From: oulijun <oulijun-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
To: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org,
jgg-uk2M96/98Pc@public.gmane.org,
linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH for-next 2/6] RDMA/hns: Update the usage of sr_max and rr_max field
Date: Mon, 25 Dec 2017 18:14:26 +0800 [thread overview]
Message-ID: <bfcfca0e-d8c3-034d-e973-c7fab6cd4f0f@huawei.com> (raw)
In-Reply-To: <20171225094112.GA2942-U/DQcQFIOTAAJjI8aNfphQ@public.gmane.org>
在 2017/12/25 17:41, Leon Romanovsky 写道:
> On Sat, Dec 23, 2017 at 04:22:18PM +0800, Lijun Ou wrote:
>> This patch fixes the usage with sr_max filed and rr_max of qp
>> context when modify qp. Its modifications include:
>> 1. Adjust location of filling sr_max filed of qpc
>> 2. Only assign the number of responder resource if
>> IB_QP_MAX_DEST_RD_ATOMIC bit is set
>> 3. Only assign the number of outstanding resource if
>> IB_QP_MAX_QP_RD_ATOMIC
>> 4. Fix the assgin algorithms for the field of sr_max
>> and rr_max of qp context
>>
>> Signed-off-by: Lijun Ou <oulijun-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
>> ---
>> drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 33 ++++++++++++++++++++----------
>> 1 file changed, 22 insertions(+), 11 deletions(-)
>>
>> diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
>> index b17dcfa..092f133 100644
>> --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
>> +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
>> @@ -2531,11 +2531,17 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
>> roce_set_bit(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_LBI_S, 0);
>> }
>>
>> - roce_set_field(context->byte_140_raq, V2_QPC_BYTE_140_RR_MAX_M,
>> - V2_QPC_BYTE_140_RR_MAX_S,
>> - ilog2((unsigned int)attr->max_dest_rd_atomic));
>> - roce_set_field(qpc_mask->byte_140_raq, V2_QPC_BYTE_140_RR_MAX_M,
>> - V2_QPC_BYTE_140_RR_MAX_S, 0);
>> + if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) {
>> + if (attr->max_dest_rd_atomic) {
>
> if ((attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) && attr->max_dest_rd_atomic) {
>
Good advice, thanks. I will fix it.
>
>
>> + roce_set_field(context->byte_140_raq,
>> + V2_QPC_BYTE_140_RR_MAX_M,
>> + V2_QPC_BYTE_140_RR_MAX_S,
>> + fls(attr->max_dest_rd_atomic - 1));
>> + roce_set_field(qpc_mask->byte_140_raq,
>> + V2_QPC_BYTE_140_RR_MAX_M,
>> + V2_QPC_BYTE_140_RR_MAX_S, 0);
>> + }
>> + }
>>
>> roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
>> V2_QPC_BYTE_56_DQPN_S, attr->dest_qp_num);
>> @@ -2625,12 +2631,6 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
>> V2_QPC_BYTE_168_LP_SGEN_INI_M,
>> V2_QPC_BYTE_168_LP_SGEN_INI_S, 0);
>>
>> - roce_set_field(context->byte_208_irrl, V2_QPC_BYTE_208_SR_MAX_M,
>> - V2_QPC_BYTE_208_SR_MAX_S,
>> - ilog2((unsigned int)attr->max_rd_atomic));
>> - roce_set_field(qpc_mask->byte_208_irrl, V2_QPC_BYTE_208_SR_MAX_M,
>> - V2_QPC_BYTE_208_SR_MAX_S, 0);
>> -
>> roce_set_field(context->byte_28_at_fl, V2_QPC_BYTE_28_SL_M,
>> V2_QPC_BYTE_28_SL_S, rdma_ah_get_sl(&attr->ah_attr));
>> roce_set_field(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_SL_M,
>> @@ -2834,6 +2834,17 @@ static int modify_qp_rtr_to_rts(struct ib_qp *ibqp,
>> roce_set_field(qpc_mask->byte_196_sq_psn, V2_QPC_BYTE_196_SQ_MAX_PSN_M,
>> V2_QPC_BYTE_196_SQ_MAX_PSN_S, 0);
>>
>> + if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC) {
>> + if (attr->max_rd_atomic) {
>> + roce_set_field(context->byte_208_irrl,
>> + V2_QPC_BYTE_208_SR_MAX_M,
>> + V2_QPC_BYTE_208_SR_MAX_S,
>> + fls(attr->max_rd_atomic - 1));
>> + roce_set_field(qpc_mask->byte_208_irrl,
>> + V2_QPC_BYTE_208_SR_MAX_M,
>> + V2_QPC_BYTE_208_SR_MAX_S, 0);
>> + }
>> + }
>> return 0;
>> }
>>
>> --
>> 1.9.1
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
>> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2017-12-25 10:14 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-23 8:22 [PATCH for-next 0/6] Add rq inline and bugfixes for hns Lijun Ou
[not found] ` <1514017342-91468-1-git-send-email-oulijun-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2017-12-23 8:22 ` [PATCH for-next 1/6] RDMA/hns: Add rq inline data support for hip08 RoCE Lijun Ou
[not found] ` <1514017342-91468-2-git-send-email-oulijun-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2017-12-25 9:34 ` Leon Romanovsky
[not found] ` <20171225093448.GZ2942-U/DQcQFIOTAAJjI8aNfphQ@public.gmane.org>
2017-12-26 9:04 ` oulijun
2017-12-23 8:22 ` [PATCH for-next 2/6] RDMA/hns: Update the usage of sr_max and rr_max field Lijun Ou
[not found] ` <1514017342-91468-3-git-send-email-oulijun-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2017-12-25 9:41 ` Leon Romanovsky
[not found] ` <20171225094112.GA2942-U/DQcQFIOTAAJjI8aNfphQ@public.gmane.org>
2017-12-25 10:14 ` oulijun [this message]
2017-12-23 8:22 ` [PATCH for-next 3/6] RDMA/hns: Set access flags of hip08 RoCE Lijun Ou
2017-12-23 8:22 ` [PATCH for-next 4/6] RDMA/hns: Filter for zero length of sge in hip08 kernel mode Lijun Ou
[not found] ` <1514017342-91468-5-git-send-email-oulijun-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2017-12-25 9:00 ` Leon Romanovsky
[not found] ` <20171225090028.GY2942-U/DQcQFIOTAAJjI8aNfphQ@public.gmane.org>
2017-12-25 10:08 ` oulijun
[not found] ` <42e22cc6-f385-b6f4-bd14-1450ae19519a-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2017-12-25 10:20 ` Leon Romanovsky
[not found] ` <20171225102045.GC2942-U/DQcQFIOTAAJjI8aNfphQ@public.gmane.org>
2017-12-26 9:19 ` oulijun
2017-12-23 8:22 ` [PATCH for-next 5/6] RDMA/hns: Fix QP state judgement before sending work requests Lijun Ou
2017-12-23 8:22 ` [PATCH for-next 6/6] RDMA/hns: Assign dest_qp when deregistering mr Lijun Ou
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=bfcfca0e-d8c3-034d-e973-c7fab6cd4f0f@huawei.com \
--to=oulijun-hv44wf8li93qt0dzr+alfa@public.gmane.org \
--cc=dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=jgg-uk2M96/98Pc@public.gmane.org \
--cc=leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox