*/
#include "ipath_verbs.h"
-#include "ipath_common.h"
+#include "ipath_kernel.h"
/*
* Convert the AETH RNR timeout code into the number of milliseconds.
spin_unlock_irqrestore(&dev->pending_lock, flags);
}
+static int init_sge(struct ipath_qp *qp, struct ipath_rwqe *wqe)
+{
+ int user = to_ipd(qp->ibqp.pd)->user;
+ int i, j, ret;
+ struct ib_wc wc;
+
+ qp->r_len = 0;
+ for (i = j = 0; i < wqe->num_sge; i++) {
+ if (wqe->sg_list[i].length == 0)
+ continue;
+ /* Check LKEY */
+ if ((user && wqe->sg_list[i].lkey == 0) ||
+ !ipath_lkey_ok(qp, &qp->r_sg_list[j], &wqe->sg_list[i],
+ IB_ACCESS_LOCAL_WRITE))
+ goto bad_lkey;
+ qp->r_len += wqe->sg_list[i].length;
+ j++;
+ }
+ qp->r_sge.sge = qp->r_sg_list[0];
+ qp->r_sge.sg_list = qp->r_sg_list + 1;
+ qp->r_sge.num_sge = j;
+ ret = 1;
+ goto bail;
+
+bad_lkey:
+ wc.wr_id = wqe->wr_id;
+ wc.status = IB_WC_LOC_PROT_ERR;
+ wc.opcode = IB_WC_RECV;
+ wc.vendor_err = 0;
+ wc.byte_len = 0;
+ wc.imm_data = 0;
+ wc.qp_num = qp->ibqp.qp_num;
+ wc.src_qp = 0;
+ wc.wc_flags = 0;
+ wc.pkey_index = 0;
+ wc.slid = 0;
+ wc.sl = 0;
+ wc.dlid_path_bits = 0;
+ wc.port_num = 0;
+ /* Signal solicited completion event. */
+ ipath_cq_enter(to_icq(qp->ibqp.recv_cq), &wc, 1);
+ ret = 0;
+bail:
+ return ret;
+}
+
/**
* ipath_get_rwqe - copy the next RWQE into the QP's RWQE
* @qp: the QP
{
unsigned long flags;
struct ipath_rq *rq;
+ struct ipath_rwq *wq;
struct ipath_srq *srq;
struct ipath_rwqe *wqe;
- int ret = 1;
+ void (*handler)(struct ib_event *, void *);
+ u32 tail;
+ int ret;
- if (!qp->ibqp.srq) {
+ if (qp->ibqp.srq) {
+ srq = to_isrq(qp->ibqp.srq);
+ handler = srq->ibsrq.event_handler;
+ rq = &srq->rq;
+ } else {
+ srq = NULL;
+ handler = NULL;
rq = &qp->r_rq;
- spin_lock_irqsave(&rq->lock, flags);
-
- if (unlikely(rq->tail == rq->head)) {
- ret = 0;
- goto done;
- }
- wqe = get_rwqe_ptr(rq, rq->tail);
- qp->r_wr_id = wqe->wr_id;
- if (!wr_id_only) {
- qp->r_sge.sge = wqe->sg_list[0];
- qp->r_sge.sg_list = wqe->sg_list + 1;
- qp->r_sge.num_sge = wqe->num_sge;
- qp->r_len = wqe->length;
- }
- if (++rq->tail >= rq->size)
- rq->tail = 0;
- goto done;
}
- srq = to_isrq(qp->ibqp.srq);
- rq = &srq->rq;
spin_lock_irqsave(&rq->lock, flags);
-
- if (unlikely(rq->tail == rq->head)) {
- ret = 0;
- goto done;
- }
- wqe = get_rwqe_ptr(rq, rq->tail);
+ wq = rq->wq;
+ tail = wq->tail;
+ /* Validate tail before using it since it is user writable. */
+ if (tail >= rq->size)
+ tail = 0;
+ do {
+ if (unlikely(tail == wq->head)) {
+ spin_unlock_irqrestore(&rq->lock, flags);
+ ret = 0;
+ goto bail;
+ }
+ wqe = get_rwqe_ptr(rq, tail);
+ if (++tail >= rq->size)
+ tail = 0;
+ } while (!wr_id_only && !init_sge(qp, wqe));
qp->r_wr_id = wqe->wr_id;
- if (!wr_id_only) {
- qp->r_sge.sge = wqe->sg_list[0];
- qp->r_sge.sg_list = wqe->sg_list + 1;
- qp->r_sge.num_sge = wqe->num_sge;
- qp->r_len = wqe->length;
- }
- if (++rq->tail >= rq->size)
- rq->tail = 0;
- if (srq->ibsrq.event_handler) {
- struct ib_event ev;
+ wq->tail = tail;
+
+ ret = 1;
+ if (handler) {
u32 n;
- if (rq->head < rq->tail)
- n = rq->size + rq->head - rq->tail;
+ /*
+ * validate head pointer value and compute
+ * the number of remaining WQEs.
+ */
+ n = wq->head;
+ if (n >= rq->size)
+ n = 0;
+ if (n < tail)
+ n += rq->size - tail;
else
- n = rq->head - rq->tail;
+ n -= tail;
if (n < srq->limit) {
+ struct ib_event ev;
+
srq->limit = 0;
spin_unlock_irqrestore(&rq->lock, flags);
ev.device = qp->ibqp.device;
ev.element.srq = qp->ibqp.srq;
ev.event = IB_EVENT_SRQ_LIMIT_REACHED;
- srq->ibsrq.event_handler(&ev,
- srq->ibsrq.srq_context);
+ handler(&ev, srq->ibsrq.srq_context);
goto bail;
}
}
-
-done:
spin_unlock_irqrestore(&rq->lock, flags);
+ qp->r_wrid_valid = 1;
+
bail:
return ret;
}
case IB_WR_RDMA_WRITE:
if (wqe->length == 0)
break;
- if (unlikely(!ipath_rkey_ok(dev, &qp->r_sge, wqe->length,
+ if (unlikely(!ipath_rkey_ok(qp, &qp->r_sge, wqe->length,
wqe->wr.wr.rdma.remote_addr,
wqe->wr.wr.rdma.rkey,
IB_ACCESS_REMOTE_WRITE))) {
break;
case IB_WR_RDMA_READ:
- if (unlikely(!ipath_rkey_ok(dev, &sqp->s_sge, wqe->length,
+ if (unlikely(!ipath_rkey_ok(qp, &sqp->s_sge, wqe->length,
wqe->wr.wr.rdma.remote_addr,
wqe->wr.wr.rdma.rkey,
IB_ACCESS_REMOTE_READ)))
case IB_WR_ATOMIC_CMP_AND_SWP:
case IB_WR_ATOMIC_FETCH_AND_ADD:
- if (unlikely(!ipath_rkey_ok(dev, &qp->r_sge, sizeof(u64),
+ if (unlikely(!ipath_rkey_ok(qp, &qp->r_sge, sizeof(u64),
wqe->wr.wr.rdma.remote_addr,
wqe->wr.wr.rdma.rkey,
IB_ACCESS_REMOTE_ATOMIC)))
wake_up(&qp->wait);
}
+static int want_buffer(struct ipath_devdata *dd)
+{
+ set_bit(IPATH_S_PIOINTBUFAVAIL, &dd->ipath_sendctrl);
+ ipath_write_kreg(dd, dd->ipath_kregs->kr_sendctrl,
+ dd->ipath_sendctrl);
+
+ return 0;
+}
+
/**
* ipath_no_bufs_available - tell the layer driver we need buffers
* @qp: the QP that caused the problem
list_add_tail(&qp->piowait, &dev->piowait);
spin_unlock_irqrestore(&dev->pending_lock, flags);
/*
- * Note that as soon as ipath_layer_want_buffer() is called and
+ * Note that as soon as want_buffer() is called and
* possibly before it returns, ipath_ib_piobufavail()
* could be called. If we are still in the tasklet function,
* tasklet_hi_schedule() will not call us until the next time
*/
clear_bit(IPATH_S_BUSY, &qp->s_flags);
tasklet_unlock(&qp->s_task);
- ipath_layer_want_buffer(dev->dd);
+ want_buffer(dev->dd);
dev->n_piowait++;
}
}
if (wr->sg_list[i].length == 0)
continue;
- if (!ipath_lkey_ok(&to_idev(qp->ibqp.device)->lk_table,
- &wqe->sg_list[j], &wr->sg_list[i],
+ if (!ipath_lkey_ok(qp, &wqe->sg_list[j], &wr->sg_list[i],
acc)) {
spin_unlock_irqrestore(&qp->s_lock, flags);
ret = -EINVAL;
hdr->hop_limit = grh->hop_limit;
/* The SGID is 32-bit aligned. */
hdr->sgid.global.subnet_prefix = dev->gid_prefix;
- hdr->sgid.global.interface_id = ipath_layer_get_guid(dev->dd);
+ hdr->sgid.global.interface_id = dev->dd->ipath_guid;
hdr->dgid = grh->dgid;
/* GRH header size in 32-bit words. */
if (test_and_set_bit(IPATH_S_BUSY, &qp->s_flags))
goto bail;
- if (unlikely(qp->remote_ah_attr.dlid ==
- ipath_layer_get_lid(dev->dd))) {
+ if (unlikely(qp->remote_ah_attr.dlid == dev->dd->ipath_lid)) {
ipath_ruc_loopback(qp);
goto clear;
}
qp->s_hdr.lrh[1] = cpu_to_be16(qp->remote_ah_attr.dlid);
qp->s_hdr.lrh[2] = cpu_to_be16(qp->s_hdrwords + nwords +
SIZE_OF_CRC);
- qp->s_hdr.lrh[3] = cpu_to_be16(ipath_layer_get_lid(dev->dd));
- bth0 |= ipath_layer_get_pkey(dev->dd, qp->s_pkey_index);
+ qp->s_hdr.lrh[3] = cpu_to_be16(dev->dd->ipath_lid);
+ bth0 |= ipath_get_pkey(dev->dd, qp->s_pkey_index);
bth0 |= extra_bytes << 20;
ohdr->bth[0] = cpu_to_be32(bth0);
ohdr->bth[1] = cpu_to_be32(qp->remote_qpn);
git://git.onelab.eu / linux-2.6.git / blobdiff