[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID:
<PH7PR21MB30711A6DBAAD7D8863735CBECEF12@PH7PR21MB3071.namprd21.prod.outlook.com>
Date: Tue, 28 May 2024 20:14:22 +0000
From: Long Li <longli@...rosoft.com>
To: Konstantin Taranov <kotaranov@...ux.microsoft.com>, Konstantin Taranov
<kotaranov@...rosoft.com>, "sharmaajay@...rosoft.com"
<sharmaajay@...rosoft.com>, "jgg@...pe.ca" <jgg@...pe.ca>, "leon@...nel.org"
<leon@...nel.org>
CC: "linux-rdma@...r.kernel.org" <linux-rdma@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: RE: [PATCH rdma-next 2/2] RDMA/mana_ib: extend query device
> Subject: [PATCH rdma-next 2/2] RDMA/mana_ib: extend query device
>
> From: Konstantin Taranov <kotaranov@...rosoft.com>
>
> Fill in properties of the ib device.
> Order the assignment in the order of fields in the struct ib_device_attr.
>
> Signed-off-by: Konstantin Taranov <kotaranov@...rosoft.com>
> ---
> drivers/infiniband/hw/mana/main.c | 19 ++++++++++++++++---
> drivers/infiniband/hw/mana/mana_ib.h | 5 +++++
> 2 files changed, 21 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/infiniband/hw/mana/main.c
> b/drivers/infiniband/hw/mana/main.c
> index 2a41135..814a61e 100644
> --- a/drivers/infiniband/hw/mana/main.c
> +++ b/drivers/infiniband/hw/mana/main.c
> @@ -547,14 +547,27 @@ int mana_ib_query_device(struct ib_device *ibdev,
> struct ib_device_attr *props,
> struct mana_ib_dev *dev = container_of(ibdev,
> struct mana_ib_dev, ib_dev);
>
> + memset(props, 0, sizeof(*props));
> + props->max_mr_size = MANA_IB_MAX_MR_SIZE;
> + props->page_size_cap = PAGE_SZ_BM;
> props->max_qp = dev->adapter_caps.max_qp_count;
> props->max_qp_wr = dev->adapter_caps.max_qp_wr;
> + props->device_cap_flags = IB_DEVICE_RC_RNR_NAK_GEN;
> + props->max_send_sge = dev->adapter_caps.max_send_sge_count;
> + props->max_recv_sge = dev->adapter_caps.max_recv_sge_count;
> + props->max_sge_rd = dev->adapter_caps.max_recv_sge_count;
> props->max_cq = dev->adapter_caps.max_cq_count;
> props->max_cqe = dev->adapter_caps.max_qp_wr;
> props->max_mr = dev->adapter_caps.max_mr_count;
> - props->max_mr_size = MANA_IB_MAX_MR_SIZE;
> - props->max_send_sge = dev->adapter_caps.max_send_sge_count;
> - props->max_recv_sge = dev->adapter_caps.max_recv_sge_count;
> + props->max_pd = dev->adapter_caps.max_pd_count;
> + props->max_qp_rd_atom = dev->adapter_caps.max_inbound_read_limit;
> + props->max_res_rd_atom = props->max_qp_rd_atom * props->max_qp;
> + props->max_qp_init_rd_atom = dev-
> >adapter_caps.max_outbound_read_limit;
> + props->atomic_cap = IB_ATOMIC_NONE;
> + props->masked_atomic_cap = IB_ATOMIC_NONE;
> + props->max_ah = INT_MAX;
> + props->max_pkeys = 1;
> + props->local_ca_ack_delay = MANA_CA_ACK_DELAY;
>
> return 0;
> }
> diff --git a/drivers/infiniband/hw/mana/mana_ib.h
> b/drivers/infiniband/hw/mana/mana_ib.h
> index 68c3b4f..1348bfb 100644
> --- a/drivers/infiniband/hw/mana/mana_ib.h
> +++ b/drivers/infiniband/hw/mana/mana_ib.h
> @@ -27,6 +27,11 @@
> */
> #define MANA_IB_MAX_MR 0xFFFFFFu
>
> +/*
> + * The CA timeout is approx. 260ms
> + */
> +#define MANA_CA_ACK_DELAY 16
Looks good. But can you add a comment on where 16 is coming from 260ms?
Powered by blists - more mailing lists