/**
* rvt_dealloc_pd - Free PD
* @ibpd: Free up PD
*
* Return: always 0
*/
int rvt_dealloc_pd(struct ib_pd *ibpd)
{
struct rvt_pd *pd = ibpd_to_rvtpd(ibpd);
struct rvt_dev_info *dev = ib_to_rvt(ibpd->device);
spin_lock(&dev->n_pds_lock);
dev->n_pds_allocated--;
spin_unlock(&dev->n_pds_lock);
kfree(pd);
return 0;
}
/*
* Validate a RWQE and fill in the SGE state.
* Return 1 if OK.
*/
static int qib_init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe)
{
int i, j, ret;
struct ib_wc wc;
struct rvt_lkey_table *rkt;
struct rvt_pd *pd;
struct rvt_sge_state *ss;
rkt = &to_idev(qp->ibqp.device)->rdi.lkey_table;
pd = ibpd_to_rvtpd(qp->ibqp.srq ? qp->ibqp.srq->pd : qp->ibqp.pd);
ss = &qp->r_sge;
ss->sg_list = qp->r_sg_list;
qp->r_len = 0;
for (i = j = 0; i < wqe->num_sge; i++) {
if (wqe->sg_list[i].length == 0)
continue;
/* Check LKEY */
ret = rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
NULL, &wqe->sg_list[i],
IB_ACCESS_LOCAL_WRITE);
if (unlikely(ret <= 0))
goto bad_lkey;
qp->r_len += wqe->sg_list[i].length;
j++;
}
ss->num_sge = j;
ss->total_len = qp->r_len;
ret = 1;
goto bail;
bad_lkey:
while (j) {
struct rvt_sge *sge = --j ? &ss->sg_list[j - 1] : &ss->sge;
rvt_put_mr(sge->mr);
}
ss->num_sge = 0;
memset(&wc, 0, sizeof(wc));
wc.wr_id = wqe->wr_id;
wc.status = IB_WC_LOC_PROT_ERR;
wc.opcode = IB_WC_RECV;
wc.qp = &qp->ibqp;
/* Signal solicited completion event. */
rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.recv_cq), &wc, 1);
ret = 0;
bail:
return ret;
}
/**
* rvt_post_one_wr - post one RC, UC, or UD send work request
* @qp: the QP to post on
* @wr: the work request to send
*/
static int rvt_post_one_wr(struct rvt_qp *qp,
struct ib_send_wr *wr,
int *call_send)
{
struct rvt_swqe *wqe;
u32 next;
int i;
int j;
int acc;
struct rvt_lkey_table *rkt;
struct rvt_pd *pd;
struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
u8 log_pmtu;
int ret;
/* IB spec says that num_sge == 0 is OK. */
if (unlikely(wr->num_sge > qp->s_max_sge))
return -EINVAL;
/*
* Don't allow RDMA reads or atomic operations on UC or
* undefined operations.
* Make sure buffer is large enough to hold the result for atomics.
*/
if (qp->ibqp.qp_type == IB_QPT_UC) {
if ((unsigned)wr->opcode >= IB_WR_RDMA_READ)
return -EINVAL;
} else if (qp->ibqp.qp_type != IB_QPT_RC) {
/* Check IB_QPT_SMI, IB_QPT_GSI, IB_QPT_UD opcode */
if (wr->opcode != IB_WR_SEND &&
wr->opcode != IB_WR_SEND_WITH_IMM)
return -EINVAL;
/* Check UD destination address PD */
if (qp->ibqp.pd != ud_wr(wr)->ah->pd)
return -EINVAL;
} else if ((unsigned)wr->opcode > IB_WR_ATOMIC_FETCH_AND_ADD) {
return -EINVAL;
} else if (wr->opcode >= IB_WR_ATOMIC_CMP_AND_SWP &&
(wr->num_sge == 0 ||
wr->sg_list[0].length < sizeof(u64) ||
wr->sg_list[0].addr & (sizeof(u64) - 1))) {
return -EINVAL;
} else if (wr->opcode >= IB_WR_RDMA_READ && !qp->s_max_rd_atomic) {
return -EINVAL;
}
/* check for avail */
if (unlikely(!qp->s_avail)) {
qp->s_avail = qp_get_savail(qp);
if (WARN_ON(qp->s_avail > (qp->s_size - 1)))
rvt_pr_err(rdi,
"More avail entries than QP RB size.\nQP: %u, size: %u, avail: %u\nhead: %u, tail: %u, cur: %u, acked: %u, last: %u",
qp->ibqp.qp_num, qp->s_size, qp->s_avail,
qp->s_head, qp->s_tail, qp->s_cur,
qp->s_acked, qp->s_last);
if (!qp->s_avail)
return -ENOMEM;
}
next = qp->s_head + 1;
if (next >= qp->s_size)
next = 0;
rkt = &rdi->lkey_table;
pd = ibpd_to_rvtpd(qp->ibqp.pd);
wqe = rvt_get_swqe_ptr(qp, qp->s_head);
if (qp->ibqp.qp_type != IB_QPT_UC &&
qp->ibqp.qp_type != IB_QPT_RC)
memcpy(&wqe->ud_wr, ud_wr(wr), sizeof(wqe->ud_wr));
else if (wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM ||
wr->opcode == IB_WR_RDMA_WRITE ||
wr->opcode == IB_WR_RDMA_READ)
memcpy(&wqe->rdma_wr, rdma_wr(wr), sizeof(wqe->rdma_wr));
else if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP ||
wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD)
memcpy(&wqe->atomic_wr, atomic_wr(wr), sizeof(wqe->atomic_wr));
else
memcpy(&wqe->wr, wr, sizeof(wqe->wr));
wqe->length = 0;
j = 0;
if (wr->num_sge) {
acc = wr->opcode >= IB_WR_RDMA_READ ?
IB_ACCESS_LOCAL_WRITE : 0;
for (i = 0; i < wr->num_sge; i++) {
u32 length = wr->sg_list[i].length;
int ok;
if (length == 0)
continue;
ok = rvt_lkey_ok(rkt, pd, &wqe->sg_list[j],
&wr->sg_list[i], acc);
if (!ok) {
ret = -EINVAL;
goto bail_inval_free;
}
wqe->length += length;
j++;
}
wqe->wr.num_sge = j;
}
/* general part of wqe valid - allow for driver checks */
if (rdi->driver_f.check_send_wqe) {
ret = rdi->driver_f.check_send_wqe(qp, wqe);
if (ret < 0)
goto bail_inval_free;
if (ret)
*call_send = ret;
}
log_pmtu = qp->log_pmtu;
if (qp->ibqp.qp_type != IB_QPT_UC &&
qp->ibqp.qp_type != IB_QPT_RC) {
struct rvt_ah *ah = ibah_to_rvtah(wqe->ud_wr.ah);
log_pmtu = ah->log_pmtu;
atomic_inc(&ibah_to_rvtah(ud_wr(wr)->ah)->refcount);
}
wqe->ssn = qp->s_ssn++;
wqe->psn = qp->s_next_psn;
wqe->lpsn = wqe->psn +
(wqe->length ? ((wqe->length - 1) >> log_pmtu) : 0);
qp->s_next_psn = wqe->lpsn + 1;
trace_rvt_post_one_wr(qp, wqe);
smp_wmb(); /* see request builders */
qp->s_avail--;
qp->s_head = next;
return 0;
bail_inval_free:
/* release mr holds */
while (j) {
struct rvt_sge *sge = &wqe->sg_list[--j];
rvt_put_mr(sge->mr);
}
return ret;
}
/**
* qib_rkey_ok - check the IB virtual address, length, and RKEY
* @qp: qp for validation
* @sge: SGE state
* @len: length of data
* @vaddr: virtual address to place data
* @rkey: rkey to check
* @acc: access flags
*
* Return 1 if successful, otherwise 0.
*
* increments the reference count upon success
*/
int qib_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
u32 len, u64 vaddr, u32 rkey, int acc)
{
struct rvt_lkey_table *rkt = &to_idev(qp->ibqp.device)->lk_table;
struct rvt_mregion *mr;
unsigned n, m;
size_t off;
/*
* We use RKEY == zero for kernel virtual addresses
* (see qib_get_dma_mr and qib_dma.c).
*/
rcu_read_lock();
if (rkey == 0) {
struct rvt_pd *pd = ibpd_to_rvtpd(qp->ibqp.pd);
struct qib_ibdev *dev = to_idev(pd->ibpd.device);
if (pd->user)
goto bail;
mr = rcu_dereference(dev->dma_mr);
if (!mr)
goto bail;
if (unlikely(!atomic_inc_not_zero(&mr->refcount)))
goto bail;
rcu_read_unlock();
sge->mr = mr;
sge->vaddr = (void *) vaddr;
sge->length = len;
sge->sge_length = len;
sge->m = 0;
sge->n = 0;
goto ok;
}
mr = rcu_dereference(
rkt->table[(rkey >> (32 - ib_rvt_lkey_table_size))]);
if (unlikely(!mr || mr->lkey != rkey || qp->ibqp.pd != mr->pd))
goto bail;
off = vaddr - mr->iova;
if (unlikely(vaddr < mr->iova || off + len > mr->length ||
(mr->access_flags & acc) == 0))
goto bail;
if (unlikely(!atomic_inc_not_zero(&mr->refcount)))
goto bail;
rcu_read_unlock();
off += mr->offset;
if (mr->page_shift) {
/*
page sizes are uniform power of 2 so no loop is necessary
entries_spanned_by_off is the number of times the loop below
would have executed.
*/
size_t entries_spanned_by_off;
entries_spanned_by_off = off >> mr->page_shift;
off -= (entries_spanned_by_off << mr->page_shift);
m = entries_spanned_by_off / RVT_SEGSZ;
n = entries_spanned_by_off % RVT_SEGSZ;
} else {
