From: Zhu Yanjun <yanjun.zhu@linux.dev>
To: Bob Pearson <rpearsonhpe@gmail.com>,
jgg@nvidia.com, linux-rdma@vger.kernel.org, dsahern@kernel.org,
davem@davemloft.net, netdev@vger.kernel.org
Subject: Re: [PATCH for-next v5 7/7] RDMA/rxe: Add module parameters for mcast limits
Date: Tue, 5 Dec 2023 13:58:23 +0800 [thread overview]
Message-ID: <95f41a77-e283-4e86-82e1-4a46c9dfeb30@linux.dev> (raw)
In-Reply-To: <20231205002613.10219-5-rpearsonhpe@gmail.com>
Add David S. Miller and David Ahern.
They are the maintainers in netdev and very familiar with mcast.
Zhu Yanjun
在 2023/12/5 8:26, Bob Pearson 写道:
> Add module parameters for max_mcast_grp, max_mcast_qp_attach,
> and tot_mcast_qp_attach to allow setting these parameters to
> small values when the driver is loaded to support testing these
> limits.
>
> Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
> ---
> drivers/infiniband/sw/rxe/Makefile | 3 ++-
> drivers/infiniband/sw/rxe/rxe.c | 6 +++---
> drivers/infiniband/sw/rxe/rxe_param.c | 23 +++++++++++++++++++++++
> drivers/infiniband/sw/rxe/rxe_param.h | 4 ++++
> 4 files changed, 32 insertions(+), 4 deletions(-)
> create mode 100644 drivers/infiniband/sw/rxe/rxe_param.c
>
> diff --git a/drivers/infiniband/sw/rxe/Makefile b/drivers/infiniband/sw/rxe/Makefile
> index 5395a581f4bb..b183924ea01d 100644
> --- a/drivers/infiniband/sw/rxe/Makefile
> +++ b/drivers/infiniband/sw/rxe/Makefile
> @@ -22,4 +22,5 @@ rdma_rxe-y := \
> rxe_mcast.o \
> rxe_task.o \
> rxe_net.o \
> - rxe_hw_counters.o
> + rxe_hw_counters.o \
> + rxe_param.o
> diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
> index 147cb16e937d..599fbfdeb426 100644
> --- a/drivers/infiniband/sw/rxe/rxe.c
> +++ b/drivers/infiniband/sw/rxe/rxe.c
> @@ -59,9 +59,9 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
> rxe->attr.max_res_rd_atom = RXE_MAX_RES_RD_ATOM;
> rxe->attr.max_qp_init_rd_atom = RXE_MAX_QP_INIT_RD_ATOM;
> rxe->attr.atomic_cap = IB_ATOMIC_HCA;
> - rxe->attr.max_mcast_grp = RXE_MAX_MCAST_GRP;
> - rxe->attr.max_mcast_qp_attach = RXE_MAX_MCAST_QP_ATTACH;
> - rxe->attr.max_total_mcast_qp_attach = RXE_MAX_TOT_MCAST_QP_ATTACH;
> + rxe->attr.max_mcast_grp = rxe_max_mcast_grp;
> + rxe->attr.max_mcast_qp_attach = rxe_max_mcast_qp_attach;
> + rxe->attr.max_total_mcast_qp_attach = rxe_max_tot_mcast_qp_attach;
> rxe->attr.max_ah = RXE_MAX_AH;
> rxe->attr.max_srq = RXE_MAX_SRQ;
> rxe->attr.max_srq_wr = RXE_MAX_SRQ_WR;
> diff --git a/drivers/infiniband/sw/rxe/rxe_param.c b/drivers/infiniband/sw/rxe/rxe_param.c
> new file mode 100644
> index 000000000000..27873e7de753
> --- /dev/null
> +++ b/drivers/infiniband/sw/rxe/rxe_param.c
> @@ -0,0 +1,23 @@
> +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
> +/*
> + * Copyright (c) 2023 Hewlett Packard Enterprise, Inc. All rights reserved.
> + */
> +
> +#include "rxe.h"
> +
> +int rxe_max_mcast_grp = RXE_MAX_MCAST_GRP;
> +module_param_named(max_mcast_grp, rxe_max_mcast_grp, int, 0444);
> +MODULE_PARM_DESC(max_mcast_grp,
> + "Maximum number of multicast groups per device");
> +
> +int rxe_max_mcast_qp_attach = RXE_MAX_MCAST_QP_ATTACH;
> +module_param_named(max_mcast_qp_attach, rxe_max_mcast_qp_attach,
> + int, 0444);
> +MODULE_PARM_DESC(max_mcast_qp_attach,
> + "Maximum number of QPs attached to a multicast group");
> +
> +int rxe_max_tot_mcast_qp_attach = RXE_MAX_TOT_MCAST_QP_ATTACH;
> +module_param_named(max_tot_mcast_qp_attach, rxe_max_tot_mcast_qp_attach,
> + int, 0444);
> +MODULE_PARM_DESC(max_tot_mcast_qp_attach,
> + "Maximum total number of QPs attached to multicast groups per device");
> diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
> index d2f57ead78ad..d6fe50f5f483 100644
> --- a/drivers/infiniband/sw/rxe/rxe_param.h
> +++ b/drivers/infiniband/sw/rxe/rxe_param.h
> @@ -125,6 +125,10 @@ enum rxe_device_param {
> RXE_VENDOR_ID = 0XFFFFFF,
> };
>
> +extern int rxe_max_mcast_grp;
> +extern int rxe_max_mcast_qp_attach;
> +extern int rxe_max_tot_mcast_qp_attach;
> +
> /* default/initial rxe port parameters */
> enum rxe_port_param {
> RXE_PORT_GID_TBL_LEN = 1024,
prev parent reply other threads:[~2023-12-05 5:58 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20231205002613.10219-1-rpearsonhpe@gmail.com>
2023-12-05 5:55 ` [PATCH for-next v5 3/7] RDMA/rxe: Register IP mcast address Zhu Yanjun
2023-12-05 10:29 ` Zhu Yanjun
2023-12-07 1:47 ` Rain River
2023-12-07 19:07 ` Bob Pearson
2023-12-08 1:24 ` Greg Sword
[not found] ` <20231205002613.10219-2-rpearsonhpe@gmail.com>
2023-12-05 5:56 ` [PATCH for-next v5 4/7] RDMA/rxe: Let rxe_lookup_mcg use rcu_read_lock Zhu Yanjun
[not found] ` <20231205002613.10219-3-rpearsonhpe@gmail.com>
2023-12-05 5:57 ` [PATCH for-next v5 5/7] RDMA/rxe: Split multicast lock Zhu Yanjun
[not found] ` <20231205002613.10219-4-rpearsonhpe@gmail.com>
2023-12-05 5:57 ` [PATCH for-next v5 6/7] RDMA/rxe: Cleanup mcg lifetime Zhu Yanjun
[not found] ` <20231205002613.10219-5-rpearsonhpe@gmail.com>
2023-12-05 5:58 ` Zhu Yanjun [this message]
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=95f41a77-e283-4e86-82e1-4a46c9dfeb30@linux.dev \
--to=yanjun.zhu@linux.dev \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=jgg@nvidia.com \
--cc=linux-rdma@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=rpearsonhpe@gmail.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).