From: Wenpeng Liang <liangwenpeng@huawei.com>
To: <jgg@nvidia.com>, <leon@kernel.org>
Cc: <linux-rdma@vger.kernel.org>, <linuxarm@huawei.com>,
<liangwenpeng@huawei.com>
Subject: [PATCH for-next 3/4] RDMA/hns: Remove the num_qpc_timer variable
Date: Mon, 29 Aug 2022 18:50:20 +0800 [thread overview]
Message-ID: <20220829105021.1427804-4-liangwenpeng@huawei.com> (raw)
In-Reply-To: <20220829105021.1427804-1-liangwenpeng@huawei.com>
From: Yixing Liu <liuyixing1@huawei.com>
The bt number of qpc_timer of HIP09 increases compared with that of HIP08.
Therefore, qpc_timer_bt_num and num_qpc_timer do not match. As a result,
the driver may fail to allocate qpc_timer. So the driver needs to uniquely
uses qpc_timer_bt_num to represent the bt number of qpc_timer.
Fixes: 0e40dc2f70cd ("RDMA/hns: Add timer allocation support for hip08")
Signed-off-by: Yixing Liu <liuyixing1@huawei.com>
Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com>
---
drivers/infiniband/hw/hns/hns_roce_device.h | 1 -
drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 3 +--
drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 +-
drivers/infiniband/hw/hns/hns_roce_main.c | 2 +-
4 files changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 1bcecc5589fa..22c5e9a564e0 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -730,7 +730,6 @@ struct hns_roce_caps {
u32 num_qps;
u32 num_pi_qps;
u32 reserved_qps;
- int num_qpc_timer;
u32 num_srqs;
u32 max_wqes;
u32 max_srq_wrs;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index fa78b141dff2..9b71ea8040c1 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -1977,7 +1977,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
caps->num_mtpts = HNS_ROCE_V2_MAX_MTPT_NUM;
caps->num_pds = HNS_ROCE_V2_MAX_PD_NUM;
- caps->num_qpc_timer = HNS_ROCE_V2_MAX_QPC_TIMER_NUM;
+ caps->qpc_timer_bt_num = HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM;
caps->cqc_timer_bt_num = HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM;
caps->max_qp_init_rdma = HNS_ROCE_V2_MAX_QP_INIT_RDMA;
@@ -2273,7 +2273,6 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
caps->max_rq_sg = le16_to_cpu(resp_a->max_rq_sg);
caps->max_rq_sg = roundup_pow_of_two(caps->max_rq_sg);
caps->max_extend_sg = le32_to_cpu(resp_a->max_extend_sg);
- caps->num_qpc_timer = le16_to_cpu(resp_a->num_qpc_timer);
caps->max_srq_sges = le16_to_cpu(resp_a->max_srq_sges);
caps->max_srq_sges = roundup_pow_of_two(caps->max_srq_sges);
caps->num_aeq_vectors = resp_a->num_aeq_vectors;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index c170cd2fe03f..da39e9a95c7e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -36,11 +36,11 @@
#include <linux/bitops.h>
#define HNS_ROCE_V2_MAX_QP_NUM 0x1000
-#define HNS_ROCE_V2_MAX_QPC_TIMER_NUM 0x200
#define HNS_ROCE_V2_MAX_WQE_NUM 0x8000
#define HNS_ROCE_V2_MAX_SRQ_WR 0x8000
#define HNS_ROCE_V2_MAX_SRQ_SGE 64
#define HNS_ROCE_V2_MAX_CQ_NUM 0x100000
+#define HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM 0x100
#define HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM 0x100
#define HNS_ROCE_V2_MAX_SRQ_NUM 0x100000
#define HNS_ROCE_V2_MAX_CQE_NUM 0x400000
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 9de3a522980a..686b1235fe11 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -734,7 +734,7 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
ret = hns_roce_init_hem_table(hr_dev, &hr_dev->qpc_timer_table,
HEM_TYPE_QPC_TIMER,
hr_dev->caps.qpc_timer_entry_sz,
- hr_dev->caps.num_qpc_timer, 1);
+ hr_dev->caps.qpc_timer_bt_num, 1);
if (ret) {
dev_err(dev,
"Failed to init QPC timer memory, aborting.\n");
--
2.30.0
next prev parent reply other threads:[~2022-08-29 10:51 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-29 10:50 [PATCH for-next 0/4] RDMA/hns: Bugfixes or cleanups for resource specs or numbers Wenpeng Liang
2022-08-29 10:50 ` [PATCH for-next 1/4] RDMA/hns: Fix supported page size Wenpeng Liang
2022-08-29 10:50 ` [PATCH for-next 2/4] RDMA/hns: Fix wrong fixed value of qp->rq.wqe_shift Wenpeng Liang
2022-08-29 10:50 ` Wenpeng Liang [this message]
2022-08-29 10:50 ` [PATCH for-next 4/4] RDMA/hns: Remove redundant member doorbell_qpn of struct hns_roce_qp Wenpeng Liang
2022-08-30 7:27 ` [PATCH for-next 0/4] RDMA/hns: Bugfixes or cleanups for resource specs or numbers Leon Romanovsky
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=20220829105021.1427804-4-liangwenpeng@huawei.com \
--to=liangwenpeng@huawei.com \
--cc=jgg@nvidia.com \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=linuxarm@huawei.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.