1 files changed, 495 insertions, 222 deletions

diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 126ac80db7b..233eaf541f5 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1,6 +1,7 @@
 /*
  * Copyright (c) 2004 Topspin Communications.  All rights reserved.
- * Copyright (c) 2005 Voltaire, Inc.  All rights reserved.
+ * Copyright (c) 2005 Voltaire, Inc.  All rights reserved.
+ * Copyright (c) 2006 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -29,8 +30,6 @@
  * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
  * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
- *
- * $Id: sa_query.c 2811 2005-07-06 18:11:43Z halr $
  */
 
 #include <linux/module.h>
@@ -39,13 +38,14 @@
 #include <linux/random.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
-#include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/kref.h>
 #include <linux/idr.h>
-
+#include <linux/workqueue.h>
+#include <uapi/linux/if_ether.h>
 #include <rdma/ib_pack.h>
-#include <rdma/ib_sa.h>
+#include <rdma/ib_cache.h>
+#include "sa.h"
 
 MODULE_AUTHOR("Roland Dreier");
 MODULE_DESCRIPTION("InfiniBand subnet administration query support");
@@ -54,6 +54,8 @@ MODULE_LICENSE("Dual BSD/GPL");
 struct ib_sa_sm_ah {
 	struct ib_ah        *ah;
 	struct kref          ref;
+	u16		     pkey_index;
+	u8		     src_path_mask;
 };
 
 struct ib_sa_port {
@@ -73,11 +75,11 @@ struct ib_sa_device {
 struct ib_sa_query {
 	void (*callback)(struct ib_sa_query *, int, struct ib_sa_mad *);
 	void (*release)(struct ib_sa_query *);
-	struct ib_sa_port  *port;
-	struct ib_sa_mad   *mad;
-	struct ib_sa_sm_ah *sm_ah;
-	DECLARE_PCI_UNMAP_ADDR(mapping)
-	int                 id;
+	struct ib_sa_client    *client;
+	struct ib_sa_port      *port;
+	struct ib_mad_send_buf *mad_buf;
+	struct ib_sa_sm_ah     *sm_ah;
+	int			id;
 };
 
 struct ib_sa_service_query {
@@ -92,6 +94,12 @@ struct ib_sa_path_query {
 	struct ib_sa_query sa_query;
 };
 
+struct ib_sa_guidinfo_query {
+	void (*callback)(int, struct ib_sa_guidinfo_rec *, void *);
+	void *context;
+	struct ib_sa_query sa_query;
+};
+
 struct ib_sa_mcmember_query {
 	void (*callback)(int, struct ib_sa_mcmember_rec *, void *);
 	void *context;
@@ -107,52 +115,22 @@ static struct ib_client sa_client = {
 	.remove = ib_sa_remove_one
 };
 
-static spinlock_t idr_lock;
+static DEFINE_SPINLOCK(idr_lock);
 static DEFINE_IDR(query_idr);
 
-static spinlock_t tid_lock;
+static DEFINE_SPINLOCK(tid_lock);
 static u32 tid;
 
-enum {
-	IB_SA_ATTR_CLASS_PORTINFO    = 0x01,
-	IB_SA_ATTR_NOTICE	     = 0x02,
-	IB_SA_ATTR_INFORM_INFO	     = 0x03,
-	IB_SA_ATTR_NODE_REC	     = 0x11,
-	IB_SA_ATTR_PORT_INFO_REC     = 0x12,
-	IB_SA_ATTR_SL2VL_REC	     = 0x13,
-	IB_SA_ATTR_SWITCH_REC	     = 0x14,
-	IB_SA_ATTR_LINEAR_FDB_REC    = 0x15,
-	IB_SA_ATTR_RANDOM_FDB_REC    = 0x16,
-	IB_SA_ATTR_MCAST_FDB_REC     = 0x17,
-	IB_SA_ATTR_SM_INFO_REC	     = 0x18,
-	IB_SA_ATTR_LINK_REC	     = 0x20,
-	IB_SA_ATTR_GUID_INFO_REC     = 0x30,
-	IB_SA_ATTR_SERVICE_REC	     = 0x31,
-	IB_SA_ATTR_PARTITION_REC     = 0x33,
-	IB_SA_ATTR_RANGE_REC	     = 0x34,
-	IB_SA_ATTR_PATH_REC	     = 0x35,
-	IB_SA_ATTR_VL_ARB_REC	     = 0x36,
-	IB_SA_ATTR_MC_GROUP_REC	     = 0x37,
-	IB_SA_ATTR_MC_MEMBER_REC     = 0x38,
-	IB_SA_ATTR_TRACE_REC	     = 0x39,
-	IB_SA_ATTR_MULTI_PATH_REC    = 0x3a,
-	IB_SA_ATTR_SERVICE_ASSOC_REC = 0x3b
-};
-
 #define PATH_REC_FIELD(field) \
 	.struct_offset_bytes = offsetof(struct ib_sa_path_rec, field),		\
 	.struct_size_bytes   = sizeof ((struct ib_sa_path_rec *) 0)->field,	\
 	.field_name          = "sa_path_rec:" #field
 
 static const struct ib_field path_rec_table[] = {
-	{ RESERVED,
+	{ PATH_REC_FIELD(service_id),
 	  .offset_words = 0,
 	  .offset_bits  = 0,
-	  .size_bits    = 32 },
-	{ RESERVED,
-	  .offset_words = 1,
-	  .offset_bits  = 0,
-	  .size_bits    = 32 },
+	  .size_bits    = 64 },
 	{ PATH_REC_FIELD(dgid),
 	  .offset_words = 2,
 	  .offset_bits  = 0,
@@ -201,7 +179,7 @@ static const struct ib_field path_rec_table[] = {
 	  .offset_words = 12,
 	  .offset_bits  = 16,
 	  .size_bits    = 16 },
-	{ RESERVED,
+	{ PATH_REC_FIELD(qos_class),
 	  .offset_words = 13,
 	  .offset_bits  = 0,
 	  .size_bits    = 12 },
@@ -375,6 +353,34 @@ static const struct ib_field service_rec_table[] = {
 	  .size_bits    = 2*64 },
 };
 
+#define GUIDINFO_REC_FIELD(field) \
+	.struct_offset_bytes = offsetof(struct ib_sa_guidinfo_rec, field),	\
+	.struct_size_bytes   = sizeof((struct ib_sa_guidinfo_rec *) 0)->field,	\
+	.field_name          = "sa_guidinfo_rec:" #field
+
+static const struct ib_field guidinfo_rec_table[] = {
+	{ GUIDINFO_REC_FIELD(lid),
+	  .offset_words = 0,
+	  .offset_bits  = 0,
+	  .size_bits    = 16 },
+	{ GUIDINFO_REC_FIELD(block_num),
+	  .offset_words = 0,
+	  .offset_bits  = 16,
+	  .size_bits    = 8 },
+	{ GUIDINFO_REC_FIELD(res1),
+	  .offset_words = 0,
+	  .offset_bits  = 24,
+	  .size_bits    = 8 },
+	{ GUIDINFO_REC_FIELD(res2),
+	  .offset_words = 1,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ GUIDINFO_REC_FIELD(guid_info_list),
+	  .offset_words = 2,
+	  .offset_bits  = 0,
+	  .size_bits    = 512 },
+};
+
 static void free_sm_ah(struct kref *kref)
 {
 	struct ib_sa_sm_ah *sm_ah = container_of(kref, struct ib_sa_sm_ah, ref);
@@ -383,10 +389,11 @@ static void free_sm_ah(struct kref *kref)
 	kfree(sm_ah);
 }
 
-static void update_sm_ah(void *port_ptr)
+static void update_sm_ah(struct work_struct *work)
 {
-	struct ib_sa_port *port = port_ptr;
-	struct ib_sa_sm_ah *new_ah, *old_ah;
+	struct ib_sa_port *port =
+		container_of(work, struct ib_sa_port, update_task);
+	struct ib_sa_sm_ah *new_ah;
 	struct ib_port_attr port_attr;
 	struct ib_ah_attr   ah_attr;
 
@@ -402,6 +409,12 @@ static void update_sm_ah(void *port_ptr)
 	}
 
 	kref_init(&new_ah->ref);
+	new_ah->src_path_mask = (1 << port_attr.lmc) - 1;
+
+	new_ah->pkey_index = 0;
+	if (ib_find_pkey(port->agent->device, port->port_num,
+			 IB_DEFAULT_PKEY_FULL, &new_ah->pkey_index))
+		printk(KERN_ERR "Couldn't find index for default PKey\n");
 
 	memset(&ah_attr, 0, sizeof ah_attr);
 	ah_attr.dlid     = port_attr.sm_lid;
@@ -416,12 +429,11 @@ static void update_sm_ah(void *port_ptr)
 	}
 
 	spin_lock_irq(&port->ah_lock);
-	old_ah = port->sm_ah;
+	if (port->sm_ah)
+		kref_put(&port->sm_ah->ref, free_sm_ah);
 	port->sm_ah = new_ah;
 	spin_unlock_irq(&port->ah_lock);
 
-	if (old_ah)
-		kref_put(&old_ah->ref, free_sm_ah);
 }
 
 static void ib_sa_event(struct ib_event_handler *handler, struct ib_event *event)
@@ -430,15 +442,42 @@ static void ib_sa_event(struct ib_event_handler *handler, struct ib_event *event
 	    event->event == IB_EVENT_PORT_ACTIVE ||
 	    event->event == IB_EVENT_LID_CHANGE  ||
 	    event->event == IB_EVENT_PKEY_CHANGE ||
-	    event->event == IB_EVENT_SM_CHANGE) {
+	    event->event == IB_EVENT_SM_CHANGE   ||
+	    event->event == IB_EVENT_CLIENT_REREGISTER) {
+		unsigned long flags;
 		struct ib_sa_device *sa_dev =
-			ib_get_client_data(event->device, &sa_client);
+			container_of(handler, typeof(*sa_dev), event_handler);
+		struct ib_sa_port *port =
+			&sa_dev->port[event->element.port_num - sa_dev->start_port];
+
+		if (rdma_port_get_link_layer(handler->device, port->port_num) != IB_LINK_LAYER_INFINIBAND)
+			return;
+
+		spin_lock_irqsave(&port->ah_lock, flags);
+		if (port->sm_ah)
+			kref_put(&port->sm_ah->ref, free_sm_ah);
+		port->sm_ah = NULL;
+		spin_unlock_irqrestore(&port->ah_lock, flags);
 
-		schedule_work(&sa_dev->port[event->element.port_num -
+		queue_work(ib_wq, &sa_dev->port[event->element.port_num -
 					    sa_dev->start_port].update_task);
 	}
 }
 
+void ib_sa_register_client(struct ib_sa_client *client)
+{
+	atomic_set(&client->users, 1);
+	init_completion(&client->comp);
+}
+EXPORT_SYMBOL(ib_sa_register_client);
+
+void ib_sa_unregister_client(struct ib_sa_client *client)
+{
+	ib_sa_client_put(client);
+	wait_for_completion(&client->comp);
+}
+EXPORT_SYMBOL(ib_sa_unregister_client);
+
 /**
  * ib_sa_cancel_query - try to cancel an SA query
  * @id:ID of query to cancel
@@ -452,6 +491,7 @@ void ib_sa_cancel_query(int id, struct ib_sa_query *query)
 {
 	unsigned long flags;
 	struct ib_mad_agent *agent;
+	struct ib_mad_send_buf *mad_buf;
 
 	spin_lock_irqsave(&idr_lock, flags);
 	if (idr_find(&query_idr, id) != query) {
@@ -459,12 +499,107 @@ void ib_sa_cancel_query(int id, struct ib_sa_query *query)
 		return;
 	}
 	agent = query->port->agent;
+	mad_buf = query->mad_buf;
 	spin_unlock_irqrestore(&idr_lock, flags);
 
-	ib_cancel_mad(agent, id);
+	ib_cancel_mad(agent, mad_buf);
 }
 EXPORT_SYMBOL(ib_sa_cancel_query);
 
+static u8 get_src_path_mask(struct ib_device *device, u8 port_num)
+{
+	struct ib_sa_device *sa_dev;
+	struct ib_sa_port   *port;
+	unsigned long flags;
+	u8 src_path_mask;
+
+	sa_dev = ib_get_client_data(device, &sa_client);
+	if (!sa_dev)
+		return 0x7f;
+
+	port  = &sa_dev->port[port_num - sa_dev->start_port];
+	spin_lock_irqsave(&port->ah_lock, flags);
+	src_path_mask = port->sm_ah ? port->sm_ah->src_path_mask : 0x7f;
+	spin_unlock_irqrestore(&port->ah_lock, flags);
+
+	return src_path_mask;
+}
+
+int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
+			 struct ib_sa_path_rec *rec, struct ib_ah_attr *ah_attr)
+{
+	int ret;
+	u16 gid_index;
+	int force_grh;
+
+	memset(ah_attr, 0, sizeof *ah_attr);
+	ah_attr->dlid = be16_to_cpu(rec->dlid);
+	ah_attr->sl = rec->sl;
+	ah_attr->src_path_bits = be16_to_cpu(rec->slid) &
+				 get_src_path_mask(device, port_num);
+	ah_attr->port_num = port_num;
+	ah_attr->static_rate = rec->rate;
+
+	force_grh = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_ETHERNET;
+
+	if (rec->hop_limit > 1 || force_grh) {
+		ah_attr->ah_flags = IB_AH_GRH;
+		ah_attr->grh.dgid = rec->dgid;
+
+		ret = ib_find_cached_gid(device, &rec->sgid, &port_num,
+					 &gid_index);
+		if (ret)
+			return ret;
+
+		ah_attr->grh.sgid_index    = gid_index;
+		ah_attr->grh.flow_label    = be32_to_cpu(rec->flow_label);
+		ah_attr->grh.hop_limit     = rec->hop_limit;
+		ah_attr->grh.traffic_class = rec->traffic_class;
+	}
+	if (force_grh) {
+		memcpy(ah_attr->dmac, rec->dmac, ETH_ALEN);
+		ah_attr->vlan_id = rec->vlan_id;
+	} else {
+		ah_attr->vlan_id = 0xffff;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ib_init_ah_from_path);
+
+static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&query->port->ah_lock, flags);
+	if (!query->port->sm_ah) {
+		spin_unlock_irqrestore(&query->port->ah_lock, flags);
+		return -EAGAIN;
+	}
+	kref_get(&query->port->sm_ah->ref);
+	query->sm_ah = query->port->sm_ah;
+	spin_unlock_irqrestore(&query->port->ah_lock, flags);
+
+	query->mad_buf = ib_create_send_mad(query->port->agent, 1,
+					    query->sm_ah->pkey_index,
+					    0, IB_MGMT_SA_HDR, IB_MGMT_SA_DATA,
+					    gfp_mask);
+	if (IS_ERR(query->mad_buf)) {
+		kref_put(&query->sm_ah->ref, free_sm_ah);
+		return -ENOMEM;
+	}
+
+	query->mad_buf->ah = query->sm_ah->ah;
+
+	return 0;
+}
+
+static void free_mad(struct ib_sa_query *query)
+{
+	ib_free_send_mad(query->mad_buf);
+	kref_put(&query->sm_ah->ref, free_sm_ah);
+}
+
 static void init_mad(struct ib_sa_mad *mad, struct ib_mad_agent *agent)
 {
 	unsigned long flags;
@@ -481,74 +616,54 @@ static void init_mad(struct ib_sa_mad *mad, struct ib_mad_agent *agent)
 	spin_unlock_irqrestore(&tid_lock, flags);
 }
 
-static int send_mad(struct ib_sa_query *query, int timeout_ms)
+static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
 {
-	struct ib_sa_port *port = query->port;
+	bool preload = !!(gfp_mask & __GFP_WAIT);
 	unsigned long flags;
-	int ret;
-	struct ib_sge      gather_list;
-	struct ib_send_wr *bad_wr, wr = {
-		.opcode      = IB_WR_SEND,
-		.sg_list     = &gather_list,
-		.num_sge     = 1,
-		.send_flags  = IB_SEND_SIGNALED,
-		.wr	     = {
-			 .ud = {
-				 .mad_hdr     = &query->mad->mad_hdr,
-				 .remote_qpn  = 1,
-				 .remote_qkey = IB_QP1_QKEY,
-				 .timeout_ms  = timeout_ms,
-			 }
-		 }
-	};
-
-retry:
-	if (!idr_pre_get(&query_idr, GFP_ATOMIC))
-		return -ENOMEM;
+	int ret, id;
+
+	if (preload)
+		idr_preload(gfp_mask);
 	spin_lock_irqsave(&idr_lock, flags);
-	ret = idr_get_new(&query_idr, query, &query->id);
-	spin_unlock_irqrestore(&idr_lock, flags);
-	if (ret == -EAGAIN)
-		goto retry;
-	if (ret)
-		return ret;
 
-	wr.wr_id = query->id;
+	id = idr_alloc(&query_idr, query, 0, 0, GFP_NOWAIT);
 
-	spin_lock_irqsave(&port->ah_lock, flags);
-	kref_get(&port->sm_ah->ref);
-	query->sm_ah = port->sm_ah;
-	wr.wr.ud.ah  = port->sm_ah->ah;
-	spin_unlock_irqrestore(&port->ah_lock, flags);
+	spin_unlock_irqrestore(&idr_lock, flags);
+	if (preload)
+		idr_preload_end();
+	if (id < 0)
+		return id;
 
-	gather_list.addr   = dma_map_single(port->agent->device->dma_device,
-					    query->mad,
-					    sizeof (struct ib_sa_mad),
-					    DMA_TO_DEVICE);
-	gather_list.length = sizeof (struct ib_sa_mad);
-	gather_list.lkey   = port->agent->mr->lkey;
-	pci_unmap_addr_set(query, mapping, gather_list.addr);
+	query->mad_buf->timeout_ms  = timeout_ms;
+	query->mad_buf->context[0] = query;
+	query->id = id;
 
-	ret = ib_post_send_mad(port->agent, &wr, &bad_wr);
+	ret = ib_post_send_mad(query->mad_buf, NULL);
 	if (ret) {
-		dma_unmap_single(port->agent->device->dma_device,
-				 pci_unmap_addr(query, mapping),
-				 sizeof (struct ib_sa_mad),
-				 DMA_TO_DEVICE);
-		kref_put(&query->sm_ah->ref, free_sm_ah);
 		spin_lock_irqsave(&idr_lock, flags);
-		idr_remove(&query_idr, query->id);
+		idr_remove(&query_idr, id);
 		spin_unlock_irqrestore(&idr_lock, flags);
 	}
 
 	/*
 	 * It's not safe to dereference query any more, because the
 	 * send may already have completed and freed the query in
-	 * another context.  So use wr.wr_id, which has a copy of the
-	 * query's id.
+	 * another context.
 	 */
-	return ret ? ret : wr.wr_id;
+	return ret ? ret : id;
+}
+
+void ib_sa_unpack_path(void *attribute, struct ib_sa_path_rec *rec)
+{
+	ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table), attribute, rec);
+}
+EXPORT_SYMBOL(ib_sa_unpack_path);
+
+void ib_sa_pack_path(struct ib_sa_path_rec *rec, void *attribute)
+{
+	ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table), rec, attribute);
 }
+EXPORT_SYMBOL(ib_sa_pack_path);
 
 static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
 				    int status,
@@ -562,6 +677,9 @@ static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
 
 		ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table),
 			  mad->data, &rec);
+		rec.vlan_id = 0xffff;
+		memset(rec.dmac, 0, ETH_ALEN);
+		memset(rec.smac, 0, ETH_ALEN);
 		query->callback(status, &rec, query->context);
 	} else
 		query->callback(status, NULL, query->context);
@@ -569,12 +687,12 @@ static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
 
 static void ib_sa_path_rec_release(struct ib_sa_query *sa_query)
 {
-	kfree(sa_query->mad);
 	kfree(container_of(sa_query, struct ib_sa_path_query, sa_query));
 }
 
 /**
  * ib_sa_path_rec_get - Start a Path get query
+ * @client:SA client
  * @device:device to send query on
  * @port_num: port number to send query on
  * @rec:Path Record to send in query
@@ -597,10 +715,11 @@ static void ib_sa_path_rec_release(struct ib_sa_query *sa_query)
  * error code.  Otherwise it is a query ID that can be used to cancel
  * the query.
  */
-int ib_sa_path_rec_get(struct ib_device *device, u8 port_num,
+int ib_sa_path_rec_get(struct ib_sa_client *client,
+		       struct ib_device *device, u8 port_num,
 		       struct ib_sa_path_rec *rec,
 		       ib_sa_comp_mask comp_mask,
-		       int timeout_ms, unsigned int __nocast gfp_mask,
+		       int timeout_ms, gfp_t gfp_mask,
 		       void (*callback)(int status,
 					struct ib_sa_path_rec *resp,
 					void *context),
@@ -609,43 +728,57 @@ int ib_sa_path_rec_get(struct ib_device *device, u8 port_num,
 {
 	struct ib_sa_path_query *query;
 	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
-	struct ib_sa_port   *port   = &sa_dev->port[port_num - sa_dev->start_port];
-	struct ib_mad_agent *agent  = port->agent;
+	struct ib_sa_port   *port;
+	struct ib_mad_agent *agent;
+	struct ib_sa_mad *mad;
 	int ret;
 
+	if (!sa_dev)
+		return -ENODEV;
+
+	port  = &sa_dev->port[port_num - sa_dev->start_port];
+	agent = port->agent;
+
 	query = kmalloc(sizeof *query, gfp_mask);
 	if (!query)
 		return -ENOMEM;
-	query->sa_query.mad = kmalloc(sizeof *query->sa_query.mad, gfp_mask);
-	if (!query->sa_query.mad) {
-		kfree(query);
-		return -ENOMEM;
-	}
 
-	query->callback = callback;
-	query->context  = context;
+	query->sa_query.port     = port;
+	ret = alloc_mad(&query->sa_query, gfp_mask);
+	if (ret)
+		goto err1;
+
+	ib_sa_client_get(client);
+	query->sa_query.client = client;
+	query->callback        = callback;
+	query->context         = context;
 
-	init_mad(query->sa_query.mad, agent);
+	mad = query->sa_query.mad_buf->mad;
+	init_mad(mad, agent);
 
-	query->sa_query.callback              = callback ? ib_sa_path_rec_callback : NULL;
-	query->sa_query.release               = ib_sa_path_rec_release;
-	query->sa_query.port                  = port;
-	query->sa_query.mad->mad_hdr.method   = IB_MGMT_METHOD_GET;
-	query->sa_query.mad->mad_hdr.attr_id  = cpu_to_be16(IB_SA_ATTR_PATH_REC);
-	query->sa_query.mad->sa_hdr.comp_mask = comp_mask;
+	query->sa_query.callback = callback ? ib_sa_path_rec_callback : NULL;
+	query->sa_query.release  = ib_sa_path_rec_release;
+	mad->mad_hdr.method	 = IB_MGMT_METHOD_GET;
+	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_PATH_REC);
+	mad->sa_hdr.comp_mask	 = comp_mask;
 
-	ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table),
-		rec, query->sa_query.mad->data);
+	ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table), rec, mad->data);
 
 	*sa_query = &query->sa_query;
 
-	ret = send_mad(&query->sa_query, timeout_ms);
-	if (ret < 0) {
-		*sa_query = NULL;
-		kfree(query->sa_query.mad);
-		kfree(query);
-	}
+	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
+	if (ret < 0)
+		goto err2;
+
+	return ret;
+
+err2:
+	*sa_query = NULL;
+	ib_sa_client_put(query->sa_query.client);
+	free_mad(&query->sa_query);
 
+err1:
+	kfree(query);
 	return ret;
 }
 EXPORT_SYMBOL(ib_sa_path_rec_get);
@@ -669,12 +802,12 @@ static void ib_sa_service_rec_callback(struct ib_sa_query *sa_query,
 
 static void ib_sa_service_rec_release(struct ib_sa_query *sa_query)
 {
-	kfree(sa_query->mad);
 	kfree(container_of(sa_query, struct ib_sa_service_query, sa_query));
 }
 
 /**
  * ib_sa_service_rec_query - Start Service Record operation
+ * @client:SA client
  * @device:device to send request on
  * @port_num: port number to send request on
  * @method:SA method - should be get, set, or delete
@@ -699,10 +832,11 @@ static void ib_sa_service_rec_release(struct ib_sa_query *sa_query)
  * error code.  Otherwise it is a request ID that can be used to cancel
  * the query.
  */
-int ib_sa_service_rec_query(struct ib_device *device, u8 port_num, u8 method,
+int ib_sa_service_rec_query(struct ib_sa_client *client,
+			    struct ib_device *device, u8 port_num, u8 method,
 			    struct ib_sa_service_rec *rec,
 			    ib_sa_comp_mask comp_mask,
-			    int timeout_ms, unsigned int __nocast gfp_mask,
+			    int timeout_ms, gfp_t gfp_mask,
 			    void (*callback)(int status,
 					     struct ib_sa_service_rec *resp,
 					     void *context),
@@ -711,10 +845,17 @@ int ib_sa_service_rec_query(struct ib_device *device, u8 port_num, u8 method,
 {
 	struct ib_sa_service_query *query;
 	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
-	struct ib_sa_port   *port   = &sa_dev->port[port_num - sa_dev->start_port];
-	struct ib_mad_agent *agent  = port->agent;
+	struct ib_sa_port   *port;
+	struct ib_mad_agent *agent;
+	struct ib_sa_mad *mad;
 	int ret;
 
+	if (!sa_dev)
+		return -ENODEV;
+
+	port  = &sa_dev->port[port_num - sa_dev->start_port];
+	agent = port->agent;
+
 	if (method != IB_MGMT_METHOD_GET &&
 	    method != IB_MGMT_METHOD_SET &&
 	    method != IB_SA_METHOD_DELETE)
@@ -723,37 +864,44 @@ int ib_sa_service_rec_query(struct ib_device *device, u8 port_num, u8 method,
 	query = kmalloc(sizeof *query, gfp_mask);
 	if (!query)
 		return -ENOMEM;
-	query->sa_query.mad = kmalloc(sizeof *query->sa_query.mad, gfp_mask);
-	if (!query->sa_query.mad) {
-		kfree(query);
-		return -ENOMEM;
-	}
 
-	query->callback = callback;
-	query->context  = context;
+	query->sa_query.port     = port;
+	ret = alloc_mad(&query->sa_query, gfp_mask);
+	if (ret)
+		goto err1;
 
-	init_mad(query->sa_query.mad, agent);
+	ib_sa_client_get(client);
+	query->sa_query.client = client;
+	query->callback        = callback;
+	query->context         = context;
 
-	query->sa_query.callback              = callback ? ib_sa_service_rec_callback : NULL;
-	query->sa_query.release               = ib_sa_service_rec_release;
-	query->sa_query.port                  = port;
-	query->sa_query.mad->mad_hdr.method   = method;
-	query->sa_query.mad->mad_hdr.attr_id  =
-				cpu_to_be16(IB_SA_ATTR_SERVICE_REC);
-	query->sa_query.mad->sa_hdr.comp_mask = comp_mask;
+	mad = query->sa_query.mad_buf->mad;
+	init_mad(mad, agent);
+
+	query->sa_query.callback = callback ? ib_sa_service_rec_callback : NULL;
+	query->sa_query.release  = ib_sa_service_rec_release;
+	mad->mad_hdr.method	 = method;
+	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_SERVICE_REC);
+	mad->sa_hdr.comp_mask	 = comp_mask;
 
 	ib_pack(service_rec_table, ARRAY_SIZE(service_rec_table),
-		rec, query->sa_query.mad->data);
+		rec, mad->data);
 
 	*sa_query = &query->sa_query;
 
-	ret = send_mad(&query->sa_query, timeout_ms);
-	if (ret < 0) {
-		*sa_query = NULL;
-		kfree(query->sa_query.mad);
-		kfree(query);
-	}
+	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
+	if (ret < 0)
+		goto err2;
+
+	return ret;
+
+err2:
+	*sa_query = NULL;
+	ib_sa_client_put(query->sa_query.client);
+	free_mad(&query->sa_query);
 
+err1:
+	kfree(query);
 	return ret;
 }
 EXPORT_SYMBOL(ib_sa_service_rec_query);
@@ -777,15 +925,15 @@ static void ib_sa_mcmember_rec_callback(struct ib_sa_query *sa_query,
 
 static void ib_sa_mcmember_rec_release(struct ib_sa_query *sa_query)
 {
-	kfree(sa_query->mad);
 	kfree(container_of(sa_query, struct ib_sa_mcmember_query, sa_query));
 }
 
-int ib_sa_mcmember_rec_query(struct ib_device *device, u8 port_num,
+int ib_sa_mcmember_rec_query(struct ib_sa_client *client,
+			     struct ib_device *device, u8 port_num,
 			     u8 method,
 			     struct ib_sa_mcmember_rec *rec,
 			     ib_sa_comp_mask comp_mask,
-			     int timeout_ms, unsigned int __nocast gfp_mask,
+			     int timeout_ms, gfp_t gfp_mask,
 			     void (*callback)(int status,
 					      struct ib_sa_mcmember_rec *resp,
 					      void *context),
@@ -794,60 +942,166 @@ int ib_sa_mcmember_rec_query(struct ib_device *device, u8 port_num,
 {
 	struct ib_sa_mcmember_query *query;
 	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
-	struct ib_sa_port   *port   = &sa_dev->port[port_num - sa_dev->start_port];
-	struct ib_mad_agent *agent  = port->agent;
+	struct ib_sa_port   *port;
+	struct ib_mad_agent *agent;
+	struct ib_sa_mad *mad;
 	int ret;
 
+	if (!sa_dev)
+		return -ENODEV;
+
+	port  = &sa_dev->port[port_num - sa_dev->start_port];
+	agent = port->agent;
+
 	query = kmalloc(sizeof *query, gfp_mask);
 	if (!query)
 		return -ENOMEM;
-	query->sa_query.mad = kmalloc(sizeof *query->sa_query.mad, gfp_mask);
-	if (!query->sa_query.mad) {
-		kfree(query);
-		return -ENOMEM;
-	}
 
-	query->callback = callback;
-	query->context  = context;
+	query->sa_query.port     = port;
+	ret = alloc_mad(&query->sa_query, gfp_mask);
+	if (ret)
+		goto err1;
+
+	ib_sa_client_get(client);
+	query->sa_query.client = client;
+	query->callback        = callback;
+	query->context         = context;
 
-	init_mad(query->sa_query.mad, agent);
+	mad = query->sa_query.mad_buf->mad;
+	init_mad(mad, agent);
 
-	query->sa_query.callback              = callback ? ib_sa_mcmember_rec_callback : NULL;
-	query->sa_query.release               = ib_sa_mcmember_rec_release;
-	query->sa_query.port                  = port;
-	query->sa_query.mad->mad_hdr.method   = method;
-	query->sa_query.mad->mad_hdr.attr_id  = cpu_to_be16(IB_SA_ATTR_MC_MEMBER_REC);
-	query->sa_query.mad->sa_hdr.comp_mask = comp_mask;
+	query->sa_query.callback = callback ? ib_sa_mcmember_rec_callback : NULL;
+	query->sa_query.release  = ib_sa_mcmember_rec_release;
+	mad->mad_hdr.method	 = method;
+	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_MC_MEMBER_REC);
+	mad->sa_hdr.comp_mask	 = comp_mask;
 
 	ib_pack(mcmember_rec_table, ARRAY_SIZE(mcmember_rec_table),
-		rec, query->sa_query.mad->data);
+		rec, mad->data);
 
 	*sa_query = &query->sa_query;
 
-	ret = send_mad(&query->sa_query, timeout_ms);
-	if (ret < 0) {
-		*sa_query = NULL;
-		kfree(query->sa_query.mad);
-		kfree(query);
+	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
+	if (ret < 0)
+		goto err2;
+
+	return ret;
+
+err2:
+	*sa_query = NULL;
+	ib_sa_client_put(query->sa_query.client);
+	free_mad(&query->sa_query);
+
+err1:
+	kfree(query);
+	return ret;
+}
+
+/* Support GuidInfoRecord */
+static void ib_sa_guidinfo_rec_callback(struct ib_sa_query *sa_query,
+					int status,
+					struct ib_sa_mad *mad)
+{
+	struct ib_sa_guidinfo_query *query =
+		container_of(sa_query, struct ib_sa_guidinfo_query, sa_query);
+
+	if (mad) {
+		struct ib_sa_guidinfo_rec rec;
+
+		ib_unpack(guidinfo_rec_table, ARRAY_SIZE(guidinfo_rec_table),
+			  mad->data, &rec);
+		query->callback(status, &rec, query->context);
+	} else
+		query->callback(status, NULL, query->context);
+}
+
+static void ib_sa_guidinfo_rec_release(struct ib_sa_query *sa_query)
+{
+	kfree(container_of(sa_query, struct ib_sa_guidinfo_query, sa_query));
+}
+
+int ib_sa_guid_info_rec_query(struct ib_sa_client *client,
+			      struct ib_device *device, u8 port_num,
+			      struct ib_sa_guidinfo_rec *rec,
+			      ib_sa_comp_mask comp_mask, u8 method,
+			      int timeout_ms, gfp_t gfp_mask,
+			      void (*callback)(int status,
+					       struct ib_sa_guidinfo_rec *resp,
+					       void *context),
+			      void *context,
+			      struct ib_sa_query **sa_query)
+{
+	struct ib_sa_guidinfo_query *query;
+	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
+	struct ib_sa_port *port;
+	struct ib_mad_agent *agent;
+	struct ib_sa_mad *mad;
+	int ret;
+
+	if (!sa_dev)
+		return -ENODEV;
+
+	if (method != IB_MGMT_METHOD_GET &&
+	    method != IB_MGMT_METHOD_SET &&
+	    method != IB_SA_METHOD_DELETE) {
+		return -EINVAL;
 	}
 
+	port  = &sa_dev->port[port_num - sa_dev->start_port];
+	agent = port->agent;
+
+	query = kmalloc(sizeof *query, gfp_mask);
+	if (!query)
+		return -ENOMEM;
+
+	query->sa_query.port = port;
+	ret = alloc_mad(&query->sa_query, gfp_mask);
+	if (ret)
+		goto err1;
+
+	ib_sa_client_get(client);
+	query->sa_query.client = client;
+	query->callback        = callback;
+	query->context         = context;
+
+	mad = query->sa_query.mad_buf->mad;
+	init_mad(mad, agent);
+
+	query->sa_query.callback = callback ? ib_sa_guidinfo_rec_callback : NULL;
+	query->sa_query.release  = ib_sa_guidinfo_rec_release;
+
+	mad->mad_hdr.method	 = method;
+	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_GUID_INFO_REC);
+	mad->sa_hdr.comp_mask	 = comp_mask;
+
+	ib_pack(guidinfo_rec_table, ARRAY_SIZE(guidinfo_rec_table), rec,
+		mad->data);
+
+	*sa_query = &query->sa_query;
+
+	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
+	if (ret < 0)
+		goto err2;
+
+	return ret;
+
+err2:
+	*sa_query = NULL;
+	ib_sa_client_put(query->sa_query.client);
+	free_mad(&query->sa_query);
+
+err1:
+	kfree(query);
 	return ret;
 }
-EXPORT_SYMBOL(ib_sa_mcmember_rec_query);
+EXPORT_SYMBOL(ib_sa_guid_info_rec_query);
 
 static void send_handler(struct ib_mad_agent *agent,
 			 struct ib_mad_send_wc *mad_send_wc)
 {
-	struct ib_sa_query *query;
+	struct ib_sa_query *query = mad_send_wc->send_buf->context[0];
 	unsigned long flags;
 
-	spin_lock_irqsave(&idr_lock, flags);
-	query = idr_find(&query_idr, mad_send_wc->wr_id);
-	spin_unlock_irqrestore(&idr_lock, flags);
-
-	if (!query)
-		return;
-
 	if (query->callback)
 		switch (mad_send_wc->status) {
 		case IB_WC_SUCCESS:
@@ -864,30 +1118,25 @@ static void send_handler(struct ib_mad_agent *agent,
 			break;
 		}
 
-	dma_unmap_single(agent->device->dma_device,
-			 pci_unmap_addr(query, mapping),
-			 sizeof (struct ib_sa_mad),
-			 DMA_TO_DEVICE);
-	kref_put(&query->sm_ah->ref, free_sm_ah);
-
-	query->release(query);
-
 	spin_lock_irqsave(&idr_lock, flags);
-	idr_remove(&query_idr, mad_send_wc->wr_id);
+	idr_remove(&query_idr, query->id);
 	spin_unlock_irqrestore(&idr_lock, flags);
+
+	free_mad(query);
+	ib_sa_client_put(query->client);
+	query->release(query);
 }
 
 static void recv_handler(struct ib_mad_agent *mad_agent,
 			 struct ib_mad_recv_wc *mad_recv_wc)
 {
 	struct ib_sa_query *query;
-	unsigned long flags;
+	struct ib_mad_send_buf *mad_buf;
 
-	spin_lock_irqsave(&idr_lock, flags);
-	query = idr_find(&query_idr, mad_recv_wc->wc->wr_id);
-	spin_unlock_irqrestore(&idr_lock, flags);
+	mad_buf = (void *) (unsigned long) mad_recv_wc->wc->wr_id;
+	query = mad_buf->context[0];
 
-	if (query && query->callback) {
+	if (query->callback) {
 		if (mad_recv_wc->wc->status == IB_WC_SUCCESS)
 			query->callback(query,
 					mad_recv_wc->recv_buf.mad->mad_hdr.status ?
@@ -905,14 +1154,17 @@ static void ib_sa_add_one(struct ib_device *device)
 	struct ib_sa_device *sa_dev;
 	int s, e, i;
 
-	if (device->node_type == IB_NODE_SWITCH)
+	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
+		return;
+
+	if (device->node_type == RDMA_NODE_IB_SWITCH)
 		s = e = 0;
 	else {
 		s = 1;
 		e = device->phys_port_cnt;
 	}
 
-	sa_dev = kmalloc(sizeof *sa_dev +
+	sa_dev = kzalloc(sizeof *sa_dev +
 			 (e - s + 1) * sizeof (struct ib_sa_port),
 			 GFP_KERNEL);
 	if (!sa_dev)
@@ -922,9 +1174,12 @@ static void ib_sa_add_one(struct ib_device *device)
 	sa_dev->end_port   = e;
 
 	for (i = 0; i <= e - s; ++i) {
+		spin_lock_init(&sa_dev->port[i].ah_lock);
+		if (rdma_port_get_link_layer(device, i + 1) != IB_LINK_LAYER_INFINIBAND)
+			continue;
+
 		sa_dev->port[i].sm_ah    = NULL;
 		sa_dev->port[i].port_num = i + s;
-		spin_lock_init(&sa_dev->port[i].ah_lock);
 
 		sa_dev->port[i].agent =
 			ib_register_mad_agent(device, i + s, IB_QPT_GSI,
@@ -933,8 +1188,7 @@ static void ib_sa_add_one(struct ib_device *device)
 		if (IS_ERR(sa_dev->port[i].agent))
 			goto err;
 
-		INIT_WORK(&sa_dev->port[i].update_task,
-			  update_sm_ah, &sa_dev->port[i]);
+		INIT_WORK(&sa_dev->port[i].update_task, update_sm_ah);
 	}
 
 	ib_set_client_data(device, &sa_client, sa_dev);
@@ -951,13 +1205,15 @@ static void ib_sa_add_one(struct ib_device *device)
 		goto err;
 
 	for (i = 0; i <= e - s; ++i)
-		update_sm_ah(&sa_dev->port[i]);
+		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND)
+			update_sm_ah(&sa_dev->port[i].update_task);
 
 	return;
 
 err:
 	while (--i >= 0)
-		ib_unregister_mad_agent(sa_dev->port[i].agent);
+		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND)
+			ib_unregister_mad_agent(sa_dev->port[i].agent);
 
 	kfree(sa_dev);
 
@@ -974,9 +1230,15 @@ static void ib_sa_remove_one(struct ib_device *device)
 
 	ib_unregister_event_handler(&sa_dev->event_handler);
 
+	flush_workqueue(ib_wq);
+
 	for (i = 0; i <= sa_dev->end_port - sa_dev->start_port; ++i) {
-		ib_unregister_mad_agent(sa_dev->port[i].agent);
-		kref_put(&sa_dev->port[i].sm_ah->ref, free_sm_ah);
+		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND) {
+			ib_unregister_mad_agent(sa_dev->port[i].agent);
+			if (sa_dev->port[i].sm_ah)
+				kref_put(&sa_dev->port[i].sm_ah->ref, free_sm_ah);
+		}
+
 	}
 
 	kfree(sa_dev);
@@ -986,21 +1248,32 @@ static int __init ib_sa_init(void)
 {
 	int ret;
 
-	spin_lock_init(&idr_lock);
-	spin_lock_init(&tid_lock);
-
 	get_random_bytes(&tid, sizeof tid);
 
 	ret = ib_register_client(&sa_client);
-	if (ret)
+	if (ret) {
 		printk(KERN_ERR "Couldn't register ib_sa client\n");
+		goto err1;
+	}
+
+	ret = mcast_init();
+	if (ret) {
+		printk(KERN_ERR "Couldn't initialize multicast handling\n");
+		goto err2;
+	}
 
+	return 0;
+err2:
+	ib_unregister_client(&sa_client);
+err1:
 	return ret;
 }
 
 static void __exit ib_sa_cleanup(void)
 {
+	mcast_cleanup();
 	ib_unregister_client(&sa_client);
+	idr_destroy(&query_idr);
 }
 
 module_init(ib_sa_init);