@@ -96,6 +96,8 @@ struct bnxt_re_wrid {
uint64_t wrid;
uint32_t bytes;
int next_idx;
+ uint32_t st_slot_idx;
+ uint8_t slots;
uint8_t sig;
};
@@ -847,9 +847,27 @@ static void bnxt_re_free_queues(struct bnxt_re_qp *qp)
bnxt_re_free_aligned(qp->jsqq->hwque);
}
+static int bnxt_re_alloc_init_swque(struct bnxt_re_joint_queue *jqq, int nwr)
+{
+ int indx;
+
+ jqq->swque = calloc(nwr, sizeof(struct bnxt_re_wrid));
+ if (!jqq->swque)
+ return -ENOMEM;
+ jqq->start_idx = 0;
+ jqq->last_idx = nwr - 1;
+ for (indx = 0; indx < nwr; indx++)
+ jqq->swque[indx].next_idx = indx + 1;
+ jqq->swque[jqq->last_idx].next_idx = 0;
+ jqq->last_idx = 0;
+
+ return 0;
+}
+
static int bnxt_re_alloc_queues(struct bnxt_re_qp *qp,
struct ibv_qp_init_attr *attr,
- uint32_t pg_size) {
+ uint32_t pg_size)
+{
struct bnxt_re_psns_ext *psns_ext;
struct bnxt_re_wrid *swque;
struct bnxt_re_queue *que;
@@ -857,22 +875,23 @@ static int bnxt_re_alloc_queues(struct bnxt_re_qp *qp,
uint32_t psn_depth;
uint32_t psn_size;
int ret, indx;
+ uint32_t nswr;
que = qp->jsqq->hwque;
que->stride = bnxt_re_get_sqe_sz();
/* 8916 adjustment */
- que->depth = roundup_pow_of_two(attr->cap.max_send_wr + 1 +
- BNXT_RE_FULL_FLAG_DELTA);
- que->diff = que->depth - attr->cap.max_send_wr;
+ nswr = roundup_pow_of_two(attr->cap.max_send_wr + 1 +
+ BNXT_RE_FULL_FLAG_DELTA);
+ que->diff = nswr - attr->cap.max_send_wr;
/* psn_depth extra entries of size que->stride */
psn_size = bnxt_re_is_chip_gen_p5(qp->cctx) ?
sizeof(struct bnxt_re_psns_ext) :
sizeof(struct bnxt_re_psns);
- psn_depth = (que->depth * psn_size) / que->stride;
- if ((que->depth * psn_size) % que->stride)
+ psn_depth = (nswr * psn_size) / que->stride;
+ if ((nswr * psn_size) % que->stride)
psn_depth++;
- que->depth += psn_depth;
+ que->depth = nswr + psn_depth;
/* PSN-search memory is allocated without checking for
* QP-Type. Kenrel driver do not map this memory if it
* is UD-qp. UD-qp use this memory to maintain WC-opcode.
@@ -884,44 +903,42 @@ static int bnxt_re_alloc_queues(struct bnxt_re_qp *qp,
/* exclude psns depth*/
que->depth -= psn_depth;
/* start of spsn space sizeof(struct bnxt_re_psns) each. */
- psns = (que->va + que->stride * que->depth);
+ psns = (que->va + que->stride * nswr);
psns_ext = (struct bnxt_re_psns_ext *)psns;
- swque = calloc(que->depth, sizeof(struct bnxt_re_wrid));
- if (!swque) {
+
+ ret = bnxt_re_alloc_init_swque(qp->jsqq, nswr);
+ if (ret) {
ret = -ENOMEM;
goto fail;
}
- for (indx = 0 ; indx < que->depth; indx++, psns++)
+ swque = qp->jsqq->swque;
+ for (indx = 0; indx < nswr; indx++, psns++)
swque[indx].psns = psns;
if (bnxt_re_is_chip_gen_p5(qp->cctx)) {
- for (indx = 0 ; indx < que->depth; indx++, psns_ext++) {
+ for (indx = 0; indx < nswr; indx++, psns_ext++) {
swque[indx].psns_ext = psns_ext;
swque[indx].psns = (struct bnxt_re_psns *)psns_ext;
}
}
- qp->jsqq->swque = swque;
-
- qp->cap.max_swr = que->depth;
+ qp->cap.max_swr = nswr;
pthread_spin_init(&que->qlock, PTHREAD_PROCESS_PRIVATE);
if (qp->jrqq) {
que = qp->jrqq->hwque;
que->stride = bnxt_re_get_rqe_sz();
- que->depth = roundup_pow_of_two(attr->cap.max_recv_wr + 1);
- que->diff = que->depth - attr->cap.max_recv_wr;
+ nswr = roundup_pow_of_two(attr->cap.max_recv_wr + 1);
+ que->depth = nswr;
+ que->diff = nswr - attr->cap.max_recv_wr;
ret = bnxt_re_alloc_aligned(que, pg_size);
if (ret)
goto fail;
- pthread_spin_init(&que->qlock, PTHREAD_PROCESS_PRIVATE);
/* For RQ only bnxt_re_wri.wrid is used. */
- qp->jrqq->swque = calloc(que->depth,
- sizeof(struct bnxt_re_wrid));
- if (!qp->jrqq->swque) {
- ret = -ENOMEM;
+ ret = bnxt_re_alloc_init_swque(qp->jrqq, nswr);
+ if (ret)
goto fail;
- }
- qp->cap.max_rwr = que->depth;
+ pthread_spin_init(&que->qlock, PTHREAD_PROCESS_PRIVATE);
+ qp->cap.max_rwr = nswr;
}
return 0;
Splitting the shadow software queue initialization into a separate function. Same is being called for both RQ and SQ during create QP. Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com> --- providers/bnxt_re/main.h | 2 ++ providers/bnxt_re/verbs.c | 65 ++++++++++++++++++++++++--------------- 2 files changed, 43 insertions(+), 24 deletions(-)