From 880388aa3c07fdea4f9b85e35641753017b1852f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 3 Jul 2017 07:29:12 -0700
Subject: net: Remove all references to SKB_GSO_UDP.

Such packets are no longer possible.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 14 --------------
 1 file changed, 14 deletions(-)

(limited to 'net/openvswitch/datapath.c')

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 45fe8c8a884d..f6e229b51dfb 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -335,8 +335,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     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;
 
@@ -347,21 +345,9 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	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;
-- 
cgit v1.2.3


From 494bea39f3201776cdfddc232705f54a0bd210c4 Mon Sep 17 00:00:00 2001
From: Liping Zhang <zlpnobody@gmail.com>
Date: Wed, 16 Aug 2017 13:30:07 +0800
Subject: openvswitch: fix skb_panic due to the incorrect actions attrlen

For sw_flow_actions, the actions_len only represents the kernel part's
size, and when we dump the actions to the userspace, we will do the
convertions, so it's true size may become bigger than the actions_len.

But unfortunately, for OVS_PACKET_ATTR_ACTIONS, we use the actions_len
to alloc the skbuff, so the user_skb's size may become insufficient and
oops will happen like this:
  skbuff: skb_over_panic: text:ffffffff8148fabf len:1749 put:157 head:
  ffff881300f39000 data:ffff881300f39000 tail:0x6d5 end:0x6c0 dev:<NULL>
  ------------[ cut here ]------------
  kernel BUG at net/core/skbuff.c:129!
  [...]
  Call Trace:
   <IRQ>
   [<ffffffff8148be82>] skb_put+0x43/0x44
   [<ffffffff8148fabf>] skb_zerocopy+0x6c/0x1f4
   [<ffffffffa0290d36>] queue_userspace_packet+0x3a3/0x448 [openvswitch]
   [<ffffffffa0292023>] ovs_dp_upcall+0x30/0x5c [openvswitch]
   [<ffffffffa028d435>] output_userspace+0x132/0x158 [openvswitch]
   [<ffffffffa01e6890>] ? ip6_rcv_finish+0x74/0x77 [ipv6]
   [<ffffffffa028e277>] do_execute_actions+0xcc1/0xdc8 [openvswitch]
   [<ffffffffa028e3f2>] ovs_execute_actions+0x74/0x106 [openvswitch]
   [<ffffffffa0292130>] ovs_dp_process_packet+0xe1/0xfd [openvswitch]
   [<ffffffffa0292b77>] ? key_extract+0x63c/0x8d5 [openvswitch]
   [<ffffffffa029848b>] ovs_vport_receive+0xa1/0xc3 [openvswitch]
  [...]

Also we can find that the actions_len is much little than the orig_len:
  crash> struct sw_flow_actions 0xffff8812f539d000
  struct sw_flow_actions {
    rcu = {
      next = 0xffff8812f5398800,
      func = 0xffffe3b00035db32
    },
    orig_len = 1384,
    actions_len = 592,
    actions = 0xffff8812f539d01c
  }

So as a quick fix, use the orig_len instead of the actions_len to alloc
the user_skb.

Last, this oops happened on our system running a relative old kernel, but
the same risk still exists on the mainline, since we use the wrong
actions_len from the beginning.

Fixes: ccea74457bbd ("openvswitch: include datapath actions with sampled-packet upcall to userspace")
Cc: Neil McKee <neil.mckee@inmon.com>
Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c  | 1 +
 net/openvswitch/datapath.c | 7 ++++---
 net/openvswitch/datapath.h | 2 ++
 3 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'net/openvswitch/datapath.c')

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index e4610676299b..a54a556fcdb5 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1337,6 +1337,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		goto out;
 	}
 
+	OVS_CB(skb)->acts_origlen = acts->orig_len;
 	err = do_execute_actions(dp, skb, key,
 				 acts->actions, acts->actions_len);
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 45fe8c8a884d..6b44fe405282 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -381,7 +381,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 }
 
 static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
-			      unsigned int hdrlen)
+			      unsigned int hdrlen, int actions_attrlen)
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
@@ -398,7 +398,7 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 
 	/* OVS_PACKET_ATTR_ACTIONS */
 	if (upcall_info->actions_len)
-		size += nla_total_size(upcall_info->actions_len);
+		size += nla_total_size(actions_attrlen);
 
 	/* OVS_PACKET_ATTR_MRU */
 	if (upcall_info->mru)
@@ -465,7 +465,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info, hlen - cutlen);
+	len = upcall_msg_size(upcall_info, hlen - cutlen,
+			      OVS_CB(skb)->acts_origlen);
 	user_skb = genlmsg_new(len, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 5d8dcd88815f..480600649d0b 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -99,11 +99,13 @@ struct datapath {
  * when a packet is received by OVS.
  * @mru: The maximum received fragement size; 0 if the packet is not
  * fragmented.
+ * @acts_origlen: The netlink size of the flow actions applied to this skb.
  * @cutlen: The number of bytes from the packet end to be removed.
  */
 struct ovs_skb_cb {
 	struct vport		*input_vport;
 	u16			mru;
+	u16			acts_origlen;
 	u32			cutlen;
 };
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
-- 
cgit v1.2.3


From 5829e62ac17a40ab08c1b905565604a4b5fa7af6 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 11 Sep 2017 21:56:20 +0200
Subject: openvswitch: Fix an error handling path in
 'ovs_nla_init_match_and_action()'

All other error handling paths in this function go through the 'error'
label. This one should do the same.

Fixes: 9cc9a5cb176c ("datapath: Avoid using stack larger than 1024.")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'net/openvswitch/datapath.c')

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 76cf273a56c7..c3aec6227c91 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1112,7 +1112,8 @@ static int ovs_nla_init_match_and_action(struct net *net,
 		if (!a[OVS_FLOW_ATTR_KEY]) {
 			OVS_NLERR(log,
 				  "Flow key attribute not present in set flow.");
-			return -EINVAL;
+			error = -EINVAL;
+			goto error;
 		}
 
 		*acts = get_flow_actions(net, a[OVS_FLOW_ATTR_ACTIONS], key,
-- 
cgit v1.2.3


From 9354d452034273a50a4fd703bea31e5d6b1fc20b Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Thu, 2 Nov 2017 17:04:37 -0200
Subject: openvswitch: reliable interface indentification in port dumps

This patch allows reliable identification of netdevice interfaces connected
to openvswitch bridges. In particular, user space queries the netdev
interfaces belonging to the ports for statistics, up/down state, etc.
Datapath dump needs to provide enough information for the user space to be
able to do that.

Currently, only interface names are returned. This is not sufficient, as
openvswitch allows its ports to be in different name spaces and the
interface name is valid only in its name space. What is needed and generally
used in other netlink APIs, is the pair ifindex+netnsid.

The solution is addition of the ifindex+netnsid pair (or only ifindex if in
the same name space) to vport get/dump operation.

On request side, ideally the ifindex+netnsid pair could be used to
get/set/del the corresponding vport. This is not implemented by this patch
and can be added later if needed.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/openvswitch.h |  2 ++
 net/openvswitch/datapath.c       | 47 +++++++++++++++++++++++++++++-----------
 net/openvswitch/datapath.h       |  4 ++--
 net/openvswitch/dp_notify.c      |  4 ++--
 4 files changed, 40 insertions(+), 17 deletions(-)

(limited to 'net/openvswitch/datapath.c')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index ffe397daad49..501e4c4e2a03 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -258,6 +258,8 @@ enum ovs_vport_attr {
 				/* receiving upcalls */
 	OVS_VPORT_ATTR_STATS,	/* struct ovs_vport_stats */
 	OVS_VPORT_ATTR_PAD,
+	OVS_VPORT_ATTR_IFINDEX,
+	OVS_VPORT_ATTR_NETNSID,
 	__OVS_VPORT_ATTR_MAX
 };
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index c3aec6227c91..4d38ac044cee 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1848,7 +1848,8 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = {
 
 /* Called with ovs_mutex or RCU read lock. */
 static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
-				   u32 portid, u32 seq, u32 flags, u8 cmd)
+				   struct net *net, u32 portid, u32 seq,
+				   u32 flags, u8 cmd)
 {
 	struct ovs_header *ovs_header;
 	struct ovs_vport_stats vport_stats;
@@ -1864,9 +1865,17 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 	if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) ||
 	    nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) ||
 	    nla_put_string(skb, OVS_VPORT_ATTR_NAME,
-			   ovs_vport_name(vport)))
+			   ovs_vport_name(vport)) ||
+	    nla_put_u32(skb, OVS_VPORT_ATTR_IFINDEX, vport->dev->ifindex))
 		goto nla_put_failure;
 
+	if (!net_eq(net, dev_net(vport->dev))) {
+		int id = peernet2id_alloc(net, dev_net(vport->dev));
+
+		if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id))
+			goto nla_put_failure;
+	}
+
 	ovs_vport_get_stats(vport, &vport_stats);
 	if (nla_put_64bit(skb, OVS_VPORT_ATTR_STATS,
 			  sizeof(struct ovs_vport_stats), &vport_stats,
@@ -1896,8 +1905,8 @@ static struct sk_buff *ovs_vport_cmd_alloc_info(void)
 }
 
 /* Called with ovs_mutex, only via ovs_dp_notify_wq(). */
-struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
-					 u32 seq, u8 cmd)
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
+					 u32 portid, u32 seq, u8 cmd)
 {
 	struct sk_buff *skb;
 	int retval;
@@ -1906,7 +1915,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd);
+	retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd);
 	BUG_ON(retval < 0);
 
 	return skb;
@@ -1920,6 +1929,8 @@ static struct vport *lookup_vport(struct net *net,
 	struct datapath *dp;
 	struct vport *vport;
 
+	if (a[OVS_VPORT_ATTR_IFINDEX])
+		return ERR_PTR(-EOPNOTSUPP);
 	if (a[OVS_VPORT_ATTR_NAME]) {
 		vport = ovs_vport_locate(net, nla_data(a[OVS_VPORT_ATTR_NAME]));
 		if (!vport)
@@ -1944,6 +1955,7 @@ static struct vport *lookup_vport(struct net *net,
 		return vport;
 	} else
 		return ERR_PTR(-EINVAL);
+
 }
 
 /* Called with ovs_mutex */
@@ -1983,6 +1995,8 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
 	    !a[OVS_VPORT_ATTR_UPCALL_PID])
 		return -EINVAL;
+	if (a[OVS_VPORT_ATTR_IFINDEX])
+		return -EOPNOTSUPP;
 
 	port_no = a[OVS_VPORT_ATTR_PORT_NO]
 		? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0;
@@ -2032,8 +2046,9 @@ restart:
 		goto exit_unlock_free;
 	}
 
-	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
-				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+				      info->snd_portid, info->snd_seq, 0,
+				      OVS_VPORT_CMD_NEW);
 
 	if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom)
 		update_headroom(dp);
@@ -2090,8 +2105,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 			goto exit_unlock_free;
 	}
 
-	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
-				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+				      info->snd_portid, info->snd_seq, 0,
+				      OVS_VPORT_CMD_NEW);
 	BUG_ON(err < 0);
 
 	ovs_unlock();
@@ -2128,8 +2144,9 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		goto exit_unlock_free;
 	}
 
-	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
-				      info->snd_seq, 0, OVS_VPORT_CMD_DEL);
+	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+				      info->snd_portid, info->snd_seq, 0,
+				      OVS_VPORT_CMD_DEL);
 	BUG_ON(err < 0);
 
 	/* the vport deletion may trigger dp headroom update */
@@ -2169,8 +2186,9 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
 		goto exit_unlock_free;
-	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
-				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+				      info->snd_portid, info->snd_seq, 0,
+				      OVS_VPORT_CMD_NEW);
 	BUG_ON(err < 0);
 	rcu_read_unlock();
 
@@ -2202,6 +2220,7 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) {
 			if (j >= skip &&
 			    ovs_vport_cmd_fill_info(vport, skb,
+						    sock_net(skb->sk),
 						    NETLINK_CB(cb->skb).portid,
 						    cb->nlh->nlmsg_seq,
 						    NLM_F_MULTI,
@@ -2228,6 +2247,8 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
+	[OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
 };
 
 static const struct genl_ops dp_vport_genl_ops[] = {
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 480600649d0b..4a104ef9e12c 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -200,8 +200,8 @@ int ovs_dp_upcall(struct datapath *, struct sk_buff *,
 		  uint32_t cutlen);
 
 const char *ovs_dp_name(const struct datapath *dp);
-struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
-					 u8 cmd);
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
+					 u32 portid, u32 seq, u8 cmd);
 
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			const struct sw_flow_actions *, struct sw_flow_key *);
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index 653d073bae45..f3ee2f2825c0 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -30,8 +30,8 @@ static void dp_detach_port_notify(struct vport *vport)
 	struct datapath *dp;
 
 	dp = vport->dp;
-	notify = ovs_vport_cmd_build_info(vport, 0, 0,
-					  OVS_VPORT_CMD_DEL);
+	notify = ovs_vport_cmd_build_info(vport, ovs_dp_get_net(dp),
+					  0, 0, OVS_VPORT_CMD_DEL);
 	ovs_dp_detach_port(vport);
 	if (IS_ERR(notify)) {
 		genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0,
-- 
cgit v1.2.3


From 9602c01e57f7b868d748c2ba2aef0efa64b71ffc Mon Sep 17 00:00:00 2001
From: Andy Zhou <azhou@ovn.org>
Date: Fri, 10 Nov 2017 12:09:41 -0800
Subject: openvswitch: export get_dp() API.

Later patches will invoke get_dp() outside of datapath.c. Export it.

Signed-off-by: Andy Zhou <azhou@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 29 -----------------------------
 net/openvswitch/datapath.h | 31 +++++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+), 29 deletions(-)

(limited to 'net/openvswitch/datapath.c')

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 4d38ac044cee..6e098035bb8f 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -142,35 +142,6 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
 				  const struct dp_upcall_info *,
 				  uint32_t cutlen);
 
-/* Must be called with rcu_read_lock. */
-static struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
-{
-	struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex);
-
-	if (dev) {
-		struct vport *vport = ovs_internal_dev_get_vport(dev);
-		if (vport)
-			return vport->dp;
-	}
-
-	return NULL;
-}
-
-/* The caller must hold either ovs_mutex or rcu_read_lock to keep the
- * returned dp pointer valid.
- */
-static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
-{
-	struct datapath *dp;
-
-	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
-	rcu_read_lock();
-	dp = get_dp_rcu(net, dp_ifindex);
-	rcu_read_unlock();
-
-	return dp;
-}
-
 /* Must be called with rcu_read_lock or ovs_mutex. */
 const char *ovs_dp_name(const struct datapath *dp)
 {
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 4a104ef9e12c..954c4ed465a5 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -30,6 +30,7 @@
 #include "conntrack.h"
 #include "flow.h"
 #include "flow_table.h"
+#include "vport-internal_dev.h"
 
 #define DP_MAX_PORTS           USHRT_MAX
 #define DP_VPORT_HASH_BUCKETS  1024
@@ -190,6 +191,36 @@ static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_n
 	return ovs_lookup_vport(dp, port_no);
 }
 
+/* Must be called with rcu_read_lock. */
+static inline struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
+{
+	struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex);
+
+	if (dev) {
+		struct vport *vport = ovs_internal_dev_get_vport(dev);
+
+		if (vport)
+			return vport->dp;
+	}
+
+	return NULL;
+}
+
+/* The caller must hold either ovs_mutex or rcu_read_lock to keep the
+ * returned dp pointer valid.
+ */
+static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
+{
+	struct datapath *dp;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
+	rcu_read_lock();
+	dp = get_dp_rcu(net, dp_ifindex);
+	rcu_read_unlock();
+
+	return dp;
+}
+
 extern struct notifier_block ovs_dp_device_notifier;
 extern struct genl_family dp_vport_genl_family;
 
-- 
cgit v1.2.3


From 96fbc13d7e770b542d2d1fcf700d0baadc6e8063 Mon Sep 17 00:00:00 2001
From: Andy Zhou <azhou@ovn.org>
Date: Fri, 10 Nov 2017 12:09:42 -0800
Subject: openvswitch: Add meter infrastructure

OVS kernel datapath so far does not support Openflow meter action.
This is the first stab at adding kernel datapath meter support.
This implementation supports only drop band type.

Signed-off-by: Andy Zhou <azhou@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/Makefile   |   1 +
 net/openvswitch/datapath.c |  14 +-
 net/openvswitch/datapath.h |   3 +
 net/openvswitch/meter.c    | 604 +++++++++++++++++++++++++++++++++++++++++++++
 net/openvswitch/meter.h    |  54 ++++
 5 files changed, 674 insertions(+), 2 deletions(-)
 create mode 100644 net/openvswitch/meter.c
 create mode 100644 net/openvswitch/meter.h

(limited to 'net/openvswitch/datapath.c')

diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile
index 299f4476cf44..41109c326f3a 100644
--- a/net/openvswitch/Makefile
+++ b/net/openvswitch/Makefile
@@ -12,6 +12,7 @@ openvswitch-y := \
 	flow.o \
 	flow_netlink.o \
 	flow_table.o \
+	meter.o \
 	vport.o \
 	vport-internal_dev.o \
 	vport-netdev.o
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6e098035bb8f..0dab33fb9844 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -55,6 +55,7 @@
 #include "flow.h"
 #include "flow_table.h"
 #include "flow_netlink.h"
+#include "meter.h"
 #include "vport-internal_dev.h"
 #include "vport-netdev.h"
 
@@ -174,6 +175,7 @@ static void destroy_dp_rcu(struct rcu_head *rcu)
 	ovs_flow_tbl_destroy(&dp->table);
 	free_percpu(dp->stats_percpu);
 	kfree(dp->ports);
+	ovs_meters_exit(dp);
 	kfree(dp);
 }
 
@@ -1572,6 +1574,10 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
 		INIT_HLIST_HEAD(&dp->ports[i]);
 
+	err = ovs_meters_init(dp);
+	if (err)
+		goto err_destroy_ports_array;
+
 	/* Set up our datapath device. */
 	parms.name = nla_data(a[OVS_DP_ATTR_NAME]);
 	parms.type = OVS_VPORT_TYPE_INTERNAL;
@@ -1600,7 +1606,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 				ovs_dp_reset_user_features(skb, info);
 		}
 
-		goto err_destroy_ports_array;
+		goto err_destroy_meters;
 	}
 
 	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1615,8 +1621,10 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
-err_destroy_ports_array:
+err_destroy_meters:
 	ovs_unlock();
+	ovs_meters_exit(dp);
+err_destroy_ports_array:
 	kfree(dp->ports);
 err_destroy_percpu:
 	free_percpu(dp->stats_percpu);
@@ -2265,6 +2273,7 @@ static struct genl_family * const dp_genl_families[] = {
 	&dp_vport_genl_family,
 	&dp_flow_genl_family,
 	&dp_packet_genl_family,
+	&dp_meter_genl_family,
 };
 
 static void dp_unregister_genl(int n_families)
@@ -2445,3 +2454,4 @@ MODULE_ALIAS_GENL_FAMILY(OVS_DATAPATH_FAMILY);
 MODULE_ALIAS_GENL_FAMILY(OVS_VPORT_FAMILY);
 MODULE_ALIAS_GENL_FAMILY(OVS_FLOW_FAMILY);
 MODULE_ALIAS_GENL_FAMILY(OVS_PACKET_FAMILY);
+MODULE_ALIAS_GENL_FAMILY(OVS_METER_FAMILY);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 954c4ed465a5..5d2997b42460 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -92,6 +92,9 @@ struct datapath {
 	u32 user_features;
 
 	u32 max_headroom;
+
+	/* Switch meters. */
+	struct hlist_head *meters;
 };
 
 /**
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
new file mode 100644
index 000000000000..2a5ba356c472
--- /dev/null
+++ b/net/openvswitch/meter.c
@@ -0,0 +1,604 @@
+/*
+ * Copyright (c) 2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/if.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/openvswitch.h>
+#include <linux/netlink.h>
+#include <linux/rculist.h>
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "datapath.h"
+#include "meter.h"
+
+#define METER_HASH_BUCKETS 1024
+
+static const struct nla_policy meter_policy[OVS_METER_ATTR_MAX + 1] = {
+	[OVS_METER_ATTR_ID] = { .type = NLA_U32, },
+	[OVS_METER_ATTR_KBPS] = { .type = NLA_FLAG },
+	[OVS_METER_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) },
+	[OVS_METER_ATTR_BANDS] = { .type = NLA_NESTED },
+	[OVS_METER_ATTR_USED] = { .type = NLA_U64 },
+	[OVS_METER_ATTR_CLEAR] = { .type = NLA_FLAG },
+	[OVS_METER_ATTR_MAX_METERS] = { .type = NLA_U32 },
+	[OVS_METER_ATTR_MAX_BANDS] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy band_policy[OVS_BAND_ATTR_MAX + 1] = {
+	[OVS_BAND_ATTR_TYPE] = { .type = NLA_U32, },
+	[OVS_BAND_ATTR_RATE] = { .type = NLA_U32, },
+	[OVS_BAND_ATTR_BURST] = { .type = NLA_U32, },
+	[OVS_BAND_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) },
+};
+
+static void rcu_free_ovs_meter_callback(struct rcu_head *rcu)
+{
+	struct dp_meter *meter = container_of(rcu, struct dp_meter, rcu);
+
+	kfree(meter);
+}
+
+static void ovs_meter_free(struct dp_meter *meter)
+{
+	if (!meter)
+		return;
+
+	call_rcu(&meter->rcu, rcu_free_ovs_meter_callback);
+}
+
+static struct hlist_head *meter_hash_bucket(const struct datapath *dp,
+					    u32 meter_id)
+{
+	return &dp->meters[meter_id & (METER_HASH_BUCKETS - 1)];
+}
+
+/* Call with ovs_mutex or RCU read lock. */
+static struct dp_meter *lookup_meter(const struct datapath *dp,
+				     u32 meter_id)
+{
+	struct dp_meter *meter;
+	struct hlist_head *head;
+
+	head = meter_hash_bucket(dp, meter_id);
+	hlist_for_each_entry_rcu(meter, head, dp_hash_node) {
+		if (meter->id == meter_id)
+			return meter;
+	}
+	return NULL;
+}
+
+static void attach_meter(struct datapath *dp, struct dp_meter *meter)
+{
+	struct hlist_head *head = meter_hash_bucket(dp, meter->id);
+
+	hlist_add_head_rcu(&meter->dp_hash_node, head);
+}
+
+static void detach_meter(struct dp_meter *meter)
+{
+	ASSERT_OVSL();
+	if (meter)
+		hlist_del_rcu(&meter->dp_hash_node);
+}
+
+static struct sk_buff *
+ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd,
+			  struct ovs_header **ovs_reply_header)
+{
+	struct sk_buff *skb;
+	struct ovs_header *ovs_header = info->userhdr;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	*ovs_reply_header = genlmsg_put(skb, info->snd_portid,
+					info->snd_seq,
+					&dp_meter_genl_family, 0, cmd);
+	if (!ovs_reply_header) {
+		nlmsg_free(skb);
+		return ERR_PTR(-EMSGSIZE);
+	}
+	(*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex;
+
+	return skb;
+}
+
+static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id,
+				     struct dp_meter *meter)
+{
+	struct nlattr *nla;
+	struct dp_meter_band *band;
+	u16 i;
+
+	if (nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id))
+		goto error;
+
+	if (!meter)
+		return 0;
+
+	if (nla_put(reply, OVS_METER_ATTR_STATS,
+		    sizeof(struct ovs_flow_stats), &meter->stats) ||
+	    nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used,
+			      OVS_METER_ATTR_PAD))
+		goto error;
+
+	nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS);
+	if (!nla)
+		goto error;
+
+	band = meter->bands;
+
+	for (i = 0; i < meter->n_bands; ++i, ++band) {
+		struct nlattr *band_nla;
+
+		band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC);
+		if (!band_nla || nla_put(reply, OVS_BAND_ATTR_STATS,
+					 sizeof(struct ovs_flow_stats),
+					 &band->stats))
+			goto error;
+		nla_nest_end(reply, band_nla);
+	}
+	nla_nest_end(reply, nla);
+
+	return 0;
+error:
+	return -EMSGSIZE;
+}
+
+static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *reply;
+	struct ovs_header *ovs_reply_header;
+	struct nlattr *nla, *band_nla;
+	int err;
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_FEATURES,
+					  &ovs_reply_header);
+	if (!reply)
+		return PTR_ERR(reply);
+
+	if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS, U32_MAX) ||
+	    nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS))
+		goto nla_put_failure;
+
+	nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS);
+	if (!nla)
+		goto nla_put_failure;
+
+	band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC);
+	if (!band_nla)
+		goto nla_put_failure;
+	/* Currently only DROP band type is supported. */
+	if (nla_put_u32(reply, OVS_BAND_ATTR_TYPE, OVS_METER_BAND_TYPE_DROP))
+		goto nla_put_failure;
+	nla_nest_end(reply, band_nla);
+	nla_nest_end(reply, nla);
+
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+nla_put_failure:
+	nlmsg_free(reply);
+	err = -EMSGSIZE;
+	return err;
+}
+
+static struct dp_meter *dp_meter_create(struct nlattr **a)
+{
+	struct nlattr *nla;
+	int rem;
+	u16 n_bands = 0;
+	struct dp_meter *meter;
+	struct dp_meter_band *band;
+	int err;
+
+	/* Validate attributes, count the bands. */
+	if (!a[OVS_METER_ATTR_BANDS])
+		return ERR_PTR(-EINVAL);
+
+	nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem)
+		if (++n_bands > DP_MAX_BANDS)
+			return ERR_PTR(-EINVAL);
+
+	/* Allocate and set up the meter before locking anything. */
+	meter = kzalloc(n_bands * sizeof(struct dp_meter_band) +
+			sizeof(*meter), GFP_KERNEL);
+	if (!meter)
+		return ERR_PTR(-ENOMEM);
+
+	meter->used = div_u64(ktime_get_ns(), 1000 * 1000);
+	meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0;
+	meter->keep_stats = !a[OVS_METER_ATTR_CLEAR];
+	spin_lock_init(&meter->lock);
+	if (meter->keep_stats && a[OVS_METER_ATTR_STATS]) {
+		meter->stats = *(struct ovs_flow_stats *)
+			nla_data(a[OVS_METER_ATTR_STATS]);
+	}
+	meter->n_bands = n_bands;
+
+	/* Set up meter bands. */
+	band = meter->bands;
+	nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) {
+		struct nlattr *attr[OVS_BAND_ATTR_MAX + 1];
+		u32 band_max_delta_t;
+
+		err = nla_parse((struct nlattr **)&attr, OVS_BAND_ATTR_MAX,
+				nla_data(nla), nla_len(nla), band_policy,
+				NULL);
+		if (err)
+			goto exit_free_meter;
+
+		if (!attr[OVS_BAND_ATTR_TYPE] ||
+		    !attr[OVS_BAND_ATTR_RATE] ||
+		    !attr[OVS_BAND_ATTR_BURST]) {
+			err = -EINVAL;
+			goto exit_free_meter;
+		}
+
+		band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]);
+		band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]);
+		band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]);
+		/* Figure out max delta_t that is enough to fill any bucket.
+		 * Keep max_delta_t size to the bucket units:
+		 * pkts => 1/1000 packets, kilobits => bits.
+		 */
+		band_max_delta_t = (band->burst_size + band->rate) * 1000;
+		/* Start with a full bucket. */
+		band->bucket = band_max_delta_t;
+		if (band_max_delta_t > meter->max_delta_t)
+			meter->max_delta_t = band_max_delta_t;
+		band++;
+	}
+
+	return meter;
+
+exit_free_meter:
+	kfree(meter);
+	return ERR_PTR(err);
+}
+
+static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct dp_meter *meter, *old_meter;
+	struct sk_buff *reply;
+	struct ovs_header *ovs_reply_header;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct datapath *dp;
+	int err;
+	u32 meter_id;
+	bool failed;
+
+	meter = dp_meter_create(a);
+	if (IS_ERR_OR_NULL(meter))
+		return PTR_ERR(meter);
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET,
+					  &ovs_reply_header);
+	if (IS_ERR(reply)) {
+		err = PTR_ERR(reply);
+		goto exit_free_meter;
+	}
+
+	ovs_lock();
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	if (!a[OVS_METER_ATTR_ID]) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+
+	/* Cannot fail after this. */
+	old_meter = lookup_meter(dp, meter_id);
+	detach_meter(old_meter);
+	attach_meter(dp, meter);
+	ovs_unlock();
+
+	/* Build response with the meter_id and stats from
+	 * the old meter, if any.
+	 */
+	failed = nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id);
+	WARN_ON(failed);
+	if (old_meter) {
+		spin_lock_bh(&old_meter->lock);
+		if (old_meter->keep_stats) {
+			err = ovs_meter_cmd_reply_stats(reply, meter_id,
+							old_meter);
+			WARN_ON(err);
+		}
+		spin_unlock_bh(&old_meter->lock);
+		ovs_meter_free(old_meter);
+	}
+
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	ovs_unlock();
+	nlmsg_free(reply);
+exit_free_meter:
+	kfree(meter);
+	return err;
+}
+
+static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	u32 meter_id;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_reply_header;
+	struct datapath *dp;
+	int err;
+	struct sk_buff *reply;
+	struct dp_meter *meter;
+
+	if (!a[OVS_METER_ATTR_ID])
+		return -EINVAL;
+
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_GET,
+					  &ovs_reply_header);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	ovs_lock();
+
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	/* Locate meter, copy stats. */
+	meter = lookup_meter(dp, meter_id);
+	if (!meter) {
+		err = -ENOENT;
+		goto exit_unlock;
+	}
+
+	spin_lock_bh(&meter->lock);
+	err = ovs_meter_cmd_reply_stats(reply, meter_id, meter);
+	spin_unlock_bh(&meter->lock);
+	if (err)
+		goto exit_unlock;
+
+	ovs_unlock();
+
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	ovs_unlock();
+	nlmsg_free(reply);
+	return err;
+}
+
+static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	u32 meter_id;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct ovs_header *ovs_reply_header;
+	struct datapath *dp;
+	int err;
+	struct sk_buff *reply;
+	struct dp_meter *old_meter;
+
+	if (!a[OVS_METER_ATTR_ID])
+		return -EINVAL;
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+
+	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_DEL,
+					  &ovs_reply_header);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	ovs_lock();
+
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	old_meter = lookup_meter(dp, meter_id);
+	if (old_meter) {
+		spin_lock_bh(&old_meter->lock);
+		err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter);
+		WARN_ON(err);
+		spin_unlock_bh(&old_meter->lock);
+		detach_meter(old_meter);
+	}
+	ovs_unlock();
+	ovs_meter_free(old_meter);
+	genlmsg_end(reply, ovs_reply_header);
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	ovs_unlock();
+	nlmsg_free(reply);
+	return err;
+}
+
+/* Meter action execution.
+ *
+ * Return true 'meter_id' drop band is triggered. The 'skb' should be
+ * dropped by the caller'.
+ */
+bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
+		       struct sw_flow_key *key, u32 meter_id)
+{
+	struct dp_meter *meter;
+	struct dp_meter_band *band;
+	long long int now_ms = div_u64(ktime_get_ns(), 1000 * 1000);
+	long long int long_delta_ms;
+	u32 delta_ms;
+	u32 cost;
+	int i, band_exceeded_max = -1;
+	u32 band_exceeded_rate = 0;
+
+	meter = lookup_meter(dp, meter_id);
+	/* Do not drop the packet when there is no meter. */
+	if (!meter)
+		return false;
+
+	/* Lock the meter while using it. */
+	spin_lock(&meter->lock);
+
+	long_delta_ms = (now_ms - meter->used); /* ms */
+
+	/* Make sure delta_ms will not be too large, so that bucket will not
+	 * wrap around below.
+	 */
+	delta_ms = (long_delta_ms > (long long int)meter->max_delta_t)
+		   ? meter->max_delta_t : (u32)long_delta_ms;
+
+	/* Update meter statistics.
+	 */
+	meter->used = now_ms;
+	meter->stats.n_packets += 1;
+	meter->stats.n_bytes += skb->len;
+
+	/* Bucket rate is either in kilobits per second, or in packets per
+	 * second.  We maintain the bucket in the units of either bits or
+	 * 1/1000th of a packet, correspondingly.
+	 * Then, when rate is multiplied with milliseconds, we get the
+	 * bucket units:
+	 * msec * kbps = bits, and
+	 * msec * packets/sec = 1/1000 packets.
+	 *
+	 * 'cost' is the number of bucket units in this packet.
+	 */
+	cost = (meter->kbps) ? skb->len * 8 : 1000;
+
+	/* Update all bands and find the one hit with the highest rate. */
+	for (i = 0; i < meter->n_bands; ++i) {
+		long long int max_bucket_size;
+
+		band = &meter->bands[i];
+		max_bucket_size = (band->burst_size + band->rate) * 1000;
+
+		band->bucket += delta_ms * band->rate;
+		if (band->bucket > max_bucket_size)
+			band->bucket = max_bucket_size;
+
+		if (band->bucket >= cost) {
+			band->bucket -= cost;
+		} else if (band->rate > band_exceeded_rate) {
+			band_exceeded_rate = band->rate;
+			band_exceeded_max = i;
+		}
+	}
+
+	if (band_exceeded_max >= 0) {
+		/* Update band statistics. */
+		band = &meter->bands[band_exceeded_max];
+		band->stats.n_packets += 1;
+		band->stats.n_bytes += skb->len;
+
+		/* Drop band triggered, let the caller drop the 'skb'.  */
+		if (band->type == OVS_METER_BAND_TYPE_DROP) {
+			spin_unlock(&meter->lock);
+			return true;
+		}
+	}
+
+	spin_unlock(&meter->lock);
+	return false;
+}
+
+static struct genl_ops dp_meter_genl_ops[] = {
+	{ .cmd = OVS_METER_CMD_FEATURES,
+		.flags = 0,		  /* OK for unprivileged users. */
+		.policy = meter_policy,
+		.doit = ovs_meter_cmd_features
+	},
+	{ .cmd = OVS_METER_CMD_SET,
+		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					   *  privilege.
+					   */
+		.policy = meter_policy,
+		.doit = ovs_meter_cmd_set,
+	},
+	{ .cmd = OVS_METER_CMD_GET,
+		.flags = 0,		  /* OK for unprivileged users. */
+		.policy = meter_policy,
+		.doit = ovs_meter_cmd_get,
+	},
+	{ .cmd = OVS_METER_CMD_DEL,
+		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					   *  privilege.
+					   */
+		.policy = meter_policy,
+		.doit = ovs_meter_cmd_del
+	},
+};
+
+static const struct genl_multicast_group ovs_meter_multicast_group = {
+	.name = OVS_METER_MCGROUP,
+};
+
+struct genl_family dp_meter_genl_family __ro_after_init = {
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_METER_FAMILY,
+	.version = OVS_METER_VERSION,
+	.maxattr = OVS_METER_ATTR_MAX,
+	.netnsok = true,
+	.parallel_ops = true,
+	.ops = dp_meter_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_meter_genl_ops),
+	.mcgrps = &ovs_meter_multicast_group,
+	.n_mcgrps = 1,
+	.module = THIS_MODULE,
+};
+
+int ovs_meters_init(struct datapath *dp)
+{
+	int i;
+
+	dp->meters = kmalloc_array(METER_HASH_BUCKETS,
+				   sizeof(struct hlist_head), GFP_KERNEL);
+
+	if (!dp->meters)
+		return -ENOMEM;
+
+	for (i = 0; i < METER_HASH_BUCKETS; i++)
+		INIT_HLIST_HEAD(&dp->meters[i]);
+
+	return 0;
+}
+
+void ovs_meters_exit(struct datapath *dp)
+{
+	int i;
+
+	for (i = 0; i < METER_HASH_BUCKETS; i++) {
+		struct hlist_head *head = &dp->meters[i];
+		struct dp_meter *meter;
+		struct hlist_node *n;
+
+		hlist_for_each_entry_safe(meter, n, head, dp_hash_node)
+			kfree(meter);
+	}
+
+	kfree(dp->meters);
+}
diff --git a/net/openvswitch/meter.h b/net/openvswitch/meter.h
new file mode 100644
index 000000000000..964ace2650f8
--- /dev/null
+++ b/net/openvswitch/meter.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#ifndef METER_H
+#define METER_H 1
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/genetlink.h>
+#include <linux/skbuff.h>
+
+#include "flow.h"
+struct datapath;
+
+#define DP_MAX_BANDS		1
+
+struct dp_meter_band {
+	u32 type;
+	u32 rate;
+	u32 burst_size;
+	u32 bucket; /* 1/1000 packets, or in bits */
+	struct ovs_flow_stats stats;
+};
+
+struct dp_meter {
+	spinlock_t lock;    /* Per meter lock */
+	struct rcu_head rcu;
+	struct hlist_node dp_hash_node; /*Element in datapath->meters
+					 * hash table.
+					 */
+	u32 id;
+	u16 kbps:1, keep_stats:1;
+	u16 n_bands;
+	u32 max_delta_t;
+	u64 used;
+	struct ovs_flow_stats stats;
+	struct dp_meter_band bands[];
+};
+
+extern struct genl_family dp_meter_genl_family;
+int ovs_meters_init(struct datapath *dp);
+void ovs_meters_exit(struct datapath *dp);
+bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
+		       struct sw_flow_key *key, u32 meter_id);
+
+#endif /* meter.h */
-- 
cgit v1.2.3


From 0c19f846d582af919db66a5914a0189f9f92c936 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 21 Nov 2017 10:22:25 -0500
Subject: net: accept UFO datagrams from tuntap and packet

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

Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com>
Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 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              |  1 +
 net/core/dev.c                  |  3 +-
 net/ipv4/af_inet.c              | 12 +++++-
 net/ipv4/udp_offload.c          | 49 ++++++++++++++++++++++--
 net/ipv6/output_core.c          | 31 +++++++++++++++
 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, 209 insertions(+), 14 deletions(-)

(limited to 'net/openvswitch/datapath.c')

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index b13890953ebb..e9489b88407c 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1077,7 +1077,7 @@ static long tap_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();
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5a2ea78a008f..6a7bde9bc4b2 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2370,6 +2370,8 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
 				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
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index dc8b4896b77b..b1b0ca7ccb2b 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -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)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6b274bfe489f..ef789e1d679e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4140,6 +4140,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	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;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ed06e1c28fc7..bc486ef23f20 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -568,6 +568,8 @@ enum {
 	SKB_GSO_SCTP = 1 << 14,
 
 	SKB_GSO_ESP = 1 << 15,
+
+	SKB_GSO_UDP = 1 << 16,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 210034c896e3..f144216febc6 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -9,7 +9,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *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(struct sk_buff *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;
 		}
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index ec14f0d5a3a1..f73797e2fa60 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -767,6 +767,7 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 __be32 ipv6_select_ident(struct net *net,
 			 const struct in6_addr *daddr,
 			 const struct in6_addr *saddr);
+__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 8ee29f4f5fa9..bbba19112f02 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2746,7 +2746,8 @@ 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;
 }
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ce4aa827be05..f00499a46927 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1223,9 +1223,10 @@ 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;
@@ -1260,6 +1261,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	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 */
@@ -1279,7 +1281,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	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;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e360d55be555..01801b77bd0d 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -187,16 +187,57 @@ out_unlock:
 }
 EXPORT_SYMBOL(skb_udp_tunnel_segment);
 
-static struct sk_buff *udp4_tunnel_segment(struct sk_buff *skb,
-					   netdev_features_t features)
+static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+					 netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int mss;
+	__wsum csum;
+	struct udphdr *uh;
+	struct iphdr *iph;
 
 	if (skb->encapsulation &&
 	    (skb_shinfo(skb)->gso_type &
-	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)))
+	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
 		segs = skb_udp_tunnel_segment(skb, features, false);
+		goto out;
+	}
+
+	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+		goto out;
+
+	mss = skb_shinfo(skb)->gso_size;
+	if (unlikely(skb->len <= mss))
+		goto out;
+
+	/* Do software UFO. Complete and fill in the UDP checksum as
+	 * HW cannot do checksum of UDP packets sent as multiple
+	 * IP fragments.
+	 */
 
+	uh = udp_hdr(skb);
+	iph = ip_hdr(skb);
+
+	uh->check = 0;
+	csum = skb_checksum(skb, 0, skb->len, 0);
+	uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
+	if (uh->check == 0)
+		uh->check = CSUM_MANGLED_0;
+
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	/* If there is no outer header we can fake a checksum offload
+	 * due to the fact that we have already done the checksum in
+	 * software prior to segmenting the frame.
+	 */
+	if (!skb->encap_hdr_csum)
+		features |= NETIF_F_HW_CSUM;
+
+	/* Fragment the skb. IP headers of the fragments are updated in
+	 * inet_gso_segment()
+	 */
+	segs = skb_segment(skb, features);
+out:
 	return segs;
 }
 
@@ -330,7 +371,7 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
-		.gso_segment = udp4_tunnel_segment,
+		.gso_segment = udp4_ufo_fragment,
 		.gro_receive  =	udp4_gro_receive,
 		.gro_complete =	udp4_gro_complete,
 	},
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 4a7e5ffa5108..4fe7c90962dd 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -31,6 +31,37 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
 	return id;
 }
 
+/* This function exists only for tap drivers that must support broken
+ * clients requesting UFO without specifying an IPv6 fragment ID.
+ *
+ * This is similar to ipv6_select_ident() but we use an independent hash
+ * seed to limit information leakage.
+ *
+ * The network header must be set before calling this.
+ */
+__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];
+	struct in6_addr *addrs;
+	u32 id;
+
+	addrs = skb_header_pointer(skb,
+				   skb_network_offset(skb) +
+				   offsetof(struct ipv6hdr, saddr),
+				   sizeof(buf), buf);
+	if (!addrs)
+		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]);
+	return htonl(id);
+}
+EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
+
 __be32 ipv6_select_ident(struct net *net,
 			 const struct in6_addr *daddr,
 			 const struct in6_addr *saddr)
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 455fd4e39333..a0f89ad76f9d 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -17,15 +17,94 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static struct sk_buff *udp6_tunnel_segment(struct sk_buff *skb,
-					   netdev_features_t features)
+static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
+					 netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int mss;
+	unsigned int unfrag_ip6hlen, unfrag_len;
+	struct frag_hdr *fptr;
+	u8 *packet_start, *prevhdr;
+	u8 nexthdr;
+	u8 frag_hdr_sz = sizeof(struct frag_hdr);
+	__wsum csum;
+	int tnl_hlen;
+	int err;
+
+	mss = skb_shinfo(skb)->gso_size;
+	if (unlikely(skb->len <= mss))
+		goto out;
 
 	if (skb->encapsulation && skb_shinfo(skb)->gso_type &
 	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
 		segs = skb_udp_tunnel_segment(skb, features, true);
+	else {
+		const struct ipv6hdr *ipv6h;
+		struct udphdr *uh;
+
+		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+			goto out;
+
+		/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
+		 * do checksum of UDP packets sent as multiple IP fragments.
+		 */
+
+		uh = udp_hdr(skb);
+		ipv6h = ipv6_hdr(skb);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, skb->len, 0);
+		uh->check = udp_v6_check(skb->len, &ipv6h->saddr,
+					  &ipv6h->daddr, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		/* If there is no outer header we can fake a checksum offload
+		 * due to the fact that we have already done the checksum in
+		 * software prior to segmenting the frame.
+		 */
+		if (!skb->encap_hdr_csum)
+			features |= NETIF_F_HW_CSUM;
+
+		/* Check if there is enough headroom to insert fragment header. */
+		tnl_hlen = skb_tnl_header_len(skb);
+		if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) {
+			if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz))
+				goto out;
+		}
+
+		/* Find the unfragmentable header and shift it left by frag_hdr_sz
+		 * bytes to insert fragment header.
+		 */
+		err = ip6_find_1stfragopt(skb, &prevhdr);
+		if (err < 0)
+			return ERR_PTR(err);
+		unfrag_ip6hlen = err;
+		nexthdr = *prevhdr;
+		*prevhdr = NEXTHDR_FRAGMENT;
+		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
+			     unfrag_ip6hlen + tnl_hlen;
+		packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset;
+		memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len);
+
+		SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz;
+		skb->mac_header -= frag_hdr_sz;
+		skb->network_header -= frag_hdr_sz;
+
+		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
+		fptr->nexthdr = nexthdr;
+		fptr->reserved = 0;
+		fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb);
+
+		/* Fragment the skb. ipv6 header and the remaining fields of the
+		 * fragment header are updated in ipv6_gso_segment()
+		 */
+		segs = skb_segment(skb, features);
+	}
 
+out:
 	return segs;
 }
 
@@ -75,7 +154,7 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv6_offload = {
 	.callbacks = {
-		.gso_segment	=	udp6_tunnel_segment,
+		.gso_segment	=	udp6_ufo_fragment,
 		.gro_receive	=	udp6_gro_receive,
 		.gro_complete	=	udp6_gro_complete,
 	},
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 0dab33fb9844..99cfafc2a139 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -308,6 +308,8 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     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;
 
@@ -318,9 +320,21 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	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;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 864ddb1e3642..dbe2379329c5 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -631,7 +631,8 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			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;
@@ -747,6 +748,9 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 
 		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)) {
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 1c40caadcff9..d836f998117b 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -229,6 +229,9 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
 	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_buff *skb, unsigned int ihl,
 	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,
-- 
cgit v1.2.3