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

Pull rdma updates from Jason Gunthorpe:
 "A smaller cycle this time. Notably we see another new driver, 'Soft
  iWarp', and the deletion of an ancient unused driver for nes.

   - Revise and simplify the signature offload RDMA MR APIs

   - More progress on hoisting object allocation boiler plate code out
     of the drivers

   - Driver bug fixes and revisions for hns, hfi1, efa, cxgb4, qib,
     i40iw

   - Tree wide cleanups: struct_size, put_user_page, xarray, rst doc
     conversion

   - Removal of obsolete ib_ucm chardev and nes driver

   - netlink based discovery of chardevs and autoloading of the modules
     providing them

   - Move more of the rdamvt/hfi1 uapi to include/uapi/rdma

   - New driver 'siw' for software based iWarp running on top of netdev,
     much like rxe's software RoCE.

   - mlx5 feature to report events in their raw devx format to userspace

   - Expose per-object counters through rdma tool

   - Adaptive interrupt moderation for RDMA (DIM), sharing the DIM core
     from netdev"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (194 commits)
  RMDA/siw: Require a 64 bit arch
  RDMA/siw: Mark expected switch fall-throughs
  RDMA/core: Fix -Wunused-const-variable warnings
  rdma/siw: Remove set but not used variable 's'
  rdma/siw: Add missing dependencies on LIBCRC32C and DMA_VIRT_OPS
  RDMA/siw: Add missing rtnl_lock around access to ifa
  rdma/siw: Use proper enumerated type in map_cqe_status
  RDMA/siw: Remove unnecessary kthread create/destroy printouts
  IB/rdmavt: Fix variable shadowing issue in rvt_create_cq
  RDMA/core: Fix race when resolving IP address
  RDMA/core: Make rdma_counter.h compile stand alone
  IB/core: Work on the caller socket net namespace in nldev_newlink()
  RDMA/rxe: Fill in wc byte_len with IB_WC_RECV_RDMA_WITH_IMM
  RDMA/mlx5: Set RDMA DIM to be enabled by default
  RDMA/nldev: Added configuration of RDMA dynamic interrupt moderation to netlink
  RDMA/core: Provide RDMA DIM support for ULPs
  linux/dim: Implement RDMA adaptive moderation (DIM)
  IB/mlx5: Report correctly tag matching rendezvous capability
  docs: infiniband: add it to the driver-api bookset
  IB/mlx5: Implement VHCA tunnel mechanism in DEVX
  ...

7 files changed, 36 insertions, 56 deletions

diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index a81905df2d0f..8d0563ef5be1 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2012 - 2017 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2012 - 2019 Intel Corporation.  All rights reserved.
  * Copyright (c) 2006 - 2012 QLogic Corporation.  * All rights reserved.
  * Copyright (c) 2005, 2006 PathScale, Inc. All rights reserved.
  *
@@ -398,7 +398,7 @@ int qib_check_send_wqe(struct rvt_qp *qp,
 	case IB_QPT_SMI:
 	case IB_QPT_GSI:
 	case IB_QPT_UD:
-		ah = ibah_to_rvtah(wqe->ud_wr.ah);
+		ah = rvt_get_swqe_ah(wqe);
 		if (wqe->length > (1 << ah->log_pmtu))
 			return -EINVAL;
 		/* progress hint */
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index 2ac4c67f5ba1..1d5e2d4ee257 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -921,20 +921,11 @@ void qib_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 		rvt_add_retry_timer(qp);
 
 	while (qp->s_last != qp->s_acked) {
-		u32 s_last;
-
 		wqe = rvt_get_swqe_ptr(qp, qp->s_last);
 		if (qib_cmp24(wqe->lpsn, qp->s_sending_psn) >= 0 &&
 		    qib_cmp24(qp->s_sending_psn, qp->s_sending_hpsn) <= 0)
 			break;
-		s_last = qp->s_last;
-		if (++s_last >= qp->s_size)
-			s_last = 0;
-		qp->s_last = s_last;
-		/* see post_send() */
-		barrier();
-		rvt_put_qp_swqe(qp, wqe);
-		rvt_qp_swqe_complete(qp,
+		rvt_qp_complete_swqe(qp,
 				     wqe,
 				     ib_qib_wc_opcode[wqe->wr.opcode],
 				     IB_WC_SUCCESS);
@@ -972,21 +963,12 @@ static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp,
 	 * is finished.
 	 */
 	if (qib_cmp24(wqe->lpsn, qp->s_sending_psn) < 0 ||
-	    qib_cmp24(qp->s_sending_psn, qp->s_sending_hpsn) > 0) {
-		u32 s_last;
-
-		rvt_put_qp_swqe(qp, wqe);
-		s_last = qp->s_last;
-		if (++s_last >= qp->s_size)
-			s_last = 0;
-		qp->s_last = s_last;
-		/* see post_send() */
-		barrier();
-		rvt_qp_swqe_complete(qp,
+	    qib_cmp24(qp->s_sending_psn, qp->s_sending_hpsn) > 0)
+		rvt_qp_complete_swqe(qp,
 				     wqe,
 				     ib_qib_wc_opcode[wqe->wr.opcode],
 				     IB_WC_SUCCESS);
-	} else
+	else
 		this_cpu_inc(*ibp->rvp.rc_delayed_comp);
 
 	qp->s_retry = qp->s_retry_cnt;
@@ -1909,8 +1891,7 @@ send_last:
 		wc.dlid_path_bits = 0;
 		wc.port_num = 0;
 		/* Signal completion event if the solicited bit is set. */
-		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-			     ib_bth_is_solicited(ohdr));
+		rvt_recv_cq(qp, &wc, ib_bth_is_solicited(ohdr));
 		break;
 
 	case OP(RDMA_WRITE_FIRST):
diff --git a/drivers/infiniband/hw/qib/qib_uc.c b/drivers/infiniband/hw/qib/qib_uc.c
index 30c70ad0f4bf..e17b91e2c22a 100644
--- a/drivers/infiniband/hw/qib/qib_uc.c
+++ b/drivers/infiniband/hw/qib/qib_uc.c
@@ -400,8 +400,7 @@ last_imm:
 		wc.dlid_path_bits = 0;
 		wc.port_num = 0;
 		/* Signal completion event if the solicited bit is set. */
-		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc,
-			     ib_bth_is_solicited(ohdr));
+		rvt_recv_cq(qp, &wc, ib_bth_is_solicited(ohdr));
 		break;
 
 	case OP(RDMA_WRITE_FIRST):
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index 5cdedba2d164..93ca21347959 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2012 - 2019 Intel Corporation.  All rights reserved.
  * Copyright (c) 2006, 2007, 2008, 2009 QLogic Corporation. All rights reserved.
  * Copyright (c) 2005, 2006 PathScale, Inc. All rights reserved.
  *
@@ -63,7 +64,7 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 	enum ib_qp_type sqptype, dqptype;
 
 	rcu_read_lock();
-	qp = rvt_lookup_qpn(rdi, &ibp->rvp, swqe->ud_wr.remote_qpn);
+	qp = rvt_lookup_qpn(rdi, &ibp->rvp, rvt_get_swqe_remote_qpn(swqe));
 	if (!qp) {
 		ibp->rvp.n_pkt_drops++;
 		goto drop;
@@ -80,7 +81,7 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 		goto drop;
 	}
 
-	ah_attr = &ibah_to_rvtah(swqe->ud_wr.ah)->attr;
+	ah_attr = rvt_get_swqe_ah_attr(swqe);
 	ppd = ppd_from_ibp(ibp);
 
 	if (qp->ibqp.qp_num > 1) {
@@ -110,8 +111,8 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 	if (qp->ibqp.qp_num) {
 		u32 qkey;
 
-		qkey = (int)swqe->ud_wr.remote_qkey < 0 ?
-			sqp->qkey : swqe->ud_wr.remote_qkey;
+		qkey = (int)rvt_get_swqe_remote_qkey(swqe) < 0 ?
+			sqp->qkey : rvt_get_swqe_remote_qkey(swqe);
 		if (unlikely(qkey != qp->qkey))
 			goto drop;
 	}
@@ -203,15 +204,14 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 	wc.qp = &qp->ibqp;
 	wc.src_qp = sqp->ibqp.qp_num;
 	wc.pkey_index = qp->ibqp.qp_type == IB_QPT_GSI ?
-		swqe->ud_wr.pkey_index : 0;
+		rvt_get_swqe_pkey_index(swqe) : 0;
 	wc.slid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
 				((1 << ppd->lmc) - 1));
 	wc.sl = rdma_ah_get_sl(ah_attr);
 	wc.dlid_path_bits = rdma_ah_get_dlid(ah_attr) & ((1 << ppd->lmc) - 1);
 	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,
-		     swqe->wr.send_flags & IB_SEND_SOLICITED);
+	rvt_recv_cq(qp, &wc, swqe->wr.send_flags & IB_SEND_SOLICITED);
 	ibp->rvp.n_loop_pkts++;
 bail_unlock:
 	spin_unlock_irqrestore(&qp->r_lock, flags);
@@ -271,7 +271,7 @@ int qib_make_ud_req(struct rvt_qp *qp, unsigned long *flags)
 	/* Construct the header. */
 	ibp = to_iport(qp->ibqp.device, qp->port_num);
 	ppd = ppd_from_ibp(ibp);
-	ah_attr = &ibah_to_rvtah(wqe->ud_wr.ah)->attr;
+	ah_attr = rvt_get_swqe_ah_attr(wqe);
 	if (rdma_ah_get_dlid(ah_attr) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) {
 		if (rdma_ah_get_dlid(ah_attr) !=
 				be16_to_cpu(IB_LID_PERMISSIVE))
@@ -363,7 +363,7 @@ int qib_make_ud_req(struct rvt_qp *qp, unsigned long *flags)
 	bth0 |= extra_bytes << 20;
 	bth0 |= qp->ibqp.qp_type == IB_QPT_SMI ? QIB_DEFAULT_P_KEY :
 		qib_get_pkey(ibp, qp->ibqp.qp_type == IB_QPT_GSI ?
-			     wqe->ud_wr.pkey_index : qp->s_pkey_index);
+			     rvt_get_swqe_pkey_index(wqe) : qp->s_pkey_index);
 	ohdr->bth[0] = cpu_to_be32(bth0);
 	/*
 	 * Use the multicast QP if the destination LID is a multicast LID.
@@ -372,14 +372,15 @@ int qib_make_ud_req(struct rvt_qp *qp, unsigned long *flags)
 			be16_to_cpu(IB_MULTICAST_LID_BASE) &&
 		rdma_ah_get_dlid(ah_attr) != be16_to_cpu(IB_LID_PERMISSIVE) ?
 		cpu_to_be32(QIB_MULTICAST_QPN) :
-		cpu_to_be32(wqe->ud_wr.remote_qpn);
+		cpu_to_be32(rvt_get_swqe_remote_qpn(wqe));
 	ohdr->bth[2] = cpu_to_be32(wqe->psn & QIB_PSN_MASK);
 	/*
 	 * Qkeys with the high order bit set mean use the
 	 * qkey from the QP context instead of the WR (see 10.2.5).
 	 */
-	ohdr->u.ud.deth[0] = cpu_to_be32((int)wqe->ud_wr.remote_qkey < 0 ?
-					 qp->qkey : wqe->ud_wr.remote_qkey);
+	ohdr->u.ud.deth[0] =
+		cpu_to_be32((int)rvt_get_swqe_remote_qkey(wqe) < 0 ? qp->qkey :
+			    rvt_get_swqe_remote_qkey(wqe));
 	ohdr->u.ud.deth[1] = cpu_to_be32(qp->ibqp.qp_num);
 
 done:
@@ -573,8 +574,7 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
 		dlid & ((1 << ppd_from_ibp(ibp)->lmc) - 1);
 	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,
-		     ib_bth_is_solicited(ohdr));
+	rvt_recv_cq(qp, &wc, ib_bth_is_solicited(ohdr));
 	return;
 
 drop:
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index f712fb7fa82f..bfbfbb7e0ff4 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -40,13 +40,10 @@
 static void __qib_release_user_pages(struct page **p, size_t num_pages,
 				     int dirty)
 {
-	size_t i;
-
-	for (i = 0; i < num_pages; i++) {
-		if (dirty)
-			set_page_dirty_lock(p[i]);
-		put_page(p[i]);
-	}
+	if (dirty)
+		put_user_pages_dirty_lock(p, num_pages);
+	else
+		put_user_pages(p, num_pages);
 }
 
 /**
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 0c204776263f..05190edc2611 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -317,7 +317,7 @@ static int qib_user_sdma_page_to_frags(const struct qib_devdata *dd,
 		 * the caller can ignore this page.
 		 */
 		if (put) {
-			put_page(page);
+			put_user_page(page);
 		} else {
 			/* coalesce case */
 			kunmap(page);
@@ -631,7 +631,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev,
 			kunmap(pkt->addr[i].page);
 
 		if (pkt->addr[i].put_page)
-			put_page(pkt->addr[i].page);
+			put_user_page(pkt->addr[i].page);
 		else
 			__free_page(pkt->addr[i].page);
 	} else if (pkt->addr[i].kvaddr) {
@@ -706,7 +706,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 	/* if error, return all pages not managed by pkt */
 free_pages:
 	while (i < j)
-		put_page(pages[i++]);
+		put_user_page(pages[i++]);
 
 done:
 	return ret;
@@ -904,10 +904,11 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
 		}
 
 		if (frag_size) {
-			int pktsize, tidsmsize, n;
+			int tidsmsize, n;
+			size_t pktsize;
 
 			n = npages*((2*PAGE_SIZE/frag_size)+1);
-			pktsize = sizeof(*pkt) + sizeof(pkt->addr[0])*n;
+			pktsize = struct_size(pkt, addr, n);
 
 			/*
 			 * Determine if this is tid-sdma or just sdma.
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index 2c4e569ce438..33778d451b82 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -1480,6 +1480,9 @@ static void qib_fill_device_attr(struct qib_devdata *dd)
 }
 
 static const struct ib_device_ops qib_dev_ops = {
+	.owner = THIS_MODULE,
+	.driver_id = RDMA_DRIVER_QIB,
+
 	.init_port = qib_create_port_files,
 	.modify_device = qib_modify_device,
 	.process_mad = qib_process_mad,
@@ -1543,7 +1546,6 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	if (!ib_qib_sys_image_guid)
 		ib_qib_sys_image_guid = ppd->guid;
 
-	ibdev->owner = THIS_MODULE;
 	ibdev->node_guid = ppd->guid;
 	ibdev->phys_port_cnt = dd->num_pports;
 	ibdev->dev.parent = &dd->pcidev->dev;
@@ -1614,7 +1616,7 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	rdma_set_device_sysfs_group(&dd->verbs_dev.rdi.ibdev, &qib_attr_group);
 
 	ib_set_device_ops(ibdev, &qib_dev_ops);
-	ret = rvt_register_device(&dd->verbs_dev.rdi, RDMA_DRIVER_QIB);
+	ret = rvt_register_device(&dd->verbs_dev.rdi);
 	if (ret)
 		goto err_tx;