Merge branch 'tcp-udp-misc'

Eric Dumazet says:

====================
net: various udp/tcp changes

First round of patches for linux-4.7

Add a generic facility for sockets to be freed after an RCU grace
period, if they need to.

Then UDP stack is changed to no longer use SLAB_DESTROY_BY_RCU,
in order to speedup rx processing for traffic encapsulated in UDP.
It gives a 17 % speedup for normal UDP reception in stress conditions.

Then TCP listeners are changed to use SOCK_RCU_FREE as well
to avoid touching sk_refcnt in synflood case :
I got up to 30 % performance increase for a mono listener.

Then three patches add SK_MEMINFO_DROPS to sock_diag
and add per socket rx drops accounting to TCP.

Last patch adds rate limiting on ACK sent on behalf of SYN_RECV
to better resist to SYNFLOOD targeting one or few flows.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/udp.h

@@ -98,11 +98,11 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
 	return udp_sk(sk)->no_check6_rx;
 }
 
-#define udp_portaddr_for_each_entry(__sk, node, list) \
-	hlist_nulls_for_each_entry(__sk, node, list, __sk_common.skc_portaddr_node)
+#define udp_portaddr_for_each_entry(__sk, list) \
+	hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node)
 
-#define udp_portaddr_for_each_entry_rcu(__sk, node, list) \
-	hlist_nulls_for_each_entry_rcu(__sk, node, list, __sk_common.skc_portaddr_node)
+#define udp_portaddr_for_each_entry_rcu(__sk, list) \
+	hlist_for_each_entry_rcu(__sk, list, __sk_common.skc_portaddr_node)
 
 #define IS_UDPLITE(__sk) (udp_sk(__sk)->pcflag)
 

include/net/inet6_hashtables.h

@@ -66,13 +66,15 @@ static inline struct sock *__inet6_lookup(struct net *net,
 					  const __be16 sport,
 					  const struct in6_addr *daddr,
 					  const u16 hnum,
-					  const int dif)
+					  const int dif,
+					  bool *refcounted)
 {
 	struct sock *sk = __inet6_lookup_established(net, hashinfo, saddr,
 						sport, daddr, hnum, dif);
+	*refcounted = true;
 	if (sk)
 		return sk;
-
+	*refcounted = false;
 	return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport,
 				     daddr, hnum, dif);
 }
@@ -81,17 +83,19 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      struct sk_buff *skb, int doff,
 					      const __be16 sport,
 					      const __be16 dport,
-					      int iif)
+					      int iif,
+					      bool *refcounted)
 {
 	struct sock *sk = skb_steal_sock(skb);
 
+	*refcounted = true;
 	if (sk)
 		return sk;
 
 	return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
 			      doff, &ipv6_hdr(skb)->saddr, sport,
 			      &ipv6_hdr(skb)->daddr, ntohs(dport),
-			      iif);
+			      iif, refcounted);
 }
 
 struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,

include/net/inet_hashtables.h

@@ -100,14 +100,10 @@ struct inet_bind_hashbucket {
 
 /*
  * Sockets can be hashed in established or listening table
- * We must use different 'nulls' end-of-chain value for listening
- * hash table, or we might find a socket that was closed and
- * reallocated/inserted into established hash table
  */
-#define LISTENING_NULLS_BASE (1U << 29)
 struct inet_listen_hashbucket {
 	spinlock_t		lock;
-	struct hlist_nulls_head	head;
+	struct hlist_head	head;
 };
 
 /* This is for listening sockets, thus all sockets which possess wildcards. */
@@ -280,11 +276,8 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 	 net_eq(sock_net(__sk), (__net)))
 #endif /* 64-bit arch */
 
-/*
- * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
+/* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
  * not check it for lookups anymore, thanks Alexey. -DaveM
- *
- * Local BH must be disabled here.
  */
 struct sock *__inet_lookup_established(struct net *net,
 				       struct inet_hashinfo *hashinfo,
@@ -307,14 +300,20 @@ static inline struct sock *__inet_lookup(struct net *net,
 					 struct sk_buff *skb, int doff,
 					 const __be32 saddr, const __be16 sport,
 					 const __be32 daddr, const __be16 dport,
-					 const int dif)
+					 const int dif,
+					 bool *refcounted)
 {
 	u16 hnum = ntohs(dport);
-	struct sock *sk = __inet_lookup_established(net, hashinfo,
-				saddr, sport, daddr, hnum, dif);
+	struct sock *sk;
 
-	return sk ? : __inet_lookup_listener(net, hashinfo, skb, doff, saddr,
-					     sport, daddr, hnum, dif);
+	sk = __inet_lookup_established(net, hashinfo, saddr, sport,
+				       daddr, hnum, dif);
+	*refcounted = true;
+	if (sk)
+		return sk;
+	*refcounted = false;
+	return __inet_lookup_listener(net, hashinfo, skb, doff, saddr,
+				      sport, daddr, hnum, dif);
 }
 
 static inline struct sock *inet_lookup(struct net *net,
@@ -325,30 +324,34 @@ static inline struct sock *inet_lookup(struct net *net,
 				       const int dif)
 {
 	struct sock *sk;
+	bool refcounted;
 
-	local_bh_disable();
 	sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
-			   dport, dif);
-	local_bh_enable();
+			   dport, dif, &refcounted);
 
+	if (sk && !refcounted && !atomic_inc_not_zero(&sk->sk_refcnt))
+		sk = NULL;
 	return sk;
 }
 
 static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 					     struct sk_buff *skb,
 					     int doff,
 					     const __be16 sport,
-					     const __be16 dport)
+					     const __be16 dport,
+					     bool *refcounted)
 {
 	struct sock *sk = skb_steal_sock(skb);
 	const struct iphdr *iph = ip_hdr(skb);
 
+	*refcounted = true;
 	if (sk)
 		return sk;
-	else
-		return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
-				     doff, iph->saddr, sport,
-				     iph->daddr, dport, inet_iif(skb));
+
+	return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
+			     doff, iph->saddr, sport,
+			     iph->daddr, dport, inet_iif(skb),
+			     refcounted);
 }
 
 u32 sk_ehashfn(const struct sock *sk);

include/net/request_sock.h

@@ -85,24 +85,23 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
 	struct request_sock *req;
 
 	req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
-
-	if (req) {
-		req->rsk_ops = ops;
-		if (attach_listener) {
-			sock_hold(sk_listener);
-			req->rsk_listener = sk_listener;
-		} else {
-			req->rsk_listener = NULL;
+	if (!req)
+		return NULL;
+	req->rsk_listener = NULL;
+	if (attach_listener) {
+		if (unlikely(!atomic_inc_not_zero(&sk_listener->sk_refcnt))) {
+			kmem_cache_free(ops->slab, req);
+			return NULL;
 		}
-		req_to_sk(req)->sk_prot = sk_listener->sk_prot;
-		sk_node_init(&req_to_sk(req)->sk_node);
-		sk_tx_queue_clear(req_to_sk(req));
-		req->saved_syn = NULL;
-		/* Following is temporary. It is coupled with debugging
-		 * helpers in reqsk_put() & reqsk_free()
-		 */
-		atomic_set(&req->rsk_refcnt, 0);
+		req->rsk_listener = sk_listener;
 	}
+	req->rsk_ops = ops;
+	req_to_sk(req)->sk_prot = sk_listener->sk_prot;
+	sk_node_init(&req_to_sk(req)->sk_node);
+	sk_tx_queue_clear(req_to_sk(req));
+	req->saved_syn = NULL;
+	atomic_set(&req->rsk_refcnt, 0);
+
 	return req;
 }
 

include/net/sock.h

@@ -178,7 +178,7 @@ struct sock_common {
 	int			skc_bound_dev_if;
 	union {
 		struct hlist_node	skc_bind_node;
-		struct hlist_nulls_node skc_portaddr_node;
+		struct hlist_node	skc_portaddr_node;
 	};
 	struct proto		*skc_prot;
 	possible_net_t		skc_net;
@@ -438,6 +438,7 @@ struct sock {
 						  struct sk_buff *skb);
 	void                    (*sk_destruct)(struct sock *sk);
 	struct sock_reuseport __rcu	*sk_reuseport_cb;
+	struct rcu_head		sk_rcu;
 };
 
 #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
@@ -669,18 +670,18 @@ static inline void sk_add_bind_node(struct sock *sk,
 	hlist_for_each_entry(__sk, list, sk_bind_node)
 
 /**
- * sk_nulls_for_each_entry_offset - iterate over a list at a given struct offset
+ * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset
  * @tpos:	the type * to use as a loop cursor.
  * @pos:	the &struct hlist_node to use as a loop cursor.
  * @head:	the head for your list.
  * @offset:	offset of hlist_node within the struct.
  *
  */
-#define sk_nulls_for_each_entry_offset(tpos, pos, head, offset)		       \
-	for (pos = (head)->first;					       \
-	     (!is_a_nulls(pos)) &&					       \
+#define sk_for_each_entry_offset_rcu(tpos, pos, head, offset)		       \
+	for (pos = rcu_dereference((head)->first);			       \
+	     pos != NULL &&						       \
 		({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;});       \
-	     pos = pos->next)
+	     pos = rcu_dereference(pos->next))
 
 static inline struct user_namespace *sk_user_ns(struct sock *sk)
 {
@@ -720,6 +721,7 @@ enum sock_flags {
 		     */
 	SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
+	SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -2010,6 +2012,13 @@ sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb)
 	SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops);
 }
 
+static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
+{
+	int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+
+	atomic_add(segs, &sk->sk_drops);
+}
+
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			   struct sk_buff *skb);
 void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,

include/net/tcp.h

@@ -1836,4 +1836,17 @@ static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb)
 		tp->data_segs_in += segs_in;
 }
 
+/*
+ * TCP listen path runs lockless.
+ * We forced "struct sock" to be const qualified to make sure
+ * we don't modify one of its field by mistake.
+ * Here, we increment sk_drops which is an atomic_t, so we can safely
+ * make sock writable again.
+ */
+static inline void tcp_listendrop(const struct sock *sk)
+{
+	atomic_inc(&((struct sock *)sk)->sk_drops);
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+}
+
 #endif	/* _TCP_H */

include/net/udp.h

@@ -59,7 +59,7 @@ struct udp_skb_cb {
  *	@lock:	spinlock protecting changes to head/count
  */
 struct udp_hslot {
-	struct hlist_nulls_head	head;
+	struct hlist_head	head;
 	int			count;
 	spinlock_t		lock;
 } __attribute__((aligned(2 * sizeof(long))));

include/uapi/linux/sock_diag.h

@@ -20,6 +20,7 @@ enum {
 	SK_MEMINFO_WMEM_QUEUED,
 	SK_MEMINFO_OPTMEM,
 	SK_MEMINFO_BACKLOG,
+	SK_MEMINFO_DROPS,
 
 	SK_MEMINFO_VARS,
 };

net/core/sock.c

@@ -1419,8 +1419,12 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 }
 EXPORT_SYMBOL(sk_alloc);
 
-void sk_destruct(struct sock *sk)
+/* Sockets having SOCK_RCU_FREE will call this function after one RCU
+ * grace period. This is the case for UDP sockets and TCP listeners.
+ */
+static void __sk_destruct(struct rcu_head *head)
 {
+	struct sock *sk = container_of(head, struct sock, sk_rcu);
 	struct sk_filter *filter;
 
 	if (sk->sk_destruct)
@@ -1449,6 +1453,14 @@ void sk_destruct(struct sock *sk)
 	sk_prot_free(sk->sk_prot_creator, sk);
 }
 
+void sk_destruct(struct sock *sk)
+{
+	if (sock_flag(sk, SOCK_RCU_FREE))
+		call_rcu(&sk->sk_rcu, __sk_destruct);
+	else
+		__sk_destruct(&sk->sk_rcu);
+}
+
 static void __sk_free(struct sock *sk)
 {
 	if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt))
@@ -1513,6 +1525,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_dst_cache	= NULL;
 		newsk->sk_wmem_queued	= 0;
 		newsk->sk_forward_alloc = 0;
+		atomic_set(&newsk->sk_drops, 0);
 		newsk->sk_send_head	= NULL;
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 

net/core/sock_diag.c

@@ -67,6 +67,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
 	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
 	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
 	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
 
 	return nla_put(skb, attrtype, sizeof(mem), &mem);
 }

net/dccp/ipv4.c

@@ -764,6 +764,7 @@ static int dccp_v4_rcv(struct sk_buff *skb)
 {
 	const struct dccp_hdr *dh;
 	const struct iphdr *iph;
+	bool refcounted;
 	struct sock *sk;
 	int min_cov;
 
@@ -801,7 +802,7 @@ static int dccp_v4_rcv(struct sk_buff *skb)
 
 lookup:
 	sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
-			       dh->dccph_sport, dh->dccph_dport);
+			       dh->dccph_sport, dh->dccph_dport, &refcounted);
 	if (!sk) {
 		dccp_pr_debug("failed to look up flow ID in table and "
 			      "get corresponding socket\n");
@@ -830,6 +831,7 @@ static int dccp_v4_rcv(struct sk_buff *skb)
 			goto lookup;
 		}
 		sock_hold(sk);
+		refcounted = true;
 		nsk = dccp_check_req(sk, skb, req);
 		if (!nsk) {
 			reqsk_put(req);
@@ -886,7 +888,8 @@ static int dccp_v4_rcv(struct sk_buff *skb)
 	return 0;
 
 discard_and_relse:
-	sock_put(sk);
+	if (refcounted)
+		sock_put(sk);
 	goto discard_it;
 }