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

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (87 commits)
  mlx4_core: Fix section mismatches
  IPoIB: Allow setting policy to ignore multicast groups
  IB/mthca: Mark error paths as unlikely() in post_srq_recv functions
  IB/ipath: Minor fix to ordering of freeing and zeroing of tid pages.
  IB/ipath: Remove redundant link state checks
  IB/ipath: Fix IB_EVENT_PORT_ERR event
  IB/ipath: Better handling of unexpected GPIO interrupts
  IB/ipath: Maintain active time on all chips
  IB/ipath: Fix QHT7040 serial number check
  IB/ipath: Indicate a couple of chip bugs to userspace
  IB/ipath: iba6110 rev4 no longer needs recv header overrun workaround
  IB/ipath: Use counters in ipath_poll and cleanup interrupts in ipath_close
  IB/ipath: Remove duplicate copy of LMC
  IB/ipath: Add ability to set the LMC via the sysfs debugging interface
  IB/ipath: Optimize completion queue entry insertion and polling
  IB/ipath: Implement IB_EVENT_QP_LAST_WQE_REACHED
  IB/ipath: Generate flush CQE when QP is in error state
  IB/ipath: Remove redundant code
  IB/ipath: Future proof eeprom checksum code (contents reading)
  IB/ipath: UC RDMA WRITE with IMMEDIATE doesn't send the immediate
  ...

89 files changed, 2498 insertions, 1710 deletions

diff --git a/Documentation/infiniband/user_mad.txt b/Documentation/infiniband/user_mad.txt
index 8ec54b974b6..744687dd195 100644
--- a/Documentation/infiniband/user_mad.txt
+++ b/Documentation/infiniband/user_mad.txt
@@ -99,6 +99,20 @@ Transaction IDs
   request/response pairs.  The upper 32 bits are reserved for use by
   the kernel and will be overwritten before a MAD is sent.
 
+P_Key Index Handling
+
+  The old ib_umad interface did not allow setting the P_Key index for
+  MADs that are sent and did not provide a way for obtaining the P_Key
+  index of received MADs.  A new layout for struct ib_user_mad_hdr
+  with a pkey_index member has been defined; however, to preserve
+  binary compatibility with older applications, this new layout will
+  not be used unless the IB_USER_MAD_ENABLE_PKEY ioctl is called
+  before a file descriptor is used for anything else.
+
+  In September 2008, the IB_USER_MAD_ABI_VERSION will be incremented
+  to 6, the new layout of struct ib_user_mad_hdr will be used by
+  default, and the IB_USER_MAD_ENABLE_PKEY ioctl will be removed.
+
 Setting IsSM Capability Bit
 
   To set the IsSM capability bit for a port, simply open the
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index c5c33d35f87..5381c80de10 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -161,8 +161,7 @@ static void addr_send_arp(struct sockaddr_in *dst_in)
 	if (ip_route_output_key(&rt, &fl))
 		return;
 
-	arp_send(ARPOP_REQUEST, ETH_P_ARP, rt->rt_gateway, rt->idev->dev,
-		 rt->rt_src, NULL, rt->idev->dev->dev_addr, NULL);
+	neigh_event_send(rt->u.dst.neighbour, NULL);
 	ip_rt_put(rt);
 }
 
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 4df269f5d9a..2e39236d189 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -2219,6 +2219,9 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
 {
 	struct cm_id_private *cm_id_priv;
 	struct ib_mad_send_buf *msg;
+	enum ib_cm_state cm_state;
+	enum ib_cm_lap_state lap_state;
+	enum cm_msg_response msg_response;
 	void *data;
 	unsigned long flags;
 	int ret;
@@ -2235,48 +2238,40 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
 	switch(cm_id_priv->id.state) {
 	case IB_CM_REQ_RCVD:
-		ret = cm_alloc_msg(cm_id_priv, &msg);
-		if (ret)
-			goto error1;
-
-		cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
-			      CM_MSG_RESPONSE_REQ, service_timeout,
-			      private_data, private_data_len);
-		ret = ib_post_send_mad(msg, NULL);
-		if (ret)
-			goto error2;
-		cm_id->state = IB_CM_MRA_REQ_SENT;
+		cm_state = IB_CM_MRA_REQ_SENT;
+		lap_state = cm_id->lap_state;
+		msg_response = CM_MSG_RESPONSE_REQ;
 		break;
 	case IB_CM_REP_RCVD:
-		ret = cm_alloc_msg(cm_id_priv, &msg);
-		if (ret)
-			goto error1;
-
-		cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
-			      CM_MSG_RESPONSE_REP, service_timeout,
-			      private_data, private_data_len);
-		ret = ib_post_send_mad(msg, NULL);
-		if (ret)
-			goto error2;
-		cm_id->state = IB_CM_MRA_REP_SENT;
+		cm_state = IB_CM_MRA_REP_SENT;
+		lap_state = cm_id->lap_state;
+		msg_response = CM_MSG_RESPONSE_REP;
 		break;
 	case IB_CM_ESTABLISHED:
+		cm_state = cm_id->state;
+		lap_state = IB_CM_MRA_LAP_SENT;
+		msg_response = CM_MSG_RESPONSE_OTHER;
+		break;
+	default:
+		ret = -EINVAL;
+		goto error1;
+	}
+
+	if (!(service_timeout & IB_CM_MRA_FLAG_DELAY)) {
 		ret = cm_alloc_msg(cm_id_priv, &msg);
 		if (ret)
 			goto error1;
 
 		cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
-			      CM_MSG_RESPONSE_OTHER, service_timeout,
+			      msg_response, service_timeout,
 			      private_data, private_data_len);
 		ret = ib_post_send_mad(msg, NULL);
 		if (ret)
 			goto error2;
-		cm_id->lap_state = IB_CM_MRA_LAP_SENT;
-		break;
-	default:
-		ret = -EINVAL;
-		goto error1;
 	}
+
+	cm_id->state = cm_state;
+	cm_id->lap_state = lap_state;
 	cm_id_priv->service_timeout = service_timeout;
 	cm_set_private_data(cm_id_priv, data, private_data_len);
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 2e641b255db..93644f82592 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -52,6 +52,7 @@ MODULE_LICENSE("Dual BSD/GPL");
 
 #define CMA_CM_RESPONSE_TIMEOUT 20
 #define CMA_MAX_CM_RETRIES 15
+#define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
 
 static void cma_add_one(struct ib_device *device);
 static void cma_remove_one(struct ib_device *device);
@@ -138,6 +139,7 @@ struct rdma_id_private {
 	u32			qkey;
 	u32			qp_num;
 	u8			srq;
+	u8			tos;
 };
 
 struct cma_multicast {
@@ -1089,6 +1091,7 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 		event.param.ud.private_data_len =
 				IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset;
 	} else {
+		ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
 		conn_id = cma_new_conn_id(&listen_id->id, ib_event);
 		cma_set_req_event_data(&event, &ib_event->param.req_rcvd,
 				       ib_event->private_data, offset);
@@ -1474,6 +1477,15 @@ err:
 }
 EXPORT_SYMBOL(rdma_listen);
 
+void rdma_set_service_type(struct rdma_cm_id *id, int tos)
+{
+	struct rdma_id_private *id_priv;
+
+	id_priv = container_of(id, struct rdma_id_private, id);
+	id_priv->tos = (u8) tos;
+}
+EXPORT_SYMBOL(rdma_set_service_type);
+
 static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec,
 			      void *context)
 {
@@ -1498,23 +1510,37 @@ static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec,
 static int cma_query_ib_route(struct rdma_id_private *id_priv, int timeout_ms,
 			      struct cma_work *work)
 {
-	struct rdma_dev_addr *addr = &id_priv->id.route.addr.dev_addr;
+	struct rdma_addr *addr = &id_priv->id.route.addr;
 	struct ib_sa_path_rec path_rec;
+	ib_sa_comp_mask comp_mask;
+	struct sockaddr_in6 *sin6;
 
 	memset(&path_rec, 0, sizeof path_rec);
-	ib_addr_get_sgid(addr, &path_rec.sgid);
-	ib_addr_get_dgid(addr, &path_rec.dgid);
-	path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(addr));
+	ib_addr_get_sgid(&addr->dev_addr, &path_rec.sgid);
+	ib_addr_get_dgid(&addr->dev_addr, &path_rec.dgid);
+	path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(&addr->dev_addr));
 	path_rec.numb_path = 1;
 	path_rec.reversible = 1;
+	path_rec.service_id = cma_get_service_id(id_priv->id.ps, &addr->dst_addr);
+
+	comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
+		    IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
+		    IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID;
+
+	if (addr->src_addr.sa_family == AF_INET) {
+		path_rec.qos_class = cpu_to_be16((u16) id_priv->tos);
+		comp_mask |= IB_SA_PATH_REC_QOS_CLASS;
+	} else {
+		sin6 = (struct sockaddr_in6 *) &addr->src_addr;
+		path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20);
+		comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS;
+	}
 
 	id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device,
-				id_priv->id.port_num, &path_rec,
-				IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
-				IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
-				IB_SA_PATH_REC_REVERSIBLE,
-				timeout_ms, GFP_KERNEL,
-				cma_query_handler, work, &id_priv->query);
+					       id_priv->id.port_num, &path_rec,
+					       comp_mask, timeout_ms,
+					       GFP_KERNEL, cma_query_handler,
+					       work, &id_priv->query);
 
 	return (id_priv->query_id < 0) ? id_priv->query_id : 0;
 }
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 2506c43ba04..5ac5ffee05c 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -120,12 +120,12 @@ static struct ib_device *__ib_device_get_by_name(const char *name)
 
 static int alloc_name(char *name)
 {
-	long *inuse;
+	unsigned long *inuse;
 	char buf[IB_DEVICE_NAME_MAX];
 	struct ib_device *device;
 	int i;
 
-	inuse = (long *) get_zeroed_page(GFP_KERNEL);
+	inuse = (unsigned long *) get_zeroed_page(GFP_KERNEL);
 	if (!inuse)
 		return -ENOMEM;
 
diff --git a/drivers/infiniband/core/fmr_pool.c b/drivers/infiniband/core/fmr_pool.c
index a06bcc65a87..d7f64525469 100644
--- a/drivers/infiniband/core/fmr_pool.c
+++ b/drivers/infiniband/core/fmr_pool.c
@@ -152,7 +152,7 @@ static void ib_fmr_batch_release(struct ib_fmr_pool *pool)
 
 #ifdef DEBUG
 		if (fmr->ref_count !=0) {
-			printk(KERN_WARNING PFX "Unmapping FMR 0x%08x with ref count %d",
+			printk(KERN_WARNING PFX "Unmapping FMR 0x%08x with ref count %d\n",
 			       fmr, fmr->ref_count);
 		}
 #endif
@@ -170,7 +170,7 @@ static void ib_fmr_batch_release(struct ib_fmr_pool *pool)
 
 	ret = ib_unmap_fmr(&fmr_list);
 	if (ret)
-		printk(KERN_WARNING PFX "ib_unmap_fmr returned %d", ret);
+		printk(KERN_WARNING PFX "ib_unmap_fmr returned %d\n", ret);
 
 	spin_lock_irq(&pool->pool_lock);
 	list_splice(&unmap_list, &pool->free_list);
@@ -235,13 +235,13 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
 
 	attr = kmalloc(sizeof *attr, GFP_KERNEL);
 	if (!attr) {
-		printk(KERN_WARNING PFX "couldn't allocate device attr struct");
+		printk(KERN_WARNING PFX "couldn't allocate device attr struct\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
 	ret = ib_query_device(device, attr);
 	if (ret) {
-		printk(KERN_WARNING PFX "couldn't query device: %d", ret);
+		printk(KERN_WARNING PFX "couldn't query device: %d\n", ret);
 		kfree(attr);
 		return ERR_PTR(ret);
 	}
@@ -255,7 +255,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
 
 	pool = kmalloc(sizeof *pool, GFP_KERNEL);
 	if (!pool) {
-		printk(KERN_WARNING PFX "couldn't allocate pool struct");
+		printk(KERN_WARNING PFX "couldn't allocate pool struct\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -272,7 +272,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
 			kmalloc(IB_FMR_HASH_SIZE * sizeof *pool->cache_bucket,
 				GFP_KERNEL);
 		if (!pool->cache_bucket) {
-			printk(KERN_WARNING PFX "Failed to allocate cache in pool");
+			printk(KERN_WARNING PFX "Failed to allocate cache in pool\n");
 			ret = -ENOMEM;
 			goto out_free_pool;
 		}
@@ -296,7 +296,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
 				      "ib_fmr(%s)",
 				      device->name);
 	if (IS_ERR(pool->thread)) {
-		printk(KERN_WARNING PFX "couldn't start cleanup thread");
+		printk(KERN_WARNING PFX "couldn't start cleanup thread\n");
 		ret = PTR_ERR(pool->thread);
 		goto out_free_pool;
 	}
@@ -314,7 +314,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
 				      GFP_KERNEL);
 			if (!fmr) {
 				printk(KERN_WARNING PFX "failed to allocate fmr "
-				       "struct for FMR %d", i);
+				       "struct for FMR %d\n", i);
 				goto out_fail;
 			}
 
@@ -326,7 +326,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
 			fmr->fmr = ib_alloc_fmr(pd, params->access, &fmr_attr);
 			if (IS_ERR(fmr->fmr)) {
 				printk(KERN_WARNING PFX "fmr_create failed "<