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
  ...

1 files changed, 151 insertions, 47 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 */