diff mbox series

[net-next,v10,06/10] tap: Introduce virtio-net hash feature

Message ID 20250313-rss-v10-6-3185d73a9af0@daynix.com (mailing list archive)
State New
Delegated to: Netdev Maintainers
Headers show
Series tun: Introduce virtio-net hashing feature | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success Errors and warnings before: 26 (+0) this patch: 26 (+0)
netdev/cc_maintainers warning 1 maintainers not CCed: andrew+netdev@lunn.ch
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning WARNING: line length of 100 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 85 exceeds 80 columns WARNING: line length of 94 exceeds 80 columns WARNING: line length of 95 exceeds 80 columns WARNING: line length of 96 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Akihiko Odaki March 13, 2025, 7:01 a.m. UTC
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 mbox series

Patch

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);