public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
From: Daniel Borkmann <daniel@iogearbox.net>
To: netdev@vger.kernel.org
Cc: bpf@vger.kernel.org, kuba@kernel.org, davem@davemloft.net,
	razor@blackwall.org, pabeni@redhat.com, willemb@google.com,
	sdf@fomichev.me, john.fastabend@gmail.com, martin.lau@kernel.org,
	jordan@jrife.io, maciej.fijalkowski@intel.com,
	magnus.karlsson@intel.com, dw@davidwei.uk, toke@redhat.com,
	yangzhenze@bytedance.com, wangdongdong.6@bytedance.com
Subject: [PATCH net-next v10 07/14] net: Proxy netdev_queue_get_dma_dev for leased queues
Date: Fri, 27 Mar 2026 13:10:42 +0100	[thread overview]
Message-ID: <20260327121049.334562-8-daniel@iogearbox.net> (raw)
In-Reply-To: <20260327121049.334562-1-daniel@iogearbox.net>

From: David Wei <dw@davidwei.uk>

Extend netdev_queue_get_dma_dev to return the physical device of the
real rxq for DMA in case the queue was leased. This allows memory
providers like io_uring zero-copy or devmem to bind to the physically
leased rxq via virtual devices such as netkit.

Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/netdev_queues.h |  3 ++-
 net/core/netdev_queues.c    | 36 ++++++++++++++++++++++++++++--------
 2 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 748b70552ed1..d14a45a13b40 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -380,7 +380,8 @@ static inline unsigned int netif_xmit_timeout_ms(struct netdev_queue *txq)
 					 get_desc, start_thrs);		\
 	})
 
-struct device *netdev_queue_get_dma_dev(struct net_device *dev, int idx);
+struct device *netdev_queue_get_dma_dev(struct net_device *dev,
+					unsigned int idx);
 bool netdev_can_create_queue(const struct net_device *dev,
 			     struct netlink_ext_ack *extack);
 bool netdev_can_lease_queue(const struct net_device *dev,
diff --git a/net/core/netdev_queues.c b/net/core/netdev_queues.c
index 177401828e79..9a945d74c3a7 100644
--- a/net/core/netdev_queues.c
+++ b/net/core/netdev_queues.c
@@ -6,27 +6,47 @@
 
 #include "dev.h"
 
+static struct device *
+__netdev_queue_get_dma_dev(struct net_device *dev, unsigned int idx)
+{
+	const struct netdev_queue_mgmt_ops *queue_ops = dev->queue_mgmt_ops;
+	struct device *dma_dev;
+
+	if (queue_ops && queue_ops->ndo_queue_get_dma_dev)
+		dma_dev = queue_ops->ndo_queue_get_dma_dev(dev, idx);
+	else
+		dma_dev = dev->dev.parent;
+
+	return dma_dev && dma_dev->dma_mask ? dma_dev : NULL;
+}
+
 /**
  * netdev_queue_get_dma_dev() - get dma device for zero-copy operations
  * @dev:	net_device
  * @idx:	queue index
  *
- * Get dma device for zero-copy operations to be used for this queue.
+ * Get dma device for zero-copy operations to be used for this queue. If the
+ * queue is leased from a physical queue, we retrieve the physical queue's
+ * dma device.
  * When such device is not available or valid, the function will return NULL.
  *
  * Return: Device or NULL on error
  */
-struct device *netdev_queue_get_dma_dev(struct net_device *dev, int idx)
+struct device *netdev_queue_get_dma_dev(struct net_device *dev,
+					unsigned int idx)
 {
-	const struct netdev_queue_mgmt_ops *queue_ops = dev->queue_mgmt_ops;
+	struct net_device *orig_dev = dev;
 	struct device *dma_dev;
 
-	if (queue_ops && queue_ops->ndo_queue_get_dma_dev)
-		dma_dev = queue_ops->ndo_queue_get_dma_dev(dev, idx);
-	else
-		dma_dev = dev->dev.parent;
+	if (!netif_rxq_is_leased(dev, idx))
+		return __netdev_queue_get_dma_dev(dev, idx);
 
-	return dma_dev && dma_dev->dma_mask ? dma_dev : NULL;
+	if (!netif_get_rx_queue_lease_locked(&dev, &idx))
+		return NULL;
+
+	dma_dev = __netdev_queue_get_dma_dev(dev, idx);
+	netif_put_rx_queue_lease_locked(orig_dev, dev);
+	return dma_dev;
 }
 
 bool netdev_can_create_queue(const struct net_device *dev,
-- 
2.43.0


  parent reply	other threads:[~2026-03-27 12:11 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-27 12:10 [PATCH net-next v10 00/14] netkit: Support for io_uring zero-copy and AF_XDP Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 01/14] net: Add queue-create operation Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 02/14] net: Implement netdev_nl_queue_create_doit Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 03/14] net: Add lease info to queue-get response Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 04/14] net, ethtool: Disallow leased real rxqs to be resized Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 05/14] net: Slightly simplify net_mp_{open,close}_rxq Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 06/14] net: Proxy netif_mp_{open,close}_rxq for leased queues Daniel Borkmann
2026-03-27 12:10 ` Daniel Borkmann [this message]
2026-03-27 12:10 ` [PATCH net-next v10 08/14] xsk: Extend xsk_rcv_check validation Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 09/14] xsk: Proxy pool management for leased queues Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 10/14] netkit: Add single device mode for netkit Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 11/14] netkit: Implement rtnl_link_ops->alloc and ndo_queue_create Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 12/14] netkit: Add netkit notifier to check for unregistering devices Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 13/14] netkit: Add xsk support for af_xdp applications Daniel Borkmann
2026-03-27 12:10 ` [PATCH net-next v10 14/14] selftests/net: Add queue leasing tests with netkit Daniel Borkmann

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=20260327121049.334562-8-daniel@iogearbox.net \
    --to=daniel@iogearbox.net \
    --cc=bpf@vger.kernel.org \
    --cc=davem@davemloft.net \
    --cc=dw@davidwei.uk \
    --cc=john.fastabend@gmail.com \
    --cc=jordan@jrife.io \
    --cc=kuba@kernel.org \
    --cc=maciej.fijalkowski@intel.com \
    --cc=magnus.karlsson@intel.com \
    --cc=martin.lau@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=razor@blackwall.org \
    --cc=sdf@fomichev.me \
    --cc=toke@redhat.com \
    --cc=wangdongdong.6@bytedance.com \
    --cc=willemb@google.com \
    --cc=yangzhenze@bytedance.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