Merge branch 'virtio_net_ufo'

Vladislav Yasevich says:

====================
Restore UFO support to virtio_net devices

commit 3d0ad094
Author: Ben Hutchings <ben@decadent.org.uk>
Date:   Thu Oct 30 18:27:12 2014 +0000

    drivers/net: Disable UFO through virtio

Turned off UFO support to virtio-net based devices due to issues
with IPv6 fragment id generation for UFO packets.  The issue
was that IPv6 UFO/GSO implementation expects the fragment id
to be supplied in skb_shinfo().  However, for packets generated
by the VMs, the fragment id is not supplied which causes all
IPv6 fragments to have the id of 0.

The problem is that turning off UFO support on tap/macvtap
as well as virtio devices caused issues with migrations.
Migrations would fail when moving a vm from a kernel supporting
expecting UFO to work to the newer kernels that disabled UFO.

This series provides a partial solution to address the migration
issue.  The series allows us to track whether skb_shinfo()->ip6_frag_id
has been set by treating value of 0 as unset.
This lets GSO code to generate fragment ids if they are necessary
(ex: packet was generated by VM or packet socket).

Since v3:
  - Resolved build issue when IPv6 is a module.
  - Removed trailing white space.

Since v2:
  - Rebase and rebuild to make sure everything works.  No changes
    to the patches were done.

Since v1:
  - Removed the skb bit and use value of 0 as tracker.
  - Used Eric's suggestion to set fragment id as 0x80000000 if id
    generation procedure yeilded a 0 result.
  - Consolidated ipv6 id genration code.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/macvtap.c

@@ -17,7 +17,6 @@
 #include <linux/fs.h>
 #include <linux/uio.h>
 
-#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include <net/rtnetlink.h>
 #include <net/sock.h>
@@ -81,7 +80,7 @@ static struct cdev macvtap_cdev;
 static const struct proto_ops macvtap_socket_ops;
 
 #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
-		      NETIF_F_TSO6)
+		      NETIF_F_TSO6 | NETIF_F_UFO)
 #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
 #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
 
@@ -586,11 +585,7 @@ static int macvtap_skb_from_vnet_hdr(struct macvtap_queue *q,
 			gso_type = SKB_GSO_TCPV6;
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
-			pr_warn_once("macvtap: %s: using disabled UFO feature; please fix this program\n",
-				     current->comm);
 			gso_type = SKB_GSO_UDP;
-			if (skb->protocol == htons(ETH_P_IPV6))
-				ipv6_proxy_select_ident(skb);
 			break;
 		default:
 			return -EINVAL;
@@ -636,6 +631,8 @@ static void macvtap_skb_to_vnet_hdr(struct macvtap_queue *q,
 			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 		else if (sinfo->gso_type & SKB_GSO_TCPV6)
 			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+		else if (sinfo->gso_type & SKB_GSO_UDP)
+			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
 		else
 			BUG();
 		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
@@ -965,6 +962,9 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg)
 			if (arg & TUN_F_TSO6)
 				feature_mask |= NETIF_F_TSO6;
 		}
+
+		if (arg & TUN_F_UFO)
+			feature_mask |= NETIF_F_UFO;
 	}
 
 	/* tun/tap driver inverts the usage for TSO offloads, where
@@ -975,7 +975,7 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg)
 	 * When user space turns off TSO, we turn off GSO/LRO so that
 	 * user-space will not receive TSO frames.
 	 */
-	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6))
+	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_UFO))
 		features |= RX_OFFLOADS;
 	else
 		features &= ~RX_OFFLOADS;
@@ -1090,7 +1090,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 	case TUNSETOFFLOAD:
 		/* let the user check for future flags */
 		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
-			    TUN_F_TSO_ECN))
+			    TUN_F_TSO_ECN | TUN_F_UFO))
 			return -EINVAL;
 
 		rtnl_lock();

drivers/net/tun.c

@@ -65,7 +65,6 @@
 #include <linux/nsproxy.h>
 #include <linux/virtio_net.h>
 #include <linux/rcupdate.h>
-#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
@@ -187,7 +186,7 @@ struct tun_struct {
 	struct net_device	*dev;
 	netdev_features_t	set_features;
 #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
-			  NETIF_F_TSO6)
+			  NETIF_F_TSO6|NETIF_F_UFO)
 
 	int			vnet_hdr_sz;
 	int			sndbuf;
@@ -1167,8 +1166,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		break;
 	}
 
-	skb_reset_network_header(skb);
-
 	if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		pr_debug("GSO!\n");
 		switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -1179,20 +1176,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
-		{
-			static bool warned;
-
-			if (!warned) {
-				warned = true;
-				netdev_warn(tun->dev,
-					    "%s: using disabled UFO feature; please fix this program\n",
-					    current->comm);
-			}
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-			if (skb->protocol == htons(ETH_P_IPV6))
-				ipv6_proxy_select_ident(skb);
 			break;
-		}
 		default:
 			tun->dev->stats.rx_frame_errors++;
 			kfree_skb(skb);
@@ -1221,6 +1206,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
 	}
 
+	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb, 0);
 
 	rxhash = skb_get_hash(skb);
@@ -1298,6 +1284,8 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 			else if (sinfo->gso_type & SKB_GSO_TCPV6)
 				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+			else if (sinfo->gso_type & SKB_GSO_UDP)
+				gso.gso_type = VIRTIO_NET_HDR_GSO_UDP;
 			else {
 				pr_err("unexpected GSO type: "
 				       "0x%x, gso_size %d, hdr_len %d\n",
@@ -1746,6 +1734,11 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
 				features |= NETIF_F_TSO6;
 			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
 		}
+
+		if (arg & TUN_F_UFO) {
+			features |= NETIF_F_UFO;
+			arg &= ~TUN_F_UFO;
+		}
 	}
 
 	/* This gives the user a way to test for new features in future by

drivers/net/virtio_net.c

@@ -490,17 +490,8 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
-		{
-			static bool warned;
-
-			if (!warned) {
-				warned = true;
-				netdev_warn(dev,
-					    "host using disabled UFO feature; please fix it\n");
-			}
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 			break;
-		}
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 			break;
@@ -888,6 +879,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
 			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+		else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
 		else
 			BUG();
 		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
@@ -1748,7 +1741,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 			dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
 
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
-			dev->hw_features |= NETIF_F_TSO
+			dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO
 				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
 		}
 		/* Individual feature bits: what can host handle? */
@@ -1758,9 +1751,11 @@ static int virtnet_probe(struct virtio_device *vdev)
 			dev->hw_features |= NETIF_F_TSO6;
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN))
 			dev->hw_features |= NETIF_F_TSO_ECN;
+		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO))
+			dev->hw_features |= NETIF_F_UFO;
 
 		if (gso)
-			dev->features |= dev->hw_features & NETIF_F_ALL_TSO;
+			dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO);
 		/* (!csum && gso) case will be fixed by register_netdev() */
 	}
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
@@ -1798,7 +1793,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
 		vi->big_packets = true;
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
@@ -1994,9 +1990,9 @@ static struct virtio_device_id id_table[] = {
 static unsigned int features[] = {
 	VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM,
 	VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC,
-	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_TSO6,
+	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6,
 	VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
-	VIRTIO_NET_F_GUEST_ECN,
+	VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
 	VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
 	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,

include/net/ipv6.h

@@ -671,6 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst,
+			struct in6_addr *src);
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
 void ipv6_proxy_select_ident(struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);

net/ipv6/ip6_output.c

@@ -537,20 +537,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
-static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static u32 ip6_idents_hashrnd __read_mostly;
-	u32 hash, id;
-
-	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
-
-	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
-
-	id = ip_idents_reserve(hash, 1);
-	fhdr->identification = htonl(id);
-}
-
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;

net/ipv6/output_core.c

@@ -9,6 +9,24 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, struct in6_addr *src)
+{
+	u32 hash, id;
+
+	hash = __ipv6_addr_jhash(dst, hashrnd);
+	hash = __ipv6_addr_jhash(src, hash);
+
+	/* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve,
+	 * set the hight order instead thus minimizing possible future
+	 * collisions.
+	 */
+	id = ip_idents_reserve(hash, 1);
+	if (unlikely(!id))
+		id = 1 << 31;
+
+	return id;
+}
+
 /* This function exists only for tap drivers that must support broken
  * clients requesting UFO without specifying an IPv6 fragment ID.
  *
@@ -22,7 +40,7 @@ void ipv6_proxy_select_ident(struct sk_buff *skb)
 	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
 	struct in6_addr *addrs;
-	u32 hash, id;
+	u32 id;
 
 	addrs = skb_header_pointer(skb,
 				   skb_network_offset(skb) +
@@ -34,14 +52,25 @@ void ipv6_proxy_select_ident(struct sk_buff *skb)
 	net_get_random_once(&ip6_proxy_idents_hashrnd,
 			    sizeof(ip6_proxy_idents_hashrnd));
 
-	hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&addrs[0], hash);
-
-	id = ip_idents_reserve(hash, 1);
-	skb_shinfo(skb)->ip6_frag_id = htonl(id);
+	id = __ipv6_select_ident(ip6_proxy_idents_hashrnd,
+				 &addrs[1], &addrs[0]);
+	skb_shinfo(skb)->ip6_frag_id = id;
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	id = __ipv6_select_ident(ip6_idents_hashrnd, &rt->rt6i_dst.addr,
+				 &rt->rt6i_src.addr);
+	fhdr->identification = htonl(id);
+}
+EXPORT_SYMBOL(ipv6_select_ident);
+
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);

net/ipv6/udp_offload.c

@@ -52,6 +52,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
 
+		/* Set the IPv6 fragment id if not set yet */
+		if (!skb_shinfo(skb)->ip6_frag_id)
+			ipv6_proxy_select_ident(skb);
+
 		segs = NULL;
 		goto out;
 	}
@@ -108,7 +112,11 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 		fptr->nexthdr = nexthdr;
 		fptr->reserved = 0;
+		if (skb_shinfo(skb)->ip6_frag_id)
 			fptr->identification = skb_shinfo(skb)->ip6_frag_id;
+		else
+			ipv6_select_ident(fptr,
+					  (struct rt6_info *)skb_dst(skb));
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
 		 * fragment header are updated in ipv6_gso_segment()