From: Akihiko Odaki <akihiko.odaki@daynix.com>
To: Jonathan Corbet <corbet@lwn.net>,
Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
Jason Wang <jasowang@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>,
Paolo Abeni <pabeni@redhat.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
Xuan Zhuo <xuanzhuo@linux.alibaba.com>,
Shuah Khan <shuah@kernel.org>,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
netdev@vger.kernel.org, kvm@vger.kernel.org,
virtualization@lists.linux-foundation.org,
linux-kselftest@vger.kernel.org,
Yuri Benditovich <yuri.benditovich@daynix.com>,
Andrew Melnychenko <andrew@daynix.com>,
Stephen Hemminger <stephen@networkplumber.org>,
gur.stavi@huawei.com, Lei Yang <leiyang@redhat.com>,
Simon Horman <horms@kernel.org>,
Akihiko Odaki <akihiko.odaki@daynix.com>
Subject: [PATCH net-next v12 06/10] tap: Introduce virtio-net hash feature
Date: Fri, 30 May 2025 13:50:10 +0900 [thread overview]
Message-ID: <20250530-rss-v12-6-95d8b348de91@daynix.com> (raw)
In-Reply-To: <20250530-rss-v12-0-95d8b348de91@daynix.com>
Add ioctls and storage required for the virtio-net hash feature to TAP.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
drivers/net/ipvlan/ipvtap.c | 2 +-
drivers/net/macvtap.c | 2 +-
drivers/net/tap.c | 72 +++++++++++++++++++++++++++++++++++++++++----
include/linux/if_tap.h | 4 ++-
4 files changed, 71 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 1afc4c47be73..305438abf7ae 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -114,7 +114,7 @@ static void ipvtap_dellink(struct net_device *dev,
struct ipvtap_dev *vlan = netdev_priv(dev);
netdev_rx_handler_unregister(dev);
- tap_del_queues(&vlan->tap);
+ tap_del(&vlan->tap);
ipvlan_link_delete(dev, head);
}
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 29a5929d48e5..e72144d05ef4 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -122,7 +122,7 @@ static void macvtap_dellink(struct net_device *dev,
struct macvtap_dev *vlantap = netdev_priv(dev);
netdev_rx_handler_unregister(dev);
- tap_del_queues(&vlantap->tap);
+ tap_del(&vlantap->tap);
macvlan_dellink(dev, head);
}
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 25c60ff2d3f2..15f056d7f632 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -49,6 +49,10 @@ struct major_info {
struct list_head next;
};
+struct tap_skb_cb {
+ struct virtio_net_hash hash;
+};
+
#define GOODCOPY_LEN 128
static const struct proto_ops tap_socket_ops;
@@ -179,9 +183,20 @@ static void tap_put_queue(struct tap_queue *q)
sock_put(&q->sk);
}
+static struct tap_skb_cb *tap_skb_cb(const struct sk_buff *skb)
+{
+ BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct tap_skb_cb));
+ return (struct tap_skb_cb *)skb->cb;
+}
+
+static struct virtio_net_hash *tap_add_hash(struct sk_buff *skb)
+{
+ return &tap_skb_cb(skb)->hash;
+}
+
static const struct virtio_net_hash *tap_find_hash(const struct sk_buff *skb)
{
- return NULL;
+ return &tap_skb_cb(skb)->hash;
}
/*
@@ -194,6 +209,7 @@ static const struct virtio_net_hash *tap_find_hash(const struct sk_buff *skb)
static struct tap_queue *tap_get_queue(struct tap_dev *tap,
struct sk_buff *skb)
{
+ struct flow_keys_basic keys_basic;
struct tap_queue *queue = NULL;
/* Access to taps array is protected by rcu, but access to numvtaps
* isn't. Below we use it to lookup a queue, but treat it as a hint
@@ -201,17 +217,47 @@ static struct tap_queue *tap_get_queue(struct tap_dev *tap,
* racing against queue removal.
*/
int numvtaps = READ_ONCE(tap->numvtaps);
+ struct tun_vnet_hash *vnet_hash = rcu_dereference(tap->vnet_hash);
__u32 rxq;
+ *tap_skb_cb(skb) = (struct tap_skb_cb) {
+ .hash = { .report = VIRTIO_NET_HASH_REPORT_NONE }
+ };
+
if (!numvtaps)
goto out;
if (numvtaps == 1)
goto single;
+ if (vnet_hash) {
+ if (vnet_hash->rss) {
+ rxq = tun_vnet_rss_select_queue(numvtaps, vnet_hash, skb, tap_add_hash);
+ queue = rcu_dereference(tap->taps[rxq]);
+ goto out;
+ }
+
+ if (!skb->l4_hash && !skb->sw_hash) {
+ struct flow_keys keys;
+
+ skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+ rxq = flow_hash_from_keys(&keys);
+ keys_basic = (struct flow_keys_basic) {
+ .control = keys.control,
+ .basic = keys.basic
+ };
+ } else {
+ skb_flow_dissect_flow_keys_basic(NULL, skb, &keys_basic, NULL, 0, 0, 0,
+ FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+ rxq = skb->hash;
+ }
+ } else {
+ rxq = skb_get_hash(skb);
+ }
+
/* Check if we can use flow to select a queue */
- rxq = skb_get_hash(skb);
if (rxq) {
+ tun_vnet_hash_report(vnet_hash, skb, &keys_basic, rxq, tap_add_hash);
queue = rcu_dereference(tap->taps[rxq % numvtaps]);
goto out;
}
@@ -234,10 +280,10 @@ static struct tap_queue *tap_get_queue(struct tap_dev *tap,
/*
* The net_device is going away, give up the reference
- * that it holds on all queues and safely set the pointer
- * from the queues to NULL.
+ * that it holds on all queues, safely set the pointer
+ * from the queues to NULL, and free vnet_hash.
*/
-void tap_del_queues(struct tap_dev *tap)
+void tap_del(struct tap_dev *tap)
{
struct tap_queue *q, *tmp;
@@ -254,8 +300,10 @@ void tap_del_queues(struct tap_dev *tap)
BUG_ON(tap->numqueues);
/* guarantee that any future tap_set_queue will fail */
tap->numvtaps = MAX_TAP_QUEUES;
+
+ kfree_rcu_mightsleep(rtnl_dereference(tap->vnet_hash));
}
-EXPORT_SYMBOL_GPL(tap_del_queues);
+EXPORT_SYMBOL_GPL(tap_del);
rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
{
@@ -998,6 +1046,18 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
rtnl_unlock();
return ret;
+ case TUNGETVNETHASHTYPES:
+ return tun_vnet_ioctl_gethashtypes(argp);
+
+ case TUNSETVNETREPORTINGAUTOMQ:
+ case TUNSETVNETREPORTINGRSS:
+ case TUNSETVNETRSS:
+ rtnl_lock();
+ tap = rtnl_dereference(q->tap);
+ ret = tap ? tun_vnet_ioctl_sethash(&tap->vnet_hash, cmd, argp) : -EBADFD;
+ rtnl_unlock();
+ return ret;
+
case SIOCGIFHWADDR:
rtnl_lock();
tap = tap_get_tap_dev(q);
diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h
index 553552fa635c..6647a7a9e956 100644
--- a/include/linux/if_tap.h
+++ b/include/linux/if_tap.h
@@ -31,6 +31,7 @@ static inline struct ptr_ring *tap_get_ptr_ring(struct file *f)
#define MAX_TAP_QUEUES 256
struct tap_queue;
+struct tun_vnet_hash;
struct tap_dev {
struct net_device *dev;
@@ -43,6 +44,7 @@ struct tap_dev {
int numqueues;
netdev_features_t tap_features;
int minor;
+ struct tun_vnet_hash __rcu *vnet_hash;
void (*update_features)(struct tap_dev *tap, netdev_features_t features);
void (*count_tx_dropped)(struct tap_dev *tap);
@@ -74,7 +76,7 @@ struct tap_queue {
};
rx_handler_result_t tap_handle_frame(struct sk_buff **pskb);
-void tap_del_queues(struct tap_dev *tap);
+void tap_del(struct tap_dev *tap);
int tap_get_minor(dev_t major, struct tap_dev *tap);
void tap_free_minor(dev_t major, struct tap_dev *tap);
int tap_queue_resize(struct tap_dev *tap);
--
2.49.0
next prev parent reply other threads:[~2025-05-30 4:50 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-30 4:50 [PATCH net-next v12 00/10] tun: Introduce virtio-net hashing feature Akihiko Odaki
2025-05-30 4:50 ` [PATCH net-next v12 01/10] virtio_net: Add functions for hashing Akihiko Odaki
2025-06-03 3:19 ` Jason Wang
2025-06-03 5:31 ` Akihiko Odaki
2025-06-04 1:18 ` Jason Wang
2025-06-04 7:20 ` Akihiko Odaki
2025-06-05 1:53 ` Jason Wang
2025-06-05 7:57 ` Akihiko Odaki
2025-06-06 0:48 ` Jason Wang
2025-06-06 9:10 ` Akihiko Odaki
2025-06-17 3:28 ` Jason Wang
2025-06-21 5:50 ` Akihiko Odaki
2025-06-22 17:40 ` Yuri Benditovich
2025-06-23 8:07 ` Jason Wang
2025-06-23 14:28 ` Yuri Benditovich
2025-06-24 0:49 ` Jason Wang
2025-05-30 4:50 ` [PATCH net-next v12 02/10] net: flow_dissector: Export flow_keys_dissector_symmetric Akihiko Odaki
2025-06-03 3:20 ` Jason Wang
2025-05-30 4:50 ` [PATCH net-next v12 03/10] tun: Allow steering eBPF program to fall back Akihiko Odaki
2025-06-04 1:27 ` Jason Wang
2025-06-04 7:24 ` Akihiko Odaki
2025-06-05 1:55 ` Jason Wang
2025-05-30 4:50 ` [PATCH net-next v12 04/10] tun: Add common virtio-net hash feature code Akihiko Odaki
2025-06-04 1:53 ` Jason Wang
2025-06-04 8:42 ` Akihiko Odaki
2025-06-05 2:46 ` Jason Wang
2025-06-05 8:18 ` Akihiko Odaki
2025-06-06 1:01 ` Jason Wang
2025-06-06 9:26 ` Akihiko Odaki
2025-06-17 3:39 ` Jason Wang
2025-06-19 17:01 ` Akihiko Odaki
2025-06-23 7:59 ` Jason Wang
2025-05-30 4:50 ` [PATCH net-next v12 05/10] tun: Introduce virtio-net hash feature Akihiko Odaki
2025-05-30 4:50 ` Akihiko Odaki [this message]
2025-05-30 4:50 ` [PATCH net-next v12 07/10] selftest: tun: Test vnet ioctls without device Akihiko Odaki
2025-05-30 4:50 ` [PATCH net-next v12 08/10] selftest: tun: Add tests for virtio-net hashing Akihiko Odaki
2025-05-30 4:50 ` [PATCH net-next v12 09/10] selftest: tap: Add tests for virtio-net ioctls Akihiko Odaki
2025-05-30 4:50 ` [PATCH net-next v12 10/10] vhost/net: Support VIRTIO_NET_F_HASH_REPORT Akihiko Odaki
2025-07-16 8:55 ` [PATCH net-next v12 00/10] tun: Introduce virtio-net hashing feature Michael S. Tsirkin
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=20250530-rss-v12-6-95d8b348de91@daynix.com \
--to=akihiko.odaki@daynix.com \
--cc=andrew@daynix.com \
--cc=corbet@lwn.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=gur.stavi@huawei.com \
--cc=horms@kernel.org \
--cc=jasowang@redhat.com \
--cc=kuba@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=leiyang@redhat.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=shuah@kernel.org \
--cc=stephen@networkplumber.org \
--cc=virtualization@lists.linux-foundation.org \
--cc=willemdebruijn.kernel@gmail.com \
--cc=xuanzhuo@linux.alibaba.com \
--cc=yuri.benditovich@daynix.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).