[PATCH RFC v4 6/9] tun: Introduce virtio-net hash reporting feature

[Akihiko Odaki <akihiko.odaki@daynix.com>]

Allow the guest to reuse the hash value to make receive steering
consistent between the host and guest, and to save hash computation.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
 Documentation/networking/tuntap.rst |   7 +++
 drivers/net/Kconfig                 |   1 +
 drivers/net/tun.c                   | 117 +++++++++++++++++++++++++++++++-----
 include/uapi/linux/if_tun.h         |  44 ++++++++++++++
 4 files changed, 155 insertions(+), 14 deletions(-)

diff --git a/Documentation/networking/tuntap.rst b/Documentation/networking/tuntap.rst
index 4d7087f727be..86b4ae8caa8a 100644
--- a/Documentation/networking/tuntap.rst
+++ b/Documentation/networking/tuntap.rst
@@ -206,6 +206,13 @@ enable is true we enable it, otherwise we disable it::
       return ioctl(fd, TUNSETQUEUE, (void *)&ifr);
   }
 
+3.4 Reference
+-------------
+
+``linux/if_tun.h`` defines the interface described below:
+
+.. kernel-doc:: include/uapi/linux/if_tun.h
+
 Universal TUN/TAP device driver Frequently Asked Question
 =========================================================
 
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 9920b3a68ed1..e2a7bd703550 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -395,6 +395,7 @@ config TUN
 	tristate "Universal TUN/TAP device driver support"
 	depends on INET
 	select CRC32
+	select SKB_EXTENSIONS
 	help
 	  TUN/TAP provides packet reception and transmission for user space
 	  programs.  It can be viewed as a simple Point-to-Point or Ethernet
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9d93ab9ee58f..986e4a5bf04d 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -173,6 +173,10 @@ struct tun_prog {
 	struct bpf_prog *prog;
 };
 
+struct tun_vnet_hash_container {
+	struct tun_vnet_hash common;
+};
+
 /* Since the socket were moved to tun_file, to preserve the behavior of persist
  * device, socket filter, sndbuf and vnet header size were restore when the
  * file were attached to a persist device.
@@ -210,6 +214,7 @@ struct tun_struct {
 	struct bpf_prog __rcu *xdp_prog;
 	struct tun_prog __rcu *steering_prog;
 	struct tun_prog __rcu *filter_prog;
+	struct tun_vnet_hash vnet_hash;
 	struct ethtool_link_ksettings link_ksettings;
 	/* init args */
 	struct file *file;
@@ -221,6 +226,11 @@ struct veth {
 	__be16 h_vlan_TCI;
 };
 
+static const struct tun_vnet_hash tun_vnet_hash_cap = {
+	.flags = TUN_VNET_HASH_REPORT,
+	.types = VIRTIO_NET_SUPPORTED_HASH_TYPES
+};
+
 static void tun_flow_init(struct tun_struct *tun);
 static void tun_flow_uninit(struct tun_struct *tun);
 
@@ -322,10 +332,15 @@ static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
 	if (get_user(be, argp))
 		return -EFAULT;
 
-	if (be)
+	if (be) {
+		if (!(tun->flags & TUN_VNET_LE) &&
+		    (tun->vnet_hash.flags & TUN_VNET_HASH_REPORT))
+			return -EBUSY;
+
 		tun->flags |= TUN_VNET_BE;
-	else
+	} else {
 		tun->flags &= ~TUN_VNET_BE;
+	}
 
 	return 0;
 }
@@ -524,12 +539,17 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
  */
 static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 {
+	struct tun_vnet_hash_ext *ext;
+	struct flow_keys keys;
 	struct tun_flow_entry *e;
 	u32 txq, numqueues;
 
 	numqueues = READ_ONCE(tun->numqueues);
 
-	txq = __skb_get_hash_symmetric(skb);
+	memset(&keys, 0, sizeof(keys));
+	skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, 0);
+
+	txq = flow_hash_from_keys(&keys);
 	e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq);
 	if (e) {
 		tun_flow_save_rps_rxhash(e, txq);
@@ -538,6 +558,16 @@ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 		txq = reciprocal_scale(txq, numqueues);
 	}
 
+	if (tun->vnet_hash.flags & TUN_VNET_HASH_REPORT) {
+		ext = skb_ext_add(skb, SKB_EXT_TUN_VNET_HASH);
+		if (ext) {
+			u32 types = tun->vnet_hash.types;
+
+			ext->report = virtio_net_hash_report(types, keys.basic);
+			ext->value = skb->l4_hash ? skb->hash : txq;
+		}
+	}
+
 	return txq;
 }
 
@@ -2120,33 +2150,58 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	}
 
 	if (vnet_hdr_sz) {
-		struct virtio_net_hdr gso;
+		struct tun_vnet_hash_ext *ext;
+		size_t vnet_hdr_content_sz = sizeof(struct virtio_net_hdr);
+		union {
+			struct virtio_net_hdr hdr;
+			struct virtio_net_hdr_v1_hash hdr_v1_hash;
+		} vnet_hdr;
+		int ret;
 
 		if (iov_iter_count(iter) < vnet_hdr_sz)
 			return -EINVAL;
 
-		if (virtio_net_hdr_from_skb(skb, &gso,
-					    tun_is_little_endian(tun), true,
-					    vlan_hlen)) {
+		ext = vnet_hdr_sz < sizeof(vnet_hdr.hdr_v1_hash) ?
+		      NULL : skb_ext_find(skb, SKB_EXT_TUN_VNET_HASH);
+
+		if (ext) {
+			vnet_hdr_content_sz = sizeof(vnet_hdr.hdr_v1_hash);
+			memset(&vnet_hdr, 0, vnet_hdr_content_sz);
+			vnet_hdr.hdr_v1_hash.hdr.num_buffers = __cpu_to_virtio16(true, 1);
+			vnet_hdr.hdr_v1_hash.hash_value = cpu_to_le32(ext->value);
+			vnet_hdr.hdr_v1_hash.hash_report = cpu_to_le16(ext->report);
+		} else {
+			vnet_hdr_content_sz = sizeof(struct virtio_net_hdr);
+		}
+
+		ret = virtio_net_hdr_from_skb(skb,
+					      &vnet_hdr.hdr,
+					      tun_is_little_endian(tun),
+					      true,
+					      vlan_hlen);
+
+		if (ret) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 
 			if (net_ratelimit()) {
 				netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
-					   sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
-					   tun16_to_cpu(tun, gso.hdr_len));
+					   sinfo->gso_type,
+					   tun16_to_cpu(tun, vnet_hdr.hdr.gso_size),
+					   tun16_to_cpu(tun, vnet_hdr.hdr.hdr_len));
 				print_hex_dump(KERN_ERR, "tun: ",
 					       DUMP_PREFIX_NONE,
 					       16, 1, skb->head,
-					       min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
+					       min(tun16_to_cpu(tun, vnet_hdr.hdr.hdr_len), 64),
+					       true);
 			}
 			WARN_ON_ONCE(1);
 			return -EINVAL;
 		}
 
-		if (copy_to_iter(&gso, sizeof(gso), iter) != sizeof(gso))
+		if (copy_to_iter(&vnet_hdr, vnet_hdr_content_sz, iter) != vnet_hdr_content_sz)
 			return -EFAULT;
 
-		iov_iter_zero(vnet_hdr_sz - sizeof(gso), iter);
+		iov_iter_zero(vnet_hdr_sz - vnet_hdr_content_sz, iter);
 	}
 
 	if (vlan_hlen) {
@@ -3094,6 +3149,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	int le;
 	int ret;
 	bool do_notify = false;
+	struct tun_vnet_hash vnet_hash;
 
 	if (cmd == TUNSETIFF || cmd == TUNSETQUEUE ||
 	    (_IOC_TYPE(cmd) == SOCK_IOC_TYPE && cmd != SIOCGSKNS)) {
@@ -3115,6 +3171,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 		return open_related_ns(&net->ns, get_net_ns);
+	} else if (cmd == TUNGETVNETHASHCAP) {
+		return copy_to_user(argp, &tun_vnet_hash_cap, sizeof(tun_vnet_hash_cap)) ?
+		       -EFAULT : 0;
 	}
 
 	rtnl_lock();
@@ -3314,6 +3373,12 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			break;
 		}
 
+		if (tun->vnet_hash.flags & TUN_VNET_HASH_REPORT &&
+		    vnet_hdr_sz < (int)sizeof(struct virtio_net_hdr_v1_hash)) {
+			ret = -EBUSY;
+			break;
+		}
+
 		tun->vnet_hdr_sz = vnet_hdr_sz;
 		break;
 
@@ -3328,10 +3393,17 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			ret = -EFAULT;
 			break;
 		}
-		if (le)
+		if (le) {
 			tun->flags |= TUN_VNET_LE;
-		else
+		} else {
+			if (tun->vnet_hash.flags & TUN_VNET_HASH_REPORT &&
+			    !tun_legacy_is_little_endian(tun)) {
+				ret = -EBUSY;
+				break;
+			}
+
 			tun->flags &= ~TUN_VNET_LE;
+		}
 		break;
 
 	case TUNGETVNETBE:
@@ -3396,6 +3468,23 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		ret = open_related_ns(&net->ns, get_net_ns);
 		break;
 
+	case TUNSETVNETHASH:
+		if (copy_from_user(&vnet_hash, argp, sizeof(vnet_hash))) {
+			ret = -EFAULT;
+			break;
+		}
+		argp = (struct tun_vnet_hash __user *)argp + 1;
+
+		if ((vnet_hash.flags & TUN_VNET_HASH_REPORT) &&
+		    (tun->vnet_hdr_sz < sizeof(struct virtio_net_hdr_v1_hash) ||
+		     !tun_is_little_endian(tun))) {
+			ret = -EBUSY;
+			break;
+		}
+
+		tun->vnet_hash = vnet_hash;
+		break;
+
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 287cdc81c939..1561e8ce0a0a 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -62,6 +62,30 @@
 #define TUNSETCARRIER _IOW('T', 226, int)
 #define TUNGETDEVNETNS _IO('T', 227)
 
+/**
+ * define TUNGETVNETHASHCAP - ioctl to get virtio_net hashing capability.
+ *
+ * The argument is a pointer to &struct tun_vnet_hash which will store the
+ * maximal virtio_net hashing configuration.
+ */
+#define TUNGETVNETHASHCAP _IOR('T', 228, struct tun_vnet_hash)
+
+/**
+ * define TUNSETVNETHASH - ioctl to configure virtio_net hashing
+ *
+ * The argument is a pointer to &struct tun_vnet_hash.
+ *
+ * %TUNSETVNETHDRSZ ioctl must be called with a number greater than or equal to
+ * the size of &struct virtio_net_hdr_v1_hash before calling this ioctl with
+ * %TUN_VNET_HASH_REPORT.
+ *
+ * The virtio_net header must be configured as little-endian before calling this
+ * ioctl with %TUN_VNET_HASH_REPORT.
+ *
+ * This ioctl currently has no effect on XDP packets.
+ */
+#define TUNSETVNETHASH _IOW('T', 229, struct tun_vnet_hash)
+
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
 #define IFF_TAP		0x0002
@@ -115,4 +139,24 @@ struct tun_filter {
 	__u8   addr[][ETH_ALEN];
 };
 
+/**
+ * define TUN_VNET_HASH_REPORT - Request virtio_net hash reporting for vhost
+ */
+#define TUN_VNET_HASH_REPORT	0x0001
+
+/**
+ * struct tun_vnet_hash - virtio_net hashing configuration
+ * @flags:
+ *		Bitmask consists of %TUN_VNET_HASH_REPORT and %TUN_VNET_HASH_RSS
+ * @pad:
+ *		Should be filled with zero before passing to %TUNSETVNETHASH
+ * @types:
+ *		Bitmask of allowed hash types
+ */
+struct tun_vnet_hash {
+	__u16 flags;
+	__u8 pad[2];
+	__u32 types;
+};
+
 #endif /* _UAPI__IF_TUN_H */

-- 
2.46.0