Add ioctls and storage required for the virtio-net hash feature to TAP.
Signed-off-by: Akihiko Odaki <akihiko.odaki@xxxxxxxxxx>
---
drivers/net/ipvlan/ipvtap.c | 2 +-
drivers/net/macvtap.c | 2 +-
drivers/net/tap.c | 70 +++++++++++++++++++++++++++++++++++++++++----
include/linux/if_tap.h | 4 ++-
4 files changed, 69 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..2213a2aa83a8 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;
}
@@ -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 +1046,16 @@ 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..9e8e02822d9c 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);
@@ -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);
--
2.48.1
