/*
* rpcrdma_ep_destroy
*
* Disconnect and destroy endpoint. After this, the only
* valid operations on the ep are to free it (if dynamically
* allocated) or re-create it.
*/
void
rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
{
int rc;
dprintk("RPC: %s: entering, connected is %d\n",
__func__, ep->rep_connected);
cancel_delayed_work_sync(&ep->rep_connect_worker);
if (ia->ri_id->qp) {
rpcrdma_ep_disconnect(ep, ia);
rdma_destroy_qp(ia->ri_id);
ia->ri_id->qp = NULL;
}
rpcrdma_free_regbuf(ia, ep->rep_padbuf);
rpcrdma_clean_cq(ep->rep_attr.recv_cq);
rc = ib_destroy_cq(ep->rep_attr.recv_cq);
if (rc)
dprintk("RPC: %s: ib_destroy_cq returned %i\n",
__func__, rc);
rpcrdma_clean_cq(ep->rep_attr.send_cq);
rc = ib_destroy_cq(ep->rep_attr.send_cq);
if (rc)
dprintk("RPC: %s: ib_destroy_cq returned %i\n",
__func__, rc);
}
/*
* Connect unconnected endpoint.
*/
int
rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
{
struct rdma_cm_id *id;
int rc = 0;
int retry_count = 0;
if (ep->rep_connected != 0) {
struct rpcrdma_xprt *xprt;
retry:
dprintk("RPC: %s: reconnecting...\n", __func__);
rc = rpcrdma_ep_disconnect(ep, ia);
if (rc && rc != -ENOTCONN)
dprintk("RPC: %s: rpcrdma_ep_disconnect"
" status %i\n", __func__, rc);
rpcrdma_clean_cq(ep->rep_attr.recv_cq);
rpcrdma_clean_cq(ep->rep_attr.send_cq);
xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
id = rpcrdma_create_id(xprt, ia,
(struct sockaddr *)&xprt->rx_data.addr);
if (IS_ERR(id)) {
rc = -EHOSTUNREACH;
goto out;
}
/* TEMP TEMP TEMP - fail if new device:
* Deregister/remarshal *all* requests!
* Close and recreate adapter, pd, etc!
* Re-determine all attributes still sane!
* More stuff I haven't thought of!
* Rrrgh!
*/
if (ia->ri_id->device != id->device) {
printk("RPC: %s: can't reconnect on "
"different device!\n", __func__);
rdma_destroy_id(id);
rc = -ENETUNREACH;
goto out;
}
/* END TEMP */
rc = rdma_create_qp(id, ia->ri_pd, &ep->rep_attr);
if (rc) {
dprintk("RPC: %s: rdma_create_qp failed %i\n",
__func__, rc);
rdma_destroy_id(id);
rc = -ENETUNREACH;
goto out;
}
rdma_destroy_qp(ia->ri_id);
rdma_destroy_id(ia->ri_id);
ia->ri_id = id;
} else {
/*
* rpcrdma_ep_destroy
*
* Disconnect and destroy endpoint. After this, the only
* valid operations on the ep are to free it (if dynamically
* allocated) or re-create it.
*
* The caller's error handling must be sure to not leak the endpoint
* if this function fails.
*/
int
rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
{
int rc;
dprintk("RPC: %s: entering, connected is %d\n",
__func__, ep->rep_connected);
if (ia->ri_id->qp) {
rc = rpcrdma_ep_disconnect(ep, ia);
if (rc)
dprintk("RPC: %s: rpcrdma_ep_disconnect"
" returned %i\n", __func__, rc);
rdma_destroy_qp(ia->ri_id);
ia->ri_id->qp = NULL;
}
/* padding - could be done in rpcrdma_buffer_destroy... */
if (ep->rep_pad_mr) {
rpcrdma_deregister_internal(ia, ep->rep_pad_mr, &ep->rep_pad);
ep->rep_pad_mr = NULL;
}
rpcrdma_clean_cq(ep->rep_cq);
rc = ib_destroy_cq(ep->rep_cq);
if (rc)
dprintk("RPC: %s: ib_destroy_cq returned %i\n",
__func__, rc);
return rc;
}
/*
* rpcrdma_ep_disconnect
*
* This is separate from destroy to facilitate the ability
* to reconnect without recreating the endpoint.
*
* This call is not reentrant, and must not be made in parallel
* on the same endpoint.
*/
int
rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
{
int rc;
rpcrdma_clean_cq(ep->rep_cq);
rc = rdma_disconnect(ia->ri_id);
if (!rc) {
/* returns without wait if not connected */
wait_event_interruptible(ep->rep_connect_wait,
ep->rep_connected != 1);
dprintk("RPC: %s: after wait, %sconnected\n", __func__,
(ep->rep_connected == 1) ? "still " : "dis");
} else {
dprintk("RPC: %s: rdma_disconnect %i\n", __func__, rc);
ep->rep_connected = rc;
}
return rc;
}
/*
* Connect unconnected endpoint.
*/
int
rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
{
struct rdma_cm_id *id;
int rc = 0;
int retry_count = 0;
if (ep->rep_connected != 0) {
struct rpcrdma_xprt *xprt;
retry:
rc = rpcrdma_ep_disconnect(ep, ia);
if (rc && rc != -ENOTCONN)
dprintk("RPC: %s: rpcrdma_ep_disconnect"
" status %i\n", __func__, rc);
rpcrdma_clean_cq(ep->rep_cq);
xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
id = rpcrdma_create_id(xprt, ia,
(struct sockaddr *)&xprt->rx_data.addr);
if (IS_ERR(id)) {
rc = PTR_ERR(id);
goto out;
}
/* TEMP TEMP TEMP - fail if new device:
* Deregister/remarshal *all* requests!
* Close and recreate adapter, pd, etc!
* Re-determine all attributes still sane!
* More stuff I haven't thought of!
* Rrrgh!
*/
if (ia->ri_id->device != id->device) {
printk("RPC: %s: can't reconnect on "
"different device!\n", __func__);
rdma_destroy_id(id);
rc = -ENETDOWN;
goto out;
}
/* END TEMP */
rdma_destroy_qp(ia->ri_id);
rdma_destroy_id(ia->ri_id);
ia->ri_id = id;
}
rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr);
if (rc) {
dprintk("RPC: %s: rdma_create_qp failed %i\n",
__func__, rc);
goto out;
}
/* XXX Tavor device performs badly with 2K MTU! */
if (strnicmp(ia->ri_id->device->dma_device->bus->name, "pci", 3) == 0) {
struct pci_dev *pcid = to_pci_dev(ia->ri_id->device->dma_device);
if (pcid->device == PCI_DEVICE_ID_MELLANOX_TAVOR &&
(pcid->vendor == PCI_VENDOR_ID_MELLANOX ||
pcid->vendor == PCI_VENDOR_ID_TOPSPIN)) {
struct ib_qp_attr attr = {
.path_mtu = IB_MTU_1024
};
rc = ib_modify_qp(ia->ri_id->qp, &attr, IB_QP_PATH_MTU);
}
}
ep->rep_connected = 0;
rc = rdma_connect(ia->ri_id, &ep->rep_remote_cma);
if (rc) {
dprintk("RPC: %s: rdma_connect() failed with %i\n",
__func__, rc);
goto out;
}
wait_event_interruptible(ep->rep_connect_wait, ep->rep_connected != 0);
/*
* Check state. A non-peer reject indicates no listener
* (ECONNREFUSED), which may be a transient state. All
* others indicate a transport condition which has already
* undergone a best-effort.
*/
if (ep->rep_connected == -ECONNREFUSED &&
++retry_count <= RDMA_CONNECT_RETRY_MAX) {
dprintk("RPC: %s: non-peer_reject, retry\n", __func__);
goto retry;
}
if (ep->rep_connected <= 0) {
/* Sometimes, the only way to reliably connect to remote
* CMs is to use same nonzero values for ORD and IRD. */
if (retry_count++ <= RDMA_CONNECT_RETRY_MAX + 1 &&
(ep->rep_remote_cma.responder_resources == 0 ||
ep->rep_remote_cma.initiator_depth !=
ep->rep_remote_cma.responder_resources)) {
if (ep->rep_remote_cma.responder_resources == 0)
ep->rep_remote_cma.responder_resources = 1;
ep->rep_remote_cma.initiator_depth =
ep->rep_remote_cma.responder_resources;
goto retry;
}
rc = ep->rep_connected;
} else {
dprintk("RPC: %s: connected\n", __func__);
}
out:
if (rc)
ep->rep_connected = rc;
return rc;
}