Merge branches 'ib_core', 'ib_ipoib', 'srpt', 'drain-cq-v4' and 'net/…

…9p' into k.o/for-4.6

drivers/infiniband/core/verbs.c

@@ -1657,3 +1657,167 @@ int ib_sg_to_pages(struct ib_mr *mr,
 	return i;
 }
 EXPORT_SYMBOL(ib_sg_to_pages);
+
+struct ib_drain_cqe {
+	struct ib_cqe cqe;
+	struct completion done;
+};
+
+static void ib_drain_qp_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct ib_drain_cqe *cqe = container_of(wc->wr_cqe, struct ib_drain_cqe,
+						cqe);
+
+	complete(&cqe->done);
+}
+
+/*
+ * Post a WR and block until its completion is reaped for the SQ.
+ */
+static void __ib_drain_sq(struct ib_qp *qp)
+{
+	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
+	struct ib_drain_cqe sdrain;
+	struct ib_send_wr swr = {}, *bad_swr;
+	int ret;
+
+	if (qp->send_cq->poll_ctx == IB_POLL_DIRECT) {
+		WARN_ONCE(qp->send_cq->poll_ctx == IB_POLL_DIRECT,
+			  "IB_POLL_DIRECT poll_ctx not supported for drain\n");
+		return;
+	}
+
+	swr.wr_cqe = &sdrain.cqe;
+	sdrain.cqe.done = ib_drain_qp_done;
+	init_completion(&sdrain.done);
+
+	ret = ib_modify_qp(qp, &attr, IB_QP_STATE);
+	if (ret) {
+		WARN_ONCE(ret, "failed to drain send queue: %d\n", ret);
+		return;
+	}
+
+	ret = ib_post_send(qp, &swr, &bad_swr);
+	if (ret) {
+		WARN_ONCE(ret, "failed to drain send queue: %d\n", ret);
+		return;
+	}
+
+	wait_for_completion(&sdrain.done);
+}
+
+/*
+ * Post a WR and block until its completion is reaped for the RQ.
+ */
+static void __ib_drain_rq(struct ib_qp *qp)
+{
+	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
+	struct ib_drain_cqe rdrain;
+	struct ib_recv_wr rwr = {}, *bad_rwr;
+	int ret;
+
+	if (qp->recv_cq->poll_ctx == IB_POLL_DIRECT) {
+		WARN_ONCE(qp->recv_cq->poll_ctx == IB_POLL_DIRECT,
+			  "IB_POLL_DIRECT poll_ctx not supported for drain\n");
+		return;
+	}
+
+	rwr.wr_cqe = &rdrain.cqe;
+	rdrain.cqe.done = ib_drain_qp_done;
+	init_completion(&rdrain.done);
+
+	ret = ib_modify_qp(qp, &attr, IB_QP_STATE);
+	if (ret) {
+		WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret);
+		return;
+	}
+
+	ret = ib_post_recv(qp, &rwr, &bad_rwr);
+	if (ret) {
+		WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret);
+		return;
+	}
+
+	wait_for_completion(&rdrain.done);
+}
+
+/**
+ * ib_drain_sq() - Block until all SQ CQEs have been consumed by the
+ *		   application.
+ * @qp:            queue pair to drain
+ *
+ * If the device has a provider-specific drain function, then
+ * call that.  Otherwise call the generic drain function
+ * __ib_drain_sq().
+ *
+ * The caller must:
+ *
+ * ensure there is room in the CQ and SQ for the drain work request and
+ * completion.
+ *
+ * allocate the CQ using ib_alloc_cq() and the CQ poll context cannot be
+ * IB_POLL_DIRECT.
+ *
+ * ensure that there are no other contexts that are posting WRs concurrently.
+ * Otherwise the drain is not guaranteed.
+ */
+void ib_drain_sq(struct ib_qp *qp)
+{
+	if (qp->device->drain_sq)
+		qp->device->drain_sq(qp);
+	else
+		__ib_drain_sq(qp);
+}
+EXPORT_SYMBOL(ib_drain_sq);
+
+/**
+ * ib_drain_rq() - Block until all RQ CQEs have been consumed by the
+ *		   application.
+ * @qp:            queue pair to drain
+ *
+ * If the device has a provider-specific drain function, then
+ * call that.  Otherwise call the generic drain function
+ * __ib_drain_rq().
+ *
+ * The caller must:
+ *
+ * ensure there is room in the CQ and RQ for the drain work request and
+ * completion.
+ *
+ * allocate the CQ using ib_alloc_cq() and the CQ poll context cannot be
+ * IB_POLL_DIRECT.
+ *
+ * ensure that there are no other contexts that are posting WRs concurrently.
+ * Otherwise the drain is not guaranteed.
+ */
+void ib_drain_rq(struct ib_qp *qp)
+{
+	if (qp->device->drain_rq)
+		qp->device->drain_rq(qp);
+	else
+		__ib_drain_rq(qp);
+}
+EXPORT_SYMBOL(ib_drain_rq);
+
+/**
+ * ib_drain_qp() - Block until all CQEs have been consumed by the
+ *		   application on both the RQ and SQ.
+ * @qp:            queue pair to drain
+ *
+ * The caller must:
+ *
+ * ensure there is room in the CQ(s), SQ, and RQ for drain work requests
+ * and completions.
+ *
+ * allocate the CQs using ib_alloc_cq() and the CQ poll context cannot be
+ * IB_POLL_DIRECT.
+ *
+ * ensure that there are no other contexts that are posting WRs concurrently.
+ * Otherwise the drain is not guaranteed.
+ */
+void ib_drain_qp(struct ib_qp *qp)
+{
+	ib_drain_sq(qp);
+	ib_drain_rq(qp);
+}
+EXPORT_SYMBOL(ib_drain_qp);

drivers/infiniband/hw/cxgb4/cq.c

@@ -815,8 +815,15 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 		}
 	}
 out:
-	if (wq)
+	if (wq) {
+		if (unlikely(qhp->attr.state != C4IW_QP_STATE_RTS)) {
+			if (t4_sq_empty(wq))
+				complete(&qhp->sq_drained);
+			if (t4_rq_empty(wq))
+				complete(&qhp->rq_drained);
+		}
 		spin_unlock(&qhp->lock);
+	}
 	return ret;
 }
 

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

@@ -476,6 +476,8 @@ struct c4iw_qp {
 	wait_queue_head_t wait;
 	struct timer_list timer;
 	int sq_sig_all;
+	struct completion rq_drained;
+	struct completion sq_drained;
 };
 
 static inline struct c4iw_qp *to_c4iw_qp(struct ib_qp *ibqp)
@@ -1016,6 +1018,8 @@ extern int c4iw_wr_log;
 extern int db_fc_threshold;
 extern int db_coalescing_threshold;
 extern int use_dsgl;
+void c4iw_drain_rq(struct ib_qp *qp);
+void c4iw_drain_sq(struct ib_qp *qp);
 
 
 #endif

drivers/infiniband/hw/cxgb4/provider.c

@@ -564,6 +564,8 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.get_protocol_stats = c4iw_get_mib;
 	dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION;
 	dev->ibdev.get_port_immutable = c4iw_port_immutable;
+	dev->ibdev.drain_sq = c4iw_drain_sq;
+	dev->ibdev.drain_rq = c4iw_drain_rq;
 
 	dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
 	if (!dev->ibdev.iwcm)

drivers/infiniband/hw/cxgb4/qp.c

@@ -1697,6 +1697,8 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	qhp->attr.max_ird = 0;
 	qhp->sq_sig_all = attrs->sq_sig_type == IB_SIGNAL_ALL_WR;
 	spin_lock_init(&qhp->lock);
+	init_completion(&qhp->sq_drained);
+	init_completion(&qhp->rq_drained);
 	mutex_init(&qhp->mutex);
 	init_waitqueue_head(&qhp->wait);
 	atomic_set(&qhp->refcnt, 1);
@@ -1888,3 +1890,17 @@ int c4iw_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	init_attr->sq_sig_type = qhp->sq_sig_all ? IB_SIGNAL_ALL_WR : 0;
 	return 0;
 }
+
+void c4iw_drain_sq(struct ib_qp *ibqp)
+{
+	struct c4iw_qp *qp = to_c4iw_qp(ibqp);
+
+	wait_for_completion(&qp->sq_drained);
+}
+
+void c4iw_drain_rq(struct ib_qp *ibqp)
+{
+	struct c4iw_qp *qp = to_c4iw_qp(ibqp);
+
+	wait_for_completion(&qp->rq_drained);
+}

drivers/infiniband/ulp/ipoib/ipoib.h

@@ -244,6 +244,7 @@ struct ipoib_cm_tx {
 	unsigned	     tx_tail;
 	unsigned long	     flags;
 	u32		     mtu;
+	unsigned             max_send_sge;
 };
 
 struct ipoib_cm_rx_buf {
@@ -390,6 +391,7 @@ struct ipoib_dev_priv {
 	int	hca_caps;
 	struct ipoib_ethtool_st ethtool;
 	struct timer_list poll_timer;
+	unsigned max_send_sge;
 };
 
 struct ipoib_ah {

drivers/infiniband/ulp/ipoib/ipoib_cm.c

@@ -710,6 +710,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_tx_buf *tx_req;
 	int rc;
+	unsigned usable_sge = tx->max_send_sge - !!skb_headlen(skb);
 
 	if (unlikely(skb->len > tx->mtu)) {
 		ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
@@ -719,7 +720,23 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 		ipoib_cm_skb_too_long(dev, skb, tx->mtu - IPOIB_ENCAP_LEN);
 		return;
 	}
-
+	if (skb_shinfo(skb)->nr_frags > usable_sge) {
+		if (skb_linearize(skb) < 0) {
+			ipoib_warn(priv, "skb could not be linearized\n");
+			++dev->stats.tx_dropped;
+			++dev->stats.tx_errors;
+			dev_kfree_skb_any(skb);
+			return;
+		}
+		/* Does skb_linearize return ok without reducing nr_frags? */
+		if (skb_shinfo(skb)->nr_frags > usable_sge) {
+			ipoib_warn(priv, "too many frags after skb linearize\n");
+			++dev->stats.tx_dropped;
+			++dev->stats.tx_errors;
+			dev_kfree_skb_any(skb);
+			return;
+		}
+	}
 	ipoib_dbg_data(priv, "sending packet: head 0x%x length %d connection 0x%x\n",
 		       tx->tx_head, skb->len, tx->qp->qp_num);
 
@@ -1031,7 +1048,8 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_
 	struct ib_qp *tx_qp;
 
 	if (dev->features & NETIF_F_SG)
-		attr.cap.max_send_sge = MAX_SKB_FRAGS + 1;
+		attr.cap.max_send_sge =
+			min_t(u32, priv->ca->attrs.max_sge, MAX_SKB_FRAGS + 1);
 
 	tx_qp = ib_create_qp(priv->pd, &attr);
 	if (PTR_ERR(tx_qp) == -EINVAL) {
@@ -1040,6 +1058,7 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_
 		attr.create_flags &= ~IB_QP_CREATE_USE_GFP_NOIO;
 		tx_qp = ib_create_qp(priv->pd, &attr);
 	}
+	tx->max_send_sge = attr.cap.max_send_sge;
 	return tx_qp;
 }
 

drivers/infiniband/ulp/ipoib/ipoib_ib.c

@@ -538,6 +538,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 	struct ipoib_tx_buf *tx_req;
 	int hlen, rc;
 	void *phead;
+	unsigned usable_sge = priv->max_send_sge - !!skb_headlen(skb);
 
 	if (skb_is_gso(skb)) {
 		hlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
@@ -561,6 +562,23 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 		phead = NULL;
 		hlen  = 0;
 	}
+	if (skb_shinfo(skb)->nr_frags > usable_sge) {
+		if (skb_linearize(skb) < 0) {
+			ipoib_warn(priv, "skb could not be linearized\n");
+			++dev->stats.tx_dropped;
+			++dev->stats.tx_errors;
+			dev_kfree_skb_any(skb);
+			return;
+		}
+		/* Does skb_linearize return ok without reducing nr_frags? */
+		if (skb_shinfo(skb)->nr_frags > usable_sge) {
+			ipoib_warn(priv, "too many frags after skb linearize\n");
+			++dev->stats.tx_dropped;
+			++dev->stats.tx_errors;
+			dev_kfree_skb_any(skb);
+			return;
+		}
+	}
 
 	ipoib_dbg_data(priv, "sending packet, length=%d address=%p qpn=0x%06x\n",
 		       skb->len, address, qpn);

drivers/infiniband/ulp/ipoib/ipoib_verbs.c

@@ -206,7 +206,8 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 		init_attr.create_flags |= IB_QP_CREATE_NETIF_QP;
 
 	if (dev->features & NETIF_F_SG)
-		init_attr.cap.max_send_sge = MAX_SKB_FRAGS + 1;
+		init_attr.cap.max_send_sge =
+			min_t(u32, priv->ca->attrs.max_sge, MAX_SKB_FRAGS + 1);
 
 	priv->qp = ib_create_qp(priv->pd, &init_attr);
 	if (IS_ERR(priv->qp)) {
@@ -233,6 +234,8 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	priv->rx_wr.next = NULL;
 	priv->rx_wr.sg_list = priv->rx_sge;
 
+	priv->max_send_sge = init_attr.cap.max_send_sge;
+
 	return 0;
 
 out_free_send_cq:

drivers/infiniband/ulp/iser/iscsi_iser.h

@@ -458,9 +458,6 @@ struct iser_fr_pool {
  * @comp:                iser completion context
  * @fr_pool:             connection fast registration poool
  * @pi_support:          Indicate device T10-PI support
- * @last:                last send wr to signal all flush errors were drained
- * @last_cqe:            cqe handler for last wr
- * @last_comp:           completes when all connection completions consumed
  */
 struct ib_conn {
 	struct rdma_cm_id           *cma_id;
@@ -472,10 +469,7 @@ struct ib_conn {
 	struct iser_comp	    *comp;
 	struct iser_fr_pool          fr_pool;
 	bool			     pi_support;
-	struct ib_send_wr	     last;
-	struct ib_cqe		     last_cqe;
 	struct ib_cqe		     reg_cqe;
-	struct completion	     last_comp;
 };
 
 /**
@@ -617,7 +611,6 @@ void iser_cmd_comp(struct ib_cq *cq, struct ib_wc *wc);
 void iser_ctrl_comp(struct ib_cq *cq, struct ib_wc *wc);
 void iser_dataout_comp(struct ib_cq *cq, struct ib_wc *wc);
 void iser_reg_comp(struct ib_cq *cq, struct ib_wc *wc);
-void iser_last_comp(struct ib_cq *cq, struct ib_wc *wc);
 
 void iser_task_rdma_init(struct iscsi_iser_task *task);
 

drivers/infiniband/ulp/iser/iser_initiator.c

@@ -729,13 +729,6 @@ void iser_dataout_comp(struct ib_cq *cq, struct ib_wc *wc)
 	kmem_cache_free(ig.desc_cache, desc);
 }
 
-void iser_last_comp(struct ib_cq *cq, struct ib_wc *wc)
-{
-	struct ib_conn *ib_conn = wc->qp->qp_context;
-
-	complete(&ib_conn->last_comp);
-}
-
 void iser_task_rdma_init(struct iscsi_iser_task *iser_task)
 
 {