| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20251031212103.310683-4-daniel@iogearbox.net>
Date: Fri, 31 Oct 2025 22:20:52 +0100
From: Daniel Borkmann <daniel@...earbox.net>
To: netdev@...r.kernel.org
Cc: bpf@...r.kernel.org,
kuba@...nel.org,
davem@...emloft.net,
razor@...ckwall.org,
pabeni@...hat.com,
willemb@...gle.com,
sdf@...ichev.me,
john.fastabend@...il.com,
martin.lau@...nel.org,
jordan@...fe.io,
maciej.fijalkowski@...el.com,
magnus.karlsson@...el.com,
dw@...idwei.uk,
toke@...hat.com,
yangzhenze@...edance.com,
wangdongdong.6@...edance.com
Subject: [PATCH net-next v4 03/14] net: Add peer info to queue-get response
From: David Wei <dw@...idwei.uk>
Add a nested peer field to the queue-get response that returns the peered
ifindex, queue id and optionally netns id if the device resides in a
different netns.
Example with ynl client:
# ip a
[...]
4: enp10s0f0np0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 xdp/id:24 qdisc mq state UP group default qlen 1000
link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff
inet 10.0.0.2/24 scope global enp10s0f0np0
valid_lft forever preferred_lft forever
inet6 fe80::eaeb:d3ff:fea3:43f6/64 scope link proto kernel_ll
valid_lft forever preferred_lft forever
[...]
# ethtool -i enp10s0f0np0
driver: mlx5_core
[...]
# ip netns exec foo ./pyynl/cli.py \
--spec ~/netlink/specs/netdev.yaml \
--do queue-get \
--json '{"ifindex": 4, "id": 15, "type": "rx"}'
{'id': 15,
'ifindex': 4,
'napi-id': 8227,
'peer': {'id': 1, 'ifindex': 8, 'netns-id': 0},
'type': 'rx',
'xsk': {}}
# ip netns list
foo (id: 0)
# ip netns exec foo ip a
[...]
8: nk@...E: <BROADCAST,MULTICAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
inet6 fe80::200:ff:fe00:0/64 scope link proto kernel_ll
valid_lft forever preferred_lft forever
[...]
# ip netns exec foo ethtool -i nk
driver: netkit
[...]
# ip netns exec foo ./pyynl/cli.py \
--spec ~/netlink/specs/netdev.yaml \
--do queue-get \
--json '{"ifindex": 8, "id": 1, "type": "rx"}'
{'id': 1, 'ifindex': 8, '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 __netif_get_rx_queue_peer()
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@...idwei.uk>
Co-developed-by: Daniel Borkmann <daniel@...earbox.net>
Signed-off-by: Daniel Borkmann <daniel@...earbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@...ckwall.org>
---
Documentation/netlink/specs/netdev.yaml | 24 +++++++++++++++++
include/net/netdev_rx_queue.h | 9 +++++++
include/uapi/linux/netdev.h | 10 ++++++++
net/core/netdev-genl.c | 34 +++++++++++++++++++++++--
net/core/netdev_rx_queue.c | 19 +++++++++++---
tools/include/uapi/linux/netdev.h | 10 ++++++++
6 files changed, 100 insertions(+), 6 deletions(-)
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 1e24c7f76de0..e1735b486222 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 3a02d47e42bc..d2505d099400 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -92,4 +92,13 @@ netif_get_rx_queue_peer_locked(struct net_device **dev,
unsigned int *rxq_idx);
void netif_put_rx_queue_peer_locked(struct net_device *orig_dev,
struct net_device *dev);
+
+enum netif_peer_dir {
+ NETIF_VIRT_TO_PHYS,
+ NETIF_PHYS_TO_VIRT,
+};
+
+struct netdev_rx_queue *
+__netif_get_rx_queue_peer(struct net_device **dev, unsigned int *rxq_idx,
+ enum netif_peer_dir dir);
#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 4fa7e881441f..5cf7a9ca2e4b 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -391,8 +391,11 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
u32 q_idx, u32 q_type, const struct genl_info *info)
{
struct pp_memory_provider_params *params;
+ struct net_device *orig_netdev = netdev;
struct netdev_rx_queue *rxq;
struct netdev_queue *txq;
+ u32 peer_q_idx = q_idx;
+ struct nlattr *nest;
void *hdr;
hdr = genlmsg_iput(rsp, info);
@@ -410,6 +413,33 @@ 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 (__netif_get_rx_queue_peer(&netdev, &peer_q_idx,
+ NETIF_PHYS_TO_VIRT)) {
+ struct net *net, *peer_net;
+
+ nest = nla_nest_start(rsp, NETDEV_A_QUEUE_PEER);
+ if (!nest)
+ goto nla_put_failure;
+
+ if (nla_put_u32(rsp, NETDEV_A_PEER_INFO_ID, peer_q_idx) ||
+ nla_put_u32(rsp, NETDEV_A_PEER_INFO_IFINDEX,
+ READ_ONCE(netdev->ifindex)))
+ goto nla_put_failure;
+
+ rcu_read_lock();
+ peer_net = dev_net_rcu(netdev);
+ net = dev_net_rcu(orig_netdev);
+ if (!net_eq(net, peer_net)) {
+ s32 id = peernet2id_alloc(net, peer_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);
+ netdev = orig_netdev;
+ }
+
params = &rxq->mp_params;
if (params->mp_ops &&
params->mp_ops->nl_fill(params->mp_priv, rsp, rxq))
@@ -419,7 +449,6 @@ 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 +463,10 @@ 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 6eb12f3b969c..889b7382cdb6 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -42,14 +42,25 @@ void netdev_rx_queue_unpeer(struct net_device *src_dev,
netdev_put(src_dev, &src_rxq->peer_tracker);
}
-static struct netdev_rx_queue *
-__netif_get_rx_queue_peer(struct net_device **dev, unsigned int *rxq_idx)
+static bool netif_peer_dir_ok(const struct net_device *dev,
+ enum netif_peer_dir dir)
+{
+ if (dir == NETIF_VIRT_TO_PHYS && !dev->dev.parent)
+ return true;
+ if (dir == NETIF_PHYS_TO_VIRT && dev->dev.parent)
+ return true;
+ return false;
+}
+
+struct netdev_rx_queue *
+__netif_get_rx_queue_peer(struct net_device **dev, unsigned int *rxq_idx,
+ enum netif_peer_dir dir)
{
struct net_device *orig_dev = *dev;
struct netdev_rx_queue *rxq = __netif_get_rx_queue(orig_dev, *rxq_idx);
if (rxq->peer) {
- if (orig_dev->dev.parent)
+ if (!netif_peer_dir_ok(orig_dev, dir))
return NULL;
rxq = rxq->peer;
*rxq_idx = get_netdev_rx_queue_index(rxq);
@@ -68,7 +79,7 @@ netif_get_rx_queue_peer_locked(struct net_device **dev, unsigned int *rxq_idx)
* see netdev_nl_bind_queue_doit().
*/
netdev_ops_assert_locked(orig_dev);
- rxq = __netif_get_rx_queue_peer(dev, rxq_idx);
+ rxq = __netif_get_rx_queue_peer(dev, rxq_idx, NETIF_VIRT_TO_PHYS);
if (rxq && orig_dev != *dev)
netdev_lock(*dev);
return rxq;
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
Powered by blists - more mailing lists