is invalid.
- */
-static inline u64 encode_rcv_header_entry_size(u16 size)
-{
-	/* there are only 3 valid receive header entry sizes */
-	if (size == 2)
-		return 1;
-	if (size == 16)
-		return 2;
-	else if (size == 32)
-		return 4;
-	return 0; /* invalid */
-}
-
-/*
  * Select the largest ccti value over all SLs to determine the intra-
  * packet gap for the link.
  *
@@ -892,10 +876,10 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
 
 	if (is_ax(dd)) {
 		atomic_set(&dd->drop_packet, DROP_PACKET_ON);
-		dd->do_drop = 1;
+		dd->do_drop = true;
 	} else {
 		atomic_set(&dd->drop_packet, DROP_PACKET_OFF);
-		dd->do_drop = 0;
+		dd->do_drop = false;
 	}
 
 	/* make sure the link is not "up" */
@@ -1149,9 +1133,9 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 		dma_free_coherent(&dd->pcidev->dev, rcvhdrq_size(rcd),
 				  rcd->rcvhdrq, rcd->rcvhdrq_dma);
 		rcd->rcvhdrq = NULL;
-		if (rcd->rcvhdrtail_kvaddr) {
+		if (hfi1_rcvhdrtail_kvaddr(rcd)) {
 			dma_free_coherent(&dd->pcidev->dev, PAGE_SIZE,
-					  (void *)rcd->rcvhdrtail_kvaddr,
+					  (void *)hfi1_rcvhdrtail_kvaddr(rcd),
 					  rcd->rcvhdrqtailaddr_dma);
 			rcd->rcvhdrtail_kvaddr = NULL;
 		}
@@ -1611,29 +1595,6 @@ static void postinit_cleanup(struct hfi1_devdata *dd)
 	hfi1_free_devdata(dd);
 }
 
-static int init_validate_rcvhdrcnt(struct hfi1_devdata *dd, uint thecnt)
-{
-	if (thecnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) {
-		dd_dev_err(dd, "Receive header queue count too small\n");
-		return -EINVAL;
-	}
-
-	if (thecnt > HFI1_MAX_HDRQ_EGRBUF_CNT) {
-		dd_dev_err(dd,
-			   "Receive header queue count cannot be greater than %u\n",
-			   HFI1_MAX_HDRQ_EGRBUF_CNT);
-		return -EINVAL;
-	}
-
-	if (thecnt % HDRQ_INCREMENT) {
-		dd_dev_err(dd, "Receive header queue count %d must be divisible by %lu\n",
-			   thecnt, HDRQ_INCREMENT);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int ret = 0, j, pidx, initfail;
@@ -1661,7 +1622,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	/* Validate some global module parameters */
-	ret = init_validate_rcvhdrcnt(dd, rcvhdrcnt);
+	ret = hfi1_validate_rcvhdrcnt(dd, rcvhdrcnt);
 	if (ret)
 		goto bail;
 
@@ -1842,7 +1803,6 @@ static void shutdown_one(struct pci_dev *pdev)
 int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 {
 	unsigned amt;
-	u64 reg;
 
 	if (!rcd->rcvhdrq) {
 		gfp_t gfp_flags;
@@ -1874,30 +1834,9 @@ int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 				goto bail_free;
 		}
 	}
-	/*
-	 * These values are per-context:
-	 *	RcvHdrCnt
-	 *	RcvHdrEntSize
-	 *	RcvHdrSize
-	 */
-	reg = ((u64)(rcd->rcvhdrq_cnt >> HDRQ_SIZE_SHIFT)
-			& RCV_HDR_CNT_CNT_MASK)
-		<< RCV_HDR_CNT_CNT_SHIFT;
-	write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_CNT, reg);
-	reg = (encode_rcv_header_entry_size(rcd->rcvhdrqentsize)
-			& RCV_HDR_ENT_SIZE_ENT_SIZE_MASK)
-		<< RCV_HDR_ENT_SIZE_ENT_SIZE_SHIFT;
-	write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_ENT_SIZE, reg);
-	reg = ((u64)DEFAULT_RCVHDRSIZE & RCV_HDR_SIZE_HDR_SIZE_MASK)
-		<< RCV_HDR_SIZE_HDR_SIZE_SHIFT;
-	write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_SIZE, reg);
 
-	/*
-	 * Program dummy tail address for every receive context
-	 * before enabling any receive context
-	 */
-	write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_TAIL_ADDR,
-			dd->rcvhdrtail_dummy_dma);
+	set_hdrq_regs(rcd->dd, rcd->ctxt, rcd->rcvhdrqentsize,
+		      rcd->rcvhdrq_cnt);
 
 	return 0;
 
diff --git a/drivers/infiniband/hw/hfi1/msix.c b/drivers/infiniband/hw/hfi1/msix.c
index d920b165d696..db82db497b2c 100644
--- a/drivers/infiniband/hw/hfi1/msix.c
+++ b/drivers/infiniband/hw/hfi1/msix.c
@@ -115,13 +115,11 @@ int msix_initialize(struct hfi1_devdata *dd)
  */
 static int msix_request_irq(struct hfi1_devdata *dd, void *arg,
 			    irq_handler_t handler, irq_handler_t thread,
-			    u32 idx, enum irq_type type)
+			    enum irq_type type, const char *name)
 {
 	unsigned long nr;
 	int irq;
 	int ret;
-	const char *err_info;
-	char name[MAX_NAME_SIZE];
 	struct hfi1_msix_entry *me;
 
 	/* Allocate an MSIx vector */
@@ -135,43 +133,15 @@ static int msix_request_irq(struct hfi1_devdata *dd, void *arg,
 	if (nr == dd->msix_info.max_requested)
 		return -ENOSPC;
 
-	/* Specific verification and determine the name */
-	switch (type) {
-	case IRQ_GENERAL:
-		/* general interrupt must be MSIx vector 0 */
-		if (nr) {
-			spin_lock(&dd->msix_info.msix_lock);
-			__clear_bit(nr, dd->msix_info.in_use_msix);
-			spin_unlock(&dd->msix_info.msix_lock);
-			dd_dev_err(dd, "Invalid index %lu for GENERAL IRQ\n",
-				   nr);
-			return -EINVAL;
-		}
-		snprintf(name, sizeof(name), DRIVER_NAME "_%d", dd->unit);
-		err_info = "general";
-		break;
-	case IRQ_SDMA:
-		snprintf(name, sizeof(name), DRIVER_NAME "_%d sdma%d",
-			 dd->unit, idx);
-		err_info = "sdma";
-		break;
-	case IRQ_RCVCTXT:
-		snprintf(name, sizeof(name), DRIVER_NAME "_%d kctxt%d",
-			 dd->unit, idx);
-		err_info = "receive context";
-		break;
-	case IRQ_OTHER:
-	default:
+	if (type < IRQ_SDMA || type >= IRQ_OTHER)
 		return -EINVAL;
-	}
-	name[sizeof(name) - 1] = 0;
 
 	irq = pci_irq_vector(dd->pcidev, nr);
 	ret = pci_request_irq(dd->pcidev, nr, handler, thread, arg, name);
 	if (ret) {
 		dd_dev_err(dd,
-			   "%s: request for IRQ %d failed, MSIx %d, err %d\n",
-			   err_info, irq, idx, ret);
+			   "%s: request for IRQ %d failed, MSIx %lu, err %d\n",
+			   name, irq, nr, ret);
 		spin_lock(&dd->msix_info.msix_lock);
 		__clear_bit(nr, dd->msix_info.in_use_msix);
 		spin_unlock(&dd->msix_info.msix_lock);
@@ -195,17 +165,13 @@ static int msix_request_irq(struct hfi1_devdata *dd, void *arg,
 	return nr;
 }
 
-/**
- * msix_request_rcd_irq() - Helper function for RCVAVAIL IRQs
- * @rcd: valid rcd context
- *
- */
-int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd)
+static int msix_request_rcd_irq_common(struct hfi1_ctxtdata *rcd,
+				       irq_handler_t handler,
+				       irq_handler_t thread,
+				       const char *name)
 {
-	int nr;
-
-	nr = msix_request_irq(rcd->dd, rcd, receive_context_interrupt,
-			      receive_context_thread, rcd->ctxt, IRQ_RCVCTXT);
+	int nr = msix_request_irq(rcd->dd, rcd, handler, thread,
+				  IRQ_RCVCTXT, name);
 	if (nr < 0)
 		return nr;
 
@@ -222,6 +188,22 @@ int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd)
 }
 
 /**
+ * msix_request_rcd_irq() - Helper function for RCVAVAIL IRQs
+ * @rcd: valid rcd context
+ *
+ */
+int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd)
+{
+	char name[MAX_NAME_SIZE];
+
+	snprintf(name, sizeof(name), DRIVER_NAME "_%d kctxt%d",
+		 rcd->dd->unit, rcd->ctxt);
+
+	return msix_request_rcd_irq_common(rcd, receive_context_interrupt,
+					   receive_context_thread, name);
+}
+
+/**
  * msix_request_smda_ira() - Helper for getting SDMA IRQ resources
  * @sde: valid sdma engine
  *
@@ -229,9 +211,12 @@ int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd)
 int msix_request_sdma_irq(struct sdma_engine *sde)
 {
 	int nr;
+	char name[MAX_NAME_SIZE];
 
+	snprintf(name, sizeof(name), DRIVER_NAME "_%d sdma%d",
+		 sde->dd->unit, sde->this_idx);
 	nr = msix_request_irq(sde->dd, sde, sdma_interrupt, NULL,
-			      sde->this_idx, IRQ_SDMA);
+			      IRQ_SDMA, name);
 	if (nr < 0)
 		return nr;
 	sde->msix_intr = nr;
@@ -241,6 +226,32 @@ int msix_request_sdma_irq(struct sdma_engine *sde)
 }
 
 /**
+ * msix_request_general_irq(void) - Helper for getting general IRQ
+ * resources
+ * @dd: valid device data
+ */
+int msix_request_general_irq(struct hfi1_devdata *dd)
+{
+	int nr;
+	char name[MAX_NAME_SIZE];
+
+	snprintf(name, sizeof(name), DRIVER_NAME "_%d", dd->unit);
+	nr = msix_request_irq(dd, dd, general_interrupt, NULL, IRQ_GENERAL,
+			      name);
+	if (nr < 0)
+		return nr;
+
+	/* general interrupt must be MSIx vector 0 */
+	if (nr) {
+		msix_free_irq(dd, (u8)nr);
+		dd_dev_err(dd, "Invalid index %d for GENERAL IRQ\n", nr);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
  * enable_sdma_src() - Helper to enable SDMA IRQ srcs
  * @dd: valid devdata structure
  * @i: index of SDMA engine
@@ -265,10 +276,9 @@ static void enable_sdma_srcs(struct hfi1_devdata *dd, int i)
 int msix_request_irqs(struct hfi1_devdata *dd)
 {
 	int i;
-	int ret;
+	int ret = msix_request_general_irq(dd);
 
-	ret = msix_request_irq(dd, dd, general_interrupt, NULL, 0, IRQ_GENERAL);
-	if (ret < 0)
+	if (ret)
 		return ret;
 
 	for (i = 0; i < dd->num_sdma; i++) {
diff --git a/drivers/infiniband/hw/hfi1/msix.h b/drivers/infiniband/hw/hfi1/msix.h
index a514881632a4..1a02ab7971c8 100644
--- a/drivers/infiniband/hw/hfi1/msix.h
+++ b/drivers/infiniband/hw/hfi1/msix.h
@@ -54,6 +54,7 @@
 int msix_initialize(struct hfi1_devdata *dd);
 int msix_request_irqs(struct hfi1_devdata *dd);
 void msix_clean_up_interrupts(struct hfi1_devdata *dd);
+int msix_request_general_irq(struct hfi1_devdata *dd);
 int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd);
 int msix_request_sdma_irq(struct sdma_engine *sde);
 void msix_free_irq(struct hfi1_devdata *dd, u8 msix_intr);
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 1a3c647675a7..f1734e5e9ac4 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -2599,7 +2599,7 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data,
 	 * to be sent before sending this one.
 	 */
 	e = NULL;
-	old_req = 1;
+	old_req = true;
 	ibp->rvp.n_rc_dupreq++;
 
 	spin_lock_irqsave(&qp->s_lock, flags);
diff --git a/drivers/infiniband/hw/hfi1/trace_ctxts.h b/drivers/infiniband/hw/hfi1/trace_ctxts.h
index e00c8a7d559c..b5fc5c6cd52f 100644
--- a/drivers/infiniband/hw/hfi1/trace_ctxts.h
+++ b/drivers/infiniband/hw/hfi1/trace_ctxts.h
@@ -80,7 +80,7 @@ TRACE_EVENT(hfi1_uctxtdata,
 			   __entry->credits = uctxt->sc->credits;
 			   __entry->hw_free = le64_to_cpu(*uctxt->sc->hw_free);
 			   __entry->piobase = uctxt->sc->base_addr;
-			   __entry->rcvhdrq_cnt = uctxt->rcvhdrq_cnt;
+			   __entry->rcvhdrq_cnt = get_hdrq_cnt(uctxt);
 			   __entry->rcvhdrq_dma = uctxt->rcvhdrq_dma;
 			   __entry->eager_cnt = uctxt->egrbufs.alloced;
 			   __entry->rcvegr_dma = uctxt->egrbufs.rcvtids[0].dma;
diff --git a/drivers/infiniband/hw/hfi1/trace_rx.h b/drivers/infiniband/hw/hfi1/trace_rx.h
index 3cec960e9674..168079ed122c 100644
--- a/drivers/infiniband/hw/hfi1/trace_rx.h
+++ b/drivers/infiniband/hw/hfi1/trace_rx.h
@@ -106,19 +106,8 @@ TRACE_EVENT(hfi1_receive_interrupt,
 			     ),
 	    TP_fast_assign(DD_DEV_ASSIGN(dd);
 			__entry->ctxt = rcd->ctxt;
-			if (rcd->do_interrupt ==
-			    &handle_receive_interrupt) {
-				__entry->slow_path = 1;
-				__entry->dma_rtail = 0xFF;
-			} else if (rcd->do_interrupt ==
-					&handle_receive_interrupt_dma_rtail){
-				__entry->dma_rtail = 1;
-				__entry->slow_path = 0;
-			} else if (rcd->do_interrupt ==
-					&handle_receive_interrupt_nodma_rtail) {
-				__entry->dma_rtail = 0;
-				__entry->slow_path = 0;
-			}
+			__entry->slow_path = hfi1_is_slowpath(rcd);
+			__entry->dma_rtail = get_dma_rtail_setting(rcd);
 			),
 	    TP_printk("[%s] ctxt %d SlowPath: %d DmaRtail: %d",
 		      __get_str(dev),
diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c
index b49e60e8397d..6b14581b9965 100644
--- a/drivers/infiniband/hw/hfi1/vnic_main.c
+++ b/drivers/infiniband/hw/hfi1/vnic_main.c
@@ -78,7 +78,7 @@ static int setup_vnic_ctxt(struct hfi1_devdata *dd, struct hfi1_ctxtdata *uctxt)
 	if (ret)
 		goto done;
 
-	if (uctxt->rcvhdrtail_kvaddr)
+	if (hfi1_rcvhdrtail_kvaddr(uctxt))
 		clear_rcvhdrtail(uctxt);
 
 	rcvctrl_ops = HFI1_RCVCTRL_CTXT_ENB;