From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
To: Or Gerlitz <ogerlitz@mellanox.com>,
"David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org, Roland Dreier <roland@kernel.org>,
Amir Vadai <amirv@mellanox.com>, Tal Alon <talal@mellanox.com>,
Moni Shoua <monis@mellanox.com>
Subject: Re: [PATCH net-next 2/3] IB/mlx4: Always use the correct port for mirrored multicast attachments
Date: Thu, 05 Feb 2015 17:04:44 +0300 [thread overview]
Message-ID: <54D3787C.3030603@cogentembedded.com> (raw)
In-Reply-To: <1423144366-11814-3-git-send-email-ogerlitz@mellanox.com>
Hello.
On 2/5/2015 4:52 PM, Or Gerlitz wrote:
> From: Moni Shoua <monis@mellanox.com>
> When attaching a QP to a multicast address in bonded mode, there was an
> assumption that the port of the QP must be #1. This assumption isn't the
> case under the flow which enables maximal usage of the physical ports.
> Fix it by always checking the port of the original flow and create the
> mirrored flow on the other port.
> Fixes: c6215745b66a ("IB/mlx4: Load balance ports in port aggregation mode")
> Signed-off-by: Moni Shoua <monis@mellanox.com>
> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
> ---
> drivers/infiniband/hw/mlx4/main.c | 8 ++++++--
> 1 files changed, 6 insertions(+), 2 deletions(-)
> diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
> index 2ed5b99..271d3f1 100644
> --- a/drivers/infiniband/hw/mlx4/main.c
> +++ b/drivers/infiniband/hw/mlx4/main.c
> @@ -1186,6 +1186,9 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
> goto err_create_flow;
> i++;
> if (is_bonded) {
> + /* Application always sees one port so the mirror rule
> + * must be on port #2
> + */
Unrelated change?
> flow_attr->port = 2;
> err = __mlx4_ib_create_flow(qp, flow_attr,
> domain, type[j],
> @@ -1279,14 +1282,15 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
>
> err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port,
> !!(mqp->flags &
> - MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
> + MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
This change is both unrelated and unneeded.
> prot, ®_id.id);
> if (err)
> goto err_malloc;
>
> reg_id.mirror = 0;
> if (mlx4_is_bonded(dev)) {
> - err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, 2,
> + err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw,
> + (mqp->port == 1) ? 2 : 1,
I doubt that these parens are needed.
WBR, Sergei
next prev parent reply other threads:[~2015-02-05 14:04 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-05 13:52 [PATCH net-next 0/3] mlx4 driver fixes for the HA/LAG support and reset flow Or Gerlitz
2015-02-05 13:52 ` [PATCH net-next 1/3] net/bonding: Fix potential bad memory access during bonding events Or Gerlitz
2015-02-05 13:52 ` [PATCH net-next 2/3] IB/mlx4: Always use the correct port for mirrored multicast attachments Or Gerlitz
2015-02-05 14:04 ` Sergei Shtylyov [this message]
2015-02-05 15:18 ` Moni Shoua
2015-02-05 13:52 ` [PATCH net-next 3/3] IB/mlx4_ib: Reset flow support for IB kernel ULPs Or Gerlitz
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=54D3787C.3030603@cogentembedded.com \
--to=sergei.shtylyov@cogentembedded.com \
--cc=amirv@mellanox.com \
--cc=davem@davemloft.net \
--cc=monis@mellanox.com \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@mellanox.com \
--cc=roland@kernel.org \
--cc=talal@mellanox.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).