#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);
struct rdma_bind_list *bind_list;
struct hlist_node node;
- struct list_head list;
- struct list_head listen_list;
+ struct list_head list; /* listen_any_list or cma_device.list */
+ struct list_head listen_list; /* per device listens */
struct cma_device *cma_dev;
struct list_head mc_list;
+ int internal_id;
enum cma_state state;
spinlock_t lock;
+ struct mutex qp_mutex;
+
struct completion comp;
atomic_t refcount;
wait_queue_head_t wait_remove;
u32 qkey;
u32 qp_num;
u8 srq;
+ u8 tos;
};
struct cma_multicast {
id_priv->id.event_handler = event_handler;
id_priv->id.ps = ps;
spin_lock_init(&id_priv->lock);
+ mutex_init(&id_priv->qp_mutex);
init_completion(&id_priv->comp);
atomic_set(&id_priv->refcount, 1);
init_waitqueue_head(&id_priv->wait_remove);
void rdma_destroy_qp(struct rdma_cm_id *id)
{
- ib_destroy_qp(id->qp);
+ struct rdma_id_private *id_priv;
+
+ id_priv = container_of(id, struct rdma_id_private, id);
+ mutex_lock(&id_priv->qp_mutex);
+ ib_destroy_qp(id_priv->id.qp);
+ id_priv->id.qp = NULL;
+ mutex_unlock(&id_priv->qp_mutex);
}
EXPORT_SYMBOL(rdma_destroy_qp);
-static int cma_modify_qp_rtr(struct rdma_cm_id *id)
+static int cma_modify_qp_rtr(struct rdma_id_private *id_priv)
{
struct ib_qp_attr qp_attr;
int qp_attr_mask, ret;
- if (!id->qp)
- return 0;
+ mutex_lock(&id_priv->qp_mutex);
+ if (!id_priv->id.qp) {
+ ret = 0;
+ goto out;
+ }
/* Need to update QP attributes from default values. */
qp_attr.qp_state = IB_QPS_INIT;
- ret = rdma_init_qp_attr(id, &qp_attr, &qp_attr_mask);
+ ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
if (ret)
- return ret;
+ goto out;
- ret = ib_modify_qp(id->qp, &qp_attr, qp_attr_mask);
+ ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
if (ret)
- return ret;
+ goto out;
qp_attr.qp_state = IB_QPS_RTR;
- ret = rdma_init_qp_attr(id, &qp_attr, &qp_attr_mask);
+ ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
if (ret)
- return ret;
+ goto out;
- return ib_modify_qp(id->qp, &qp_attr, qp_attr_mask);
+ ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
+out:
+ mutex_unlock(&id_priv->qp_mutex);
+ return ret;
}
-static int cma_modify_qp_rts(struct rdma_cm_id *id)
+static int cma_modify_qp_rts(struct rdma_id_private *id_priv)
{
struct ib_qp_attr qp_attr;
int qp_attr_mask, ret;
- if (!id->qp)
- return 0;
+ mutex_lock(&id_priv->qp_mutex);
+ if (!id_priv->id.qp) {
+ ret = 0;
+ goto out;
+ }
qp_attr.qp_state = IB_QPS_RTS;
- ret = rdma_init_qp_attr(id, &qp_attr, &qp_attr_mask);
+ ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
if (ret)
- return ret;
+ goto out;
- return ib_modify_qp(id->qp, &qp_attr, qp_attr_mask);
+ ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
+out:
+ mutex_unlock(&id_priv->qp_mutex);
+ return ret;
}
-static int cma_modify_qp_err(struct rdma_cm_id *id)
+static int cma_modify_qp_err(struct rdma_id_private *id_priv)
{
struct ib_qp_attr qp_attr;
+ int ret;
- if (!id->qp)
- return 0;
+ mutex_lock(&id_priv->qp_mutex);
+ if (!id_priv->id.qp) {
+ ret = 0;
+ goto out;
+ }
qp_attr.qp_state = IB_QPS_ERR;
- return ib_modify_qp(id->qp, &qp_attr, IB_QP_STATE);
+ ret = ib_modify_qp(id_priv->id.qp, &qp_attr, IB_QP_STATE);
+out:
+ mutex_unlock(&id_priv->qp_mutex);
+ return ret;
}
static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv,
}
}
-static inline int cma_internal_listen(struct rdma_id_private *id_priv)
-{
- return (id_priv->state == CMA_LISTEN) && id_priv->cma_dev &&
- cma_any_addr(&id_priv->id.route.addr.src_addr);
-}
-
-static void cma_destroy_listen(struct rdma_id_private *id_priv)
-{
- cma_exch(id_priv, CMA_DESTROYING);
-
- if (id_priv->cma_dev) {
- switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
- case RDMA_TRANSPORT_IB:
- if (id_priv->cm_id.ib && !IS_ERR(id_priv->cm_id.ib))
- ib_destroy_cm_id(id_priv->cm_id.ib);
- break;
- case RDMA_TRANSPORT_IWARP:
- if (id_priv->cm_id.iw && !IS_ERR(id_priv->cm_id.iw))
- iw_destroy_cm_id(id_priv->cm_id.iw);
- break;
- default:
- break;
- }
- cma_detach_from_dev(id_priv);
- }
- list_del(&id_priv->listen_list);
-
- cma_deref_id(id_priv);
- wait_for_completion(&id_priv->comp);
-
- kfree(id_priv);
-}
-
static void cma_cancel_listens(struct rdma_id_private *id_priv)
{
struct rdma_id_private *dev_id_priv;
+ /*
+ * Remove from listen_any_list to prevent added devices from spawning
+ * additional listen requests.
+ */
mutex_lock(&lock);
list_del(&id_priv->list);
while (!list_empty(&id_priv->listen_list)) {
dev_id_priv = list_entry(id_priv->listen_list.next,
struct rdma_id_private, listen_list);
- cma_destroy_listen(dev_id_priv);
+ /* sync with device removal to avoid duplicate destruction */
+ list_del_init(&dev_id_priv->list);
+ list_del(&dev_id_priv->listen_list);
+ mutex_unlock(&lock);
+
+ rdma_destroy_id(&dev_id_priv->id);
+ mutex_lock(&lock);
}
mutex_unlock(&lock);
}
cma_deref_id(id_priv);
wait_for_completion(&id_priv->comp);
+ if (id_priv->internal_id)
+ cma_deref_id(id_priv->id.context);
+
kfree(id_priv->id.route.path_rec);
kfree(id_priv);
}
{
int ret;
- ret = cma_modify_qp_rtr(&id_priv->id);
+ ret = cma_modify_qp_rtr(id_priv);
if (ret)
goto reject;
- ret = cma_modify_qp_rts(&id_priv->id);
+ ret = cma_modify_qp_rts(id_priv);
if (ret)
goto reject;
return 0;
reject:
- cma_modify_qp_err(&id_priv->id);
+ cma_modify_qp_err(id_priv);
ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED,
NULL, 0, NULL, 0);
return ret;
/* ignore event */
goto out;
case IB_CM_REJ_RECEIVED:
- cma_modify_qp_err(&id_priv->id);
+ cma_modify_qp_err(id_priv);
event.status = ib_event->param.rej_rcvd.reason;
event.event = RDMA_CM_EVENT_REJECTED;
event.param.conn.private_data = ib_event->private_data;
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);
cm_id->cm_handler = cma_ib_handler;
ret = conn_id->id.event_handler(&conn_id->id, &event);
- if (!ret)
+ if (!ret) {
+ cma_enable_remove(conn_id);
goto out;
+ }
/* Destroy the CM ID by returning a non-zero value. */
conn_id->cm_id.ib = NULL;
struct net_device *dev = NULL;
struct rdma_cm_event event;
int ret;
+ struct ib_device_attr attr;
listen_id = cm_id->context;
if (cma_disable_remove(listen_id, CMA_LISTEN))
sin = (struct sockaddr_in *) &new_cm_id->route.addr.dst_addr;
*sin = iw_event->remote_addr;
+ ret = ib_query_device(conn_id->id.device, &attr);
+ if (ret) {
+ cma_enable_remove(conn_id);
+ rdma_destroy_id(new_cm_id);
+ goto out;
+ }
+
memset(&event, 0, sizeof event);
event.event = RDMA_CM_EVENT_CONNECT_REQUEST;
event.param.conn.private_data = iw_event->private_data;
event.param.conn.private_data_len = iw_event->private_data_len;
+ event.param.conn.initiator_depth = attr.max_qp_init_rd_atom;
+ event.param.conn.responder_resources = attr.max_qp_rd_atom;
ret = conn_id->id.event_handler(&conn_id->id, &event);
if (ret) {
/* User wants to destroy the CM ID */
cma_attach_to_dev(dev_id_priv, cma_dev);
list_add_tail(&dev_id_priv->listen_list, &id_priv->listen_list);
+ atomic_inc(&id_priv->refcount);
+ dev_id_priv->internal_id = 1;
ret = rdma_listen(id, id_priv->backlog);
if (ret)
- goto err;
-
- return;
-err:
- cma_destroy_listen(dev_id_priv);
+ printk(KERN_WARNING "RDMA CMA: cma_listen_on_dev, error %d, "
+ "listening on device %s", ret, cma_dev->device->name);
}
static void cma_listen_on_all(struct rdma_id_private *id_priv)
}
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)
{
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;
}
static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
{
struct rdma_bind_list *bind_list;
- int port, ret;
+ int port, ret, low, high;
bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);
if (!bind_list)
return -ENOMEM;
retry:
+ /* FIXME: add proper port randomization per like inet_csk_get_port */
do {
ret = idr_get_new_above(ps, bind_list, next_port, &port);
} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
if (ret)
goto err1;
- if (port > sysctl_local_port_range[1]) {
- if (next_port != sysctl_local_port_range[0]) {
+ inet_get_local_port_range(&low, &high);
+ if (port > high) {
+ if (next_port != low) {
idr_remove(ps, port);
- next_port = sysctl_local_port_range[0];
+ next_port = low;
goto retry;
}
ret = -EADDRNOTAVAIL;
goto err2;
}
- if (port == sysctl_local_port_range[1])
- next_port = sysctl_local_port_range[0];
+ if (port == high)
+ next_port = low;
else
next_port = port + 1;
sin = (struct sockaddr_in*) &id_priv->id.route.addr.dst_addr;
cm_id->remote_addr = *sin;
- ret = cma_modify_qp_rtr(&id_priv->id);
+ ret = cma_modify_qp_rtr(id_priv);
if (ret)
goto out;
int qp_attr_mask, ret;
if (id_priv->id.qp) {
- ret = cma_modify_qp_rtr(&id_priv->id);
+ ret = cma_modify_qp_rtr(id_priv);
if (ret)
goto out;
struct iw_cm_conn_param iw_param;
int ret;
- ret = cma_modify_qp_rtr(&id_priv->id);
+ ret = cma_modify_qp_rtr(id_priv);
if (ret)
return ret;
return 0;
reject:
- cma_modify_qp_err(id);
+ cma_modify_qp_err(id_priv);
rdma_reject(id, NULL, 0);
return ret;
}
switch (rdma_node_get_transport(id->device->node_type)) {
case RDMA_TRANSPORT_IB:
- ret = cma_modify_qp_err(id);
+ ret = cma_modify_qp_err(id_priv);
if (ret)
goto out;
/* Initiate or respond to a disconnect. */
cma_disable_remove(id_priv, CMA_ADDR_RESOLVED))
return 0;
+ mutex_lock(&id_priv->qp_mutex);
if (!status && id_priv->id.qp)
status = ib_attach_mcast(id_priv->id.qp, &multicast->rec.mgid,
multicast->rec.mlid);
+ mutex_unlock(&id_priv->qp_mutex);
memset(&event, 0, sizeof event);
event.status = status;
/* IPv6 address is an SA assigned MGID. */
memcpy(mgid, &sin6->sin6_addr, sizeof *mgid);
} else {
- ip_ib_mc_map(sin->sin_addr.s_addr, mc_map);
+ ip_ib_mc_map(sin->sin_addr.s_addr, dev_addr->broadcast, mc_map);
if (id_priv->id.ps == RDMA_PS_UDP)
mc_map[7] = 0x01; /* Use RDMA CM signature */
- mc_map[8] = ib_addr_get_pkey(dev_addr) >> 8;
- mc_map[9] = (unsigned char) ib_addr_get_pkey(dev_addr);
*mgid = *(union ib_gid *) (mc_map + 4);
}
}
id_priv = list_entry(cma_dev->id_list.next,
struct rdma_id_private, list);
- if (cma_internal_listen(id_priv)) {
- cma_destroy_listen(id_priv);
- continue;
- }
-
+ list_del(&id_priv->listen_list);
list_del_init(&id_priv->list);
atomic_inc(&id_priv->refcount);
mutex_unlock(&lock);
- ret = cma_remove_id_dev(id_priv);
+ ret = id_priv->internal_id ? 1 : cma_remove_id_dev(id_priv);
cma_deref_id(id_priv);
if (ret)
rdma_destroy_id(&id_priv->id);
static int cma_init(void)
{
- int ret;
+ int ret, low, high, remaining;
get_random_bytes(&next_port, sizeof next_port);
- next_port = ((unsigned int) next_port %
- (sysctl_local_port_range[1] - sysctl_local_port_range[0])) +
- sysctl_local_port_range[0];
+ inet_get_local_port_range(&low, &high);
+ remaining = (high - low) + 1;
+ next_port = ((unsigned int) next_port % remaining) + low;
+
cma_wq = create_singlethread_workqueue("rdma_cm");
if (!cma_wq)
return -ENOMEM;