Skip to contentSkip to conversation

Patch "net: accept UFO datagrams from tuntap and packet" has been added to the 4.14-stable tree

PATCH [email protected] 1 participant 1 message Dec 14, 2017

Subsystems (9)
lore
Share & tools
lore

[email protected]

author maintainer Applied
#0 lore raw

This is a note to let you know that I've just added the patch titled

net: accept UFO datagrams from tuntap and packet

to the 4.14-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
net-accept-ufo-datagrams-from-tuntap-and-packet.patch
and it can be found in the queue-4.14 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

Quoted 1 line

From foo@baz Thu Dec 14 11:45:40 CET 2017

From: Willem de Bruijn <[email protected]>
Date: Tue, 21 Nov 2017 10:22:25 -0500
Subject: net: accept UFO datagrams from tuntap and packet

From: Willem de Bruijn <[email protected]>

[ Upstream commit 0c19f846d582af919db66a5914a0189f9f92c936 ]

Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively.

Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does.

Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation.

It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap.

To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO").

(*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn.

Tested
Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch ethtool -k eth0 shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel.

A UFO packet sent from the guest appears on the tap device:

    host:
      nc -l -p -u 8000 &
      tcpdump -n -i tap0

    guest:
      dd if=/dev/zero of=payload.txt bs=1 count=2000
      nc -u 192.16.1.1 8000 < payload.txt

Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented:

    ./with_tap_pair.sh ./tap_send_ufo tap0 tap1
    (from https://github.com/wdebruij/kerneltools/tree/master/tests)

Changes
v1 -> v2
- simplified set_offload change (review comment)
- documented test procedure

---
 drivers/net/tap.c               |    2 
 drivers/net/tun.c               |    2 
 include/linux/netdev_features.h |    4 +
 include/linux/netdevice.h       |    1 
 include/linux/skbuff.h          |    2 
 include/linux/virtio_net.h      |    5 +-
 include/net/ipv6.h              |    2 
 net/core/dev.c                  |    3 -
 net/ipv4/af_inet.c              |   12 ++++-
 net/ipv4/udp_offload.c          |   49 +++++++++++++++++++++--
 net/ipv6/output_core.c          |    6 +-
 net/ipv6/udp_offload.c          |   85 ++++++++++++++++++++++++++++++++++++++--
 net/openvswitch/datapath.c      |   14 ++++++
 net/openvswitch/flow.c          |    6 ++
 net/sched/act_csum.c            |    6 ++
 15 files changed, 181 insertions(+), 18 deletions(-)
drivers/net/tap.c +1 -1
@@ -1080,7 +1080,7 @@ static long tap_ioctl(struct file *file,
 	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 +2 -0
@@ -2157,6 +2157,8 @@ static int set_offload(struct tun_struct
 				features |= NETIF_F_TSO6;
 			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
 		}
+
+		arg &= ~TUN_F_UFO;
 	}
 
 	/* This gives the user a way to test for new features in future by
include/linux/netdev_features.h +3 -1
@@ -54,8 +54,9 @@ enum {
 	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
 	NETIF_F_GSO_SCTP_BIT,		/* ... SCTP fragmentation */
 	NETIF_F_GSO_ESP_BIT,		/* ... ESP with TSO */
+	NETIF_F_GSO_UDP_BIT,		/* ... UFO, deprecated except tuntap */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_ESP_BIT,
+		NETIF_F_GSO_UDP_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CRC_BIT,		/* SCTP checksum offload */
@@ -132,6 +133,7 @@ enum {
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_GSO_SCTP	__NETIF_F(GSO_SCTP)
 #define NETIF_F_GSO_ESP		__NETIF_F(GSO_ESP)
+#define NETIF_F_GSO_UDP		__NETIF_F(GSO_UDP)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)
include/linux/netdevice.h +1 -0
@@ -4101,6 +4101,7 @@ static inline bool net_gso_ok(netdev_fea
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_SCTP    != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
include/linux/skbuff.h +2 -0
@@ -569,6 +569,8 @@ enum {
 	SKB_GSO_SCTP = 1 << 14,
 
 	SKB_GSO_ESP = 1 << 15,
+
+	SKB_GSO_UDP = 1 << 16,
 };
 
 #if BITS_PER_LONG > 32
include/linux/virtio_net.h +4 -1
@@ -9,7 +9,7 @@ static inline int virtio_net_hdr_to_skb(
 					const struct virtio_net_hdr *hdr,
 					bool little_endian)
 {
-	unsigned short gso_type = 0;
+	unsigned int gso_type = 0;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -19,6 +19,9 @@ static inline int virtio_net_hdr_to_skb(
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			gso_type = SKB_GSO_TCPV6;
 			break;
+		case VIRTIO_NET_HDR_GSO_UDP:
+			gso_type = SKB_GSO_UDP;
+			break;
 		default:
 			return -EINVAL;
 		}
include/net/ipv6.h +1 -1
@@ -727,7 +727,7 @@ static inline int ipv6_addr_diff(const s
 __be32 ipv6_select_ident(struct net *net,
 			 const struct in6_addr *daddr,
 			 const struct in6_addr *saddr);
-void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb);
+__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
 
net/core/dev.c +2 -1
@@ -2735,7 +2735,8 @@ EXPORT_SYMBOL(skb_mac_gso_segment);
 static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
 {
 	if (tx_path)
-		return skb->ip_summed != CHECKSUM_PARTIAL;
+		return skb->ip_summed != CHECKSUM_PARTIAL &&
+		       skb->ip_summed != CHECKSUM_UNNECESSARY;
 
 	return skb->ip_summed == CHECKSUM_NONE;
 }
net/ipv4/af_inet.c +10 -2
@@ -1221,9 +1221,10 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				 netdev_features_t features)
 {
-	bool fixedid = false, gso_partial, encap;
+	bool udpfrag = false, fixedid = false, gso_partial, encap;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
+	unsigned int offset = 0;
 	struct iphdr *iph;
 	int proto, tot_len;
 	int nhoff;
@@ -1258,6 +1259,7 @@ struct sk_buff *inet_gso_segment(struct
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
 	if (!skb->encapsulation || encap) {
+		udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
 		fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
 
 		/* fixed ID is invalid if DF bit is not set */
@@ -1277,7 +1279,13 @@ struct sk_buff *inet_gso_segment(struct
 	skb = segs;
 	do {
 		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
-		if (skb_is_gso(skb)) {
+		if (udpfrag) {
+			iph->frag_off = htons(offset >> 3);
+			if (skb->next)
+				iph->frag_off |= htons(IP_MF);
+			offset += skb->len - nhoff - ihl;
+			tot_len = skb->len - nhoff;
+		} else if (skb_is_gso(skb)) {
 			if (!fixedid) {
 				iph->id = htons(id);
 				id += skb_shinfo(skb)->gso_segs;
net/ipv4/udp_offload.c +45 -4

68 lines not on this page · raw message

net/ipv6/output_core.c +3 -3
@@ -39,7 +39,7 @@ static u32 __ipv6_select_ident(struct ne
  *
  * The network header must be set before calling this.
  */
-void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
+__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
 {
 	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
@@ -51,14 +51,14 @@ void ipv6_proxy_select_ident(struct net
 				   offsetof(struct ipv6hdr, saddr),
 				   sizeof(buf), buf);
 	if (!addrs)
-		return;
+		return 0;
 
 	net_get_random_once(&ip6_proxy_idents_hashrnd,
 			    sizeof(ip6_proxy_idents_hashrnd));
 
 	id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd,
 				 &addrs[1], &addrs[0]);
-	skb_shinfo(skb)->ip6_frag_id = htonl(id);
+	return htonl(id);
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
net/ipv6/udp_offload.c +82 -3

104 lines not on this page · raw message

net/openvswitch/datapath.c +14 -0
@@ -335,6 +335,8 @@ static int queue_gso_packets(struct data
 			     const struct dp_upcall_info *upcall_info,
 				 uint32_t cutlen)
 {
+	unsigned short gso_type = skb_shinfo(skb)->gso_type;
+	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
 	int err;
 
@@ -345,9 +347,21 @@ static int queue_gso_packets(struct data
 	if (segs == NULL)
 		return -EINVAL;
 
+	if (gso_type & SKB_GSO_UDP) {
+		/* The initial flow key extracted by ovs_flow_key_extract()
+		 * in this case is for a first fragment, so we need to
+		 * properly mark later fragments.
+		 */
+		later_key = *key;
+		later_key.ip.frag = OVS_FRAG_TYPE_LATER;
+	}
+
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
+		if (gso_type & SKB_GSO_UDP && skb != segs)
+			key = &later_key;
+
 		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 		if (err)
 			break;
net/openvswitch/flow.c +5 -1
@@ -584,7 +584,8 @@ static int key_extract(struct sk_buff *s
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
 			return 0;
 		}
-		if (nh->frag_off & htons(IP_MF))
+		if (nh->frag_off & htons(IP_MF) ||
+			skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
 			key->ip.frag = OVS_FRAG_TYPE_FIRST;
 		else
 			key->ip.frag = OVS_FRAG_TYPE_NONE;
@@ -700,6 +701,9 @@ static int key_extract(struct sk_buff *s
 
 		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
 			return 0;
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+
 		/* Transport layer. */
 		if (key->ip.proto == NEXTHDR_TCP) {
 			if (tcphdr_ok(skb)) {
net/sched/act_csum.c +6 -0
@@ -229,6 +229,9 @@ static int tcf_csum_ipv4_udp(struct sk_b
 	const struct iphdr *iph;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,
@@ -282,6 +285,9 @@ static int tcf_csum_ipv6_udp(struct sk_b
 	const struct ipv6hdr *ip6h;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,

Patches currently in stable-queue which might be from [email protected] are

queue-4.14/net-accept-ufo-datagrams-from-tuntap-and-packet.patch queue-4.14/net-openvswitch-datapath-fix-data-type-in-queue_gso_packets.patch