1 files changed, 248 insertions, 82 deletions

diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index f2c22c682851..e3b099c14eff 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -7,13 +7,13 @@
 #include <linux/tc_act/tc_csum.h>
 #include <net/flow_offload.h>
 #include <net/netfilter/nf_flow_table.h>
+#include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 
-static struct work_struct nf_flow_offload_work;
-static DEFINE_SPINLOCK(flow_offload_pending_list_lock);
-static LIST_HEAD(flow_offload_pending_list);
+static struct workqueue_struct *nf_flow_offload_wq;
 
 struct flow_offload_work {
 	struct list_head	list;
@@ -21,40 +21,68 @@ struct flow_offload_work {
 	int			priority;
 	struct nf_flowtable	*flowtable;
 	struct flow_offload	*flow;
-};
-
-struct nf_flow_key {
-	struct flow_dissector_key_meta			meta;
-	struct flow_dissector_key_control		control;
-	struct flow_dissector_key_basic			basic;
-	union {
-		struct flow_dissector_key_ipv4_addrs	ipv4;
-		struct flow_dissector_key_ipv6_addrs	ipv6;
-	};
-	struct flow_dissector_key_tcp			tcp;
-	struct flow_dissector_key_ports			tp;
-} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
-
-struct nf_flow_match {
-	struct flow_dissector	dissector;
-	struct nf_flow_key	key;
-	struct nf_flow_key	mask;
-};
-
-struct nf_flow_rule {
-	struct nf_flow_match	match;
-	struct flow_rule	*rule;
+	struct work_struct	work;
 };
 
 #define NF_FLOW_DISSECTOR(__match, __type, __field)	\
 	(__match)->dissector.offset[__type] =		\
 		offsetof(struct nf_flow_key, __field)
 
+static void nf_flow_rule_lwt_match(struct nf_flow_match *match,
+				   struct ip_tunnel_info *tun_info)
+{
+	struct nf_flow_key *mask = &match->mask;
+	struct nf_flow_key *key = &match->key;
+	unsigned int enc_keys;
+
+	if (!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX))
+		return;
+
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_CONTROL, enc_control);
+	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
+	key->enc_key_id.keyid = tunnel_id_to_key32(tun_info->key.tun_id);
+	mask->enc_key_id.keyid = 0xffffffff;
+	enc_keys = BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+		   BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL);
+
+	if (ip_tunnel_info_af(tun_info) == AF_INET) {
+		NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+				  enc_ipv4);
+		key->enc_ipv4.src = tun_info->key.u.ipv4.dst;
+		key->enc_ipv4.dst = tun_info->key.u.ipv4.src;
+		if (key->enc_ipv4.src)
+			mask->enc_ipv4.src = 0xffffffff;
+		if (key->enc_ipv4.dst)
+			mask->enc_ipv4.dst = 0xffffffff;
+		enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
+		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+	} else {
+		memcpy(&key->enc_ipv6.src, &tun_info->key.u.ipv6.dst,
+		       sizeof(struct in6_addr));
+		memcpy(&key->enc_ipv6.dst, &tun_info->key.u.ipv6.src,
+		       sizeof(struct in6_addr));
+		if (memcmp(&key->enc_ipv6.src, &in6addr_any,
+			   sizeof(struct in6_addr)))
+			memset(&key->enc_ipv6.src, 0xff,
+			       sizeof(struct in6_addr));
+		if (memcmp(&key->enc_ipv6.dst, &in6addr_any,
+			   sizeof(struct in6_addr)))
+			memset(&key->enc_ipv6.dst, 0xff,
+			       sizeof(struct in6_addr));
+		enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS);
+		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+	}
+
+	match->dissector.used_keys |= enc_keys;
+}
+
 static int nf_flow_rule_match(struct nf_flow_match *match,
-			      const struct flow_offload_tuple *tuple)
+			      const struct flow_offload_tuple *tuple,
+			      struct dst_entry *other_dst)
 {
 	struct nf_flow_key *mask = &match->mask;
 	struct nf_flow_key *key = &match->key;
+	struct ip_tunnel_info *tun_info;
 
 	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_META, meta);
 	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control);
@@ -64,6 +92,11 @@ static int nf_flow_rule_match(struct nf_flow_match *match,
 	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp);
 	NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp);
 
+	if (other_dst && other_dst->lwtstate) {
+		tun_info = lwt_tun_info(other_dst->lwtstate);
+		nf_flow_rule_lwt_match(match, tun_info);
+	}
+
 	key->meta.ingress_ifindex = tuple->iifidx;
 	mask->meta.ingress_ifindex = 0xffffffff;
 
@@ -443,10 +476,52 @@ static void flow_offload_redirect(const struct flow_offload *flow,
 	dev_hold(rt->dst.dev);
 }
 
+static void flow_offload_encap_tunnel(const struct flow_offload *flow,
+				      enum flow_offload_tuple_dir dir,
+				      struct nf_flow_rule *flow_rule)
+{
+	struct flow_action_entry *entry;
+	struct dst_entry *dst;
+
+	dst = flow->tuplehash[dir].tuple.dst_cache;
+	if (dst && dst->lwtstate) {
+		struct ip_tunnel_info *tun_info;
+
+		tun_info = lwt_tun_info(dst->lwtstate);
+		if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) {
+			entry = flow_action_entry_next(flow_rule);
+			entry->id = FLOW_ACTION_TUNNEL_ENCAP;
+			entry->tunnel = tun_info;
+		}
+	}
+}
+
+static void flow_offload_decap_tunnel(const struct flow_offload *flow,
+				      enum flow_offload_tuple_dir dir,
+				      struct nf_flow_rule *flow_rule)
+{
+	struct flow_action_entry *entry;
+	struct dst_entry *dst;
+
+	dst = flow->tuplehash[!dir].tuple.dst_cache;
+	if (dst && dst->lwtstate) {
+		struct ip_tunnel_info *tun_info;
+
+		tun_info = lwt_tun_info(dst->lwtstate);
+		if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) {
+			entry = flow_action_entry_next(flow_rule);
+			entry->id = FLOW_ACTION_TUNNEL_DECAP;
+		}
+	}
+}
+
 int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow,
 			    enum flow_offload_tuple_dir dir,
 			    struct nf_flow_rule *flow_rule)
 {
+	flow_offload_decap_tunnel(flow, dir, flow_rule);
+	flow_offload_encap_tunnel(flow, dir, flow_rule);
+
 	if (flow_offload_eth_src(net, flow, dir, flow_rule) < 0 ||
 	    flow_offload_eth_dst(net, flow, dir, flow_rule) < 0)
 		return -1;
@@ -473,6 +548,9 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow,
 			    enum flow_offload_tuple_dir dir,
 			    struct nf_flow_rule *flow_rule)
 {
+	flow_offload_decap_tunnel(flow, dir, flow_rule);
+	flow_offload_encap_tunnel(flow, dir, flow_rule);
+
 	if (flow_offload_eth_src(net, flow, dir, flow_rule) < 0 ||
 	    flow_offload_eth_dst(net, flow, dir, flow_rule) < 0)
 		return -1;
@@ -503,6 +581,7 @@ nf_flow_offload_rule_alloc(struct net *net,
 	const struct flow_offload *flow = offload->flow;
 	const struct flow_offload_tuple *tuple;
 	struct nf_flow_rule *flow_rule;
+	struct dst_entry *other_dst;
 	int err = -ENOMEM;
 
 	flow_rule = kzalloc(sizeof(*flow_rule), GFP_KERNEL);
@@ -518,7 +597,8 @@ nf_flow_offload_rule_alloc(struct net *net,
 	flow_rule->rule->match.key = &flow_rule->match.key;
 
 	tuple = &flow->tuplehash[dir].tuple;
-	err = nf_flow_rule_match(&flow_rule->match, tuple);
+	other_dst = flow->tuplehash[!dir].tuple.dst_cache;
+	err = nf_flow_rule_match(&flow_rule->match, tuple, other_dst);
 	if (err < 0)
 		goto err_flow_match;
 
@@ -598,6 +678,7 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable,
 				 struct nf_flow_rule *flow_rule,
 				 enum flow_offload_tuple_dir dir,
 				 int priority, int cmd,
+				 struct flow_stats *stats,
 				 struct list_head *block_cb_list)
 {
 	struct flow_cls_offload cls_flow = {};
@@ -611,6 +692,7 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable,
 	if (cmd == FLOW_CLS_REPLACE)
 		cls_flow.rule = flow_rule->rule;
 
+	down_read(&flowtable->flow_block_lock);
 	list_for_each_entry(block_cb, block_cb_list, list) {
 		err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow,
 				   block_cb->cb_priv);
@@ -619,6 +701,10 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable,
 
 		i++;
 	}
+	up_read(&flowtable->flow_block_lock);
+
+	if (cmd == FLOW_CLS_STATS)
+		memcpy(stats, &cls_flow.stats, sizeof(*stats));
 
 	return i;
 }
@@ -629,7 +715,7 @@ static int flow_offload_tuple_add(struct flow_offload_work *offload,
 {
 	return nf_flow_offload_tuple(offload->flowtable, offload->flow,
 				     flow_rule, dir, offload->priority,
-				     FLOW_CLS_REPLACE,
+				     FLOW_CLS_REPLACE, NULL,
 				     &offload->flowtable->flow_block.cb_list);
 }
 
@@ -637,7 +723,7 @@ static void flow_offload_tuple_del(struct flow_offload_work *offload,
 				   enum flow_offload_tuple_dir dir)
 {
 	nf_flow_offload_tuple(offload->flowtable, offload->flow, NULL, dir,
-			      offload->priority, FLOW_CLS_DESTROY,
+			      offload->priority, FLOW_CLS_DESTROY, NULL,
 			      &offload->flowtable->flow_block.cb_list);
 }
 
@@ -683,19 +769,9 @@ static void flow_offload_tuple_stats(struct flow_offload_work *offload,
 				     enum flow_offload_tuple_dir dir,
 				     struct flow_stats *stats)
 {
-	struct nf_flowtable *flowtable = offload->flowtable;
-	struct flow_cls_offload cls_flow = {};
-	struct flow_block_cb *block_cb;
-	struct netlink_ext_ack extack;
-	__be16 proto = ETH_P_ALL;
-
-	nf_flow_offload_init(&cls_flow, proto, offload->priority,
-			     FLOW_CLS_STATS,
-			     &offload->flow->tuplehash[dir].tuple, &extack);
-
-	list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list)
-		block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv);
-	memcpy(stats, &cls_flow.stats, sizeof(*stats));
+	nf_flow_offload_tuple(offload->flowtable, offload->flow, NULL, dir,
+			      offload->priority, FLOW_CLS_STATS, stats,
+			      &offload->flowtable->flow_block.cb_list);
 }
 
 static void flow_offload_work_stats(struct flow_offload_work *offload)
@@ -709,19 +785,25 @@ static void flow_offload_work_stats(struct flow_offload_work *offload)
 	lastused = max_t(u64, stats[0].lastused, stats[1].lastused);
 	offload->flow->timeout = max_t(u64, offload->flow->timeout,
 				       lastused + NF_FLOW_TIMEOUT);
+
+	if (offload->flowtable->flags & NF_FLOWTABLE_COUNTER) {
+		if (stats[0].pkts)
+			nf_ct_acct_add(offload->flow->ct,
+				       FLOW_OFFLOAD_DIR_ORIGINAL,
+				       stats[0].pkts, stats[0].bytes);
+		if (stats[1].pkts)
+			nf_ct_acct_add(offload->flow->ct,
+				       FLOW_OFFLOAD_DIR_REPLY,
+				       stats[1].pkts, stats[1].bytes);
+	}
 }
 
 static void flow_offload_work_handler(struct work_struct *work)
 {
-	struct flow_offload_work *offload, *next;
-	LIST_HEAD(offload_pending_list);
-
-	spin_lock_bh(&flow_offload_pending_list_lock);
-	list_replace_init(&flow_offload_pending_list, &offload_pending_list);
-	spin_unlock_bh(&flow_offload_pending_list_lock);
+	struct flow_offload_work *offload;
 
-	list_for_each_entry_safe(offload, next, &offload_pending_list, list) {
-		switch (offload->cmd) {
+	offload = container_of(work, struct flow_offload_work, work);
+	switch (offload->cmd) {
 		case FLOW_CLS_REPLACE:
 			flow_offload_work_add(offload);
 			break;
@@ -733,19 +815,14 @@ static void flow_offload_work_handler(struct work_struct *work)
 			break;
 		default:
 			WARN_ON_ONCE(1);
-		}
-		list_del(&offload->list);
-		kfree(offload);
 	}
+
+	kfree(offload);
 }
 
 static void flow_offload_queue_work(struct flow_offload_work *offload)
 {
-	spin_lock_bh(&flow_offload_pending_list_lock);
-	list_add_tail(&offload->list, &flow_offload_pending_list);
-	spin_unlock_bh(&flow_offload_pending_list_lock);
-
-	schedule_work(&nf_flow_offload_work);
+	queue_work(nf_flow_offload_wq, &offload->work);
 }
 
 static struct flow_offload_work *
@@ -762,6 +839,7 @@ nf_flow_offload_work_alloc(struct nf_flowtable *flowtable,
 	offload->flow = flow;
 	offload->priority = flowtable->priority;
 	offload->flowtable = flowtable;
+	INIT_WORK(&offload->work, flow_offload_work_handler);
 
 	return offload;
 }
@@ -812,7 +890,7 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
 void nf_flow_table_offload_flush(struct nf_flowtable *flowtable)
 {
 	if (nf_flowtable_hw_offload(flowtable))
-		flush_work(&nf_flow_offload_work);
+		flush_workqueue(nf_flow_offload_wq);
 }
 
 static int nf_flow_table_block_setup(struct nf_flowtable *flowtable,
@@ -840,25 +918,47 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable,
 	return err;
 }
 
-static int nf_flow_table_offload_cmd(struct flow_block_offload *bo,
-				     struct nf_flowtable *flowtable,
-				     struct net_device *dev,
-				     enum flow_block_command cmd,
-				     struct netlink_ext_ack *extack)
+static void nf_flow_table_block_offload_init(struct flow_block_offload *bo,
+					     struct net *net,
+					     enum flow_block_command cmd,
+					     struct nf_flowtable *flowtable,
+					     struct netlink_ext_ack *extack)
 {
-	int err;
-
-	if (!dev->netdev_ops->ndo_setup_tc)
-		return -EOPNOTSUPP;
-
 	memset(bo, 0, sizeof(*bo));
-	bo->net		= dev_net(dev);
+	bo->net		= net;
 	bo->block	= &flowtable->flow_block;
 	bo->command	= cmd;
 	bo->binder_type	= FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	bo->extack	= extack;
 	INIT_LIST_HEAD(&bo->cb_list);
+}
+
+static int nf_flow_table_indr_offload_cmd(struct flow_block_offload *bo,
+					  struct nf_flowtable *flowtable,
+					  struct net_device *dev,
+					  enum flow_block_command cmd,
+					  struct netlink_ext_ack *extack)
+{
+	nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable,
+					 extack);
+	flow_indr_block_call(dev, bo, cmd, TC_SETUP_FT);
+
+	if (list_empty(&bo->cb_list))
+		return -EOPNOTSUPP;
 
+	return 0;
+}
+
+static int nf_flow_table_offload_cmd(struct flow_block_offload *bo,
+				     struct nf_flowtable *flowtable,
+				     struct net_device *dev,
+				     enum flow_block_command cmd,
+				     struct netlink_ext_ack *extack)
+{
+	int err;
+
+	nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable,
+					 extack);
 	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo);
 	if (err < 0)
 		return err;
@@ -877,7 +977,12 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
 	if (!nf_flowtable_hw_offload(flowtable))
 		return 0;
 
-	err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack);
+	if (dev->netdev_ops->ndo_setup_tc)
+		err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd,
+						&extack);
+	else
+		err = nf_flow_table_indr_offload_cmd(&bo, flowtable, dev, cmd,
+						     &extack);
 	if (err < 0)
 		return err;
 
@@ -885,22 +990,83 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_offload_setup);
 
-int nf_flow_table_offload_init(void)
+static void nf_flow_table_indr_block_ing_cmd(struct net_device *dev,
+					     struct nf_flowtable *flowtable,
+					     flow_indr_block_bind_cb_t *cb,
+					     void *cb_priv,
+					     enum flow_block_command cmd)
 {
-	INIT_WORK(&nf_flow_offload_work, flow_offload_work_handler);
+	struct netlink_ext_ack extack = {};
+	struct flow_block_offload bo;
 
-	return 0;
+	if (!flowtable)
+		return;
+
+	nf_flow_table_block_offload_init(&bo, dev_net(dev), cmd, flowtable,
+					 &extack);
+
+	cb(dev, cb_priv, TC_SETUP_FT, &bo);
+
+	nf_flow_table_block_setup(flowtable, &bo, cmd);
 }
 
-void nf_flow_table_offload_exit(void)
+static void nf_flow_table_indr_block_cb_cmd(struct nf_flowtable *flowtable,
+					    struct net_device *dev,
+					    flow_indr_block_bind_cb_t *cb,
+					    void *cb_priv,
+					    enum flow_block_command cmd)
 {
-	struct flow_offload_work *offload, *next;
-	LIST_HEAD(offload_pending_list);
+	if (!(flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD))
+		return;
 
-	cancel_work_sync(&nf_flow_offload_work);
+	nf_flow_table_indr_block_ing_cmd(dev, flowtable, cb, cb_priv, cmd);
+}
 
-	list_for_each_entry_safe(offload, next, &offload_pending_list, list) {
-		list_del(&offload->list);
-		kfree(offload);
+static void nf_flow_table_indr_block_cb(struct net_device *dev,
+					flow_indr_block_bind_cb_t *cb,
+					void *cb_priv,
+					enum flow_block_command cmd)
+{
+	struct net *net = dev_net(dev);
+	struct nft_flowtable *nft_ft;
+	struct nft_table *table;
+	struct nft_hook *hook;
+
+	mutex_lock(&net->nft.commit_mutex);
+	list_for_each_entry(table, &net->nft.tables, list) {
+		list_for_each_entry(nft_ft, &table->flowtables, list) {
+			list_for_each_entry(hook, &nft_ft->hook_list, list) {
+				if (hook->ops.dev != dev)
+					continue;
+
+				nf_flow_table_indr_block_cb_cmd(&nft_ft->data,
+								dev, cb,
+								cb_priv, cmd);
+			}
+		}
 	}
+	mutex_unlock(&net->nft.commit_mutex);
+}
+
+static struct flow_indr_block_entry block_ing_entry = {
+	.cb	= nf_flow_table_indr_block_cb,
+	.list	= LIST_HEAD_INIT(block_ing_entry.list),
+};
+
+int nf_flow_table_offload_init(void)
+{
+	nf_flow_offload_wq  = alloc_workqueue("nf_flow_table_offload",
+					      WQ_UNBOUND | WQ_MEM_RECLAIM, 0);
+	if (!nf_flow_offload_wq)
+		return -ENOMEM;
+
+	flow_indr_add_block_cb(&block_ing_entry);
+
+	return 0;
+}
+
+void nf_flow_table_offload_exit(void)
+{
+	flow_indr_del_block_cb(&block_ing_entry);
+	destroy_workqueue(nf_flow_offload_wq);
 }