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

Pull rdma updates from Jason Gunthorpe:
 "Small cycle, with some typical driver updates:

   - General code tidying in siw, hfi1, idrdma, usnic, hns rtrs and
     bnxt_re

   - Many small siw cleanups without an overeaching theme

   - Debugfs stats for hns

   - Fix a TX queue timeout in IPoIB and missed locking of the mcast
     list

   - Support more features of P7 devices in bnxt_re including a new work
     submission protocol

   - CQ interrupts for MANA

   - netlink stats for erdma

   - EFA multipath PCI support

   - Fix Incorrect MR invalidation in iser"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (66 commits)
  RDMA/bnxt_re: Fix error code in bnxt_re_create_cq()
  RDMA/efa: Add EFA query MR support
  IB/iser: Prevent invalidating wrong MR
  RDMA/erdma: Add hardware statistics support
  RDMA/erdma: Introduce dma pool for hardware responses of CMDQ requests
  IB/iser: iscsi_iser.h: fix kernel-doc warning and spellos
  RDMA/mana_ib: Add CQ interrupt support for RAW QP
  RDMA/mana_ib: query device capabilities
  RDMA/mana_ib: register RDMA device with GDMA
  RDMA/bnxt_re: Fix the sparse warnings
  RDMA/bnxt_re: Fix the offset for GenP7 adapters for user applications
  RDMA/bnxt_re: Share a page to expose per CQ info with userspace
  RDMA/bnxt_re: Add UAPI to share a page with user space
  IB/ipoib: Fix mcast list locking
  RDMA/mlx5: Expose register c0 for RDMA device
  net/mlx5: E-Switch, expose eswitch manager vport
  net/mlx5: Manage ICM type of SW encap
  RDMA/mlx5: Support handling of SW encap ICM area
  net/mlx5: Introduce indirect-sw-encap ICM properties
  RDMA/bnxt_re: Adds MSN table capability for Gen P7 adapters
  ...

81 files changed, 1921 insertions, 638 deletions

diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index 9fd9849ebdd1..9dca451ed522 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -41,6 +41,7 @@
 #define __BNXT_RE_H__
 #include <rdma/uverbs_ioctl.h>
 #include "hw_counters.h"
+#include <linux/hashtable.h>
 #define ROCE_DRV_MODULE_NAME		"bnxt_re"
 
 #define BNXT_RE_DESC	"Broadcom NetXtreme-C/E RoCE Driver"
@@ -135,6 +136,7 @@ struct bnxt_re_pacing {
 #define BNXT_RE_DB_FIFO_ROOM_SHIFT 15
 #define BNXT_RE_GRC_FIFO_REG_BASE 0x2000
 
+#define MAX_CQ_HASH_BITS		(16)
 struct bnxt_re_dev {
 	struct ib_device		ibdev;
 	struct list_head		list;
@@ -189,6 +191,7 @@ struct bnxt_re_dev {
 	struct bnxt_re_pacing pacing;
 	struct work_struct dbq_fifo_check_work;
 	struct delayed_work dbq_pacing_work;
+	DECLARE_HASHTABLE(cq_hash, MAX_CQ_HASH_BITS);
 };
 
 #define to_bnxt_re_dev(ptr, member)	\
diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c
index 93572405d6fa..128651c01595 100644
--- a/drivers/infiniband/hw/bnxt_re/hw_counters.c
+++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c
@@ -371,7 +371,7 @@ int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev,
 	}
 
 done:
-	return bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ?
+	return bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx) ?
 		BNXT_RE_NUM_EXT_COUNTERS : BNXT_RE_NUM_STD_COUNTERS;
 }
 
@@ -381,7 +381,7 @@ struct rdma_hw_stats *bnxt_re_ib_alloc_hw_port_stats(struct ib_device *ibdev,
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
 	int num_counters = 0;
 
-	if (bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx))
+	if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))
 		num_counters = BNXT_RE_NUM_EXT_COUNTERS;
 	else
 		num_counters = BNXT_RE_NUM_STD_COUNTERS;
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index faa88d12ee86..824349659d69 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -50,6 +50,7 @@
 #include <rdma/ib_mad.h>
 #include <rdma/ib_cache.h>
 #include <rdma/uverbs_ioctl.h>
+#include <linux/hashtable.h>
 
 #include "bnxt_ulp.h"
 
@@ -567,6 +568,7 @@ bnxt_re_mmap_entry_insert(struct bnxt_re_ucontext *uctx, u64 mem_offset,
 	case BNXT_RE_MMAP_WC_DB:
 	case BNXT_RE_MMAP_DBR_BAR:
 	case BNXT_RE_MMAP_DBR_PAGE:
+	case BNXT_RE_MMAP_TOGGLE_PAGE:
 		ret = rdma_user_mmap_entry_insert(&uctx->ib_uctx,
 						  &entry->rdma_entry, PAGE_SIZE);
 		break;
@@ -1023,7 +1025,7 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd,
 	bytes = (qplib_qp->sq.max_wqe * qplib_qp->sq.wqe_size);
 	/* Consider mapping PSN search memory only for RC QPs. */
 	if (qplib_qp->type == CMDQ_CREATE_QP_TYPE_RC) {
-		psn_sz = bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ?
+		psn_sz = bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx) ?
 						   sizeof(struct sq_psn_search_ext) :
 						   sizeof(struct sq_psn_search);
 		psn_nume = (qplib_qp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC) ?
@@ -1184,7 +1186,8 @@ fail:
 }
 
 static int bnxt_re_init_rq_attr(struct bnxt_re_qp *qp,
-				struct ib_qp_init_attr *init_attr)
+				struct ib_qp_init_attr *init_attr,
+				struct bnxt_re_ucontext *uctx)
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
 	struct bnxt_qplib_qp *qplqp;
@@ -1213,7 +1216,7 @@ static int bnxt_re_init_rq_attr(struct bnxt_re_qp *qp,
 		/* Allocate 1 more than what's provided so posting max doesn't
 		 * mean empty.
 		 */
-		entries = roundup_pow_of_two(init_attr->cap.max_recv_wr + 1);
+		entries = bnxt_re_init_depth(init_attr->cap.max_recv_wr + 1, uctx);
 		rq->max_wqe = min_t(u32, entries, dev_attr->max_qp_wqes + 1);
 		rq->q_full_delta = 0;
 		rq->sg_info.pgsize = PAGE_SIZE;
@@ -1233,7 +1236,7 @@ static void bnxt_re_adjust_gsi_rq_attr(struct bnxt_re_qp *qp)
 	qplqp = &qp->qplib_qp;
 	dev_attr = &rdev->dev_attr;
 
-	if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) {
+	if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) {
 		qplqp->rq.max_sge = dev_attr->max_qp_sges;
 		if (qplqp->rq.max_sge > dev_attr->max_qp_sges)
 			qplqp->rq.max_sge = dev_attr->max_qp_sges;
@@ -1243,7 +1246,7 @@ static void bnxt_re_adjust_gsi_rq_attr(struct bnxt_re_qp *qp)
 
 static int bnxt_re_init_sq_attr(struct bnxt_re_qp *qp,
 				struct ib_qp_init_attr *init_attr,
-				struct ib_udata *udata)
+				struct bnxt_re_ucontext *uctx)
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
 	struct bnxt_qplib_qp *qplqp;
@@ -1272,7 +1275,7 @@ static int bnxt_re_init_sq_attr(struct bnxt_re_qp *qp,
 	/* Allocate 128 + 1 more than what's provided */
 	diff = (qplqp->wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE) ?
 		0 : BNXT_QPLIB_RESERVED_QP_WRS;
-	entries = roundup_pow_of_two(entries + diff + 1);
+	entries = bnxt_re_init_depth(entries + diff + 1, uctx);
 	sq->max_wqe = min_t(u32, entries, dev_attr->max_qp_wqes + diff + 1);
 	sq->q_full_delta = diff + 1;
 	/*
@@ -1288,7 +1291,8 @@ static int bnxt_re_init_sq_attr(struct bnxt_re_qp *qp,
 }
 
 static void bnxt_re_adjust_gsi_sq_attr(struct bnxt_re_qp *qp,
-				       struct ib_qp_init_attr *init_attr)
+				       struct ib_qp_init_attr *init_attr,
+				       struct bnxt_re_ucontext *uctx)
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
 	struct bnxt_qplib_qp *qplqp;
@@ -1299,8 +1303,8 @@ static void bnxt_re_adjust_gsi_sq_attr(struct bnxt_re_qp *qp,
 	qplqp = &qp->qplib_qp;
 	dev_attr = &rdev->dev_attr;
 
-	if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) {
-		entries = roundup_pow_of_two(init_attr->cap.max_send_wr + 1);
+	if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) {
+		entries = bnxt_re_init_depth(init_attr->cap.max_send_wr + 1, uctx);
 		qplqp->sq.max_wqe = min_t(u32, entries,
 					  dev_attr->max_qp_wqes + 1);
 		qplqp->sq.q_full_delta = qplqp->sq.max_wqe -
@@ -1326,7 +1330,7 @@ static int bnxt_re_init_qp_type(struct bnxt_re_dev *rdev,
 		goto out;
 	}
 
-	if (bnxt_qplib_is_chip_gen_p5(chip_ctx) &&
+	if (bnxt_qplib_is_chip_gen_p5_p7(chip_ctx) &&
 	    init_attr->qp_type == IB_QPT_GSI)
 		qptype = CMDQ_CREATE_QP_TYPE_GSI;
 out:
@@ -1338,6 +1342,7 @@ static int bnxt_re_init_qp_attr(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd,
 				struct ib_udata *udata)
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
+	struct bnxt_re_ucontext *uctx;
 	struct bnxt_qplib_qp *qplqp;
 	struct bnxt_re_dev *rdev;
 	struct bnxt_re_cq *cq;
@@ -1347,6 +1352,7 @@ static int bnxt_re_init_qp_attr(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd,
 	qplqp = &qp->qplib_qp;
 	dev_attr = &rdev->dev_attr;
 
+	uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
 	/* Setup misc params */
 	ether_addr_copy(qplqp->smac, rdev->netdev->dev_addr);
 	qplqp->pd = &pd->qplib_pd;
@@ -1388,18 +1394,18 @@ static int bnxt_re_init_qp_attr(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd,
 	}
 
 	/* Setup RQ/SRQ */
-	rc = bnxt_re_init_rq_attr(qp, init_attr);
+	rc = bnxt_re_init_rq_attr(qp, init_attr, uctx);
 	if (rc)
 		goto out;
 	if (init_attr->qp_type == IB_QPT_GSI)
 		bnxt_re_adjust_gsi_rq_attr(qp);
 
 	/* Setup SQ */
-	rc = bnxt_re_init_sq_attr(qp, init_attr, udata);
+	rc = bnxt_re_init_sq_attr(qp, init_attr, uctx);
 	if (rc)
 		goto out;
 	if (init_attr->qp_type == IB_QPT_GSI)
-		bnxt_re_adjust_gsi_sq_attr(qp, init_attr);
+		bnxt_re_adjust_gsi_sq_attr(qp, init_attr, uctx);
 
 	if (udata) /* This will update DPI and qp_handle */
 		rc = bnxt_re_init_user_qp(rdev, pd, qp, udata);
@@ -1523,7 +1529,7 @@ int bnxt_re_create_qp(struct ib_qp *ib_qp, struct ib_qp_init_attr *qp_init_attr,
 		goto fail;
 
 	if (qp_init_attr->qp_type == IB_QPT_GSI &&
-	    !(bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx))) {
+	    !(bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))) {
 		rc = bnxt_re_create_gsi_qp(qp, pd, qp_init_attr);
 		if (rc == -ENODEV)
 			goto qp_destroy;
@@ -1715,6 +1721,7 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
 	struct bnxt_qplib_nq *nq = NULL;
+	struct bnxt_re_ucontext *uctx;
 	struct bnxt_re_dev *rdev;
 	struct bnxt_re_srq *srq;
 	struct bnxt_re_pd *pd;
@@ -1739,13 +1746,14 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 		goto exit;
 	}
 
+	uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
 	srq->rdev = rdev;
 	srq->qplib_srq.pd = &pd->qplib_pd;
 	srq->qplib_srq.dpi = &rdev->dpi_privileged;
 	/* Allocate 1 more than what's provided so posting max doesn't
 	 * mean empty
 	 */
-	entries = roundup_pow_of_two(srq_init_attr->attr.max_wr + 1);
+	entries = bnxt_re_init_depth(srq_init_attr->attr.max_wr + 1, uctx);
 	if (entries > dev_attr->max_srq_wqes + 1)
 		entries = dev_attr->max_srq_wqes + 1;
 	srq->qplib_srq.max_wqe = entries;
@@ -2103,6 +2111,9 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 		qp->qplib_qp.max_dest_rd_atomic = qp_attr->max_dest_rd_atomic;
 	}
 	if (qp_attr_mask & IB_QP_CAP) {
+		struct bnxt_re_ucontext *uctx =
+			rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
+
 		qp->qplib_qp.modify_flags |=
 				CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SIZE |
 				CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SIZE |
@@ -2119,7 +2130,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 				  "Create QP failed - max exceeded");
 			return -EINVAL;
 		}
-		entries = roundup_pow_of_two(qp_attr->cap.max_send_wr);
+		entries = bnxt_re_init_depth(qp_attr->cap.max_send_wr, uctx);
 		qp->qplib_qp.sq.max_wqe = min_t(u32, entries,
 						dev_attr->max_qp_wqes + 1);
 		qp->qplib_qp.sq.q_full_delta = qp->qplib_qp.sq.max_wqe -
@@ -2132,7 +2143,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 		qp->qplib_qp.sq.q_full_delta -= 1;
 		qp->qplib_qp.sq.max_sge = qp_attr->cap.max_send_sge;
 		if (qp->qplib_qp.rq.max_wqe) {
-			entries = roundup_pow_of_two(qp_attr->cap.max_recv_wr);
+			entries = bnxt_re_init_depth(qp_attr->cap.max_recv_wr, uctx);
 			qp->qplib_qp.rq.max_wqe =
 				min_t(u32, entries, dev_attr->max_qp_wqes + 1);
 			qp->qplib_qp.rq.q_full_delta = qp->qplib_qp.rq.max_wqe -
@@ -2900,14 +2911,20 @@ int bnxt_re_post_recv(struct ib_qp *ib_qp, const struct ib_recv_wr *wr,
 /* Completion Queues */
 int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 {
-	struct bnxt_re_cq *cq;
+	struct bnxt_qplib_chip_ctx *cctx;
 	struct bnxt_qplib_nq *nq;
 	struct bnxt_re_dev *rdev;
+	struct bnxt_re_cq *cq;
 
 	cq = container_of(ib_cq, struct bnxt_re_cq, ib_cq);
 	rdev = cq->rdev;
 	nq = cq->qplib_cq.nq;
+	cctx = rdev->chip_ctx;
 
+	if (cctx->modes.toggle_bits & BNXT_QPLIB_CQ_TOGGLE_BIT) {
+		free_page((unsigned long)cq->uctx_cq_page);
+		hash_del(&cq->hash_entry);
+	}
 	bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
 	ib_umem_release(cq->umem);
 
@@ -2920,13 +2937,16 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		      struct ib_udata *udata)
 {
+	struct bnxt_re_cq *cq = container_of(ibcq, struct bnxt_re_cq, ib_cq);
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibcq->device, ibdev);
+	struct bnxt_re_ucontext *uctx =
+		rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
 	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
-	struct bnxt_re_cq *cq = container_of(ibcq, struct bnxt_re_cq, ib_cq);
-	int rc, entries;
-	int cqe = attr->cqe;
+	struct bnxt_qplib_chip_ctx *cctx;
 	struct bnxt_qplib_nq *nq = NULL;
 	unsigned int nq_alloc_cnt;
+	int cqe = attr->cqe;
+	int rc, entries;
 	u32 active_cqs;
 
 	if (attr->flags)
@@ -2939,9 +2959,10 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	}
 
 	cq->rdev = rdev;
+	cctx = rdev->chip_ctx;
 	cq->qplib_cq.cq_handle = (u64)(unsigned long)(&cq->qplib_cq);
 
-	entries = roundup_pow_of_two(cqe + 1);
+	entries = bnxt_re_init_depth(cqe + 1, uctx);
 	if (entries > dev_attr->max_cq_wqes + 1)
 		entries = dev_attr->max_cq_wqes + 1;
 
@@ -2949,8 +2970,6 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	cq->qplib_cq.sg_info.pgshft = PAGE_SHIFT;
 	if (udata) {
 		struct bnxt_re_cq_req req;
-		struct bnxt_re_ucontext *uctx = rdma_udata_to_drv_context(
-			udata, struct bnxt_re_ucontext, ib_uctx);
 		if (ib_copy_from_udata(&req, udata, sizeof(req))) {
 			rc = -EFAULT;
 			goto fail;
@@ -3002,22 +3021,34 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	spin_lock_init(&cq->cq_lock);
 
 	if (udata) {
-		struct bnxt_re_cq_resp resp;
+		struct bnxt_re_cq_resp resp = {};
 
+		if (cctx->modes.toggle_bits & BNXT_QPLIB_CQ_TOGGLE_BIT) {