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 v10 06/10] tap: Introduce virtio-net hash feature
Date: Thu, 13 Mar 2025 16:01:09 +0900 [thread overview]
Message-ID: <20250313-rss-v10-6-3185d73a9af0@daynix.com> (raw)
In-Reply-To: <20250313-rss-v10-0-3185d73a9af0@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/tap.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++--
include/linux/if_tap.h | 2 ++
2 files changed, 60 insertions(+), 2 deletions(-)
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 25c60ff2d3f2..86b5e7b88614 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_container *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->common.flags & TUN_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;
}
@@ -998,6 +1044,16 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
rtnl_unlock();
return ret;
+ case TUNGETVNETHASHCAP:
+ return tun_vnet_ioctl_gethashcap(argp);
+
+ case TUNSETVNETHASH:
+ rtnl_lock();
+ tap = rtnl_dereference(q->tap);
+ ret = tap ? tun_vnet_ioctl_sethash(&tap->vnet_hash, 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..7334c46a3f10 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_container;
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_container __rcu *vnet_hash;
void (*update_features)(struct tap_dev *tap, netdev_features_t features);
void (*count_tx_dropped)(struct tap_dev *tap);
--
2.48.1
next prev parent reply other threads:[~2025-03-13 7:02 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-13 7:01 [PATCH net-next v10 00/10] tun: Introduce virtio-net hashing feature Akihiko Odaki
2025-03-13 7:01 ` [PATCH net-next v10 01/10] virtio_net: Add functions for hashing Akihiko Odaki
2025-03-13 7:01 ` [PATCH net-next v10 02/10] net: flow_dissector: Export flow_keys_dissector_symmetric Akihiko Odaki
2025-03-13 7:01 ` [PATCH net-next v10 03/10] tun: Allow steering eBPF program to fall back Akihiko Odaki
2025-03-17 1:25 ` Jason Wang
2025-03-13 7:01 ` [PATCH net-next v10 04/10] tun: Add common virtio-net hash feature code Akihiko Odaki
2025-03-13 7:01 ` [PATCH net-next v10 05/10] tun: Introduce virtio-net hash feature Akihiko Odaki
2025-03-13 7:01 ` Akihiko Odaki [this message]
2025-03-17 8:34 ` [PATCH net-next v10 06/10] tap: " Paolo Abeni
2025-03-13 7:01 ` [PATCH net-next v10 07/10] selftest: tun: Test vnet ioctls without device Akihiko Odaki
2025-03-13 7:01 ` [PATCH net-next v10 08/10] selftest: tun: Add tests for virtio-net hashing Akihiko Odaki
2025-03-13 7:01 ` [PATCH net-next v10 09/10] selftest: tap: Add tests for virtio-net ioctls Akihiko Odaki
2025-03-13 7:01 ` [PATCH net-next v10 10/10] vhost/net: Support VIRTIO_NET_F_HASH_REPORT Akihiko Odaki
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=20250313-rss-v10-6-3185d73a9af0@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).