netdev.vger.kernel.org archive mirror
 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 v2 03/15] net: Add peer info to queue-get response
Date: Wed, 15 Oct 2025 16:01:28 +0200	[thread overview]
Message-ID: <20251015140140.62273-4-daniel@iogearbox.net> (raw)
In-Reply-To: <20251015140140.62273-1-daniel@iogearbox.net>

From: David Wei <dw@davidwei.uk>

Add a nested peer field to the queue-get response that returns the peered
ifindex and queue id.

Example with ynl client:

  # ip netns exec foo ./pyynl/cli.py \
      --spec ~/netlink/specs/netdev.yaml \
      --do queue-get \
      --json '{"ifindex": 3, "id": 1, "type": "rx"}'
  {'id': 1, 'ifindex': 3, 'peer': {'id': 15, 'ifindex': 4, 'netns-id': 21}, 'type': 'rx'}

Note that the caller of netdev_nl_queue_fill_one() holds the netdevice
lock. For the queue-get we do not lock both devices. When queues get
{un,}peered, both devices are locked, thus if netdev_rx_queue_peered()
returns true, the peer pointer points to a valid device. The netns-id
is fetched via peernet2id_alloc() similarly as done in OVS.

Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 Documentation/netlink/specs/netdev.yaml | 24 ++++++++++++++++++
 include/net/netdev_rx_queue.h           |  3 +++
 include/uapi/linux/netdev.h             | 10 ++++++++
 net/core/netdev-genl.c                  | 33 +++++++++++++++++++++++--
 net/core/netdev_rx_queue.c              |  8 ++++++
 tools/include/uapi/linux/netdev.h       | 10 ++++++++
 6 files changed, 86 insertions(+), 2 deletions(-)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 20bb00b7e9ac..a3c562dfd205 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -297,6 +297,24 @@ attribute-sets:
   -
     name: xsk-info
     attributes: []
+  -
+    name: peer-info
+    attributes:
+      -
+        name: id
+        doc: Queue index of the netdevice to which the peer queue belongs.
+        type: u32
+      -
+        name: ifindex
+        doc: ifindex of the netdevice to which the peer queue belongs.
+        type: u32
+      -
+        name: netns-id
+        doc: |
+          Network namespace of the netdevice to which the peer queue belongs.
+          This is populated if the netdevices are not in the same network
+          namespace.
+        type: s32
   -
     name: queue
     attributes:
@@ -338,6 +356,11 @@ attribute-sets:
         doc: XSK information for this queue, if any.
         type: nest
         nested-attributes: xsk-info
+      -
+        name: peer
+        doc: Whether this queue was bound to another peer queue.
+        type: nest
+        nested-attributes: peer-info
   -
     name: qstats
     doc: |
@@ -723,6 +746,7 @@ operations:
             - dmabuf
             - io-uring
             - xsk
+            - peer
       dump:
         request:
           attributes:
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index db3ef94c0744..ea23cca947bb 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -90,4 +90,7 @@ struct netdev_rx_queue *
 netif_get_rx_queue_peer_locked(struct net_device **dev,
 			       unsigned int *rxq_idx,
 			       bool *needs_unlock);
+struct netdev_rx_queue *
+netif_get_rx_queue_peer_any(struct net_device **dev,
+			    unsigned int *rxq_idx);
 #endif /* _LINUX_NETDEV_RX_QUEUE_H */
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 4ef04d0bc412..d4d5d9f86eee 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -150,6 +150,15 @@ enum {
 	NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1)
 };
 
+enum {
+	NETDEV_A_PEER_INFO_ID = 1,
+	NETDEV_A_PEER_INFO_IFINDEX,
+	NETDEV_A_PEER_INFO_NETNS_ID,
+
+	__NETDEV_A_PEER_INFO_MAX,
+	NETDEV_A_PEER_INFO_MAX = (__NETDEV_A_PEER_INFO_MAX - 1)
+};
+
 enum {
 	NETDEV_A_QUEUE_ID = 1,
 	NETDEV_A_QUEUE_IFINDEX,
@@ -158,6 +167,7 @@ enum {
 	NETDEV_A_QUEUE_DMABUF,
 	NETDEV_A_QUEUE_IO_URING,
 	NETDEV_A_QUEUE_XSK,
+	NETDEV_A_QUEUE_PEER,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 579469abac8c..28658b5cd7a4 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -393,6 +393,7 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 	struct pp_memory_provider_params *params;
 	struct netdev_rx_queue *rxq;
 	struct netdev_queue *txq;
+	struct nlattr *nest;
 	void *hdr;
 
 	hdr = genlmsg_iput(rsp, info);
@@ -410,6 +411,34 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 		if (nla_put_napi_id(rsp, rxq->napi))
 			goto nla_put_failure;
 
+		if (netdev_rx_queue_peered(netdev, q_idx)) {
+			struct net_device *p_netdev = netdev;
+			struct net *net, *p_net;
+			u32 p_q_idx = q_idx;
+
+			nest = nla_nest_start(rsp, NETDEV_A_QUEUE_PEER);
+			if (!nest)
+				goto nla_put_failure;
+
+			netif_get_rx_queue_peer_any(&p_netdev, &p_q_idx);
+			if (nla_put_u32(rsp, NETDEV_A_PEER_INFO_ID, p_q_idx) ||
+			    nla_put_u32(rsp, NETDEV_A_PEER_INFO_IFINDEX,
+					READ_ONCE(p_netdev->ifindex)))
+				goto nla_put_failure;
+
+			rcu_read_lock();
+			p_net = dev_net_rcu(p_netdev);
+			net = dev_net_rcu(netdev);
+			if (!net_eq(net, p_net)) {
+				s32 id = peernet2id_alloc(net, p_net, GFP_ATOMIC);
+
+				if (nla_put_s32(rsp, NETDEV_A_PEER_INFO_NETNS_ID, id))
+					goto nla_put_failure_unlock;
+			}
+			rcu_read_unlock();
+			nla_nest_end(rsp, nest);
+		}
+
 		params = &rxq->mp_params;
 		if (params->mp_ops &&
 		    params->mp_ops->nl_fill(params->mp_priv, rsp, rxq))
@@ -419,7 +448,6 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 			if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK))
 				goto nla_put_failure;
 #endif
-
 		break;
 	case NETDEV_QUEUE_TYPE_TX:
 		txq = netdev_get_tx_queue(netdev, q_idx);
@@ -434,9 +462,10 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 	}
 
 	genlmsg_end(rsp, hdr);
-
 	return 0;
 
+nla_put_failure_unlock:
+	rcu_read_unlock();
 nla_put_failure:
 	genlmsg_cancel(rsp, hdr);
 	return -EMSGSIZE;
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index 85cf1b3749ee..686a6300df78 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -77,6 +77,14 @@ netif_get_rx_queue_peer_locked(struct net_device **dev, unsigned int *rxq_idx,
 	return rxq;
 }
 
+struct netdev_rx_queue *
+netif_get_rx_queue_peer_any(struct net_device **dev, unsigned int *rxq_idx)
+{
+	netdev_assert_locked(*dev);
+	/* Retrieves both virt-to-phys and phys-to-virt peering. */
+	return __netif_get_rx_queue_peer(dev, rxq_idx, false);
+}
+
 int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 {
 	struct netdev_rx_queue *rxq = __netif_get_rx_queue(dev, rxq_idx);
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 4ef04d0bc412..d4d5d9f86eee 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -150,6 +150,15 @@ enum {
 	NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1)
 };
 
+enum {
+	NETDEV_A_PEER_INFO_ID = 1,
+	NETDEV_A_PEER_INFO_IFINDEX,
+	NETDEV_A_PEER_INFO_NETNS_ID,
+
+	__NETDEV_A_PEER_INFO_MAX,
+	NETDEV_A_PEER_INFO_MAX = (__NETDEV_A_PEER_INFO_MAX - 1)
+};
+
 enum {
 	NETDEV_A_QUEUE_ID = 1,
 	NETDEV_A_QUEUE_IFINDEX,
@@ -158,6 +167,7 @@ enum {
 	NETDEV_A_QUEUE_DMABUF,
 	NETDEV_A_QUEUE_IO_URING,
 	NETDEV_A_QUEUE_XSK,
+	NETDEV_A_QUEUE_PEER,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
-- 
2.43.0


  parent reply	other threads:[~2025-10-15 14:02 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-15 14:01 [PATCH net-next v2 00/15] netkit: Support for io_uring zero-copy and AF_XDP Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 01/15] net: Add bind-queue operation Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 02/15] net: Implement netdev_nl_bind_queue_doit Daniel Borkmann
2025-10-15 14:01 ` Daniel Borkmann [this message]
2025-10-15 14:01 ` [PATCH net-next v2 04/15] net, ethtool: Disallow peered real rxqs to be resized Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 05/15] net: Proxy net_mp_{open,close}_rxq for mapped queues Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 06/15] xsk: Move NETDEV_XDP_ACT_ZC into generic header Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 07/15] xsk: Move pool registration into single function Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 08/15] xsk: Add small helper xp_pool_bindable Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 09/15] xsk: Change xsk_rcv_check to check netdev/queue_id from pool Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 10/15] xsk: Proxy pool management for mapped queues Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 11/15] netkit: Add single device mode for netkit Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 12/15] netkit: Document fast vs slowpath members via macros Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 13/15] netkit: Implement rtnl_link_ops->alloc and ndo_queue_create Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 14/15] netkit: Add io_uring zero-copy support for TCP Daniel Borkmann
2025-10-15 14:01 ` [PATCH net-next v2 15/15] netkit: Add xsk support for af_xdp applications Daniel Borkmann
2025-10-15 18:46 ` [syzbot ci] Re: netkit: Support for io_uring zero-copy and AF_XDP syzbot ci
2025-10-15 19:13   ` Daniel Borkmann
2025-10-16 12:12     ` 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=20251015140140.62273-4-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;
as well as URLs for NNTP newsgroup(s).