From: Jason Gunthorpe <jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
To: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Cc: Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
Somnath Kotur
<Somnath.Kotur-xCNTGe7nOvUAvxtiuMwx3w@public.gmane.org>,
linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH for-next V5 10/12] IB/mlx4: Implement ib_device callbacks
Date: Thu, 11 Jun 2015 00:31:08 -0600 [thread overview]
Message-ID: <20150611063108.GE22369@obsidianresearch.com> (raw)
In-Reply-To: <1433772735-22416-11-git-send-email-matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
On Mon, Jun 08, 2015 at 05:12:13PM +0300, Matan Barak wrote:
> +static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, u8 port_num)
> +{
This function is never referenced in this patch, so we get compile
warnings?
Warnings are not a huge deal, but you did compile test every patch in
the series??
> + if (mlx4_is_bonded(ibdev->dev)) {
> + struct net_device *dev;
> + struct net_device *upper = NULL;
So, I see this code in mlx4 touching bonding, but I don't see similar
code in ocrdma..
If bonding is a general feature why is this bit in the driver? Should
the core code be doing this?
Does bonding work in ocrdma at the end of this series? I was expecting
it to..
> + gid_tbl = mailbox->buf;
> +
> + for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i)
> + memcpy(&gid_tbl[i], &gids[i].gid, sizeof(union ib_gid));
> +
> + err = mlx4_cmd(dev, mailbox->dma,
> + MLX4_SET_PORT_GID_TABLE << 8 | port_num,
> + 1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
> + MLX4_CMD_WRAPPED);
> + if (mlx4_is_bonded(dev))
> + err += mlx4_cmd(dev, mailbox->dma,
> + MLX4_SET_PORT_GID_TABLE << 8 | 2,
> + 1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
> + MLX4_CMD_WRAPPED);
Again, wonder why the driver is sensitive to bonding, and ocrdma is not..
> @@ -477,11 +673,22 @@ out:
> static int iboe_query_gid(struct ib_device *ibdev, u8 port, int index,
> union ib_gid *gid)
> {
> - struct mlx4_ib_dev *dev = to_mdev(ibdev);
> + int ret;
>
> - *gid = dev->iboe.gid_table[port - 1][index];
> + if (!rdma_cap_roce_gid_table(ibdev, port)) {
> + struct mlx4_ib_dev *dev = to_mdev(ibdev);
>
> - return 0;
> + *gid = dev->iboe.gid_table[port - 1][index];
> + return 0;
> + }
> +
> + ret = ib_get_cached_gid(ibdev, port, index, gid);
> + if (ret == -EAGAIN) {
> + memcpy(gid, &zgid, sizeof(*gid));
> + return 0;
> + }
> +
> + return ret;
> }
Hum, is it Ok to change iboe_query_gid like this at this point in the
series? Should this be in patch 11?
Jason
--
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:[~2015-06-11 6:31 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-08 14:12 [PATCH for-next V5 00/12] Move RoCE GID management to IB/Core Matan Barak
[not found] ` <1433772735-22416-1-git-send-email-matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-06-08 14:12 ` [PATCH for-next V5 01/12] IB/core: Add RoCE GID table Matan Barak
2015-06-08 14:12 ` [PATCH for-next V5 02/12] IB/core: Add rwsem to allow reading device list or client list Matan Barak
2015-06-08 14:12 ` [PATCH for-next V5 03/12] IB/core: Add RoCE GID population Matan Barak
[not found] ` <1433772735-22416-4-git-send-email-matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-06-11 4:18 ` Jason Gunthorpe
2015-06-08 14:12 ` [PATCH for-next V5 04/12] net/ipv6: Export addrconf_ifid_eui48 Matan Barak
2015-06-08 14:12 ` [PATCH for-next V5 05/12] IB/core: Add default GID for RoCE GID table Matan Barak
[not found] ` <1433772735-22416-6-git-send-email-matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-06-11 6:20 ` Jason Gunthorpe
[not found] ` <20150611062017.GC22369-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-06-11 15:30 ` Matan Barak
2015-06-08 14:12 ` [PATCH for-next V5 06/12] net: Add info for NETDEV_CHANGEUPPER event Matan Barak
2015-06-08 14:12 ` [PATCH for-next V5 07/12] IB/core: Add RoCE table bonding support Matan Barak
[not found] ` <1433772735-22416-8-git-send-email-matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-06-11 6:18 ` Jason Gunthorpe
[not found] ` <20150611061818.GB22369-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-06-11 16:00 ` Matan Barak
2015-06-08 14:12 ` [PATCH for-next V5 08/12] IB/core: ib_cache routines should use roce_gid_table when needed Matan Barak
2015-06-08 14:12 ` [PATCH for-next V5 09/12] net/mlx4: Postpone the registration of net_device Matan Barak
2015-06-08 14:12 ` [PATCH for-next V5 10/12] IB/mlx4: Implement ib_device callbacks Matan Barak
[not found] ` <1433772735-22416-11-git-send-email-matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-06-11 6:31 ` Jason Gunthorpe [this message]
[not found] ` <20150611063108.GE22369-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-06-11 6:53 ` Moni Shoua
2015-06-08 14:12 ` [PATCH for-next V5 11/12] IB/mlx4: Replace mechanism for RoCE GID management Matan Barak
2015-06-08 14:12 ` [PATCH for-next V5 12/12] RDMA/ocrdma: Changes in driver to incorporate the moving of GID Table mgmt to IB/Core Matan Barak
[not found] ` <1433772735-22416-13-git-send-email-matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-06-11 4:11 ` Jason Gunthorpe
[not found] ` <20150611041124.GC16599-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-06-11 6:04 ` Somnath Kotur
2015-06-08 21:37 ` [PATCH for-next V5 00/12] Move RoCE GID management " Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A82373A8FE5D17-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2015-06-09 7:27 ` Matan Barak
[not found] ` <55769561.8000300-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-06-10 8:53 ` Or Gerlitz
[not found] ` <5577FAFB.8020205-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-06-10 15:00 ` Jason Gunthorpe
[not found] ` <20150610150010.GA11243-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-06-10 15:08 ` Matan Barak
[not found] ` <557852EE.5030107-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2015-06-10 18:49 ` Jason Gunthorpe
[not found] ` <20150610184954.GA26404-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-06-10 20:19 ` Matan Barak
[not found] ` <CAAKD3BB90iZ98B2ADG+=ZYuEVtLq26a99BEjQCR8U1vzvcG+Gw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-06-10 22:01 ` Jason Gunthorpe
[not found] ` <20150610220154.GA4391-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-06-11 9:49 ` Matan Barak
[not found] ` <CAAKD3BChd10Gd4P2Mwm+46aW+PJBT3j7K-BLex0Fkm5UdtUG3w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-06-11 16:27 ` Jason Gunthorpe
2015-06-12 12:29 ` Or Gerlitz
[not found] ` <CAJ3xEMiXWN9wC5u6iapKMVb4=bfzdnuy3CaZryV0nOFL_Cgmhw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-06-12 16:11 ` Jason Gunthorpe
2015-06-11 1:06 ` Doug Ledford
[not found] ` <1433984788.71666.78.camel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-06-11 3:57 ` Jason Gunthorpe
[not found] ` <20150611035727.GA16599-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2015-06-11 4:49 ` Doug Ledford
[not found] ` <1433998199.71666.144.camel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-06-11 5:38 ` Jason Gunthorpe
2015-06-11 10:15 ` Matan Barak
2015-06-11 10:09 ` Matan Barak
2015-06-11 0:15 ` Doug Ledford
[not found] ` <1433981756.71666.60.camel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-06-11 4:07 ` Jason Gunthorpe
2015-06-11 9:51 ` Matan Barak
2015-06-10 15:09 ` Hefty, Sean
[not found] ` <1828884A29C6694DAF28B7E6B8A82373A8FE6616-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org>
2015-06-10 15:19 ` Matan Barak
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=20150611063108.GE22369@obsidianresearch.com \
--to=jgunthorpe-epgobjl8dl3ta4ec/59zmfatqe2ktcn/@public.gmane.org \
--cc=Somnath.Kotur-xCNTGe7nOvUAvxtiuMwx3w@public.gmane.org \
--cc=dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
--cc=monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
--cc=ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
--cc=sean.hefty-ral2JQCrhuEAvxtiuMwx3w@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