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

Pull InfiniBand/RDMA updates from Roland Dreier:

 - IPoIB fixes from Doug Ledford and Erez Shitrit

 - iSER updates from Sagi Grimberg

 - mlx4 GUID handling changes from Yishai Hadas

 - other misc fixes

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (51 commits)
  mlx5: wrong page mask if CONFIG_ARCH_DMA_ADDR_T_64BIT enabled for 32Bit architectures
  IB/iser: Rewrite bounce buffer code path
  IB/iser: Bump version to 1.6
  IB/iser: Remove code duplication for a single DMA entry
  IB/iser: Pass struct iser_mem_reg to iser_fast_reg_mr and iser_reg_sig_mr
  IB/iser: Modify struct iser_mem_reg members
  IB/iser: Make fastreg pool cache friendly
  IB/iser: Move PI context alloc/free to routines
  IB/iser: Move fastreg descriptor pool get/put to helper functions
  IB/iser: Merge build page-vec into register page-vec
  IB/iser: Get rid of struct iser_rdma_regd
  IB/iser: Remove redundant assignments in iser_reg_page_vec
  IB/iser: Move memory reg/dereg routines to iser_memory.c
  IB/iser: Don't pass ib_device to fall_to_bounce_buff routine
  IB/iser: Remove a redundant struct iser_data_buf
  IB/iser: Remove redundant cmd_data_len calculation
  IB/iser: Fix wrong calculation of protection buffer length
  IB/iser: Handle fastreg/local_inv completion errors
  IB/iser: Fix unload during ep_poll wrong dereference
  ib_srpt: convert printk's to pr_* functions
  ...

Documentation/filesystems/nfs/nfs-rdma.txt

@@ -187,8 +187,10 @@ Check RDMA and NFS Setup
     To further test the InfiniBand software stack, use IPoIB (this
     assumes you have two IB hosts named host1 and host2):
 
-    host1$ ifconfig ib0 a.b.c.x
-    host2$ ifconfig ib0 a.b.c.y
+    host1$ ip link set dev ib0 up
+    host1$ ip address add dev ib0 a.b.c.x
+    host2$ ip link set dev ib0 up
+    host2$ ip address add dev ib0 a.b.c.y
     host1$ ping a.b.c.y
     host2$ ping a.b.c.x
 
@@ -229,7 +231,8 @@ NFS/RDMA Setup
 
     $ modprobe ib_mthca
     $ modprobe ib_ipoib
-    $ ifconfig ib0 a.b.c.d
+    $ ip li set dev ib0 up
+    $ ip addr add dev ib0 a.b.c.d
 
     NOTE: use unique addresses for the client and server
 

MAINTAINERS

@@ -8803,6 +8803,15 @@ W:	http://www.emulex.com
 S:	Supported
 F:	drivers/net/ethernet/emulex/benet/
 
+EMULEX ONECONNECT ROCE DRIVER
+M:	Selvin Xavier <selvin.xavier@emulex.com>
+M:	Devesh Sharma <devesh.sharma@emulex.com>
+M:	Mitesh Ahuja <mitesh.ahuja@emulex.com>
+L:	linux-rdma@vger.kernel.org
+W:	http://www.emulex.com
+S:	Supported
+F:	drivers/infiniband/hw/ocrdma/
+
 SFC NETWORK DRIVER
 M:	Solarflare linux maintainers <linux-net-drivers@solarflare.com>
 M:	Shradha Shah <sshah@solarflare.com>

drivers/infiniband/core/umem.c

@@ -99,12 +99,15 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	if (dmasync)
 		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
 
+	if (!size)
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * If the combination of the addr and size requested for this memory
 	 * region causes an integer overflow, return error.
 	 */
-	if ((PAGE_ALIGN(addr + size) <= size) ||
-	    (PAGE_ALIGN(addr + size) <= addr))
+	if (((addr + size) < addr) ||
+	    PAGE_ALIGN(addr + size) < (addr + size))
 		return ERR_PTR(-EINVAL);
 
 	if (!can_do_mlock())

drivers/infiniband/core/uverbs_main.c

@@ -246,6 +246,17 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 		kfree(uqp);
 	}
 
+	list_for_each_entry_safe(uobj, tmp, &context->srq_list, list) {
+		struct ib_srq *srq = uobj->object;
+		struct ib_uevent_object *uevent =
+			container_of(uobj, struct ib_uevent_object, uobject);
+
+		idr_remove_uobj(&ib_uverbs_srq_idr, uobj);
+		ib_destroy_srq(srq);
+		ib_uverbs_release_uevent(file, uevent);
+		kfree(uevent);
+	}
+
 	list_for_each_entry_safe(uobj, tmp, &context->cq_list, list) {
 		struct ib_cq *cq = uobj->object;
 		struct ib_uverbs_event_file *ev_file = cq->cq_context;
@@ -258,17 +269,6 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 		kfree(ucq);
 	}
 
-	list_for_each_entry_safe(uobj, tmp, &context->srq_list, list) {
-		struct ib_srq *srq = uobj->object;
-		struct ib_uevent_object *uevent =
-			container_of(uobj, struct ib_uevent_object, uobject);
-
-		idr_remove_uobj(&ib_uverbs_srq_idr, uobj);
-		ib_destroy_srq(srq);
-		ib_uverbs_release_uevent(file, uevent);
-		kfree(uevent);
-	}
-
 	list_for_each_entry_safe(uobj, tmp, &context->mr_list, list) {
 		struct ib_mr *mr = uobj->object;
 

drivers/infiniband/hw/mlx4/mad.c

@@ -1430,6 +1430,10 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
 							tun_qp->ring[i].addr,
 							rx_buf_size,
 							DMA_FROM_DEVICE);
+		if (ib_dma_mapping_error(ctx->ib_dev, tun_qp->ring[i].map)) {
+			kfree(tun_qp->ring[i].addr);
+			goto err;
+		}
 	}
 
 	for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) {
@@ -1442,6 +1446,11 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
 					  tun_qp->tx_ring[i].buf.addr,
 					  tx_buf_size,
 					  DMA_TO_DEVICE);
+		if (ib_dma_mapping_error(ctx->ib_dev,
+					 tun_qp->tx_ring[i].buf.map)) {
+			kfree(tun_qp->tx_ring[i].buf.addr);
+			goto tx_err;
+		}
 		tun_qp->tx_ring[i].ah = NULL;
 	}
 	spin_lock_init(&tun_qp->tx_lock);

drivers/infiniband/hw/mlx4/main.c

@@ -66,9 +66,9 @@ MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_VERSION(DRV_VERSION);
 
-int mlx4_ib_sm_guid_assign = 1;
+int mlx4_ib_sm_guid_assign = 0;
 module_param_named(sm_guid_assign, mlx4_ib_sm_guid_assign, int, 0444);
-MODULE_PARM_DESC(sm_guid_assign, "Enable SM alias_GUID assignment if sm_guid_assign > 0 (Default: 1)");
+MODULE_PARM_DESC(sm_guid_assign, "Enable SM alias_GUID assignment if sm_guid_assign > 0 (Default: 0)");
 
 static const char mlx4_ib_version[] =
 	DRV_NAME ": Mellanox ConnectX InfiniBand driver v"
@@ -2791,9 +2791,31 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 	case MLX4_DEV_EVENT_SLAVE_INIT:
 		/* here, p is the slave id */
 		do_slave_init(ibdev, p, 1);
+		if (mlx4_is_master(dev)) {
+			int i;
+
+			for (i = 1; i <= ibdev->num_ports; i++) {
+				if (rdma_port_get_link_layer(&ibdev->ib_dev, i)
+					== IB_LINK_LAYER_INFINIBAND)
+					mlx4_ib_slave_alias_guid_event(ibdev,
+								       p, i,
+								       1);
+			}
+		}
 		return;
 
 	case MLX4_DEV_EVENT_SLAVE_SHUTDOWN:
+		if (mlx4_is_master(dev)) {
+			int i;
+
+			for (i = 1; i <= ibdev->num_ports; i++) {
+				if (rdma_port_get_link_layer(&ibdev->ib_dev, i)
+					== IB_LINK_LAYER_INFINIBAND)
+					mlx4_ib_slave_alias_guid_event(ibdev,
+								       p, i,
+								       0);
+			}
+		}
 		/* here, p is the slave id */
 		do_slave_init(ibdev, p, 0);
 		return;

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -342,14 +342,9 @@ struct mlx4_ib_ah {
 enum mlx4_guid_alias_rec_status {
 	MLX4_GUID_INFO_STATUS_IDLE,
 	MLX4_GUID_INFO_STATUS_SET,
-	MLX4_GUID_INFO_STATUS_PENDING,
 };
 
-enum mlx4_guid_alias_rec_ownership {
-	MLX4_GUID_DRIVER_ASSIGN,
-	MLX4_GUID_SYSADMIN_ASSIGN,
-	MLX4_GUID_NONE_ASSIGN, /*init state of each record*/
-};
+#define GUID_STATE_NEED_PORT_INIT 0x01
 
 enum mlx4_guid_alias_rec_method {
 	MLX4_GUID_INFO_RECORD_SET	= IB_MGMT_METHOD_SET,
@@ -360,8 +355,8 @@ struct mlx4_sriov_alias_guid_info_rec_det {
 	u8 all_recs[GUID_REC_SIZE * NUM_ALIAS_GUID_IN_REC];
 	ib_sa_comp_mask guid_indexes; /*indicates what from the 8 records are valid*/
 	enum mlx4_guid_alias_rec_status status; /*indicates the administraively status of the record.*/
-	u8 method; /*set or delete*/
-	enum mlx4_guid_alias_rec_ownership ownership; /*indicates who assign that alias_guid record*/
+	unsigned int guids_retry_schedule[NUM_ALIAS_GUID_IN_REC];
+	u64 time_to_run;
 };
 
 struct mlx4_sriov_alias_guid_port_rec_det {
@@ -369,6 +364,7 @@ struct mlx4_sriov_alias_guid_port_rec_det {
 	struct workqueue_struct *wq;
 	struct delayed_work alias_guid_work;
 	u8 port;
+	u32 state_flags;
 	struct mlx4_sriov_alias_guid *parent;
 	struct list_head cb_list;
 };
@@ -802,6 +798,8 @@ int add_sysfs_port_mcg_attr(struct mlx4_ib_dev *device, int port_num,
 void del_sysfs_port_mcg_attr(struct mlx4_ib_dev *device, int port_num,
 			     struct attribute *attr);
 ib_sa_comp_mask mlx4_ib_get_aguid_comp_mask_from_ix(int index);
+void mlx4_ib_slave_alias_guid_event(struct mlx4_ib_dev *dev, int slave,
+				    int port, int slave_init);
 
 int mlx4_ib_device_register_sysfs(struct mlx4_ib_dev *device) ;
 

drivers/infiniband/hw/mlx4/qp.c

@@ -566,6 +566,10 @@ static int alloc_proxy_bufs(struct ib_device *dev, struct mlx4_ib_qp *qp)
 			ib_dma_map_single(dev, qp->sqp_proxy_rcv[i].addr,
 					  sizeof (struct mlx4_ib_proxy_sqp_hdr),
 					  DMA_FROM_DEVICE);
+		if (ib_dma_mapping_error(dev, qp->sqp_proxy_rcv[i].map)) {
+			kfree(qp->sqp_proxy_rcv[i].addr);
+			goto err;
+		}
 	}
 	return 0;
 
@@ -2605,8 +2609,7 @@ static int build_lso_seg(struct mlx4_wqe_lso_seg *wqe, struct ib_send_wr *wr,
 
 	memcpy(wqe->header, wr->wr.ud.header, wr->wr.ud.hlen);
 
-	*lso_hdr_sz  = cpu_to_be32((wr->wr.ud.mss - wr->wr.ud.hlen) << 16 |
-				   wr->wr.ud.hlen);
+	*lso_hdr_sz  = cpu_to_be32(wr->wr.ud.mss << 16 | wr->wr.ud.hlen);
 	*lso_seg_len = halign;
 	return 0;
 }

drivers/infiniband/hw/mlx4/sysfs.c

@@ -46,21 +46,17 @@
 static ssize_t show_admin_alias_guid(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
-	int record_num;/*0-15*/
-	int guid_index_in_rec; /*0 - 7*/
 	struct mlx4_ib_iov_sysfs_attr *mlx4_ib_iov_dentry =
 		container_of(attr, struct mlx4_ib_iov_sysfs_attr, dentry);
 	struct mlx4_ib_iov_port *port = mlx4_ib_iov_dentry->ctx;
 	struct mlx4_ib_dev *mdev = port->dev;
+	__be64 sysadmin_ag_val;
 
-	record_num = mlx4_ib_iov_dentry->entry_num / 8 ;
-	guid_index_in_rec = mlx4_ib_iov_dentry->entry_num % 8 ;
+	sysadmin_ag_val = mlx4_get_admin_guid(mdev->dev,
+					      mlx4_ib_iov_dentry->entry_num,
+					      port->num);
 
-	return sprintf(buf, "%llx\n",
-		       be64_to_cpu(*(__be64 *)&mdev->sriov.alias_guid.
-				   ports_guid[port->num - 1].
-				   all_rec_per_port[record_num].
-				   all_recs[8 * guid_index_in_rec]));
+	return sprintf(buf, "%llx\n", be64_to_cpu(sysadmin_ag_val));
 }
 
 /* store_admin_alias_guid stores the (new) administratively assigned value of that GUID.
@@ -80,6 +76,7 @@ static ssize_t store_admin_alias_guid(struct device *dev,
 	struct mlx4_ib_iov_port *port = mlx4_ib_iov_dentry->ctx;
 	struct mlx4_ib_dev *mdev = port->dev;
 	u64 sysadmin_ag_val;
+	unsigned long flags;
 
 	record_num = mlx4_ib_iov_dentry->entry_num / 8;
 	guid_index_in_rec = mlx4_ib_iov_dentry->entry_num % 8;
@@ -87,6 +84,7 @@ static ssize_t store_admin_alias_guid(struct device *dev,
 		pr_err("GUID 0 block 0 is RO\n");
 		return count;
 	}
+	spin_lock_irqsave(&mdev->sriov.alias_guid.ag_work_lock, flags);
 	sscanf(buf, "%llx", &sysadmin_ag_val);
 	*(__be64 *)&mdev->sriov.alias_guid.ports_guid[port->num - 1].
 		all_rec_per_port[record_num].
@@ -96,33 +94,15 @@ static ssize_t store_admin_alias_guid(struct device *dev,
 	/* Change the state to be pending for update */
 	mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].status
 		= MLX4_GUID_INFO_STATUS_IDLE ;
-
-	mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].method
-		= MLX4_GUID_INFO_RECORD_SET;
-
-	switch (sysadmin_ag_val) {
-	case MLX4_GUID_FOR_DELETE_VAL:
-		mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].method
-			= MLX4_GUID_INFO_RECORD_DELETE;
-		mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].ownership
-			= MLX4_GUID_SYSADMIN_ASSIGN;
-		break;
-	/* The sysadmin requests the SM to re-assign */
-	case MLX4_NOT_SET_GUID:
-		mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].ownership
-			= MLX4_GUID_DRIVER_ASSIGN;
-		break;
-	/* The sysadmin requests a specific value.*/
-	default:
-		mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].ownership
-			= MLX4_GUID_SYSADMIN_ASSIGN;
-		break;
-	}
+	mlx4_set_admin_guid(mdev->dev, cpu_to_be64(sysadmin_ag_val),
+			    mlx4_ib_iov_dentry->entry_num,
+			    port->num);
 
 	/* set the record index */
 	mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].guid_indexes
-		= mlx4_ib_get_aguid_comp_mask_from_ix(guid_index_in_rec);
+		|= mlx4_ib_get_aguid_comp_mask_from_ix(guid_index_in_rec);
 
+	spin_unlock_irqrestore(&mdev->sriov.alias_guid.ag_work_lock, flags);
 	mlx4_ib_init_alias_guid_work(mdev, port->num - 1);
 
 	return count;

drivers/infiniband/ulp/ipoib/ipoib.h

@@ -87,7 +87,6 @@ enum {
 	IPOIB_FLAG_ADMIN_UP	  = 2,
 	IPOIB_PKEY_ASSIGNED	  = 3,
 	IPOIB_FLAG_SUBINTERFACE	  = 5,
-	IPOIB_MCAST_RUN		  = 6,
 	IPOIB_STOP_REAPER	  = 7,
 	IPOIB_FLAG_ADMIN_CM	  = 9,
 	IPOIB_FLAG_UMCAST	  = 10,
@@ -98,9 +97,15 @@ enum {
 
 	IPOIB_MCAST_FLAG_FOUND	  = 0,	/* used in set_multicast_list */
 	IPOIB_MCAST_FLAG_SENDONLY = 1,
-	IPOIB_MCAST_FLAG_BUSY	  = 2,	/* joining or already joined */
+	/*
+	 * For IPOIB_MCAST_FLAG_BUSY
+	 * When set, in flight join and mcast->mc is unreliable
+	 * When clear and mcast->mc IS_ERR_OR_NULL, need to restart or
+	 *   haven't started yet
+	 * When clear and mcast->mc is valid pointer, join was successful
+	 */
+	IPOIB_MCAST_FLAG_BUSY	  = 2,
 	IPOIB_MCAST_FLAG_ATTACHED = 3,
-	IPOIB_MCAST_JOIN_STARTED  = 4,
 
 	MAX_SEND_CQE		  = 16,
 	IPOIB_CM_COPYBREAK	  = 256,
@@ -148,6 +153,7 @@ struct ipoib_mcast {
 
 	unsigned long created;
 	unsigned long backoff;
+	unsigned long delay_until;
 
 	unsigned long flags;
 	unsigned char logcount;
@@ -292,6 +298,11 @@ struct ipoib_neigh_table {
 	struct completion		deleted;
 };
 
+struct ipoib_qp_state_validate {
+	struct work_struct work;
+	struct ipoib_dev_priv   *priv;
+};
+
 /*
  * Device private locking: network stack tx_lock protects members used
  * in TX fast path, lock protects everything else.  lock nests inside
@@ -317,6 +328,7 @@ struct ipoib_dev_priv {
 	struct list_head multicast_list;
 	struct rb_root multicast_tree;
 
+	struct workqueue_struct *wq;
 	struct delayed_work mcast_task;
 	struct work_struct carrier_on_task;
 	struct work_struct flush_light;
@@ -426,11 +438,6 @@ struct ipoib_neigh {
 #define IPOIB_UD_MTU(ib_mtu)		(ib_mtu - IPOIB_ENCAP_LEN)
 #define IPOIB_UD_BUF_SIZE(ib_mtu)	(ib_mtu + IB_GRH_BYTES)
 
-static inline int ipoib_ud_need_sg(unsigned int ib_mtu)
-{
-	return IPOIB_UD_BUF_SIZE(ib_mtu) > PAGE_SIZE;
-}
-
 void ipoib_neigh_dtor(struct ipoib_neigh *neigh);
 static inline void ipoib_neigh_put(struct ipoib_neigh *neigh)
 {
@@ -477,10 +484,10 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work);
 void ipoib_pkey_event(struct work_struct *work);
 void ipoib_ib_dev_cleanup(struct net_device *dev);
 
-int ipoib_ib_dev_open(struct net_device *dev, int flush);
+int ipoib_ib_dev_open(struct net_device *dev);
 int ipoib_ib_dev_up(struct net_device *dev);
-int ipoib_ib_dev_down(struct net_device *dev, int flush);
-int ipoib_ib_dev_stop(struct net_device *dev, int flush);
+int ipoib_ib_dev_down(struct net_device *dev);
+int ipoib_ib_dev_stop(struct net_device *dev);
 void ipoib_pkey_dev_check_presence(struct net_device *dev);
 
 int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
@@ -492,7 +499,7 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb);
 
 void ipoib_mcast_restart_task(struct work_struct *work);
 int ipoib_mcast_start_thread(struct net_device *dev);
-int ipoib_mcast_stop_thread(struct net_device *dev, int flush);
+int ipoib_mcast_stop_thread(struct net_device *dev);
 
 void ipoib_mcast_dev_down(struct net_device *dev);
 void ipoib_mcast_dev_flush(struct net_device *dev);

drivers/infiniband/ulp/ipoib/ipoib_cm.c

@@ -474,7 +474,7 @@ static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even
 	}
 
 	spin_lock_irq(&priv->lock);
-	queue_delayed_work(ipoib_workqueue,
+	queue_delayed_work(priv->wq,
 			   &priv->cm.stale_task, IPOIB_CM_RX_DELAY);
 	/* Add this entry to passive ids list head, but do not re-add it
 	 * if IB_EVENT_QP_LAST_WQE_REACHED has moved it to flush list. */
@@ -576,7 +576,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 			spin_lock_irqsave(&priv->lock, flags);
 			list_splice_init(&priv->cm.rx_drain_list, &priv->cm.rx_reap_list);
 			ipoib_cm_start_rx_drain(priv);
-			queue_work(ipoib_workqueue, &priv->cm.rx_reap_task);
+			queue_work(priv->wq, &priv->cm.rx_reap_task);
 			spin_unlock_irqrestore(&priv->lock, flags);
 		} else
 			ipoib_warn(priv, "cm recv completion event with wrid %d (> %d)\n",
@@ -603,7 +603,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 				spin_lock_irqsave(&priv->lock, flags);
 				list_move(&p->list, &priv->cm.rx_reap_list);
 				spin_unlock_irqrestore(&priv->lock, flags);
-				queue_work(ipoib_workqueue, &priv->cm.rx_reap_task);
+				queue_work(priv->wq, &priv->cm.rx_reap_task);
 			}
 			return;
 		}
@@ -827,7 +827,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 
 		if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
 			list_move(&tx->list, &priv->cm.reap_list);
-			queue_work(ipoib_workqueue, &priv->cm.reap_task);
+			queue_work(priv->wq, &priv->cm.reap_task);
 		}
 
 		clear_bit(IPOIB_FLAG_OPER_UP, &tx->flags);
@@ -1255,7 +1255,7 @@ static int ipoib_cm_tx_handler(struct ib_cm_id *cm_id,
 
 		if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
 			list_move(&tx->list, &priv->cm.reap_list);
-			queue_work(ipoib_workqueue, &priv->cm.reap_task);
+			queue_work(priv->wq, &priv->cm.reap_task);
 		}
 
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1284,7 +1284,7 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path
 	tx->dev = dev;
 	list_add(&tx->list, &priv->cm.start_list);
 	set_bit(IPOIB_FLAG_INITIALIZED, &tx->flags);
-	queue_work(ipoib_workqueue, &priv->cm.start_task);
+	queue_work(priv->wq, &priv->cm.start_task);
 	return tx;
 }
 
@@ -1295,7 +1295,7 @@ void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx)
 	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);
+		queue_work(priv->wq, &priv->cm.reap_task);
 		ipoib_dbg(priv, "Reap connection for gid %pI6\n",
 			  tx->neigh->daddr + 4);
 		tx->neigh = NULL;
@@ -1417,7 +1417,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb,
 
 	skb_queue_tail(&priv->cm.skb_queue, skb);
 	if (e)
-		queue_work(ipoib_workqueue, &priv->cm.skb_task);
+		queue_work(priv->wq, &priv->cm.skb_task);
 }
 
 static void ipoib_cm_rx_reap(struct work_struct *work)
@@ -1450,7 +1450,7 @@ static void ipoib_cm_stale_task(struct work_struct *work)
 	}
 
 	if (!list_empty(&priv->cm.passive_ids))
-		queue_delayed_work(ipoib_workqueue,
+		queue_delayed_work(priv->wq,
 				   &priv->cm.stale_task, IPOIB_CM_RX_DELAY);
 	spin_unlock_irq(&priv->lock);
 }

drivers/infiniband/ulp/ipoib/ipoib_ib.c

@@ -94,41 +94,11 @@ void ipoib_free_ah(struct kref *kref)
 static void ipoib_ud_dma_unmap_rx(struct ipoib_dev_priv *priv,
 				  u64 mapping[IPOIB_UD_RX_SG])
 {
-	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
-		ib_dma_unmap_single(priv->ca, mapping[0], IPOIB_UD_HEAD_SIZE,
-				    DMA_FROM_DEVICE);
-		ib_dma_unmap_page(priv->ca, mapping[1], PAGE_SIZE,
-				  DMA_FROM_DEVICE);
-	} else
 	ib_dma_unmap_single(priv->ca, mapping[0],
 			    IPOIB_UD_BUF_SIZE(priv->max_ib_mtu),
 			    DMA_FROM_DEVICE);
 }
 
-static void ipoib_ud_skb_put_frags(struct ipoib_dev_priv *priv,
-				   struct sk_buff *skb,
-				   unsigned int length)
-{
-	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
-		skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
-		unsigned int size;
-		/*
-		 * There is only two buffers needed for max_payload = 4K,
-		 * first buf size is IPOIB_UD_HEAD_SIZE
-		 */
-		skb->tail += IPOIB_UD_HEAD_SIZE;
-		skb->len  += length;
-
-		size = length - IPOIB_UD_HEAD_SIZE;
-
-		skb_frag_size_set(frag, size);
-		skb->data_len += size;
-		skb->truesize += PAGE_SIZE;
-	} else
-		skb_put(skb, length);
-
-}
-
 static int ipoib_ib_post_receive(struct net_device *dev, int id)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -156,18 +126,11 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct sk_buff *skb;
 	int buf_size;
-	int tailroom;
 	u64 *mapping;
 
-	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
-		buf_size = IPOIB_UD_HEAD_SIZE;
-		tailroom = 128; /* reserve some tailroom for IP/TCP headers */
-	} else {
 	buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
-		tailroom = 0;
-	}
 
-	skb = dev_alloc_skb(buf_size + tailroom + 4);
+	skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -184,23 +147,8 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
 	if (unlikely(ib_dma_mapping_error(priv->ca, mapping[0])))
 		goto error;
 
-	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
-		struct page *page = alloc_page(GFP_ATOMIC);
-		if (!page)
-			goto partial_error;
-		skb_fill_page_desc(skb, 0, page, 0, PAGE_SIZE);
-		mapping[1] =
-			ib_dma_map_page(priv->ca, page,
-					0, PAGE_SIZE, DMA_FROM_DEVICE);
-		if (unlikely(ib_dma_mapping_error(priv->ca, mapping[1])))
-			goto partial_error;
-	}
-
 	priv->rx_ring[id].skb = skb;
 	return skb;
-
-partial_error:
-	ib_dma_unmap_single(priv->ca, mapping[0], buf_size, DMA_FROM_DEVICE);
 error:
 	dev_kfree_skb_any(skb);
 	return NULL;
@@ -278,7 +226,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 		       wc->byte_len, wc->slid);
 
 	ipoib_ud_dma_unmap_rx(priv, mapping);
-	ipoib_ud_skb_put_frags(priv, skb, wc->byte_len);
+
+	skb_put(skb, wc->byte_len);
 
 	/* First byte of dgid signals multicast when 0xff */
 	dgid = &((struct ib_grh *)skb->data)->dgid;
@@ -296,6 +245,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	skb_reset_mac_header(skb);
 	skb_pull(skb, IPOIB_ENCAP_LEN);
 
+	skb->truesize = SKB_TRUESIZE(skb->len);
+
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
 
@@ -376,6 +327,51 @@ static void ipoib_dma_unmap_tx(struct ib_device *ca,
 	}
 }
 
+/*
+ * As the result of a completion error the QP Can be transferred to SQE states.
+ * The function checks if the (send)QP is in SQE state and
+ * moves it back to RTS state, that in order to have it functional again.
+ */
+static void ipoib_qp_state_validate_work(struct work_struct *work)
+{
+	struct ipoib_qp_state_validate *qp_work =
+		container_of(work, struct ipoib_qp_state_validate, work);
+
+	struct ipoib_dev_priv *priv = qp_work->priv;
+	struct ib_qp_attr qp_attr;
+	struct ib_qp_init_attr query_init_attr;
+	int ret;
+
+	ret = ib_query_qp(priv->qp, &qp_attr, IB_QP_STATE, &query_init_attr);
+	if (ret) {
+		ipoib_warn(priv, "%s: Failed to query QP ret: %d\n",
+			   __func__, ret);
+		goto free_res;
+	}
+	pr_info("%s: QP: 0x%x is in state: %d\n",
+		__func__, priv->qp->qp_num, qp_attr.qp_state);
+
+	/* currently support only in SQE->RTS transition*/
+	if (qp_attr.qp_state == IB_QPS_SQE) {
+		qp_attr.qp_state = IB_QPS_RTS;
+
+		ret = ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE);
+		if (ret) {
+			pr_warn("failed(%d) modify QP:0x%x SQE->RTS\n",
+				ret, priv->qp->qp_num);
+			goto free_res;
+		}
+		pr_info("%s: QP: 0x%x moved from IB_QPS_SQE to IB_QPS_RTS\n",
+			__func__, priv->qp->qp_num);
+	} else {
+		pr_warn("QP (%d) will stay in state: %d\n",
+			priv->qp->qp_num, qp_attr.qp_state);
+	}
+
+free_res:
+	kfree(qp_work);
+}
+
 static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -407,10 +403,22 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 		netif_wake_queue(dev);
 
 	if (wc->status != IB_WC_SUCCESS &&
-	    wc->status != IB_WC_WR_FLUSH_ERR)
+	    wc->status != IB_WC_WR_FLUSH_ERR) {
+		struct ipoib_qp_state_validate *qp_work;
 		ipoib_warn(priv, "failed send event "
 			   "(status=%d, wrid=%d vend_err %x)\n",
 			   wc->status, wr_id, wc->vendor_err);
+		qp_work = kzalloc(sizeof(*qp_work), GFP_ATOMIC);
+		if (!qp_work) {
+			ipoib_warn(priv, "%s Failed alloc ipoib_qp_state_validate for qp: 0x%x\n",
+				   __func__, priv->qp->qp_num);
+			return;
+		}
+
+		INIT_WORK(&qp_work->work, ipoib_qp_state_validate_work);
+		qp_work->priv = priv;
+		queue_work(priv->wq, &qp_work->work);
+	}
 }
 
 static int poll_tx(struct ipoib_dev_priv *priv)
@@ -655,16 +663,33 @@ void ipoib_reap_ah(struct work_struct *work)
 	__ipoib_reap_ah(dev);
 
 	if (!test_bit(IPOIB_STOP_REAPER, &priv->flags))
-		queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
+		queue_delayed_work(priv->wq, &priv->ah_reap_task,
 				   round_jiffies_relative(HZ));
 }
 
+static void ipoib_flush_ah(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+	cancel_delayed_work(&priv->ah_reap_task);
+	flush_workqueue(priv->wq);
+	ipoib_reap_ah(&priv->ah_reap_task.work);
+}
+
+static void ipoib_stop_ah(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+	set_bit(IPOIB_STOP_REAPER, &priv->flags);
+	ipoib_flush_ah(dev);
+}
+
 static void ipoib_ib_tx_timer_func(unsigned long ctx)
 {
 	drain_tx_cq((struct net_device *)ctx);
 }
 
-int ipoib_ib_dev_open(struct net_device *dev, int flush)
+int ipoib_ib_dev_open(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret;
@@ -696,7 +721,7 @@ int ipoib_ib_dev_open(struct net_device *dev, int flush)
 	}
 
 	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
-	queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
+	queue_delayed_work(priv->wq, &priv->ah_reap_task,
 			   round_jiffies_relative(HZ));
 
 	if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
@@ -706,7 +731,7 @@ int ipoib_ib_dev_open(struct net_device *dev, int flush)
 dev_stop:
 	if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
 		napi_enable(&priv->napi);
-	ipoib_ib_dev_stop(dev, flush);
+	ipoib_ib_dev_stop(dev);
 	return -1;
 }
 
@@ -738,7 +763,7 @@ int ipoib_ib_dev_up(struct net_device *dev)
 	return ipoib_mcast_start_thread(dev);
 }
 
-int ipoib_ib_dev_down(struct net_device *dev, int flush)
+int ipoib_ib_dev_down(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -747,7 +772,7 @@ int ipoib_ib_dev_down(struct net_device *dev, int flush)
 	clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
 	netif_carrier_off(dev);
 
-	ipoib_mcast_stop_thread(dev, flush);
+	ipoib_mcast_stop_thread(dev);
 	ipoib_mcast_dev_flush(dev);
 
 	ipoib_flush_paths(dev);
@@ -807,7 +832,7 @@ void ipoib_drain_cq(struct net_device *dev)
 	local_bh_enable();
 }
 
-int ipoib_ib_dev_stop(struct net_device *dev, int flush)
+int ipoib_ib_dev_stop(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_qp_attr qp_attr;
@@ -877,24 +902,7 @@ int ipoib_ib_dev_stop(struct net_device *dev, int flush)
 	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
 		ipoib_warn(priv, "Failed to modify QP to RESET state\n");
 
-	/* Wait for all AHs to be reaped */
-	set_bit(IPOIB_STOP_REAPER, &priv->flags);
-	cancel_delayed_work(&priv->ah_reap_task);
-	if (flush)
-		flush_workqueue(ipoib_workqueue);
-
-	begin = jiffies;
-
-	while (!list_empty(&priv->dead_ahs)) {
-		__ipoib_reap_ah(dev);
-
-		if (time_after(jiffies, begin + HZ)) {
-			ipoib_warn(priv, "timing out; will leak address handles\n");
-			break;
-		}
-
-		msleep(1);
-	}
+	ipoib_flush_ah(dev);
 
 	ib_req_notify_cq(priv->recv_cq, IB_CQ_NEXT_COMP);
 
@@ -918,7 +926,7 @@ int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
 		    (unsigned long) dev);
 
 	if (dev->flags & IFF_UP) {
-		if (ipoib_ib_dev_open(dev, 1)) {
+		if (ipoib_ib_dev_open(dev)) {
 			ipoib_transport_dev_cleanup(dev);
 			return -ENODEV;
 		}
@@ -1037,15 +1045,16 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 	if (level == IPOIB_FLUSH_LIGHT) {
 		ipoib_mark_paths_invalid(dev);
 		ipoib_mcast_dev_flush(dev);
+		ipoib_flush_ah(dev);
 	}
 
 	if (level >= IPOIB_FLUSH_NORMAL)
-		ipoib_ib_dev_down(dev, 0);
+		ipoib_ib_dev_down(dev);
 
 	if (level == IPOIB_FLUSH_HEAVY) {
 		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
-			ipoib_ib_dev_stop(dev, 0);
-		if (ipoib_ib_dev_open(dev, 0) != 0)
+			ipoib_ib_dev_stop(dev);
+		if (ipoib_ib_dev_open(dev) != 0)
 			return;
 		if (netif_queue_stopped(dev))
 			netif_start_queue(dev);
@@ -1097,9 +1106,17 @@ void ipoib_ib_dev_cleanup(struct net_device *dev)
 	 */
 	ipoib_flush_paths(dev);
 
-	ipoib_mcast_stop_thread(dev, 1);
+	ipoib_mcast_stop_thread(dev);
 	ipoib_mcast_dev_flush(dev);
 
+	/*
+	 * All of our ah references aren't free until after
+	 * ipoib_mcast_dev_flush(), ipoib_flush_paths, and
+	 * the neighbor garbage collection is stopped and reaped.
+	 * That should all be done now, so make a final ah flush.
+	 */
+	ipoib_stop_ah(dev);
+
 	ipoib_transport_dev_cleanup(dev);
 }
 

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -108,7 +108,7 @@ int ipoib_open(struct net_device *dev)
 
 	set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
 
-	if (ipoib_ib_dev_open(dev, 1)) {
+	if (ipoib_ib_dev_open(dev)) {
 		if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
 			return 0;
 		goto err_disable;
@@ -139,7 +139,7 @@ int ipoib_open(struct net_device *dev)
 	return 0;
 
 err_stop:
-	ipoib_ib_dev_stop(dev, 1);
+	ipoib_ib_dev_stop(dev);
 
 err_disable:
 	clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
@@ -157,8 +157,8 @@ static int ipoib_stop(struct net_device *dev)
 
 	netif_stop_queue(dev);
 
-	ipoib_ib_dev_down(dev, 1);
-	ipoib_ib_dev_stop(dev, 0);
+	ipoib_ib_dev_down(dev);
+	ipoib_ib_dev_stop(dev);
 
 	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
 		struct ipoib_dev_priv *cpriv;
@@ -640,8 +640,10 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 
 		if (!path->query && path_rec_start(dev, path))
 			goto err_path;
-
+		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
 			__skb_queue_tail(&neigh->queue, skb);
+		else
+			goto err_drop;
 	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
@@ -676,7 +678,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 			new_path = 1;
 		}
 		if (path) {
+			if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
 				__skb_queue_tail(&path->queue, skb);
+			} else {
+				++dev->stats.tx_dropped;
+				dev_kfree_skb_any(skb);
+			}
 
 			if (!path->query && path_rec_start(dev, path)) {
 				spin_unlock_irqrestore(&priv->lock, flags);
@@ -839,7 +846,7 @@ static void ipoib_set_mcast_list(struct net_device *dev)
 		return;
 	}
 
-	queue_work(ipoib_workqueue, &priv->restart_task);
+	queue_work(priv->wq, &priv->restart_task);
 }
 
 static int ipoib_get_iflink(const struct net_device *dev)
@@ -966,7 +973,7 @@ static void ipoib_reap_neigh(struct work_struct *work)
 	__ipoib_reap_neigh(priv);
 
 	if (!test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
-		queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task,
+		queue_delayed_work(priv->wq, &priv->neigh_reap_task,
 				   arp_tbl.gc_interval);
 }
 
@@ -1145,7 +1152,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
 
 	/* start garbage collection */
 	clear_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
-	queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task,
+	queue_delayed_work(priv->wq, &priv->neigh_reap_task,
 			   arp_tbl.gc_interval);
 
 	return 0;
@@ -1274,15 +1281,13 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
-	if (ipoib_neigh_hash_init(priv) < 0)
-		goto out;
 	/* Allocate RX/TX "rings" to hold queued skbs */
 	priv->rx_ring =	kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring,
 				GFP_KERNEL);
 	if (!priv->rx_ring) {
 		printk(KERN_WARNING "%s: failed to allocate RX ring (%d entries)\n",
 		       ca->name, ipoib_recvq_size);
-		goto out_neigh_hash_cleanup;
+		goto out;
 	}
 
 	priv->tx_ring = vzalloc(ipoib_sendq_size * sizeof *priv->tx_ring);
@@ -1297,16 +1302,24 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
 	if (ipoib_ib_dev_init(dev, ca, port))
 		goto out_tx_ring_cleanup;
 
+	/*
+	 * Must be after ipoib_ib_dev_init so we can allocate a per
+	 * device wq there and use it here
+	 */
+	if (ipoib_neigh_hash_init(priv) < 0)
+		goto out_dev_uninit;
+
 	return 0;
 
+out_dev_uninit:
+	ipoib_ib_dev_cleanup(dev);
+
 out_tx_ring_cleanup:
 	vfree(priv->tx_ring);
 
 out_rx_ring_cleanup:
 	kfree(priv->rx_ring);
 
-out_neigh_hash_cleanup:
-	ipoib_neigh_hash_uninit(dev);
 out:
 	return -ENOMEM;
 }
@@ -1329,6 +1342,12 @@ void ipoib_dev_cleanup(struct net_device *dev)
 	}
 	unregister_netdevice_many(&head);
 
+	/*
+	 * Must be before ipoib_ib_dev_cleanup or we delete an in use
+	 * work queue
+	 */
+	ipoib_neigh_hash_uninit(dev);
+
 	ipoib_ib_dev_cleanup(dev);
 
 	kfree(priv->rx_ring);
@@ -1336,8 +1355,6 @@ void ipoib_dev_cleanup(struct net_device *dev)
 
 	priv->rx_ring = NULL;
 	priv->tx_ring = NULL;
-
-	ipoib_neigh_hash_uninit(dev);
 }
 
 static const struct header_ops ipoib_header_ops = {
@@ -1646,10 +1663,11 @@ static struct net_device *ipoib_add_port(const char *format,
 
 register_failed:
 	ib_unregister_event_handler(&priv->event_handler);
+	flush_workqueue(ipoib_workqueue);
 	/* Stop GC if started before flush */
 	set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 	cancel_delayed_work(&priv->neigh_reap_task);
-	flush_workqueue(ipoib_workqueue);
+	flush_workqueue(priv->wq);
 
 event_failed:
 	ipoib_dev_cleanup(priv->dev);
@@ -1712,6 +1730,7 @@ static void ipoib_remove_one(struct ib_device *device)
 
 	list_for_each_entry_safe(priv, tmp, dev_list, list) {
 		ib_unregister_event_handler(&priv->event_handler);
+		flush_workqueue(ipoib_workqueue);
 
 		rtnl_lock();
 		dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP);
@@ -1720,7 +1739,7 @@ static void ipoib_remove_one(struct ib_device *device)
 		/* Stop GC */
 		set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 		cancel_delayed_work(&priv->neigh_reap_task);
-		flush_workqueue(ipoib_workqueue);
+		flush_workqueue(priv->wq);
 
 		unregister_netdev(priv->dev);
 		free_netdev(priv->dev);
@@ -1755,14 +1774,16 @@ static int __init ipoib_init_module(void)
 		return ret;
 
 	/*
-	 * We create our own workqueue mainly because we want to be
-	 * able to flush it when devices are being removed.  We can't
-	 * use schedule_work()/flush_scheduled_work() because both
-	 * unregister_netdev() and linkwatch_event take the rtnl lock,
-	 * so flush_scheduled_work() can deadlock during device
-	 * removal.
+	 * We create a global workqueue here that is used for all flush
+	 * operations.  However, if you attempt to flush a workqueue
+	 * from a task on that same workqueue, it deadlocks the system.
+	 * We want to be able to flush the tasks associated with a
+	 * specific net device, so we also create a workqueue for each
+	 * netdevice.  We queue up the tasks for that device only on
+	 * its private workqueue, and we only queue up flush events
+	 * on our global flush workqueue.  This avoids the deadlocks.
 	 */
-	ipoib_workqueue = create_singlethread_workqueue("ipoib");
+	ipoib_workqueue = create_singlethread_workqueue("ipoib_flush");
 	if (!ipoib_workqueue) {
 		ret = -ENOMEM;
 		goto err_fs;

drivers/infiniband/ulp/ipoib/ipoib_verbs.c

@@ -157,6 +157,16 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 		goto out_free_pd;
 	}
 
+	/*
+	 * the various IPoIB tasks assume they will never race against
+	 * themselves, so always use a single thread workqueue
+	 */
+	priv->wq = create_singlethread_workqueue("ipoib_wq");
+	if (!priv->wq) {
+		printk(KERN_WARNING "ipoib: failed to allocate device WQ\n");
+		goto out_free_mr;
+	}
+
 	size = ipoib_recvq_size + 1;
 	ret = ipoib_cm_dev_init(dev);
 	if (!ret) {
@@ -165,12 +175,13 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 			size += ipoib_recvq_size + 1; /* 1 extra for rx_drain_qp */
 		else
 			size += ipoib_recvq_size * ipoib_max_conn_qp;
-	}
+	} else
+		goto out_free_wq;
 
 	priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, dev, size, 0);
 	if (IS_ERR(priv->recv_cq)) {
 		printk(KERN_WARNING "%s: failed to create receive CQ\n", ca->name);
-		goto out_free_mr;
+		goto out_cm_dev_cleanup;
 	}
 
 	priv->send_cq = ib_create_cq(priv->ca, ipoib_send_comp_handler, NULL,
@@ -216,15 +227,10 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	priv->tx_wr.send_flags	= IB_SEND_SIGNALED;
 
 	priv->rx_sge[0].lkey = priv->mr->lkey;
-	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
-		priv->rx_sge[0].length = IPOIB_UD_HEAD_SIZE;
-		priv->rx_sge[1].length = PAGE_SIZE;
-		priv->rx_sge[1].lkey = priv->mr->lkey;
-		priv->rx_wr.num_sge = IPOIB_UD_RX_SG;
-	} else {
+
 	priv->rx_sge[0].length = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
 	priv->rx_wr.num_sge = 1;
-	}
+
 	priv->rx_wr.next = NULL;
 	priv->rx_wr.sg_list = priv->rx_sge;
 
@@ -236,12 +242,19 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 out_free_recv_cq:
 	ib_destroy_cq(priv->recv_cq);
 
+out_cm_dev_cleanup:
+	ipoib_cm_dev_cleanup(dev);
+
+out_free_wq:
+	destroy_workqueue(priv->wq);
+	priv->wq = NULL;
+
 out_free_mr:
 	ib_dereg_mr(priv->mr);
-	ipoib_cm_dev_cleanup(dev);
 
 out_free_pd:
 	ib_dealloc_pd(priv->pd);
+
 	return -ENODEV;
 }
 
@@ -265,11 +278,18 @@ void ipoib_transport_dev_cleanup(struct net_device *dev)
 
 	ipoib_cm_dev_cleanup(dev);
 
+	if (priv->wq) {
+		flush_workqueue(priv->wq);
+		destroy_workqueue(priv->wq);
+		priv->wq = NULL;
+	}
+
 	if (ib_dereg_mr(priv->mr))
 		ipoib_warn(priv, "ib_dereg_mr failed\n");
 
 	if (ib_dealloc_pd(priv->pd))
 		ipoib_warn(priv, "ib_dealloc_pd failed\n");
+
 }
 
 void ipoib_event(struct ib_event_handler *handler,

drivers/infiniband/ulp/iser/iscsi_iser.h

@@ -69,7 +69,7 @@
 
 #define DRV_NAME	"iser"
 #define PFX		DRV_NAME ": "
-#define DRV_VER		"1.5"
+#define DRV_VER		"1.6"
 
 #define iser_dbg(fmt, arg...)				 \
 	do {						 \
@@ -218,22 +218,21 @@ enum iser_data_dir {
 /**
  * struct iser_data_buf - iSER data buffer
  *
- * @buf:          pointer to the sg list
+ * @sg:           pointer to the sg list
  * @size:         num entries of this sg
  * @data_len:     total beffer byte len
  * @dma_nents:    returned by dma_map_sg
- * @copy_buf:     allocated copy buf for SGs unaligned
- *                for rdma which are copied
- * @sg_single:    SG-ified clone of a non SG SC or
- *                unaligned SG
+ * @orig_sg:      pointer to the original sg list (in case
+ *                we used a copy)
+ * @orig_size:    num entris of orig sg list
  */
 struct iser_data_buf {
-	void               *buf;
+	struct scatterlist *sg;
 	unsigned int       size;
 	unsigned long      data_len;
 	unsigned int       dma_nents;
-	char               *copy_buf;
-	struct scatterlist sg_single;
+	struct scatterlist *orig_sg;
+	unsigned int       orig_size;
   };
 
 /* fwd declarations */
@@ -244,37 +243,16 @@ struct iscsi_endpoint;
 /**
  * struct iser_mem_reg - iSER memory registration info
  *
- * @lkey:         MR local key
- * @rkey:         MR remote key
- * @va:           MR start address (buffer va)
- * @len:          MR length
+ * @sge:          memory region sg element
+ * @rkey:         memory region remote key
  * @mem_h:        pointer to registration context (FMR/Fastreg)
  */
 struct iser_mem_reg {
-	u32  lkey;
+	struct ib_sge	 sge;
 	u32		 rkey;
-	u64  va;
-	u64  len;
 	void		*mem_h;
 };
 
-/**
- * struct iser_regd_buf - iSER buffer registration desc
- *
- * @reg:          memory registration info
- * @virt_addr:    virtual address of buffer
- * @device:       reference to iser device
- * @direction:    dma direction (for dma_unmap)
- * @data_size:    data buffer size in bytes
- */
-struct iser_regd_buf {
-	struct iser_mem_reg     reg;
-	void                    *virt_addr;
-	struct iser_device      *device;
-	enum dma_data_direction direction;
-	unsigned int            data_size;
-};
-
 enum iser_desc_type {
 	ISCSI_TX_CONTROL ,
 	ISCSI_TX_SCSI_COMMAND,
@@ -534,11 +512,9 @@ struct iser_conn {
  * @sc:               link to scsi command
  * @command_sent:     indicate if command was sent
  * @dir:              iser data direction
- * @rdma_regd:        task rdma registration desc
+ * @rdma_reg:         task rdma registration desc
  * @data:             iser data buffer desc
- * @data_copy:        iser data copy buffer desc (bounce buffer)
  * @prot:             iser protection buffer desc
- * @prot_copy:        iser protection copy buffer desc (bounce buffer)
  */
 struct iscsi_iser_task {
 	struct iser_tx_desc          desc;
@@ -547,11 +523,9 @@ struct iscsi_iser_task {
 	struct scsi_cmnd	     *sc;
 	int                          command_sent;
 	int                          dir[ISER_DIRS_NUM];
-	struct iser_regd_buf         rdma_regd[ISER_DIRS_NUM];
+	struct iser_mem_reg          rdma_reg[ISER_DIRS_NUM];
 	struct iser_data_buf         data[ISER_DIRS_NUM];
-	struct iser_data_buf         data_copy[ISER_DIRS_NUM];
 	struct iser_data_buf         prot[ISER_DIRS_NUM];
-	struct iser_data_buf         prot_copy[ISER_DIRS_NUM];
 };
 
 struct iser_page_vec {
@@ -621,7 +595,6 @@ void iser_free_rx_descriptors(struct iser_conn *iser_conn);
 
 void iser_finalize_rdma_unaligned_sg(struct iscsi_iser_task *iser_task,
 				     struct iser_data_buf *mem,
-				     struct iser_data_buf *mem_copy,
 				     enum iser_data_dir cmd_dir);
 
 int  iser_reg_rdma_mem_fmr(struct iscsi_iser_task *task,
@@ -634,10 +607,6 @@ int  iser_connect(struct iser_conn *iser_conn,
 		  struct sockaddr *dst_addr,
 		  int non_blocking);
 
-int  iser_reg_page_vec(struct ib_conn *ib_conn,
-		       struct iser_page_vec *page_vec,
-		       struct iser_mem_reg *mem_reg);
-
 void iser_unreg_mem_fmr(struct iscsi_iser_task *iser_task,
 			enum iser_data_dir cmd_dir);
 void iser_unreg_mem_fastreg(struct iscsi_iser_task *iser_task,
@@ -667,4 +636,9 @@ int iser_create_fastreg_pool(struct ib_conn *ib_conn, unsigned cmds_max);
 void iser_free_fastreg_pool(struct ib_conn *ib_conn);
 u8 iser_check_task_pi_status(struct iscsi_iser_task *iser_task,
 			     enum iser_data_dir cmd_dir, sector_t *sector);
+struct fast_reg_descriptor *
+iser_reg_desc_get(struct ib_conn *ib_conn);
+void
+iser_reg_desc_put(struct ib_conn *ib_conn,
+		  struct fast_reg_descriptor *desc);
 #endif

drivers/infiniband/ulp/iser/iser_initiator.c

@@ -50,7 +50,7 @@ static int iser_prepare_read_cmd(struct iscsi_task *task)
 {
 	struct iscsi_iser_task *iser_task = task->dd_data;
 	struct iser_device  *device = iser_task->iser_conn->ib_conn.device;
-	struct iser_regd_buf *regd_buf;
+	struct iser_mem_reg *mem_reg;
 	int err;
 	struct iser_hdr *hdr = &iser_task->desc.iser_header;
 	struct iser_data_buf *buf_in = &iser_task->data[ISER_DIR_IN];
@@ -78,15 +78,15 @@ static int iser_prepare_read_cmd(struct iscsi_task *task)
 		iser_err("Failed to set up Data-IN RDMA\n");
 		return err;
 	}
-	regd_buf = &iser_task->rdma_regd[ISER_DIR_IN];
+	mem_reg = &iser_task->rdma_reg[ISER_DIR_IN];
 
 	hdr->flags    |= ISER_RSV;
-	hdr->read_stag = cpu_to_be32(regd_buf->reg.rkey);
-	hdr->read_va   = cpu_to_be64(regd_buf->reg.va);
+	hdr->read_stag = cpu_to_be32(mem_reg->rkey);
+	hdr->read_va   = cpu_to_be64(mem_reg->sge.addr);
 
 	iser_dbg("Cmd itt:%d READ tags RKEY:%#.4X VA:%#llX\n",
-		 task->itt, regd_buf->reg.rkey,
-		 (unsigned long long)regd_buf->reg.va);
+		 task->itt, mem_reg->rkey,
+		 (unsigned long long)mem_reg->sge.addr);
 
 	return 0;
 }
@@ -104,7 +104,7 @@ iser_prepare_write_cmd(struct iscsi_task *task,
 {
 	struct iscsi_iser_task *iser_task = task->dd_data;
 	struct iser_device  *device = iser_task->iser_conn->ib_conn.device;
-	struct iser_regd_buf *regd_buf;
+	struct iser_mem_reg *mem_reg;
 	int err;
 	struct iser_hdr *hdr = &iser_task->desc.iser_header;
 	struct iser_data_buf *buf_out = &iser_task->data[ISER_DIR_OUT];
@@ -134,25 +134,25 @@ iser_prepare_write_cmd(struct iscsi_task *task,
 		return err;
 	}
 
-	regd_buf = &iser_task->rdma_regd[ISER_DIR_OUT];
+	mem_reg = &iser_task->rdma_reg[ISER_DIR_OUT];
 
 	if (unsol_sz < edtl) {
 		hdr->flags     |= ISER_WSV;
-		hdr->write_stag = cpu_to_be32(regd_buf->reg.rkey);
-		hdr->write_va   = cpu_to_be64(regd_buf->reg.va + unsol_sz);
+		hdr->write_stag = cpu_to_be32(mem_reg->rkey);
+		hdr->write_va   = cpu_to_be64(mem_reg->sge.addr + unsol_sz);
 
 		iser_dbg("Cmd itt:%d, WRITE tags, RKEY:%#.4X "
 			 "VA:%#llX + unsol:%d\n",
-			 task->itt, regd_buf->reg.rkey,
-			 (unsigned long long)regd_buf->reg.va, unsol_sz);
+			 task->itt, mem_reg->rkey,
+			 (unsigned long long)mem_reg->sge.addr, unsol_sz);
 	}
 
 	if (imm_sz > 0) {
 		iser_dbg("Cmd itt:%d, WRITE, adding imm.data sz: %d\n",
 			 task->itt, imm_sz);
-		tx_dsg->addr   = regd_buf->reg.va;
+		tx_dsg->addr = mem_reg->sge.addr;
 		tx_dsg->length = imm_sz;
-		tx_dsg->lkey   = regd_buf->reg.lkey;
+		tx_dsg->lkey = mem_reg->sge.lkey;
 		iser_task->desc.num_sge = 2;
 	}
 
@@ -401,16 +401,16 @@ int iser_send_command(struct iscsi_conn *conn,
 	}
 
 	if (scsi_sg_count(sc)) { /* using a scatter list */
-		data_buf->buf  = scsi_sglist(sc);
+		data_buf->sg = scsi_sglist(sc);
 		data_buf->size = scsi_sg_count(sc);
 	}
 	data_buf->data_len = scsi_bufflen(sc);
 
 	if (scsi_prot_sg_count(sc)) {
-		prot_buf->buf  = scsi_prot_sglist(sc);
+		prot_buf->sg  = scsi_prot_sglist(sc);
 		prot_buf->size = scsi_prot_sg_count(sc);
-		prot_buf->data_len = data_buf->data_len >>
-				     ilog2(sc->device->sector_size) * 8;
+		prot_buf->data_len = (data_buf->data_len >>
+				     ilog2(sc->device->sector_size)) * 8;
 	}
 
 	if (hdr->flags & ISCSI_FLAG_CMD_READ) {
@@ -450,7 +450,7 @@ int iser_send_data_out(struct iscsi_conn *conn,
 	struct iser_conn *iser_conn = conn->dd_data;
 	struct iscsi_iser_task *iser_task = task->dd_data;
 	struct iser_tx_desc *tx_desc = NULL;
-	struct iser_regd_buf *regd_buf;
+	struct iser_mem_reg *mem_reg;
 	unsigned long buf_offset;
 	unsigned long data_seg_len;
 	uint32_t itt;
@@ -477,11 +477,11 @@ int iser_send_data_out(struct iscsi_conn *conn,
 	/* build the tx desc */
 	iser_initialize_task_headers(task, tx_desc);
 
-	regd_buf = &iser_task->rdma_regd[ISER_DIR_OUT];
+	mem_reg = &iser_task->rdma_reg[ISER_DIR_OUT];
 	tx_dsg = &tx_desc->tx_sg[1];
-	tx_dsg->addr    = regd_buf->reg.va + buf_offset;
+	tx_dsg->addr = mem_reg->sge.addr + buf_offset;
 	tx_dsg->length = data_seg_len;
-	tx_dsg->lkey    = regd_buf->reg.lkey;
+	tx_dsg->lkey = mem_reg->sge.lkey;
 	tx_desc->num_sge = 2;
 
 	if (buf_offset + data_seg_len > iser_task->data[ISER_DIR_OUT].data_len) {
@@ -658,10 +658,10 @@ void iser_task_rdma_init(struct iscsi_iser_task *iser_task)
 	iser_task->prot[ISER_DIR_IN].data_len  = 0;
 	iser_task->prot[ISER_DIR_OUT].data_len = 0;
 
-	memset(&iser_task->rdma_regd[ISER_DIR_IN], 0,
-	       sizeof(struct iser_regd_buf));
-	memset(&iser_task->rdma_regd[ISER_DIR_OUT], 0,
-	       sizeof(struct iser_regd_buf));
+	memset(&iser_task->rdma_reg[ISER_DIR_IN], 0,
+	       sizeof(struct iser_mem_reg));
+	memset(&iser_task->rdma_reg[ISER_DIR_OUT], 0,
+	       sizeof(struct iser_mem_reg));
 }
 
 void iser_task_rdma_finalize(struct iscsi_iser_task *iser_task)
@@ -674,35 +674,31 @@ void iser_task_rdma_finalize(struct iscsi_iser_task *iser_task)
 	/* if we were reading, copy back to unaligned sglist,
 	 * anyway dma_unmap and free the copy
 	 */
-	if (iser_task->data_copy[ISER_DIR_IN].copy_buf != NULL) {
+	if (iser_task->data[ISER_DIR_IN].orig_sg) {
 		is_rdma_data_aligned = 0;
 		iser_finalize_rdma_unaligned_sg(iser_task,
 						&iser_task->data[ISER_DIR_IN],
-						&iser_task->data_copy[ISER_DIR_IN],
 						ISER_DIR_IN);
 	}
 
-	if (iser_task->data_copy[ISER_DIR_OUT].copy_buf != NULL) {
+	if (iser_task->data[ISER_DIR_OUT].orig_sg) {
 		is_rdma_data_aligned = 0;
 		iser_finalize_rdma_unaligned_sg(iser_task,
 						&iser_task->data[ISER_DIR_OUT],
-						&iser_task->data_copy[ISER_DIR_OUT],
 						ISER_DIR_OUT);
 	}
 
-	if (iser_task->prot_copy[ISER_DIR_IN].copy_buf != NULL) {
+	if (iser_task->prot[ISER_DIR_IN].orig_sg) {
 		is_rdma_prot_aligned = 0;
 		iser_finalize_rdma_unaligned_sg(iser_task,
 						&iser_task->prot[ISER_DIR_IN],
-						&iser_task->prot_copy[ISER_DIR_IN],
 						ISER_DIR_IN);
 	}
 
-	if (iser_task->prot_copy[ISER_DIR_OUT].copy_buf != NULL) {
+	if (iser_task->prot[ISER_DIR_OUT].orig_sg) {
 		is_rdma_prot_aligned = 0;
 		iser_finalize_rdma_unaligned_sg(iser_task,
 						&iser_task->prot[ISER_DIR_OUT],
-						&iser_task->prot_copy[ISER_DIR_OUT],
 						ISER_DIR_OUT);
 	}
 

drivers/infiniband/ulp/iser/iser_verbs.c

@@ -274,46 +274,24 @@ void iser_free_fmr_pool(struct ib_conn *ib_conn)
 }
 
 static int
-iser_create_fastreg_desc(struct ib_device *ib_device, struct ib_pd *pd,
-			 bool pi_enable, struct fast_reg_descriptor *desc)
+iser_alloc_pi_ctx(struct ib_device *ib_device, struct ib_pd *pd,
+		  struct fast_reg_descriptor *desc)
 {
-	int ret;
-
-	desc->data_frpl = ib_alloc_fast_reg_page_list(ib_device,
-						      ISCSI_ISER_SG_TABLESIZE + 1);
-	if (IS_ERR(desc->data_frpl)) {
-		ret = PTR_ERR(desc->data_frpl);
-		iser_err("Failed to allocate ib_fast_reg_page_list err=%d\n",
-			 ret);
-		return PTR_ERR(desc->data_frpl);
-	}
-
-	desc->data_mr = ib_alloc_fast_reg_mr(pd, ISCSI_ISER_SG_TABLESIZE + 1);
-	if (IS_ERR(desc->data_mr)) {
-		ret = PTR_ERR(desc->data_mr);
-		iser_err("Failed to allocate ib_fast_reg_mr err=%d\n", ret);
-		goto fast_reg_mr_failure;
-	}
-	desc->reg_indicators |= ISER_DATA_KEY_VALID;
-
-	if (pi_enable) {
-		struct ib_mr_init_attr mr_init_attr = {0};
 	struct iser_pi_context *pi_ctx = NULL;
+	struct ib_mr_init_attr mr_init_attr = {.max_reg_descriptors = 2,
+					       .flags = IB_MR_SIGNATURE_EN};
+	int ret = 0;
 
 	desc->pi_ctx = kzalloc(sizeof(*desc->pi_ctx), GFP_KERNEL);
-		if (!desc->pi_ctx) {
-			iser_err("Failed to allocate pi context\n");
-			ret = -ENOMEM;
-			goto pi_ctx_alloc_failure;
-		}
+	if (!desc->pi_ctx)
+		return -ENOMEM;
+
 	pi_ctx = desc->pi_ctx;
 
 	pi_ctx->prot_frpl = ib_alloc_fast_reg_page_list(ib_device,
 					    ISCSI_ISER_SG_TABLESIZE);
 	if (IS_ERR(pi_ctx->prot_frpl)) {
 		ret = PTR_ERR(pi_ctx->prot_frpl);
-			iser_err("Failed to allocate prot frpl ret=%d\n",
-				 ret);
 		goto prot_frpl_failure;
 	}
 
@@ -321,35 +299,69 @@ iser_create_fastreg_desc(struct ib_device *ib_device, struct ib_pd *pd,
 					ISCSI_ISER_SG_TABLESIZE + 1);
 	if (IS_ERR(pi_ctx->prot_mr)) {
 		ret = PTR_ERR(pi_ctx->prot_mr);
-			iser_err("Failed to allocate prot frmr ret=%d\n",
-				 ret);
 		goto prot_mr_failure;
 	}
 	desc->reg_indicators |= ISER_PROT_KEY_VALID;
 
-		mr_init_attr.max_reg_descriptors = 2;
-		mr_init_attr.flags |= IB_MR_SIGNATURE_EN;
 	pi_ctx->sig_mr = ib_create_mr(pd, &mr_init_attr);
 	if (IS_ERR(pi_ctx->sig_mr)) {
 		ret = PTR_ERR(pi_ctx->sig_mr);
-			iser_err("Failed to allocate signature enabled mr err=%d\n",
-				 ret);
 		goto sig_mr_failure;
 	}
 	desc->reg_indicators |= ISER_SIG_KEY_VALID;
-	}
 	desc->reg_indicators &= ~ISER_FASTREG_PROTECTED;
 
-	iser_dbg("Create fr_desc %p page_list %p\n",
-		 desc, desc->data_frpl->page_list);
-
 	return 0;
+
 sig_mr_failure:
 	ib_dereg_mr(desc->pi_ctx->prot_mr);
 prot_mr_failure:
 	ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl);
 prot_frpl_failure:
 	kfree(desc->pi_ctx);
+
+	return ret;
+}
+
+static void
+iser_free_pi_ctx(struct iser_pi_context *pi_ctx)
+{
+	ib_free_fast_reg_page_list(pi_ctx->prot_frpl);
+	ib_dereg_mr(pi_ctx->prot_mr);
+	ib_destroy_mr(pi_ctx->sig_mr);
+	kfree(pi_ctx);
+}
+
+static int
+iser_create_fastreg_desc(struct ib_device *ib_device, struct ib_pd *pd,
+			 bool pi_enable, struct fast_reg_descriptor *desc)
+{
+	int ret;
+
+	desc->data_frpl = ib_alloc_fast_reg_page_list(ib_device,
+						      ISCSI_ISER_SG_TABLESIZE + 1);
+	if (IS_ERR(desc->data_frpl)) {
+		ret = PTR_ERR(desc->data_frpl);
+		iser_err("Failed to allocate ib_fast_reg_page_list err=%d\n",
+			 ret);
+		return PTR_ERR(desc->data_frpl);
+	}
+
+	desc->data_mr = ib_alloc_fast_reg_mr(pd, ISCSI_ISER_SG_TABLESIZE + 1);
+	if (IS_ERR(desc->data_mr)) {
+		ret = PTR_ERR(desc->data_mr);
+		iser_err("Failed to allocate ib_fast_reg_mr err=%d\n", ret);
+		goto fast_reg_mr_failure;
+	}
+	desc->reg_indicators |= ISER_DATA_KEY_VALID;
+
+	if (pi_enable) {
+		ret = iser_alloc_pi_ctx(ib_device, pd, desc);
+		if (ret)
+			goto pi_ctx_alloc_failure;
+	}
+
+	return 0;
 pi_ctx_alloc_failure:
 	ib_dereg_mr(desc->data_mr);
 fast_reg_mr_failure:
@@ -416,12 +428,8 @@ void iser_free_fastreg_pool(struct ib_conn *ib_conn)
 		list_del(&desc->list);
 		ib_free_fast_reg_page_list(desc->data_frpl);
 		ib_dereg_mr(desc->data_mr);
-		if (desc->pi_ctx) {
-			ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl);
-			ib_dereg_mr(desc->pi_ctx->prot_mr);
-			ib_destroy_mr(desc->pi_ctx->sig_mr);
-			kfree(desc->pi_ctx);
-		}
+		if (desc->pi_ctx)
+			iser_free_pi_ctx(desc->pi_ctx);
 		kfree(desc);
 		++i;
 	}
@@ -721,7 +729,7 @@ static void iser_connect_error(struct rdma_cm_id *cma_id)
 	struct iser_conn *iser_conn;
 
 	iser_conn = (struct iser_conn *)cma_id->context;
-	iser_conn->state = ISER_CONN_DOWN;
+	iser_conn->state = ISER_CONN_TERMINATING;
 }
 
 /**
@@ -992,93 +1000,6 @@ int iser_connect(struct iser_conn   *iser_conn,
 	return err;
 }
 
-/**
- * iser_reg_page_vec - Register physical memory
- *
- * returns: 0 on success, errno code on failure
- */
-int iser_reg_page_vec(struct ib_conn *ib_conn,
-		      struct iser_page_vec *page_vec,
-		      struct iser_mem_reg  *mem_reg)
-{
-	struct ib_pool_fmr *mem;
-	u64		   io_addr;
-	u64		   *page_list;
-	int		   status;
-
-	page_list = page_vec->pages;
-	io_addr	  = page_list[0];
-
-	mem  = ib_fmr_pool_map_phys(ib_conn->fmr.pool,
-				    page_list,
-				    page_vec->length,
-				    io_addr);
-
-	if (IS_ERR(mem)) {
-		status = (int)PTR_ERR(mem);
-		iser_err("ib_fmr_pool_map_phys failed: %d\n", status);
-		return status;
-	}
-
-	mem_reg->lkey  = mem->fmr->lkey;
-	mem_reg->rkey  = mem->fmr->rkey;
-	mem_reg->len   = page_vec->length * SIZE_4K;
-	mem_reg->va    = io_addr;
-	mem_reg->mem_h = (void *)mem;
-
-	mem_reg->va   += page_vec->offset;
-	mem_reg->len   = page_vec->data_size;
-
-	iser_dbg("PHYSICAL Mem.register, [PHYS p_array: 0x%p, sz: %d, "
-		 "entry[0]: (0x%08lx,%ld)] -> "
-		 "[lkey: 0x%08X mem_h: 0x%p va: 0x%08lX sz: %ld]\n",
-		 page_vec, page_vec->length,
-		 (unsigned long)page_vec->pages[0],
-		 (unsigned long)page_vec->data_size,
-		 (unsigned int)mem_reg->lkey, mem_reg->mem_h,
-		 (unsigned long)mem_reg->va, (unsigned long)mem_reg->len);
-	return 0;
-}
-
-/**
- * Unregister (previosuly registered using FMR) memory.
- * If memory is non-FMR does nothing.
- */
-void iser_unreg_mem_fmr(struct iscsi_iser_task *iser_task,
-			enum iser_data_dir cmd_dir)
-{
-	struct iser_mem_reg *reg = &iser_task->rdma_regd[cmd_dir].reg;
-	int ret;
-
-	if (!reg->mem_h)
-		return;
-
-	iser_dbg("PHYSICAL Mem.Unregister mem_h %p\n",reg->mem_h);
-
-	ret = ib_fmr_pool_unmap((struct ib_pool_fmr *)reg->mem_h);
-	if (ret)
-		iser_err("ib_fmr_pool_unmap failed %d\n", ret);
-
-	reg->mem_h = NULL;
-}
-
-void iser_unreg_mem_fastreg(struct iscsi_iser_task *iser_task,
-			    enum iser_data_dir cmd_dir)
-{
-	struct iser_mem_reg *reg = &iser_task->rdma_regd[cmd_dir].reg;
-	struct iser_conn *iser_conn = iser_task->iser_conn;
-	struct ib_conn *ib_conn = &iser_conn->ib_conn;
-	struct fast_reg_descriptor *desc = reg->mem_h;
-
-	if (!desc)
-		return;
-
-	reg->mem_h = NULL;
-	spin_lock_bh(&ib_conn->lock);
-	list_add_tail(&desc->list, &ib_conn->fastreg.pool);
-	spin_unlock_bh(&ib_conn->lock);
-}
-
 int iser_post_recvl(struct iser_conn *iser_conn)
 {
 	struct ib_recv_wr rx_wr, *rx_wr_failed;
@@ -1210,6 +1131,9 @@ iser_handle_comp_error(struct ib_conn *ib_conn,
 			iscsi_conn_failure(iser_conn->iscsi_conn,
 					   ISCSI_ERR_CONN_FAILED);
 
+	if (wc->wr_id == ISER_FASTREG_LI_WRID)
+		return;
+
 	if (is_iser_tx_desc(iser_conn, wr_id)) {
 		struct iser_tx_desc *desc = wr_id;
 
@@ -1254,13 +1178,11 @@ static void iser_handle_wc(struct ib_wc *wc)
 		else
 			iser_dbg("flush error: wr id %llx\n", wc->wr_id);
 
-		if (wc->wr_id != ISER_FASTREG_LI_WRID &&
-		    wc->wr_id != ISER_BEACON_WRID)
-			iser_handle_comp_error(ib_conn, wc);
-
-		/* complete in case all flush errors were consumed */
 		if (wc->wr_id == ISER_BEACON_WRID)
+			/* all flush errors were consumed */
 			complete(&ib_conn->flush_comp);
+		else
+			iser_handle_comp_error(ib_conn, wc);
 	}
 }
 
@@ -1306,7 +1228,7 @@ static void iser_cq_callback(struct ib_cq *cq, void *cq_context)
 u8 iser_check_task_pi_status(struct iscsi_iser_task *iser_task,
 			     enum iser_data_dir cmd_dir, sector_t *sector)
 {
-	struct iser_mem_reg *reg = &iser_task->rdma_regd[cmd_dir].reg;
+	struct iser_mem_reg *reg = &iser_task->rdma_reg[cmd_dir];
 	struct fast_reg_descriptor *desc = reg->mem_h;
 	unsigned long sector_size = iser_task->sc->device->sector_size;
 	struct ib_mr_status mr_status;

drivers/infiniband/ulp/srp/ib_srp.c

@@ -40,6 +40,7 @@
 #include <linux/parser.h>
 #include <linux/random.h>
 #include <linux/jiffies.h>
+#include <rdma/ib_cache.h>
 
 #include <linux/atomic.h>
 
@@ -265,7 +266,7 @@ static int srp_init_qp(struct srp_target_port *target,
 	if (!attr)
 		return -ENOMEM;
 
-	ret = ib_find_pkey(target->srp_host->srp_dev->dev,
+	ret = ib_find_cached_pkey(target->srp_host->srp_dev->dev,
 				  target->srp_host->port,
 				  be16_to_cpu(target->pkey),
 				  &attr->pkey_index);

drivers/net/ethernet/mellanox/mlx4/cmd.c

@@ -939,21 +939,34 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 				return err;
 			}
 			if (smp->attr_id == IB_SMP_ATTR_GUID_INFO) {
-				/* compute slave's gid block */
-				smp->attr_mod = cpu_to_be32(slave / 8);
-				/* execute cmd */
-				err = mlx4_cmd_box(dev, inbox->dma, outbox->dma,
-					     vhcr->in_modifier, opcode_modifier,
-					     vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
-				if (!err) {
-					/* if needed, move slave gid to index 0 */
-					if (slave % 8)
-						memcpy(outsmp->data,
-						       outsmp->data + (slave % 8) * 8, 8);
-					/* delete all other gids */
-					memset(outsmp->data + 8, 0, 56);
-				}
+				__be64 guid = mlx4_get_admin_guid(dev, slave,
+								  port);
+
+				/* set the PF admin guid to the FW/HW burned
+				 * GUID, if it wasn't yet set
+				 */
+				if (slave == 0 && guid == 0) {
+					smp->attr_mod = 0;
+					err = mlx4_cmd_box(dev,
+							   inbox->dma,
+							   outbox->dma,
+							   vhcr->in_modifier,
+							   opcode_modifier,
+							   vhcr->op,
+							   MLX4_CMD_TIME_CLASS_C,
+							   MLX4_CMD_NATIVE);
+					if (err)
 						return err;
+					mlx4_set_admin_guid(dev,
+							    *(__be64 *)outsmp->
+							    data, slave, port);
+				} else {
+					memcpy(outsmp->data, &guid, 8);
+				}
+
+				/* clean all other gids */
+				memset(outsmp->data + 8, 0, 56);
+				return 0;
 			}
 			if (smp->attr_id == IB_SMP_ATTR_NODE_INFO) {
 				err = mlx4_cmd_box(dev, inbox->dma, outbox->dma,
@@ -2350,6 +2363,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 				oper_vport->qos_vport = MLX4_VPP_DEFAULT_VPORT;
 				vf_oper->vport[port].vlan_idx = NO_INDX;
 				vf_oper->vport[port].mac_idx = NO_INDX;
+				mlx4_set_random_admin_guid(dev, i, port);
 			}
 			spin_lock_init(&s_state->lock);
 		}

drivers/net/ethernet/mellanox/mlx4/eq.c

@@ -702,6 +702,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 				priv->mfunc.master.slave_state[flr_slave].is_slave_going_down = 1;
 			}
 			spin_unlock_irqrestore(&priv->mfunc.master.slave_state_lock, flags);
+			mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN,
+					    flr_slave);
 			queue_work(priv->mfunc.master.comm_wq,
 				   &priv->mfunc.master.slave_flr_event_work);
 			break;

drivers/net/ethernet/mellanox/mlx4/main.c

@@ -2260,6 +2260,37 @@ void mlx4_counter_free(struct mlx4_dev *dev, u32 idx)
 }
 EXPORT_SYMBOL_GPL(mlx4_counter_free);
 
+void mlx4_set_admin_guid(struct mlx4_dev *dev, __be64 guid, int entry, int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	priv->mfunc.master.vf_admin[entry].vport[port].guid = guid;
+}
+EXPORT_SYMBOL_GPL(mlx4_set_admin_guid);
+
+__be64 mlx4_get_admin_guid(struct mlx4_dev *dev, int entry, int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return priv->mfunc.master.vf_admin[entry].vport[port].guid;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_admin_guid);
+
+void mlx4_set_random_admin_guid(struct mlx4_dev *dev, int entry, int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	__be64 guid;
+
+	/* hw GUID */
+	if (entry == 0)
+		return;
+
+	get_random_bytes((char *)&guid, sizeof(guid));
+	guid &= ~(cpu_to_be64(1ULL << 56));
+	guid |= cpu_to_be64(1ULL << 57);
+	priv->mfunc.master.vf_admin[entry].vport[port].guid = guid;
+}
+
 static int mlx4_setup_hca(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);

drivers/net/ethernet/mellanox/mlx4/mlx4.h

@@ -499,6 +499,7 @@ struct mlx4_vport_state {
 	bool spoofchk;
 	u32 link_state;
 	u8 qos_vport;
+	__be64 guid;
 };
 
 struct mlx4_vf_admin_state {

drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c

@@ -211,26 +211,28 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr)
 	return 0;
 }
 
+#define MLX5_U64_4K_PAGE_MASK ((~(u64)0U) << PAGE_SHIFT)
+
 static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 {
 	struct fw_page *fwp;
 	int n;
 
-	fwp = find_fw_page(dev, addr & PAGE_MASK);
+	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK);
 	if (!fwp) {
 		mlx5_core_warn(dev, "page not found\n");
 		return;
 	}
 
-	n = (addr & ~PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
+	n = (addr & ~MLX5_U64_4K_PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
 	fwp->free_count++;
 	set_bit(n, &fwp->bitmask);
 	if (fwp->free_count == MLX5_NUM_4K_IN_PAGE) {
 		rb_erase(&fwp->rb_node, &dev->priv.page_root);
 		if (fwp->free_count != 1)
 			list_del(&fwp->list);
-		dma_unmap_page(&dev->pdev->dev, addr & PAGE_MASK, PAGE_SIZE,
-			       DMA_BIDIRECTIONAL);
+		dma_unmap_page(&dev->pdev->dev, addr & MLX5_U64_4K_PAGE_MASK,
+			       PAGE_SIZE, DMA_BIDIRECTIONAL);
 		__free_page(fwp->page);
 		kfree(fwp);
 	} else if (fwp->free_count == 1) {

include/linux/mlx4/device.h

@@ -1345,6 +1345,10 @@ int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
 int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx);
 void mlx4_counter_free(struct mlx4_dev *dev, u32 idx);
 
+void mlx4_set_admin_guid(struct mlx4_dev *dev, __be64 guid, int entry,
+			 int port);
+__be64 mlx4_get_admin_guid(struct mlx4_dev *dev, int entry, int port);
+void mlx4_set_random_admin_guid(struct mlx4_dev *dev, int entry, int port);
 int mlx4_flow_attach(struct mlx4_dev *dev,
 		     struct mlx4_net_trans_rule *rule, u64 *reg_id);
 int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id);