RDMA: Globally allocate and release QP memory

Convert QP object to follow IB/core general allocation scheme.  That
change allows us to make sure that restrack properly kref the memory.

Link: https://lore.kernel.org/r/48e767124758aeecc433360ddd85eaa6325b34d9.1627040189.git.leonro@nvidia.com
Reviewed-by: Gal Pressman <[email protected]> #efa
Tested-by: Gal Pressman <[email protected]>
Reviewed-by: Dennis Dalessandro <[email protected]> #rdma and core
Tested-by: Dennis Dalessandro <[email protected]>
Signed-off-by: Leon Romanovsky <[email protected]>
Tested-by: Tatyana Nikolova <[email protected]>
Signed-off-by: Jason Gunthorpe <[email protected]>

Author: rleon

drivers/infiniband/core/core_priv.h

@@ -322,13 +322,14 @@ _ib_create_qp(struct ib_device *dev, struct ib_pd *pd,
 	      struct ib_uqp_object *uobj, const char *caller)
 {
 	struct ib_qp *qp;
+	int ret;
 
 	if (!dev->ops.create_qp)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	qp = dev->ops.create_qp(pd, attr, udata);
-	if (IS_ERR(qp))
-		return qp;
+	qp = rdma_zalloc_drv_obj_numa(dev, ib_qp);
+	if (!qp)
+		return ERR_PTR(-ENOMEM);
 
 	qp->device = dev;
 	qp->pd = pd;
@@ -337,23 +338,36 @@ _ib_create_qp(struct ib_device *dev, struct ib_pd *pd,
 
 	qp->qp_type = attr->qp_type;
 	qp->rwq_ind_tbl = attr->rwq_ind_tbl;
-	qp->send_cq = attr->send_cq;
-	qp->recv_cq = attr->recv_cq;
 	qp->srq = attr->srq;
-	qp->rwq_ind_tbl = attr->rwq_ind_tbl;
 	qp->event_handler = attr->event_handler;
 	qp->port = attr->port_num;
 
-	atomic_set(&qp->usecnt, 0);
 	spin_lock_init(&qp->mr_lock);
 	INIT_LIST_HEAD(&qp->rdma_mrs);
 	INIT_LIST_HEAD(&qp->sig_mrs);
 
 	rdma_restrack_new(&qp->res, RDMA_RESTRACK_QP);
 	WARN_ONCE(!udata && !caller, "Missing kernel QP owner");
 	rdma_restrack_set_name(&qp->res, udata ? NULL : caller);
+	ret = dev->ops.create_qp(qp, attr, udata);
+	if (ret)
+		goto err_create;
+
+	/*
+	 * TODO: The mlx4 internally overwrites send_cq and recv_cq.
+	 * Unfortunately, it is not an easy task to fix that driver.
+	 */
+	qp->send_cq = attr->send_cq;
+	qp->recv_cq = attr->recv_cq;
+
 	rdma_restrack_add(&qp->res);
 	return qp;
+
+err_create:
+	rdma_restrack_put(&qp->res);
+	kfree(qp);
+	return ERR_PTR(ret);
+
 }
 
 struct rdma_dev_addr;

drivers/infiniband/core/device.c

@@ -2654,6 +2654,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, get_hw_stats);
 	SET_DEVICE_OP(dev_ops, get_link_layer);
 	SET_DEVICE_OP(dev_ops, get_netdev);
+	SET_DEVICE_OP(dev_ops, get_numa_node);
 	SET_DEVICE_OP(dev_ops, get_port_immutable);
 	SET_DEVICE_OP(dev_ops, get_vector_affinity);
 	SET_DEVICE_OP(dev_ops, get_vf_config);
@@ -2710,6 +2711,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_OBJ_SIZE(dev_ops, ib_cq);
 	SET_OBJ_SIZE(dev_ops, ib_mw);
 	SET_OBJ_SIZE(dev_ops, ib_pd);
+	SET_OBJ_SIZE(dev_ops, ib_qp);
 	SET_OBJ_SIZE(dev_ops, ib_rwq_ind_table);
 	SET_OBJ_SIZE(dev_ops, ib_srq);
 	SET_OBJ_SIZE(dev_ops, ib_ucontext);

drivers/infiniband/core/restrack.c

@@ -343,7 +343,7 @@ void rdma_restrack_del(struct rdma_restrack_entry *res)
 	rt = &dev->res[res->type];
 
 	old = xa_erase(&rt->xa, res->id);
-	if (res->type == RDMA_RESTRACK_MR || res->type == RDMA_RESTRACK_QP)
+	if (res->type == RDMA_RESTRACK_MR)
 		return;
 	WARN_ON(old != res);
 

drivers/infiniband/core/verbs.c

@@ -1963,30 +1963,32 @@ int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata)
 		rdma_rw_cleanup_mrs(qp);
 
 	rdma_counter_unbind_qp(qp, true);
-	rdma_restrack_del(&qp->res);
 	ret = qp->device->ops.destroy_qp(qp, udata);
-	if (!ret) {
-		if (alt_path_sgid_attr)
-			rdma_put_gid_attr(alt_path_sgid_attr);
-		if (av_sgid_attr)
-			rdma_put_gid_attr(av_sgid_attr);
-		if (pd)
-			atomic_dec(&pd->usecnt);
-		if (scq)
-			atomic_dec(&scq->usecnt);
-		if (rcq)
-			atomic_dec(&rcq->usecnt);
-		if (srq)
-			atomic_dec(&srq->usecnt);
-		if (ind_tbl)
-			atomic_dec(&ind_tbl->usecnt);
-		if (sec)
-			ib_destroy_qp_security_end(sec);
-	} else {
+	if (ret) {
 		if (sec)
 			ib_destroy_qp_security_abort(sec);
+		return ret;
 	}
 
+	if (alt_path_sgid_attr)
+		rdma_put_gid_attr(alt_path_sgid_attr);
+	if (av_sgid_attr)
+		rdma_put_gid_attr(av_sgid_attr);
+	if (pd)
+		atomic_dec(&pd->usecnt);
+	if (scq)
+		atomic_dec(&scq->usecnt);
+	if (rcq)
+		atomic_dec(&rcq->usecnt);
+	if (srq)
+		atomic_dec(&srq->usecnt);
+	if (ind_tbl)
+		atomic_dec(&ind_tbl->usecnt);
+	if (sec)
+		ib_destroy_qp_security_end(sec);
+
+	rdma_restrack_del(&qp->res);
+	kfree(qp);
 	return ret;
 }
 EXPORT_SYMBOL(ib_destroy_qp_user);

drivers/infiniband/hw/bnxt_re/ib_verbs.c

@@ -815,7 +815,7 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 	if (ib_qp->qp_type == IB_QPT_GSI && rdev->gsi_ctx.gsi_sqp) {
 		rc = bnxt_re_destroy_gsi_sqp(qp);
 		if (rc)
-			goto sh_fail;
+			return rc;
 	}
 
 	mutex_lock(&rdev->qp_lock);
@@ -826,10 +826,7 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 	ib_umem_release(qp->rumem);
 	ib_umem_release(qp->sumem);
 
-	kfree(qp);
 	return 0;
-sh_fail:
-	return rc;
 }
 
 static u8 __from_ib_qp_type(enum ib_qp_type type)
@@ -1402,27 +1399,22 @@ static bool bnxt_re_test_qp_limits(struct bnxt_re_dev *rdev,
 	return rc;
 }
 
-struct ib_qp *bnxt_re_create_qp(struct ib_pd *ib_pd,
-				struct ib_qp_init_attr *qp_init_attr,
-				struct ib_udata *udata)
+int bnxt_re_create_qp(struct ib_qp *ib_qp, struct ib_qp_init_attr *qp_init_attr,
+		      struct ib_udata *udata)
 {
+	struct ib_pd *ib_pd = ib_qp->pd;
 	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
 	struct bnxt_re_dev *rdev = pd->rdev;
 	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
-	struct bnxt_re_qp *qp;
+	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
 	int rc;
 
 	rc = bnxt_re_test_qp_limits(rdev, qp_init_attr, dev_attr);
 	if (!rc) {
 		rc = -EINVAL;
-		goto exit;
+		goto fail;
 	}
 
-	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
-	if (!qp) {
-		rc = -ENOMEM;
-		goto exit;
-	}
 	qp->rdev = rdev;
 	rc = bnxt_re_init_qp_attr(qp, pd, qp_init_attr, udata);
 	if (rc)
@@ -1465,16 +1457,14 @@ struct ib_qp *bnxt_re_create_qp(struct ib_pd *ib_pd,
 	mutex_unlock(&rdev->qp_lock);
 	atomic_inc(&rdev->qp_count);
 
-	return &qp->ib_qp;
+	return 0;
 qp_destroy:
 	bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp);
 free_umem:
 	ib_umem_release(qp->rumem);
 	ib_umem_release(qp->sumem);
 fail:
-	kfree(qp);
-exit:
-	return ERR_PTR(rc);
+	return rc;
 }
 
 static u8 __from_ib_qp_state(enum ib_qp_state state)

drivers/infiniband/hw/bnxt_re/ib_verbs.h

@@ -78,9 +78,9 @@ struct bnxt_re_srq {
 };
 
 struct bnxt_re_qp {
+	struct ib_qp		ib_qp;
 	struct list_head	list;
 	struct bnxt_re_dev	*rdev;
-	struct ib_qp		ib_qp;
 	spinlock_t		sq_lock;	/* protect sq */
 	spinlock_t		rq_lock;	/* protect rq */
 	struct bnxt_qplib_qp	qplib_qp;
@@ -179,9 +179,8 @@ int bnxt_re_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
 int bnxt_re_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
 int bnxt_re_post_srq_recv(struct ib_srq *srq, const struct ib_recv_wr *recv_wr,
 			  const struct ib_recv_wr **bad_recv_wr);
-struct ib_qp *bnxt_re_create_qp(struct ib_pd *pd,
-				struct ib_qp_init_attr *qp_init_attr,
-				struct ib_udata *udata);
+int bnxt_re_create_qp(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr,
+		      struct ib_udata *udata);
 int bnxt_re_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
 		      int qp_attr_mask, struct ib_udata *udata);
 int bnxt_re_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,

drivers/infiniband/hw/bnxt_re/main.c

@@ -709,6 +709,7 @@ static const struct ib_device_ops bnxt_re_dev_ops = {
 	INIT_RDMA_OBJ_SIZE(ib_ah, bnxt_re_ah, ib_ah),
 	INIT_RDMA_OBJ_SIZE(ib_cq, bnxt_re_cq, ib_cq),
 	INIT_RDMA_OBJ_SIZE(ib_pd, bnxt_re_pd, ib_pd),
+	INIT_RDMA_OBJ_SIZE(ib_qp, bnxt_re_qp, ib_qp),
 	INIT_RDMA_OBJ_SIZE(ib_srq, bnxt_re_srq, ib_srq),
 	INIT_RDMA_OBJ_SIZE(ib_ucontext, bnxt_re_ucontext, ib_uctx),
 };

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

@@ -989,9 +989,8 @@ int c4iw_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata);
 int c4iw_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *attrs,
 		    struct ib_udata *udata);
 int c4iw_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata);
-struct ib_qp *c4iw_create_qp(struct ib_pd *pd,
-			     struct ib_qp_init_attr *attrs,
-			     struct ib_udata *udata);
+int c4iw_create_qp(struct ib_qp *qp, struct ib_qp_init_attr *attrs,
+		   struct ib_udata *udata);
 int c4iw_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 				 int attr_mask, struct ib_udata *udata);
 int c4iw_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,

drivers/infiniband/hw/cxgb4/provider.c

@@ -499,6 +499,7 @@ static const struct ib_device_ops c4iw_dev_ops = {
 	INIT_RDMA_OBJ_SIZE(ib_cq, c4iw_cq, ibcq),
 	INIT_RDMA_OBJ_SIZE(ib_mw, c4iw_mw, ibmw),
 	INIT_RDMA_OBJ_SIZE(ib_pd, c4iw_pd, ibpd),
+	INIT_RDMA_OBJ_SIZE(ib_qp, c4iw_qp, ibqp),
 	INIT_RDMA_OBJ_SIZE(ib_srq, c4iw_srq, ibsrq),
 	INIT_RDMA_OBJ_SIZE(ib_ucontext, c4iw_ucontext, ibucontext),
 };

drivers/infiniband/hw/cxgb4/qp.c

@@ -2103,16 +2103,15 @@ int c4iw_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 		   ucontext ? &ucontext->uctx : &rhp->rdev.uctx, !qhp->srq);
 
 	c4iw_put_wr_wait(qhp->wr_waitp);
-
-	kfree(qhp);
 	return 0;
 }
 
-struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
-			     struct ib_udata *udata)
+int c4iw_create_qp(struct ib_qp *qp, struct ib_qp_init_attr *attrs,
+		   struct ib_udata *udata)
 {
+	struct ib_pd *pd = qp->pd;
 	struct c4iw_dev *rhp;
-	struct c4iw_qp *qhp;
+	struct c4iw_qp *qhp = to_c4iw_qp(qp);
 	struct c4iw_pd *php;
 	struct c4iw_cq *schp;
 	struct c4iw_cq *rchp;
@@ -2124,44 +2123,36 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	struct c4iw_mm_entry *sq_key_mm, *rq_key_mm = NULL, *sq_db_key_mm;
 	struct c4iw_mm_entry *rq_db_key_mm = NULL, *ma_sync_key_mm = NULL;
 
-	pr_debug("ib_pd %p\n", pd);
-
 	if (attrs->qp_type != IB_QPT_RC || attrs->create_flags)
-		return ERR_PTR(-EOPNOTSUPP);
+		return -EOPNOTSUPP;
 
 	php = to_c4iw_pd(pd);
 	rhp = php->rhp;
 	schp = get_chp(rhp, ((struct c4iw_cq *)attrs->send_cq)->cq.cqid);
 	rchp = get_chp(rhp, ((struct c4iw_cq *)attrs->recv_cq)->cq.cqid);
 	if (!schp || !rchp)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	if (attrs->cap.max_inline_data > T4_MAX_SEND_INLINE)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	if (!attrs->srq) {
 		if (attrs->cap.max_recv_wr > rhp->rdev.hw_queue.t4_max_rq_size)
-			return ERR_PTR(-E2BIG);
+			return -E2BIG;
 		rqsize = attrs->cap.max_recv_wr + 1;
 		if (rqsize < 8)
 			rqsize = 8;
 	}
 
 	if (attrs->cap.max_send_wr > rhp->rdev.hw_queue.t4_max_sq_size)
-		return ERR_PTR(-E2BIG);
+		return -E2BIG;
 	sqsize = attrs->cap.max_send_wr + 1;
 	if (sqsize < 8)
 		sqsize = 8;
 
-	qhp = kzalloc(sizeof(*qhp), GFP_KERNEL);
-	if (!qhp)
-		return ERR_PTR(-ENOMEM);
-
 	qhp->wr_waitp = c4iw_alloc_wr_wait(GFP_KERNEL);
-	if (!qhp->wr_waitp) {
-		ret = -ENOMEM;
-		goto err_free_qhp;
-	}
+	if (!qhp->wr_waitp)
+		return -ENOMEM;
 
 	qhp->wq.sq.size = sqsize;
 	qhp->wq.sq.memsize =
@@ -2339,7 +2330,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		 qhp->wq.sq.qid, qhp->wq.sq.size, qhp->wq.sq.memsize,
 		 attrs->cap.max_send_wr, qhp->wq.rq.qid, qhp->wq.rq.size,
 		 qhp->wq.rq.memsize, attrs->cap.max_recv_wr);
-	return &qhp->ibqp;
+	return 0;
 err_free_ma_sync_key:
 	kfree(ma_sync_key_mm);
 err_free_rq_db_key:
@@ -2359,9 +2350,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		   ucontext ? &ucontext->uctx : &rhp->rdev.uctx, !attrs->srq);
 err_free_wr_wait:
 	c4iw_put_wr_wait(qhp->wr_waitp);
-err_free_qhp:
-	kfree(qhp);
-	return ERR_PTR(ret);
+	return ret;
 }
 
 int c4iw_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,