From: longli@linuxonhyperv.com
To: Jason Gunthorpe <jgg@ziepe.ca>, Leon Romanovsky <leon@kernel.org>,
Konstantin Taranov <kotaranov@microsoft.com>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: linux-rdma@vger.kernel.org, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-hyperv@vger.kernel.org,
Long Li <longli@microsoft.com>
Subject: [patch rdma-next v4 2/2] RDMA/mana_ib: Handle net event for pointing to the current netdev
Date: Wed, 5 Mar 2025 14:22:40 -0800 [thread overview]
Message-ID: <1741213360-14567-2-git-send-email-longli@linuxonhyperv.com> (raw)
In-Reply-To: <1741213360-14567-1-git-send-email-longli@linuxonhyperv.com>
From: Long Li <longli@microsoft.com>
When running under Hyper-V, the master device to the RDMA device is always
bonded to this RDMA device. This is not user-configurable.
The master device can be unbind/bind from the kernel. During those events,
the RDMA device should set to the current netdev to reflect the change of
master device from those events.
Signed-off-by: Long Li <longli@microsoft.com>
---
Changes
v2: Add missing error handling when register_netdevice_notifier() fails.
v3: Change mana_get_primary_netdev() to return with netdev refcount held.
v4: use netdev_put().
drivers/infiniband/hw/mana/device.c | 47 ++++++++++++++++++++++++++--
drivers/infiniband/hw/mana/mana_ib.h | 1 +
2 files changed, 46 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/mana/device.c b/drivers/infiniband/hw/mana/device.c
index 2b4dd34a41ba..d71e1715aea8 100644
--- a/drivers/infiniband/hw/mana/device.c
+++ b/drivers/infiniband/hw/mana/device.c
@@ -51,6 +51,38 @@ static const struct ib_device_ops mana_ib_dev_ops = {
ib_ind_table),
};
+static int mana_ib_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct mana_ib_dev *dev = container_of(this, struct mana_ib_dev, nb);
+ struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+ struct gdma_context *gc = dev->gdma_dev->gdma_context;
+ struct mana_context *mc = gc->mana.driver_data;
+ struct net_device *ndev;
+
+ /* Only process events from our parent device */
+ if (event_dev != mc->ports[0])
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_CHANGEUPPER:
+ ndev = mana_get_primary_netdev(mc, 0);
+ /*
+ * RDMA core will setup GID based on updated netdev.
+ * It's not possible to race with the core as rtnl lock is being
+ * held.
+ */
+ ib_device_set_netdev(&dev->ib_dev, ndev, 1);
+
+ /* mana_get_primary_netdev() returns ndev with refcount held */
+ netdev_put(ndev, NULL);
+
+ return NOTIFY_OK;
+ default:
+ return NOTIFY_DONE;
+ }
+}
+
static int mana_ib_probe(struct auxiliary_device *adev,
const struct auxiliary_device_id *id)
{
@@ -108,17 +140,25 @@ static int mana_ib_probe(struct auxiliary_device *adev,
}
dev->gdma_dev = &mdev->gdma_context->mana_ib;
+ dev->nb.notifier_call = mana_ib_netdev_event;
+ ret = register_netdevice_notifier(&dev->nb);
+ if (ret) {
+ ibdev_err(&dev->ib_dev, "Failed to register net notifier, %d",
+ ret);
+ goto deregister_device;
+ }
+
ret = mana_ib_gd_query_adapter_caps(dev);
if (ret) {
ibdev_err(&dev->ib_dev, "Failed to query device caps, ret %d",
ret);
- goto deregister_device;
+ goto deregister_net_notifier;
}
ret = mana_ib_create_eqs(dev);
if (ret) {
ibdev_err(&dev->ib_dev, "Failed to create EQs, ret %d", ret);
- goto deregister_device;
+ goto deregister_net_notifier;
}
ret = mana_ib_gd_create_rnic_adapter(dev);
@@ -147,6 +187,8 @@ static int mana_ib_probe(struct auxiliary_device *adev,
mana_ib_gd_destroy_rnic_adapter(dev);
destroy_eqs:
mana_ib_destroy_eqs(dev);
+deregister_net_notifier:
+ unregister_netdevice_notifier(&dev->nb);
deregister_device:
mana_gd_deregister_device(dev->gdma_dev);
free_ib_device:
@@ -162,6 +204,7 @@ static void mana_ib_remove(struct auxiliary_device *adev)
xa_destroy(&dev->qp_table_wq);
mana_ib_gd_destroy_rnic_adapter(dev);
mana_ib_destroy_eqs(dev);
+ unregister_netdevice_notifier(&dev->nb);
mana_gd_deregister_device(dev->gdma_dev);
ib_dealloc_device(&dev->ib_dev);
}
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
index b53a5b4de908..d88187072899 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -64,6 +64,7 @@ struct mana_ib_dev {
struct gdma_queue **eqs;
struct xarray qp_table_wq;
struct mana_ib_adapter_caps adapter_caps;
+ struct notifier_block nb;
};
struct mana_ib_wq {
--
2.34.1
next prev parent reply other threads:[~2025-03-05 22:22 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-05 22:22 [patch rdma-next v4 1/2] net: mana: Change the function signature of mana_get_primary_netdev_rcu longli
2025-03-05 22:22 ` longli [this message]
2025-03-05 22:56 ` Jakub Kicinski
2025-03-05 23:29 ` [EXTERNAL] " Long Li
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=1741213360-14567-2-git-send-email-longli@linuxonhyperv.com \
--to=longli@linuxonhyperv.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=jgg@ziepe.ca \
--cc=kotaranov@microsoft.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=longli@microsoft.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.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).