diff --git a/drivers/infiniband/hw/qib/qib_keys.c b/drivers/infiniband/hw/qib/qib_keys.c
index 8fd19a47df0c..8b5ee3aa8e3d 100644
--- a/drivers/infiniband/hw/qib/qib_keys.c
+++ b/drivers/infiniband/hw/qib/qib_keys.c
@@ -35,21 +35,40 @@
 
 /**
  * qib_alloc_lkey - allocate an lkey
- * @rkt: lkey table in which to allocate the lkey
  * @mr: memory region that this lkey protects
+ * @dma_region: 0->normal key, 1->restricted DMA key
+ *
+ * Returns 0 if successful, otherwise returns -errno.
+ *
+ * Increments mr reference count and sets published
+ * as required.
+ *
+ * Sets the lkey field mr for non-dma regions.
  *
- * Returns 1 if successful, otherwise returns 0.
  */
 
-int qib_alloc_lkey(struct qib_lkey_table *rkt, struct qib_mregion *mr)
+int qib_alloc_lkey(struct qib_mregion *mr, int dma_region)
 {
 	unsigned long flags;
 	u32 r;
 	u32 n;
-	int ret;
+	int ret = 0;
+	struct qib_ibdev *dev = to_idev(mr->pd->device);
+	struct qib_lkey_table *rkt = &dev->lk_table;
 
 	spin_lock_irqsave(&rkt->lock, flags);
 
+	/* special case for dma_mr lkey == 0 */
+	if (dma_region) {
+		/* should the dma_mr be relative to the pd? */
+		if (!dev->dma_mr) {
+			qib_get_mr(mr);
+			dev->dma_mr = mr;
+			mr->lkey_published = 1;
+		}
+		goto success;
+	}
+
 	/* Find the next available LKEY */
 	r = rkt->next;
 	n = r;
@@ -57,11 +76,8 @@ int qib_alloc_lkey(struct qib_lkey_table *rkt, struct qib_mregion *mr)
 		if (rkt->table[r] == NULL)
 			break;
 		r = (r + 1) & (rkt->max - 1);
-		if (r == n) {
-			spin_unlock_irqrestore(&rkt->lock, flags);
-			ret = 0;
+		if (r == n)
 			goto bail;
-		}
 	}
 	rkt->next = (r + 1) & (rkt->max - 1);
 	/*
@@ -76,46 +92,50 @@ int qib_alloc_lkey(struct qib_lkey_table *rkt, struct qib_mregion *mr)
 		mr->lkey |= 1 << 8;
 		rkt->gen++;
 	}
+	qib_get_mr(mr);
 	rkt->table[r] = mr;
+	mr->lkey_published = 1;
+success:
 	spin_unlock_irqrestore(&rkt->lock, flags);
-
-	ret = 1;
-
-bail:
+out:
 	return ret;
+bail:
+	spin_unlock_irqrestore(&rkt->lock, flags);
+	ret = -ENOMEM;
+	goto out;
 }
 
 /**
  * qib_free_lkey - free an lkey
- * @rkt: table from which to free the lkey
- * @lkey: lkey id to free
+ * @mr: mr to free from tables
  */
-int qib_free_lkey(struct qib_ibdev *dev, struct qib_mregion *mr)
+void qib_free_lkey(struct qib_mregion *mr)
 {
 	unsigned long flags;
 	u32 lkey = mr->lkey;
 	u32 r;
-	int ret;
+	struct qib_ibdev *dev = to_idev(mr->pd->device);
+	struct qib_lkey_table *rkt = &dev->lk_table;
+
+	spin_lock_irqsave(&rkt->lock, flags);
+	if (!mr->lkey_published)
+		goto out;
+	mr->lkey_published = 0;
+
 
 	spin_lock_irqsave(&dev->lk_table.lock, flags);
 	if (lkey == 0) {
 		if (dev->dma_mr && dev->dma_mr == mr) {
-			ret = atomic_read(&dev->dma_mr->refcount);
-			if (!ret)
-				dev->dma_mr = NULL;
-		} else
-			ret = 0;
+			qib_put_mr(dev->dma_mr);
+			dev->dma_mr = NULL;
+		}
 	} else {
 		r = lkey >> (32 - ib_qib_lkey_table_size);
-		ret = atomic_read(&dev->lk_table.table[r]->refcount);
-		if (!ret)
-			dev->lk_table.table[r] = NULL;
+		qib_put_mr(dev->dma_mr);
+		rkt->table[r] = NULL;
 	}
+out:
 	spin_unlock_irqrestore(&dev->lk_table.lock, flags);
-
-	if (ret)
-		ret = -EBUSY;
-	return ret;
 }
 
 /**
@@ -150,7 +170,7 @@ int qib_lkey_ok(struct qib_lkey_table *rkt, struct qib_pd *pd,
 			goto bail;
 		if (!dev->dma_mr)
 			goto bail;
-		atomic_inc(&dev->dma_mr->refcount);
+		qib_get_mr(dev->dma_mr);
 		spin_unlock_irqrestore(&rkt->lock, flags);
 
 		isge->mr = dev->dma_mr;
@@ -171,7 +191,7 @@ int qib_lkey_ok(struct qib_lkey_table *rkt, struct qib_pd *pd,
 		     off + sge->length > mr->length ||
 		     (mr->access_flags & acc) != acc))
 		goto bail;
-	atomic_inc(&mr->refcount);
+	qib_get_mr(mr);
 	spin_unlock_irqrestore(&rkt->lock, flags);
 
 	off += mr->offset;
@@ -245,7 +265,7 @@ int qib_rkey_ok(struct qib_qp *qp, struct qib_sge *sge,
 			goto bail;
 		if (!dev->dma_mr)
 			goto bail;
-		atomic_inc(&dev->dma_mr->refcount);
+		qib_get_mr(dev->dma_mr);
 		spin_unlock_irqrestore(&rkt->lock, flags);
 
 		sge->mr = dev->dma_mr;
@@ -265,7 +285,7 @@ int qib_rkey_ok(struct qib_qp *qp, struct qib_sge *sge,
 	if (unlikely(vaddr < mr->iova || off + len > mr->length ||
 		     (mr->access_flags & acc) == 0))
 		goto bail;
-	atomic_inc(&mr->refcount);
+	qib_get_mr(mr);
 	spin_unlock_irqrestore(&rkt->lock, flags);
 
 	off += mr->offset;
diff --git a/drivers/infiniband/hw/qib/qib_mr.c b/drivers/infiniband/hw/qib/qib_mr.c
index 08944e2ee334..6a2028a56e3d 100644
--- a/drivers/infiniband/hw/qib/qib_mr.c
+++ b/drivers/infiniband/hw/qib/qib_mr.c
@@ -47,6 +47,43 @@ static inline struct qib_fmr *to_ifmr(struct ib_fmr *ibfmr)
 	return container_of(ibfmr, struct qib_fmr, ibfmr);
 }
 
+static int init_qib_mregion(struct qib_mregion *mr, struct ib_pd *pd,
+	int count)
+{
+	int m, i = 0;
+	int rval = 0;
+
+	m = (count + QIB_SEGSZ - 1) / QIB_SEGSZ;
+	for (; i < m; i++) {
+		mr->map[i] = kzalloc(sizeof *mr->map[0], GFP_KERNEL);
+		if (!mr->map[i])
+			goto bail;
+	}
+	mr->mapsz = m;
+	init_completion(&mr->comp);
+	/* count returning the ptr to user */
+	atomic_set(&mr->refcount, 1);
+	mr->pd = pd;
+	mr->max_segs = count;
+out:
+	return rval;
+bail:
+	while (i)
+		kfree(mr->map[--i]);
+	rval = -ENOMEM;
+	goto out;
+}
+
+static void deinit_qib_mregion(struct qib_mregion *mr)
+{
+	int i = mr->mapsz;
+
+	mr->mapsz = 0;
+	while (i)
+		kfree(mr->map[--i]);
+}
+
+
 /**
  * qib_get_dma_mr - get a DMA memory region
  * @pd: protection domain for this memory region
@@ -58,10 +95,9 @@ static inline struct qib_fmr *to_ifmr(struct ib_fmr *ibfmr)
  */
 struct ib_mr *qib_get_dma_mr(struct ib_pd *pd, int acc)
 {
-	struct qib_ibdev *dev = to_idev(pd->device);
-	struct qib_mr *mr;
+	struct qib_mr *mr = NULL;
 	struct ib_mr *ret;
-	unsigned long flags;
+	int rval;
 
 	if (to_ipd(pd)->user) {
 		ret = ERR_PTR(-EPERM);
@@ -74,61 +110,64 @@ struct ib_mr *qib_get_dma_mr(struct ib_pd *pd, int acc)
 		goto bail;
 	}
 
+	rval = init_qib_mregion(&mr->mr, pd, 0);
+	if (rval) {
+		ret = ERR_PTR(rval);
+		goto bail;
+	}
+
+
+	rval = qib_alloc_lkey(&mr->mr, 1);
+	if (rval) {
+		ret = ERR_PTR(rval);
+		goto bail_mregion;
+	}
+
 	mr->mr.access_flags = acc;
-	atomic_set(&mr->mr.refcount, 0);
-
-	spin_lock_irqsave(&dev->lk_table.lock, flags);
-	if (!dev->dma_mr)
-		dev->dma_mr = &mr->mr;
-	spin_unlock_irqrestore(&dev->lk_table.lock, flags);
-
 	ret = &mr->ibmr;
-
-bail:
+done:
 	return ret;
+
+bail_mregion:
+	deinit_qib_mregion(&mr->mr);
+bail:
+	kfree(mr);
+	goto done;
 }
 
-static struct qib_mr *alloc_mr(int count, struct qib_lkey_table *lk_table)
+static struct qib_mr *alloc_mr(int count, struct ib_pd *pd)
 {
 	struct qib_mr *mr;
-	int m, i = 0;
+	int rval = -ENOMEM;
+	int m;
 
 	/* Allocate struct plus pointers to first level page tables. */
 	m = (count + QIB_SEGSZ - 1) / QIB_SEGSZ;
-	mr = kmalloc(sizeof *mr + m * sizeof mr->mr.map[0], GFP_KERNEL);
+	mr = kzalloc(sizeof *mr + m * sizeof mr->mr.map[0], GFP_KERNEL);
 	if (!mr)
-		goto done;
-
-	/* Allocate first level page tables. */
-	for (; i < m; i++) {
-		mr->mr.map[i] = kmalloc(sizeof *mr->mr.map[0], GFP_KERNEL);
-		if (!mr->mr.map[i])
-			goto bail;
-	}
-	mr->mr.mapsz = m;
-	mr->mr.page_shift = 0;
-	mr->mr.max_segs = count;
+		goto bail;
 
+	rval = init_qib_mregion(&mr->mr, pd, count);
+	if (rval)
+		goto bail;
 	/*
 	 * ib_reg_phys_mr() will initialize mr->ibmr except for
 	 * lkey and rkey.
 	 */
-	if (!qib_alloc_lkey(lk_table, &mr->mr))
-		goto bail;
+	rval = qib_alloc_lkey(&mr->mr, 0);
+	if (rval)
+		goto bail_mregion;
 	mr->ibmr.lkey = mr->mr.lkey;
 	mr->ibmr.rkey = mr->mr.lkey;
-
-	atomic_set(&mr->mr.refcount, 0);
-	goto done;
-
-bail:
-	while (i)
-		kfree(mr->mr.map[--i]);
-	kfree(mr);
-	mr = NULL;
-
 done:
 	return mr;
+
+bail_mregion:
+	deinit_qib_mregion(&mr->mr);
+bail:
+	kfree(mr);
+	mr = ERR_PTR(rval);
+	goto done;
 }
 
 /**
@@ -148,19 +187,15 @@ struct ib_mr *qib_reg_phys_mr(struct ib_pd *pd,
 	int n, m, i;
 	struct ib_mr *ret;
 
-	mr = alloc_mr(num_phys_buf, &to_idev(pd->device)->lk_table);
-	if (mr == NULL) {
-		ret = ERR_PTR(-ENOMEM);
+	mr = alloc_mr(num_phys_buf, pd);
+	if (IS_ERR(mr)) {
+		ret = (struct ib_mr *)mr;
 		goto bail;
 	}
 
-	mr->mr.pd = pd;
 	mr->mr.user_base = *iova_start;
 	mr->mr.iova = *iova_start;
-	mr->mr.length = 0;
-	mr->mr.offset = 0;
 	mr->mr.access_flags = acc;
-	mr->umem = NULL;
 
 	m = 0;
 	n = 0;
@@ -186,7 +221,6 @@ bail:
  * @pd: protection domain for this memory region
  * @start: starting userspace address
  * @length: length of region to register
- * @virt_addr: virtual address to use (from HCA's point of view)
  * @mr_access_flags: access flags for this memory region
  * @udata: unused by the QLogic_IB driver
  *
@@ -216,14 +250,13 @@ struct ib_mr *qib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	list_for_each_entry(chunk, &umem->chunk_list, list)
 		n += chunk->nents;
 
-	mr = alloc_mr(n, &to_idev(pd->device)->lk_table);
-	if (!mr) {
-		ret = ERR_PTR(-ENOMEM);
+	mr = alloc_mr(n, pd);
+	if (IS_ERR(mr)) {
+		ret = (struct ib_mr *)mr;
 		ib_umem_release(umem);
 		goto bail;
 	}
 
-	mr->mr.pd = pd;
 	mr->mr.user_base = start;
 	mr->mr.iova = virt_addr;
 	mr->mr.length = length;
@@ -271,21 +304,25 @@ bail:
 int qib_dereg_mr(struct ib_mr *ibmr)
 {
 	struct qib_mr *mr = to_imr(ibmr);
-	struct qib_ibdev *dev = to_idev(ibmr->device);
-	int ret;
-	int i;
+	int ret = 0;
+	unsigned long timeout;
 
-	ret = qib_free_lkey(dev, &mr->mr);
-	if (ret)
-		return ret;
+	qib_free_lkey(&mr->mr);
 
-	i = mr->mr.mapsz;
-	while (i)
-		kfree(mr->mr.map[--i]);
+	qib_put_mr(&mr->mr); /* will set completion if last */
+	timeout = wait_for_completion_timeout(&mr->mr.comp,
+		5 * HZ);
+	if (!timeout) {
+		qib_get_mr(&mr->mr);
+		ret = -EBUSY;
+		goto out;
+	}
+	deinit_qib_mregion(&mr->mr);
 	if (mr->umem)
 		ib_umem_release(mr->umem);
 	kfree(mr);
-	return 0;
+out:
+	return ret;
 }
 
 /*
@@ -298,17 +335,9 @@ struct ib_mr *qib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len)
 {
 	struct qib_mr *mr;
 
-	mr = alloc_mr(max_page_list_len, &to_idev(pd->device)->lk_table);
-	if (mr == NULL)
-		return ERR_PTR(-ENOMEM);
-
-	mr->mr.pd = pd;
-	mr->mr.user_base = 0;
-	mr->mr.iova = 0;
-	mr->mr.length = 0;
-	mr->mr.offset = 0;
-	mr->mr.access_flags = 0;
-	mr->umem = NULL;
+	mr = alloc_mr(max_page_list_len, pd);
+	if (IS_ERR(mr))
+		return (struct ib_mr *)mr;
 
 	return &mr->ibmr;
 }
@@ -322,11 +351,11 @@ qib_alloc_fast_reg_page_list(struct ib_device *ibdev, int page_list_len)
 	if (size > PAGE_SIZE)
 		return ERR_PTR(-EINVAL);
 
-	pl = kmalloc(sizeof *pl, GFP_KERNEL);
+	pl = kzalloc(sizeof *pl, GFP_KERNEL);
 	if (!pl)
 		return ERR_PTR(-ENOMEM);
 
-	pl->page_list = kmalloc(size, GFP_KERNEL);
+	pl->page_list = kzalloc(size, GFP_KERNEL);
 	if (!pl->page_list)
 		goto err_free;
 
@@ -355,57 +384,47 @@ struct ib_fmr *qib_alloc_fmr(struct ib_pd *pd, int mr_access_flags,
 			     struct ib_fmr_attr *fmr_attr)
 {
 	struct qib_fmr *fmr;
-	int m, i = 0;
+	int m;
 	struct ib_fmr *ret;
+	int rval = -ENOMEM;
 
 	/* Allocate struct plus pointers to first level page tables. */
 	m = (fmr_attr->max_pages + QIB_SEGSZ - 1) / QIB_SEGSZ;
-	fmr = kmalloc(sizeof *fmr + m * sizeof fmr->mr.map[0], GFP_KERNEL);
+	fmr = kzalloc(sizeof *fmr + m * sizeof fmr->mr.map[0], GFP_KERNEL);
 	if (!fmr)
 		goto bail;
 
-	/* Allocate first level page tables. */
-	for (; i < m; i++) {
-		fmr->mr.map[i] = kmalloc(sizeof *fmr->mr.map[0],
-					 GFP_KERNEL);
-		if (!fmr->mr.map[i])
-			goto bail;
-	}
-	fmr->mr.mapsz = m;
+	rval = init_qib_mregion(&fmr->mr, pd, fmr_attr->max_pages);
+	if (rval)
+		goto bail;
 
 	/*
 	 * ib_alloc_fmr() will initialize fmr->ibfmr except for lkey &
 	 * rkey.
 	 */
-	if (!qib_alloc_lkey(&to_idev(pd->device)->lk_table, &fmr->mr))
-		goto bail;
+	rval = qib_alloc_lkey(&fmr->mr, 0);
+	if (rval)
+		goto bail_mregion;
 	fmr->ibfmr.rkey = fmr->mr.lkey;
 	fmr->ibfmr.lkey = fmr->mr.lkey;
 	/*
 	 * Resources are allocated but no valid mapping (RKEY can't be
 	 * used).
 	 */
-	fmr->mr.pd = pd;
-	fmr->mr.user_base = 0;
-	fmr->mr.iova = 0;
-	fmr->mr.length = 0;
-	fmr->mr.offset = 0;
 	fmr->mr.access_flags = mr_access_flags;
 	fmr->mr.max_segs = fmr_attr->max_pages;
 	fmr->mr.page_shift = fmr_attr->page_shift;
 
-	atomic_set(&fmr->mr.refcount, 0);
 	ret = &fmr->ibfmr;
-	goto done;
-
-bail:
-	while (i)
-		kfree(fmr->mr.map[--i]);
-	kfree(fmr);
-	ret = ERR_PTR(-ENOMEM);
-
 done:
 	return ret;
+
+bail_mregion:
+	deinit_qib_mregion(&fmr->mr);
+bail:
+	kfree(fmr);
+	ret = ERR_PTR(rval);
+	goto done;
 }
 
 /**
@@ -428,7 +447,8 @@ int qib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
 	u32 ps;
 	int ret;
 
-	if (atomic_read(&fmr->mr.refcount))
+	i = atomic_read(&fmr->mr.refcount);
+	if (i > 2)
 		return -EBUSY;
 
 	if (list_len > fmr->mr.max_segs) {
@@ -490,16 +510,20 @@ int qib_unmap_fmr(struct list_head *fmr_list)
 int qib_dealloc_fmr(struct ib_fmr *ibfmr)
 {
 	struct qib_fmr *fmr = to_ifmr(ibfmr);
-	int ret;
-	int i;
+	int ret = 0;
+	unsigned long timeout;
 
-	ret = qib_free_lkey(to_idev(ibfmr->device), &fmr->mr);
-	if (ret)
-		return ret;
-
-	i = fmr->mr.mapsz;
-	while (i)
-		kfree(fmr->mr.map[--i]);
+	qib_free_lkey(&fmr->mr);
+	qib_put_mr(&fmr->mr); /* will set completion if last */
+	timeout = wait_for_completion_timeout(&fmr->mr.comp,
+		5 * HZ);
+	if (!timeout) {
+		qib_get_mr(&fmr->mr);
+		ret = -EBUSY;
+		goto out;
+	}
+	deinit_qib_mregion(&fmr->mr);
 	kfree(fmr);
-	return 0;
+out:
+	return ret;
 }
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 1ce56b51ab1a..693041b076f0 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -406,18 +406,9 @@ static void clear_mr_refs(struct qib_qp *qp, int clr_sends)
 	unsigned n;
 
 	if (test_and_clear_bit(QIB_R_REWIND_SGE, &qp->r_aflags))
-		while (qp->s_rdma_read_sge.num_sge) {
-			atomic_dec(&qp->s_rdma_read_sge.sge.mr->refcount);
-			if (--qp->s_rdma_read_sge.num_sge)
-				qp->s_rdma_read_sge.sge =
-					*qp->s_rdma_read_sge.sg_list++;
-		}
+		qib_put_ss(&qp->s_rdma_read_sge);
 
-	while (qp->r_sge.num_sge) {
-		atomic_dec(&qp->r_sge.sge.mr->refcount);
-		if (--qp->r_sge.num_sge)
-			qp->r_sge.sge = *qp->r_sge.sg_list++;
-	}
+	qib_put_ss(&qp->r_sge);
 
 	if (clr_sends) {
 		while (qp->s_last != qp->s_head) {
@@ -427,7 +418,7 @@ static void clear_mr_refs(struct qib_qp *qp, int clr_sends)
 			for (i = 0; i < wqe->wr.num_sge; i++) {
 				struct qib_sge *sge = &wqe->sg_list[i];
 
-				atomic_dec(&sge->mr->refcount);
+				qib_put_mr(sge->mr);
 			}
 			if (qp->ibqp.qp_type == IB_QPT_UD ||
 			    qp->ibqp.qp_type == IB_QPT_SMI ||
@@ -437,7 +428,7 @@ static void clear_mr_refs(struct qib_qp *qp, int clr_sends)
 				qp->s_last = 0;
 		}
 		if (qp->s_rdma_mr) {
-			atomic_dec(&qp->s_rdma_mr->refcount);
+			qib_put_mr(qp->s_rdma_mr);
 			qp->s_rdma_mr = NULL;
 		}
 	}
@@ -450,7 +441,7 @@ static void clear_mr_refs(struct qib_qp *qp, int clr_sends)
 
 		if (e->opcode == IB_OPCODE_RC_RDMA_READ_REQUEST &&
 		    e->rdma_sge.mr) {
-			atomic_dec(&e->rdma_sge.mr->refcount);
+			qib_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}
 	}
@@ -495,7 +486,7 @@ int qib_error_qp(struct qib_qp *qp, enum ib_wc_status err)
 	if (!(qp->s_flags & QIB_S_BUSY)) {
 		qp->s_hdrwords = 0;
 		if (qp->s_rdma_mr) {
-			atomic_dec(&qp->s_rdma_mr->refcount);
+			qib_put_mr(qp->s_rdma_mr);
 			qp->s_rdma_mr = NULL;
 		}
 		if (qp->s_tx) {
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index b641416148eb..3ab341320ead 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -95,7 +95,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct qib_qp *qp,
 	case OP(RDMA_READ_RESPONSE_ONLY):
 		e = &qp->s_ack_queue[qp->s_tail_ack_queue];
 		if (e->rdma_sge.mr) {
-			atomic_dec(&e->rdma_sge.mr->refcount);
+			qib_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}
 		/* FALLTHROUGH */
@@ -133,7 +133,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct qib_qp *qp,
 			/* Copy SGE state in case we need to resend */
 			qp->s_rdma_mr = e->rdma_sge.mr;
 			if (qp->s_rdma_mr)
-				atomic_inc(&qp->s_rdma_mr->refcount);
+				qib_get_mr(qp->s_rdma_mr);
 			qp->s_ack_rdma_sge.sge = e->rdma_sge;
 			qp->s_ack_rdma_sge.num_sge = 1;
 			qp->s_cur_sge = &qp->s_ack_rdma_sge;
@@ -172,7 +172,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct qib_qp *qp,
 		qp->s_cur_sge = &qp->s_ack_rdma_sge;
 		qp->s_rdma_mr = qp->s_ack_rdma_sge.sge.mr;
 		if (qp->s_rdma_mr)
-			atomic_inc(&qp->s_rdma_mr->refcount);
+			qib_get_mr(qp->s_rdma_mr);
 		len = qp->s_ack_rdma_sge.sge.sge_length;
 		if (len > pmtu)
 			len = pmtu;
@@ -1012,7 +1012,7 @@ void qib_rc_send_complete(struct qib_qp *qp, struct qib_ib_header *hdr)
 		for (i = 0; i < wqe->wr.num_sge; i++) {
 			struct qib_sge *sge = &wqe->sg_list[i];
 
-			atomic_dec(&sge->mr->refcount);
+			qib_put_mr(sge->mr);
 		}
 		/* Post a send completion queue entry if requested. */
 		if (!(qp->s_flags & QIB_S_SIGNAL_REQ_WR) ||
@@ -1068,7 +1068,7 @@ static struct qib_swqe *do_rc_completion(struct qib_qp *qp,
 		for (i = 0; i < wqe->wr.num_sge; i++) {
 			struct qib_sge *sge = &wqe->sg_list[i];
 
-			atomic_dec(&sge->mr->refcount);
+			qib_put_mr(sge->mr);
 		}
 		/* Post a send completion queue entry if requested. */
 		if (!(qp->s_flags & QIB_S_SIGNAL_REQ_WR) ||
@@ -1730,7 +1730,7 @@ static int qib_rc_rcv_error(struct qib_other_headers *ohdr,
 		if (unlikely(offset + len != e->rdma_sge.sge_length))
 			goto unlock_done;
 		if (e->rdma_sge.mr) {
-			atomic_dec(&e->rdma_sge.mr->refcount);
+			qib_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}
 		if (len != 0) {
@@ -2024,11 +2024,7 @@ send_last:
 		if (unlikely(wc.byte_len > qp->r_len))
 			goto nack_inv;
 		qib_copy_sge(&qp->r_sge, data, tlen, 1);
-		while (qp->r_sge.num_sge) {
-			atomic_dec(&qp->r_sge.sge.mr->refcount);
-			if (--qp->r_sge.num_sge)
-				qp->r_sge.sge = *qp->r_sge.sg_list++;
-		}
+		qib_put_ss(&qp->r_sge);
 		qp->r_msn++;
 		if (!test_and_clear_bit(QIB_R_WRID_VALID, &qp->r_aflags))
 			break;
@@ -2116,7 +2112,7 @@ send_last:
 		}
 		e = &qp->s_ack_queue[qp->r_head_ack_queue];
 		if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) {
-			atomic_dec(&e->rdma_sge.mr->refcount);
+			qib_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}
 		reth = &ohdr->u.rc.reth;
@@ -2188,7 +2184,7 @@ send_last:
 		}
 		e = &qp->s_ack_queue[qp->r_head_ack_queue];
 		if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) {
-			atomic_dec(&e->rdma_sge.mr->refcount);
+			qib_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}
 		ateth = &ohdr->u.atomic_eth;
@@ -2210,7 +2206,7 @@ send_last:
 			(u64) cmpxchg((u64 *) qp->r_sge.sge.vaddr,
 				      be64_to_cpu(ateth->compare_data),
 				      sdata);
-		atomic_dec(&qp->r_sge.sge.mr->refcount);
+		qib_put_mr(qp->r_sge.sge.mr);
 		qp->r_sge.num_sge = 0;
 		e->opcode = opcode;
 		e->sent = 0;
diff --git a/drivers/infiniband/hw/qib/qib_ruc.c b/drivers/infiniband/hw/qib/qib_ruc.c
index c0ee7e095d81..357b6cfcd46c 100644
--- a/drivers/infiniband/hw/qib/qib_ruc.c
+++ b/drivers/infiniband/hw/qib/qib_ruc.c
@@ -110,7 +110,7 @@ bad_lkey:
 	while (j) {
 		struct qib_sge *sge = --j ? &ss->sg_list[j - 1] : &ss->sge;
 
-		atomic_dec(&sge->mr->refcount);
+		qib_put_mr(sge->mr);
 	}
 	ss->num_sge = 0;
 	memset(&wc, 0, sizeof(wc));
@@ -501,7 +501,7 @@ again:
 			(u64) atomic64_add_return(sdata, maddr) - sdata :
 			(u64) cmpxchg((u64 *) qp->r_sge.sge.vaddr,
 				      sdata, wqe->wr.wr.atomic.swap);
-		atomic_dec(&qp->r_sge.sge.mr->refcount);
+		qib_put_mr(qp->r_sge.sge.mr);
 		qp->r_sge.num_sge = 0;
 		goto send_comp;
 
@@ -525,7 +525,7 @@ again:
 		sge->sge_length -= len;
 		if (sge->sge_length == 0) {
 			if (!release)
-				atomic_dec(&sge->mr->refcount);
+				qib_put_mr(sge->mr);
 			if (--sqp->s_sge.num_sge)
 				*sge = *sqp->s_sge.sg_list++;
 		} else if (sge->length == 0 && sge->mr->lkey) {
@@ -542,11 +542,7 @@ again:
 		sqp->s_len -= len;
 	}
 	if (release)
-		while (qp->r_sge.num_sge) {
-			atomic_dec(&qp->r_sge.sge.mr->refcount);
-			if (--qp->r_sge.num_sge)
-				qp->r_sge.sge = *qp->r_sge.sg_list++;
-		}
+		qib_put_ss(&qp->r_sge);
 
 	if (!test_and_clear_bit(QIB_R_WRID_VALID, &qp->r_aflags))
 		goto send_comp;
@@ -782,7 +778,7 @@ void qib_send_complete(struct qib_qp *qp, struct qib_swqe *wqe,
 	for (i = 0; i < wqe->wr.num_sge; i++) {
 		struct qib_sge *sge = &wqe->sg_list[i];
 
-		atomic_dec(&sge->mr->refcount);
+		qib_put_mr(sge->mr);
 	}
 	if (qp->ibqp.qp_type == IB_QPT_UD ||
 	    qp->ibqp.qp_type == IB_QPT_SMI ||
diff --git a/drivers/infiniband/hw/qib/qib_uc.c b/drivers/infiniband/hw/qib/qib_uc.c
index 70b4cb710f9a..aa3a8035bb68 100644
--- a/drivers/infiniband/hw/qib/qib_uc.c
+++ b/drivers/infiniband/hw/qib/qib_uc.c
@@ -281,11 +281,7 @@ inv:
 			set_bit(QIB_R_REWIND_SGE, &qp->r_aflags);
 			qp->r_sge.num_sge = 0;
 		} else
-			while (qp->r_sge.num_sge) {
-				atomic_dec(&qp->r_sge.sge.mr->refcount);
-				if (--qp->r_sge.num_sge)
-					qp->r_sge.sge = *qp->r_sge.sg_list++;
-			}
+			qib_put_ss(&qp->r_sge);
 		qp->r_state = OP(SEND_LAST);
 		switch (opcode) {
 		case OP(SEND_FIRST):
@@ -404,12 +400,7 @@ send_last:
 			goto rewind;
 		wc.opcode = IB_WC_RECV;
 		qib_copy_sge(&qp->r_sge, data, tlen, 0);
-		while (qp->s_rdma_read_sge.num_sge) {
-			atomic_dec(&qp->s_rdma_read_sge.sge.mr->refcount);
-			if (--qp->s_rdma_read_sge.num_sge)
-				qp->s_rdma_read_sge.sge =
-					*qp->s_rdma_read_sge.sg_list++;
-		}
+		qib_put_ss(&qp->s_rdma_read_sge);
 last_imm:
 		wc.wr_id = qp->r_wr_id;
 		wc.status = IB_WC_SUCCESS;
@@ -493,13 +484,7 @@ rdma_last_imm:
 		if (unlikely(tlen + qp->r_rcv_len != qp->r_len))
 			goto drop;
 		if (test_and_clear_bit(QIB_R_REWIND_SGE, &qp->r_aflags))
-			while (qp->s_rdma_read_sge.num_sge) {
-				atomic_dec(&qp->s_rdma_read_sge.sge.mr->
-					   refcount);
-				if (--qp->s_rdma_read_sge.num_sge)
-					qp->s_rdma_read_sge.sge =
-						*qp->s_rdma_read_sge.sg_list++;
-			}
+			qib_put_ss(&qp->s_rdma_read_sge);
 		else {
 			ret = qib_get_rwqe(qp, 1);
 			if (ret < 0)
@@ -510,11 +495,7 @@ rdma_last_imm:
 		wc.byte_len = qp->r_len;
 		wc.opcode = IB_WC_RECV_RDMA_WITH_IMM;
 		qib_copy_sge(&qp->r_sge, data, tlen, 1);
-		while (qp->r_sge.num_sge) {
-			atomic_dec(&qp->r_sge.sge.mr->refcount);
-			if (--qp->r_sge.num_sge)
-				qp->r_sge.sge = *qp->r_sge.sg_list++;
-		}
+		qib_put_ss(&qp->r_sge);
 		goto last_imm;
 
 	case OP(RDMA_WRITE_LAST):
@@ -530,11 +511,7 @@ rdma_last:
 		if (unlikely(tlen + qp->r_rcv_len != qp->r_len))
 			goto drop;
 		qib_copy_sge(&qp->r_sge, data, tlen, 1);
-		while (qp->r_sge.num_sge) {
-			atomic_dec(&qp->r_sge.sge.mr->refcount);
-			if (--qp->r_sge.num_sge)
-				qp->r_sge.sge = *qp->r_sge.sg_list++;
-		}
+		qib_put_ss(&qp->r_sge);
 		break;
 
 	default:
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index a468bf2d4465..d6c7fe7f88d5 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -194,11 +194,7 @@ static void qib_ud_loopback(struct qib_qp *sqp, struct qib_swqe *swqe)
 		}
 		length -= len;
 	}
-	while (qp->r_sge.num_sge) {
-		atomic_dec(&qp->r_sge.sge.mr->refcount);
-		if (--qp->r_sge.num_sge)
-			qp->r_sge.sge = *qp->r_sge.sg_list++;
-	}
+	qib_put_ss(&qp->r_sge);
 	if (!test_and_clear_bit(QIB_R_WRID_VALID, &qp->r_aflags))
 		goto bail_unlock;
 	wc.wr_id = qp->r_wr_id;
@@ -556,11 +552,7 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct qib_ib_header *hdr,
 	} else
 		qib_skip_sge(&qp->r_sge, sizeof(struct ib_grh), 1);
 	qib_copy_sge(&qp->r_sge, data, wc.byte_len - sizeof(struct ib_grh), 1);
-	while (qp->r_sge.num_sge) {
-		atomic_dec(&qp->r_sge.sge.mr->refcount);
-		if (--qp->r_sge.num_sge)
-			qp->r_sge.sge = *qp->r_sge.sg_list++;
-	}
+	qib_put_ss(&qp->r_sge);
 	if (!test_and_clear_bit(QIB_R_WRID_VALID, &qp->r_aflags))
 		return;
 	wc.wr_id = qp->r_wr_id;
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index 7b6c3bffa9d9..76d7ce8a8c6e 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -183,7 +183,7 @@ void qib_copy_sge(struct qib_sge_state *ss, void *data, u32 length, int release)
 		sge->sge_length -= len;
 		if (sge->sge_length == 0) {
 			if (release)
-				atomic_dec(&sge->mr->refcount);
+				qib_put_mr(sge->mr);
 			if (--ss->num_sge)
 				*sge = *ss->sg_list++;
 		} else if (sge->length == 0 && sge->mr->lkey) {
@@ -224,7 +224,7 @@ void qib_skip_sge(struct qib_sge_state *ss, u32 length, int release)
 		sge->sge_length -= len;
 		if (sge->sge_length == 0) {
 			if (release)
-				atomic_dec(&sge->mr->refcount);
+				qib_put_mr(sge->mr);
 			if (--ss->num_sge)
 				*sge = *ss->sg_list++;
 		} else if (sge->length == 0 && sge->mr->lkey) {
@@ -435,7 +435,7 @@ bail_inval_free:
 	while (j) {
 		struct qib_sge *sge = &wqe->sg_list[--j];
 
-		atomic_dec(&sge->mr->refcount);
+		qib_put_mr(sge->mr);
 	}
 bail_inval:
 	ret = -EINVAL;
@@ -978,7 +978,7 @@ void qib_put_txreq(struct qib_verbs_txreq *tx)
 	if (atomic_dec_and_test(&qp->refcount))
 		wake_up(&qp->wait);
 	if (tx->mr) {
-		atomic_dec(&tx->mr->refcount);
+		qib_put_mr(tx->mr);
 		tx->mr = NULL;
 	}
 	if (tx->txreq.flags & QIB_SDMA_TXREQ_F_FREEBUF) {
@@ -1336,7 +1336,7 @@ done:
 	}
 	qib_sendbuf_done(dd, pbufn);
 	if (qp->s_rdma_mr) {
-		atomic_dec(&qp->s_rdma_mr->refcount);
+		qib_put_mr(qp->s_rdma_mr);
 		qp->s_rdma_mr = NULL;
 	}
 	if (qp->s_wqe) {
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index 487606024659..4a2277bc059e 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -41,6 +41,7 @@
 #include <linux/interrupt.h>
 #include <linux/kref.h>
 #include <linux/workqueue.h>
+#include <linux/completion.h>
 #include <rdma/ib_pack.h>
 #include <rdma/ib_user_verbs.h>
 
@@ -302,6 +303,8 @@ struct qib_mregion {
 	u32 max_segs;           /* number of qib_segs in all the arrays */
 	u32 mapsz;              /* size of the map array */
 	u8  page_shift;         /* 0 - non unform/non powerof2 sizes */
+	u8  lkey_published;	/* in global table */
+	struct completion comp; /* complete when refcount goes to zero */
 	atomic_t refcount;
 	struct qib_segarray *map[0];    /* the segments */
 };
@@ -944,9 +947,9 @@ int qib_post_ud_send(struct qib_qp *qp, struct ib_send_wr *wr);
 void qib_ud_rcv(struct qib_ibport *ibp, struct qib_ib_header *hdr,
 		int has_grh, void *data, u32 tlen, struct qib_qp *qp);
 
-int qib_alloc_lkey(struct qib_lkey_table *rkt, struct qib_mregion *mr);
+int qib_alloc_lkey(struct qib_mregion *mr, int dma_region);
 
-int qib_free_lkey(struct qib_ibdev *dev, struct qib_mregion *mr);
+void qib_free_lkey(struct qib_mregion *mr);
 
 int qib_lkey_ok(struct qib_lkey_table *rkt, struct qib_pd *pd,
 		struct qib_sge *isge, struct ib_sge *sge, int acc);
@@ -1014,6 +1017,27 @@ int qib_unmap_fmr(struct list_head *fmr_list);
 
 int qib_dealloc_fmr(struct ib_fmr *ibfmr);
 
+static inline void qib_get_mr(struct qib_mregion *mr)
+{
+	atomic_inc(&mr->refcount);
+}
+
+static inline void qib_put_mr(struct qib_mregion *mr)
+{
+	if (unlikely(atomic_dec_and_test(&mr->refcount)))
+		complete(&mr->comp);
+}
+
+static inline void qib_put_ss(struct qib_sge_state *ss)
+{
+	while (ss->num_sge) {
+		qib_put_mr(ss->sge.mr);
+		if (--ss->num_sge)
+			ss->sge = *ss->sg_list++;
+	}
+}
+
+
 void qib_release_mmap_info(struct kref *ref);
 
 struct qib_mmap_info *qib_create_mmap_info(struct qib_ibdev *dev, u32 size,