/*
- * Copyright (c) 2004, 2005 Intel Corporation. All rights reserved.
+ * Copyright (c) 2004-2006 Intel Corporation. All rights reserved.
* Copyright (c) 2004 Topspin Corporation. All rights reserved.
* Copyright (c) 2004, 2005 Voltaire Corporation. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*
- * $Id: cm.c 2821 2005-07-08 17:07:28Z sean.hefty $
+ * $Id: cm.c 4311 2005-12-05 18:42:01Z sean.hefty $
*/
+
+#include <linux/completion.h>
#include <linux/dma-mapping.h>
#include <linux/err.h>
#include <linux/idr.h>
#include <linux/interrupt.h>
#include <linux/pci.h>
+#include <linux/random.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/workqueue.h>
struct rb_root remote_id_table;
struct rb_root remote_sidr_table;
struct idr local_id_table;
+ __be32 random_id_operand;
+ struct list_head timewait_list;
struct workqueue_struct *wq;
} cm;
};
struct cm_work {
- struct work_struct work;
+ struct delayed_work work;
struct list_head list;
struct cm_port *port;
struct ib_mad_recv_wc *mad_recv_wc; /* Received MADs */
struct cm_timewait_info {
struct cm_work work; /* Must be first. */
+ struct list_head list;
struct rb_node remote_qp_node;
struct rb_node remote_id_node;
__be64 remote_ca_guid;
struct rb_node service_node;
struct rb_node sidr_id_node;
- spinlock_t lock;
- wait_queue_head_t wait;
+ spinlock_t lock; /* Do not acquire inside cm.lock */
+ struct completion comp;
atomic_t refcount;
struct ib_mad_send_buf *msg;
/* todo: use alternate port on send failure */
struct cm_av av;
struct cm_av alt_av;
+ struct ib_cm_compare_data *compare_data;
void *private_data;
__be64 tid;
__be32 rq_psn;
int timeout_ms;
enum ib_mtu path_mtu;
+ __be16 pkey;
u8 private_data_len;
u8 max_cm_retries;
u8 peer_to_peer;
u8 responder_resources;
u8 initiator_depth;
- u8 local_ack_timeout;
u8 retry_count;
u8 rnr_retry_count;
u8 service_timeout;
atomic_t work_count;
};
-static void cm_work_handler(void *data);
+static void cm_work_handler(struct work_struct *work);
static inline void cm_deref_id(struct cm_id_private *cm_id_priv)
{
if (atomic_dec_and_test(&cm_id_priv->refcount))
- wake_up(&cm_id_priv->wait);
+ complete(&cm_id_priv->comp);
}
static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
if (IS_ERR(ah))
return PTR_ERR(ah);
- m = ib_create_send_mad(mad_agent, cm_id_priv->id.remote_cm_qpn,
+ m = ib_create_send_mad(mad_agent, cm_id_priv->id.remote_cm_qpn,
cm_id_priv->av.pkey_index,
0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
GFP_ATOMIC);
if (!private_data || !private_data_len)
return NULL;
- data = kmalloc(private_data_len, GFP_KERNEL);
+ data = kmemdup(private_data, private_data_len, GFP_KERNEL);
if (!data)
return ERR_PTR(-ENOMEM);
- memcpy(data, private_data, private_data_len);
return data;
}
cm_id_priv->private_data_len = private_data_len;
}
-static void cm_set_ah_attr(struct ib_ah_attr *ah_attr, u8 port_num,
- u16 dlid, u8 sl, u16 src_path_bits)
-{
- memset(ah_attr, 0, sizeof ah_attr);
- ah_attr->dlid = dlid;
- ah_attr->sl = sl;
- ah_attr->src_path_bits = src_path_bits;
- ah_attr->port_num = port_num;
-}
-
-static void cm_init_av_for_response(struct cm_port *port,
- struct ib_wc *wc, struct cm_av *av)
+static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
+ struct ib_grh *grh, struct cm_av *av)
{
av->port = port;
av->pkey_index = wc->pkey_index;
- cm_set_ah_attr(&av->ah_attr, port->port_num, wc->slid,
- wc->sl, wc->dlid_path_bits);
+ ib_init_ah_from_wc(port->cm_dev->device, port->port_num, wc,
+ grh, &av->ah_attr);
}
static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
return ret;
av->port = port;
- cm_set_ah_attr(&av->ah_attr, av->port->port_num,
- be16_to_cpu(path->dlid), path->sl,
- be16_to_cpu(path->slid) & 0x7F);
+ ib_init_ah_from_path(cm_dev->device, port->port_num, path,
+ &av->ah_attr);
av->packet_life_time = path->packet_life_time;
return 0;
}
static int cm_alloc_id(struct cm_id_private *cm_id_priv)
{
unsigned long flags;
- int ret;
+ int ret, id;
static int next_id;
do {
spin_lock_irqsave(&cm.lock, flags);
- ret = idr_get_new_above(&cm.local_id_table, cm_id_priv, next_id++,
- (__force int *) &cm_id_priv->id.local_id);
+ ret = idr_get_new_above(&cm.local_id_table, cm_id_priv,
+ next_id++, &id);
spin_unlock_irqrestore(&cm.lock, flags);
} while( (ret == -EAGAIN) && idr_pre_get(&cm.local_id_table, GFP_KERNEL) );
+
+ cm_id_priv->id.local_id = (__force __be32) (id ^ cm.random_id_operand);
return ret;
}
unsigned long flags;
spin_lock_irqsave(&cm.lock, flags);
- idr_remove(&cm.local_id_table, (__force int) local_id);
+ idr_remove(&cm.local_id_table,
+ (__force int) (local_id ^ cm.random_id_operand));
spin_unlock_irqrestore(&cm.lock, flags);
}
{
struct cm_id_private *cm_id_priv;
- cm_id_priv = idr_find(&cm.local_id_table, (__force int) local_id);
+ cm_id_priv = idr_find(&cm.local_id_table,
+ (__force int) (local_id ^ cm.random_id_operand));
if (cm_id_priv) {
if (cm_id_priv->id.remote_id == remote_id)
atomic_inc(&cm_id_priv->refcount);
return cm_id_priv;
}
+static void cm_mask_copy(u8 *dst, u8 *src, u8 *mask)
+{
+ int i;
+
+ for (i = 0; i < IB_CM_COMPARE_SIZE / sizeof(unsigned long); i++)
+ ((unsigned long *) dst)[i] = ((unsigned long *) src)[i] &
+ ((unsigned long *) mask)[i];
+}
+
+static int cm_compare_data(struct ib_cm_compare_data *src_data,
+ struct ib_cm_compare_data *dst_data)
+{
+ u8 src[IB_CM_COMPARE_SIZE];
+ u8 dst[IB_CM_COMPARE_SIZE];
+
+ if (!src_data || !dst_data)
+ return 0;
+
+ cm_mask_copy(src, src_data->data, dst_data->mask);
+ cm_mask_copy(dst, dst_data->data, src_data->mask);
+ return memcmp(src, dst, IB_CM_COMPARE_SIZE);
+}
+
+static int cm_compare_private_data(u8 *private_data,
+ struct ib_cm_compare_data *dst_data)
+{
+ u8 src[IB_CM_COMPARE_SIZE];
+
+ if (!dst_data)
+ return 0;
+
+ cm_mask_copy(src, private_data, dst_data->mask);
+ return memcmp(src, dst_data->data, IB_CM_COMPARE_SIZE);
+}
+
static struct cm_id_private * cm_insert_listen(struct cm_id_private *cm_id_priv)
{
struct rb_node **link = &cm.listen_service_table.rb_node;
struct cm_id_private *cur_cm_id_priv;
__be64 service_id = cm_id_priv->id.service_id;
__be64 service_mask = cm_id_priv->id.service_mask;
+ int data_cmp;
while (*link) {
parent = *link;
cur_cm_id_priv = rb_entry(parent, struct cm_id_private,
service_node);
+ data_cmp = cm_compare_data(cm_id_priv->compare_data,
+ cur_cm_id_priv->compare_data);
if ((cur_cm_id_priv->id.service_mask & service_id) ==
(service_mask & cur_cm_id_priv->id.service_id) &&
- (cm_id_priv->id.device == cur_cm_id_priv->id.device))
+ (cm_id_priv->id.device == cur_cm_id_priv->id.device) &&
+ !data_cmp)
return cur_cm_id_priv;
if (cm_id_priv->id.device < cur_cm_id_priv->id.device)
link = &(*link)->rb_right;
else if (service_id < cur_cm_id_priv->id.service_id)
link = &(*link)->rb_left;
+ else if (service_id > cur_cm_id_priv->id.service_id)
+ link = &(*link)->rb_right;
+ else if (data_cmp < 0)
+ link = &(*link)->rb_left;
else
link = &(*link)->rb_right;
}
}
static struct cm_id_private * cm_find_listen(struct ib_device *device,
- __be64 service_id)
+ __be64 service_id,
+ u8 *private_data)
{
struct rb_node *node = cm.listen_service_table.rb_node;
struct cm_id_private *cm_id_priv;
+ int data_cmp;
while (node) {
cm_id_priv = rb_entry(node, struct cm_id_private, service_node);
+ data_cmp = cm_compare_private_data(private_data,
+ cm_id_priv->compare_data);
if ((cm_id_priv->id.service_mask & service_id) ==
cm_id_priv->id.service_id &&
- (cm_id_priv->id.device == device))
+ (cm_id_priv->id.device == device) && !data_cmp)
return cm_id_priv;
if (device < cm_id_priv->id.device)
node = node->rb_right;
else if (service_id < cm_id_priv->id.service_id)
node = node->rb_left;
+ else if (service_id > cm_id_priv->id.service_id)
+ node = node->rb_right;
+ else if (data_cmp < 0)
+ node = node->rb_left;
else
node = node->rb_right;
}
goto error;
spin_lock_init(&cm_id_priv->lock);
- init_waitqueue_head(&cm_id_priv->wait);
+ init_completion(&cm_id_priv->comp);
INIT_LIST_HEAD(&cm_id_priv->work_list);
atomic_set(&cm_id_priv->work_count, -1);
atomic_set(&cm_id_priv->refcount, 1);
static void cm_cleanup_timewait(struct cm_timewait_info *timewait_info)
{
- unsigned long flags;
-
- if (!timewait_info->inserted_remote_id &&
- !timewait_info->inserted_remote_qp)
- return;
-
- spin_lock_irqsave(&cm.lock, flags);
if (timewait_info->inserted_remote_id) {
rb_erase(&timewait_info->remote_id_node, &cm.remote_id_table);
timewait_info->inserted_remote_id = 0;
rb_erase(&timewait_info->remote_qp_node, &cm.remote_qp_table);
timewait_info->inserted_remote_qp = 0;
}
- spin_unlock_irqrestore(&cm.lock, flags);
}
static struct cm_timewait_info * cm_create_timewait_info(__be32 local_id)
return ERR_PTR(-ENOMEM);
timewait_info->work.local_id = local_id;
- INIT_WORK(&timewait_info->work.work, cm_work_handler,
- &timewait_info->work);
+ INIT_DELAYED_WORK(&timewait_info->work.work, cm_work_handler);
timewait_info->work.cm_event.event = IB_CM_TIMEWAIT_EXIT;
return timewait_info;
}
static void cm_enter_timewait(struct cm_id_private *cm_id_priv)
{
int wait_time;
+ unsigned long flags;
+
+ spin_lock_irqsave(&cm.lock, flags);
+ cm_cleanup_timewait(cm_id_priv->timewait_info);
+ list_add_tail(&cm_id_priv->timewait_info->list, &cm.timewait_list);
+ spin_unlock_irqrestore(&cm.lock, flags);
/*
* The cm_id could be destroyed by the user before we exit timewait.
* timewait before notifying the user that we've exited timewait.
*/
cm_id_priv->id.state = IB_CM_TIMEWAIT;
- wait_time = cm_convert_to_ms(cm_id_priv->local_ack_timeout);
+ wait_time = cm_convert_to_ms(cm_id_priv->av.packet_life_time + 1);
queue_delayed_work(cm.wq, &cm_id_priv->timewait_info->work.work,
msecs_to_jiffies(wait_time));
cm_id_priv->timewait_info = NULL;
static void cm_reset_to_idle(struct cm_id_private *cm_id_priv)
{
+ unsigned long flags;
+
cm_id_priv->id.state = IB_CM_IDLE;
if (cm_id_priv->timewait_info) {
+ spin_lock_irqsave(&cm.lock, flags);
cm_cleanup_timewait(cm_id_priv->timewait_info);
+ spin_unlock_irqrestore(&cm.lock, flags);
kfree(cm_id_priv->timewait_info);
cm_id_priv->timewait_info = NULL;
}
}
-void ib_destroy_cm_id(struct ib_cm_id *cm_id)
+static void cm_destroy_id(struct ib_cm_id *cm_id, int err)
{
struct cm_id_private *cm_id_priv;
struct cm_work *work;
sizeof cm_id_priv->av.port->cm_dev->ca_guid,
NULL, 0);
break;
+ case IB_CM_REQ_RCVD:
+ if (err == -ENOMEM) {
+ /* Do not reject to allow future retries. */
+ cm_reset_to_idle(cm_id_priv);
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ } else {
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ ib_send_cm_rej(cm_id, IB_CM_REJ_CONSUMER_DEFINED,
+ NULL, 0, NULL, 0);
+ }
+ break;
case IB_CM_MRA_REQ_RCVD:
case IB_CM_REP_SENT:
case IB_CM_MRA_REP_RCVD:
ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
/* Fall through */
- case IB_CM_REQ_RCVD:
case IB_CM_MRA_REQ_SENT:
case IB_CM_REP_RCVD:
case IB_CM_MRA_REP_SENT:
}
cm_free_id(cm_id->local_id);
- atomic_dec(&cm_id_priv->refcount);
- wait_event(cm_id_priv->wait, !atomic_read(&cm_id_priv->refcount));
+ cm_deref_id(cm_id_priv);
+ wait_for_completion(&cm_id_priv->comp);
while ((work = cm_dequeue_work(cm_id_priv)) != NULL)
cm_free_work(work);
- if (cm_id_priv->private_data && cm_id_priv->private_data_len)
- kfree(cm_id_priv->private_data);
+ kfree(cm_id_priv->compare_data);
+ kfree(cm_id_priv->private_data);
kfree(cm_id_priv);
}
+
+void ib_destroy_cm_id(struct ib_cm_id *cm_id)
+{
+ cm_destroy_id(cm_id, 0);
+}
EXPORT_SYMBOL(ib_destroy_cm_id);
-int ib_cm_listen(struct ib_cm_id *cm_id,
- __be64 service_id,
- __be64 service_mask)
+int ib_cm_listen(struct ib_cm_id *cm_id, __be64 service_id, __be64 service_mask,
+ struct ib_cm_compare_data *compare_data)
{
struct cm_id_private *cm_id_priv, *cur_cm_id_priv;
unsigned long flags;
return -EINVAL;
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
- BUG_ON(cm_id->state != IB_CM_IDLE);
+ if (cm_id->state != IB_CM_IDLE)
+ return -EINVAL;
+
+ if (compare_data) {
+ cm_id_priv->compare_data = kzalloc(sizeof *compare_data,
+ GFP_KERNEL);
+ if (!cm_id_priv->compare_data)
+ return -ENOMEM;
+ cm_mask_copy(cm_id_priv->compare_data->data,
+ compare_data->data, compare_data->mask);
+ memcpy(cm_id_priv->compare_data->mask, compare_data->mask,
+ IB_CM_COMPARE_SIZE);
+ }
cm_id->state = IB_CM_LISTEN;
if (cur_cm_id_priv) {
cm_id->state = IB_CM_IDLE;
+ kfree(cm_id_priv->compare_data);
+ cm_id_priv->compare_data = NULL;
ret = -EBUSY;
}
return ret;
cm_id_priv->timewait_info = cm_create_timewait_info(cm_id_priv->
id.local_id);
- if (IS_ERR(cm_id_priv->timewait_info))
+ if (IS_ERR(cm_id_priv->timewait_info)) {
+ ret = PTR_ERR(cm_id_priv->timewait_info);
goto out;
+ }
ret = cm_init_av_by_path(param->primary_path, &cm_id_priv->av);
if (ret)
cm_id_priv->responder_resources = param->responder_resources;
cm_id_priv->retry_count = param->retry_count;
cm_id_priv->path_mtu = param->primary_path->mtu;
+ cm_id_priv->pkey = param->primary_path->pkey;
cm_id_priv->qp_type = param->qp_type;
ret = cm_alloc_msg(cm_id_priv, &cm_id_priv->msg);
cm_id_priv->local_qpn = cm_req_get_local_qpn(req_msg);
cm_id_priv->rq_psn = cm_req_get_starting_psn(req_msg);
- cm_id_priv->local_ack_timeout =
- cm_req_get_primary_local_ack_timeout(req_msg);
spin_lock_irqsave(&cm_id_priv->lock, flags);
ret = ib_post_send_mad(cm_id_priv->msg, NULL);
}
cm_deref_id(cm_id_priv);
if (ret)
- ib_destroy_cm_id(&cm_id_priv->id);
+ cm_destroy_id(&cm_id_priv->id, ret);
}
static void cm_format_mra(struct cm_mra_msg *mra_msg,
if (timewait_info) {
cur_cm_id_priv = cm_get_id(timewait_info->work.local_id,
timewait_info->work.remote_id);
+ cm_cleanup_timewait(cm_id_priv->timewait_info);
spin_unlock_irqrestore(&cm.lock, flags);
if (cur_cm_id_priv) {
cm_dup_req_handler(work, cur_cm_id_priv);
cm_issue_rej(work->port, work->mad_recv_wc,
IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REQ,
NULL, 0);
- goto error;
+ listen_cm_id_priv = NULL;
+ goto out;
}
/* Find matching listen request. */
listen_cm_id_priv = cm_find_listen(cm_id_priv->id.device,
- req_msg->service_id);
+ req_msg->service_id,
+ req_msg->private_data);
if (!listen_cm_id_priv) {
+ cm_cleanup_timewait(cm_id_priv->timewait_info);
spin_unlock_irqrestore(&cm.lock, flags);
cm_issue_rej(work->port, work->mad_recv_wc,
IB_CM_REJ_INVALID_SERVICE_ID, CM_MSG_RESPONSE_REQ,
NULL, 0);
- goto error;
+ goto out;
}
atomic_inc(&listen_cm_id_priv->refcount);
atomic_inc(&cm_id_priv->refcount);
cm_id_priv->id.state = IB_CM_REQ_RCVD;
atomic_inc(&cm_id_priv->work_count);
spin_unlock_irqrestore(&cm.lock, flags);
+out:
return listen_cm_id_priv;
-
-error: cm_cleanup_timewait(cm_id_priv->timewait_info);
- return NULL;
}
static int cm_req_handler(struct cm_work *work)
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
cm_id_priv->id.remote_id = req_msg->local_comm_id;
cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
+ work->mad_recv_wc->recv_buf.grh,
&cm_id_priv->av);
cm_id_priv->timewait_info = cm_create_timewait_info(cm_id_priv->
id.local_id);
if (IS_ERR(cm_id_priv->timewait_info)) {
ret = PTR_ERR(cm_id_priv->timewait_info);
- goto error1;
+ goto destroy;
}
cm_id_priv->timewait_info->work.remote_id = req_msg->local_comm_id;
cm_id_priv->timewait_info->remote_ca_guid = req_msg->local_ca_guid;
listen_cm_id_priv = cm_match_req(work, cm_id_priv);
if (!listen_cm_id_priv) {
ret = -EINVAL;
- goto error2;
+ kfree(cm_id_priv->timewait_info);
+ goto destroy;
}
cm_id_priv->id.cm_handler = listen_cm_id_priv->id.cm_handler;
cm_format_paths_from_req(req_msg, &work->path[0], &work->path[1]);
ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av);
- if (ret)
- goto error3;
+ if (ret) {
+ ib_get_cached_gid(work->port->cm_dev->device,
+ work->port->port_num, 0, &work->path[0].sgid);
+ ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
+ &work->path[0].sgid, sizeof work->path[0].sgid,
+ NULL, 0);
+ goto rejected;
+ }
if (req_msg->alt_local_lid) {
ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av);
- if (ret)
- goto error3;
+ if (ret) {
+ ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_ALT_GID,
+ &work->path[0].sgid,
+ sizeof work->path[0].sgid, NULL, 0);
+ goto rejected;
+ }
}
cm_id_priv->tid = req_msg->hdr.tid;
cm_id_priv->timeout_ms = cm_convert_to_ms(
cm_id_priv->initiator_depth = cm_req_get_resp_res(req_msg);
cm_id_priv->responder_resources = cm_req_get_init_depth(req_msg);
cm_id_priv->path_mtu = cm_req_get_path_mtu(req_msg);
+ cm_id_priv->pkey = req_msg->pkey;
cm_id_priv->sq_psn = cm_req_get_starting_psn(req_msg);
- cm_id_priv->local_ack_timeout =
- cm_req_get_primary_local_ack_timeout(req_msg);
cm_id_priv->retry_count = cm_req_get_retry_count(req_msg);
cm_id_priv->rnr_retry_count = cm_req_get_rnr_retry_count(req_msg);
cm_id_priv->qp_type = cm_req_get_qp_type(req_msg);
cm_deref_id(listen_cm_id_priv);
return 0;
-error3: atomic_dec(&cm_id_priv->refcount);
+rejected:
+ atomic_dec(&cm_id_priv->refcount);
cm_deref_id(listen_cm_id_priv);
- cm_cleanup_timewait(cm_id_priv->timewait_info);
-error2: kfree(cm_id_priv->timewait_info);
- cm_id_priv->timewait_info = NULL;
-error1: ib_destroy_cm_id(&cm_id_priv->id);
+destroy:
+ ib_destroy_cm_id(cm_id);
return ret;
}
return -EINVAL;
}
+ cm_format_rep_event(work);
+
+ spin_lock_irqsave(&cm_id_priv->lock, flags);
+ switch (cm_id_priv->id.state) {
+ case IB_CM_REQ_SENT:
+ case IB_CM_MRA_REQ_RCVD:
+ break;
+ default:
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ ret = -EINVAL;
+ goto error;
+ }
+
cm_id_priv->timewait_info->work.remote_id = rep_msg->local_comm_id;
cm_id_priv->timewait_info->remote_ca_guid = rep_msg->local_ca_guid;
cm_id_priv->timewait_info->remote_qpn = cm_rep_get_local_qpn(rep_msg);
- spin_lock_irqsave(&cm.lock, flags);
+ spin_lock(&cm.lock);
/* Check for duplicate REP. */
if (cm_insert_remote_id(cm_id_priv->timewait_info)) {
- spin_unlock_irqrestore(&cm.lock, flags);
+ spin_unlock(&cm.lock);
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
ret = -EINVAL;
goto error;
}
/* Check for a stale connection. */
if (cm_insert_remote_qpn(cm_id_priv->timewait_info)) {
- spin_unlock_irqrestore(&cm.lock, flags);
+ rb_erase(&cm_id_priv->timewait_info->remote_id_node,
+ &cm.remote_id_table);
+ cm_id_priv->timewait_info->inserted_remote_id = 0;
+ spin_unlock(&cm.lock);
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
cm_issue_rej(work->port, work->mad_recv_wc,
IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REP,
NULL, 0);
ret = -EINVAL;
goto error;
}
- spin_unlock_irqrestore(&cm.lock, flags);
-
- cm_format_rep_event(work);
+ spin_unlock(&cm.lock);
- spin_lock_irqsave(&cm_id_priv->lock, flags);
- switch (cm_id_priv->id.state) {
- case IB_CM_REQ_SENT:
- case IB_CM_MRA_REQ_RCVD:
- break;
- default:
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
- ret = -EINVAL;
- goto error;
- }
cm_id_priv->id.state = IB_CM_REP_RCVD;
cm_id_priv->id.remote_id = rep_msg->local_comm_id;
cm_id_priv->remote_qpn = cm_rep_get_local_qpn(rep_msg);
cm_deref_id(cm_id_priv);
return 0;
-error: cm_cleanup_timewait(cm_id_priv->timewait_info);
+error:
cm_deref_id(cm_id_priv);
return ret;
}
unsigned long flags;
int ret;
- /* See comment in ib_cm_establish about lookup. */
+ /* See comment in cm_establish about lookup. */
cm_id_priv = cm_acquire_id(work->local_id, work->remote_id);
if (!cm_id_priv)
return -EINVAL;
}
EXPORT_SYMBOL(ib_send_cm_drep);
+static int cm_issue_drep(struct cm_port *port,
+ struct ib_mad_recv_wc *mad_recv_wc)
+{
+ struct ib_mad_send_buf *msg = NULL;
+ struct cm_dreq_msg *dreq_msg;
+ struct cm_drep_msg *drep_msg;
+ int ret;
+
+ ret = cm_alloc_response_msg(port, mad_recv_wc, &msg);
+ if (ret)
+ return ret;
+
+ dreq_msg = (struct cm_dreq_msg *) mad_recv_wc->recv_buf.mad;
+ drep_msg = (struct cm_drep_msg *) msg->mad;
+
+ cm_format_mad_hdr(&drep_msg->hdr, CM_DREP_ATTR_ID, dreq_msg->hdr.tid);
+ drep_msg->remote_comm_id = dreq_msg->local_comm_id;
+ drep_msg->local_comm_id = dreq_msg->remote_comm_id;
+
+ ret = ib_post_send_mad(msg, NULL);
+ if (ret)
+ cm_free_msg(msg);
+
+ return ret;
+}
+
static int cm_dreq_handler(struct cm_work *work)
{
struct cm_id_private *cm_id_priv;
dreq_msg = (struct cm_dreq_msg *)work->mad_recv_wc->recv_buf.mad;
cm_id_priv = cm_acquire_id(dreq_msg->remote_comm_id,
dreq_msg->local_comm_id);
- if (!cm_id_priv)
+ if (!cm_id_priv) {
+ cm_issue_drep(work->port, work->mad_recv_wc);
return -EINVAL;
+ }
work->cm_event.private_data = &dreq_msg->private_data;
spin_unlock_irqrestore(&cm.lock, flags);
return NULL;
}
- cm_id_priv = idr_find(&cm.local_id_table,
- (__force int) timewait_info->work.local_id);
+ cm_id_priv = idr_find(&cm.local_id_table, (__force int)
+ (timewait_info->work.local_id ^
+ cm.random_id_operand));
if (cm_id_priv) {
if (cm_id_priv->id.remote_id == remote_id)
atomic_inc(&cm_id_priv->refcount);
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
spin_lock_irqsave(&cm_id_priv->lock, flags);
if (cm_id->state != IB_CM_ESTABLISHED ||
- cm_id->lap_state != IB_CM_LAP_IDLE) {
+ (cm_id->lap_state != IB_CM_LAP_UNINIT &&
+ cm_id->lap_state != IB_CM_LAP_IDLE)) {
ret = -EINVAL;
goto out;
}
+ ret = cm_init_av_by_path(alternate_path, &cm_id_priv->alt_av);
+ if (ret)
+ goto out;
+
ret = cm_alloc_msg(cm_id_priv, &msg);
if (ret)
goto out;
}
EXPORT_SYMBOL(ib_send_cm_lap);
-static void cm_format_path_from_lap(struct ib_sa_path_rec *path,
+static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv,
+ struct ib_sa_path_rec *path,
struct cm_lap_msg *lap_msg)
{
memset(path, 0, sizeof *path);
path->hop_limit = lap_msg->alt_hop_limit;
path->traffic_class = cm_lap_get_traffic_class(lap_msg);
path->reversible = 1;
- /* pkey is same as in REQ */
+ path->pkey = cm_id_priv->pkey;
path->sl = cm_lap_get_sl(lap_msg);
path->mtu_selector = IB_SA_EQ;
- /* mtu is same as in REQ */
+ path->mtu = cm_id_priv->path_mtu;
path->rate_selector = IB_SA_EQ;
path->rate = cm_lap_get_packet_rate(lap_msg);
path->packet_life_time_selector = IB_SA_EQ;
param = &work->cm_event.param.lap_rcvd;
param->alternate_path = &work->path[0];
- cm_format_path_from_lap(param->alternate_path, lap_msg);
+ cm_format_path_from_lap(cm_id_priv, param->alternate_path, lap_msg);
work->cm_event.private_data = &lap_msg->private_data;
spin_lock_irqsave(&cm_id_priv->lock, flags);
goto unlock;
switch (cm_id_priv->id.lap_state) {
+ case IB_CM_LAP_UNINIT:
case IB_CM_LAP_IDLE:
break;
case IB_CM_MRA_LAP_SENT:
cm_id_priv->id.lap_state = IB_CM_LAP_RCVD;
cm_id_priv->tid = lap_msg->hdr.tid;
+ cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
+ work->mad_recv_wc->recv_buf.grh,
+ &cm_id_priv->av);
+ cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av);
ret = atomic_inc_and_test(&cm_id_priv->work_count);
if (!ret)
list_add_tail(&work->list, &cm_id_priv->work_list);
{
struct cm_timewait_info *timewait_info;
struct cm_id_private *cm_id_priv;
- unsigned long flags;
int ret;
timewait_info = (struct cm_timewait_info *)work;
- cm_cleanup_timewait(timewait_info);
+ spin_lock_irq(&cm.lock);
+ list_del(&timewait_info->list);
+ spin_unlock_irq(&cm.lock);
cm_id_priv = cm_acquire_id(timewait_info->work.local_id,
timewait_info->work.remote_id);
if (!cm_id_priv)
return -EINVAL;
- spin_lock_irqsave(&cm_id_priv->lock, flags);
+ spin_lock_irq(&cm_id_priv->lock);
if (cm_id_priv->id.state != IB_CM_TIMEWAIT ||
cm_id_priv->remote_qpn != timewait_info->remote_qpn) {
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ spin_unlock_irq(&cm_id_priv->lock);
goto out;
}
cm_id_priv->id.state = IB_CM_IDLE;
ret = atomic_inc_and_test(&cm_id_priv->work_count);
if (!ret)
list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ spin_unlock_irq(&cm_id_priv->lock);
if (ret)
cm_process_work(cm_id_priv, work);
cm_format_mad_hdr(&sidr_req_msg->hdr, CM_SIDR_REQ_ATTR_ID,
cm_form_tid(cm_id_priv, CM_MSG_SEQUENCE_SIDR));
sidr_req_msg->request_id = cm_id_priv->id.local_id;
- sidr_req_msg->pkey = cpu_to_be16(param->pkey);
+ sidr_req_msg->pkey = cpu_to_be16(param->path->pkey);
sidr_req_msg->service_id = param->service_id;
if (param->private_data && param->private_data_len)
cm_id_priv->av.dgid.global.subnet_prefix = cpu_to_be64(wc->slid);
cm_id_priv->av.dgid.global.interface_id = 0;
cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
+ work->mad_recv_wc->recv_buf.grh,
&cm_id_priv->av);
cm_id_priv->id.remote_id = sidr_req_msg->request_id;
cm_id_priv->id.state = IB_CM_SIDR_REQ_RCVD;
goto out; /* Duplicate message. */
}
cur_cm_id_priv = cm_find_listen(cm_id->device,
- sidr_req_msg->service_id);
+ sidr_req_msg->service_id,
+ sidr_req_msg->private_data);
if (!cur_cm_id_priv) {
rb_erase(&cm_id_priv->sidr_id_node, &cm.remote_sidr_table);
spin_unlock_irqrestore(&cm.lock, flags);
}
}
-static void cm_work_handler(void *data)
+static void cm_work_handler(struct work_struct *_work)
{
- struct cm_work *work = data;
+ struct cm_work *work = container_of(_work, struct cm_work, work.work);
int ret;
switch (work->cm_event.event) {
cm_free_work(work);
}
-int ib_cm_establish(struct ib_cm_id *cm_id)
+static int cm_establish(struct ib_cm_id *cm_id)
{
struct cm_id_private *cm_id_priv;
struct cm_work *work;
* we need to find the cm_id once we're in the context of the
* worker thread, rather than holding a reference on it.
*/
- INIT_WORK(&work->work, cm_work_handler, work);
+ INIT_DELAYED_WORK(&work->work, cm_work_handler);
work->local_id = cm_id->local_id;
work->remote_id = cm_id->remote_id;
work->mad_recv_wc = NULL;
work->cm_event.event = IB_CM_USER_ESTABLISHED;
- queue_work(cm.wq, &work->work);
+ queue_delayed_work(cm.wq, &work->work, 0);
out:
return ret;
}
-EXPORT_SYMBOL(ib_cm_establish);
+
+static int cm_migrate(struct ib_cm_id *cm_id)
+{
+ struct cm_id_private *cm_id_priv;
+ unsigned long flags;
+ int ret = 0;
+
+ cm_id_priv = container_of(cm_id, struct cm_id_private, id);
+ spin_lock_irqsave(&cm_id_priv->lock, flags);
+ if (cm_id->state == IB_CM_ESTABLISHED &&
+ (cm_id->lap_state == IB_CM_LAP_UNINIT ||
+ cm_id->lap_state == IB_CM_LAP_IDLE)) {
+ cm_id->lap_state = IB_CM_LAP_IDLE;
+ cm_id_priv->av = cm_id_priv->alt_av;
+ } else
+ ret = -EINVAL;
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+
+ return ret;
+}
+
+int ib_cm_notify(struct ib_cm_id *cm_id, enum ib_event_type event)
+{
+ int ret;
+
+ switch (event) {
+ case IB_EVENT_COMM_EST:
+ ret = cm_establish(cm_id);
+ break;
+ case IB_EVENT_PATH_MIG:
+ ret = cm_migrate(cm_id);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ return ret;
+}
+EXPORT_SYMBOL(ib_cm_notify);
static void cm_recv_handler(struct ib_mad_agent *mad_agent,
struct ib_mad_recv_wc *mad_recv_wc)
return;
}
- INIT_WORK(&work->work, cm_work_handler, work);
+ INIT_DELAYED_WORK(&work->work, cm_work_handler);
work->cm_event.event = event;
work->mad_recv_wc = mad_recv_wc;
work->port = (struct cm_port *)mad_agent->context;
- queue_work(cm.wq, &work->work);
+ queue_delayed_work(cm.wq, &work->work, 0);
}
static int cm_init_qp_init_attr(struct cm_id_private *cm_id_priv,
case IB_CM_ESTABLISHED:
*qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS |
IB_QP_PKEY_INDEX | IB_QP_PORT;
- qp_attr->qp_access_flags = IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_WRITE;
+ qp_attr->qp_access_flags = IB_ACCESS_REMOTE_WRITE;
if (cm_id_priv->responder_resources)
- qp_attr->qp_access_flags |= IB_ACCESS_REMOTE_READ;
+ qp_attr->qp_access_flags |= IB_ACCESS_REMOTE_READ |
+ IB_ACCESS_REMOTE_ATOMIC;
qp_attr->pkey_index = cm_id_priv->av.pkey_index;
qp_attr->port_num = cm_id_priv->av.port->port_num;
ret = 0;
}
if (cm_id_priv->alt_av.ah_attr.dlid) {
*qp_attr_mask |= IB_QP_ALT_PATH;
+ qp_attr->alt_port_num = cm_id_priv->alt_av.port->port_num;
+ qp_attr->alt_pkey_index = cm_id_priv->alt_av.pkey_index;
+ qp_attr->alt_timeout =
+ cm_id_priv->alt_av.packet_life_time + 1;
qp_attr->alt_ah_attr = cm_id_priv->alt_av.ah_attr;
}
ret = 0;
spin_lock_irqsave(&cm_id_priv->lock, flags);
switch (cm_id_priv->id.state) {
+ /* Allow transition to RTS before sending REP */
+ case IB_CM_REQ_RCVD:
+ case IB_CM_MRA_REQ_SENT:
+
case IB_CM_REP_RCVD:
case IB_CM_MRA_REP_SENT:
case IB_CM_REP_SENT:
case IB_CM_MRA_REP_RCVD:
case IB_CM_ESTABLISHED:
- *qp_attr_mask = IB_QP_STATE | IB_QP_SQ_PSN;
- qp_attr->sq_psn = be32_to_cpu(cm_id_priv->sq_psn);
- if (cm_id_priv->qp_type == IB_QPT_RC) {
- *qp_attr_mask |= IB_QP_TIMEOUT | IB_QP_RETRY_CNT |
- IB_QP_RNR_RETRY |
- IB_QP_MAX_QP_RD_ATOMIC;
- qp_attr->timeout = cm_id_priv->local_ack_timeout;
- qp_attr->retry_cnt = cm_id_priv->retry_count;
- qp_attr->rnr_retry = cm_id_priv->rnr_retry_count;
- qp_attr->max_rd_atomic = cm_id_priv->initiator_depth;
- }
- if (cm_id_priv->alt_av.ah_attr.dlid) {
- *qp_attr_mask |= IB_QP_PATH_MIG_STATE;
+ if (cm_id_priv->id.lap_state == IB_CM_LAP_UNINIT) {
+ *qp_attr_mask = IB_QP_STATE | IB_QP_SQ_PSN;
+ qp_attr->sq_psn = be32_to_cpu(cm_id_priv->sq_psn);
+ if (cm_id_priv->qp_type == IB_QPT_RC) {
+ *qp_attr_mask |= IB_QP_TIMEOUT | IB_QP_RETRY_CNT |
+ IB_QP_RNR_RETRY |
+ IB_QP_MAX_QP_RD_ATOMIC;
+ qp_attr->timeout =
+ cm_id_priv->av.packet_life_time + 1;
+ qp_attr->retry_cnt = cm_id_priv->retry_count;
+ qp_attr->rnr_retry = cm_id_priv->rnr_retry_count;
+ qp_attr->max_rd_atomic =
+ cm_id_priv->initiator_depth;
+ }
+ if (cm_id_priv->alt_av.ah_attr.dlid) {
+ *qp_attr_mask |= IB_QP_PATH_MIG_STATE;
+ qp_attr->path_mig_state = IB_MIG_REARM;
+ }
+ } else {
+ *qp_attr_mask = IB_QP_ALT_PATH | IB_QP_PATH_MIG_STATE;
+ qp_attr->alt_port_num = cm_id_priv->alt_av.port->port_num;
+ qp_attr->alt_pkey_index = cm_id_priv->alt_av.pkey_index;
+ qp_attr->alt_timeout =
+ cm_id_priv->alt_av.packet_life_time + 1;
+ qp_attr->alt_ah_attr = cm_id_priv->alt_av.ah_attr;
qp_attr->path_mig_state = IB_MIG_REARM;
}
ret = 0;
int ret;
u8 i;
+ if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
+ return;
+
cm_dev = kmalloc(sizeof(*cm_dev) + sizeof(*port) *
device->phys_port_cnt, GFP_KERNEL);
if (!cm_dev)
cm.remote_qp_table = RB_ROOT;
cm.remote_sidr_table = RB_ROOT;
idr_init(&cm.local_id_table);
+ get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand);
idr_pre_get(&cm.local_id_table, GFP_KERNEL);
+ INIT_LIST_HEAD(&cm.timewait_list);
cm.wq = create_workqueue("ib_cm");
if (!cm.wq)
static void __exit ib_cm_cleanup(void)
{
- flush_workqueue(cm.wq);
+ struct cm_timewait_info *timewait_info, *tmp;
+
+ spin_lock_irq(&cm.lock);
+ list_for_each_entry(timewait_info, &cm.timewait_list, list)
+ cancel_delayed_work(&timewait_info->work.work);
+ spin_unlock_irq(&cm.lock);
+
destroy_workqueue(cm.wq);
+
+ list_for_each_entry_safe(timewait_info, tmp, &cm.timewait_list, list) {
+ list_del(&timewait_info->list);
+ kfree(timewait_info);
+ }
+
ib_unregister_client(&cm_client);
idr_destroy(&cm.local_id_table);
}
git://git.onelab.eu / linux-2.6.git / blobdiff