Merge branch 'sg_nents' into rdma.git for-next

From Maor Gottlieb
====================

Fix the use of nents and orig_nents in the sg table append helpers. The
nents should be used by the DMA layer to store the number of DMA mapped
sges, the orig_nents is the number of CPU sges.

Since the sg append logic doesn't always create a SGL with exactly
orig_nents entries store a total_nents as well to allow the table to be
properly free'd and reorganize the freeing logic to share across all the
use cases.

====================

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

* 'sg_nents':
  RDMA: Use the sg_table directly and remove the opencoded version from umem
  lib/scatterlist: Fix wrong update of orig_nents
  lib/scatterlist: Provide a dedicated function to support table append

3 files changed, 13 insertions, 8 deletions

diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 6c8c910f4e86..c7e8d7b3baa1 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -967,6 +967,12 @@ int c4iw_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 	return !err || err == -ENODATA ? npolled : err;
 }
 
+void c4iw_cq_rem_ref(struct c4iw_cq *chp)
+{
+	if (refcount_dec_and_test(&chp->refcnt))
+		complete(&chp->cq_rel_comp);
+}
+
 int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 {
 	struct c4iw_cq *chp;
@@ -976,8 +982,8 @@ int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 	chp = to_c4iw_cq(ib_cq);
 
 	xa_erase_irq(&chp->rhp->cqs, chp->cq.cqid);
-	refcount_dec(&chp->refcnt);
-	wait_event(chp->wait, !refcount_read(&chp->refcnt));
+	c4iw_cq_rem_ref(chp);
+	wait_for_completion(&chp->cq_rel_comp);
 
 	ucontext = rdma_udata_to_drv_context(udata, struct c4iw_ucontext,
 					     ibucontext);
@@ -1081,7 +1087,7 @@ int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	spin_lock_init(&chp->lock);
 	spin_lock_init(&chp->comp_handler_lock);
 	refcount_set(&chp->refcnt, 1);
-	init_waitqueue_head(&chp->wait);
+	init_completion(&chp->cq_rel_comp);
 	ret = xa_insert_irq(&rhp->cqs, chp->cq.cqid, chp, GFP_KERNEL);
 	if (ret)
 		goto err_destroy_cq;
diff --git a/drivers/infiniband/hw/cxgb4/ev.c b/drivers/infiniband/hw/cxgb4/ev.c
index 7798d090888b..34211a533d5c 100644
--- a/drivers/infiniband/hw/cxgb4/ev.c
+++ b/drivers/infiniband/hw/cxgb4/ev.c
@@ -213,8 +213,7 @@ void c4iw_ev_dispatch(struct c4iw_dev *dev, struct t4_cqe *err_cqe)
 		break;
 	}
 done:
-	if (refcount_dec_and_test(&chp->refcnt))
-		wake_up(&chp->wait);
+	c4iw_cq_rem_ref(chp);
 	c4iw_qp_rem_ref(&qhp->ibqp);
 out:
 	return;
@@ -234,8 +233,7 @@ int c4iw_ev_handler(struct c4iw_dev *dev, u32 qid)
 		spin_lock_irqsave(&chp->comp_handler_lock, flag);
 		(*chp->ibcq.comp_handler)(&chp->ibcq, chp->ibcq.cq_context);
 		spin_unlock_irqrestore(&chp->comp_handler_lock, flag);
-		if (refcount_dec_and_test(&chp->refcnt))
-			wake_up(&chp->wait);
+		c4iw_cq_rem_ref(chp);
 	} else {
 		pr_debug("unknown cqid 0x%x\n", qid);
 		xa_unlock_irqrestore(&dev->cqs, flag);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 6a2a415ec791..12f33467c672 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -428,7 +428,7 @@ struct c4iw_cq {
 	spinlock_t lock;
 	spinlock_t comp_handler_lock;
 	refcount_t refcnt;
-	wait_queue_head_t wait;
+	struct completion cq_rel_comp;
 	struct c4iw_wr_wait *wr_waitp;
 };
 
@@ -979,6 +979,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start,
 struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc);
 int c4iw_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata);
 int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
+void c4iw_cq_rem_ref(struct c4iw_cq *chp);
 int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		   struct ib_udata *udata);
 int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);