/*
* Create unconnected endpoint.
*/
int
rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
struct rpcrdma_create_data_internal *cdata)
{
struct ib_device_attr devattr;
struct ib_cq *sendcq, *recvcq;
int rc, err;
rc = ib_query_device(ia->ri_id->device, &devattr);
if (rc) {
dprintk("RPC: %s: ib_query_device failed %d\n",
__func__, rc);
return rc;
}
/* check provider's send/recv wr limits */
if (cdata->max_requests > devattr.max_qp_wr)
cdata->max_requests = devattr.max_qp_wr;
ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall;
ep->rep_attr.qp_context = ep;
/* send_cq and recv_cq initialized below */
ep->rep_attr.srq = NULL;
ep->rep_attr.cap.max_send_wr = cdata->max_requests;
switch (ia->ri_memreg_strategy) {
case RPCRDMA_FRMR: {
int depth = 7;
/* Add room for frmr register and invalidate WRs.
* 1. FRMR reg WR for head
* 2. FRMR invalidate WR for head
* 3. N FRMR reg WRs for pagelist
* 4. N FRMR invalidate WRs for pagelist
* 5. FRMR reg WR for tail
* 6. FRMR invalidate WR for tail
* 7. The RDMA_SEND WR
*/
/* Calculate N if the device max FRMR depth is smaller than
* RPCRDMA_MAX_DATA_SEGS.
*/
if (ia->ri_max_frmr_depth < RPCRDMA_MAX_DATA_SEGS) {
int delta = RPCRDMA_MAX_DATA_SEGS -
ia->ri_max_frmr_depth;
do {
depth += 2; /* FRMR reg + invalidate */
delta -= ia->ri_max_frmr_depth;
} while (delta > 0);
}
ep->rep_attr.cap.max_send_wr *= depth;
if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr) {
cdata->max_requests = devattr.max_qp_wr / depth;
if (!cdata->max_requests)
return -EINVAL;
ep->rep_attr.cap.max_send_wr = cdata->max_requests *
depth;
}
break;
}
default:
break;
}
ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
ep->rep_attr.cap.max_send_sge = (cdata->padding ? 4 : 2);
ep->rep_attr.cap.max_recv_sge = 1;
ep->rep_attr.cap.max_inline_data = 0;
ep->rep_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
ep->rep_attr.qp_type = IB_QPT_RC;
ep->rep_attr.port_num = ~0;
dprintk("RPC: %s: requested max: dtos: send %d recv %d; "
"iovs: send %d recv %d\n",
__func__,
ep->rep_attr.cap.max_send_wr,
ep->rep_attr.cap.max_recv_wr,
ep->rep_attr.cap.max_send_sge,
ep->rep_attr.cap.max_recv_sge);
/* set trigger for requesting send completion */
ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1;
if (ep->rep_cqinit <= 2)
ep->rep_cqinit = 0;
INIT_CQCOUNT(ep);
ep->rep_ia = ia;
init_waitqueue_head(&ep->rep_connect_wait);
INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker);
sendcq = ib_create_cq(ia->ri_id->device, rpcrdma_sendcq_upcall,
rpcrdma_cq_async_error_upcall, ep,
ep->rep_attr.cap.max_send_wr + 1, 0);
if (IS_ERR(sendcq)) {
rc = PTR_ERR(sendcq);
dprintk("RPC: %s: failed to create send CQ: %i\n",
__func__, rc);
goto out1;
}
rc = ib_req_notify_cq(sendcq, IB_CQ_NEXT_COMP);
if (rc) {
dprintk("RPC: %s: ib_req_notify_cq failed: %i\n",
__func__, rc);
goto out2;
}
recvcq = ib_create_cq(ia->ri_id->device, rpcrdma_recvcq_upcall,
rpcrdma_cq_async_error_upcall, ep,
ep->rep_attr.cap.max_recv_wr + 1, 0);
if (IS_ERR(recvcq)) {
rc = PTR_ERR(recvcq);
dprintk("RPC: %s: failed to create recv CQ: %i\n",
__func__, rc);
goto out2;
}
rc = ib_req_notify_cq(recvcq, IB_CQ_NEXT_COMP);
if (rc) {
dprintk("RPC: %s: ib_req_notify_cq failed: %i\n",
__func__, rc);
ib_destroy_cq(recvcq);
goto out2;
}
ep->rep_attr.send_cq = sendcq;
ep->rep_attr.recv_cq = recvcq;
/* Initialize cma parameters */
/* RPC/RDMA does not use private data */
ep->rep_remote_cma.private_data = NULL;
ep->rep_remote_cma.private_data_len = 0;
/* Client offers RDMA Read but does not initiate */
ep->rep_remote_cma.initiator_depth = 0;
if (devattr.max_qp_rd_atom > 32) /* arbitrary but <= 255 */
ep->rep_remote_cma.responder_resources = 32;
else
ep->rep_remote_cma.responder_resources = devattr.max_qp_rd_atom;
ep->rep_remote_cma.retry_count = 7;
ep->rep_remote_cma.flow_control = 0;
ep->rep_remote_cma.rnr_retry_count = 0;
return 0;
out2:
err = ib_destroy_cq(sendcq);
if (err)
dprintk("RPC: %s: ib_destroy_cq returned %i\n",
__func__, err);
out1:
return rc;
}
/*
* Create unconnected endpoint.
*/
int
rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
struct rpcrdma_create_data_internal *cdata)
{
struct ib_device_attr devattr;
int rc, err;
rc = ib_query_device(ia->ri_id->device, &devattr);
if (rc) {
dprintk("RPC: %s: ib_query_device failed %d\n",
__func__, rc);
return rc;
}
/* check provider's send/recv wr limits */
if (cdata->max_requests > devattr.max_qp_wr)
cdata->max_requests = devattr.max_qp_wr;
ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall;
ep->rep_attr.qp_context = ep;
/* send_cq and recv_cq initialized below */
ep->rep_attr.srq = NULL;
ep->rep_attr.cap.max_send_wr = cdata->max_requests;
switch (ia->ri_memreg_strategy) {
case RPCRDMA_FRMR:
/* Add room for frmr register and invalidate WRs */
ep->rep_attr.cap.max_send_wr *= 3;
if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr)
return -EINVAL;
break;
case RPCRDMA_MEMWINDOWS_ASYNC:
case RPCRDMA_MEMWINDOWS:
/* Add room for mw_binds+unbinds - overkill! */
ep->rep_attr.cap.max_send_wr++;
ep->rep_attr.cap.max_send_wr *= (2 * RPCRDMA_MAX_SEGS);
if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr)
return -EINVAL;
break;
default:
break;
}
ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
ep->rep_attr.cap.max_send_sge = (cdata->padding ? 4 : 2);
ep->rep_attr.cap.max_recv_sge = 1;
ep->rep_attr.cap.max_inline_data = 0;
ep->rep_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
ep->rep_attr.qp_type = IB_QPT_RC;
ep->rep_attr.port_num = ~0;
dprintk("RPC: %s: requested max: dtos: send %d recv %d; "
"iovs: send %d recv %d\n",
__func__,
ep->rep_attr.cap.max_send_wr,
ep->rep_attr.cap.max_recv_wr,
ep->rep_attr.cap.max_send_sge,
ep->rep_attr.cap.max_recv_sge);
/* set trigger for requesting send completion */
ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 /* - 1*/;
switch (ia->ri_memreg_strategy) {
case RPCRDMA_MEMWINDOWS_ASYNC:
case RPCRDMA_MEMWINDOWS:
ep->rep_cqinit -= RPCRDMA_MAX_SEGS;
break;
default:
break;
}
if (ep->rep_cqinit <= 2)
ep->rep_cqinit = 0;
INIT_CQCOUNT(ep);
ep->rep_ia = ia;
init_waitqueue_head(&ep->rep_connect_wait);
/*
* Create a single cq for receive dto and mw_bind (only ever
* care about unbind, really). Send completions are suppressed.
* Use single threaded tasklet upcalls to maintain ordering.
*/
ep->rep_cq = ib_create_cq(ia->ri_id->device, rpcrdma_cq_event_upcall,
rpcrdma_cq_async_error_upcall, NULL,
ep->rep_attr.cap.max_recv_wr +
ep->rep_attr.cap.max_send_wr + 1, 0);
if (IS_ERR(ep->rep_cq)) {
rc = PTR_ERR(ep->rep_cq);
dprintk("RPC: %s: ib_create_cq failed: %i\n",
__func__, rc);
goto out1;
}
rc = ib_req_notify_cq(ep->rep_cq, IB_CQ_NEXT_COMP);
if (rc) {
dprintk("RPC: %s: ib_req_notify_cq failed: %i\n",
__func__, rc);
goto out2;
}
ep->rep_attr.send_cq = ep->rep_cq;
ep->rep_attr.recv_cq = ep->rep_cq;
/* Initialize cma parameters */
/* RPC/RDMA does not use private data */
ep->rep_remote_cma.private_data = NULL;
ep->rep_remote_cma.private_data_len = 0;
/* Client offers RDMA Read but does not initiate */
ep->rep_remote_cma.initiator_depth = 0;
if (ia->ri_memreg_strategy == RPCRDMA_BOUNCEBUFFERS)
ep->rep_remote_cma.responder_resources = 0;
else if (devattr.max_qp_rd_atom > 32) /* arbitrary but <= 255 */
ep->rep_remote_cma.responder_resources = 32;
else
ep->rep_remote_cma.responder_resources = devattr.max_qp_rd_atom;
ep->rep_remote_cma.retry_count = 7;
ep->rep_remote_cma.flow_control = 0;
ep->rep_remote_cma.rnr_retry_count = 0;
return 0;
out2:
err = ib_destroy_cq(ep->rep_cq);
if (err)
dprintk("RPC: %s: ib_destroy_cq returned %i\n",
__func__, err);
out1:
return rc;
}
/*
* Create unconnected endpoint.
*/
int
rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
struct rpcrdma_create_data_internal *cdata)
{
struct ib_cq *sendcq, *recvcq;
unsigned int max_qp_wr;
int rc;
if (ia->ri_device->attrs.max_sge < RPCRDMA_MAX_IOVS) {
dprintk("RPC: %s: insufficient sge's available\n",
__func__);
return -ENOMEM;
}
if (ia->ri_device->attrs.max_qp_wr <= RPCRDMA_BACKWARD_WRS) {
dprintk("RPC: %s: insufficient wqe's available\n",
__func__);
return -ENOMEM;
}
max_qp_wr = ia->ri_device->attrs.max_qp_wr - RPCRDMA_BACKWARD_WRS - 1;
/* check provider's send/recv wr limits */
if (cdata->max_requests > max_qp_wr)
cdata->max_requests = max_qp_wr;
ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall;
ep->rep_attr.qp_context = ep;
ep->rep_attr.srq = NULL;
ep->rep_attr.cap.max_send_wr = cdata->max_requests;
ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS;
ep->rep_attr.cap.max_send_wr += 1; /* drain cqe */
rc = ia->ri_ops->ro_open(ia, ep, cdata);
if (rc)
return rc;
ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
ep->rep_attr.cap.max_recv_wr += 1; /* drain cqe */
ep->rep_attr.cap.max_send_sge = RPCRDMA_MAX_IOVS;
ep->rep_attr.cap.max_recv_sge = 1;
ep->rep_attr.cap.max_inline_data = 0;
ep->rep_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
ep->rep_attr.qp_type = IB_QPT_RC;
ep->rep_attr.port_num = ~0;
dprintk("RPC: %s: requested max: dtos: send %d recv %d; "
"iovs: send %d recv %d\n",
__func__,
ep->rep_attr.cap.max_send_wr,
ep->rep_attr.cap.max_recv_wr,
ep->rep_attr.cap.max_send_sge,
ep->rep_attr.cap.max_recv_sge);
/* set trigger for requesting send completion */
ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1;
if (ep->rep_cqinit <= 2)
ep->rep_cqinit = 0; /* always signal? */
INIT_CQCOUNT(ep);
init_waitqueue_head(&ep->rep_connect_wait);
INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker);
sendcq = ib_alloc_cq(ia->ri_device, NULL,
ep->rep_attr.cap.max_send_wr + 1,
0, IB_POLL_SOFTIRQ);
if (IS_ERR(sendcq)) {
rc = PTR_ERR(sendcq);
dprintk("RPC: %s: failed to create send CQ: %i\n",
__func__, rc);
goto out1;
}
recvcq = ib_alloc_cq(ia->ri_device, NULL,
ep->rep_attr.cap.max_recv_wr + 1,
0, IB_POLL_SOFTIRQ);
if (IS_ERR(recvcq)) {
rc = PTR_ERR(recvcq);
dprintk("RPC: %s: failed to create recv CQ: %i\n",
__func__, rc);
goto out2;
}
ep->rep_attr.send_cq = sendcq;
ep->rep_attr.recv_cq = recvcq;
/* Initialize cma parameters */
memset(&ep->rep_remote_cma, 0, sizeof(ep->rep_remote_cma));
/* RPC/RDMA does not use private data */
ep->rep_remote_cma.private_data = NULL;
ep->rep_remote_cma.private_data_len = 0;
/* Client offers RDMA Read but does not initiate */
ep->rep_remote_cma.initiator_depth = 0;
if (ia->ri_device->attrs.max_qp_rd_atom > 32) /* arbitrary but <= 255 */
ep->rep_remote_cma.responder_resources = 32;
else
ep->rep_remote_cma.responder_resources =
ia->ri_device->attrs.max_qp_rd_atom;
/* Limit transport retries so client can detect server
* GID changes quickly. RPC layer handles re-establishing
* transport connection and retransmission.
*/
ep->rep_remote_cma.retry_count = 6;
/* RPC-over-RDMA handles its own flow control. In addition,
* make all RNR NAKs visible so we know that RPC-over-RDMA
* flow control is working correctly (no NAKs should be seen).
*/
ep->rep_remote_cma.flow_control = 0;
ep->rep_remote_cma.rnr_retry_count = 0;
return 0;
out2:
ib_free_cq(sendcq);
out1:
return rc;
}
/*
* Create unconnected endpoint.
*/
int
rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
struct rpcrdma_create_data_internal *cdata)
{
struct ib_device_attr *devattr = &ia->ri_devattr;
struct ib_cq *sendcq, *recvcq;
struct ib_cq_init_attr cq_attr = {};
unsigned int max_qp_wr;
int rc, err;
if (devattr->max_sge < RPCRDMA_MAX_IOVS) {
dprintk("RPC: %s: insufficient sge's available\n",
__func__);
return -ENOMEM;
}
if (devattr->max_qp_wr <= RPCRDMA_BACKWARD_WRS) {
dprintk("RPC: %s: insufficient wqe's available\n",
__func__);
return -ENOMEM;
}
max_qp_wr = devattr->max_qp_wr - RPCRDMA_BACKWARD_WRS;
/* check provider's send/recv wr limits */
if (cdata->max_requests > max_qp_wr)
cdata->max_requests = max_qp_wr;
ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall;
ep->rep_attr.qp_context = ep;
ep->rep_attr.srq = NULL;
ep->rep_attr.cap.max_send_wr = cdata->max_requests;
ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS;
rc = ia->ri_ops->ro_open(ia, ep, cdata);
if (rc)
return rc;
ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
ep->rep_attr.cap.max_send_sge = RPCRDMA_MAX_IOVS;
ep->rep_attr.cap.max_recv_sge = 1;
ep->rep_attr.cap.max_inline_data = 0;
ep->rep_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
ep->rep_attr.qp_type = IB_QPT_RC;
ep->rep_attr.port_num = ~0;
dprintk("RPC: %s: requested max: dtos: send %d recv %d; "
"iovs: send %d recv %d\n",
__func__,
ep->rep_attr.cap.max_send_wr,
ep->rep_attr.cap.max_recv_wr,
ep->rep_attr.cap.max_send_sge,
ep->rep_attr.cap.max_recv_sge);
/* set trigger for requesting send completion */
ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1;
if (ep->rep_cqinit <= 2)
ep->rep_cqinit = 0; /* always signal? */
INIT_CQCOUNT(ep);
init_waitqueue_head(&ep->rep_connect_wait);
INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker);
cq_attr.cqe = ep->rep_attr.cap.max_send_wr + 1;
sendcq = ib_create_cq(ia->ri_device, rpcrdma_sendcq_upcall,
rpcrdma_cq_async_error_upcall, NULL, &cq_attr);
if (IS_ERR(sendcq)) {
rc = PTR_ERR(sendcq);
dprintk("RPC: %s: failed to create send CQ: %i\n",
__func__, rc);
goto out1;
}
rc = ib_req_notify_cq(sendcq, IB_CQ_NEXT_COMP);
if (rc) {
dprintk("RPC: %s: ib_req_notify_cq failed: %i\n",
__func__, rc);
goto out2;
}
cq_attr.cqe = ep->rep_attr.cap.max_recv_wr + 1;
recvcq = ib_create_cq(ia->ri_device, rpcrdma_recvcq_upcall,
rpcrdma_cq_async_error_upcall, NULL, &cq_attr);
if (IS_ERR(recvcq)) {
rc = PTR_ERR(recvcq);
dprintk("RPC: %s: failed to create recv CQ: %i\n",
__func__, rc);
goto out2;
}
rc = ib_req_notify_cq(recvcq, IB_CQ_NEXT_COMP);
if (rc) {
dprintk("RPC: %s: ib_req_notify_cq failed: %i\n",
__func__, rc);
ib_destroy_cq(recvcq);
goto out2;
}
ep->rep_attr.send_cq = sendcq;
ep->rep_attr.recv_cq = recvcq;
/* Initialize cma parameters */
/* RPC/RDMA does not use private data */
ep->rep_remote_cma.private_data = NULL;
ep->rep_remote_cma.private_data_len = 0;
/* Client offers RDMA Read but does not initiate */
ep->rep_remote_cma.initiator_depth = 0;
if (devattr->max_qp_rd_atom > 32) /* arbitrary but <= 255 */
ep->rep_remote_cma.responder_resources = 32;
else
ep->rep_remote_cma.responder_resources =
devattr->max_qp_rd_atom;
ep->rep_remote_cma.retry_count = 7;
ep->rep_remote_cma.flow_control = 0;
ep->rep_remote_cma.rnr_retry_count = 0;
return 0;
out2:
err = ib_destroy_cq(sendcq);
if (err)
dprintk("RPC: %s: ib_destroy_cq returned %i\n",
__func__, err);
out1:
if (ia->ri_dma_mr)
ib_dereg_mr(ia->ri_dma_mr);
return rc;
}
