Merge branch 'bart-srpt-for-next' into k.o/wip/dl-for-next

Merging in 12 patch series from Bart that required changes in the
current for-rc branch in order to apply cleanly.
Signed-off-by: NDoug Ledford <dledford@redhat.com>

drivers/infiniband/core/core_priv.h

@@ -293,7 +293,7 @@ static inline int ib_mad_enforce_security(struct ib_mad_agent_private *map,
 }
 #endif
 
-struct ib_device *__ib_device_get_by_index(u32 ifindex);
+struct ib_device *ib_device_get_by_index(u32 ifindex);
 /* RDMA device netlink */
 void nldev_init(void);
 void nldev_exit(void);

drivers/infiniband/core/device.c

@@ -134,7 +134,7 @@ static int ib_device_check_mandatory(struct ib_device *device)
 	return 0;
 }
 
-struct ib_device *__ib_device_get_by_index(u32 index)
+static struct ib_device *__ib_device_get_by_index(u32 index)
 {
 	struct ib_device *device;
 
@@ -145,6 +145,22 @@ struct ib_device *__ib_device_get_by_index(u32 index)
 	return NULL;
 }
 
+/*
+ * Caller is responsible to return refrerence count by calling put_device()
+ */
+struct ib_device *ib_device_get_by_index(u32 index)
+{
+	struct ib_device *device;
+
+	down_read(&lists_rwsem);
+	device = __ib_device_get_by_index(index);
+	if (device)
+		get_device(&device->dev);
+
+	up_read(&lists_rwsem);
+	return device;
+}
+
 static struct ib_device *__ib_device_get_by_name(const char *name)
 {
 	struct ib_device *device;

drivers/infiniband/core/nldev.c

@@ -150,27 +150,34 @@ static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
 
-	device = __ib_device_get_by_index(index);
+	device = ib_device_get_by_index(index);
 	if (!device)
 		return -EINVAL;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
+	if (!msg) {
+		err = -ENOMEM;
+		goto err;
+	}
 
 	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
 			0, 0);
 
 	err = fill_dev_info(msg, device);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
+	if (err)
+		goto err_free;
 
 	nlmsg_end(msg, nlh);
 
+	put_device(&device->dev);
 	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+
+err_free:
+	nlmsg_free(msg);
+err:
+	put_device(&device->dev);
+	return err;
 }
 
 static int _nldev_get_dumpit(struct ib_device *device,
@@ -228,31 +235,40 @@ static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 
 	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
-	device = __ib_device_get_by_index(index);
+	device = ib_device_get_by_index(index);
 	if (!device)
 		return -EINVAL;
 
 	port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
-	if (!rdma_is_port_valid(device, port))
-		return -EINVAL;
+	if (!rdma_is_port_valid(device, port)) {
+		err = -EINVAL;
+		goto err;
+	}
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
+	if (!msg) {
+		err = -ENOMEM;
+		goto err;
+	}
 
 	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
 			0, 0);
 
 	err = fill_port_info(msg, device, port);
-	if (err) {
-		nlmsg_free(msg);
-		return err;
-	}
+	if (err)
+		goto err_free;
 
 	nlmsg_end(msg, nlh);
+	put_device(&device->dev);
 
 	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+
+err_free:
+	nlmsg_free(msg);
+err:
+	put_device(&device->dev);
+	return err;
 }
 
 static int nldev_port_get_dumpit(struct sk_buff *skb,
@@ -273,7 +289,7 @@ static int nldev_port_get_dumpit(struct sk_buff *skb,
 		return -EINVAL;
 
 	ifindex = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
-	device = __ib_device_get_by_index(ifindex);
+	device = ib_device_get_by_index(ifindex);
 	if (!device)
 		return -EINVAL;
 
@@ -307,7 +323,9 @@ static int nldev_port_get_dumpit(struct sk_buff *skb,
 		nlmsg_end(skb, nlh);
 	}
 
-out:	cb->args[0] = idx;
+out:
+	put_device(&device->dev);
+	cb->args[0] = idx;
 	return skb->len;
 }
 

drivers/infiniband/hw/mlx4/mr.c

@@ -642,7 +642,6 @@ struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
 		goto err_free_mr;
 
 	mr->max_pages = max_num_sg;
-
 	err = mlx4_mr_enable(dev->dev, &mr->mmr);
 	if (err)
 		goto err_free_pl;
@@ -653,6 +652,7 @@ struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
 	return &mr->ibmr;
 
 err_free_pl:
+	mr->ibmr.device = pd->device;
 	mlx4_free_priv_pages(mr);
 err_free_mr:
 	(void) mlx4_mr_free(dev->dev, &mr->mmr);

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -926,8 +926,8 @@ static int path_rec_start(struct net_device *dev,
 	return 0;
 }
 
-static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
-			   struct net_device *dev)
+static struct ipoib_neigh *neigh_add_path(struct sk_buff *skb, u8 *daddr,
+					  struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 	struct rdma_netdev *rn = netdev_priv(dev);
@@ -941,7 +941,15 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 		spin_unlock_irqrestore(&priv->lock, flags);
 		++dev->stats.tx_dropped;
 		dev_kfree_skb_any(skb);
-		return;
+		return NULL;
+	}
+
+	/* To avoid race condition, make sure that the
+	 * neigh will be added only once.
+	 */
+	if (unlikely(!list_empty(&neigh->list))) {
+		spin_unlock_irqrestore(&priv->lock, flags);
+		return neigh;
 	}
 
 	path = __path_find(dev, daddr + 4);
@@ -980,7 +988,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 			path->ah->last_send = rn->send(dev, skb, path->ah->ah,
 						       IPOIB_QPN(daddr));
 			ipoib_neigh_put(neigh);
-			return;
+			return NULL;
 		}
 	} else {
 		neigh->ah  = NULL;
@@ -997,7 +1005,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 	ipoib_neigh_put(neigh);
-	return;
+	return NULL;
 
 err_path:
 	ipoib_neigh_free(neigh);
@@ -1007,6 +1015,8 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 	ipoib_neigh_put(neigh);
+
+	return NULL;
 }
 
 static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
@@ -1127,8 +1137,9 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	case htons(ETH_P_TIPC):
 		neigh = ipoib_neigh_get(dev, phdr->hwaddr);
 		if (unlikely(!neigh)) {
-			neigh_add_path(skb, phdr->hwaddr, dev);
-			return NETDEV_TX_OK;
+			neigh = neigh_add_path(skb, phdr->hwaddr, dev);
+			if (likely(!neigh))
+				return NETDEV_TX_OK;
 		}
 		break;
 	case htons(ETH_P_ARP):

drivers/infiniband/ulp/ipoib/ipoib_multicast.c

@@ -816,7 +816,10 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
 		spin_lock_irqsave(&priv->lock, flags);
 		if (!neigh) {
 			neigh = ipoib_neigh_alloc(daddr, dev);
-			if (neigh) {
+			/* Make sure that the neigh will be added only
+			 * once to mcast list.
+			 */
+			if (neigh && list_empty(&neigh->list)) {
 				kref_get(&mcast->ah->ref);
 				neigh->ah	= mcast->ah;
 				list_add_tail(&neigh->list, &mcast->neigh_list);

drivers/infiniband/ulp/srpt/ib_srpt.h

@@ -114,7 +114,7 @@ enum {
 
 	MIN_SRPT_SQ_SIZE = 16,
 	DEF_SRPT_SQ_SIZE = 4096,
-	SRPT_RQ_SIZE = 128,
+	MAX_SRPT_RQ_SIZE = 128,
 	MIN_SRPT_SRQ_SIZE = 4,
 	DEFAULT_SRPT_SRQ_SIZE = 4095,
 	MAX_SRPT_SRQ_SIZE = 65535,
@@ -134,7 +134,7 @@ enum {
 };
 
 /**
- * enum srpt_command_state - SCSI command state managed by SRPT.
+ * enum srpt_command_state - SCSI command state managed by SRPT
  * @SRPT_STATE_NEW:           New command arrived and is being processed.
  * @SRPT_STATE_NEED_DATA:     Processing a write or bidir command and waiting
  *                            for data arrival.
@@ -158,7 +158,8 @@ enum srpt_command_state {
 };
 
 /**
- * struct srpt_ioctx - Shared SRPT I/O context information.
+ * struct srpt_ioctx - shared SRPT I/O context information
+ * @cqe:   Completion queue element.
  * @buf:   Pointer to the buffer.
  * @dma:   DMA address of the buffer.
  * @index: Index of the I/O context in its ioctx_ring array.
@@ -171,7 +172,7 @@ struct srpt_ioctx {
 };
 
 /**
- * struct srpt_recv_ioctx - SRPT receive I/O context.
+ * struct srpt_recv_ioctx - SRPT receive I/O context
  * @ioctx:     See above.
  * @wait_list: Node for insertion in srpt_rdma_ch.cmd_wait_list.
  */
@@ -187,13 +188,20 @@ struct srpt_rw_ctx {
 };
 
 /**
- * struct srpt_send_ioctx - SRPT send I/O context.
+ * struct srpt_send_ioctx - SRPT send I/O context
  * @ioctx:       See above.
  * @ch:          Channel pointer.
- * @spinlock:    Protects 'state'.
+ * @s_rw_ctx:    @rw_ctxs points here if only a single rw_ctx is needed.
+ * @rw_ctxs:     RDMA read/write contexts.
+ * @rdma_cqe:    RDMA completion queue element.
+ * @free_list:   Node in srpt_rdma_ch.free_list.
  * @state:       I/O context state.
  * @cmd:         Target core command data structure.
  * @sense_data:  SCSI sense data.
+ * @n_rdma:      Number of work requests needed to transfer this ioctx.
+ * @n_rw_ctx:    Size of rw_ctxs array.
+ * @queue_status_only: Send a SCSI status back to the initiator but no data.
+ * @sense_data:  Sense data to be sent to the initiator.
  */
 struct srpt_send_ioctx {
 	struct srpt_ioctx	ioctx;
@@ -204,10 +212,8 @@ struct srpt_send_ioctx {
 
 	struct ib_cqe		rdma_cqe;
 	struct list_head	free_list;
-	spinlock_t		spinlock;
 	enum srpt_command_state	state;
 	struct se_cmd		cmd;
-	struct completion	tx_done;
 	u8			n_rdma;
 	u8			n_rw_ctx;
 	bool			queue_status_only;
@@ -215,7 +221,7 @@ struct srpt_send_ioctx {
 };
 
 /**
- * enum rdma_ch_state - SRP channel state.
+ * enum rdma_ch_state - SRP channel state
  * @CH_CONNECTING:    QP is in RTR state; waiting for RTU.
  * @CH_LIVE:	      QP is in RTS state.
  * @CH_DISCONNECTING: DREQ has been sent and waiting for DREP or DREQ has
@@ -233,12 +239,14 @@ enum rdma_ch_state {
 };
 
 /**
- * struct srpt_rdma_ch - RDMA channel.
+ * struct srpt_rdma_ch - RDMA channel
  * @cm_id:         IB CM ID associated with the channel.
  * @qp:            IB queue pair used for communicating over this channel.
  * @cq:            IB completion queue for this channel.
+ * @zw_cqe:	   Zero-length write CQE.
+ * @kref:	   kref for this channel.
  * @rq_size:       IB receive queue size.
- * @rsp_size	   IB response message size in bytes.
+ * @max_rsp_size:  Maximum size of an RSP response message in bytes.
  * @sq_wr_avail:   number of work requests available in the send queue.
  * @sport:         pointer to the information of the HCA port used by this
  *                 channel.
@@ -270,7 +278,7 @@ struct srpt_rdma_ch {
 	struct ib_cqe		zw_cqe;
 	struct kref		kref;
 	int			rq_size;
-	u32			rsp_size;
+	u32			max_rsp_size;
 	atomic_t		sq_wr_avail;
 	struct srpt_port	*sport;
 	u8			i_port_id[16];
@@ -293,7 +301,7 @@ struct srpt_rdma_ch {
 };
 
 /**
- * struct srpt_port_attib - Attributes for SRPT port
+ * struct srpt_port_attib - attributes for SRPT port
  * @srp_max_rdma_size: Maximum size of SRP RDMA transfers for new connections.
  * @srp_max_rsp_size: Maximum size of SRP response messages in bytes.
  * @srp_sq_size: Shared receive queue (SRQ) size.
@@ -307,7 +315,7 @@ struct srpt_port_attrib {
 };
 
 /**
- * struct srpt_port - Information associated by SRPT with a single IB port.
+ * struct srpt_port - information associated by SRPT with a single IB port
  * @sdev:      backpointer to the HCA information.
  * @mad_agent: per-port management datagram processing information.
  * @enabled:   Whether or not this target port is enabled.
@@ -323,7 +331,7 @@ struct srpt_port_attrib {
  * @port_guid_wwn: WWN associated with target port GUID.
  * @port_gid_tpg:  TPG associated with target port GID.
  * @port_gid_wwn:  WWN associated with target port GID.
- * @port_acl_list: Head of the list with all node ACLs for this port.
+ * @port_attrib:   Port attributes that can be accessed through configfs.
  */
 struct srpt_port {
 	struct srpt_device	*sdev;
@@ -344,7 +352,7 @@ struct srpt_port {
 };
 
 /**
- * struct srpt_device - Information associated by SRPT with a single HCA.
+ * struct srpt_device - information associated by SRPT with a single HCA
  * @device:        Backpointer to the struct ib_device managed by the IB core.
  * @pd:            IB protection domain.
  * @lkey:          L_Key (local key) with write access to all local memory.