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,
@@ -325,12 +324,13 @@ 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;
 }
 
@@ -338,17 +338,20 @@ 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;
 }
 

net/dccp/ipv6.c

@@ -642,6 +642,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 static int dccp_v6_rcv(struct sk_buff *skb)
 {
 	const struct dccp_hdr *dh;
+	bool refcounted;
 	struct sock *sk;
 	int min_cov;
 
@@ -670,7 +671,7 @@ static int dccp_v6_rcv(struct sk_buff *skb)
 lookup:
 	sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
 			        dh->dccph_sport, dh->dccph_dport,
-				inet6_iif(skb));
+				inet6_iif(skb), &refcounted);
 	if (!sk) {
 		dccp_pr_debug("failed to look up flow ID in table and "
 			      "get corresponding socket\n");
@@ -699,6 +700,7 @@ static int dccp_v6_rcv(struct sk_buff *skb)
 			goto lookup;
 		}
 		sock_hold(sk);
+		refcounted = true;
 		nsk = dccp_check_req(sk, skb, req);
 		if (!nsk) {
 			reqsk_put(req);
@@ -752,7 +754,8 @@ static int dccp_v6_rcv(struct sk_buff *skb)
 	return 0;
 
 discard_and_relse:
-	sock_put(sk);
+	if (refcounted)
+		sock_put(sk);
 	goto discard_it;
 }
 

net/ipv4/inet_diag.c

@@ -356,6 +356,7 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
 {
 	struct sock *sk;
 
+	rcu_read_lock();
 	if (req->sdiag_family == AF_INET)
 		sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0],
 				 req->id.idiag_dport, req->id.idiag_src[0],
@@ -376,9 +377,11 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
 					  req->id.idiag_if);
 	}
 #endif
-	else
+	else {
+		rcu_read_unlock();
 		return ERR_PTR(-EINVAL);
-
+	}
+	rcu_read_unlock();
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
@@ -772,13 +775,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
 
 		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
 			struct inet_listen_hashbucket *ilb;
-			struct hlist_nulls_node *node;
 			struct sock *sk;
 
 			num = 0;
 			ilb = &hashinfo->listening_hash[i];
 			spin_lock_bh(&ilb->lock);
-			sk_nulls_for_each(sk, node, &ilb->head) {
+			sk_for_each(sk, &ilb->head) {
 				struct inet_sock *inet = inet_sk(sk);
 
 				if (!net_eq(sock_net(sk), net))

net/ipv4/inet_hashtables.c

@@ -198,13 +198,13 @@ static inline int compute_score(struct sock *sk, struct net *net,
 }
 
 /*
- * Don't inline this cruft. Here are some nice properties to exploit here. The
- * BSD API does not allow a listening sock to specify the remote port nor the
+ * Here are some nice properties to exploit here. The BSD API
+ * does not allow a listening sock to specify the remote port nor the
  * remote address for the connection. So always assume those are both
  * wildcarded during the search since they can never be otherwise.
  */
 
-
+/* called with rcu_read_lock() : No refcount taken on the socket */
 struct sock *__inet_lookup_listener(struct net *net,
 				    struct inet_hashinfo *hashinfo,
 				    struct sk_buff *skb, int doff,
@@ -212,38 +212,27 @@ struct sock *__inet_lookup_listener(struct net *net,
 				    const __be32 daddr, const unsigned short hnum,
 				    const int dif)
 {
-	struct sock *sk, *result;
-	struct hlist_nulls_node *node;
 	unsigned int hash = inet_lhashfn(net, hnum);
 	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
-	int score, hiscore, matches = 0, reuseport = 0;
-	bool select_ok = true;
+	int score, hiscore = 0, matches = 0, reuseport = 0;
+	struct sock *sk, *result = NULL;
 	u32 phash = 0;
 
-	rcu_read_lock();
-begin:
-	result = NULL;
-	hiscore = 0;
-	sk_nulls_for_each_rcu(sk, node, &ilb->head) {
+	sk_for_each_rcu(sk, &ilb->head) {
 		score = compute_score(sk, net, hnum, daddr, dif);
 		if (score > hiscore) {
-			result = sk;
-			hiscore = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
 				phash = inet_ehashfn(net, daddr, hnum,
 						     saddr, sport);
-				if (select_ok) {
-					struct sock *sk2;
-					sk2 = reuseport_select_sock(sk, phash,
-								    skb, doff);
-					if (sk2) {
-						result = sk2;
-						goto found;
-					}
-				}
+				result = reuseport_select_sock(sk, phash,
+							       skb, doff);
+				if (result)
+					return result;
 				matches = 1;
 			}
+			result = sk;
+			hiscore = score;
 		} else if (score == hiscore && reuseport) {
 			matches++;
 			if (reciprocal_scale(phash, matches) == 0)
@@ -251,25 +240,6 @@ struct sock *__inet_lookup_listener(struct net *net,
 			phash = next_pseudo_random32(phash);
 		}
 	}
-	/*
-	 * if the nulls value we got at the end of this lookup is
-	 * not the expected one, we must restart lookup.
-	 * We probably met an item that was moved to another chain.
-	 */
-	if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE)
-		goto begin;
-	if (result) {
-found:
-		if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
-			result = NULL;
-		else if (unlikely(compute_score(result, net, hnum, daddr,
-				  dif) < hiscore)) {
-			sock_put(result);
-			select_ok = false;
-			goto begin;
-		}
-	}
-	rcu_read_unlock();
 	return result;
 }
 EXPORT_SYMBOL_GPL(__inet_lookup_listener);
@@ -312,7 +282,6 @@ struct sock *__inet_lookup_established(struct net *net,
 	unsigned int slot = hash & hashinfo->ehash_mask;
 	struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
 
-	rcu_read_lock();
 begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		if (sk->sk_hash != hash)
@@ -339,7 +308,6 @@ struct sock *__inet_lookup_established(struct net *net,
 out:
 	sk = NULL;
 found:
-	rcu_read_unlock();
 	return sk;
 }
 EXPORT_SYMBOL_GPL(__inet_lookup_established);
@@ -512,7 +480,8 @@ int __inet_hash(struct sock *sk, struct sock *osk,
 		if (err)
 			goto unlock;
 	}
-	__sk_nulls_add_node_rcu(sk, &ilb->head);
+	hlist_add_head_rcu(&sk->sk_node, &ilb->head);
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 unlock:
 	spin_unlock(&ilb->lock);
@@ -539,20 +508,25 @@ void inet_unhash(struct sock *sk)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
 	spinlock_t *lock;
+	bool listener = false;
 	int done;
 
 	if (sk_unhashed(sk))
 		return;
 
-	if (sk->sk_state == TCP_LISTEN)
+	if (sk->sk_state == TCP_LISTEN) {
 		lock = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)].lock;
-	else
+		listener = true;
+	} else {
 		lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
-
+	}
 	spin_lock_bh(lock);
 	if (rcu_access_pointer(sk->sk_reuseport_cb))
 		reuseport_detach_sock(sk);
-	done = __sk_nulls_del_node_init_rcu(sk);
+	if (listener)
+		done = __sk_del_node_init(sk);
+	else
+		done = __sk_nulls_del_node_init_rcu(sk);
 	if (done)
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	spin_unlock_bh(lock);
@@ -688,9 +662,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
 
 	for (i = 0; i < INET_LHTABLE_SIZE; i++) {
 		spin_lock_init(&h->listening_hash[i].lock);
-		INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].head,
-				      i + LISTENING_NULLS_BASE);
-		}
+		INIT_HLIST_HEAD(&h->listening_hash[i].head);
+	}
 }
 EXPORT_SYMBOL_GPL(inet_hashinfo_init);
 

net/ipv4/tcp_input.c

@@ -4307,6 +4307,12 @@ static bool tcp_try_coalesce(struct sock *sk,
 	return true;
 }
 
+static void tcp_drop(struct sock *sk, struct sk_buff *skb)
+{
+	sk_drops_add(sk, skb);
+	__kfree_skb(skb);
+}
+
 /* This one checks to see if we can put data from the
  * out_of_order queue into the receive_queue.
  */
@@ -4331,7 +4337,7 @@ static void tcp_ofo_queue(struct sock *sk)
 		__skb_unlink(skb, &tp->out_of_order_queue);
 		if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
 			SOCK_DEBUG(sk, "ofo packet was already received\n");
-			__kfree_skb(skb);
+			tcp_drop(sk, skb);
 			continue;
 		}
 		SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n",
@@ -4383,7 +4389,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP);
-		__kfree_skb(skb);
+		tcp_drop(sk, skb);
 		return;
 	}
 
@@ -4447,7 +4453,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
 			/* All the bits are present. Drop. */
 			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE);
-			__kfree_skb(skb);
+			tcp_drop(sk, skb);
 			skb = NULL;
 			tcp_dsack_set(sk, seq, end_seq);
 			goto add_sack;
@@ -4486,7 +4492,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
 				 TCP_SKB_CB(skb1)->end_seq);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE);
-		__kfree_skb(skb1);
+		tcp_drop(sk, skb1);
 	}
 
 add_sack:
@@ -4569,12 +4575,13 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int eaten = -1;
 	bool fragstolen = false;
+	int eaten = -1;
 
-	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
-		goto drop;
-
+	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
+		__kfree_skb(skb);
+		return;
+	}
 	skb_dst_drop(skb);
 	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
@@ -4656,7 +4663,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 		tcp_enter_quickack_mode(sk);
 		inet_csk_schedule_ack(sk);
 drop:
-		__kfree_skb(skb);
+		tcp_drop(sk, skb);
 		return;
 	}
 
@@ -5233,7 +5240,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	return true;
 
 discard:
-	__kfree_skb(skb);
+	tcp_drop(sk, skb);
 	return false;
 }
 
@@ -5451,7 +5458,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
 
 discard:
-	__kfree_skb(skb);
+	tcp_drop(sk, skb);
 }
 EXPORT_SYMBOL(tcp_rcv_established);
 
@@ -5682,7 +5689,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
 
 discard:
-			__kfree_skb(skb);
+			tcp_drop(sk, skb);
 			return 0;
 		} else {
 			tcp_send_ack(sk);
@@ -6043,7 +6050,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 	if (!queued) {
 discard:
-		__kfree_skb(skb);
+		tcp_drop(sk, skb);
 	}
 	return 0;
 }
@@ -6332,8 +6339,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
 		af_ops->send_synack(sk, dst, &fl, req,
 				    &foc, !want_cookie);
-		if (want_cookie)
-			goto drop_and_free;
+		if (want_cookie) {
+			reqsk_free(req);
+			return 0;
+		}
 	}
 	reqsk_put(req);
 	return 0;
@@ -6343,7 +6352,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 drop_and_free:
 	reqsk_free(req);
 drop:
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+	tcp_listendrop(sk);
 	return 0;
 }
 EXPORT_SYMBOL(tcp_conn_request);

net/ipv4/tcp_ipv4.c

@@ -329,7 +329,7 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 		 * errors returned from accept().
 		 */
 		inet_csk_reqsk_queue_drop(req->rsk_listener, req);
-		NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS);
+		tcp_listendrop(req->rsk_listener);
 	}
 	reqsk_put(req);
 }
@@ -628,6 +628,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 
 	net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
 #ifdef CONFIG_TCP_MD5SIG
+	rcu_read_lock();
 	hash_location = tcp_parse_md5sig_option(th);
 	if (sk && sk_fullsock(sk)) {
 		key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
@@ -646,16 +647,18 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 					     ntohs(th->source), inet_iif(skb));
 		/* don't send rst if it can't find key */
 		if (!sk1)
-			return;
-		rcu_read_lock();
+			goto out;
+
 		key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *)
 					&ip_hdr(skb)->saddr, AF_INET);
 		if (!key)
-			goto release_sk1;
+			goto out;
+
 
 		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
 		if (genhash || memcmp(hash_location, newhash, 16) != 0)
-			goto release_sk1;
+			goto out;
+
 	}
 
 	if (key) {
@@ -698,11 +701,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
 
 #ifdef CONFIG_TCP_MD5SIG
-release_sk1:
-	if (sk1) {
-		rcu_read_unlock();
-		sock_put(sk1);
-	}
+out:
+	rcu_read_unlock();
 #endif
 }
 
@@ -1246,7 +1246,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 				&tcp_request_sock_ipv4_ops, sk, skb);
 
 drop:
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+	tcp_listendrop(sk);
 	return 0;
 }
 EXPORT_SYMBOL(tcp_v4_conn_request);
@@ -1348,7 +1348,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 exit_nonewsk:
 	dst_release(dst);
 exit:
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+	tcp_listendrop(sk);
 	return NULL;
 put_and_exit:
 	inet_csk_prepare_forced_close(newsk);
@@ -1538,11 +1538,12 @@ EXPORT_SYMBOL(tcp_prequeue);
 
 int tcp_v4_rcv(struct sk_buff *skb)
 {
+	struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
+	bool refcounted;
 	struct sock *sk;
 	int ret;
-	struct net *net = dev_net(skb->dev);
 
 	if (skb->pkt_type != PACKET_HOST)
 		goto discard_it;
@@ -1588,7 +1589,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 
 lookup:
 	sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
-			       th->dest);
+			       th->dest, &refcounted);
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1609,7 +1610,11 @@ int tcp_v4_rcv(struct sk_buff *skb)
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		/* We own a reference on the listener, increase it again
+		 * as we might lose it too soon.
+		 */
 		sock_hold(sk);
+		refcounted = true;
 		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
@@ -1665,7 +1670,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	bh_unlock_sock(sk);
 
 put_and_return:
-	sock_put(sk);
+	if (refcounted)
+		sock_put(sk);
 
 	return ret;
 
@@ -1688,7 +1694,9 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	return 0;
 
 discard_and_relse:
-	sock_put(sk);
+	sk_drops_add(sk, skb);
+	if (refcounted)
+		sock_put(sk);
 	goto discard_it;
 
 do_time_wait:
@@ -1712,6 +1720,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		if (sk2) {
 			inet_twsk_deschedule_put(inet_twsk(sk));
 			sk = sk2;
+			refcounted = false;
 			goto process;
 		}
 		/* Fall through to ACK */
@@ -1845,17 +1854,17 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock);
  */
 static void *listening_get_next(struct seq_file *seq, void *cur)
 {
-	struct inet_connection_sock *icsk;
-	struct hlist_nulls_node *node;
-	struct sock *sk = cur;
-	struct inet_listen_hashbucket *ilb;
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct inet_listen_hashbucket *ilb;
+	struct inet_connection_sock *icsk;
+	struct sock *sk = cur;
 
 	if (!sk) {
+get_head:
 		ilb = &tcp_hashinfo.listening_hash[st->bucket];
 		spin_lock_bh(&ilb->lock);
-		sk = sk_nulls_head(&ilb->head);
+		sk = sk_head(&ilb->head);
 		st->offset = 0;
 		goto get_sk;
 	}
@@ -1863,28 +1872,20 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	++st->num;
 	++st->offset;
 
-	sk = sk_nulls_next(sk);
+	sk = sk_next(sk);
 get_sk:
-	sk_nulls_for_each_from(sk, node) {
+	sk_for_each_from(sk) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
-		if (sk->sk_family == st->family) {
-			cur = sk;
-			goto out;
-		}
+		if (sk->sk_family == st->family)
+			return sk;
 		icsk = inet_csk(sk);
 	}
 	spin_unlock_bh(&ilb->lock);
 	st->offset = 0;
-	if (++st->bucket < INET_LHTABLE_SIZE) {
-		ilb = &tcp_hashinfo.listening_hash[st->bucket];
-		spin_lock_bh(&ilb->lock);
-		sk = sk_nulls_head(&ilb->head);
-		goto get_sk;
-	}
-	cur = NULL;
-out:
-	return cur;
+	if (++st->bucket < INET_LHTABLE_SIZE)
+		goto get_head;
+	return NULL;
 }
 
 static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
@@ -2383,6 +2384,7 @@ static int __net_init tcp_sk_init(struct net *net)
 					   IPPROTO_TCP, net);
 		if (res)
 			goto fail;
+		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
 		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
 	}
 

net/ipv4/tcp_minisocks.c

@@ -704,7 +704,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
 					  tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) {
 		/* Out of window: send ACK and drop. */
-		if (!(flg & TCP_FLAG_RST))
+		if (!(flg & TCP_FLAG_RST) &&
+		    !tcp_oow_rate_limited(sock_net(sk), skb,
+					  LINUX_MIB_TCPACKSKIPPEDSYNRECV,
+					  &tcp_rsk(req)->last_oow_ack_time))
 			req->rsk_ops->send_ack(sk, skb, req);
 		if (paws_reject)
 			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);

net/ipv4/udp_diag.c

@@ -36,10 +36,11 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 			const struct inet_diag_req_v2 *req)
 {
 	int err = -EINVAL;
-	struct sock *sk;
+	struct sock *sk = NULL;
 	struct sk_buff *rep;
 	struct net *net = sock_net(in_skb->sk);
 
+	rcu_read_lock();
 	if (req->sdiag_family == AF_INET)
 		sk = __udp4_lib_lookup(net,
 				req->id.idiag_src[0], req->id.idiag_sport,
@@ -54,9 +55,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 				req->id.idiag_dport,
 				req->id.idiag_if, tbl, NULL);
 #endif
-	else
-		goto out_nosk;
-
+	if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+		sk = NULL;
+	rcu_read_unlock();
 	err = -ENOENT;
 	if (!sk)
 		goto out_nosk;
@@ -96,24 +97,23 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb,
 		     struct netlink_callback *cb,
 		     const struct inet_diag_req_v2 *r, struct nlattr *bc)
 {
-	int num, s_num, slot, s_slot;
 	struct net *net = sock_net(skb->sk);
+	int num, s_num, slot, s_slot;
 
 	s_slot = cb->args[0];
 	num = s_num = cb->args[1];
 
 	for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) {
-		struct sock *sk;
-		struct hlist_nulls_node *node;
 		struct udp_hslot *hslot = &table->hash[slot];
+		struct sock *sk;
 
 		num = 0;
 
-		if (hlist_nulls_empty(&hslot->head))
+		if (hlist_empty(&hslot->head))
 			continue;
 
 		spin_lock_bh(&hslot->lock);
-		sk_nulls_for_each(sk, node, &hslot->head) {
+		sk_for_each(sk, &hslot->head) {
 			struct inet_sock *inet = inet_sk(sk);
 
 			if (!net_eq(sock_net(sk), net))

net/ipv6/inet6_hashtables.c

@@ -69,7 +69,6 @@ struct sock *__inet6_lookup_established(struct net *net,
 	struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
 
 
-	rcu_read_lock();
 begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		if (sk->sk_hash != hash)
@@ -90,7 +89,6 @@ struct sock *__inet6_lookup_established(struct net *net,
 out:
 	sk = NULL;
 found:
-	rcu_read_unlock();
 	return sk;
 }
 EXPORT_SYMBOL(__inet6_lookup_established);
@@ -122,6 +120,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
+/* called with rcu_read_lock() */
 struct sock *inet6_lookup_listener(struct net *net,
 		struct inet_hashinfo *hashinfo,
 		struct sk_buff *skb, int doff,
@@ -129,39 +128,27 @@ struct sock *inet6_lookup_listener(struct net *net,
 		const __be16 sport, const struct in6_addr *daddr,
 		const unsigned short hnum, const int dif)
 {
-	struct sock *sk;
-	const struct hlist_nulls_node *node;
-	struct sock *result;
-	int score, hiscore, matches = 0, reuseport = 0;
-	bool select_ok = true;
-	u32 phash = 0;
 	unsigned int hash = inet_lhashfn(net, hnum);
 	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
+	int score, hiscore = 0, matches = 0, reuseport = 0;
+	struct sock *sk, *result = NULL;
+	u32 phash = 0;
 
-	rcu_read_lock();
-begin:
-	result = NULL;
-	hiscore = 0;
-	sk_nulls_for_each(sk, node, &ilb->head) {
+	sk_for_each(sk, &ilb->head) {
 		score = compute_score(sk, net, hnum, daddr, dif);
 		if (score > hiscore) {
 			hiscore = score;
-			result = sk;
-			reuseport = sk->sk_reuseport;
 			if (reuseport) {
 				phash = inet6_ehashfn(net, daddr, hnum,
 						      saddr, sport);
-				if (select_ok) {
-					struct sock *sk2;
-					sk2 = reuseport_select_sock(sk, phash,
-								    skb, doff);
-					if (sk2) {
-						result = sk2;
-						goto found;
-					}
-				}
+				result = reuseport_select_sock(sk, phash,
+							       skb, doff);
+				if (result)
+					return result;
 				matches = 1;
 			}
+			result = sk;
+			reuseport = sk->sk_reuseport;
 		} else if (score == hiscore && reuseport) {
 			matches++;
 			if (reciprocal_scale(phash, matches) == 0)
@@ -169,25 +156,6 @@ struct sock *inet6_lookup_listener(struct net *net,
 			phash = next_pseudo_random32(phash);
 		}
 	}
-	/*
-	 * if the nulls value we got at the end of this lookup is
-	 * not the expected one, we must restart lookup.
-	 * We probably met an item that was moved to another chain.
-	 */
-	if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE)
-		goto begin;
-	if (result) {
-found:
-		if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
-			result = NULL;
-		else if (unlikely(compute_score(result, net, hnum, daddr,
-				  dif) < hiscore)) {
-			sock_put(result);
-			select_ok = false;
-			goto begin;
-		}
-	}
-	rcu_read_unlock();
 	return result;
 }
 EXPORT_SYMBOL_GPL(inet6_lookup_listener);
@@ -199,12 +167,12 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
 			  const int dif)
 {
 	struct sock *sk;
+	bool refcounted;
 
-	local_bh_disable();
 	sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
-			    ntohs(dport), dif);
-	local_bh_enable();
-
+			    ntohs(dport), dif, &refcounted);
+	if (sk && !refcounted && !atomic_inc_not_zero(&sk->sk_refcnt))
+		sk = NULL;
 	return sk;
 }
 EXPORT_SYMBOL_GPL(inet6_lookup);

net/ipv6/tcp_ipv6.c

@@ -858,6 +858,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 		return;
 
 #ifdef CONFIG_TCP_MD5SIG
+	rcu_read_lock();
 	hash_location = tcp_parse_md5sig_option(th);
 	if (sk && sk_fullsock(sk)) {
 		key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr);
@@ -875,16 +876,15 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 					   th->source, &ipv6h->daddr,
 					   ntohs(th->source), tcp_v6_iif(skb));
 		if (!sk1)
-			return;
+			goto out;
 
-		rcu_read_lock();
 		key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr);
 		if (!key)
-			goto release_sk1;
+			goto out;
 
 		genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb);
 		if (genhash || memcmp(hash_location, newhash, 16) != 0)
-			goto release_sk1;
+			goto out;
 	}
 #endif
 
@@ -898,11 +898,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
 
 #ifdef CONFIG_TCP_MD5SIG
-release_sk1:
-	if (sk1) {
-		rcu_read_unlock();
-		sock_put(sk1);
-	}
+out:
+	rcu_read_unlock();
 #endif
 }
 
@@ -967,7 +964,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 				&tcp_request_sock_ipv6_ops, sk, skb);
 
 drop:
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+	tcp_listendrop(sk);
 	return 0; /* don't send reset */
 }
 
@@ -1172,7 +1169,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 out_nonewsk:
 	dst_release(dst);
 out:
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+	tcp_listendrop(sk);
 	return NULL;
 }
 
@@ -1351,6 +1348,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 {
 	const struct tcphdr *th;
 	const struct ipv6hdr *hdr;
+	bool refcounted;
 	struct sock *sk;
 	int ret;
 	struct net *net = dev_net(skb->dev);
@@ -1381,7 +1379,8 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 
 lookup:
 	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th),
-				th->source, th->dest, inet6_iif(skb));
+				th->source, th->dest, inet6_iif(skb),
+				&refcounted);
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1404,6 +1403,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 			goto lookup;
 		}
 		sock_hold(sk);
+		refcounted = true;
 		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
@@ -1460,7 +1460,8 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	bh_unlock_sock(sk);
 
 put_and_return:
-	sock_put(sk);
+	if (refcounted)
+		sock_put(sk);
 	return ret ? -1 : 0;
 
 no_tcp_socket:
@@ -1483,7 +1484,9 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	return 0;
 
 discard_and_relse:
-	sock_put(sk);
+	sk_drops_add(sk, skb);
+	if (refcounted)
+		sock_put(sk);
 	goto discard_it;
 
 do_time_wait:
@@ -1514,6 +1517,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 			inet_twsk_deschedule_put(tw);
 			sk = sk2;
 			tcp_v6_restore_cb(skb);
+			refcounted = false;
 			goto process;
 		}
 		/* Fall through to ACK */

net/ipv6/udp.c

@@ -213,37 +213,28 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		struct sk_buff *skb)
 {
 	struct sock *sk, *result;
-	struct hlist_nulls_node *node;
 	int score, badness, matches = 0, reuseport = 0;
-	bool select_ok = true;
 	u32 hash = 0;
 
-begin:
 	result = NULL;
 	badness = -1;
-	udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
+	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		score = compute_score2(sk, net, saddr, sport,
 				      daddr, hnum, dif);
 		if (score > badness) {
-			result = sk;
-			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
 				hash = udp6_ehashfn(net, daddr, hnum,
 						    saddr, sport);
-				if (select_ok) {
-					struct sock *sk2;
 
-					sk2 = reuseport_select_sock(sk, hash, skb,
+				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-					if (sk2) {
-						result = sk2;
-						select_ok = false;
-						goto found;
-					}
-				}
+				if (result)
+					return result;
 				matches = 1;
 			}
+			result = sk;
+			badness = score;
 		} else if (score == badness && reuseport) {
 			matches++;
 			if (reciprocal_scale(hash, matches) == 0)
@@ -251,27 +242,10 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 			hash = next_pseudo_random32(hash);
 		}
 	}
-	/*
-	 * if the nulls value we got at the end of this lookup is
-	 * not the expected one, we must restart lookup.
-	 * We probably met an item that was moved to another chain.
-	 */
-	if (get_nulls_value(node) != slot2)
-		goto begin;
-
-	if (result) {
-found:
-		if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
-			result = NULL;
-		else if (unlikely(compute_score2(result, net, saddr, sport,
-				  daddr, hnum, dif) < badness)) {
-			sock_put(result);
-			goto begin;
-		}
-	}
 	return result;
 }
 
+/* rcu_read_lock() must be held */
 struct sock *__udp6_lib_lookup(struct net *net,
 				      const struct in6_addr *saddr, __be16 sport,
 				      const struct in6_addr *daddr, __be16 dport,
@@ -279,15 +253,12 @@ struct sock *__udp6_lib_lookup(struct net *net,
 				      struct sk_buff *skb)
 {
 	struct sock *sk, *result;
-	struct hlist_nulls_node *node;
 	unsigned short hnum = ntohs(dport);
 	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
 	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
 	int score, badness, matches = 0, reuseport = 0;
-	bool select_ok = true;
 	u32 hash = 0;
 
-	rcu_read_lock();
 	if (hslot->count > 10) {
 		hash2 = udp6_portaddr_hash(net, daddr, hnum);
 		slot2 = hash2 & udptable->mask;
@@ -309,34 +280,26 @@ struct sock *__udp6_lib_lookup(struct net *net,
 						  &in6addr_any, hnum, dif,
 						  hslot2, slot2, skb);
 		}
-		rcu_read_unlock();
 		return result;
 	}
 begin:
 	result = NULL;
 	badness = -1;
-	sk_nulls_for_each_rcu(sk, node, &hslot->head) {
+	sk_for_each_rcu(sk, &hslot->head) {
 		score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif);
 		if (score > badness) {
-			result = sk;
-			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
 				hash = udp6_ehashfn(net, daddr, hnum,
 						    saddr, sport);
-				if (select_ok) {
-					struct sock *sk2;
-
-					sk2 = reuseport_select_sock(sk, hash, skb,
+				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-					if (sk2) {
-						result = sk2;
-						select_ok = false;
-						goto found;
-					}
-				}
+				if (result)
+					return result;
 				matches = 1;
 			}
+			result = sk;
+			badness = score;
 		} else if (score == badness && reuseport) {
 			matches++;
 			if (reciprocal_scale(hash, matches) == 0)
@@ -344,25 +307,6 @@ struct sock *__udp6_lib_lookup(struct net *net,
 			hash = next_pseudo_random32(hash);
 		}
 	}
-	/*
-	 * if the nulls value we got at the end of this lookup is
-	 * not the expected one, we must restart lookup.
-	 * We probably met an item that was moved to another chain.
-	 */
-	if (get_nulls_value(node) != slot)
-		goto begin;
-
-	if (result) {
-found:
-		if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
-			result = NULL;
-		else if (unlikely(compute_score(result, net, hnum, saddr, sport,
-					daddr, dport, dif) < badness)) {
-			sock_put(result);
-			goto begin;
-		}
-	}
-	rcu_read_unlock();
 	return result;
 }
 EXPORT_SYMBOL_GPL(__udp6_lib_lookup);
@@ -382,12 +326,24 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 				 udptable, skb);
 }
 
+/* Must be called under rcu_read_lock().
+ * Does increment socket refcount.
+ */
+#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \
+    IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY)
 struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
 			     const struct in6_addr *daddr, __be16 dport, int dif)
 {
-	return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL);
+	struct sock *sk;
+
+	sk =  __udp6_lib_lookup(net, saddr, sport, daddr, dport,
+				dif, &udp_table, NULL);
+	if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+		sk = NULL;
+	return sk;
 }
 EXPORT_SYMBOL_GPL(udp6_lib_lookup);
+#endif
 
 /*
  *	This should be easy, if there is something there we
@@ -585,7 +541,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	sk->sk_err = err;
 	sk->sk_error_report(sk);
 out:
-	sock_put(sk);
+	return;
 }
 
 static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
@@ -747,33 +703,6 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
 	return true;
 }
 
-static void flush_stack(struct sock **stack, unsigned int count,
-			struct sk_buff *skb, unsigned int final)
-{
-	struct sk_buff *skb1 = NULL;
-	struct sock *sk;
-	unsigned int i;
-
-	for (i = 0; i < count; i++) {
-		sk = stack[i];
-		if (likely(!skb1))
-			skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC);
-		if (!skb1) {
-			atomic_inc(&sk->sk_drops);
-			UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
-					  IS_UDPLITE(sk));
-			UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS,
-					  IS_UDPLITE(sk));
-		}
-
-		if (skb1 && udpv6_queue_rcv_skb(sk, skb1) <= 0)
-			skb1 = NULL;
-		sock_put(sk);
-	}
-	if (unlikely(skb1))
-		kfree_skb(skb1);
-}
-
 static void udp6_csum_zero_error(struct sk_buff *skb)
 {
 	/* RFC 2460 section 8.1 says that we SHOULD log
@@ -792,15 +721,15 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 		const struct in6_addr *saddr, const struct in6_addr *daddr,
 		struct udp_table *udptable, int proto)
 {
-	struct sock *sk, *stack[256 / sizeof(struct sock *)];
+	struct sock *sk, *first = NULL;
 	const struct udphdr *uh = udp_hdr(skb);
-	struct hlist_nulls_node *node;
 	unsigned short hnum = ntohs(uh->dest);
 	struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum);
-	int dif = inet6_iif(skb);
-	unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node);
+	unsigned int offset = offsetof(typeof(*sk), sk_node);
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
-	bool inner_flushed = false;
+	int dif = inet6_iif(skb);
+	struct hlist_node *node;
+	struct sk_buff *nskb;
 
 	if (use_hash2) {
 		hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) &
@@ -811,27 +740,32 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 		offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
 	}
 
-	spin_lock(&hslot->lock);
-	sk_nulls_for_each_entry_offset(sk, node, &hslot->head, offset) {
-		if (__udp_v6_is_mcast_sock(net, sk,
-					   uh->dest, daddr,
-					   uh->source, saddr,
-					   dif, hnum) &&
-		    /* If zero checksum and no_check is not on for
-		     * the socket then skip it.
-		     */
-		    (uh->check || udp_sk(sk)->no_check6_rx)) {
-			if (unlikely(count == ARRAY_SIZE(stack))) {
-				flush_stack(stack, count, skb, ~0);
-				inner_flushed = true;
-				count = 0;
-			}
-			stack[count++] = sk;
-			sock_hold(sk);
+	sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
+		if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
+					    uh->source, saddr, dif, hnum))
+			continue;
+		/* If zero checksum and no_check is not on for
+		 * the socket then skip it.
+		 */
+		if (!uh->check && !udp_sk(sk)->no_check6_rx)
+			continue;
+		if (!first) {
+			first = sk;
+			continue;
+		}
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (unlikely(!nskb)) {
+			atomic_inc(&sk->sk_drops);
+			UDP6_INC_STATS_BH(net, UDP_MIB_RCVBUFERRORS,
+					  IS_UDPLITE(sk));
+			UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS,
+					  IS_UDPLITE(sk));
+			continue;
 		}
-	}
 
-	spin_unlock(&hslot->lock);
+		if (udpv6_queue_rcv_skb(sk, nskb) > 0)
+			consume_skb(nskb);
+	}
 
 	/* Also lookup *:port if we are using hash2 and haven't done so yet. */
 	if (use_hash2 && hash2 != hash2_any) {
@@ -839,13 +773,13 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 		goto start_lookup;
 	}
 
-	if (count) {
-		flush_stack(stack, count, skb, count - 1);
+	if (first) {
+		if (udpv6_queue_rcv_skb(first, skb) > 0)
+			consume_skb(skb);
 	} else {
-		if (!inner_flushed)
-			UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
-					  proto == IPPROTO_UDPLITE);
-		consume_skb(skb);
+		kfree_skb(skb);
+		UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+				  proto == IPPROTO_UDPLITE);
 	}
 	return 0;
 }
@@ -853,10 +787,10 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		   int proto)
 {
+	const struct in6_addr *saddr, *daddr;
 	struct net *net = dev_net(skb->dev);
-	struct sock *sk;
 	struct udphdr *uh;
-	const struct in6_addr *saddr, *daddr;
+	struct sock *sk;
 	u32 ulen = 0;
 
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
@@ -910,7 +844,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		int ret;
 
 		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
-			sock_put(sk);
 			udp6_csum_zero_error(skb);
 			goto csum_error;
 		}
@@ -920,7 +853,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 						 ip6_compute_pseudo);
 
 		ret = udpv6_queue_rcv_skb(sk, skb);
-		sock_put(sk);
 
 		/* a return value > 0 means to resubmit the input */
 		if (ret > 0)

net/netfilter/xt_socket.c

@@ -120,9 +120,9 @@ xt_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff,
 {
 	switch (protocol) {
 	case IPPROTO_TCP:
-		return __inet_lookup(net, &tcp_hashinfo, skb, doff,
-				     saddr, sport, daddr, dport,
-				     in->ifindex);
+		return inet_lookup(net, &tcp_hashinfo, skb, doff,
+				   saddr, sport, daddr, dport,
+				   in->ifindex);
 	case IPPROTO_UDP:
 		return udp4_lib_lookup(net, saddr, sport, daddr, dport,
 				       in->ifindex);