From: Jack Wang <jinpu.w...@cloud.ionos.com>
[ Upstream commit f47e4e3e71724f625958b0059f6c8ac5d44d27ef ]
Currently rtrs when create_qp use a coarse numbers (bigger in general),
which leads to hardware create more resources which only waste memory
with no benefits.
- SERVICE con,
For max_send_wr/max_recv_wr, it's 2 times SERVICE_CON_QUEUE_DEPTH + 2
- IO con
For max_send_wr/max_recv_wr, it's sess->queue_depth * 3 + 1
Fixes: 6a98d71daea1 ("RDMA/rtrs: client: main functionality")
Link:
https://lore.kernel.org/r/20201217141915.56989-6-jinpu.w...@cloud.ionos.com
Signed-off-by: Jack Wang <jinpu.w...@cloud.ionos.com>
Reviewed-by: Md Haris Iqbal <haris.iq...@cloud.ionos.com>
Signed-off-by: Jason Gunthorpe <j...@nvidia.com>
Signed-off-by: Sasha Levin <sas...@kernel.org>
---
drivers/infiniband/ulp/rtrs/rtrs-clt.c | 19 ++++++++++++-------
1 file changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 719254fc83a1c..b3fb5fb93815f 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -1511,7 +1511,7 @@ static void destroy_con(struct rtrs_clt_con *con)
static int create_con_cq_qp(struct rtrs_clt_con *con)
{
struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
- u32 wr_queue_size;
+ u32 max_send_wr, max_recv_wr, cq_size;
int err, cq_vector;
struct rtrs_msg_rkey_rsp *rsp;
@@ -1523,7 +1523,8 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
* + 2 for drain and heartbeat
* in case qp gets into error state
*/
- wr_queue_size = SERVICE_CON_QUEUE_DEPTH * 3 + 2;
+ max_send_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
+ max_recv_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
/* We must be the first here */
if (WARN_ON(sess->s.dev))
return -EINVAL;
@@ -1555,25 +1556,29 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
/* Shared between connections */
sess->s.dev_ref++;
- wr_queue_size =
+ max_send_wr =
min_t(int, sess->s.dev->ib_dev->attrs.max_qp_wr,
/* QD * (REQ + RSP + FR REGS or INVS) + drain */
sess->queue_depth * 3 + 1);
+ max_recv_wr =
+ min_t(int, sess->s.dev->ib_dev->attrs.max_qp_wr,
+ sess->queue_depth * 3 + 1);
}
/* alloc iu to recv new rkey reply when server reports flags set */
if (sess->flags == RTRS_MSG_NEW_RKEY_F || con->c.cid == 0) {
- con->rsp_ius = rtrs_iu_alloc(wr_queue_size, sizeof(*rsp),
+ con->rsp_ius = rtrs_iu_alloc(max_recv_wr, sizeof(*rsp),
GFP_KERNEL, sess->s.dev->ib_dev,
DMA_FROM_DEVICE,
rtrs_clt_rdma_done);
if (!con->rsp_ius)
return -ENOMEM;
- con->queue_size = wr_queue_size;
+ con->queue_size = max_recv_wr;
}
+ cq_size = max_send_wr + max_recv_wr;
cq_vector = con->cpu % sess->s.dev->ib_dev->num_comp_vectors;
err = rtrs_cq_qp_create(&sess->s, &con->c, sess->max_send_sge,
- cq_vector, wr_queue_size, wr_queue_size,
- wr_queue_size, IB_POLL_SOFTIRQ);
+ cq_vector, cq_size, max_send_wr,
+ max_recv_wr, IB_POLL_SOFTIRQ);
/*
* In case of error we do not bother to clean previous allocations,
* since destroy_con_cq_qp() must be called.
--
2.27.0
