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

Pull infiniband/rdma fixes from Roland Dreier:
 "Grab bag of InfiniBand/RDMA fixes:
   - IPoIB fixes for regressions introduced by path database conversion
   - mlx4 fixes for bugs with large memory systems and regressions from
     SR-IOV patches
   - RDMA CM fix for passing bad event up to userspace
   - Other minor fixes"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  IB/mlx4: Check iboe netdev pointer before dereferencing it
  mlx4_core: Clean up buddy bitmap allocation
  mlx4_core: Fix integer overflow issues around MTT table
  mlx4_core: Allow large mlx4_buddy bitmaps
  IB/srp: Fix a race condition
  IB/qib: Fix error return code in qib_init_7322_variables()
  IB: Fix typos in infiniband drivers
  IB/ipoib: Fix RCU pointer dereference of wrong object
  IB/ipoib: Add missing locking when CM object is deleted
  RDMA/ucma.c: Fix for events with wrong context on iWARP
  RDMA/ocrdma: Don't call vlan_dev_real_dev() for non-VLAN netdevs
  IB/mlx4: Fix possible deadlock on sm_lock spinlock

18 files changed, 130 insertions, 65 deletions

diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 6bf850422895..055ed59838dc 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -267,6 +267,7 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id,
 	if (!uevent)
 		return event->event == RDMA_CM_EVENT_CONNECT_REQUEST;
 
+	mutex_lock(&ctx->file->mut);
 	uevent->cm_id = cm_id;
 	ucma_set_event_context(ctx, event, uevent);
 	uevent->resp.event = event->event;
@@ -277,7 +278,6 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id,
 		ucma_copy_conn_event(&uevent->resp.param.conn,
 				     &event->param.conn);
 
-	mutex_lock(&ctx->file->mut);
 	if (event->event == RDMA_CM_EVENT_CONNECT_REQUEST) {
 		if (!ctx->backlog) {
 			ret = -ENOMEM;
diff --git a/drivers/infiniband/hw/amso1100/c2_rnic.c b/drivers/infiniband/hw/amso1100/c2_rnic.c
index 8c81992fa6db..e4a73158fc7f 100644
--- a/drivers/infiniband/hw/amso1100/c2_rnic.c
+++ b/drivers/infiniband/hw/amso1100/c2_rnic.c
@@ -439,7 +439,7 @@ static int c2_rnic_close(struct c2_dev *c2dev)
 
 /*
  * Called by c2_probe to initialize the RNIC. This principally
- * involves initalizing the various limits and resouce pools that
+ * involves initializing the various limits and resource pools that
  * comprise the RNIC instance.
  */
 int __devinit c2_rnic_init(struct c2_dev *c2dev)
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index 77b6b182778a..aaf88ef9409c 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -1680,7 +1680,7 @@ static int close_con_rpl(struct t3cdev *tdev, struct sk_buff *skb, void *ctx)
  * T3A does 3 things when a TERM is received:
  * 1) send up a CPL_RDMA_TERMINATE message with the TERM packet
  * 2) generate an async event on the QP with the TERMINATE opcode
- * 3) post a TERMINATE opcde cqe into the associated CQ.
+ * 3) post a TERMINATE opcode cqe into the associated CQ.
  *
  * For (1), we save the message in the qp for later consumer consumption.
  * For (2), we move the QP into TERMINATE, post a QP event and disconnect.
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index c27141fef1ab..9c2ae7efd00f 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -125,6 +125,7 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
 {
 	struct ib_ah *new_ah;
 	struct ib_ah_attr ah_attr;
+	unsigned long flags;
 
 	if (!dev->send_agent[port_num - 1][0])
 		return;
@@ -139,11 +140,11 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
 	if (IS_ERR(new_ah))
 		return;
 
-	spin_lock(&dev->sm_lock);
+	spin_lock_irqsave(&dev->sm_lock, flags);
 	if (dev->sm_ah[port_num - 1])
 		ib_destroy_ah(dev->sm_ah[port_num - 1]);
 	dev->sm_ah[port_num - 1] = new_ah;
-	spin_unlock(&dev->sm_lock);
+	spin_unlock_irqrestore(&dev->sm_lock, flags);
 }
 
 /*
@@ -197,13 +198,15 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
 static void node_desc_override(struct ib_device *dev,
 			       struct ib_mad *mad)
 {
+	unsigned long flags;
+
 	if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
 	     mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
 	    mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP &&
 	    mad->mad_hdr.attr_id == IB_SMP_ATTR_NODE_DESC) {
-		spin_lock(&to_mdev(dev)->sm_lock);
+		spin_lock_irqsave(&to_mdev(dev)->sm_lock, flags);
 		memcpy(((struct ib_smp *) mad)->data, dev->node_desc, 64);
-		spin_unlock(&to_mdev(dev)->sm_lock);
+		spin_unlock_irqrestore(&to_mdev(dev)->sm_lock, flags);
 	}
 }
 
@@ -213,6 +216,7 @@ static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *ma
 	struct ib_mad_send_buf *send_buf;
 	struct ib_mad_agent *agent = dev->send_agent[port_num - 1][qpn];
 	int ret;
+	unsigned long flags;
 
 	if (agent) {
 		send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR,
@@ -225,13 +229,13 @@ static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *ma
 		 * wrong following the IB spec strictly, but we know
 		 * it's OK for our devices).
 		 */
-		spin_lock(&dev->sm_lock);
+		spin_lock_irqsave(&dev->sm_lock, flags);
 		memcpy(send_buf->mad, mad, sizeof *mad);
 		if ((send_buf->ah = dev->sm_ah[port_num - 1]))
 			ret = ib_post_send_mad(send_buf, NULL);
 		else
 			ret = -EINVAL;
-		spin_unlock(&dev->sm_lock);
+		spin_unlock_irqrestore(&dev->sm_lock, flags);
 
 		if (ret)
 			ib_free_send_mad(send_buf);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index fe2088cfa6ee..cc05579ebce7 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -423,6 +423,7 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
 				 struct ib_device_modify *props)
 {
 	struct mlx4_cmd_mailbox *mailbox;
+	unsigned long flags;
 
 	if (mask & ~IB_DEVICE_MODIFY_NODE_DESC)
 		return -EOPNOTSUPP;
@@ -430,9 +431,9 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
 	if (!(mask & IB_DEVICE_MODIFY_NODE_DESC))
 		return 0;
 
-	spin_lock(&to_mdev(ibdev)->sm_lock);
+	spin_lock_irqsave(&to_mdev(ibdev)->sm_lock, flags);
 	memcpy(ibdev->node_desc, props->node_desc, 64);
-	spin_unlock(&to_mdev(ibdev)->sm_lock);
+	spin_unlock_irqrestore(&to_mdev(ibdev)->sm_lock, flags);
 
 	/*
 	 * If possible, pass node desc to FW, so it can generate
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index a6d8ea060ea8..f585eddef4b7 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1407,6 +1407,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 	struct mlx4_wqe_mlx_seg *mlx = wqe;
 	struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
 	struct mlx4_ib_ah *ah = to_mah(wr->wr.ud.ah);
+	struct net_device *ndev;
 	union ib_gid sgid;
 	u16 pkey;
 	int send_size;
@@ -1483,7 +1484,10 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 
 		memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6);
 		/* FIXME: cache smac value? */
-		smac = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1]->dev_addr;
+		ndev = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1];
+		if (!ndev)
+			return -ENODEV;
+		smac = ndev->dev_addr;
 		memcpy(sqp->ud_header.eth.smac_h, smac, 6);
 		if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6))
 			mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 5a044526e4f4..c4e0131f1b57 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -161,7 +161,7 @@ static void ocrdma_add_default_sgid(struct ocrdma_dev *dev)
 	ocrdma_get_guid(dev, &sgid->raw[8]);
 }
 
-#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
 static void ocrdma_add_vlan_sgids(struct ocrdma_dev *dev)
 {
 	struct net_device *netdev, *tmp;
@@ -202,14 +202,13 @@ static int ocrdma_build_sgid_tbl(struct ocrdma_dev *dev)
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_VLAN_8021Q)
+#if IS_ENABLED(CONFIG_IPV6)
 
 static int ocrdma_inet6addr_event(struct notifier_block *notifier,
 				  unsigned long event, void *ptr)
 {
 	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
-	struct net_device *event_netdev = ifa->idev->dev;
-	struct net_device *netdev = NULL;
+	struct net_device *netdev = ifa->idev->dev;
 	struct ib_event gid_event;
 	struct ocrdma_dev *dev;
 	bool found = false;
@@ -217,11 +216,12 @@ static int ocrdma_inet6addr_event(struct notifier_block *notifier,
 	bool is_vlan = false;
 	u16 vid = 0;
 
-	netdev = vlan_dev_real_dev(event_netdev);
-	if (netdev != event_netdev) {
-		is_vlan = true;
-		vid = vlan_dev_vlan_id(event_netdev);
+	is_vlan = netdev->priv_flags & IFF_802_1Q_VLAN;
+	if (is_vlan) {
+		vid = vlan_dev_vlan_id(netdev);
+		netdev = vlan_dev_real_dev(netdev);
 	}
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(dev, &ocrdma_dev_list, entry) {
 		if (dev->nic_info.netdev == netdev) {
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 0d7280af99bc..3f6b21e9dc11 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -6346,8 +6346,10 @@ static int qib_init_7322_variables(struct qib_devdata *dd)
 			dd->piobcnt4k * dd->align4k;
 		dd->piovl15base	= ioremap_nocache(vl15off,
 						  NUM_VL15_BUFS * dd->align4k);
-		if (!dd->piovl15base)
+		if (!dd->piovl15base) {
+			ret = -ENOMEM;
 			goto bail;
+		}
 	}
 	qib_7322_set_baseaddrs(dd); /* set chip access pointers now */
 
diff --git a/drivers/infiniband/hw/qib/qib_sd7220.c b/drivers/infiniband/hw/qib/qib_sd7220.c
index a322d5171a2c..50a8a0d4fe67 100644
--- a/drivers/infiniband/hw/qib/qib_sd7220.c
+++ b/drivers/infiniband/hw/qib/qib_sd7220.c
@@ -372,7 +372,7 @@ static void qib_sd_trimdone_monitor(struct qib_devdata *dd,
 		/* Read CTRL reg for each channel to check TRIMDONE */
 		if (baduns & (1 << chn)) {
 			qib_dev_err(dd,
-				"Reseting TRIMDONE on chn %d (%s)\n",
+				"Resetting TRIMDONE on chn %d (%s)\n",
 				chn, where);
 			ret = qib_sd7220_reg_mod(dd, IB_7220_SERDES,
 				IB_CTRL2(chn), 0x10, 0x10);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 95ecf4eadf5f..24683fda8e21 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1271,12 +1271,15 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path
 void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(tx->dev);
+	unsigned long flags;
 	if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
+		spin_lock_irqsave(&priv->lock, flags);
 		list_move(&tx->list, &priv->cm.reap_list);
 		queue_work(ipoib_workqueue, &priv->cm.reap_task);
 		ipoib_dbg(priv, "Reap connection for gid %pI6\n",
 			  tx->neigh->daddr + 4);
 		tx->neigh = NULL;
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 }
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 97920b77a5d0..3e2085a3ee47 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1052,7 +1052,7 @@ void ipoib_neigh_free(struct ipoib_neigh *neigh)
 	for (n = rcu_dereference_protected(*np,
 					    lockdep_is_held(&ntbl->rwlock));
 	     n != NULL;
-	     n = rcu_dereference_protected(neigh->hnext,
+	     n = rcu_dereference_protected(*np,
 					lockdep_is_held(&ntbl->rwlock))) {
 		if (n == neigh) {
 			/* found */
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index bcbf22ee0aa7..1b5b0c730054 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -586,24 +586,62 @@ static void srp_unmap_data(struct scsi_cmnd *scmnd,
 			scmnd->sc_data_direction);
 }
 
-static void srp_remove_req(struct srp_target_port *target,
-			   struct srp_request *req, s32 req_lim_delta)
+/**
+ * srp_claim_req - Take ownership of the scmnd associated with a request.
+ * @target: SRP target port.
+ * @req: SRP request.
+ * @scmnd: If NULL, take ownership of @req->scmnd. If not NULL, only take
+ *         ownership of @req->scmnd if it equals @scmnd.
+ *
+ * Return value:
+ * Either NULL or a pointer to the SCSI command the caller became owner of.
+ */
+static struct scsi_cmnd *srp_claim_req(struct srp_target_port *target,
+				       struct srp_request *req,
+				       struct scsi_cmnd *scmnd)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&target->lock, flags);
+	if (!scmnd) {
+		scmnd = req->scmnd;
+		req->scmnd = NULL;
+	} else if (req->scmnd == scmnd) {
+		req->scmnd = NULL;
+	} else {
+		scmnd = NULL;
+	}
+	spin_unlock_irqrestore(&target->lock, flags);
+
+	return scmnd;
+}
+
+/**
+ * srp_free_req() - Unmap data and add request to the free request list.
+ */
+static void srp_free_req(struct srp_target_port *target,
+			 struct srp_request *req, struct scsi_cmnd *scmnd,
+			 s32 req_lim_delta)
 {
 	unsigned long flags;
 
-	srp_unmap_data(req->scmnd, target, req);
+	srp_unmap_data(scmnd, target, req);
+
 	spin_lock_irqsave(&target->lock, flags);
 	target->req_lim += req_lim_delta;
-	req->scmnd = NULL;
 	list_add_tail(&req->list, &target->free_reqs);
 	spin_unlock_irqrestore(&target->lock, flags);
 }
 
 static void srp_reset_req(struct srp_target_port *target, struct srp_request *req)
 {
-	req->scmnd->result = DID_RESET << 16;
-	req->scmnd->scsi_done(req->scmnd);
-	srp_remove_req(target, req, 0);
+	struct scsi_cmnd *scmnd = srp_claim_req(target, req, NULL);
+
+	if (scmnd) {
+		scmnd->result = DID_RESET << 16;
+		scmnd->scsi_done(scmnd);
+		srp_free_req(target, req, scmnd, 0);
+	}
 }
 
 static int srp_reconnect_target(struct srp_target_port *target)
@@ -1073,11 +1111,18 @@ static void srp_process_rsp(struct srp_target_port *target, struct srp_rsp *rsp)
 		complete(&target->tsk_mgmt_done);
 	} else {
 		req = &target->req_ring[rsp->tag];
-		scmnd = req->scmnd;
-		if (!scmnd)
+		scmnd = srp_claim_req(target, req, NULL);
+		if (!scmnd) {
 			shost_printk(KERN_ERR, target->scsi_host,
 				     "Null scmnd for RSP w/tag %016llx\n",
 				     (unsigned long long) rsp->tag);
+
+			spin_lock_irqsave(&target->lock, flags);
+			target->req_lim += be32_to_cpu(rsp->req_lim_delta);
+			spin_unlock_irqrestore(&target->lock, flags);
+
+			return;
+		}
 		scmnd->result = rsp->status;
 
 		if (rsp->flags & SRP_RSP_FLAG_SNSVALID) {
@@ -1092,7 +1137,9 @@ static void srp_process_rsp(struct srp_target_port *target, struct srp_rsp *rsp)
 		else if (rsp->flags & (SRP_RSP_FLAG_DIOVER | SRP_RSP_FLAG_DIUNDER))
 			scsi_set_resid(scmnd, be32_to_cpu(rsp->data_in_res_cnt));
 
-		srp_remove_req(target, req, be32_to_cpu(rsp->req_lim_delta));
+		srp_free_req(target, req, scmnd,
+			     be32_to_cpu(rsp->req_lim_delta));
+
 		scmnd->host_scribble = NULL;
 		scmnd->scsi_done(scmnd);
 	}
@@ -1631,25 +1678,17 @@ static int srp_abort(struct scsi_cmnd *scmnd)
 {
 	struct srp_target_port *target = host_to_target(scmnd->device->host);
 	struct srp_request *req = (struct srp_request *) scmnd->host_scribble;
-	int ret = SUCCESS;
 
 	shost_printk(KERN_ERR, target->scsi_host, "SRP abort called\n");
 
-	if (!req || target->qp_in_error)
+	if (!req || target->qp_in_error || !srp_claim_req(target, req, scmnd))
 		return FAILED;
-	if (srp_send_tsk_mgmt(target, req->index, scmnd->device->lun,
-			      SRP_TSK_ABORT_TASK))
-		return FAILED;
-
-	if (req->scmnd) {
-		if (!target->tsk_mgmt_status) {
-			srp_remove_req(target, req, 0);
-			scmnd->result = DID_ABORT << 16;
-		} else
-			ret = FAILED;
-	}
+	srp_send_tsk_mgmt(target, req->index, scmnd->device->lun,
+			  SRP_TSK_ABORT_TASK);
+	srp_free_req(target, req, scmnd, 0);
+	scmnd->result = DID_ABORT << 16;
 
-	return ret;
+	return SUCCESS;
 }
 
 static int srp_reset_device(struct scsi_cmnd *scmnd)
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 7a0ce8d42887..9e1449f8c6a2 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1469,7 +1469,7 @@ static void srpt_handle_send_comp(struct srpt_rdma_ch *ch,
  *
  * XXX: what is now target_execute_cmd used to be asynchronous, and unmapping
  * the data that has been transferred via IB RDMA had to be postponed until the
- * check_stop_free() callback.  None of this is nessecary anymore and needs to
+ * check_stop_free() callback.  None of this is necessary anymore and needs to
  * be cleaned up.
  */
 static void srpt_handle_rdma_comp(struct srpt_rdma_ch *ch,
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 88b7b3e75ab1..daf417923661 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -358,13 +358,14 @@ void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 }
 
 int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
-			u64 virt, int obj_size,	int nobj, int reserved,
+			u64 virt, int obj_size,	u32 nobj, int reserved,
 			int use_lowmem, int use_coherent)
 {
 	int obj_per_chunk;
 	int num_icm;
 	unsigned chunk_size;
 	int i;
+	u64 size;
 
 	obj_per_chunk = MLX4_TABLE_CHUNK_SIZE / obj_size;
 	num_icm = (nobj + obj_per_chunk - 1) / obj_per_chunk;
@@ -380,10 +381,12 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 	table->coherent = use_coherent;
 	mutex_init(&table->mutex);
 
+	size = (u64) nobj * obj_size;
 	for (i = 0; i * MLX4_TABLE_CHUNK_SIZE < reserved * obj_size; ++i) {
 		chunk_size = MLX4_TABLE_CHUNK_SIZE;
-		if ((i + 1) * MLX4_TABLE_CHUNK_SIZE > nobj * obj_size)
-			chunk_size = PAGE_ALIGN(nobj * obj_size - i * MLX4_TABLE_CHUNK_SIZE);
+		if ((i + 1) * MLX4_TABLE_CHUNK_SIZE > size)
+			chunk_size = PAGE_ALIGN(size -
+					i * MLX4_TABLE_CHUNK_SIZE);
 
 		table->icm[i] = mlx4_alloc_icm(dev, chunk_size >> PAGE_SHIFT,
 					       (use_lowmem ? GFP_KERNEL : GFP_HIGHUSER) |
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.h b/drivers/net/ethernet/mellanox/mlx4/icm.h
index 19e4efc0b342..a67744f53506 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.h
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.h
@@ -78,7 +78,7 @@ int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 			  int start, int end);
 int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
-			u64 virt, int obj_size,	int nobj, int reserved,
+			u64 virt, int obj_size,	u32 nobj, int reserved,
 			int use_lowmem, int use_coherent);
 void mlx4_cleanup_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table);
 void *mlx4_table_find(struct mlx4_icm_table *table, int obj, dma_addr_t *dma_handle);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 59ebc0339638..4d9df8f2a126 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -249,7 +249,7 @@ struct mlx4_bitmap {
 struct mlx4_buddy {
 	unsigned long	      **bits;
 	unsigned int	       *num_free;
-	int			max_order;
+	u32			max_order;
 	spinlock_t		lock;
 };
 
@@ -258,7 +258,7 @@ struct mlx4_icm;
 struct mlx4_icm_table {
 	u64			virt;
 	int			num_icm;
-	int			num_obj;
+	u32			num_obj;
 	int			obj_size;
 	int			lowmem;
 	int			coherent;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index af55b7ce5341..c202d3ad2a0e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -37,6 +37,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
+#include <linux/vmalloc.h>
 
 #include <linux/mlx4/cmd.h>
 
@@ -120,7 +121,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 	buddy->max_order = max_order;
 	spin_lock_init(&buddy->lock);
 
-	buddy->bits = kzalloc((buddy->max_order + 1) * sizeof (long *),
+	buddy->bits = kcalloc(buddy->max_order + 1, sizeof (long *),
 			      GFP_KERNEL);
 	buddy->num_free = kcalloc((buddy->max_order + 1), sizeof *buddy->num_free,
 				  GFP_KERNEL);
@@ -129,10 +130,12 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 
 	for (i = 0; i <= buddy->max_order; ++i) {
 		s = BITS_TO_LONGS(1 << (buddy->max_order - i));
-		buddy->bits[i] = kmalloc(s * sizeof (long), GFP_KERNEL);
-		if (!buddy->bits[i])
-			goto err_out_free;
-		bitmap_zero(buddy->bits[i], 1 << (buddy->max_order - i));
+		buddy->bits[i] = kcalloc(s, sizeof (long), GFP_KERNEL | __GFP_NOWARN);
+		if (!buddy->bits[i]) {
+			buddy->bits[i] = vzalloc(s * sizeof(long));
+			if (!buddy->bits[i])
+				goto err_out_free;
+		}
 	}
 
 	set_bit(0, buddy->bits[buddy->max_order]);
@@ -142,7 +145,10 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 
 err_out_free:
 	for (i = 0; i <= buddy->max_order; ++i)
-		kfree(buddy->bits[i]);
+		if (buddy->bits[i] && is_vmalloc_addr(buddy->bits[i]))
+			vfree(buddy->bits[i]);
+		else
+			kfree(buddy->bits[i]);
 
 err_out:
 	kfree(buddy->bits);
@@ -156,7 +162,10 @@ static void mlx4_buddy_cleanup(struct mlx4_buddy *buddy)
 	int i;
 
 	for (i = 0; i <= buddy->max_order; ++i)
-		kfree(buddy->bits[i]);
+		if (is_vmalloc_addr(buddy->bits[i]))
+			vfree(buddy->bits[i]);
+		else
+			kfree(buddy->bits[i]);
 
 	kfree(buddy->bits);
 	kfree(buddy->num_free);
@@ -668,7 +677,7 @@ int mlx4_init_mr_table(struct mlx4_dev *dev)
 		return err;
 
 	err = mlx4_buddy_init(&mr_table->mtt_buddy,
-			      ilog2(dev->caps.num_mtts /
+			      ilog2((u32)dev->caps.num_mtts /
 			      (1 << log_mtts_per_seg)));
 	if (err)
 		goto err_buddy;
@@ -678,7 +687,7 @@ int mlx4_init_mr_table(struct mlx4_dev *dev)
 			mlx4_alloc_mtt_range(dev,
 					     fls(dev->caps.reserved_mtts - 1));
 		if (priv->reserved_mtts < 0) {
-			mlx4_warn(dev, "MTT table of order %d is too small.\n",
+			mlx4_warn(dev, "MTT table of order %u is too small.\n",
 				  mr_table->mtt_buddy.max_order);
 			err = -ENOMEM;
 			goto err_reserve_mtts;
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index 9ee4725363d5..8e0c3cc2a1ec 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -76,7 +76,7 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 		u64 size;
 		u64 start;
 		int type;
-		int num;
+		u32 num;
 		int log_num;
 	};
 
@@ -105,7 +105,7 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	si_meminfo(&si);
 	request->num_mtt =
 		roundup_pow_of_two(max_t(unsigned, request->num_mtt,
-					 min(1UL << 31,
+					 min(1UL << (31 - log_mtts_per_seg),
 					     si.totalram >> (log_mtts_per_seg - 1))));
 
 	profile[MLX4_RES_QP].size     = dev_cap->qpc_entry_sz;