瀏覽代碼

Merge branch 'act_tunnel_key'

Hadar Hen Zion says:

====================
net/sched: ip tunnel metadata set/release/classify by using TC

This patchset introduces ip tunnel manipulation support using the TC subsystem.

In the decap flow, it enables the user to redirect packets from a shared tunnel
device and classify by outer and inner headers. The outer headers are extracted
from the metadata and used by the flower filter. A new action act_tunnel_key,
releases the metadata.

In the encap flow, act_tunnel_key creates a metadata object to be used by the
shared tunnel device. The actual redirection to the tunnel device is done using
act_mirred.

For example:
$ tc qdisc add dev vnet0 ingress
$ tc filter add dev vnet0 protocol ip parent ffff: \
	flower \
	 ip_proto 1 \
	action tunnel_key set \
	 src_ip 11.11.0.1 \
	 dst_ip 11.11.0.2 \
	 id 11 \
	action mirred egress redirect dev vxlan0

$ tc qdisc add dev vxlan0 ingress
$ tc filter add dev vxlan0 protocol ip parent ffff: \
	flower \
	 enc_src_ip 11.11.0.2 \
	 enc_dst_ip 11.11.0.1 \
	 enc_key_id 11 \
	action tunnel_key release \
	action mirred egress redirect dev vnet0

Amir & Hadar

Changes from V6:
- Add kfree_rcu to tunnel_key_release function
- Use reverse Christmas tree order in tunnel_key_init function

Changes from V5:
- Add __rcu notation to struct tcf_tunnel_key_params in struct tcf_tunnel_key
- Fix indentation in include/net/dst_metadata.h
- Fix syntx error in commit message

Changes from V4:
- Fix tunnel_key_init function error flow.
- Add 'action' variable to struct tcf_tunnel_key_params and use it instead of
  tcf_action variable which is not protected by rcu lock.

Changes from V3:
- Use percpu stats
- No spinlock on datapatch - protecting parameters with rcu
- Fix buggy handling of set/release dst
- Use nla_get_in_addr and nla_put_in_addr
- Fix change logs
- Pass in6_addr by pointer
- Rename utility functions to start with double underscore

Changes from V2:
- Use union in struct fl_flow_key for enc_ipv6 and enc_ipv4.
- Rename functions _ip_tun_rx_dst and _ipv6_tun_rx_dst to _ip_tun_set_dst and
  _ipv6_tun_set_dst accordingly.
- Remove local parameter 'encapdecap' from tunnel_key_init function.
- Don't copy in6_addr values in tunnel_key_dump_addresses function, use pointers.

Changes from V1:
- More cleanups to key32_to_tunnel_id() and tunnel_id_to_key32()
- IPv6 Support added
- Set TUNNEL_KEY flag to make GRE work
- Handle zero tunnel id properly in act_tunnel_key
- Don't leave junk in decap action
- Fix bug in act_tunnel_key initialization where (exists & ocr) is true
- Remove BUG() from code
- Rename action to tunnel_key
- Improve grep-ability of code
- Reuse code from ip_tun_rx_dst() and ipv6_tun_rx_dst()

Changes from RFC:
- Add a new action instead of making mirred too complex
- No need to specify UDP port in action - it is already in the tunnel device
  configuration
- Added a decap operation to drop tunnel metadata
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller 9 年之前
父節點
當前提交
d1ba24feb4

+ 2 - 2
drivers/net/vxlan.c

@@ -1291,7 +1291,7 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 		struct metadata_dst *tun_dst;
 
 		tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY,
-					 vxlan_vni_to_tun_id(vni), sizeof(*md));
+					 key32_to_tunnel_id(vni), sizeof(*md));
 
 		if (!tun_dst)
 			goto drop;
@@ -1945,7 +1945,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto drop;
 		}
 		dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
-		vni = vxlan_tun_id_to_vni(info->key.tun_id);
+		vni = tunnel_id_to_key32(info->key.tun_id);
 		remote_ip.sa.sa_family = ip_tunnel_info_af(info);
 		if (remote_ip.sa.sa_family == AF_INET) {
 			remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst;

+ 39 - 13
include/net/dst_metadata.h

@@ -112,12 +112,13 @@ static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb
 	return &dst->u.tun_info;
 }
 
-static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
-						 __be16 flags,
-						 __be64 tunnel_id,
-						 int md_size)
+static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr,
+						    __be32 daddr,
+						    __u8 tos, __u8 ttl,
+						    __be16 flags,
+						    __be64 tunnel_id,
+						    int md_size)
 {
-	const struct iphdr *iph = ip_hdr(skb);
 	struct metadata_dst *tun_dst;
 
 	tun_dst = tun_rx_dst(md_size);
@@ -125,17 +126,30 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
 		return NULL;
 
 	ip_tunnel_key_init(&tun_dst->u.tun_info.key,
-			   iph->saddr, iph->daddr, iph->tos, iph->ttl,
+			   saddr, daddr, tos, ttl,
 			   0, 0, 0, tunnel_id, flags);
 	return tun_dst;
 }
 
-static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
+static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
 						 __be16 flags,
 						 __be64 tunnel_id,
 						 int md_size)
 {
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	const struct iphdr *iph = ip_hdr(skb);
+
+	return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl,
+				flags, tunnel_id, md_size);
+}
+
+static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr,
+						      const struct in6_addr *daddr,
+						      __u8 tos, __u8 ttl,
+						      __be32 label,
+						      __be16 flags,
+						      __be64 tunnel_id,
+						      int md_size)
+{
 	struct metadata_dst *tun_dst;
 	struct ip_tunnel_info *info;
 
@@ -150,14 +164,26 @@ static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
 	info->key.tp_src = 0;
 	info->key.tp_dst = 0;
 
-	info->key.u.ipv6.src = ip6h->saddr;
-	info->key.u.ipv6.dst = ip6h->daddr;
+	info->key.u.ipv6.src = *saddr;
+	info->key.u.ipv6.dst = *daddr;
 
-	info->key.tos = ipv6_get_dsfield(ip6h);
-	info->key.ttl = ip6h->hop_limit;
-	info->key.label = ip6_flowlabel(ip6h);
+	info->key.tos = tos;
+	info->key.ttl = ttl;
+	info->key.label = label;
 
 	return tun_dst;
 }
 
+static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
+						   __be16 flags,
+						   __be64 tunnel_id,
+						   int md_size)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+
+	return __ipv6_tun_set_dst(&ip6h->saddr, &ip6h->daddr,
+				  ipv6_get_dsfield(ip6h), ip6h->hop_limit,
+				  ip6_flowlabel(ip6h), flags, tunnel_id,
+				  md_size);
+}
 #endif /* __NET_DST_METADATA_H */

+ 19 - 0
include/net/ip_tunnels.h

@@ -222,6 +222,25 @@ static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info
 	return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET;
 }
 
+static inline __be64 key32_to_tunnel_id(__be32 key)
+{
+#ifdef __BIG_ENDIAN
+	return (__force __be64)key;
+#else
+	return (__force __be64)((__force u64)key << 32);
+#endif
+}
+
+/* Returns the least-significant 32 bits of a __be64. */
+static inline __be32 tunnel_id_to_key32(__be64 tun_id)
+{
+#ifdef __BIG_ENDIAN
+	return (__force __be32)tun_id;
+#else
+	return (__force __be32)((__force u64)tun_id >> 32);
+#endif
+}
+
 #ifdef CONFIG_INET
 
 int ip_tunnel_init(struct net_device *dev);

+ 30 - 0
include/net/tc_act/tc_tunnel_key.h

@@ -0,0 +1,30 @@
+/*
+ * Copyright (c) 2016, Amir Vadai <amir@vadai.me>
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __NET_TC_TUNNEL_KEY_H
+#define __NET_TC_TUNNEL_KEY_H
+
+#include <net/act_api.h>
+
+struct tcf_tunnel_key_params {
+	struct rcu_head		rcu;
+	int			tcft_action;
+	int			action;
+	struct metadata_dst     *tcft_enc_metadata;
+};
+
+struct tcf_tunnel_key {
+	struct tc_action	      common;
+	struct tcf_tunnel_key_params __rcu *params;
+};
+
+#define to_tunnel_key(a) ((struct tcf_tunnel_key *)a)
+
+#endif /* __NET_TC_TUNNEL_KEY_H */

+ 0 - 18
include/net/vxlan.h

@@ -350,24 +350,6 @@ static inline __be32 vxlan_vni_field(__be32 vni)
 #endif
 }
 
-static inline __be32 vxlan_tun_id_to_vni(__be64 tun_id)
-{
-#if defined(__BIG_ENDIAN)
-	return (__force __be32)tun_id;
-#else
-	return (__force __be32)((__force u64)tun_id >> 32);
-#endif
-}
-
-static inline __be64 vxlan_vni_to_tun_id(__be32 vni)
-{
-#if defined(__BIG_ENDIAN)
-	return (__force __be64)vni;
-#else
-	return (__force __be64)((u64)(__force u32)vni << 32);
-#endif
-}
-
 static inline size_t vxlan_rco_start(__be32 vni_field)
 {
 	return be32_to_cpu(vni_field & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;

+ 11 - 0
include/uapi/linux/pkt_cls.h

@@ -431,6 +431,17 @@ enum {
 	TCA_FLOWER_KEY_VLAN_ID,
 	TCA_FLOWER_KEY_VLAN_PRIO,
 	TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+
+	TCA_FLOWER_KEY_ENC_KEY_ID,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
 	__TCA_FLOWER_MAX,
 };
 

+ 41 - 0
include/uapi/linux/tc_act/tc_tunnel_key.h

@@ -0,0 +1,41 @@
+/*
+ * Copyright (c) 2016, Amir Vadai <amir@vadai.me>
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_TUNNEL_KEY_H
+#define __LINUX_TC_TUNNEL_KEY_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_TUNNEL_KEY 17
+
+#define TCA_TUNNEL_KEY_ACT_SET	    1
+#define TCA_TUNNEL_KEY_ACT_RELEASE  2
+
+struct tc_tunnel_key {
+	tc_gen;
+	int t_action;
+};
+
+enum {
+	TCA_TUNNEL_KEY_UNSPEC,
+	TCA_TUNNEL_KEY_TM,
+	TCA_TUNNEL_KEY_PARMS,
+	TCA_TUNNEL_KEY_ENC_IPV4_SRC,	/* be32 */
+	TCA_TUNNEL_KEY_ENC_IPV4_DST,	/* be32 */
+	TCA_TUNNEL_KEY_ENC_IPV6_SRC,	/* struct in6_addr */
+	TCA_TUNNEL_KEY_ENC_IPV6_DST,	/* struct in6_addr */
+	TCA_TUNNEL_KEY_ENC_KEY_ID,	/* be64 */
+	TCA_TUNNEL_KEY_PAD,
+	__TCA_TUNNEL_KEY_MAX,
+};
+
+#define TCA_TUNNEL_KEY_MAX (__TCA_TUNNEL_KEY_MAX - 1)
+
+#endif

+ 2 - 21
net/ipv4/ip_gre.c

@@ -246,25 +246,6 @@ static void gre_err(struct sk_buff *skb, u32 info)
 	ipgre_err(skb, info, &tpi);
 }
 
-static __be64 key_to_tunnel_id(__be32 key)
-{
-#ifdef __BIG_ENDIAN
-	return (__force __be64)((__force u32)key);
-#else
-	return (__force __be64)((__force u64)key << 32);
-#endif
-}
-
-/* Returns the least-significant 32 bits of a __be64. */
-static __be32 tunnel_id_to_key(__be64 x)
-{
-#ifdef __BIG_ENDIAN
-	return (__force __be32)x;
-#else
-	return (__force __be32)((__force u64)x >> 32);
-#endif
-}
-
 static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 		       struct ip_tunnel_net *itn, int hdr_len, bool raw_proto)
 {
@@ -290,7 +271,7 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 			__be64 tun_id;
 
 			flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY);
-			tun_id = key_to_tunnel_id(tpi->key);
+			tun_id = key32_to_tunnel_id(tpi->key);
 			tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0);
 			if (!tun_dst)
 				return PACKET_REJECT;
@@ -446,7 +427,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY);
 	gre_build_header(skb, tunnel_hlen, flags, proto,
-			 tunnel_id_to_key(tun_info->key.tun_id), 0);
+			 tunnel_id_to_key32(tun_info->key.tun_id), 0);
 
 	df = key->tun_flags & TUNNEL_DONT_FRAGMENT ?  htons(IP_DF) : 0;
 

+ 11 - 0
net/sched/Kconfig

@@ -761,6 +761,17 @@ config NET_ACT_IFE
 	  To compile this code as a module, choose M here: the
 	  module will be called act_ife.
 
+config NET_ACT_TUNNEL_KEY
+        tristate "IP tunnel metadata manipulation"
+        depends on NET_CLS_ACT
+        ---help---
+	  Say Y here to set/release ip tunnel metadata.
+
+	  If unsure, say N.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_tunnel_key.
+
 config NET_IFE_SKBMARK
         tristate "Support to encoding decoding skb mark on IFE action"
         depends on NET_ACT_IFE

+ 1 - 0
net/sched/Makefile

@@ -22,6 +22,7 @@ obj-$(CONFIG_NET_ACT_CONNMARK)	+= act_connmark.o
 obj-$(CONFIG_NET_ACT_IFE)	+= act_ife.o
 obj-$(CONFIG_NET_IFE_SKBMARK)	+= act_meta_mark.o
 obj-$(CONFIG_NET_IFE_SKBPRIO)	+= act_meta_skbprio.o
+obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o
 obj-$(CONFIG_NET_SCH_FIFO)	+= sch_fifo.o
 obj-$(CONFIG_NET_SCH_CBQ)	+= sch_cbq.o
 obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o

+ 351 - 0
net/sched/act_tunnel_key.c

@@ -0,0 +1,351 @@
+/*
+ * Copyright (c) 2016, Amir Vadai <amir@vadai.me>
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/dst.h>
+#include <net/dst_metadata.h>
+
+#include <linux/tc_act/tc_tunnel_key.h>
+#include <net/tc_act/tc_tunnel_key.h>
+
+#define TUNNEL_KEY_TAB_MASK     15
+
+static int tunnel_key_net_id;
+static struct tc_action_ops act_tunnel_key_ops;
+
+static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
+			  struct tcf_result *res)
+{
+	struct tcf_tunnel_key *t = to_tunnel_key(a);
+	struct tcf_tunnel_key_params *params;
+	int action;
+
+	rcu_read_lock();
+
+	params = rcu_dereference(t->params);
+
+	tcf_lastuse_update(&t->tcf_tm);
+	bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb);
+	action = params->action;
+
+	switch (params->tcft_action) {
+	case TCA_TUNNEL_KEY_ACT_RELEASE:
+		skb_dst_drop(skb);
+		break;
+	case TCA_TUNNEL_KEY_ACT_SET:
+		skb_dst_drop(skb);
+		skb_dst_set(skb, dst_clone(&params->tcft_enc_metadata->dst));
+		break;
+	default:
+		WARN_ONCE(1, "Bad tunnel_key action %d.\n",
+			  params->tcft_action);
+		break;
+	}
+
+	rcu_read_unlock();
+
+	return action;
+}
+
+static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
+	[TCA_TUNNEL_KEY_PARMS]	    = { .len = sizeof(struct tc_tunnel_key) },
+	[TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 },
+	[TCA_TUNNEL_KEY_ENC_IPV4_DST] = { .type = NLA_U32 },
+	[TCA_TUNNEL_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
+	[TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) },
+	[TCA_TUNNEL_KEY_ENC_KEY_ID]   = { .type = NLA_U32 },
+};
+
+static int tunnel_key_init(struct net *net, struct nlattr *nla,
+			   struct nlattr *est, struct tc_action **a,
+			   int ovr, int bind)
+{
+	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
+	struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1];
+	struct tcf_tunnel_key_params *params_old;
+	struct tcf_tunnel_key_params *params_new;
+	struct metadata_dst *metadata = NULL;
+	struct tc_tunnel_key *parm;
+	struct tcf_tunnel_key *t;
+	bool exists = false;
+	__be64 key_id;
+	int ret = 0;
+	int err;
+
+	if (!nla)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_TUNNEL_KEY_PARMS])
+		return -EINVAL;
+
+	parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
+	exists = tcf_hash_check(tn, parm->index, a, bind);
+	if (exists && bind)
+		return 0;
+
+	switch (parm->t_action) {
+	case TCA_TUNNEL_KEY_ACT_RELEASE:
+		break;
+	case TCA_TUNNEL_KEY_ACT_SET:
+		if (!tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) {
+			ret = -EINVAL;
+			goto err_out;
+		}
+
+		key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]));
+
+		if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
+		    tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
+			__be32 saddr;
+			__be32 daddr;
+
+			saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]);
+			daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]);
+
+			metadata = __ip_tun_set_dst(saddr, daddr, 0, 0,
+						    TUNNEL_KEY, key_id, 0);
+		} else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] &&
+			   tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) {
+			struct in6_addr saddr;
+			struct in6_addr daddr;
+
+			saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]);
+			daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]);
+
+			metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, 0,
+						      TUNNEL_KEY, key_id, 0);
+		}
+
+		if (!metadata) {
+			ret = -EINVAL;
+			goto err_out;
+		}
+
+		metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX;
+		break;
+	default:
+		goto err_out;
+	}
+
+	if (!exists) {
+		ret = tcf_hash_create(tn, parm->index, est, a,
+				      &act_tunnel_key_ops, bind, true);
+		if (ret)
+			return ret;
+
+		ret = ACT_P_CREATED;
+	} else {
+		tcf_hash_release(*a, bind);
+		if (!ovr)
+			return -EEXIST;
+	}
+
+	t = to_tunnel_key(*a);
+
+	ASSERT_RTNL();
+	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
+	if (unlikely(!params_new)) {
+		if (ret == ACT_P_CREATED)
+			tcf_hash_release(*a, bind);
+		return -ENOMEM;
+	}
+
+	params_old = rtnl_dereference(t->params);
+
+	params_new->action = parm->action;
+	params_new->tcft_action = parm->t_action;
+	params_new->tcft_enc_metadata = metadata;
+
+	rcu_assign_pointer(t->params, params_new);
+
+	if (params_old)
+		kfree_rcu(params_old, rcu);
+
+	if (ret == ACT_P_CREATED)
+		tcf_hash_insert(tn, *a);
+
+	return ret;
+
+err_out:
+	if (exists)
+		tcf_hash_release(*a, bind);
+	return ret;
+}
+
+static void tunnel_key_release(struct tc_action *a, int bind)
+{
+	struct tcf_tunnel_key *t = to_tunnel_key(a);
+	struct tcf_tunnel_key_params *params;
+
+	rcu_read_lock();
+	params = rcu_dereference(t->params);
+
+	if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
+		dst_release(&params->tcft_enc_metadata->dst);
+
+	kfree_rcu(params, rcu);
+
+	rcu_read_unlock();
+}
+
+static int tunnel_key_dump_addresses(struct sk_buff *skb,
+				     const struct ip_tunnel_info *info)
+{
+	unsigned short family = ip_tunnel_info_af(info);
+
+	if (family == AF_INET) {
+		__be32 saddr = info->key.u.ipv4.src;
+		__be32 daddr = info->key.u.ipv4.dst;
+
+		if (!nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_SRC, saddr) &&
+		    !nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_DST, daddr))
+			return 0;
+	}
+
+	if (family == AF_INET6) {
+		const struct in6_addr *saddr6 = &info->key.u.ipv6.src;
+		const struct in6_addr *daddr6 = &info->key.u.ipv6.dst;
+
+		if (!nla_put_in6_addr(skb,
+				      TCA_TUNNEL_KEY_ENC_IPV6_SRC, saddr6) &&
+		    !nla_put_in6_addr(skb,
+				      TCA_TUNNEL_KEY_ENC_IPV6_DST, daddr6))
+			return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
+			   int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_tunnel_key *t = to_tunnel_key(a);
+	struct tcf_tunnel_key_params *params;
+	struct tc_tunnel_key opt = {
+		.index    = t->tcf_index,
+		.refcnt   = t->tcf_refcnt - ref,
+		.bindcnt  = t->tcf_bindcnt - bind,
+	};
+	struct tcf_t tm;
+	int ret = -1;
+
+	rcu_read_lock();
+	params = rcu_dereference(t->params);
+
+	opt.t_action = params->tcft_action;
+	opt.action = params->action;
+
+	if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) {
+		struct ip_tunnel_key *key =
+			&params->tcft_enc_metadata->u.tun_info.key;
+		__be32 key_id = tunnel_id_to_key32(key->tun_id);
+
+		if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) ||
+		    tunnel_key_dump_addresses(skb,
+					      &params->tcft_enc_metadata->u.tun_info))
+			goto nla_put_failure;
+	}
+
+	tcf_tm_dump(&tm, &t->tcf_tm);
+	if (nla_put_64bit(skb, TCA_TUNNEL_KEY_TM, sizeof(tm),
+			  &tm, TCA_TUNNEL_KEY_PAD))
+		goto nla_put_failure;
+
+	ret = skb->len;
+	goto out;
+
+nla_put_failure:
+	nlmsg_trim(skb, b);
+out:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int tunnel_key_walker(struct net *net, struct sk_buff *skb,
+			     struct netlink_callback *cb, int type,
+			     const struct tc_action_ops *ops)
+{
+	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
+
+	return tcf_generic_walker(tn, skb, cb, type, ops);
+}
+
+static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
+
+	return tcf_hash_search(tn, a, index);
+}
+
+static struct tc_action_ops act_tunnel_key_ops = {
+	.kind		=	"tunnel_key",
+	.type		=	TCA_ACT_TUNNEL_KEY,
+	.owner		=	THIS_MODULE,
+	.act		=	tunnel_key_act,
+	.dump		=	tunnel_key_dump,
+	.init		=	tunnel_key_init,
+	.cleanup	=	tunnel_key_release,
+	.walk		=	tunnel_key_walker,
+	.lookup		=	tunnel_key_search,
+	.size		=	sizeof(struct tcf_tunnel_key),
+};
+
+static __net_init int tunnel_key_init_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
+
+	return tc_action_net_init(tn, &act_tunnel_key_ops, TUNNEL_KEY_TAB_MASK);
+}
+
+static void __net_exit tunnel_key_exit_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
+
+	tc_action_net_exit(tn);
+}
+
+static struct pernet_operations tunnel_key_net_ops = {
+	.init = tunnel_key_init_net,
+	.exit = tunnel_key_exit_net,
+	.id   = &tunnel_key_net_id,
+	.size = sizeof(struct tc_action_net),
+};
+
+static int __init tunnel_key_init_module(void)
+{
+	return tcf_register_action(&act_tunnel_key_ops, &tunnel_key_net_ops);
+}
+
+static void __exit tunnel_key_cleanup_module(void)
+{
+	tcf_unregister_action(&act_tunnel_key_ops, &tunnel_key_net_ops);
+}
+
+module_init(tunnel_key_init_module);
+module_exit(tunnel_key_cleanup_module);
+
+MODULE_AUTHOR("Amir Vadai <amir@vadai.me>");
+MODULE_DESCRIPTION("ip tunnel manipulation actions");
+MODULE_LICENSE("GPL v2");

+ 99 - 1
net/sched/cls_flower.c

@@ -23,9 +23,13 @@
 #include <net/ip.h>
 #include <net/flow_dissector.h>
 
+#include <net/dst.h>
+#include <net/dst_metadata.h>
+
 struct fl_flow_key {
 	int	indev_ifindex;
 	struct flow_dissector_key_control control;
+	struct flow_dissector_key_control enc_control;
 	struct flow_dissector_key_basic basic;
 	struct flow_dissector_key_eth_addrs eth;
 	struct flow_dissector_key_vlan vlan;
@@ -35,6 +39,11 @@ struct fl_flow_key {
 		struct flow_dissector_key_ipv6_addrs ipv6;
 	};
 	struct flow_dissector_key_ports tp;
+	struct flow_dissector_key_keyid enc_key_id;
+	union {
+		struct flow_dissector_key_ipv4_addrs enc_ipv4;
+		struct flow_dissector_key_ipv6_addrs enc_ipv6;
+	};
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -124,11 +133,31 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	struct cls_fl_filter *f;
 	struct fl_flow_key skb_key;
 	struct fl_flow_key skb_mkey;
+	struct ip_tunnel_info *info;
 
 	if (!atomic_read(&head->ht.nelems))
 		return -1;
 
 	fl_clear_masked_range(&skb_key, &head->mask);
+
+	info = skb_tunnel_info(skb);
+	if (info) {
+		struct ip_tunnel_key *key = &info->key;
+
+		switch (ip_tunnel_info_af(info)) {
+		case AF_INET:
+			skb_key.enc_ipv4.src = key->u.ipv4.src;
+			skb_key.enc_ipv4.dst = key->u.ipv4.dst;
+			break;
+		case AF_INET6:
+			skb_key.enc_ipv6.src = key->u.ipv6.src;
+			skb_key.enc_ipv6.dst = key->u.ipv6.dst;
+			break;
+		}
+
+		skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id);
+	}
+
 	skb_key.indev_ifindex = skb->skb_iif;
 	/* skb_flow_dissect() does not set n_proto in case an unknown protocol,
 	 * so do it rather here.
@@ -297,7 +326,15 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_VLAN_ID]	= { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_VLAN_PRIO]	= { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_VLAN_ETH_TYPE]	= { .type = NLA_U16 },
-
+	[TCA_FLOWER_KEY_ENC_KEY_ID]	= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV4_SRC]	= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK] = { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV4_DST]	= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV4_DST_MASK] = { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV6_SRC]	= { .len = sizeof(struct in6_addr) },
+	[TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) },
+	[TCA_FLOWER_KEY_ENC_IPV6_DST]	= { .len = sizeof(struct in6_addr) },
+	[TCA_FLOWER_KEY_ENC_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) },
 };
 
 static void fl_set_key_val(struct nlattr **tb,
@@ -409,6 +446,40 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 			       sizeof(key->tp.dst));
 	}
 
+	if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
+	    tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) {
+		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+		fl_set_key_val(tb, &key->enc_ipv4.src,
+			       TCA_FLOWER_KEY_ENC_IPV4_SRC,
+			       &mask->enc_ipv4.src,
+			       TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,
+			       sizeof(key->enc_ipv4.src));
+		fl_set_key_val(tb, &key->enc_ipv4.dst,
+			       TCA_FLOWER_KEY_ENC_IPV4_DST,
+			       &mask->enc_ipv4.dst,
+			       TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,
+			       sizeof(key->enc_ipv4.dst));
+	}
+
+	if (tb[TCA_FLOWER_KEY_ENC_IPV6_SRC] ||
+	    tb[TCA_FLOWER_KEY_ENC_IPV6_DST]) {
+		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+		fl_set_key_val(tb, &key->enc_ipv6.src,
+			       TCA_FLOWER_KEY_ENC_IPV6_SRC,
+			       &mask->enc_ipv6.src,
+			       TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,
+			       sizeof(key->enc_ipv6.src));
+		fl_set_key_val(tb, &key->enc_ipv6.dst,
+			       TCA_FLOWER_KEY_ENC_IPV6_DST,
+			       &mask->enc_ipv6.dst,
+			       TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,
+			       sizeof(key->enc_ipv6.dst));
+	}
+
+	fl_set_key_val(tb, &key->enc_key_id.keyid, TCA_FLOWER_KEY_ENC_KEY_ID,
+		       &mask->enc_key_id.keyid, TCA_FLOWER_KEY_ENC_KEY_ID,
+		       sizeof(key->enc_key_id.keyid));
+
 	return 0;
 }
 
@@ -821,6 +892,33 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 				  sizeof(key->tp.dst))))
 		goto nla_put_failure;
 
+	if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
+	    (fl_dump_key_val(skb, &key->enc_ipv4.src,
+			    TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src,
+			    TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,
+			    sizeof(key->enc_ipv4.src)) ||
+	     fl_dump_key_val(skb, &key->enc_ipv4.dst,
+			     TCA_FLOWER_KEY_ENC_IPV4_DST, &mask->enc_ipv4.dst,
+			     TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,
+			     sizeof(key->enc_ipv4.dst))))
+		goto nla_put_failure;
+	else if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS &&
+		 (fl_dump_key_val(skb, &key->enc_ipv6.src,
+			    TCA_FLOWER_KEY_ENC_IPV6_SRC, &mask->enc_ipv6.src,
+			    TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,
+			    sizeof(key->enc_ipv6.src)) ||
+		 fl_dump_key_val(skb, &key->enc_ipv6.dst,
+				 TCA_FLOWER_KEY_ENC_IPV6_DST,
+				 &mask->enc_ipv6.dst,
+				 TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,
+			    sizeof(key->enc_ipv6.dst))))
+		goto nla_put_failure;
+
+	if (fl_dump_key_val(skb, &key->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID,
+			    &mask->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID,
+			    sizeof(key->enc_key_id)))
+		goto nla_put_failure;
+
 	nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags);
 
 	if (tcf_exts_dump(skb, &f->exts))